From 04052a318fb93491f1f3b4d282cb806f588e9326 Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@linux.alibaba.com>
Date: Fri, 6 Nov 2020 16:10:37 +0800
Subject: [PATCH 0001/1820] net/ieee802154: remove unused macros to tame gcc

Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Stefan Schmidt <stefan@datenfreihafen.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: linux-wpan@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Link: https://lore.kernel.org/r/1604650237-22192-1-git-send-email-alex.shi@linux.alibaba.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 7c5a1aa5adb4..1cebdcedc48c 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -2098,11 +2098,7 @@ static int nl802154_del_llsec_seclevel(struct sk_buff *skb,
 #define NL802154_FLAG_NEED_NETDEV	0x02
 #define NL802154_FLAG_NEED_RTNL		0x04
 #define NL802154_FLAG_CHECK_NETDEV_UP	0x08
-#define NL802154_FLAG_NEED_NETDEV_UP	(NL802154_FLAG_NEED_NETDEV |\
-					 NL802154_FLAG_CHECK_NETDEV_UP)
 #define NL802154_FLAG_NEED_WPAN_DEV	0x10
-#define NL802154_FLAG_NEED_WPAN_DEV_UP	(NL802154_FLAG_NEED_WPAN_DEV |\
-					 NL802154_FLAG_CHECK_NETDEV_UP)
 
 static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
 			     struct genl_info *info)

From e51ea5442996261d4bc3a5b934d27cc0ce6a991c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 14 Jul 2020 15:10:46 -0400
Subject: [PATCH 0002/1820] sparc32: don't bother with lookup_fault() in
 __bzero()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/sparc/lib/memset.S | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index b89d42b29e34..725041c5224a 100644
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -19,7 +19,7 @@
 98: 	x,y;					\
 	.section .fixup,ALLOC,EXECINSTR;	\
 	.align	4;				\
-99:	ba 30f;					\
+99:	retl;					\
 	 a, b, %o0;				\
 	.section __ex_table,ALLOC;		\
 	.align	4;				\
@@ -194,24 +194,15 @@ __memset_end:
 1:
 	sll	%g2, 3, %g2
 	add	%o3, %o1, %o0
-	b 30f
+	retl
 	 sub	%o0, %g2, %o0
 21:
 	mov	8, %o0
 	and	%o1, 7, %o1
 	sub	%o0, %g2, %o0
 	sll	%o0, 3, %o0
-	b 30f
+	retl
 	 add	%o0, %o1, %o0
-30:
-/* %o4 is faulting address, %o5 is %pc where fault occurred */
-	save	%sp, -104, %sp
-	mov	%i5, %o0
-	mov	%i7, %o1
-	call	lookup_fault
-	 mov	%i4, %o2
-	ret
-	 restore
 
 	.globl __bzero_end
 __bzero_end:

From 5f99d33810b00666825784342868240e5790c704 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 14 Jul 2020 15:12:34 -0400
Subject: [PATCH 0003/1820] sparc32: kill lookup_fault()

No callers left.  As the result we can kill
	* lookup_fault() itself
	* the kludge in do_sparc_fault() for passing the
arguments for eventual lookup_fault() into exception handler and
labels used by it
	* the last of magical exception table entries (in __clear_user())

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/sparc/include/asm/uaccess_32.h |  5 ---
 arch/sparc/lib/memset.S             |  3 --
 arch/sparc/mm/fault_32.c            | 56 -----------------------------
 arch/sparc/mm/mm_32.h               |  2 --
 4 files changed, 66 deletions(-)

diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index 0a2d3ebc4bb8..54a3ba742647 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -252,12 +252,7 @@ static inline unsigned long __clear_user(void __user *addr, unsigned long size)
 	unsigned long ret;
 
 	__asm__ __volatile__ (
-		".section __ex_table,#alloc\n\t"
-		".align 4\n\t"
-		".word 1f,3\n\t"
-		".previous\n\t"
 		"mov %2, %%o1\n"
-		"1:\n\t"
 		"call __bzero\n\t"
 		" mov %1, %%o0\n\t"
 		"mov %%o0, %0\n"
diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index 725041c5224a..d79550e3e63f 100644
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -68,8 +68,6 @@ __bzero_begin:
 	.globl	memset
 	EXPORT_SYMBOL(__bzero)
 	EXPORT_SYMBOL(memset)
-	.globl	__memset_start, __memset_end
-__memset_start:
 memset:
 	mov	%o0, %g1
 	mov	1, %g4
@@ -181,7 +179,6 @@ __bzero:
 5:
 	retl
 	 clr	%o0
-__memset_end:
 
 	.section .fixup,#alloc,#execinstr
 	.align	4
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 40ce087dfecf..290869fd6b6a 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -54,54 +54,6 @@ static void __noreturn unhandled_fault(unsigned long address,
 	die_if_kernel("Oops", regs);
 }
 
-asmlinkage int lookup_fault(unsigned long pc, unsigned long ret_pc,
-			    unsigned long address)
-{
-	struct pt_regs regs;
-	unsigned long g2;
-	unsigned int insn;
-	int i;
-
-	i = search_extables_range(ret_pc, &g2);
-	switch (i) {
-	case 3:
-		/* load & store will be handled by fixup */
-		return 3;
-
-	case 1:
-		/* store will be handled by fixup, load will bump out */
-		/* for _to_ macros */
-		insn = *((unsigned int *) pc);
-		if ((insn >> 21) & 1)
-			return 1;
-		break;
-
-	case 2:
-		/* load will be handled by fixup, store will bump out */
-		/* for _from_ macros */
-		insn = *((unsigned int *) pc);
-		if (!((insn >> 21) & 1) || ((insn>>19)&0x3f) == 15)
-			return 2;
-		break;
-
-	default:
-		break;
-	}
-
-	memset(&regs, 0, sizeof(regs));
-	regs.pc = pc;
-	regs.npc = pc + 4;
-	__asm__ __volatile__(
-		"rd %%psr, %0\n\t"
-		"nop\n\t"
-		"nop\n\t"
-		"nop\n" : "=r" (regs.psr));
-	unhandled_fault(address, current, &regs);
-
-	/* Not reached */
-	return 0;
-}
-
 static inline void
 show_signal_msg(struct pt_regs *regs, int sig, int code,
 		unsigned long address, struct task_struct *tsk)
@@ -286,20 +238,12 @@ no_context:
 		fixup = search_extables_range(regs->pc, &g2);
 		/* Values below 10 are reserved for other things */
 		if (fixup > 10) {
-			extern const unsigned int __memset_start[];
-			extern const unsigned int __memset_end[];
-
 #ifdef DEBUG_EXCEPTIONS
 			printk("Exception: PC<%08lx> faddr<%08lx>\n",
 			       regs->pc, address);
 			printk("EX_TABLE: insn<%08lx> fixup<%08x> g2<%08lx>\n",
 				regs->pc, fixup, g2);
 #endif
-			if ((regs->pc >= (unsigned long)__memset_start &&
-			     regs->pc < (unsigned long)__memset_end)) {
-				regs->u_regs[UREG_I4] = address;
-				regs->u_regs[UREG_I5] = regs->pc;
-			}
 			regs->u_regs[UREG_G2] = g2;
 			regs->pc = fixup;
 			regs->npc = regs->pc + 4;
diff --git a/arch/sparc/mm/mm_32.h b/arch/sparc/mm/mm_32.h
index ce750a99eea9..ee55f1080634 100644
--- a/arch/sparc/mm/mm_32.h
+++ b/arch/sparc/mm/mm_32.h
@@ -1,7 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* fault_32.c - visible as they are called from assembler */
-asmlinkage int lookup_fault(unsigned long pc, unsigned long ret_pc,
-                            unsigned long address);
 asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
                                unsigned long address);
 

From df06c27ebd86af2b4c43f698c3d38b781dbc722d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 14 Jul 2020 17:27:56 -0400
Subject: [PATCH 0004/1820] sparc32: switch __bzero() away from range exception
 table entries

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/sparc/lib/memset.S | 72 ++++++++++++++++++-----------------------
 1 file changed, 32 insertions(+), 40 deletions(-)

diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index d79550e3e63f..eaff68213fdf 100644
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -27,35 +27,44 @@
 	.text;					\
 	.align	4
 
-#define EXT(start,end,handler) 			\
+#define STORE(source, base, offset, n)		\
+98: 	std source, [base + offset + n];	\
+	.section .fixup,ALLOC,EXECINSTR;	\
+	.align	4;				\
+99:	ba 30f;					\
+	 sub %o3, n - offset, %o3;		\
 	.section __ex_table,ALLOC;		\
 	.align	4;				\
-	.word	start, 0, end, handler;		\
+	.word	98b, 99b;			\
 	.text;					\
-	.align	4
+	.align	4;
+
+#define STORE_LAST(source, base, offset, n)	\
+	EX(std source, [base - offset - n],	\
+	   add %o1, offset + n);
 
 /* Please don't change these macros, unless you change the logic
  * in the .fixup section below as well.
  * Store 64 bytes at (BASE + OFFSET) using value SOURCE. */
-#define ZERO_BIG_BLOCK(base, offset, source)    \
-	std	source, [base + offset + 0x00]; \
-	std	source, [base + offset + 0x08]; \
-	std	source, [base + offset + 0x10]; \
-	std	source, [base + offset + 0x18]; \
-	std	source, [base + offset + 0x20]; \
-	std	source, [base + offset + 0x28]; \
-	std	source, [base + offset + 0x30]; \
-	std	source, [base + offset + 0x38];
+#define ZERO_BIG_BLOCK(base, offset, source)	\
+	STORE(source, base, offset, 0x00);	\
+	STORE(source, base, offset, 0x08);	\
+	STORE(source, base, offset, 0x10);	\
+	STORE(source, base, offset, 0x18);	\
+	STORE(source, base, offset, 0x20);	\
+	STORE(source, base, offset, 0x28);	\
+	STORE(source, base, offset, 0x30);	\
+	STORE(source, base, offset, 0x38);
 
 #define ZERO_LAST_BLOCKS(base, offset, source)	\
-	std	source, [base - offset - 0x38]; \
-	std	source, [base - offset - 0x30]; \
-	std	source, [base - offset - 0x28]; \
-	std	source, [base - offset - 0x20]; \
-	std	source, [base - offset - 0x18]; \
-	std	source, [base - offset - 0x10]; \
-	std	source, [base - offset - 0x08]; \
-	std	source, [base - offset - 0x00];
+	STORE_LAST(source, base, offset, 0x38);	\
+	STORE_LAST(source, base, offset, 0x30); \
+	STORE_LAST(source, base, offset, 0x28);	\
+	STORE_LAST(source, base, offset, 0x20);	\
+	STORE_LAST(source, base, offset, 0x18);	\
+	STORE_LAST(source, base, offset, 0x10);	\
+	STORE_LAST(source, base, offset, 0x08);	\
+	STORE_LAST(source, base, offset, 0x00);
 
 	.text
 	.align 4
@@ -120,8 +129,6 @@ __bzero:
 	ZERO_BIG_BLOCK(%o0, 0x00, %g2)
 	subcc	%o3, 128, %o3
 	ZERO_BIG_BLOCK(%o0, 0x40, %g2)
-11:
-	EXT(10b, 11b, 20f)
 	bne	10b
 	 add	%o0, 128, %o0
 
@@ -136,7 +143,6 @@ __bzero:
 	jmp	%o4
 	 add	%o0, %o2, %o0
 
-12:
 	ZERO_LAST_BLOCKS(%o0, 0x48, %g2)
 	ZERO_LAST_BLOCKS(%o0, 0x08, %g2)
 13:
@@ -182,24 +188,10 @@ __bzero:
 
 	.section .fixup,#alloc,#execinstr
 	.align	4
-20:
-	cmp	%g2, 8
-	bleu	1f
-	 and	%o1, 0x7f, %o1
-	sub	%g2, 9, %g2
-	add	%o3, 64, %o3
-1:
-	sll	%g2, 3, %g2
-	add	%o3, %o1, %o0
+30:
+	and	%o1, 0x7f, %o1
 	retl
-	 sub	%o0, %g2, %o0
-21:
-	mov	8, %o0
-	and	%o1, 7, %o1
-	sub	%o0, %g2, %o0
-	sll	%o0, 3, %o0
-	retl
-	 add	%o0, %o1, %o0
+	 add	%o3, %o1, %o0
 
 	.globl __bzero_end
 __bzero_end:

From cfd5fa7021a54b8ed9bad16246b6b34851fd48d1 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 14 Jul 2020 17:33:55 -0400
Subject: [PATCH 0005/1820] sparc32: get rid of range exception table entries
 in checksum_32.S

trivial - we don't even look at instruction offsets in the handler

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/sparc/lib/checksum_32.S | 64 +++++++++++++++---------------------
 1 file changed, 27 insertions(+), 37 deletions(-)

diff --git a/arch/sparc/lib/checksum_32.S b/arch/sparc/lib/checksum_32.S
index 7488d130faf7..781e39b3c009 100644
--- a/arch/sparc/lib/checksum_32.S
+++ b/arch/sparc/lib/checksum_32.S
@@ -155,13 +155,6 @@ cpout:	retl						! get outta here
         .text;                                  \
         .align  4
 
-#define EXT(start,end)				\
-        .section __ex_table,ALLOC;		\
-        .align  4;                              \
-        .word   start, 0, end, cc_fault;         \
-        .text;                                  \
-        .align  4
-
 	/* This aligned version executes typically in 8.5 superscalar cycles, this
 	 * is the best I can do.  I say 8.5 because the final add will pair with
 	 * the next ldd in the main unrolled loop.  Thus the pipe is always full.
@@ -169,20 +162,20 @@ cpout:	retl						! get outta here
 	 * please check the fixup code below as well.
 	 */
 #define CSUMCOPY_BIGCHUNK_ALIGNED(src, dst, sum, off, t0, t1, t2, t3, t4, t5, t6, t7)	\
-	ldd	[src + off + 0x00], t0;							\
-	ldd	[src + off + 0x08], t2;							\
+	EX(ldd	[src + off + 0x00], t0);						\
+	EX(ldd	[src + off + 0x08], t2);						\
 	addxcc	t0, sum, sum;								\
-	ldd	[src + off + 0x10], t4;							\
+	EX(ldd	[src + off + 0x10], t4);						\
 	addxcc	t1, sum, sum;								\
-	ldd	[src + off + 0x18], t6;							\
+	EX(ldd	[src + off + 0x18], t6);						\
 	addxcc	t2, sum, sum;								\
-	std	t0, [dst + off + 0x00];							\
+	EX(std	t0, [dst + off + 0x00]);						\
 	addxcc	t3, sum, sum;								\
-	std	t2, [dst + off + 0x08];							\
+	EX(std	t2, [dst + off + 0x08]);						\
 	addxcc	t4, sum, sum;								\
-	std	t4, [dst + off + 0x10];							\
+	EX(std	t4, [dst + off + 0x10]);						\
 	addxcc	t5, sum, sum;								\
-	std	t6, [dst + off + 0x18];							\
+	EX(std	t6, [dst + off + 0x18]);						\
 	addxcc	t6, sum, sum;								\
 	addxcc	t7, sum, sum;
 
@@ -191,39 +184,39 @@ cpout:	retl						! get outta here
 	 * Viking MXCC into streaming mode.  Ho hum...
 	 */
 #define CSUMCOPY_BIGCHUNK(src, dst, sum, off, t0, t1, t2, t3, t4, t5, t6, t7)	\
-	ldd	[src + off + 0x00], t0;						\
-	ldd	[src + off + 0x08], t2;						\
-	ldd	[src + off + 0x10], t4;						\
-	ldd	[src + off + 0x18], t6;						\
-	st	t0, [dst + off + 0x00];						\
+	EX(ldd	[src + off + 0x00], t0);					\
+	EX(ldd	[src + off + 0x08], t2);					\
+	EX(ldd	[src + off + 0x10], t4);					\
+	EX(ldd	[src + off + 0x18], t6);					\
+	EX(st	t0, [dst + off + 0x00]);					\
 	addxcc	t0, sum, sum;							\
-	st	t1, [dst + off + 0x04];						\
+	EX(st	t1, [dst + off + 0x04]);					\
 	addxcc	t1, sum, sum;							\
-	st	t2, [dst + off + 0x08];						\
+	EX(st	t2, [dst + off + 0x08]);					\
 	addxcc	t2, sum, sum;							\
-	st	t3, [dst + off + 0x0c];						\
+	EX(st	t3, [dst + off + 0x0c]);					\
 	addxcc	t3, sum, sum;							\
-	st	t4, [dst + off + 0x10];						\
+	EX(st	t4, [dst + off + 0x10]);					\
 	addxcc	t4, sum, sum;							\
-	st	t5, [dst + off + 0x14];						\
+	EX(st	t5, [dst + off + 0x14]);					\
 	addxcc	t5, sum, sum;							\
-	st	t6, [dst + off + 0x18];						\
+	EX(st	t6, [dst + off + 0x18]);					\
 	addxcc	t6, sum, sum;							\
-	st	t7, [dst + off + 0x1c];						\
+	EX(st	t7, [dst + off + 0x1c]);					\
 	addxcc	t7, sum, sum;
 
 	/* Yuck, 6 superscalar cycles... */
 #define CSUMCOPY_LASTCHUNK(src, dst, sum, off, t0, t1, t2, t3)	\
-	ldd	[src - off - 0x08], t0;				\
-	ldd	[src - off - 0x00], t2;				\
+	EX(ldd	[src - off - 0x08], t0);			\
+	EX(ldd	[src - off - 0x00], t2);			\
 	addxcc	t0, sum, sum;					\
-	st	t0, [dst - off - 0x08];				\
+	EX(st	t0, [dst - off - 0x08]);			\
 	addxcc	t1, sum, sum;					\
-	st	t1, [dst - off - 0x04];				\
+	EX(st	t1, [dst - off - 0x04]);			\
 	addxcc	t2, sum, sum;					\
-	st	t2, [dst - off - 0x00];				\
+	EX(st	t2, [dst - off - 0x00]);			\
 	addxcc	t3, sum, sum;					\
-	st	t3, [dst - off + 0x04];
+	EX(st	t3, [dst - off + 0x04]);
 
 	/* Handle the end cruft code out of band for better cache patterns. */
 cc_end_cruft:
@@ -331,7 +324,6 @@ __csum_partial_copy_sparc_generic:
 	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-10:	EXT(5b, 10b)			! note for exception handling
 	sub	%g1, 128, %g1		! detract from length
 	addx	%g0, %g7, %g7		! add in last carry bit
 	andcc	%g1, 0xffffff80, %g0	! more to csum?
@@ -356,8 +348,7 @@ cctbl:	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x68,%g2,%g3,%g4,%g5)
 	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x28,%g2,%g3,%g4,%g5)
 	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x18,%g2,%g3,%g4,%g5)
 	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x08,%g2,%g3,%g4,%g5)
-12:	EXT(cctbl, 12b)			! note for exception table handling
-	addx	%g0, %g7, %g7
+12:	addx	%g0, %g7, %g7
 	andcc	%o3, 0xf, %g0		! check for low bits set
 ccte:	bne	cc_end_cruft		! something left, handle it out of band
 	 andcc	%o3, 8, %g0		! begin checks for that code
@@ -367,7 +358,6 @@ ccdbl:	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x00,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o
 	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-11:	EXT(ccdbl, 11b)			! note for exception table handling
 	sub	%g1, 128, %g1		! detract from length
 	addx	%g0, %g7, %g7		! add in last carry bit
 	andcc	%g1, 0xffffff80, %g0	! more to csum?

From c4da8e0dc6f7cec80f32af080cadf47c1753a2ab Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 16 Jul 2020 10:19:37 -0400
Subject: [PATCH 0006/1820] sparc32: switch copy_user.S away from range
 exception table entries

Those were the last range exception table entries, which will allow
to get rid of a lot of weirdness.  Emits the same code into .text.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/sparc/lib/copy_user.S | 311 +++++++++++++------------------------
 1 file changed, 110 insertions(+), 201 deletions(-)

diff --git a/arch/sparc/lib/copy_user.S b/arch/sparc/lib/copy_user.S
index dc72f2b970b7..954572c78539 100644
--- a/arch/sparc/lib/copy_user.S
+++ b/arch/sparc/lib/copy_user.S
@@ -21,98 +21,134 @@
 /* Work around cpp -rob */
 #define ALLOC #alloc
 #define EXECINSTR #execinstr
+
+#define EX_ENTRY(l1, l2)			\
+	.section __ex_table,ALLOC;		\
+	.align	4;				\
+	.word	l1, l2;				\
+	.text;
+
 #define EX(x,y,a,b) 				\
 98: 	x,y;					\
 	.section .fixup,ALLOC,EXECINSTR;	\
 	.align	4;				\
-99:	ba fixupretl;				\
-	 a, b, %g3;				\
-	.section __ex_table,ALLOC;		\
-	.align	4;				\
-	.word	98b, 99b;			\
-	.text;					\
-	.align	4
+99:	retl;					\
+	 a, b, %o0;				\
+	EX_ENTRY(98b, 99b)
 
 #define EX2(x,y,c,d,e,a,b) 			\
 98: 	x,y;					\
 	.section .fixup,ALLOC,EXECINSTR;	\
 	.align	4;				\
 99:	c, d, e;				\
-	ba fixupretl;				\
-	 a, b, %g3;				\
-	.section __ex_table,ALLOC;		\
-	.align	4;				\
-	.word	98b, 99b;			\
-	.text;					\
-	.align	4
+	retl;					\
+	 a, b, %o0;				\
+	EX_ENTRY(98b, 99b)
 
 #define EXO2(x,y) 				\
 98: 	x, y;					\
-	.section __ex_table,ALLOC;		\
-	.align	4;				\
-	.word	98b, 97f;			\
-	.text;					\
-	.align	4
+	EX_ENTRY(98b, 97f)
 
-#define EXT(start,end,handler)			\
-	.section __ex_table,ALLOC;		\
-	.align	4;				\
-	.word	start, 0, end, handler;		\
-	.text;					\
-	.align	4
+#define LD(insn, src, offset, reg, label)	\
+98:	insn [%src + (offset)], %reg;		\
+	.section .fixup,ALLOC,EXECINSTR;	\
+99:	ba	label;				\
+	 mov	offset, %g5;			\
+	EX_ENTRY(98b, 99b)
 
-/* Please do not change following macros unless you change logic used
- * in .fixup at the end of this file as well
- */
+#define ST(insn, dst, offset, reg, label)	\
+98:	insn %reg, [%dst + (offset)];		\
+	.section .fixup,ALLOC,EXECINSTR;	\
+99:	ba	label;				\
+	 mov	offset, %g5;			\
+	EX_ENTRY(98b, 99b)
 
 /* Both these macros have to start with exactly the same insn */
+/* left: g7 + (g1 % 128) - offset */
 #define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
-	ldd	[%src + (offset) + 0x00], %t0; \
-	ldd	[%src + (offset) + 0x08], %t2; \
-	ldd	[%src + (offset) + 0x10], %t4; \
-	ldd	[%src + (offset) + 0x18], %t6; \
-	st	%t0, [%dst + (offset) + 0x00]; \
-	st	%t1, [%dst + (offset) + 0x04]; \
-	st	%t2, [%dst + (offset) + 0x08]; \
-	st	%t3, [%dst + (offset) + 0x0c]; \
-	st	%t4, [%dst + (offset) + 0x10]; \
-	st	%t5, [%dst + (offset) + 0x14]; \
-	st	%t6, [%dst + (offset) + 0x18]; \
-	st	%t7, [%dst + (offset) + 0x1c];
+	LD(ldd, src, offset + 0x00, t0, bigchunk_fault)	\
+	LD(ldd, src, offset + 0x08, t2, bigchunk_fault)	\
+	LD(ldd, src, offset + 0x10, t4, bigchunk_fault)	\
+	LD(ldd, src, offset + 0x18, t6, bigchunk_fault)	\
+	ST(st, dst, offset + 0x00, t0, bigchunk_fault)	\
+	ST(st, dst, offset + 0x04, t1, bigchunk_fault)	\
+	ST(st, dst, offset + 0x08, t2, bigchunk_fault)	\
+	ST(st, dst, offset + 0x0c, t3, bigchunk_fault)	\
+	ST(st, dst, offset + 0x10, t4, bigchunk_fault)	\
+	ST(st, dst, offset + 0x14, t5, bigchunk_fault)	\
+	ST(st, dst, offset + 0x18, t6, bigchunk_fault)	\
+	ST(st, dst, offset + 0x1c, t7, bigchunk_fault)
 
+/* left: g7 + (g1 % 128) - offset */
 #define MOVE_BIGALIGNCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
-	ldd	[%src + (offset) + 0x00], %t0; \
-	ldd	[%src + (offset) + 0x08], %t2; \
-	ldd	[%src + (offset) + 0x10], %t4; \
-	ldd	[%src + (offset) + 0x18], %t6; \
-	std	%t0, [%dst + (offset) + 0x00]; \
-	std	%t2, [%dst + (offset) + 0x08]; \
-	std	%t4, [%dst + (offset) + 0x10]; \
-	std	%t6, [%dst + (offset) + 0x18];
+	LD(ldd, src, offset + 0x00, t0, bigchunk_fault)	\
+	LD(ldd, src, offset + 0x08, t2, bigchunk_fault)	\
+	LD(ldd, src, offset + 0x10, t4, bigchunk_fault)	\
+	LD(ldd, src, offset + 0x18, t6, bigchunk_fault)	\
+	ST(std, dst, offset + 0x00, t0, bigchunk_fault)	\
+	ST(std, dst, offset + 0x08, t2, bigchunk_fault)	\
+	ST(std, dst, offset + 0x10, t4, bigchunk_fault)	\
+	ST(std, dst, offset + 0x18, t6, bigchunk_fault)
 
+	.section .fixup,#alloc,#execinstr
+bigchunk_fault:
+	sub	%g7, %g5, %o0
+	and	%g1, 127, %g1
+	retl
+	 add	%o0, %g1, %o0
+
+/* left: offset + 16 + (g1 % 16) */
 #define MOVE_LASTCHUNK(src, dst, offset, t0, t1, t2, t3) \
-	ldd	[%src - (offset) - 0x10], %t0; \
-	ldd	[%src - (offset) - 0x08], %t2; \
-	st	%t0, [%dst - (offset) - 0x10]; \
-	st	%t1, [%dst - (offset) - 0x0c]; \
-	st	%t2, [%dst - (offset) - 0x08]; \
-	st	%t3, [%dst - (offset) - 0x04];
+	LD(ldd, src, -(offset + 0x10), t0, lastchunk_fault)	\
+	LD(ldd, src, -(offset + 0x08), t2, lastchunk_fault)	\
+	ST(st, dst, -(offset + 0x10), t0, lastchunk_fault)	\
+	ST(st, dst, -(offset + 0x0c), t1, lastchunk_fault)	\
+	ST(st, dst, -(offset + 0x08), t2, lastchunk_fault)	\
+	ST(st, dst, -(offset + 0x04), t3, lastchunk_fault)
 
+	.section .fixup,#alloc,#execinstr
+lastchunk_fault:
+	and	%g1, 15, %g1
+	retl
+	 sub	%g1, %g5, %o0
+
+/* left: o3 + (o2 % 16) - offset */
 #define MOVE_HALFCHUNK(src, dst, offset, t0, t1, t2, t3) \
-	lduh	[%src + (offset) + 0x00], %t0; \
-	lduh	[%src + (offset) + 0x02], %t1; \
-	lduh	[%src + (offset) + 0x04], %t2; \
-	lduh	[%src + (offset) + 0x06], %t3; \
-	sth	%t0, [%dst + (offset) + 0x00]; \
-	sth	%t1, [%dst + (offset) + 0x02]; \
-	sth	%t2, [%dst + (offset) + 0x04]; \
-	sth	%t3, [%dst + (offset) + 0x06];
+	LD(lduh, src, offset + 0x00, t0, halfchunk_fault)	\
+	LD(lduh, src, offset + 0x02, t1, halfchunk_fault)	\
+	LD(lduh, src, offset + 0x04, t2, halfchunk_fault)	\
+	LD(lduh, src, offset + 0x06, t3, halfchunk_fault)	\
+	ST(sth, dst, offset + 0x00, t0, halfchunk_fault)	\
+	ST(sth, dst, offset + 0x02, t1, halfchunk_fault)	\
+	ST(sth, dst, offset + 0x04, t2, halfchunk_fault)	\
+	ST(sth, dst, offset + 0x06, t3, halfchunk_fault)
 
+/* left: o3 + (o2 % 16) + offset + 2 */
 #define MOVE_SHORTCHUNK(src, dst, offset, t0, t1) \
-	ldub	[%src - (offset) - 0x02], %t0; \
-	ldub	[%src - (offset) - 0x01], %t1; \
-	stb	%t0, [%dst - (offset) - 0x02]; \
-	stb	%t1, [%dst - (offset) - 0x01];
+	LD(ldub, src, -(offset + 0x02), t0, halfchunk_fault)	\
+	LD(ldub, src, -(offset + 0x01), t1, halfchunk_fault)	\
+	ST(stb, dst, -(offset + 0x02), t0, halfchunk_fault)	\
+	ST(stb, dst, -(offset + 0x01), t1, halfchunk_fault)
+
+	.section .fixup,#alloc,#execinstr
+halfchunk_fault:
+	and	%o2, 15, %o2
+	sub	%o3, %g5, %o3
+	retl
+	 add	%o2, %o3, %o0
+
+/* left: offset + 2 + (o2 % 2) */
+#define MOVE_LAST_SHORTCHUNK(src, dst, offset, t0, t1) \
+	LD(ldub, src, -(offset + 0x02), t0, last_shortchunk_fault)	\
+	LD(ldub, src, -(offset + 0x01), t1, last_shortchunk_fault)	\
+	ST(stb, dst, -(offset + 0x02), t0, last_shortchunk_fault)	\
+	ST(stb, dst, -(offset + 0x01), t1, last_shortchunk_fault)
+
+	.section .fixup,#alloc,#execinstr
+last_shortchunk_fault:
+	and	%o2, 1, %o2
+	retl
+	 sub	%o2, %g5, %o0
 
 	.text
 	.align	4
@@ -182,8 +218,6 @@ __copy_user:	/* %o0=dst %o1=src %o2=len */
 	MOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-80:
-	EXT(5b, 80b, 50f)
 	subcc	%g7, 128, %g7
 	add	%o1, 128, %o1
 	bne	5b
@@ -201,7 +235,6 @@ __copy_user:	/* %o0=dst %o1=src %o2=len */
 	jmpl	%o5 + %lo(copy_user_table_end), %g0
 	 add	%o0, %g7, %o0
 
-copy_user_table:
 	MOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g4, g5)
 	MOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g4, g5)
 	MOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g4, g5)
@@ -210,7 +243,6 @@ copy_user_table:
 	MOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g4, g5)
 	MOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
 copy_user_table_end:
-	EXT(copy_user_table, copy_user_table_end, 51f)
 	be	copy_user_last7
 	 andcc	%g1, 4, %g0
 
@@ -250,8 +282,6 @@ ldd_std:
 	MOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-81:
-	EXT(ldd_std, 81b, 52f)
 	subcc	%g7, 128, %g7
 	add	%o1, 128, %o1
 	bne	ldd_std
@@ -290,8 +320,6 @@ cannot_optimize:
 10:
 	MOVE_HALFCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
 	MOVE_HALFCHUNK(o1, o0, 0x08, g2, g3, g4, g5)
-82:
-	EXT(10b, 82b, 53f)
 	subcc	%o3, 0x10, %o3
 	add	%o1, 0x10, %o1
 	bne	10b
@@ -308,8 +336,6 @@ byte_chunk:
 	MOVE_SHORTCHUNK(o1, o0, -0x0c, g2, g3)
 	MOVE_SHORTCHUNK(o1, o0, -0x0e, g2, g3)
 	MOVE_SHORTCHUNK(o1, o0, -0x10, g2, g3)
-83:
-	EXT(byte_chunk, 83b, 54f)
 	subcc	%o3, 0x10, %o3
 	add	%o1, 0x10, %o1
 	bne	byte_chunk
@@ -325,16 +351,14 @@ short_end:
 	add	%o1, %o3, %o1
 	jmpl	%o5 + %lo(short_table_end), %g0
 	 andcc	%o2, 1, %g0
-84:
-	MOVE_SHORTCHUNK(o1, o0, 0x0c, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x0a, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x08, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x06, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x04, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x02, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x00, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x0c, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x0a, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x08, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x06, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x04, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x02, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x00, g2, g3)
 short_table_end:
-	EXT(84b, short_table_end, 55f)
 	be	1f
 	 nop
 	EX(ldub	[%o1], %g2, add %g0, 1)
@@ -363,123 +387,8 @@ short_aligned_end:
 	.section .fixup,#alloc,#execinstr
 	.align	4
 97:
-	mov	%o2, %g3
-fixupretl:
 	retl
-	 mov	%g3, %o0
-
-/* exception routine sets %g2 to (broken_insn - first_insn)>>2 */
-50:
-/* This magic counts how many bytes are left when crash in MOVE_BIGCHUNK
- * happens. This is derived from the amount ldd reads, st stores, etc.
- * x = g2 % 12;
- * g3 = g1 + g7 - ((g2 / 12) * 32 + (x < 4) ? 0 : (x - 4) * 4);
- * o0 += (g2 / 12) * 32;
- */
-	cmp	%g2, 12
-	add	%o0, %g7, %o0
-	bcs	1f
-	 cmp	%g2, 24
-	bcs	2f
-	 cmp	%g2, 36
-	bcs	3f
-	 nop
-	sub	%g2, 12, %g2
-	sub	%g7, 32, %g7
-3:	sub	%g2, 12, %g2
-	sub	%g7, 32, %g7
-2:	sub	%g2, 12, %g2
-	sub	%g7, 32, %g7
-1:	cmp	%g2, 4
-	bcs,a	60f
-	 clr	%g2
-	sub	%g2, 4, %g2
-	sll	%g2, 2, %g2
-60:	and	%g1, 0x7f, %g3
-	sub	%o0, %g7, %o0
-	add	%g3, %g7, %g3
-	ba	fixupretl
-	 sub	%g3, %g2, %g3
-51:
-/* i = 41 - g2; j = i % 6;
- * g3 = (g1 & 15) + (i / 6) * 16 + (j < 4) ? (j + 1) * 4 : 16;
- * o0 -= (i / 6) * 16 + 16;
- */
-	neg	%g2
-	and	%g1, 0xf, %g1
-	add	%g2, 41, %g2
-	add	%o0, %g1, %o0
-1:	cmp	%g2, 6
-	bcs,a	2f
-	 cmp	%g2, 4
-	add	%g1, 16, %g1
-	b	1b
-	 sub	%g2, 6, %g2
-2:	bcc,a	2f
-	 mov	16, %g2
-	inc	%g2
-	sll	%g2, 2, %g2
-2:	add	%g1, %g2, %g3
-	ba	fixupretl
-	 sub	%o0, %g3, %o0
-52:
-/* g3 = g1 + g7 - (g2 / 8) * 32 + (g2 & 4) ? (g2 & 3) * 8 : 0;
-   o0 += (g2 / 8) * 32 */
-	andn	%g2, 7, %g4
-	add	%o0, %g7, %o0
-	andcc	%g2, 4, %g0
-	and	%g2, 3, %g2
-	sll	%g4, 2, %g4
-	sll	%g2, 3, %g2
-	bne	60b
-	 sub	%g7, %g4, %g7
-	ba	60b
-	 clr	%g2
-53:
-/* g3 = o3 + (o2 & 15) - (g2 & 8) - (g2 & 4) ? (g2 & 3) * 2 : 0;
-   o0 += (g2 & 8) */
-	and	%g2, 3, %g4
-	andcc	%g2, 4, %g0
-	and	%g2, 8, %g2
-	sll	%g4, 1, %g4
-	be	1f
-	 add	%o0, %g2, %o0
-	add	%g2, %g4, %g2
-1:	and	%o2, 0xf, %g3
-	add	%g3, %o3, %g3
-	ba	fixupretl
-	 sub	%g3, %g2, %g3
-54:
-/* g3 = o3 + (o2 & 15) - (g2 / 4) * 2 - (g2 & 2) ? (g2 & 1) : 0;
-   o0 += (g2 / 4) * 2 */
-	srl	%g2, 2, %o4
-	and	%g2, 1, %o5
-	srl	%g2, 1, %g2
-	add	%o4, %o4, %o4
-	and	%o5, %g2, %o5
-	and	%o2, 0xf, %o2
-	add	%o0, %o4, %o0
-	sub	%o3, %o5, %o3
-	sub	%o2, %o4, %o2
-	ba	fixupretl
-	 add	%o2, %o3, %g3
-55:
-/* i = 27 - g2;
-   g3 = (o2 & 1) + i / 4 * 2 + !(i & 3);
-   o0 -= i / 4 * 2 + 1 */
-	neg	%g2
-	and	%o2, 1, %o2
-	add	%g2, 27, %g2
-	srl	%g2, 2, %o5
-	andcc	%g2, 3, %g0
-	mov	1, %g2
-	add	%o5, %o5, %o5
-	be,a	1f
-	 clr	%g2
-1:	add	%g2, %o5, %g3
-	sub	%o0, %g3, %o0
-	ba	fixupretl
-	 add	%g3, %o2, %g3
+	 mov	%o2, %o0
 
 	.globl  __copy_user_end
 __copy_user_end:

From b4edf06c8aaae30ef926bd6853df6e59a7579ee9 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 16 Jul 2020 14:05:36 -0400
Subject: [PATCH 0007/1820] sparc32: switch to generic extables

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/sparc/include/asm/elf_64.h               |   1 -
 .../include/asm/{extable_64.h => extable.h}   |   4 +-
 arch/sparc/include/asm/uaccess.h              |   3 +
 arch/sparc/include/asm/uaccess_32.h           |  33 ------
 arch/sparc/include/asm/uaccess_64.h           |   1 -
 arch/sparc/kernel/unaligned_32.c              |  10 +-
 arch/sparc/mm/Makefile                        |   2 +-
 arch/sparc/mm/extable.c                       | 107 ------------------
 arch/sparc/mm/fault_32.c                      |  26 ++---
 lib/extable.c                                 |   5 -
 10 files changed, 22 insertions(+), 170 deletions(-)
 rename arch/sparc/include/asm/{extable_64.h => extable.h} (92%)
 delete mode 100644 arch/sparc/mm/extable.c

diff --git a/arch/sparc/include/asm/elf_64.h b/arch/sparc/include/asm/elf_64.h
index 7e078bc73ef5..8fb09eec8c3e 100644
--- a/arch/sparc/include/asm/elf_64.h
+++ b/arch/sparc/include/asm/elf_64.h
@@ -8,7 +8,6 @@
 
 #include <asm/ptrace.h>
 #include <asm/processor.h>
-#include <asm/extable_64.h>
 #include <asm/spitfire.h>
 #include <asm/adi.h>
 
diff --git a/arch/sparc/include/asm/extable_64.h b/arch/sparc/include/asm/extable.h
similarity index 92%
rename from arch/sparc/include/asm/extable_64.h
rename to arch/sparc/include/asm/extable.h
index 5a0171907b7e..554a9dc376fc 100644
--- a/arch/sparc/include/asm/extable_64.h
+++ b/arch/sparc/include/asm/extable.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_EXTABLE64_H
-#define __ASM_EXTABLE64_H
+#ifndef __ASM_EXTABLE_H
+#define __ASM_EXTABLE_H
 /*
  * The exception table consists of pairs of addresses: the first is the
  * address of an instruction that is allowed to fault, and the second is
diff --git a/arch/sparc/include/asm/uaccess.h b/arch/sparc/include/asm/uaccess.h
index dd85bc2c2cad..390094200fc4 100644
--- a/arch/sparc/include/asm/uaccess.h
+++ b/arch/sparc/include/asm/uaccess.h
@@ -1,6 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ___ASM_SPARC_UACCESS_H
 #define ___ASM_SPARC_UACCESS_H
+
+#include <asm/extable.h>
+
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/uaccess_64.h>
 #else
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index 54a3ba742647..4a12346bb69c 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -13,9 +13,6 @@
 
 #include <asm/processor.h>
 
-#define ARCH_HAS_SORT_EXTABLE
-#define ARCH_HAS_SEARCH_EXTABLE
-
 /* Sparc is not segmented, however we need to be able to fool access_ok()
  * when doing system calls from kernel mode legitimately.
  *
@@ -40,36 +37,6 @@
 #define __access_ok(addr, size) (__user_ok((addr) & get_fs().seg, (size)))
 #define access_ok(addr, size) __access_ok((unsigned long)(addr), size)
 
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- *
- * There is a special way how to put a range of potentially faulting
- * insns (like twenty ldd/std's with now intervening other instructions)
- * You specify address of first in insn and 0 in fixup and in the next
- * exception_table_entry you specify last potentially faulting insn + 1
- * and in fixup the routine which should handle the fault.
- * That fixup code will get
- * (faulting_insn_address - first_insn_in_the_range_address)/4
- * in %g2 (ie. index of the faulting instruction in the range).
- */
-
-struct exception_table_entry
-{
-        unsigned long insn, fixup;
-};
-
-/* Returns 0 if exception not found and fixup otherwise.  */
-unsigned long search_extables_range(unsigned long addr, unsigned long *g2);
-
 /* Uh, these should become the main single-value transfer routines..
  * They automatically use the right size if we just have the right
  * pointer type..
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index 698cf69f74e9..30eb4c6414d1 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -10,7 +10,6 @@
 #include <linux/string.h>
 #include <asm/asi.h>
 #include <asm/spitfire.h>
-#include <asm/extable_64.h>
 
 #include <asm/processor.h>
 
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index 83db94c0b431..1d7c3eaabdd4 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -16,6 +16,7 @@
 #include <linux/uaccess.h>
 #include <linux/smp.h>
 #include <linux/perf_event.h>
+#include <linux/extable.h>
 
 #include <asm/setup.h>
 
@@ -213,10 +214,10 @@ static inline int ok_for_kernel(unsigned int insn)
 
 static void kernel_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
 {
-	unsigned long g2 = regs->u_regs [UREG_G2];
-	unsigned long fixup = search_extables_range(regs->pc, &g2);
+	const struct exception_table_entry *entry;
 
-	if (!fixup) {
+	entry = search_exception_tables(regs->pc);
+	if (!entry) {
 		unsigned long address = compute_effective_address(regs, insn);
         	if(address < PAGE_SIZE) {
                 	printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference in mna handler");
@@ -232,9 +233,8 @@ static void kernel_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
 	        die_if_kernel("Oops", regs);
 		/* Not reached */
 	}
-	regs->pc = fixup;
+	regs->pc = entry->fixup;
 	regs->npc = regs->pc + 4;
-	regs->u_regs [UREG_G2] = g2;
 }
 
 asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index 68db1f859b02..871354aa3c00 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -8,7 +8,7 @@ ccflags-y := -Werror
 obj-$(CONFIG_SPARC64)   += ultra.o tlb.o tsb.o
 obj-y                   += fault_$(BITS).o
 obj-y                   += init_$(BITS).o
-obj-$(CONFIG_SPARC32)   += extable.o srmmu.o iommu.o io-unit.o
+obj-$(CONFIG_SPARC32)   += srmmu.o iommu.o io-unit.o
 obj-$(CONFIG_SPARC32)   += srmmu_access.o
 obj-$(CONFIG_SPARC32)   += hypersparc.o viking.o tsunami.o swift.o
 obj-$(CONFIG_SPARC32)   += leon_mm.o
diff --git a/arch/sparc/mm/extable.c b/arch/sparc/mm/extable.c
deleted file mode 100644
index 241b40641873..000000000000
--- a/arch/sparc/mm/extable.c
+++ /dev/null
@@ -1,107 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * linux/arch/sparc/mm/extable.c
- */
-
-#include <linux/module.h>
-#include <linux/extable.h>
-#include <linux/uaccess.h>
-
-void sort_extable(struct exception_table_entry *start,
-		  struct exception_table_entry *finish)
-{
-}
-
-/* Caller knows they are in a range if ret->fixup == 0 */
-const struct exception_table_entry *
-search_extable(const struct exception_table_entry *base,
-	       const size_t num,
-	       unsigned long value)
-{
-	int i;
-
-	/* Single insn entries are encoded as:
-	 *	word 1:	insn address
-	 *	word 2:	fixup code address
-	 *
-	 * Range entries are encoded as:
-	 *	word 1: first insn address
-	 *	word 2: 0
-	 *	word 3: last insn address + 4 bytes
-	 *	word 4: fixup code address
-	 *
-	 * Deleted entries are encoded as:
-	 *	word 1: unused
-	 *	word 2: -1
-	 *
-	 * See asm/uaccess.h for more details.
-	 */
-
-	/* 1. Try to find an exact match. */
-	for (i = 0; i < num; i++) {
-		if (base[i].fixup == 0) {
-			/* A range entry, skip both parts. */
-			i++;
-			continue;
-		}
-
-		/* A deleted entry; see trim_init_extable */
-		if (base[i].fixup == -1)
-			continue;
-
-		if (base[i].insn == value)
-			return &base[i];
-	}
-
-	/* 2. Try to find a range match. */
-	for (i = 0; i < (num - 1); i++) {
-		if (base[i].fixup)
-			continue;
-
-		if (base[i].insn <= value && base[i + 1].insn > value)
-			return &base[i];
-
-		i++;
-	}
-
-        return NULL;
-}
-
-#ifdef CONFIG_MODULES
-/* We could memmove them around; easier to mark the trimmed ones. */
-void trim_init_extable(struct module *m)
-{
-	unsigned int i;
-	bool range;
-
-	for (i = 0; i < m->num_exentries; i += range ? 2 : 1) {
-		range = m->extable[i].fixup == 0;
-
-		if (within_module_init(m->extable[i].insn, m)) {
-			m->extable[i].fixup = -1;
-			if (range)
-				m->extable[i+1].fixup = -1;
-		}
-		if (range)
-			i++;
-	}
-}
-#endif /* CONFIG_MODULES */
-
-/* Special extable search, which handles ranges.  Returns fixup */
-unsigned long search_extables_range(unsigned long addr, unsigned long *g2)
-{
-	const struct exception_table_entry *entry;
-
-	entry = search_exception_tables(addr);
-	if (!entry)
-		return 0;
-
-	/* Inside range?  Fix g2 and return correct fixup */
-	if (!entry->fixup) {
-		*g2 = (addr - entry->insn) / 4;
-		return (entry + 1)->fixup;
-	}
-
-	return entry->fixup;
-}
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 290869fd6b6a..de2031c2b2d7 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/kdebug.h>
 #include <linux/uaccess.h>
+#include <linux/extable.h>
 
 #include <asm/page.h>
 #include <asm/openprom.h>
@@ -114,8 +115,6 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	struct vm_area_struct *vma;
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
-	unsigned int fixup;
-	unsigned long g2;
 	int from_user = !(regs->psr & PSR_PS);
 	int code;
 	vm_fault_t fault;
@@ -233,22 +232,19 @@ bad_area_nosemaphore:
 
 	/* Is this in ex_table? */
 no_context:
-	g2 = regs->u_regs[UREG_G2];
 	if (!from_user) {
-		fixup = search_extables_range(regs->pc, &g2);
-		/* Values below 10 are reserved for other things */
-		if (fixup > 10) {
+		const struct exception_table_entry *entry;
+
+		entry = search_exception_tables(regs->pc);
 #ifdef DEBUG_EXCEPTIONS
-			printk("Exception: PC<%08lx> faddr<%08lx>\n",
-			       regs->pc, address);
-			printk("EX_TABLE: insn<%08lx> fixup<%08x> g2<%08lx>\n",
-				regs->pc, fixup, g2);
+		printk("Exception: PC<%08lx> faddr<%08lx>\n",
+		       regs->pc, address);
+		printk("EX_TABLE: insn<%08lx> fixup<%08x>\n",
+			regs->pc, entry->fixup);
 #endif
-			regs->u_regs[UREG_G2] = g2;
-			regs->pc = fixup;
-			regs->npc = regs->pc + 4;
-			return;
-		}
+		regs->pc = entry->fixup;
+		regs->npc = regs->pc + 4;
+		return;
 	}
 
 	unhandled_fault(address, tsk, regs);
diff --git a/lib/extable.c b/lib/extable.c
index c3e59caf7ffa..9c9f40bd2b3d 100644
--- a/lib/extable.c
+++ b/lib/extable.c
@@ -21,7 +21,6 @@ static inline unsigned long ex_to_insn(const struct exception_table_entry *x)
 }
 #endif
 
-#ifndef ARCH_HAS_SORT_EXTABLE
 #ifndef ARCH_HAS_RELATIVE_EXTABLE
 #define swap_ex		NULL
 #else
@@ -88,9 +87,6 @@ void trim_init_extable(struct module *m)
 		m->num_exentries--;
 }
 #endif /* CONFIG_MODULES */
-#endif /* !ARCH_HAS_SORT_EXTABLE */
-
-#ifndef ARCH_HAS_SEARCH_EXTABLE
 
 static int cmp_ex_search(const void *key, const void *elt)
 {
@@ -120,4 +116,3 @@ search_extable(const struct exception_table_entry *base,
 	return bsearch(&value, base, num,
 		       sizeof(struct exception_table_entry), cmp_ex_search);
 }
-#endif

From d17b9ec777d86c590a77a404565be5d6005f2fe2 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 19 Aug 2020 17:50:40 -0400
Subject: [PATCH 0008/1820] sparc64: get rid of fake_swapper_regs

no reason to have ->kregs of initial thread set up in a special
way - we can keep them on stack, same as for every other thread.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/sparc/include/asm/thread_info_64.h | 1 +
 arch/sparc/kernel/head_64.S             | 2 +-
 arch/sparc/kernel/setup_64.c            | 4 ----
 3 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 42cd4cd3892e..8047a9caab2f 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -118,6 +118,7 @@ struct thread_info {
 	.task		=	&tsk,			\
 	.current_ds	=	ASI_P,			\
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
+	.kregs		=	(struct pt_regs *)(init_stack+THREAD_SIZE)-1 \
 }
 
 /* how to get the thread information struct from C */
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index c5ff2472b3d9..72a5bdc833ea 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -706,7 +706,7 @@ tlb_fixup_done:
 	wr	%g0, ASI_P, %asi
 	mov	1, %g1
 	sllx	%g1, THREAD_SHIFT, %g1
-	sub	%g1, (STACKFRAME_SZ + STACK_BIAS), %g1
+	sub	%g1, (STACKFRAME_SZ + STACK_BIAS + TRACEREG_SZ), %g1
 	add	%g6, %g1, %sp
 
 	/* Set per-cpu pointer initially to zero, this makes
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index d87244197d5c..48abee4eee29 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -165,8 +165,6 @@ extern int root_mountflags;
 
 char reboot_command[COMMAND_LINE_SIZE];
 
-static struct pt_regs fake_swapper_regs = { { 0, }, 0, 0, 0, 0 };
-
 static void __init per_cpu_patch(void)
 {
 	struct cpuid_patch_entry *p;
@@ -661,8 +659,6 @@ void __init setup_arch(char **cmdline_p)
 	rd_image_start = ram_flags & RAMDISK_IMAGE_START_MASK;
 #endif
 
-	task_thread_info(&init_task)->kregs = &fake_swapper_regs;
-
 #ifdef CONFIG_IP_PNP
 	if (!ic_set_manually) {
 		phandle chosen = prom_finddevice("/chosen");

From af7652500b4c43643a8531b82974e97b1248a03a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 19 Aug 2020 18:05:02 -0400
Subject: [PATCH 0009/1820] sparc32: get rid of fake_swapper_regs

no reason to have ->kregs of initial thread set up in a special
way - we can keep them on stack, same as for every other thread.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/sparc/include/asm/processor_32.h | 1 +
 arch/sparc/kernel/head_32.S           | 2 +-
 arch/sparc/kernel/process_32.c        | 9 +--------
 arch/sparc/kernel/setup_32.c          | 3 ---
 4 files changed, 3 insertions(+), 12 deletions(-)

diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index 3c4bc2189092..d7b71d7bed1f 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/arch/sparc/include/asm/processor_32.h
@@ -60,6 +60,7 @@ struct thread_struct {
 #define INIT_THREAD  { \
 	.flags = SPARC_FLAG_KTHREAD, \
 	.current_ds = KERNEL_DS, \
+	.kregs = (struct pt_regs *)(init_stack+THREAD_SIZE)-1 \
 }
 
 /* Do necessary setup to start up a newly executed thread. */
diff --git a/arch/sparc/kernel/head_32.S b/arch/sparc/kernel/head_32.S
index be30c8d4cc73..6044b82b9767 100644
--- a/arch/sparc/kernel/head_32.S
+++ b/arch/sparc/kernel/head_32.S
@@ -515,7 +515,7 @@ continue_boot:
 
 		/* I want a kernel stack NOW! */
 		set	init_thread_union, %g1
-		set	(THREAD_SIZE - STACKFRAME_SZ), %g2
+		set	(THREAD_SIZE - STACKFRAME_SZ - TRACEREG_SZ), %g2
 		add	%g1, %g2, %sp
 		mov	0, %fp			/* And for good luck */
 
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index a02363735915..97549e01f540 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -218,14 +218,7 @@ void flush_thread(void)
 	}
 
 	/* This task is no longer a kernel thread. */
-	if (current->thread.flags & SPARC_FLAG_KTHREAD) {
-		current->thread.flags &= ~SPARC_FLAG_KTHREAD;
-
-		/* We must fixup kregs as well. */
-		/* XXX This was not fixed for ti for a while, worked. Unused? */
-		current->thread.kregs = (struct pt_regs *)
-		    (task_stack_page(current) + (THREAD_SIZE - TRACEREG_SZ));
-	}
+	current->thread.flags &= ~SPARC_FLAG_KTHREAD;
 }
 
 static inline struct sparc_stackf __user *
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index eea43a1aef1b..c8e0dd99f370 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -266,7 +266,6 @@ static __init void leon_patch(void)
 }
 
 struct tt_entry *sparc_ttable;
-static struct pt_regs fake_swapper_regs;
 
 /* Called from head_32.S - before we have setup anything
  * in the kernel. Be very careful with what you do here.
@@ -363,8 +362,6 @@ void __init setup_arch(char **cmdline_p)
 		(*(linux_dbvec->teach_debugger))();
 	}
 
-	init_task.thread.kregs = &fake_swapper_regs;
-
 	/* Run-time patch instructions to match the cpu model */
 	per_cpu_patch();
 

From 415ddc3b105616d6a4fec279ed7d87841cbfa3fb Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 20 Aug 2020 10:55:25 -0400
Subject: [PATCH 0010/1820] sparc32: take ->thread.flags out

it was used for two things - dealing with unusual ->kregs for kernel
threads and "emulate unaligned userland accesses for this thread";
the former is killed off by the previous commit, the latter never
had been set in the first place.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/sparc/include/asm/processor_32.h |  5 --
 arch/sparc/kernel/process_32.c        |  5 --
 arch/sparc/kernel/unaligned_32.c      | 96 +--------------------------
 3 files changed, 1 insertion(+), 105 deletions(-)

diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index d7b71d7bed1f..b6242f7771e9 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/arch/sparc/include/asm/processor_32.h
@@ -50,15 +50,10 @@ struct thread_struct {
 	unsigned long   fsr;
 	unsigned long   fpqdepth;
 	struct fpq	fpqueue[16];
-	unsigned long flags;
 	mm_segment_t current_ds;
 };
 
-#define SPARC_FLAG_KTHREAD      0x1    /* task is a kernel thread */
-#define SPARC_FLAG_UNALIGNED    0x2    /* is allowed to do unaligned accesses */
-
 #define INIT_THREAD  { \
-	.flags = SPARC_FLAG_KTHREAD, \
 	.current_ds = KERNEL_DS, \
 	.kregs = (struct pt_regs *)(init_stack+THREAD_SIZE)-1 \
 }
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 97549e01f540..f75caecff115 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -216,9 +216,6 @@ void flush_thread(void)
 		clear_thread_flag(TIF_USEDFPU);
 #endif
 	}
-
-	/* This task is no longer a kernel thread. */
-	current->thread.flags &= ~SPARC_FLAG_KTHREAD;
 }
 
 static inline struct sparc_stackf __user *
@@ -306,7 +303,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 		extern int nwindows;
 		unsigned long psr;
 		memset(new_stack, 0, STACKFRAME_SZ + TRACEREG_SZ);
-		p->thread.flags |= SPARC_FLAG_KTHREAD;
 		p->thread.current_ds = KERNEL_DS;
 		ti->kpc = (((unsigned long) ret_from_kernel_thread) - 0x8);
 		childregs->u_regs[UREG_G1] = sp; /* function */
@@ -318,7 +314,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	}
 	memcpy(new_stack, (char *)regs - STACKFRAME_SZ, STACKFRAME_SZ + TRACEREG_SZ);
 	childregs->u_regs[UREG_FP] = sp;
-	p->thread.flags &= ~SPARC_FLAG_KTHREAD;
 	p->thread.current_ds = USER_DS;
 	ti->kpc = (((unsigned long) ret_from_fork) - 0x8);
 	ti->kpsr = current->thread.fork_kpsr | PSR_PIL;
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index 83db94c0b431..82b60d09ea3c 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -274,103 +274,9 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 	}
 }
 
-static inline int ok_for_user(struct pt_regs *regs, unsigned int insn,
-			      enum direction dir)
-{
-	unsigned int reg;
-	int size = ((insn >> 19) & 3) == 3 ? 8 : 4;
-
-	if ((regs->pc | regs->npc) & 3)
-		return 0;
-
-	/* Must access_ok() in all the necessary places. */
-#define WINREG_ADDR(regnum) \
-	((void __user *)(((unsigned long *)regs->u_regs[UREG_FP])+(regnum)))
-
-	reg = (insn >> 25) & 0x1f;
-	if (reg >= 16) {
-		if (!access_ok(WINREG_ADDR(reg - 16), size))
-			return -EFAULT;
-	}
-	reg = (insn >> 14) & 0x1f;
-	if (reg >= 16) {
-		if (!access_ok(WINREG_ADDR(reg - 16), size))
-			return -EFAULT;
-	}
-	if (!(insn & 0x2000)) {
-		reg = (insn & 0x1f);
-		if (reg >= 16) {
-			if (!access_ok(WINREG_ADDR(reg - 16), size))
-				return -EFAULT;
-		}
-	}
-#undef WINREG_ADDR
-	return 0;
-}
-
-static void user_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
+asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 {
 	send_sig_fault(SIGBUS, BUS_ADRALN,
 		       (void __user *)safe_compute_effective_address(regs, insn),
 		       0, current);
 }
-
-asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
-{
-	enum direction dir;
-
-	if(!(current->thread.flags & SPARC_FLAG_UNALIGNED) ||
-	   (((insn >> 30) & 3) != 3))
-		goto kill_user;
-	dir = decode_direction(insn);
-	if(!ok_for_user(regs, insn, dir)) {
-		goto kill_user;
-	} else {
-		int err, size = decode_access_size(insn);
-		unsigned long addr;
-
-		if(floating_point_load_or_store_p(insn)) {
-			printk("User FPU load/store unaligned unsupported.\n");
-			goto kill_user;
-		}
-
-		addr = compute_effective_address(regs, insn);
-		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
-		switch(dir) {
-		case load:
-			err = do_int_load(fetch_reg_addr(((insn>>25)&0x1f),
-							 regs),
-					  size, (unsigned long *) addr,
-					  decode_signedness(insn));
-			break;
-
-		case store:
-			err = do_int_store(((insn>>25)&0x1f), size,
-					   (unsigned long *) addr, regs);
-			break;
-
-		case both:
-			/*
-			 * This was supported in 2.4. However, we question
-			 * the value of SWAP instruction across word boundaries.
-			 */
-			printk("Unaligned SWAP unsupported.\n");
-			err = -EFAULT;
-			break;
-
-		default:
-			unaligned_panic("Impossible user unaligned trap.");
-			goto out;
-		}
-		if (err)
-			goto kill_user;
-		else
-			advance(regs);
-		goto out;
-	}
-
-kill_user:
-	user_mna_trap_fault(regs, insn);
-out:
-	;
-}

From 7d200b283aa049fcda0d43dd6e03e9e783d2799c Mon Sep 17 00:00:00 2001
From: Jonathan Albrieux <jonathan.albrieux@gmail.com>
Date: Wed, 13 Jan 2021 16:18:07 +0100
Subject: [PATCH 0011/1820] iio:adc:qcom-spmi-vadc: add default scale to
 LR_MUX2_BAT_ID channel

Checking at both msm8909-pm8916.dtsi and msm8916.dtsi from downstream
it is indicated that "batt_id" channel has to be scaled with the default
function:

	chan@31 {
		label = "batt_id";
		reg = <0x31>;
		qcom,decimation = <0>;
		qcom,pre-div-channel-scaling = <0>;
		qcom,calibration-type = "ratiometric";
		qcom,scale-function = <0>;
		qcom,hw-settle-time = <0xb>;
		qcom,fast-avg-setup = <0>;
	};

Change LR_MUX2_BAT_ID scaling accordingly.

Signed-off-by: Jonathan Albrieux <jonathan.albrieux@gmail.com>
Acked-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Fixes: 7c271eea7b8a ("iio: adc: spmi-vadc: Changes to support different scaling")
Link: https://lore.kernel.org/r/20210113151808.4628-2-jonathan.albrieux@gmail.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/qcom-spmi-vadc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/qcom-spmi-vadc.c b/drivers/iio/adc/qcom-spmi-vadc.c
index b0388f8a69f4..7e7d408452ec 100644
--- a/drivers/iio/adc/qcom-spmi-vadc.c
+++ b/drivers/iio/adc/qcom-spmi-vadc.c
@@ -598,7 +598,7 @@ static const struct vadc_channels vadc_chans[] = {
 	VADC_CHAN_NO_SCALE(P_MUX16_1_3, 1)
 
 	VADC_CHAN_NO_SCALE(LR_MUX1_BAT_THERM, 0)
-	VADC_CHAN_NO_SCALE(LR_MUX2_BAT_ID, 0)
+	VADC_CHAN_VOLT(LR_MUX2_BAT_ID, 0, SCALE_DEFAULT)
 	VADC_CHAN_NO_SCALE(LR_MUX3_XO_THERM, 0)
 	VADC_CHAN_NO_SCALE(LR_MUX4_AMUX_THM1, 0)
 	VADC_CHAN_NO_SCALE(LR_MUX5_AMUX_THM2, 0)

From d68c592e02f6f49a88e705f13dfc1883432cf300 Mon Sep 17 00:00:00 2001
From: Ye Xiang <xiang.ye@intel.com>
Date: Sat, 30 Jan 2021 18:25:30 +0800
Subject: [PATCH 0012/1820] iio: hid-sensor-prox: Fix scale not correct issue

Currently, the proxy sensor scale is zero because it just return the
exponent directly. To fix this issue, this patch use
hid_sensor_format_scale to process the scale first then return the
output.

Fixes: 39a3a0138f61 ("iio: hid-sensors: Added Proximity Sensor Driver")
Signed-off-by: Ye Xiang <xiang.ye@intel.com>
Link: https://lore.kernel.org/r/20210130102530.31064-1-xiang.ye@intel.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/hid-sensor-prox.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index 330cf359e0b8..e9e00ce0c6d4 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -23,6 +23,9 @@ struct prox_state {
 	struct hid_sensor_common common_attributes;
 	struct hid_sensor_hub_attribute_info prox_attr;
 	u32 human_presence;
+	int scale_pre_decml;
+	int scale_post_decml;
+	int scale_precision;
 };
 
 /* Channel definitions */
@@ -93,8 +96,9 @@ static int prox_read_raw(struct iio_dev *indio_dev,
 		ret_type = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SCALE:
-		*val = prox_state->prox_attr.units;
-		ret_type = IIO_VAL_INT;
+		*val = prox_state->scale_pre_decml;
+		*val2 = prox_state->scale_post_decml;
+		ret_type = prox_state->scale_precision;
 		break;
 	case IIO_CHAN_INFO_OFFSET:
 		*val = hid_sensor_convert_exponent(
@@ -234,6 +238,11 @@ static int prox_parse_report(struct platform_device *pdev,
 			HID_USAGE_SENSOR_HUMAN_PRESENCE,
 			&st->common_attributes.sensitivity);
 
+	st->scale_precision = hid_sensor_format_scale(
+				hsdev->usage,
+				&st->prox_attr,
+				&st->scale_pre_decml, &st->scale_post_decml);
+
 	return ret;
 }
 

From 7d7275b3e866cf8092bd12553ec53ba26864f7bb Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 28 Jan 2021 21:15:48 +0200
Subject: [PATCH 0013/1820] bus: omap_l3_noc: mark l3 irqs as IRQF_NO_THREAD

The main purpose of l3 IRQs is to catch OCP bus access errors and identify
corresponding code places by showing call stack, so it's important to
handle L3 interconnect errors as fast as possible. On RT these IRQs will
became threaded and will be scheduled much more late from the moment actual
error occurred so showing completely useless information.

Hence, mark l3 IRQs as IRQF_NO_THREAD so they will not be forced threaded
on RT or if force_irqthreads = true.

Fixes: 0ee7261c9212 ("drivers: bus: Move the OMAP interconnect driver to drivers/bus/")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 drivers/bus/omap_l3_noc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/bus/omap_l3_noc.c b/drivers/bus/omap_l3_noc.c
index b040447575ad..dcfb32ee5cb6 100644
--- a/drivers/bus/omap_l3_noc.c
+++ b/drivers/bus/omap_l3_noc.c
@@ -285,7 +285,7 @@ static int omap_l3_probe(struct platform_device *pdev)
 	 */
 	l3->debug_irq = platform_get_irq(pdev, 0);
 	ret = devm_request_irq(l3->dev, l3->debug_irq, l3_interrupt_handler,
-			       0x0, "l3-dbg-irq", l3);
+			       IRQF_NO_THREAD, "l3-dbg-irq", l3);
 	if (ret) {
 		dev_err(l3->dev, "request_irq failed for %d\n",
 			l3->debug_irq);
@@ -294,7 +294,7 @@ static int omap_l3_probe(struct platform_device *pdev)
 
 	l3->app_irq = platform_get_irq(pdev, 1);
 	ret = devm_request_irq(l3->dev, l3->app_irq, l3_interrupt_handler,
-			       0x0, "l3-app-irq", l3);
+			       IRQF_NO_THREAD, "l3-app-irq", l3);
 	if (ret)
 		dev_err(l3->dev, "request_irq failed for %d\n", l3->app_irq);
 

From 9bbce32a20d6a72c767a7f85fd6127babd1410ac Mon Sep 17 00:00:00 2001
From: Mans Rullgard <mans@mansr.com>
Date: Thu, 28 Jan 2021 15:56:44 +0000
Subject: [PATCH 0014/1820] ARM: dts: am33xx: add aliases for mmc interfaces

Without DT aliases, the numbering of mmc interfaces is unpredictable.
Adding them makes it possible to refer to devices consistently.  The
popular suggestion to use UUIDs obviously doesn't work with a blank
device fresh from the factory.

See commit fa2d0aa96941 ("mmc: core: Allow setting slot index via
device tree alias") for more discussion.

Signed-off-by: Mans Rullgard <mans@mansr.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/boot/dts/am33xx.dtsi | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 5b213a1e68bb..5e33d0e88f5b 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -40,6 +40,9 @@
 		ethernet1 = &cpsw_emac1;
 		spi0 = &spi0;
 		spi1 = &spi1;
+		mmc0 = &mmc1;
+		mmc1 = &mmc2;
+		mmc2 = &mmc3;
 	};
 
 	cpus {

From b22ac48b0a4d74415beef10e49e434e8f228a2bf Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Mon, 8 Feb 2021 08:16:19 +0100
Subject: [PATCH 0015/1820] MAINTAINERS: rectify BROADCOM PMB (POWER MANAGEMENT
 BUS) DRIVER
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 8bcac4011ebe ("soc: bcm: add PM driver for Broadcom's PMB") includes
a new MAINTAINERS section BROADCOM PMB (POWER MANAGEMENT BUS) DRIVER with
'drivers/soc/bcm/bcm-pmb.c', but the file was actually added at
'drivers/soc/bcm/bcm63xx/bcm-pmb.c'.

Hence, ./scripts/get_maintainer.pl --self-test=patterns complains:

  warning: no file matches  F:    drivers/soc/bcm/bcm-pmb.c

Point the file entry to the right location.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Acked-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3bbb974bd11e..db4368285674 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3690,7 +3690,7 @@ M:	bcm-kernel-feedback-list@broadcom.com
 L:	linux-pm@vger.kernel.org
 S:	Maintained
 T:	git git://github.com/broadcom/stblinux.git
-F:	drivers/soc/bcm/bcm-pmb.c
+F:	drivers/soc/bcm/bcm63xx/bcm-pmb.c
 F:	include/dt-bindings/soc/bcm-pmb.h
 
 BROADCOM SPECIFIC AMBA DRIVER (BCMA)

From f890987fac8153227258121740a9609668c427f3 Mon Sep 17 00:00:00 2001
From: Wilfried Wessner <wilfried.wessner@gmail.com>
Date: Mon, 8 Feb 2021 15:27:05 +0100
Subject: [PATCH 0016/1820] iio: adc: ad7949: fix wrong ADC result due to
 incorrect bit mask

Fixes a wrong bit mask used for the ADC's result, which was caused by an
improper usage of the GENMASK() macro. The bits higher than ADC's
resolution are undefined and if not masked out correctly, a wrong result
can be given. The GENMASK() macro indexing is zero based, so the mask has
to go from [resolution - 1 , 0].

Fixes: 7f40e0614317f ("iio:adc:ad7949: Add AD7949 ADC driver family")
Signed-off-by: Wilfried Wessner <wilfried.wessner@gmail.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Charles-Antoine Couret <charles-antoine.couret@essensium.com>
Cc: <Stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210208142705.GA51260@ubuntu
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7949.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ad7949.c b/drivers/iio/adc/ad7949.c
index 5d597e5050f6..1b4b3203e428 100644
--- a/drivers/iio/adc/ad7949.c
+++ b/drivers/iio/adc/ad7949.c
@@ -91,7 +91,7 @@ static int ad7949_spi_read_channel(struct ad7949_adc_chip *ad7949_adc, int *val,
 	int ret;
 	int i;
 	int bits_per_word = ad7949_adc->resolution;
-	int mask = GENMASK(ad7949_adc->resolution, 0);
+	int mask = GENMASK(ad7949_adc->resolution - 1, 0);
 	struct spi_message msg;
 	struct spi_transfer tx[] = {
 		{

From be24c65e9fa2486bb8ec98d9f592bdcf04bedd88 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Wed, 10 Feb 2021 12:50:44 +0200
Subject: [PATCH 0017/1820] iio: adc: adi-axi-adc: add proper Kconfig
 dependencies

The ADI AXI ADC driver requires IO mem access and OF to work. This change
adds these dependencies to the Kconfig symbol of the driver.

This was also found via the lkp bot, as the
devm_platform_ioremap_resource() symbol was not found at link-time on the
S390 architecture.

Fixes: ef04070692a21 ("iio: adc: adi-axi-adc: add support for AXI ADC IP core")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Cc: <Stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210210105044.48914-1-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 15587a1bc80d..8d0be5b3029a 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -266,6 +266,8 @@ config ADI_AXI_ADC
 	select IIO_BUFFER
 	select IIO_BUFFER_HW_CONSUMER
 	select IIO_BUFFER_DMAENGINE
+	depends on HAS_IOMEM
+	depends on OF
 	help
 	  Say yes here to build support for Analog Devices Generic
 	  AXI ADC IP core. The IP core is used for interfacing with

From a249ca66d15fa4b54dc6deaff4155df3db1308e1 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Wed, 10 Feb 2021 10:37:51 +0200
Subject: [PATCH 0018/1820] soc: ti: omap-prm: Fix reboot issue with invalid
 pcie reset map for dra7

Yongqin Liu <yongqin.liu@linaro.org> reported an issue where reboot hangs
on beagleboard-x15. This started happening after commit 7078a5ba7a58
("soc: ti: omap-prm: Fix boot time errors for rst_map_012 bits 0 and 1").

We now assert any 012 type resets on init to prevent unconfigured
accelerator MMUs getting enabled on init depending on the bootloader or
kexec configured state.

Turns out that we now also wrongly assert dra7 l3init domain PCIe reset
bits causing a hang during reboot. Let's fix the l3init reset bits to
use a 01 map instead of 012 map. There are only two rstctrl bits and not
three. This is documented in TRM "Table 3-1647. RM_PCIESS_RSTCTRL".

Fixes: 5a68c87afde0 ("soc: ti: omap-prm: dra7: add genpd support for remaining PRM instances")
Fixes: 7078a5ba7a58 ("soc: ti: omap-prm: Fix boot time errors for rst_map_012 bits 0 and 1")
Cc: Kishon Vijay Abraham I <kishon@ti.com>
Reported-by: Yongqin Liu <yongqin.liu@linaro.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 drivers/soc/ti/omap_prm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/soc/ti/omap_prm.c b/drivers/soc/ti/omap_prm.c
index bf1468e5bccb..17ea6a74a988 100644
--- a/drivers/soc/ti/omap_prm.c
+++ b/drivers/soc/ti/omap_prm.c
@@ -332,7 +332,7 @@ static const struct omap_prm_data dra7_prm_data[] = {
 	{
 		.name = "l3init", .base = 0x4ae07300,
 		.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
-		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012,
+		.rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01,
 		.clkdm_name = "pcie"
 	},
 	{

From fbfa463be8dc7957ee4f81556e9e1ea2a951807d Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Wed, 10 Feb 2021 10:53:48 +0200
Subject: [PATCH 0019/1820] ARM: OMAP2+: Fix smartreflex init regression after
 dropping legacy data

When I dropped legacy data for omap4 and dra7 smartreflex in favor of
device tree based data, it seems I only testd for the "SmartReflex Class3
initialized" line in dmesg. I missed the fact that there is also
omap_devinit_smartreflex() that happens later, and now it produces an
error on boot for "No Voltage table for the corresponding vdd. Cannot
create debugfs entries for n-values".

This happens as we no longer have the smartreflex instance legacy data,
and have not yet moved completely to device tree based booting for the
driver. Let's fix the issue by changing the smartreflex init to use names.
This should all eventually go away in favor of doing the init in the
driver based on devicetree compatible value.

Note that dra7xx_init_early() is not calling any voltage domain init like
omap54xx_voltagedomains_init(), or a dra7 specific voltagedomains init.
This means that on dra7 smartreflex is still not fully initialized, and
also seems to be missing the related devicetree nodes.

Fixes: a6b1e717e942 ("ARM: OMAP2+: Drop legacy platform data for omap4 smartreflex")
Fixes: e54740b4afe8 ("ARM: OMAP2+: Drop legacy platform data for dra7 smartreflex")
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/sr_device.c | 75 +++++++++++++++++++++++++--------
 1 file changed, 58 insertions(+), 17 deletions(-)

diff --git a/arch/arm/mach-omap2/sr_device.c b/arch/arm/mach-omap2/sr_device.c
index 62df666c2bd0..17b66f0d0dee 100644
--- a/arch/arm/mach-omap2/sr_device.c
+++ b/arch/arm/mach-omap2/sr_device.c
@@ -88,34 +88,26 @@ static void __init sr_set_nvalues(struct omap_volt_data *volt_data,
 
 extern struct omap_sr_data omap_sr_pdata[];
 
-static int __init sr_dev_init(struct omap_hwmod *oh, void *user)
+static int __init sr_init_by_name(const char *name, const char *voltdm)
 {
 	struct omap_sr_data *sr_data = NULL;
 	struct omap_volt_data *volt_data;
-	struct omap_smartreflex_dev_attr *sr_dev_attr;
 	static int i;
 
-	if (!strncmp(oh->name, "smartreflex_mpu_iva", 20) ||
-	    !strncmp(oh->name, "smartreflex_mpu", 16))
+	if (!strncmp(name, "smartreflex_mpu_iva", 20) ||
+	    !strncmp(name, "smartreflex_mpu", 16))
 		sr_data = &omap_sr_pdata[OMAP_SR_MPU];
-	else if (!strncmp(oh->name, "smartreflex_core", 17))
+	else if (!strncmp(name, "smartreflex_core", 17))
 		sr_data = &omap_sr_pdata[OMAP_SR_CORE];
-	else if (!strncmp(oh->name, "smartreflex_iva", 16))
+	else if (!strncmp(name, "smartreflex_iva", 16))
 		sr_data = &omap_sr_pdata[OMAP_SR_IVA];
 
 	if (!sr_data) {
-		pr_err("%s: Unknown instance %s\n", __func__, oh->name);
+		pr_err("%s: Unknown instance %s\n", __func__, name);
 		return -EINVAL;
 	}
 
-	sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr;
-	if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) {
-		pr_err("%s: No voltage domain specified for %s. Cannot initialize\n",
-		       __func__, oh->name);
-		goto exit;
-	}
-
-	sr_data->name = oh->name;
+	sr_data->name = name;
 	if (cpu_is_omap343x())
 		sr_data->ip_type = 1;
 	else
@@ -136,10 +128,10 @@ static int __init sr_dev_init(struct omap_hwmod *oh, void *user)
 		}
 	}
 
-	sr_data->voltdm = voltdm_lookup(sr_dev_attr->sensor_voltdm_name);
+	sr_data->voltdm = voltdm_lookup(voltdm);
 	if (!sr_data->voltdm) {
 		pr_err("%s: Unable to get voltage domain pointer for VDD %s\n",
-			__func__, sr_dev_attr->sensor_voltdm_name);
+			__func__, voltdm);
 		goto exit;
 	}
 
@@ -160,6 +152,20 @@ exit:
 	return 0;
 }
 
+static int __init sr_dev_init(struct omap_hwmod *oh, void *user)
+{
+	struct omap_smartreflex_dev_attr *sr_dev_attr;
+
+	sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr;
+	if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) {
+		pr_err("%s: No voltage domain specified for %s. Cannot initialize\n",
+		       __func__, oh->name);
+		return 0;
+	}
+
+	return sr_init_by_name(oh->name, sr_dev_attr->sensor_voltdm_name);
+}
+
 /*
  * API to be called from board files to enable smartreflex
  * autocompensation at init.
@@ -169,7 +175,42 @@ void __init omap_enable_smartreflex_on_init(void)
 	sr_enable_on_init = true;
 }
 
+static const char * const omap4_sr_instances[] = {
+	"mpu",
+	"iva",
+	"core",
+};
+
+static const char * const dra7_sr_instances[] = {
+	"mpu",
+	"core",
+};
+
 int __init omap_devinit_smartreflex(void)
 {
+	const char * const *sr_inst;
+	int i, nr_sr = 0;
+
+	if (soc_is_omap44xx()) {
+		sr_inst = omap4_sr_instances;
+		nr_sr = ARRAY_SIZE(omap4_sr_instances);
+
+	} else if (soc_is_dra7xx()) {
+		sr_inst = dra7_sr_instances;
+		nr_sr = ARRAY_SIZE(dra7_sr_instances);
+	}
+
+	if (nr_sr) {
+		const char *name, *voltdm;
+
+		for (i = 0; i < nr_sr; i++) {
+			name = kasprintf(GFP_KERNEL, "smartreflex_%s", sr_inst[i]);
+			voltdm = sr_inst[i];
+			sr_init_by_name(name, voltdm);
+		}
+
+		return 0;
+	}
+
 	return omap_hwmod_for_each_by_class("smartreflex", sr_dev_init, NULL);
 }

From 443f0bb8e29fa031ec4d5beb3c3143350438dc97 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 12 Feb 2021 11:07:31 -0800
Subject: [PATCH 0020/1820] Revert "ARM: dts: bcm2711: Add the BSC interrupt
 controller"

As Dave reported:

This seems to have unintended side effects.  GIC interrupt 117 is shared
between the standard I2C controllers (i2c-bcm2835) and the l2-intc block
handling the HDMI I2C interrupts.

There is not a great way to share an interrupt between an interrupt
controller using the chained IRQ handler which is an interrupt flow and
another driver like i2c-bcm2835 which uses an interrupt handler
(although it specifies IRQF_SHARED).

Simply revert this change for now which will mean that HDMI I2C will be
polled, like it was before.

Reported-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Acked-by: Maxime Ripard <mripard@kernel.org>
Acked-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 arch/arm/boot/dts/bcm2711.dtsi | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi
index 462b1dfb0385..720beec54d61 100644
--- a/arch/arm/boot/dts/bcm2711.dtsi
+++ b/arch/arm/boot/dts/bcm2711.dtsi
@@ -308,14 +308,6 @@
 			#reset-cells = <1>;
 		};
 
-		bsc_intr: interrupt-controller@7ef00040 {
-			compatible = "brcm,bcm2711-l2-intc", "brcm,l2-intc";
-			reg = <0x7ef00040 0x30>;
-			interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-controller;
-			#interrupt-cells = <1>;
-		};
-
 		aon_intr: interrupt-controller@7ef00100 {
 			compatible = "brcm,bcm2711-l2-intc", "brcm,l2-intc";
 			reg = <0x7ef00100 0x30>;
@@ -362,8 +354,6 @@
 			reg = <0x7ef04500 0x100>, <0x7ef00b00 0x300>;
 			reg-names = "bsc", "auto-i2c";
 			clock-frequency = <97500>;
-			interrupt-parent = <&bsc_intr>;
-			interrupts = <0>;
 			status = "disabled";
 		};
 
@@ -405,8 +395,6 @@
 			reg = <0x7ef09500 0x100>, <0x7ef05b00 0x300>;
 			reg-names = "bsc", "auto-i2c";
 			clock-frequency = <97500>;
-			interrupt-parent = <&bsc_intr>;
-			interrupts = <1>;
 			status = "disabled";
 		};
 	};

From 3b9ea7206d7e1fdd7419cbd10badd3b2c80d04b4 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Sun, 14 Feb 2021 19:49:11 +0100
Subject: [PATCH 0021/1820] ath9k: fix transmitting to stations in dynamic SMPS
 mode

When transmitting to a receiver in dynamic SMPS mode, all transmissions that
use multiple spatial streams need to be sent using CTS-to-self or RTS/CTS to
give the receiver's extra chains some time to wake up.
This fixes the tx rate getting stuck at <= MCS7 for some clients, especially
Intel ones, which make aggressive use of SMPS.

Cc: stable@vger.kernel.org
Reported-by: Martin Kennedy <hurricos@gmail.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210214184911.96702-1-nbd@nbd.name
---
 drivers/net/wireless/ath/ath9k/ath9k.h | 3 ++-
 drivers/net/wireless/ath/ath9k/xmit.c  | 6 ++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index 13b4f5f50f8a..ef6f5ea06c1f 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -177,7 +177,8 @@ struct ath_frame_info {
 	s8 txq;
 	u8 keyix;
 	u8 rtscts_rate;
-	u8 retries : 7;
+	u8 retries : 6;
+	u8 dyn_smps : 1;
 	u8 baw_tracked : 1;
 	u8 tx_power;
 	enum ath9k_key_type keytype:2;
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index e60d4737fc6e..5691bd6eb82c 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1271,6 +1271,11 @@ static void ath_buf_set_rate(struct ath_softc *sc, struct ath_buf *bf,
 				 is_40, is_sgi, is_sp);
 			if (rix < 8 && (tx_info->flags & IEEE80211_TX_CTL_STBC))
 				info->rates[i].RateFlags |= ATH9K_RATESERIES_STBC;
+			if (rix >= 8 && fi->dyn_smps) {
+				info->rates[i].RateFlags |=
+					ATH9K_RATESERIES_RTS_CTS;
+				info->flags |= ATH9K_TXDESC_CTSENA;
+			}
 
 			info->txpower[i] = ath_get_rate_txpower(sc, bf, rix,
 								is_40, false);
@@ -2114,6 +2119,7 @@ static void setup_frame_info(struct ieee80211_hw *hw,
 		fi->keyix = an->ps_key;
 	else
 		fi->keyix = ATH9K_TXKEYIX_INVALID;
+	fi->dyn_smps = sta && sta->smps_mode == IEEE80211_SMPS_DYNAMIC;
 	fi->keytype = keytype;
 	fi->framelen = framelen;
 	fi->tx_power = txpower;

From ae064fc0e32a4d28389086d9f4b260a0c157cfee Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 16 Feb 2021 14:51:18 +0100
Subject: [PATCH 0022/1820] mt76: fix tx skb error handling in
 mt76_dma_tx_queue_skb

When running out of room in the tx queue after calling drv->tx_prepare_skb,
the buffer list will already have been modified on MT7615 and newer drivers.
This can leak a DMA mapping and will show up as swiotlb allocation failures
on x86.

Fix this by moving the queue length check further up. This is less accurate,
since it can overestimate the needed room in the queue on MT7615 and newer,
but the difference is small enough to not matter in practice.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210216135119.23809-1-nbd@nbd.name
---
 drivers/net/wireless/mediatek/mt76/dma.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 19098b852d0a..abdc8d364361 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -345,7 +345,6 @@ mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
 	};
 	struct ieee80211_hw *hw;
 	int len, n = 0, ret = -ENOMEM;
-	struct mt76_queue_entry e;
 	struct mt76_txwi_cache *t;
 	struct sk_buff *iter;
 	dma_addr_t addr;
@@ -387,6 +386,11 @@ mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
 	}
 	tx_info.nbuf = n;
 
+	if (q->queued + (tx_info.nbuf + 1) / 2 >= q->ndesc - 1) {
+		ret = -ENOMEM;
+		goto unmap;
+	}
+
 	dma_sync_single_for_cpu(dev->dev, t->dma_addr, dev->drv->txwi_size,
 				DMA_TO_DEVICE);
 	ret = dev->drv->tx_prepare_skb(dev, txwi, q->qid, wcid, sta, &tx_info);
@@ -395,11 +399,6 @@ mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
 	if (ret < 0)
 		goto unmap;
 
-	if (q->queued + (tx_info.nbuf + 1) / 2 >= q->ndesc - 1) {
-		ret = -ENOMEM;
-		goto unmap;
-	}
-
 	return mt76_dma_add_buf(dev, q, tx_info.buf, tx_info.nbuf,
 				tx_info.info, tx_info.skb, t);
 
@@ -419,9 +418,7 @@ free:
 	}
 #endif
 
-	e.skb = tx_info.skb;
-	e.txwi = t;
-	dev->drv->tx_complete_skb(dev, &e);
+	dev_kfree_skb(tx_info.skb);
 	mt76_put_txwi(dev, t);
 	return ret;
 }

From 94f0e6256c2ab6803c935634aa1f653174c94879 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 16 Feb 2021 14:51:19 +0100
Subject: [PATCH 0023/1820] mt76: mt7915: only modify tx buffer list after
 allocating tx token id

Modifying the tx buffer list too early can leak DMA mappings

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210216135119.23809-2-nbd@nbd.name
---
 drivers/net/wireless/mediatek/mt76/mt7915/mac.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index eb889f8d6fea..e5a258958ac9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -967,11 +967,6 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	}
 	txp->nbuf = nbuf;
 
-	/* pass partial skb header to fw */
-	tx_info->buf[1].len = MT_CT_PARSE_LEN;
-	tx_info->buf[1].skip_unmap = true;
-	tx_info->nbuf = MT_CT_DMA_BUF_NUM;
-
 	txp->flags = cpu_to_le16(MT_CT_INFO_APPLY_TXD | MT_CT_INFO_FROM_HOST);
 
 	if (!key)
@@ -1009,6 +1004,11 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 		txp->rept_wds_wcid = cpu_to_le16(0x3ff);
 	tx_info->skb = DMA_DUMMY_DATA;
 
+	/* pass partial skb header to fw */
+	tx_info->buf[1].len = MT_CT_PARSE_LEN;
+	tx_info->buf[1].skip_unmap = true;
+	tx_info->nbuf = MT_CT_DMA_BUF_NUM;
+
 	return 0;
 }
 

From a7b5d7c4969aba8d1f04c29048906abaa71fb6a9 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Thu, 18 Feb 2021 13:06:57 +0200
Subject: [PATCH 0024/1820] bus: ti-sysc: Fix warning on unbind if reset is not
 deasserted

We currently get thefollowing on driver unbind if a reset is configured
and asserted:

WARNING: CPU: 0 PID: 993 at drivers/reset/core.c:432 reset_control_assert
...
(reset_control_assert) from [<c0fecda8>] (sysc_remove+0x190/0x1e4)
(sysc_remove) from [<c0a2bb58>] (platform_remove+0x24/0x3c)
(platform_remove) from [<c0a292fc>] (__device_release_driver+0x154/0x214)
(__device_release_driver) from [<c0a2a210>] (device_driver_detach+0x3c/0x8c)
(device_driver_detach) from [<c0a27d64>] (unbind_store+0x60/0xd4)
(unbind_store) from [<c0546bec>] (kernfs_fop_write_iter+0x10c/0x1cc)

Let's fix it by checking the reset status.

Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 drivers/bus/ti-sysc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index a27d751cf219..3d74f237f005 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -3053,7 +3053,9 @@ static int sysc_remove(struct platform_device *pdev)
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	reset_control_assert(ddata->rsts);
+
+	if (!reset_control_status(ddata->rsts))
+		reset_control_assert(ddata->rsts);
 
 unprepare:
 	sysc_unprepare(ddata);

From effe89e40037038db7711bdab5d3401fe297d72c Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Thu, 18 Feb 2021 13:46:33 +0200
Subject: [PATCH 0025/1820] soc: ti: omap-prm: Fix occasional abort on reset
 deassert for dra7 iva

On reset deassert, we must wait a bit after the rstst bit change before
we allow clockdomain autoidle again. Otherwise we get the following oops
sometimes on dra7 with iva:

Unhandled fault: imprecise external abort (0x1406) at 0x00000000
44000000.ocp:L3 Standard Error: MASTER MPU TARGET IVA_CONFIG (Read Link):
At Address: 0x0005A410 : Data Access in User mode during Functional access
Internal error: : 1406 [#1] SMP ARM
...
(sysc_write_sysconfig) from [<c0782cb0>] (sysc_enable_module+0xcc/0x260)
(sysc_enable_module) from [<c0782f0c>] (sysc_runtime_resume+0xc8/0x174)
(sysc_runtime_resume) from [<c0a3e1ac>] (genpd_runtime_resume+0x94/0x224)
(genpd_runtime_resume) from [<c0a33f0c>] (__rpm_callback+0xd8/0x180)

It is unclear what all devices this might affect, but presumably other
devices with the rstst bit too can be affected. So let's just enable the
delay for all the devices with rstst bit for now. Later on we may want to
limit the list to the know affected devices if needed.

Fixes: d30cd83f6853 ("soc: ti: omap-prm: add support for denying idle for reset clockdomain")
Reported-by: Yongqin Liu <yongqin.liu@linaro.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 drivers/soc/ti/omap_prm.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/soc/ti/omap_prm.c b/drivers/soc/ti/omap_prm.c
index 17ea6a74a988..51143a68a889 100644
--- a/drivers/soc/ti/omap_prm.c
+++ b/drivers/soc/ti/omap_prm.c
@@ -830,8 +830,12 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev,
 		       reset->prm->data->name, id);
 
 exit:
-	if (reset->clkdm)
+	if (reset->clkdm) {
+		/* At least dra7 iva needs a delay before clkdm idle */
+		if (has_rstst)
+			udelay(1);
 		pdata->clkdm_allow_idle(reset->clkdm);
+	}
 
 	return ret;
 }

From a71266e454b5df10d019b06f5ebacd579f76be28 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 16 Feb 2021 22:42:13 +0300
Subject: [PATCH 0026/1820] iio: adis16400: Fix an error code in
 adis16400_initial_setup()

This is to silence a new Smatch warning:

    drivers/iio/imu/adis16400.c:492 adis16400_initial_setup()
    warn: sscanf doesn't return error codes

If the condition "if (st->variant->flags & ADIS16400_HAS_SLOW_MODE) {"
is false then we return 1 instead of returning 0 and probe will fail.

Fixes: 72a868b38bdd ("iio: imu: check sscanf return value")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: <Stable@vger.kernel.org>
Link: https://lore.kernel.org/r/YCwgFb3JVG6qrlQ+@mwanda
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/adis16400.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/iio/imu/adis16400.c b/drivers/iio/imu/adis16400.c
index 54af2ed664f6..785a4ce606d8 100644
--- a/drivers/iio/imu/adis16400.c
+++ b/drivers/iio/imu/adis16400.c
@@ -462,8 +462,7 @@ static int adis16400_initial_setup(struct iio_dev *indio_dev)
 		if (ret)
 			goto err_ret;
 
-		ret = sscanf(indio_dev->name, "adis%u\n", &device_id);
-		if (ret != 1) {
+		if (sscanf(indio_dev->name, "adis%u\n", &device_id) != 1) {
 			ret = -EINVAL;
 			goto err_ret;
 		}

From 121875b28e3bd7519a675bf8ea2c2e793452c2bd Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Sun, 24 Jan 2021 19:50:34 +0000
Subject: [PATCH 0027/1820] iio:adc:stm32-adc: Add HAS_IOMEM dependency

Seems that there are config combinations in which this driver gets enabled
and hence selects the MFD, but with out HAS_IOMEM getting pulled in
via some other route.  MFD is entirely contained in an
if HAS_IOMEM block, leading to the build issue in this bugzilla.

https://bugzilla.kernel.org/show_bug.cgi?id=209889

Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20210124195034.22576-1-jic23@kernel.org
---
 drivers/iio/adc/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 8d0be5b3029a..be1f73166a32 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -925,6 +925,7 @@ config STM32_ADC_CORE
 	depends on ARCH_STM32 || COMPILE_TEST
 	depends on OF
 	depends on REGULATOR
+	depends on HAS_IOMEM
 	select IIO_BUFFER
 	select MFD_STM32_TIMERS
 	select IIO_STM32_TIMER_TRIGGER

From 4f5434086d9223f20b3128a7dc78b35271e76655 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 24 Dec 2020 02:17:00 +0100
Subject: [PATCH 0028/1820] iio: adc: ab8500-gpadc: Fix off by 10 to 3

Fix an off by three orders of magnitude error in the AB8500
GPADC driver. Luckily it showed up quite quickly when trying
to make use of it. The processed reads were returning
microvolts, microamperes and microcelsius instead of millivolts,
milliamperes and millicelsius as advertised.

Cc: stable@vger.kernel.org
Fixes: 07063bbfa98e ("iio: adc: New driver for the AB8500 GPADC")
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20201224011700.1059659-1-linus.walleij@linaro.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ab8500-gpadc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ab8500-gpadc.c b/drivers/iio/adc/ab8500-gpadc.c
index 1bb987a4acba..8d81505282dd 100644
--- a/drivers/iio/adc/ab8500-gpadc.c
+++ b/drivers/iio/adc/ab8500-gpadc.c
@@ -918,7 +918,7 @@ static int ab8500_gpadc_read_raw(struct iio_dev *indio_dev,
 			return processed;
 
 		/* Return millivolt or milliamps or millicentigrades */
-		*val = processed * 1000;
+		*val = processed;
 		return IIO_VAL_INT;
 	}
 

From 4538c5ed0f7e892f1b643472e48146757d1e60c5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 19 Feb 2021 13:35:07 +0100
Subject: [PATCH 0029/1820] iwlwifi: avoid crash on unsupported debug
 collection

If the opmode doesn't support debug collection (DVM) then don't
crash, but just skip the callback.

Fixes: d01293154c0a ("iwlwifi: dbg: add op_mode callback for collecting debug data.")
Reported-by: Andy Lavr <andy.lavr@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210219133506.ecabe285bc7d.I73d230d555c595fa2d9bf284f80078729fe18aa4@changeid
---
 drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
index 868da7e79a45..e6d2e0994317 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
@@ -205,6 +205,8 @@ static inline void iwl_op_mode_time_point(struct iwl_op_mode *op_mode,
 					  enum iwl_fw_ini_time_point tp_id,
 					  union iwl_dbg_tlv_tp_data *tp_data)
 {
+	if (!op_mode || !op_mode->ops || !op_mode->ops->time_point)
+		return;
 	op_mode->ops->time_point(op_mode, tp_id, tp_data);
 }
 

From b29dd96b905f3dd543f4ca729447286adf934dd6 Mon Sep 17 00:00:00 2001
From: Brendan Jackman <jackmanb@google.com>
Date: Tue, 16 Feb 2021 12:53:07 +0000
Subject: [PATCH 0030/1820] bpf, x86: Fix BPF_FETCH atomic and/or/xor with r0
 as src

This code generates a CMPXCHG loop in order to implement atomic_fetch
bitwise operations. Because CMPXCHG is hard-coded to use rax (which
holds the BPF r0 value), it saves the _real_ r0 value into the
internal "ax" temporary register and restores it once the loop is
complete.

In the middle of the loop, the actual bitwise operation is performed
using src_reg. The bug occurs when src_reg is r0: as described above,
r0 has been clobbered and the real r0 value is in the ax register.

Therefore, perform this operation on the ax register instead, when
src_reg is r0.

Fixes: 981f94c3e921 ("bpf: Add bitwise atomic instructions")
Signed-off-by: Brendan Jackman <jackmanb@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: KP Singh <kpsingh@kernel.org>
Link: https://lore.kernel.org/bpf/20210216125307.1406237-1-jackmanb@google.com
---
 arch/x86/net/bpf_jit_comp.c                   | 10 +++++---
 .../selftests/bpf/verifier/atomic_and.c       | 23 +++++++++++++++++++
 2 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 79e7a0ec1da5..6926d0ca6c71 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1349,6 +1349,7 @@ st:			if (is_imm8(insn->off))
 			    insn->imm == (BPF_XOR | BPF_FETCH)) {
 				u8 *branch_target;
 				bool is64 = BPF_SIZE(insn->code) == BPF_DW;
+				u32 real_src_reg = src_reg;
 
 				/*
 				 * Can't be implemented with a single x86 insn.
@@ -1357,6 +1358,9 @@ st:			if (is_imm8(insn->off))
 
 				/* Will need RAX as a CMPXCHG operand so save R0 */
 				emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0);
+				if (src_reg == BPF_REG_0)
+					real_src_reg = BPF_REG_AX;
+
 				branch_target = prog;
 				/* Load old value */
 				emit_ldx(&prog, BPF_SIZE(insn->code),
@@ -1366,9 +1370,9 @@ st:			if (is_imm8(insn->off))
 				 * put the result in the AUX_REG.
 				 */
 				emit_mov_reg(&prog, is64, AUX_REG, BPF_REG_0);
-				maybe_emit_mod(&prog, AUX_REG, src_reg, is64);
+				maybe_emit_mod(&prog, AUX_REG, real_src_reg, is64);
 				EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)],
-				      add_2reg(0xC0, AUX_REG, src_reg));
+				      add_2reg(0xC0, AUX_REG, real_src_reg));
 				/* Attempt to swap in new value */
 				err = emit_atomic(&prog, BPF_CMPXCHG,
 						  dst_reg, AUX_REG, insn->off,
@@ -1381,7 +1385,7 @@ st:			if (is_imm8(insn->off))
 				 */
 				EMIT2(X86_JNE, -(prog - branch_target) - 2);
 				/* Return the pre-modification value */
-				emit_mov_reg(&prog, is64, src_reg, BPF_REG_0);
+				emit_mov_reg(&prog, is64, real_src_reg, BPF_REG_0);
 				/* Restore R0 after clobbering RAX */
 				emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX);
 				break;
diff --git a/tools/testing/selftests/bpf/verifier/atomic_and.c b/tools/testing/selftests/bpf/verifier/atomic_and.c
index 1bdc8e6684f7..fe4bb70eb9c5 100644
--- a/tools/testing/selftests/bpf/verifier/atomic_and.c
+++ b/tools/testing/selftests/bpf/verifier/atomic_and.c
@@ -75,3 +75,26 @@
 	},
 	.result = ACCEPT,
 },
+{
+	"BPF_ATOMIC_AND with fetch - r0 as source reg",
+	.insns = {
+		/* val = 0x110; */
+		BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0x110),
+		/* old = atomic_fetch_and(&val, 0x011); */
+		BPF_MOV64_IMM(BPF_REG_0, 0x011),
+		BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_10, BPF_REG_0, -8),
+		/* if (old != 0x110) exit(3); */
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0x110, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 3),
+		BPF_EXIT_INSN(),
+		/* if (val != 0x010) exit(2); */
+		BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -8),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x010, 2),
+		BPF_MOV64_IMM(BPF_REG_1, 2),
+		BPF_EXIT_INSN(),
+		/* exit(0); */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+},

From 33ccec5fd740d0d5b78b77846f76eb5b4feb4327 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 17 Feb 2021 10:45:25 +0300
Subject: [PATCH 0031/1820] bpf: Fix a warning message in
 mark_ptr_not_null_reg()

The WARN_ON() argument is a condition, not an error message.  So this
code will print a stack trace but will not print the warning message.
Fix that and also change it to only WARN_ONCE().

Fixes: 4ddb74165ae5 ("bpf: Extract nullable reg type conversion into a helper function")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/YCzJlV3hnF%2Ft1Pk4@mwanda
---
 kernel/bpf/verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1dda9d81f12c..3d34ba492d46 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1120,7 +1120,7 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
 		reg->type = PTR_TO_RDWR_BUF;
 		break;
 	default:
-		WARN_ON("unknown nullable register type");
+		WARN_ONCE(1, "unknown nullable register type");
 	}
 }
 

From 53f523f3052ac16bbc7718032aa6b848f971d28c Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Wed, 17 Feb 2021 16:16:47 -0800
Subject: [PATCH 0032/1820] bpf: Clear percpu pointers in bpf_prog_clone_free()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Similar to bpf_prog_realloc(), bpf_prog_clone_create() also copies
the percpu pointers, but the clone still shares them with the original
prog, so we have to clear these two percpu pointers in
bpf_prog_clone_free(). Otherwise we would get a double free:

 BUG: kernel NULL pointer dereference, address: 0000000000000000
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: 0000 [#1] SMP PTI
 CPU: 13 PID: 8140 Comm: kworker/13:247 Kdump: loaded Tainted: G                W    OE
  5.11.0-rc4.bm.1-amd64+ #1
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
 test_bpf: #1 TXA
 Workqueue: events bpf_prog_free_deferred
 RIP: 0010:percpu_ref_get_many.constprop.97+0x42/0xf0
 Code: [...]
 RSP: 0018:ffffa6bce1f9bda0 EFLAGS: 00010002
 RAX: 0000000000000001 RBX: 0000000000000000 RCX: 00000000021dfc7b
 RDX: ffffffffae2eeb90 RSI: 867f92637e338da5 RDI: 0000000000000046
 RBP: ffffa6bce1f9bda8 R08: 0000000000000000 R09: 0000000000000001
 R10: 0000000000000046 R11: 0000000000000000 R12: 0000000000000280
 R13: 0000000000000000 R14: 0000000000000000 R15: ffff9b5f3ffdedc0
 FS:    0000000000000000(0000) GS:ffff9b5f2fb40000(0000) knlGS:0000000000000000
 CS:    0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000000 CR3: 000000027c36c002 CR4: 00000000003706e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 Call Trace:
    refill_obj_stock+0x5e/0xd0
    free_percpu+0xee/0x550
    __bpf_prog_free+0x4d/0x60
    process_one_work+0x26a/0x590
    worker_thread+0x3c/0x390
    ? process_one_work+0x590/0x590
    kthread+0x130/0x150
    ? kthread_park+0x80/0x80
    ret_from_fork+0x1f/0x30

This bug is 100% reproducible with test_kmod.sh.

Fixes: 700d4796ef59 ("bpf: Optimize program stats")
Fixes: ca06f55b9002 ("bpf: Add per-program recursion prevention mechanism")
Reported-by: Jiang Wang <jiang.wang@bytedance.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210218001647.71631-1-xiyou.wangcong@gmail.com
---
 kernel/bpf/core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 0ae015ad1e05..aa1e64196d8d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1118,6 +1118,8 @@ static void bpf_prog_clone_free(struct bpf_prog *fp)
 	 * clone is guaranteed to not be locked.
 	 */
 	fp->aux = NULL;
+	fp->stats = NULL;
+	fp->active = NULL;
 	__bpf_prog_free(fp);
 }
 

From 8fc0e3b6a8666d656923d214e4dc791e9a17164a Mon Sep 17 00:00:00 2001
From: Eyal Birger <eyal.birger@gmail.com>
Date: Sat, 20 Feb 2021 15:01:15 +0200
Subject: [PATCH 0033/1820] xfrm: interface: fix ipv4 pmtu check to honor ip
 header df

Frag needed should only be sent if the header enables DF.

This fix allows packets larger than MTU to pass the xfrm interface
and be fragmented after encapsulation, aligning behavior with
non-interface xfrm.

Fixes: f203b76d7809 ("xfrm: Add virtual xfrm interfaces")
Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_interface.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 495b1f5c979b..8831f5a9e992 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -306,6 +306,8 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 
 			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		} else {
+			if (!(ip_hdr(skb)->frag_off & htons(IP_DF)))
+				goto xmit;
 			icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				      htonl(mtu));
 		}
@@ -314,6 +316,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 		return -EMSGSIZE;
 	}
 
+xmit:
 	xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev)));
 	skb_dst_set(skb, dst);
 	skb->dev = tdev;

From 743c97ca9dc989b0b08ca1fbfd134a83b37fe9ec Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Thu, 11 Feb 2021 14:40:58 -0800
Subject: [PATCH 0034/1820] drm/msm/kms: Use nested locking for crtc lock
 instead of custom classes

We don't need to make up custom lock classes here, we can simply use
mutex_lock_nested() and pass in the index of the crtc to the locking
APIs instead. This helps lockdep understand that these are really
different locks while avoiding having to allocate custom lockdep
classes.

Cc: Krishna Manikandan <mkrishn@codeaurora.org>
Suggested-by: Daniel Vetter <daniel@ffwll.ch>
Fixes: b3d91800d9ac ("drm/msm: Fix race condition in msm driver with async layer updates")
Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/msm_atomic.c | 7 +++++--
 drivers/gpu/drm/msm/msm_kms.h    | 8 ++------
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index 6a326761dc4a..edcaccaa27e6 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -57,10 +57,13 @@ static void vblank_put(struct msm_kms *kms, unsigned crtc_mask)
 
 static void lock_crtcs(struct msm_kms *kms, unsigned int crtc_mask)
 {
+	int crtc_index;
 	struct drm_crtc *crtc;
 
-	for_each_crtc_mask(kms->dev, crtc, crtc_mask)
-		mutex_lock(&kms->commit_lock[drm_crtc_index(crtc)]);
+	for_each_crtc_mask(kms->dev, crtc, crtc_mask) {
+		crtc_index = drm_crtc_index(crtc);
+		mutex_lock_nested(&kms->commit_lock[crtc_index], crtc_index);
+	}
 }
 
 static void unlock_crtcs(struct msm_kms *kms, unsigned int crtc_mask)
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index 4735251a394d..d8151a89e163 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -157,7 +157,6 @@ struct msm_kms {
 	 * from the crtc's pending_timer close to end of the frame:
 	 */
 	struct mutex commit_lock[MAX_CRTCS];
-	struct lock_class_key commit_lock_keys[MAX_CRTCS];
 	unsigned pending_crtc_mask;
 	struct msm_pending_timer pending_timers[MAX_CRTCS];
 };
@@ -167,11 +166,8 @@ static inline int msm_kms_init(struct msm_kms *kms,
 {
 	unsigned i, ret;
 
-	for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) {
-		lockdep_register_key(&kms->commit_lock_keys[i]);
-		__mutex_init(&kms->commit_lock[i], "&kms->commit_lock[i]",
-			     &kms->commit_lock_keys[i]);
-	}
+	for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++)
+		mutex_init(&kms->commit_lock[i]);
 
 	kms->funcs = funcs;
 

From 65aee407a0f5d0548c560e5fc3cad21e51b6f7fd Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Mon, 8 Feb 2021 13:55:54 -0500
Subject: [PATCH 0035/1820] drm/msm: fix a6xx_gmu_clear_oob

The cleanup patch broke a6xx_gmu_clear_oob, fix it by adding the missing
bitshift operation.

Fixes: 555c50a4a19b ("drm/msm: Clean up GMU OOB set/clear handling")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 9066e98eb8ef..863047b98bf3 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -339,7 +339,7 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 	else
 		bit = a6xx_gmu_oob_bits[state].ack_new;
 
-	gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, bit);
+	gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, 1 << bit);
 }
 
 /* Enable CPU control of SPTP power power collapse */

From 8490f02a3ca45fd1bbcadc243b4db9b69d0e3450 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 9 Feb 2021 17:52:05 -0700
Subject: [PATCH 0036/1820] drm/msm: a6xx: Make sure the SQE microcode is safe

Most a6xx targets have security issues that were fixed with new versions
of the microcode(s). Make sure that we are booting with a safe version of
the microcode for the target and print a message and error if not.

v2: Add more informative error messages and fix typos

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Reviewed-by: Akhil P Oommen <akhilpo@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 77 ++++++++++++++++++++++-----
 1 file changed, 64 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index ba8e9d3cf0fe..064b7face504 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -522,28 +522,73 @@ static int a6xx_cp_init(struct msm_gpu *gpu)
 	return a6xx_idle(gpu, ring) ? 0 : -EINVAL;
 }
 
-static void a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
+/*
+ * Check that the microcode version is new enough to include several key
+ * security fixes. Return true if the ucode is safe.
+ */
+static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 		struct drm_gem_object *obj)
 {
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	struct msm_gpu *gpu = &adreno_gpu->base;
 	u32 *buf = msm_gem_get_vaddr(obj);
+	bool ret = false;
 
 	if (IS_ERR(buf))
-		return;
+		return false;
 
 	/*
-	 * If the lowest nibble is 0xa that is an indication that this microcode
-	 * has been patched. The actual version is in dword [3] but we only care
-	 * about the patchlevel which is the lowest nibble of dword [3]
-	 *
-	 * Otherwise check that the firmware is greater than or equal to 1.90
-	 * which was the first version that had this fix built in
+	 * Targets up to a640 (a618, a630 and a640) need to check for a
+	 * microcode version that is patched to support the whereami opcode or
+	 * one that is new enough to include it by default.
 	 */
-	if (((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1)
-		a6xx_gpu->has_whereami = true;
-	else if ((buf[0] & 0xfff) > 0x190)
-		a6xx_gpu->has_whereami = true;
+	if (adreno_is_a618(adreno_gpu) || adreno_is_a630(adreno_gpu) ||
+		adreno_is_a640(adreno_gpu)) {
+		/*
+		 * If the lowest nibble is 0xa that is an indication that this
+		 * microcode has been patched. The actual version is in dword
+		 * [3] but we only care about the patchlevel which is the lowest
+		 * nibble of dword [3]
+		 *
+		 * Otherwise check that the firmware is greater than or equal
+		 * to 1.90 which was the first version that had this fix built
+		 * in
+		 */
+		if ((((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) ||
+			(buf[0] & 0xfff) >= 0x190) {
+			a6xx_gpu->has_whereami = true;
+			ret = true;
+			goto out;
+		}
 
+		DRM_DEV_ERROR(&gpu->pdev->dev,
+			"a630 SQE ucode is too old. Have version %x need at least %x\n",
+			buf[0] & 0xfff, 0x190);
+	}  else {
+		/*
+		 * a650 tier targets don't need whereami but still need to be
+		 * equal to or newer than 1.95 for other security fixes
+		 */
+		if (adreno_is_a650(adreno_gpu)) {
+			if ((buf[0] & 0xfff) >= 0x195) {
+				ret = true;
+				goto out;
+			}
+
+			DRM_DEV_ERROR(&gpu->pdev->dev,
+				"a650 SQE ucode is too old. Have version %x need at least %x\n",
+				buf[0] & 0xfff, 0x195);
+		}
+
+		/*
+		 * When a660 is added those targets should return true here
+		 * since those have all the critical security fixes built in
+		 * from the start
+		 */
+	}
+out:
 	msm_gem_put_vaddr(obj);
+	return ret;
 }
 
 static int a6xx_ucode_init(struct msm_gpu *gpu)
@@ -566,7 +611,13 @@ static int a6xx_ucode_init(struct msm_gpu *gpu)
 		}
 
 		msm_gem_object_set_name(a6xx_gpu->sqe_bo, "sqefw");
-		a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo);
+		if (!a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo)) {
+			msm_gem_unpin_iova(a6xx_gpu->sqe_bo, gpu->aspace);
+			drm_gem_object_put(a6xx_gpu->sqe_bo);
+
+			a6xx_gpu->sqe_bo = NULL;
+			return -EPERM;
+		}
 	}
 
 	gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO,

From 9aa940047ae81fa1806506556cde1efd0c39aef9 Mon Sep 17 00:00:00 2001
From: Sharvari Harisangam <sharvari.harisangam@nxp.com>
Date: Mon, 22 Feb 2021 18:19:44 +0530
Subject: [PATCH 0037/1820] MAINTAINERS: update for mwifiex driver maintainers

Add Sharvari Harisangam to Maintainer list.
Replace Ganapathi Bhat's email id in Maintainer list.

Signed-off-by: Rakesh Parmar <rakesh.parmar@nxp.com>
Signed-off-by: Sharvari Harisangam <sharvari.harisangam@nxp.com>
Acked-by: Ganapathi Bhat <ganapathi.bhat@nxp.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/1613998184-20047-1-git-send-email-sharvari.harisangam@nxp.com
---
 MAINTAINERS | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 99335fd22c0a..98fd98ebe6b2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10685,7 +10685,8 @@ F:	drivers/net/ethernet/marvell/mvpp2/
 
 MARVELL MWIFIEX WIRELESS DRIVER
 M:	Amitkumar Karwar <amitkarwar@gmail.com>
-M:	Ganapathi Bhat <ganapathi.bhat@nxp.com>
+M:	Ganapathi Bhat <ganapathi017@gmail.com>
+M:	Sharvari Harisangam <sharvari.harisangam@nxp.com>
 M:	Xinming Hu <huxinming820@gmail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained

From ebb9d34e073dc965e9e1f0632a95dcb83736f166 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Sun, 21 Feb 2021 19:27:54 +0100
Subject: [PATCH 0038/1820] ath11k: qmi: use %pad to format dma_addr_t
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If CONFIG_ARCH_DMA_ADDR_T_64BIT=n:

    drivers/net/wireless/ath/ath11k/qmi.c: In function ‘ath11k_qmi_respond_fw_mem_request’:
    drivers/net/wireless/ath/ath11k/qmi.c:1690:8: warning: format ‘%llx’ expects argument of type ‘long long unsigned int’, but argument 5 has type ‘dma_addr_t’ {aka ‘unsigned int’} [-Wformat=]
     1690 |        "qmi req mem_seg[%d] 0x%llx %u %u\n", i,
	  |        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     1691 |         ab->qmi.target_mem[i].paddr,
	  |         ~~~~~~~~~~~~~~~~~~~~~~~~~~~
	  |                              |
	  |                              dma_addr_t {aka unsigned int}
    drivers/net/wireless/ath/ath11k/debug.h:64:30: note: in definition of macro ‘ath11k_dbg’
       64 |   __ath11k_dbg(ar, dbg_mask, fmt, ##__VA_ARGS__); \
	  |                              ^~~
    drivers/net/wireless/ath/ath11k/qmi.c:1690:34: note: format string is defined here
     1690 |        "qmi req mem_seg[%d] 0x%llx %u %u\n", i,
	  |                               ~~~^
	  |                                  |
	  |                                  long long unsigned int
	  |                               %x

Fixes: d5395a5486596308 ("ath11k: qmi: add debug message for allocated memory segment addresses and sizes")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210221182754.2071863-1-geert@linux-m68k.org
---
 drivers/net/wireless/ath/ath11k/qmi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index 1aca841cd147..7968fe4eda22 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -1687,8 +1687,8 @@ static int ath11k_qmi_respond_fw_mem_request(struct ath11k_base *ab)
 			req->mem_seg[i].size = ab->qmi.target_mem[i].size;
 			req->mem_seg[i].type = ab->qmi.target_mem[i].type;
 			ath11k_dbg(ab, ATH11K_DBG_QMI,
-				   "qmi req mem_seg[%d] 0x%llx %u %u\n", i,
-				    ab->qmi.target_mem[i].paddr,
+				   "qmi req mem_seg[%d] %pad %u %u\n", i,
+				    &ab->qmi.target_mem[i].paddr,
 				    ab->qmi.target_mem[i].size,
 				    ab->qmi.target_mem[i].type);
 		}

From 77d7e87128d4dfb400df4208b2812160e999c165 Mon Sep 17 00:00:00 2001
From: Kalle Valo <kvalo@codeaurora.org>
Date: Mon, 22 Feb 2021 17:14:09 +0200
Subject: [PATCH 0039/1820] ath11k: fix AP mode for QCA6390

Commit c134d1f8c436 ("ath11k: Handle errors if peer creation fails") completely
broke AP mode on QCA6390:

kernel: [  151.230734] ath11k_pci 0000:06:00.0: failed to create peer after vdev start delay: -22
wpa_supplicant[2307]: Failed to set beacon parameters
wpa_supplicant[2307]: Interface initialization failed
wpa_supplicant[2307]: wlan0: interface state UNINITIALIZED->DISABLED
wpa_supplicant[2307]: wlan0: AP-DISABLED
wpa_supplicant[2307]: wlan0: Unable to setup interface.
wpa_supplicant[2307]: Failed to initialize AP interface

This was because commit c134d1f8c436 ("ath11k: Handle errors if peer creation
fails") added error handling for ath11k_peer_create(), which had been failing
all along but was unnoticed due to the missing error handling. The actual bug
was introduced already in commit aa44b2f3ecd4 ("ath11k: start vdev if a bss peer is
already created").

ath11k_peer_create() was failing because for AP mode the peer is created
already earlier op_add_interface() and we should skip creation here, but the
check for modes was wrong.  Fixing that makes AP mode work again.

This shouldn't affect IPQ8074 nor QCN9074 as they have hw_params.vdev_start_delay disabled.

Tested-on: QCA6390 hw2.0 PCI WLAN.HST.1.0.1-01740-QCAHSTSWPLZ_V2_TO_X86-1

Fixes: c134d1f8c436 ("ath11k: Handle errors if peer creation fails")
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/1614006849-25764-1-git-send-email-kvalo@codeaurora.org
---
 drivers/net/wireless/ath/ath11k/mac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index b391169576e2..faa2e678e63e 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -5450,8 +5450,8 @@ ath11k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 	}
 
 	if (ab->hw_params.vdev_start_delay &&
-	    (arvif->vdev_type == WMI_VDEV_TYPE_AP ||
-	    arvif->vdev_type == WMI_VDEV_TYPE_MONITOR)) {
+	    arvif->vdev_type != WMI_VDEV_TYPE_AP &&
+	    arvif->vdev_type != WMI_VDEV_TYPE_MONITOR) {
 		param.vdev_id = arvif->vdev_id;
 		param.peer_type = WMI_PEER_TYPE_DEFAULT;
 		param.peer_addr = ar->mac_addr;

From 37feaaf5ceb2245e474369312bb7b922ce7bce69 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 21 Feb 2021 12:43:18 -0500
Subject: [PATCH 0040/1820] net: ieee802154: fix nl802154 del llsec key

This patch fixes a nullpointer dereference if NL802154_ATTR_SEC_KEY is
not set by the user. If this is the case nl802154 will return -EINVAL.

Reported-by: syzbot+ac5c11d2959a8b3c4806@syzkaller.appspotmail.com
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210221174321.14210-1-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 1cebdcedc48c..f4a4d4a417e0 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1592,7 +1592,8 @@ static int nl802154_del_llsec_key(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1];
 	struct ieee802154_llsec_key_id id;
 
-	if (nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
+	if (!info->attrs[NL802154_ATTR_SEC_KEY] ||
+	    nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
 		return -EINVAL;
 
 	if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0)

From 3d1eac2f45585690d942cf47fd7fbd04093ebd1b Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 21 Feb 2021 12:43:19 -0500
Subject: [PATCH 0041/1820] net: ieee802154: fix nl802154 del llsec dev

This patch fixes a nullpointer dereference if NL802154_ATTR_SEC_DEVICE is
not set by the user. If this is the case nl802154 will return -EINVAL.

Reported-by: syzbot+d946223c2e751d136c94@syzkaller.appspotmail.com
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210221174321.14210-2-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index f4a4d4a417e0..460e53889781 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1758,7 +1758,8 @@ static int nl802154_del_llsec_dev(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1];
 	__le64 extended_addr;
 
-	if (nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVICE], nl802154_dev_policy, info->extack))
+	if (!info->attrs[NL802154_ATTR_SEC_DEVICE] ||
+	    nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVICE], nl802154_dev_policy, info->extack))
 		return -EINVAL;
 
 	if (!attrs[NL802154_DEV_ATTR_EXTENDED_ADDR])

From 20d5fe2d7103f5c43ad11a3d6d259e9d61165c35 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 21 Feb 2021 12:43:20 -0500
Subject: [PATCH 0042/1820] net: ieee802154: fix nl802154 add llsec key

This patch fixes a nullpointer dereference if NL802154_ATTR_SEC_KEY is
not set by the user. If this is the case nl802154 will return -EINVAL.

Reported-by: syzbot+ce4e062c2d51977ddc50@syzkaller.appspotmail.com
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210221174321.14210-3-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 460e53889781..4aa9000b7eea 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1544,7 +1544,8 @@ static int nl802154_add_llsec_key(struct sk_buff *skb, struct genl_info *info)
 	struct ieee802154_llsec_key_id id = { };
 	u32 commands[NL802154_CMD_FRAME_NR_IDS / 32] = { };
 
-	if (nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
+	if (!info->attrs[NL802154_ATTR_SEC_KEY] ||
+	    nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
 		return -EINVAL;
 
 	if (!attrs[NL802154_KEY_ATTR_USAGE_FRAMES] ||

From 27c746869e1a135dffc2f2a80715bb7aa00445b4 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 21 Feb 2021 12:43:21 -0500
Subject: [PATCH 0043/1820] net: ieee802154: fix nl802154 del llsec devkey

This patch fixes a nullpointer dereference if NL802154_ATTR_SEC_DEVKEY is
not set by the user. If this is the case nl802154 will return -EINVAL.

Reported-by: syzbot+368672e0da240db53b5f@syzkaller.appspotmail.com
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210221174321.14210-4-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 4aa9000b7eea..1600edb98107 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1916,7 +1916,8 @@ static int nl802154_del_llsec_devkey(struct sk_buff *skb, struct genl_info *info
 	struct ieee802154_llsec_device_key key;
 	__le64 extended_addr;
 
-	if (nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack))
+	if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] ||
+	    nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack))
 		return -EINVAL;
 
 	if (!attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR])

From f4eda8b6e4a5c7897c6bb992ed63a27061b371ef Mon Sep 17 00:00:00 2001
From: Dmitrii Banshchikov <me@ubique.spb.ru>
Date: Tue, 23 Feb 2021 13:04:16 +0400
Subject: [PATCH 0044/1820] bpf: Drop imprecise log message

Now it is possible for global function to have a pointer argument that
points to something different than struct. Drop the irrelevant log
message and keep the logic same.

Fixes: e5069b9c23b3 ("bpf: Support pointers in global func args")
Signed-off-by: Dmitrii Banshchikov <me@ubique.spb.ru>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210223090416.333943-1-me@ubique.spb.ru
---
 kernel/bpf/btf.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2efeb5f4b343..b1a76fe046cb 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4321,8 +4321,6 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
 		 * is not supported yet.
 		 * BPF_PROG_TYPE_RAW_TRACEPOINT is fine.
 		 */
-		if (log->level & BPF_LOG_LEVEL)
-			bpf_log(log, "arg#%d type is not a struct\n", arg);
 		return NULL;
 	}
 	tname = btf_name_by_offset(btf, t->name_off);

From c41d81bfbb4579c3e583457e383dd63d026bf947 Mon Sep 17 00:00:00 2001
From: Dmitrii Banshchikov <me@ubique.spb.ru>
Date: Tue, 23 Feb 2021 12:22:11 +0400
Subject: [PATCH 0045/1820] selftests/bpf: Fix a compiler warning in global
 func test

Add an explicit 'const void *' cast to pass program ctx pointer type into
a global function that expects pointer to structure.

warning: incompatible pointer types
passing 'struct __sk_buff *' to parameter of type 'const struct S *'
[-Wincompatible-pointer-types]
        return foo(skb);
                   ^~~
progs/test_global_func11.c:10:36: note: passing argument to parameter 's' here
__noinline int foo(const struct S *s)
                                   ^

Fixes: 8b08807d039a ("selftests/bpf: Add unit tests for pointers in global functions")
Signed-off-by: Dmitrii Banshchikov <me@ubique.spb.ru>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210223082211.302596-1-me@ubique.spb.ru
---
 tools/testing/selftests/bpf/progs/test_global_func11.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/test_global_func11.c b/tools/testing/selftests/bpf/progs/test_global_func11.c
index 28488047c849..ef5277d982d9 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func11.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func11.c
@@ -15,5 +15,5 @@ __noinline int foo(const struct S *s)
 SEC("cgroup_skb/ingress")
 int test_cls(struct __sk_buff *skb)
 {
-	return foo(skb);
+	return foo((const void *)skb);
 }

From 41462c6e730ca0e63f5fed5a517052385d980c54 Mon Sep 17 00:00:00 2001
From: Kun-Chuan Hsieh <jetswayss@gmail.com>
Date: Wed, 24 Feb 2021 05:27:52 +0000
Subject: [PATCH 0046/1820] tools/resolve_btfids: Fix build error with older
 host toolchains

Older libelf.h and glibc elf.h might not yet define the ELF compression
types.

Checking and defining SHF_COMPRESSED fix the build error when compiling
with older toolchains. Also, the tool resolve_btfids is compiled with host
toolchain. The host toolchain is more likely to be older than the cross
compile toolchain.

Fixes: 51f6463aacfb ("tools/resolve_btfids: Fix sections with wrong alignment")
Signed-off-by: Kun-Chuan Hsieh <jetswayss@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Link: https://lore.kernel.org/bpf/20210224052752.5284-1-jetswayss@gmail.com
---
 tools/bpf/resolve_btfids/main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index 7409d7860aa6..80d966cfcaa1 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -260,6 +260,11 @@ static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size)
 	return btf_id__add(root, id, false);
 }
 
+/* Older libelf.h and glibc elf.h might not yet define the ELF compression types. */
+#ifndef SHF_COMPRESSED
+#define SHF_COMPRESSED (1 << 11) /* Section with compressed data. */
+#endif
+
 /*
  * The data of compressed section should be aligned to 4
  * (for 32bit) or 8 (for 64 bit) bytes. The binutils ld

From a7c9c25a99bbdaff51da26b874d2faaa8fdd72b5 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 23 Feb 2021 21:14:57 +0800
Subject: [PATCH 0047/1820] bpf: Remove blank line in bpf helper description
 comment

Commit 34b2021cc616 ("bpf: Add BPF-helper for MTU checking") added an extra
blank line in bpf helper description. This will make bpf_helpers_doc.py stop
building bpf_helper_defs.h immediately after bpf_check_mtu(), which will
affect future added functions.

Fixes: 34b2021cc616 ("bpf: Add BPF-helper for MTU checking")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/20210223131457.1378978-1-liuhangbin@gmail.com
---
 include/uapi/linux/bpf.h       | 1 -
 tools/include/uapi/linux/bpf.h | 1 -
 2 files changed, 2 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4c24daa43bac..79c893310492 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3850,7 +3850,6 @@ union bpf_attr {
  *
  * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
  *	Description
-
  *		Check ctx packet size against exceeding MTU of net device (based
  *		on *ifindex*).  This helper will likely be used in combination
  *		with helpers that adjust/change the packet size.
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4c24daa43bac..79c893310492 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3850,7 +3850,6 @@ union bpf_attr {
  *
  * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
  *	Description
-
  *		Check ctx packet size against exceeding MTU of net device (based
  *		on *ifindex*).  This helper will likely be used in combination
  *		with helpers that adjust/change the packet size.

From 557c223b643a35effec9654958d8edc62fd2603a Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 24 Feb 2021 16:14:03 +0800
Subject: [PATCH 0048/1820] selftests/bpf: No need to drop the packet when
 there is no geneve opt

In bpf geneve tunnel test we set geneve option on tx side. On rx side we
only call bpf_skb_get_tunnel_opt(). Since commit 9c2e14b48119 ("ip_tunnels:
Set tunnel option flag when tunnel metadata is present") geneve_rx() will
not add TUNNEL_GENEVE_OPT flag if there is no geneve option, which cause
bpf_skb_get_tunnel_opt() return ENOENT and _geneve_get_tunnel() in
test_tunnel_kern.c drop the packet.

As it should be valid that bpf_skb_get_tunnel_opt() return error when
there is not tunnel option, there is no need to drop the packet and
break all geneve rx traffic. Just set opt_class to 0 in this test and
keep returning TC_ACT_OK.

Fixes: 933a741e3b82 ("selftests/bpf: bpf tunnel test.")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: William Tu <u9012063@gmail.com>
Link: https://lore.kernel.org/bpf/20210224081403.1425474-1-liuhangbin@gmail.com
---
 tools/testing/selftests/bpf/progs/test_tunnel_kern.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index a621b58ab079..9afe947cfae9 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -446,10 +446,8 @@ int _geneve_get_tunnel(struct __sk_buff *skb)
 	}
 
 	ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
-	if (ret < 0) {
-		ERROR(ret);
-		return TC_ACT_SHOT;
-	}
+	if (ret < 0)
+		gopt.opt_class = 0;
 
 	bpf_trace_printk(fmt, sizeof(fmt),
 			key.tunnel_id, key.remote_ipv4, gopt.opt_class);

From f00bdce0455233a0b76dae6364442dca717a574c Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 23 Feb 2021 14:19:04 +0800
Subject: [PATCH 0049/1820] vdpa: set the virtqueue num during register

This patch delay the queue number setting to vDPA device
registering. This allows us to probe the virtqueue numbers between
device allocation and registering.

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20210223061905.422659-3-jasowang@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/ifcvf/ifcvf_main.c      |  5 ++---
 drivers/vdpa/mlx5/net/mlx5_vnet.c    |  4 ++--
 drivers/vdpa/vdpa.c                  | 18 ++++++++++--------
 drivers/vdpa/vdpa_sim/vdpa_sim.c     |  2 +-
 drivers/vdpa/vdpa_sim/vdpa_sim_net.c |  2 +-
 include/linux/vdpa.h                 | 10 +++++-----
 6 files changed, 21 insertions(+), 20 deletions(-)

diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index 7c8bbfcf6c3e..d555a6a5d1ba 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -431,8 +431,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
-				    dev, &ifc_vdpa_ops,
-				    IFCVF_MAX_QUEUE_PAIRS * 2, NULL);
+				    dev, &ifc_vdpa_ops, NULL);
 	if (adapter == NULL) {
 		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
 		return -ENOMEM;
@@ -456,7 +455,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++)
 		vf->vring[i].irq = -EINVAL;
 
-	ret = vdpa_register_device(&adapter->vdpa);
+	ret = vdpa_register_device(&adapter->vdpa, IFCVF_MAX_QUEUE_PAIRS * 2);
 	if (ret) {
 		IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus");
 		goto err;
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 10e9b09932eb..71397fdafa6a 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1982,7 +1982,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
 	max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS);
 
 	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
-				 2 * mlx5_vdpa_max_qps(max_vqs), NULL);
+				 NULL);
 	if (IS_ERR(ndev))
 		return PTR_ERR(ndev);
 
@@ -2009,7 +2009,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
 	if (err)
 		goto err_res;
 
-	err = vdpa_register_device(&mvdev->vdev);
+	err = vdpa_register_device(&mvdev->vdev, 2 * mlx5_vdpa_max_qps(max_vqs));
 	if (err)
 		goto err_reg;
 
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index da67f07e24fd..5cffce67cab0 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -69,7 +69,6 @@ static void vdpa_release_dev(struct device *d)
  * initialized but before registered.
  * @parent: the parent device
  * @config: the bus operations that is supported by this device
- * @nvqs: number of virtqueues supported by this device
  * @size: size of the parent structure that contains private data
  * @name: name of the vdpa device; optional.
  *
@@ -81,7 +80,7 @@ static void vdpa_release_dev(struct device *d)
  */
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					int nvqs, size_t size, const char *name)
+					size_t size, const char *name)
 {
 	struct vdpa_device *vdev;
 	int err = -EINVAL;
@@ -107,7 +106,6 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	vdev->index = err;
 	vdev->config = config;
 	vdev->features_valid = false;
-	vdev->nvqs = nvqs;
 
 	if (name)
 		err = dev_set_name(&vdev->dev, "%s", name);
@@ -136,10 +134,12 @@ static int vdpa_name_match(struct device *dev, const void *data)
 	return (strcmp(dev_name(&vdev->dev), data) == 0);
 }
 
-static int __vdpa_register_device(struct vdpa_device *vdev)
+static int __vdpa_register_device(struct vdpa_device *vdev, int nvqs)
 {
 	struct device *dev;
 
+	vdev->nvqs = nvqs;
+
 	lockdep_assert_held(&vdpa_dev_mutex);
 	dev = bus_find_device(&vdpa_bus, NULL, dev_name(&vdev->dev), vdpa_name_match);
 	if (dev) {
@@ -155,15 +155,16 @@ static int __vdpa_register_device(struct vdpa_device *vdev)
  * Caller must invoke this routine in the management device dev_add()
  * callback after setting up valid mgmtdev for this vdpa device.
  * @vdev: the vdpa device to be registered to vDPA bus
+ * @nvqs: number of virtqueues supported by this device
  *
  * Returns an error when fail to add device to vDPA bus
  */
-int _vdpa_register_device(struct vdpa_device *vdev)
+int _vdpa_register_device(struct vdpa_device *vdev, int nvqs)
 {
 	if (!vdev->mdev)
 		return -EINVAL;
 
-	return __vdpa_register_device(vdev);
+	return __vdpa_register_device(vdev, nvqs);
 }
 EXPORT_SYMBOL_GPL(_vdpa_register_device);
 
@@ -171,15 +172,16 @@ EXPORT_SYMBOL_GPL(_vdpa_register_device);
  * vdpa_register_device - register a vDPA device
  * Callers must have a succeed call of vdpa_alloc_device() before.
  * @vdev: the vdpa device to be registered to vDPA bus
+ * @nvqs: number of virtqueues supported by this device
  *
  * Returns an error when fail to add to vDPA bus
  */
-int vdpa_register_device(struct vdpa_device *vdev)
+int vdpa_register_device(struct vdpa_device *vdev, int nvqs)
 {
 	int err;
 
 	mutex_lock(&vdpa_dev_mutex);
-	err = __vdpa_register_device(vdev);
+	err = __vdpa_register_device(vdev, nvqs);
 	mutex_unlock(&vdpa_dev_mutex);
 	return err;
 }
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index d5942842432d..5b6b2f87d40c 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -235,7 +235,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)
 		ops = &vdpasim_config_ops;
 
 	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops,
-				    dev_attr->nvqs, dev_attr->name);
+				    dev_attr->name);
 	if (!vdpasim)
 		goto err_alloc;
 
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
index d344c5b7c914..702be74877d2 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
@@ -147,7 +147,7 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
 	if (IS_ERR(simdev))
 		return PTR_ERR(simdev);
 
-	ret = _vdpa_register_device(&simdev->vdpa);
+	ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_NET_VQ_NUM);
 	if (ret)
 		goto reg_err;
 
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 4ab5494503a8..15fa085fab05 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -250,20 +250,20 @@ struct vdpa_config_ops {
 
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					int nvqs, size_t size, const char *name);
+					size_t size, const char *name);
 
-#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs, name)   \
+#define vdpa_alloc_device(dev_struct, member, parent, config, name)   \
 			  container_of(__vdpa_alloc_device( \
-				       parent, config, nvqs, \
+				       parent, config, \
 				       sizeof(dev_struct) + \
 				       BUILD_BUG_ON_ZERO(offsetof( \
 				       dev_struct, member)), name), \
 				       dev_struct, member)
 
-int vdpa_register_device(struct vdpa_device *vdev);
+int vdpa_register_device(struct vdpa_device *vdev, int nvqs);
 void vdpa_unregister_device(struct vdpa_device *vdev);
 
-int _vdpa_register_device(struct vdpa_device *vdev);
+int _vdpa_register_device(struct vdpa_device *vdev, int nvqs);
 void _vdpa_unregister_device(struct vdpa_device *vdev);
 
 /**

From 62541e266703549550e77fd46138422dbdc881f1 Mon Sep 17 00:00:00 2001
From: Kalle Valo <kvalo@codeaurora.org>
Date: Thu, 25 Feb 2021 09:04:21 +0200
Subject: [PATCH 0050/1820] iwlwifi: pcie: fix iwl_so_trans_cfg link error when
 CONFIG_IWLMVM is disabled

Randy reported an error on his randconfig builds:

ERROR: modpost: "iwl_so_trans_cfg" [drivers/net/wireless/intel/iwlwifi/iwlwifi.ko] undefined!

The problem was that when CONFIG_IWLMVM was disabled we were still accessing
iwl_so_trans_cfg. Fix it by moving IS_ENABLED() check before the access.

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Fixes: 930be4e76f26 ("iwlwifi: add support for SnJ with Jf devices")
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Acked-by: Luca Coelho <luciano.coelho@intel.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/1614236661-20274-1-git-send-email-kvalo@codeaurora.org
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 314fec4a89ad..ffaf973dae94 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1106,6 +1106,8 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	}
 
+#if IS_ENABLED(CONFIG_IWLMVM)
+
 	/*
 	 * Workaround for problematic SnJ device: sometimes when
 	 * certain RF modules are connected to SnJ, the device ID
@@ -1116,7 +1118,6 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (CSR_HW_REV_TYPE(iwl_trans->hw_rev) == IWL_CFG_MAC_TYPE_SNJ)
 		iwl_trans->trans_cfg = &iwl_so_trans_cfg;
 
-#if IS_ENABLED(CONFIG_IWLMVM)
 	/*
 	 * special-case 7265D, it has the same PCI IDs.
 	 *

From fb5fabb192b22293b70bc3351696473c50746d90 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 25 Feb 2021 15:59:15 +0100
Subject: [PATCH 0051/1820] mt76: mt7921: remove incorrect error handling

Clang points out a mistake in the error handling in
mt7921_mcu_tx_rate_report(), which tries to dereference a pointer that
cannot be initialized because of the error that is being handled:

drivers/net/wireless/mediatek/mt76/mt7921/mcu.c:409:3: warning: variable 'stats' is uninitialized when used here [-Wuninitialized]
                stats->tx_rate = rate;
                ^~~~~
drivers/net/wireless/mediatek/mt76/mt7921/mcu.c:401:32: note: initialize the variable 'stats' to silence this warning
        struct mt7921_sta_stats *stats;
                                      ^
Just remove the obviously incorrect line.

Fixes: 1c099ab44727 ("mt76: mt7921: add MCU support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210225145953.404859-2-arnd@kernel.org
---
 drivers/net/wireless/mediatek/mt76/mt7921/mcu.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index db125cd22b91..b5cc72e7e81c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -405,10 +405,8 @@ mt7921_mcu_tx_rate_report(struct mt7921_dev *dev, struct sk_buff *skb,
 	if (wlan_idx >= MT76_N_WCIDS)
 		return;
 	wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
-	if (!wcid) {
-		stats->tx_rate = rate;
+	if (!wcid)
 		return;
-	}
 
 	msta = container_of(wcid, struct mt7921_sta, wcid);
 	stats = &msta->stats;

From d0bd52c591a1070c54dc428e926660eb4f981099 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sun, 7 Feb 2021 12:48:31 +0100
Subject: [PATCH 0052/1820] mt76: dma: do not report truncated frames to
 mac80211

Commit b102f0c522cf6 ("mt76: fix array overflow on receiving too many
fragments for a packet") fixes a possible OOB access but it introduces a
memory leak since the pending frame is not released to page_frag_cache
if the frag array of skb_shared_info is full. Commit 93a1d4791c10
("mt76: dma: fix a possible memory leak in mt76_add_fragment()") fixes
the issue but does not free the truncated skb that is forwarded to
mac80211 layer. Fix the leftover issue discarding even truncated skbs.

Fixes: 93a1d4791c10 ("mt76: dma: fix a possible memory leak in mt76_add_fragment()")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/a03166fcc8214644333c68674a781836e0f57576.1612697217.git.lorenzo@kernel.org
---
 drivers/net/wireless/mediatek/mt76/dma.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index abdc8d364361..2f27c43ad76d 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -512,13 +512,13 @@ mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data,
 {
 	struct sk_buff *skb = q->rx_head;
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	int nr_frags = shinfo->nr_frags;
 
-	if (shinfo->nr_frags < ARRAY_SIZE(shinfo->frags)) {
+	if (nr_frags < ARRAY_SIZE(shinfo->frags)) {
 		struct page *page = virt_to_head_page(data);
 		int offset = data - page_address(page) + q->buf_offset;
 
-		skb_add_rx_frag(skb, shinfo->nr_frags, page, offset, len,
-				q->buf_size);
+		skb_add_rx_frag(skb, nr_frags, page, offset, len, q->buf_size);
 	} else {
 		skb_free_frag(data);
 	}
@@ -527,7 +527,10 @@ mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data,
 		return;
 
 	q->rx_head = NULL;
-	dev->drv->rx_skb(dev, q - dev->q_rx, skb);
+	if (nr_frags < ARRAY_SIZE(shinfo->frags))
+		dev->drv->rx_skb(dev, q - dev->q_rx, skb);
+	else
+		dev_kfree_skb(skb);
 }
 
 static int

From c490492f15f656340b35cb9e36b9bfdea3539e19 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 26 Feb 2021 15:21:27 +0100
Subject: [PATCH 0053/1820] mt76: mt7915: fix unused 'mode' variable

clang points out a possible corner case in the mt7915_tm_set_tx_cont()
function if called with invalid arguments:

drivers/net/wireless/mediatek/mt76/mt7915/testmode.c:593:2: warning: variable 'mode' is used uninitialized whenever switch default is taken [-Wsometimes-uninitialized]
        default:
        ^~~~~~~
drivers/net/wireless/mediatek/mt76/mt7915/testmode.c:597:13: note: uninitialized use occurs here
        rateval =  mode << 6 | rate_idx;
                   ^~~~
drivers/net/wireless/mediatek/mt76/mt7915/testmode.c:506:37: note: initialize the variable 'mode' to silence this warning
        u8 rate_idx = td->tx_rate_idx, mode;
                                           ^

Change it to return an error instead of continuing with invalid data
here.

Fixes: 3f0caa3cbf94 ("mt76: mt7915: add support for continuous tx in testmode")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt7915/testmode.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c
index 7fb2170a9561..bd798df748ba 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c
@@ -543,7 +543,7 @@ mt7915_tm_set_tx_cont(struct mt7915_phy *phy, bool en)
 		tx_cont->bw = CMD_CBW_20MHZ;
 		break;
 	default:
-		break;
+		return -EINVAL;
 	}
 
 	if (!en) {
@@ -591,7 +591,7 @@ mt7915_tm_set_tx_cont(struct mt7915_phy *phy, bool en)
 		mode = MT_PHY_TYPE_HE_MU;
 		break;
 	default:
-		break;
+		return -EINVAL;
 	}
 
 	rateval =  mode << 6 | rate_idx;

From a3e860a83397bf761ec1128a3f0ba186445992c6 Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang@nxp.com>
Date: Thu, 25 Feb 2021 17:01:10 +0800
Subject: [PATCH 0054/1820] net: stmmac: stop each tx channel independently

If clear GMAC_CONFIG_TE bit, it would stop all tx channels, but users
may only want to stop specific tx channel.

Fixes: 48863ce5940f ("stmmac: add DMA support for GMAC 4.xx")
Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index 0b4ee2dbb691..71e50751ef2d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -53,10 +53,6 @@ void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan)
 
 	value &= ~DMA_CONTROL_ST;
 	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
-
-	value = readl(ioaddr + GMAC_CONFIG);
-	value &= ~GMAC_CONFIG_TE;
-	writel(value, ioaddr + GMAC_CONFIG);
 }
 
 void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan)

From c511819d138de38e1637eedb645c207e09680d0f Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang@nxp.com>
Date: Thu, 25 Feb 2021 17:01:11 +0800
Subject: [PATCH 0055/1820] net: stmmac: fix watchdog timeout during
 suspend/resume stress test

stmmac_xmit() call stmmac_tx_timer_arm() at the end to modify tx timer to
do the transmission cleanup work. Imagine such a situation, stmmac enters
suspend immediately after tx timer modified, it's expire callback
stmmac_tx_clean() would not be invoked. This could affect BQL, since
netdev_tx_sent_queue() has been called, but netdev_tx_completed_queue()
have not been involved, as a result, dql_avail(&dev_queue->dql) finally
always return a negative value.

__dev_queue_xmit->__dev_xmit_skb->qdisc_run->__qdisc_run->qdisc_restart->dequeue_skb:
	if ((q->flags & TCQ_F_ONETXQUEUE) &&
		netif_xmit_frozen_or_stopped(txq)) // __QUEUE_STATE_STACK_XOFF is set

Net core will stop transmitting any more. Finillay, net watchdong would timeout.
To fix this issue, we should call netdev_tx_reset_queue() in stmmac_resume().

Fixes: 54139cf3bb33 ("net: stmmac: adding multiple buffers for rx")
Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 26b971cd4da5..12ed337a239b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -5257,6 +5257,8 @@ static void stmmac_reset_queues_param(struct stmmac_priv *priv)
 		tx_q->cur_tx = 0;
 		tx_q->dirty_tx = 0;
 		tx_q->mss = 0;
+
+		netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 }
 

From bfaf91ca848e758ed7be99b61fd936d03819fa56 Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang@nxp.com>
Date: Thu, 25 Feb 2021 17:01:12 +0800
Subject: [PATCH 0056/1820] net: stmmac: fix dma physical address of descriptor
 when display ring

Driver uses dma_alloc_coherent to allocate dma memory for descriptors,
dma_alloc_coherent will return both the virtual address and physical
address. AFAIK, virt_to_phys could not convert virtual address to
physical address, for which memory is allocated by dma_alloc_coherent.

dwmac4_display_ring() function is broken for various descriptor, it only
support normal descriptor(struct dma_desc) now, this patch also extends to
support all descriptor types.

Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/stmicro/stmmac/dwmac4_descs.c    | 50 +++++++++++++---
 .../net/ethernet/stmicro/stmmac/enh_desc.c    |  9 ++-
 drivers/net/ethernet/stmicro/stmmac/hwif.h    |  3 +-
 .../net/ethernet/stmicro/stmmac/norm_desc.c   |  9 ++-
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 57 ++++++++++++-------
 5 files changed, 94 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index c6540b003b43..ee87811b0ca5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -402,19 +402,53 @@ static void dwmac4_rd_set_tx_ic(struct dma_desc *p)
 	p->des2 |= cpu_to_le32(TDES2_INTERRUPT_ON_COMPLETION);
 }
 
-static void dwmac4_display_ring(void *head, unsigned int size, bool rx)
+static void dwmac4_display_ring(void *head, unsigned int size, bool rx,
+				dma_addr_t dma_rx_phy, unsigned int desc_size)
 {
-	struct dma_desc *p = (struct dma_desc *)head;
+	dma_addr_t dma_addr;
 	int i;
 
 	pr_info("%s descriptor ring:\n", rx ? "RX" : "TX");
 
-	for (i = 0; i < size; i++) {
-		pr_info("%03d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
-			i, (unsigned int)virt_to_phys(p),
-			le32_to_cpu(p->des0), le32_to_cpu(p->des1),
-			le32_to_cpu(p->des2), le32_to_cpu(p->des3));
-		p++;
+	if (desc_size == sizeof(struct dma_desc)) {
+		struct dma_desc *p = (struct dma_desc *)head;
+
+		for (i = 0; i < size; i++) {
+			dma_addr = dma_rx_phy + i * sizeof(*p);
+			pr_info("%03d [%pad]: 0x%x 0x%x 0x%x 0x%x\n",
+				i, &dma_addr,
+				le32_to_cpu(p->des0), le32_to_cpu(p->des1),
+				le32_to_cpu(p->des2), le32_to_cpu(p->des3));
+			p++;
+		}
+	} else if (desc_size == sizeof(struct dma_extended_desc)) {
+		struct dma_extended_desc *extp = (struct dma_extended_desc *)head;
+
+		for (i = 0; i < size; i++) {
+			dma_addr = dma_rx_phy + i * sizeof(*extp);
+			pr_info("%03d [%pad]: 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x\n",
+				i, &dma_addr,
+				le32_to_cpu(extp->basic.des0), le32_to_cpu(extp->basic.des1),
+				le32_to_cpu(extp->basic.des2), le32_to_cpu(extp->basic.des3),
+				le32_to_cpu(extp->des4), le32_to_cpu(extp->des5),
+				le32_to_cpu(extp->des6), le32_to_cpu(extp->des7));
+			extp++;
+		}
+	} else if (desc_size == sizeof(struct dma_edesc)) {
+		struct dma_edesc *ep = (struct dma_edesc *)head;
+
+		for (i = 0; i < size; i++) {
+			dma_addr = dma_rx_phy + i * sizeof(*ep);
+			pr_info("%03d [%pad]: 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x\n",
+				i, &dma_addr,
+				le32_to_cpu(ep->des4), le32_to_cpu(ep->des5),
+				le32_to_cpu(ep->des6), le32_to_cpu(ep->des7),
+				le32_to_cpu(ep->basic.des0), le32_to_cpu(ep->basic.des1),
+				le32_to_cpu(ep->basic.des2), le32_to_cpu(ep->basic.des3));
+			ep++;
+		}
+	} else {
+		pr_err("unsupported descriptor!");
 	}
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index d02cec296f51..6650edfab5bc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -417,19 +417,22 @@ static int enh_desc_get_rx_timestamp_status(void *desc, void *next_desc,
 	}
 }
 
-static void enh_desc_display_ring(void *head, unsigned int size, bool rx)
+static void enh_desc_display_ring(void *head, unsigned int size, bool rx,
+				  dma_addr_t dma_rx_phy, unsigned int desc_size)
 {
 	struct dma_extended_desc *ep = (struct dma_extended_desc *)head;
+	dma_addr_t dma_addr;
 	int i;
 
 	pr_info("Extended %s descriptor ring:\n", rx ? "RX" : "TX");
 
 	for (i = 0; i < size; i++) {
 		u64 x;
+		dma_addr = dma_rx_phy + i * sizeof(*ep);
 
 		x = *(u64 *)ep;
-		pr_info("%03d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
-			i, (unsigned int)virt_to_phys(ep),
+		pr_info("%03d [%pad]: 0x%x 0x%x 0x%x 0x%x\n",
+			i, &dma_addr,
 			(unsigned int)x, (unsigned int)(x >> 32),
 			ep->basic.des2, ep->basic.des3);
 		ep++;
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index b40b2e0667bb..7417db31402f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -78,7 +78,8 @@ struct stmmac_desc_ops {
 	/* get rx timestamp status */
 	int (*get_rx_timestamp_status)(void *desc, void *next_desc, u32 ats);
 	/* Display ring */
-	void (*display_ring)(void *head, unsigned int size, bool rx);
+	void (*display_ring)(void *head, unsigned int size, bool rx,
+			     dma_addr_t dma_rx_phy, unsigned int desc_size);
 	/* set MSS via context descriptor */
 	void (*set_mss)(struct dma_desc *p, unsigned int mss);
 	/* get descriptor skbuff address */
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index f083360e4ba6..98ef43f35802 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -269,19 +269,22 @@ static int ndesc_get_rx_timestamp_status(void *desc, void *next_desc, u32 ats)
 		return 1;
 }
 
-static void ndesc_display_ring(void *head, unsigned int size, bool rx)
+static void ndesc_display_ring(void *head, unsigned int size, bool rx,
+			       dma_addr_t dma_rx_phy, unsigned int desc_size)
 {
 	struct dma_desc *p = (struct dma_desc *)head;
+	dma_addr_t dma_addr;
 	int i;
 
 	pr_info("%s descriptor ring:\n", rx ? "RX" : "TX");
 
 	for (i = 0; i < size; i++) {
 		u64 x;
+		dma_addr = dma_rx_phy + i * sizeof(*p);
 
 		x = *(u64 *)p;
-		pr_info("%03d [0x%x]: 0x%x 0x%x 0x%x 0x%x",
-			i, (unsigned int)virt_to_phys(p),
+		pr_info("%03d [%pad]: 0x%x 0x%x 0x%x 0x%x",
+			i, &dma_addr,
 			(unsigned int)x, (unsigned int)(x >> 32),
 			p->des2, p->des3);
 		p++;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 12ed337a239b..730f2d71578c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1133,6 +1133,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 static void stmmac_display_rx_rings(struct stmmac_priv *priv)
 {
 	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	unsigned int desc_size;
 	void *head_rx;
 	u32 queue;
 
@@ -1142,19 +1143,24 @@ static void stmmac_display_rx_rings(struct stmmac_priv *priv)
 
 		pr_info("\tRX Queue %u rings\n", queue);
 
-		if (priv->extend_desc)
+		if (priv->extend_desc) {
 			head_rx = (void *)rx_q->dma_erx;
-		else
+			desc_size = sizeof(struct dma_extended_desc);
+		} else {
 			head_rx = (void *)rx_q->dma_rx;
+			desc_size = sizeof(struct dma_desc);
+		}
 
 		/* Display RX ring */
-		stmmac_display_ring(priv, head_rx, priv->dma_rx_size, true);
+		stmmac_display_ring(priv, head_rx, priv->dma_rx_size, true,
+				    rx_q->dma_rx_phy, desc_size);
 	}
 }
 
 static void stmmac_display_tx_rings(struct stmmac_priv *priv)
 {
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	unsigned int desc_size;
 	void *head_tx;
 	u32 queue;
 
@@ -1164,14 +1170,19 @@ static void stmmac_display_tx_rings(struct stmmac_priv *priv)
 
 		pr_info("\tTX Queue %d rings\n", queue);
 
-		if (priv->extend_desc)
+		if (priv->extend_desc) {
 			head_tx = (void *)tx_q->dma_etx;
-		else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+			desc_size = sizeof(struct dma_extended_desc);
+		} else if (tx_q->tbs & STMMAC_TBS_AVAIL) {
 			head_tx = (void *)tx_q->dma_entx;
-		else
+			desc_size = sizeof(struct dma_edesc);
+		} else {
 			head_tx = (void *)tx_q->dma_tx;
+			desc_size = sizeof(struct dma_desc);
+		}
 
-		stmmac_display_ring(priv, head_tx, priv->dma_tx_size, false);
+		stmmac_display_ring(priv, head_tx, priv->dma_tx_size, false,
+				    tx_q->dma_tx_phy, desc_size);
 	}
 }
 
@@ -3736,18 +3747,23 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	unsigned int count = 0, error = 0, len = 0;
 	int status = 0, coe = priv->hw->rx_csum;
 	unsigned int next_entry = rx_q->cur_rx;
+	unsigned int desc_size;
 	struct sk_buff *skb = NULL;
 
 	if (netif_msg_rx_status(priv)) {
 		void *rx_head;
 
 		netdev_dbg(priv->dev, "%s: descriptor ring:\n", __func__);
-		if (priv->extend_desc)
+		if (priv->extend_desc) {
 			rx_head = (void *)rx_q->dma_erx;
-		else
+			desc_size = sizeof(struct dma_extended_desc);
+		} else {
 			rx_head = (void *)rx_q->dma_rx;
+			desc_size = sizeof(struct dma_desc);
+		}
 
-		stmmac_display_ring(priv, rx_head, priv->dma_rx_size, true);
+		stmmac_display_ring(priv, rx_head, priv->dma_rx_size, true,
+				    rx_q->dma_rx_phy, desc_size);
 	}
 	while (count < limit) {
 		unsigned int buf1_len = 0, buf2_len = 0;
@@ -4315,24 +4331,27 @@ static int stmmac_set_mac_address(struct net_device *ndev, void *addr)
 static struct dentry *stmmac_fs_dir;
 
 static void sysfs_display_ring(void *head, int size, int extend_desc,
-			       struct seq_file *seq)
+			       struct seq_file *seq, dma_addr_t dma_phy_addr)
 {
 	int i;
 	struct dma_extended_desc *ep = (struct dma_extended_desc *)head;
 	struct dma_desc *p = (struct dma_desc *)head;
+	dma_addr_t dma_addr;
 
 	for (i = 0; i < size; i++) {
 		if (extend_desc) {
-			seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
-				   i, (unsigned int)virt_to_phys(ep),
+			dma_addr = dma_phy_addr + i * sizeof(*ep);
+			seq_printf(seq, "%d [%pad]: 0x%x 0x%x 0x%x 0x%x\n",
+				   i, &dma_addr,
 				   le32_to_cpu(ep->basic.des0),
 				   le32_to_cpu(ep->basic.des1),
 				   le32_to_cpu(ep->basic.des2),
 				   le32_to_cpu(ep->basic.des3));
 			ep++;
 		} else {
-			seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
-				   i, (unsigned int)virt_to_phys(p),
+			dma_addr = dma_phy_addr + i * sizeof(*p);
+			seq_printf(seq, "%d [%pad]: 0x%x 0x%x 0x%x 0x%x\n",
+				   i, &dma_addr,
 				   le32_to_cpu(p->des0), le32_to_cpu(p->des1),
 				   le32_to_cpu(p->des2), le32_to_cpu(p->des3));
 			p++;
@@ -4360,11 +4379,11 @@ static int stmmac_rings_status_show(struct seq_file *seq, void *v)
 		if (priv->extend_desc) {
 			seq_printf(seq, "Extended descriptor ring:\n");
 			sysfs_display_ring((void *)rx_q->dma_erx,
-					   priv->dma_rx_size, 1, seq);
+					   priv->dma_rx_size, 1, seq, rx_q->dma_rx_phy);
 		} else {
 			seq_printf(seq, "Descriptor ring:\n");
 			sysfs_display_ring((void *)rx_q->dma_rx,
-					   priv->dma_rx_size, 0, seq);
+					   priv->dma_rx_size, 0, seq, rx_q->dma_rx_phy);
 		}
 	}
 
@@ -4376,11 +4395,11 @@ static int stmmac_rings_status_show(struct seq_file *seq, void *v)
 		if (priv->extend_desc) {
 			seq_printf(seq, "Extended descriptor ring:\n");
 			sysfs_display_ring((void *)tx_q->dma_etx,
-					   priv->dma_tx_size, 1, seq);
+					   priv->dma_tx_size, 1, seq, tx_q->dma_tx_phy);
 		} else if (!(tx_q->tbs & STMMAC_TBS_AVAIL)) {
 			seq_printf(seq, "Descriptor ring:\n");
 			sysfs_display_ring((void *)tx_q->dma_tx,
-					   priv->dma_tx_size, 0, seq);
+					   priv->dma_tx_size, 0, seq, tx_q->dma_tx_phy);
 		}
 	}
 

From 396e13e11577b614db77db0bbb6fca935b94eb1b Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang@nxp.com>
Date: Thu, 25 Feb 2021 17:01:13 +0800
Subject: [PATCH 0057/1820] net: stmmac: fix wrongly set buffer2 valid when sph
 unsupport

In current driver, buffer2 available only when hardware supports split
header. Wrongly set buffer2 valid in stmmac_rx_refill when refill buffer
address. You can see that desc3 is 0x81000000 after initialization, but
turn out to be 0x83000000 after refill.

Fixes: 67afd6d1cfdf ("net: stmmac: Add Split Header support and enable it in XGMAC cores")
Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c   | 9 +++++++--
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c | 2 +-
 drivers/net/ethernet/stmicro/stmmac/hwif.h           | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c    | 8 ++++++--
 4 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index ee87811b0ca5..cbf4429fb1d2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -533,10 +533,15 @@ static void dwmac4_get_rx_header_len(struct dma_desc *p, unsigned int *len)
 	*len = le32_to_cpu(p->des2) & RDES2_HL;
 }
 
-static void dwmac4_set_sec_addr(struct dma_desc *p, dma_addr_t addr)
+static void dwmac4_set_sec_addr(struct dma_desc *p, dma_addr_t addr, bool buf2_valid)
 {
 	p->des2 = cpu_to_le32(lower_32_bits(addr));
-	p->des3 = cpu_to_le32(upper_32_bits(addr) | RDES3_BUFFER2_VALID_ADDR);
+	p->des3 = cpu_to_le32(upper_32_bits(addr));
+
+	if (buf2_valid)
+		p->des3 |= cpu_to_le32(RDES3_BUFFER2_VALID_ADDR);
+	else
+		p->des3 &= cpu_to_le32(~RDES3_BUFFER2_VALID_ADDR);
 }
 
 static void dwmac4_set_tbs(struct dma_edesc *p, u32 sec, u32 nsec)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
index 0aaf19ab5672..ccfb0102dde4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -292,7 +292,7 @@ static void dwxgmac2_get_rx_header_len(struct dma_desc *p, unsigned int *len)
 		*len = le32_to_cpu(p->des2) & XGMAC_RDES2_HL;
 }
 
-static void dwxgmac2_set_sec_addr(struct dma_desc *p, dma_addr_t addr)
+static void dwxgmac2_set_sec_addr(struct dma_desc *p, dma_addr_t addr, bool is_valid)
 {
 	p->des2 = cpu_to_le32(lower_32_bits(addr));
 	p->des3 = cpu_to_le32(upper_32_bits(addr));
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 7417db31402f..979ac9fca23c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -92,7 +92,7 @@ struct stmmac_desc_ops {
 	int (*get_rx_hash)(struct dma_desc *p, u32 *hash,
 			   enum pkt_hash_types *type);
 	void (*get_rx_header_len)(struct dma_desc *p, unsigned int *len);
-	void (*set_sec_addr)(struct dma_desc *p, dma_addr_t addr);
+	void (*set_sec_addr)(struct dma_desc *p, dma_addr_t addr, bool buf2_valid);
 	void (*set_sarc)(struct dma_desc *p, u32 sarc_type);
 	void (*set_vlan_tag)(struct dma_desc *p, u16 tag, u16 inner_tag,
 			     u32 inner_type);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 730f2d71578c..cd7709da0969 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1314,9 +1314,10 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 			return -ENOMEM;
 
 		buf->sec_addr = page_pool_get_dma_addr(buf->sec_page);
-		stmmac_set_desc_sec_addr(priv, p, buf->sec_addr);
+		stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, true);
 	} else {
 		buf->sec_page = NULL;
+		stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, false);
 	}
 
 	buf->addr = page_pool_get_dma_addr(buf->page);
@@ -3659,7 +3660,10 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 					   DMA_FROM_DEVICE);
 
 		stmmac_set_desc_addr(priv, p, buf->addr);
-		stmmac_set_desc_sec_addr(priv, p, buf->sec_addr);
+		if (priv->sph)
+			stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, true);
+		else
+			stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, false);
 		stmmac_refill_desc3(priv, rx_q, p);
 
 		rx_q->rx_count_frames++;

From 9c63faaa931e443e7abbbee9de0169f1d4710546 Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang@nxp.com>
Date: Thu, 25 Feb 2021 17:01:14 +0800
Subject: [PATCH 0058/1820] net: stmmac: re-init rx buffers when mac resume
 back

During suspend/resume stress test, we found descriptor write back by DMA
could exhibit unusual behavior, e.g.:
	003 [0xc4310030]: 0x0 0x40 0x0 0xb5010040

We can see that desc3 write back is 0xb5010040, it is still ownd by DMA,
so application would not recycle this buffer. It will trigger fatal bus
error when DMA try to use this descriptor again. To fix this issue, we
should re-init all rx buffers when mac resume back.

Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 84 ++++++++++++++++++-
 1 file changed, 83 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index cd7709da0969..0eba44e9c1f8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1379,6 +1379,88 @@ static void stmmac_free_tx_buffer(struct stmmac_priv *priv, u32 queue, int i)
 	}
 }
 
+/**
+ * stmmac_reinit_rx_buffers - reinit the RX descriptor buffer.
+ * @priv: driver private structure
+ * Description: this function is called to re-allocate a receive buffer, perform
+ * the DMA mapping and init the descriptor.
+ */
+static void stmmac_reinit_rx_buffers(struct stmmac_priv *priv)
+{
+	u32 rx_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+	int i;
+
+	for (queue = 0; queue < rx_count; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		for (i = 0; i < priv->dma_rx_size; i++) {
+			struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
+
+			if (buf->page) {
+				page_pool_recycle_direct(rx_q->page_pool, buf->page);
+				buf->page = NULL;
+			}
+
+			if (priv->sph && buf->sec_page) {
+				page_pool_recycle_direct(rx_q->page_pool, buf->sec_page);
+				buf->sec_page = NULL;
+			}
+		}
+	}
+
+	for (queue = 0; queue < rx_count; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		for (i = 0; i < priv->dma_rx_size; i++) {
+			struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
+			struct dma_desc *p;
+
+			if (priv->extend_desc)
+				p = &((rx_q->dma_erx + i)->basic);
+			else
+				p = rx_q->dma_rx + i;
+
+			if (!buf->page) {
+				buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+				if (!buf->page)
+					goto err_reinit_rx_buffers;
+
+				buf->addr = page_pool_get_dma_addr(buf->page);
+			}
+
+			if (priv->sph && !buf->sec_page) {
+				buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool);
+				if (!buf->sec_page)
+					goto err_reinit_rx_buffers;
+
+				buf->sec_addr = page_pool_get_dma_addr(buf->sec_page);
+			}
+
+			stmmac_set_desc_addr(priv, p, buf->addr);
+			if (priv->sph)
+				stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, true);
+			else
+				stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, false);
+			if (priv->dma_buf_sz == BUF_SIZE_16KiB)
+				stmmac_init_desc3(priv, p);
+		}
+	}
+
+	return;
+
+err_reinit_rx_buffers:
+	do {
+		while (--i >= 0)
+			stmmac_free_rx_buffer(priv, queue, i);
+
+		if (queue == 0)
+			break;
+
+		i = priv->dma_rx_size;
+	} while (queue-- > 0);
+}
+
 /**
  * init_dma_rx_desc_rings - init the RX descriptor rings
  * @dev: net device structure
@@ -5343,7 +5425,7 @@ int stmmac_resume(struct device *dev)
 	mutex_lock(&priv->lock);
 
 	stmmac_reset_queues_param(priv);
-
+	stmmac_reinit_rx_buffers(priv);
 	stmmac_free_tx_skbufs(priv);
 	stmmac_clear_descriptors(priv);
 

From 907310ceb27ee4259bedb6c1257f5d05ee44f3ce Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 25 Feb 2021 15:38:31 +0100
Subject: [PATCH 0059/1820] net: mscc: ocelot: select NET_DEVLINK

Without this option, the driver fails to link:

ld.lld: error: undefined symbol: devlink_sb_register
>>> referenced by ocelot_devlink.c
>>>               net/ethernet/mscc/ocelot_devlink.o:(ocelot_devlink_sb_register) in archive drivers/built-in.a
>>> referenced by ocelot_devlink.c
>>>               net/ethernet/mscc/ocelot_devlink.o:(ocelot_devlink_sb_register) in archive drivers/built-in.a

Fixes: f59fd9cab730 ("net: mscc: ocelot: configure watermarks using devlink-sb")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20210225143910.3964364-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mscc/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mscc/Kconfig b/drivers/net/ethernet/mscc/Kconfig
index c0ede0ca7115..05cb040c2677 100644
--- a/drivers/net/ethernet/mscc/Kconfig
+++ b/drivers/net/ethernet/mscc/Kconfig
@@ -13,6 +13,7 @@ if NET_VENDOR_MICROSEMI
 
 # Users should depend on NET_SWITCHDEV, HAS_IOMEM
 config MSCC_OCELOT_SWITCH_LIB
+	select NET_DEVLINK
 	select REGMAP_MMIO
 	select PACKING
 	select PHYLIB

From 01c2c1ad8f45e0c191bfd961dc41cd77df0d7a2f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 25 Feb 2021 15:38:32 +0100
Subject: [PATCH 0060/1820] net: dsa: tag_ocelot_8021q: fix driver dependency

When the ocelot driver code is in a library, the dsa tag
code cannot be built-in:

ld.lld: error: undefined symbol: ocelot_can_inject
>>> referenced by tag_ocelot_8021q.c
>>>               dsa/tag_ocelot_8021q.o:(ocelot_xmit) in archive net/built-in.a

ld.lld: error: undefined symbol: ocelot_port_inject_frame
>>> referenced by tag_ocelot_8021q.c
>>>               dsa/tag_ocelot_8021q.o:(ocelot_xmit) in archive net/built-in.a

Building the tag support only really makes sense for compile-testing
when the driver is available, so add a Kconfig dependency that prevents
the broken configuration while allowing COMPILE_TEST alternative when
MSCC_OCELOT_SWITCH_LIB is disabled entirely.  This case is handled
through the #ifdef check in include/soc/mscc/ocelot.h.

Fixes: 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20210225143910.3964364-2-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/dsa/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 3589224c8da9..58b8fc82cd3c 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -118,6 +118,8 @@ config NET_DSA_TAG_OCELOT
 
 config NET_DSA_TAG_OCELOT_8021Q
 	tristate "Tag driver for Ocelot family of switches, using VLAN"
+	depends on MSCC_OCELOT_SWITCH_LIB || \
+	          (MSCC_OCELOT_SWITCH_LIB=n && COMPILE_TEST)
 	select NET_DSA_TAG_8021Q
 	help
 	  Say Y or M if you want to enable support for tagging frames with a

From 63c75c053b4160f7b90a418dcc4e5bcfac2fb6fc Mon Sep 17 00:00:00 2001
From: DENG Qingfang <dqfext@gmail.com>
Date: Fri, 26 Feb 2021 14:32:26 +0800
Subject: [PATCH 0061/1820] net: dsa: mt7530: don't build GPIO support if
 !GPIOLIB

The new GPIO support may be optional at runtime, but it requires
building against gpiolib:

ERROR: modpost: "gpiochip_get_data" [drivers/net/dsa/mt7530.ko]
undefined!
ERROR: modpost: "devm_gpiochip_add_data_with_key"
[drivers/net/dsa/mt7530.ko] undefined!

Add #ifdef to exclude GPIO support if GPIOLIB is not enabled.

Fixes: 429a0edeefd8 ("net: dsa: mt7530: MT7530 optional GPIO support")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: DENG Qingfang <dqfext@gmail.com>
Link: https://lore.kernel.org/r/20210226063226.8474-1-dqfext@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mt7530.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index c17de2bcf2fe..f06f5fa2f898 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -1624,6 +1624,7 @@ mtk_get_tag_protocol(struct dsa_switch *ds, int port,
 	}
 }
 
+#ifdef CONFIG_GPIOLIB
 static inline u32
 mt7530_gpio_to_bit(unsigned int offset)
 {
@@ -1726,6 +1727,7 @@ mt7530_setup_gpio(struct mt7530_priv *priv)
 
 	return devm_gpiochip_add_data(dev, gc, priv);
 }
+#endif /* CONFIG_GPIOLIB */
 
 static int
 mt7530_setup(struct dsa_switch *ds)
@@ -1868,11 +1870,13 @@ mt7530_setup(struct dsa_switch *ds)
 		}
 	}
 
+#ifdef CONFIG_GPIOLIB
 	if (of_property_read_bool(priv->dev->of_node, "gpio-controller")) {
 		ret = mt7530_setup_gpio(priv);
 		if (ret)
 			return ret;
 	}
+#endif /* CONFIG_GPIOLIB */
 
 	mt7530_setup_port5(ds, interface);
 

From 7f654157f0aefba04cd7f6297351c87b76b47b89 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 25 Feb 2021 15:57:27 +0100
Subject: [PATCH 0062/1820] net: phy: make mdio_bus_phy_suspend/resume as
 __maybe_unused

When CONFIG_PM_SLEEP is disabled, the compiler warns about unused
functions:

drivers/net/phy/phy_device.c:273:12: error: unused function 'mdio_bus_phy_suspend' [-Werror,-Wunused-function]
static int mdio_bus_phy_suspend(struct device *dev)
drivers/net/phy/phy_device.c:293:12: error: unused function 'mdio_bus_phy_resume' [-Werror,-Wunused-function]
static int mdio_bus_phy_resume(struct device *dev)

The logic is intentional, so just mark these two as __maybe_unused
and remove the incorrect #ifdef.

Fixes: 4c0d2e96ba05 ("net: phy: consider that suspend2ram may cut off PHY power")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20210225145748.404410-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index ce495473cd5d..cc38e326405a 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -230,7 +230,6 @@ static struct phy_driver genphy_driver;
 static LIST_HEAD(phy_fixup_list);
 static DEFINE_MUTEX(phy_fixup_lock);
 
-#ifdef CONFIG_PM
 static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
 {
 	struct device_driver *drv = phydev->mdio.dev.driver;
@@ -270,7 +269,7 @@ out:
 	return !phydev->suspended;
 }
 
-static int mdio_bus_phy_suspend(struct device *dev)
+static __maybe_unused int mdio_bus_phy_suspend(struct device *dev)
 {
 	struct phy_device *phydev = to_phy_device(dev);
 
@@ -290,7 +289,7 @@ static int mdio_bus_phy_suspend(struct device *dev)
 	return phy_suspend(phydev);
 }
 
-static int mdio_bus_phy_resume(struct device *dev)
+static __maybe_unused int mdio_bus_phy_resume(struct device *dev)
 {
 	struct phy_device *phydev = to_phy_device(dev);
 	int ret;
@@ -316,7 +315,6 @@ no_resume:
 
 static SIMPLE_DEV_PM_OPS(mdio_bus_phy_pm_ops, mdio_bus_phy_suspend,
 			 mdio_bus_phy_resume);
-#endif /* CONFIG_PM */
 
 /**
  * phy_register_fixup - creates a new phy_fixup and adds it to the list

From 6a4d7234ae9a3bb31181f348ade9bbdb55aeb5c5 Mon Sep 17 00:00:00 2001
From: Heiko Thiery <heiko.thiery@gmail.com>
Date: Thu, 25 Feb 2021 22:15:16 +0100
Subject: [PATCH 0063/1820] net: fec: ptp: avoid register access when ipg clock
 is disabled

When accessing the timecounter register on an i.MX8MQ the kernel hangs.
This is only the case when the interface is down. This can be reproduced
by reading with 'phc_ctrl eth0 get'.

Like described in the change in 91c0d987a9788dcc5fe26baafd73bf9242b68900
the igp clock is disabled when the interface is down and leads to a
system hang.

So we check if the ptp clock status before reading the timecounter
register.

Signed-off-by: Heiko Thiery <heiko.thiery@gmail.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Link: https://lore.kernel.org/r/20210225211514.9115-1-heiko.thiery@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_ptp.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 2e344aada4c6..1753807cbf97 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -377,9 +377,16 @@ static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
 	u64 ns;
 	unsigned long flags;
 
+	mutex_lock(&adapter->ptp_clk_mutex);
+	/* Check the ptp clock */
+	if (!adapter->ptp_clk_on) {
+		mutex_unlock(&adapter->ptp_clk_mutex);
+		return -EINVAL;
+	}
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
 	ns = timecounter_read(&adapter->tc);
 	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+	mutex_unlock(&adapter->ptp_clk_mutex);
 
 	*ts = ns_to_timespec64(ns);
 

From 2107d45f17bedd7dbf4178462da0ac223835a2a7 Mon Sep 17 00:00:00 2001
From: Arjun Roy <arjunroy@google.com>
Date: Thu, 25 Feb 2021 15:26:28 -0800
Subject: [PATCH 0064/1820] tcp: Fix sign comparison bug in
 getsockopt(TCP_ZEROCOPY_RECEIVE)

getsockopt(TCP_ZEROCOPY_RECEIVE) has a bug where we read a
user-provided "len" field of type signed int, and then compare the
value to the result of an "offsetofend" operation, which is unsigned.

Negative values provided by the user will be promoted to large
positive numbers; thus checking that len < offsetofend() will return
false when the intention was that it return true.

Note that while len is originally checked for negative values earlier
on in do_tcp_getsockopt(), subsequent calls to get_user() re-read the
value from userspace which may have changed in the meantime.

Therefore, re-add the check for negative values after the call to
get_user in the handler code for TCP_ZEROCOPY_RECEIVE.

Fixes: c8856c051454 ("tcp-zerocopy: Return inq along with tcp receive zerocopy.")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Arjun Roy <arjunroy@google.com>
Link: https://lore.kernel.org/r/20210225232628.4033281-1-arjunroy.kdev@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a3422e42784e..dfb6f286c1de 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4143,7 +4143,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 
 		if (get_user(len, optlen))
 			return -EFAULT;
-		if (len < offsetofend(struct tcp_zerocopy_receive, length))
+		if (len < 0 ||
+		    len < offsetofend(struct tcp_zerocopy_receive, length))
 			return -EINVAL;
 		if (unlikely(len > sizeof(zc))) {
 			err = check_zeroed_user(optval + sizeof(zc),

From edcbf5137f093b5502f5f6b97cce3cbadbde27aa Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Thu, 25 Feb 2021 18:57:19 +0200
Subject: [PATCH 0065/1820] selftests: forwarding: Fix race condition in mirror
 installation

When mirroring to a gretap in hardware the device expects to be
programmed with the egress port and all the encapsulating headers. This
requires the driver to resolve the path the packet will take in the
software data path and program the device accordingly.

If the path cannot be resolved (in this case because of an unresolved
neighbor), then mirror installation fails until the path is resolved.
This results in a race that causes the test to sometimes fail.

Fix this by setting the neighbor's state to permanent, so that it is
always valid.

Fixes: b5b029399fa6d ("selftests: forwarding: mirror_gre_bridge_1d_vlan: Add STP test")
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/forwarding/mirror_gre_bridge_1d_vlan.sh          | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
index 197e769c2ed1..f8cda822c1ce 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
@@ -86,11 +86,20 @@ test_ip6gretap()
 
 test_gretap_stp()
 {
+	# Sometimes after mirror installation, the neighbor's state is not valid.
+	# The reason is that there is no SW datapath activity related to the
+	# neighbor for the remote GRE address. Therefore whether the corresponding
+	# neighbor will be valid is a matter of luck, and the test is thus racy.
+	# Set the neighbor's state to permanent, so it would be always valid.
+	ip neigh replace 192.0.2.130 lladdr $(mac_get $h3) \
+		nud permanent dev br2
 	full_test_span_gre_stp gt4 $swp3.555 "mirror to gretap"
 }
 
 test_ip6gretap_stp()
 {
+	ip neigh replace 2001:db8:2::2 lladdr $(mac_get $h3) \
+		nud permanent dev br2
 	full_test_span_gre_stp gt6 $swp3.555 "mirror to ip6gretap"
 }
 

From ae9b24ddb69b4e31cda1b5e267a5a08a1db11717 Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Thu, 25 Feb 2021 18:57:20 +0200
Subject: [PATCH 0066/1820] mlxsw: spectrum_ethtool: Add an external speed to
 PTYS register

Currently, only external bits are added to the PTYS register, whereas
there is one external bit that is wrongly marked as internal, and so was
recently removed from the register.

Add that bit to the PTYS register again, as this bit is no longer
internal.

Its removal resulted in '100000baseLR4_ER4/Full' link mode no longer
being supported, causing a regression on some setups.

Fixes: 5bf01b571cf4 ("mlxsw: spectrum_ethtool: Remove internal speeds from PTYS register")
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reported-by: Eddie Shklaer <eddies@nvidia.com>
Tested-by: Eddie Shklaer <eddies@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h              | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c | 5 +++++
 drivers/net/ethernet/mellanox/mlxsw/switchx2.c         | 3 ++-
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 16e2df6ef2f4..c4adc7f740d3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -4430,6 +4430,7 @@ MLXSW_ITEM32(reg, ptys, ext_eth_proto_cap, 0x08, 0, 32);
 #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4		BIT(20)
 #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4		BIT(21)
 #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4		BIT(22)
+#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4	BIT(23)
 #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR		BIT(27)
 #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR		BIT(28)
 #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR		BIT(29)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
index bd7f873f6290..0bd64169bf81 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
@@ -1169,6 +1169,11 @@ static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = {
 		.mask_ethtool	= ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
 		.speed		= SPEED_100000,
 	},
+	{
+		.mask		= MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4,
+		.mask_ethtool	= ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
+		.speed		= SPEED_100000,
+	},
 };
 
 #define MLXSW_SP1_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp1_port_link_mode)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 40e2e79d4517..131b2a53d261 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -613,7 +613,8 @@ static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = {
 	{
 		.mask		= MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 |
 				  MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 |
-				  MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4,
+				  MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 |
+				  MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4,
 		.speed		= 100000,
 	},
 };

From dc860b88ce0a7ed9a048d5042cbb175daf60b657 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 25 Feb 2021 18:57:21 +0200
Subject: [PATCH 0067/1820] mlxsw: spectrum_router: Ignore routes using a
 deleted nexthop object

Routes are currently processed from a workqueue whereas nexthop objects
are processed in system call context. This can result in the driver not
finding a suitable nexthop group for a route and issuing a warning [1].

Fix this by ignoring such routes earlier in the process. The subsequent
deletion notification will be ignored as well.

[1]
 WARNING: CPU: 2 PID: 7754 at drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:4853 mlxsw_sp_router_fib_event_work+0x1112/0x1e00 [mlxsw_spectrum]
 [...]
 CPU: 2 PID: 7754 Comm: kworker/u8:0 Not tainted 5.11.0-rc6-cq-20210207-1 #16
 Hardware name: Mellanox Technologies Ltd. MSN2100/SA001390, BIOS 5.6.5 05/24/2018
 Workqueue: mlxsw_core_ordered mlxsw_sp_router_fib_event_work [mlxsw_spectrum]
 RIP: 0010:mlxsw_sp_router_fib_event_work+0x1112/0x1e00 [mlxsw_spectrum]

Fixes: cdd6cfc54c64 ("mlxsw: spectrum_router: Allow programming routes with nexthop objects")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reported-by: Alex Veber <alexve@nvidia.com>
Tested-by: Alex Veber <alexve@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 9ce90841f92d..eda99d82766a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -5951,6 +5951,10 @@ mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp,
 	if (mlxsw_sp->router->aborted)
 		return 0;
 
+	if (fen_info->fi->nh &&
+	    !mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, fen_info->fi->nh->id))
+		return 0;
+
 	fib_node = mlxsw_sp_fib_node_get(mlxsw_sp, fen_info->tb_id,
 					 &fen_info->dst, sizeof(fen_info->dst),
 					 fen_info->dst_len,
@@ -6601,6 +6605,9 @@ static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp,
 	if (mlxsw_sp_fib6_rt_should_ignore(rt))
 		return 0;
 
+	if (rt->nh && !mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, rt->nh->id))
+		return 0;
+
 	fib_node = mlxsw_sp_fib_node_get(mlxsw_sp, rt->fib6_table->tb6_id,
 					 &rt->fib6_dst.addr,
 					 sizeof(rt->fib6_dst.addr),

From d20cd745218cde1b268bef5282095ec6c95a3ea2 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Fri, 26 Feb 2021 04:43:09 -0500
Subject: [PATCH 0068/1820] bnxt_en: Fix race between firmware reset and driver
 remove.

The driver's error recovery reset sequence can take many seconds to
complete and only the critical sections are protected by rtnl_lock.
A recent change has introduced a regression in this sequence.

bnxt_remove_one() may be called while the recovery is in progress.
Normally, unregister_netdev() would cause bnxt_close_nic() to be
called and this would cause the error recovery to safely abort
with the BNXT_STATE_ABORT_ERR flag set in bnxt_close_nic().

Recently, we added bnxt_reinit_after_abort() to allow the user to
reopen the device after an aborted recovery.  This causes the
regression in the scenario described above because we would
attempt to re-open even after the netdev has been unregistered.

Fix it by checking the netdev reg_state in
bnxt_reinit_after_abort() and abort if it is unregistered.

Fixes: 6882c36cf82e ("bnxt_en: attempt to reinitialize after aborted reset")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a680fd9c68ea..c55189c7bb36 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9890,6 +9890,9 @@ static int bnxt_reinit_after_abort(struct bnxt *bp)
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 		return -EBUSY;
 
+	if (bp->dev->reg_state == NETREG_UNREGISTERED)
+		return -ENODEV;
+
 	rc = bnxt_fw_init_one(bp);
 	if (!rc) {
 		bnxt_clear_int_mode(bp);

From 20d7d1c5c9b11e9f538ed4a2289be106de970d3e Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Fri, 26 Feb 2021 04:43:10 -0500
Subject: [PATCH 0069/1820] bnxt_en: reliably allocate IRQ table on reset to
 avoid crash

The following trace excerpt corresponds with a NULL pointer dereference
of 'bp->irq_tbl' in bnxt_setup_inta() on an Aarch64 system after many
device resets:

    Unable to handle kernel NULL pointer dereference at ... 000000d
    ...
    pc : string+0x3c/0x80
    lr : vsnprintf+0x294/0x7e0
    sp : ffff00000f61ba70 pstate : 20000145
    x29: ffff00000f61ba70 x28: 000000000000000d
    x27: ffff0000009c8b5a x26: ffff00000f61bb80
    x25: ffff0000009c8b5a x24: 0000000000000012
    x23: 00000000ffffffe0 x22: ffff000008990428
    x21: ffff00000f61bb80 x20: 000000000000000d
    x19: 000000000000001f x18: 0000000000000000
    x17: 0000000000000000 x16: ffff800b6d0fb400
    x15: 0000000000000000 x14: ffff800b7fe31ae8
    x13: 00001ed16472c920 x12: ffff000008c6b1c9
    x11: ffff000008cf0580 x10: ffff00000f61bb80
    x9 : 00000000ffffffd8 x8 : 000000000000000c
    x7 : ffff800b684b8000 x6 : 0000000000000000
    x5 : 0000000000000065 x4 : 0000000000000001
    x3 : ffff0a00ffffff04 x2 : 000000000000001f
    x1 : 0000000000000000 x0 : 000000000000000d
    Call trace:
    string+0x3c/0x80
    vsnprintf+0x294/0x7e0
    snprintf+0x44/0x50
    __bnxt_open_nic+0x34c/0x928 [bnxt_en]
    bnxt_open+0xe8/0x238 [bnxt_en]
    __dev_open+0xbc/0x130
    __dev_change_flags+0x12c/0x168
    dev_change_flags+0x20/0x60
    ...

Ordinarily, a call to bnxt_setup_inta() (not in trace due to inlining)
would not be expected on a system supporting MSIX at all. However, if
bnxt_init_int_mode() does not end up being called after the call to
bnxt_clear_int_mode() in bnxt_fw_reset_close(), then the driver will
think that only INTA is supported and bp->irq_tbl will be NULL,
causing the above crash.

In the error recovery scenario, we call bnxt_clear_int_mode() in
bnxt_fw_reset_close() early in the sequence. Ordinarily, we will
call bnxt_init_int_mode() in bnxt_hwrm_if_change() after we
reestablish communication with the firmware after reset.  However,
if the sequence has to abort before we call bnxt_init_int_mode() and
if the user later attempts to re-open the device, then it will cause
the crash above.

We fix it in 2 ways:

1. Check for bp->irq_tbl in bnxt_setup_int_mode(). If it is NULL, call
bnxt_init_init_mode().

2. If we need to abort in bnxt_hwrm_if_change() and cannot complete
the error recovery sequence, set the BNXT_STATE_ABORT_ERR flag.  This
will cause more drastic recovery at the next attempt to re-open the
device, including a call to bnxt_init_int_mode().

Fixes: 3bc7d4a352ef ("bnxt_en: Add BNXT_STATE_IN_FW_RESET state.")
Reviewed-by: Scott Branden <scott.branden@broadcom.com>
Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c55189c7bb36..b53a0d87371a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8556,10 +8556,18 @@ static void bnxt_setup_inta(struct bnxt *bp)
 	bp->irq_tbl[0].handler = bnxt_inta;
 }
 
+static int bnxt_init_int_mode(struct bnxt *bp);
+
 static int bnxt_setup_int_mode(struct bnxt *bp)
 {
 	int rc;
 
+	if (!bp->irq_tbl) {
+		rc = bnxt_init_int_mode(bp);
+		if (rc || !bp->irq_tbl)
+			return rc ?: -ENODEV;
+	}
+
 	if (bp->flags & BNXT_FLAG_USING_MSIX)
 		bnxt_setup_msix(bp);
 	else
@@ -8744,7 +8752,7 @@ static int bnxt_init_inta(struct bnxt *bp)
 
 static int bnxt_init_int_mode(struct bnxt *bp)
 {
-	int rc = 0;
+	int rc = -ENODEV;
 
 	if (bp->flags & BNXT_FLAG_MSIX_CAP)
 		rc = bnxt_init_msix(bp);
@@ -9514,7 +9522,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 {
 	struct hwrm_func_drv_if_change_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_func_drv_if_change_input req = {0};
-	bool resc_reinit = false, fw_reset = false;
+	bool fw_reset = !bp->irq_tbl;
+	bool resc_reinit = false;
 	int rc, retry = 0;
 	u32 flags = 0;
 
@@ -9557,6 +9566,7 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state) && !fw_reset) {
 		netdev_err(bp->dev, "RESET_DONE not set during FW reset.\n");
+		set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
 		return -ENODEV;
 	}
 	if (resc_reinit || fw_reset) {

From 7bf168c8fe8c6166b5dc10005fe7f250164da0ad Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Fri, 26 Feb 2021 16:26:01 -0800
Subject: [PATCH 0070/1820] drm/msm: Fix speed-bin support not to access
 outside valid memory

When running the latest kernel on an sc7180 with KASAN I got this
splat:
  BUG: KASAN: slab-out-of-bounds in a6xx_gpu_init+0x618/0x644
  Read of size 4 at addr ffffff8088f36100 by task kworker/7:1/58
  CPU: 7 PID: 58 Comm: kworker/7:1 Not tainted 5.11.0+ #3
  Hardware name: Google Lazor (rev1 - 2) with LTE (DT)
  Workqueue: events deferred_probe_work_func
  Call trace:
   dump_backtrace+0x0/0x3a8
   show_stack+0x24/0x30
   dump_stack+0x174/0x1e0
   print_address_description+0x70/0x2e4
   kasan_report+0x178/0x1bc
   __asan_report_load4_noabort+0x44/0x50
   a6xx_gpu_init+0x618/0x644
   adreno_bind+0x26c/0x438

This is because the speed bin is defined like this:
  gpu_speed_bin: gpu_speed_bin@1d2 {
    reg = <0x1d2 0x2>;
    bits = <5 8>;
  };

As you can see the "length" is 2 bytes. That means that the nvmem
subsystem allocates only 2 bytes. The GPU code, however, was casting
the pointer allocated by nvmem to a (u32 *) and dereferencing. That's
not so good.

Let's fix this to just use the nvmem_cell_read_u16() accessor function
which simplifies things and also gets rid of the splat.

Let's also put an explicit conversion from little endian in place just
to make things clear. The nvmem subsystem today is assuming little
endian and this makes it clear. Specifically, the way the above sc7180
cell is interpreted:

NVMEM:
 +--------+--------+--------+--------+--------+
 | ...... | 0x1d3  | 0x1d2  | ...... | 0x000  |
 +--------+--------+--------+--------+--------+
              ^       ^
             msb     lsb

You can see that the least significant data is at the lower address
which is little endian.

NOTE: someone who is truly paying attention might wonder about me
picking the "u16" version of this accessor instead of the "u8" (since
the value is 8 bits big) or the u32 version (just for fun). At the
moment you need to pick the accessor that exactly matches the length
the cell was specified as in the device tree. Hopefully future
patches to the nvmem subsystem will fix this.

Fixes: fe7952c629da ("drm/msm: Add speed-bin support to a618 gpu")
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 31 +++++++--------------------
 1 file changed, 8 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 064b7face504..690409ca8a18 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1401,35 +1401,20 @@ static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
 		u32 revn)
 {
 	struct opp_table *opp_table;
-	struct nvmem_cell *cell;
 	u32 supp_hw = UINT_MAX;
-	void *buf;
+	u16 speedbin;
+	int ret;
 
-	cell = nvmem_cell_get(dev, "speed_bin");
-	/*
-	 * -ENOENT means that the platform doesn't support speedbin which is
-	 * fine
-	 */
-	if (PTR_ERR(cell) == -ENOENT)
-		return 0;
-	else if (IS_ERR(cell)) {
+	ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin);
+	if (ret) {
 		DRM_DEV_ERROR(dev,
-				"failed to read speed-bin. Some OPPs may not be supported by hardware");
+			      "failed to read speed-bin (%d). Some OPPs may not be supported by hardware",
+			      ret);
 		goto done;
 	}
+	speedbin = le16_to_cpu(speedbin);
 
-	buf = nvmem_cell_read(cell, NULL);
-	if (IS_ERR(buf)) {
-		nvmem_cell_put(cell);
-		DRM_DEV_ERROR(dev,
-				"failed to read speed-bin. Some OPPs may not be supported by hardware");
-		goto done;
-	}
-
-	supp_hw = fuse_to_supp_hw(dev, revn, *((u32 *) buf));
-
-	kfree(buf);
-	nvmem_cell_put(cell);
+	supp_hw = fuse_to_supp_hw(dev, revn, speedbin);
 
 done:
 	opp_table = dev_pm_opp_set_supported_hw(dev, &supp_hw, 1);

From fae6f62e6a580b663ecf42c2120a0898deae9137 Mon Sep 17 00:00:00 2001
From: William Breathitt Gray <vilhelm.gray@gmail.com>
Date: Fri, 26 Feb 2021 10:29:31 +0900
Subject: [PATCH 0071/1820] counter: stm32-timer-cnt: Report count function
 when SLAVE_MODE_DISABLED

When in SLAVE_MODE_DISABLED mode, the count still increases if the
counter is enabled because an internal clock is used. This patch fixes
the stm32_count_function_get() and stm32_count_function_set() functions
to properly handle this behavior.

Fixes: ad29937e206f ("counter: Add STM32 Timer quadrature encoder")
Cc: Fabrice Gasnier <fabrice.gasnier@st.com>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: William Breathitt Gray <vilhelm.gray@gmail.com>
Reviewed-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Link: https://lore.kernel.org/r/20210226012931.161429-1-vilhelm.gray@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/counter/stm32-timer-cnt.c | 39 ++++++++++++++++++++-----------
 1 file changed, 25 insertions(+), 14 deletions(-)

diff --git a/drivers/counter/stm32-timer-cnt.c b/drivers/counter/stm32-timer-cnt.c
index ef2a974a2f10..cd50dc12bd02 100644
--- a/drivers/counter/stm32-timer-cnt.c
+++ b/drivers/counter/stm32-timer-cnt.c
@@ -44,13 +44,14 @@ struct stm32_timer_cnt {
  * @STM32_COUNT_ENCODER_MODE_3: counts on both TI1FP1 and TI2FP2 edges
  */
 enum stm32_count_function {
-	STM32_COUNT_SLAVE_MODE_DISABLED = -1,
+	STM32_COUNT_SLAVE_MODE_DISABLED,
 	STM32_COUNT_ENCODER_MODE_1,
 	STM32_COUNT_ENCODER_MODE_2,
 	STM32_COUNT_ENCODER_MODE_3,
 };
 
 static enum counter_count_function stm32_count_functions[] = {
+	[STM32_COUNT_SLAVE_MODE_DISABLED] = COUNTER_COUNT_FUNCTION_INCREASE,
 	[STM32_COUNT_ENCODER_MODE_1] = COUNTER_COUNT_FUNCTION_QUADRATURE_X2_A,
 	[STM32_COUNT_ENCODER_MODE_2] = COUNTER_COUNT_FUNCTION_QUADRATURE_X2_B,
 	[STM32_COUNT_ENCODER_MODE_3] = COUNTER_COUNT_FUNCTION_QUADRATURE_X4,
@@ -90,6 +91,9 @@ static int stm32_count_function_get(struct counter_device *counter,
 	regmap_read(priv->regmap, TIM_SMCR, &smcr);
 
 	switch (smcr & TIM_SMCR_SMS) {
+	case 0:
+		*function = STM32_COUNT_SLAVE_MODE_DISABLED;
+		return 0;
 	case 1:
 		*function = STM32_COUNT_ENCODER_MODE_1;
 		return 0;
@@ -99,9 +103,9 @@ static int stm32_count_function_get(struct counter_device *counter,
 	case 3:
 		*function = STM32_COUNT_ENCODER_MODE_3;
 		return 0;
+	default:
+		return -EINVAL;
 	}
-
-	return -EINVAL;
 }
 
 static int stm32_count_function_set(struct counter_device *counter,
@@ -112,6 +116,9 @@ static int stm32_count_function_set(struct counter_device *counter,
 	u32 cr1, sms;
 
 	switch (function) {
+	case STM32_COUNT_SLAVE_MODE_DISABLED:
+		sms = 0;
+		break;
 	case STM32_COUNT_ENCODER_MODE_1:
 		sms = 1;
 		break;
@@ -122,8 +129,7 @@ static int stm32_count_function_set(struct counter_device *counter,
 		sms = 3;
 		break;
 	default:
-		sms = 0;
-		break;
+		return -EINVAL;
 	}
 
 	/* Store enable status */
@@ -274,31 +280,36 @@ static int stm32_action_get(struct counter_device *counter,
 	size_t function;
 	int err;
 
-	/* Default action mode (e.g. STM32_COUNT_SLAVE_MODE_DISABLED) */
-	*action = STM32_SYNAPSE_ACTION_NONE;
-
 	err = stm32_count_function_get(counter, count, &function);
 	if (err)
-		return 0;
+		return err;
 
 	switch (function) {
+	case STM32_COUNT_SLAVE_MODE_DISABLED:
+		/* counts on internal clock when CEN=1 */
+		*action = STM32_SYNAPSE_ACTION_NONE;
+		return 0;
 	case STM32_COUNT_ENCODER_MODE_1:
 		/* counts up/down on TI1FP1 edge depending on TI2FP2 level */
 		if (synapse->signal->id == count->synapses[0].signal->id)
 			*action = STM32_SYNAPSE_ACTION_BOTH_EDGES;
-		break;
+		else
+			*action = STM32_SYNAPSE_ACTION_NONE;
+		return 0;
 	case STM32_COUNT_ENCODER_MODE_2:
 		/* counts up/down on TI2FP2 edge depending on TI1FP1 level */
 		if (synapse->signal->id == count->synapses[1].signal->id)
 			*action = STM32_SYNAPSE_ACTION_BOTH_EDGES;
-		break;
+		else
+			*action = STM32_SYNAPSE_ACTION_NONE;
+		return 0;
 	case STM32_COUNT_ENCODER_MODE_3:
 		/* counts up/down on both TI1FP1 and TI2FP2 edges */
 		*action = STM32_SYNAPSE_ACTION_BOTH_EDGES;
-		break;
+		return 0;
+	default:
+		return -EINVAL;
 	}
-
-	return 0;
 }
 
 static const struct counter_ops stm32_timer_cnt_ops = {

From c33cb0020ee6dd96cc9976d6085a7d8422f6dbed Mon Sep 17 00:00:00 2001
From: "Dmitry V. Levin" <ldv@altlinux.org>
Date: Mon, 22 Feb 2021 08:00:00 +0000
Subject: [PATCH 0072/1820] uapi: nfnetlink_cthelper.h: fix userspace
 compilation error

Apparently, <linux/netfilter/nfnetlink_cthelper.h> and
<linux/netfilter/nfnetlink_acct.h> could not be included into the same
compilation unit because of a cut-and-paste typo in the former header.

Fixes: 12f7a505331e6 ("netfilter: add user-space connection tracking helper infrastructure")
Cc: <stable@vger.kernel.org> # v3.6
Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nfnetlink_cthelper.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/netfilter/nfnetlink_cthelper.h b/include/uapi/linux/netfilter/nfnetlink_cthelper.h
index a13137afc429..70af02092d16 100644
--- a/include/uapi/linux/netfilter/nfnetlink_cthelper.h
+++ b/include/uapi/linux/netfilter/nfnetlink_cthelper.h
@@ -5,7 +5,7 @@
 #define NFCT_HELPER_STATUS_DISABLED	0
 #define NFCT_HELPER_STATUS_ENABLED	1
 
-enum nfnl_acct_msg_types {
+enum nfnl_cthelper_msg_types {
 	NFNL_MSG_CTHELPER_NEW,
 	NFNL_MSG_CTHELPER_GET,
 	NFNL_MSG_CTHELPER_DEL,

From c57ea2d7d81fbaa72c7d0ffbff61ade1039f4a0c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Klemen=20Ko=C5=A1ir?= <klemen.kosir@kream.io>
Date: Sat, 20 Feb 2021 18:29:26 +0900
Subject: [PATCH 0073/1820] netfilter: conntrack: Remove a double space in a
 log message
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Removed an extra space in a log message and an extra blank line in code.

Signed-off-by: Klemen Košir <klemen.kosir@kream.io>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_helper.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 118f415928ae..b055187235f8 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -219,7 +219,7 @@ nf_ct_lookup_helper(struct nf_conn *ct, struct net *net)
 			return NULL;
 		pr_info("nf_conntrack: default automatic helper assignment "
 			"has been turned off for security reasons and CT-based "
-			" firewall rule not found. Use the iptables CT target "
+			"firewall rule not found. Use the iptables CT target "
 			"to attach helpers instead.\n");
 		net->ct.auto_assign_helper_warned = 1;
 		return NULL;
@@ -228,7 +228,6 @@ nf_ct_lookup_helper(struct nf_conn *ct, struct net *net)
 	return __nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
 }
 
-
 int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
 			      gfp_t flags)
 {

From 03a3ca37e4c6478e3a84f04c8429dd5889e107fd Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 24 Feb 2021 17:23:19 +0100
Subject: [PATCH 0074/1820] netfilter: nf_nat: undo erroneous tcp edemux lookup

Under extremely rare conditions TCP early demux will retrieve the wrong
socket.

1. local machine establishes a connection to a remote server, S, on port
   p.

   This gives:
   laddr:lport -> S:p
   ... both in tcp and conntrack.

2. local machine establishes a connection to host H, on port p2.
   2a. TCP stack choses same laddr:lport, so we have
   laddr:lport -> H:p2 from TCP point of view.
   2b). There is a destination NAT rewrite in place, translating
        H:p2 to S:p.  This results in following conntrack entries:

   I)  laddr:lport -> S:p  (origin)  S:p -> laddr:lport (reply)
   II) laddr:lport -> H:p2 (origin)  S:p -> laddr:lport2 (reply)

   NAT engine has rewritten laddr:lport to laddr:lport2 to map
   the reply packet to the correct origin.

   When server sends SYN/ACK to laddr:lport2, the PREROUTING hook
   will undo-the SNAT transformation, rewriting IP header to
   S:p -> laddr:lport

   This causes TCP early demux to associate the skb with the TCP socket
   of the first connection.

   The INPUT hook will then reverse the DNAT transformation, rewriting
   the IP header to H:p2 -> laddr:lport.

Because packet ends up with the wrong socket, the new connection
never completes: originator stays in SYN_SENT and conntrack entry
remains in SYN_RECV until timeout, and responder retransmits SYN/ACK
until it gives up.

To resolve this, orphan the skb after the input rewrite:
Because the source IP address changed, the socket must be incorrect.
We can't move the DNAT undo to prerouting due to backwards
compatibility, doing so will make iptables/nftables rules to no longer
match the way they did.

After orphan, the packet will be handed to the next protocol layer
(tcp, udp, ...) and that will repeat the socket lookup just like as if
early demux was disabled.

Fixes: 41063e9dd1195 ("ipv4: Early TCP socket demux.")
Closes: https://bugzilla.netfilter.org/show_bug.cgi?id=1427
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_nat_proto.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index e87b6bd6b3cd..4731d21fc3ad 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -646,8 +646,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
 }
 
 static unsigned int
-nf_nat_ipv4_in(void *priv, struct sk_buff *skb,
-	       const struct nf_hook_state *state)
+nf_nat_ipv4_pre_routing(void *priv, struct sk_buff *skb,
+			const struct nf_hook_state *state)
 {
 	unsigned int ret;
 	__be32 daddr = ip_hdr(skb)->daddr;
@@ -659,6 +659,23 @@ nf_nat_ipv4_in(void *priv, struct sk_buff *skb,
 	return ret;
 }
 
+static unsigned int
+nf_nat_ipv4_local_in(void *priv, struct sk_buff *skb,
+		     const struct nf_hook_state *state)
+{
+	__be32 saddr = ip_hdr(skb)->saddr;
+	struct sock *sk = skb->sk;
+	unsigned int ret;
+
+	ret = nf_nat_ipv4_fn(priv, skb, state);
+
+	if (ret == NF_ACCEPT && sk && saddr != ip_hdr(skb)->saddr &&
+	    !inet_sk_transparent(sk))
+		skb_orphan(skb); /* TCP edemux obtained wrong socket */
+
+	return ret;
+}
+
 static unsigned int
 nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
 		const struct nf_hook_state *state)
@@ -736,7 +753,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
 static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv4_in,
+		.hook		= nf_nat_ipv4_pre_routing,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_PRE_ROUTING,
 		.priority	= NF_IP_PRI_NAT_DST,
@@ -757,7 +774,7 @@ static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv4_fn,
+		.hook		= nf_nat_ipv4_local_in,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_LOCAL_IN,
 		.priority	= NF_IP_PRI_NAT_SRC,

From 07b5a76e18925a595bfef44531dbf2f397bb5507 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 24 Feb 2021 17:23:20 +0100
Subject: [PATCH 0075/1820] netfilter: conntrack: avoid misleading 'invalid' in
 log message

The packet is not flagged as invalid: conntrack will accept it and
its associated with the conntrack entry.

This happens e.g. when receiving a retransmitted SYN in SYN_RECV state.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_proto_tcp.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 1d7e1c595546..ec23330687a5 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -982,8 +982,10 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
 					IP_CT_EXP_CHALLENGE_ACK;
 		}
 		spin_unlock_bh(&ct->lock);
-		nf_ct_l4proto_log_invalid(skb, ct, "invalid packet ignored in "
-					  "state %s ", tcp_conntrack_names[old_state]);
+		nf_ct_l4proto_log_invalid(skb, ct,
+					  "packet (index %d) in dir %d ignored, state %s",
+					  index, dir,
+					  tcp_conntrack_names[old_state]);
 		return NF_ACCEPT;
 	case TCP_CONNTRACK_MAX:
 		/* Special case for SYN proxy: when the SYN to the server or

From c2c16ccba2f55d527dd145a5d8c038694b3b343f Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 24 Feb 2021 17:23:21 +0100
Subject: [PATCH 0076/1820] selftests: netfilter: test nat port clash
 resolution interaction with tcp early demux

Convert Antonio Ojeas bug reproducer to a kselftest.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/netfilter/Makefile    |  2 +-
 .../selftests/netfilter/nf_nat_edemux.sh      | 99 +++++++++++++++++++
 2 files changed, 100 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/netfilter/nf_nat_edemux.sh

diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 3006a8e5b41a..3171069a6b46 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -4,7 +4,7 @@
 TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
 	conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
 	nft_concat_range.sh nft_conntrack_helper.sh \
-	nft_queue.sh nft_meta.sh \
+	nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
 	ipip-conntrack-mtu.sh
 
 LDLIBS = -lmnl
diff --git a/tools/testing/selftests/netfilter/nf_nat_edemux.sh b/tools/testing/selftests/netfilter/nf_nat_edemux.sh
new file mode 100755
index 000000000000..cfee3b65be0f
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nf_nat_edemux.sh
@@ -0,0 +1,99 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test NAT source port clash resolution
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+
+cleanup()
+{
+	ip netns del $ns1
+	ip netns del $ns2
+}
+
+iperf3 -v > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without iperf3"
+	exit $ksft_skip
+fi
+
+iptables --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without iptables"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+ip netns add "$ns1"
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not create net namespace $ns1"
+	exit $ksft_skip
+fi
+
+trap cleanup EXIT
+
+ip netns add $ns2
+
+# Connect the namespaces using a veth pair
+ip link add name veth2 type veth peer name veth1
+ip link set netns $ns1 dev veth1
+ip link set netns $ns2 dev veth2
+
+ip netns exec $ns1 ip link set up dev lo
+ip netns exec $ns1 ip link set up dev veth1
+ip netns exec $ns1 ip addr add 192.168.1.1/24 dev veth1
+
+ip netns exec $ns2 ip link set up dev lo
+ip netns exec $ns2 ip link set up dev veth2
+ip netns exec $ns2 ip addr add 192.168.1.2/24 dev veth2
+
+# Create a server in one namespace
+ip netns exec $ns1 iperf3 -s > /dev/null 2>&1 &
+iperfs=$!
+
+# Restrict source port to just one so we don't have to exhaust
+# all others.
+ip netns exec $ns2 sysctl -q net.ipv4.ip_local_port_range="10000 10000"
+
+# add a virtual IP using DNAT
+ip netns exec $ns2 iptables -t nat -A OUTPUT -d 10.96.0.1/32 -p tcp --dport 443 -j DNAT --to-destination 192.168.1.1:5201
+
+# ... and route it to the other namespace
+ip netns exec $ns2 ip route add 10.96.0.1 via 192.168.1.1
+
+sleep 1
+
+# add a persistent connection from the other namespace
+ip netns exec $ns2 nc -q 10 -w 10 192.168.1.1 5201 > /dev/null &
+
+sleep 1
+
+# ip daddr:dport will be rewritten to 192.168.1.1 5201
+# NAT must reallocate source port 10000 because
+# 192.168.1.2:10000 -> 192.168.1.1:5201 is already in use
+echo test | ip netns exec $ns2 nc -w 3 -q 3 10.96.0.1 443 >/dev/null
+ret=$?
+
+kill $iperfs
+
+# Check nc can connect to 10.96.0.1:443 (aka 192.168.1.1:5201).
+if [ $ret -eq 0 ]; then
+	echo "PASS: nc can connect via NAT'd address"
+else
+	echo "FAIL: nc cannot connect via NAT'd address"
+	exit 1
+fi
+
+exit 0

From 8e24edddad152b998b37a7f583175137ed2e04a5 Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs@virtuozzo.com>
Date: Sat, 27 Feb 2021 11:27:45 +0300
Subject: [PATCH 0077/1820] netfilter: x_tables: gpf inside xt_find_revision()

nested target/match_revfn() calls work with xt[NFPROTO_UNSPEC] lists
without taking xt[NFPROTO_UNSPEC].mutex. This can race with module unload
and cause host to crash:

general protection fault: 0000 [#1]
Modules linked in: ... [last unloaded: xt_cluster]
CPU: 0 PID: 542455 Comm: iptables
RIP: 0010:[<ffffffff8ffbd518>]  [<ffffffff8ffbd518>] strcmp+0x18/0x40
RDX: 0000000000000003 RSI: ffff9a5a5d9abe10 RDI: dead000000000111
R13: ffff9a5a5d9abe10 R14: ffff9a5a5d9abd8c R15: dead000000000100
(VvS: %R15 -- &xt_match,  %RDI -- &xt_match.name,
xt_cluster unregister match in xt[NFPROTO_UNSPEC].match list)
Call Trace:
 [<ffffffff902ccf44>] match_revfn+0x54/0xc0
 [<ffffffff902ccf9f>] match_revfn+0xaf/0xc0
 [<ffffffff902cd01e>] xt_find_revision+0x6e/0xf0
 [<ffffffffc05a5be0>] do_ipt_get_ctl+0x100/0x420 [ip_tables]
 [<ffffffff902cc6bf>] nf_getsockopt+0x4f/0x70
 [<ffffffff902dd99e>] ip_getsockopt+0xde/0x100
 [<ffffffff903039b5>] raw_getsockopt+0x25/0x50
 [<ffffffff9026c5da>] sock_common_getsockopt+0x1a/0x20
 [<ffffffff9026b89d>] SyS_getsockopt+0x7d/0xf0
 [<ffffffff903cbf92>] system_call_fastpath+0x25/0x2a

Fixes: 656caff20e1 ("netfilter 04/09: x_tables: fix match/target revision lookup")
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/x_tables.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index acce622582e3..bce6ca203d46 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -330,6 +330,7 @@ static int match_revfn(u8 af, const char *name, u8 revision, int *bestp)
 	const struct xt_match *m;
 	int have_rev = 0;
 
+	mutex_lock(&xt[af].mutex);
 	list_for_each_entry(m, &xt[af].match, list) {
 		if (strcmp(m->name, name) == 0) {
 			if (m->revision > *bestp)
@@ -338,6 +339,7 @@ static int match_revfn(u8 af, const char *name, u8 revision, int *bestp)
 				have_rev = 1;
 		}
 	}
+	mutex_unlock(&xt[af].mutex);
 
 	if (af != NFPROTO_UNSPEC && !have_rev)
 		return match_revfn(NFPROTO_UNSPEC, name, revision, bestp);
@@ -350,6 +352,7 @@ static int target_revfn(u8 af, const char *name, u8 revision, int *bestp)
 	const struct xt_target *t;
 	int have_rev = 0;
 
+	mutex_lock(&xt[af].mutex);
 	list_for_each_entry(t, &xt[af].target, list) {
 		if (strcmp(t->name, name) == 0) {
 			if (t->revision > *bestp)
@@ -358,6 +361,7 @@ static int target_revfn(u8 af, const char *name, u8 revision, int *bestp)
 				have_rev = 1;
 		}
 	}
+	mutex_unlock(&xt[af].mutex);
 
 	if (af != NFPROTO_UNSPEC && !have_rev)
 		return target_revfn(NFPROTO_UNSPEC, name, revision, bestp);
@@ -371,12 +375,10 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target,
 {
 	int have_rev, best = -1;
 
-	mutex_lock(&xt[af].mutex);
 	if (target == 1)
 		have_rev = target_revfn(af, name, revision, &best);
 	else
 		have_rev = match_revfn(af, name, revision, &best);
-	mutex_unlock(&xt[af].mutex);
 
 	/* Nothing at all?  Return 0 to try loading module. */
 	if (best == -1) {

From a4fc088ad4ff4a99d01978aa41065132b574b4b2 Mon Sep 17 00:00:00 2001
From: Yinjun Zhang <yinjun.zhang@corigine.com>
Date: Thu, 25 Feb 2021 13:51:02 +0100
Subject: [PATCH 0078/1820] ethtool: fix the check logic of at least one
 channel for RX/TX

The command "ethtool -L <intf> combined 0" may clean the RX/TX channel
count and skip the error path, since the attrs
tb[ETHTOOL_A_CHANNELS_RX_COUNT] and tb[ETHTOOL_A_CHANNELS_TX_COUNT]
are NULL in this case when recent ethtool is used.

Tested using ethtool v5.10.

Fixes: 7be92514b99c ("ethtool: check if there is at least one channel for TX/RX in the core")
Signed-off-by: Yinjun Zhang <yinjun.zhang@corigine.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Louis Peens <louis.peens@netronome.com>
Link: https://lore.kernel.org/r/20210225125102.23989-1-simon.horman@netronome.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/channels.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c
index 25a9e566ef5c..6a070dc8e4b0 100644
--- a/net/ethtool/channels.c
+++ b/net/ethtool/channels.c
@@ -116,10 +116,9 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info)
 	struct ethtool_channels channels = {};
 	struct ethnl_req_info req_info = {};
 	struct nlattr **tb = info->attrs;
-	const struct nlattr *err_attr;
+	u32 err_attr, max_rx_in_use = 0;
 	const struct ethtool_ops *ops;
 	struct net_device *dev;
-	u32 max_rx_in_use = 0;
 	int ret;
 
 	ret = ethnl_parse_header_dev_get(&req_info,
@@ -157,34 +156,35 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info)
 
 	/* ensure new channel counts are within limits */
 	if (channels.rx_count > channels.max_rx)
-		err_attr = tb[ETHTOOL_A_CHANNELS_RX_COUNT];
+		err_attr = ETHTOOL_A_CHANNELS_RX_COUNT;
 	else if (channels.tx_count > channels.max_tx)
-		err_attr = tb[ETHTOOL_A_CHANNELS_TX_COUNT];
+		err_attr = ETHTOOL_A_CHANNELS_TX_COUNT;
 	else if (channels.other_count > channels.max_other)
-		err_attr = tb[ETHTOOL_A_CHANNELS_OTHER_COUNT];
+		err_attr = ETHTOOL_A_CHANNELS_OTHER_COUNT;
 	else if (channels.combined_count > channels.max_combined)
-		err_attr = tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT];
+		err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT;
 	else
-		err_attr = NULL;
+		err_attr = 0;
 	if (err_attr) {
 		ret = -EINVAL;
-		NL_SET_ERR_MSG_ATTR(info->extack, err_attr,
+		NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr],
 				    "requested channel count exceeds maximum");
 		goto out_ops;
 	}
 
 	/* ensure there is at least one RX and one TX channel */
 	if (!channels.combined_count && !channels.rx_count)
-		err_attr = tb[ETHTOOL_A_CHANNELS_RX_COUNT];
+		err_attr = ETHTOOL_A_CHANNELS_RX_COUNT;
 	else if (!channels.combined_count && !channels.tx_count)
-		err_attr = tb[ETHTOOL_A_CHANNELS_TX_COUNT];
+		err_attr = ETHTOOL_A_CHANNELS_TX_COUNT;
 	else
-		err_attr = NULL;
+		err_attr = 0;
 	if (err_attr) {
 		if (mod_combined)
-			err_attr = tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT];
+			err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT;
 		ret = -EINVAL;
-		NL_SET_ERR_MSG_ATTR(info->extack, err_attr, "requested channel counts would result in no RX or TX channel being configured");
+		NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr],
+				    "requested channel counts would result in no RX or TX channel being configured");
 		goto out_ops;
 	}
 

From d313d16bbaea0f11a2e98f04a6c678b43c208915 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Fri, 26 Feb 2021 14:20:38 +0100
Subject: [PATCH 0079/1820] net: broadcom: bcm4908_enet: enable RX after
 processing packets
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When receiving a lot of packets hardware may run out of free
descriptiors and stop RX ring. Enable it every time after handling
received packets.

Fixes: 4feffeadbcb2 ("net: broadcom: bcm4908enet: add BCM4908 controller driver")
Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Link: https://lore.kernel.org/r/20210226132038.29849-1-zajec5@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bcm4908_enet.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c
index 0b70e9e0ddad..98cf82dea3e4 100644
--- a/drivers/net/ethernet/broadcom/bcm4908_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c
@@ -592,6 +592,9 @@ static int bcm4908_enet_poll(struct napi_struct *napi, int weight)
 		bcm4908_enet_intrs_on(enet);
 	}
 
+	/* Hardware could disable ring if it run out of descriptors */
+	bcm4908_enet_dma_rx_ring_enable(enet, &enet->rx_ring);
+
 	return handled;
 }
 

From 89e5c58fc1e2857ccdaae506fb8bc5fed57ee063 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 26 Feb 2021 22:22:48 +0100
Subject: [PATCH 0080/1820] net: Fix gro aggregation for udp encaps with zero
 csum

We noticed a GRO issue for UDP-based encaps such as vxlan/geneve when the
csum for the UDP header itself is 0. In that case, GRO aggregation does
not take place on the phys dev, but instead is deferred to the vxlan/geneve
driver (see trace below).

The reason is essentially that GRO aggregation bails out in udp_gro_receive()
for such case when drivers marked the skb with CHECKSUM_UNNECESSARY (ice, i40e,
others) where for non-zero csums 2abb7cdc0dc8 ("udp: Add support for doing
checksum unnecessary conversion") promotes those skbs to CHECKSUM_COMPLETE
and napi context has csum_valid set. This is however not the case for zero
UDP csum (here: csum_cnt is still 0 and csum_valid continues to be false).

At the same time 57c67ff4bd92 ("udp: additional GRO support") added matches
on !uh->check ^ !uh2->check as part to determine candidates for aggregation,
so it certainly is expected to handle zero csums in udp_gro_receive(). The
purpose of the check added via 662880f44203 ("net: Allow GRO to use and set
levels of checksum unnecessary") seems to catch bad csum and stop aggregation
right away.

One way to fix aggregation in the zero case is to only perform the !csum_valid
check in udp_gro_receive() if uh->check is infact non-zero.

Before:

  [...]
  swapper     0 [008]   731.946506: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100400 len=1500   (1)
  swapper     0 [008]   731.946507: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100200 len=1500
  swapper     0 [008]   731.946507: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101100 len=1500
  swapper     0 [008]   731.946508: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101700 len=1500
  swapper     0 [008]   731.946508: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101b00 len=1500
  swapper     0 [008]   731.946508: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100600 len=1500
  swapper     0 [008]   731.946508: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100f00 len=1500
  swapper     0 [008]   731.946509: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100a00 len=1500
  swapper     0 [008]   731.946516: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100500 len=1500
  swapper     0 [008]   731.946516: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100700 len=1500
  swapper     0 [008]   731.946516: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101d00 len=1500   (2)
  swapper     0 [008]   731.946517: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101000 len=1500
  swapper     0 [008]   731.946517: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101c00 len=1500
  swapper     0 [008]   731.946517: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101400 len=1500
  swapper     0 [008]   731.946518: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100e00 len=1500
  swapper     0 [008]   731.946518: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497101600 len=1500
  swapper     0 [008]   731.946521: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff966497100800 len=774
  swapper     0 [008]   731.946530: net:netif_receive_skb: dev=test_vxlan skbaddr=0xffff966497100400 len=14032 (1)
  swapper     0 [008]   731.946530: net:netif_receive_skb: dev=test_vxlan skbaddr=0xffff966497101d00 len=9112  (2)
  [...]

  # netperf -H 10.55.10.4 -t TCP_STREAM -l 20
  MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.55.10.4 () port 0 AF_INET : demo
  Recv   Send    Send
  Socket Socket  Message  Elapsed
  Size   Size    Size     Time     Throughput
  bytes  bytes   bytes    secs.    10^6bits/sec

   87380  16384  16384    20.01    13129.24

After:

  [...]
  swapper     0 [026]   521.862641: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff93ab0d479000 len=11286 (1)
  swapper     0 [026]   521.862643: net:netif_receive_skb: dev=test_vxlan skbaddr=0xffff93ab0d479000 len=11236 (1)
  swapper     0 [026]   521.862650: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff93ab0d478500 len=2898  (2)
  swapper     0 [026]   521.862650: net:netif_receive_skb: dev=enp10s0f0  skbaddr=0xffff93ab0d479f00 len=8490  (3)
  swapper     0 [026]   521.862653: net:netif_receive_skb: dev=test_vxlan skbaddr=0xffff93ab0d478500 len=2848  (2)
  swapper     0 [026]   521.862653: net:netif_receive_skb: dev=test_vxlan skbaddr=0xffff93ab0d479f00 len=8440  (3)
  [...]

  # netperf -H 10.55.10.4 -t TCP_STREAM -l 20
  MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.55.10.4 () port 0 AF_INET : demo
  Recv   Send    Send
  Socket Socket  Message  Elapsed
  Size   Size    Size     Time     Throughput
  bytes  bytes   bytes    secs.    10^6bits/sec

   87380  16384  16384    20.01    24576.53

Fixes: 57c67ff4bd92 ("udp: additional GRO support")
Fixes: 662880f44203 ("net: Allow GRO to use and set levels of checksum unnecessary")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Cc: Tom Herbert <tom@herbertland.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/r/20210226212248.8300-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udp_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index b76c48efd37e..c5b4b586570f 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -526,7 +526,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 	}
 
 	if (!sk || NAPI_GRO_CB(skb)->encap_mark ||
-	    (skb->ip_summed != CHECKSUM_PARTIAL &&
+	    (uh->check && skb->ip_summed != CHECKSUM_PARTIAL &&
 	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
 	     !NAPI_GRO_CB(skb)->csum_valid) ||
 	    !udp_sk(sk)->gro_receive)

From ae85ddda0f1b341b2d25f5a5e0eff1d42b6ef3df Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Sat, 27 Feb 2021 15:24:51 +0800
Subject: [PATCH 0081/1820] net: hns3: fix error mask definition of flow
 director

Currently, some bit filed definitions of flow director TCAM
configuration command are incorrect. Since the wrong MSB is
always 0, and these fields are assgined in order, so it still works.

Fix it by redefine them.

Fixes: 117328680288 ("net: hns3: Add input key and action config support for flow director")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index ff52a65b4cff..057dda735492 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -1053,16 +1053,16 @@ struct hclge_fd_tcam_config_3_cmd {
 #define HCLGE_FD_AD_DROP_B		0
 #define HCLGE_FD_AD_DIRECT_QID_B	1
 #define HCLGE_FD_AD_QID_S		2
-#define HCLGE_FD_AD_QID_M		GENMASK(12, 2)
+#define HCLGE_FD_AD_QID_M		GENMASK(11, 2)
 #define HCLGE_FD_AD_USE_COUNTER_B	12
 #define HCLGE_FD_AD_COUNTER_NUM_S	13
 #define HCLGE_FD_AD_COUNTER_NUM_M	GENMASK(20, 13)
 #define HCLGE_FD_AD_NXT_STEP_B		20
 #define HCLGE_FD_AD_NXT_KEY_S		21
-#define HCLGE_FD_AD_NXT_KEY_M		GENMASK(26, 21)
+#define HCLGE_FD_AD_NXT_KEY_M		GENMASK(25, 21)
 #define HCLGE_FD_AD_WR_RULE_ID_B	0
 #define HCLGE_FD_AD_RULE_ID_S		1
-#define HCLGE_FD_AD_RULE_ID_M		GENMASK(13, 1)
+#define HCLGE_FD_AD_RULE_ID_M		GENMASK(12, 1)
 #define HCLGE_FD_AD_TC_OVRD_B		16
 #define HCLGE_FD_AD_TC_SIZE_S		17
 #define HCLGE_FD_AD_TC_SIZE_M		GENMASK(20, 17)

From c75ec148a316e8cf52274d16b9b422703b96f5ce Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Sat, 27 Feb 2021 15:24:52 +0800
Subject: [PATCH 0082/1820] net: hns3: fix query vlan mask value error for flow
 director

Currently, the driver returns VLAN_VID_MASK for vlan mask field,
when get flow director rule information for rule doesn't use vlan.
It may cause the vlan mask value display as 0xf000 in this
case, like below:

estuary:/$ ethtool -u eth1
50 RX rings available
Total 1 rules

Filter: 2
Rule Type: TCP over IPv4
Src IP addr: 0.0.0.0 mask: 255.255.255.255
Dest IP addr: 0.0.0.0 mask: 255.255.255.255
TOS: 0x0 mask: 0xff
Src port: 0 mask: 0xffff
Dest port: 0 mask: 0xffff
VLAN EtherType: 0x0 mask: 0xffff
VLAN: 0x0 mask: 0xf000
User-defined: 0x1234 mask: 0x0
Action: Direct to queue 3

Fix it by return 0.

Fixes: 05c2314fe6a8 ("net: hns3: Add support for rule query of flow director")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 34b744df6709..932cfd1fb7e9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6330,8 +6330,7 @@ static void hclge_fd_get_ext_info(struct ethtool_rx_flow_spec *fs,
 		fs->h_ext.vlan_tci = cpu_to_be16(rule->tuples.vlan_tag1);
 		fs->m_ext.vlan_tci =
 				rule->unused_tuple & BIT(INNER_VLAN_TAG_FST) ?
-				cpu_to_be16(VLAN_VID_MASK) :
-				cpu_to_be16(rule->tuples_mask.vlan_tag1);
+				0 : cpu_to_be16(rule->tuples_mask.vlan_tag1);
 	}
 
 	if (fs->flow_type & FLOW_MAC_EXT) {

From b36fc875bcdee56865c444a2cdae17d354a6d5f5 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Sat, 27 Feb 2021 15:24:53 +0800
Subject: [PATCH 0083/1820] net: hns3: fix bug when calculating the TCAM table
 info

The function hclge_fd_convert_tuple() is used to convert tuples
and tuples mask to TCAM x and y.  But it misuses the source mac
as source mac mask when convert INNER_SRC_MAC, which may cause
the flow director rule works unexpectedly. So fix it.

Fixes: 117328680288 ("net: hns3: Add input key and action config support for flow director")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 932cfd1fb7e9..e3f81c7e0ce7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5245,9 +5245,9 @@ static bool hclge_fd_convert_tuple(u32 tuple_bit, u8 *key_x, u8 *key_y,
 	case BIT(INNER_SRC_MAC):
 		for (i = 0; i < ETH_ALEN; i++) {
 			calc_x(key_x[ETH_ALEN - 1 - i], rule->tuples.src_mac[i],
-			       rule->tuples.src_mac[i]);
+			       rule->tuples_mask.src_mac[i]);
 			calc_y(key_y[ETH_ALEN - 1 - i], rule->tuples.src_mac[i],
-			       rule->tuples.src_mac[i]);
+			       rule->tuples_mask.src_mac[i]);
 		}
 
 		return true;

From eead089311f4d935ab5d1d8fbb0c42ad44699ada Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 18 Feb 2021 23:30:58 +1100
Subject: [PATCH 0084/1820] powerpc/4xx: Fix build errors from mfdcr()

lkp reported a build error in fsp2.o:

  CC      arch/powerpc/platforms/44x/fsp2.o
  {standard input}:577: Error: unsupported relocation against base

Which comes from:

  pr_err("GESR0: 0x%08x\n", mfdcr(base + PLB4OPB_GESR0));

Where our mfdcr() macro is stringifying "base + PLB4OPB_GESR0", and
passing that to the assembler, which obviously doesn't work.

The mfdcr() macro already checks that the argument is constant using
__builtin_constant_p(), and if not calls the out-of-line version of
mfdcr(). But in this case GCC is smart enough to notice that "base +
PLB4OPB_GESR0" will be constant, even though it's not something we can
immediately stringify into a register number.

Segher pointed out that passing the register number to the inline asm
as a constant would be better, and in fact it fixes the build error,
presumably because it gives GCC a chance to resolve the value.

While we're at it, change mtdcr() similarly.

Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Feng Tang <feng.tang@intel.com>
Link: https://lore.kernel.org/r/20210218123058.748882-1-mpe@ellerman.id.au
---
 arch/powerpc/include/asm/dcr-native.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h
index 7141ccea8c94..a92059964579 100644
--- a/arch/powerpc/include/asm/dcr-native.h
+++ b/arch/powerpc/include/asm/dcr-native.h
@@ -53,8 +53,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val)
 #define mfdcr(rn)						\
 	({unsigned int rval;					\
 	if (__builtin_constant_p(rn) && rn < 1024)		\
-		asm volatile("mfdcr %0," __stringify(rn)	\
-		              : "=r" (rval));			\
+		asm volatile("mfdcr %0, %1" : "=r" (rval)	\
+			      : "n" (rn));			\
 	else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))	\
 		rval = mfdcrx(rn);				\
 	else							\
@@ -64,8 +64,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val)
 #define mtdcr(rn, v)						\
 do {								\
 	if (__builtin_constant_p(rn) && rn < 1024)		\
-		asm volatile("mtdcr " __stringify(rn) ",%0"	\
-			      : : "r" (v)); 			\
+		asm volatile("mtdcr %0, %1"			\
+			      : : "n" (rn), "r" (v));		\
 	else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))	\
 		mtdcrx(rn, v);					\
 	else							\

From f9619d5e5174867536b7e558683bc4408eab833f Mon Sep 17 00:00:00 2001
From: Greg Kurz <groug@kaod.org>
Date: Mon, 15 Feb 2021 10:45:06 +0100
Subject: [PATCH 0085/1820] powerpc/pseries: Don't enforce MSI affinity with
 kdump
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Depending on the number of online CPUs in the original kernel, it is
likely for CPU #0 to be offline in a kdump kernel. The associated IRQs
in the affinity mappings provided by irq_create_affinity_masks() are
thus not started by irq_startup(), as per-design with managed IRQs.

This can be a problem with multi-queue block devices driven by blk-mq :
such a non-started IRQ is very likely paired with the single queue
enforced by blk-mq during kdump (see blk_mq_alloc_tag_set()). This
causes the device to remain silent and likely hangs the guest at
some point.

This is a regression caused by commit 9ea69a55b3b9 ("powerpc/pseries:
Pass MSI affinity to irq_create_mapping()"). Note that this only happens
with the XIVE interrupt controller because XICS has a workaround to bypass
affinity, which is activated during kdump with the "noirqdistrib" kernel
parameter.

The issue comes from a combination of factors:
- discrepancy between the number of queues detected by the multi-queue
  block driver, that was used to create the MSI vectors, and the single
  queue mode enforced later on by blk-mq because of kdump (i.e. keeping
  all queues fixes the issue)
- CPU#0 offline (i.e. kdump always succeed with CPU#0)

Given that I couldn't reproduce on x86, which seems to always have CPU#0
online even during kdump, I'm not sure where this should be fixed. Hence
going for another approach : fine-grained affinity is for performance
and we don't really care about that during kdump. Simply revert to the
previous working behavior of ignoring affinity masks in this case only.

Fixes: 9ea69a55b3b9 ("powerpc/pseries: Pass MSI affinity to irq_create_mapping()")
Cc: stable@vger.kernel.org # v5.10+
Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210215094506.1196119-1-groug@kaod.org
---
 arch/powerpc/platforms/pseries/msi.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index b3ac2455faad..637300330507 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -4,6 +4,7 @@
  * Copyright 2006-2007 Michael Ellerman, IBM Corp.
  */
 
+#include <linux/crash_dump.h>
 #include <linux/device.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
@@ -458,8 +459,28 @@ again:
 			return hwirq;
 		}
 
-		virq = irq_create_mapping_affinity(NULL, hwirq,
-						   entry->affinity);
+		/*
+		 * Depending on the number of online CPUs in the original
+		 * kernel, it is likely for CPU #0 to be offline in a kdump
+		 * kernel. The associated IRQs in the affinity mappings
+		 * provided by irq_create_affinity_masks() are thus not
+		 * started by irq_startup(), as per-design for managed IRQs.
+		 * This can be a problem with multi-queue block devices driven
+		 * by blk-mq : such a non-started IRQ is very likely paired
+		 * with the single queue enforced by blk-mq during kdump (see
+		 * blk_mq_alloc_tag_set()). This causes the device to remain
+		 * silent and likely hangs the guest at some point.
+		 *
+		 * We don't really care for fine-grained affinity when doing
+		 * kdump actually : simply ignore the pre-computed affinity
+		 * masks in this case and let the default mask with all CPUs
+		 * be used when creating the IRQ mappings.
+		 */
+		if (is_kdump_kernel())
+			virq = irq_create_mapping(NULL, hwirq);
+		else
+			virq = irq_create_mapping_affinity(NULL, hwirq,
+							   entry->affinity);
 
 		if (!virq) {
 			pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq);

From c119565a15a628efdfa51352f9f6c5186e506a1c Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Mon, 1 Feb 2021 06:29:50 +0000
Subject: [PATCH 0086/1820] powerpc/603: Fix protection of user pages mapped
 with PROT_NONE

On book3s/32, page protection is defined by the PP bits in the PTE
which provide the following protection depending on the access
keys defined in the matching segment register:
- PP 00 means RW with key 0 and N/A with key 1.
- PP 01 means RW with key 0 and RO with key 1.
- PP 10 means RW with both key 0 and key 1.
- PP 11 means RO with both key 0 and key 1.

Since the implementation of kernel userspace access protection,
PP bits have been set as follows:
- PP00 for pages without _PAGE_USER
- PP01 for pages with _PAGE_USER and _PAGE_RW
- PP11 for pages with _PAGE_USER and without _PAGE_RW

For kernelspace segments, kernel accesses are performed with key 0
and user accesses are performed with key 1. As PP00 is used for
non _PAGE_USER pages, user can't access kernel pages not flagged
_PAGE_USER while kernel can.

For userspace segments, both kernel and user accesses are performed
with key 0, therefore pages not flagged _PAGE_USER are still
accessible to the user.

This shouldn't be an issue, because userspace is expected to be
accessible to the user. But unlike most other architectures, powerpc
implements PROT_NONE protection by removing _PAGE_USER flag instead of
flagging the page as not valid. This means that pages in userspace
that are not flagged _PAGE_USER shall remain inaccessible.

To get the expected behaviour, just mimic other architectures in the
TLB miss handler by checking _PAGE_USER permission on userspace
accesses as if it was the _PAGE_PRESENT bit.

Note that this problem only is only for 603 cores. The 604+ have
an hash table, and hash_page() function already implement the
verification of _PAGE_USER permission on userspace pages.

Fixes: f342adca3afc ("powerpc/32s: Prepare Kernel Userspace Access Protection")
Cc: stable@vger.kernel.org # v5.2+
Reported-by: Christoph Plattner <christoph.plattner@thalesgroup.com>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/4a0c6e3bb8f0c162457bf54d9bc6fd8d7b55129f.1612160907.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/kernel/head_book3s_32.S | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 727fdab557c9..565e84e20a72 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -457,11 +457,12 @@ InstructionTLBMiss:
 	cmplw	0,r1,r3
 #endif
 	mfspr	r2, SPRN_SDR1
-	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER
 	rlwinm	r2, r2, 28, 0xfffff000
 #ifdef CONFIG_MODULES
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
+	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
 #endif
 112:	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
@@ -520,10 +521,11 @@ DataLoadTLBMiss:
 	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 	mfspr	r2, SPRN_SDR1
-	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED
+	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
 	rlwinm	r2, r2, 28, 0xfffff000
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
+	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
 112:	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
 	lwz	r2,0(r2)		/* get pmd entry */
@@ -597,10 +599,11 @@ DataStoreTLBMiss:
 	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 	mfspr	r2, SPRN_SDR1
-	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
+	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
 	rlwinm	r2, r2, 28, 0xfffff000
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
+	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
 112:	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
 	lwz	r2,0(r2)		/* get pmd entry */

From 91b6c5dbe9e072dbdb181eed89c5c824e92ac0f5 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Wed, 24 Feb 2021 06:34:22 +0000
Subject: [PATCH 0087/1820] powerpc/syscall: Force inlining of
 __prep_irq_for_enabled_exit()

As reported by kernel test robot, a randconfig with high amount of
debuging options can lead to build failure for undefined reference
to replay_soft_interrupts() on ppc32.

This is due to gcc not seeing that __prep_irq_for_enabled_exit()
always returns true on ppc32 because it doesn't inline it for
some reason.

Force inlining of __prep_irq_for_enabled_exit() to fix the build.

Fixes: 344bb20b159d ("powerpc/syscall: Make interrupt.c buildable on PPC32")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/53f3a1f719441761000c41154602bf097d4350b5.1614148356.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/kernel/interrupt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 398cd86b6ada..2ef3c4051bb9 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -149,7 +149,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
  * enabled when the interrupt handler returns (indicating a process-context /
  * synchronous interrupt) then irqs_enabled should be true.
  */
-static notrace inline bool __prep_irq_for_enabled_exit(bool clear_ri)
+static notrace __always_inline bool __prep_irq_for_enabled_exit(bool clear_ri)
 {
 	/* This must be done with RI=1 because tracing may touch vmaps */
 	trace_hardirqs_on();

From 449052cfebf624b670faa040245d3feed770d22f Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang@nxp.com>
Date: Thu, 18 Feb 2021 19:00:35 +0800
Subject: [PATCH 0088/1820] can: flexcan: assert FRZ bit in
 flexcan_chip_freeze()

Assert HALT bit to enter freeze mode, there is a premise that FRZ bit is
asserted. This patch asserts FRZ bit in flexcan_chip_freeze, although
the reset value is 1b'1. This is a prepare patch, later patch will
invoke flexcan_chip_freeze() to enter freeze mode, which polling freeze
mode acknowledge.

Fixes: b1aa1c7a2165b ("can: flexcan: fix transition from and to freeze mode in chip_{,un}freeze")
Link: https://lore.kernel.org/r/20210218110037.16591-2-qiangqing.zhang@nxp.com
Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 971ada36e37f..ee2d4967d66a 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -701,7 +701,7 @@ static int flexcan_chip_freeze(struct flexcan_priv *priv)
 	u32 reg;
 
 	reg = priv->read(&regs->mcr);
-	reg |= FLEXCAN_MCR_HALT;
+	reg |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT;
 	priv->write(reg, &regs->mcr);
 
 	while (timeout-- && !(priv->read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK))

From ec15e27cc8904605846a354bb1f808ea1432f853 Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang@nxp.com>
Date: Thu, 18 Feb 2021 19:00:36 +0800
Subject: [PATCH 0089/1820] can: flexcan: enable RX FIFO after FRZ/HALT valid

RX FIFO enable failed could happen when do system reboot stress test:

[    0.303958] flexcan 5a8d0000.can: 5a8d0000.can supply xceiver not found, using dummy regulator
[    0.304281] flexcan 5a8d0000.can (unnamed net_device) (uninitialized): Could not enable RX FIFO, unsupported core
[    0.314640] flexcan 5a8d0000.can: registering netdev failed
[    0.320728] flexcan 5a8e0000.can: 5a8e0000.can supply xceiver not found, using dummy regulator
[    0.320991] flexcan 5a8e0000.can (unnamed net_device) (uninitialized): Could not enable RX FIFO, unsupported core
[    0.331360] flexcan 5a8e0000.can: registering netdev failed
[    0.337444] flexcan 5a8f0000.can: 5a8f0000.can supply xceiver not found, using dummy regulator
[    0.337716] flexcan 5a8f0000.can (unnamed net_device) (uninitialized): Could not enable RX FIFO, unsupported core
[    0.348117] flexcan 5a8f0000.can: registering netdev failed

RX FIFO should be enabled after the FRZ/HALT are valid. But the current
code enable RX FIFO and FRZ/HALT at the same time.

Fixes: e955cead03117 ("CAN: Add Flexcan CAN controller driver")
Link: https://lore.kernel.org/r/20210218110037.16591-3-qiangqing.zhang@nxp.com
Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index ee2d4967d66a..e66a51dbea0a 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -1865,10 +1865,14 @@ static int register_flexcandev(struct net_device *dev)
 	if (err)
 		goto out_chip_disable;
 
-	/* set freeze, halt and activate FIFO, restrict register access */
+	/* set freeze, halt */
+	err = flexcan_chip_freeze(priv);
+	if (err)
+		goto out_chip_disable;
+
+	/* activate FIFO, restrict register access */
 	reg = priv->read(&regs->mcr);
-	reg |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT |
-		FLEXCAN_MCR_FEN | FLEXCAN_MCR_SUPV;
+	reg |=  FLEXCAN_MCR_FEN | FLEXCAN_MCR_SUPV;
 	priv->write(reg, &regs->mcr);
 
 	/* Currently we only support newer versions of this core

From c63820045e2000f05657467a08715c18c9f490d9 Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang@nxp.com>
Date: Thu, 18 Feb 2021 19:00:37 +0800
Subject: [PATCH 0090/1820] can: flexcan: invoke flexcan_chip_freeze() to enter
 freeze mode

Invoke flexcan_chip_freeze() to enter freeze mode, since need poll
freeze mode acknowledge.

Fixes: e955cead03117 ("CAN: Add Flexcan CAN controller driver")
Link: https://lore.kernel.org/r/20210218110037.16591-4-qiangqing.zhang@nxp.com
Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index e66a51dbea0a..134c05757a3b 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -1480,10 +1480,13 @@ static int flexcan_chip_start(struct net_device *dev)
 
 	flexcan_set_bittiming(dev);
 
+	/* set freeze, halt */
+	err = flexcan_chip_freeze(priv);
+	if (err)
+		goto out_chip_disable;
+
 	/* MCR
 	 *
-	 * enable freeze
-	 * halt now
 	 * only supervisor access
 	 * enable warning int
 	 * enable individual RX masking
@@ -1492,9 +1495,8 @@ static int flexcan_chip_start(struct net_device *dev)
 	 */
 	reg_mcr = priv->read(&regs->mcr);
 	reg_mcr &= ~FLEXCAN_MCR_MAXMB(0xff);
-	reg_mcr |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT | FLEXCAN_MCR_SUPV |
-		FLEXCAN_MCR_WRN_EN | FLEXCAN_MCR_IRMQ | FLEXCAN_MCR_IDAM_C |
-		FLEXCAN_MCR_MAXMB(priv->tx_mb_idx);
+	reg_mcr |= FLEXCAN_MCR_SUPV | FLEXCAN_MCR_WRN_EN | FLEXCAN_MCR_IRMQ |
+		FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_MAXMB(priv->tx_mb_idx);
 
 	/* MCR
 	 *

From 2afe72ead5ab672c8012bda83cbe65f8145568e0 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Mon, 22 Feb 2021 20:46:06 +0100
Subject: [PATCH 0091/1820] can: mcp251xfd: revert "can: mcp251xfd: add BQL
 support"

In the following 4 patches

| 99842c9685ab can: dev: can_rx_offload_get_echo_skb(): extend to return can frame length
| 9420e1d495e2 can: dev: can_get_echo_skb(): extend to return can frame length
| 1dcb6e57db83 can: dev: can_put_echo_skb(): extend to handle frame_len
| f0ef72febc9a can: dev: extend struct can_skb_priv to hold CAN frame length

the CAN echo SKB support was extended to hold the CAN frame
length (which is the length of the CAN frame on the wire). It is meant
as a helper for BQL support, to avoid the re-calculation of the frame
length before sending it and on TX-completion.

However if the CAN frame is send without the request to be looped back
the SKB is discarded in can_put_echo_skb() and the subsequent
can_get_echo_skb() and can_rx_offload_get_echo_skb() return 0 for the
CAN frame length. This results in BQL stalling the TX queue after a
few packages.

Until the BQL helpers can_get_echo_skb() and
can_rx_offload_get_echo_skb() are fixed, revert the BQL support for
the mcp251xfd driver.

This reverts commit 4162e18e949ba520d5116ac0323500355479a00e.

Fixes: 4162e18e949b ("can: mcp251xfd: add BQL support")
Cc: Manivannan Sadhasivam <mani@kernel.org>
Cc: Thomas Kopp <thomas.kopp@microchip.com>
Link: https://lore.kernel.org/r/20210228083347.28580-1-mkl@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../net/can/spi/mcp251xfd/mcp251xfd-core.c    | 21 ++++---------------
 1 file changed, 4 insertions(+), 17 deletions(-)

diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 3c5b92911d46..799e9d5d3481 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -335,8 +335,6 @@ static void mcp251xfd_ring_init(struct mcp251xfd_priv *priv)
 	u8 len;
 	int i, j;
 
-	netdev_reset_queue(priv->ndev);
-
 	/* TEF */
 	tef_ring = priv->tef;
 	tef_ring->head = 0;
@@ -1249,8 +1247,7 @@ mcp251xfd_handle_tefif_recover(const struct mcp251xfd_priv *priv, const u32 seq)
 
 static int
 mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv,
-			   const struct mcp251xfd_hw_tef_obj *hw_tef_obj,
-			   unsigned int *frame_len_ptr)
+			   const struct mcp251xfd_hw_tef_obj *hw_tef_obj)
 {
 	struct net_device_stats *stats = &priv->ndev->stats;
 	u32 seq, seq_masked, tef_tail_masked;
@@ -1272,8 +1269,7 @@ mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv,
 	stats->tx_bytes +=
 		can_rx_offload_get_echo_skb(&priv->offload,
 					    mcp251xfd_get_tef_tail(priv),
-					    hw_tef_obj->ts,
-					    frame_len_ptr);
+					    hw_tef_obj->ts, NULL);
 	stats->tx_packets++;
 	priv->tef->tail++;
 
@@ -1331,7 +1327,6 @@ mcp251xfd_tef_obj_read(const struct mcp251xfd_priv *priv,
 static int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
 {
 	struct mcp251xfd_hw_tef_obj hw_tef_obj[MCP251XFD_TX_OBJ_NUM_MAX];
-	unsigned int total_frame_len = 0;
 	u8 tef_tail, len, l;
 	int err, i;
 
@@ -1353,9 +1348,7 @@ static int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
 	}
 
 	for (i = 0; i < len; i++) {
-		unsigned int frame_len;
-
-		err = mcp251xfd_handle_tefif_one(priv, &hw_tef_obj[i], &frame_len);
+		err = mcp251xfd_handle_tefif_one(priv, &hw_tef_obj[i]);
 		/* -EAGAIN means the Sequence Number in the TEF
 		 * doesn't match our tef_tail. This can happen if we
 		 * read the TEF objects too early. Leave loop let the
@@ -1365,8 +1358,6 @@ static int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
 			goto out_netif_wake_queue;
 		if (err)
 			return err;
-
-		total_frame_len += frame_len;
 	}
 
  out_netif_wake_queue:
@@ -1397,7 +1388,6 @@ static int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
 			return err;
 
 		tx_ring->tail += len;
-		netdev_completed_queue(priv->ndev, len, total_frame_len);
 
 		err = mcp251xfd_check_tef_tail(priv);
 		if (err)
@@ -2443,7 +2433,6 @@ static netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb,
 	struct mcp251xfd_priv *priv = netdev_priv(ndev);
 	struct mcp251xfd_tx_ring *tx_ring = priv->tx;
 	struct mcp251xfd_tx_obj *tx_obj;
-	unsigned int frame_len;
 	u8 tx_head;
 	int err;
 
@@ -2462,9 +2451,7 @@ static netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb,
 	if (mcp251xfd_get_tx_free(tx_ring) == 0)
 		netif_stop_queue(ndev);
 
-	frame_len = can_skb_get_frame_len(skb);
-	can_put_echo_skb(skb, ndev, tx_head, frame_len);
-	netdev_sent_queue(priv->ndev, frame_len);
+	can_put_echo_skb(skb, ndev, tx_head, 0);
 
 	err = mcp251xfd_tx_obj_write(priv, tx_obj);
 	if (err)

From e940e0895a82c6fbaa259f2615eb52b57ee91a7e Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 26 Feb 2021 10:24:56 +0100
Subject: [PATCH 0092/1820] can: skb: can_skb_set_owner(): fix ref counting if
 socket was closed before setting skb ownership

There are two ref count variables controlling the free()ing of a socket:
- struct sock::sk_refcnt - which is changed by sock_hold()/sock_put()
- struct sock::sk_wmem_alloc - which accounts the memory allocated by
  the skbs in the send path.

In case there are still TX skbs on the fly and the socket() is closed,
the struct sock::sk_refcnt reaches 0. In the TX-path the CAN stack
clones an "echo" skb, calls sock_hold() on the original socket and
references it. This produces the following back trace:

| WARNING: CPU: 0 PID: 280 at lib/refcount.c:25 refcount_warn_saturate+0x114/0x134
| refcount_t: addition on 0; use-after-free.
| Modules linked in: coda_vpu(E) v4l2_jpeg(E) videobuf2_vmalloc(E) imx_vdoa(E)
| CPU: 0 PID: 280 Comm: test_can.sh Tainted: G            E     5.11.0-04577-gf8ff6603c617 #203
| Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree)
| Backtrace:
| [<80bafea4>] (dump_backtrace) from [<80bb0280>] (show_stack+0x20/0x24) r7:00000000 r6:600f0113 r5:00000000 r4:81441220
| [<80bb0260>] (show_stack) from [<80bb593c>] (dump_stack+0xa0/0xc8)
| [<80bb589c>] (dump_stack) from [<8012b268>] (__warn+0xd4/0x114) r9:00000019 r8:80f4a8c2 r7:83e4150c r6:00000000 r5:00000009 r4:80528f90
| [<8012b194>] (__warn) from [<80bb09c4>] (warn_slowpath_fmt+0x88/0xc8) r9:83f26400 r8:80f4a8d1 r7:00000009 r6:80528f90 r5:00000019 r4:80f4a8c2
| [<80bb0940>] (warn_slowpath_fmt) from [<80528f90>] (refcount_warn_saturate+0x114/0x134) r8:00000000 r7:00000000 r6:82b44000 r5:834e5600 r4:83f4d540
| [<80528e7c>] (refcount_warn_saturate) from [<8079a4c8>] (__refcount_add.constprop.0+0x4c/0x50)
| [<8079a47c>] (__refcount_add.constprop.0) from [<8079a57c>] (can_put_echo_skb+0xb0/0x13c)
| [<8079a4cc>] (can_put_echo_skb) from [<8079ba98>] (flexcan_start_xmit+0x1c4/0x230) r9:00000010 r8:83f48610 r7:0fdc0000 r6:0c080000 r5:82b44000 r4:834e5600
| [<8079b8d4>] (flexcan_start_xmit) from [<80969078>] (netdev_start_xmit+0x44/0x70) r9:814c0ba0 r8:80c8790c r7:00000000 r6:834e5600 r5:82b44000 r4:82ab1f00
| [<80969034>] (netdev_start_xmit) from [<809725a4>] (dev_hard_start_xmit+0x19c/0x318) r9:814c0ba0 r8:00000000 r7:82ab1f00 r6:82b44000 r5:00000000 r4:834e5600
| [<80972408>] (dev_hard_start_xmit) from [<809c6584>] (sch_direct_xmit+0xcc/0x264) r10:834e5600 r9:00000000 r8:00000000 r7:82b44000 r6:82ab1f00 r5:834e5600 r4:83f27400
| [<809c64b8>] (sch_direct_xmit) from [<809c6c0c>] (__qdisc_run+0x4f0/0x534)

To fix this problem, only set skb ownership to sockets which have still
a ref count > 0.

Fixes: 0ae89beb283a ("can: add destructor for self generated skbs")
Cc: Oliver Hartkopp <socketcan@hartkopp.net>
Cc: Andre Naujoks <nautsch2@gmail.com>
Link: https://lore.kernel.org/r/20210226092456.27126-1-o.rempel@pengutronix.de
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/linux/can/skb.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index 685f34cfba20..d438eb058069 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -65,8 +65,12 @@ static inline void can_skb_reserve(struct sk_buff *skb)
 
 static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk)
 {
-	if (sk) {
-		sock_hold(sk);
+	/* If the socket has already been closed by user space, the
+	 * refcount may already be 0 (and the socket will be freed
+	 * after the last TX skb has been freed). So only increase
+	 * socket refcount if the refcount is > 0.
+	 */
+	if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) {
 		skb->destructor = sock_efree;
 		skb->sk = sk;
 	}

From 2712625200ed69c642b9abc3a403830c4643364c Mon Sep 17 00:00:00 2001
From: Torin Cooper-Bennun <torin@maxiluxsystems.com>
Date: Fri, 26 Feb 2021 16:34:41 +0000
Subject: [PATCH 0093/1820] can: tcan4x5x: tcan4x5x_init(): fix initialization
 - clear MRAM before entering Normal Mode

This patch prevents a potentially destructive race condition. The
device is fully operational on the bus after entering Normal Mode, so
zeroing the MRAM after entering this mode may lead to loss of
information, e.g. new received messages.

This patch fixes the problem by first initializing the MRAM, then
bringing the device into Normale Mode.

Fixes: 5443c226ba91 ("can: tcan4x5x: Add tcan4x5x driver to the kernel")
Link: https://lore.kernel.org/r/20210226163440.313628-1-torin@maxiluxsystems.com
Suggested-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Torin Cooper-Bennun <torin@maxiluxsystems.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/tcan4x5x-core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c
index b7caec769ddb..4147cecfbbd6 100644
--- a/drivers/net/can/m_can/tcan4x5x-core.c
+++ b/drivers/net/can/m_can/tcan4x5x-core.c
@@ -237,14 +237,14 @@ static int tcan4x5x_init(struct m_can_classdev *cdev)
 	if (ret)
 		return ret;
 
+	/* Zero out the MCAN buffers */
+	m_can_init_ram(cdev);
+
 	ret = regmap_update_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG,
 				 TCAN4X5X_MODE_SEL_MASK, TCAN4X5X_MODE_NORMAL);
 	if (ret)
 		return ret;
 
-	/* Zero out the MCAN buffers */
-	m_can_init_ram(cdev);
-
 	return ret;
 }
 

From 73f476aa1975bae6a792b340f5b26ffcfba869a6 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Fri, 26 Feb 2021 17:30:20 +0200
Subject: [PATCH 0094/1820] net: phy: ti: take into account all possible
 interrupt sources

The previous implementation of .handle_interrupt() did not take into
account the fact that all the interrupt status registers should be
acknowledged since multiple interrupt sources could be asserted.

Fix this by reading all the status registers before exiting with
IRQ_NONE or triggering the PHY state machine.

Fixes: 1d1ae3c6ca3f ("net: phy: ti: implement generic .handle_interrupt() callback")
Reported-by: Sven Schuchmann <schuchmann@schleissheimer.de>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://lore.kernel.org/r/20210226153020.867852-1-ciorneiioana@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/dp83822.c   |  9 +++++----
 drivers/net/phy/dp83tc811.c | 11 ++++++-----
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index be1224b4447b..f7a2ec150e54 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -290,6 +290,7 @@ static int dp83822_config_intr(struct phy_device *phydev)
 
 static irqreturn_t dp83822_handle_interrupt(struct phy_device *phydev)
 {
+	bool trigger_machine = false;
 	int irq_status;
 
 	/* The MISR1 and MISR2 registers are holding the interrupt status in
@@ -305,7 +306,7 @@ static irqreturn_t dp83822_handle_interrupt(struct phy_device *phydev)
 		return IRQ_NONE;
 	}
 	if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
-		goto trigger_machine;
+		trigger_machine = true;
 
 	irq_status = phy_read(phydev, MII_DP83822_MISR2);
 	if (irq_status < 0) {
@@ -313,11 +314,11 @@ static irqreturn_t dp83822_handle_interrupt(struct phy_device *phydev)
 		return IRQ_NONE;
 	}
 	if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
-		goto trigger_machine;
+		trigger_machine = true;
 
-	return IRQ_NONE;
+	if (!trigger_machine)
+		return IRQ_NONE;
 
-trigger_machine:
 	phy_trigger_machine(phydev);
 
 	return IRQ_HANDLED;
diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c
index 688fadffb249..7ea32fb77190 100644
--- a/drivers/net/phy/dp83tc811.c
+++ b/drivers/net/phy/dp83tc811.c
@@ -264,6 +264,7 @@ static int dp83811_config_intr(struct phy_device *phydev)
 
 static irqreturn_t dp83811_handle_interrupt(struct phy_device *phydev)
 {
+	bool trigger_machine = false;
 	int irq_status;
 
 	/* The INT_STAT registers 1, 2 and 3 are holding the interrupt status
@@ -279,7 +280,7 @@ static irqreturn_t dp83811_handle_interrupt(struct phy_device *phydev)
 		return IRQ_NONE;
 	}
 	if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
-		goto trigger_machine;
+		trigger_machine = true;
 
 	irq_status = phy_read(phydev, MII_DP83811_INT_STAT2);
 	if (irq_status < 0) {
@@ -287,7 +288,7 @@ static irqreturn_t dp83811_handle_interrupt(struct phy_device *phydev)
 		return IRQ_NONE;
 	}
 	if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
-		goto trigger_machine;
+		trigger_machine = true;
 
 	irq_status = phy_read(phydev, MII_DP83811_INT_STAT3);
 	if (irq_status < 0) {
@@ -295,11 +296,11 @@ static irqreturn_t dp83811_handle_interrupt(struct phy_device *phydev)
 		return IRQ_NONE;
 	}
 	if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
-		goto trigger_machine;
+		trigger_machine = true;
 
-	return IRQ_NONE;
+	if (!trigger_machine)
+		return IRQ_NONE;
 
-trigger_machine:
 	phy_trigger_machine(phydev);
 
 	return IRQ_HANDLED;

From 826d82170b539f16e1955ab940222543c012044e Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@suse.com>
Date: Thu, 25 Feb 2021 16:39:01 +0100
Subject: [PATCH 0095/1820] xen-netback: use local var in xenvif_tx_check_gop()
 instead of re-calculating

shinfo already holds the result of skb_shinfo(skb) at this point - no
need to re-invoke the construct even twice.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/netback.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index e5c73f819662..aff5ac1f002a 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -557,8 +557,8 @@ check_frags:
 	}
 
 	if (skb_has_frag_list(skb) && !first_shinfo) {
-		first_shinfo = skb_shinfo(skb);
-		shinfo = skb_shinfo(skb_shinfo(skb)->frag_list);
+		first_shinfo = shinfo;
+		shinfo = skb_shinfo(shinfo->frag_list);
 		nr_frags = shinfo->nr_frags;
 
 		goto check_frags;

From 9eb8bc593a5eed167dac2029abef343854c5ba75 Mon Sep 17 00:00:00 2001
From: DENG Qingfang <dqfext@gmail.com>
Date: Mon, 1 Mar 2021 01:08:23 +0800
Subject: [PATCH 0096/1820] net: dsa: tag_rtl4_a: fix egress tags

Commit 86dd9868b878 has several issues, but was accepted too soon
before anyone could take a look.

- Double free. dsa_slave_xmit() will free the skb if the xmit function
  returns NULL, but the skb is already freed by eth_skb_pad(). Use
  __skb_put_padto() to avoid that.
- Unnecessary allocation. It has been done by DSA core since commit
  a3b0b6479700.
- A u16 pointer points to skb data. It should be __be16 for network
  byte order.
- Typo in comments. "numer" -> "number".

Fixes: 86dd9868b878 ("net: dsa: tag_rtl4_a: Support also egress tags")
Signed-off-by: DENG Qingfang <dqfext@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_rtl4_a.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c
index c17d39b4a1a0..e9176475bac8 100644
--- a/net/dsa/tag_rtl4_a.c
+++ b/net/dsa/tag_rtl4_a.c
@@ -35,14 +35,12 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb,
 				      struct net_device *dev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
+	__be16 *p;
 	u8 *tag;
-	u16 *p;
 	u16 out;
 
 	/* Pad out to at least 60 bytes */
-	if (unlikely(eth_skb_pad(skb)))
-		return NULL;
-	if (skb_cow_head(skb, RTL4_A_HDR_LEN) < 0)
+	if (unlikely(__skb_put_padto(skb, ETH_ZLEN, false)))
 		return NULL;
 
 	netdev_dbg(dev, "add realtek tag to package to port %d\n",
@@ -53,13 +51,13 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb,
 	tag = skb->data + 2 * ETH_ALEN;
 
 	/* Set Ethertype */
-	p = (u16 *)tag;
+	p = (__be16 *)tag;
 	*p = htons(RTL4_A_ETHERTYPE);
 
 	out = (RTL4_A_PROTOCOL_RTL8366RB << 12) | (2 << 8);
-	/* The lower bits is the port numer */
+	/* The lower bits is the port number */
 	out |= (u8)dp->index;
-	p = (u16 *)(tag + 2);
+	p = (__be16 *)(tag + 2);
 	*p = htons(out);
 
 	return skb;

From 4372339efc06bc2a796f4cc9d0a7a929dfda4967 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Sat, 27 Feb 2021 01:40:19 +0100
Subject: [PATCH 0097/1820] net: always use icmp{,v6}_ndo_send from
 ndo_start_xmit

There were a few remaining tunnel drivers that didn't receive the prior
conversion to icmp{,v6}_ndo_send. Knowing now that this could lead to
memory corrution (see ee576c47db60 ("net: icmp: pass zeroed opts from
icmp{,v6}_ndo_send before sending") for details), there's even more
imperative to have these all converted. So this commit goes through the
remaining cases that I could find and does a boring translation to the
ndo variety.

The Fixes: line below is the merge that originally added icmp{,v6}_
ndo_send and converted the first batch of icmp{,v6}_send users. The
rationale then for the change applies equally to this patch. It's just
that these drivers were left out of the initial conversion because these
network devices are hiding in net/ rather than in drivers/net/.

Cc: Florian Westphal <fw@strlen.de>
Cc: Willem de Bruijn <willemb@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: David Ahern <dsahern@kernel.org>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Fixes: 803381f9f117 ("Merge branch 'icmp-account-for-NAT-when-sending-icmps-from-ndo-layer'")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c  |  5 ++---
 net/ipv4/ip_vti.c     |  6 +++---
 net/ipv6/ip6_gre.c    | 16 ++++++++--------
 net/ipv6/ip6_tunnel.c | 10 +++++-----
 net/ipv6/ip6_vti.c    |  6 +++---
 net/ipv6/sit.c        |  2 +-
 6 files changed, 22 insertions(+), 23 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 76a420c76f16..f6cc26de5ed3 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -502,8 +502,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 		if (!skb_is_gso(skb) &&
 		    (inner_iph->frag_off & htons(IP_DF)) &&
 		    mtu < pkt_size) {
-			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
+			icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
 			return -E2BIG;
 		}
 	}
@@ -527,7 +526,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 
 		if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
 					mtu < pkt_size) {
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 			return -E2BIG;
 		}
 	}
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index abc171e79d3e..eb207089ece0 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -238,13 +238,13 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 	if (skb->len > mtu) {
 		skb_dst_update_pmtu_no_confirm(skb, mtu);
 		if (skb->protocol == htons(ETH_P_IP)) {
-			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-				  htonl(mtu));
+			icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+				      htonl(mtu));
 		} else {
 			if (mtu < IPV6_MIN_MTU)
 				mtu = IPV6_MIN_MTU;
 
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		}
 
 		dst_release(dst);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c3bc89b6b1a1..1baf43aacb2e 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -678,8 +678,8 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb,
 
 		tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
 		if (tel->encap_limit == 0) {
-			icmpv6_send(skb, ICMPV6_PARAMPROB,
-				    ICMPV6_HDR_FIELD, offset + 2);
+			icmpv6_ndo_send(skb, ICMPV6_PARAMPROB,
+					ICMPV6_HDR_FIELD, offset + 2);
 			return -1;
 		}
 		*encap_limit = tel->encap_limit - 1;
@@ -805,8 +805,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 	if (err != 0) {
 		/* XXX: send ICMP error even if DF is not set. */
 		if (err == -EMSGSIZE)
-			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-				  htonl(mtu));
+			icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+				      htonl(mtu));
 		return -1;
 	}
 
@@ -837,7 +837,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
 			  &mtu, skb->protocol);
 	if (err != 0) {
 		if (err == -EMSGSIZE)
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		return -1;
 	}
 
@@ -1063,10 +1063,10 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 		/* XXX: send ICMP error even if DF is not set. */
 		if (err == -EMSGSIZE) {
 			if (skb->protocol == htons(ETH_P_IP))
-				icmp_send(skb, ICMP_DEST_UNREACH,
-					  ICMP_FRAG_NEEDED, htonl(mtu));
+				icmp_ndo_send(skb, ICMP_DEST_UNREACH,
+					      ICMP_FRAG_NEEDED, htonl(mtu));
 			else
-				icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+				icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		}
 
 		goto tx_err;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a7950baa05e5..3fa0eca5a06f 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1332,8 +1332,8 @@ ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev,
 
 				tel = (void *)&skb_network_header(skb)[offset];
 				if (tel->encap_limit == 0) {
-					icmpv6_send(skb, ICMPV6_PARAMPROB,
-						ICMPV6_HDR_FIELD, offset + 2);
+					icmpv6_ndo_send(skb, ICMPV6_PARAMPROB,
+							ICMPV6_HDR_FIELD, offset + 2);
 					return -1;
 				}
 				encap_limit = tel->encap_limit - 1;
@@ -1385,11 +1385,11 @@ ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev,
 		if (err == -EMSGSIZE)
 			switch (protocol) {
 			case IPPROTO_IPIP:
-				icmp_send(skb, ICMP_DEST_UNREACH,
-					  ICMP_FRAG_NEEDED, htonl(mtu));
+				icmp_ndo_send(skb, ICMP_DEST_UNREACH,
+					      ICMP_FRAG_NEEDED, htonl(mtu));
 				break;
 			case IPPROTO_IPV6:
-				icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+				icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 				break;
 			default:
 				break;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 0225fd694192..f10e7a72ea62 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -521,10 +521,10 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 			if (mtu < IPV6_MIN_MTU)
 				mtu = IPV6_MIN_MTU;
 
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		} else {
-			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-				  htonl(mtu));
+			icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+				      htonl(mtu));
 		}
 
 		err = -EMSGSIZE;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 93636867aee2..63ccd9f2dccc 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -987,7 +987,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 		if (skb->len > mtu && !skb_is_gso(skb)) {
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 			ip_rt_put(rt);
 			goto tx_error;
 		}

From d9032dba5a2b2bbf0fdce67c8795300ec9923b43 Mon Sep 17 00:00:00 2001
From: Guangbin Huang <huangguangbin2@huawei.com>
Date: Sat, 27 Feb 2021 11:05:58 +0800
Subject: [PATCH 0098/1820] net: phy: fix save wrong speed and duplex problem
 if autoneg is on

If phy uses generic driver and autoneg is on, enter command
"ethtool -s eth0 speed 50" will not change phy speed actually, but
command "ethtool eth0" shows speed is 50Mb/s because phydev->speed
has been set to 50 and no update later.

And duplex setting has same problem too.

However, if autoneg is on, phy only changes speed and duplex according to
phydev->advertising, but not phydev->speed and phydev->duplex. So in this
case, phydev->speed and phydev->duplex don't need to be set in function
phy_ethtool_ksettings_set() if autoneg is on.

Fixes: 51e2a3846eab ("PHY: Avoid unnecessary aneg restarts")
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 1be07e45d314..fc2e7cb5b2e5 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -276,14 +276,16 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev,
 
 	phydev->autoneg = autoneg;
 
-	phydev->speed = speed;
+	if (autoneg == AUTONEG_DISABLE) {
+		phydev->speed = speed;
+		phydev->duplex = duplex;
+	}
 
 	linkmode_copy(phydev->advertising, advertising);
 
 	linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
 			 phydev->advertising, autoneg == AUTONEG_ENABLE);
 
-	phydev->duplex = duplex;
 	phydev->master_slave_set = cmd->base.master_slave_cfg;
 	phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl;
 

From 4deb550bc3b698a1f03d0332cde3df154d1b6c1e Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Sat, 27 Feb 2021 16:15:06 -0500
Subject: [PATCH 0099/1820] atm: eni: dont release is never initialized

label err_eni_release is reachable when eni_start() fail.
In eni_start() it calls dev->phy->start() in the last step, if start()
fail we don't need to call phy->stop(), if start() is never called, we
neither need to call phy->stop(), otherwise null-ptr-deref will happen.

In order to fix this issue, don't call phy->stop() in label err_eni_release

[    4.875714] ==================================================================
[    4.876091] BUG: KASAN: null-ptr-deref in suni_stop+0x47/0x100 [suni]
[    4.876433] Read of size 8 at addr 0000000000000030 by task modprobe/95
[    4.876778]
[    4.876862] CPU: 0 PID: 95 Comm: modprobe Not tainted 5.11.0-rc7-00090-gdcc0b49040c7 #2
[    4.877290] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-48-gd94
[    4.877876] Call Trace:
[    4.878009]  dump_stack+0x7d/0xa3
[    4.878191]  kasan_report.cold+0x10c/0x10e
[    4.878410]  ? __slab_free+0x2f0/0x340
[    4.878612]  ? suni_stop+0x47/0x100 [suni]
[    4.878832]  suni_stop+0x47/0x100 [suni]
[    4.879043]  eni_do_release+0x3b/0x70 [eni]
[    4.879269]  eni_init_one.cold+0x1152/0x1747 [eni]
[    4.879528]  ? _raw_spin_lock_irqsave+0x7b/0xd0
[    4.879768]  ? eni_ioctl+0x270/0x270 [eni]
[    4.879990]  ? __mutex_lock_slowpath+0x10/0x10
[    4.880226]  ? eni_ioctl+0x270/0x270 [eni]
[    4.880448]  local_pci_probe+0x6f/0xb0
[    4.880650]  pci_device_probe+0x171/0x240
[    4.880864]  ? pci_device_remove+0xe0/0xe0
[    4.881086]  ? kernfs_create_link+0xb6/0x110
[    4.881315]  ? sysfs_do_create_link_sd.isra.0+0x76/0xe0
[    4.881594]  really_probe+0x161/0x420
[    4.881791]  driver_probe_device+0x6d/0xd0
[    4.882010]  device_driver_attach+0x82/0x90
[    4.882233]  ? device_driver_attach+0x90/0x90
[    4.882465]  __driver_attach+0x60/0x100
[    4.882671]  ? device_driver_attach+0x90/0x90
[    4.882903]  bus_for_each_dev+0xe1/0x140
[    4.883114]  ? subsys_dev_iter_exit+0x10/0x10
[    4.883346]  ? klist_node_init+0x61/0x80
[    4.883557]  bus_add_driver+0x254/0x2a0
[    4.883764]  driver_register+0xd3/0x150
[    4.883971]  ? 0xffffffffc0038000
[    4.884149]  do_one_initcall+0x84/0x250
[    4.884355]  ? trace_event_raw_event_initcall_finish+0x150/0x150
[    4.884674]  ? unpoison_range+0xf/0x30
[    4.884875]  ? ____kasan_kmalloc.constprop.0+0x84/0xa0
[    4.885150]  ? unpoison_range+0xf/0x30
[    4.885352]  ? unpoison_range+0xf/0x30
[    4.885557]  do_init_module+0xf8/0x350
[    4.885760]  load_module+0x3fe6/0x4340
[    4.885960]  ? vm_unmap_ram+0x1d0/0x1d0
[    4.886166]  ? ____kasan_kmalloc.constprop.0+0x84/0xa0
[    4.886441]  ? module_frob_arch_sections+0x20/0x20
[    4.886697]  ? __do_sys_finit_module+0x108/0x170
[    4.886941]  __do_sys_finit_module+0x108/0x170
[    4.887178]  ? __ia32_sys_init_module+0x40/0x40
[    4.887419]  ? file_open_root+0x200/0x200
[    4.887634]  ? do_sys_open+0x85/0xe0
[    4.887826]  ? filp_open+0x50/0x50
[    4.888009]  ? fpregs_assert_state_consistent+0x4d/0x60
[    4.888287]  ? exit_to_user_mode_prepare+0x2f/0x130
[    4.888547]  do_syscall_64+0x33/0x40
[    4.888739]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[    4.889010] RIP: 0033:0x7ff62fcf1cf7
[    4.889202] Code: 48 89 57 30 48 8b 04 24 48 89 47 38 e9 1d a0 02 00 48 89 f8 48 89 f71
[    4.890172] RSP: 002b:00007ffe6644ade8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[    4.890570] RAX: ffffffffffffffda RBX: 0000000000f2ca70 RCX: 00007ff62fcf1cf7
[    4.890944] RDX: 0000000000000000 RSI: 0000000000f2b9e0 RDI: 0000000000000003
[    4.891318] RBP: 0000000000000003 R08: 0000000000000000 R09: 0000000000000001
[    4.891691] R10: 00007ff62fd55300 R11: 0000000000000246 R12: 0000000000f2b9e0
[    4.892064] R13: 0000000000000000 R14: 0000000000f2bdd0 R15: 0000000000000001
[    4.892439] ==================================================================

Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/eni.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index 316a9947541f..b574cce98dc3 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -2260,7 +2260,8 @@ out:
 	return rc;
 
 err_eni_release:
-	eni_do_release(dev);
+	dev->phy = NULL;
+	iounmap(ENI_DEV(dev)->ioaddr);
 err_unregister:
 	atm_dev_deregister(dev);
 err_free_consistent:

From a2bd45834e83d6c5a04d397bde13d744a4812dfc Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Sat, 27 Feb 2021 22:55:50 -0500
Subject: [PATCH 0100/1820] atm: lanai: dont run lanai_dev_close if not open

lanai_dev_open() can fail. When it fail, lanai->base is unmapped and the
pci device is disabled. The caller, lanai_init_one(), then tries to run
atm_dev_deregister(). This will subsequently call lanai_dev_close() and
use the already released MMIO area.

To fix this issue, set the lanai->base to NULL if open fail,
and test the flag in lanai_dev_close().

[    8.324153] lanai: lanai_start() failed, err=19
[    8.324819] lanai(itf 0): shutting down interface
[    8.325211] BUG: unable to handle page fault for address: ffffc90000180024
[    8.325781] #PF: supervisor write access in kernel mode
[    8.326215] #PF: error_code(0x0002) - not-present page
[    8.326641] PGD 100000067 P4D 100000067 PUD 100139067 PMD 10013a067 PTE 0
[    8.327206] Oops: 0002 [#1] SMP KASAN NOPTI
[    8.327557] CPU: 0 PID: 95 Comm: modprobe Not tainted 5.11.0-rc7-00090-gdcc0b49040c7 #12
[    8.328229] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-48-gd9c812dda519-4
[    8.329145] RIP: 0010:lanai_dev_close+0x4f/0xe5 [lanai]
[    8.329587] Code: 00 48 c7 c7 00 d3 01 c0 e8 49 4e 0a c2 48 8d bd 08 02 00 00 e8 6e 52 14 c1 48 80
[    8.330917] RSP: 0018:ffff8881029ef680 EFLAGS: 00010246
[    8.331196] RAX: 000000000003fffe RBX: ffff888102fb4800 RCX: ffffffffc001a98a
[    8.331572] RDX: ffffc90000180000 RSI: 0000000000000246 RDI: ffff888102fb4000
[    8.331948] RBP: ffff888102fb4000 R08: ffffffff8115da8a R09: ffffed102053deaa
[    8.332326] R10: 0000000000000003 R11: ffffed102053dea9 R12: ffff888102fb48a4
[    8.332701] R13: ffffffffc00123c0 R14: ffff888102fb4b90 R15: ffff888102fb4b88
[    8.333077] FS:  00007f08eb9056a0(0000) GS:ffff88815b400000(0000) knlGS:0000000000000000
[    8.333502] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    8.333806] CR2: ffffc90000180024 CR3: 0000000102a28000 CR4: 00000000000006f0
[    8.334182] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[    8.334557] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[    8.334932] Call Trace:
[    8.335066]  atm_dev_deregister+0x161/0x1a0 [atm]
[    8.335324]  lanai_init_one.cold+0x20c/0x96d [lanai]
[    8.335594]  ? lanai_send+0x2a0/0x2a0 [lanai]
[    8.335831]  local_pci_probe+0x6f/0xb0
[    8.336039]  pci_device_probe+0x171/0x240
[    8.336255]  ? pci_device_remove+0xe0/0xe0
[    8.336475]  ? kernfs_create_link+0xb6/0x110
[    8.336704]  ? sysfs_do_create_link_sd.isra.0+0x76/0xe0
[    8.336983]  really_probe+0x161/0x420
[    8.337181]  driver_probe_device+0x6d/0xd0
[    8.337401]  device_driver_attach+0x82/0x90
[    8.337626]  ? device_driver_attach+0x90/0x90
[    8.337859]  __driver_attach+0x60/0x100
[    8.338065]  ? device_driver_attach+0x90/0x90
[    8.338298]  bus_for_each_dev+0xe1/0x140
[    8.338511]  ? subsys_dev_iter_exit+0x10/0x10
[    8.338745]  ? klist_node_init+0x61/0x80
[    8.338956]  bus_add_driver+0x254/0x2a0
[    8.339164]  driver_register+0xd3/0x150
[    8.339370]  ? 0xffffffffc0028000
[    8.339550]  do_one_initcall+0x84/0x250
[    8.339755]  ? trace_event_raw_event_initcall_finish+0x150/0x150
[    8.340076]  ? free_vmap_area_noflush+0x1a5/0x5c0
[    8.340329]  ? unpoison_range+0xf/0x30
[    8.340532]  ? ____kasan_kmalloc.constprop.0+0x84/0xa0
[    8.340806]  ? unpoison_range+0xf/0x30
[    8.341014]  ? unpoison_range+0xf/0x30
[    8.341217]  do_init_module+0xf8/0x350
[    8.341419]  load_module+0x3fe6/0x4340
[    8.341621]  ? vm_unmap_ram+0x1d0/0x1d0
[    8.341826]  ? ____kasan_kmalloc.constprop.0+0x84/0xa0
[    8.342101]  ? module_frob_arch_sections+0x20/0x20
[    8.342358]  ? __do_sys_finit_module+0x108/0x170
[    8.342604]  __do_sys_finit_module+0x108/0x170
[    8.342841]  ? __ia32_sys_init_module+0x40/0x40
[    8.343083]  ? file_open_root+0x200/0x200
[    8.343298]  ? do_sys_open+0x85/0xe0
[    8.343491]  ? filp_open+0x50/0x50
[    8.343675]  ? exit_to_user_mode_prepare+0xfc/0x130
[    8.343935]  do_syscall_64+0x33/0x40
[    8.344132]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[    8.344401] RIP: 0033:0x7f08eb887cf7
[    8.344594] Code: 48 89 57 30 48 8b 04 24 48 89 47 38 e9 1d a0 02 00 48 89 f8 48 89 f7 48 89 d6 41
[    8.345565] RSP: 002b:00007ffcd5c98ad8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[    8.345962] RAX: ffffffffffffffda RBX: 00000000008fea70 RCX: 00007f08eb887cf7
[    8.346336] RDX: 0000000000000000 RSI: 00000000008fd9e0 RDI: 0000000000000003
[    8.346711] RBP: 0000000000000003 R08: 0000000000000000 R09: 0000000000000001
[    8.347085] R10: 00007f08eb8eb300 R11: 0000000000000246 R12: 00000000008fd9e0
[    8.347460] R13: 0000000000000000 R14: 00000000008fddd0 R15: 0000000000000001
[    8.347836] Modules linked in: lanai(+) atm
[    8.348065] CR2: ffffc90000180024
[    8.348244] ---[ end trace 7fdc1c668f2003e5 ]---
[    8.348490] RIP: 0010:lanai_dev_close+0x4f/0xe5 [lanai]
[    8.348772] Code: 00 48 c7 c7 00 d3 01 c0 e8 49 4e 0a c2 48 8d bd 08 02 00 00 e8 6e 52 14 c1 48 80
[    8.349745] RSP: 0018:ffff8881029ef680 EFLAGS: 00010246
[    8.350022] RAX: 000000000003fffe RBX: ffff888102fb4800 RCX: ffffffffc001a98a
[    8.350397] RDX: ffffc90000180000 RSI: 0000000000000246 RDI: ffff888102fb4000
[    8.350772] RBP: ffff888102fb4000 R08: ffffffff8115da8a R09: ffffed102053deaa
[    8.351151] R10: 0000000000000003 R11: ffffed102053dea9 R12: ffff888102fb48a4
[    8.351525] R13: ffffffffc00123c0 R14: ffff888102fb4b90 R15: ffff888102fb4b88
[    8.351918] FS:  00007f08eb9056a0(0000) GS:ffff88815b400000(0000) knlGS:0000000000000000
[    8.352343] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    8.352647] CR2: ffffc90000180024 CR3: 0000000102a28000 CR4: 00000000000006f0
[    8.353022] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[    8.353397] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[    8.353958] modprobe (95) used greatest stack depth: 26216 bytes left

Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/lanai.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/atm/lanai.c b/drivers/atm/lanai.c
index d7277c26e423..32d7aa141d96 100644
--- a/drivers/atm/lanai.c
+++ b/drivers/atm/lanai.c
@@ -2233,6 +2233,7 @@ static int lanai_dev_open(struct atm_dev *atmdev)
 	conf1_write(lanai);
 #endif
 	iounmap(lanai->base);
+	lanai->base = NULL;
     error_pci:
 	pci_disable_device(lanai->pci);
     error:
@@ -2245,6 +2246,8 @@ static int lanai_dev_open(struct atm_dev *atmdev)
 static void lanai_dev_close(struct atm_dev *atmdev)
 {
 	struct lanai_dev *lanai = (struct lanai_dev *) atmdev->dev_data;
+	if (lanai->base==NULL)
+		return;
 	printk(KERN_INFO DEV_LABEL "(itf %d): shutting down interface\n",
 	    lanai->number);
 	lanai_timed_poll_stop(lanai);
@@ -2552,7 +2555,7 @@ static int lanai_init_one(struct pci_dev *pci,
 	struct atm_dev *atmdev;
 	int result;
 
-	lanai = kmalloc(sizeof(*lanai), GFP_KERNEL);
+	lanai = kzalloc(sizeof(*lanai), GFP_KERNEL);
 	if (lanai == NULL) {
 		printk(KERN_ERR DEV_LABEL
 		       ": couldn't allocate dev_data structure!\n");

From 8c91bc3d44dfef8284af384877fbe61117e8b7d1 Mon Sep 17 00:00:00 2001
From: Sergey Shtylyov <s.shtylyov@omprussia.ru>
Date: Sun, 28 Feb 2021 23:25:43 +0300
Subject: [PATCH 0101/1820] sh_eth: fix TRSCER mask for SH771x

According  to  the SH7710, SH7712, SH7713 Group User's Manual: Hardware,
Rev. 3.00, the TRSCER register actually has only bit 7 valid (and named
differently), with all the other bits reserved. Apparently, this was not
the case with some early revisions of the manual as we have the other
bits declared (and set) in the original driver.  Follow the suit and add
the explicit sh_eth_cpu_data::trscer_err_mask initializer for SH771x...

Fixes: 86a74ff21a7a ("net: sh_eth: add support for Renesas SuperH Ethernet")
Signed-off-by: Sergey Shtylyov <s.shtylyov@omprussia.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 590b088bc4c7..e79bb0a3ced5 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1089,6 +1089,9 @@ static struct sh_eth_cpu_data sh771x_data = {
 			  EESIPR_CEEFIP | EESIPR_CELFIP |
 			  EESIPR_RRFIP | EESIPR_RTLFIP | EESIPR_RTSFIP |
 			  EESIPR_PREIP | EESIPR_CERFIP,
+
+	.trscer_err_mask = DESC_I_RINT8,
+
 	.tsu		= 1,
 	.dual_port	= 1,
 };

From 75be7fb7f978202c4c3a1a713af4485afb2ff5f6 Mon Sep 17 00:00:00 2001
From: Sergey Shtylyov <s.shtylyov@omprussia.ru>
Date: Sun, 28 Feb 2021 23:26:34 +0300
Subject: [PATCH 0102/1820] sh_eth: fix TRSCER mask for R7S72100

According  to  the RZ/A1H Group, RZ/A1M Group User's Manual: Hardware,
Rev. 4.00, the TRSCER register has bit 9 reserved, hence we can't use
the driver's default TRSCER mask.  Add the explicit initializer for
sh_eth_cpu_data::trscer_err_mask for R7S72100.

Fixes: db893473d313 ("sh_eth: Add support for r7s72100")
Signed-off-by: Sergey Shtylyov <s.shtylyov@omprussia.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index e79bb0a3ced5..7f14d4aa5b3e 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -560,6 +560,8 @@ static struct sh_eth_cpu_data r7s72100_data = {
 			  EESR_TDE,
 	.fdr_value	= 0x0000070f,
 
+	.trscer_err_mask = DESC_I_RINT8 | DESC_I_RINT5,
+
 	.no_psr		= 1,
 	.apr		= 1,
 	.mpr		= 1,

From 165bc5a4f30eee4735845aa7dbd6b738643f2603 Mon Sep 17 00:00:00 2001
From: Sergey Shtylyov <s.shtylyov@omprussia.ru>
Date: Sun, 28 Feb 2021 23:27:32 +0300
Subject: [PATCH 0103/1820] sh_eth: fix TRSCER mask for R7S9210

According  to the RZ/A2M Group User's Manual: Hardware, Rev. 2.00,
the TRSCER register has bit 9 reserved, hence we can't use the driver's
default TRSCER mask.  Add the explicit initializer for sh_eth_cpu_data::
trscer_err_mask for R7S9210.

Fixes: 6e0bb04d0e4f ("sh_eth: Add R7S9210 support")
Signed-off-by: Sergey Shtylyov <s.shtylyov@omprussia.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 7f14d4aa5b3e..f029c7c03804 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -782,6 +782,8 @@ static struct sh_eth_cpu_data r7s9210_data = {
 
 	.fdr_value	= 0x0000070f,
 
+	.trscer_err_mask = DESC_I_RINT8 | DESC_I_RINT5,
+
 	.apr		= 1,
 	.mpr		= 1,
 	.tpauser	= 1,

From 093b036aa94e01a0bea31a38d7f0ee28a2749023 Mon Sep 17 00:00:00 2001
From: Pavel Skripkin <paskripkin@gmail.com>
Date: Mon, 1 Mar 2021 02:22:40 +0300
Subject: [PATCH 0104/1820] net/qrtr: fix __netdev_alloc_skb call

syzbot found WARNING in __alloc_pages_nodemask()[1] when order >= MAX_ORDER.
It was caused by a huge length value passed from userspace to qrtr_tun_write_iter(),
which tries to allocate skb. Since the value comes from the untrusted source
there is no need to raise a warning in __alloc_pages_nodemask().

[1] WARNING in __alloc_pages_nodemask+0x5f8/0x730 mm/page_alloc.c:5014
Call Trace:
 __alloc_pages include/linux/gfp.h:511 [inline]
 __alloc_pages_node include/linux/gfp.h:524 [inline]
 alloc_pages_node include/linux/gfp.h:538 [inline]
 kmalloc_large_node+0x60/0x110 mm/slub.c:3999
 __kmalloc_node_track_caller+0x319/0x3f0 mm/slub.c:4496
 __kmalloc_reserve net/core/skbuff.c:150 [inline]
 __alloc_skb+0x4e4/0x5a0 net/core/skbuff.c:210
 __netdev_alloc_skb+0x70/0x400 net/core/skbuff.c:446
 netdev_alloc_skb include/linux/skbuff.h:2832 [inline]
 qrtr_endpoint_post+0x84/0x11b0 net/qrtr/qrtr.c:442
 qrtr_tun_write_iter+0x11f/0x1a0 net/qrtr/tun.c:98
 call_write_iter include/linux/fs.h:1901 [inline]
 new_sync_write+0x426/0x650 fs/read_write.c:518
 vfs_write+0x791/0xa30 fs/read_write.c:605
 ksys_write+0x12d/0x250 fs/read_write.c:658
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Reported-by: syzbot+80dccaee7c6630fa9dcf@syzkaller.appspotmail.com
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Acked-by: Alexander Lobakin <alobakin@pm.me>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index b34358282f37..82d2eb8c21d1 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -439,7 +439,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 	if (len == 0 || len & 3)
 		return -EINVAL;
 
-	skb = netdev_alloc_skb(NULL, len);
+	skb = __netdev_alloc_skb(NULL, len, GFP_ATOMIC | __GFP_NOWARN);
 	if (!skb)
 		return -ENOMEM;
 

From 8bd2a05527349c8627d2b9795d3c7a6f76033676 Mon Sep 17 00:00:00 2001
From: Yejune Deng <yejune.deng@gmail.com>
Date: Mon, 1 Mar 2021 14:05:48 +0800
Subject: [PATCH 0105/1820] inetpeer: use div64_ul() and clamp_val() calculate
 inet_peer_threshold

In inet_initpeers(), struct inet_peer on IA32 uses 128 bytes in nowdays.
Get rid of the cascade and use div64_ul() and clamp_val() calculate that
will not need to be adjusted in the future as suggested by Eric Dumazet.

Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Yejune Deng <yejune.deng@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inetpeer.c | 21 +++++++--------------
 1 file changed, 7 insertions(+), 14 deletions(-)

diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index ff327a62c9ce..da21dfce24d7 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -65,7 +65,7 @@ EXPORT_SYMBOL_GPL(inet_peer_base_init);
 #define PEER_MAX_GC 32
 
 /* Exported for sysctl_net_ipv4.  */
-int inet_peer_threshold __read_mostly = 65536 + 128;	/* start to throw entries more
+int inet_peer_threshold __read_mostly;	/* start to throw entries more
 					 * aggressively at this stage */
 int inet_peer_minttl __read_mostly = 120 * HZ;	/* TTL under high load: 120 sec */
 int inet_peer_maxttl __read_mostly = 10 * 60 * HZ;	/* usual time to live: 10 min */
@@ -73,20 +73,13 @@ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ;	/* usual time to live: 10 min
 /* Called from ip_output.c:ip_init  */
 void __init inet_initpeers(void)
 {
-	struct sysinfo si;
+	u64 nr_entries;
 
-	/* Use the straight interface to information about memory. */
-	si_meminfo(&si);
-	/* The values below were suggested by Alexey Kuznetsov
-	 * <kuznet@ms2.inr.ac.ru>.  I don't have any opinion about the values
-	 * myself.  --SAW
-	 */
-	if (si.totalram <= (32768*1024)/PAGE_SIZE)
-		inet_peer_threshold >>= 1; /* max pool size about 1MB on IA32 */
-	if (si.totalram <= (16384*1024)/PAGE_SIZE)
-		inet_peer_threshold >>= 1; /* about 512KB */
-	if (si.totalram <= (8192*1024)/PAGE_SIZE)
-		inet_peer_threshold >>= 2; /* about 128KB */
+	 /* 1% of physical memory */
+	nr_entries = div64_ul((u64)totalram_pages() << PAGE_SHIFT,
+			      100 * L1_CACHE_ALIGN(sizeof(struct inet_peer)));
+
+	inet_peer_threshold = clamp_val(nr_entries, 4096, 65536 + 128);
 
 	peer_cachep = kmem_cache_create("inet_peer_cache",
 			sizeof(struct inet_peer),

From c646d10dda2dcde82c6ce5a474522621ab2b8b19 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 1 Mar 2021 13:18:11 +0200
Subject: [PATCH 0106/1820] net: enetc: don't overwrite the RSS indirection
 table when initializing

After the blamed patch, all RX traffic gets hashed to CPU 0 because the
hashing indirection table set up in:

enetc_pf_probe
-> enetc_alloc_si_resources
   -> enetc_configure_si
      -> enetc_setup_default_rss_table

is overwritten later in:

enetc_pf_probe
-> enetc_init_port_rss_memory

which zero-initializes the entire port RSS table in order to avoid ECC errors.

The trouble really is that enetc_init_port_rss_memory really neads
enetc_alloc_si_resources to be called, because it depends upon
enetc_alloc_cbdr and enetc_setup_cbdr. But that whole enetc_configure_si
thing could have been better thought out, it has nothing to do in a
function called "alloc_si_resources", especially since its counterpart,
"free_si_resources", does nothing to unwind the configuration of the SI.

The point is, we need to pull out enetc_configure_si out of
enetc_alloc_resources, and move it after enetc_init_port_rss_memory.
This allows us to set up the default RSS indirection table after
initializing the memory.

Fixes: 07bf34a50e32 ("net: enetc: initialize the RFS and RSS memories")
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c    | 11 +++--------
 drivers/net/ethernet/freescale/enetc/enetc.h    |  1 +
 drivers/net/ethernet/freescale/enetc/enetc_pf.c |  7 +++++++
 drivers/net/ethernet/freescale/enetc/enetc_vf.c |  7 +++++++
 4 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index c78d12229730..fdb6b9e8da78 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1058,13 +1058,12 @@ static int enetc_setup_default_rss_table(struct enetc_si *si, int num_groups)
 	return 0;
 }
 
-static int enetc_configure_si(struct enetc_ndev_priv *priv)
+int enetc_configure_si(struct enetc_ndev_priv *priv)
 {
 	struct enetc_si *si = priv->si;
 	struct enetc_hw *hw = &si->hw;
 	int err;
 
-	enetc_setup_cbdr(hw, &si->cbd_ring);
 	/* set SI cache attributes */
 	enetc_wr(hw, ENETC_SICAR0,
 		 ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT);
@@ -1112,6 +1111,8 @@ int enetc_alloc_si_resources(struct enetc_ndev_priv *priv)
 	if (err)
 		return err;
 
+	enetc_setup_cbdr(&si->hw, &si->cbd_ring);
+
 	priv->cls_rules = kcalloc(si->num_fs_entries, sizeof(*priv->cls_rules),
 				  GFP_KERNEL);
 	if (!priv->cls_rules) {
@@ -1119,14 +1120,8 @@ int enetc_alloc_si_resources(struct enetc_ndev_priv *priv)
 		goto err_alloc_cls;
 	}
 
-	err = enetc_configure_si(priv);
-	if (err)
-		goto err_config_si;
-
 	return 0;
 
-err_config_si:
-	kfree(priv->cls_rules);
 err_alloc_cls:
 	enetc_clear_cbdr(&si->hw);
 	enetc_free_cbdr(priv->dev, &si->cbd_ring);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 8532d23b54f5..f8275cef3b5c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -292,6 +292,7 @@ void enetc_get_si_caps(struct enetc_si *si);
 void enetc_init_si_rings_params(struct enetc_ndev_priv *priv);
 int enetc_alloc_si_resources(struct enetc_ndev_priv *priv);
 void enetc_free_si_resources(struct enetc_ndev_priv *priv);
+int enetc_configure_si(struct enetc_ndev_priv *priv);
 
 int enetc_open(struct net_device *ndev);
 int enetc_close(struct net_device *ndev);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 515c5b29d7aa..d02ecb2e46ae 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -1108,6 +1108,12 @@ static int enetc_pf_probe(struct pci_dev *pdev,
 		goto err_init_port_rss;
 	}
 
+	err = enetc_configure_si(priv);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to configure SI\n");
+		goto err_config_si;
+	}
+
 	err = enetc_alloc_msix(priv);
 	if (err) {
 		dev_err(&pdev->dev, "MSIX alloc failed\n");
@@ -1136,6 +1142,7 @@ err_phylink_create:
 	enetc_mdiobus_destroy(pf);
 err_mdiobus_create:
 	enetc_free_msix(priv);
+err_config_si:
 err_init_port_rss:
 err_init_port_rfs:
 err_alloc_msix:
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
index 39c1a09e69a9..9b755a84c2d6 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -171,6 +171,12 @@ static int enetc_vf_probe(struct pci_dev *pdev,
 		goto err_alloc_si_res;
 	}
 
+	err = enetc_configure_si(priv);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to configure SI\n");
+		goto err_config_si;
+	}
+
 	err = enetc_alloc_msix(priv);
 	if (err) {
 		dev_err(&pdev->dev, "MSIX alloc failed\n");
@@ -187,6 +193,7 @@ static int enetc_vf_probe(struct pci_dev *pdev,
 
 err_reg_netdev:
 	enetc_free_msix(priv);
+err_config_si:
 err_alloc_msix:
 	enetc_free_si_resources(priv);
 err_alloc_si_res:

From 3222b5b613db558e9a494bbf53f3c984d90f71ea Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 1 Mar 2021 13:18:12 +0200
Subject: [PATCH 0107/1820] net: enetc: initialize RFS/RSS memories for unused
 ports too

Michael reports that since linux-next-20210211, the AER messages for ECC
errors have started reappearing, and this time they can be reliably
reproduced with the first ping on one of his LS1028A boards.

$ ping 1[   33.258069] pcieport 0000:00:1f.0: AER: Multiple Corrected error received: 0000:00:00.0
72.16.0.1
PING [   33.267050] pcieport 0000:00:1f.0: AER: can't find device of ID0000
172.16.0.1 (172.16.0.1): 56 data bytes
64 bytes from 172.16.0.1: seq=0 ttl=64 time=17.124 ms
64 bytes from 172.16.0.1: seq=1 ttl=64 time=0.273 ms

$ devmem 0x1f8010e10 32
0xC0000006

It isn't clear why this is necessary, but it seems that for the errors
to go away, we must clear the entire RFS and RSS memory, not just for
the ports in use.

Sadly the code is structured in such a way that we can't have unified
logic for the used and unused ports. For the minimal initialization of
an unused port, we need just to enable and ioremap the PF memory space,
and a control buffer descriptor ring. Unused ports must then free the
CBDR because the driver will exit, but used ports can not pick up from
where that code path left, since the CBDR API does not reinitialize a
ring when setting it up, so its producer and consumer indices are out of
sync between the software and hardware state. So a separate
enetc_init_unused_port function was created, and it gets called right
after the PF memory space is enabled.

Fixes: 07bf34a50e32 ("net: enetc: initialize the RFS and RSS memories")
Reported-by: Michael Walle <michael@walle.cc>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Michael Walle <michael@walle.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c  |  8 ++---
 drivers/net/ethernet/freescale/enetc/enetc.h  |  4 +++
 .../net/ethernet/freescale/enetc/enetc_pf.c   | 33 ++++++++++++++++---
 3 files changed, 36 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index fdb6b9e8da78..eb45830a1667 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -984,7 +984,7 @@ static void enetc_free_rxtx_rings(struct enetc_ndev_priv *priv)
 		enetc_free_tx_ring(priv->tx_ring[i]);
 }
 
-static int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
+int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
 {
 	int size = cbdr->bd_count * sizeof(struct enetc_cbd);
 
@@ -1005,7 +1005,7 @@ static int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
 	return 0;
 }
 
-static void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
+void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
 {
 	int size = cbdr->bd_count * sizeof(struct enetc_cbd);
 
@@ -1013,7 +1013,7 @@ static void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
 	cbdr->bd_base = NULL;
 }
 
-static void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr)
+void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr)
 {
 	/* set CBDR cache attributes */
 	enetc_wr(hw, ENETC_SICAR2,
@@ -1033,7 +1033,7 @@ static void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr)
 	cbdr->cir = hw->reg + ENETC_SICBDRCIR;
 }
 
-static void enetc_clear_cbdr(struct enetc_hw *hw)
+void enetc_clear_cbdr(struct enetc_hw *hw)
 {
 	enetc_wr(hw, ENETC_SICBDRMR, 0);
 }
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index f8275cef3b5c..8b380fc13314 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -310,6 +310,10 @@ int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 void enetc_set_ethtool_ops(struct net_device *ndev);
 
 /* control buffer descriptor ring (CBDR) */
+int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr);
+void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr);
+void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr);
+void enetc_clear_cbdr(struct enetc_hw *hw);
 int enetc_set_mac_flt_entry(struct enetc_si *si, int index,
 			    char *mac_addr, int si_map);
 int enetc_clear_mac_flt_entry(struct enetc_si *si, int index);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index d02ecb2e46ae..62ba4bf56f0d 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -1041,6 +1041,26 @@ static int enetc_init_port_rss_memory(struct enetc_si *si)
 	return err;
 }
 
+static void enetc_init_unused_port(struct enetc_si *si)
+{
+	struct device *dev = &si->pdev->dev;
+	struct enetc_hw *hw = &si->hw;
+	int err;
+
+	si->cbd_ring.bd_count = ENETC_CBDR_DEFAULT_SIZE;
+	err = enetc_alloc_cbdr(dev, &si->cbd_ring);
+	if (err)
+		return;
+
+	enetc_setup_cbdr(hw, &si->cbd_ring);
+
+	enetc_init_port_rfs_memory(si);
+	enetc_init_port_rss_memory(si);
+
+	enetc_clear_cbdr(hw);
+	enetc_free_cbdr(dev, &si->cbd_ring);
+}
+
 static int enetc_pf_probe(struct pci_dev *pdev,
 			  const struct pci_device_id *ent)
 {
@@ -1051,11 +1071,6 @@ static int enetc_pf_probe(struct pci_dev *pdev,
 	struct enetc_pf *pf;
 	int err;
 
-	if (node && !of_device_is_available(node)) {
-		dev_info(&pdev->dev, "device is disabled, skipping\n");
-		return -ENODEV;
-	}
-
 	err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(*pf));
 	if (err) {
 		dev_err(&pdev->dev, "PCI probing failed\n");
@@ -1069,6 +1084,13 @@ static int enetc_pf_probe(struct pci_dev *pdev,
 		goto err_map_pf_space;
 	}
 
+	if (node && !of_device_is_available(node)) {
+		enetc_init_unused_port(si);
+		dev_info(&pdev->dev, "device is disabled, skipping\n");
+		err = -ENODEV;
+		goto err_device_disabled;
+	}
+
 	pf = enetc_si_priv(si);
 	pf->si = si;
 	pf->total_vfs = pci_sriov_get_totalvfs(pdev);
@@ -1151,6 +1173,7 @@ err_alloc_si_res:
 	si->ndev = NULL;
 	free_netdev(ndev);
 err_alloc_netdev:
+err_device_disabled:
 err_map_pf_space:
 	enetc_pci_remove(pdev);
 

From 6d36ecdbc4410e61a0e02adc5d3abeee22a8ffd3 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 1 Mar 2021 13:18:13 +0200
Subject: [PATCH 0108/1820] net: enetc: take the MDIO lock only once per NAPI
 poll cycle

The workaround for the ENETC MDIO erratum caused a performance
degradation of 82 Kpps (seen with IP forwarding of two 1Gbps streams of
64B packets). This is due to excessive locking and unlocking in the fast
path, which can be avoided.

By taking the MDIO read-side lock only once per NAPI poll cycle, we are
able to regain 54 Kpps (65%) of the performance hit. The rest of the
performance degradation comes from the TX data path, but unfortunately
it doesn't look like we can optimize that away easily, even with
netdev_xmit_more(), there just isn't any skb batching done, to help with
taking the MDIO lock less often than once per packet.

We need to change the register accessor type for enetc_get_tx_tstamp,
because it now runs under the enetc_lock_mdio as per the new call path
detailed below:

enetc_msix
-> napi_schedule
   -> enetc_poll
      -> enetc_lock_mdio
      -> enetc_clean_tx_ring
         -> enetc_get_tx_tstamp
      -> enetc_clean_rx_ring
      -> enetc_unlock_mdio

Fixes: fd5736bf9f23 ("enetc: Workaround for MDIO register access issue")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c  | 31 ++++++-------------
 .../net/ethernet/freescale/enetc/enetc_hw.h   |  2 ++
 2 files changed, 11 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index eb45830a1667..9bcceb74fb9c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -281,6 +281,8 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 	int work_done;
 	int i;
 
+	enetc_lock_mdio();
+
 	for (i = 0; i < v->count_tx_rings; i++)
 		if (!enetc_clean_tx_ring(&v->tx_ring[i], budget))
 			complete = false;
@@ -291,8 +293,10 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 	if (work_done)
 		v->rx_napi_work = true;
 
-	if (!complete)
+	if (!complete) {
+		enetc_unlock_mdio();
 		return budget;
+	}
 
 	napi_complete_done(napi, work_done);
 
@@ -301,8 +305,6 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 
 	v->rx_napi_work = false;
 
-	enetc_lock_mdio();
-
 	/* enable interrupts */
 	enetc_wr_reg_hot(v->rbier, ENETC_RBIER_RXTIE);
 
@@ -327,8 +329,8 @@ static void enetc_get_tx_tstamp(struct enetc_hw *hw, union enetc_tx_bd *txbd,
 {
 	u32 lo, hi, tstamp_lo;
 
-	lo = enetc_rd(hw, ENETC_SICTR0);
-	hi = enetc_rd(hw, ENETC_SICTR1);
+	lo = enetc_rd_hot(hw, ENETC_SICTR0);
+	hi = enetc_rd_hot(hw, ENETC_SICTR1);
 	tstamp_lo = le32_to_cpu(txbd->wb.tstamp);
 	if (lo <= tstamp_lo)
 		hi -= 1;
@@ -358,9 +360,7 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget)
 	i = tx_ring->next_to_clean;
 	tx_swbd = &tx_ring->tx_swbd[i];
 
-	enetc_lock_mdio();
 	bds_to_clean = enetc_bd_ready_count(tx_ring, i);
-	enetc_unlock_mdio();
 
 	do_tstamp = false;
 
@@ -403,8 +403,6 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget)
 			tx_swbd = tx_ring->tx_swbd;
 		}
 
-		enetc_lock_mdio();
-
 		/* BD iteration loop end */
 		if (is_eof) {
 			tx_frm_cnt++;
@@ -415,8 +413,6 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget)
 
 		if (unlikely(!bds_to_clean))
 			bds_to_clean = enetc_bd_ready_count(tx_ring, i);
-
-		enetc_unlock_mdio();
 	}
 
 	tx_ring->next_to_clean = i;
@@ -660,8 +656,6 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
 		u32 bd_status;
 		u16 size;
 
-		enetc_lock_mdio();
-
 		if (cleaned_cnt >= ENETC_RXBD_BUNDLE) {
 			int count = enetc_refill_rx_ring(rx_ring, cleaned_cnt);
 
@@ -672,19 +666,15 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
 
 		rxbd = enetc_rxbd(rx_ring, i);
 		bd_status = le32_to_cpu(rxbd->r.lstatus);
-		if (!bd_status) {
-			enetc_unlock_mdio();
+		if (!bd_status)
 			break;
-		}
 
 		enetc_wr_reg_hot(rx_ring->idr, BIT(rx_ring->index));
 		dma_rmb(); /* for reading other rxbd fields */
 		size = le16_to_cpu(rxbd->r.buf_len);
 		skb = enetc_map_rx_buff_to_skb(rx_ring, i, size);
-		if (!skb) {
-			enetc_unlock_mdio();
+		if (!skb)
 			break;
-		}
 
 		enetc_get_offloads(rx_ring, rxbd, skb);
 
@@ -696,7 +686,6 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
 
 		if (unlikely(bd_status &
 			     ENETC_RXBD_LSTATUS(ENETC_RXBD_ERR_MASK))) {
-			enetc_unlock_mdio();
 			dev_kfree_skb(skb);
 			while (!(bd_status & ENETC_RXBD_LSTATUS_F)) {
 				dma_rmb();
@@ -736,8 +725,6 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
 
 		enetc_process_skb(rx_ring, skb);
 
-		enetc_unlock_mdio();
-
 		napi_gro_receive(napi, skb);
 
 		rx_frm_cnt++;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index c71fe8d751d5..8b54562f5da6 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -453,6 +453,8 @@ static inline u64 _enetc_rd_reg64_wa(void __iomem *reg)
 #define enetc_wr_reg(reg, val)		_enetc_wr_reg_wa((reg), (val))
 #define enetc_rd(hw, off)		enetc_rd_reg((hw)->reg + (off))
 #define enetc_wr(hw, off, val)		enetc_wr_reg((hw)->reg + (off), val)
+#define enetc_rd_hot(hw, off)		enetc_rd_reg_hot((hw)->reg + (off))
+#define enetc_wr_hot(hw, off, val)	enetc_wr_reg_hot((hw)->reg + (off), val)
 #define enetc_rd64(hw, off)		_enetc_rd_reg64_wa((hw)->reg + (off))
 /* port register accessors - PF only */
 #define enetc_port_rd(hw, off)		enetc_rd_reg((hw)->port + (off))

From 827b6fd046516af605e190c872949f22208b5d41 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 1 Mar 2021 13:18:14 +0200
Subject: [PATCH 0109/1820] net: enetc: fix incorrect TPID when receiving
 802.1ad tagged packets

When the enetc ports have rx-vlan-offload enabled, they report a TPID of
ETH_P_8021Q regardless of what was actually in the packet. When
rx-vlan-offload is disabled, packets have the proper TPID. Fix this
inconsistency by finishing the TODO left in the code.

Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c  | 34 ++++++++++++++-----
 .../net/ethernet/freescale/enetc/enetc_hw.h   |  3 ++
 2 files changed, 29 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 9bcceb74fb9c..8ddf0cdc37a5 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -523,9 +523,8 @@ static void enetc_get_rx_tstamp(struct net_device *ndev,
 static void enetc_get_offloads(struct enetc_bdr *rx_ring,
 			       union enetc_rx_bd *rxbd, struct sk_buff *skb)
 {
-#ifdef CONFIG_FSL_ENETC_PTP_CLOCK
 	struct enetc_ndev_priv *priv = netdev_priv(rx_ring->ndev);
-#endif
+
 	/* TODO: hashing */
 	if (rx_ring->ndev->features & NETIF_F_RXCSUM) {
 		u16 inet_csum = le16_to_cpu(rxbd->r.inet_csum);
@@ -534,12 +533,31 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring,
 		skb->ip_summed = CHECKSUM_COMPLETE;
 	}
 
-	/* copy VLAN to skb, if one is extracted, for now we assume it's a
-	 * standard TPID, but HW also supports custom values
-	 */
-	if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN)
-		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
-				       le16_to_cpu(rxbd->r.vlan_opt));
+	if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN) {
+		__be16 tpid = 0;
+
+		switch (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TPID) {
+		case 0:
+			tpid = htons(ETH_P_8021Q);
+			break;
+		case 1:
+			tpid = htons(ETH_P_8021AD);
+			break;
+		case 2:
+			tpid = htons(enetc_port_rd(&priv->si->hw,
+						   ENETC_PCVLANR1));
+			break;
+		case 3:
+			tpid = htons(enetc_port_rd(&priv->si->hw,
+						   ENETC_PCVLANR2));
+			break;
+		default:
+			break;
+		}
+
+		__vlan_hwaccel_put_tag(skb, tpid, le16_to_cpu(rxbd->r.vlan_opt));
+	}
+
 #ifdef CONFIG_FSL_ENETC_PTP_CLOCK
 	if (priv->active_offloads & ENETC_F_RX_TSTAMP)
 		enetc_get_rx_tstamp(rx_ring->ndev, rxbd, skb);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 8b54562f5da6..a62604a1e54e 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -172,6 +172,8 @@ enum enetc_bdr_type {TX, RX};
 #define ENETC_PSIPMAR0(n)	(0x0100 + (n) * 0x8) /* n = SI index */
 #define ENETC_PSIPMAR1(n)	(0x0104 + (n) * 0x8)
 #define ENETC_PVCLCTR		0x0208
+#define ENETC_PCVLANR1		0x0210
+#define ENETC_PCVLANR2		0x0214
 #define ENETC_VLAN_TYPE_C	BIT(0)
 #define ENETC_VLAN_TYPE_S	BIT(1)
 #define ENETC_PVCLCTR_OVTPIDL(bmp)	((bmp) & 0xff) /* VLAN_TYPE */
@@ -570,6 +572,7 @@ union enetc_rx_bd {
 #define ENETC_RXBD_LSTATUS(flags)	((flags) << 16)
 #define ENETC_RXBD_FLAG_VLAN	BIT(9)
 #define ENETC_RXBD_FLAG_TSTMP	BIT(10)
+#define ENETC_RXBD_FLAG_TPID	GENMASK(1, 0)
 
 #define ENETC_MAC_ADDR_FILT_CNT	8 /* # of supported entries per port */
 #define EMETC_MAC_ADDR_FILT_RES	3 /* # of reserved entries at the beginning */

From a74dbce9d4541888fe0d39afe69a3a95004669b4 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 1 Mar 2021 13:18:15 +0200
Subject: [PATCH 0110/1820] net: enetc: don't disable VLAN filtering in
 IFF_PROMISC mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Quoting from the blamed commit:

    In promiscuous mode, it is more intuitive that all traffic is received,
    including VLAN tagged traffic. It appears that it is necessary to set
    the flag in PSIPVMR for that to be the case, so VLAN promiscuous mode is
    also temporarily enabled. On exit from promiscuous mode, the setting
    made by ethtool is restored.

Intuitive or not, there isn't any definition issued by a standards body
which says that promiscuity has anything to do with VLAN filtering - it
only has to do with accepting packets regardless of destination MAC address.

In fact people are already trying to use this misunderstanding/bug of
the enetc driver as a justification to transform promiscuity into
something it never was about: accepting every packet (maybe that would
be the "rx-all" netdev feature?):
https://lore.kernel.org/netdev/20201110153958.ci5ekor3o2ekg3ky@ipetronik.com/

This is relevant because there are use cases in the kernel (such as
tc-flower rules with the protocol 802.1Q and a vlan_id key) which do not
(yet) use the vlan_vid_add API to be compatible with VLAN-filtering NICs
such as enetc, so for those, disabling rx-vlan-filter is currently the
only right solution to make these setups work:
https://lore.kernel.org/netdev/CA+h21hoxwRdhq4y+w8Kwgm74d4cA0xLeiHTrmT-VpSaM7obhkg@mail.gmail.com/
The blamed patch has unintentionally introduced one more way for this to
work, which is to enable IFF_PROMISC, however this is non-portable
because port promiscuity is not meant to disable VLAN filtering.
Therefore, it could invite people to write broken scripts for enetc, and
then wonder why they are broken when migrating to other drivers that
don't handle promiscuity in the same way.

Fixes: 7070eea5e95a ("enetc: permit configuration of rx-vlan-filter with ethtool")
Cc: Markus Blöchl <Markus.Bloechl@ipetronik.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc_pf.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 62ba4bf56f0d..49681a0566ed 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -190,7 +190,6 @@ static void enetc_pf_set_rx_mode(struct net_device *ndev)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct enetc_pf *pf = enetc_si_priv(priv->si);
-	char vlan_promisc_simap = pf->vlan_promisc_simap;
 	struct enetc_hw *hw = &priv->si->hw;
 	bool uprom = false, mprom = false;
 	struct enetc_mac_filter *filter;
@@ -203,16 +202,12 @@ static void enetc_pf_set_rx_mode(struct net_device *ndev)
 		psipmr = ENETC_PSIPMR_SET_UP(0) | ENETC_PSIPMR_SET_MP(0);
 		uprom = true;
 		mprom = true;
-		/* Enable VLAN promiscuous mode for SI0 (PF) */
-		vlan_promisc_simap |= BIT(0);
 	} else if (ndev->flags & IFF_ALLMULTI) {
 		/* enable multi cast promisc mode for SI0 (PF) */
 		psipmr = ENETC_PSIPMR_SET_MP(0);
 		mprom = true;
 	}
 
-	enetc_set_vlan_promisc(&pf->si->hw, vlan_promisc_simap);
-
 	/* first 2 filter entries belong to PF */
 	if (!uprom) {
 		/* Update unicast filters */

From c76a97218dcbb2cb7cec1404ace43ef96c87d874 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 1 Mar 2021 13:18:16 +0200
Subject: [PATCH 0111/1820] net: enetc: force the RGMII speed and duplex
 instead of operating in inband mode

The ENETC port 0 MAC supports in-band status signaling coming from a PHY
when operating in RGMII mode, and this feature is enabled by default.

It has been reported that RGMII is broken in fixed-link, and that is not
surprising considering the fact that no PHY is attached to the MAC in
that case, but a switch.

This brings us to the topic of the patch: the enetc driver should have
not enabled the optional in-band status signaling for RGMII unconditionally,
but should have forced the speed and duplex to what was resolved by
phylink.

Note that phylink does not accept the RGMII modes as valid for in-band
signaling, and these operate a bit differently than 1000base-x and SGMII
(notably there is no clause 37 state machine so no ACK required from the
MAC, instead the PHY sends extra code words on RXD[3:0] whenever it is
not transmitting something else, so it should be safe to leave a PHY
with this option unconditionally enabled even if we ignore it). The spec
talks about this here:
https://e2e.ti.com/cfs-file/__key/communityserver-discussions-components-files/138/RGMIIv1_5F00_3.pdf

Fixes: 71b77a7a27a3 ("enetc: Migrate to PHYLINK and PCS_LYNX")
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/freescale/enetc/enetc_hw.h   | 13 +++--
 .../net/ethernet/freescale/enetc/enetc_pf.c   | 53 ++++++++++++++++---
 2 files changed, 56 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index a62604a1e54e..de0d20b0f489 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -238,10 +238,17 @@ enum enetc_bdr_type {TX, RX};
 #define ENETC_PM_IMDIO_BASE	0x8030
 
 #define ENETC_PM0_IF_MODE	0x8300
-#define ENETC_PMO_IFM_RG	BIT(2)
+#define ENETC_PM0_IFM_RG	BIT(2)
 #define ENETC_PM0_IFM_RLP	(BIT(5) | BIT(11))
-#define ENETC_PM0_IFM_RGAUTO	(BIT(15) | ENETC_PMO_IFM_RG | BIT(1))
-#define ENETC_PM0_IFM_XGMII	BIT(12)
+#define ENETC_PM0_IFM_EN_AUTO	BIT(15)
+#define ENETC_PM0_IFM_SSP_MASK	GENMASK(14, 13)
+#define ENETC_PM0_IFM_SSP_1000	(2 << 13)
+#define ENETC_PM0_IFM_SSP_100	(0 << 13)
+#define ENETC_PM0_IFM_SSP_10	(1 << 13)
+#define ENETC_PM0_IFM_FULL_DPX	BIT(12)
+#define ENETC_PM0_IFM_IFMODE_MASK GENMASK(1, 0)
+#define ENETC_PM0_IFM_IFMODE_XGMII 0
+#define ENETC_PM0_IFM_IFMODE_GMII 2
 #define ENETC_PSIDCAPR		0x1b08
 #define ENETC_PSIDCAPR_MSK	GENMASK(15, 0)
 #define ENETC_PSFCAPR		0x1b18
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 49681a0566ed..ca02f033bea2 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -315,7 +315,7 @@ static void enetc_set_loopback(struct net_device *ndev, bool en)
 	u32 reg;
 
 	reg = enetc_port_rd(hw, ENETC_PM0_IF_MODE);
-	if (reg & ENETC_PMO_IFM_RG) {
+	if (reg & ENETC_PM0_IFM_RG) {
 		/* RGMII mode */
 		reg = (reg & ~ENETC_PM0_IFM_RLP) |
 		      (en ? ENETC_PM0_IFM_RLP : 0);
@@ -494,13 +494,20 @@ static void enetc_configure_port_mac(struct enetc_hw *hw)
 
 static void enetc_mac_config(struct enetc_hw *hw, phy_interface_t phy_mode)
 {
-	/* set auto-speed for RGMII */
-	if (enetc_port_rd(hw, ENETC_PM0_IF_MODE) & ENETC_PMO_IFM_RG ||
-	    phy_interface_mode_is_rgmii(phy_mode))
-		enetc_port_wr(hw, ENETC_PM0_IF_MODE, ENETC_PM0_IFM_RGAUTO);
+	u32 val;
 
-	if (phy_mode == PHY_INTERFACE_MODE_USXGMII)
-		enetc_port_wr(hw, ENETC_PM0_IF_MODE, ENETC_PM0_IFM_XGMII);
+	if (phy_interface_mode_is_rgmii(phy_mode)) {
+		val = enetc_port_rd(hw, ENETC_PM0_IF_MODE);
+		val &= ~ENETC_PM0_IFM_EN_AUTO;
+		val &= ENETC_PM0_IFM_IFMODE_MASK;
+		val |= ENETC_PM0_IFM_IFMODE_GMII | ENETC_PM0_IFM_RG;
+		enetc_port_wr(hw, ENETC_PM0_IF_MODE, val);
+	}
+
+	if (phy_mode == PHY_INTERFACE_MODE_USXGMII) {
+		val = ENETC_PM0_IFM_FULL_DPX | ENETC_PM0_IFM_IFMODE_XGMII;
+		enetc_port_wr(hw, ENETC_PM0_IF_MODE, val);
+	}
 }
 
 static void enetc_mac_enable(struct enetc_hw *hw, bool en)
@@ -932,6 +939,34 @@ static void enetc_pl_mac_config(struct phylink_config *config,
 		phylink_set_pcs(priv->phylink, &pf->pcs->pcs);
 }
 
+static void enetc_force_rgmii_mac(struct enetc_hw *hw, int speed, int duplex)
+{
+	u32 old_val, val;
+
+	old_val = val = enetc_port_rd(hw, ENETC_PM0_IF_MODE);
+
+	if (speed == SPEED_1000) {
+		val &= ~ENETC_PM0_IFM_SSP_MASK;
+		val |= ENETC_PM0_IFM_SSP_1000;
+	} else if (speed == SPEED_100) {
+		val &= ~ENETC_PM0_IFM_SSP_MASK;
+		val |= ENETC_PM0_IFM_SSP_100;
+	} else if (speed == SPEED_10) {
+		val &= ~ENETC_PM0_IFM_SSP_MASK;
+		val |= ENETC_PM0_IFM_SSP_10;
+	}
+
+	if (duplex == DUPLEX_FULL)
+		val |= ENETC_PM0_IFM_FULL_DPX;
+	else
+		val &= ~ENETC_PM0_IFM_FULL_DPX;
+
+	if (val == old_val)
+		return;
+
+	enetc_port_wr(hw, ENETC_PM0_IF_MODE, val);
+}
+
 static void enetc_pl_mac_link_up(struct phylink_config *config,
 				 struct phy_device *phy, unsigned int mode,
 				 phy_interface_t interface, int speed,
@@ -944,6 +979,10 @@ static void enetc_pl_mac_link_up(struct phylink_config *config,
 	if (priv->active_offloads & ENETC_F_QBV)
 		enetc_sched_speed_set(priv, speed);
 
+	if (!phylink_autoneg_inband(mode) &&
+	    phy_interface_mode_is_rgmii(interface))
+		enetc_force_rgmii_mac(&pf->si->hw, speed, duplex);
+
 	enetc_mac_enable(&pf->si->hw, true);
 }
 

From 96a5223b918c8b79270fc0fec235a7ebad459098 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 1 Mar 2021 13:18:17 +0200
Subject: [PATCH 0112/1820] net: enetc: remove bogus write to SIRXIDR from
 enetc_setup_rxbdr

The Station Interface Receive Interrupt Detect Register (SIRXIDR)
contains a 16-bit wide mask of 'interrupt detected' events for each ring
associated with a port. Bit i is write-1-to-clean for RX ring i.

I have no explanation whatsoever how this line of code came to be
inserted in the blamed commit. I checked the downstream versions of that
patch and none of them have it.

The somewhat comical aspect of it is that we're writing a binary number
to the SIRXIDR register, which is derived from enetc_bd_unused(rx_ring).
Since the RX rings have 512 buffer descriptors, we end up writing 511 to
this register, which is 0x1ff, so we are effectively clearing the
'interrupt detected' event for rings 0-8.

This register is not what is used for interrupt handling though - it
only provides a summary for the entire SI. The hardware provides one
separate Interrupt Detect Register per RX ring, which auto-clears upon
read. So there doesn't seem to be any adverse effect caused by this
bogus write.

There is, however, one reason why this should be handled as a bugfix:
next_to_clean _should_ be committed to hardware, just not to that
register, and this was obscuring the fact that it wasn't. This is fixed
in the next patch, and removing the bogus line now allows the fix patch
to be backported beyond that point.

Fixes: fd5736bf9f23 ("enetc: Workaround for MDIO register access issue")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 8ddf0cdc37a5..abb29ee81463 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1212,7 +1212,6 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring)
 	rx_ring->idr = hw->reg + ENETC_SIRXIDR;
 
 	enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring));
-	enetc_wr(hw, ENETC_SIRXIDR, rx_ring->next_to_use);
 
 	/* enable ring */
 	enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr);

From 3a5d12c9be6f30080600c8bacaf310194e37d029 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 1 Mar 2021 13:18:18 +0200
Subject: [PATCH 0113/1820] net: enetc: keep RX ring consumer index in sync
 with hardware

The RX rings have a producer index owned by hardware, where newly
received frame buffers are placed, and a consumer index owned by
software, where newly allocated buffers are placed, in expectation of
hardware being able to place frame data in them.

Hardware increments the producer index when a frame is received, however
it is not allowed to increment the producer index to match the consumer
index (RBCIR) since the ring can hold at most RBLENR[LENGTH]-1 received
BDs. Whenever the producer index matches the value of the consumer
index, the ring has no unprocessed received frames and all BDs in the
ring have been initialized/prepared by software, i.e. hardware owns all
BDs in the ring.

The code uses the next_to_clean variable to keep track of the producer
index, and the next_to_use variable to keep track of the consumer index.

The RX rings are seeded from enetc_refill_rx_ring, which is called from
two places:

1. initially the ring is seeded until full with enetc_bd_unused(rx_ring),
   i.e. with 511 buffers. This will make next_to_clean=0 and next_to_use=511:

.ndo_open
-> enetc_open
   -> enetc_setup_bdrs
      -> enetc_setup_rxbdr
         -> enetc_refill_rx_ring

2. then during the data path processing, it is refilled with 16 buffers
   at a time:

enetc_msix
-> napi_schedule
   -> enetc_poll
      -> enetc_clean_rx_ring
         -> enetc_refill_rx_ring

There is just one problem: the initial seeding done during .ndo_open
updates just the producer index (ENETC_RBPIR) with 0, and the software
next_to_clean and next_to_use variables. Notably, it will not update the
consumer index to make the hardware aware of the newly added buffers.

Wait, what? So how does it work?

Well, the reset values of the producer index and of the consumer index
of a ring are both zero. As per the description in the second paragraph,
it means that the ring is full of buffers waiting for hardware to put
frames in them, which by coincidence is almost true, because we have in
fact seeded 511 buffers into the ring.

But will the hardware attempt to access the 512th entry of the ring,
which has an invalid BD in it? Well, no, because in order to do that, it
would have to first populate the first 511 entries, and the NAPI
enetc_poll will kick in by then. Eventually, after 16 processed slots
have become available in the RX ring, enetc_clean_rx_ring will call
enetc_refill_rx_ring and then will [ finally ] update the consumer index
with the new software next_to_use variable. From now on, the
next_to_clean and next_to_use variables are in sync with the producer
and consumer ring indices.

So the day is saved, right? Well, not quite. Freeing the memory
allocated for the rings is done in:

enetc_close
-> enetc_clear_bdrs
   -> enetc_clear_rxbdr
      -> this just disables the ring
-> enetc_free_rxtx_rings
   -> enetc_free_rx_ring
      -> sets next_to_clean and next_to_use to 0

but again, nothing is committed to the hardware producer and consumer
indices (yay!). The assumption is that the ring is disabled, so the
indices don't matter anyway, and it's the responsibility of the "open"
code path to set those up.

.. Except that the "open" code path does not set those up properly.

While initially, things almost work, during subsequent enetc_close ->
enetc_open sequences, we have problems. To be precise, the enetc_open
that is subsequent to enetc_close will again refill the ring with 511
entries, but it will leave the consumer index untouched. Untouched
means, of course, equal to the value it had before disabling the ring
and draining the old buffers in enetc_close.

But as mentioned, enetc_setup_rxbdr will at least update the producer
index though, through this line of code:

	enetc_rxbdr_wr(hw, idx, ENETC_RBPIR, 0);

so at this stage we'll have:

next_to_clean=0 (in hardware 0)
next_to_use=511 (in hardware we'll have the refill index prior to enetc_close)

Again, the next_to_clean and producer index are in sync and set to
correct values, so the driver manages to limp on. Eventually, 16 ring
entries will be consumed by enetc_poll, and the savior
enetc_clean_rx_ring will come and call enetc_refill_rx_ring, and then
update the hardware consumer ring based upon the new next_to_use.

So.. it works?
Well, by coincidence, it almost does, but there's a circumstance where
enetc_clean_rx_ring won't be there to save us. If the previous value of
the consumer index was 15, there's a problem, because the NAPI poll
sequence will only issue a refill when 16 or more buffers have been
consumed.

It's easiest to illustrate this with an example:

ip link set eno0 up
ip addr add 192.168.100.1/24 dev eno0
ping 192.168.100.1 -c 20 # ping this port from another board
ip link set eno0 down
ip link set eno0 up
ping 192.168.100.1 -c 20 # ping it again from the same other board

One by one:

1. ip link set eno0 up
-> calls enetc_setup_rxbdr:
   -> calls enetc_refill_rx_ring(511 buffers)
   -> next_to_clean=0 (in hw 0)
   -> next_to_use=511 (in hw 0)

2. ping 192.168.100.1 -c 20 # ping this port from another board
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=1 next_to_clean 0 (in hw 1) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=2 next_to_clean 1 (in hw 2) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=3 next_to_clean 2 (in hw 3) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=4 next_to_clean 3 (in hw 4) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=5 next_to_clean 4 (in hw 5) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=6 next_to_clean 5 (in hw 6) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=7 next_to_clean 6 (in hw 7) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=8 next_to_clean 7 (in hw 8) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=9 next_to_clean 8 (in hw 9) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=10 next_to_clean 9 (in hw 10) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=11 next_to_clean 10 (in hw 11) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=12 next_to_clean 11 (in hw 12) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=13 next_to_clean 12 (in hw 13) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=14 next_to_clean 13 (in hw 14) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=15 next_to_clean 14 (in hw 15) next_to_use 511 (in hw 0)
enetc_clean_rx_ring: enetc_refill_rx_ring(16) increments next_to_use by 16 (mod 512) and writes it to hw
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=0 next_to_clean 15 (in hw 16) next_to_use 15 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=1 next_to_clean 16 (in hw 17) next_to_use 15 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=2 next_to_clean 17 (in hw 18) next_to_use 15 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=3 next_to_clean 18 (in hw 19) next_to_use 15 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=4 next_to_clean 19 (in hw 20) next_to_use 15 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=5 next_to_clean 20 (in hw 21) next_to_use 15 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=6 next_to_clean 21 (in hw 22) next_to_use 15 (in hw 15)

20 packets transmitted, 20 packets received, 0% packet loss

3. ip link set eno0 down
enetc_free_rx_ring: next_to_clean 0 (in hw 22), next_to_use 0 (in hw 15)

4. ip link set eno0 up
-> calls enetc_setup_rxbdr:
   -> calls enetc_refill_rx_ring(511 buffers)
   -> next_to_clean=0 (in hw 0)
   -> next_to_use=511 (in hw 15)

5. ping 192.168.100.1 -c 20 # ping it again from the same other board
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=1 next_to_clean 0 (in hw 1) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=2 next_to_clean 1 (in hw 2) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=3 next_to_clean 2 (in hw 3) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=4 next_to_clean 3 (in hw 4) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=5 next_to_clean 4 (in hw 5) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=6 next_to_clean 5 (in hw 6) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=7 next_to_clean 6 (in hw 7) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=8 next_to_clean 7 (in hw 8) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=9 next_to_clean 8 (in hw 9) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=10 next_to_clean 9 (in hw 10) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=11 next_to_clean 10 (in hw 11) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=12 next_to_clean 11 (in hw 12) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=13 next_to_clean 12 (in hw 13) next_to_use 511 (in hw 15)
enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=14 next_to_clean 13 (in hw 14) next_to_use 511 (in hw 15)

20 packets transmitted, 12 packets received, 40% packet loss

And there it dies. No enetc_refill_rx_ring (because cleaned_cnt must be equal
to 15 for that to happen), no nothing. The hardware enters the condition where
the producer (14) + 1 is equal to the consumer (15) index, which makes it
believe it has no more free buffers to put packets in, so it starts discarding
them:

ip netns exec ns0 ethtool -S eno0 | grep -v ': 0'
NIC statistics:
     Rx ring  0 discarded frames: 8

Summarized, if the interface receives between 16 and 32 (mod 512) frames
and then there is a link flap, then the port will eventually die with no
way to recover. If it receives less than 16 (mod 512) frames, then the
initial NAPI poll [ before the link flap ] will not update the consumer
index in hardware (it will remain zero) which will be ok when the buffers
are later reinitialized. If more than 32 (mod 512) frames are received,
the initial NAPI poll has the chance to refill the ring twice, updating
the consumer index to at least 32. So after the link flap, the consumer
index is still wrong, but the post-flap NAPI poll gets a chance to
refill the ring once (because it passes through cleaned_cnt=15) and
makes the consumer index be again back in sync with next_to_use.

The solution to this problem is actually simple, we just need to write
next_to_use into the hardware consumer index at enetc_open time, which
always brings it back in sync after an initial buffer seeding process.

The simpler thing would be to put the write to the consumer index into
enetc_refill_rx_ring directly, but there are issues with the MDIO
locking: in the NAPI poll code we have the enetc_lock_mdio() taken from
top-level and we use the unlocked enetc_wr_reg_hot, whereas in
enetc_open, the enetc_lock_mdio() is not taken at the top level, but
instead by each individual enetc_wr_reg, so we are forced to put an
additional enetc_wr_reg in enetc_setup_rxbdr. Better organization of
the code is left as a refactoring exercise.

Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index abb29ee81463..30d7d4e83900 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1212,6 +1212,8 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring)
 	rx_ring->idr = hw->reg + ENETC_SIRXIDR;
 
 	enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring));
+	/* update ENETC's consumer index */
+	enetc_rxbdr_wr(hw, idx, ENETC_RBCIR, rx_ring->next_to_use);
 
 	/* enable ring */
 	enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr);

From 2353db75c3db1dd26ff9c8feccfd3543a9cb73be Mon Sep 17 00:00:00 2001
From: Masanari Iida <standby24x7@gmail.com>
Date: Mon, 1 Mar 2021 21:28:23 +0900
Subject: [PATCH 0114/1820] docs: networking: bonding.rst Fix a typo in
 bonding.rst

This patch fixes a spelling typo in bonding.rst.

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/bonding.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst
index 5f690f0ad0e4..62f2aab8eaec 100644
--- a/Documentation/networking/bonding.rst
+++ b/Documentation/networking/bonding.rst
@@ -1988,7 +1988,7 @@ netif_carrier.
 If use_carrier is 0, then the MII monitor will first query the
 device's (via ioctl) MII registers and check the link state.  If that
 request fails (not just that it returns carrier down), then the MII
-monitor will make an ethtool ETHOOL_GLINK request to attempt to obtain
+monitor will make an ethtool ETHTOOL_GLINK request to attempt to obtain
 the same information.  If both methods fail (i.e., the driver either
 does not support or had some error in processing both the MII register
 and ethtool requests), then the MII monitor will assume the link is

From b228c9b058760500fda5edb3134527f629fc2dc3 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 1 Mar 2021 15:09:44 +0000
Subject: [PATCH 0115/1820] net: expand textsearch ts_state to fit
 skb_seq_state

The referenced commit expands the skb_seq_state used by
skb_find_text with a 4B frag_off field, growing it to 48B.

This exceeds container ts_state->cb, causing a stack corruption:

[   73.238353] Kernel panic - not syncing: stack-protector: Kernel stack
is corrupted in: skb_find_text+0xc5/0xd0
[   73.247384] CPU: 1 PID: 376 Comm: nping Not tainted 5.11.0+ #4
[   73.252613] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS 1.14.0-2 04/01/2014
[   73.260078] Call Trace:
[   73.264677]  dump_stack+0x57/0x6a
[   73.267866]  panic+0xf6/0x2b7
[   73.270578]  ? skb_find_text+0xc5/0xd0
[   73.273964]  __stack_chk_fail+0x10/0x10
[   73.277491]  skb_find_text+0xc5/0xd0
[   73.280727]  string_mt+0x1f/0x30
[   73.283639]  ipt_do_table+0x214/0x410

The struct is passed between skb_find_text and its callbacks
skb_prepare_seq_read, skb_seq_read and skb_abort_seq read through
the textsearch interface using TS_SKB_CB.

I assumed that this mapped to skb->cb like other .._SKB_CB wrappers.
skb->cb is 48B. But it maps to ts_state->cb, which is only 40B.

skb->cb was increased from 40B to 48B after ts_state was introduced,
in commit 3e3850e989c5 ("[NETFILTER]: Fix xfrm lookup in
ip_route_me_harder/ip6_route_me_harder").

Increase ts_state.cb[] to 48 to fit the struct.

Also add a BUILD_BUG_ON to avoid a repeat.

The alternative is to directly add a dependency from textsearch onto
linux/skbuff.h, but I think the intent is textsearch to have no such
dependencies on its callers.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=211911
Fixes: 97550f6fa592 ("net: compound page support in skb_seq_read")
Reported-by: Kris Karas <bugs-a17@moonlit-rail.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/textsearch.h | 2 +-
 net/core/skbuff.c          | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h
index 13770cfe33ad..6673e4d4ac2e 100644
--- a/include/linux/textsearch.h
+++ b/include/linux/textsearch.h
@@ -23,7 +23,7 @@ struct ts_config;
 struct ts_state
 {
 	unsigned int		offset;
-	char			cb[40];
+	char			cb[48];
 };
 
 /**
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 545a472273a5..c421c8f80925 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3659,6 +3659,8 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
 	struct ts_state state;
 	unsigned int ret;
 
+	BUILD_BUG_ON(sizeof(struct skb_seq_state) > sizeof(state.cb));
+
 	config->get_next_block = skb_ts_get_next_block;
 	config->finish = skb_ts_finish;
 

From 9200f515c41f4cbaeffd8fdd1d8b6373a18b1b67 Mon Sep 17 00:00:00 2001
From: DENG Qingfang <dqfext@gmail.com>
Date: Tue, 2 Mar 2021 00:01:59 +0800
Subject: [PATCH 0116/1820] net: dsa: tag_mtk: fix 802.1ad VLAN egress

A different TPID bit is used for 802.1ad VLAN frames.

Reported-by: Ilario Gelmetti <iochesonome@gmail.com>
Fixes: f0af34317f4b ("net: dsa: mediatek: combine MediaTek tag with VLAN tag")
Signed-off-by: DENG Qingfang <dqfext@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_mtk.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index 38dcdded74c0..59748487664f 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -13,6 +13,7 @@
 #define MTK_HDR_LEN		4
 #define MTK_HDR_XMIT_UNTAGGED		0
 #define MTK_HDR_XMIT_TAGGED_TPID_8100	1
+#define MTK_HDR_XMIT_TAGGED_TPID_88A8	2
 #define MTK_HDR_RECV_SOURCE_PORT_MASK	GENMASK(2, 0)
 #define MTK_HDR_XMIT_DP_BIT_MASK	GENMASK(5, 0)
 #define MTK_HDR_XMIT_SA_DIS		BIT(6)
@@ -21,8 +22,8 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 				    struct net_device *dev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
+	u8 xmit_tpid;
 	u8 *mtk_tag;
-	bool is_vlan_skb = true;
 	unsigned char *dest = eth_hdr(skb)->h_dest;
 	bool is_multicast_skb = is_multicast_ether_addr(dest) &&
 				!is_broadcast_ether_addr(dest);
@@ -33,10 +34,17 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 	 * the both special and VLAN tag at the same time and then look up VLAN
 	 * table with VID.
 	 */
-	if (!skb_vlan_tagged(skb)) {
+	switch (skb->protocol) {
+	case htons(ETH_P_8021Q):
+		xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_8100;
+		break;
+	case htons(ETH_P_8021AD):
+		xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_88A8;
+		break;
+	default:
+		xmit_tpid = MTK_HDR_XMIT_UNTAGGED;
 		skb_push(skb, MTK_HDR_LEN);
 		memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN);
-		is_vlan_skb = false;
 	}
 
 	mtk_tag = skb->data + 2 * ETH_ALEN;
@@ -44,8 +52,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 	/* Mark tag attribute on special tag insertion to notify hardware
 	 * whether that's a combined special tag with 802.1Q header.
 	 */
-	mtk_tag[0] = is_vlan_skb ? MTK_HDR_XMIT_TAGGED_TPID_8100 :
-		     MTK_HDR_XMIT_UNTAGGED;
+	mtk_tag[0] = xmit_tpid;
 	mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
 
 	/* Disable SA learning for multicast frames */
@@ -53,7 +60,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 		mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS;
 
 	/* Tag control information is kept for 802.1Q */
-	if (!is_vlan_skb) {
+	if (xmit_tpid == MTK_HDR_XMIT_UNTAGGED) {
 		mtk_tag[2] = 0;
 		mtk_tag[3] = 0;
 	}

From 3946688edbc5b629110c339b3babf10aa9e7adad Mon Sep 17 00:00:00 2001
From: "Andrea Parri (Microsoft)" <parri.andrea@gmail.com>
Date: Mon, 1 Mar 2021 19:25:30 +0100
Subject: [PATCH 0117/1820] hv_netvsc: Fix validation in
 netvsc_linkstatus_callback()

Contrary to the RNDIS protocol specification, certain (pre-Fe)
implementations of Hyper-V's vSwitch did not account for the status
buffer field in the length of an RNDIS packet; the bug was fixed in
newer implementations.  Validate the status buffer fields using the
length of the 'vmtransfer_page' packet (all implementations), that
is known/validated to be less than or equal to the receive section
size and not smaller than the length of the RNDIS message.

Reported-by: Dexuan Cui <decui@microsoft.com>
Suggested-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Fixes: 505e3f00c3f36 ("hv_netvsc: Add (more) validation for untrusted Hyper-V values")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h   |  2 +-
 drivers/net/hyperv/netvsc_drv.c   | 13 +++++++++----
 drivers/net/hyperv/rndis_filter.c |  2 +-
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index e1a497d3c9ba..59ac04a610ad 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -229,7 +229,7 @@ int netvsc_send(struct net_device *net,
 		bool xdp_tx);
 void netvsc_linkstatus_callback(struct net_device *net,
 				struct rndis_message *resp,
-				void *data);
+				void *data, u32 data_buflen);
 int netvsc_recv_callback(struct net_device *net,
 			 struct netvsc_device *nvdev,
 			 struct netvsc_channel *nvchan);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 8176fa0c8b16..15f262b70489 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -744,7 +744,7 @@ static netdev_tx_t netvsc_start_xmit(struct sk_buff *skb,
  */
 void netvsc_linkstatus_callback(struct net_device *net,
 				struct rndis_message *resp,
-				void *data)
+				void *data, u32 data_buflen)
 {
 	struct rndis_indicate_status *indicate = &resp->msg.indicate_status;
 	struct net_device_context *ndev_ctx = netdev_priv(net);
@@ -765,11 +765,16 @@ void netvsc_linkstatus_callback(struct net_device *net,
 	if (indicate->status == RNDIS_STATUS_LINK_SPEED_CHANGE) {
 		u32 speed;
 
-		/* Validate status_buf_offset */
+		/* Validate status_buf_offset and status_buflen.
+		 *
+		 * Certain (pre-Fe) implementations of Hyper-V's vSwitch didn't account
+		 * for the status buffer field in resp->msg_len; perform the validation
+		 * using data_buflen (>= resp->msg_len).
+		 */
 		if (indicate->status_buflen < sizeof(speed) ||
 		    indicate->status_buf_offset < sizeof(*indicate) ||
-		    resp->msg_len - RNDIS_HEADER_SIZE < indicate->status_buf_offset ||
-		    resp->msg_len - RNDIS_HEADER_SIZE - indicate->status_buf_offset
+		    data_buflen - RNDIS_HEADER_SIZE < indicate->status_buf_offset ||
+		    data_buflen - RNDIS_HEADER_SIZE - indicate->status_buf_offset
 				< indicate->status_buflen) {
 			netdev_err(net, "invalid rndis_indicate_status packet\n");
 			return;
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 123cc9d25f5e..c0e89e107d57 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -620,7 +620,7 @@ int rndis_filter_receive(struct net_device *ndev,
 
 	case RNDIS_MSG_INDICATE:
 		/* notification msgs */
-		netvsc_linkstatus_callback(ndev, rndis_msg, data);
+		netvsc_linkstatus_callback(ndev, rndis_msg, data, buflen);
 		break;
 	default:
 		netdev_err(ndev,

From 8811f4a9836e31c14ecdf79d9f3cb7c5d463265d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 1 Mar 2021 10:29:17 -0800
Subject: [PATCH 0118/1820] tcp: add sanity tests to TCP_QUEUE_SEQ

Qingyu Li reported a syzkaller bug where the repro
changes RCV SEQ _after_ restoring data in the receive queue.

mprotect(0x4aa000, 12288, PROT_READ)    = 0
mmap(0x1ffff000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x1ffff000
mmap(0x20000000, 16777216, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x20000000
mmap(0x21000000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x21000000
socket(AF_INET6, SOCK_STREAM, IPPROTO_IP) = 3
setsockopt(3, SOL_TCP, TCP_REPAIR, [1], 4) = 0
connect(3, {sa_family=AF_INET6, sin6_port=htons(0), sin6_flowinfo=htonl(0), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_scope_id=0}, 28) = 0
setsockopt(3, SOL_TCP, TCP_REPAIR_QUEUE, [1], 4) = 0
sendmsg(3, {msg_name=NULL, msg_namelen=0, msg_iov=[{iov_base="0x0000000000000003\0\0", iov_len=20}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 20
setsockopt(3, SOL_TCP, TCP_REPAIR, [0], 4) = 0
setsockopt(3, SOL_TCP, TCP_QUEUE_SEQ, [128], 4) = 0
recvfrom(3, NULL, 20, 0, NULL, NULL)    = -1 ECONNRESET (Connection reset by peer)

syslog shows:
[  111.205099] TCP recvmsg seq # bug 2: copied 80, seq 0, rcvnxt 80, fl 0
[  111.207894] WARNING: CPU: 1 PID: 356 at net/ipv4/tcp.c:2343 tcp_recvmsg_locked+0x90e/0x29a0

This should not be allowed. TCP_QUEUE_SEQ should only be used
when queues are empty.

This patch fixes this case, and the tx path as well.

Fixes: ee9952831cfd ("tcp: Initial repair mode")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=212005
Reported-by: Qingyu Li <ieatmuttonchuan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dfb6f286c1de..de7cc8445ac0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3469,16 +3469,23 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case TCP_QUEUE_SEQ:
-		if (sk->sk_state != TCP_CLOSE)
+		if (sk->sk_state != TCP_CLOSE) {
 			err = -EPERM;
-		else if (tp->repair_queue == TCP_SEND_QUEUE)
-			WRITE_ONCE(tp->write_seq, val);
-		else if (tp->repair_queue == TCP_RECV_QUEUE) {
-			WRITE_ONCE(tp->rcv_nxt, val);
-			WRITE_ONCE(tp->copied_seq, val);
-		}
-		else
+		} else if (tp->repair_queue == TCP_SEND_QUEUE) {
+			if (!tcp_rtx_queue_empty(sk))
+				err = -EPERM;
+			else
+				WRITE_ONCE(tp->write_seq, val);
+		} else if (tp->repair_queue == TCP_RECV_QUEUE) {
+			if (tp->rcv_nxt != tp->copied_seq) {
+				err = -EPERM;
+			} else {
+				WRITE_ONCE(tp->rcv_nxt, val);
+				WRITE_ONCE(tp->copied_seq, val);
+			}
+		} else {
 			err = -EINVAL;
+		}
 		break;
 
 	case TCP_REPAIR_OPTIONS:

From 42a382a466a967dc053c73b969cd2ac2fec502cf Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Sat, 27 Feb 2021 06:17:26 +0100
Subject: [PATCH 0119/1820] selftests/bpf: Use the last page in
 test_snprintf_btf on s390

test_snprintf_btf fails on s390, because NULL points to a readable
struct lowcore there. Fix by using the last page instead.

Error message example:

    printing fffffffffffff000 should generate error, got (361)

Fixes: 076a95f5aff2 ("selftests/bpf: Add bpf_snprintf_btf helper tests")
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210227051726.121256-1-iii@linux.ibm.com
---
 .../testing/selftests/bpf/progs/netif_receive_skb.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/netif_receive_skb.c b/tools/testing/selftests/bpf/progs/netif_receive_skb.c
index 6b670039ea67..1d8918dfbd3f 100644
--- a/tools/testing/selftests/bpf/progs/netif_receive_skb.c
+++ b/tools/testing/selftests/bpf/progs/netif_receive_skb.c
@@ -16,6 +16,13 @@ bool skip = false;
 #define STRSIZE			2048
 #define EXPECTED_STRSIZE	256
 
+#if defined(bpf_target_s390)
+/* NULL points to a readable struct lowcore on s390, so take the last page */
+#define BADPTR			((void *)0xFFFFFFFFFFFFF000ULL)
+#else
+#define BADPTR			0
+#endif
+
 #ifndef ARRAY_SIZE
 #define ARRAY_SIZE(x)	(sizeof(x) / sizeof((x)[0]))
 #endif
@@ -113,11 +120,11 @@ int BPF_PROG(trace_netif_receive_skb, struct sk_buff *skb)
 	}
 
 	/* Check invalid ptr value */
-	p.ptr = 0;
+	p.ptr = BADPTR;
 	__ret = bpf_snprintf_btf(str, STRSIZE, &p, sizeof(p), 0);
 	if (__ret >= 0) {
-		bpf_printk("printing NULL should generate error, got (%d)",
-			   __ret);
+		bpf_printk("printing %llx should generate error, got (%d)",
+			   (unsigned long long)BADPTR, __ret);
 		ret = -ERANGE;
 	}
 

From 6185266c5a853bb0f2a459e3ff594546f277609b Mon Sep 17 00:00:00 2001
From: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Date: Sun, 28 Feb 2021 12:30:17 +0200
Subject: [PATCH 0120/1820] selftests/bpf: Mask bpf_csum_diff() return value to
 16 bits in test_verifier

The verifier test labelled "valid read map access into a read-only array
2" calls the bpf_csum_diff() helper and checks its return value. However,
architecture implementations of csum_partial() (which is what the helper
uses) differ in whether they fold the return value to 16 bit or not. For
example, x86 version has ...

	if (unlikely(odd)) {
		result = from32to16(result);
		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
	}

... while generic lib/checksum.c does:

	result = from32to16(result);
	if (odd)
		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);

This makes the helper return different values on different architectures,
breaking the test on non-x86. To fix this, add an additional instruction
to always mask the return value to 16 bits, and update the expected return
value accordingly.

Fixes: fb2abb73e575 ("bpf, selftest: test {rd, wr}only flags and direct value access")
Signed-off-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210228103017.320240-1-yauheni.kaliuta@redhat.com
---
 tools/testing/selftests/bpf/verifier/array_access.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c
index bed53b561e04..1b138cd2b187 100644
--- a/tools/testing/selftests/bpf/verifier/array_access.c
+++ b/tools/testing/selftests/bpf/verifier/array_access.c
@@ -250,12 +250,13 @@
 	BPF_MOV64_IMM(BPF_REG_5, 0),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
 		     BPF_FUNC_csum_diff),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffff),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.fixup_map_array_ro = { 3 },
 	.result = ACCEPT,
-	.retval = -29,
+	.retval = 65507,
 },
 {
 	"invalid write map access into a read-only array 1",

From 386a966f5ce71a0364b158c5d0a6971f4e418ea8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <uwe@kleine-koenig.org>
Date: Thu, 25 Feb 2021 23:18:34 +0100
Subject: [PATCH 0121/1820] vio: make remove callback return void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The driver core ignores the return value of struct bus_type::remove()
because there is only little that can be done. To simplify the quest to
make this function return void, let struct vio_driver::remove() return
void, too. All users already unconditionally return 0, this commit makes
it obvious that returning an error code is a bad idea.

Note there are two nominally different implementations for a vio bus:
one in arch/sparc/kernel/vio.c and the other in
arch/powerpc/platforms/pseries/vio.c. This patch only adapts the powerpc
one.

Before this patch for a device that was bound to a driver without a
remove callback vio_cmo_bus_remove(viodev) wasn't called. As the device
core still considers the device unbound after vio_bus_remove() returns
calling this unconditionally is the consistent behaviour which is
implemented here.

Signed-off-by: Uwe Kleine-König <uwe@kleine-koenig.org>
Reviewed-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Acked-by: Lijun Pan <ljp@linux.ibm.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[mpe: Drop unneeded hvcs_remove() forward declaration, squash in
 change from sfr to drop ibmvnic_remove() forward declaration]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210225221834.160083-1-uwe@kleine-koenig.org
---
 arch/powerpc/include/asm/vio.h           | 2 +-
 arch/powerpc/platforms/pseries/vio.c     | 7 +++----
 drivers/char/hw_random/pseries-rng.c     | 3 +--
 drivers/char/tpm/tpm_ibmvtpm.c           | 4 +---
 drivers/crypto/nx/nx-842-pseries.c       | 4 +---
 drivers/crypto/nx/nx.c                   | 4 +---
 drivers/misc/ibmvmc.c                    | 4 +---
 drivers/net/ethernet/ibm/ibmveth.c       | 4 +---
 drivers/net/ethernet/ibm/ibmvnic.c       | 5 +----
 drivers/scsi/ibmvscsi/ibmvfc.c           | 3 +--
 drivers/scsi/ibmvscsi/ibmvscsi.c         | 4 +---
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 4 +---
 drivers/tty/hvc/hvcs.c                   | 4 +---
 13 files changed, 15 insertions(+), 37 deletions(-)

diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h
index 0cf52746531b..721c0d6715ac 100644
--- a/arch/powerpc/include/asm/vio.h
+++ b/arch/powerpc/include/asm/vio.h
@@ -113,7 +113,7 @@ struct vio_driver {
 	const char *name;
 	const struct vio_device_id *id_table;
 	int (*probe)(struct vio_dev *dev, const struct vio_device_id *id);
-	int (*remove)(struct vio_dev *dev);
+	void (*remove)(struct vio_dev *dev);
 	/* A driver must have a get_desired_dma() function to
 	 * be loaded in a CMO environment if it uses DMA.
 	 */
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index b2797cfe4e2b..9cb4fc839fd5 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1261,7 +1261,6 @@ static int vio_bus_remove(struct device *dev)
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct vio_driver *viodrv = to_vio_driver(dev->driver);
 	struct device *devptr;
-	int ret = 1;
 
 	/*
 	 * Hold a reference to the device after the remove function is called
@@ -1270,13 +1269,13 @@ static int vio_bus_remove(struct device *dev)
 	devptr = get_device(dev);
 
 	if (viodrv->remove)
-		ret = viodrv->remove(viodev);
+		viodrv->remove(viodev);
 
-	if (!ret && firmware_has_feature(FW_FEATURE_CMO))
+	if (firmware_has_feature(FW_FEATURE_CMO))
 		vio_cmo_bus_remove(viodev);
 
 	put_device(devptr);
-	return ret;
+	return 0;
 }
 
 /**
diff --git a/drivers/char/hw_random/pseries-rng.c b/drivers/char/hw_random/pseries-rng.c
index 8038a8a9fb58..f4949b689bd5 100644
--- a/drivers/char/hw_random/pseries-rng.c
+++ b/drivers/char/hw_random/pseries-rng.c
@@ -54,10 +54,9 @@ static int pseries_rng_probe(struct vio_dev *dev,
 	return hwrng_register(&pseries_rng);
 }
 
-static int pseries_rng_remove(struct vio_dev *dev)
+static void pseries_rng_remove(struct vio_dev *dev)
 {
 	hwrng_unregister(&pseries_rng);
-	return 0;
 }
 
 static const struct vio_device_id pseries_rng_driver_ids[] = {
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index 994385bf37c0..903604769de9 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -343,7 +343,7 @@ static int ibmvtpm_crq_send_init_complete(struct ibmvtpm_dev *ibmvtpm)
  *
  * Return: Always 0.
  */
-static int tpm_ibmvtpm_remove(struct vio_dev *vdev)
+static void tpm_ibmvtpm_remove(struct vio_dev *vdev)
 {
 	struct tpm_chip *chip = dev_get_drvdata(&vdev->dev);
 	struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
@@ -372,8 +372,6 @@ static int tpm_ibmvtpm_remove(struct vio_dev *vdev)
 	kfree(ibmvtpm);
 	/* For tpm_ibmvtpm_get_desired_dma */
 	dev_set_drvdata(&vdev->dev, NULL);
-
-	return 0;
 }
 
 /**
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index 2de5e3672e42..cc8dd3072b8b 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -1042,7 +1042,7 @@ error:
 	return ret;
 }
 
-static int nx842_remove(struct vio_dev *viodev)
+static void nx842_remove(struct vio_dev *viodev)
 {
 	struct nx842_devdata *old_devdata;
 	unsigned long flags;
@@ -1063,8 +1063,6 @@ static int nx842_remove(struct vio_dev *viodev)
 	if (old_devdata)
 		kfree(old_devdata->counters);
 	kfree(old_devdata);
-
-	return 0;
 }
 
 static const struct vio_device_id nx842_vio_driver_ids[] = {
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index 0d2dc5be7f19..1d0e8a1ba160 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -783,7 +783,7 @@ static int nx_probe(struct vio_dev *viodev, const struct vio_device_id *id)
 	return nx_register_algs();
 }
 
-static int nx_remove(struct vio_dev *viodev)
+static void nx_remove(struct vio_dev *viodev)
 {
 	dev_dbg(&viodev->dev, "entering nx_remove for UA 0x%x\n",
 		viodev->unit_address);
@@ -811,8 +811,6 @@ static int nx_remove(struct vio_dev *viodev)
 		nx_unregister_skcipher(&nx_ecb_aes_alg, NX_FC_AES,
 				       NX_MODE_AES_ECB);
 	}
-
-	return 0;
 }
 
 
diff --git a/drivers/misc/ibmvmc.c b/drivers/misc/ibmvmc.c
index 2d778d0f011e..c0fe3295c330 100644
--- a/drivers/misc/ibmvmc.c
+++ b/drivers/misc/ibmvmc.c
@@ -2288,15 +2288,13 @@ crq_failed:
 	return -EPERM;
 }
 
-static int ibmvmc_remove(struct vio_dev *vdev)
+static void ibmvmc_remove(struct vio_dev *vdev)
 {
 	struct crq_server_adapter *adapter = dev_get_drvdata(&vdev->dev);
 
 	dev_info(adapter->dev, "Entering remove for UA 0x%x\n",
 		 vdev->unit_address);
 	ibmvmc_release_crq_queue(adapter);
-
-	return 0;
 }
 
 static struct vio_device_id ibmvmc_device_table[] = {
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index c3ec9ceed833..7fea9ae60f13 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1758,7 +1758,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	return 0;
 }
 
-static int ibmveth_remove(struct vio_dev *dev)
+static void ibmveth_remove(struct vio_dev *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(&dev->dev);
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
@@ -1771,8 +1771,6 @@ static int ibmveth_remove(struct vio_dev *dev)
 
 	free_netdev(netdev);
 	dev_set_drvdata(&dev->dev, NULL);
-
-	return 0;
 }
 
 static struct attribute veth_active_attr;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 118a4bd3f877..fe3201ba2034 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -78,7 +78,6 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION(IBMVNIC_DRIVER_VERSION);
 
 static int ibmvnic_version = IBMVNIC_INITIAL_VERSION;
-static int ibmvnic_remove(struct vio_dev *);
 static void release_sub_crqs(struct ibmvnic_adapter *, bool);
 static int ibmvnic_reset_crq(struct ibmvnic_adapter *);
 static int ibmvnic_send_crq_init(struct ibmvnic_adapter *);
@@ -5396,7 +5395,7 @@ ibmvnic_init_fail:
 	return rc;
 }
 
-static int ibmvnic_remove(struct vio_dev *dev)
+static void ibmvnic_remove(struct vio_dev *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(&dev->dev);
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
@@ -5437,8 +5436,6 @@ static int ibmvnic_remove(struct vio_dev *dev)
 	device_remove_file(&dev->dev, &dev_attr_failover);
 	free_netdev(netdev);
 	dev_set_drvdata(&dev->dev, NULL);
-
-	return 0;
 }
 
 static ssize_t failover_store(struct device *dev, struct device_attribute *attr,
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 755313b766b9..e663085a8944 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -6038,7 +6038,7 @@ out:
  * Return value:
  * 	0
  **/
-static int ibmvfc_remove(struct vio_dev *vdev)
+static void ibmvfc_remove(struct vio_dev *vdev)
 {
 	struct ibmvfc_host *vhost = dev_get_drvdata(&vdev->dev);
 	LIST_HEAD(purge);
@@ -6070,7 +6070,6 @@ static int ibmvfc_remove(struct vio_dev *vdev)
 	spin_unlock(&ibmvfc_driver_lock);
 	scsi_host_put(vhost->host);
 	LEAVE;
-	return 0;
 }
 
 /**
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 29fcc44be2d5..77fafb1bc173 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -2335,7 +2335,7 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	return -1;
 }
 
-static int ibmvscsi_remove(struct vio_dev *vdev)
+static void ibmvscsi_remove(struct vio_dev *vdev)
 {
 	struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev);
 
@@ -2356,8 +2356,6 @@ static int ibmvscsi_remove(struct vio_dev *vdev)
 	spin_unlock(&ibmvscsi_driver_lock);
 
 	scsi_host_put(hostdata->host);
-
-	return 0;
 }
 
 /**
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index cc3908c2d2f9..9abd9e253af6 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -3595,7 +3595,7 @@ free_adapter:
 	return rc;
 }
 
-static int ibmvscsis_remove(struct vio_dev *vdev)
+static void ibmvscsis_remove(struct vio_dev *vdev)
 {
 	struct scsi_info *vscsi = dev_get_drvdata(&vdev->dev);
 
@@ -3622,8 +3622,6 @@ static int ibmvscsis_remove(struct vio_dev *vdev)
 	list_del(&vscsi->list);
 	spin_unlock_bh(&ibmvscsis_dev_lock);
 	kfree(vscsi);
-
-	return 0;
 }
 
 static ssize_t system_id_show(struct device *dev,
diff --git a/drivers/tty/hvc/hvcs.c b/drivers/tty/hvc/hvcs.c
index c90848919644..9afa1dcef2c2 100644
--- a/drivers/tty/hvc/hvcs.c
+++ b/drivers/tty/hvc/hvcs.c
@@ -317,7 +317,6 @@ static void hvcs_hangup(struct tty_struct * tty);
 
 static int hvcs_probe(struct vio_dev *dev,
 		const struct vio_device_id *id);
-static int hvcs_remove(struct vio_dev *dev);
 static int __init hvcs_module_init(void);
 static void __exit hvcs_module_exit(void);
 static int hvcs_initialize(void);
@@ -819,7 +818,7 @@ static int hvcs_probe(
 	return 0;
 }
 
-static int hvcs_remove(struct vio_dev *dev)
+static void hvcs_remove(struct vio_dev *dev)
 {
 	struct hvcs_struct *hvcsd = dev_get_drvdata(&dev->dev);
 	unsigned long flags;
@@ -849,7 +848,6 @@ static int hvcs_remove(struct vio_dev *dev)
 
 	printk(KERN_INFO "HVCS: vty-server@%X removed from the"
 			" vio bus.\n", dev->unit_address);
-	return 0;
 };
 
 static struct vio_driver hvcs_vio_driver = {

From acdad8fb4a1574323db88f98a38b630691574e16 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Sat, 27 Feb 2021 16:30:48 +0000
Subject: [PATCH 0122/1820] powerpc: Force inlining of mmu_has_feature to fix
 build failure

The test robot has managed to generate a random config leading
to following build failure:

  LD      .tmp_vmlinux.kallsyms1
powerpc64-linux-ld: arch/powerpc/mm/pgtable.o: in function `ptep_set_access_flags':
pgtable.c:(.text.ptep_set_access_flags+0xf0): undefined reference to `hash__flush_tlb_page'
powerpc64-linux-ld: arch/powerpc/mm/book3s32/mmu.o: in function `MMU_init_hw_patch':
mmu.c:(.init.text+0x452): undefined reference to `patch__hash_page_A0'
powerpc64-linux-ld: mmu.c:(.init.text+0x45e): undefined reference to `patch__hash_page_A0'
powerpc64-linux-ld: mmu.c:(.init.text+0x46a): undefined reference to `patch__hash_page_A1'
powerpc64-linux-ld: mmu.c:(.init.text+0x476): undefined reference to `patch__hash_page_A1'
powerpc64-linux-ld: mmu.c:(.init.text+0x482): undefined reference to `patch__hash_page_A2'
powerpc64-linux-ld: mmu.c:(.init.text+0x48e): undefined reference to `patch__hash_page_A2'
powerpc64-linux-ld: mmu.c:(.init.text+0x49e): undefined reference to `patch__hash_page_B'
powerpc64-linux-ld: mmu.c:(.init.text+0x4aa): undefined reference to `patch__hash_page_B'
powerpc64-linux-ld: mmu.c:(.init.text+0x4b6): undefined reference to `patch__hash_page_C'
powerpc64-linux-ld: mmu.c:(.init.text+0x4c2): undefined reference to `patch__hash_page_C'
powerpc64-linux-ld: mmu.c:(.init.text+0x4ce): undefined reference to `patch__flush_hash_A0'
powerpc64-linux-ld: mmu.c:(.init.text+0x4da): undefined reference to `patch__flush_hash_A0'
powerpc64-linux-ld: mmu.c:(.init.text+0x4e6): undefined reference to `patch__flush_hash_A1'
powerpc64-linux-ld: mmu.c:(.init.text+0x4f2): undefined reference to `patch__flush_hash_A1'
powerpc64-linux-ld: mmu.c:(.init.text+0x4fe): undefined reference to `patch__flush_hash_A2'
powerpc64-linux-ld: mmu.c:(.init.text+0x50a): undefined reference to `patch__flush_hash_A2'
powerpc64-linux-ld: mmu.c:(.init.text+0x522): undefined reference to `patch__flush_hash_B'
powerpc64-linux-ld: mmu.c:(.init.text+0x532): undefined reference to `patch__flush_hash_B'
powerpc64-linux-ld: arch/powerpc/mm/book3s32/mmu.o: in function `update_mmu_cache':
mmu.c:(.text.update_mmu_cache+0xa0): undefined reference to `add_hash_page'
powerpc64-linux-ld: mm/memory.o: in function `zap_pte_range':
memory.c:(.text.zap_pte_range+0x160): undefined reference to `flush_hash_pages'
powerpc64-linux-ld: mm/memory.o: in function `handle_pte_fault':
memory.c:(.text.handle_pte_fault+0x180): undefined reference to `hash__flush_tlb_page'

This is due to mmu_has_feature() not being inlined. See extract of build of
mmu.c with -Winline:

In file included from ./include/linux/mm_types.h:19,
                 from ./include/linux/mmzone.h:21,
                 from ./include/linux/gfp.h:6,
                 from ./include/linux/mm.h:10,
                 from arch/powerpc/mm/book3s32/mmu.c:21:
./arch/powerpc/include/asm/mmu.h: In function 'find_free_bat':
./arch/powerpc/include/asm/mmu.h:231:20: warning: inlining failed in call to 'early_mmu_has_feature': call is unlikely and code size would grow [-Winline]
  231 | static inline bool early_mmu_has_feature(unsigned long feature)
      |                    ^~~~~~~~~~~~~~~~~~~~~
./arch/powerpc/include/asm/mmu.h:291:9: note: called from here
  291 |  return early_mmu_has_feature(feature);
      |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The code relies on constant folding of MMU_FTRS_POSSIBLE at buildtime
and elimination of non possible parts of code at compile time.
For this to work, mmu_has_feature() and early_mmu_has_feature()
must be inlined.

Fixes: 259149cf7c3c ("powerpc/32s: Only build hash code when CONFIG_PPC_BOOK3S_604 is selected")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/cf61345912c078c96f171afd0fcc48ef27cbdc3f.1614443418.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/include/asm/mmu.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 80b27f5d9648..607168b1aef4 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -228,7 +228,7 @@ enum {
 #define MMU_FTRS_ALWAYS		0
 #endif
 
-static inline bool early_mmu_has_feature(unsigned long feature)
+static __always_inline bool early_mmu_has_feature(unsigned long feature)
 {
 	if (MMU_FTRS_ALWAYS & feature)
 		return true;
@@ -286,7 +286,7 @@ static inline void mmu_feature_keys_init(void)
 
 }
 
-static inline bool mmu_has_feature(unsigned long feature)
+static __always_inline bool mmu_has_feature(unsigned long feature)
 {
 	return early_mmu_has_feature(feature);
 }

From 5ae5fbd2107959b68ac69a8b75412208663aea88 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Thu, 25 Feb 2021 05:10:39 -0500
Subject: [PATCH 0123/1820] powerpc/perf: Fix handling of privilege level
 checks in perf interrupt context

Running "perf mem record" in powerpc platforms with selinux enabled
resulted in soft lockup's. Below call-trace was seen in the logs:

  CPU: 58 PID: 3751 Comm: sssd_nss Not tainted 5.11.0-rc7+ #2
  NIP:  c000000000dff3d4 LR: c000000000dff3d0 CTR: 0000000000000000
  REGS: c000007fffab7d60 TRAP: 0100   Not tainted  (5.11.0-rc7+)
  ...
  NIP _raw_spin_lock_irqsave+0x94/0x120
  LR  _raw_spin_lock_irqsave+0x90/0x120
  Call Trace:
    0xc00000000fd47260 (unreliable)
    skb_queue_tail+0x3c/0x90
    audit_log_end+0x6c/0x180
    common_lsm_audit+0xb0/0xe0
    slow_avc_audit+0xa4/0x110
    avc_has_perm+0x1c4/0x260
    selinux_perf_event_open+0x74/0xd0
    security_perf_event_open+0x68/0xc0
    record_and_restart+0x6e8/0x7f0
    perf_event_interrupt+0x22c/0x560
    performance_monitor_exception0x4c/0x60
    performance_monitor_common_virt+0x1c8/0x1d0
  interrupt: f00 at _raw_spin_lock_irqsave+0x38/0x120
  NIP:  c000000000dff378 LR: c000000000b5fbbc CTR: c0000000007d47f0
  REGS: c00000000fd47860 TRAP: 0f00   Not tainted  (5.11.0-rc7+)
  ...
  NIP _raw_spin_lock_irqsave+0x38/0x120
  LR  skb_queue_tail+0x3c/0x90
  interrupt: f00
    0x38 (unreliable)
    0xc00000000aae6200
    audit_log_end+0x6c/0x180
    audit_log_exit+0x344/0xf80
    __audit_syscall_exit+0x2c0/0x320
    do_syscall_trace_leave+0x148/0x200
    syscall_exit_prepare+0x324/0x390
    system_call_common+0xfc/0x27c

The above trace shows that while the CPU was handling a performance
monitor exception, there was a call to security_perf_event_open()
function. In powerpc core-book3s, this function is called from
perf_allow_kernel() check during recording of data address in the
sample via perf_get_data_addr().

Commit da97e18458fb ("perf_event: Add support for LSM and SELinux
checks") introduced security enhancements to perf. As part of this
commit, the new security hook for perf_event_open() was added in all
places where perf paranoid check was previously used. In powerpc
core-book3s code, originally had paranoid checks in
perf_get_data_addr() and power_pmu_bhrb_read(). So
perf_paranoid_kernel() checks were replaced with perf_allow_kernel()
in these PMU helper functions as well.

The intention of paranoid checks in core-book3s was to verify
privilege access before capturing some of the sample data. Along with
paranoid checks, perf_allow_kernel() also does a
security_perf_event_open(). Since these functions are accessed while
recording a sample, we end up calling selinux_perf_event_open() in PMI
context. Some of the security functions use spinlock like
sidtab_sid2str_put(). If a perf interrupt hits under a spin lock and
if we end up in calling selinux hook functions in PMI handler, this
could cause a dead lock.

Since the purpose of this security hook is to control access to
perf_event_open(), it is not right to call this in interrupt context.

The paranoid checks in powerpc core-book3s were done at interrupt time
which is also not correct.

Reference commits:
  Commit cd1231d7035f ("powerpc/perf: Prevent kernel address leak via perf_get_data_addr()")
  Commit bb19af816025 ("powerpc/perf: Prevent kernel address leak to userspace via BHRB buffer")

We only allow creation of events that have already passed the
privilege checks in perf_event_open(). So these paranoid checks are
not needed at event time. As a fix, patch uses
'event->attr.exclude_kernel' check to prevent exposing kernel address
for userspace only sampling.

Fixes: cd1231d7035f ("powerpc/perf: Prevent kernel address leak via perf_get_data_addr()")
Cc: stable@vger.kernel.org # v4.17+
Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1614247839-1428-1-git-send-email-atrajeev@linux.vnet.ibm.com
---
 arch/powerpc/perf/core-book3s.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 6817331e22ff..766f064f00fb 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -222,7 +222,7 @@ static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *
 	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid)
 		*addrp = mfspr(SPRN_SDAR);
 
-	if (is_kernel_addr(mfspr(SPRN_SDAR)) && perf_allow_kernel(&event->attr) != 0)
+	if (is_kernel_addr(mfspr(SPRN_SDAR)) && event->attr.exclude_kernel)
 		*addrp = 0;
 }
 
@@ -507,7 +507,7 @@ static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *
 			 * addresses, hence include a check before filtering code
 			 */
 			if (!(ppmu->flags & PPMU_ARCH_31) &&
-				is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0)
+			    is_kernel_addr(addr) && event->attr.exclude_kernel)
 				continue;
 
 			/* Branches are read most recent first (ie. mfbhrb 0 is

From 5c88a17e15795226b56d83f579cbb9b7a4864f79 Mon Sep 17 00:00:00 2001
From: Jordan Niethe <jniethe5@gmail.com>
Date: Thu, 25 Feb 2021 14:19:46 +1100
Subject: [PATCH 0124/1820] powerpc/sstep: Fix VSX instruction emulation

Commit af99da74333b ("powerpc/sstep: Support VSX vector paired storage
access instructions") added loading and storing 32 word long data into
adjacent VSRs. However the calculation used to determine if two VSRs
needed to be loaded/stored inadvertently prevented the load/storing
taking place for instructions with a data length less than 16 words.

This causes the emulation to not function correctly, which can be seen
by the alignment_handler selftest:

$ ./alignment_handler
[snip]
test: test_alignment_handler_vsx_207
tags: git_version:powerpc-5.12-1-0-g82d2c16b350f
VSX: 2.07B
        Doing lxsspx:   PASSED
        Doing lxsiwax:  FAILED: Wrong Data
        Doing lxsiwzx:  PASSED
        Doing stxsspx:  PASSED
        Doing stxsiwx:  PASSED
failure: test_alignment_handler_vsx_207
test: test_alignment_handler_vsx_300
tags: git_version:powerpc-5.12-1-0-g82d2c16b350f
VSX: 3.00B
        Doing lxsd:     PASSED
        Doing lxsibzx:  PASSED
        Doing lxsihzx:  PASSED
        Doing lxssp:    FAILED: Wrong Data
        Doing lxv:      PASSED
        Doing lxvb16x:  PASSED
        Doing lxvh8x:   PASSED
        Doing lxvx:     PASSED
        Doing lxvwsx:   FAILED: Wrong Data
        Doing lxvl:     PASSED
        Doing lxvll:    PASSED
        Doing stxsd:    PASSED
        Doing stxsibx:  PASSED
        Doing stxsihx:  PASSED
        Doing stxssp:   PASSED
        Doing stxv:     PASSED
        Doing stxvb16x: PASSED
        Doing stxvh8x:  PASSED
        Doing stxvx:    PASSED
        Doing stxvl:    PASSED
        Doing stxvll:   PASSED
failure: test_alignment_handler_vsx_300
[snip]

Fix this by making sure all VSX instruction emulation correctly
load/store from the VSRs.

Fixes: af99da74333b ("powerpc/sstep: Support VSX vector paired storage access instructions")
Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210225031946.1458206-1-jniethe5@gmail.com
---
 arch/powerpc/lib/sstep.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index bb5c20d4ca91..c6aebc149d14 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -904,7 +904,7 @@ static nokprobe_inline int do_vsx_load(struct instruction_op *op,
 	if (!address_ok(regs, ea, size) || copy_mem_in(mem, ea, size, regs))
 		return -EFAULT;
 
-	nr_vsx_regs = size / sizeof(__vector128);
+	nr_vsx_regs = max(1ul, size / sizeof(__vector128));
 	emulate_vsx_load(op, buf, mem, cross_endian);
 	preempt_disable();
 	if (reg < 32) {
@@ -951,7 +951,7 @@ static nokprobe_inline int do_vsx_store(struct instruction_op *op,
 	if (!address_ok(regs, ea, size))
 		return -EFAULT;
 
-	nr_vsx_regs = size / sizeof(__vector128);
+	nr_vsx_regs = max(1ul, size / sizeof(__vector128));
 	preempt_disable();
 	if (reg < 32) {
 		/* FP regs + extensions */

From 9cc0001a18b4e5f46ec481201c88ae16f0a69bb0 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Sat, 27 Feb 2021 22:31:27 +0100
Subject: [PATCH 0125/1820] netfilter: nftables: disallow updates on table
 ownership

Disallow updating the ownership bit on an existing table: Do not allow
to grab ownership on an existing table. Do not allow to drop ownership
on an existing table.

Fixes: 6001a930ce03 ("netfilter: nftables: introduce table ownership")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c1eb5cdb3033..b07703e19108 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -916,6 +916,12 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
 	if (flags == ctx->table->flags)
 		return 0;
 
+	if ((nft_table_has_owner(ctx->table) &&
+	     !(flags & NFT_TABLE_F_OWNER)) ||
+	    (!nft_table_has_owner(ctx->table) &&
+	     flags & NFT_TABLE_F_OWNER))
+		return -EOPNOTSUPP;
+
 	trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE,
 				sizeof(struct nft_trans_table));
 	if (trans == NULL)

From 778e45d7720d663811352943dd515b41f6849637 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Tue, 2 Mar 2021 21:07:07 +0100
Subject: [PATCH 0126/1820] parisc: Enable -mlong-calls gcc option with
 CONFIG_COMPILE_TEST

The kernel test robot reported multiple linkage problems like this:

    hppa64-linux-ld: init/main.o(.init.text+0x56c): cannot reach printk
    init/main.o: in function `unknown_bootoption':
    (.init.text+0x56c): relocation truncated to fit: R_PARISC_PCREL22F against
	symbol `printk' defined in .text.unlikely section in kernel/printk/printk.o

There are two ways to solve it:
a) Enable the -mlong-call compiler option (CONFIG_MLONGCALLS),
b) Add long branch stub support in 64-bit linker.

While b) is the long-term solution, this patch works around the issue by
automatically enabling the CONFIG_MLONGCALLS option when
CONFIG_COMPILE_TEST is set, which indicates that a non-production kernel
(e.g. 0-day kernel) is built.

Signed-off-by: Helge Deller <deller@gmx.de>
Reported-by: kernel test robot <lkp@intel.com>
Fixes: 00e35f2b0e8a ("parisc: Enable -mlong-calls gcc option by default when !CONFIG_MODULES")
Cc: stable@vger.kernel.org # v5.6+
---
 arch/parisc/Kconfig | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 4e53ac46e857..afc3b8d03572 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -203,9 +203,12 @@ config PREFETCH
 	def_bool y
 	depends on PA8X00 || PA7200
 
+config PARISC_HUGE_KERNEL
+	def_bool y if !MODULES || UBSAN || FTRACE || COMPILE_TEST
+
 config MLONGCALLS
-	def_bool y if !MODULES || UBSAN || FTRACE
-	bool "Enable the -mlong-calls compiler option for big kernels" if MODULES && !UBSAN && !FTRACE
+	def_bool y if PARISC_HUGE_KERNEL
+	bool "Enable the -mlong-calls compiler option for big kernels" if !PARISC_HUGE_KERNEL
 	depends on PA8X00
 	help
 	  If you configure the kernel to include many drivers built-in instead

From 6f7f657f24405f426212c09260bf7fe8a52cef33 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 28 Feb 2021 10:18:03 -0500
Subject: [PATCH 0127/1820] net: ieee802154: nl-mac: fix check on panid

This patch fixes a null pointer derefence for panid handle by move the
check for the netlink variable directly before accessing them.

Reported-by: syzbot+d4c07de0144f6f63be3a@syzkaller.appspotmail.com
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210228151817.95700-4-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl-mac.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index 9c640d670ffe..0c1b0770c59e 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -551,9 +551,7 @@ ieee802154_llsec_parse_key_id(struct genl_info *info,
 	desc->mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]);
 
 	if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) {
-		if (!info->attrs[IEEE802154_ATTR_PAN_ID] &&
-		    !(info->attrs[IEEE802154_ATTR_SHORT_ADDR] ||
-		      info->attrs[IEEE802154_ATTR_HW_ADDR]))
+		if (!info->attrs[IEEE802154_ATTR_PAN_ID])
 			return -EINVAL;
 
 		desc->device_addr.pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]);
@@ -562,6 +560,9 @@ ieee802154_llsec_parse_key_id(struct genl_info *info,
 			desc->device_addr.mode = IEEE802154_ADDR_SHORT;
 			desc->device_addr.short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]);
 		} else {
+			if (!info->attrs[IEEE802154_ATTR_HW_ADDR])
+				return -EINVAL;
+
 			desc->device_addr.mode = IEEE802154_ADDR_LONG;
 			desc->device_addr.extended_addr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
 		}

From fa706dce2f2d7012654e2eab40da2b526c1424b3 Mon Sep 17 00:00:00 2001
From: Wong Vee Khee <vee.khee.wong@intel.com>
Date: Tue, 2 Mar 2021 16:57:21 +0800
Subject: [PATCH 0128/1820] stmmac: intel: Fix mdio bus registration issue for
 TGL-H/ADL-S

On Intel platforms which consist of two Ethernet Controllers such as
TGL-H and ADL-S, a unique MDIO bus id is required for MDIO bus to be
successful registered:

[   13.076133] sysfs: cannot create duplicate filename '/class/mdio_bus/stmmac-1'
[   13.083404] CPU: 8 PID: 1898 Comm: systemd-udevd Tainted: G     U            5.11.0-net-next #106
[   13.092410] Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-S ADP-S DRR4 CRB, BIOS ADLIFSI1.R00.1494.B00.2012031421 12/03/2020
[   13.105709] Call Trace:
[   13.108176]  dump_stack+0x64/0x7c
[   13.111553]  sysfs_warn_dup+0x56/0x70
[   13.115273]  sysfs_do_create_link_sd.isra.2+0xbd/0xd0
[   13.120371]  device_add+0x4df/0x840
[   13.123917]  ? complete_all+0x2a/0x40
[   13.127636]  __mdiobus_register+0x98/0x310 [libphy]
[   13.132572]  stmmac_mdio_register+0x1c5/0x3f0 [stmmac]
[   13.137771]  ? stmmac_napi_add+0xa5/0xf0 [stmmac]
[   13.142493]  stmmac_dvr_probe+0x806/0xee0 [stmmac]
[   13.147341]  intel_eth_pci_probe+0x1cb/0x250 [dwmac_intel]
[   13.152884]  pci_device_probe+0xd2/0x150
[   13.156897]  really_probe+0xf7/0x4d0
[   13.160527]  driver_probe_device+0x5d/0x140
[   13.164761]  device_driver_attach+0x4f/0x60
[   13.168996]  __driver_attach+0xa2/0x140
[   13.172891]  ? device_driver_attach+0x60/0x60
[   13.177300]  bus_for_each_dev+0x76/0xc0
[   13.181188]  bus_add_driver+0x189/0x230
[   13.185083]  ? 0xffffffffc0795000
[   13.188446]  driver_register+0x5b/0xf0
[   13.192249]  ? 0xffffffffc0795000
[   13.195577]  do_one_initcall+0x4d/0x210
[   13.199467]  ? kmem_cache_alloc_trace+0x2ff/0x490
[   13.204228]  do_init_module+0x5b/0x21c
[   13.208031]  load_module+0x2a0c/0x2de0
[   13.211838]  ? __do_sys_finit_module+0xb1/0x110
[   13.216420]  __do_sys_finit_module+0xb1/0x110
[   13.220825]  do_syscall_64+0x33/0x40
[   13.224451]  entry_SYSCALL_64_after_hwframe+0x44/0xae
[   13.229515] RIP: 0033:0x7fc2b1919ccd
[   13.233113] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 93 31 0c 00 f7 d8 64 89 01 48
[   13.251912] RSP: 002b:00007ffcea2e5b98 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[   13.259527] RAX: ffffffffffffffda RBX: 0000560558920f10 RCX: 00007fc2b1919ccd
[   13.266706] RDX: 0000000000000000 RSI: 00007fc2b1a881e3 RDI: 0000000000000012
[   13.273887] RBP: 0000000000020000 R08: 0000000000000000 R09: 0000000000000000
[   13.281036] R10: 0000000000000012 R11: 0000000000000246 R12: 00007fc2b1a881e3
[   13.288183] R13: 0000000000000000 R14: 0000000000000000 R15: 00007ffcea2e5d58
[   13.295389] libphy: mii_bus stmmac-1 failed to register

Fixes: 88af9bd4efbd ("stmmac: intel: Add ADL-S 1Gbps PCI IDs")
Fixes: 8450e23f142f ("stmmac: intel: Add PCI IDs for TGL-H platform")
Signed-off-by: Wong Vee Khee <vee.khee.wong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/dwmac-intel.c | 54 ++++++++++++++-----
 1 file changed, 41 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 751dfdeec41c..f2896872a86c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -446,8 +446,8 @@ static int tgl_common_data(struct pci_dev *pdev,
 	return intel_mgbe_common_data(pdev, plat);
 }
 
-static int tgl_sgmii_data(struct pci_dev *pdev,
-			  struct plat_stmmacenet_data *plat)
+static int tgl_sgmii_phy0_data(struct pci_dev *pdev,
+			       struct plat_stmmacenet_data *plat)
 {
 	plat->bus_id = 1;
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
@@ -456,12 +456,26 @@ static int tgl_sgmii_data(struct pci_dev *pdev,
 	return tgl_common_data(pdev, plat);
 }
 
-static struct stmmac_pci_info tgl_sgmii1g_info = {
-	.setup = tgl_sgmii_data,
+static struct stmmac_pci_info tgl_sgmii1g_phy0_info = {
+	.setup = tgl_sgmii_phy0_data,
 };
 
-static int adls_sgmii_data(struct pci_dev *pdev,
-			   struct plat_stmmacenet_data *plat)
+static int tgl_sgmii_phy1_data(struct pci_dev *pdev,
+			       struct plat_stmmacenet_data *plat)
+{
+	plat->bus_id = 2;
+	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+	plat->serdes_powerup = intel_serdes_powerup;
+	plat->serdes_powerdown = intel_serdes_powerdown;
+	return tgl_common_data(pdev, plat);
+}
+
+static struct stmmac_pci_info tgl_sgmii1g_phy1_info = {
+	.setup = tgl_sgmii_phy1_data,
+};
+
+static int adls_sgmii_phy0_data(struct pci_dev *pdev,
+				struct plat_stmmacenet_data *plat)
 {
 	plat->bus_id = 1;
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
@@ -471,10 +485,24 @@ static int adls_sgmii_data(struct pci_dev *pdev,
 	return tgl_common_data(pdev, plat);
 }
 
-static struct stmmac_pci_info adls_sgmii1g_info = {
-	.setup = adls_sgmii_data,
+static struct stmmac_pci_info adls_sgmii1g_phy0_info = {
+	.setup = adls_sgmii_phy0_data,
 };
 
+static int adls_sgmii_phy1_data(struct pci_dev *pdev,
+				struct plat_stmmacenet_data *plat)
+{
+	plat->bus_id = 2;
+	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+
+	/* SerDes power up and power down are done in BIOS for ADL */
+
+	return tgl_common_data(pdev, plat);
+}
+
+static struct stmmac_pci_info adls_sgmii1g_phy1_info = {
+	.setup = adls_sgmii_phy1_data,
+};
 static const struct stmmac_pci_func_data galileo_stmmac_func_data[] = {
 	{
 		.func = 6,
@@ -756,11 +784,11 @@ static const struct pci_device_id intel_eth_pci_id_table[] = {
 	{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_RGMII1G_ID, &ehl_pse1_rgmii1g_info) },
 	{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII1G_ID, &ehl_pse1_sgmii1g_info) },
 	{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII2G5_ID, &ehl_pse1_sgmii1g_info) },
-	{ PCI_DEVICE_DATA(INTEL, TGL_SGMII1G_ID, &tgl_sgmii1g_info) },
-	{ PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_0_ID, &tgl_sgmii1g_info) },
-	{ PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_1_ID, &tgl_sgmii1g_info) },
-	{ PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_0_ID, &adls_sgmii1g_info) },
-	{ PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_1_ID, &adls_sgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, TGL_SGMII1G_ID, &tgl_sgmii1g_phy0_info) },
+	{ PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_0_ID, &tgl_sgmii1g_phy0_info) },
+	{ PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_1_ID, &tgl_sgmii1g_phy1_info) },
+	{ PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_0_ID, &adls_sgmii1g_phy0_info) },
+	{ PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_1_ID, &adls_sgmii1g_phy1_info) },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, intel_eth_pci_id_table);

From 95b39f07a17faef3a9b225248ba449b976e529c8 Mon Sep 17 00:00:00 2001
From: Biao Huang <biao.huang@mediatek.com>
Date: Tue, 2 Mar 2021 11:33:23 +0800
Subject: [PATCH 0129/1820] net: ethernet: mtk-star-emac: fix wrong unmap in RX
 handling

mtk_star_dma_unmap_rx() should unmap the dma_addr of old skb rather than
that of new skb.
Assign new_dma_addr to desc_data.dma_addr after all handling of old skb
ends to avoid unexpected receive side error.

Fixes: f96e9641e92b ("net: ethernet: mtk-star-emac: fix error path in RX handling")
Signed-off-by: Biao Huang <biao.huang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_star_emac.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index a8641a407c06..96d2891f1675 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1225,8 +1225,6 @@ static int mtk_star_receive_packet(struct mtk_star_priv *priv)
 		goto push_new_skb;
 	}
 
-	desc_data.dma_addr = new_dma_addr;
-
 	/* We can't fail anymore at this point: it's safe to unmap the skb. */
 	mtk_star_dma_unmap_rx(priv, &desc_data);
 
@@ -1236,6 +1234,9 @@ static int mtk_star_receive_packet(struct mtk_star_priv *priv)
 	desc_data.skb->dev = ndev;
 	netif_receive_skb(desc_data.skb);
 
+	/* update dma_addr for new skb */
+	desc_data.dma_addr = new_dma_addr;
+
 push_new_skb:
 	desc_data.len = skb_tailroom(new_skb);
 	desc_data.skb = new_skb;

From c7c1abfd6d42be8f09d390ab912cd84983000fa2 Mon Sep 17 00:00:00 2001
From: Eyal Birger <eyal.birger@gmail.com>
Date: Fri, 26 Feb 2021 23:35:05 +0200
Subject: [PATCH 0130/1820] vti: fix ipv4 pmtu check to honor ip header df

Frag needed should only be sent if the header enables DF.

This fix allows packets larger than MTU to pass the vti interface
and be fragmented after encapsulation, aligning behavior with
non-vti xfrm.

Fixes: d6af1a31cc72 ("vti: Add pmtu handling to vti_xmit.")
Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv4/ip_vti.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index abc171e79d3e..613741384490 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -218,7 +218,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (dst->flags & DST_XFRM_QUEUE)
-		goto queued;
+		goto xmit;
 
 	if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
 		dev->stats.tx_carrier_errors++;
@@ -238,6 +238,8 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 	if (skb->len > mtu) {
 		skb_dst_update_pmtu_no_confirm(skb, mtu);
 		if (skb->protocol == htons(ETH_P_IP)) {
+			if (!(ip_hdr(skb)->frag_off & htons(IP_DF)))
+				goto xmit;
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				  htonl(mtu));
 		} else {
@@ -251,7 +253,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-queued:
+xmit:
 	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
 	skb_dst_set(skb, dst);
 	skb->dev = skb_dst(skb)->dev;

From 4c38255892c06b9de2fb3bf6aea63f4ebdff3d11 Mon Sep 17 00:00:00 2001
From: Eyal Birger <eyal.birger@gmail.com>
Date: Fri, 26 Feb 2021 23:35:06 +0200
Subject: [PATCH 0131/1820] vti6: fix ipv4 pmtu check to honor ip header df

Frag needed should only be sent if the header enables DF.

This fix allows IPv4 packets larger than MTU to pass the vti6 interface
and be fragmented after encapsulation, aligning behavior with
non-vti6 xfrm.

Fixes: ccd740cbc6e0 ("vti6: Add pmtu handling to vti6_xmit.")
Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv6/ip6_vti.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 0225fd694192..2f0be5ac021c 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -494,7 +494,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	}
 
 	if (dst->flags & DST_XFRM_QUEUE)
-		goto queued;
+		goto xmit;
 
 	x = dst->xfrm;
 	if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr))
@@ -523,6 +523,8 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		} else {
+			if (!(ip_hdr(skb)->frag_off & htons(IP_DF)))
+				goto xmit;
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				  htonl(mtu));
 		}
@@ -531,7 +533,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 		goto tx_err_dst_release;
 	}
 
-queued:
+xmit:
 	skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
 	skb_dst_set(skb, dst);
 	skb->dev = skb_dst(skb)->dev;

From 9ab1265d52314fce1b51e8665ea6dbc9ac1a027c Mon Sep 17 00:00:00 2001
From: Evan Nimmo <evan.nimmo@alliedtelesis.co.nz>
Date: Tue, 2 Mar 2021 08:00:04 +1300
Subject: [PATCH 0132/1820] xfrm: Use actual socket sk instead of skb socket
 for xfrm_output_resume

A situation can occur where the interface bound to the sk is different
to the interface bound to the sk attached to the skb. The interface
bound to the sk is the correct one however this information is lost inside
xfrm_output2 and instead the sk on the skb is used in xfrm_output_resume
instead. This assumes that the sk bound interface and the bound interface
attached to the sk within the skb are the same which can lead to lookup
failures inside ip_route_me_harder resulting in the packet being dropped.

We have an l2tp v3 tunnel with ipsec protection. The tunnel is in the
global VRF however we have an encapsulated dot1q tunnel interface that
is within a different VRF. We also have a mangle rule that marks the
packets causing them to be processed inside ip_route_me_harder.

Prior to commit 31c70d5956fc ("l2tp: keep original skb ownership") this
worked fine as the sk attached to the skb was changed from the dot1q
encapsulated interface to the sk for the tunnel which meant the interface
bound to the sk and the interface bound to the skb were identical.
Commit 46d6c5ae953c ("netfilter: use actual socket sk rather than skb sk
when routing harder") fixed some of these issues however a similar
problem existed in the xfrm code.

Fixes: 31c70d5956fc ("l2tp: keep original skb ownership")
Signed-off-by: Evan Nimmo <evan.nimmo@alliedtelesis.co.nz>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h     |  2 +-
 net/ipv4/ah4.c         |  2 +-
 net/ipv4/esp4.c        |  2 +-
 net/ipv6/ah6.c         |  2 +-
 net/ipv6/esp6.c        |  2 +-
 net/xfrm/xfrm_output.c | 10 +++++-----
 6 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b2a06f10b62c..bfbc7810df94 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1557,7 +1557,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 int xfrm_trans_queue(struct sk_buff *skb,
 		     int (*finish)(struct net *, struct sock *,
 				   struct sk_buff *));
-int xfrm_output_resume(struct sk_buff *skb, int err);
+int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err);
 int xfrm_output(struct sock *sk, struct sk_buff *skb);
 
 #if IS_ENABLED(CONFIG_NET_PKTGEN)
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index d99e1be94019..36ed85bf2ad5 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -141,7 +141,7 @@ static void ah_output_done(struct crypto_async_request *base, int err)
 	}
 
 	kfree(AH_SKB_CB(skb)->tmp);
-	xfrm_output_resume(skb, err);
+	xfrm_output_resume(skb->sk, skb, err);
 }
 
 static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index a3271ec3e162..4b834bbf95e0 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -279,7 +279,7 @@ static void esp_output_done(struct crypto_async_request *base, int err)
 		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 			esp_output_tail_tcp(x, skb);
 		else
-			xfrm_output_resume(skb, err);
+			xfrm_output_resume(skb->sk, skb, err);
 	}
 }
 
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 440080da805b..080ee7f44c64 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -316,7 +316,7 @@ static void ah6_output_done(struct crypto_async_request *base, int err)
 	}
 
 	kfree(AH_SKB_CB(skb)->tmp);
-	xfrm_output_resume(skb, err);
+	xfrm_output_resume(skb->sk, skb, err);
 }
 
 static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 153ad103ba74..727d791ed5e6 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -314,7 +314,7 @@ static void esp_output_done(struct crypto_async_request *base, int err)
 		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 			esp_output_tail_tcp(x, skb);
 		else
-			xfrm_output_resume(skb, err);
+			xfrm_output_resume(skb->sk, skb, err);
 	}
 }
 
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index a7ab19353313..b81ca117dac7 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -503,22 +503,22 @@ out:
 	return err;
 }
 
-int xfrm_output_resume(struct sk_buff *skb, int err)
+int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err)
 {
 	struct net *net = xs_net(skb_dst(skb)->xfrm);
 
 	while (likely((err = xfrm_output_one(skb, err)) == 0)) {
 		nf_reset_ct(skb);
 
-		err = skb_dst(skb)->ops->local_out(net, skb->sk, skb);
+		err = skb_dst(skb)->ops->local_out(net, sk, skb);
 		if (unlikely(err != 1))
 			goto out;
 
 		if (!skb_dst(skb)->xfrm)
-			return dst_output(net, skb->sk, skb);
+			return dst_output(net, sk, skb);
 
 		err = nf_hook(skb_dst(skb)->ops->family,
-			      NF_INET_POST_ROUTING, net, skb->sk, skb,
+			      NF_INET_POST_ROUTING, net, sk, skb,
 			      NULL, skb_dst(skb)->dev, xfrm_output2);
 		if (unlikely(err != 1))
 			goto out;
@@ -534,7 +534,7 @@ EXPORT_SYMBOL_GPL(xfrm_output_resume);
 
 static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	return xfrm_output_resume(skb, 1);
+	return xfrm_output_resume(sk, skb, 1);
 }
 
 static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb)

From a22549f12767fce49c74c53a853595f82b727935 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Tue, 23 Feb 2021 14:00:39 +0000
Subject: [PATCH 0133/1820] iwlwifi: mvm: add terminate entry for dmi_system_id
 tables

Make sure dmi_system_id tables are NULL terminated. This crashed when LTO was enabled:

BUG: KASAN: global-out-of-bounds in dmi_check_system+0x5a/0x70
Read of size 1 at addr ffffffffc16af750 by task NetworkManager/1913

CPU: 4 PID: 1913 Comm: NetworkManager Not tainted 5.12.0-rc1+ #10057
Hardware name: LENOVO 20THCTO1WW/20THCTO1WW, BIOS N2VET27W (1.12 ) 12/21/2020
Call Trace:
 dump_stack+0x90/0xbe
 print_address_description.constprop.0+0x1d/0x140
 ? dmi_check_system+0x5a/0x70
 ? dmi_check_system+0x5a/0x70
 kasan_report.cold+0x7b/0xd4
 ? dmi_check_system+0x5a/0x70
 __asan_load1+0x4d/0x50
 dmi_check_system+0x5a/0x70
 iwl_mvm_up+0x1360/0x1690 [iwlmvm]
 ? iwl_mvm_send_recovery_cmd+0x270/0x270 [iwlmvm]
 ? setup_object.isra.0+0x27/0xd0
 ? kasan_poison+0x20/0x50
 ? ___slab_alloc.constprop.0+0x483/0x5b0
 ? mempool_kmalloc+0x17/0x20
 ? ftrace_graph_ret_addr+0x2a/0xb0
 ? kasan_poison+0x3c/0x50
 ? cfg80211_iftype_allowed+0x2e/0x90 [cfg80211]
 ? __kasan_check_write+0x14/0x20
 ? mutex_lock+0x86/0xe0
 ? __mutex_lock_slowpath+0x20/0x20
 __iwl_mvm_mac_start+0x49/0x290 [iwlmvm]
 iwl_mvm_mac_start+0x37/0x50 [iwlmvm]
 drv_start+0x73/0x1b0 [mac80211]
 ieee80211_do_open+0x53e/0xf10 [mac80211]
 ? ieee80211_check_concurrent_iface+0x266/0x2e0 [mac80211]
 ieee80211_open+0xb9/0x100 [mac80211]
 __dev_open+0x1b8/0x280

Fixes: a2ac0f48a07c ("iwlwifi: mvm: implement approved list for the PPAG feature")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Victor Michel <vic.michel.web@gmail.com>
Acked-by: Luca Coelho <luciano.coelho@intel.com>
[kvalo@codeaurora.org: improve commit log]
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210223140039.1708534-1-weiyongjun1@huawei.com
---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 15e2773ce7e7..5ee64f7f3c85 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1083,6 +1083,7 @@ static const struct dmi_system_id dmi_ppag_approved_list[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek COMPUTER INC."),
 		},
 	},
+	{}
 };
 
 static int iwl_mvm_ppag_init(struct iwl_mvm *mvm)

From 436b265671d653787eed9bc716f44882d2a458cb Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 1 Mar 2021 19:16:37 -0600
Subject: [PATCH 0134/1820] iwlwifi: fix ARCH=i386 compilation warnings

An unsigned long variable should rely on '%lu' format strings, not '%zd'

Fixes: a1a6a4cf49ece ("iwlwifi: pnvm: implement reading PNVM from UEFI")
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Acked-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210302011640.1276636-1-pierre-louis.bossart@linux.intel.com
---
 drivers/net/wireless/intel/iwlwifi/fw/pnvm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c
index fd070ca5e517..40f2109a097f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c
@@ -271,12 +271,12 @@ static int iwl_pnvm_get_from_efi(struct iwl_trans *trans,
 	err = efivar_entry_get(pnvm_efivar, NULL, &package_size, package);
 	if (err) {
 		IWL_DEBUG_FW(trans,
-			     "PNVM UEFI variable not found %d (len %zd)\n",
+			     "PNVM UEFI variable not found %d (len %lu)\n",
 			     err, package_size);
 		goto out;
 	}
 
-	IWL_DEBUG_FW(trans, "Read PNVM fro UEFI with size %zd\n", package_size);
+	IWL_DEBUG_FW(trans, "Read PNVM fro UEFI with size %lu\n", package_size);
 
 	*data = kmemdup(package->data, *len, GFP_KERNEL);
 	if (!*data)

From 295d4cd82b0181dd36b145fd535c13d623d7a335 Mon Sep 17 00:00:00 2001
From: Jiri Kosina <jkosina@suse.cz>
Date: Tue, 2 Mar 2021 11:34:51 +0100
Subject: [PATCH 0135/1820] iwlwifi: don't call netif_napi_add() with rxq->lock
 held (was Re: Lockdep warning in iwl_pcie_rx_handle())

We can't call netif_napi_add() with rxq-lock held, as there is a potential
for deadlock as spotted by lockdep (see below). rxq->lock is not
protecting anything over the netif_napi_add() codepath anyway, so let's
drop it just before calling into NAPI.

 ========================================================
 WARNING: possible irq lock inversion dependency detected
 5.12.0-rc1-00002-gbada49429032 #5 Not tainted
 --------------------------------------------------------
 irq/136-iwlwifi/565 just changed the state of lock:
 ffff89f28433b0b0 (&rxq->lock){+.-.}-{2:2}, at: iwl_pcie_rx_handle+0x7f/0x960 [iwlwifi]
 but this lock took another, SOFTIRQ-unsafe lock in the past:
  (napi_hash_lock){+.+.}-{2:2}

 and interrupts could create inverse lock ordering between them.

 other info that might help us debug this:
  Possible interrupt unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(napi_hash_lock);
                                local_irq_disable();
                                lock(&rxq->lock);
                                lock(napi_hash_lock);
   <Interrupt>
     lock(&rxq->lock);

  *** DEADLOCK ***

 1 lock held by irq/136-iwlwifi/565:
  #0: ffff89f2b1440170 (sync_cmd_lockdep_map){+.+.}-{0:0}, at: iwl_pcie_irq_handler+0x5/0xb30

 the shortest dependencies between 2nd lock and 1st lock:
  -> (napi_hash_lock){+.+.}-{2:2} {
     HARDIRQ-ON-W at:
                       lock_acquire+0x277/0x3d0
                       _raw_spin_lock+0x2c/0x40
                       netif_napi_add+0x14b/0x270
                       e1000_probe+0x2fe/0xee0 [e1000e]
                       local_pci_probe+0x42/0x90
                       pci_device_probe+0x10b/0x1c0
                       really_probe+0xef/0x4b0
                       driver_probe_device+0xde/0x150
                       device_driver_attach+0x4f/0x60
                       __driver_attach+0x9c/0x140
                       bus_for_each_dev+0x79/0xc0
                       bus_add_driver+0x18d/0x220
                       driver_register+0x5b/0xf0
                       do_one_initcall+0x5b/0x300
                       do_init_module+0x5b/0x21c
                       load_module+0x1dae/0x22c0
                       __do_sys_finit_module+0xad/0x110
                       do_syscall_64+0x33/0x80
                       entry_SYSCALL_64_after_hwframe+0x44/0xae
     SOFTIRQ-ON-W at:
                       lock_acquire+0x277/0x3d0
                       _raw_spin_lock+0x2c/0x40
                       netif_napi_add+0x14b/0x270
                       e1000_probe+0x2fe/0xee0 [e1000e]
                       local_pci_probe+0x42/0x90
                       pci_device_probe+0x10b/0x1c0
                       really_probe+0xef/0x4b0
                       driver_probe_device+0xde/0x150
                       device_driver_attach+0x4f/0x60
                       __driver_attach+0x9c/0x140
                       bus_for_each_dev+0x79/0xc0
                       bus_add_driver+0x18d/0x220
                       driver_register+0x5b/0xf0
                       do_one_initcall+0x5b/0x300
                       do_init_module+0x5b/0x21c
                       load_module+0x1dae/0x22c0
                       __do_sys_finit_module+0xad/0x110
                       do_syscall_64+0x33/0x80
                       entry_SYSCALL_64_after_hwframe+0x44/0xae
     INITIAL USE at:
                      lock_acquire+0x277/0x3d0
                      _raw_spin_lock+0x2c/0x40
                      netif_napi_add+0x14b/0x270
                      e1000_probe+0x2fe/0xee0 [e1000e]
                      local_pci_probe+0x42/0x90
                      pci_device_probe+0x10b/0x1c0
                      really_probe+0xef/0x4b0
                      driver_probe_device+0xde/0x150
                      device_driver_attach+0x4f/0x60
                      __driver_attach+0x9c/0x140
                      bus_for_each_dev+0x79/0xc0
                      bus_add_driver+0x18d/0x220
                      driver_register+0x5b/0xf0
                      do_one_initcall+0x5b/0x300
                      do_init_module+0x5b/0x21c
                      load_module+0x1dae/0x22c0
                      __do_sys_finit_module+0xad/0x110
                      do_syscall_64+0x33/0x80
                      entry_SYSCALL_64_after_hwframe+0x44/0xae
   }
   ... key      at: [<ffffffffae84ef38>] napi_hash_lock+0x18/0x40
   ... acquired at:
    _raw_spin_lock+0x2c/0x40
    netif_napi_add+0x14b/0x270
    _iwl_pcie_rx_init+0x1f4/0x710 [iwlwifi]
    iwl_pcie_rx_init+0x1b/0x3b0 [iwlwifi]
    iwl_trans_pcie_start_fw+0x2ac/0x6a0 [iwlwifi]
    iwl_mvm_load_ucode_wait_alive+0x116/0x460 [iwlmvm]
    iwl_run_init_mvm_ucode+0xa4/0x3a0 [iwlmvm]
    iwl_op_mode_mvm_start+0x9ed/0xbf0 [iwlmvm]
    _iwl_op_mode_start.isra.4+0x42/0x80 [iwlwifi]
    iwl_opmode_register+0x71/0xe0 [iwlwifi]
    iwl_mvm_init+0x34/0x1000 [iwlmvm]
    do_one_initcall+0x5b/0x300
    do_init_module+0x5b/0x21c
    load_module+0x1dae/0x22c0
    __do_sys_finit_module+0xad/0x110
    do_syscall_64+0x33/0x80
    entry_SYSCALL_64_after_hwframe+0x44/0xae

[ ... lockdep output trimmed .... ]

Fixes: 25edc8f259c7106 ("iwlwifi: pcie: properly implement NAPI")
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/nycvar.YFH.7.76.2103021134060.12405@cbobk.fhfr.pm
---
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 42426e25cac6..2bec97133119 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1129,6 +1129,8 @@ static int _iwl_pcie_rx_init(struct iwl_trans *trans)
 
 		iwl_pcie_rx_init_rxb_lists(rxq);
 
+		spin_unlock_bh(&rxq->lock);
+
 		if (!rxq->napi.poll) {
 			int (*poll)(struct napi_struct *, int) = iwl_pcie_napi_poll;
 
@@ -1149,7 +1151,6 @@ static int _iwl_pcie_rx_init(struct iwl_trans *trans)
 			napi_enable(&rxq->napi);
 		}
 
-		spin_unlock_bh(&rxq->lock);
 	}
 
 	/* move the pool to the default queue and allocator ownerships */

From 2378b2c9ecf437b918dff246b81b5b624ec14f80 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 2 Mar 2021 14:21:54 +0300
Subject: [PATCH 0136/1820] octeontx2-af: cn10k: fix an array overflow in
 is_lmac_valid()

The value of "lmac_id" can be controlled by the user and if it is larger
then the number of bits in long then it reads outside the bitmap.
The highest valid value is less than MAX_LMAC_PER_CGX (4).

Fixes: 91c6945ea1f9 ("octeontx2-af: cn10k: Add RPM MAC support")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 9caa375d01b1..68deae529bc9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -56,7 +56,9 @@ static bool is_dev_rpm(void *cgxd)
 
 bool is_lmac_valid(struct cgx *cgx, int lmac_id)
 {
-	return cgx && test_bit(lmac_id, &cgx->lmac_bmap);
+	if (!cgx || lmac_id < 0 || lmac_id >= MAX_LMAC_PER_CGX)
+		return false;
+	return test_bit(lmac_id, &cgx->lmac_bmap);
 }
 
 struct mac_ops *get_mac_ops(void *cgxd)

From 6881b07fdd24850def1f03761c66042b983ff86e Mon Sep 17 00:00:00 2001
From: Michal Suchanek <msuchanek@suse.de>
Date: Tue, 2 Mar 2021 20:47:47 +0100
Subject: [PATCH 0137/1820] ibmvnic: Fix possibly uninitialized
 old_num_tx_queues variable warning.

GCC 7.5 reports:
../drivers/net/ethernet/ibm/ibmvnic.c: In function 'ibmvnic_reset_init':
../drivers/net/ethernet/ibm/ibmvnic.c:5373:51: warning: 'old_num_tx_queues' may be used uninitialized in this function [-Wmaybe-uninitialized]
../drivers/net/ethernet/ibm/ibmvnic.c:5373:6: warning: 'old_num_rx_queues' may be used uninitialized in this function [-Wmaybe-uninitialized]

The variable is initialized only if(reset) and used only if(reset &&
something) so this is a false positive. However, there is no reason to
not initialize the variables unconditionally avoiding the warning.

Fixes: 635e442f4a48 ("ibmvnic: merge ibmvnic_reset_init and ibmvnic_init")
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
Reviewed-by: Sukadev Bhattiprolu <sukadev@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 118a4bd3f877..3bad762083c5 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -5219,16 +5219,14 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset)
 {
 	struct device *dev = &adapter->vdev->dev;
 	unsigned long timeout = msecs_to_jiffies(20000);
-	u64 old_num_rx_queues, old_num_tx_queues;
+	u64 old_num_rx_queues = adapter->req_rx_queues;
+	u64 old_num_tx_queues = adapter->req_tx_queues;
 	int rc;
 
 	adapter->from_passive_init = false;
 
-	if (reset) {
-		old_num_rx_queues = adapter->req_rx_queues;
-		old_num_tx_queues = adapter->req_tx_queues;
+	if (reset)
 		reinit_completion(&adapter->init_done);
-	}
 
 	adapter->init_done_rc = 0;
 	rc = ibmvnic_send_crq_init(adapter);

From 879c348c35bb5fb758dd881d8a97409c1862dae8 Mon Sep 17 00:00:00 2001
From: Ong Boon Leong <boon.leong.ong@intel.com>
Date: Wed, 3 Mar 2021 20:38:40 +0530
Subject: [PATCH 0138/1820] net: stmmac: fix incorrect DMA channel intr enable
 setting of EQoS v4.10

We introduce dwmac410_dma_init_channel() here for both EQoS v4.10 and
above which use different DMA_CH(n)_Interrupt_Enable bit definitions for
NIE and AIE.

Fixes: 48863ce5940f ("stmmac: add DMA support for GMAC 4.xx")
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Ramesh Babu B <ramesh.babu.b@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/dwmac4_dma.c  | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index bb29bfcd62c3..62aa0e95beb7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -124,6 +124,23 @@ static void dwmac4_dma_init_channel(void __iomem *ioaddr,
 	       ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
+static void dwmac410_dma_init_channel(void __iomem *ioaddr,
+				      struct stmmac_dma_cfg *dma_cfg, u32 chan)
+{
+	u32 value;
+
+	/* common channel control register config */
+	value = readl(ioaddr + DMA_CHAN_CONTROL(chan));
+	if (dma_cfg->pblx8)
+		value = value | DMA_BUS_MODE_PBL;
+
+	writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
+
+	/* Mask interrupts by writing to CSR7 */
+	writel(DMA_CHAN_INTR_DEFAULT_MASK_4_10,
+	       ioaddr + DMA_CHAN_INTR_ENA(chan));
+}
+
 static void dwmac4_dma_init(void __iomem *ioaddr,
 			    struct stmmac_dma_cfg *dma_cfg, int atds)
 {
@@ -523,7 +540,7 @@ const struct stmmac_dma_ops dwmac4_dma_ops = {
 const struct stmmac_dma_ops dwmac410_dma_ops = {
 	.reset = dwmac4_dma_reset,
 	.init = dwmac4_dma_init,
-	.init_chan = dwmac4_dma_init_channel,
+	.init_chan = dwmac410_dma_init_channel,
 	.init_rx_chan = dwmac4_dma_init_rx_chan,
 	.init_tx_chan = dwmac4_dma_init_tx_chan,
 	.axi = dwmac4_dma_axi,

From dbbe7c962c3a8163bf724dbc3c9fdfc9b16d3117 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 2 Mar 2021 18:46:43 -0800
Subject: [PATCH 0139/1820] docs: networking: drop special stable handling

Leave it to Greg.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/netdev-FAQ.rst       | 72 ++-----------------
 Documentation/process/stable-kernel-rules.rst |  6 --
 Documentation/process/submitting-patches.rst  |  5 --
 3 files changed, 6 insertions(+), 77 deletions(-)

diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst
index a64c01b52b4c..91b2cf712801 100644
--- a/Documentation/networking/netdev-FAQ.rst
+++ b/Documentation/networking/netdev-FAQ.rst
@@ -142,73 +142,13 @@ Please send incremental versions on top of what has been merged in order to fix
 the patches the way they would look like if your latest patch series was to be
 merged.
 
-How can I tell what patches are queued up for backporting to the various stable releases?
------------------------------------------------------------------------------------------
-Normally Greg Kroah-Hartman collects stable commits himself, but for
-networking, Dave collects up patches he deems critical for the
-networking subsystem, and then hands them off to Greg.
-
-There is a patchworks queue that you can see here:
-
-  https://patchwork.kernel.org/bundle/netdev/stable/?state=*
-
-It contains the patches which Dave has selected, but not yet handed off
-to Greg.  If Greg already has the patch, then it will be here:
-
-  https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git
-
-A quick way to find whether the patch is in this stable-queue is to
-simply clone the repo, and then git grep the mainline commit ID, e.g.
-::
-
-  stable-queue$ git grep -l 284041ef21fdf2e
-  releases/3.0.84/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
-  releases/3.4.51/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
-  releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
-  stable/stable-queue$
-
-I see a network patch and I think it should be backported to stable. Should I request it via stable@vger.kernel.org like the references in the kernel's Documentation/process/stable-kernel-rules.rst file say?
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
-No, not for networking.  Check the stable queues as per above first
-to see if it is already queued.  If not, then send a mail to netdev,
-listing the upstream commit ID and why you think it should be a stable
-candidate.
-
-Before you jump to go do the above, do note that the normal stable rules
-in :ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`
-still apply.  So you need to explicitly indicate why it is a critical
-fix and exactly what users are impacted.  In addition, you need to
-convince yourself that you *really* think it has been overlooked,
-vs. having been considered and rejected.
-
-Generally speaking, the longer it has had a chance to "soak" in
-mainline, the better the odds that it is an OK candidate for stable.  So
-scrambling to request a commit be added the day after it appears should
-be avoided.
-
-I have created a network patch and I think it should be backported to stable. Should I add a Cc: stable@vger.kernel.org like the references in the kernel's Documentation/ directory say?
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
-No.  See above answer.  In short, if you think it really belongs in
-stable, then ensure you write a decent commit log that describes who
-gets impacted by the bug fix and how it manifests itself, and when the
-bug was introduced.  If you do that properly, then the commit will get
-handled appropriately and most likely get put in the patchworks stable
-queue if it really warrants it.
-
-If you think there is some valid information relating to it being in
-stable that does *not* belong in the commit log, then use the three dash
-marker line as described in
-:ref:`Documentation/process/submitting-patches.rst <the_canonical_patch_format>`
-to temporarily embed that information into the patch that you send.
-
-Are all networking bug fixes backported to all stable releases?
+Are there special rules regarding stable submissions on netdev?
 ---------------------------------------------------------------
-Due to capacity, Dave could only take care of the backports for the
-last two stable releases. For earlier stable releases, each stable
-branch maintainer is supposed to take care of them. If you find any
-patch is missing from an earlier stable branch, please notify
-stable@vger.kernel.org with either a commit ID or a formal patch
-backported, and CC Dave and other relevant networking developers.
+While it used to be the case that netdev submissions were not supposed
+to carry explicit ``CC: stable@vger.kernel.org`` tags that is no longer
+the case today. Please follow the standard stable rules in
+:ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`,
+and make sure you include appropriate Fixes tags!
 
 Is the comment style convention different for the networking content?
 ---------------------------------------------------------------------
diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst
index 3973556250e1..003c865e9c21 100644
--- a/Documentation/process/stable-kernel-rules.rst
+++ b/Documentation/process/stable-kernel-rules.rst
@@ -35,12 +35,6 @@ Rules on what kind of patches are accepted, and which ones are not, into the
 Procedure for submitting patches to the -stable tree
 ----------------------------------------------------
 
- - If the patch covers files in net/ or drivers/net please follow netdev stable
-   submission guidelines as described in
-   :ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>`
-   after first checking the stable networking queue at
-   https://patchwork.kernel.org/bundle/netdev/stable/?state=*
-   to ensure the requested patch is not already queued up.
  - Security patches should not be handled (solely) by the -stable review
    process but should follow the procedures in
    :ref:`Documentation/admin-guide/security-bugs.rst <securitybugs>`.
diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst
index 8c991c863628..91de63b201c1 100644
--- a/Documentation/process/submitting-patches.rst
+++ b/Documentation/process/submitting-patches.rst
@@ -250,11 +250,6 @@ should also read
 :ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`
 in addition to this file.
 
-Note, however, that some subsystem maintainers want to come to their own
-conclusions on which patches should go to the stable trees.  The networking
-maintainer, in particular, would rather not see individual developers
-adding lines like the above to their patches.
-
 If changes affect userland-kernel interfaces, please send the MAN-PAGES
 maintainer (as listed in the MAINTAINERS file) a man-pages patch, or at
 least a notification of the change, so that some information makes its way

From fc7c5c208eb7bc2df3a9f4234f14eca250001cb6 Mon Sep 17 00:00:00 2001
From: John Ernberg <john.ernberg@actia.se>
Date: Wed, 3 Mar 2021 18:14:39 +0000
Subject: [PATCH 0140/1820] ALSA: usb: Add Plantronics C320-M USB ctrl msg
 delay quirk

The microphone in the Plantronics C320-M headset will randomly
fail to initialize properly, at least when using Microsoft Teams.
Introducing a 20ms delay on the control messages appears to
resolve the issue.

Link: https://gitlab.freedesktop.org/pulseaudio/pulseaudio/-/issues/1065
Tested-by: Andreas Kempe <kempe@lysator.liu.se>
Signed-off-by: John Ernberg <john.ernberg@actia.se>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210303181405.39835-1-john.ernberg@actia.se
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 737b2729c0d3..0864692d8a7b 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1670,6 +1670,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	    && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
 		msleep(20);
 
+	/*
+	 * Plantronics C320-M needs a delay to avoid random
+	 * microhpone failures.
+	 */
+	if (chip->usb_id == USB_ID(0x047f, 0xc025)  &&
+	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
+		msleep(20);
+
 	/* Zoom R16/24, many Logitech(at least H650e/H570e/BCC950),
 	 * Jabra 550a, Kingston HyperX needs a tiny delay here,
 	 * otherwise requests like get/set frequency return

From b12422362ce947098ac420ac3c975fc006af4c02 Mon Sep 17 00:00:00 2001
From: Atish Patra <atish.patra@wdc.com>
Date: Wed, 3 Mar 2021 11:55:49 -0800
Subject: [PATCH 0141/1820] net: macb: Add default usrio config to default gem
 config

There is no usrio config defined for default gem config leading to
a kernel panic devices that don't define a data. This issue can be
reprdouced with microchip polar fire soc where compatible string
is defined as "cdns,macb".

Fixes: edac63861db7 ("add userio bits as platform configuration")

Signed-off-by: Atish Patra <atish.patra@wdc.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 472bf8f220bc..15362d016a87 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3954,6 +3954,13 @@ static int macb_init(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct macb_usrio_config macb_default_usrio = {
+	.mii = MACB_BIT(MII),
+	.rmii = MACB_BIT(RMII),
+	.rgmii = GEM_BIT(RGMII),
+	.refclk = MACB_BIT(CLKEN),
+};
+
 #if defined(CONFIG_OF)
 /* 1518 rounded up */
 #define AT91ETHER_MAX_RBUFF_SZ	0x600
@@ -4439,13 +4446,6 @@ static int fu540_c000_init(struct platform_device *pdev)
 	return macb_init(pdev);
 }
 
-static const struct macb_usrio_config macb_default_usrio = {
-	.mii = MACB_BIT(MII),
-	.rmii = MACB_BIT(RMII),
-	.rgmii = GEM_BIT(RGMII),
-	.refclk = MACB_BIT(CLKEN),
-};
-
 static const struct macb_usrio_config sama7g5_usrio = {
 	.mii = 0,
 	.rmii = 1,
@@ -4594,6 +4594,7 @@ static const struct macb_config default_gem_config = {
 	.dma_burst_length = 16,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
+	.usrio = &macb_default_usrio,
 	.jumbo_max_len = 10240,
 };
 

From 3e59e8856758eb5a2dfe1f831ef53b168fd58105 Mon Sep 17 00:00:00 2001
From: Matthias Schiffer <mschiffer@universe-factory.net>
Date: Wed, 3 Mar 2021 16:50:49 +0100
Subject: [PATCH 0142/1820] net: l2tp: reduce log level of messages in receive
 path, add counter instead

Commit 5ee759cda51b ("l2tp: use standard API for warning log messages")
changed a number of warnings about invalid packets in the receive path
so that they are always shown, instead of only when a special L2TP debug
flag is set. Even with rate limiting these warnings can easily cause
significant log spam - potentially triggered by a malicious party
sending invalid packets on purpose.

In addition these warnings were noticed by projects like Tunneldigger [1],
which uses L2TP for its data path, but implements its own control
protocol (which is sufficiently different from L2TP data packets that it
would always be passed up to userspace even with future extensions of
L2TP).

Some of the warnings were already redundant, as l2tp_stats has a counter
for these packets. This commit adds one additional counter for invalid
packets that are passed up to userspace. Packets with unknown session are
not counted as invalid, as there is nothing wrong with the format of
these packets.

With the additional counter, all of these messages are either redundant
or benign, so we reduce them to pr_debug_ratelimited().

[1] https://github.com/wlanslovenija/tunneldigger/issues/160

Fixes: 5ee759cda51b ("l2tp: use standard API for warning log messages")
Signed-off-by: Matthias Schiffer <mschiffer@universe-factory.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/l2tp.h |  1 +
 net/l2tp/l2tp_core.c      | 41 +++++++++++++++++++++------------------
 net/l2tp/l2tp_core.h      |  1 +
 net/l2tp/l2tp_netlink.c   |  6 ++++++
 4 files changed, 30 insertions(+), 19 deletions(-)

diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 30c80d5ba4bf..bab8c9708611 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -145,6 +145,7 @@ enum {
 	L2TP_ATTR_RX_ERRORS,		/* u64 */
 	L2TP_ATTR_STATS_PAD,
 	L2TP_ATTR_RX_COOKIE_DISCARDS,	/* u64 */
+	L2TP_ATTR_RX_INVALID,		/* u64 */
 	__L2TP_ATTR_STATS_MAX,
 };
 
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 7be5103ff2a8..203890e378cb 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -649,9 +649,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 	/* Parse and check optional cookie */
 	if (session->peer_cookie_len > 0) {
 		if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) {
-			pr_warn_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n",
-					    tunnel->name, tunnel->tunnel_id,
-					    session->session_id);
+			pr_debug_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n",
+					     tunnel->name, tunnel->tunnel_id,
+					     session->session_id);
 			atomic_long_inc(&session->stats.rx_cookie_discards);
 			goto discard;
 		}
@@ -702,8 +702,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		 * If user has configured mandatory sequence numbers, discard.
 		 */
 		if (session->recv_seq) {
-			pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
-					    session->name);
+			pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
+					     session->name);
 			atomic_long_inc(&session->stats.rx_seq_discards);
 			goto discard;
 		}
@@ -718,8 +718,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 			session->send_seq = 0;
 			l2tp_session_set_header_len(session, tunnel->version);
 		} else if (session->send_seq) {
-			pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
-					    session->name);
+			pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
+					     session->name);
 			atomic_long_inc(&session->stats.rx_seq_discards);
 			goto discard;
 		}
@@ -809,9 +809,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 
 	/* Short packet? */
 	if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) {
-		pr_warn_ratelimited("%s: recv short packet (len=%d)\n",
-				    tunnel->name, skb->len);
-		goto error;
+		pr_debug_ratelimited("%s: recv short packet (len=%d)\n",
+				     tunnel->name, skb->len);
+		goto invalid;
 	}
 
 	/* Point to L2TP header */
@@ -824,9 +824,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 	/* Check protocol version */
 	version = hdrflags & L2TP_HDR_VER_MASK;
 	if (version != tunnel->version) {
-		pr_warn_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n",
-				    tunnel->name, version, tunnel->version);
-		goto error;
+		pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n",
+				     tunnel->name, version, tunnel->version);
+		goto invalid;
 	}
 
 	/* Get length of L2TP packet */
@@ -834,7 +834,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 
 	/* If type is control packet, it is handled by userspace. */
 	if (hdrflags & L2TP_HDRFLAG_T)
-		goto error;
+		goto pass;
 
 	/* Skip flags */
 	ptr += 2;
@@ -863,21 +863,24 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 			l2tp_session_dec_refcount(session);
 
 		/* Not found? Pass to userspace to deal with */
-		pr_warn_ratelimited("%s: no session found (%u/%u). Passing up.\n",
-				    tunnel->name, tunnel_id, session_id);
-		goto error;
+		pr_debug_ratelimited("%s: no session found (%u/%u). Passing up.\n",
+				     tunnel->name, tunnel_id, session_id);
+		goto pass;
 	}
 
 	if (tunnel->version == L2TP_HDR_VER_3 &&
 	    l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
-		goto error;
+		goto invalid;
 
 	l2tp_recv_common(session, skb, ptr, optr, hdrflags, length);
 	l2tp_session_dec_refcount(session);
 
 	return 0;
 
-error:
+invalid:
+	atomic_long_inc(&tunnel->stats.rx_invalid);
+
+pass:
 	/* Put UDP header back */
 	__skb_push(skb, sizeof(struct udphdr));
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index cb21d906343e..98ea98eb9567 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -39,6 +39,7 @@ struct l2tp_stats {
 	atomic_long_t		rx_oos_packets;
 	atomic_long_t		rx_errors;
 	atomic_long_t		rx_cookie_discards;
+	atomic_long_t		rx_invalid;
 };
 
 struct l2tp_tunnel;
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 83956c9ee1fc..96eb91be9238 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -428,6 +428,9 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 			      L2TP_ATTR_STATS_PAD) ||
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_ERRORS,
 			      atomic_long_read(&tunnel->stats.rx_errors),
+			      L2TP_ATTR_STATS_PAD) ||
+	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_INVALID,
+			      atomic_long_read(&tunnel->stats.rx_invalid),
 			      L2TP_ATTR_STATS_PAD))
 		goto nla_put_failure;
 	nla_nest_end(skb, nest);
@@ -771,6 +774,9 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 			      L2TP_ATTR_STATS_PAD) ||
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_ERRORS,
 			      atomic_long_read(&session->stats.rx_errors),
+			      L2TP_ATTR_STATS_PAD) ||
+	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_INVALID,
+			      atomic_long_read(&session->stats.rx_invalid),
 			      L2TP_ATTR_STATS_PAD))
 		goto nla_put_failure;
 	nla_nest_end(skb, nest);

From 4b5dc1a94d4f92b5845e98bd9ae344b26d933aad Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 3 Mar 2021 16:39:47 +0800
Subject: [PATCH 0143/1820] Revert "r8152: adjust the settings about MAC clock
 speed down for RTL8153"

This reverts commit 134f98bcf1b898fb9d6f2b91bc85dd2e5478b4b8.

The r8153_mac_clk_spd() is used for RTL8153A only, because the register
table of RTL8153B is different from RTL8153A. However, this function would
be called when RTL8153B calls r8153_first_init() and r8153_enter_oob().
That causes RTL8153B becomes unstable when suspending and resuming. The
worst case may let the device stop working.

Besides, revert this commit to disable MAC clock speed down for RTL8153A.
It would avoid the known issue when enabling U1. The data of the first
control transfer may be wrong when exiting U1.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 35 ++++++-----------------------------
 1 file changed, 6 insertions(+), 29 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index b246817f3405..90f1c0200042 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3021,29 +3021,6 @@ static void __rtl_set_wol(struct r8152 *tp, u32 wolopts)
 		device_set_wakeup_enable(&tp->udev->dev, false);
 }
 
-static void r8153_mac_clk_spd(struct r8152 *tp, bool enable)
-{
-	/* MAC clock speed down */
-	if (enable) {
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL,
-			       ALDPS_SPDWN_RATIO);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2,
-			       EEE_SPDWN_RATIO);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3,
-			       PKT_AVAIL_SPDWN_EN | SUSPEND_SPDWN_EN |
-			       U1U2_SPDWN_EN | L1_SPDWN_EN);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4,
-			       PWRSAVE_SPDWN_EN | RXDV_SPDWN_EN | TX10MIDLE_EN |
-			       TP100_SPDWN_EN | TP500_SPDWN_EN | EEE_SPDWN_EN |
-			       TP1000_SPDWN_EN);
-	} else {
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, 0);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, 0);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, 0);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, 0);
-	}
-}
-
 static void r8153_u1u2en(struct r8152 *tp, bool enable)
 {
 	u8 u1u2[8];
@@ -3338,11 +3315,9 @@ static void rtl8153_runtime_enable(struct r8152 *tp, bool enable)
 	if (enable) {
 		r8153_u1u2en(tp, false);
 		r8153_u2p3en(tp, false);
-		r8153_mac_clk_spd(tp, true);
 		rtl_runtime_suspend_enable(tp, true);
 	} else {
 		rtl_runtime_suspend_enable(tp, false);
-		r8153_mac_clk_spd(tp, false);
 
 		switch (tp->version) {
 		case RTL_VER_03:
@@ -4718,7 +4693,6 @@ static void r8153_first_init(struct r8152 *tp)
 {
 	u32 ocp_data;
 
-	r8153_mac_clk_spd(tp, false);
 	rxdy_gated_en(tp, true);
 	r8153_teredo_off(tp);
 
@@ -4769,8 +4743,6 @@ static void r8153_enter_oob(struct r8152 *tp)
 {
 	u32 ocp_data;
 
-	r8153_mac_clk_spd(tp, true);
-
 	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
 	ocp_data &= ~NOW_IS_OOB;
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
@@ -5496,10 +5468,15 @@ static void r8153_init(struct r8152 *tp)
 
 	ocp_write_word(tp, MCU_TYPE_USB, USB_CONNECT_TIMER, 0x0001);
 
+	/* MAC clock speed down */
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, 0);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, 0);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, 0);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, 0);
+
 	r8153_power_cut_en(tp, false);
 	rtl_runtime_suspend_enable(tp, false);
 	r8153_u1u2en(tp, true);
-	r8153_mac_clk_spd(tp, false);
 	usb_enable_lpm(tp->udev);
 
 	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);

From d65614a01d24704b016635abf5cc028a54e45a62 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Tue, 2 Mar 2021 17:19:32 +0800
Subject: [PATCH 0144/1820] net: 9p: advance iov on empty read

I met below warning when cating a small size(about 80bytes) txt file
on 9pfs(msize=2097152 is passed to 9p mount option), the reason is we
miss iov_iter_advance() if the read count is 0 for zerocopy case, so
we didn't truncate the pipe, then iov_iter_pipe() thinks the pipe is
full. Fix it by removing the exception for 0 to ensure to call
iov_iter_advance() even on empty read for zerocopy case.

[    8.279568] WARNING: CPU: 0 PID: 39 at lib/iov_iter.c:1203 iov_iter_pipe+0x31/0x40
[    8.280028] Modules linked in:
[    8.280561] CPU: 0 PID: 39 Comm: cat Not tainted 5.11.0+ #6
[    8.281260] RIP: 0010:iov_iter_pipe+0x31/0x40
[    8.281974] Code: 2b 42 54 39 42 5c 76 22 c7 07 20 00 00 00 48 89 57 18 8b 42 50 48 c7 47 08 b
[    8.283169] RSP: 0018:ffff888000cbbd80 EFLAGS: 00000246
[    8.283512] RAX: 0000000000000010 RBX: ffff888000117d00 RCX: 0000000000000000
[    8.283876] RDX: ffff88800031d600 RSI: 0000000000000000 RDI: ffff888000cbbd90
[    8.284244] RBP: ffff888000cbbe38 R08: 0000000000000000 R09: ffff8880008d2058
[    8.284605] R10: 0000000000000002 R11: ffff888000375510 R12: 0000000000000050
[    8.284964] R13: ffff888000cbbe80 R14: 0000000000000050 R15: ffff88800031d600
[    8.285439] FS:  00007f24fd8af600(0000) GS:ffff88803ec00000(0000) knlGS:0000000000000000
[    8.285844] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    8.286150] CR2: 00007f24fd7d7b90 CR3: 0000000000c97000 CR4: 00000000000406b0
[    8.286710] Call Trace:
[    8.288279]  generic_file_splice_read+0x31/0x1a0
[    8.289273]  ? do_splice_to+0x2f/0x90
[    8.289511]  splice_direct_to_actor+0xcc/0x220
[    8.289788]  ? pipe_to_sendpage+0xa0/0xa0
[    8.290052]  do_splice_direct+0x8b/0xd0
[    8.290314]  do_sendfile+0x1ad/0x470
[    8.290576]  do_syscall_64+0x2d/0x40
[    8.290818]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[    8.291409] RIP: 0033:0x7f24fd7dca0a
[    8.292511] Code: c3 0f 1f 80 00 00 00 00 4c 89 d2 4c 89 c6 e9 bd fd ff ff 0f 1f 44 00 00 31 8
[    8.293360] RSP: 002b:00007ffc20932818 EFLAGS: 00000206 ORIG_RAX: 0000000000000028
[    8.293800] RAX: ffffffffffffffda RBX: 0000000001000000 RCX: 00007f24fd7dca0a
[    8.294153] RDX: 0000000000000000 RSI: 0000000000000003 RDI: 0000000000000001
[    8.294504] RBP: 0000000000000003 R08: 0000000000000000 R09: 0000000000000000
[    8.294867] R10: 0000000001000000 R11: 0000000000000206 R12: 0000000000000003
[    8.295217] R13: 0000000000000001 R14: 0000000000000001 R15: 0000000000000000
[    8.295782] ---[ end trace 63317af81b3ca24b ]---

Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/9p/client.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/9p/client.c b/net/9p/client.c
index 4f62f299da0c..0a9019da18f3 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -1623,10 +1623,6 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to,
 	}
 
 	p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
-	if (!count) {
-		p9_tag_remove(clnt, req);
-		return 0;
-	}
 
 	if (non_zc) {
 		int n = copy_to_iter(dataptr, count, to);

From a9ecb0cbf03746b17a7c13bd8e3464e6789f73e8 Mon Sep 17 00:00:00 2001
From: zhang kai <zhangkaiheb@126.com>
Date: Tue, 2 Mar 2021 18:16:07 +0800
Subject: [PATCH 0145/1820] rtnetlink: using dev_base_seq from target net

Signed-off-by: zhang kai <zhangkaiheb@126.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 0edc0b2baaa4..1bdcb33fb561 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2147,7 +2147,7 @@ out:
 out_err:
 	cb->args[1] = idx;
 	cb->args[0] = h;
-	cb->seq = net->dev_base_seq;
+	cb->seq = tgt_net->dev_base_seq;
 	nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 	if (netnsid >= 0)
 		put_net(tgt_net);

From 2888b080d05c819205bbfe52c624a639f44c266a Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 3 Mar 2021 23:58:27 +0100
Subject: [PATCH 0146/1820] netfilter: nftables: fix possible double hook
 unregistration with table owner

Skip hook unregistration of owner tables from the netns exit path,
nft_rcv_nl_event() unregisters the table hooks before tearing down
the table content.

Fixes: 6001a930ce03 ("netfilter: nftables: introduce table ownership")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index b07703e19108..796ce86ef7eb 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -9028,8 +9028,12 @@ static void __nft_release_hooks(struct net *net)
 {
 	struct nft_table *table;
 
-	list_for_each_entry(table, &net->nft.tables, list)
+	list_for_each_entry(table, &net->nft.tables, list) {
+		if (nft_table_has_owner(table))
+			continue;
+
 		__nft_release_hook(net, table);
+	}
 }
 
 static void __nft_release_table(struct net *net, struct nft_table *table)

From bd1777b3a88f98e223392221b330668458aac7f1 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 4 Mar 2021 04:00:09 +0100
Subject: [PATCH 0147/1820] netfilter: nftables: bogus check for netlink portID
 with table owner

The existing branch checks for 0 != table->nlpid which always evaluates
true for tables that have an owner.

Fixes: 6001a930ce03 ("netfilter: nftables: introduce table ownership")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 796ce86ef7eb..224c8e537cb3 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -9083,13 +9083,12 @@ static void __nft_release_table(struct net *net, struct nft_table *table)
 	nf_tables_table_destroy(&ctx);
 }
 
-static void __nft_release_tables(struct net *net, u32 nlpid)
+static void __nft_release_tables(struct net *net)
 {
 	struct nft_table *table, *nt;
 
 	list_for_each_entry_safe(table, nt, &net->nft.tables, list) {
-		if (nft_table_has_owner(table) &&
-		    nlpid != table->nlpid)
+		if (nft_table_has_owner(table))
 			continue;
 
 		__nft_release_table(net, table);
@@ -9155,7 +9154,7 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 	mutex_lock(&net->nft.commit_mutex);
 	if (!list_empty(&net->nft.commit_list))
 		__nf_tables_abort(net, NFNL_ABORT_NONE);
-	__nft_release_tables(net, 0);
+	__nft_release_tables(net);
 	mutex_unlock(&net->nft.commit_mutex);
 	WARN_ON_ONCE(!list_empty(&net->nft.tables));
 	WARN_ON_ONCE(!list_empty(&net->nft.module_list));

From 9799110825dba087c2bdce886977cf84dada2005 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Thu, 4 Mar 2021 12:34:16 +0800
Subject: [PATCH 0148/1820] ALSA: usb-audio: Disable USB autosuspend properly
 in setup_disable_autosuspend()

Rear audio on Lenovo ThinkStation P620 stops working after commit
1965c4364bdd ("ALSA: usb-audio: Disable autosuspend for Lenovo
ThinkStation P620"):
[    6.013526] usbcore: registered new interface driver snd-usb-audio
[    6.023064] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x100, wIndex = 0x0, type = 1
[    6.023083] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x202, wIndex = 0x0, type = 4
[    6.023090] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x100, wIndex = 0x0, type = 1
[    6.023098] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x202, wIndex = 0x0, type = 4
[    6.023103] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x100, wIndex = 0x0, type = 1
[    6.023110] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x202, wIndex = 0x0, type = 4
[    6.045846] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x100, wIndex = 0x0, type = 1
[    6.045866] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x202, wIndex = 0x0, type = 4
[    6.045877] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x100, wIndex = 0x0, type = 1
[    6.045886] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x202, wIndex = 0x0, type = 4
[    6.045894] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x100, wIndex = 0x0, type = 1
[    6.045908] usb 3-6: cannot get ctl value: req = 0x81, wValue = 0x202, wIndex = 0x0, type = 4

I overlooked the issue because when I was working on the said commit,
only the front audio is tested. Apology for that.

Changing supports_autosuspend in driver is too late for disabling
autosuspend, because it was already used by USB probe routine, so it can
break the balance on the following code that depends on
supports_autosuspend.

Fix it by using usb_disable_autosuspend() helper, and balance the
suspend count in disconnect callback.

Fixes: 1965c4364bdd ("ALSA: usb-audio: Disable autosuspend for Lenovo ThinkStation P620")
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210304043419.287191-1-kai.heng.feng@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/card.c     | 5 +++++
 sound/usb/quirks.c   | 2 +-
 sound/usb/usbaudio.h | 1 +
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/sound/usb/card.c b/sound/usb/card.c
index 85ed8507e41a..08c794883299 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -830,6 +830,8 @@ static int usb_audio_probe(struct usb_interface *intf,
 		snd_media_device_create(chip, intf);
 	}
 
+	chip->quirk_type = quirk->type;
+
 	usb_chip[chip->index] = chip;
 	chip->intf[chip->num_interfaces] = intf;
 	chip->num_interfaces++;
@@ -912,6 +914,9 @@ static void usb_audio_disconnect(struct usb_interface *intf)
 	} else {
 		mutex_unlock(&register_mutex);
 	}
+
+	if (chip->quirk_type & QUIRK_SETUP_DISABLE_AUTOSUSPEND)
+		usb_enable_autosuspend(interface_to_usbdev(intf));
 }
 
 /* lock the shutdown (disconnect) task and autoresume */
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 0864692d8a7b..66efedaa3aeb 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -547,7 +547,7 @@ static int setup_disable_autosuspend(struct snd_usb_audio *chip,
 				       struct usb_driver *driver,
 				       const struct snd_usb_audio_quirk *quirk)
 {
-	driver->supports_autosuspend = 0;
+	usb_disable_autosuspend(interface_to_usbdev(iface));
 	return 1;	/* Continue with creating streams and mixer */
 }
 
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index 215c1771dd57..60b9dd7df6bb 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -27,6 +27,7 @@ struct snd_usb_audio {
 	struct snd_card *card;
 	struct usb_interface *intf[MAX_CARD_INTERFACES];
 	u32 usb_id;
+	uint16_t quirk_type;
 	struct mutex mutex;
 	unsigned int system_suspend;
 	atomic_t active;

From 460c9f1c944b4bf04f2934478fd3f865b730b771 Mon Sep 17 00:00:00 2001
From: Zhang Yunkai <zhang.yunkai@zte.com.cn>
Date: Wed, 3 Mar 2021 18:24:10 -0800
Subject: [PATCH 0149/1820] arch/parisc/kernel: remove duplicate include in
 ptrace

'linux/compat.h' included in 'arch/parisc/kernel/ptrace.c' is duplicated.
It is also included in the 24th line.

Signed-off-by: Zhang Yunkai <zhang.yunkai@zte.com.cn>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/ptrace.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 2127974982df..65de6c4c9354 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -567,8 +567,6 @@ static const struct user_regset_view user_parisc_native_view = {
 };
 
 #ifdef CONFIG_64BIT
-#include <linux/compat.h>
-
 static int gpr32_get(struct task_struct *target,
 		     const struct user_regset *regset,
 		     struct membuf to)

From a14a6219996ee6f6e858d83b11affc7907633687 Mon Sep 17 00:00:00 2001
From: Mark Pearson <markpearson@lenovo.com>
Date: Tue, 2 Mar 2021 09:10:03 -0500
Subject: [PATCH 0150/1820] ALSA: hda: ignore invalid NHLT table

On some Lenovo systems if the microphone is disabled in the BIOS
only the NHLT table header is created, with no data. This means
the endpoints field is not correctly set to zero - leading to an
unintialised variable and hence invalid descriptors are parsed
leading to page faults.

The Lenovo firmware team is addressing this, but adding a check
preventing invalid tables being parsed is worthwhile.

Tested on a Lenovo T14.

Tested-by: Philipp Leskovitz <philipp.leskovitz@secunet.com>
Reported-by: Philipp Leskovitz <philipp.leskovitz@secunet.com>
Signed-off-by: Mark Pearson <markpearson@lenovo.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210302141003.7342-1-markpearson@lenovo.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/intel-nhlt.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/hda/intel-nhlt.c b/sound/hda/intel-nhlt.c
index d053beccfaec..e2237239d922 100644
--- a/sound/hda/intel-nhlt.c
+++ b/sound/hda/intel-nhlt.c
@@ -39,6 +39,11 @@ int intel_nhlt_get_dmic_geo(struct device *dev, struct nhlt_acpi_table *nhlt)
 	if (!nhlt)
 		return 0;
 
+	if (nhlt->header.length <= sizeof(struct acpi_table_header)) {
+		dev_warn(dev, "Invalid DMIC description table\n");
+		return 0;
+	}
+
 	for (j = 0, epnt = nhlt->desc; j < nhlt->endpoint_count; j++,
 	     epnt = (struct nhlt_endpoint *)((u8 *)epnt + epnt->length)) {
 

From fec60c3bc5d1713db2727cdffc638d48f9c07dc3 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 4 Mar 2021 09:30:21 +0100
Subject: [PATCH 0151/1820] ALSA: usb-audio: Fix "cannot get freq eq" errors on
 Dell AE515 sound bar

Dell AE515 sound bar (413c:a506) spews the error messages when the
driver tries to read the current sample frequency, hence it needs to
be on the list in snd_usb_get_sample_rate_quirk().

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=211551
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210304083021.2152-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 66efedaa3aeb..6ef73af00913 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1520,6 +1520,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
 	case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */
 	case USB_ID(0x21b4, 0x0081): /* AudioQuest DragonFly */
 	case USB_ID(0x2912, 0x30c8): /* Audioengine D1 */
+	case USB_ID(0x413c, 0xa506): /* Dell AE515 sound bar */
 		return true;
 	}
 

From 06abcb18b3a021ba1a3f2020cbefb3ed04e59e72 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 4 Mar 2021 09:50:09 +0100
Subject: [PATCH 0152/1820] ALSA: usb-audio: Apply the control quirk to
 Plantronics headsets

Other Plantronics headset models seem requiring the same workaround as
C320-M to add the 20ms delay for the control messages, too.  Apply the
workaround generically for devices with the vendor ID 0x047f.

Note that the problem didn't surface before 5.11 just with luck.
Since 5.11 got a big code rewrite about the stream handling, the
parameter setup procedure has changed, and this seemed triggering the
problem more often.

BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1182552
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210304085009.4770-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 6ef73af00913..d3001fb18141 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1672,10 +1672,10 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 		msleep(20);
 
 	/*
-	 * Plantronics C320-M needs a delay to avoid random
-	 * microhpone failures.
+	 * Plantronics headsets (C320, C320-M, etc) need a delay to avoid
+	 * random microhpone failures.
 	 */
-	if (chip->usb_id == USB_ID(0x047f, 0xc025)  &&
+	if (USB_ID_VENDOR(chip->usb_id) == 0x047f &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
 		msleep(20);
 

From 775c5033a0d164622d9d10dd0f0a5531639ed3ed Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 4 Mar 2021 11:09:12 +0200
Subject: [PATCH 0153/1820] fuse: fix live lock in fuse_iget()

Commit 5d069dbe8aaf ("fuse: fix bad inode") replaced make_bad_inode()
in fuse_iget() with a private implementation fuse_make_bad().

The private implementation fails to remove the bad inode from inode
cache, so the retry loop with iget5_locked() finds the same bad inode
and marks it bad forever.

kmsg snip:

[ ] rcu: INFO: rcu_sched self-detected stall on CPU
...
[ ]  ? bit_wait_io+0x50/0x50
[ ]  ? fuse_init_file_inode+0x70/0x70
[ ]  ? find_inode.isra.32+0x60/0xb0
[ ]  ? fuse_init_file_inode+0x70/0x70
[ ]  ilookup5_nowait+0x65/0x90
[ ]  ? fuse_init_file_inode+0x70/0x70
[ ]  ilookup5.part.36+0x2e/0x80
[ ]  ? fuse_init_file_inode+0x70/0x70
[ ]  ? fuse_inode_eq+0x20/0x20
[ ]  iget5_locked+0x21/0x80
[ ]  ? fuse_inode_eq+0x20/0x20
[ ]  fuse_iget+0x96/0x1b0

Fixes: 5d069dbe8aaf ("fuse: fix bad inode")
Cc: stable@vger.kernel.org # 5.10+
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/fuse_i.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 68cca8d4db6e..63d97a15ffde 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -863,6 +863,7 @@ static inline u64 fuse_get_attr_version(struct fuse_conn *fc)
 
 static inline void fuse_make_bad(struct inode *inode)
 {
+	remove_inode_hash(inode);
 	set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state);
 }
 

From c95c34f01bbda4421c25fdc9b04a4a4aab10d36c Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 3 Mar 2021 19:56:34 +0100
Subject: [PATCH 0154/1820] xsk: Remove dangling function declaration from
 header file
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

xdp_umem_query() is dead for a long time, drop the declaration from
include/linux/netdevice.h

Fixes: c9b47cc1fabc ("xsk: fix bug when trying to use both copy and zero-copy on one queue id")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/20210303185636.18070-2-maciej.fijalkowski@intel.com
---
 include/linux/netdevice.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f06fbee8638e..5b67ea89d5f2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3959,8 +3959,6 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
 
-int xdp_umem_query(struct net_device *dev, u16 queue_id);
-
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb);

From 6bc6699881012b5bd5d49fa861a69a37fc01b49c Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 3 Mar 2021 19:56:35 +0100
Subject: [PATCH 0155/1820] samples, bpf: Add missing munmap in xdpsock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We mmap the umem region, but we never munmap it.
Add the missing call at the end of the cleanup.

Fixes: 3945b37a975d ("samples/bpf: use hugepages in xdpsock app")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/20210303185636.18070-3-maciej.fijalkowski@intel.com
---
 samples/bpf/xdpsock_user.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index db0cb73513a5..1e2a1105d0e6 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -1699,5 +1699,7 @@ int main(int argc, char **argv)
 
 	xdpsock_cleanup();
 
+	munmap(bufs, NUM_FRAMES * opt_xsk_frame_size);
+
 	return 0;
 }

From 2b2aedabc44e9660f90ccf7ba1ca2706d75f411f Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 3 Mar 2021 19:56:36 +0100
Subject: [PATCH 0156/1820] libbpf: Clear map_info before each
 bpf_obj_get_info_by_fd
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

xsk_lookup_bpf_maps, based on prog_fd, looks whether current prog has a
reference to XSKMAP. BPF prog can include insns that work on various BPF
maps and this is covered by iterating through map_ids.

The bpf_map_info that is passed to bpf_obj_get_info_by_fd for filling
needs to be cleared at each iteration, so that it doesn't contain any
outdated fields and that is currently missing in the function of
interest.

To fix that, zero-init map_info via memset before each
bpf_obj_get_info_by_fd call.

Also, since the area of this code is touched, in general strcmp is
considered harmful, so let's convert it to strncmp and provide the
size of the array name for current map_info.

While at it, do s/continue/break/ once we have found the xsks_map to
terminate the search.

Fixes: 5750902a6e9b ("libbpf: proper XSKMAP cleanup")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/20210303185636.18070-4-maciej.fijalkowski@intel.com
---
 tools/lib/bpf/xsk.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index ffbb588724d8..526fc35c0b23 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -610,15 +610,16 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
 		if (fd < 0)
 			continue;
 
+		memset(&map_info, 0, map_len);
 		err = bpf_obj_get_info_by_fd(fd, &map_info, &map_len);
 		if (err) {
 			close(fd);
 			continue;
 		}
 
-		if (!strcmp(map_info.name, "xsks_map")) {
+		if (!strncmp(map_info.name, "xsks_map", sizeof(map_info.name))) {
 			ctx->xsks_map_fd = fd;
-			continue;
+			break;
 		}
 
 		close(fd);

From 83a2881903f3d5bc08ded4fb04f6e3bedb1fba65 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Mon, 1 Mar 2021 16:40:19 +0100
Subject: [PATCH 0157/1820] bpf: Account for BPF_FETCH in insn_has_def32()

insn_has_def32() returns false for 32-bit BPF_FETCH insns. This makes
adjust_insn_aux_data() incorrectly set zext_dst, as can be seen in [1].
This happens because insn_no_def() does not know about the BPF_FETCH
variants of BPF_STX.

Fix in two steps.

First, replace insn_no_def() with insn_def_regno(), which returns the
register an insn defines. Normally insn_no_def() calls are followed by
insn->dst_reg uses; replace those with the insn_def_regno() return
value.

Second, adjust the BPF_STX special case in is_reg64() to deal with
queries made from opt_subreg_zext_lo32_rnd_hi32(), where the state
information is no longer available. Add a comment, since the purpose
of this special case is not clear at first glance.

  [1] https://lore.kernel.org/bpf/20210223150845.1857620-1-jackmanb@google.com/

Fixes: 5ffa25502b5a ("bpf: Add instructions for atomic_[cmp]xchg")
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Brendan Jackman <jackmanb@google.com>
Link: https://lore.kernel.org/bpf/20210301154019.129110-1-iii@linux.ibm.com
---
 kernel/bpf/verifier.c | 70 ++++++++++++++++++++++++-------------------
 1 file changed, 39 insertions(+), 31 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3d34ba492d46..bb3eaab934f3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1703,7 +1703,11 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	}
 
 	if (class == BPF_STX) {
-		if (reg->type != SCALAR_VALUE)
+		/* BPF_STX (including atomic variants) has multiple source
+		 * operands, one of which is a ptr. Check whether the caller is
+		 * asking about it.
+		 */
+		if (t == SRC_OP && reg->type != SCALAR_VALUE)
 			return true;
 		return BPF_SIZE(code) == BPF_DW;
 	}
@@ -1735,22 +1739,38 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	return true;
 }
 
-/* Return TRUE if INSN doesn't have explicit value define. */
-static bool insn_no_def(struct bpf_insn *insn)
+/* Return the regno defined by the insn, or -1. */
+static int insn_def_regno(const struct bpf_insn *insn)
 {
-	u8 class = BPF_CLASS(insn->code);
-
-	return (class == BPF_JMP || class == BPF_JMP32 ||
-		class == BPF_STX || class == BPF_ST);
+	switch (BPF_CLASS(insn->code)) {
+	case BPF_JMP:
+	case BPF_JMP32:
+	case BPF_ST:
+		return -1;
+	case BPF_STX:
+		if (BPF_MODE(insn->code) == BPF_ATOMIC &&
+		    (insn->imm & BPF_FETCH)) {
+			if (insn->imm == BPF_CMPXCHG)
+				return BPF_REG_0;
+			else
+				return insn->src_reg;
+		} else {
+			return -1;
+		}
+	default:
+		return insn->dst_reg;
+	}
 }
 
 /* Return TRUE if INSN has defined any 32-bit value explicitly. */
 static bool insn_has_def32(struct bpf_verifier_env *env, struct bpf_insn *insn)
 {
-	if (insn_no_def(insn))
+	int dst_reg = insn_def_regno(insn);
+
+	if (dst_reg == -1)
 		return false;
 
-	return !is_reg64(env, insn, insn->dst_reg, NULL, DST_OP);
+	return !is_reg64(env, insn, dst_reg, NULL, DST_OP);
 }
 
 static void mark_insn_zext(struct bpf_verifier_env *env,
@@ -11006,9 +11026,10 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
 	for (i = 0; i < len; i++) {
 		int adj_idx = i + delta;
 		struct bpf_insn insn;
-		u8 load_reg;
+		int load_reg;
 
 		insn = insns[adj_idx];
+		load_reg = insn_def_regno(&insn);
 		if (!aux[adj_idx].zext_dst) {
 			u8 code, class;
 			u32 imm_rnd;
@@ -11018,14 +11039,14 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
 
 			code = insn.code;
 			class = BPF_CLASS(code);
-			if (insn_no_def(&insn))
+			if (load_reg == -1)
 				continue;
 
 			/* NOTE: arg "reg" (the fourth one) is only used for
-			 *       BPF_STX which has been ruled out in above
-			 *       check, it is safe to pass NULL here.
+			 *       BPF_STX + SRC_OP, so it is safe to pass NULL
+			 *       here.
 			 */
-			if (is_reg64(env, &insn, insn.dst_reg, NULL, DST_OP)) {
+			if (is_reg64(env, &insn, load_reg, NULL, DST_OP)) {
 				if (class == BPF_LD &&
 				    BPF_MODE(code) == BPF_IMM)
 					i++;
@@ -11040,7 +11061,7 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
 			imm_rnd = get_random_int();
 			rnd_hi32_patch[0] = insn;
 			rnd_hi32_patch[1].imm = imm_rnd;
-			rnd_hi32_patch[3].dst_reg = insn.dst_reg;
+			rnd_hi32_patch[3].dst_reg = load_reg;
 			patch = rnd_hi32_patch;
 			patch_len = 4;
 			goto apply_patch_buffer;
@@ -11049,22 +11070,9 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
 		if (!bpf_jit_needs_zext())
 			continue;
 
-		/* zext_dst means that we want to zero-extend whatever register
-		 * the insn defines, which is dst_reg most of the time, with
-		 * the notable exception of BPF_STX + BPF_ATOMIC + BPF_FETCH.
-		 */
-		if (BPF_CLASS(insn.code) == BPF_STX &&
-		    BPF_MODE(insn.code) == BPF_ATOMIC) {
-			/* BPF_STX + BPF_ATOMIC insns without BPF_FETCH do not
-			 * define any registers, therefore zext_dst cannot be
-			 * set.
-			 */
-			if (WARN_ON(!(insn.imm & BPF_FETCH)))
-				return -EINVAL;
-			load_reg = insn.imm == BPF_CMPXCHG ? BPF_REG_0
-							   : insn.src_reg;
-		} else {
-			load_reg = insn.dst_reg;
+		if (WARN_ON(load_reg == -1)) {
+			verbose(env, "verifier bug. zext_dst is set, but no reg is defined\n");
+			return -EFAULT;
 		}
 
 		zext_patch[0] = insn;

From d785e1fec60179f534fbe8d006c890e5ad186e51 Mon Sep 17 00:00:00 2001
From: Antony Antony <antony@phenome.org>
Date: Wed, 14 Oct 2020 16:17:48 +0200
Subject: [PATCH 0158/1820] ixgbe: fail to create xfrm offload of IPsec tunnel
 mode SA

Based on talks and indirect references ixgbe IPsec offlod do not
support IPsec tunnel mode offload. It can only support IPsec transport
mode offload. Now explicitly fail when creating non transport mode SA
with offload to avoid false performance expectations.

Fixes: 63a67fe229ea ("ixgbe: add ipsec offload add and remove SA")
Signed-off-by: Antony Antony <antony@phenome.org>
Acked-by: Shannon Nelson <snelson@pensando.io>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c | 5 +++++
 drivers/net/ethernet/intel/ixgbevf/ipsec.c     | 5 +++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index eca73526ac86..54d47265a7ac 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -575,6 +575,11 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs)
 		return -EINVAL;
 	}
 
+	if (xs->props.mode != XFRM_MODE_TRANSPORT) {
+		netdev_err(dev, "Unsupported mode for ipsec offload\n");
+		return -EINVAL;
+	}
+
 	if (ixgbe_ipsec_check_mgmt_ip(xs)) {
 		netdev_err(dev, "IPsec IP addr clash with mgmt filters\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
index 5170dd9d8705..caaea2c920a6 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
@@ -272,6 +272,11 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs)
 		return -EINVAL;
 	}
 
+	if (xs->props.mode != XFRM_MODE_TRANSPORT) {
+		netdev_err(dev, "Unsupported mode for ipsec offload\n");
+		return -EINVAL;
+	}
+
 	if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
 		struct rx_sa rsa;
 

From 7a766381634da19fc837619b0a34590498d9d29a Mon Sep 17 00:00:00 2001
From: Dinghao Liu <dinghao.liu@zju.edu.cn>
Date: Sun, 3 Jan 2021 16:08:42 +0800
Subject: [PATCH 0159/1820] ixgbe: Fix memleak in ixgbe_configure_clsu32

When ixgbe_fdir_write_perfect_filter_82599() fails,
input allocated by kzalloc() has not been freed,
which leads to memleak.

Signed-off-by: Dinghao Liu <dinghao.liu@zju.edu.cn>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index fae84202d870..9f3f12e2ccf2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9565,8 +9565,10 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter,
 	ixgbe_atr_compute_perfect_hash_82599(&input->filter, mask);
 	err = ixgbe_fdir_write_perfect_filter_82599(hw, &input->filter,
 						    input->sw_idx, queue);
-	if (!err)
-		ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx);
+	if (err)
+		goto err_out_w_lock;
+
+	ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx);
 	spin_unlock(&adapter->fdir_perfect_lock);
 
 	if ((uhtid != 0x800) && (adapter->jump_tables[uhtid]))

From d93ef301644ee82925bce1d57fdfe70475dc0bae Mon Sep 17 00:00:00 2001
From: Drew Fustini <drew@beagleboard.org>
Date: Wed, 3 Mar 2021 21:55:49 -0800
Subject: [PATCH 0160/1820] net: sctp: trivial: fix typo in comment

Fix typo of 'overflow' for comment in sctp_tsnmap_check().

Reported-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Drew Fustini <drew@beagleboard.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/tsnmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c
index a9c6af5795d8..5ba456727f63 100644
--- a/net/sctp/tsnmap.c
+++ b/net/sctp/tsnmap.c
@@ -75,7 +75,7 @@ int sctp_tsnmap_check(const struct sctp_tsnmap *map, __u32 tsn)
 		return 1;
 
 	/* Verify that we can hold this TSN and that it will not
-	 * overlfow our map
+	 * overflow our map
 	 */
 	if (!TSN_lt(tsn, map->base_tsn + SCTP_TSN_MAP_SIZE))
 		return -1;

From 76c03bf8e2624076b88d93542d78e22d5345c88e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 4 Mar 2021 10:57:53 +0200
Subject: [PATCH 0161/1820] nexthop: Do not flush blackhole nexthops when
 loopback goes down

As far as user space is concerned, blackhole nexthops do not have a
nexthop device and therefore should not be affected by the
administrative or carrier state of any netdev.

However, when the loopback netdev goes down all the blackhole nexthops
are flushed. This happens because internally the kernel associates
blackhole nexthops with the loopback netdev.

This behavior is both confusing to those not familiar with kernel
internals and also diverges from the legacy API where blackhole IPv4
routes are not flushed when the loopback netdev goes down:

 # ip route add blackhole 198.51.100.0/24
 # ip link set dev lo down
 # ip route show 198.51.100.0/24
 blackhole 198.51.100.0/24

Blackhole IPv6 routes are flushed, but at least user space knows that
they are associated with the loopback netdev:

 # ip -6 route show 2001:db8:1::/64
 blackhole 2001:db8:1::/64 dev lo metric 1024 pref medium

Fix this by only flushing blackhole nexthops when the loopback netdev is
unregistered.

Fixes: ab84be7e54fc ("net: Initial nexthop code")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reported-by: Donald Sharp <sharpd@nvidia.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/nexthop.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index f1c6cbdb9e43..743777bce179 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1399,7 +1399,7 @@ out:
 
 /* rtnl */
 /* remove all nexthops tied to a device being deleted */
-static void nexthop_flush_dev(struct net_device *dev)
+static void nexthop_flush_dev(struct net_device *dev, unsigned long event)
 {
 	unsigned int hash = nh_dev_hashfn(dev->ifindex);
 	struct net *net = dev_net(dev);
@@ -1411,6 +1411,10 @@ static void nexthop_flush_dev(struct net_device *dev)
 		if (nhi->fib_nhc.nhc_dev != dev)
 			continue;
 
+		if (nhi->reject_nh &&
+		    (event == NETDEV_DOWN || event == NETDEV_CHANGE))
+			continue;
+
 		remove_nexthop(net, nhi->nh_parent, NULL);
 	}
 }
@@ -2189,11 +2193,11 @@ static int nh_netdev_event(struct notifier_block *this,
 	switch (event) {
 	case NETDEV_DOWN:
 	case NETDEV_UNREGISTER:
-		nexthop_flush_dev(dev);
+		nexthop_flush_dev(dev, event);
 		break;
 	case NETDEV_CHANGE:
 		if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP)))
-			nexthop_flush_dev(dev);
+			nexthop_flush_dev(dev, event);
 		break;
 	case NETDEV_CHANGEMTU:
 		info_ext = ptr;

From 3a1099d3147f391fa11320a759bbcb1bb857fca1 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 4 Mar 2021 10:57:54 +0200
Subject: [PATCH 0162/1820] selftests: fib_nexthops: Test blackhole nexthops
 when loopback goes down

Test that blackhole nexthops are not flushed when the loopback device
goes down.

Output without previous patch:

 # ./fib_nexthops.sh -t basic

 Basic functional tests
 ----------------------
 TEST: List with nothing defined                                     [ OK ]
 TEST: Nexthop get on non-existent id                                [ OK ]
 TEST: Nexthop with no device or gateway                             [ OK ]
 TEST: Nexthop with down device                                      [ OK ]
 TEST: Nexthop with device that is linkdown                          [ OK ]
 TEST: Nexthop with device only                                      [ OK ]
 TEST: Nexthop with duplicate id                                     [ OK ]
 TEST: Blackhole nexthop                                             [ OK ]
 TEST: Blackhole nexthop with other attributes                       [ OK ]
 TEST: Blackhole nexthop with loopback device down                   [FAIL]
 TEST: Create group                                                  [ OK ]
 TEST: Create group with blackhole nexthop                           [FAIL]
 TEST: Create multipath group where 1 path is a blackhole            [ OK ]
 TEST: Multipath group can not have a member replaced by blackhole   [ OK ]
 TEST: Create group with non-existent nexthop                        [ OK ]
 TEST: Create group with same nexthop multiple times                 [ OK ]
 TEST: Replace nexthop with nexthop group                            [ OK ]
 TEST: Replace nexthop group with nexthop                            [ OK ]
 TEST: Nexthop group and device                                      [ OK ]
 TEST: Test proto flush                                              [ OK ]
 TEST: Nexthop group and blackhole                                   [ OK ]

 Tests passed:  19
 Tests failed:   2

Output with previous patch:

 # ./fib_nexthops.sh -t basic

 Basic functional tests
 ----------------------
 TEST: List with nothing defined                                     [ OK ]
 TEST: Nexthop get on non-existent id                                [ OK ]
 TEST: Nexthop with no device or gateway                             [ OK ]
 TEST: Nexthop with down device                                      [ OK ]
 TEST: Nexthop with device that is linkdown                          [ OK ]
 TEST: Nexthop with device only                                      [ OK ]
 TEST: Nexthop with duplicate id                                     [ OK ]
 TEST: Blackhole nexthop                                             [ OK ]
 TEST: Blackhole nexthop with other attributes                       [ OK ]
 TEST: Blackhole nexthop with loopback device down                   [ OK ]
 TEST: Create group                                                  [ OK ]
 TEST: Create group with blackhole nexthop                           [ OK ]
 TEST: Create multipath group where 1 path is a blackhole            [ OK ]
 TEST: Multipath group can not have a member replaced by blackhole   [ OK ]
 TEST: Create group with non-existent nexthop                        [ OK ]
 TEST: Create group with same nexthop multiple times                 [ OK ]
 TEST: Replace nexthop with nexthop group                            [ OK ]
 TEST: Replace nexthop group with nexthop                            [ OK ]
 TEST: Nexthop group and device                                      [ OK ]
 TEST: Test proto flush                                              [ OK ]
 TEST: Nexthop group and blackhole                                   [ OK ]

 Tests passed:  21
 Tests failed:   0

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_nexthops.sh | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 4c7d33618437..d98fb85e201c 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -1524,6 +1524,14 @@ basic()
 	run_cmd "$IP nexthop replace id 2 blackhole dev veth1"
 	log_test $? 2 "Blackhole nexthop with other attributes"
 
+	# blackhole nexthop should not be affected by the state of the loopback
+	# device
+	run_cmd "$IP link set dev lo down"
+	check_nexthop "id 2" "id 2 blackhole"
+	log_test $? 0 "Blackhole nexthop with loopback device down"
+
+	run_cmd "$IP link set dev lo up"
+
 	#
 	# groups
 	#

From f1becbed411c6fa29d7ce3def3a1dcd4f63f2d74 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 4 Mar 2021 12:29:43 +0200
Subject: [PATCH 0163/1820] net: mscc: ocelot: properly reject destination IP
 keys in VCAP IS1

An attempt is made to warn the user about the fact that VCAP IS1 cannot
offload keys matching on destination IP (at least given the current half
key format), but sadly that warning fails miserably in practice, due to
the fact that it operates on an uninitialized "match" variable. We must
first decode the keys from the flow rule.

Fixes: 75944fda1dfe ("net: mscc: ocelot: offload ingress skbedit and vlan actions to VCAP IS1")
Reported-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_flower.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index c3ac026f6aea..a41b458b1b3e 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -540,13 +540,14 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress,
 			return -EOPNOTSUPP;
 		}
 
+		flow_rule_match_ipv4_addrs(rule, &match);
+
 		if (filter->block_id == VCAP_IS1 && *(u32 *)&match.mask->dst) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Key type S1_NORMAL cannot match on destination IP");
 			return -EOPNOTSUPP;
 		}
 
-		flow_rule_match_ipv4_addrs(rule, &match);
 		tmp = &filter->key.ipv4.sip.value.addr[0];
 		memcpy(tmp, &match.key->src, 4);
 

From 053d8ad10d585adf9891fcd049637536e2fe9ea7 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 4 Mar 2021 12:56:53 +0200
Subject: [PATCH 0164/1820] net: dsa: sja1105: fix SGMII PCS being forced to
 SPEED_UNKNOWN instead of SPEED_10

When using MLO_AN_PHY or MLO_AN_FIXED, the MII_BMCR of the SGMII PCS is
read before resetting the switch so it can be reprogrammed afterwards.
This works for the speeds of 1Gbps and 100Mbps, but not for 10Mbps,
because SPEED_10 is actually 0, so AND-ing anything with 0 is false,
therefore that last branch is dead code.

Do what others do (genphy_read_status_fixed, phy_mii_ioctl) and just
remove the check for SPEED_10, let it fall into the default case.

Fixes: ffe10e679cec ("net: dsa: sja1105: Add support for the SGMII port")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 7692338730df..c1982615c631 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1922,7 +1922,7 @@ out_unlock_ptp:
 				speed = SPEED_1000;
 			else if (bmcr & BMCR_SPEED100)
 				speed = SPEED_100;
-			else if (bmcr & BMCR_SPEED10)
+			else
 				speed = SPEED_10;
 
 			sja1105_sgmii_pcs_force_speed(priv, speed);

From 6a5166e07c029182ee0e15c1a97b08c3179b2aaf Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 4 Mar 2021 12:56:54 +0200
Subject: [PATCH 0165/1820] net: dsa: sja1105: fix ucast/bcast flooding always
 remaining enabled

In the blamed patch I managed to introduce a bug while moving code
around: the same logic is applied to the ucast_egress_floods and
bcast_egress_floods variables both on the "if" and the "else" branches.

This is clearly an unintended change compared to how the code used to be
prior to that bugfix, so restore it.

Fixes: 7f7ccdea8c73 ("net: dsa: sja1105: fix leakage of flooded frames outside bridging domain")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index c1982615c631..51ea104c63bb 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -3369,14 +3369,14 @@ static int sja1105_port_ucast_bcast_flood(struct sja1105_private *priv, int to,
 		if (flags.val & BR_FLOOD)
 			priv->ucast_egress_floods |= BIT(to);
 		else
-			priv->ucast_egress_floods |= BIT(to);
+			priv->ucast_egress_floods &= ~BIT(to);
 	}
 
 	if (flags.mask & BR_BCAST_FLOOD) {
 		if (flags.val & BR_BCAST_FLOOD)
 			priv->bcast_egress_floods |= BIT(to);
 		else
-			priv->bcast_egress_floods |= BIT(to);
+			priv->bcast_egress_floods &= ~BIT(to);
 	}
 
 	return sja1105_manage_flood_domains(priv);

From 443cc4b45c1be0b25313c9a507b033074334b490 Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.ibm.com>
Date: Tue, 2 Mar 2021 17:05:39 -0600
Subject: [PATCH 0166/1820] scsi: ibmvfc: Simplify handling of sub-CRQ
 initialization

If ibmvfc_init_sub_crqs() fails ibmvfc_probe() simply parrots registration
failure reported elsewhere, and futher vhost->scsi_scrq.scrq == NULL is
indication enough to the driver that it has no sub-CRQs available. The
mq_enabled check can also be moved into ibmvfc_init_sub_crqs() such that
each caller doesn't have to gate the call with a mq_enabled check. Finally,
in the case of sub-CRQ setup failure setting do_enquiry can be turned off
to putting the driver into single queue fallback mode.

The aforementioned changes also simplify the next patch in the series that
fixes a hard reset issue, by tying a sub-CRQ setup failure and do_enquiry
logic into ibmvfc_init_sub_crqs().

Link: https://lore.kernel.org/r/20210302230543.9905-2-tyreld@linux.ibm.com
Reviewed-by: Brian King <brking@linux.ibm.com>
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ibmvscsi/ibmvfc.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 755313b766b9..e518dbee6a47 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -5707,17 +5707,21 @@ static void ibmvfc_deregister_scsi_channel(struct ibmvfc_host *vhost, int index)
 	LEAVE;
 }
 
-static int ibmvfc_init_sub_crqs(struct ibmvfc_host *vhost)
+static void ibmvfc_init_sub_crqs(struct ibmvfc_host *vhost)
 {
 	int i, j;
 
 	ENTER;
+	if (!vhost->mq_enabled)
+		return;
 
 	vhost->scsi_scrqs.scrqs = kcalloc(nr_scsi_hw_queues,
 					  sizeof(*vhost->scsi_scrqs.scrqs),
 					  GFP_KERNEL);
-	if (!vhost->scsi_scrqs.scrqs)
-		return -1;
+	if (!vhost->scsi_scrqs.scrqs) {
+		vhost->do_enquiry = 0;
+		return;
+	}
 
 	for (i = 0; i < nr_scsi_hw_queues; i++) {
 		if (ibmvfc_register_scsi_channel(vhost, i)) {
@@ -5726,13 +5730,12 @@ static int ibmvfc_init_sub_crqs(struct ibmvfc_host *vhost)
 			kfree(vhost->scsi_scrqs.scrqs);
 			vhost->scsi_scrqs.scrqs = NULL;
 			vhost->scsi_scrqs.active_queues = 0;
-			LEAVE;
-			return -1;
+			vhost->do_enquiry = 0;
+			break;
 		}
 	}
 
 	LEAVE;
-	return 0;
 }
 
 static void ibmvfc_release_sub_crqs(struct ibmvfc_host *vhost)
@@ -5999,11 +6002,7 @@ static int ibmvfc_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 		goto remove_shost;
 	}
 
-	if (vhost->mq_enabled) {
-		rc = ibmvfc_init_sub_crqs(vhost);
-		if (rc)
-			dev_warn(dev, "Failed to allocate Sub-CRQs. rc=%d\n", rc);
-	}
+	ibmvfc_init_sub_crqs(vhost);
 
 	if (shost_to_fc_host(shost)->rqst_q)
 		blk_queue_max_segments(shost_to_fc_host(shost)->rqst_q, 1);

From 6c59cff38e66584ae3ac6c2f0cbd8d039c710ba7 Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Thu, 4 Mar 2021 14:15:13 +0100
Subject: [PATCH 0167/1820] net: usb: qmi_wwan: allow qmimux add/del with
 master up
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There's no reason for preventing the creation and removal
of qmimux network interfaces when the underlying interface
is up.

This makes qmi_wwan mux implementation more similar to the
rmnet one, simplifying userspace management of the same
logical interfaces.

Fixes: c6adf77953bc ("net: usb: qmi_wwan: add qmap mux protocol support")
Reported-by: Aleksander Morgado <aleksander@aleksander.es>
Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 17a050521b86..6700f1970b24 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -429,13 +429,6 @@ static ssize_t add_mux_store(struct device *d,  struct device_attribute *attr, c
 		goto err;
 	}
 
-	/* we don't want to modify a running netdev */
-	if (netif_running(dev->net)) {
-		netdev_err(dev->net, "Cannot change a running device\n");
-		ret = -EBUSY;
-		goto err;
-	}
-
 	ret = qmimux_register_device(dev->net, mux_id);
 	if (!ret) {
 		info->flags |= QMI_WWAN_FLAG_MUX;
@@ -465,13 +458,6 @@ static ssize_t del_mux_store(struct device *d,  struct device_attribute *attr, c
 	if (!rtnl_trylock())
 		return restart_syscall();
 
-	/* we don't want to modify a running netdev */
-	if (netif_running(dev->net)) {
-		netdev_err(dev->net, "Cannot change a running device\n");
-		ret = -EBUSY;
-		goto err;
-	}
-
 	del_dev = qmimux_find_dev(dev, mux_id);
 	if (!del_dev) {
 		netdev_err(dev->net, "mux_id not present\n");

From 5cf529649be20dc27500c1141d58ba57131e2530 Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.ibm.com>
Date: Tue, 2 Mar 2021 17:05:40 -0600
Subject: [PATCH 0168/1820] scsi: ibmvfc: Fix invalid sub-CRQ handles after
 hard reset

A hard reset results in a complete transport disconnect such that the CRQ
connection with the partner VIOS is broken. This has the side effect of
also invalidating the associated sub-CRQs. The current code assumes that
the sub-CRQs are perserved resulting in a protocol violation after trying
to reconnect them with the VIOS. This introduces an infinite loop such that
the VIOS forces a disconnect after each subsequent attempt to re-register
with invalid handles.

Avoid the aforementioned issue by releasing the sub-CRQs prior to CRQ
disconnect, and driving a reinitialization of the sub-CRQs once a new CRQ
is registered with the hypervisor.

Link: https://lore.kernel.org/r/20210302230543.9905-3-tyreld@linux.ibm.com
Fixes: 3034ebe26389 ("scsi: ibmvfc: Add alloc/dealloc routines for SCSI Sub-CRQ Channels")
Reviewed-by: Brian King <brking@linux.ibm.com>
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ibmvscsi/ibmvfc.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index e518dbee6a47..ba4c811ce75a 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -158,6 +158,9 @@ static void ibmvfc_npiv_logout(struct ibmvfc_host *);
 static void ibmvfc_tgt_implicit_logout_and_del(struct ibmvfc_target *);
 static void ibmvfc_tgt_move_login(struct ibmvfc_target *);
 
+static void ibmvfc_release_sub_crqs(struct ibmvfc_host *);
+static void ibmvfc_init_sub_crqs(struct ibmvfc_host *);
+
 static const char *unknown_error = "unknown error";
 
 static long h_reg_sub_crq(unsigned long unit_address, unsigned long ioba,
@@ -926,8 +929,8 @@ static int ibmvfc_reset_crq(struct ibmvfc_host *vhost)
 	unsigned long flags;
 	struct vio_dev *vdev = to_vio_dev(vhost->dev);
 	struct ibmvfc_queue *crq = &vhost->crq;
-	struct ibmvfc_queue *scrq;
-	int i;
+
+	ibmvfc_release_sub_crqs(vhost);
 
 	/* Close the CRQ */
 	do {
@@ -947,16 +950,6 @@ static int ibmvfc_reset_crq(struct ibmvfc_host *vhost)
 	memset(crq->msgs.crq, 0, PAGE_SIZE);
 	crq->cur = 0;
 
-	if (vhost->scsi_scrqs.scrqs) {
-		for (i = 0; i < nr_scsi_hw_queues; i++) {
-			scrq = &vhost->scsi_scrqs.scrqs[i];
-			spin_lock(scrq->q_lock);
-			memset(scrq->msgs.scrq, 0, PAGE_SIZE);
-			scrq->cur = 0;
-			spin_unlock(scrq->q_lock);
-		}
-	}
-
 	/* And re-open it again */
 	rc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address,
 				crq->msg_token, PAGE_SIZE);
@@ -966,9 +959,12 @@ static int ibmvfc_reset_crq(struct ibmvfc_host *vhost)
 		dev_warn(vhost->dev, "Partner adapter not ready\n");
 	else if (rc != 0)
 		dev_warn(vhost->dev, "Couldn't register crq (rc=%d)\n", rc);
+
 	spin_unlock(vhost->crq.q_lock);
 	spin_unlock_irqrestore(vhost->host->host_lock, flags);
 
+	ibmvfc_init_sub_crqs(vhost);
+
 	return rc;
 }
 
@@ -5694,6 +5690,7 @@ static void ibmvfc_deregister_scsi_channel(struct ibmvfc_host *vhost, int index)
 
 	free_irq(scrq->irq, scrq);
 	irq_dispose_mapping(scrq->irq);
+	scrq->irq = 0;
 
 	do {
 		rc = plpar_hcall_norets(H_FREE_SUB_CRQ, vdev->unit_address,

From 2162dc23f80770e355ef00b43573b67b80466001 Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.ibm.com>
Date: Tue, 2 Mar 2021 17:05:41 -0600
Subject: [PATCH 0169/1820] scsi: ibmvfc: Treat H_CLOSED as success during
 sub-CRQ registration

A non-zero return code for H_REG_SUB_CRQ is currently treated as a failure
resulting in failing sub-CRQ setup. The case of H_CLOSED should not be
treated as a failure. This return code translates to a successful sub-CRQ
registration by the hypervisor, and is meant to communicate back that there
is currently no partner VIOS CRQ connection established as of yet. This is
a common occurrence during a disconnect where the client adapter can
possibly come back up prior to the partner adapter.

For non-zero return code from H_REG_SUB_CRQ treat a H_CLOSED as success so
that sub-CRQs are successfully setup.

Link: https://lore.kernel.org/r/20210302230543.9905-4-tyreld@linux.ibm.com
Fixes: 3034ebe26389 ("scsi: ibmvfc: Add alloc/dealloc routines for SCSI Sub-CRQ Channels")
Reviewed-by: Brian King <brking@linux.ibm.com>
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ibmvscsi/ibmvfc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index ba4c811ce75a..abc8030e90e0 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -5638,7 +5638,8 @@ static int ibmvfc_register_scsi_channel(struct ibmvfc_host *vhost,
 	rc = h_reg_sub_crq(vdev->unit_address, scrq->msg_token, PAGE_SIZE,
 			   &scrq->cookie, &scrq->hw_irq);
 
-	if (rc) {
+	/* H_CLOSED indicates successful register, but no CRQ partner */
+	if (rc && rc != H_CLOSED) {
 		dev_warn(dev, "Error registering sub-crq: %d\n", rc);
 		if (rc == H_PARAMETER)
 			dev_warn_once(dev, "Firmware may not support MQ\n");

From 0217a272fe134578d88a4e9c7f5e968551bf952a Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.ibm.com>
Date: Tue, 2 Mar 2021 17:05:42 -0600
Subject: [PATCH 0170/1820] scsi: ibmvfc: Store return code of H_FREE_SUB_CRQ
 during cleanup

The H_FREE_SUB_CRQ hypercall can return a retry delay return code that
indicates the call needs to be retried after a specific amount of time
delay. The error path to free a sub-CRQ in case of a failure during channel
registration fails to capture the return code of H_FREE_SUB_CRQ which will
result in the delay loop being skipped in the case of a retry delay return
code.

Store the return code result of the H_FREE_SUB_CRQ call such that the
return code check in the delay loop evaluates a meaningful value. Also, use
the rtas_busy_delay() to check the rc value and delay for the appropriate
amount of time.

Link: https://lore.kernel.org/r/20210302230543.9905-5-tyreld@linux.ibm.com
Fixes: 39e461fddff0 ("scsi: ibmvfc: Map/request irq and register Sub-CRQ interrupt handler")
Reviewed-by: Brian King <brking@linux.ibm.com>
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ibmvscsi/ibmvfc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index abc8030e90e0..5897ee995aee 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -21,6 +21,7 @@
 #include <linux/bsg-lib.h>
 #include <asm/firmware.h>
 #include <asm/irq.h>
+#include <asm/rtas.h>
 #include <asm/vio.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -5672,8 +5673,8 @@ static int ibmvfc_register_scsi_channel(struct ibmvfc_host *vhost,
 
 irq_failed:
 	do {
-		plpar_hcall_norets(H_FREE_SUB_CRQ, vdev->unit_address, scrq->cookie);
-	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));
+		rc = plpar_hcall_norets(H_FREE_SUB_CRQ, vdev->unit_address, scrq->cookie);
+	} while (rtas_busy_delay(rc));
 reg_failed:
 	ibmvfc_free_queue(vhost, scrq);
 	LEAVE;

From dbdbb81bde2440d9a1653acf1333c6c812f9c4b0 Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.ibm.com>
Date: Tue, 2 Mar 2021 17:05:43 -0600
Subject: [PATCH 0171/1820] scsi: ibmvfc: Reinitialize sub-CRQs and perform
 channel enquiry after LPM

A live partition migration (LPM) results in a CRQ disconnect similar to a
hard reset. In this LPM case the hypervisor mostly preserves the CRQ
transport such that it simply needs to be reenabled. However, the
capabilities may have changed such as fewer channels, or no channels at
all. Further, its possible that there may be sub-CRQ support, but no
channel support. The CRQ reenable path currently doesn't take any of this
into consideration.

For simplicity release and reinitialize sub-CRQs during reenable, and set
do_enquiry and using_channels with the appropriate values to trigger
channel renegotiation.

Link: https://lore.kernel.org/r/20210302230543.9905-6-tyreld@linux.ibm.com
Fixes: 3034ebe26389 ("scsi: ibmvfc: Add alloc/dealloc routines for SCSI Sub-CRQ Channels")
Reviewed-by: Brian King <brking@linux.ibm.com>
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ibmvscsi/ibmvfc.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 5897ee995aee..338e29d3e025 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -903,6 +903,9 @@ static int ibmvfc_reenable_crq_queue(struct ibmvfc_host *vhost)
 {
 	int rc = 0;
 	struct vio_dev *vdev = to_vio_dev(vhost->dev);
+	unsigned long flags;
+
+	ibmvfc_release_sub_crqs(vhost);
 
 	/* Re-enable the CRQ */
 	do {
@@ -914,6 +917,15 @@ static int ibmvfc_reenable_crq_queue(struct ibmvfc_host *vhost)
 	if (rc)
 		dev_err(vhost->dev, "Error enabling adapter (rc=%d)\n", rc);
 
+	spin_lock_irqsave(vhost->host->host_lock, flags);
+	spin_lock(vhost->crq.q_lock);
+	vhost->do_enquiry = 1;
+	vhost->using_channels = 0;
+	spin_unlock(vhost->crq.q_lock);
+	spin_unlock_irqrestore(vhost->host->host_lock, flags);
+
+	ibmvfc_init_sub_crqs(vhost);
+
 	return rc;
 }
 

From aa53f580e67b49ec5f4d9bd1de81eb9eb0dc079f Mon Sep 17 00:00:00 2001
From: Can Guo <cang@codeaurora.org>
Date: Tue, 23 Feb 2021 21:36:47 -0800
Subject: [PATCH 0172/1820] scsi: ufs: Minor adjustments to error handling

In error handling prepare stage, after SCSI requests are blocked, do a
down/up_write(clk_scaling_lock) to clean up the queuecommand() path.
Meanwhile, stop eeh_work in case it disturbs error recovery. Moreover,
reset ufshcd_state at the entrance of ufshcd_probe_hba(), since it may be
called multiple times during error recovery.

Link: https://lore.kernel.org/r/1614145010-36079-2-git-send-email-cang@codeaurora.org
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/ufshcd.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 77161750c9fb..607fdfa5a508 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -4987,6 +4987,7 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 			 * UFS device needs urgent BKOPs.
 			 */
 			if (!hba->pm_op_in_progress &&
+			    !ufshcd_eh_in_progress(hba) &&
 			    ufshcd_is_exception_event(lrbp->ucd_rsp_ptr) &&
 			    schedule_work(&hba->eeh_work)) {
 				/*
@@ -5784,13 +5785,20 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba)
 			ufshcd_suspend_clkscaling(hba);
 		ufshcd_clk_scaling_allow(hba, false);
 	}
+	ufshcd_scsi_block_requests(hba);
+	/* Drain ufshcd_queuecommand() */
+	down_write(&hba->clk_scaling_lock);
+	up_write(&hba->clk_scaling_lock);
+	cancel_work_sync(&hba->eeh_work);
 }
 
 static void ufshcd_err_handling_unprepare(struct ufs_hba *hba)
 {
+	ufshcd_scsi_unblock_requests(hba);
 	ufshcd_release(hba);
 	if (ufshcd_is_clkscaling_supported(hba))
 		ufshcd_clk_scaling_suspend(hba, false);
+	ufshcd_clear_ua_wluns(hba);
 	pm_runtime_put(hba->dev);
 }
 
@@ -5882,8 +5890,8 @@ static void ufshcd_err_handler(struct work_struct *work)
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	ufshcd_err_handling_prepare(hba);
 	spin_lock_irqsave(hba->host->host_lock, flags);
-	ufshcd_scsi_block_requests(hba);
-	hba->ufshcd_state = UFSHCD_STATE_RESET;
+	if (hba->ufshcd_state != UFSHCD_STATE_ERROR)
+		hba->ufshcd_state = UFSHCD_STATE_RESET;
 
 	/* Complete requests that have door-bell cleared by h/w */
 	ufshcd_complete_requests(hba);
@@ -6042,12 +6050,8 @@ skip_err_handling:
 	}
 	ufshcd_clear_eh_in_progress(hba);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
-	ufshcd_scsi_unblock_requests(hba);
 	ufshcd_err_handling_unprepare(hba);
 	up(&hba->host_sem);
-
-	if (!err && needs_reset)
-		ufshcd_clear_ua_wluns(hba);
 }
 
 /**
@@ -7858,6 +7862,8 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool async)
 	unsigned long flags;
 	ktime_t start = ktime_get();
 
+	hba->ufshcd_state = UFSHCD_STATE_RESET;
+
 	ret = ufshcd_link_startup(hba);
 	if (ret)
 		goto out;

From 4a791574a0ccf36eb3a0a46fbd71d2768df3eef9 Mon Sep 17 00:00:00 2001
From: Nitin Rawat <nitirawa@codeaurora.org>
Date: Tue, 23 Feb 2021 21:36:48 -0800
Subject: [PATCH 0173/1820] scsi: ufs: ufs-qcom: Disable interrupt in reset
 path

Disable interrupt in reset path to flush pending IRQ handler in order to
avoid possible NoC issues.

Link: https://lore.kernel.org/r/1614145010-36079-3-git-send-email-cang@codeaurora.org
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Nitin Rawat <nitirawa@codeaurora.org>
Signed-off-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/ufs-qcom.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c
index f97d7b0ae3b6..a9dc8d7c9f78 100644
--- a/drivers/scsi/ufs/ufs-qcom.c
+++ b/drivers/scsi/ufs/ufs-qcom.c
@@ -253,12 +253,17 @@ static int ufs_qcom_host_reset(struct ufs_hba *hba)
 {
 	int ret = 0;
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
+	bool reenable_intr = false;
 
 	if (!host->core_reset) {
 		dev_warn(hba->dev, "%s: reset control not set\n", __func__);
 		goto out;
 	}
 
+	reenable_intr = hba->is_irq_enabled;
+	disable_irq(hba->irq);
+	hba->is_irq_enabled = false;
+
 	ret = reset_control_assert(host->core_reset);
 	if (ret) {
 		dev_err(hba->dev, "%s: core_reset assert failed, err = %d\n",
@@ -280,6 +285,11 @@ static int ufs_qcom_host_reset(struct ufs_hba *hba)
 
 	usleep_range(1000, 1100);
 
+	if (reenable_intr) {
+		enable_irq(hba->irq);
+		hba->is_irq_enabled = true;
+	}
+
 out:
 	return ret;
 }

From 4d195dc451570db79251a58022309728cc7b29de Mon Sep 17 00:00:00 2001
From: Can Guo <cang@codeaurora.org>
Date: Tue, 23 Feb 2021 21:36:49 -0800
Subject: [PATCH 0174/1820] scsi: ufs: Remove redundant checks of !hba in
 suspend/resume callbacks

Runtime and system suspend/resume can only come after hba probe invokes
platform_set_drvdata(pdev, hba), meaning hba cannot be NULL in these PM
callbacks, so remove the checks of !hba.

Link: https://lore.kernel.org/r/1614145010-36079-4-git-send-email-cang@codeaurora.org
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/ufshcd.c | 21 ---------------------
 1 file changed, 21 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 607fdfa5a508..a81a3825aed6 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -95,8 +95,6 @@
 		       16, 4, buf, __len, false);                        \
 } while (0)
 
-static bool early_suspend;
-
 int ufshcd_dump_regs(struct ufs_hba *hba, size_t offset, size_t len,
 		     const char *prefix)
 {
@@ -8978,11 +8976,6 @@ int ufshcd_system_suspend(struct ufs_hba *hba)
 	int ret = 0;
 	ktime_t start = ktime_get();
 
-	if (!hba) {
-		early_suspend = true;
-		return 0;
-	}
-
 	down(&hba->host_sem);
 
 	if (!hba->is_powered)
@@ -9034,14 +9027,6 @@ int ufshcd_system_resume(struct ufs_hba *hba)
 	int ret = 0;
 	ktime_t start = ktime_get();
 
-	if (!hba)
-		return -EINVAL;
-
-	if (unlikely(early_suspend)) {
-		early_suspend = false;
-		down(&hba->host_sem);
-	}
-
 	if (!hba->is_powered || pm_runtime_suspended(hba->dev))
 		/*
 		 * Let the runtime resume take care of resuming
@@ -9074,9 +9059,6 @@ int ufshcd_runtime_suspend(struct ufs_hba *hba)
 	int ret = 0;
 	ktime_t start = ktime_get();
 
-	if (!hba)
-		return -EINVAL;
-
 	if (!hba->is_powered)
 		goto out;
 	else
@@ -9115,9 +9097,6 @@ int ufshcd_runtime_resume(struct ufs_hba *hba)
 	int ret = 0;
 	ktime_t start = ktime_get();
 
-	if (!hba)
-		return -EINVAL;
-
 	if (!hba->is_powered)
 		goto out;
 	else

From 1481b7fe438fff3bd918bcb344e75bdf7ce47bb8 Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Tue, 2 Mar 2021 14:08:18 +0800
Subject: [PATCH 0175/1820] scsi: ufs: Convert sysfs sprintf/snprintf family to
 sysfs_emit

Fix the following coccicheck warning:

./drivers/scsi/ufs/ufshcd.c:1538:8-16: WARNING: use scnprintf or
sprintf.

Link: https://lore.kernel.org/r/1614665298-115183-1-git-send-email-jiapeng.chong@linux.alibaba.com
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/ufshcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index a81a3825aed6..c86760788c72 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -1533,7 +1533,7 @@ static ssize_t ufshcd_clkscale_enable_show(struct device *dev,
 {
 	struct ufs_hba *hba = dev_get_drvdata(dev);
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", hba->clk_scaling.is_enabled);
+	return sysfs_emit(buf, "%d\n", hba->clk_scaling.is_enabled);
 }
 
 static ssize_t ufshcd_clkscale_enable_store(struct device *dev,

From 1112963427d6d186f8729cf36fefb70d5ca5a84a Mon Sep 17 00:00:00 2001
From: Vishal Bhakta <vbhakta@vmware.com>
Date: Fri, 26 Feb 2021 15:43:48 -0800
Subject: [PATCH 0176/1820] scsi: vmw_pvscsi: MAINTAINERS: Update maintainer

The entries in the source files are removed as well.

Link: https://lore.kernel.org/r/20210226234347.21535-1-vbhakta@vmware.com
Signed-off-by: Vishal Bhakta <vbhakta@vmware.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 MAINTAINERS               | 2 +-
 drivers/scsi/vmw_pvscsi.c | 2 --
 drivers/scsi/vmw_pvscsi.h | 2 --
 3 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d92f85ca831d..dede3b947834 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19165,7 +19165,7 @@ S:	Maintained
 F:	drivers/infiniband/hw/vmw_pvrdma/
 
 VMware PVSCSI driver
-M:	Jim Gill <jgill@vmware.com>
+M:	Vishal Bhakta <vbhakta@vmware.com>
 M:	VMware PV-Drivers <pv-drivers@vmware.com>
 L:	linux-scsi@vger.kernel.org
 S:	Maintained
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 081f54ab7d86..8a79605d9652 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -17,8 +17,6 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
  *
- * Maintained by: Jim Gill <jgill@vmware.com>
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/scsi/vmw_pvscsi.h b/drivers/scsi/vmw_pvscsi.h
index 75966d3f326e..51a82f7803d3 100644
--- a/drivers/scsi/vmw_pvscsi.h
+++ b/drivers/scsi/vmw_pvscsi.h
@@ -17,8 +17,6 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
  *
- * Maintained by: Jim Gill <jgill@vmware.com>
- *
  */
 
 #ifndef _VMW_PVSCSI_H_

From bfc2560563586372212b0a8aeca7428975fa91fe Mon Sep 17 00:00:00 2001
From: Maximilian Heyne <mheyne@amazon.de>
Date: Thu, 4 Mar 2021 14:43:17 +0000
Subject: [PATCH 0177/1820] net: sched: avoid duplicates in classes dump

This is a follow up of commit ea3274695353 ("net: sched: avoid
duplicates in qdisc dump") which has fixed the issue only for the qdisc
dump.

The duplicate printing also occurs when dumping the classes via
  tc class show dev eth0

Fixes: 59cc1f61f09c ("net: sched: convert qdisc linked list to hashtable")
Signed-off-by: Maximilian Heyne <mheyne@amazon.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index e2e4353db8a7..f87d07736a14 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -2168,7 +2168,7 @@ static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb,
 
 static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb,
 			       struct tcmsg *tcm, struct netlink_callback *cb,
-			       int *t_p, int s_t)
+			       int *t_p, int s_t, bool recur)
 {
 	struct Qdisc *q;
 	int b;
@@ -2179,7 +2179,7 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb,
 	if (tc_dump_tclass_qdisc(root, skb, tcm, cb, t_p, s_t) < 0)
 		return -1;
 
-	if (!qdisc_dev(root))
+	if (!qdisc_dev(root) || !recur)
 		return 0;
 
 	if (tcm->tcm_parent) {
@@ -2214,13 +2214,13 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb)
 	s_t = cb->args[0];
 	t = 0;
 
-	if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0)
+	if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t, true) < 0)
 		goto done;
 
 	dev_queue = dev_ingress_queue(dev);
 	if (dev_queue &&
 	    tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb,
-				&t, s_t) < 0)
+				&t, s_t, false) < 0)
 		goto done;
 
 done:

From e0be4931f3fee2e04dec4013ea4f27ec2db8556f Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 4 Mar 2021 13:32:08 -0800
Subject: [PATCH 0178/1820] mptcp: reset last_snd on subflow close

Send logic caches last active subflow in the msk, so it needs to be
cleared when the cached subflow is closed.

Fixes: d5f49190def61c ("mptcp: allow picking different xmit subflows")
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/155
Reported-by: Christoph Paasch <cpaasch@apple.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index c5d5e68940ea..7362a536cbc0 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2126,6 +2126,8 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
 static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 			      struct mptcp_subflow_context *subflow)
 {
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
 	list_del(&subflow->node);
 
 	lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
@@ -2154,6 +2156,9 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	release_sock(ssk);
 
 	sock_put(ssk);
+
+	if (ssk == msk->last_snd)
+		msk->last_snd = NULL;
 }
 
 void mptcp_close_ssk(struct sock *sk, struct sock *ssk,

From f07157792c633b528de5fc1dbe2e4ea54f8e09d4 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 4 Mar 2021 13:32:09 -0800
Subject: [PATCH 0179/1820] mptcp: put subflow sock on connect error

mptcp_add_pending_subflow() performs a sock_hold() on the subflow,
then adds the subflow to the join list.

Without a sock_put the subflow sk won't be freed in case connect() fails.

unreferenced object 0xffff88810c03b100 (size 3000):
[..]
    sk_prot_alloc.isra.0+0x2f/0x110
    sk_alloc+0x5d/0xc20
    inet6_create+0x2b7/0xd30
    __sock_create+0x17f/0x410
    mptcp_subflow_create_socket+0xff/0x9c0
    __mptcp_subflow_connect+0x1da/0xaf0
    mptcp_pm_nl_work+0x6e0/0x1120
    mptcp_worker+0x508/0x9a0

Fixes: 5b950ff4331ddda ("mptcp: link MPC subflow into msk only after accept")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/subflow.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index e1fbcab257e6..41695e26c374 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1297,6 +1297,7 @@ failed_unlink:
 	spin_lock_bh(&msk->join_list_lock);
 	list_del(&subflow->node);
 	spin_unlock_bh(&msk->join_list_lock);
+	sock_put(mptcp_subflow_tcp_sock(subflow));
 
 failed:
 	subflow->disposable = 1;

From eaeef1ce55ec9161e0c44ff27017777b1644b421 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 4 Mar 2021 13:32:10 -0800
Subject: [PATCH 0180/1820] mptcp: fix memory accounting on allocation error

In case of memory pressure the MPTCP xmit path keeps
at most a single skb in the tx cache, eventually freeing
additional ones.

The associated counter for forward memory is not update
accordingly, and that causes the following splat:

WARNING: CPU: 0 PID: 12 at net/core/stream.c:208 sk_stream_kill_queues+0x3ca/0x530 net/core/stream.c:208
Modules linked in:
CPU: 0 PID: 12 Comm: kworker/0:1 Not tainted 5.11.0-rc2 #59
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
Workqueue: events mptcp_worker
RIP: 0010:sk_stream_kill_queues+0x3ca/0x530 net/core/stream.c:208
Code: 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e 63 01 00 00 8b ab 00 01 00 00 e9 60 ff ff ff e8 2f 24 d3 fe 0f 0b eb 97 e8 26 24 d3 fe <0f> 0b eb a0 e8 1d 24 d3 fe 0f 0b e9 a5 fe ff ff 4c 89 e7 e8 0e d0
RSP: 0018:ffffc900000c7bc8 EFLAGS: 00010293
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: ffff88810030ac40 RSI: ffffffff8262ca4a RDI: 0000000000000003
RBP: 0000000000000d00 R08: 0000000000000000 R09: ffffffff85095aa7
R10: ffffffff8262c9ea R11: 0000000000000001 R12: ffff888108908100
R13: ffffffff85095aa0 R14: ffffc900000c7c48 R15: 1ffff92000018f85
FS:  0000000000000000(0000) GS:ffff88811b200000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fa7444baef8 CR3: 0000000035ee9005 CR4: 0000000000170ef0
Call Trace:
 __mptcp_destroy_sock+0x4a7/0x6c0 net/mptcp/protocol.c:2547
 mptcp_worker+0x7dd/0x1610 net/mptcp/protocol.c:2272
 process_one_work+0x896/0x1170 kernel/workqueue.c:2275
 worker_thread+0x605/0x1350 kernel/workqueue.c:2421
 kthread+0x344/0x410 kernel/kthread.c:292
 ret_from_fork+0x22/0x30 arch/x86/entry/entry_64.S:296

At close time, as reported by syzkaller/Christoph.

This change address the issue properly updating the fwd
allocated memory counter in the error path.

Reported-by: Christoph Paasch <cpaasch@apple.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/136
Fixes: 724cfd2ee8aa ("mptcp: allocate TX skbs in msk context")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7362a536cbc0..aa59101ffe54 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1189,6 +1189,7 @@ static bool mptcp_tx_cache_refill(struct sock *sk, int size,
 			 */
 			while (skbs->qlen > 1) {
 				skb = __skb_dequeue_tail(skbs);
+				*total_ts -= skb->truesize;
 				__kfree_skb(skb);
 			}
 			return skbs->qlen > 0;

From 17aee05dc8822e354f5ad2d68ee39e3ba4b6acf2 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 4 Mar 2021 13:32:11 -0800
Subject: [PATCH 0181/1820] mptcp: dispose initial struct socket when its
 subflow is closed

Christoph Paasch reported following crash:
dst_release underflow
WARNING: CPU: 0 PID: 1319 at net/core/dst.c:175 dst_release+0xc1/0xd0 net/core/dst.c:175
CPU: 0 PID: 1319 Comm: syz-executor217 Not tainted 5.11.0-rc6af8e85128b4d0d24083c5cac646e891227052e0c #70
Call Trace:
 rt_cache_route+0x12e/0x140 net/ipv4/route.c:1503
 rt_set_nexthop.constprop.0+0x1fc/0x590 net/ipv4/route.c:1612
 __mkroute_output net/ipv4/route.c:2484 [inline]
...

The worker leaves msk->subflow alone even when it
happened to close the subflow ssk associated with it.

Fixes: 866f26f2a9c33b ("mptcp: always graft subflow socket to parent")
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/157
Reported-by: Christoph Paasch <cpaasch@apple.com>
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index aa59101ffe54..a58da04bed71 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2116,6 +2116,14 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
 	return backup;
 }
 
+static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk)
+{
+	if (msk->subflow) {
+		iput(SOCK_INODE(msk->subflow));
+		msk->subflow = NULL;
+	}
+}
+
 /* subflow sockets can be either outgoing (connect) or incoming
  * (accept).
  *
@@ -2160,6 +2168,9 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 
 	if (ssk == msk->last_snd)
 		msk->last_snd = NULL;
+
+	if (msk->subflow && ssk == msk->subflow->sk)
+		mptcp_dispose_initial_subflow(msk);
 }
 
 void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
@@ -2529,12 +2540,6 @@ static void __mptcp_destroy_sock(struct sock *sk)
 
 	might_sleep();
 
-	/* dispose the ancillatory tcp socket, if any */
-	if (msk->subflow) {
-		iput(SOCK_INODE(msk->subflow));
-		msk->subflow = NULL;
-	}
-
 	/* be sure to always acquire the join list lock, to sync vs
 	 * mptcp_finish_join().
 	 */
@@ -2559,6 +2564,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sk_stream_kill_queues(sk);
 	xfrm_sk_free_policy(sk);
 	sk_refcnt_debug_release(sk);
+	mptcp_dispose_initial_subflow(msk);
 	sock_put(sk);
 }
 

From c8fe62f0768cc9378103fc89fb96804645f527c9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 4 Mar 2021 13:32:12 -0800
Subject: [PATCH 0182/1820] mptcp: reset 'first' and ack_hint on subflow close

Just like with last_snd, we have to NULL 'first' on subflow close.

ack_hint isn't strictly required (its never dereferenced), but better to
clear this explicitly as well instead of making it an exception.

msk->first is dereferenced unconditionally at accept time, but
at that point the ssk is not on the conn_list yet -- this means
worker can't see it when iterating the conn_list.

Reported-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a58da04bed71..3dcb564b03ad 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2169,6 +2169,12 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	if (ssk == msk->last_snd)
 		msk->last_snd = NULL;
 
+	if (ssk == msk->ack_hint)
+		msk->ack_hint = NULL;
+
+	if (ssk == msk->first)
+		msk->first = NULL;
+
 	if (msk->subflow && ssk == msk->subflow->sk)
 		mptcp_dispose_initial_subflow(msk);
 }
@@ -3297,6 +3303,9 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 		/* PM/worker can now acquire the first subflow socket
 		 * lock without racing with listener queue cleanup,
 		 * we can notify it, if needed.
+		 *
+		 * Even if remote has reset the initial subflow by now
+		 * the refcnt is still at least one.
 		 */
 		subflow = mptcp_subflow_ctx(msk->first);
 		list_add(&subflow->node, &msk->conn_list);

From 2948d0a1e5aedc789fed27a4473040b6db741426 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 4 Mar 2021 13:32:13 -0800
Subject: [PATCH 0183/1820] mptcp: factor out __mptcp_retrans helper()

Will simplify the following patch, no functional change
intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 93 ++++++++++++++++++++++++--------------------
 1 file changed, 50 insertions(+), 43 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3dcb564b03ad..67aaf7154dca 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2261,14 +2261,58 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 	mptcp_close_wake_up(sk);
 }
 
-static void mptcp_worker(struct work_struct *work)
+static void __mptcp_retrans(struct sock *sk)
 {
-	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
-	struct sock *ssk, *sk = &msk->sk.icsk_inet.sk;
+	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_sendmsg_info info = {};
 	struct mptcp_data_frag *dfrag;
 	size_t copied = 0;
-	int state, ret;
+	struct sock *ssk;
+	int ret;
+
+	__mptcp_clean_una(sk);
+	dfrag = mptcp_rtx_head(sk);
+	if (!dfrag)
+		return;
+
+	ssk = mptcp_subflow_get_retrans(msk);
+	if (!ssk)
+		goto reset_timer;
+
+	lock_sock(ssk);
+
+	/* limit retransmission to the bytes already sent on some subflows */
+	info.sent = 0;
+	info.limit = dfrag->already_sent;
+	while (info.sent < dfrag->already_sent) {
+		if (!mptcp_alloc_tx_skb(sk, ssk))
+			break;
+
+		ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+		if (ret <= 0)
+			break;
+
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
+		copied += ret;
+		info.sent += ret;
+	}
+	if (copied)
+		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+			 info.size_goal);
+
+	mptcp_set_timeout(sk, ssk);
+	release_sock(ssk);
+
+reset_timer:
+	if (!mptcp_timer_pending(sk))
+		mptcp_reset_timer(sk);
+}
+
+static void mptcp_worker(struct work_struct *work)
+{
+	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
+	struct sock *sk = &msk->sk.icsk_inet.sk;
+	int state;
 
 	lock_sock(sk);
 	state = sk->sk_state;
@@ -2303,45 +2347,8 @@ static void mptcp_worker(struct work_struct *work)
 	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
 		__mptcp_close_subflow(msk);
 
-	if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
-		goto unlock;
-
-	__mptcp_clean_una(sk);
-	dfrag = mptcp_rtx_head(sk);
-	if (!dfrag)
-		goto unlock;
-
-	ssk = mptcp_subflow_get_retrans(msk);
-	if (!ssk)
-		goto reset_unlock;
-
-	lock_sock(ssk);
-
-	/* limit retransmission to the bytes already sent on some subflows */
-	info.sent = 0;
-	info.limit = dfrag->already_sent;
-	while (info.sent < dfrag->already_sent) {
-		if (!mptcp_alloc_tx_skb(sk, ssk))
-			break;
-
-		ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
-		if (ret <= 0)
-			break;
-
-		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
-		copied += ret;
-		info.sent += ret;
-	}
-	if (copied)
-		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
-			 info.size_goal);
-
-	mptcp_set_timeout(sk, ssk);
-	release_sock(ssk);
-
-reset_unlock:
-	if (!mptcp_timer_pending(sk))
-		mptcp_reset_timer(sk);
+	if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
+		__mptcp_retrans(sk);
 
 unlock:
 	release_sock(sk);

From c2e6048fa1cf2228063aec299f93ac6eb256b457 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 4 Mar 2021 13:32:14 -0800
Subject: [PATCH 0184/1820] mptcp: fix race in release_cb

If we receive a MPTCP_PUSH_PENDING even from a subflow when
mptcp_release_cb() is serving the previous one, the latter
will be delayed up to the next release_sock(msk).

Address the issue implementing a test/serve loop for such
event.

Additionally rename the push helper to __mptcp_push_pending()
to be more consistent with the existing code.

Fixes: 6e628cd3a8f7 ("mptcp: use mptcp release_cb for delayed tasks")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 33 +++++++++++++++++++++------------
 1 file changed, 21 insertions(+), 12 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 67aaf7154dca..d2a2169e6d9e 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1445,7 +1445,7 @@ static void mptcp_push_release(struct sock *sk, struct sock *ssk,
 	release_sock(ssk);
 }
 
-static void mptcp_push_pending(struct sock *sk, unsigned int flags)
+static void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 {
 	struct sock *prev_ssk = NULL, *ssk = NULL;
 	struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1697,14 +1697,14 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 wait_for_memory:
 		mptcp_set_nospace(sk);
-		mptcp_push_pending(sk, msg->msg_flags);
+		__mptcp_push_pending(sk, msg->msg_flags);
 		ret = sk_stream_wait_memory(sk, &timeo);
 		if (ret)
 			goto out;
 	}
 
 	if (copied)
-		mptcp_push_pending(sk, msg->msg_flags);
+		__mptcp_push_pending(sk, msg->msg_flags);
 
 out:
 	release_sock(sk);
@@ -2959,13 +2959,14 @@ static void mptcp_release_cb(struct sock *sk)
 {
 	unsigned long flags, nflags;
 
-	/* push_pending may touch wmem_reserved, do it before the later
-	 * cleanup
-	 */
-	if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags))
-		__mptcp_clean_una(sk);
-	if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) {
-		/* mptcp_push_pending() acquires the subflow socket lock
+	for (;;) {
+		flags = 0;
+		if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags))
+			flags |= MPTCP_PUSH_PENDING;
+		if (!flags)
+			break;
+
+		/* the following actions acquire the subflow socket lock
 		 *
 		 * 1) can't be invoked in atomic scope
 		 * 2) must avoid ABBA deadlock with msk socket spinlock: the RX
@@ -2974,13 +2975,21 @@ static void mptcp_release_cb(struct sock *sk)
 		 */
 
 		spin_unlock_bh(&sk->sk_lock.slock);
-		mptcp_push_pending(sk, 0);
+		if (flags & MPTCP_PUSH_PENDING)
+			__mptcp_push_pending(sk, 0);
+
+		cond_resched();
 		spin_lock_bh(&sk->sk_lock.slock);
 	}
+
+	if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags))
+		__mptcp_clean_una(sk);
 	if (test_and_clear_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->flags))
 		__mptcp_error_report(sk);
 
-	/* clear any wmem reservation and errors */
+	/* push_pending may touch wmem_reserved, ensure we do the cleanup
+	 * later
+	 */
 	__mptcp_update_wmem(sk);
 	__mptcp_update_rmem(sk);
 

From 417789df4a03bc820b082bcc503f0d4c5e4704b9 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 4 Mar 2021 13:32:15 -0800
Subject: [PATCH 0185/1820] mptcp: fix missing wakeup

__mptcp_clean_una() can free write memory and should wake-up
user-space processes when needed.

When such function is invoked by the MPTCP receive path, the wakeup
is not needed, as the TCP stack will later trigger subflow_write_space
which will do the wakeup as needed.

Other __mptcp_clean_una() call sites need an additional wakeup check
Let's bundle the relevant code in a new helper and use it.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/165
Fixes: 6e628cd3a8f7 ("mptcp: use mptcp release_cb for delayed tasks")
Fixes: 64b9cea7a0af ("mptcp: fix spurious retransmissions")
Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index d2a2169e6d9e..76958570ae7f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1061,6 +1061,12 @@ out:
 	}
 }
 
+static void __mptcp_clean_una_wakeup(struct sock *sk)
+{
+	__mptcp_clean_una(sk);
+	mptcp_write_space(sk);
+}
+
 static void mptcp_enter_memory_pressure(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
@@ -2270,7 +2276,7 @@ static void __mptcp_retrans(struct sock *sk)
 	struct sock *ssk;
 	int ret;
 
-	__mptcp_clean_una(sk);
+	__mptcp_clean_una_wakeup(sk);
 	dfrag = mptcp_rtx_head(sk);
 	if (!dfrag)
 		return;
@@ -2983,7 +2989,7 @@ static void mptcp_release_cb(struct sock *sk)
 	}
 
 	if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags))
-		__mptcp_clean_una(sk);
+		__mptcp_clean_una_wakeup(sk);
 	if (test_and_clear_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->flags))
 		__mptcp_error_report(sk);
 

From 9238e900d6ec2e9b9ca3d8a9731acfd587fc577a Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Thu, 4 Mar 2021 13:32:16 -0800
Subject: [PATCH 0186/1820] mptcp: free resources when the port number is
 mismatched

When the port number is mismatched with the announced ones, use
'goto dispose_child' to free the resources instead of using 'goto out'.

This patch also moves the port number checking code in
subflow_syn_recv_sock before mptcp_finish_join, otherwise subflow_drop_ctx
will fail in dispose_child.

Fixes: 5bc56388c74f ("mptcp: add port number check for MP_JOIN")
Reported-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/subflow.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 41695e26c374..3d47d670e665 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -687,11 +687,6 @@ create_child:
 			/* move the msk reference ownership to the subflow */
 			subflow_req->msk = NULL;
 			ctx->conn = (struct sock *)owner;
-			if (!mptcp_finish_join(child))
-				goto dispose_child;
-
-			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
-			tcp_rsk(req)->drop_req = true;
 
 			if (subflow_use_different_sport(owner, sk)) {
 				pr_debug("ack inet_sport=%d %d",
@@ -699,10 +694,16 @@ create_child:
 					 ntohs(inet_sk((struct sock *)owner)->inet_sport));
 				if (!mptcp_pm_sport_in_anno_list(owner, sk)) {
 					SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX);
-					goto out;
+					goto dispose_child;
 				}
 				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX);
 			}
+
+			if (!mptcp_finish_join(child))
+				goto dispose_child;
+
+			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
+			tcp_rsk(req)->drop_req = true;
 		}
 	}
 

From 863a42b289c22df63db62b10fc2c2ffc237e2125 Mon Sep 17 00:00:00 2001
From: Hillf Danton <hdanton@sina.com>
Date: Thu, 4 Mar 2021 10:30:09 -0800
Subject: [PATCH 0187/1820] netdevsim: init u64 stats for 32bit hardware

Init the u64 stats in order to avoid the lockdep prints on the 32bit
hardware like

 INFO: trying to register non-static key.
 the code is fine but needs lockdep annotation.
 turning off the locking correctness validator.
 CPU: 0 PID: 4695 Comm: syz-executor.0 Not tainted 5.11.0-rc5-syzkaller #0
 Hardware name: ARM-Versatile Express
 Backtrace:
 [<826fc5b8>] (dump_backtrace) from [<826fc82c>] (show_stack+0x18/0x1c arch/arm/kernel/traps.c:252)
 [<826fc814>] (show_stack) from [<8270d1f8>] (__dump_stack lib/dump_stack.c:79 [inline])
 [<826fc814>] (show_stack) from [<8270d1f8>] (dump_stack+0xa8/0xc8 lib/dump_stack.c:120)
 [<8270d150>] (dump_stack) from [<802bf9c0>] (assign_lock_key kernel/locking/lockdep.c:935 [inline])
 [<8270d150>] (dump_stack) from [<802bf9c0>] (register_lock_class+0xabc/0xb68 kernel/locking/lockdep.c:1247)
 [<802bef04>] (register_lock_class) from [<802baa2c>] (__lock_acquire+0x84/0x32d4 kernel/locking/lockdep.c:4711)
 [<802ba9a8>] (__lock_acquire) from [<802be840>] (lock_acquire.part.0+0xf0/0x554 kernel/locking/lockdep.c:5442)
 [<802be750>] (lock_acquire.part.0) from [<802bed10>] (lock_acquire+0x6c/0x74 kernel/locking/lockdep.c:5415)
 [<802beca4>] (lock_acquire) from [<81560548>] (seqcount_lockdep_reader_access include/linux/seqlock.h:103 [inline])
 [<802beca4>] (lock_acquire) from [<81560548>] (__u64_stats_fetch_begin include/linux/u64_stats_sync.h:164 [inline])
 [<802beca4>] (lock_acquire) from [<81560548>] (u64_stats_fetch_begin include/linux/u64_stats_sync.h:175 [inline])
 [<802beca4>] (lock_acquire) from [<81560548>] (nsim_get_stats64+0xdc/0xf0 drivers/net/netdevsim/netdev.c:70)
 [<8156046c>] (nsim_get_stats64) from [<81e2efa0>] (dev_get_stats+0x44/0xd0 net/core/dev.c:10405)
 [<81e2ef5c>] (dev_get_stats) from [<81e53204>] (rtnl_fill_stats+0x38/0x120 net/core/rtnetlink.c:1211)
 [<81e531cc>] (rtnl_fill_stats) from [<81e59d58>] (rtnl_fill_ifinfo+0x6d4/0x148c net/core/rtnetlink.c:1783)
 [<81e59684>] (rtnl_fill_ifinfo) from [<81e5ceb4>] (rtmsg_ifinfo_build_skb+0x9c/0x108 net/core/rtnetlink.c:3798)
 [<81e5ce18>] (rtmsg_ifinfo_build_skb) from [<81e5d0ac>] (rtmsg_ifinfo_event net/core/rtnetlink.c:3830 [inline])
 [<81e5ce18>] (rtmsg_ifinfo_build_skb) from [<81e5d0ac>] (rtmsg_ifinfo_event net/core/rtnetlink.c:3821 [inline])
 [<81e5ce18>] (rtmsg_ifinfo_build_skb) from [<81e5d0ac>] (rtmsg_ifinfo+0x44/0x70 net/core/rtnetlink.c:3839)
 [<81e5d068>] (rtmsg_ifinfo) from [<81e45c2c>] (register_netdevice+0x664/0x68c net/core/dev.c:10103)
 [<81e455c8>] (register_netdevice) from [<815608bc>] (nsim_create+0xf8/0x124 drivers/net/netdevsim/netdev.c:317)
 [<815607c4>] (nsim_create) from [<81561184>] (__nsim_dev_port_add+0x108/0x188 drivers/net/netdevsim/dev.c:941)
 [<8156107c>] (__nsim_dev_port_add) from [<815620d8>] (nsim_dev_port_add_all drivers/net/netdevsim/dev.c:990 [inline])
 [<8156107c>] (__nsim_dev_port_add) from [<815620d8>] (nsim_dev_probe+0x5cc/0x750 drivers/net/netdevsim/dev.c:1119)
 [<81561b0c>] (nsim_dev_probe) from [<815661dc>] (nsim_bus_probe+0x10/0x14 drivers/net/netdevsim/bus.c:287)
 [<815661cc>] (nsim_bus_probe) from [<811724c0>] (really_probe+0x100/0x50c drivers/base/dd.c:554)
 [<811723c0>] (really_probe) from [<811729c4>] (driver_probe_device+0xf8/0x1c8 drivers/base/dd.c:740)
 [<811728cc>] (driver_probe_device) from [<81172fe4>] (__device_attach_driver+0x8c/0xf0 drivers/base/dd.c:846)
 [<81172f58>] (__device_attach_driver) from [<8116fee0>] (bus_for_each_drv+0x88/0xd8 drivers/base/bus.c:431)
 [<8116fe58>] (bus_for_each_drv) from [<81172c6c>] (__device_attach+0xdc/0x1d0 drivers/base/dd.c:914)
 [<81172b90>] (__device_attach) from [<8117305c>] (device_initial_probe+0x14/0x18 drivers/base/dd.c:961)
 [<81173048>] (device_initial_probe) from [<81171358>] (bus_probe_device+0x90/0x98 drivers/base/bus.c:491)
 [<811712c8>] (bus_probe_device) from [<8116e77c>] (device_add+0x320/0x824 drivers/base/core.c:3109)
 [<8116e45c>] (device_add) from [<8116ec9c>] (device_register+0x1c/0x20 drivers/base/core.c:3182)
 [<8116ec80>] (device_register) from [<81566710>] (nsim_bus_dev_new drivers/net/netdevsim/bus.c:336 [inline])
 [<8116ec80>] (device_register) from [<81566710>] (new_device_store+0x178/0x208 drivers/net/netdevsim/bus.c:215)
 [<81566598>] (new_device_store) from [<8116fcb4>] (bus_attr_store+0x2c/0x38 drivers/base/bus.c:122)
 [<8116fc88>] (bus_attr_store) from [<805b4b8c>] (sysfs_kf_write+0x48/0x54 fs/sysfs/file.c:139)
 [<805b4b44>] (sysfs_kf_write) from [<805b3c90>] (kernfs_fop_write_iter+0x128/0x1ec fs/kernfs/file.c:296)
 [<805b3b68>] (kernfs_fop_write_iter) from [<804d22fc>] (call_write_iter include/linux/fs.h:1901 [inline])
 [<805b3b68>] (kernfs_fop_write_iter) from [<804d22fc>] (new_sync_write fs/read_write.c:518 [inline])
 [<805b3b68>] (kernfs_fop_write_iter) from [<804d22fc>] (vfs_write+0x3dc/0x57c fs/read_write.c:605)
 [<804d1f20>] (vfs_write) from [<804d2604>] (ksys_write+0x68/0xec fs/read_write.c:658)
 [<804d259c>] (ksys_write) from [<804d2698>] (__do_sys_write fs/read_write.c:670 [inline])
 [<804d259c>] (ksys_write) from [<804d2698>] (sys_write+0x10/0x14 fs/read_write.c:667)
 [<804d2688>] (sys_write) from [<80200060>] (ret_fast_syscall+0x0/0x2c arch/arm/mm/proc-v7.S:64)

Fixes: 83c9e13aa39a ("netdevsim: add software driver for testing offloads")
Reported-by: syzbot+e74a6857f2d0efe3ad81@syzkaller.appspotmail.com
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Hillf Danton <hdanton@sina.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/netdev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index aec92440eef1..659d3dceb687 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -294,6 +294,7 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 	dev_net_set(dev, nsim_dev_net(nsim_dev));
 	ns = netdev_priv(dev);
 	ns->netdev = dev;
+	u64_stats_init(&ns->syncp);
 	ns->nsim_dev = nsim_dev;
 	ns->nsim_dev_port = nsim_dev_port;
 	ns->nsim_bus_dev = nsim_dev->nsim_bus_dev;

From 67eb211487f0c993d9f402d1c196ef159fd6a3b5 Mon Sep 17 00:00:00 2001
From: Jiri Wiesner <jwiesner@suse.com>
Date: Thu, 4 Mar 2021 17:18:28 +0100
Subject: [PATCH 0188/1820] ibmvnic: always store valid MAC address

The last change to ibmvnic_set_mac(), 8fc3672a8ad3, meant to prevent
users from setting an invalid MAC address on an ibmvnic interface
that has not been brought up yet. The change also prevented the
requested MAC address from being stored by the adapter object for an
ibmvnic interface when the state of the ibmvnic interface is
VNIC_PROBED - that is after probing has finished but before the
ibmvnic interface is brought up. The MAC address stored by the
adapter object is used and sent to the hypervisor for checking when
an ibmvnic interface is brought up.

The ibmvnic driver ignoring the requested MAC address when in
VNIC_PROBED state caused LACP bonds (bonds in 802.3ad mode) with more
than one slave to malfunction. The bonding code must be able to
change the MAC address of its slaves before they are brought up
during enslaving. The inability of kernels with 8fc3672a8ad3 to set
the MAC addresses of bonding slaves is observable in the output of
"ip address show". The MAC addresses of the slaves are the same as
the MAC address of the bond on a working system whereas the slaves
retain their original MAC addresses on a system with a malfunctioning
LACP bond.

Fixes: 8fc3672a8ad3 ("ibmvnic: fix ibmvnic_set_mac")
Signed-off-by: Jiri Wiesner <jwiesner@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 3bad762083c5..b6102ccf9b90 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1906,10 +1906,9 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	if (adapter->state != VNIC_PROBED) {
-		ether_addr_copy(adapter->mac_addr, addr->sa_data);
+	ether_addr_copy(adapter->mac_addr, addr->sa_data);
+	if (adapter->state != VNIC_PROBED)
 		rc = __ibmvnic_set_mac(netdev, addr->sa_data);
-	}
 
 	return rc;
 }

From ad5d07f4a9cd671233ae20983848874731102c08 Mon Sep 17 00:00:00 2001
From: Paul Moore <paul@paul-moore.com>
Date: Thu, 4 Mar 2021 16:29:51 -0500
Subject: [PATCH 0189/1820] cipso,calipso: resolve a number of problems with
 the DOI refcounts

The current CIPSO and CALIPSO refcounting scheme for the DOI
definitions is a bit flawed in that we:

1. Don't correctly match gets/puts in netlbl_cipsov4_list().
2. Decrement the refcount on each attempt to remove the DOI from the
   DOI list, only removing it from the list once the refcount drops
   to zero.

This patch fixes these problems by adding the missing "puts" to
netlbl_cipsov4_list() and introduces a more conventional, i.e.
not-buggy, refcounting mechanism to the DOI definitions.  Upon the
addition of a DOI to the DOI list, it is initialized with a refcount
of one, removing a DOI from the list removes it from the list and
drops the refcount by one; "gets" and "puts" behave as expected with
respect to refcounts, increasing and decreasing the DOI's refcount by
one.

Fixes: b1edeb102397 ("netlabel: Replace protocol/NetLabel linking with refrerence counts")
Fixes: d7cce01504a0 ("netlabel: Add support for removing a CALIPSO DOI.")
Reported-by: syzbot+9ec037722d2603a9f52e@syzkaller.appspotmail.com
Signed-off-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/cipso_ipv4.c            | 11 +----------
 net/ipv6/calipso.c               | 14 +++++---------
 net/netlabel/netlabel_cipso_v4.c |  3 +++
 3 files changed, 9 insertions(+), 19 deletions(-)

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 471d33a0d095..be09c7669a79 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -519,16 +519,10 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info)
 		ret_val = -ENOENT;
 		goto doi_remove_return;
 	}
-	if (!refcount_dec_and_test(&doi_def->refcount)) {
-		spin_unlock(&cipso_v4_doi_list_lock);
-		ret_val = -EBUSY;
-		goto doi_remove_return;
-	}
 	list_del_rcu(&doi_def->list);
 	spin_unlock(&cipso_v4_doi_list_lock);
 
-	cipso_v4_cache_invalidate();
-	call_rcu(&doi_def->rcu, cipso_v4_doi_free_rcu);
+	cipso_v4_doi_putdef(doi_def);
 	ret_val = 0;
 
 doi_remove_return:
@@ -585,9 +579,6 @@ void cipso_v4_doi_putdef(struct cipso_v4_doi *doi_def)
 
 	if (!refcount_dec_and_test(&doi_def->refcount))
 		return;
-	spin_lock(&cipso_v4_doi_list_lock);
-	list_del_rcu(&doi_def->list);
-	spin_unlock(&cipso_v4_doi_list_lock);
 
 	cipso_v4_cache_invalidate();
 	call_rcu(&doi_def->rcu, cipso_v4_doi_free_rcu);
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 51184a70ac7e..1578ed9e97d8 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -83,6 +83,9 @@ struct calipso_map_cache_entry {
 
 static struct calipso_map_cache_bkt *calipso_cache;
 
+static void calipso_cache_invalidate(void);
+static void calipso_doi_putdef(struct calipso_doi *doi_def);
+
 /* Label Mapping Cache Functions
  */
 
@@ -444,15 +447,10 @@ static int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info)
 		ret_val = -ENOENT;
 		goto doi_remove_return;
 	}
-	if (!refcount_dec_and_test(&doi_def->refcount)) {
-		spin_unlock(&calipso_doi_list_lock);
-		ret_val = -EBUSY;
-		goto doi_remove_return;
-	}
 	list_del_rcu(&doi_def->list);
 	spin_unlock(&calipso_doi_list_lock);
 
-	call_rcu(&doi_def->rcu, calipso_doi_free_rcu);
+	calipso_doi_putdef(doi_def);
 	ret_val = 0;
 
 doi_remove_return:
@@ -508,10 +506,8 @@ static void calipso_doi_putdef(struct calipso_doi *doi_def)
 
 	if (!refcount_dec_and_test(&doi_def->refcount))
 		return;
-	spin_lock(&calipso_doi_list_lock);
-	list_del_rcu(&doi_def->list);
-	spin_unlock(&calipso_doi_list_lock);
 
+	calipso_cache_invalidate();
 	call_rcu(&doi_def->rcu, calipso_doi_free_rcu);
 }
 
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index 726dda95934c..4f50a64315cf 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -575,6 +575,7 @@ list_start:
 
 		break;
 	}
+	cipso_v4_doi_putdef(doi_def);
 	rcu_read_unlock();
 
 	genlmsg_end(ans_skb, data);
@@ -583,12 +584,14 @@ list_start:
 list_retry:
 	/* XXX - this limit is a guesstimate */
 	if (nlsze_mult < 4) {
+		cipso_v4_doi_putdef(doi_def);
 		rcu_read_unlock();
 		kfree_skb(ans_skb);
 		nlsze_mult *= 2;
 		goto list_start;
 	}
 list_failure_lock:
+	cipso_v4_doi_putdef(doi_def);
 	rcu_read_unlock();
 list_failure:
 	kfree_skb(ans_skb);

From 39491867ace594b4912c35f576864d204beed2b3 Mon Sep 17 00:00:00 2001
From: Brendan Jackman <jackmanb@google.com>
Date: Thu, 4 Mar 2021 18:56:46 -0800
Subject: [PATCH 0190/1820] bpf: Explicitly zero-extend R0 after 32-bit cmpxchg

As pointed out by Ilya and explained in the new comment, there's a
discrepancy between x86 and BPF CMPXCHG semantics: BPF always loads
the value from memory into r0, while x86 only does so when r0 and the
value in memory are different. The same issue affects s390.

At first this might sound like pure semantics, but it makes a real
difference when the comparison is 32-bit, since the load will
zero-extend r0/rax.

The fix is to explicitly zero-extend rax after doing such a
CMPXCHG. Since this problem affects multiple archs, this is done in
the verifier by patching in a BPF_ZEXT_REG instruction after every
32-bit cmpxchg. Any archs that don't need such manual zero-extension
can do a look-ahead with insn_is_zext to skip the unnecessary mov.

Note this still goes on top of Ilya's patch:

https://lore.kernel.org/bpf/20210301154019.129110-1-iii@linux.ibm.com/T/#u

Differences v5->v6[1]:
 - Moved is_cmpxchg_insn and ensured it can be safely re-used. Also renamed it
   and removed 'inline' to match the style of the is_*_function helpers.
 - Fixed up comments in verifier test (thanks for the careful review, Martin!)

Differences v4->v5[1]:
 - Moved the logic entirely into opt_subreg_zext_lo32_rnd_hi32, thanks to Martin
   for suggesting this.

Differences v3->v4[1]:
 - Moved the optimization against pointless zext into the correct place:
   opt_subreg_zext_lo32_rnd_hi32 is called _after_ fixup_bpf_calls.

Differences v2->v3[1]:
 - Moved patching into fixup_bpf_calls (patch incoming to rename this function)
 - Added extra commentary on bpf_jit_needs_zext
 - Added check to avoid adding a pointless zext(r0) if there's already one there.

Difference v1->v2[1]: Now solved centrally in the verifier instead of
  specifically for the x86 JIT. Thanks to Ilya and Daniel for the suggestions!

[1] v5: https://lore.kernel.org/bpf/CA+i-1C3ytZz6FjcPmUg5s4L51pMQDxWcZNvM86w4RHZ_o2khwg@mail.gmail.com/T/#t
    v4: https://lore.kernel.org/bpf/CA+i-1C3ytZz6FjcPmUg5s4L51pMQDxWcZNvM86w4RHZ_o2khwg@mail.gmail.com/T/#t
    v3: https://lore.kernel.org/bpf/08669818-c99d-0d30-e1db-53160c063611@iogearbox.net/T/#t
    v2: https://lore.kernel.org/bpf/08669818-c99d-0d30-e1db-53160c063611@iogearbox.net/T/#t
    v1: https://lore.kernel.org/bpf/d7ebaefb-bfd6-a441-3ff2-2fdfe699b1d2@iogearbox.net/T/#t

Reported-by: Ilya Leoshkevich <iii@linux.ibm.com>
Fixes: 5ffa25502b5a ("bpf: Add instructions for atomic_[cmp]xchg")
Signed-off-by: Brendan Jackman <jackmanb@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/core.c                             |  4 +++
 kernel/bpf/verifier.c                         | 19 +++++++++++++-
 .../selftests/bpf/verifier/atomic_cmpxchg.c   | 25 +++++++++++++++++++
 .../selftests/bpf/verifier/atomic_or.c        | 25 +++++++++++++++++++
 4 files changed, 72 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index aa1e64196d8d..3a283bf97f2f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2344,6 +2344,10 @@ bool __weak bpf_helper_changes_pkt_data(void *func)
 /* Return TRUE if the JIT backend wants verifier to enable sub-register usage
  * analysis code and wants explicit zero extension inserted by verifier.
  * Otherwise, return FALSE.
+ *
+ * The verifier inserts an explicit zero extension after BPF_CMPXCHGs even if
+ * you don't override this. JITs that don't want these extra insns can detect
+ * them using insn_is_zext.
  */
 bool __weak bpf_jit_needs_zext(void)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bb3eaab934f3..c56e3fcb5f1a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -504,6 +504,13 @@ static bool is_ptr_cast_function(enum bpf_func_id func_id)
 		func_id == BPF_FUNC_skc_to_tcp_request_sock;
 }
 
+static bool is_cmpxchg_insn(const struct bpf_insn *insn)
+{
+	return BPF_CLASS(insn->code) == BPF_STX &&
+	       BPF_MODE(insn->code) == BPF_ATOMIC &&
+	       insn->imm == BPF_CMPXCHG;
+}
+
 /* string representation of 'enum bpf_reg_type' */
 static const char * const reg_type_str[] = {
 	[NOT_INIT]		= "?",
@@ -11067,7 +11074,17 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
 			goto apply_patch_buffer;
 		}
 
-		if (!bpf_jit_needs_zext())
+		/* Add in an zero-extend instruction if a) the JIT has requested
+		 * it or b) it's a CMPXCHG.
+		 *
+		 * The latter is because: BPF_CMPXCHG always loads a value into
+		 * R0, therefore always zero-extends. However some archs'
+		 * equivalent instruction only does this load when the
+		 * comparison is successful. This detail of CMPXCHG is
+		 * orthogonal to the general zero-extension behaviour of the
+		 * CPU, so it's treated independently of bpf_jit_needs_zext.
+		 */
+		if (!bpf_jit_needs_zext() && !is_cmpxchg_insn(&insn))
 			continue;
 
 		if (WARN_ON(load_reg == -1)) {
diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
index 2efd8bcf57a1..6e52dfc64415 100644
--- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
+++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
@@ -94,3 +94,28 @@
 	.result = REJECT,
 	.errstr = "invalid read from stack",
 },
+{
+	"BPF_W cmpxchg should zero top 32 bits",
+	.insns = {
+		/* r0 = U64_MAX; */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 1),
+		/* u64 val = r0; */
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+		/* r0 = (u32)atomic_cmpxchg((u32 *)&val, r0, 1); */
+		BPF_MOV32_IMM(BPF_REG_1, 1),
+		BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_1, -8),
+		/* r1 = 0x00000000FFFFFFFFull; */
+		BPF_MOV64_IMM(BPF_REG_1, 1),
+		BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32),
+		BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
+		/* if (r0 != r1) exit(1); */
+		BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_1, 2),
+		BPF_MOV32_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		/* exit(0); */
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/atomic_or.c b/tools/testing/selftests/bpf/verifier/atomic_or.c
index 70f982e1f9f0..9d0716ac5080 100644
--- a/tools/testing/selftests/bpf/verifier/atomic_or.c
+++ b/tools/testing/selftests/bpf/verifier/atomic_or.c
@@ -75,3 +75,28 @@
 	},
 	.result = ACCEPT,
 },
+{
+	"BPF_W atomic_fetch_or should zero top 32 bits",
+	.insns = {
+		/* r1 = U64_MAX; */
+		BPF_MOV64_IMM(BPF_REG_1, 0),
+		BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
+		/* u64 val = r1; */
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+		/* r1 = (u32)atomic_fetch_or((u32 *)&val, 2); */
+		BPF_MOV32_IMM(BPF_REG_1, 2),
+		BPF_ATOMIC_OP(BPF_W, BPF_OR | BPF_FETCH, BPF_REG_10, BPF_REG_1, -8),
+		/* r2 = 0x00000000FFFFFFFF; */
+		BPF_MOV64_IMM(BPF_REG_2, 1),
+		BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 32),
+		BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 1),
+		/* if (r2 != r1) exit(1); */
+		BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_1, 2),
+		BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+		BPF_EXIT_INSN(),
+		/* exit(0); */
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+},

From beda430177f56656e7980dcce93456ffaa35676b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 4 Mar 2021 18:18:08 -0800
Subject: [PATCH 0191/1820] KVM: x86: Ensure deadline timer has truly expired
 before posting its IRQ

When posting a deadline timer interrupt, open code the checks guarding
__kvm_wait_lapic_expire() in order to skip the lapic_timer_int_injected()
check in kvm_wait_lapic_expire().  The injection check will always fail
since the interrupt has not yet be injected.  Moving the call after
injection would also be wrong as that wouldn't actually delay delivery
of the IRQ if it is indeed sent via posted interrupt.

Fixes: 010fd37fddf6 ("KVM: LAPIC: Reduce world switch latency caused by timer_advance_ns")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210305021808.3769732-1-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/lapic.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 45d40bfacb7c..cb8ebfaccfb6 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1642,7 +1642,16 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
 	}
 
 	if (kvm_use_posted_timer_interrupt(apic->vcpu)) {
-		kvm_wait_lapic_expire(vcpu);
+		/*
+		 * Ensure the guest's timer has truly expired before posting an
+		 * interrupt.  Open code the relevant checks to avoid querying
+		 * lapic_timer_int_injected(), which will be false since the
+		 * interrupt isn't yet injected.  Waiting until after injecting
+		 * is not an option since that won't help a posted interrupt.
+		 */
+		if (vcpu->arch.apic->lapic_timer.expired_tscdeadline &&
+		    vcpu->arch.apic->lapic_timer.timer_advance_ns)
+			__kvm_wait_lapic_expire(vcpu);
 		kvm_apic_inject_pending_timer_irqs(apic);
 		return;
 	}

From 99840a75454b66d69d2a450ab04e6438d75eba48 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 4 Mar 2021 18:16:37 -0800
Subject: [PATCH 0192/1820] KVM: SVM: Connect 'npt' module param to KVM's
 internal 'npt_enabled'

Directly connect the 'npt' param to the 'npt_enabled' variable so that
runtime adjustments to npt_enabled are reflected in sysfs.  Move the
!PAE restriction to a runtime check to ensure NPT is forced off if the
host is using 2-level paging, and add a comment explicitly stating why
NPT requires a 64-bit kernel or a kernel with PAE enabled.

Opportunistically switch the param to octal permissions.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210305021637.3768573-1-seanjc@google.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/svm.c | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index baee91c1e936..58a45bb139f8 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -115,13 +115,6 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_INVALID,				.always = false },
 };
 
-/* enable NPT for AMD64 and X86 with PAE */
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-bool npt_enabled = true;
-#else
-bool npt_enabled;
-#endif
-
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * pause_filter_count: On processors that support Pause filtering(indicated
@@ -170,9 +163,12 @@ module_param(pause_filter_count_shrink, ushort, 0444);
 static unsigned short pause_filter_count_max = KVM_SVM_DEFAULT_PLE_WINDOW_MAX;
 module_param(pause_filter_count_max, ushort, 0444);
 
-/* allow nested paging (virtualized MMU) for all guests */
-static int npt = true;
-module_param(npt, int, S_IRUGO);
+/*
+ * Use nested page tables by default.  Note, NPT may get forced off by
+ * svm_hardware_setup() if it's unsupported by hardware or the host kernel.
+ */
+bool npt_enabled = true;
+module_param_named(npt, npt_enabled, bool, 0444);
 
 /* allow nested virtualization in KVM/SVM */
 static int nested = true;
@@ -988,10 +984,15 @@ static __init int svm_hardware_setup(void)
 			goto err;
 	}
 
-	if (!boot_cpu_has(X86_FEATURE_NPT))
+	/*
+	 * KVM's MMU doesn't support using 2-level paging for itself, and thus
+	 * NPT isn't supported if the host is using 2-level paging since host
+	 * CR4 is unchanged on VMRUN.
+	 */
+	if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE))
 		npt_enabled = false;
 
-	if (npt_enabled && !npt)
+	if (!boot_cpu_has(X86_FEATURE_NPT))
 		npt_enabled = false;
 
 	kvm_configure_mmu(npt_enabled, get_max_npt_level(), PG_LEVEL_1G);

From 3f9b9efd82a84f27e95d0414f852caf1fa839e83 Mon Sep 17 00:00:00 2001
From: Vivek Goyal <vgoyal@redhat.com>
Date: Tue, 9 Feb 2021 17:47:54 -0500
Subject: [PATCH 0193/1820] virtiofs: Fail dax mount if device does not support
 it

Right now "mount -t virtiofs -o dax myfs /mnt/virtiofs" succeeds even
if filesystem deivce does not have a cache window and hence DAX can't
be supported.

This gives a false sense to user that they are using DAX with virtiofs
but fact of the matter is that they are not.

Fix this by returning error if dax can't be supported and user has asked
for it.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/virtio_fs.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 8868ac31a3c0..4ee6f734ba83 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -1324,8 +1324,15 @@ static int virtio_fs_fill_super(struct super_block *sb, struct fs_context *fsc)
 
 	/* virtiofs allocates and installs its own fuse devices */
 	ctx->fudptr = NULL;
-	if (ctx->dax)
+	if (ctx->dax) {
+		if (!fs->dax_dev) {
+			err = -EINVAL;
+			pr_err("virtio-fs: dax can't be enabled as filesystem"
+			       " device does not support it.\n");
+			goto err_free_fuse_devs;
+		}
 		ctx->dax_dev = fs->dax_dev;
+	}
 	err = fuse_fill_super_common(sb, ctx);
 	if (err < 0)
 		goto err_free_fuse_devs;

From 56887cffe946bb0a90c74429fa94d6110a73119d Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 22 Feb 2021 10:48:09 +0100
Subject: [PATCH 0194/1820] block: Try to handle busy underlying device on
 discard

Commit 384d87ef2c95 ("block: Do not discard buffers under a mounted
filesystem") made paths issuing discard or zeroout requests to the
underlying device try to grab block device in exclusive mode. If that
failed we returned EBUSY to userspace. This however caused unexpected
fallout in userspace where e.g. FUSE filesystems issue discard requests
from userspace daemons although the device is open exclusively by the
kernel. Also shrinking of logical volume by LVM issues discard requests
to a device which may be claimed exclusively because there's another LV
on the same PV. So to avoid these userspace regressions, fall back to
invalidate_inode_pages2_range() instead of returning EBUSY to userspace
and return EBUSY only of that call fails as well (meaning that there's
indeed someone using the particular device range we are trying to
discard).

Link: https://bugzilla.kernel.org/show_bug.cgi?id=211167
Fixes: 384d87ef2c95 ("block: Do not discard buffers under a mounted filesystem")
CC: stable@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 4aa1f88d5bf8..03166b3dea4d 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -118,13 +118,22 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
 	if (!(mode & FMODE_EXCL)) {
 		int err = bd_prepare_to_claim(bdev, truncate_bdev_range);
 		if (err)
-			return err;
+			goto invalidate;
 	}
 
 	truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
 	if (!(mode & FMODE_EXCL))
 		bd_abort_claiming(bdev, truncate_bdev_range);
 	return 0;
+
+invalidate:
+	/*
+	 * Someone else has handle exclusively open. Try invalidating instead.
+	 * The 'end' argument is inclusive so the rounding is safe.
+	 */
+	return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping,
+					     lstart >> PAGE_SHIFT,
+					     lend >> PAGE_SHIFT);
 }
 
 static void set_init_blocksize(struct block_device *bdev)

From 7d365bd0bff3c0310c39ebaffc9a8458e036d666 Mon Sep 17 00:00:00 2001
From: Stefan Haberland <sth@linux.ibm.com>
Date: Fri, 5 Mar 2021 13:54:38 +0100
Subject: [PATCH 0195/1820] s390/dasd: fix hanging DASD driver unbind

In case of an unbind of the DASD device driver the function
dasd_generic_remove() is called which shuts down the device.
Among others this functions removes the int_handler from the cdev.
During shutdown the device cancels all outstanding IO requests and waits
for completion of the clear request.
Unfortunately the clear interrupt will never be received when there is no
interrupt handler connected.

Fix by moving the int_handler removal after the call to the state machine
where no request or interrupt is outstanding.

Cc: stable@vger.kernel.org
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Tested-by: Bjoern Walk <bwalk@linux.ibm.com>
Reviewed-by: Jan Hoeppner <hoeppner@linux.ibm.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/s390/block/dasd.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 28c04a4efa66..22805115ebc2 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -3487,8 +3487,6 @@ void dasd_generic_remove(struct ccw_device *cdev)
 	struct dasd_device *device;
 	struct dasd_block *block;
 
-	cdev->handler = NULL;
-
 	device = dasd_device_from_cdev(cdev);
 	if (IS_ERR(device)) {
 		dasd_remove_sysfs_files(cdev);
@@ -3507,6 +3505,7 @@ void dasd_generic_remove(struct ccw_device *cdev)
 	 * no quite down yet.
 	 */
 	dasd_set_target_state(device, DASD_STATE_NEW);
+	cdev->handler = NULL;
 	/* dasd_delete_device destroys the device reference. */
 	block = device->block;
 	dasd_delete_device(device);

From 66f669a272898feb1c69b770e1504aa2ec7723d1 Mon Sep 17 00:00:00 2001
From: Stefan Haberland <sth@linux.ibm.com>
Date: Fri, 5 Mar 2021 13:54:39 +0100
Subject: [PATCH 0196/1820] s390/dasd: fix hanging IO request during DASD
 driver unbind

Prevent that an IO request is build during device shutdown initiated by
a driver unbind. This request will never be able to be processed or
canceled and will hang forever. This will lead also to a hanging unbind.

Fix by checking not only if the device is in READY state but also check
that there is no device offline initiated before building a new IO request.

Fixes: e443343e509a ("s390/dasd: blk-mq conversion")

Cc: <stable@vger.kernel.org> # v4.14+
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Tested-by: Bjoern Walk <bwalk@linux.ibm.com>
Reviewed-by: Jan Hoeppner <hoeppner@linux.ibm.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/s390/block/dasd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 22805115ebc2..ba9ce4e0d30a 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -3052,7 +3052,8 @@ static blk_status_t do_dasd_request(struct blk_mq_hw_ctx *hctx,
 
 	basedev = block->base;
 	spin_lock_irq(&dq->lock);
-	if (basedev->state < DASD_STATE_READY) {
+	if (basedev->state < DASD_STATE_READY ||
+	    test_bit(DASD_FLAG_OFFLINE, &basedev->flags)) {
 		DBF_DEV_EVENT(DBF_ERR, basedev,
 			      "device not ready for request %p", req);
 		rc = BLK_STS_IOERR;

From 4f44657d74873735e93a50eb25014721a66aac19 Mon Sep 17 00:00:00 2001
From: Xunlei Pang <xlpang@linux.alibaba.com>
Date: Fri, 5 Mar 2021 16:13:27 +0800
Subject: [PATCH 0197/1820] blk-cgroup: Fix the recursive blkg rwstat

The current blkio.throttle.io_service_bytes_recursive doesn't
work correctly.

As an example, for the following blkcg hierarchy:
 (Made 1GB READ in test1, 512MB READ in test2)
     test
    /    \
 test1   test2

$ head -n 1 test/test1/blkio.throttle.io_service_bytes_recursive
8:0 Read 1073684480
$ head -n 1 test/test2/blkio.throttle.io_service_bytes_recursive
8:0 Read 537448448
$ head -n 1 test/blkio.throttle.io_service_bytes_recursive
8:0 Read 537448448

Clearly, above data of "test" reflects "test2" not "test1"+"test2".

Do the correct summary in blkg_rwstat_recursive_sum().

Signed-off-by: Xunlei Pang <xlpang@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup-rwstat.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c
index 85d5790ac49b..3304e841df7c 100644
--- a/block/blk-cgroup-rwstat.c
+++ b/block/blk-cgroup-rwstat.c
@@ -109,6 +109,7 @@ void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
 
 	lockdep_assert_held(&blkg->q->queue_lock);
 
+	memset(sum, 0, sizeof(*sum));
 	rcu_read_lock();
 	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
 		struct blkg_rwstat *rwstat;
@@ -122,7 +123,7 @@ void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
 			rwstat = (void *)pos_blkg + off;
 
 		for (i = 0; i < BLKG_RWSTAT_NR; i++)
-			sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i);
+			sum->cnt[i] += blkg_rwstat_read_counter(rwstat, i);
 	}
 	rcu_read_unlock();
 }

From 00ff801bb8ce6711e919af4530b6ffa14a22390a Mon Sep 17 00:00:00 2001
From: "Kevin(Yudong) Yang" <yyd@google.com>
Date: Wed, 3 Mar 2021 09:43:54 -0500
Subject: [PATCH 0198/1820] net/mlx4_en: update moderation when config reset

This patch fixes a bug that the moderation config will not be
applied when calling mlx4_en_reset_config. For example, when
turning on rx timestamping, mlx4_en_reset_config() will be called,
causing the NIC to forget previous moderation config.

This fix is in phase with a previous fix:
commit 79c54b6bbf06 ("net/mlx4_en: Fix TX moderation info loss
after set_ringparam is called")

Tested: Before this patch, on a host with NIC using mlx4, run
netserver and stream TCP to the host at full utilization.
$ sar -I SUM 1
                 INTR    intr/s
14:03:56          sum  48758.00

After rx hwtstamp is enabled:
$ sar -I SUM 1
14:10:38          sum 317771.00
We see the moderation is not working properly and issued 7x more
interrupts.

After the patch, and turned on rx hwtstamp, the rate of interrupts
is as expected:
$ sar -I SUM 1
14:52:11          sum  49332.00

Fixes: 79c54b6bbf06 ("net/mlx4_en: Fix TX moderation info loss after set_ringparam is called")
Signed-off-by: Kevin(Yudong) Yang <yyd@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
CC: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 2 +-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c  | 2 ++
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h    | 1 +
 3 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 23849f2b9c25..1434df66fcf2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -47,7 +47,7 @@
 #define EN_ETHTOOL_SHORT_MASK cpu_to_be16(0xffff)
 #define EN_ETHTOOL_WORD_MASK  cpu_to_be32(0xffffffff)
 
-static int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
+int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
 {
 	int i, t;
 	int err = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 51b9700fce83..5d0c9c62382d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3554,6 +3554,8 @@ int mlx4_en_reset_config(struct net_device *dev,
 			en_err(priv, "Failed starting port\n");
 	}
 
+	if (!err)
+		err = mlx4_en_moderation_update(priv);
 out:
 	mutex_unlock(&mdev->state_lock);
 	kfree(tmp);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index e8ed23190de0..f3d1a20201ef 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -775,6 +775,7 @@ void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev);
 #define DEV_FEATURE_CHANGED(dev, new_features, feature) \
 	((dev->features & feature) ^ (new_features & feature))
 
+int mlx4_en_moderation_update(struct mlx4_en_priv *priv);
 int mlx4_en_reset_config(struct net_device *dev,
 			 struct hwtstamp_config ts_config,
 			 netdev_features_t new_features);

From 38c26ff3048af50eee3fcd591921357ee5bfd9ee Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 4 Mar 2021 18:06:48 -0800
Subject: [PATCH 0199/1820] net: tehuti: fix error return code in bdx_probe()

When bdx_read_mac() fails, no error return code of bdx_probe()
is assigned.
To fix this bug, err is assigned with -EFAULT as error return code.

Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/tehuti/tehuti.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index b8f4f419173f..d054c6e83b1c 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -2044,6 +2044,7 @@ bdx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		/*bdx_hw_reset(priv); */
 		if (bdx_read_mac(priv)) {
 			pr_err("load MAC address failed\n");
+			err = -EFAULT;
 			goto err_out_iomap;
 		}
 		SET_NETDEV_DEV(ndev, &pdev->dev);

From 6650d31f21b8a0043613ae0a4a2e42e49dc20b2d Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 4 Mar 2021 19:10:10 -0800
Subject: [PATCH 0200/1820] net: intel: iavf: fix error return code of
 iavf_init_get_resources()

When iavf_process_config() fails, no error return code of
iavf_init_get_resources() is assigned.
To fix this bug, err is assigned with the return value of
iavf_process_config(), and then err is checked.

Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 0a867d64d467..dc5b3c06d1e0 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1776,7 +1776,8 @@ static int iavf_init_get_resources(struct iavf_adapter *adapter)
 		goto err_alloc;
 	}
 
-	if (iavf_process_config(adapter))
+	err = iavf_process_config(adapter);
+	if (err)
 		goto err_alloc;
 	adapter->current_op = VIRTCHNL_OP_UNKNOWN;
 

From 9a7b3950c7e15968e23d83be215e95ccc7c92a53 Mon Sep 17 00:00:00 2001
From: Ong Boon Leong <boon.leong.ong@intel.com>
Date: Fri, 5 Mar 2021 13:49:30 +0800
Subject: [PATCH 0201/1820] net: stmmac: Fix VLAN filter delete timeout issue
 in Intel mGBE SGMII

For Intel mGbE controller, MAC VLAN filter delete operation will time-out
if serdes power-down sequence happened first during driver remove() with
below message.

[82294.764958] intel-eth-pci 0000:00:1e.4 eth2: stmmac_dvr_remove: removing driver
[82294.778677] intel-eth-pci 0000:00:1e.4 eth2: Timeout accessing MAC_VLAN_Tag_Filter
[82294.779997] intel-eth-pci 0000:00:1e.4 eth2: failed to kill vid 0081/0
[82294.947053] intel-eth-pci 0000:00:1d.2 eth1: stmmac_dvr_remove: removing driver
[82295.002091] intel-eth-pci 0000:00:1d.1 eth0: stmmac_dvr_remove: removing driver

Therefore, we delay the serdes power-down to be after unregister_netdev()
which triggers the VLAN filter delete.

Fixes: b9663b7ca6ff ("net: stmmac: Enable SERDES power up/down sequence")
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 0eba44e9c1f8..208cae344ffa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -5249,13 +5249,16 @@ int stmmac_dvr_remove(struct device *dev)
 	netdev_info(priv->dev, "%s: removing driver", __func__);
 
 	stmmac_stop_all_dma(priv);
-
-	if (priv->plat->serdes_powerdown)
-		priv->plat->serdes_powerdown(ndev, priv->plat->bsp_priv);
-
 	stmmac_mac_set(priv, priv->ioaddr, false);
 	netif_carrier_off(ndev);
 	unregister_netdev(ndev);
+
+	/* Serdes power down needs to happen after VLAN filter
+	 * is deleted that is triggered by unregister_netdev().
+	 */
+	if (priv->plat->serdes_powerdown)
+		priv->plat->serdes_powerdown(ndev, priv->plat->bsp_priv);
+
 #ifdef CONFIG_DEBUG_FS
 	stmmac_exit_fs(ndev);
 #endif

From 8eb37ab7cc045ec6305a6a1a9c32374695a1a977 Mon Sep 17 00:00:00 2001
From: Wong Vee Khee <vee.khee.wong@intel.com>
Date: Fri, 5 Mar 2021 14:03:42 +0800
Subject: [PATCH 0202/1820] stmmac: intel: Fixes clock registration error seen
 for multiple interfaces

Issue seen when enumerating multiple Intel mGbE interfaces in EHL.

[    6.898141] intel-eth-pci 0000:00:1d.2: enabling device (0000 -> 0002)
[    6.900971] intel-eth-pci 0000:00:1d.2: Fail to register stmmac-clk
[    6.906434] intel-eth-pci 0000:00:1d.2: User ID: 0x51, Synopsys ID: 0x52

We fix it by making the clock name to be unique following the format
of stmmac-pci_name(pci_dev) so that we can differentiate the clock for
these Intel mGbE interfaces in EHL platform as follow:

  /sys/kernel/debug/clk/stmmac-0000:00:1d.1
  /sys/kernel/debug/clk/stmmac-0000:00:1d.2
  /sys/kernel/debug/clk/stmmac-0000:00:1e.4

Fixes: 58da0cfa6cf1 ("net: stmmac: create dwmac-intel.c to contain all Intel platform")
Signed-off-by: Wong Vee Khee <vee.khee.wong@intel.com>
Signed-off-by: Voon Weifeng <weifeng.voon@intel.com>
Co-developed-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index f2896872a86c..0b64f7710d17 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -233,6 +233,7 @@ static void common_default_data(struct plat_stmmacenet_data *plat)
 static int intel_mgbe_common_data(struct pci_dev *pdev,
 				  struct plat_stmmacenet_data *plat)
 {
+	char clk_name[20];
 	int ret;
 	int i;
 
@@ -301,8 +302,10 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	plat->eee_usecs_rate = plat->clk_ptp_rate;
 
 	/* Set system clock */
+	sprintf(clk_name, "%s-%s", "stmmac", pci_name(pdev));
+
 	plat->stmmac_clk = clk_register_fixed_rate(&pdev->dev,
-						   "stmmac-clk", NULL, 0,
+						   clk_name, NULL, 0,
 						   plat->clk_ptp_rate);
 
 	if (IS_ERR(plat->stmmac_clk)) {

From e233febda6ebab750e30662a7cc9b9efad127685 Mon Sep 17 00:00:00 2001
From: Sergey Nazarov <s-nazarov@yandex.ru>
Date: Fri, 5 Mar 2021 11:05:54 +0300
Subject: [PATCH 0203/1820] CIPSO: Fix unaligned memory access in
 cipso_v4_gentag_hdr

We need to use put_unaligned when writing 32-bit DOI value
in cipso_v4_gentag_hdr to avoid unaligned memory access.

v2: unneeded type cast removed as Ondrej Mosnacek suggested.

Signed-off-by: Sergey Nazarov <s-nazarov@yandex.ru>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/cipso_ipv4.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index be09c7669a79..bfaf327e9d12 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1153,7 +1153,7 @@ static void cipso_v4_gentag_hdr(const struct cipso_v4_doi *doi_def,
 {
 	buf[0] = IPOPT_CIPSO;
 	buf[1] = CIPSO_V4_HDR_LEN + len;
-	*(__be32 *)&buf[2] = htonl(doi_def->doi);
+	put_unaligned_be32(doi_def->doi, &buf[2]);
 }
 
 /**

From 69cdb7947adb816fc9325b4ec02a6dddd5070b82 Mon Sep 17 00:00:00 2001
From: Junlin Yang <yangjunlin@yulong.com>
Date: Fri, 5 Mar 2021 16:48:39 +0800
Subject: [PATCH 0204/1820] ibmvnic: remove excessive irqsave

ibmvnic_remove locks multiple spinlocks while disabling interrupts:
spin_lock_irqsave(&adapter->state_lock, flags);
spin_lock_irqsave(&adapter->rwi_lock, flags);

As reported by coccinelle, the second _irqsave() overwrites the value
saved in 'flags' by the first _irqsave(),   therefore when the second
_irqrestore() comes,the value in 'flags' is not valid,the value saved
by the first _irqsave() has been lost.
This likely leads to IRQs remaining disabled. So remove the second
_irqsave():
spin_lock_irqsave(&adapter->state_lock, flags);
spin_lock(&adapter->rwi_lock);

Generated by: ./scripts/coccinelle/locks/flags.cocci
./drivers/net/ethernet/ibm/ibmvnic.c:5413:1-18:
ERROR: nested lock+irqsave that reuses flags from line 5404.

Fixes: 4a41c421f367 ("ibmvnic: serialize access to work queue on remove")
Signed-off-by: Junlin Yang <yangjunlin@yulong.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index b6102ccf9b90..161fa95e8768 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -5408,9 +5408,9 @@ static int ibmvnic_remove(struct vio_dev *dev)
 	 * after setting state, so __ibmvnic_reset() which is called
 	 * from the flush_work() below, can make progress.
 	 */
-	spin_lock_irqsave(&adapter->rwi_lock, flags);
+	spin_lock(&adapter->rwi_lock);
 	adapter->state = VNIC_REMOVING;
-	spin_unlock_irqrestore(&adapter->rwi_lock, flags);
+	spin_unlock(&adapter->rwi_lock);
 
 	spin_unlock_irqrestore(&adapter->state_lock, flags);
 

From 0a7e0c3b5702a6a76cf7e5b8cc10a73e51dc221e Mon Sep 17 00:00:00 2001
From: Xu Wang <vulab@iscas.ac.cn>
Date: Fri, 5 Mar 2021 09:33:06 +0000
Subject: [PATCH 0205/1820] selftest/net/ipsec.c: Remove unneeded semicolon

fix semicolon.cocci warning:
tools/testing/selftests/net/ipsec.c:1788:2-3: Unneeded semicolon

Signed-off-by: Xu Wang <vulab@iscas.ac.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/ipsec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c
index 17ced7d6ce25..f23438d512c5 100644
--- a/tools/testing/selftests/net/ipsec.c
+++ b/tools/testing/selftests/net/ipsec.c
@@ -1785,7 +1785,7 @@ static void grand_child_serv(unsigned int nr, int cmd_fd, void *buf,
 		break;
 	default:
 		printk("got unknown msg type %d", msg->type);
-	};
+	}
 }
 
 static int grand_child_f(unsigned int nr, int cmd_fd, void *buf)

From abbf9a0ef8848dca58c5b97750c1c59bbee45637 Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Fri, 5 Mar 2021 17:34:41 +0800
Subject: [PATCH 0206/1820] r8169: fix r8168fp_adjust_ocp_cmd function

The (0xBAF70000 & 0x00FFF000) << 6 should be (0xf70 << 18).

Fixes: 561535b0f239 ("r8169: fix OCP access on RTL8117")
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Acked-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index f704da3f214c..7aad0ba53372 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -767,7 +767,7 @@ static void r8168fp_adjust_ocp_cmd(struct rtl8169_private *tp, u32 *cmd, int typ
 	if (type == ERIAR_OOB &&
 	    (tp->mac_version == RTL_GIGA_MAC_VER_52 ||
 	     tp->mac_version == RTL_GIGA_MAC_VER_53))
-		*cmd |= 0x7f0 << 18;
+		*cmd |= 0xf70 << 18;
 }
 
 DECLARE_RTL_COND(rtl_eriar_cond)

From 85554bcd123e307282631defe6bf6fac5031cf60 Mon Sep 17 00:00:00 2001
From: Denis Efremov <efremov@linux.com>
Date: Fri, 5 Mar 2021 19:26:22 +0300
Subject: [PATCH 0207/1820] net/hamradio/6pack: remove redundant check in
 sp_encaps()

"len > sp->mtu" checked twice in a row in sp_encaps().
Remove the second check.

Signed-off-by: Denis Efremov <efremov@linux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hamradio/6pack.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 71d6629e65c9..9f5b5614a150 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -171,11 +171,6 @@ static void sp_encaps(struct sixpack *sp, unsigned char *icp, int len)
 		goto out_drop;
 	}
 
-	if (len > sp->mtu) {	/* sp->mtu = AX25_MTU = max. PACLEN = 256 */
-		msg = "oversized transmit packet!";
-		goto out_drop;
-	}
-
 	if (p[0] > 5) {
 		msg = "invalid KISS command";
 		goto out_drop;

From 155b23e6e53475ca3b8c2a946299b4d4dd6a5a1e Mon Sep 17 00:00:00 2001
From: Denis Efremov <efremov@linux.com>
Date: Fri, 5 Mar 2021 20:02:12 +0300
Subject: [PATCH 0208/1820] sun/niu: fix wrong RXMAC_BC_FRM_CNT_COUNT count

RXMAC_BC_FRM_CNT_COUNT added to mp->rx_bcasts twice in a row
in niu_xmac_interrupt(). Remove the second addition.

Signed-off-by: Denis Efremov <efremov@linux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sun/niu.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 68695d4afacd..707ccdd03b19 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -3931,8 +3931,6 @@ static void niu_xmac_interrupt(struct niu *np)
 		mp->rx_mcasts += RXMAC_MC_FRM_CNT_COUNT;
 	if (val & XRXMAC_STATUS_RXBCAST_CNT_EXP)
 		mp->rx_bcasts += RXMAC_BC_FRM_CNT_COUNT;
-	if (val & XRXMAC_STATUS_RXBCAST_CNT_EXP)
-		mp->rx_bcasts += RXMAC_BC_FRM_CNT_COUNT;
 	if (val & XRXMAC_STATUS_RXHIST1_CNT_EXP)
 		mp->rx_hist_cnt1 += RXMAC_HIST_CNT1_COUNT;
 	if (val & XRXMAC_STATUS_RXHIST2_CNT_EXP)

From d8861bab48b6c1fc3cdbcab8ff9d1eaea43afe7f Mon Sep 17 00:00:00 2001
From: Michael Braun <michael-dev@fami-braun.de>
Date: Thu, 4 Mar 2021 20:52:52 +0100
Subject: [PATCH 0209/1820] gianfar: fix jumbo packets+napi+rx overrun crash

When using jumbo packets and overrunning rx queue with napi enabled,
the following sequence is observed in gfar_add_rx_frag:

   | lstatus                              |       | skb                   |
t  | lstatus,  size, flags                | first | len, data_len, *ptr   |
---+--------------------------------------+-------+-----------------------+
13 | 18002348, 9032, INTERRUPT LAST       | 0     | 9600, 8000,  f554c12e |
12 | 10000640, 1600, INTERRUPT            | 0     | 8000, 6400,  f554c12e |
11 | 10000640, 1600, INTERRUPT            | 0     | 6400, 4800,  f554c12e |
10 | 10000640, 1600, INTERRUPT            | 0     | 4800, 3200,  f554c12e |
09 | 10000640, 1600, INTERRUPT            | 0     | 3200, 1600,  f554c12e |
08 | 14000640, 1600, INTERRUPT FIRST      | 0     | 1600, 0,     f554c12e |
07 | 14000640, 1600, INTERRUPT FIRST      | 1     | 0,    0,     f554c12e |
06 | 1c000080, 128,  INTERRUPT LAST FIRST | 1     | 0,    0,     abf3bd6e |
05 | 18002348, 9032, INTERRUPT LAST       | 0     | 8000, 6400,  c5a57780 |
04 | 10000640, 1600, INTERRUPT            | 0     | 6400, 4800,  c5a57780 |
03 | 10000640, 1600, INTERRUPT            | 0     | 4800, 3200,  c5a57780 |
02 | 10000640, 1600, INTERRUPT            | 0     | 3200, 1600,  c5a57780 |
01 | 10000640, 1600, INTERRUPT            | 0     | 1600, 0,     c5a57780 |
00 | 14000640, 1600, INTERRUPT FIRST      | 1     | 0,    0,     c5a57780 |

So at t=7 a new packets is started but not finished, probably due to rx
overrun - but rx overrun is not indicated in the flags. Instead a new
packets starts at t=8. This results in skb->len to exceed size for the LAST
fragment at t=13 and thus a negative fragment size added to the skb.

This then crashes:

kernel BUG at include/linux/skbuff.h:2277!
Oops: Exception in kernel mode, sig: 5 [#1]
...
NIP [c04689f4] skb_pull+0x2c/0x48
LR [c03f62ac] gfar_clean_rx_ring+0x2e4/0x844
Call Trace:
[ec4bfd38] [c06a84c4] _raw_spin_unlock_irqrestore+0x60/0x7c (unreliable)
[ec4bfda8] [c03f6a44] gfar_poll_rx_sq+0x48/0xe4
[ec4bfdc8] [c048d504] __napi_poll+0x54/0x26c
[ec4bfdf8] [c048d908] net_rx_action+0x138/0x2c0
[ec4bfe68] [c06a8f34] __do_softirq+0x3a4/0x4fc
[ec4bfed8] [c0040150] run_ksoftirqd+0x58/0x70
[ec4bfee8] [c0066ecc] smpboot_thread_fn+0x184/0x1cc
[ec4bff08] [c0062718] kthread+0x140/0x144
[ec4bff38] [c0012350] ret_from_kernel_thread+0x14/0x1c

This patch fixes this by checking for computed LAST fragment size, so a
negative sized fragment is never added.
In order to prevent the newer rx frame from getting corrupted, the FIRST
flag is checked to discard the incomplete older frame.

Signed-off-by: Michael Braun <michael-dev@fami-braun.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/gianfar.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 541de32ea662..1cf8ef717453 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2390,6 +2390,10 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus,
 		if (lstatus & BD_LFLAG(RXBD_LAST))
 			size -= skb->len;
 
+		WARN(size < 0, "gianfar: rx fragment size underflow");
+		if (size < 0)
+			return false;
+
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
 				rxb->page_offset + RXBUF_ALIGNMENT,
 				size, GFAR_RXB_TRUESIZE);
@@ -2552,6 +2556,17 @@ static int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue,
 		if (lstatus & BD_LFLAG(RXBD_EMPTY))
 			break;
 
+		/* lost RXBD_LAST descriptor due to overrun */
+		if (skb &&
+		    (lstatus & BD_LFLAG(RXBD_FIRST))) {
+			/* discard faulty buffer */
+			dev_kfree_skb(skb);
+			skb = NULL;
+			rx_queue->stats.rx_dropped++;
+
+			/* can continue normally */
+		}
+
 		/* order rx buffer descriptor reads */
 		rmb();
 

From 3e21a10fdea3c2e4e4d1b72cb9d720256461af40 Mon Sep 17 00:00:00 2001
From: George McCollister <george.mccollister@gmail.com>
Date: Fri, 5 Mar 2021 16:24:45 -0600
Subject: [PATCH 0210/1820] lan743x: trim all 4 bytes of the FCS; not just 2

Trim all 4 bytes of the received FCS; not just 2 of them. Leaving 2
bytes of the FCS on the frame breaks DSA tailing tag drivers.

Fixes: a8db76d40e4d ("lan743x: boost performance on cpu archs w/o dma cache snooping")
Signed-off-by: George McCollister <george.mccollister@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index dbdfabff3b00..1c3e204d727c 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -2040,7 +2040,7 @@ lan743x_rx_trim_skb(struct sk_buff *skb, int frame_length)
 		dev_kfree_skb_irq(skb);
 		return NULL;
 	}
-	frame_length = max_t(int, 0, frame_length - RX_HEAD_PADDING - 2);
+	frame_length = max_t(int, 0, frame_length - RX_HEAD_PADDING - 4);
 	if (skb->len > frame_length) {
 		skb->tail -= skb->len - frame_length;
 		skb->len = frame_length;

From edbea922025169c0e5cdca5ebf7bf5374cc5566c Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 3 Mar 2021 16:29:03 +0100
Subject: [PATCH 0211/1820] veth: Store queue_mapping independently of XDP prog
 presence

Currently, veth_xmit() would call the skb_record_rx_queue() only when
there is XDP program loaded on peer interface in native mode.

If peer has XDP prog in generic mode, then netif_receive_generic_xdp()
has a call to netif_get_rxqueue(skb), so for multi-queue veth it will
not be possible to grab a correct rxq.

To fix that, store queue_mapping independently of XDP prog presence on
peer interface.

Fixes: 638264dc9022 ("veth: Support per queue XDP ring")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Toshiaki Makita <toshiaki.makita1@gmail.com>
Link: https://lore.kernel.org/bpf/20210303152903.11172-1-maciej.fijalkowski@intel.com
---
 drivers/net/veth.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index aa1a66ad2ce5..34e49c75db42 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -302,8 +302,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (rxq < rcv->real_num_rx_queues) {
 		rq = &rcv_priv->rq[rxq];
 		rcv_xdp = rcu_access_pointer(rq->xdp_prog);
-		if (rcv_xdp)
-			skb_record_rx_queue(skb, rxq);
+		skb_record_rx_queue(skb, rxq);
 	}
 
 	skb_tx_timestamp(skb);

From a4dcfbc4ee2218abd567d81d795082d8d4afcdf6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 5 Mar 2021 14:17:29 -0800
Subject: [PATCH 0212/1820] ethernet: alx: fix order of calls on resume

netif_device_attach() will unpause the queues so we can't call
it before __alx_open(). This went undetected until
commit b0999223f224 ("alx: add ability to allocate and free
alx_napi structures") but now if stack tries to xmit immediately
on resume before __alx_open() we'll crash on the NAPI being null:

 BUG: kernel NULL pointer dereference, address: 0000000000000198
 CPU: 0 PID: 12 Comm: ksoftirqd/0 Tainted: G           OE 5.10.0-3-amd64 #1 Debian 5.10.13-1
 Hardware name: Gigabyte Technology Co., Ltd. To be filled by O.E.M./H77-D3H, BIOS F15 11/14/2013
 RIP: 0010:alx_start_xmit+0x34/0x650 [alx]
 Code: 41 56 41 55 41 54 55 53 48 83 ec 20 0f b7 57 7c 8b 8e b0
0b 00 00 39 ca 72 06 89 d0 31 d2 f7 f1 89 d2 48 8b 84 df
 RSP: 0018:ffffb09240083d28 EFLAGS: 00010297
 RAX: 0000000000000000 RBX: ffffa04d80ae7800 RCX: 0000000000000004
 RDX: 0000000000000000 RSI: ffffa04d80afa000 RDI: ffffa04e92e92a00
 RBP: 0000000000000042 R08: 0000000000000100 R09: ffffa04ea3146700
 R10: 0000000000000014 R11: 0000000000000000 R12: ffffa04e92e92100
 R13: 0000000000000001 R14: ffffa04e92e92a00 R15: ffffa04e92e92a00
 FS:  0000000000000000(0000) GS:ffffa0508f600000(0000) knlGS:0000000000000000
 i915 0000:00:02.0: vblank wait timed out on crtc 0
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000198 CR3: 000000004460a001 CR4: 00000000001706f0
 Call Trace:
  dev_hard_start_xmit+0xc7/0x1e0
  sch_direct_xmit+0x10f/0x310

Cc: <stable@vger.kernel.org> # 4.9+
Fixes: bc2bebe8de8e ("alx: remove WoL support")
Reported-by: Zbynek Michl <zbynek.michl@gmail.com>
Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=983595
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Tested-by: Zbynek Michl <zbynek.michl@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/alx/main.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 9b7f1af5f574..9e02f8864593 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1894,13 +1894,16 @@ static int alx_resume(struct device *dev)
 
 	if (!netif_running(alx->dev))
 		return 0;
-	netif_device_attach(alx->dev);
 
 	rtnl_lock();
 	err = __alx_open(alx, true);
 	rtnl_unlock();
+	if (err)
+		return err;
 
-	return err;
+	netif_device_attach(alx->dev);
+
+	return 0;
 }
 
 static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume);

From 4691453406c3a799fdebac83a689919c2c877f04 Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <musamaanjum@gmail.com>
Date: Fri, 5 Mar 2021 23:08:16 +0500
Subject: [PATCH 0213/1820] kvm: x86: use NULL instead of using plain integer
 as pointer

Sparse warnings removed:
warning: Using plain integer as NULL pointer

Signed-off-by: Muhammad Usama Anjum <musamaanjum@gmail.com>
Message-Id: <20210305180816.GA488770@LEGION>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 868213ca4f98..46b0e52671bb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10600,7 +10600,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 			return (void __user *)hva;
 	} else {
 		if (!slot || !slot->npages)
-			return 0;
+			return NULL;
 
 		old_npages = slot->npages;
 		hva = slot->userspace_addr;

From b96b0c5de685df82019e16826a282d53d86d112c Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Fri, 5 Mar 2021 18:52:47 +0000
Subject: [PATCH 0214/1820] KVM: arm64: nvhe: Save the SPE context early

The nVHE KVM hyp drains and disables the SPE buffer, before
entering the guest, as the EL1&0 translation regime
is going to be loaded with that of the guest.

But this operation is performed way too late, because :
  - The owning translation regime of the SPE buffer
    is transferred to EL2. (MDCR_EL2_E2PB == 0)
  - The guest Stage1 is loaded.

Thus the flush could use the host EL1 virtual address,
but use the EL2 translations instead of host EL1, for writing
out any cached data.

Fix this by moving the SPE buffer handling early enough.
The restore path is doing the right thing.

Fixes: 014c4c77aad7 ("KVM: arm64: Improve debug register save/restore flow")
Cc: stable@vger.kernel.org
Cc: Christoffer Dall <christoffer.dall@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexandru Elisei <alexandru.elisei@arm.com>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210302120345.3102874-1-suzuki.poulose@arm.com
Message-Id: <20210305185254.3730990-2-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/include/asm/kvm_hyp.h   |  5 +++++
 arch/arm64/kvm/hyp/nvhe/debug-sr.c | 12 ++++++++++--
 arch/arm64/kvm/hyp/nvhe/switch.c   | 11 ++++++++++-
 3 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index c0450828378b..385bd7dd3d39 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -83,6 +83,11 @@ void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt);
 void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
 void __debug_switch_to_host(struct kvm_vcpu *vcpu);
 
+#ifdef __KVM_NVHE_HYPERVISOR__
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+#endif
+
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
 
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
index 91a711aa8382..f401724f12ef 100644
--- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -58,16 +58,24 @@ static void __debug_restore_spe(u64 pmscr_el1)
 	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
 }
 
-void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu)
 {
 	/* Disable and flush SPE data generation */
 	__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
+}
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
 	__debug_switch_to_guest_common(vcpu);
 }
 
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu)
+{
+	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+}
+
 void __debug_switch_to_host(struct kvm_vcpu *vcpu)
 {
-	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
 	__debug_switch_to_host_common(vcpu);
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index f3d0e9eca56c..59aa1045fdaf 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -192,6 +192,14 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
 
 	__sysreg_save_state_nvhe(host_ctxt);
+	/*
+	 * We must flush and disable the SPE buffer for nVHE, as
+	 * the translation regime(EL1&0) is going to be loaded with
+	 * that of the guest. And we must do this before we change the
+	 * translation regime to EL2 (via MDCR_EL2_E2PB == 0) and
+	 * before we load guest Stage1.
+	 */
+	__debug_save_host_buffers_nvhe(vcpu);
 
 	__adjust_pc(vcpu);
 
@@ -234,11 +242,12 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
 		__fpsimd_save_fpexc32(vcpu);
 
+	__debug_switch_to_host(vcpu);
 	/*
 	 * This must come after restoring the host sysregs, since a non-VHE
 	 * system may enable SPE here and make use of the TTBRs.
 	 */
-	__debug_switch_to_host(vcpu);
+	__debug_restore_host_buffers_nvhe(vcpu);
 
 	if (pmu_switch_needed)
 		__pmu_switch_to_host(host_ctxt);

From 31948332d5fa392ad933f4a6a10026850649ed76 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 5 Mar 2021 18:52:48 +0000
Subject: [PATCH 0215/1820] KVM: arm64: Avoid corrupting vCPU context register
 in guest exit

Commit 7db21530479f ("KVM: arm64: Restore hyp when panicking in guest
context") tracks the currently running vCPU, clearing the pointer to
NULL on exit from a guest.

Unfortunately, the use of 'set_loaded_vcpu' clobbers x1 to point at the
kvm_hyp_ctxt instead of the vCPU context, causing the subsequent RAS
code to go off into the weeds when it saves the DISR assuming that the
CPU context is embedded in a struct vCPU.

Leave x1 alone and use x3 as a temporary register instead when clearing
the vCPU on the guest exit path.

Cc: Marc Zyngier <maz@kernel.org>
Cc: Andrew Scull <ascull@google.com>
Cc: <stable@vger.kernel.org>
Fixes: 7db21530479f ("KVM: arm64: Restore hyp when panicking in guest context")
Suggested-by: Quentin Perret <qperret@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210226181211.14542-1-will@kernel.org
Message-Id: <20210305185254.3730990-3-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/hyp/entry.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index b0afad7a99c6..0c66a1d408fd 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -146,7 +146,7 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
 	// Now restore the hyp regs
 	restore_callee_saved_regs x2
 
-	set_loaded_vcpu xzr, x1, x2
+	set_loaded_vcpu xzr, x2, x3
 
 alternative_if ARM64_HAS_RAS_EXTN
 	// If we have the RAS extensions we can consume a pending error

From c4b000c3928d4f20acef79dccf3a65ae3795e0b0 Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Fri, 5 Mar 2021 18:52:49 +0000
Subject: [PATCH 0216/1820] KVM: arm64: Fix nVHE hyp panic host context restore

When panicking from the nVHE hyp and restoring the host context, x29 is
expected to hold a pointer to the host context. This wasn't being done
so fix it to make sure there's a valid pointer the host context being
used.

Rather than passing a boolean indicating whether or not the host context
should be restored, instead pass the pointer to the host context. NULL
is passed to indicate that no context should be restored.

Fixes: a2e102e20fd6 ("KVM: arm64: nVHE: Handle hyp panics")
Cc: stable@vger.kernel.org
Signed-off-by: Andrew Scull <ascull@google.com>
[maz: partial rewrite to fit 5.12-rc1]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210219122406.1337626-1-ascull@google.com
Message-Id: <20210305185254.3730990-4-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/include/asm/kvm_hyp.h |  3 ++-
 arch/arm64/kvm/hyp/nvhe/host.S   | 15 ++++++++-------
 arch/arm64/kvm/hyp/nvhe/switch.c |  3 +--
 3 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 385bd7dd3d39..32ae676236b6 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -102,7 +102,8 @@ bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt);
 
 void __noreturn hyp_panic(void);
 #ifdef __KVM_NVHE_HYPERVISOR__
-void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
+void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
+			       u64 elr, u64 par);
 #endif
 
 #endif /* __ARM64_KVM_HYP_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 6585a7cbbc56..5d94584840cc 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -71,7 +71,8 @@ SYM_FUNC_START(__host_enter)
 SYM_FUNC_END(__host_enter)
 
 /*
- * void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
+ * void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
+ * 				  u64 elr, u64 par);
  */
 SYM_FUNC_START(__hyp_do_panic)
 	/* Prepare and exit to the host's panic funciton. */
@@ -82,9 +83,11 @@ SYM_FUNC_START(__hyp_do_panic)
 	hyp_kimg_va lr, x6
 	msr	elr_el2, lr
 
-	/* Set the panic format string. Use the, now free, LR as scratch. */
-	ldr	lr, =__hyp_panic_string
-	hyp_kimg_va lr, x6
+	mov	x29, x0
+
+	/* Load the format string into x0 and arguments into x1-7 */
+	ldr	x0, =__hyp_panic_string
+	hyp_kimg_va x0, x6
 
 	/* Load the format arguments into x1-7. */
 	mov	x6, x3
@@ -94,9 +97,7 @@ SYM_FUNC_START(__hyp_do_panic)
 	mrs	x5, hpfar_el2
 
 	/* Enter the host, conditionally restoring the host context. */
-	cmp	x0, xzr
-	mov	x0, lr
-	b.eq	__host_enter_without_restoring
+	cbz	x29, __host_enter_without_restoring
 	b	__host_enter_for_panic
 SYM_FUNC_END(__hyp_do_panic)
 
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 59aa1045fdaf..68ab6b4d5141 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -266,7 +266,6 @@ void __noreturn hyp_panic(void)
 	u64 spsr = read_sysreg_el2(SYS_SPSR);
 	u64 elr = read_sysreg_el2(SYS_ELR);
 	u64 par = read_sysreg_par();
-	bool restore_host = true;
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_vcpu *vcpu;
 
@@ -280,7 +279,7 @@ void __noreturn hyp_panic(void)
 		__sysreg_restore_state_nvhe(host_ctxt);
 	}
 
-	__hyp_do_panic(restore_host, spsr, elr, par);
+	__hyp_do_panic(host_ctxt, spsr, elr, par);
 	unreachable();
 }
 

From 6b5b368fccd7109b052e45af8ba1464c8d140a49 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 5 Mar 2021 18:52:50 +0000
Subject: [PATCH 0217/1820] KVM: arm64: Turn kvm_arm_support_pmu_v3() into a
 static key

We currently find out about the presence of a HW PMU (or the handling
of that PMU by perf, which amounts to the same thing) in a fairly
roundabout way, by checking the number of counters available to perf.
That's good enough for now, but we will soon need to find about about
that on paths where perf is out of reach (in the world switch).

Instead, let's turn kvm_arm_support_pmu_v3() into a static key.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Link: https://lore.kernel.org/r/20210209114844.3278746-2-maz@kernel.org
Message-Id: <20210305185254.3730990-5-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/perf.c     | 10 ++++++++++
 arch/arm64/kvm/pmu-emul.c | 10 ----------
 include/kvm/arm_pmu.h     |  9 +++++++--
 3 files changed, 17 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c
index d45b8b9a4415..739164324afe 100644
--- a/arch/arm64/kvm/perf.c
+++ b/arch/arm64/kvm/perf.c
@@ -11,6 +11,8 @@
 
 #include <asm/kvm_emulate.h>
 
+DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
+
 static int kvm_is_in_guest(void)
 {
         return kvm_get_running_vcpu() != NULL;
@@ -48,6 +50,14 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = {
 
 int kvm_perf_init(void)
 {
+	/*
+	 * Check if HW_PERF_EVENTS are supported by checking the number of
+	 * hardware performance counters. This could ensure the presence of
+	 * a physical PMU and CONFIG_PERF_EVENT is selected.
+	 */
+	if (IS_ENABLED(CONFIG_ARM_PMU) && perf_num_counters() > 0)
+		static_branch_enable(&kvm_arm_pmu_available);
+
 	return perf_register_guest_info_callbacks(&kvm_guest_cbs);
 }
 
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index e9ec08b0b070..e32c6e139a09 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -823,16 +823,6 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	return val & mask;
 }
 
-bool kvm_arm_support_pmu_v3(void)
-{
-	/*
-	 * Check if HW_PERF_EVENTS are supported by checking the number of
-	 * hardware performance counters. This could ensure the presence of
-	 * a physical PMU and CONFIG_PERF_EVENT is selected.
-	 */
-	return (perf_num_counters() > 0);
-}
-
 int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 {
 	if (!kvm_vcpu_has_pmu(vcpu))
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 8dcb3e1477bc..6fd3cda608e4 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -13,6 +13,13 @@
 #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
 #define ARMV8_PMU_MAX_COUNTER_PAIRS	((ARMV8_PMU_MAX_COUNTERS + 1) >> 1)
 
+DECLARE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
+
+static __always_inline bool kvm_arm_support_pmu_v3(void)
+{
+	return static_branch_likely(&kvm_arm_pmu_available);
+}
+
 #ifdef CONFIG_HW_PERF_EVENTS
 
 struct kvm_pmc {
@@ -47,7 +54,6 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 				    u64 select_idx);
-bool kvm_arm_support_pmu_v3(void);
 int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
@@ -87,7 +93,6 @@ static inline void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu,
 						  u64 data, u64 select_idx) {}
-static inline bool kvm_arm_support_pmu_v3(void) { return false; }
 static inline int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
 					  struct kvm_device_attr *attr)
 {

From f27647b588c13647a60074b5a8dd39a86d919a1d Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 5 Mar 2021 18:52:51 +0000
Subject: [PATCH 0218/1820] KVM: arm64: Don't access PMSELR_EL0/PMUSERENR_EL0
 when no PMU is available

When running under a nesting hypervisor, it isn't guaranteed that
the virtual HW will include a PMU. In which case, let's not try
to access the PMU registers in the world switch, as that'd be
deadly.

Reported-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Link: https://lore.kernel.org/r/20210209114844.3278746-3-maz@kernel.org
Message-Id: <20210305185254.3730990-6-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kernel/image-vars.h          | 3 +++
 arch/arm64/kvm/hyp/include/hyp/switch.h | 9 ++++++---
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 23f1a557bd9f..5aa9ed1e9ec6 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -101,6 +101,9 @@ KVM_NVHE_ALIAS(__stop___kvm_ex_table);
 /* Array containing bases of nVHE per-CPU memory regions. */
 KVM_NVHE_ALIAS(kvm_arm_hyp_percpu_base);
 
+/* PMU available static key */
+KVM_NVHE_ALIAS(kvm_arm_pmu_available);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 54f4860cd87c..6c1f51f25eb3 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -90,15 +90,18 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
 	 * EL1 instead of being trapped to EL2.
 	 */
-	write_sysreg(0, pmselr_el0);
-	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+	if (kvm_arm_support_pmu_v3()) {
+		write_sysreg(0, pmselr_el0);
+		write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+	}
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 }
 
 static inline void __deactivate_traps_common(void)
 {
 	write_sysreg(0, hstr_el2);
-	write_sysreg(0, pmuserenr_el0);
+	if (kvm_arm_support_pmu_v3())
+		write_sysreg(0, pmuserenr_el0);
 }
 
 static inline void ___activate_traps(struct kvm_vcpu *vcpu)

From b9d699e2694d032aa8ecc15141f698ccb050dc95 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 5 Mar 2021 18:52:52 +0000
Subject: [PATCH 0219/1820] KVM: arm64: Rename __vgic_v3_get_ich_vtr_el2() to
 __vgic_v3_get_gic_config()

As we are about to report a bit more information to the rest of
the kernel, rename __vgic_v3_get_ich_vtr_el2() to the more
explicit __vgic_v3_get_gic_config().

No functional change.

Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Message-Id: <20210305185254.3730990-7-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/include/asm/kvm_asm.h   | 4 ++--
 arch/arm64/kvm/hyp/nvhe/hyp-main.c | 6 +++---
 arch/arm64/kvm/hyp/vgic-v3-sr.c    | 7 ++++++-
 arch/arm64/kvm/vgic/vgic-v3.c      | 4 +++-
 4 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 22d933e9b59e..9c0e396dd03f 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -50,7 +50,7 @@
 #define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_local_vmid	5
 #define __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff		6
 #define __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs			7
-#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_ich_vtr_el2		8
+#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config		8
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr		9
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr		10
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs		11
@@ -192,7 +192,7 @@ extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
-extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern u64 __vgic_v3_get_gic_config(void);
 extern u64 __vgic_v3_read_vmcr(void);
 extern void __vgic_v3_write_vmcr(u32 vmcr);
 extern void __vgic_v3_init_lrs(void);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index f012f8665ecc..8f129968204e 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -67,9 +67,9 @@ static void handle___kvm_enable_ssbs(struct kvm_cpu_context *host_ctxt)
 	write_sysreg_el2(tmp, SYS_SCTLR);
 }
 
-static void handle___vgic_v3_get_ich_vtr_el2(struct kvm_cpu_context *host_ctxt)
+static void handle___vgic_v3_get_gic_config(struct kvm_cpu_context *host_ctxt)
 {
-	cpu_reg(host_ctxt, 1) = __vgic_v3_get_ich_vtr_el2();
+	cpu_reg(host_ctxt, 1) = __vgic_v3_get_gic_config();
 }
 
 static void handle___vgic_v3_read_vmcr(struct kvm_cpu_context *host_ctxt)
@@ -118,7 +118,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_tlb_flush_local_vmid),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
 	HANDLE_FUNC(__kvm_enable_ssbs),
-	HANDLE_FUNC(__vgic_v3_get_ich_vtr_el2),
+	HANDLE_FUNC(__vgic_v3_get_gic_config),
 	HANDLE_FUNC(__vgic_v3_read_vmcr),
 	HANDLE_FUNC(__vgic_v3_write_vmcr),
 	HANDLE_FUNC(__vgic_v3_init_lrs),
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 80406f463c28..005daa0c9dd7 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -405,7 +405,12 @@ void __vgic_v3_init_lrs(void)
 		__gic_v3_set_lr(0, i);
 }
 
-u64 __vgic_v3_get_ich_vtr_el2(void)
+/*
+ * Return the GIC CPU configuration:
+ * - [31:0]  ICH_VTR_EL2
+ * - [63:32] RES0
+ */
+u64 __vgic_v3_get_gic_config(void)
 {
 	return read_gicreg(ICH_VTR_EL2);
 }
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 52915b342351..c3e6c3fd333b 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -574,9 +574,11 @@ early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable);
  */
 int vgic_v3_probe(const struct gic_kvm_info *info)
 {
-	u32 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_ich_vtr_el2);
+	u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config);
 	int ret;
 
+	ich_vtr_el2 = (u32)ich_vtr_el2;
+
 	/*
 	 * The ListRegs field is 5 bits, but there is an architectural
 	 * maximum of 16 list registers. Just ignore bit 4...

From 9739f6ef053f104a997165701c6e15582c4307ee Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 5 Mar 2021 18:52:53 +0000
Subject: [PATCH 0220/1820] KVM: arm64: Workaround firmware wrongly advertising
 GICv2-on-v3 compatibility

It looks like we have broken firmware out there that wrongly advertises
a GICv2 compatibility interface, despite the CPUs not being able to deal
with it.

To work around this, check that the CPU initialising KVM is actually able
to switch to MMIO instead of system registers, and use that as a
precondition to enable GICv2 compatibility in KVM.

Note that the detection happens on a single CPU. If the firmware is
lying *and* that the CPUs are asymetric, all hope is lost anyway.

Reported-by: Shameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com>
Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Message-Id: <20210305185254.3730990-8-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/hyp/vgic-v3-sr.c | 35 +++++++++++++++++++++++++++++++--
 arch/arm64/kvm/vgic/vgic-v3.c   |  8 ++++++--
 2 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 005daa0c9dd7..ee3682b9873c 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -408,11 +408,42 @@ void __vgic_v3_init_lrs(void)
 /*
  * Return the GIC CPU configuration:
  * - [31:0]  ICH_VTR_EL2
- * - [63:32] RES0
+ * - [62:32] RES0
+ * - [63]    MMIO (GICv2) capable
  */
 u64 __vgic_v3_get_gic_config(void)
 {
-	return read_gicreg(ICH_VTR_EL2);
+	u64 val, sre = read_gicreg(ICC_SRE_EL1);
+	unsigned long flags = 0;
+
+	/*
+	 * To check whether we have a MMIO-based (GICv2 compatible)
+	 * CPU interface, we need to disable the system register
+	 * view. To do that safely, we have to prevent any interrupt
+	 * from firing (which would be deadly).
+	 *
+	 * Note that this only makes sense on VHE, as interrupts are
+	 * already masked for nVHE as part of the exception entry to
+	 * EL2.
+	 */
+	if (has_vhe())
+		flags = local_daif_save();
+
+	write_gicreg(0, ICC_SRE_EL1);
+	isb();
+
+	val = read_gicreg(ICC_SRE_EL1);
+
+	write_gicreg(sre, ICC_SRE_EL1);
+	isb();
+
+	if (has_vhe())
+		local_daif_restore(flags);
+
+	val  = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
+	val |= read_gicreg(ICH_VTR_EL2);
+
+	return val;
 }
 
 u64 __vgic_v3_read_vmcr(void)
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index c3e6c3fd333b..6f530925a231 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -575,8 +575,10 @@ early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable);
 int vgic_v3_probe(const struct gic_kvm_info *info)
 {
 	u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config);
+	bool has_v2;
 	int ret;
 
+	has_v2 = ich_vtr_el2 >> 63;
 	ich_vtr_el2 = (u32)ich_vtr_el2;
 
 	/*
@@ -596,13 +598,15 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 			 gicv4_enable ? "en" : "dis");
 	}
 
+	kvm_vgic_global_state.vcpu_base = 0;
+
 	if (!info->vcpu.start) {
 		kvm_info("GICv3: no GICV resource entry\n");
-		kvm_vgic_global_state.vcpu_base = 0;
+	} else if (!has_v2) {
+		pr_warn(FW_BUG "CPU interface incapable of MMIO access\n");
 	} else if (!PAGE_ALIGNED(info->vcpu.start)) {
 		pr_warn("GICV physical address 0x%llx not page aligned\n",
 			(unsigned long long)info->vcpu.start);
-		kvm_vgic_global_state.vcpu_base = 0;
 	} else {
 		kvm_vgic_global_state.vcpu_base = info->vcpu.start;
 		kvm_vgic_global_state.can_emulate_gicv2 = true;

From 357ad203d45c0f9d76a8feadbd5a1c5d460c638b Mon Sep 17 00:00:00 2001
From: Jia He <justin.he@arm.com>
Date: Fri, 5 Mar 2021 18:52:54 +0000
Subject: [PATCH 0221/1820] KVM: arm64: Fix range alignment when walking page
 tables

When walking the page tables at a given level, and if the start
address for the range isn't aligned for that level, we propagate
the misalignment on each iteration at that level.

This results in the walker ignoring a number of entries (depending
on the original misalignment) on each subsequent iteration.

Properly aligning the address before the next iteration addresses
this issue.

Cc: stable@vger.kernel.org
Reported-by: Howard Zhang <Howard.Zhang@arm.com>
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Jia He <justin.he@arm.com>
Fixes: b1e57de62cfb ("KVM: arm64: Add stand-alone page-table walker infrastructure")
[maz: rewrite commit message]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210303024225.2591-1-justin.he@arm.com
Message-Id: <20210305185254.3730990-9-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/hyp/pgtable.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 4d177ce1d536..926fc07074f5 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -223,6 +223,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 		goto out;
 
 	if (!table) {
+		data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level));
 		data->addr += kvm_granule_size(level);
 		goto out;
 	}

From 56678a5f44ef5f0ad9a67194bbee2280c6286534 Mon Sep 17 00:00:00 2001
From: Alban Bedel <albeu@free.fr>
Date: Mon, 22 Feb 2021 15:15:59 +0100
Subject: [PATCH 0222/1820] platform/x86: intel-hid: Support Lenovo ThinkPad X1
 Tablet Gen 2

Like a few other system the Lenovo ThinkPad X1 Tablet Gen 2 miss the
HEBC method, which prevent the power button from working. Add a quirk
to enable the button array on this system family and fix the power
button.

Signed-off-by: Alban Bedel <albeu@free.fr>
Tested-by: Alexander Kobel <a-kobel@a-kobel.de>
Link: https://lore.kernel.org/r/20210222141559.3775-1-albeu@free.fr
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/intel-hid.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index 2f5b8d09143e..57cc92891a57 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -90,6 +90,13 @@ static const struct dmi_system_id button_array_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP Spectre x2 Detachable"),
 		},
 	},
+	{
+		.ident = "Lenovo ThinkPad X1 Tablet Gen 2",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Tablet Gen 2"),
+		},
+	},
 	{ }
 };
 

From 56b26497bb4b7ff970612dc25a8a008c34463f7b Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Sat, 6 Mar 2021 10:50:18 +0100
Subject: [PATCH 0223/1820] ALSA: hda/conexant: Add quirk for mute LED control
 on HP ZBook G5

The mute and mic-mute LEDs on HP ZBook Studio G5 are controlled via
GPIO bits 0x10 and 0x20, respectively, and we need the extra setup for
those.

As the similar code is already present for other HP models but with
different GPIO pins, this patch factors out the common helper code and
applies those GPIO values for each model.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=211893
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210306095018.11746-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_conexant.c | 66 ++++++++++++++++++++++++----------
 1 file changed, 47 insertions(+), 19 deletions(-)

diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index f2aa226d1373..c20dad46a7c9 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -149,6 +149,21 @@ static int cx_auto_vmaster_mute_led(struct led_classdev *led_cdev,
 	return 0;
 }
 
+static void cxt_init_gpio_led(struct hda_codec *codec)
+{
+	struct conexant_spec *spec = codec->spec;
+	unsigned int mask = spec->gpio_mute_led_mask | spec->gpio_mic_led_mask;
+
+	if (mask) {
+		snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_MASK,
+				    mask);
+		snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DIRECTION,
+				    mask);
+		snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
+				    spec->gpio_led);
+	}
+}
+
 static int cx_auto_init(struct hda_codec *codec)
 {
 	struct conexant_spec *spec = codec->spec;
@@ -156,6 +171,7 @@ static int cx_auto_init(struct hda_codec *codec)
 	if (!spec->dynamic_eapd)
 		cx_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, true);
 
+	cxt_init_gpio_led(codec);
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_INIT);
 
 	return 0;
@@ -215,6 +231,7 @@ enum {
 	CXT_FIXUP_HP_SPECTRE,
 	CXT_FIXUP_HP_GATE_MIC,
 	CXT_FIXUP_MUTE_LED_GPIO,
+	CXT_FIXUP_HP_ZBOOK_MUTE_LED,
 	CXT_FIXUP_HEADSET_MIC,
 	CXT_FIXUP_HP_MIC_NO_PRESENCE,
 };
@@ -654,31 +671,36 @@ static int cxt_gpio_micmute_update(struct led_classdev *led_cdev,
 	return 0;
 }
 
+static void cxt_setup_mute_led(struct hda_codec *codec,
+			       unsigned int mute, unsigned int mic_mute)
+{
+	struct conexant_spec *spec = codec->spec;
+
+	spec->gpio_led = 0;
+	spec->mute_led_polarity = 0;
+	if (mute) {
+		snd_hda_gen_add_mute_led_cdev(codec, cxt_gpio_mute_update);
+		spec->gpio_mute_led_mask = mute;
+	}
+	if (mic_mute) {
+		snd_hda_gen_add_micmute_led_cdev(codec, cxt_gpio_micmute_update);
+		spec->gpio_mic_led_mask = mic_mute;
+	}
+}
 
 static void cxt_fixup_mute_led_gpio(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
-	struct conexant_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x03 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x03 },
-		{}
-	};
-
-	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		snd_hda_gen_add_mute_led_cdev(codec, cxt_gpio_mute_update);
-		spec->gpio_led = 0;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x01;
-		spec->gpio_mic_led_mask = 0x02;
-		snd_hda_gen_add_micmute_led_cdev(codec, cxt_gpio_micmute_update);
-	}
-	snd_hda_add_verbs(codec, gpio_init);
-	if (spec->gpio_led)
-		snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
-				    spec->gpio_led);
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		cxt_setup_mute_led(codec, 0x01, 0x02);
 }
 
+static void cxt_fixup_hp_zbook_mute_led(struct hda_codec *codec,
+					const struct hda_fixup *fix, int action)
+{
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		cxt_setup_mute_led(codec, 0x10, 0x20);
+}
 
 /* ThinkPad X200 & co with cxt5051 */
 static const struct hda_pintbl cxt_pincfg_lenovo_x200[] = {
@@ -839,6 +861,10 @@ static const struct hda_fixup cxt_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cxt_fixup_mute_led_gpio,
 	},
+	[CXT_FIXUP_HP_ZBOOK_MUTE_LED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = cxt_fixup_hp_zbook_mute_led,
+	},
 	[CXT_FIXUP_HEADSET_MIC] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cxt_fixup_headset_mic,
@@ -917,6 +943,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8402, "HP ProBook 645 G4", CXT_FIXUP_MUTE_LED_GPIO),
+	SND_PCI_QUIRK(0x103c, 0x8427, "HP ZBook Studio G5", CXT_FIXUP_HP_ZBOOK_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8456, "HP Z2 G4 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE),
@@ -956,6 +983,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = {
 	{ .id = CXT_FIXUP_MUTE_LED_EAPD, .name = "mute-led-eapd" },
 	{ .id = CXT_FIXUP_HP_DOCK, .name = "hp-dock" },
 	{ .id = CXT_FIXUP_MUTE_LED_GPIO, .name = "mute-led-gpio" },
+	{ .id = CXT_FIXUP_HP_ZBOOK_MUTE_LED, .name = "hp-zbook-mute-led" },
 	{ .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" },
 	{}
 };

From 50bf8080a94d171e843fc013abec19d8ab9f50ae Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 25 Feb 2021 23:03:51 +0100
Subject: [PATCH 0224/1820] static_call: Fix the module key fixup

Provided the target address of a R_X86_64_PC32 relocation is aligned,
the low two bits should be invariant between the relative and absolute
value.

Turns out the address is not aligned and things go sideways, ensure we
transfer the bits in the absolute form when fixing up the key address.

Fixes: 73f44fe19d35 ("static_call: Allow module use without exposing static_call_key")
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/20210225220351.GE4746@worktop.programming.kicks-ass.net
---
 kernel/static_call.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/static_call.c b/kernel/static_call.c
index 6906c6ec4c97..ae825295cf68 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -349,7 +349,8 @@ static int static_call_add_module(struct module *mod)
 	struct static_call_site *site;
 
 	for (site = start; site != stop; site++) {
-		unsigned long addr = (unsigned long)static_call_key(site);
+		unsigned long s_key = (long)site->key + (long)&site->key;
+		unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS;
 		unsigned long key;
 
 		/*
@@ -373,8 +374,8 @@ static int static_call_add_module(struct module *mod)
 			return -EINVAL;
 		}
 
-		site->key = (key - (long)&site->key) |
-			    (site->key & STATIC_CALL_SITE_FLAGS);
+		key |= s_key & STATIC_CALL_SITE_FLAGS;
+		site->key = key - (long)&site->key;
 	}
 
 	return __static_call_init(mod, start, stop);

From a5398bffc01fe044848c5024e5e867e407f239b8 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Mon, 30 Nov 2020 11:38:40 -0800
Subject: [PATCH 0225/1820] perf/core: Flush PMU internal buffers for per-CPU
 events

Sometimes the PMU internal buffers have to be flushed for per-CPU events
during a context switch, e.g., large PEBS. Otherwise, the perf tool may
report samples in locations that do not belong to the process where the
samples are processed in, because PEBS does not tag samples with PID/TID.

The current code only flush the buffers for a per-task event. It doesn't
check a per-CPU event.

Add a new event state flag, PERF_ATTACH_SCHED_CB, to indicate that the
PMU internal buffers have to be flushed for this event during a context
switch.

Add sched_cb_entry and perf_sched_cb_usages back to track the PMU/cpuctx
which is required to be flushed.

Only need to invoke the sched_task() for per-CPU events in this patch.
The per-task events have been handled in perf_event_context_sched_in/out
already.

Fixes: 9c964efa4330 ("perf/x86/intel: Drain the PEBS buffer during context switches")
Reported-by: Gabriel Marin <gmx@google.com>
Originally-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20201130193842.10569-1-kan.liang@linux.intel.com
---
 include/linux/perf_event.h |  2 ++
 kernel/events/core.c       | 42 ++++++++++++++++++++++++++++++++++----
 2 files changed, 40 insertions(+), 4 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fab42cfbd350..3f7f89ea5e51 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -606,6 +606,7 @@ struct swevent_hlist {
 #define PERF_ATTACH_TASK	0x04
 #define PERF_ATTACH_TASK_DATA	0x08
 #define PERF_ATTACH_ITRACE	0x10
+#define PERF_ATTACH_SCHED_CB	0x20
 
 struct perf_cgroup;
 struct perf_buffer;
@@ -872,6 +873,7 @@ struct perf_cpu_context {
 	struct list_head		cgrp_cpuctx_entry;
 #endif
 
+	struct list_head		sched_cb_entry;
 	int				sched_cb_usage;
 
 	int				online;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0aeca5f3c0ac..03db40f6cba9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -386,6 +386,7 @@ static DEFINE_MUTEX(perf_sched_mutex);
 static atomic_t perf_sched_count;
 
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
@@ -3461,11 +3462,16 @@ unlock:
 	}
 }
 
+static DEFINE_PER_CPU(struct list_head, sched_cb_list);
+
 void perf_sched_cb_dec(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	--cpuctx->sched_cb_usage;
+	this_cpu_dec(perf_sched_cb_usages);
+
+	if (!--cpuctx->sched_cb_usage)
+		list_del(&cpuctx->sched_cb_entry);
 }
 
 
@@ -3473,7 +3479,10 @@ void perf_sched_cb_inc(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	cpuctx->sched_cb_usage++;
+	if (!cpuctx->sched_cb_usage++)
+		list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
+
+	this_cpu_inc(perf_sched_cb_usages);
 }
 
 /*
@@ -3502,6 +3511,24 @@ static void __perf_pmu_sched_task(struct perf_cpu_context *cpuctx, bool sched_in
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
+static void perf_pmu_sched_task(struct task_struct *prev,
+				struct task_struct *next,
+				bool sched_in)
+{
+	struct perf_cpu_context *cpuctx;
+
+	if (prev == next)
+		return;
+
+	list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) {
+		/* will be handled in perf_event_context_sched_in/out */
+		if (cpuctx->task_ctx)
+			continue;
+
+		__perf_pmu_sched_task(cpuctx, sched_in);
+	}
+}
+
 static void perf_event_switch(struct task_struct *task,
 			      struct task_struct *next_prev, bool sched_in);
 
@@ -3524,6 +3551,9 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(task, next, false);
+
 	if (atomic_read(&nr_switch_events))
 		perf_event_switch(task, next, false);
 
@@ -3832,6 +3862,9 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 
 	if (atomic_read(&nr_switch_events))
 		perf_event_switch(task, prev, true);
+
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(prev, task, true);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -4656,7 +4689,7 @@ static void unaccount_event(struct perf_event *event)
 	if (event->parent)
 		return;
 
-	if (event->attach_state & PERF_ATTACH_TASK)
+	if (event->attach_state & (PERF_ATTACH_TASK | PERF_ATTACH_SCHED_CB))
 		dec = true;
 	if (event->attr.mmap || event->attr.mmap_data)
 		atomic_dec(&nr_mmap_events);
@@ -11175,7 +11208,7 @@ static void account_event(struct perf_event *event)
 	if (event->parent)
 		return;
 
-	if (event->attach_state & PERF_ATTACH_TASK)
+	if (event->attach_state & (PERF_ATTACH_TASK | PERF_ATTACH_SCHED_CB))
 		inc = true;
 	if (event->attr.mmap || event->attr.mmap_data)
 		atomic_inc(&nr_mmap_events);
@@ -12972,6 +13005,7 @@ static void __init perf_event_init_all_cpus(void)
 #ifdef CONFIG_CGROUP_PERF
 		INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu));
 #endif
+		INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
 	}
 }
 

From afbef30149587ad46f4780b1e0cc5e219745ce90 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Mon, 30 Nov 2020 11:38:41 -0800
Subject: [PATCH 0226/1820] perf/x86/intel: Set PERF_ATTACH_SCHED_CB for large
 PEBS and LBR

To supply a PID/TID for large PEBS, it requires flushing the PEBS buffer
in a context switch.

For normal LBRs, a context switch can flip the address space and LBR
entries are not tagged with an identifier, we need to wipe the LBR, even
for per-cpu events.

For LBR callstack, save/restore the stack is required during a context
switch.

Set PERF_ATTACH_SCHED_CB for the event with large PEBS & LBR.

Fixes: 9c964efa4330 ("perf/x86/intel: Drain the PEBS buffer during context switches")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20201130193842.10569-2-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 5bac48d5c18e..7bbb5bb98d8c 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3662,8 +3662,10 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
-			      ~intel_pmu_large_pebs_flags(event)))
+			      ~intel_pmu_large_pebs_flags(event))) {
 				event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
+				event->attach_state |= PERF_ATTACH_SCHED_CB;
+			}
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
@@ -3676,6 +3678,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		ret = intel_pmu_setup_lbr_filter(event);
 		if (ret)
 			return ret;
+		event->attach_state |= PERF_ATTACH_SCHED_CB;
 
 		/*
 		 * BTS is set up earlier in this path, so don't account twice

From e504e74cc3a2c092b05577ce3e8e013fae7d94e6 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Fri, 5 Feb 2021 08:24:02 -0600
Subject: [PATCH 0227/1820] x86/unwind/orc: Disable KASAN checking in the ORC
 unwinder, part 2

KASAN reserves "redzone" areas between stack frames in order to detect
stack overruns.  A read or write to such an area triggers a KASAN
"stack-out-of-bounds" BUG.

Normally, the ORC unwinder stays in-bounds and doesn't access the
redzone.  But sometimes it can't find ORC metadata for a given
instruction.  This can happen for code which is missing ORC metadata, or
for generated code.  In such cases, the unwinder attempts to fall back
to frame pointers, as a best-effort type thing.

This fallback often works, but when it doesn't, the unwinder can get
confused and go off into the weeds into the KASAN redzone, triggering
the aforementioned KASAN BUG.

But in this case, the unwinder's confusion is actually harmless and
working as designed.  It already has checks in place to prevent
off-stack accesses, but those checks get short-circuited by the KASAN
BUG.  And a BUG is a lot more disruptive than a harmless unwinder
warning.

Disable the KASAN checks by using READ_ONCE_NOCHECK() for all stack
accesses.  This finishes the job started by commit 881125bfe65b
("x86/unwind: Disable KASAN checking in the ORC unwinder"), which only
partially fixed the issue.

Fixes: ee9f8fce9964 ("x86/unwind: Add the ORC unwinder")
Reported-by: Ivan Babrou <ivan@cloudflare.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Tested-by: Ivan Babrou <ivan@cloudflare.com>
Cc: stable@kernel.org
Link: https://lkml.kernel.org/r/9583327904ebbbeda399eca9c56d6c7085ac20fe.1612534649.git.jpoimboe@redhat.com
---
 arch/x86/kernel/unwind_orc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 2a1d47f47eee..1bcc14c870ab 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -367,8 +367,8 @@ static bool deref_stack_regs(struct unwind_state *state, unsigned long addr,
 	if (!stack_access_ok(state, addr, sizeof(struct pt_regs)))
 		return false;
 
-	*ip = regs->ip;
-	*sp = regs->sp;
+	*ip = READ_ONCE_NOCHECK(regs->ip);
+	*sp = READ_ONCE_NOCHECK(regs->sp);
 	return true;
 }
 
@@ -380,8 +380,8 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr
 	if (!stack_access_ok(state, addr, IRET_FRAME_SIZE))
 		return false;
 
-	*ip = regs->ip;
-	*sp = regs->sp;
+	*ip = READ_ONCE_NOCHECK(regs->ip);
+	*sp = READ_ONCE_NOCHECK(regs->sp);
 	return true;
 }
 
@@ -402,12 +402,12 @@ static bool get_reg(struct unwind_state *state, unsigned int reg_off,
 		return false;
 
 	if (state->full_regs) {
-		*val = ((unsigned long *)state->regs)[reg];
+		*val = READ_ONCE_NOCHECK(((unsigned long *)state->regs)[reg]);
 		return true;
 	}
 
 	if (state->prev_regs) {
-		*val = ((unsigned long *)state->prev_regs)[reg];
+		*val = READ_ONCE_NOCHECK(((unsigned long *)state->prev_regs)[reg]);
 		return true;
 	}
 

From b59cc97674c947861783ca92b9a6e7d043adba96 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Fri, 5 Feb 2021 08:24:03 -0600
Subject: [PATCH 0228/1820] x86/unwind/orc: Silence warnings caused by missing
 ORC data

The ORC unwinder attempts to fall back to frame pointers when ORC data
is missing for a given instruction.  It sets state->error, but then
tries to keep going as a best-effort type of thing.  That may result in
further warnings if the unwinder gets lost.

Until we have some way to register generated code with the unwinder,
missing ORC will be expected, and occasionally going off the rails will
also be expected.  So don't warn about it.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Ivan Babrou <ivan@cloudflare.com>
Link: https://lkml.kernel.org/r/06d02c4bbb220bd31668db579278b0352538efbb.1612534649.git.jpoimboe@redhat.com
---
 arch/x86/kernel/unwind_orc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 1bcc14c870ab..a1202536fc57 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -13,7 +13,7 @@
 
 #define orc_warn_current(args...)					\
 ({									\
-	if (state->task == current)					\
+	if (state->task == current && !state->error)			\
 		orc_warn(args);						\
 })
 

From 5d5675df792ff67e74a500c4c94db0f99e6a10ef Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Thu, 4 Mar 2021 11:05:54 -0800
Subject: [PATCH 0229/1820] x86/entry: Fix entry/exit mismatch on failed fast
 32-bit syscalls

On a 32-bit fast syscall that fails to read its arguments from user
memory, the kernel currently does syscall exit work but not
syscall entry work.  This confuses audit and ptrace.  For example:

    $ ./tools/testing/selftests/x86/syscall_arg_fault_32
    ...
    strace: pid 264258: entering, ptrace_syscall_info.op == 2
    ...

This is a minimal fix intended for ease of backporting.  A more
complete cleanup is coming.

Fixes: 0b085e68f407 ("x86/entry: Consolidate 32/64 bit syscall entry")
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/8c82296ddf803b91f8d1e5eac89e5803ba54ab0e.1614884673.git.luto@kernel.org
---
 arch/x86/entry/common.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index a2433ae8a65e..4efd39aacb9f 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -128,7 +128,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 		regs->ax = -EFAULT;
 
 		instrumentation_end();
-		syscall_exit_to_user_mode(regs);
+		local_irq_disable();
+		irqentry_exit_to_user_mode(regs);
 		return false;
 	}
 

From a65a802aadba072ca7514fc0c301fd7fdc6fc6cb Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 5 Mar 2021 09:41:22 +0100
Subject: [PATCH 0230/1820] m68k: Fix virt_addr_valid() W=1 compiler warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If CONFIG_DEBUG_SG=y, and CONFIG_MMU=y:

    include/linux/scatterlist.h: In function ‘sg_set_buf’:
    arch/m68k/include/asm/page_mm.h:174:49: warning: ordered comparison of pointer with null pointer [-Wextra]
      174 | #define virt_addr_valid(kaddr) ((void *)(kaddr) >= (void *)PAGE_OFFSET && (void *)(kaddr) < high_memory)
	  |                                                 ^~

or CONFIG_MMU=n:

    include/linux/scatterlist.h: In function ‘sg_set_buf’:
    arch/m68k/include/asm/page_no.h:33:50: warning: ordered comparison of pointer with null pointer [-Wextra]
       33 | #define virt_addr_valid(kaddr) (((void *)(kaddr) >= (void *)PAGE_OFFSET) && \
	  |                                                  ^~

Fix this by doing the comparison in the "unsigned long" instead of the
"void *" domain.

Note that for now this is only seen when compiling btrfs, due to commit
e9aa7c285d20a69c ("btrfs: enable W=1 checks for btrfs"), but as people
are doing more W=1 compile testing, it will start to show up elsewhere,
too.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
Link: https://lore.kernel.org/r/20210305084122.4118826-1-geert@linux-m68k.org
---
 arch/m68k/include/asm/page_mm.h | 2 +-
 arch/m68k/include/asm/page_no.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/m68k/include/asm/page_mm.h b/arch/m68k/include/asm/page_mm.h
index 7f5912af2a52..9e8f0cc30a2c 100644
--- a/arch/m68k/include/asm/page_mm.h
+++ b/arch/m68k/include/asm/page_mm.h
@@ -171,7 +171,7 @@ static inline __attribute_const__ int __virt_to_node_shift(void)
 #include <asm-generic/memory_model.h>
 #endif
 
-#define virt_addr_valid(kaddr)	((void *)(kaddr) >= (void *)PAGE_OFFSET && (void *)(kaddr) < high_memory)
+#define virt_addr_valid(kaddr)	((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory)
 #define pfn_valid(pfn)		virt_addr_valid(pfn_to_virt(pfn))
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h
index 6bbe52025de3..8d0f862ee9d7 100644
--- a/arch/m68k/include/asm/page_no.h
+++ b/arch/m68k/include/asm/page_no.h
@@ -30,8 +30,8 @@ extern unsigned long memory_end;
 #define page_to_pfn(page)	virt_to_pfn(page_to_virt(page))
 #define pfn_valid(pfn)	        ((pfn) < max_mapnr)
 
-#define	virt_addr_valid(kaddr)	(((void *)(kaddr) >= (void *)PAGE_OFFSET) && \
-				((void *)(kaddr) < (void *)memory_end))
+#define	virt_addr_valid(kaddr)	(((unsigned long)(kaddr) >= PAGE_OFFSET) && \
+				((unsigned long)(kaddr) < memory_end))
 
 #endif /* __ASSEMBLY__ */
 

From e4c3e133294c0a292d21073899b05ebf530169bd Mon Sep 17 00:00:00 2001
From: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Date: Tue, 2 Mar 2021 15:43:55 +0100
Subject: [PATCH 0231/1820] counter: stm32-timer-cnt: fix ceiling write max
 value

The ceiling value isn't checked before writing it into registers. The user
could write a value higher than the counter resolution (e.g. 16 or 32 bits
indicated by max_arr). This makes most significant bits to be truncated.
Fix it by checking the max_arr to report a range error [1] to the user.

[1] https://lkml.org/lkml/2021/2/12/358

Fixes: ad29937e206f ("counter: Add STM32 Timer quadrature encoder")
Signed-off-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Acked-by: William Breathitt Gray <vilhelm.gray@gmail.com>
Cc: <Stable@vger.kernel.org>
Link: https://lore.kernel.org/r/1614696235-24088-1-git-send-email-fabrice.gasnier@foss.st.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/counter/stm32-timer-cnt.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/counter/stm32-timer-cnt.c b/drivers/counter/stm32-timer-cnt.c
index cd50dc12bd02..2295be3f309a 100644
--- a/drivers/counter/stm32-timer-cnt.c
+++ b/drivers/counter/stm32-timer-cnt.c
@@ -32,6 +32,7 @@ struct stm32_timer_cnt {
 	struct regmap *regmap;
 	struct clk *clk;
 	u32 ceiling;
+	u32 max_arr;
 	bool enabled;
 	struct stm32_timer_regs bak;
 };
@@ -191,6 +192,9 @@ static ssize_t stm32_count_ceiling_write(struct counter_device *counter,
 	if (ret)
 		return ret;
 
+	if (ceiling > priv->max_arr)
+		return -ERANGE;
+
 	/* TIMx_ARR register shouldn't be buffered (ARPE=0) */
 	regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0);
 	regmap_write(priv->regmap, TIM_ARR, ceiling);
@@ -371,6 +375,7 @@ static int stm32_timer_cnt_probe(struct platform_device *pdev)
 	priv->regmap = ddata->regmap;
 	priv->clk = ddata->clk;
 	priv->ceiling = ddata->max_arr;
+	priv->max_arr = ddata->max_arr;
 
 	priv->counter.name = dev_name(dev);
 	priv->counter.parent = dev;

From b14d72ac731753708a7c1a6b3657b9312b6f0042 Mon Sep 17 00:00:00 2001
From: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Date: Wed, 3 Mar 2021 18:49:49 +0100
Subject: [PATCH 0232/1820] counter: stm32-timer-cnt: fix ceiling
 miss-alignment with reload register

Ceiling value may be miss-aligned with what's actually configured into the
ARR register. This is seen after probe as currently the ARR value is zero,
whereas ceiling value is set to the maximum. So:
- reading ceiling reports zero
- in case the counter gets enabled without any prior configuration,
  it won't count.
- in case the function gets set by the user 1st, (priv->ceiling) is used.

Fix it by getting rid of the cached "priv->ceiling" variable. Rather use
the ARR register value directly by using regmap read or write when needed.
There should be no drawback on performance as priv->ceiling isn't used in
performance critical path.
There's also no point in writing ARR while setting function (sms), so
it can be safely removed.

Fixes: ad29937e206f ("counter: Add STM32 Timer quadrature encoder")
Suggested-by: William Breathitt Gray <vilhelm.gray@gmail.com>
Signed-off-by: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
Acked-by: William Breathitt Gray <vilhelm.gray@gmail.com>
Cc: <Stable@vger.kernel.org>
Link: https://lore.kernel.org/r/1614793789-10346-1-git-send-email-fabrice.gasnier@foss.st.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/counter/stm32-timer-cnt.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/counter/stm32-timer-cnt.c b/drivers/counter/stm32-timer-cnt.c
index 2295be3f309a..75bc401fdd18 100644
--- a/drivers/counter/stm32-timer-cnt.c
+++ b/drivers/counter/stm32-timer-cnt.c
@@ -31,7 +31,6 @@ struct stm32_timer_cnt {
 	struct counter_device counter;
 	struct regmap *regmap;
 	struct clk *clk;
-	u32 ceiling;
 	u32 max_arr;
 	bool enabled;
 	struct stm32_timer_regs bak;
@@ -75,8 +74,10 @@ static int stm32_count_write(struct counter_device *counter,
 			     const unsigned long val)
 {
 	struct stm32_timer_cnt *const priv = counter->priv;
+	u32 ceiling;
 
-	if (val > priv->ceiling)
+	regmap_read(priv->regmap, TIM_ARR, &ceiling);
+	if (val > ceiling)
 		return -EINVAL;
 
 	return regmap_write(priv->regmap, TIM_CNT, val);
@@ -138,10 +139,6 @@ static int stm32_count_function_set(struct counter_device *counter,
 
 	regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, 0);
 
-	/* TIMx_ARR register shouldn't be buffered (ARPE=0) */
-	regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0);
-	regmap_write(priv->regmap, TIM_ARR, priv->ceiling);
-
 	regmap_update_bits(priv->regmap, TIM_SMCR, TIM_SMCR_SMS, sms);
 
 	/* Make sure that registers are updated */
@@ -199,7 +196,6 @@ static ssize_t stm32_count_ceiling_write(struct counter_device *counter,
 	regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0);
 	regmap_write(priv->regmap, TIM_ARR, ceiling);
 
-	priv->ceiling = ceiling;
 	return len;
 }
 
@@ -374,7 +370,6 @@ static int stm32_timer_cnt_probe(struct platform_device *pdev)
 
 	priv->regmap = ddata->regmap;
 	priv->clk = ddata->clk;
-	priv->ceiling = ddata->max_arr;
 	priv->max_arr = ddata->max_arr;
 
 	priv->counter.name = dev_name(dev);

From efc61345274d6c7a46a0570efbc916fcbe3e927b Mon Sep 17 00:00:00 2001
From: Eric Whitney <enwlinux@gmail.com>
Date: Thu, 18 Feb 2021 10:11:32 -0500
Subject: [PATCH 0233/1820] ext4: shrink race window in
 ext4_should_retry_alloc()

When generic/371 is run on kvm-xfstests using 5.10 and 5.11 kernels, it
fails at significant rates on the two test scenarios that disable
delayed allocation (ext3conv and data_journal) and force actual block
allocation for the fallocate and pwrite functions in the test.  The
failure rate on 5.10 for both ext3conv and data_journal on one test
system typically runs about 85%.  On 5.11, the failure rate on ext3conv
sometimes drops to as low as 1% while the rate on data_journal
increases to nearly 100%.

The observed failures are largely due to ext4_should_retry_alloc()
cutting off block allocation retries when s_mb_free_pending (used to
indicate that a transaction in progress will free blocks) is 0.
However, free space is usually available when this occurs during runs
of generic/371.  It appears that a thread attempting to allocate
blocks is just missing transaction commits in other threads that
increase the free cluster count and reset s_mb_free_pending while
the allocating thread isn't running.  Explicitly testing for free space
availability avoids this race.

The current code uses a post-increment operator in the conditional
expression that determines whether the retry limit has been exceeded.
This means that the conditional expression uses the value of the
retry counter before it's increased, resulting in an extra retry cycle.
The current code actually retries twice before hitting its retry limit
rather than once.

Increasing the retry limit to 3 from the current actual maximum retry
count of 2 in combination with the change described above reduces the
observed failure rate to less that 0.1% on both ext3conv and
data_journal with what should be limited impact on users sensitive to
the overhead caused by retries.

A per filesystem percpu counter exported via sysfs is added to allow
users or developers to track the number of times the retry limit is
exceeded without resorting to debugging methods.  This should provide
some insight into worst case retry behavior.

Signed-off-by: Eric Whitney <enwlinux@gmail.com>
Link: https://lore.kernel.org/r/20210218151132.19678-1-enwlinux@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/balloc.c | 38 ++++++++++++++++++++++++++------------
 fs/ext4/ext4.h   |  1 +
 fs/ext4/super.c  |  5 +++++
 fs/ext4/sysfs.c  |  7 +++++++
 4 files changed, 39 insertions(+), 12 deletions(-)

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index f45f9feebe59..74a5172c2d83 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -626,27 +626,41 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
 
 /**
  * ext4_should_retry_alloc() - check if a block allocation should be retried
- * @sb:			super block
- * @retries:		number of attemps has been made
+ * @sb:			superblock
+ * @retries:		number of retry attempts made so far
  *
- * ext4_should_retry_alloc() is called when ENOSPC is returned, and if
- * it is profitable to retry the operation, this function will wait
- * for the current or committing transaction to complete, and then
- * return TRUE.  We will only retry once.
+ * ext4_should_retry_alloc() is called when ENOSPC is returned while
+ * attempting to allocate blocks.  If there's an indication that a pending
+ * journal transaction might free some space and allow another attempt to
+ * succeed, this function will wait for the current or committing transaction
+ * to complete and then return TRUE.
  */
 int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 {
-	if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
-	    (*retries)++ > 1 ||
-	    !EXT4_SB(sb)->s_journal)
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (!sbi->s_journal)
 		return 0;
 
+	if (++(*retries) > 3) {
+		percpu_counter_inc(&sbi->s_sra_exceeded_retry_limit);
+		return 0;
+	}
+
+	/*
+	 * if there's no indication that blocks are about to be freed it's
+	 * possible we just missed a transaction commit that did so
+	 */
 	smp_mb();
-	if (EXT4_SB(sb)->s_mb_free_pending == 0)
-		return 0;
+	if (sbi->s_mb_free_pending == 0)
+		return ext4_has_free_clusters(sbi, 1, 0);
 
+	/*
+	 * it's possible we've just missed a transaction commit here,
+	 * so ignore the returned status
+	 */
 	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
-	jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+	(void) jbd2_journal_force_commit_nested(sbi->s_journal);
 	return 1;
 }
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 644fd69185d3..ea3b41579f38 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1484,6 +1484,7 @@ struct ext4_sb_info {
 	struct percpu_counter s_freeinodes_counter;
 	struct percpu_counter s_dirs_counter;
 	struct percpu_counter s_dirtyclusters_counter;
+	struct percpu_counter s_sra_exceeded_retry_limit;
 	struct blockgroup_lock *s_blockgroup_lock;
 	struct proc_dir_entry *s_proc;
 	struct kobject s_kobj;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index ad34a37278cd..a0a256859662 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1210,6 +1210,7 @@ static void ext4_put_super(struct super_block *sb)
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
 	percpu_free_rwsem(&sbi->s_writepages_rwsem);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
@@ -5011,6 +5012,9 @@ no_journal:
 	if (!err)
 		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
 					  GFP_KERNEL);
+	if (!err)
+		err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0,
+					  GFP_KERNEL);
 	if (!err)
 		err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
 
@@ -5124,6 +5128,7 @@ failed_mount6:
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
 	percpu_free_rwsem(&sbi->s_writepages_rwsem);
 failed_mount5:
 	ext4_ext_release(sb);
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 075aa3a19ff5..a3d08276d441 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -24,6 +24,7 @@ typedef enum {
 	attr_session_write_kbytes,
 	attr_lifetime_write_kbytes,
 	attr_reserved_clusters,
+	attr_sra_exceeded_retry_limit,
 	attr_inode_readahead,
 	attr_trigger_test_error,
 	attr_first_error_time,
@@ -202,6 +203,7 @@ EXT4_ATTR_FUNC(delayed_allocation_blocks, 0444);
 EXT4_ATTR_FUNC(session_write_kbytes, 0444);
 EXT4_ATTR_FUNC(lifetime_write_kbytes, 0444);
 EXT4_ATTR_FUNC(reserved_clusters, 0644);
+EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444);
 
 EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead,
 		 ext4_sb_info, s_inode_readahead_blks);
@@ -251,6 +253,7 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(session_write_kbytes),
 	ATTR_LIST(lifetime_write_kbytes),
 	ATTR_LIST(reserved_clusters),
+	ATTR_LIST(sra_exceeded_retry_limit),
 	ATTR_LIST(inode_readahead_blks),
 	ATTR_LIST(inode_goal),
 	ATTR_LIST(mb_stats),
@@ -374,6 +377,10 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
 		return snprintf(buf, PAGE_SIZE, "%llu\n",
 				(unsigned long long)
 				atomic64_read(&sbi->s_resv_clusters));
+	case attr_sra_exceeded_retry_limit:
+		return snprintf(buf, PAGE_SIZE, "%llu\n",
+				(unsigned long long)
+			percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit));
 	case attr_inode_readahead:
 	case attr_pointer_ui:
 		if (!ptr)

From 163f0ec1df33cf468509ff38cbcbb5eb0d7fac60 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 22 Feb 2021 18:16:26 +0100
Subject: [PATCH 0234/1820] ext4: add reclaim checks to xattr code

Syzbot is reporting that ext4 can enter fs reclaim from kvmalloc() while
the transaction is started like:

  fs_reclaim_acquire+0x117/0x150 mm/page_alloc.c:4340
  might_alloc include/linux/sched/mm.h:193 [inline]
  slab_pre_alloc_hook mm/slab.h:493 [inline]
  slab_alloc_node mm/slub.c:2817 [inline]
  __kmalloc_node+0x5f/0x430 mm/slub.c:4015
  kmalloc_node include/linux/slab.h:575 [inline]
  kvmalloc_node+0x61/0xf0 mm/util.c:587
  kvmalloc include/linux/mm.h:781 [inline]
  ext4_xattr_inode_cache_find fs/ext4/xattr.c:1465 [inline]
  ext4_xattr_inode_lookup_create fs/ext4/xattr.c:1508 [inline]
  ext4_xattr_set_entry+0x1ce6/0x3780 fs/ext4/xattr.c:1649
  ext4_xattr_ibody_set+0x78/0x2b0 fs/ext4/xattr.c:2224
  ext4_xattr_set_handle+0x8f4/0x13e0 fs/ext4/xattr.c:2380
  ext4_xattr_set+0x13a/0x340 fs/ext4/xattr.c:2493

This should be impossible since transaction start sets PF_MEMALLOC_NOFS.
Add some assertions to the code to catch if something isn't working as
expected early.

Link: https://lore.kernel.org/linux-ext4/000000000000563a0205bafb7970@google.com/
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20210222171626.21884-1-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/xattr.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 372208500f4e..083c95126781 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1462,6 +1462,9 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value,
 	if (!ce)
 		return NULL;
 
+	WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) &&
+		     !(current->flags & PF_MEMALLOC_NOFS));
+
 	ea_data = kvmalloc(value_len, GFP_KERNEL);
 	if (!ea_data) {
 		mb_cache_entry_put(ea_inode_cache, ce);
@@ -2327,6 +2330,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 			error = -ENOSPC;
 			goto cleanup;
 		}
+		WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS));
 	}
 
 	error = ext4_reserve_inode_write(handle, inode, &is.iloc);

From f91436d55a279f045987e8b8c1385585dca54be9 Mon Sep 17 00:00:00 2001
From: Sabyrzhan Tasbolatov <snovitoll@gmail.com>
Date: Wed, 24 Feb 2021 15:58:00 +0600
Subject: [PATCH 0235/1820] fs/ext4: fix integer overflow in
 s_log_groups_per_flex

syzbot found UBSAN: shift-out-of-bounds in ext4_mb_init [1], when
1 << sbi->s_es->s_log_groups_per_flex is bigger than UINT_MAX,
where sbi->s_mb_prefetch is unsigned integer type.

32 is the maximum allowed power of s_log_groups_per_flex. Following if
check will also trigger UBSAN shift-out-of-bound:

if (1 << sbi->s_es->s_log_groups_per_flex >= UINT_MAX) {

So I'm checking it against the raw number, perhaps there is another way
to calculate UINT_MAX max power. Also use min_t as to make sure it's
uint type.

[1] UBSAN: shift-out-of-bounds in fs/ext4/mballoc.c:2713:24
shift exponent 60 is too large for 32-bit type 'int'
Call Trace:
 __dump_stack lib/dump_stack.c:79 [inline]
 dump_stack+0x137/0x1be lib/dump_stack.c:120
 ubsan_epilogue lib/ubsan.c:148 [inline]
 __ubsan_handle_shift_out_of_bounds+0x432/0x4d0 lib/ubsan.c:395
 ext4_mb_init_backend fs/ext4/mballoc.c:2713 [inline]
 ext4_mb_init+0x19bc/0x19f0 fs/ext4/mballoc.c:2898
 ext4_fill_super+0xc2ec/0xfbe0 fs/ext4/super.c:4983

Reported-by: syzbot+a8b4b0c60155e87e9484@syzkaller.appspotmail.com
Signed-off-by: Sabyrzhan Tasbolatov <snovitoll@gmail.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20210224095800.3350002-1-snovitoll@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 99bf091fee10..a02fadf4fc84 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2709,8 +2709,15 @@ static int ext4_mb_init_backend(struct super_block *sb)
 	}
 
 	if (ext4_has_feature_flex_bg(sb)) {
-		/* a single flex group is supposed to be read by a single IO */
-		sbi->s_mb_prefetch = min(1 << sbi->s_es->s_log_groups_per_flex,
+		/* a single flex group is supposed to be read by a single IO.
+		 * 2 ^ s_log_groups_per_flex != UINT_MAX as s_mb_prefetch is
+		 * unsigned integer, so the maximum shift is 32.
+		 */
+		if (sbi->s_es->s_log_groups_per_flex >= 32) {
+			ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group");
+			goto err_freesgi;
+		}
+		sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex,
 			BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9));
 		sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */
 	} else {

From c915fb80eaa6194fa9bd0a4487705cd5b0dda2f1 Mon Sep 17 00:00:00 2001
From: Zhaolong Zhang <zhangzl2013@126.com>
Date: Tue, 2 Mar 2021 17:42:31 +0800
Subject: [PATCH 0236/1820] ext4: fix bh ref count on error paths

__ext4_journalled_writepage should drop bhs' ref count on error paths

Signed-off-by: Zhaolong Zhang <zhangzl2013@126.com>
Link: https://lore.kernel.org/r/1614678151-70481-1-git-send-email-zhangzl2013@126.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 650c5acd2f2d..a79a9ea58c56 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1938,13 +1938,13 @@ static int __ext4_journalled_writepage(struct page *page,
 	if (!ret)
 		ret = err;
 
-	if (!ext4_has_inline_data(inode))
-		ext4_walk_page_buffers(NULL, page_bufs, 0, len,
-				       NULL, bput_one);
 	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 out:
 	unlock_page(page);
 out_no_pagelock:
+	if (!inline_data && page_bufs)
+		ext4_walk_page_buffers(NULL, page_bufs, 0, len,
+				       NULL, bput_one);
 	brelse(inode_bh);
 	return ret;
 }

From 37e89e574dc238a4ebe439543c5ab4fbb2f0311b Mon Sep 17 00:00:00 2001
From: Ye Xiang <xiang.ye@intel.com>
Date: Wed, 3 Mar 2021 14:36:12 +0800
Subject: [PATCH 0237/1820] iio: hid-sensor-humidity: Fix alignment issue of
 timestamp channel

This patch ensures that, there is sufficient space and correct
alignment for the timestamp.

Fixes: d7ed89d5aadf ("iio: hid: Add humidity sensor support")
Signed-off-by: Ye Xiang <xiang.ye@intel.com>
Cc: <Stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210303063615.12130-2-xiang.ye@intel.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/humidity/hid-sensor-humidity.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/humidity/hid-sensor-humidity.c b/drivers/iio/humidity/hid-sensor-humidity.c
index 52f605114ef7..d62705448ae2 100644
--- a/drivers/iio/humidity/hid-sensor-humidity.c
+++ b/drivers/iio/humidity/hid-sensor-humidity.c
@@ -15,7 +15,10 @@
 struct hid_humidity_state {
 	struct hid_sensor_common common_attributes;
 	struct hid_sensor_hub_attribute_info humidity_attr;
-	s32 humidity_data;
+	struct {
+		s32 humidity_data;
+		u64 timestamp __aligned(8);
+	} scan;
 	int scale_pre_decml;
 	int scale_post_decml;
 	int scale_precision;
@@ -125,9 +128,8 @@ static int humidity_proc_event(struct hid_sensor_hub_device *hsdev,
 	struct hid_humidity_state *humid_st = iio_priv(indio_dev);
 
 	if (atomic_read(&humid_st->common_attributes.data_ready))
-		iio_push_to_buffers_with_timestamp(indio_dev,
-					&humid_st->humidity_data,
-					iio_get_time_ns(indio_dev));
+		iio_push_to_buffers_with_timestamp(indio_dev, &humid_st->scan,
+						   iio_get_time_ns(indio_dev));
 
 	return 0;
 }
@@ -142,7 +144,7 @@ static int humidity_capture_sample(struct hid_sensor_hub_device *hsdev,
 
 	switch (usage_id) {
 	case HID_USAGE_SENSOR_ATMOSPHERIC_HUMIDITY:
-		humid_st->humidity_data = *(s32 *)raw_data;
+		humid_st->scan.humidity_data = *(s32 *)raw_data;
 
 		return 0;
 	default:

From 141e7633aa4d2838d1f6ad5c74cccc53547c16ac Mon Sep 17 00:00:00 2001
From: Ye Xiang <xiang.ye@intel.com>
Date: Wed, 3 Mar 2021 14:36:14 +0800
Subject: [PATCH 0238/1820] iio: hid-sensor-temperature: Fix issues of
 timestamp channel

This patch fixes 2 issues of timestamp channel:
1. This patch ensures that there is sufficient space and correct
alignment for the timestamp.
2. Correct the timestamp channel scan index.

Fixes: 59d0f2da3569 ("iio: hid: Add temperature sensor support")
Signed-off-by: Ye Xiang <xiang.ye@intel.com>
Cc: <Stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210303063615.12130-4-xiang.ye@intel.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/temperature/hid-sensor-temperature.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/iio/temperature/hid-sensor-temperature.c b/drivers/iio/temperature/hid-sensor-temperature.c
index 81688f1b932f..da9a247097fa 100644
--- a/drivers/iio/temperature/hid-sensor-temperature.c
+++ b/drivers/iio/temperature/hid-sensor-temperature.c
@@ -15,7 +15,10 @@
 struct temperature_state {
 	struct hid_sensor_common common_attributes;
 	struct hid_sensor_hub_attribute_info temperature_attr;
-	s32 temperature_data;
+	struct {
+		s32 temperature_data;
+		u64 timestamp __aligned(8);
+	} scan;
 	int scale_pre_decml;
 	int scale_post_decml;
 	int scale_precision;
@@ -32,7 +35,7 @@ static const struct iio_chan_spec temperature_channels[] = {
 			BIT(IIO_CHAN_INFO_SAMP_FREQ) |
 			BIT(IIO_CHAN_INFO_HYSTERESIS),
 	},
-	IIO_CHAN_SOFT_TIMESTAMP(3),
+	IIO_CHAN_SOFT_TIMESTAMP(1),
 };
 
 /* Adjust channel real bits based on report descriptor */
@@ -123,9 +126,8 @@ static int temperature_proc_event(struct hid_sensor_hub_device *hsdev,
 	struct temperature_state *temp_st = iio_priv(indio_dev);
 
 	if (atomic_read(&temp_st->common_attributes.data_ready))
-		iio_push_to_buffers_with_timestamp(indio_dev,
-				&temp_st->temperature_data,
-				iio_get_time_ns(indio_dev));
+		iio_push_to_buffers_with_timestamp(indio_dev, &temp_st->scan,
+						   iio_get_time_ns(indio_dev));
 
 	return 0;
 }
@@ -140,7 +142,7 @@ static int temperature_capture_sample(struct hid_sensor_hub_device *hsdev,
 
 	switch (usage_id) {
 	case HID_USAGE_SENSOR_DATA_ENVIRONMENTAL_TEMPERATURE:
-		temp_st->temperature_data = *(s32 *)raw_data;
+		temp_st->scan.temperature_data = *(s32 *)raw_data;
 		return 0;
 	default:
 		return -EINVAL;

From 6dbbbe4cfd398704b72b21c1d4a5d3807e909d60 Mon Sep 17 00:00:00 2001
From: Dinghao Liu <dinghao.liu@zju.edu.cn>
Date: Mon, 1 Mar 2021 16:04:21 +0800
Subject: [PATCH 0239/1820] iio: gyro: mpu3050: Fix error handling in
 mpu3050_trigger_handler

There is one regmap_bulk_read() call in mpu3050_trigger_handler
that we have caught its return value bug lack further handling.
Check and terminate the execution flow just like the other three
regmap_bulk_read() calls in this function.

Fixes: 3904b28efb2c7 ("iio: gyro: Add driver for the MPU-3050 gyroscope")
Signed-off-by: Dinghao Liu <dinghao.liu@zju.edu.cn>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20210301080421.13436-1-dinghao.liu@zju.edu.cn
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/gyro/mpu3050-core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c
index dfa31a23500f..ac90be03332a 100644
--- a/drivers/iio/gyro/mpu3050-core.c
+++ b/drivers/iio/gyro/mpu3050-core.c
@@ -551,6 +551,8 @@ static irqreturn_t mpu3050_trigger_handler(int irq, void *p)
 					       MPU3050_FIFO_R,
 					       &fifo_values[offset],
 					       toread);
+			if (ret)
+				goto out_trigger_unlock;
 
 			dev_dbg(mpu3050->dev,
 				"%04x %04x %04x %04x %04x\n",

From a249cc8bc2e2fed680047d326eb9a50756724198 Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Thu, 4 Mar 2021 17:42:21 +0000
Subject: [PATCH 0240/1820] cifs: fix credit accounting for extra channel

With multichannel, operations like the queries
from "ls -lR" can cause all credits to be used and
errors to be returned since max_credits was not
being set correctly on the secondary channels and
thus the client was requesting 0 credits incorrectly
in some cases (which can lead to not having
enough credits to perform any operation on that
channel).

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
CC: <stable@vger.kernel.org> # v5.8+
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/connect.c | 10 +++++-----
 fs/cifs/sess.c    |  1 +
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 112692300fb6..68642e3d4270 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1429,6 +1429,11 @@ smbd_connected:
 	tcp_ses->min_offload = ctx->min_offload;
 	tcp_ses->tcpStatus = CifsNeedNegotiate;
 
+	if ((ctx->max_credits < 20) || (ctx->max_credits > 60000))
+		tcp_ses->max_credits = SMB2_MAX_CREDITS_AVAILABLE;
+	else
+		tcp_ses->max_credits = ctx->max_credits;
+
 	tcp_ses->nr_targets = 1;
 	tcp_ses->ignore_signature = ctx->ignore_signature;
 	/* thread spawned, put it on the list */
@@ -2832,11 +2837,6 @@ static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cif
 
 	*nserver = server;
 
-	if ((ctx->max_credits < 20) || (ctx->max_credits > 60000))
-		server->max_credits = SMB2_MAX_CREDITS_AVAILABLE;
-	else
-		server->max_credits = ctx->max_credits;
-
 	/* get a reference to a SMB session */
 	ses = cifs_get_smb_ses(server, ctx);
 	if (IS_ERR(ses)) {
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 183a3a868d7b..63d517b9f2ff 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -230,6 +230,7 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
 	ctx.noautotune = ses->server->noautotune;
 	ctx.sockopt_tcp_nodelay = ses->server->tcp_nodelay;
 	ctx.echo_interval = ses->server->echo_interval / HZ;
+	ctx.max_credits = ses->server->max_credits;
 
 	/*
 	 * This will be used for encoding/decoding user/domain/pw

From 88fd98a2306755b965e4f4567f84e73db3b6738c Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Thu, 4 Mar 2021 17:51:48 +0000
Subject: [PATCH 0241/1820] cifs: ask for more credit on async read/write code
 paths

When doing a large read or write workload we only
very gradually increase the number of credits
which can cause problems with parallelizing large i/o
(I/O ramps up more slowly than it should for large
read/write workloads) especially with multichannel
when the number of credits on the secondary channels
starts out low (e.g. less than about 130) or when
recovering after server throttled back the number
of credit.

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/smb2pdu.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 4bbb6126b14d..2199a9bfae8f 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -4041,8 +4041,7 @@ smb2_async_readv(struct cifs_readdata *rdata)
 	if (rdata->credits.value > 0) {
 		shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes,
 						SMB2_MAX_BUFFER_SIZE));
-		shdr->CreditRequest =
-			cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 1);
+		shdr->CreditRequest = cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 8);
 
 		rc = adjust_credits(server, &rdata->credits, rdata->bytes);
 		if (rc)
@@ -4348,8 +4347,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	if (wdata->credits.value > 0) {
 		shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes,
 						    SMB2_MAX_BUFFER_SIZE));
-		shdr->CreditRequest =
-			cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 1);
+		shdr->CreditRequest = cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 8);
 
 		rc = adjust_credits(server, &wdata->credits, wdata->bytes);
 		if (rc)

From 886d0137f104a440d9dfa1d16efc1db06c9a2c02 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 5 Mar 2021 12:59:30 -0700
Subject: [PATCH 0242/1820] io-wq: fix race in freeing 'wq' and worker access

Ran into a use-after-free on the main io-wq struct, wq. It has a worker
ref and completion event, but the manager itself isn't holding a
reference. This can lead to a race where the manager thinks there are
no workers and exits, but a worker is being added. That leads to the
following trace:

BUG: KASAN: use-after-free in io_wqe_worker+0x4c0/0x5e0
Read of size 8 at addr ffff888108baa8a0 by task iou-wrk-3080422/3080425

CPU: 5 PID: 3080425 Comm: iou-wrk-3080422 Not tainted 5.12.0-rc1+ #110
Hardware name: Micro-Star International Co., Ltd. MS-7C60/TRX40 PRO 10G (MS-7C60), BIOS 1.60 05/13/2020
Call Trace:
 dump_stack+0x90/0xbe
 print_address_description.constprop.0+0x67/0x28d
 ? io_wqe_worker+0x4c0/0x5e0
 kasan_report.cold+0x7b/0xd4
 ? io_wqe_worker+0x4c0/0x5e0
 __asan_load8+0x6d/0xa0
 io_wqe_worker+0x4c0/0x5e0
 ? io_worker_handle_work+0xc00/0xc00
 ? recalc_sigpending+0xe5/0x120
 ? io_worker_handle_work+0xc00/0xc00
 ? io_worker_handle_work+0xc00/0xc00
 ret_from_fork+0x1f/0x30

Allocated by task 3080422:
 kasan_save_stack+0x23/0x60
 __kasan_kmalloc+0x80/0xa0
 kmem_cache_alloc_node_trace+0xa0/0x480
 io_wq_create+0x3b5/0x600
 io_uring_alloc_task_context+0x13c/0x380
 io_uring_add_task_file+0x109/0x140
 __x64_sys_io_uring_enter+0x45f/0x660
 do_syscall_64+0x32/0x80
 entry_SYSCALL_64_after_hwframe+0x44/0xae

Freed by task 3080422:
 kasan_save_stack+0x23/0x60
 kasan_set_track+0x20/0x40
 kasan_set_free_info+0x24/0x40
 __kasan_slab_free+0xe8/0x120
 kfree+0xa8/0x400
 io_wq_put+0x14a/0x220
 io_wq_put_and_exit+0x9a/0xc0
 io_uring_clean_tctx+0x101/0x140
 __io_uring_files_cancel+0x36e/0x3c0
 do_exit+0x169/0x1340
 __x64_sys_exit+0x34/0x40
 do_syscall_64+0x32/0x80
 entry_SYSCALL_64_after_hwframe+0x44/0xae

Have the manager itself hold a reference, and now both drop points drop
and complete if we hit zero, and the manager can unconditionally do a
wait_for_completion() instead of having a race between reading the ref
count and waiting if it was non-zero.

Fixes: fb3a1f6c745c ("io-wq: have manager wait for all workers to exit")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 28868eb4cd09..1bfdb86336e4 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -722,9 +722,9 @@ static int io_wq_manager(void *data)
 		io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL);
 	rcu_read_unlock();
 
-	/* we might not ever have created any workers */
-	if (atomic_read(&wq->worker_refs))
-		wait_for_completion(&wq->worker_done);
+	if (atomic_dec_and_test(&wq->worker_refs))
+		complete(&wq->worker_done);
+	wait_for_completion(&wq->worker_done);
 
 	spin_lock_irq(&wq->hash->wait.lock);
 	for_each_node(node)
@@ -774,7 +774,8 @@ static int io_wq_fork_manager(struct io_wq *wq)
 	if (wq->manager)
 		return 0;
 
-	reinit_completion(&wq->worker_done);
+	init_completion(&wq->worker_done);
+	atomic_set(&wq->worker_refs, 1);
 	tsk = create_io_thread(io_wq_manager, wq, NUMA_NO_NODE);
 	if (!IS_ERR(tsk)) {
 		wq->manager = get_task_struct(tsk);
@@ -782,6 +783,9 @@ static int io_wq_fork_manager(struct io_wq *wq)
 		return 0;
 	}
 
+	if (atomic_dec_and_test(&wq->worker_refs))
+		complete(&wq->worker_done);
+
 	return PTR_ERR(tsk);
 }
 
@@ -1018,13 +1022,9 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 	init_completion(&wq->exited);
 	refcount_set(&wq->refs, 1);
 
-	init_completion(&wq->worker_done);
-	atomic_set(&wq->worker_refs, 0);
-
 	ret = io_wq_fork_manager(wq);
 	if (!ret)
 		return wq;
-
 err:
 	io_wq_put_hash(data->hash);
 	cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node);

From 003e8dccdb22712dae388e682182d5f08b32386f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 6 Mar 2021 09:22:27 -0700
Subject: [PATCH 0243/1820] io-wq: always track creds for async issue

If we go async with a request, grab the creds that the task currently has
assigned and make sure that the async side switches to them. This is
handled in the same way that we do for registered personalities.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.h    |  2 +-
 fs/io_uring.c | 33 +++++++++++++++++++--------------
 2 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/fs/io-wq.h b/fs/io-wq.h
index 5fbf7997149e..1ac2f3248088 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -79,8 +79,8 @@ static inline void wq_list_del(struct io_wq_work_list *list,
 
 struct io_wq_work {
 	struct io_wq_work_node list;
+	const struct cred *creds;
 	unsigned flags;
-	unsigned short personality;
 };
 
 static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 92c25b5f1349..d51c6ba9268b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1183,6 +1183,9 @@ static void io_prep_async_work(struct io_kiocb *req)
 	const struct io_op_def *def = &io_op_defs[req->opcode];
 	struct io_ring_ctx *ctx = req->ctx;
 
+	if (!req->work.creds)
+		req->work.creds = get_current_cred();
+
 	if (req->flags & REQ_F_FORCE_ASYNC)
 		req->work.flags |= IO_WQ_WORK_CONCURRENT;
 
@@ -1648,6 +1651,10 @@ static void io_dismantle_req(struct io_kiocb *req)
 		io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE));
 	if (req->fixed_rsrc_refs)
 		percpu_ref_put(req->fixed_rsrc_refs);
+	if (req->work.creds) {
+		put_cred(req->work.creds);
+		req->work.creds = NULL;
+	}
 
 	if (req->flags & REQ_F_INFLIGHT) {
 		struct io_ring_ctx *ctx = req->ctx;
@@ -5916,18 +5923,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	const struct cred *creds = NULL;
 	int ret;
 
-	if (req->work.personality) {
-		const struct cred *new_creds;
-
-		if (!(issue_flags & IO_URING_F_NONBLOCK))
-			mutex_lock(&ctx->uring_lock);
-		new_creds = idr_find(&ctx->personality_idr, req->work.personality);
-		if (!(issue_flags & IO_URING_F_NONBLOCK))
-			mutex_unlock(&ctx->uring_lock);
-		if (!new_creds)
-			return -EINVAL;
-		creds = override_creds(new_creds);
-	}
+	if (req->work.creds && req->work.creds != current_cred())
+		creds = override_creds(req->work.creds);
 
 	switch (req->opcode) {
 	case IORING_OP_NOP:
@@ -6291,7 +6288,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 {
 	struct io_submit_state *state;
 	unsigned int sqe_flags;
-	int ret = 0;
+	int personality, ret = 0;
 
 	req->opcode = READ_ONCE(sqe->opcode);
 	/* same numerical values with corresponding REQ_F_*, safe to copy */
@@ -6324,8 +6321,16 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		return -EOPNOTSUPP;
 
 	req->work.list.next = NULL;
+	personality = READ_ONCE(sqe->personality);
+	if (personality) {
+		req->work.creds = idr_find(&ctx->personality_idr, personality);
+		if (!req->work.creds)
+			return -EINVAL;
+		get_cred(req->work.creds);
+	} else {
+		req->work.creds = NULL;
+	}
 	req->work.flags = 0;
-	req->work.personality = READ_ONCE(sqe->personality);
 	state = &ctx->submit_state;
 
 	/*

From 3ae0415d0bb401abad1db7468105e3d3756e153f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 23 Feb 2021 09:16:45 -0300
Subject: [PATCH 0244/1820] tools headers UAPI: Update tools's copy of drm.h
 headers

Picking the changes from:

  0e0dc448005583a6 ("drm/doc: demote old doc-comments in drm.h")

Silencing these perf build warnings:

  Warning: Kernel ABI header at 'tools/include/uapi/drm/drm.h' differs from latest version at 'include/uapi/drm/drm.h'
  diff -u tools/include/uapi/drm/drm.h include/uapi/drm/drm.h

No changes in tooling as these are just C comment documentation changes.

Cc: Simon Ser <contact@emersion.fr>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/drm/drm.h | 97 ++++++++++++++++++------------------
 1 file changed, 49 insertions(+), 48 deletions(-)

diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 808b48a93330..0827037c5484 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -1,11 +1,10 @@
-/**
- * \file drm.h
+/*
  * Header for the Direct Rendering Manager
  *
- * \author Rickard E. (Rik) Faith <faith@valinux.com>
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
  *
- * \par Acknowledgments:
- * Dec 1999, Richard Henderson <rth@twiddle.net>, move to generic \c cmpxchg.
+ * Acknowledgments:
+ * Dec 1999, Richard Henderson <rth@twiddle.net>, move to generic cmpxchg.
  */
 
 /*
@@ -85,7 +84,7 @@ typedef unsigned int drm_context_t;
 typedef unsigned int drm_drawable_t;
 typedef unsigned int drm_magic_t;
 
-/**
+/*
  * Cliprect.
  *
  * \warning: If you change this structure, make sure you change
@@ -101,7 +100,7 @@ struct drm_clip_rect {
 	unsigned short y2;
 };
 
-/**
+/*
  * Drawable information.
  */
 struct drm_drawable_info {
@@ -109,7 +108,7 @@ struct drm_drawable_info {
 	struct drm_clip_rect *rects;
 };
 
-/**
+/*
  * Texture region,
  */
 struct drm_tex_region {
@@ -120,7 +119,7 @@ struct drm_tex_region {
 	unsigned int age;
 };
 
-/**
+/*
  * Hardware lock.
  *
  * The lock structure is a simple cache-line aligned integer.  To avoid
@@ -132,7 +131,7 @@ struct drm_hw_lock {
 	char padding[60];			/**< Pad to cache line */
 };
 
-/**
+/*
  * DRM_IOCTL_VERSION ioctl argument type.
  *
  * \sa drmGetVersion().
@@ -149,7 +148,7 @@ struct drm_version {
 	char __user *desc;	  /**< User-space buffer to hold desc */
 };
 
-/**
+/*
  * DRM_IOCTL_GET_UNIQUE ioctl argument type.
  *
  * \sa drmGetBusid() and drmSetBusId().
@@ -168,7 +167,7 @@ struct drm_block {
 	int unused;
 };
 
-/**
+/*
  * DRM_IOCTL_CONTROL ioctl argument type.
  *
  * \sa drmCtlInstHandler() and drmCtlUninstHandler().
@@ -183,7 +182,7 @@ struct drm_control {
 	int irq;
 };
 
-/**
+/*
  * Type of memory to map.
  */
 enum drm_map_type {
@@ -195,7 +194,7 @@ enum drm_map_type {
 	_DRM_CONSISTENT = 5	  /**< Consistent memory for PCI DMA */
 };
 
-/**
+/*
  * Memory mapping flags.
  */
 enum drm_map_flags {
@@ -214,7 +213,7 @@ struct drm_ctx_priv_map {
 	void *handle;		 /**< Handle of map */
 };
 
-/**
+/*
  * DRM_IOCTL_GET_MAP, DRM_IOCTL_ADD_MAP and DRM_IOCTL_RM_MAP ioctls
  * argument type.
  *
@@ -231,7 +230,7 @@ struct drm_map {
 	/*   Private data */
 };
 
-/**
+/*
  * DRM_IOCTL_GET_CLIENT ioctl argument type.
  */
 struct drm_client {
@@ -263,7 +262,7 @@ enum drm_stat_type {
 	    /* Add to the *END* of the list */
 };
 
-/**
+/*
  * DRM_IOCTL_GET_STATS ioctl argument type.
  */
 struct drm_stats {
@@ -274,7 +273,7 @@ struct drm_stats {
 	} data[15];
 };
 
-/**
+/*
  * Hardware locking flags.
  */
 enum drm_lock_flags {
@@ -289,7 +288,7 @@ enum drm_lock_flags {
 	_DRM_HALT_CUR_QUEUES = 0x20  /**< Halt all current queues */
 };
 
-/**
+/*
  * DRM_IOCTL_LOCK, DRM_IOCTL_UNLOCK and DRM_IOCTL_FINISH ioctl argument type.
  *
  * \sa drmGetLock() and drmUnlock().
@@ -299,7 +298,7 @@ struct drm_lock {
 	enum drm_lock_flags flags;
 };
 
-/**
+/*
  * DMA flags
  *
  * \warning
@@ -328,7 +327,7 @@ enum drm_dma_flags {
 	_DRM_DMA_LARGER_OK = 0x40     /**< Larger-than-requested buffers OK */
 };
 
-/**
+/*
  * DRM_IOCTL_ADD_BUFS and DRM_IOCTL_MARK_BUFS ioctl argument type.
  *
  * \sa drmAddBufs().
@@ -351,7 +350,7 @@ struct drm_buf_desc {
 				  */
 };
 
-/**
+/*
  * DRM_IOCTL_INFO_BUFS ioctl argument type.
  */
 struct drm_buf_info {
@@ -359,7 +358,7 @@ struct drm_buf_info {
 	struct drm_buf_desc __user *list;
 };
 
-/**
+/*
  * DRM_IOCTL_FREE_BUFS ioctl argument type.
  */
 struct drm_buf_free {
@@ -367,7 +366,7 @@ struct drm_buf_free {
 	int __user *list;
 };
 
-/**
+/*
  * Buffer information
  *
  * \sa drm_buf_map.
@@ -379,7 +378,7 @@ struct drm_buf_pub {
 	void __user *address;	       /**< Address of buffer */
 };
 
-/**
+/*
  * DRM_IOCTL_MAP_BUFS ioctl argument type.
  */
 struct drm_buf_map {
@@ -392,7 +391,7 @@ struct drm_buf_map {
 	struct drm_buf_pub __user *list;	/**< Buffer information */
 };
 
-/**
+/*
  * DRM_IOCTL_DMA ioctl argument type.
  *
  * Indices here refer to the offset into the buffer list in drm_buf_get.
@@ -417,7 +416,7 @@ enum drm_ctx_flags {
 	_DRM_CONTEXT_2DONLY = 0x02
 };
 
-/**
+/*
  * DRM_IOCTL_ADD_CTX ioctl argument type.
  *
  * \sa drmCreateContext() and drmDestroyContext().
@@ -427,7 +426,7 @@ struct drm_ctx {
 	enum drm_ctx_flags flags;
 };
 
-/**
+/*
  * DRM_IOCTL_RES_CTX ioctl argument type.
  */
 struct drm_ctx_res {
@@ -435,14 +434,14 @@ struct drm_ctx_res {
 	struct drm_ctx __user *contexts;
 };
 
-/**
+/*
  * DRM_IOCTL_ADD_DRAW and DRM_IOCTL_RM_DRAW ioctl argument type.
  */
 struct drm_draw {
 	drm_drawable_t handle;
 };
 
-/**
+/*
  * DRM_IOCTL_UPDATE_DRAW ioctl argument type.
  */
 typedef enum {
@@ -456,14 +455,14 @@ struct drm_update_draw {
 	unsigned long long data;
 };
 
-/**
+/*
  * DRM_IOCTL_GET_MAGIC and DRM_IOCTL_AUTH_MAGIC ioctl argument type.
  */
 struct drm_auth {
 	drm_magic_t magic;
 };
 
-/**
+/*
  * DRM_IOCTL_IRQ_BUSID ioctl argument type.
  *
  * \sa drmGetInterruptFromBusID().
@@ -505,7 +504,7 @@ struct drm_wait_vblank_reply {
 	long tval_usec;
 };
 
-/**
+/*
  * DRM_IOCTL_WAIT_VBLANK ioctl argument type.
  *
  * \sa drmWaitVBlank().
@@ -518,7 +517,7 @@ union drm_wait_vblank {
 #define _DRM_PRE_MODESET 1
 #define _DRM_POST_MODESET 2
 
-/**
+/*
  * DRM_IOCTL_MODESET_CTL ioctl argument type
  *
  * \sa drmModesetCtl().
@@ -528,7 +527,7 @@ struct drm_modeset_ctl {
 	__u32 cmd;
 };
 
-/**
+/*
  * DRM_IOCTL_AGP_ENABLE ioctl argument type.
  *
  * \sa drmAgpEnable().
@@ -537,7 +536,7 @@ struct drm_agp_mode {
 	unsigned long mode;	/**< AGP mode */
 };
 
-/**
+/*
  * DRM_IOCTL_AGP_ALLOC and DRM_IOCTL_AGP_FREE ioctls argument type.
  *
  * \sa drmAgpAlloc() and drmAgpFree().
@@ -549,7 +548,7 @@ struct drm_agp_buffer {
 	unsigned long physical;	/**< Physical used by i810 */
 };
 
-/**
+/*
  * DRM_IOCTL_AGP_BIND and DRM_IOCTL_AGP_UNBIND ioctls argument type.
  *
  * \sa drmAgpBind() and drmAgpUnbind().
@@ -559,7 +558,7 @@ struct drm_agp_binding {
 	unsigned long offset;	/**< In bytes -- will round to page boundary */
 };
 
-/**
+/*
  * DRM_IOCTL_AGP_INFO ioctl argument type.
  *
  * \sa drmAgpVersionMajor(), drmAgpVersionMinor(), drmAgpGetMode(),
@@ -580,7 +579,7 @@ struct drm_agp_info {
 	unsigned short id_device;
 };
 
-/**
+/*
  * DRM_IOCTL_SG_ALLOC ioctl argument type.
  */
 struct drm_scatter_gather {
@@ -588,7 +587,7 @@ struct drm_scatter_gather {
 	unsigned long handle;	/**< Used for mapping / unmapping */
 };
 
-/**
+/*
  * DRM_IOCTL_SET_VERSION ioctl argument type.
  */
 struct drm_set_version {
@@ -598,14 +597,14 @@ struct drm_set_version {
 	int drm_dd_minor;
 };
 
-/** DRM_IOCTL_GEM_CLOSE ioctl argument type */
+/* DRM_IOCTL_GEM_CLOSE ioctl argument type */
 struct drm_gem_close {
 	/** Handle of the object to be closed. */
 	__u32 handle;
 	__u32 pad;
 };
 
-/** DRM_IOCTL_GEM_FLINK ioctl argument type */
+/* DRM_IOCTL_GEM_FLINK ioctl argument type */
 struct drm_gem_flink {
 	/** Handle for the object being named */
 	__u32 handle;
@@ -614,7 +613,7 @@ struct drm_gem_flink {
 	__u32 name;
 };
 
-/** DRM_IOCTL_GEM_OPEN ioctl argument type */
+/* DRM_IOCTL_GEM_OPEN ioctl argument type */
 struct drm_gem_open {
 	/** Name of object being opened */
 	__u32 name;
@@ -652,7 +651,7 @@ struct drm_gem_open {
 #define DRM_CAP_SYNCOBJ		0x13
 #define DRM_CAP_SYNCOBJ_TIMELINE	0x14
 
-/** DRM_IOCTL_GET_CAP ioctl argument type */
+/* DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {
 	__u64 capability;
 	__u64 value;
@@ -678,7 +677,9 @@ struct drm_get_cap {
 /**
  * DRM_CLIENT_CAP_ATOMIC
  *
- * If set to 1, the DRM core will expose atomic properties to userspace
+ * If set to 1, the DRM core will expose atomic properties to userspace. This
+ * implicitly enables &DRM_CLIENT_CAP_UNIVERSAL_PLANES and
+ * &DRM_CLIENT_CAP_ASPECT_RATIO.
  */
 #define DRM_CLIENT_CAP_ATOMIC	3
 
@@ -698,7 +699,7 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
 
-/** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
+/* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
 	__u64 value;
@@ -950,7 +951,7 @@ extern "C" {
 
 #define DRM_IOCTL_MODE_GETFB2		DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
 
-/**
+/*
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
  * Generic IOCTLS restart at 0xA0.
@@ -961,7 +962,7 @@ extern "C" {
 #define DRM_COMMAND_BASE                0x40
 #define DRM_COMMAND_END			0xA0
 
-/**
+/*
  * Header for events written back to userspace on the drm fd.  The
  * type defines the type of event, the length specifies the total
  * length of the event (including the header), and user_data is

From c2446944b3f588d6a0186f2022a2999c90e0cb63 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 23 Feb 2021 09:21:00 -0300
Subject: [PATCH 0245/1820] tools headers UAPI: Sync drm/i915_drm.h with the
 kernel sources

To pick the changes in:

  8c3b1ba0e7ea9a80 ("drm/i915/gt: Track the overall awake/busy time")
  348fb0cb0a79bce0 ("drm/i915/pmu: Deprecate I915_PMU_LAST and optimize state tracking")

That don't result in any change in tooling:

  $ tools/perf/trace/beauty/drm_ioctl.sh > before
  $ cp include/uapi/drm/i915_drm.h tools/include/uapi/drm/i915_drm.h
  $ tools/perf/trace/beauty/drm_ioctl.sh > after
  $ diff -u before after
  $

Only silences this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h'
  diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/drm/i915_drm.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index fa1f3d62f9a6..1987e2ea79a3 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -177,8 +177,9 @@ enum drm_i915_pmu_engine_sample {
 #define I915_PMU_REQUESTED_FREQUENCY	__I915_PMU_OTHER(1)
 #define I915_PMU_INTERRUPTS		__I915_PMU_OTHER(2)
 #define I915_PMU_RC6_RESIDENCY		__I915_PMU_OTHER(3)
+#define I915_PMU_SOFTWARE_GT_AWAKE_TIME	__I915_PMU_OTHER(4)
 
-#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY
+#define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY
 
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */

From 1e61463cfcd0b3e7a19ba36b8a98c64ebaac5c6e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 23 Feb 2021 09:44:37 -0300
Subject: [PATCH 0246/1820] tools headers UAPI: Sync openat2.h with the kernel
 sources

To pick the changes in:

  99668f618062816c ("fs: expose LOOKUP_CACHED through openat2() RESOLVE_CACHED")

That don't result in any change in tooling, only silences this perf
build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/openat2.h' differs from latest version at 'include/uapi/linux/openat2.h'
  diff -u tools/include/uapi/linux/openat2.h include/uapi/linux/openat2.h

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/openat2.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h
index 58b1eb711360..a5feb7604948 100644
--- a/tools/include/uapi/linux/openat2.h
+++ b/tools/include/uapi/linux/openat2.h
@@ -35,5 +35,9 @@ struct open_how {
 #define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
 					be scoped inside the dirfd
 					(similar to chroot(2)). */
+#define RESOLVE_CACHED		0x20 /* Only complete if resolution can be
+					completed through cached lookup. May
+					return -EAGAIN if that's not
+					possible. */
 
 #endif /* _UAPI_LINUX_OPENAT2_H */

From add76c0113ba6343a221f1ba1fa5edc8963db07c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 23 Feb 2021 09:48:05 -0300
Subject: [PATCH 0247/1820] perf arch powerpc: Sync powerpc syscall.tbl with
 the kernel sources

To get the changes in:

  fbcee2ebe8edbb6a ("powerpc/32: Always save non volatile GPRs at syscall entry")

That shouldn't cause any change in tooling, just silences the following
tools/perf/ build warning:

  Warning: Kernel ABI header at 'tools/perf/arch/powerpc/entry/syscalls/syscall.tbl' differs from latest version at 'arch/powerpc/kernel/syscalls/syscall.tbl'

Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/powerpc/entry/syscalls/syscall.tbl   | 20 +++++--------------
 1 file changed, 5 insertions(+), 15 deletions(-)

diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index f744eb5cba88..96b2157f0371 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -9,9 +9,7 @@
 #
 0	nospu	restart_syscall			sys_restart_syscall
 1	nospu	exit				sys_exit
-2	32	fork				ppc_fork			sys_fork
-2	64	fork				sys_fork
-2	spu	fork				sys_ni_syscall
+2	nospu	fork				sys_fork
 3	common	read				sys_read
 4	common	write				sys_write
 5	common	open				sys_open			compat_sys_open
@@ -160,9 +158,7 @@
 119	32	sigreturn			sys_sigreturn			compat_sys_sigreturn
 119	64	sigreturn			sys_ni_syscall
 119	spu	sigreturn			sys_ni_syscall
-120	32	clone				ppc_clone			sys_clone
-120	64	clone				sys_clone
-120	spu	clone				sys_ni_syscall
+120	nospu	clone				sys_clone
 121	common	setdomainname			sys_setdomainname
 122	common	uname				sys_newuname
 123	common	modify_ldt			sys_ni_syscall
@@ -244,9 +240,7 @@
 186	spu	sendfile			sys_sendfile64
 187	common	getpmsg				sys_ni_syscall
 188	common 	putpmsg				sys_ni_syscall
-189	32	vfork				ppc_vfork			sys_vfork
-189	64	vfork				sys_vfork
-189	spu	vfork				sys_ni_syscall
+189	nospu	vfork				sys_vfork
 190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
 191	common	readahead			sys_readahead			compat_sys_readahead
 192	32	mmap2				sys_mmap2			compat_sys_mmap2
@@ -322,9 +316,7 @@
 248	32	clock_nanosleep			sys_clock_nanosleep_time32
 248	64	clock_nanosleep			sys_clock_nanosleep
 248	spu	clock_nanosleep			sys_clock_nanosleep
-249	32	swapcontext			ppc_swapcontext			compat_sys_swapcontext
-249	64	swapcontext			sys_swapcontext
-249	spu	swapcontext			sys_ni_syscall
+249	nospu	swapcontext			sys_swapcontext			compat_sys_swapcontext
 250	common	tgkill				sys_tgkill
 251	32	utimes				sys_utimes_time32
 251	64	utimes				sys_utimes
@@ -522,9 +514,7 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
-435	32	clone3				ppc_clone3			sys_clone3
-435	64	clone3				sys_clone3
-435	spu	clone3				sys_ni_syscall
+435	nospu	clone3				sys_clone3
 436	common	close_range			sys_close_range
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd

From 303550a44741de7e853d1c0f1d252a8719a88cb1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 23 Feb 2021 09:51:17 -0300
Subject: [PATCH 0248/1820] tools headers UAPI s390: Sync ptrace.h kernel
 headers

To pick up the changes from:

  56e62a7370283601 ("s390: convert to generic entry")

That only adds two new defines, so shouldn't cause problems when
building the BPF selftests.

Silencing this perf build warning:

  Warning: Kernel ABI header at 'tools/arch/s390/include/uapi/asm/ptrace.h' differs from latest version at 'arch/s390/include/uapi/asm/ptrace.h'
  diff -u tools/arch/s390/include/uapi/asm/ptrace.h arch/s390/include/uapi/asm/ptrace.h

Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/s390/include/uapi/asm/ptrace.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/arch/s390/include/uapi/asm/ptrace.h b/tools/arch/s390/include/uapi/asm/ptrace.h
index 543dd70e12c8..ad64d673b5e6 100644
--- a/tools/arch/s390/include/uapi/asm/ptrace.h
+++ b/tools/arch/s390/include/uapi/asm/ptrace.h
@@ -179,8 +179,9 @@
 #define ACR_SIZE	4
 
 
-#define PTRACE_OLDSETOPTIONS	     21
-
+#define PTRACE_OLDSETOPTIONS		21
+#define PTRACE_SYSEMU			31
+#define PTRACE_SYSEMU_SINGLESTEP	32
 #ifndef __ASSEMBLY__
 #include <linux/stddef.h>
 #include <linux/types.h>

From 21b7e35bdf0a0e44525ec4e8a7862eb4a8df8ebe Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 23 Feb 2021 09:56:50 -0300
Subject: [PATCH 0249/1820] tools headers UAPI: Sync kvm.h headers with the
 kernel sources

To pick the changes in:

  d9a47edabc4f9481 ("KVM: PPC: Book3S HV: Introduce new capability for 2nd DAWR")
  8d4e7e80838f45d3 ("KVM: x86: declare Xen HVM shared info capability and add test case")
  40da8ccd724f7ca2 ("KVM: x86/xen: Add event channel interrupt vector upcall")

These new IOCTLs are now supported on 'perf trace':

  $ tools/perf/trace/beauty/kvm_ioctl.sh > before
  $ cp include/uapi/linux/kvm.h tools/include/uapi/linux/kvm.h
  $ tools/perf/trace/beauty/kvm_ioctl.sh > after
  $ diff -u before after
  --- before	2021-02-23 09:55:46.229058308 -0300
  +++ after	2021-02-23 09:55:57.509308058 -0300
  @@ -91,6 +91,10 @@
   	[0xc1] = "GET_SUPPORTED_HV_CPUID",
   	[0xc6] = "X86_SET_MSR_FILTER",
   	[0xc7] = "RESET_DIRTY_RINGS",
  +	[0xc8] = "XEN_HVM_GET_ATTR",
  +	[0xc9] = "XEN_HVM_SET_ATTR",
  +	[0xca] = "XEN_VCPU_GET_ATTR",
  +	[0xcb] = "XEN_VCPU_SET_ATTR",
   	[0xe0] = "CREATE_DEVICE",
   	[0xe1] = "SET_DEVICE_ATTR",
   	[0xe2] = "GET_DEVICE_ATTR",
  $

Addressing this perf build warning:
  Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h'
  diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h

Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/kvm.h | 73 ++++++++++++++++++++++++++++++++++
 1 file changed, 73 insertions(+)

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index abb89bbe5635..8b281f722e5b 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -216,6 +216,20 @@ struct kvm_hyperv_exit {
 	} u;
 };
 
+struct kvm_xen_exit {
+#define KVM_EXIT_XEN_HCALL          1
+	__u32 type;
+	union {
+		struct {
+			__u32 longmode;
+			__u32 cpl;
+			__u64 input;
+			__u64 result;
+			__u64 params[6];
+		} hcall;
+	} u;
+};
+
 #define KVM_S390_GET_SKEYS_NONE   1
 #define KVM_S390_SKEYS_MAX        1048576
 
@@ -252,6 +266,8 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_X86_WRMSR        30
 #define KVM_EXIT_DIRTY_RING_FULL  31
 #define KVM_EXIT_AP_RESET_HOLD    32
+#define KVM_EXIT_X86_BUS_LOCK     33
+#define KVM_EXIT_XEN              34
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -428,6 +444,8 @@ struct kvm_run {
 			__u32 index; /* kernel -> user */
 			__u64 data; /* kernel <-> user */
 		} msr;
+		/* KVM_EXIT_XEN */
+		struct kvm_xen_exit xen;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1058,6 +1076,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
 #define KVM_CAP_SYS_HYPERV_CPUID 191
 #define KVM_CAP_DIRTY_LOG_RING 192
+#define KVM_CAP_X86_BUS_LOCK_EXIT 193
 #define KVM_CAP_PPC_DAWR1 194
 
 #ifdef KVM_CAP_IRQ_ROUTING
@@ -1132,6 +1151,10 @@ struct kvm_x86_mce {
 #endif
 
 #ifdef KVM_CAP_XEN_HVM
+#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR	(1 << 0)
+#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL	(1 << 1)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO		(1 << 2)
+
 struct kvm_xen_hvm_config {
 	__u32 flags;
 	__u32 msr;
@@ -1566,6 +1589,45 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_DIRTY_LOG_RING */
 #define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
 
+/* Per-VM Xen attributes */
+#define KVM_XEN_HVM_GET_ATTR	_IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr)
+#define KVM_XEN_HVM_SET_ATTR	_IOW(KVMIO,  0xc9, struct kvm_xen_hvm_attr)
+
+struct kvm_xen_hvm_attr {
+	__u16 type;
+	__u16 pad[3];
+	union {
+		__u8 long_mode;
+		__u8 vector;
+		struct {
+			__u64 gfn;
+		} shared_info;
+		__u64 pad[8];
+	} u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_ATTR_TYPE_LONG_MODE		0x0
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO		0x1
+#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR		0x2
+
+/* Per-vCPU Xen attributes */
+#define KVM_XEN_VCPU_GET_ATTR	_IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
+#define KVM_XEN_VCPU_SET_ATTR	_IOW(KVMIO,  0xcb, struct kvm_xen_vcpu_attr)
+
+struct kvm_xen_vcpu_attr {
+	__u16 type;
+	__u16 pad[3];
+	union {
+		__u64 gpa;
+		__u64 pad[8];
+	} u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO	0x0
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO	0x1
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1594,6 +1656,8 @@ enum sev_cmd_id {
 	KVM_SEV_DBG_ENCRYPT,
 	/* Guest certificates commands */
 	KVM_SEV_CERT_EXPORT,
+	/* Attestation report */
+	KVM_SEV_GET_ATTESTATION_REPORT,
 
 	KVM_SEV_NR_MAX,
 };
@@ -1646,6 +1710,12 @@ struct kvm_sev_dbg {
 	__u32 len;
 };
 
+struct kvm_sev_attestation_report {
+	__u8 mnonce[16];
+	__u64 uaddr;
+	__u32 len;
+};
+
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
 #define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)
@@ -1767,4 +1837,7 @@ struct kvm_dirty_gfn {
 	__u64 offset;
 };
 
+#define KVM_BUS_LOCK_DETECTION_OFF             (1 << 0)
+#define KVM_BUS_LOCK_DETECTION_EXIT            (1 << 1)
+
 #endif /* __LINUX_KVM_H */

From ded2e511a8af9f14482b11225f73db63231fc7a4 Mon Sep 17 00:00:00 2001
From: Pierre Gondois <Pierre.Gondois@arm.com>
Date: Wed, 24 Feb 2021 18:24:10 +0000
Subject: [PATCH 0250/1820] perf tools: Cast (struct timeval).tv_sec when
 printing

The musl-libc [1] defines (struct timeval).tv_sec as a 'long long' for
arm and other architectures. The default build having a '-Wformat' flag,
not casting the field when printing prevents from building perf.

This patch casts the (struct timeval).tv_sec fields to the expected
format.

[1] git://git.musl-libc.org/musl

Signed-off-by: Pierre Gondois <Pierre.Gondois@arm.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Douglas.raillard@arm.com
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210224182410.5366-1-Pierre.Gondois@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/sched-messaging.c | 4 ++--
 tools/perf/bench/sched-pipe.c      | 4 ++--
 tools/perf/bench/syscall.c         | 4 ++--
 tools/perf/util/header.c           | 4 ++--
 tools/perf/util/stat-display.c     | 2 +-
 5 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index cecce93ccc63..488f6e6ba1a5 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -309,11 +309,11 @@ int bench_sched_messaging(int argc, const char **argv)
 		       num_groups, num_groups * 2 * num_fds,
 		       thread_mode ? "threads" : "processes");
 		printf(" %14s: %lu.%03lu [sec]\n", "Total time",
-		       diff.tv_sec,
+		       (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 		break;
 	case BENCH_FORMAT_SIMPLE:
-		printf("%lu.%03lu\n", diff.tv_sec,
+		printf("%lu.%03lu\n", (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 		break;
 	default:
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 3c88d1f201f1..a960e7a93aec 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -156,7 +156,7 @@ int bench_sched_pipe(int argc, const char **argv)
 		result_usec += diff.tv_usec;
 
 		printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
-		       diff.tv_sec,
+		       (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 
 		printf(" %14lf usecs/op\n",
@@ -168,7 +168,7 @@ int bench_sched_pipe(int argc, const char **argv)
 
 	case BENCH_FORMAT_SIMPLE:
 		printf("%lu.%03lu\n",
-		       diff.tv_sec,
+		       (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 		break;
 
diff --git a/tools/perf/bench/syscall.c b/tools/perf/bench/syscall.c
index 5fe621cff8e9..9b751016f4b6 100644
--- a/tools/perf/bench/syscall.c
+++ b/tools/perf/bench/syscall.c
@@ -54,7 +54,7 @@ int bench_syscall_basic(int argc, const char **argv)
 		result_usec += diff.tv_usec;
 
 		printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
-		       diff.tv_sec,
+		       (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec/1000));
 
 		printf(" %14lf usecs/op\n",
@@ -66,7 +66,7 @@ int bench_syscall_basic(int argc, const char **argv)
 
 	case BENCH_FORMAT_SIMPLE:
 		printf("%lu.%03lu\n",
-		       diff.tv_sec,
+		       (unsigned long) diff.tv_sec,
 		       (unsigned long) (diff.tv_usec / 1000));
 		break;
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 4fe9e2a54346..20effdff76ce 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1618,8 +1618,8 @@ static void print_clock_data(struct feat_fd *ff, FILE *fp)
 
 	fprintf(fp, "# clockid: %s (%u)\n", clockid_name(clockid), clockid);
 	fprintf(fp, "# reference time: %s = %ld.%06d (TOD) = %ld.%09ld (%s)\n",
-		    tstr, tod_ns.tv_sec, (int) tod_ns.tv_usec,
-		    clockid_ns.tv_sec, clockid_ns.tv_nsec,
+		    tstr, (long) tod_ns.tv_sec, (int) tod_ns.tv_usec,
+		    (long) clockid_ns.tv_sec, clockid_ns.tv_nsec,
 		    clockid_name(clockid));
 }
 
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index cce7a76d6473..7f09cdaf5b60 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -983,7 +983,7 @@ static void print_interval(struct perf_stat_config *config,
 	if (config->interval_clear)
 		puts(CONSOLE_CLEAR);
 
-	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
+	sprintf(prefix, "%6lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep);
 
 	if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
 		switch (config->aggr_mode) {

From 762323eb39a257c3b9875172d5ee134bd448692c Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 24 Feb 2021 16:08:31 +0100
Subject: [PATCH 0251/1820] perf build: Move feature cleanup under tools/build

Arnaldo reported issue for following build command:

  $ rm -rf /tmp/krava; mkdir /tmp/krava; make O=/tmp/krava clean
    CLEAN    config
  /bin/sh: line 0: cd: /tmp/krava/feature/: No such file or directory
  ../../scripts/Makefile.include:17: *** output directory "/tmp/krava/feature/" does not exist.  Stop.
  make[1]: *** [Makefile.perf:1010: config-clean] Error 2
  make: *** [Makefile:90: clean] Error 2

The problem is that now that we include scripts/Makefile.include
in feature's Makefile (which is fine and needed), we need to ensure
the OUTPUT directory exists, before executing (out of tree) clean
command.

Removing the feature's cleanup from perf Makefile and fixing
feature's cleanup under build Makefile, so it now checks that
there's existing OUTPUT directory before calling the clean.

Fixes: 211a741cd3e1 ("tools: Factor Clang, LLC and LLVM utils definitions")
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com> # LLVM/Clang v13-git
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210224150831.409639-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Makefile     |  8 +++++++-
 tools/perf/Makefile.perf | 10 +---------
 2 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/tools/build/Makefile b/tools/build/Makefile
index bae48e6fa995..5ed41b96fcde 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -30,12 +30,18 @@ build     := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
 all: $(OUTPUT)fixdep
 
+# Make sure there's anything to clean,
+# feature contains check for existing OUTPUT
+TMP_O := $(if $(OUTPUT),$(OUTPUT)/feature,./)
+
 clean:
 	$(call QUIET_CLEAN, fixdep)
 	$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)rm -f $(OUTPUT)fixdep
 	$(call QUIET_CLEAN, feature-detect)
-	$(Q)$(MAKE) -C feature/ clean >/dev/null
+ifneq ($(wildcard $(TMP_O)),)
+	$(Q)$(MAKE) -C feature OUTPUT=$(TMP_O) clean >/dev/null
+endif
 
 $(OUTPUT)fixdep-in.o: FORCE
 	$(Q)$(MAKE) $(build)=fixdep
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5345ac70cd83..536f6f90af92 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1001,14 +1001,6 @@ $(INSTALL_DOC_TARGETS):
 
 ### Cleaning rules
 
-#
-# This is here, not in Makefile.config, because Makefile.config does
-# not get included for the clean target:
-#
-config-clean:
-	$(call QUIET_CLEAN, config)
-	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
-
 python-clean:
 	$(python-clean)
 
@@ -1048,7 +1040,7 @@ endif # BUILD_BPF_SKEL
 bpf-skel-clean:
 	$(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS)
 
-clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean config-clean fixdep-clean python-clean bpf-skel-clean
+clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean fixdep-clean python-clean bpf-skel-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
 	$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) $(OUTPUT).config-detected

From 2b1919ec8338fad3e950f264c0c81f8b17eb6c7e Mon Sep 17 00:00:00 2001
From: Andreas Wendleder <andreas.wendleder@gmail.com>
Date: Mon, 1 Mar 2021 19:56:42 +0100
Subject: [PATCH 0252/1820] perf tools: Clean 'generated' directory used for
 creating the syscall table on x86

Remove generated directory tools/perf/arch/x86/include/generated.

Signed-off-by: Andreas Wendleder <andreas.wendleder@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210301185642.163396-1-gonsolo@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/Makefile | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 8cc6642fce7a..5a9f9a7bf07d 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -10,10 +10,11 @@ PERF_HAVE_JITDUMP := 1
 # Syscall table generation
 #
 
-out    := $(OUTPUT)arch/x86/include/generated/asm
-header := $(out)/syscalls_64.c
-sys    := $(srctree)/tools/perf/arch/x86/entry/syscalls
-systbl := $(sys)/syscalltbl.sh
+generated := $(OUTPUT)arch/x86/include/generated
+out       := $(generated)/asm
+header    := $(out)/syscalls_64.c
+sys       := $(srctree)/tools/perf/arch/x86/entry/syscalls
+systbl    := $(sys)/syscalltbl.sh
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
@@ -22,6 +23,6 @@ $(header): $(sys)/syscall_64.tbl $(systbl)
 	$(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@
 
 clean::
-	$(call QUIET_CLEAN, x86) $(RM) $(header)
+	$(call QUIET_CLEAN, x86) $(RM) -r $(header) $(generated)
 
 archheaders: $(header)

From ffc52b7ae5e6ff2b57c05fa8954fd4cae4efaab4 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Tue, 2 Mar 2021 02:35:33 +0000
Subject: [PATCH 0253/1820] perf diff: Don't crash on freeing errno-session on
 the error path

__cmd_diff() sets result of perf_session__new() to d->session.

In case of failure, it's errno and perf-diff may crash with:

  failed to open perf.data: Permission denied
  Failed to open perf.data
  Segmentation fault (core dumped)

From the coredump:

0  0x00005569a62b5955 in auxtrace__free (session=0xffffffffffffffff)
    at util/auxtrace.c:2681
1  0x00005569a626b37d in perf_session__delete (session=0xffffffffffffffff)
    at util/session.c:295
2  perf_session__delete (session=0xffffffffffffffff) at util/session.c:291
3  0x00005569a618008a in __cmd_diff () at builtin-diff.c:1239
4  cmd_diff (argc=<optimized out>, argv=<optimized out>) at builtin-diff.c:2011
[..]

Funny enough, it won't always crash. For me it crashes only if failed
file is second in cmd-line: the reason is that cmd_diff() check files for
branch-stacks [in check_file_brstack()] and if the first file doesn't
have brstacks, it doesn't proceed to try open other files from cmd-line.

Check d->session before calling perf_session__delete().

Another solution would be assigning to temporary variable, checking it,
but I find it easier to follow with IS_ERR() check in the same function.
After some time it's still obvious why the check is needed, and with
temp variable it's possible to make the same mistake.

Committer testing:

  $ perf record sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.001 MB perf.data (8 samples) ]
  $ perf diff
  failed to open perf.data.old: No such file or directory
  Failed to open perf.data.old
  $ perf record sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.001 MB perf.data (8 samples) ]
  $ perf diff
  # Event 'cycles:u'
  #
  # Baseline  Delta Abs  Shared Object     Symbol
  # ........  .........  ................  ..........................
  #
       0.92%    +87.66%  [unknown]         [k] 0xffffffff8825de16
      11.39%     +0.04%  ld-2.32.so        [.] __GI___tunables_init
      87.70%             ld-2.32.so        [.] _dl_check_map_versions
  $ sudo chown root:root perf.data
  [sudo] password for acme:
  $ perf diff
  failed to open perf.data: Permission denied
  Failed to open perf.data
  Segmentation fault (core dumped)
  $

After the patch:

  $ perf diff
  failed to open perf.data: Permission denied
  Failed to open perf.data
  $

Signed-off-by: Dmitry Safonov <dima@arista.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Dmitry Safonov <0x7f454c46@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: dmitry safonov <dima@arista.com>
Link: http://lore.kernel.org/lkml/20210302023533.1572231-1-dima@arista.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-diff.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 8f6c784ce629..878e04b1fab7 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1236,7 +1236,8 @@ static int __cmd_diff(void)
 
  out_delete:
 	data__for_each_file(i, d) {
-		perf_session__delete(d->session);
+		if (!IS_ERR(d->session))
+			perf_session__delete(d->session);
 		data__free(d);
 	}
 

From 394e4306b093d037bddcee7e1f0e8e6c53a558fc Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Thu, 25 Feb 2021 11:50:02 -0500
Subject: [PATCH 0254/1820] perf bench numa: Fix the condition checks for max
 number of NUMA nodes

In systems having higher node numbers available like node
255, perf numa bench will fail with SIGABORT.

  <<>>
  perf: bench/numa.c:1416: init: Assertion `!(g->p.nr_nodes > 64 || g->p.nr_nodes < 0)' failed.
  Aborted (core dumped)
  <<>>

Snippet from 'numactl -H' below on a powerpc system where the highest
node number available is 255:

  available: 6 nodes (0,8,252-255)
  node 0 cpus: <cpu-list>
  node 0 size: 519587 MB
  node 0 free: 516659 MB
  node 8 cpus: <cpu-list>
  node 8 size: 523607 MB
  node 8 free: 486757 MB
  node 252 cpus:
  node 252 size: 0 MB
  node 252 free: 0 MB
  node 253 cpus:
  node 253 size: 0 MB
  node 253 free: 0 MB
  node 254 cpus:
  node 254 size: 0 MB
  node 254 free: 0 MB
  node 255 cpus:
  node 255 size: 0 MB
  node 255 free: 0 MB
  node distances:
  node   0   8  252  253  254  255

Note: <cpu-list> expands to actual cpu list in the original output.
These nodes 252-255 are to represent the memory on GPUs and are valid
nodes.

The perf numa bench init code has a condition check to see if the number
of NUMA nodes (nr_nodes) exceeds MAX_NR_NODES. The value of MAX_NR_NODES
defined in perf code is 64. And the 'nr_nodes' is the value from
numa_max_node() which represents the highest node number available in the
system. In some systems where we could have NUMA node 255, this condition
check fails and results in SIGABORT.

The numa benchmark uses static value of MAX_NR_NODES in the code to
represent size of two NUMA node arrays and node bitmask used for setting
memory policy. Patch adds a fix to dynamically allocate size for the
two arrays and bitmask value based on the node numbers available in the
system. With the fix, perf numa benchmark will work with node configuration
on any system and thus removes the static MAX_NR_NODES value.

Signed-off-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lore.kernel.org/lkml/1614271802-1503-1-git-send-email-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/numa.c | 42 ++++++++++++++++++++++++++++-------------
 1 file changed, 29 insertions(+), 13 deletions(-)

diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 11726ec6285f..20b87e29c96f 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -344,18 +344,22 @@ static void mempol_restore(void)
 
 static void bind_to_memnode(int node)
 {
-	unsigned long nodemask;
+	struct bitmask *node_mask;
 	int ret;
 
 	if (node == NUMA_NO_NODE)
 		return;
 
-	BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask)*8);
-	nodemask = 1L << node;
+	node_mask = numa_allocate_nodemask();
+	BUG_ON(!node_mask);
 
-	ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask)*8);
-	dprintf("binding to node %d, mask: %016lx => %d\n", node, nodemask, ret);
+	numa_bitmask_clearall(node_mask);
+	numa_bitmask_setbit(node_mask, node);
 
+	ret = set_mempolicy(MPOL_BIND, node_mask->maskp, node_mask->size + 1);
+	dprintf("binding to node %d, mask: %016lx => %d\n", node, *node_mask->maskp, ret);
+
+	numa_bitmask_free(node_mask);
 	BUG_ON(ret);
 }
 
@@ -876,8 +880,6 @@ static void update_curr_cpu(int task_nr, unsigned long bytes_worked)
 	prctl(0, bytes_worked);
 }
 
-#define MAX_NR_NODES	64
-
 /*
  * Count the number of nodes a process's threads
  * are spread out on.
@@ -888,10 +890,15 @@ static void update_curr_cpu(int task_nr, unsigned long bytes_worked)
  */
 static int count_process_nodes(int process_nr)
 {
-	char node_present[MAX_NR_NODES] = { 0, };
+	char *node_present;
 	int nodes;
 	int n, t;
 
+	node_present = (char *)malloc(g->p.nr_nodes * sizeof(char));
+	BUG_ON(!node_present);
+	for (nodes = 0; nodes < g->p.nr_nodes; nodes++)
+		node_present[nodes] = 0;
+
 	for (t = 0; t < g->p.nr_threads; t++) {
 		struct thread_data *td;
 		int task_nr;
@@ -901,17 +908,20 @@ static int count_process_nodes(int process_nr)
 		td = g->threads + task_nr;
 
 		node = numa_node_of_cpu(td->curr_cpu);
-		if (node < 0) /* curr_cpu was likely still -1 */
+		if (node < 0) /* curr_cpu was likely still -1 */ {
+			free(node_present);
 			return 0;
+		}
 
 		node_present[node] = 1;
 	}
 
 	nodes = 0;
 
-	for (n = 0; n < MAX_NR_NODES; n++)
+	for (n = 0; n < g->p.nr_nodes; n++)
 		nodes += node_present[n];
 
+	free(node_present);
 	return nodes;
 }
 
@@ -980,7 +990,7 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 {
 	unsigned int loops_done_min, loops_done_max;
 	int process_groups;
-	int nodes[MAX_NR_NODES];
+	int *nodes;
 	int distance;
 	int nr_min;
 	int nr_max;
@@ -994,6 +1004,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 	if (!g->p.show_convergence && !g->p.measure_convergence)
 		return;
 
+	nodes = (int *)malloc(g->p.nr_nodes * sizeof(int));
+	BUG_ON(!nodes);
 	for (node = 0; node < g->p.nr_nodes; node++)
 		nodes[node] = 0;
 
@@ -1035,8 +1047,10 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 
 	BUG_ON(sum > g->p.nr_tasks);
 
-	if (0 && (sum < g->p.nr_tasks))
+	if (0 && (sum < g->p.nr_tasks)) {
+		free(nodes);
 		return;
+	}
 
 	/*
 	 * Count the number of distinct process groups present
@@ -1088,6 +1102,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 		}
 		tprintf("\n");
 	}
+
+	free(nodes);
 }
 
 static void show_summary(double runtime_ns_max, int l, double *convergence)
@@ -1413,7 +1429,7 @@ static int init(void)
 	g->p.nr_nodes = numa_max_node() + 1;
 
 	/* char array in count_process_nodes(): */
-	BUG_ON(g->p.nr_nodes > MAX_NR_NODES || g->p.nr_nodes < 0);
+	BUG_ON(g->p.nr_nodes < 0);
 
 	if (g->p.show_quiet && !g->p.show_details)
 		g->p.show_details = -1;

From 137a5258939aca56558f3a23eb229b9c4b293917 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 26 Feb 2021 14:14:31 -0800
Subject: [PATCH 0255/1820] perf traceevent: Ensure read cmdlines are null
 terminated.

Issue detected by address sanitizer.

Fixes: cd4ceb63438e9e28 ("perf util: Save pid-cmdline mapping into tracing header")
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20210226221431.1985458-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/trace-event-read.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index f507dff713c9..8a01af783310 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -361,6 +361,7 @@ static int read_saved_cmdline(struct tep_handle *pevent)
 		pr_debug("error reading saved cmdlines\n");
 		goto out;
 	}
+	buf[ret] = '\0';
 
 	parse_saved_cmdline(pevent, buf, size);
 	ret = 0;

From b55ff1d1456c86209ba28fd06b1b5fb0e05d92c3 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 26 Feb 2021 10:31:44 -0800
Subject: [PATCH 0256/1820] perf tools: Fix documentation of verbose options

Option doesn't take a value, make sure the man pages agree. For example:

  $ perf evlist --verbose=1
   Error: option `verbose' takes no value

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20210226183145.1878782-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-evlist.txt   | 2 +-
 tools/perf/Documentation/perf-ftrace.txt   | 4 ++--
 tools/perf/Documentation/perf-kallsyms.txt | 2 +-
 tools/perf/Documentation/perf-trace.txt    | 4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
index c0a66400a960..9af8b8dfb7b6 100644
--- a/tools/perf/Documentation/perf-evlist.txt
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -29,7 +29,7 @@ OPTIONS
 	Show just the sample frequency used for each event.
 
 -v::
---verbose=::
+--verbose::
 	Show all fields.
 
 -g::
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
index 1e91121bac0f..6e82b7cc0bf0 100644
--- a/tools/perf/Documentation/perf-ftrace.txt
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -28,8 +28,8 @@ OPTIONS
 	specified: function_graph or function.
 
 -v::
---verbose=::
-        Verbosity level.
+--verbose::
+        Increase the verbosity level.
 
 -F::
 --funcs::
diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
index f3c620951f6e..c97527df8ecd 100644
--- a/tools/perf/Documentation/perf-kallsyms.txt
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -20,5 +20,5 @@ modules).
 OPTIONS
 -------
 -v::
---verbose=::
+--verbose::
 	Increase verbosity level, showing details about symbol table loading, etc.
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index abc9b5d83312..f0da8cf63e9a 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -97,8 +97,8 @@ filter out the startup phase of the program, which is often very different.
 	Filter out events for these pids and for 'trace' itself (comma separated list).
 
 -v::
---verbose=::
-        Verbosity level.
+--verbose::
+        Increase the verbosity level.
 
 --no-inherit::
 	Child tasks do not inherit counters.

From dacfc08dcafa7d443ab339592999e37bbb8a3ef0 Mon Sep 17 00:00:00 2001
From: Antonio Terceiro <antonio.terceiro@linaro.org>
Date: Wed, 24 Feb 2021 10:00:46 -0300
Subject: [PATCH 0257/1820] perf build: Fix ccache usage in $(CC) when
 generating arch errno table

This was introduced by commit e4ffd066ff440a57 ("perf: Normalize gcc
parameter when generating arch errno table").

Assuming the first word of $(CC) is the actual compiler breaks usage
like CC="ccache gcc": the script ends up calling ccache directly with
gcc arguments, what fails. Instead of getting the first word, just
remove from $(CC) any word that starts with a "-". This maintains the
spirit of the original patch, while not breaking ccache users.

Fixes: e4ffd066ff440a57 ("perf: Normalize gcc parameter when generating arch errno table")
Signed-off-by: Antonio Terceiro <antonio.terceiro@linaro.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: He Zhe <zhe.he@windriver.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: http://lore.kernel.org/lkml/20210224130046.346977-1-antonio.terceiro@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 536f6f90af92..f6e609673de2 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -607,7 +607,7 @@ arch_errno_hdr_dir := $(srctree)/tools
 arch_errno_tbl := $(srctree)/tools/perf/trace/beauty/arch_errno_names.sh
 
 $(arch_errno_name_array): $(arch_errno_tbl)
-	$(Q)$(SHELL) '$(arch_errno_tbl)' $(firstword $(CC)) $(arch_errno_hdr_dir) > $@
+	$(Q)$(SHELL) '$(arch_errno_tbl)' '$(patsubst -%,,$(CC))' $(arch_errno_hdr_dir) > $@
 
 sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c
 sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh

From 31bf4e7cb61363b87f1606ec8efb71eebd6393cf Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 1 Mar 2021 13:25:09 +0100
Subject: [PATCH 0258/1820] perf daemon: Fix control fifo permissions

Add proper mode for mkfifo calls to get read and write permissions for
user. We can't use O_RDWR in here, changing to standard permission
value.

Fixes: 6a6d1804a190 ("perf daemon: Set control fifo for session")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210301122510.64402-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-daemon.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index 617feaf020f6..8f0ed2e59280 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -373,12 +373,12 @@ static int daemon_session__run(struct daemon_session *session,
 	dup2(fd, 2);
 	close(fd);
 
-	if (mkfifo(SESSION_CONTROL, O_RDWR) && errno != EEXIST) {
+	if (mkfifo(SESSION_CONTROL, 0600) && errno != EEXIST) {
 		perror("failed: create control fifo");
 		return -1;
 	}
 
-	if (mkfifo(SESSION_ACK, O_RDWR) && errno != EEXIST) {
+	if (mkfifo(SESSION_ACK, 0600) && errno != EEXIST) {
 		perror("failed: create ack fifo");
 		return -1;
 	}

From 36bc511f63fd21c0c44f973c6d064c1228ba15ae Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 1 Mar 2021 13:25:10 +0100
Subject: [PATCH 0259/1820] perf daemon: Fix running test for non root user

John reported that the daemon test is not working for non root user.
Changing the tests configurations so it's allowed to run under normal
user.

Fixes: 2291bb915b55 ("perf tests: Add daemon 'list' command test")
Reported-by: John Garry <john.garry@huawei.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: John Garry <john.garry@huawei.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210301122510.64402-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/daemon.sh | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh
index e5b824dd08d9..5ad3ca8d681b 100755
--- a/tools/perf/tests/shell/daemon.sh
+++ b/tools/perf/tests/shell/daemon.sh
@@ -140,10 +140,10 @@ test_list()
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 
 [session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}
@@ -159,14 +159,14 @@ EOF
 	# check 1st session
 	# pid:size:-e cpu-clock:base/size:base/size/output:base/size/control:base/size/ack:0
 	local line=`perf daemon --config ${config} -x: | head -2 | tail -1`
-	check_line_other "${line}" size "-e cpu-clock" ${base}/session-size \
+	check_line_other "${line}" size "-e cpu-clock -m 1 sleep 10" ${base}/session-size \
 			 ${base}/session-size/output ${base}/session-size/control \
 			 ${base}/session-size/ack "0"
 
 	# check 2nd session
 	# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
 	local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
-	check_line_other "${line}" time "-e task-clock" ${base}/session-time \
+	check_line_other "${line}" time "-e task-clock -m 1 sleep 10" ${base}/session-time \
 			 ${base}/session-time/output ${base}/session-time/control \
 			 ${base}/session-time/ack "0"
 
@@ -190,10 +190,10 @@ test_reconfig()
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 
 [session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}
@@ -204,7 +204,7 @@ EOF
 	# check 2nd session
 	# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
 	local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
-	check_line_other "${line}" time "-e task-clock" ${base}/session-time \
+	check_line_other "${line}" time "-e task-clock -m 1 sleep 10" ${base}/session-time \
 			 ${base}/session-time/output ${base}/session-time/control ${base}/session-time/ack "0"
 	local pid=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $1 }'`
 
@@ -215,10 +215,10 @@ EOF
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 
 [session-time]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 EOF
 
 	# TEST 1 - change config
@@ -238,7 +238,7 @@ EOF
 	# check reconfigured 2nd session
 	# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
 	local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
-	check_line_other "${line}" time "-e cpu-clock" ${base}/session-time \
+	check_line_other "${line}" time "-e cpu-clock -m 1 sleep 10" ${base}/session-time \
 			 ${base}/session-time/output ${base}/session-time/control ${base}/session-time/ack "0"
 
 	# TEST 2 - empty config
@@ -309,10 +309,10 @@ test_stop()
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 
 [session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}
@@ -361,7 +361,7 @@ test_signal()
 base=BASE
 
 [session-test]
-run = -e cpu-clock --switch-output
+run = -e cpu-clock --switch-output -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}
@@ -400,10 +400,10 @@ test_ping()
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 
 [session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}
@@ -439,7 +439,7 @@ test_lock()
 base=BASE
 
 [session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
 EOF
 
 	sed -i -e "s|BASE|${base}|" ${config}

From 84ea603650ec41273cc97d50eb01feed8e6baa2e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 1 Mar 2021 13:23:15 +0100
Subject: [PATCH 0260/1820] perf tools: Fix event's PMU name parsing

Jin Yao reported parser error for software event:

  # perf stat -e software/r1a/ -a -- sleep 1
  event syntax error: 'software/r1a/'
                       \___ parser error

This happens after commit 8c3b1ba0e7ea9a80 ("drm/i915/gt: Track the
overall awake/busy time"), where new software-gt-awake-time event's
non-pmu-event-style makes event parser conflict with software PMU.

If we allow PE_PMU_EVENT_PRE to be parsed as PMU name, we fix the
conflict and the following character '/' for PMU or '-' for
non-pmu-event-style event allows parser to decide what even is
specified.

Fixes: 8c3b1ba0e7ea9a80 ("drm/i915/gt: Track the overall awake/busy time")
Reported-by: Jin Yao <yao.jin@linux.intel.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210301122315.63471-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.y | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index d5b6aff82f21..d57ac86ce7ca 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -89,6 +89,7 @@ static void inc_group_count(struct list_head *list,
 %type <str> PE_EVENT_NAME
 %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE
 %type <str> PE_DRV_CFG_TERM
+%type <str> event_pmu_name
 %destructor { free ($$); } <str>
 %type <term> event_term
 %destructor { parse_events_term__delete ($$); } <term>
@@ -272,8 +273,11 @@ event_def: event_pmu |
 	   event_legacy_raw sep_dc |
 	   event_bpf_file
 
+event_pmu_name:
+PE_NAME | PE_PMU_EVENT_PRE
+
 event_pmu:
-PE_NAME opt_pmu_config
+event_pmu_name opt_pmu_config
 {
 	struct parse_events_state *parse_state = _parse_state;
 	struct parse_events_error *error = parse_state->error;

From b0faef924d21d0a4592ec81c4bc2b4badc35a343 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 1 Mar 2021 23:03:59 +0900
Subject: [PATCH 0261/1820] perf test: Fix cpu and thread map leaks in basic
 mmap test

The evlist has the maps with its own refcounts so we don't need to set
the pointers to NULL.  Otherwise following error was reported by Asan.

  # perf test -v 4
   4: Read samples using the mmap interface      :
  --- start ---
  test child forked, pid 139782
  mmap size 528384B

  =================================================================
  ==139782==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 40 byte(s) in 1 object(s) allocated from:
    #0 0x7f1f76daee8f in __interceptor_malloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:145
    #1 0x564ba21a0fea in cpu_map__trim_new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:79
    #2 0x564ba21a1a0f in perf_cpu_map__read /home/namhyung/project/linux/tools/lib/perf/cpumap.c:149
    #3 0x564ba21a21cf in cpu_map__read_all_cpu_map /home/namhyung/project/linux/tools/lib/perf/cpumap.c:166
    #4 0x564ba21a21cf in perf_cpu_map__new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:181
    #5 0x564ba1e48298 in test__basic_mmap tests/mmap-basic.c:55
    #6 0x564ba1e278fb in run_test tests/builtin-test.c:428
    #7 0x564ba1e278fb in test_and_print tests/builtin-test.c:458
    #8 0x564ba1e29a53 in __cmd_test tests/builtin-test.c:679
    #9 0x564ba1e29a53 in cmd_test tests/builtin-test.c:825
    #10 0x564ba1e95cb4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #11 0x564ba1d1fa88 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #12 0x564ba1d1fa88 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #13 0x564ba1d1fa88 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #14 0x7f1f768e4d09 in __libc_start_main ../csu/libc-start.c:308

    ...
  test child finished with 1
  ---- end ----
  Read samples using the mmap interface: FAILED!
  failed to open shell test directory: /home/namhyung/libexec/perf-core/tests/shell

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/r/20210301140409.184570-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/mmap-basic.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 57093aeacc6f..73ae8f7aa066 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -158,8 +158,6 @@ out_init:
 
 out_delete_evlist:
 	evlist__delete(evlist);
-	cpus	= NULL;
-	threads = NULL;
 out_free_cpus:
 	perf_cpu_map__put(cpus);
 out_free_threads:

From 09a61c8f86aee7b9c514c6906244a22ec37ef028 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 1 Mar 2021 23:04:00 +0900
Subject: [PATCH 0262/1820] perf test: Fix a memory leak in attr test

The get_argv_exec_path() returns a dynamic memory so it should be
freed after use.

  $ perf test -v 17
  ...
  ==141682==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 33 byte(s) in 1 object(s) allocated from:
    #0 0x7f09107d2e8f in __interceptor_malloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:145
    #1 0x7f091035f6a7 in __vasprintf_internal libio/vasprintf.c:71

  SUMMARY: AddressSanitizer: 33 byte(s) leaked in 1 allocation(s).

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210301140409.184570-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/attr.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index ec972e0892ab..dd39ce9b0277 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -182,14 +182,20 @@ int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused)
 	struct stat st;
 	char path_perf[PATH_MAX];
 	char path_dir[PATH_MAX];
+	char *exec_path;
 
 	/* First try development tree tests. */
 	if (!lstat("./tests", &st))
 		return run_dir("./tests", "./perf");
 
+	exec_path = get_argv_exec_path();
+	if (exec_path == NULL)
+		return -1;
+
 	/* Then installed path. */
-	snprintf(path_dir,  PATH_MAX, "%s/tests", get_argv_exec_path());
+	snprintf(path_dir,  PATH_MAX, "%s/tests", exec_path);
 	snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR);
+	free(exec_path);
 
 	if (!lstat(path_dir, &st) &&
 	    !lstat(path_perf, &st))

From 83d25ccde591fe2356ba336e994b190361158b1e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 1 Mar 2021 23:04:01 +0900
Subject: [PATCH 0263/1820] perf test: Fix cpu and thread map leaks in
 task_exit test

The evlist has the maps with its own refcounts so we don't need to set
the pointers to NULL.  Otherwise following error was reported by Asan.

Also change the goto label since it doesn't need to have two.

  # perf test -v 24
  24: Number of exit events of a simple workload :
  --- start ---
  test child forked, pid 145915
  mmap size 528384B

  =================================================================
  ==145915==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 32 byte(s) in 1 object(s) allocated from:
    #0 0x7fc44e50d1f8 in __interceptor_realloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:164
    #1 0x561cf50f4d2e in perf_thread_map__realloc /home/namhyung/project/linux/tools/lib/perf/threadmap.c:23
    #2 0x561cf4eeb949 in thread_map__new_by_tid util/thread_map.c:63
    #3 0x561cf4db7fd2 in test__task_exit tests/task-exit.c:74
    #4 0x561cf4d798fb in run_test tests/builtin-test.c:428
    #5 0x561cf4d798fb in test_and_print tests/builtin-test.c:458
    #6 0x561cf4d7ba53 in __cmd_test tests/builtin-test.c:679
    #7 0x561cf4d7ba53 in cmd_test tests/builtin-test.c:825
    #8 0x561cf4de7d04 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #9 0x561cf4c71a88 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #10 0x561cf4c71a88 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #11 0x561cf4c71a88 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #12 0x7fc44e042d09 in __libc_start_main ../csu/libc-start.c:308

    ...
  test child finished with 1
  ---- end ----
  Number of exit events of a simple workload: FAILED!

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210301140409.184570-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/task-exit.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index bbf94e4aa145..4c2969db59b0 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -75,14 +75,11 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	if (!cpus || !threads) {
 		err = -ENOMEM;
 		pr_debug("Not enough memory to create thread/cpu maps\n");
-		goto out_free_maps;
+		goto out_delete_evlist;
 	}
 
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
 
-	cpus	= NULL;
-	threads = NULL;
-
 	err = evlist__prepare_workload(evlist, &target, argv, false, workload_exec_failed_signal);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
@@ -137,7 +134,7 @@ out_init:
 		if (retry_count++ > 1000) {
 			pr_debug("Failed after retrying 1000 times\n");
 			err = -1;
-			goto out_free_maps;
+			goto out_delete_evlist;
 		}
 
 		goto retry;
@@ -148,10 +145,9 @@ out_init:
 		err = -1;
 	}
 
-out_free_maps:
+out_delete_evlist:
 	perf_cpu_map__put(cpus);
 	perf_thread_map__put(threads);
-out_delete_evlist:
 	evlist__delete(evlist);
 	return err;
 }

From 97ab7c524fdcaf3098997f81bdf9d01157816f30 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 1 Mar 2021 23:04:02 +0900
Subject: [PATCH 0264/1820] perf test: Fix cpu and thread map leaks in
 sw_clock_freq test

The evlist has the maps with its own refcounts so we don't need to set
the pointers to NULL.  Otherwise following error was reported by Asan.

Also change the goto label since it doesn't need to have two.

  # perf test -v 25
  25: Software clock events period values        :
  --- start ---
  test child forked, pid 149154
  mmap size 528384B
  mmap size 528384B

  =================================================================
  ==149154==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 32 byte(s) in 1 object(s) allocated from:
    #0 0x7fef5cd071f8 in __interceptor_realloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:164
    #1 0x56260d5e8b8e in perf_thread_map__realloc /home/namhyung/project/linux/tools/lib/perf/threadmap.c:23
    #2 0x56260d3df7a9 in thread_map__new_by_tid util/thread_map.c:63
    #3 0x56260d2ac6b2 in __test__sw_clock_freq tests/sw-clock.c:65
    #4 0x56260d26d8fb in run_test tests/builtin-test.c:428
    #5 0x56260d26d8fb in test_and_print tests/builtin-test.c:458
    #6 0x56260d26fa53 in __cmd_test tests/builtin-test.c:679
    #7 0x56260d26fa53 in cmd_test tests/builtin-test.c:825
    #8 0x56260d2dbb64 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #9 0x56260d165a88 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #10 0x56260d165a88 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #11 0x56260d165a88 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #12 0x7fef5c83cd09 in __libc_start_main ../csu/libc-start.c:308

    ...
  test child finished with 1
  ---- end ----
  Software clock events period values      : FAILED!

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210301140409.184570-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/sw-clock.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index a49c9e23053b..74988846be1d 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -42,8 +42,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		.disabled = 1,
 		.freq = 1,
 	};
-	struct perf_cpu_map *cpus;
-	struct perf_thread_map *threads;
+	struct perf_cpu_map *cpus = NULL;
+	struct perf_thread_map *threads = NULL;
 	struct mmap *md;
 
 	attr.sample_freq = 500;
@@ -66,14 +66,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	if (!cpus || !threads) {
 		err = -ENOMEM;
 		pr_debug("Not enough memory to create thread/cpu maps\n");
-		goto out_free_maps;
+		goto out_delete_evlist;
 	}
 
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
 
-	cpus	= NULL;
-	threads = NULL;
-
 	if (evlist__open(evlist)) {
 		const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate";
 
@@ -129,10 +126,9 @@ out_init:
 		err = -1;
 	}
 
-out_free_maps:
+out_delete_evlist:
 	perf_cpu_map__put(cpus);
 	perf_thread_map__put(threads);
-out_delete_evlist:
 	evlist__delete(evlist);
 	return err;
 }

From e06c3ca4922ccf24bd36c007a87f193b235cee93 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 1 Mar 2021 23:04:03 +0900
Subject: [PATCH 0265/1820] perf test: Fix cpu and thread map leaks in
 code_reading test

The evlist and the cpu/thread maps should be released together.
Otherwise following error was reported by Asan.

Note that this test still has memory leaks in DSOs so it still fails
even after this change.  I'll take a look at that too.

  # perf test -v 26
  26: Object code reading                        :
  --- start ---
  test child forked, pid 154184
  Looking at the vmlinux_path (8 entries long)
  symsrc__init: build id mismatch for vmlinux.
  symsrc__init: cannot get elf header.
  Using /proc/kcore for kernel data
  Using /proc/kallsyms for symbols
  Parsing event 'cycles'
  mmap size 528384B
  ...
  =================================================================
  ==154184==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 439 byte(s) in 1 object(s) allocated from:
    #0 0x7fcb66e77037 in __interceptor_calloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:154
    #1 0x55ad9b7e821e in dso__new_id util/dso.c:1256
    #2 0x55ad9b8cfd4a in __machine__addnew_vdso util/vdso.c:132
    #3 0x55ad9b8cfd4a in machine__findnew_vdso util/vdso.c:347
    #4 0x55ad9b845b7e in map__new util/map.c:176
    #5 0x55ad9b8415a2 in machine__process_mmap2_event util/machine.c:1787
    #6 0x55ad9b8fab16 in perf_tool__process_synth_event util/synthetic-events.c:64
    #7 0x55ad9b8fab16 in perf_event__synthesize_mmap_events util/synthetic-events.c:499
    #8 0x55ad9b8fbfdf in __event__synthesize_thread util/synthetic-events.c:741
    #9 0x55ad9b8ff3e3 in perf_event__synthesize_thread_map util/synthetic-events.c:833
    #10 0x55ad9b738585 in do_test_code_reading tests/code-reading.c:608
    #11 0x55ad9b73b25d in test__code_reading tests/code-reading.c:722
    #12 0x55ad9b6f28fb in run_test tests/builtin-test.c:428
    #13 0x55ad9b6f28fb in test_and_print tests/builtin-test.c:458
    #14 0x55ad9b6f4a53 in __cmd_test tests/builtin-test.c:679
    #15 0x55ad9b6f4a53 in cmd_test tests/builtin-test.c:825
    #16 0x55ad9b760cc4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #17 0x55ad9b5eaa88 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #18 0x55ad9b5eaa88 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #19 0x55ad9b5eaa88 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #20 0x7fcb669acd09 in __libc_start_main ../csu/libc-start.c:308

    ...
  SUMMARY: AddressSanitizer: 471 byte(s) leaked in 2 allocation(s).
  test child finished with 1
  ---- end ----
  Object code reading: FAILED!

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210301140409.184570-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/code-reading.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 280f0348a09c..2fdc7b2f996e 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -706,13 +706,9 @@ static int do_test_code_reading(bool try_kcore)
 out_put:
 	thread__put(thread);
 out_err:
-
-	if (evlist) {
-		evlist__delete(evlist);
-	} else {
-		perf_cpu_map__put(cpus);
-		perf_thread_map__put(threads);
-	}
+	evlist__delete(evlist);
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
 	machine__delete_threads(machine);
 	machine__delete(machine);
 

From f2c3202ba0c7746c50c71c14d1ab977d929c0a27 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 1 Mar 2021 23:04:04 +0900
Subject: [PATCH 0266/1820] perf test: Fix cpu and thread map leaks in
 keep_tracking test

The evlist and the cpu/thread maps should be released together.
Otherwise following error was reported by Asan.

  $ perf test -v 28
  28: Use a dummy software event to keep tracking:
  --- start ---
  test child forked, pid 156810
  mmap size 528384B

  =================================================================
  ==156810==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 40 byte(s) in 1 object(s) allocated from:
    #0 0x7f637d2bce8f in __interceptor_malloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:145
    #1 0x55cc6295cffa in cpu_map__trim_new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:79
    #2 0x55cc6295da1f in perf_cpu_map__read /home/namhyung/project/linux/tools/lib/perf/cpumap.c:149
    #3 0x55cc6295e1df in cpu_map__read_all_cpu_map /home/namhyung/project/linux/tools/lib/perf/cpumap.c:166
    #4 0x55cc6295e1df in perf_cpu_map__new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:181
    #5 0x55cc626287cf in test__keep_tracking tests/keep-tracking.c:84
    #6 0x55cc625e38fb in run_test tests/builtin-test.c:428
    #7 0x55cc625e38fb in test_and_print tests/builtin-test.c:458
    #8 0x55cc625e5a53 in __cmd_test tests/builtin-test.c:679
    #9 0x55cc625e5a53 in cmd_test tests/builtin-test.c:825
    #10 0x55cc62651cc4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #11 0x55cc624dba88 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #12 0x55cc624dba88 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #13 0x55cc624dba88 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #14 0x7f637cdf2d09 in __libc_start_main ../csu/libc-start.c:308

  SUMMARY: AddressSanitizer: 72 byte(s) leaked in 2 allocation(s).
  test child finished with 1
  ---- end ----
  Use a dummy software event to keep tracking: FAILED!

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210301140409.184570-7-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/keep-tracking.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index e6f1b2a38e03..a0438b0f0805 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -154,10 +154,9 @@ out_err:
 	if (evlist) {
 		evlist__disable(evlist);
 		evlist__delete(evlist);
-	} else {
-		perf_cpu_map__put(cpus);
-		perf_thread_map__put(threads);
 	}
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
 
 	return err;
 }

From 953e7b5960f1cf0825da60dbdc762e19b127a94c Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 1 Mar 2021 23:04:05 +0900
Subject: [PATCH 0267/1820] perf test: Fix cpu and thread map leaks in
 switch_tracking test

The evlist and cpu/thread maps should be released together.
Otherwise the following error was reported by Asan.

  $ perf test -v 35
  35: Track with sched_switch                    :
  --- start ---
  test child forked, pid 159287
  Using CPUID GenuineIntel-6-8E-C
  mmap size 528384B
  1295 events recorded

  =================================================================
  ==159287==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 40 byte(s) in 1 object(s) allocated from:
    #0 0x7fa28d9a2e8f in __interceptor_malloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:145
    #1 0x5652f5a5affa in cpu_map__trim_new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:79
    #2 0x5652f5a5ba1f in perf_cpu_map__read /home/namhyung/project/linux/tools/lib/perf/cpumap.c:149
    #3 0x5652f5a5c1df in cpu_map__read_all_cpu_map /home/namhyung/project/linux/tools/lib/perf/cpumap.c:166
    #4 0x5652f5a5c1df in perf_cpu_map__new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:181
    #5 0x5652f5723bbf in test__switch_tracking tests/switch-tracking.c:350
    #6 0x5652f56e18fb in run_test tests/builtin-test.c:428
    #7 0x5652f56e18fb in test_and_print tests/builtin-test.c:458
    #8 0x5652f56e3a53 in __cmd_test tests/builtin-test.c:679
    #9 0x5652f56e3a53 in cmd_test tests/builtin-test.c:825
    #10 0x5652f574fcc4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #11 0x5652f55d9a88 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #12 0x5652f55d9a88 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #13 0x5652f55d9a88 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #14 0x7fa28d4d8d09 in __libc_start_main ../csu/libc-start.c:308

  SUMMARY: AddressSanitizer: 72 byte(s) leaked in 2 allocation(s).
  test child finished with 1
  ---- end ----
  Track with sched_switch: FAILED!

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210301140409.184570-8-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/switch-tracking.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 15a2ab765d89..3ebaa758df77 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -574,10 +574,9 @@ out:
 	if (evlist) {
 		evlist__disable(evlist);
 		evlist__delete(evlist);
-	} else {
-		perf_cpu_map__put(cpus);
-		perf_thread_map__put(threads);
 	}
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
 
 	return err;
 

From 4be42882e1f9c8a2d7d7bc066f420418f45b566c Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 1 Mar 2021 23:04:06 +0900
Subject: [PATCH 0268/1820] perf test: Fix a thread map leak in
 thread_map_synthesize test

It missed to call perf_thread_map__put() after using the map.

  $ perf test -v 43
  43: Synthesize thread map                      :
  --- start ---
  test child forked, pid 162640

  =================================================================
  ==162640==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 32 byte(s) in 1 object(s) allocated from:
    #0 0x7fd48cdaa1f8 in __interceptor_realloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:164
    #1 0x563e6d5f8d0e in perf_thread_map__realloc /home/namhyung/project/linux/tools/lib/perf/threadmap.c:23
    #2 0x563e6d3ef69a in thread_map__new_by_pid util/thread_map.c:46
    #3 0x563e6d2cec90 in test__thread_map_synthesize tests/thread-map.c:97
    #4 0x563e6d27d8fb in run_test tests/builtin-test.c:428
    #5 0x563e6d27d8fb in test_and_print tests/builtin-test.c:458
    #6 0x563e6d27fa53 in __cmd_test tests/builtin-test.c:679
    #7 0x563e6d27fa53 in cmd_test tests/builtin-test.c:825
    #8 0x563e6d2ebce4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #9 0x563e6d175a88 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #10 0x563e6d175a88 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #11 0x563e6d175a88 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #12 0x7fd48c8dfd09 in __libc_start_main ../csu/libc-start.c:308

  SUMMARY: AddressSanitizer: 8224 byte(s) leaked in 2 allocation(s).
  test child finished with 1
  ---- end ----
  Synthesize thread map: FAILED!

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210301140409.184570-9-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/thread-map.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index 28f51c4bd373..9e1cf11149ef 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -102,6 +102,7 @@ int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __
 	TEST_ASSERT_VAL("failed to synthesize map",
 		!perf_event__synthesize_thread_map2(NULL, threads, process_event, NULL));
 
+	perf_thread_map__put(threads);
 	return 0;
 }
 

From 641b6250337027311a09009e18264bb65c4d521c Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 1 Mar 2021 23:04:07 +0900
Subject: [PATCH 0269/1820] perf test: Fix a memory leak in thread_map_remove
 test

The str should be freed after creating a thread map.  Also change the
open-coded thread map deletion to a call to perf_thread_map__put().

  $ perf test -v 44
  44: Remove thread map                          :
  --- start ---
  test child forked, pid 165536
  2 threads: 165535, 165536
  1 thread: 165536
  0 thread:

  =================================================================
  ==165536==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 14 byte(s) in 1 object(s) allocated from:
    #0 0x7f54453ffe8f in __interceptor_malloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:145
    #1 0x7f5444f8c6a7 in __vasprintf_internal libio/vasprintf.c:71

  SUMMARY: AddressSanitizer: 14 byte(s) leaked in 1 allocation(s).
  test child finished with 1
  ---- end ----
  Remove thread map: FAILED!

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210301140409.184570-10-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/thread-map.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index 9e1cf11149ef..d1e208b4a571 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -110,12 +110,12 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb
 {
 	struct perf_thread_map *threads;
 	char *str;
-	int i;
 
 	TEST_ASSERT_VAL("failed to allocate map string",
 			asprintf(&str, "%d,%d", getpid(), getppid()) >= 0);
 
 	threads = thread_map__new_str(str, NULL, 0, false);
+	free(str);
 
 	TEST_ASSERT_VAL("failed to allocate thread_map",
 			threads);
@@ -142,9 +142,6 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb
 	TEST_ASSERT_VAL("failed to not remove thread",
 			thread_map__remove(threads, 0));
 
-	for (i = 0; i < threads->nr; i++)
-		zfree(&threads->map[i].comm);
-
-	free(threads);
+	perf_thread_map__put(threads);
 	return 0;
 }

From 690d91f5ec388448f6c2e9e3a8b3da856f400311 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 1 Mar 2021 23:04:08 +0900
Subject: [PATCH 0270/1820] perf test: Fix cpu map leaks in cpu_map_print test

It should be released after printing the map.

  $ perf test -v 52
  52: Print cpu map                              :
  --- start ---
  test child forked, pid 172233

  =================================================================
  ==172233==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 156 byte(s) in 1 object(s) allocated from:
    #0 0x7fc472518e8f in __interceptor_malloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:145
    #1 0x55e63b378f7a in cpu_map__trim_new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:79
    #2 0x55e63b37a05c in perf_cpu_map__new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:237
    #3 0x55e63b056d16 in cpu_map_print tests/cpumap.c:102
    #4 0x55e63b056d16 in test__cpu_map_print tests/cpumap.c:120
    #5 0x55e63afff8fb in run_test tests/builtin-test.c:428
    #6 0x55e63afff8fb in test_and_print tests/builtin-test.c:458
    #7 0x55e63b001a53 in __cmd_test tests/builtin-test.c:679
    #8 0x55e63b001a53 in cmd_test tests/builtin-test.c:825
    #9 0x55e63b06dc44 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #10 0x55e63aef7a88 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #11 0x55e63aef7a88 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #12 0x55e63aef7a88 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #13 0x7fc47204ed09 in __libc_start_main ../csu/libc-start.c:308
  ...

  SUMMARY: AddressSanitizer: 448 byte(s) leaked in 7 allocation(s).
  test child finished with 1
  ---- end ----
  Print cpu map: FAILED!

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210301140409.184570-11-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/cpumap.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 29c793ac7d10..0472b110fe65 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -106,6 +106,8 @@ static int cpu_map_print(const char *str)
 		return -1;
 
 	cpu_map__snprint(map, buf, sizeof(buf));
+	perf_cpu_map__put(map);
+
 	return !strcmp(buf, str);
 }
 

From 846580c235b3e2625ed494f654a28d235976d3b0 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 1 Mar 2021 23:04:09 +0900
Subject: [PATCH 0271/1820] perf test: Fix cpu and thread map leaks in
 perf_time_to_tsc test

It should release the maps at the end.

  $ perf test -v 71
  71: Convert perf time to TSC                   :
  --- start ---
  test child forked, pid 178744
  mmap size 528384B
  1st event perf time 59207256505278 tsc 13187166645142
  rdtsc          time 59207256542151 tsc 13187166723020
  2nd event perf time 59207256543749 tsc 13187166726393

  =================================================================
  ==178744==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 40 byte(s) in 1 object(s) allocated from:
    #0 0x7faf601f9e8f in __interceptor_malloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:145
    #1 0x55b620cfc00a in cpu_map__trim_new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:79
    #2 0x55b620cfca2f in perf_cpu_map__read /home/namhyung/project/linux/tools/lib/perf/cpumap.c:149
    #3 0x55b620cfd1ef in cpu_map__read_all_cpu_map /home/namhyung/project/linux/tools/lib/perf/cpumap.c:166
    #4 0x55b620cfd1ef in perf_cpu_map__new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:181
    #5 0x55b6209ef1b2 in test__perf_time_to_tsc tests/perf-time-to-tsc.c:73
    #6 0x55b6209828fb in run_test tests/builtin-test.c:428
    #7 0x55b6209828fb in test_and_print tests/builtin-test.c:458
    #8 0x55b620984a53 in __cmd_test tests/builtin-test.c:679
    #9 0x55b620984a53 in cmd_test tests/builtin-test.c:825
    #10 0x55b6209f0cd4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #11 0x55b62087aa88 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #12 0x55b62087aa88 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #13 0x55b62087aa88 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #14 0x7faf5fd2fd09 in __libc_start_main ../csu/libc-start.c:308

  SUMMARY: AddressSanitizer: 72 byte(s) leaked in 2 allocation(s).
  test child finished with 1
  ---- end ----
  Convert perf time to TSC: FAILED!

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210301140409.184570-12-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/perf-time-to-tsc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 7cff02664d0e..680c3cffb128 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -167,6 +167,8 @@ next_event:
 
 out_err:
 	evlist__delete(evlist);
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
 	return err;
 }
 

From 743108e1048ee73e0eda394597c1fc2ea46a599b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 2 Mar 2021 16:44:14 -0300
Subject: [PATCH 0272/1820] tools headers: Update syscall.tbl files to support
 mount_setattr

To pick the changes from:

  9caccd41541a6f7d ("fs: introduce MOUNT_ATTR_IDMAP")

This adds this new syscall to the tables used by tools such as 'perf
trace', so that one can specify it by name and have it filtered, etc.

Addressing these perf build warnings:

  Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'
  diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
  Warning: Kernel ABI header at 'tools/perf/arch/powerpc/entry/syscalls/syscall.tbl' differs from latest version at 'arch/powerpc/kernel/syscalls/syscall.tbl'
  diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl
  Warning: Kernel ABI header at 'tools/perf/arch/s390/entry/syscalls/syscall.tbl' differs from latest version at 'arch/s390/kernel/syscalls/syscall.tbl'
  diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/YD6Wsxr9ByUbab/a@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/mount.h                 | 16 ++++++++++++++++
 .../perf/arch/powerpc/entry/syscalls/syscall.tbl |  1 +
 tools/perf/arch/s390/entry/syscalls/syscall.tbl  |  1 +
 .../perf/arch/x86/entry/syscalls/syscall_64.tbl  |  1 +
 4 files changed, 19 insertions(+)

diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index dd8306ea336c..e6524ead2b7b 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -1,6 +1,8 @@
 #ifndef _UAPI_LINUX_MOUNT_H
 #define _UAPI_LINUX_MOUNT_H
 
+#include <linux/types.h>
+
 /*
  * These are the fs-independent mount-flags: up to 32 flags are supported
  *
@@ -117,5 +119,19 @@ enum fsconfig_command {
 #define MOUNT_ATTR_NOATIME	0x00000010 /* - Do not update access times. */
 #define MOUNT_ATTR_STRICTATIME	0x00000020 /* - Always perform atime updates */
 #define MOUNT_ATTR_NODIRATIME	0x00000080 /* Do not update directory access times */
+#define MOUNT_ATTR_IDMAP	0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
+
+/*
+ * mount_setattr()
+ */
+struct mount_attr {
+	__u64 attr_set;
+	__u64 attr_clr;
+	__u64 propagation;
+	__u64 userns_fd;
+};
+
+/* List of all mount_attr versions. */
+#define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
 
 #endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 96b2157f0371..0b2480cf3e47 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -521,3 +521,4 @@
 439	common	faccessat2			sys_faccessat2
 440	common	process_madvise			sys_process_madvise
 441	common	epoll_pwait2			sys_epoll_pwait2		compat_sys_epoll_pwait2
+442	common	mount_setattr			sys_mount_setattr
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index d443423495e5..3abef2144dac 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -444,3 +444,4 @@
 439  common	faccessat2		sys_faccessat2			sys_faccessat2
 440  common	process_madvise		sys_process_madvise		sys_process_madvise
 441  common	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
+442  common	mount_setattr		sys_mount_setattr		sys_mount_setattr
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 78672124d28b..7bf01cbe582f 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -363,6 +363,7 @@
 439	common	faccessat2		sys_faccessat2
 440	common	process_madvise		sys_process_madvise
 441	common	epoll_pwait2		sys_epoll_pwait2
+442	common	mount_setattr		sys_mount_setattr
 
 #
 # Due to a historical design error, certain syscalls are numbered differently

From 6c0afc579aff90e84736d35ee35a1945ec0f279f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 2 Mar 2021 17:10:52 -0300
Subject: [PATCH 0273/1820] tools headers UAPI: Update tools' copy of
 linux/coresight-pmu.h

To get the changes in these commits:

  88f11864cf1d1324 ("coresight: etm-perf: Support PID tracing for kernel at EL2")
  53abf3fe83175626 ("coresight: etm-perf: Clarify comment on perf options")

This will possibly be used in patches lined up for v5.13.

And silence this perf build warning:

  Warning: Kernel ABI header at 'tools/include/linux/coresight-pmu.h' differs from latest version at 'include/linux/coresight-pmu.h'
  diff -u tools/include/linux/coresight-pmu.h include/linux/coresight-pmu.h

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/coresight-pmu.h | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
index b0e35eec6499..4ac5c081af93 100644
--- a/tools/include/linux/coresight-pmu.h
+++ b/tools/include/linux/coresight-pmu.h
@@ -10,17 +10,27 @@
 #define CORESIGHT_ETM_PMU_NAME "cs_etm"
 #define CORESIGHT_ETM_PMU_SEED  0x10
 
-/* ETMv3.5/PTM's ETMCR config bit */
-#define ETM_OPT_CYCACC  12
-#define ETM_OPT_CTXTID	14
-#define ETM_OPT_TS      28
-#define ETM_OPT_RETSTK	29
+/*
+ * Below are the definition of bit offsets for perf option, and works as
+ * arbitrary values for all ETM versions.
+ *
+ * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore,
+ * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and
+ * directly use below macros as config bits.
+ */
+#define ETM_OPT_CYCACC		12
+#define ETM_OPT_CTXTID		14
+#define ETM_OPT_CTXTID2		15
+#define ETM_OPT_TS		28
+#define ETM_OPT_RETSTK		29
 
 /* ETMv4 CONFIGR programming bits for the ETM OPTs */
 #define ETM4_CFG_BIT_CYCACC	4
 #define ETM4_CFG_BIT_CTXTID	6
+#define ETM4_CFG_BIT_VMID	7
 #define ETM4_CFG_BIT_TS		11
 #define ETM4_CFG_BIT_RETSTK	12
+#define ETM4_CFG_BIT_VMID_OPT	15
 
 static inline int coresight_get_trace_id(int cpu)
 {

From 1a9bcadd0058a3e81c1beca48e5e08dee9446a01 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 2 Mar 2021 17:16:17 -0300
Subject: [PATCH 0274/1820] tools headers cpufeatures: Sync with the kernel
 sources

To pick the changes from:

  3b9c723ed7cfa4e1 ("KVM: SVM: Add support for SVM instruction address check change")
  b85a0425d8056f3b ("Enumerate AVX Vector Neural Network instructions")
  fb35d30fe5b06cc2 ("x86/cpufeatures: Assign dedicated feature word for CPUID_0x8000001F[EAX]")

This only causes these perf files to be rebuilt:

  CC       /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o
  CC       /tmp/build/perf/bench/mem-memset-x86-64-asm.o

And addresses this perf build warning:

  Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h'
  diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h

Cc: Borislav Petkov <bp@suse.de>
Cc: Kyung Min Park <kyung.min.park@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Wei Huang <wei.huang2@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/cpufeatures.h | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 84b887825f12..cc96e26d69f7 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS			19	   /* N 32-bit words worth of info */
+#define NCAPINTS			20	   /* N 32-bit words worth of info */
 #define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
@@ -96,7 +96,7 @@
 #define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in IA32 userspace */
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
-#define X86_FEATURE_SME_COHERENT	( 3*32+17) /* "" AMD hardware-enforced cache coherency */
+/* FREE!                                ( 3*32+17) */
 #define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
@@ -201,7 +201,7 @@
 #define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
+/* FREE!                                ( 7*32+10) */
 #define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
 #define X86_FEATURE_RETPOLINE		( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
@@ -211,7 +211,7 @@
 #define X86_FEATURE_SSBD		( 7*32+17) /* Speculative Store Bypass Disable */
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
-#define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
+/* FREE!                                ( 7*32+20) */
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
@@ -236,8 +236,6 @@
 #define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
-#define X86_FEATURE_SEV_ES		( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
-#define X86_FEATURE_VM_PAGE_FLUSH	( 8*32+21) /* "" VM Page Flush MSR is supported */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -294,6 +292,7 @@
 #define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
@@ -337,6 +336,7 @@
 #define X86_FEATURE_AVIC		(15*32+13) /* Virtual Interrupt Controller */
 #define X86_FEATURE_V_VMSAVE_VMLOAD	(15*32+15) /* Virtual VMSAVE VMLOAD */
 #define X86_FEATURE_VGIF		(15*32+16) /* Virtual GIF */
+#define X86_FEATURE_SVME_ADDR_CHK	(15*32+28) /* "" SVME addr check */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
 #define X86_FEATURE_AVX512VBMI		(16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
@@ -385,6 +385,13 @@
 #define X86_FEATURE_CORE_CAPABILITIES	(18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
+/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */
+#define X86_FEATURE_SME			(19*32+ 0) /* AMD Secure Memory Encryption */
+#define X86_FEATURE_SEV			(19*32+ 1) /* AMD Secure Encrypted Virtualization */
+#define X86_FEATURE_VM_PAGE_FLUSH	(19*32+ 2) /* "" VM Page Flush MSR is supported */
+#define X86_FEATURE_SEV_ES		(19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
+
 /*
  * BUG word(s)
  */

From 33dc525f93216bc83935ce98518644def04d6c54 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 2 Mar 2021 17:20:08 -0300
Subject: [PATCH 0275/1820] tools headers UAPI: Sync KVM's kvm.h and vmx.h
 headers with the kernel sources

To pick the changes in:

  fe6b6bc802b40081 ("KVM: VMX: Enable bus lock VM exit")

That makes 'perf kvm-stat' aware of this new BUS_LOCK exit reason, thus
addressing the following perf build warning:

  Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/vmx.h' differs from latest version at 'arch/x86/include/uapi/asm/vmx.h'
  diff -u tools/arch/x86/include/uapi/asm/vmx.h arch/x86/include/uapi/asm/vmx.h

Cc: Chenyi Qiang <chenyi.qiang@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/kvm.h | 1 +
 tools/arch/x86/include/uapi/asm/vmx.h | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 8e76d3701db3..5a3022c8af82 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -112,6 +112,7 @@ struct kvm_ioapic_state {
 #define KVM_NR_IRQCHIPS          3
 
 #define KVM_RUN_X86_SMM		 (1 << 0)
+#define KVM_RUN_X86_BUS_LOCK     (1 << 1)
 
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index ada955c5ebb6..b8e650a985e3 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -89,6 +89,7 @@
 #define EXIT_REASON_XRSTORS             64
 #define EXIT_REASON_UMWAIT              67
 #define EXIT_REASON_TPAUSE              68
+#define EXIT_REASON_BUS_LOCK            74
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -150,7 +151,8 @@
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
 	{ EXIT_REASON_UMWAIT,                "UMWAIT" }, \
-	{ EXIT_REASON_TPAUSE,                "TPAUSE" }
+	{ EXIT_REASON_TPAUSE,                "TPAUSE" }, \
+	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }
 
 #define VMX_EXIT_REASON_FLAGS \
 	{ VMX_EXIT_REASONS_FAILED_VMENTRY,	"FAILED_VMENTRY" }

From 034f7ee130c19b7b04347238395cff1f402198c3 Mon Sep 17 00:00:00 2001
From: Jin Yao <yao.jin@linux.intel.com>
Date: Thu, 28 Jan 2021 09:34:17 +0800
Subject: [PATCH 0276/1820] perf stat: Fix wrong skipping for per-die
 aggregation

Uncore becomes die-scope on Xeon Cascade Lake-AP and perf has supported
--per-die aggregation yet.

One issue is found in check_per_pkg() for uncore events running on AP
system. On cascade Lake-AP, we have:

S0-D0
S0-D1
S1-D0
S1-D1

But in check_per_pkg(), S0-D1 and S1-D1 are skipped because the mask
bits for S0 and S1 have been set for S0-D0 and S1-D0. It doesn't check
die_id. So the counting for S0-D1 and S1-D1 are set to zero.  That's not
correct.

  root@lkp-csl-2ap4 ~# ./perf stat -a -I 1000 -e llc_misses.mem_read --per-die -- sleep 5
     1.001460963 S0-D0           1            1317376 Bytes llc_misses.mem_read
     1.001460963 S0-D1           1             998016 Bytes llc_misses.mem_read
     1.001460963 S1-D0           1             970496 Bytes llc_misses.mem_read
     1.001460963 S1-D1           1            1291264 Bytes llc_misses.mem_read
     2.003488021 S0-D0           1            1082048 Bytes llc_misses.mem_read
     2.003488021 S0-D1           1            1919040 Bytes llc_misses.mem_read
     2.003488021 S1-D0           1             890752 Bytes llc_misses.mem_read
     2.003488021 S1-D1           1            2380800 Bytes llc_misses.mem_read
     3.005613270 S0-D0           1            1126080 Bytes llc_misses.mem_read
     3.005613270 S0-D1           1            2898176 Bytes llc_misses.mem_read
     3.005613270 S1-D0           1             870912 Bytes llc_misses.mem_read
     3.005613270 S1-D1           1            3388608 Bytes llc_misses.mem_read
     4.007627598 S0-D0           1            1124608 Bytes llc_misses.mem_read
     4.007627598 S0-D1           1            3884416 Bytes llc_misses.mem_read
     4.007627598 S1-D0           1             921088 Bytes llc_misses.mem_read
     4.007627598 S1-D1           1            4451840 Bytes llc_misses.mem_read
     5.001479927 S0-D0           1             963328 Bytes llc_misses.mem_read
     5.001479927 S0-D1           1            4831936 Bytes llc_misses.mem_read
     5.001479927 S1-D0           1             895104 Bytes llc_misses.mem_read
     5.001479927 S1-D1           1            5496640 Bytes llc_misses.mem_read

From above output, we can see S0-D1 and S1-D1 don't report the interval
values, they are continued to grow. That's because check_per_pkg()
wrongly decides to use zero counts for S0-D1 and S1-D1.

So in check_per_pkg(), we should use hashmap(socket,die) to decide if
the cpu counts needs to skip. Only considering socket is not enough.

Now with this patch,

  root@lkp-csl-2ap4 ~# ./perf stat -a -I 1000 -e llc_misses.mem_read --per-die -- sleep 5
     1.001586691 S0-D0           1            1229440 Bytes llc_misses.mem_read
     1.001586691 S0-D1           1             976832 Bytes llc_misses.mem_read
     1.001586691 S1-D0           1             938304 Bytes llc_misses.mem_read
     1.001586691 S1-D1           1            1227328 Bytes llc_misses.mem_read
     2.003776312 S0-D0           1            1586752 Bytes llc_misses.mem_read
     2.003776312 S0-D1           1             875392 Bytes llc_misses.mem_read
     2.003776312 S1-D0           1             855616 Bytes llc_misses.mem_read
     2.003776312 S1-D1           1             949376 Bytes llc_misses.mem_read
     3.006512788 S0-D0           1            1338880 Bytes llc_misses.mem_read
     3.006512788 S0-D1           1             920064 Bytes llc_misses.mem_read
     3.006512788 S1-D0           1             877184 Bytes llc_misses.mem_read
     3.006512788 S1-D1           1            1020736 Bytes llc_misses.mem_read
     4.008895291 S0-D0           1             926592 Bytes llc_misses.mem_read
     4.008895291 S0-D1           1             906368 Bytes llc_misses.mem_read
     4.008895291 S1-D0           1             892224 Bytes llc_misses.mem_read
     4.008895291 S1-D1           1             987712 Bytes llc_misses.mem_read
     5.001590993 S0-D0           1             962624 Bytes llc_misses.mem_read
     5.001590993 S0-D1           1             912512 Bytes llc_misses.mem_read
     5.001590993 S1-D0           1             891200 Bytes llc_misses.mem_read
     5.001590993 S1-D1           1             978432 Bytes llc_misses.mem_read

On no-die system, die_id is 0, actually it's hashmap(socket,0), original behavior
is not changed.

Reported-by: Ying Huang <ying.huang@intel.com>
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ying Huang <ying.huang@intel.com>
Link: http://lore.kernel.org/lkml/20210128013417.25597-1-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c            | 18 +++++++++++-
 tools/perf/util/evsel.h            |  4 ++-
 tools/perf/util/python-ext-sources |  1 +
 tools/perf/util/stat.c             | 47 ++++++++++++++++++++++++------
 4 files changed, 59 insertions(+), 11 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1bf76864c4f2..7ecbc8e2fbfa 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -46,6 +46,7 @@
 #include "string2.h"
 #include "memswap.h"
 #include "util.h"
+#include "hashmap.h"
 #include "../perf-sys.h"
 #include "util/parse-branch-options.h"
 #include <internal/xyarray.h>
@@ -1390,7 +1391,9 @@ void evsel__exit(struct evsel *evsel)
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	zfree(&evsel->pmu_name);
-	zfree(&evsel->per_pkg_mask);
+	evsel__zero_per_pkg(evsel);
+	hashmap__free(evsel->per_pkg_mask);
+	evsel->per_pkg_mask = NULL;
 	zfree(&evsel->metric_events);
 	perf_evsel__object.fini(evsel);
 }
@@ -2781,3 +2784,16 @@ int evsel__store_ids(struct evsel *evsel, struct evlist *evlist)
 
 	return store_evsel_ids(evsel, evlist);
 }
+
+void evsel__zero_per_pkg(struct evsel *evsel)
+{
+	struct hashmap_entry *cur;
+	size_t bkt;
+
+	if (evsel->per_pkg_mask) {
+		hashmap__for_each_entry(evsel->per_pkg_mask, cur, bkt)
+			free((char *)cur->key);
+
+		hashmap__clear(evsel->per_pkg_mask);
+	}
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4e8e49fb7e9d..6026487353dd 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -19,6 +19,7 @@ struct perf_stat_evsel;
 union perf_event;
 struct bpf_counter_ops;
 struct target;
+struct hashmap;
 
 typedef int (evsel__sb_cb_t)(union perf_event *event, void *data);
 
@@ -112,7 +113,7 @@ struct evsel {
 	bool			merged_stat;
 	bool			reset_group;
 	bool			errored;
-	unsigned long		*per_pkg_mask;
+	struct hashmap		*per_pkg_mask;
 	struct evsel		*leader;
 	struct list_head	config_terms;
 	int			err;
@@ -433,4 +434,5 @@ struct perf_env *evsel__env(struct evsel *evsel);
 
 int evsel__store_ids(struct evsel *evsel, struct evlist *evlist);
 
+void evsel__zero_per_pkg(struct evsel *evsel);
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 71b753523fac..845dd46e3c61 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -36,3 +36,4 @@ util/symbol_fprintf.c
 util/units.c
 util/affinity.c
 util/rwsem.c
+util/hashmap.c
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 5d8af29447f4..c400f8dde017 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -13,6 +13,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
+#include "hashmap.h"
 #include <linux/zalloc.h>
 
 void update_stats(struct stats *stats, u64 val)
@@ -277,18 +278,29 @@ void evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
 	}
 }
 
-static void zero_per_pkg(struct evsel *counter)
+static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused)
 {
-	if (counter->per_pkg_mask)
-		memset(counter->per_pkg_mask, 0, cpu__max_cpu());
+	uint64_t *key = (uint64_t *) __key;
+
+	return *key & 0xffffffff;
+}
+
+static bool pkg_id_equal(const void *__key1, const void *__key2,
+			 void *ctx __maybe_unused)
+{
+	uint64_t *key1 = (uint64_t *) __key1;
+	uint64_t *key2 = (uint64_t *) __key2;
+
+	return *key1 == *key2;
 }
 
 static int check_per_pkg(struct evsel *counter,
 			 struct perf_counts_values *vals, int cpu, bool *skip)
 {
-	unsigned long *mask = counter->per_pkg_mask;
+	struct hashmap *mask = counter->per_pkg_mask;
 	struct perf_cpu_map *cpus = evsel__cpus(counter);
-	int s;
+	int s, d, ret = 0;
+	uint64_t *key;
 
 	*skip = false;
 
@@ -299,7 +311,7 @@ static int check_per_pkg(struct evsel *counter,
 		return 0;
 
 	if (!mask) {
-		mask = zalloc(cpu__max_cpu());
+		mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL);
 		if (!mask)
 			return -ENOMEM;
 
@@ -321,8 +333,25 @@ static int check_per_pkg(struct evsel *counter,
 	if (s < 0)
 		return -1;
 
-	*skip = test_and_set_bit(s, mask) == 1;
-	return 0;
+	/*
+	 * On multi-die system, die_id > 0. On no-die system, die_id = 0.
+	 * We use hashmap(socket, die) to check the used socket+die pair.
+	 */
+	d = cpu_map__get_die(cpus, cpu, NULL).die;
+	if (d < 0)
+		return -1;
+
+	key = malloc(sizeof(*key));
+	if (!key)
+		return -ENOMEM;
+
+	*key = (uint64_t)d << 32 | s;
+	if (hashmap__find(mask, (void *)key, NULL))
+		*skip = true;
+	else
+		ret = hashmap__add(mask, (void *)key, (void *)1);
+
+	return ret;
 }
 
 static int
@@ -422,7 +451,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	}
 
 	if (counter->per_pkg)
-		zero_per_pkg(counter);
+		evsel__zero_per_pkg(counter);
 
 	ret = process_counter_maps(config, counter);
 	if (ret)

From e2a99c9a9aa02ddc7c08d5089ef140965879f8f4 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 25 Feb 2021 12:51:47 +0900
Subject: [PATCH 0277/1820] libperf: Add perf_evlist__reset_id_hash()

Add the perf_evlist__reset_id_hash() function as an internal function so
that it can be called by perf to reset the hash table.  This is
necessary for 'perf stat' to run the workload multiple times.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210225035148.778569-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/perf/evlist.c                  | 13 +++++++++----
 tools/lib/perf/include/internal/evlist.h |  2 ++
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 17465d454a0e..a0aaf385cbb5 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -26,13 +26,10 @@
 
 void perf_evlist__init(struct perf_evlist *evlist)
 {
-	int i;
-
-	for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
-		INIT_HLIST_HEAD(&evlist->heads[i]);
 	INIT_LIST_HEAD(&evlist->entries);
 	evlist->nr_entries = 0;
 	fdarray__init(&evlist->pollfd, 64);
+	perf_evlist__reset_id_hash(evlist);
 }
 
 static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
@@ -237,6 +234,14 @@ static void perf_evlist__id_hash(struct perf_evlist *evlist,
 	hlist_add_head(&sid->node, &evlist->heads[hash]);
 }
 
+void perf_evlist__reset_id_hash(struct perf_evlist *evlist)
+{
+	int i;
+
+	for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
+		INIT_HLIST_HEAD(&evlist->heads[i]);
+}
+
 void perf_evlist__id_add(struct perf_evlist *evlist,
 			 struct perf_evsel *evsel,
 			 int cpu, int thread, u64 id)
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index 2d0fa02b036f..212c29063ad4 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -124,4 +124,6 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 			   struct perf_evsel *evsel,
 			   int cpu, int thread, int fd);
 
+void perf_evlist__reset_id_hash(struct perf_evlist *evlist);
+
 #endif /* __LIBPERF_INTERNAL_EVLIST_H */

From 513068f2b1fe39a60d89f6f8afbdd79c2534889c Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 25 Feb 2021 12:51:48 +0900
Subject: [PATCH 0278/1820] perf stat: Fix use-after-free when -r option is
 used

I got a segfault when using -r option with event groups.  The option
makes it run the workload multiple times and it will reuse the evlist
and evsel for each run.

While most of resources are allocated and freed properly, the id hash
in the evlist was not and it resulted in the bug.  You can see it with
the address sanitizer like below:

  $ perf stat -r 100 -e '{cycles,instructions}' true
  =================================================================
  ==693052==ERROR: AddressSanitizer: heap-use-after-free on
      address 0x6080000003d0 at pc 0x558c57732835 bp 0x7fff1526adb0 sp 0x7fff1526ada8
  WRITE of size 8 at 0x6080000003d0 thread T0
    #0 0x558c57732834 in hlist_add_head /home/namhyung/project/linux/tools/include/linux/list.h:644
    #1 0x558c57732834 in perf_evlist__id_hash /home/namhyung/project/linux/tools/lib/perf/evlist.c:237
    #2 0x558c57732834 in perf_evlist__id_add /home/namhyung/project/linux/tools/lib/perf/evlist.c:244
    #3 0x558c57732834 in perf_evlist__id_add_fd /home/namhyung/project/linux/tools/lib/perf/evlist.c:285
    #4 0x558c5747733e in store_evsel_ids util/evsel.c:2765
    #5 0x558c5747733e in evsel__store_ids util/evsel.c:2782
    #6 0x558c5730b717 in __run_perf_stat /home/namhyung/project/linux/tools/perf/builtin-stat.c:895
    #7 0x558c5730b717 in run_perf_stat /home/namhyung/project/linux/tools/perf/builtin-stat.c:1014
    #8 0x558c5730b717 in cmd_stat /home/namhyung/project/linux/tools/perf/builtin-stat.c:2446
    #9 0x558c57427c24 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #10 0x558c572b1a48 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #11 0x558c572b1a48 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #12 0x558c572b1a48 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #13 0x7fcadb9f7d09 in __libc_start_main ../csu/libc-start.c:308
    #14 0x558c572b60f9 in _start (/home/namhyung/project/linux/tools/perf/perf+0x45d0f9)

Actually the nodes in the hash table are struct perf_stream_id and
they were freed in the previous run.  Fix it by resetting the hash.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210225035148.778569-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 5121b4db66fe..882cd1f721d9 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1306,6 +1306,7 @@ void evlist__close(struct evlist *evlist)
 		perf_evsel__free_fd(&evsel->core);
 		perf_evsel__free_id(&evsel->core);
 	}
+	perf_evlist__reset_id_hash(&evlist->core);
 }
 
 static int evlist__create_syswide_maps(struct evlist *evlist)

From bd57a9f33abc0adede5bafa06b2f1af3de03190d Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 24 Feb 2021 16:14:38 +0900
Subject: [PATCH 0279/1820] perf daemon: Fix compile error with Asan
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I'm seeing a build failure when build with address sanitizer.  It seems
we could write to the name[100] if the var is longer.

  $ make EXTRA_CFLAGS=-fsanitize=address
  ...
    CC       builtin-daemon.o
  In function ‘get_session_name’,
    inlined from ‘session_config’ at builtin-daemon.c:164:6,
    inlined from ‘server_config’ at builtin-daemon.c:223:10:
  builtin-daemon.c:155:11: error: writing 1 byte into a region of size 0 [-Werror=stringop-overflow=]
    155 |  *session = 0;
        |  ~~~~~~~~~^~~
  builtin-daemon.c: In function ‘server_config’:
  builtin-daemon.c:162:7: note: at offset 100 to object ‘name’ with size 100 declared here
    162 |  char name[100];
        |       ^~~~

Fixes: c0666261ff38 ("perf daemon: Add config file support")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210224071438.686677-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-daemon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index 8f0ed2e59280..ace8772a4f03 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -161,7 +161,7 @@ static int session_config(struct daemon *daemon, const char *var, const char *va
 	struct daemon_session *session;
 	char name[100];
 
-	if (get_session_name(var, name, sizeof(name)))
+	if (get_session_name(var, name, sizeof(name) - 1))
 		return -EINVAL;
 
 	var = strchr(var, '.');

From ec4d0a7680c793ef68d47507fcec245019ee6f33 Mon Sep 17 00:00:00 2001
From: Nicholas Fraser <nfraser@codeweavers.com>
Date: Fri, 19 Feb 2021 11:09:32 -0500
Subject: [PATCH 0280/1820] perf archive: Fix filtering of empty build-ids

A non-existent build-id used to be treated as all-zero SHA-1 hash.
Build-ids are now variable width. A non-existent build-id is an empty
string and "perf buildid-list" pads this with spaces. This is true even
when using old perf.data files recorded from older versions of perf;
"perf buildid-list" never reports an all-zero hash anymore.

This fixes "perf-archive" to skip missing build-ids by skipping lines
that start with a padding space rather than with zeroes.

Signed-off-by: Nicholas Fraser <nfraser@codeweavers.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Huw Davies <huw@codeweavers.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ulrich Czekalla <uczekalla@codeweavers.com>
Link: https://lore.kernel.org/r/442bffc7-ac5c-0975-b876-a549efce2413@codeweavers.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/perf-archive.sh | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 0cfb3e2cefef..133f0eddbcc4 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -20,9 +20,8 @@ else
 fi
 
 BUILDIDS=$(mktemp /tmp/perf-archive-buildids.XXXXXX)
-NOBUILDID=0000000000000000000000000000000000000000
 
-perf buildid-list -i $PERF_DATA --with-hits | grep -v "^$NOBUILDID " > $BUILDIDS
+perf buildid-list -i $PERF_DATA --with-hits | grep -v "^ " > $BUILDIDS
 if [ ! -s $BUILDIDS ] ; then
 	echo "perf archive: no build-ids found"
 	rm $BUILDIDS || true

From a8146d66ab0184ad1728eaeb59cfdf256f4b8fbf Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 3 Mar 2021 08:01:24 -0800
Subject: [PATCH 0281/1820] perf test: Fix sample-parsing failure on non-x86
 platforms

Executing 'perf test 27' fails on s390:

  [root@t35lp46 perf]# ./perf test -Fv 27
  27: Sample parsing
  --- start ---
  ---- end ----
  Sample parsing: FAILED!
  [root@t35lp46 perf]#

The commit fbefe9c2f87fd392 ("perf tools: Support arch specific
PERF_SAMPLE_WEIGHT_STRUCT processing") changes the ins_lat to a
model-specific variable only for X86, but perf test still verify the
variable in the generic test.

Remove the ins_lat check in the generic test. The following patch will
add it in the X86 specific test.

Fixes: fbefe9c2f87fd392 ("perf tools: Support arch specific PERF_SAMPLE_WEIGHT_STRUCT processing")
Reported-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: http://lore.kernel.org/lkml/1614787285-104151-1-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/sample-parsing.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 0dbe3aa99853..8fd8a4ef97da 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -129,9 +129,6 @@ static bool samples_same(const struct perf_sample *s1,
 	if (type & PERF_SAMPLE_WEIGHT)
 		COMP(weight);
 
-	if (type & PERF_SAMPLE_WEIGHT_STRUCT)
-		COMP(ins_lat);
-
 	if (type & PERF_SAMPLE_DATA_SRC)
 		COMP(data_src);
 
@@ -245,7 +242,6 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 		.cgroup		= 114,
 		.data_page_size = 115,
 		.code_page_size = 116,
-		.ins_lat        = 117,
 		.aux_sample	= {
 			.size	= sizeof(aux_data),
 			.data	= (void *)aux_data,

From 7d9d4c6edba93cd96899affe2fc60c3341df152c Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 3 Mar 2021 08:01:25 -0800
Subject: [PATCH 0282/1820] perf test: Support the ins_lat check in the X86
 specific test

The ins_lat of PERF_SAMPLE_WEIGHT_STRUCT stands for the instruction
latency, which is only available for X86. Add a X86 specific test for
the ins_lat and PERF_SAMPLE_WEIGHT_STRUCT type.

The test__x86_sample_parsing() uses the same way as the
test__sample_parsing() to verify a sample type. Since the ins_lat and
PERF_SAMPLE_WEIGHT_STRUCT are the only X86 specific sample type for now,
the test__x86_sample_parsing() only verify the PERF_SAMPLE_WEIGHT_STRUCT
type. Other sample types are still verified in the generic test.

  $ perf test 77 -v
  77: x86 Sample parsing                                              :
  --- start ---
  test child forked, pid 102370
  test child finished with 0
  ---- end ----
  x86 Sample parsing: Ok

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: http://lore.kernel.org/lkml/1614787285-104151-2-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/include/arch-tests.h   |   1 +
 tools/perf/arch/x86/tests/Build            |   1 +
 tools/perf/arch/x86/tests/arch-tests.c     |   4 +
 tools/perf/arch/x86/tests/sample-parsing.c | 121 +++++++++++++++++++++
 4 files changed, 127 insertions(+)
 create mode 100644 tools/perf/arch/x86/tests/sample-parsing.c

diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index 6a54b94f1c25..0e20f3dc69f3 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -10,6 +10,7 @@ int test__rdpmc(struct test *test __maybe_unused, int subtest);
 int test__insn_x86(struct test *test __maybe_unused, int subtest);
 int test__intel_pt_pkt_decoder(struct test *test, int subtest);
 int test__bp_modify(struct test *test, int subtest);
+int test__x86_sample_parsing(struct test *test, int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index 36d4f248b51d..28d793390198 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -3,5 +3,6 @@ perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 
 perf-y += arch-tests.o
 perf-y += rdpmc.o
+perf-y += sample-parsing.o
 perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o
 perf-$(CONFIG_X86_64) += bp-modify.o
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index bc25d727b4e9..71aa67367ad6 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -30,6 +30,10 @@ struct test arch_tests[] = {
 		.func = test__bp_modify,
 	},
 #endif
+	{
+		.desc = "x86 Sample parsing",
+		.func = test__x86_sample_parsing,
+	},
 	{
 		.func = NULL,
 	},
diff --git a/tools/perf/arch/x86/tests/sample-parsing.c b/tools/perf/arch/x86/tests/sample-parsing.c
new file mode 100644
index 000000000000..c92db87e4479
--- /dev/null
+++ b/tools/perf/arch/x86/tests/sample-parsing.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <stdbool.h>
+#include <inttypes.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include "event.h"
+#include "evsel.h"
+#include "debug.h"
+#include "util/synthetic-events.h"
+
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+#define COMP(m) do {					\
+	if (s1->m != s2->m) {				\
+		pr_debug("Samples differ at '"#m"'\n");	\
+		return false;				\
+	}						\
+} while (0)
+
+static bool samples_same(const struct perf_sample *s1,
+			 const struct perf_sample *s2,
+			 u64 type)
+{
+	if (type & PERF_SAMPLE_WEIGHT_STRUCT)
+		COMP(ins_lat);
+
+	return true;
+}
+
+static int do_test(u64 sample_type)
+{
+	struct evsel evsel = {
+		.needs_swap = false,
+		.core = {
+			. attr = {
+				.sample_type = sample_type,
+				.read_format = 0,
+			},
+		},
+	};
+	union perf_event *event;
+	struct perf_sample sample = {
+		.weight		= 101,
+		.ins_lat        = 102,
+	};
+	struct perf_sample sample_out;
+	size_t i, sz, bufsz;
+	int err, ret = -1;
+
+	sz = perf_event__sample_event_size(&sample, sample_type, 0);
+	bufsz = sz + 4096; /* Add a bit for overrun checking */
+	event = malloc(bufsz);
+	if (!event) {
+		pr_debug("malloc failed\n");
+		return -1;
+	}
+
+	memset(event, 0xff, bufsz);
+	event->header.type = PERF_RECORD_SAMPLE;
+	event->header.misc = 0;
+	event->header.size = sz;
+
+	err = perf_event__synthesize_sample(event, sample_type, 0, &sample);
+	if (err) {
+		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+			 "perf_event__synthesize_sample", sample_type, err);
+		goto out_free;
+	}
+
+	/* The data does not contain 0xff so we use that to check the size */
+	for (i = bufsz; i > 0; i--) {
+		if (*(i - 1 + (u8 *)event) != 0xff)
+			break;
+	}
+	if (i != sz) {
+		pr_debug("Event size mismatch: actual %zu vs expected %zu\n",
+			 i, sz);
+		goto out_free;
+	}
+
+	evsel.sample_size = __evsel__sample_size(sample_type);
+
+	err = evsel__parse_sample(&evsel, event, &sample_out);
+	if (err) {
+		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+			 "evsel__parse_sample", sample_type, err);
+		goto out_free;
+	}
+
+	if (!samples_same(&sample, &sample_out, sample_type)) {
+		pr_debug("parsing failed for sample_type %#"PRIx64"\n",
+			 sample_type);
+		goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	free(event);
+
+	return ret;
+}
+
+/**
+ * test__x86_sample_parsing - test X86 specific sample parsing
+ *
+ * This function implements a test that synthesizes a sample event, parses it
+ * and then checks that the parsed sample matches the original sample. If the
+ * test passes %0 is returned, otherwise %-1 is returned.
+ *
+ * For now, the PERF_SAMPLE_WEIGHT_STRUCT is the only X86 specific sample type.
+ * The test only checks the PERF_SAMPLE_WEIGHT_STRUCT type.
+ */
+int test__x86_sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused)
+{
+	return do_test(PERF_SAMPLE_WEIGHT_STRUCT);
+}

From c1f272df510c6b1db68ca6597724d17b557d1407 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 4 Mar 2021 09:51:52 -0300
Subject: [PATCH 0283/1820] perf tests x86: Move insn.h include to make sure it
 finds stddef.h

In some versions of alpine Linux the perf build is broken since commit
1d509f2a6ebca1ae ("x86/insn: Support big endian cross-compiles"):

  In file included from /usr/include/linux/byteorder/little_endian.h:13,
                   from /usr/include/asm/byteorder.h:5,
                   from arch/x86/util/../../../../arch/x86/include/asm/insn.h:10,
                   from arch/x86/util/archinsn.c:2:
  /usr/include/linux/swab.h:161:8: error: unknown type name '__always_inline'
   static __always_inline __u16 __swab16p(const __u16 *p)

So move the inclusion of arch/x86/include/asm/insn.h to later in the
places where linux/stddef.h (that conditionally defines
__always_inline) to workaround this problem on Alpine Linux 3.9 to 3.11,
3.12 onwards works.

Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/tests/insn-x86.c | 2 +-
 tools/perf/arch/x86/util/archinsn.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index f782ef8c5982..4f75ae990140 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
-#include "../../../../arch/x86/include/asm/insn.h"
 #include <string.h>
 
 #include "debug.h"
 #include "tests/tests.h"
 #include "arch-tests.h"
+#include "../../../../arch/x86/include/asm/insn.h"
 
 #include "intel-pt-decoder/intel-pt-insn-decoder.h"
 
diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c
index 3e6791531ca5..34d600c51044 100644
--- a/tools/perf/arch/x86/util/archinsn.c
+++ b/tools/perf/arch/x86/util/archinsn.c
@@ -1,10 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../../../../arch/x86/include/asm/insn.h"
 #include "archinsn.h"
 #include "event.h"
 #include "machine.h"
 #include "thread.h"
 #include "symbol.h"
+#include "../../../../arch/x86/include/asm/insn.h"
 
 void arch_fetch_insn(struct perf_sample *sample,
 		     struct thread *thread,

From 6740a4e70e5d1b9d8e7fe41fd46dd5656d65dadf Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Date: Thu, 4 Mar 2021 11:59:58 +0530
Subject: [PATCH 0284/1820] perf report: Fix -F for branch & mem modes

perf report fails to add valid additional fields with -F when
used with branch or mem modes. Fix it.

Before patch:

  $ perf record -b
  $ perf report -b -F +srcline_from --stdio
  Error:
  Invalid --fields key: `srcline_from'

After patch:

  $ perf report -b -F +srcline_from --stdio
  # Samples: 8K of event 'cycles'
  # Event count (approx.): 8784
  ...

Committer notes:

There was an inversion: when looking at branch stack dimensions (keys)
it was checking if the sort mode was 'mem', not 'branch'.

Fixes: aa6b3c99236b ("perf report: Make -F more strict like -s")
Reported-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/20210304062958.85465-1-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/sort.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 0d5ad42812b9..552b590485bf 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -3140,7 +3140,7 @@ int output_field_add(struct perf_hpp_list *list, char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		if (sort__mode != SORT_MODE__MEMORY)
+		if (sort__mode != SORT_MODE__BRANCH)
 			return -EINVAL;
 
 		return __sort_dimension__add_output(list, sd);
@@ -3152,7 +3152,7 @@ int output_field_add(struct perf_hpp_list *list, char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		if (sort__mode != SORT_MODE__BRANCH)
+		if (sort__mode != SORT_MODE__MEMORY)
 			return -EINVAL;
 
 		return __sort_dimension__add_output(list, sd);

From 77d02bd00cea9f1a87afe58113fa75b983d6c23a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 5 Mar 2021 10:02:09 -0300
Subject: [PATCH 0285/1820] perf map: Tighten snprintf() string precision to
 pass gcc check on some 32-bit arches

Noticed on a debian:experimental mips and mipsel cross build build
environment:

  perfbuilder@ec265a086e9b:~$ mips-linux-gnu-gcc --version | head -1
  mips-linux-gnu-gcc (Debian 10.2.1-3) 10.2.1 20201224
  perfbuilder@ec265a086e9b:~$

    CC       /tmp/build/perf/util/map.o
  util/map.c: In function 'map__new':
  util/map.c:109:5: error: '%s' directive output may be truncated writing between 1 and 2147483645 bytes into a region of size 4096 [-Werror=format-truncation=]
    109 |    "%s/platforms/%s/arch-%s/usr/lib/%s",
        |     ^~
  In file included from /usr/mips-linux-gnu/include/stdio.h:867,
                   from util/symbol.h:11,
                   from util/map.c:2:
  /usr/mips-linux-gnu/include/bits/stdio2.h:67:10: note: '__builtin___snprintf_chk' output 32 or more bytes (assuming 4294967321) into a destination of size 4096
     67 |   return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1,
        |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     68 |        __bos (__s), __fmt, __va_arg_pack ());
        |        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  cc1: all warnings being treated as errors

Since we have the lenghts for what lands in that place, use it to give
the compiler more info and make it happy.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/map.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 692e56dc832e..fbc40a2c17d4 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -77,8 +77,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 	if (strstarts(filename, "/system/lib/")) {
 		char *ndk, *app;
 		const char *arch;
-		size_t ndk_length;
-		size_t app_length;
+		int ndk_length, app_length;
 
 		ndk = getenv("NDK_ROOT");
 		app = getenv("APP_PLATFORM");
@@ -106,8 +105,8 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 		if (new_length > PATH_MAX)
 			return false;
 		snprintf(newfilename, new_length,
-			"%s/platforms/%s/arch-%s/usr/lib/%s",
-			ndk, app, arch, libname);
+			"%.*s/platforms/%.*s/arch-%s/usr/lib/%s",
+			ndk_length, ndk, app_length, app, arch, libname);
 
 		return true;
 	}

From 86a19008af5d88d5d523dbfe9b6ede11473e9a7f Mon Sep 17 00:00:00 2001
From: Michael Petlan <mpetlan@redhat.com>
Date: Tue, 2 Mar 2021 15:41:20 +0100
Subject: [PATCH 0286/1820] perf trace: Fix race in signal handling

Since a lot of stuff happens before the SIGINT signal handler is registered
(scanning /proc/*, etc.), on bigger systems, such as Cavium Sabre CN99xx,
it may happen that first interrupt signal is lost and perf isn't correctly
terminated.

The reproduction code might look like the following:

    perf trace -a &
    PERF_PID=$!
    sleep 4
    kill -INT $PERF_PID

The issue has been found on a CN99xx machine with RHEL-8 and the patch fixes
it by registering the signal handlers earlier in the init stage.

Suggested-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Michael Petlan <mpetlan@redhat.com>
Tested-by: Michael Petlan <mpetlan@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: https://lore.kernel.org/lkml/YEJnaMzH2ctp3PPx@kernel.org/
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 85b6a46e85b6..7ec18ff57fc4 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3964,9 +3964,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 	evlist__config(evlist, &trace->opts, &callchain_param);
 
-	signal(SIGCHLD, sig_handler);
-	signal(SIGINT, sig_handler);
-
 	if (forks) {
 		err = evlist__prepare_workload(evlist, &trace->opts.target, argv, false, NULL);
 		if (err < 0) {
@@ -4827,6 +4824,8 @@ int cmd_trace(int argc, const char **argv)
 
 	signal(SIGSEGV, sighandler_dump_stack);
 	signal(SIGFPE, sighandler_dump_stack);
+	signal(SIGCHLD, sig_handler);
+	signal(SIGINT, sig_handler);
 
 	trace.evlist = evlist__new();
 	trace.sctbl = syscalltbl__new();

From 6fc5baf5471700fd613f0b4e52ab4563f1942b78 Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Sat, 6 Feb 2021 23:08:29 +0800
Subject: [PATCH 0287/1820] perf cs-etm: Fix bitmap for option

When set option with macros ETM_OPT_CTXTID and ETM_OPT_TS, it wrongly
takes these two values (14 and 28 prespectively) as bit masks, but
actually both are the offset for bits.  But this doesn't lead to
further failure due to the AND logic operation will be always true for
ETM_OPT_CTXTID / ETM_OPT_TS.

This patch defines new independent macros (rather than using the
"config" bits) for requesting the "contextid" and "timestamp" for
cs_etm_set_option().

Signed-off-by: Suzuki Poulouse <suzuki.poulose@arm.com>
Reviewed-by: Mike Leach <mike.leach@linaro.org>
Cc: Al Grant <al.grant@arm.com>
Cc: Daniel Kiss <daniel.kiss@arm.com>
Cc: Denis Nikitin <denik@chromium.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Link: http://lore.kernel.org/lkml/20210206150833.42120-5-leo.yan@linaro.org
[ Extract the change as a separate patch for easier review ]
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm/util/cs-etm.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index bd446aba64f7..c25c878fd06c 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -156,6 +156,10 @@ out:
 	return err;
 }
 
+#define ETM_SET_OPT_CTXTID	(1 << 0)
+#define ETM_SET_OPT_TS		(1 << 1)
+#define ETM_SET_OPT_MASK	(ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS)
+
 static int cs_etm_set_option(struct auxtrace_record *itr,
 			     struct evsel *evsel, u32 option)
 {
@@ -169,17 +173,17 @@ static int cs_etm_set_option(struct auxtrace_record *itr,
 		    !cpu_map__has(online_cpus, i))
 			continue;
 
-		if (option & ETM_OPT_CTXTID) {
+		if (option & ETM_SET_OPT_CTXTID) {
 			err = cs_etm_set_context_id(itr, evsel, i);
 			if (err)
 				goto out;
 		}
-		if (option & ETM_OPT_TS) {
+		if (option & ETM_SET_OPT_TS) {
 			err = cs_etm_set_timestamp(itr, evsel, i);
 			if (err)
 				goto out;
 		}
-		if (option & ~(ETM_OPT_CTXTID | ETM_OPT_TS))
+		if (option & ~(ETM_SET_OPT_MASK))
 			/* Nothing else is currently supported */
 			goto out;
 	}
@@ -406,7 +410,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 		evsel__set_sample_bit(cs_etm_evsel, CPU);
 
 		err = cs_etm_set_option(itr, cs_etm_evsel,
-					ETM_OPT_CTXTID | ETM_OPT_TS);
+					ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS);
 		if (err)
 			goto out;
 	}

From d30881f573e565ebb5dbb50b31ed6106b5c81328 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Thu, 18 Feb 2021 21:02:07 -0500
Subject: [PATCH 0288/1820] nfsd: Don't keep looking up unhashed files in the
 nfsd file cache

If a file is unhashed, then we're going to reject it anyway and retry,
so make sure we skip it when we're doing the RCU lockless lookup.
This avoids a number of unnecessary nfserr_jukebox returns from
nfsd_file_acquire()

Fixes: 65294c1f2c5e ("nfsd: add a new struct file caching facility to nfsd")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/filecache.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 53fcbf79bdca..7629248fdd53 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -898,6 +898,8 @@ nfsd_file_find_locked(struct inode *inode, unsigned int may_flags,
 			continue;
 		if (!nfsd_match_cred(nf->nf_cred, current_cred()))
 			continue;
+		if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags))
+			continue;
 		if (nfsd_file_get(nf) != NULL)
 			return nf;
 	}

From 6820bf77864d5894ff67b5c00d7dba8f92011e3d Mon Sep 17 00:00:00 2001
From: Timo Rothenpieler <timo@rothenpieler.org>
Date: Tue, 23 Feb 2021 00:36:19 +0100
Subject: [PATCH 0289/1820] svcrdma: disable timeouts on rdma backchannel

This brings it in line with the regular tcp backchannel, which also has
all those timeouts disabled.

Prevents the backchannel from timing out, getting some async operations
like server side copying getting stuck indefinitely on the client side.

Signed-off-by: Timo Rothenpieler <timo@rothenpieler.org>
Fixes: 5d252f90a800 ("svcrdma: Add class for RDMA backwards direction transport")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 4a1edbb4028e..9150df35fb6f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -252,9 +252,9 @@ xprt_setup_rdma_bc(struct xprt_create *args)
 	xprt->timeout = &xprt_rdma_bc_timeout;
 	xprt_set_bound(xprt);
 	xprt_set_connected(xprt);
-	xprt->bind_timeout = RPCRDMA_BIND_TO;
-	xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
-	xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO;
+	xprt->bind_timeout = 0;
+	xprt->reestablish_timeout = 0;
+	xprt->idle_timeout = 0;
 
 	xprt->prot = XPRT_TRANSPORT_BC_RDMA;
 	xprt->ops = &xprt_rdma_bc_procs;

From 7005227369079963d25fb2d5d736d0feb2c44cf6 Mon Sep 17 00:00:00 2001
From: Julian Braha <julianbraha@gmail.com>
Date: Fri, 19 Feb 2021 16:56:10 -0500
Subject: [PATCH 0290/1820] fs: nfsd: fix kconfig dependency warning for
 NFSD_V4

When NFSD_V4 is enabled and CRYPTO is disabled,
Kbuild gives the following warning:

WARNING: unmet direct dependencies detected for CRYPTO_SHA256
  Depends on [n]: CRYPTO [=n]
  Selected by [y]:
  - NFSD_V4 [=y] && NETWORK_FILESYSTEMS [=y] && NFSD [=y] && PROC_FS [=y]

WARNING: unmet direct dependencies detected for CRYPTO_MD5
  Depends on [n]: CRYPTO [=n]
  Selected by [y]:
  - NFSD_V4 [=y] && NETWORK_FILESYSTEMS [=y] && NFSD [=y] && PROC_FS [=y]

This is because NFSD_V4 selects CRYPTO_MD5 and CRYPTO_SHA256,
without depending on or selecting CRYPTO, despite those config options
being subordinate to CRYPTO.

Signed-off-by: Julian Braha <julianbraha@gmail.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 821e5913faee..d6cff5fbe705 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -73,6 +73,7 @@ config NFSD_V4
 	select NFSD_V3
 	select FS_POSIX_ACL
 	select SUNRPC_GSS
+	select CRYPTO
 	select CRYPTO_MD5
 	select CRYPTO_SHA256
 	select GRACE_PERIOD

From bfdd89f232aa2de5a4b3fc985cba894148b830a8 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Wed, 24 Feb 2021 13:39:50 -0500
Subject: [PATCH 0291/1820] nfsd: don't abort copies early

The typical result of the backwards comparison here is that the source
server in a server-to-server copy will return BAD_STATEID within a few
seconds of the copy starting, instead of giving the copy a full lease
period, so the copy_file_range() call will end up unnecessarily
returning a short read.

Fixes: 624322f1adc5 "NFSD add COPY_NOTIFY operation"
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 423fd6683f3a..61552e89bd89 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5389,7 +5389,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 	idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
 		cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
 		if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
-				cps->cpntf_time > cutoff)
+				cps->cpntf_time < cutoff)
 			_free_cpntf_state_locked(nn, cps);
 	}
 	spin_unlock(&nn->s2s_cp_lock);

From c7de87ff9dac5f396f62d584f3908f80ddc0e07b Mon Sep 17 00:00:00 2001
From: Joe Korty <joe.korty@concurrent-rt.com>
Date: Fri, 26 Feb 2021 09:38:20 -0500
Subject: [PATCH 0292/1820] NFSD: Repair misuse of sv_lock in 5.10.16-rt30.

[ This problem is in mainline, but only rt has the chops to be
able to detect it. ]

Lockdep reports a circular lock dependency between serv->sv_lock and
softirq_ctl.lock on system shutdown, when using a kernel built with
CONFIG_PREEMPT_RT=y, and a nfs mount exists.

This is due to the definition of spin_lock_bh on rt:

	local_bh_disable();
	rt_spin_lock(lock);

which forces a softirq_ctl.lock -> serv->sv_lock dependency.  This is
not a problem as long as _every_ lock of serv->sv_lock is a:

	spin_lock_bh(&serv->sv_lock);

but there is one of the form:

	spin_lock(&serv->sv_lock);

This is what is causing the circular dependency splat.  The spin_lock()
grabs the lock without first grabbing softirq_ctl.lock via local_bh_disable.
If later on in the critical region,  someone does a local_bh_disable, we
get a serv->sv_lock -> softirq_ctrl.lock dependency established.  Deadlock.

Fix is to make serv->sv_lock be locked with spin_lock_bh everywhere, no
exceptions.

[  OK  ] Stopped target NFS client services.
         Stopping Logout off all iSCSI sessions on shutdown...
         Stopping NFS server and services...
[  109.442380]
[  109.442385] ======================================================
[  109.442386] WARNING: possible circular locking dependency detected
[  109.442387] 5.10.16-rt30 #1 Not tainted
[  109.442389] ------------------------------------------------------
[  109.442390] nfsd/1032 is trying to acquire lock:
[  109.442392] ffff994237617f60 ((softirq_ctrl.lock).lock){+.+.}-{2:2}, at: __local_bh_disable_ip+0xd9/0x270
[  109.442405]
[  109.442405] but task is already holding lock:
[  109.442406] ffff994245cb00b0 (&serv->sv_lock){+.+.}-{0:0}, at: svc_close_list+0x1f/0x90
[  109.442415]
[  109.442415] which lock already depends on the new lock.
[  109.442415]
[  109.442416]
[  109.442416] the existing dependency chain (in reverse order) is:
[  109.442417]
[  109.442417] -> #1 (&serv->sv_lock){+.+.}-{0:0}:
[  109.442421]        rt_spin_lock+0x2b/0xc0
[  109.442428]        svc_add_new_perm_xprt+0x42/0xa0
[  109.442430]        svc_addsock+0x135/0x220
[  109.442434]        write_ports+0x4b3/0x620
[  109.442438]        nfsctl_transaction_write+0x45/0x80
[  109.442440]        vfs_write+0xff/0x420
[  109.442444]        ksys_write+0x4f/0xc0
[  109.442446]        do_syscall_64+0x33/0x40
[  109.442450]        entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  109.442454]
[  109.442454] -> #0 ((softirq_ctrl.lock).lock){+.+.}-{2:2}:
[  109.442457]        __lock_acquire+0x1264/0x20b0
[  109.442463]        lock_acquire+0xc2/0x400
[  109.442466]        rt_spin_lock+0x2b/0xc0
[  109.442469]        __local_bh_disable_ip+0xd9/0x270
[  109.442471]        svc_xprt_do_enqueue+0xc0/0x4d0
[  109.442474]        svc_close_list+0x60/0x90
[  109.442476]        svc_close_net+0x49/0x1a0
[  109.442478]        svc_shutdown_net+0x12/0x40
[  109.442480]        nfsd_destroy+0xc5/0x180
[  109.442482]        nfsd+0x1bc/0x270
[  109.442483]        kthread+0x194/0x1b0
[  109.442487]        ret_from_fork+0x22/0x30
[  109.442492]
[  109.442492] other info that might help us debug this:
[  109.442492]
[  109.442493]  Possible unsafe locking scenario:
[  109.442493]
[  109.442493]        CPU0                    CPU1
[  109.442494]        ----                    ----
[  109.442495]   lock(&serv->sv_lock);
[  109.442496]                                lock((softirq_ctrl.lock).lock);
[  109.442498]                                lock(&serv->sv_lock);
[  109.442499]   lock((softirq_ctrl.lock).lock);
[  109.442501]
[  109.442501]  *** DEADLOCK ***
[  109.442501]
[  109.442501] 3 locks held by nfsd/1032:
[  109.442503]  #0: ffffffff93b49258 (nfsd_mutex){+.+.}-{3:3}, at: nfsd+0x19a/0x270
[  109.442508]  #1: ffff994245cb00b0 (&serv->sv_lock){+.+.}-{0:0}, at: svc_close_list+0x1f/0x90
[  109.442512]  #2: ffffffff93a81b20 (rcu_read_lock){....}-{1:2}, at: rt_spin_lock+0x5/0xc0
[  109.442518]
[  109.442518] stack backtrace:
[  109.442519] CPU: 0 PID: 1032 Comm: nfsd Not tainted 5.10.16-rt30 #1
[  109.442522] Hardware name: Supermicro X9DRL-3F/iF/X9DRL-3F/iF, BIOS 3.2 09/22/2015
[  109.442524] Call Trace:
[  109.442527]  dump_stack+0x77/0x97
[  109.442533]  check_noncircular+0xdc/0xf0
[  109.442546]  __lock_acquire+0x1264/0x20b0
[  109.442553]  lock_acquire+0xc2/0x400
[  109.442564]  rt_spin_lock+0x2b/0xc0
[  109.442570]  __local_bh_disable_ip+0xd9/0x270
[  109.442573]  svc_xprt_do_enqueue+0xc0/0x4d0
[  109.442577]  svc_close_list+0x60/0x90
[  109.442581]  svc_close_net+0x49/0x1a0
[  109.442585]  svc_shutdown_net+0x12/0x40
[  109.442588]  nfsd_destroy+0xc5/0x180
[  109.442590]  nfsd+0x1bc/0x270
[  109.442595]  kthread+0x194/0x1b0
[  109.442600]  ret_from_fork+0x22/0x30
[  109.518225] nfsd: last server has exited, flushing export cache
[  OK  ] Stopped NFSv4 ID-name mapping service.
[  OK  ] Stopped GSSAPI Proxy Daemon.
[  OK  ] Stopped NFS Mount Daemon.
[  OK  ] Stopped NFS status monitor for NFSv2/3 locking..

Fixes: 719f8bcc883e ("svcrpc: fix xpt_list traversal locking on shutdown")
Signed-off-by: Joe Korty <joe.korty@concurrent-rt.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/svc_xprt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index dcc50ae54550..3cdd71a8df1e 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1060,7 +1060,7 @@ static int svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, st
 	struct svc_xprt *xprt;
 	int ret = 0;
 
-	spin_lock(&serv->sv_lock);
+	spin_lock_bh(&serv->sv_lock);
 	list_for_each_entry(xprt, xprt_list, xpt_list) {
 		if (xprt->xpt_net != net)
 			continue;
@@ -1068,7 +1068,7 @@ static int svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, st
 		set_bit(XPT_CLOSE, &xprt->xpt_flags);
 		svc_xprt_enqueue(xprt);
 	}
-	spin_unlock(&serv->sv_lock);
+	spin_unlock_bh(&serv->sv_lock);
 	return ret;
 }
 

From f1442d6349a2e7bb7a6134791bdc26cb776c79af Mon Sep 17 00:00:00 2001
From: Daniel Kobras <kobras@puzzle-itc.de>
Date: Sat, 27 Feb 2021 00:04:37 +0100
Subject: [PATCH 0293/1820] sunrpc: fix refcount leak for rpc auth modules

If an auth module's accept op returns SVC_CLOSE, svc_process_common()
enters a call path that does not call svc_authorise() before leaving the
function, and thus leaks a reference on the auth module's refcount. Hence,
make sure calls to svc_authenticate() and svc_authorise() are paired for
all call paths, to make sure rpc auth modules can be unloaded.

Signed-off-by: Daniel Kobras <kobras@puzzle-itc.de>
Fixes: 4d712ef1db05 ("svcauth_gss: Close connection when dropping an incoming message")
Link: https://lore.kernel.org/linux-nfs/3F1B347F-B809-478F-A1E9-0BE98E22B0F0@oracle.com/T/#t
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/svc.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 61fb8a18552c..d76dc9d95d16 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1413,7 +1413,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 
  sendit:
 	if (svc_authorise(rqstp))
-		goto close;
+		goto close_xprt;
 	return 1;		/* Caller can now send it */
 
 release_dropit:
@@ -1425,6 +1425,8 @@ release_dropit:
 	return 0;
 
  close:
+	svc_authorise(rqstp);
+close_xprt:
 	if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
 		svc_close_xprt(rqstp->rq_xprt);
 	dprintk("svc: svc_process close\n");
@@ -1433,7 +1435,7 @@ release_dropit:
 err_short_len:
 	svc_printk(rqstp, "short len %zd, dropping request\n",
 			argv->iov_len);
-	goto close;
+	goto close_xprt;
 
 err_bad_rpc:
 	serv->sv_stats->rpcbadfmt++;

From 0ddc942394013f08992fc379ca04cffacbbe3dae Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Tue, 2 Mar 2021 10:48:38 -0500
Subject: [PATCH 0294/1820] rpc: fix NULL dereference on kmalloc failure

I think this is unlikely but possible:

svc_authenticate sets rq_authop and calls svcauth_gss_accept.  The
kmalloc(sizeof(*svcdata), GFP_KERNEL) fails, leaving rq_auth_data NULL,
and returning SVC_DENIED.

This causes svc_process_common to go to err_bad_auth, and eventually
call svc_authorise.  That calls ->release == svcauth_gss_release, which
tries to dereference rq_auth_data.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Link: https://lore.kernel.org/linux-nfs/3F1B347F-B809-478F-A1E9-0BE98E22B0F0@oracle.com/T/#t
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/auth_gss/svcauth_gss.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index bd4678db9d76..6dff64374bfe 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1825,11 +1825,14 @@ static int
 svcauth_gss_release(struct svc_rqst *rqstp)
 {
 	struct gss_svc_data *gsd = (struct gss_svc_data *)rqstp->rq_auth_data;
-	struct rpc_gss_wire_cred *gc = &gsd->clcred;
+	struct rpc_gss_wire_cred *gc;
 	struct xdr_buf *resbuf = &rqstp->rq_res;
 	int stat = -EINVAL;
 	struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id);
 
+	if (!gsd)
+		goto out;
+	gc = &gsd->clcred;
 	if (gc->gc_proc != RPC_GSS_PROC_DATA)
 		goto out;
 	/* Release can be called twice, but we only wrap once. */
@@ -1870,10 +1873,10 @@ out_err:
 	if (rqstp->rq_cred.cr_group_info)
 		put_group_info(rqstp->rq_cred.cr_group_info);
 	rqstp->rq_cred.cr_group_info = NULL;
-	if (gsd->rsci)
+	if (gsd && gsd->rsci) {
 		cache_put(&gsd->rsci->h, sn->rsc_cache);
-	gsd->rsci = NULL;
-
+		gsd->rsci = NULL;
+	}
 	return stat;
 }
 

From 9e9888a0fe97b9501a40f717225d2bef7100a2c1 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 5 Mar 2021 10:21:05 +0100
Subject: [PATCH 0295/1820] efi: stub: omit SetVirtualAddressMap() if marked
 unsupported in RT_PROP table

The EFI_RT_PROPERTIES_TABLE contains a mask of runtime services that are
available after ExitBootServices(). This mostly does not concern the EFI
stub at all, given that it runs before that. However, there is one call
that is made at runtime, which is the call to SetVirtualAddressMap()
(which is not even callable at boot time to begin with)

So add the missing handling of the RT_PROP table to ensure that we only
call SetVirtualAddressMap() if it is not being advertised as unsupported
by the firmware.

Cc: <stable@vger.kernel.org> # v5.10+
Tested-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/efi-stub.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/firmware/efi/libstub/efi-stub.c b/drivers/firmware/efi/libstub/efi-stub.c
index ec2f3985bef3..26e69788f27a 100644
--- a/drivers/firmware/efi/libstub/efi-stub.c
+++ b/drivers/firmware/efi/libstub/efi-stub.c
@@ -96,6 +96,18 @@ static void install_memreserve_table(void)
 		efi_err("Failed to install memreserve config table!\n");
 }
 
+static u32 get_supported_rt_services(void)
+{
+	const efi_rt_properties_table_t *rt_prop_table;
+	u32 supported = EFI_RT_SUPPORTED_ALL;
+
+	rt_prop_table = get_efi_config_table(EFI_RT_PROPERTIES_TABLE_GUID);
+	if (rt_prop_table)
+		supported &= rt_prop_table->runtime_services_supported;
+
+	return supported;
+}
+
 /*
  * EFI entry point for the arm/arm64 EFI stubs.  This is the entrypoint
  * that is described in the PE/COFF header.  Most of the code is the same
@@ -250,6 +262,10 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 			  (prop_tbl->memory_protection_attribute &
 			   EFI_PROPERTIES_RUNTIME_MEMORY_PROTECTION_NON_EXECUTABLE_PE_DATA);
 
+	/* force efi_novamap if SetVirtualAddressMap() is unsupported */
+	efi_novamap |= !(get_supported_rt_services() &
+			 EFI_RT_SUPPORTED_SET_VIRTUAL_ADDRESS_MAP);
+
 	/* hibernation expects the runtime regions to stay in the same place */
 	if (!IS_ENABLED(CONFIG_HIBERNATION) && !efi_nokaslr && !flat_va_mapping) {
 		/*

From eb602521f43876b3f76c4686de596c9804977228 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Thu, 4 Mar 2021 09:28:57 -0500
Subject: [PATCH 0296/1820] gfs2: make function gfs2_make_fs_ro() to void type

It fixes the following warning detected by coccinelle:
./fs/gfs2/super.c:592:5-10: Unneeded variable: "error". Return "0" on
line 628

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/ops_fstype.c |  4 +---
 fs/gfs2/super.c      | 10 ++--------
 fs/gfs2/super.h      |  2 +-
 fs/gfs2/util.c       |  2 +-
 4 files changed, 5 insertions(+), 13 deletions(-)

diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 74c7d01723b9..aa4136055a83 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1539,9 +1539,7 @@ static int gfs2_reconfigure(struct fs_context *fc)
 			return -EINVAL;
 
 		if (fc->sb_flags & SB_RDONLY) {
-			error = gfs2_make_fs_ro(sdp);
-			if (error)
-				errorfc(fc, "unable to remount read-only");
+			gfs2_make_fs_ro(sdp);
 		} else {
 			error = gfs2_make_fs_rw(sdp);
 			if (error)
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 861ed5fe02a5..97076d3f562f 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -587,9 +587,8 @@ out:
  * Returns: errno
  */
 
-int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
+void gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 {
-	int error = 0;
 	int log_write_allowed = test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
 
 	gfs2_flush_delete_work(sdp);
@@ -624,8 +623,6 @@ int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 
 	if (!log_write_allowed)
 		sdp->sd_vfs->s_flags |= SB_RDONLY;
-
-	return error;
 }
 
 /**
@@ -637,7 +634,6 @@ int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 static void gfs2_put_super(struct super_block *sb)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
-	int error;
 	struct gfs2_jdesc *jd;
 
 	/* No more recovery requests */
@@ -658,9 +654,7 @@ restart:
 	spin_unlock(&sdp->sd_jindex_spin);
 
 	if (!sb_rdonly(sb)) {
-		error = gfs2_make_fs_ro(sdp);
-		if (error)
-			gfs2_io_error(sdp);
+		gfs2_make_fs_ro(sdp);
 	}
 	WARN_ON(gfs2_withdrawing(sdp));
 
diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h
index 08e502dec7ec..ec4affb33ed5 100644
--- a/fs/gfs2/super.h
+++ b/fs/gfs2/super.h
@@ -34,7 +34,7 @@ extern int gfs2_lookup_in_master_dir(struct gfs2_sbd *sdp, char *filename,
 				     struct gfs2_inode **ipp);
 
 extern int gfs2_make_fs_rw(struct gfs2_sbd *sdp);
-extern int gfs2_make_fs_ro(struct gfs2_sbd *sdp);
+extern void gfs2_make_fs_ro(struct gfs2_sbd *sdp);
 extern void gfs2_online_uevent(struct gfs2_sbd *sdp);
 extern int gfs2_statfs_init(struct gfs2_sbd *sdp);
 extern void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 8d3c670c990f..58743315cda9 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -156,7 +156,7 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
 				ret = 0;
 		}
 		if (!ret)
-			ret = gfs2_make_fs_ro(sdp);
+			gfs2_make_fs_ro(sdp);
 		gfs2_freeze_unlock(&freeze_gh);
 	}
 

From 1a5a2cfd34c17db73c53ef127272c8c1ae220485 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Thu, 25 Feb 2021 11:11:09 -0500
Subject: [PATCH 0297/1820] gfs2: fix use-after-free in trans_drain

This patch adds code to function trans_drain to remove drained
bd elements from the ail lists, if queued, before freeing the bd.
If we don't remove the bd from the ail, function ail_drain will
try to reference the bd after it has been freed by trans_drain.

Thanks to Andy Price for his analysis of the problem.

Reported-by: Andy Price <anprice@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/log.c   | 4 ++++
 fs/gfs2/trans.c | 2 ++
 2 files changed, 6 insertions(+)

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 16937ebb2a3e..760af666576c 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -998,12 +998,16 @@ static void trans_drain(struct gfs2_trans *tr)
 	while (!list_empty(head)) {
 		bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
 		list_del_init(&bd->bd_list);
+		if (!list_empty(&bd->bd_ail_st_list))
+			gfs2_remove_from_ail(bd);
 		kmem_cache_free(gfs2_bufdata_cachep, bd);
 	}
 	head = &tr->tr_databuf;
 	while (!list_empty(head)) {
 		bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
 		list_del_init(&bd->bd_list);
+		if (!list_empty(&bd->bd_ail_st_list))
+			gfs2_remove_from_ail(bd);
 		kmem_cache_free(gfs2_bufdata_cachep, bd);
 	}
 }
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index ab96cf0bf26b..63fec11ef2ce 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -169,6 +169,8 @@ static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl,
 	bd->bd_bh = bh;
 	bd->bd_gl = gl;
 	INIT_LIST_HEAD(&bd->bd_list);
+	INIT_LIST_HEAD(&bd->bd_ail_st_list);
+	INIT_LIST_HEAD(&bd->bd_ail_gl_list);
 	bh->b_private = bd;
 	return bd;
 }

From 2941267bd3dad018de1d51fe2cd996b7bc1e5a5d Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sat, 6 Mar 2021 11:02:11 +0000
Subject: [PATCH 0298/1820] io_uring: make del_task_file more forgiving

Rework io_uring_del_task_file(), so it accepts an index to delete, and
it's not necessarily have to be in the ->xa. Infer file from xa_erase()
to maintain a single origin of truth.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index d51c6ba9268b..00a736867b76 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8785,15 +8785,18 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
 /*
  * Remove this io_uring_file -> task mapping.
  */
-static void io_uring_del_task_file(struct file *file)
+static void io_uring_del_task_file(unsigned long index)
 {
 	struct io_uring_task *tctx = current->io_uring;
+	struct file *file;
+
+	file = xa_erase(&tctx->xa, index);
+	if (!file)
+		return;
 
 	if (tctx->last == file)
 		tctx->last = NULL;
-	file = xa_erase(&tctx->xa, (unsigned long)file);
-	if (file)
-		fput(file);
+	fput(file);
 }
 
 static void io_uring_clean_tctx(struct io_uring_task *tctx)
@@ -8802,7 +8805,7 @@ static void io_uring_clean_tctx(struct io_uring_task *tctx)
 	unsigned long index;
 
 	xa_for_each(&tctx->xa, index, file)
-		io_uring_del_task_file(file);
+		io_uring_del_task_file(index);
 	if (tctx->io_wq) {
 		io_wq_put_and_exit(tctx->io_wq);
 		tctx->io_wq = NULL;

From 13bf43f5f4739739751c0049a1582610c283bdde Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sat, 6 Mar 2021 11:02:12 +0000
Subject: [PATCH 0299/1820] io_uring: introduce ctx to tctx back map

For each pair tcxt-ctx create an object and chain it into ctx, so we
have a way to traverse all tctx that are using current ctx. Preparation
patch, will be used later.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 58 ++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 44 insertions(+), 14 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 00a736867b76..9a2cff0662e0 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -454,6 +454,7 @@ struct io_ring_ctx {
 
 	/* Keep this last, we don't need it for the fast path */
 	struct work_struct		exit_work;
+	struct list_head		tctx_list;
 };
 
 /*
@@ -805,6 +806,13 @@ struct io_kiocb {
 	struct io_wq_work		work;
 };
 
+struct io_tctx_node {
+	struct list_head	ctx_node;
+	struct task_struct	*task;
+	struct file		*file;
+	struct io_ring_ctx	*ctx;
+};
+
 struct io_defer_entry {
 	struct list_head	list;
 	struct io_kiocb		*req;
@@ -1144,6 +1152,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_LIST_HEAD(&ctx->rsrc_ref_list);
 	INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work);
 	init_llist_head(&ctx->rsrc_put_llist);
+	INIT_LIST_HEAD(&ctx->tctx_list);
 	INIT_LIST_HEAD(&ctx->submit_state.comp.free_list);
 	INIT_LIST_HEAD(&ctx->submit_state.comp.locked_free_list);
 	return ctx;
@@ -8748,6 +8757,7 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
 static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
 {
 	struct io_uring_task *tctx = current->io_uring;
+	struct io_tctx_node *node;
 	int ret;
 
 	if (unlikely(!tctx)) {
@@ -8760,13 +8770,25 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
 		void *old = xa_load(&tctx->xa, (unsigned long)file);
 
 		if (!old) {
+			node = kmalloc(sizeof(*node), GFP_KERNEL);
+			if (!node)
+				return -ENOMEM;
+			node->ctx = ctx;
+			node->file = file;
+			node->task = current;
+
 			get_file(file);
 			ret = xa_err(xa_store(&tctx->xa, (unsigned long)file,
-						file, GFP_KERNEL));
+						node, GFP_KERNEL));
 			if (ret) {
 				fput(file);
+				kfree(node);
 				return ret;
 			}
+
+			mutex_lock(&ctx->uring_lock);
+			list_add(&node->ctx_node, &ctx->tctx_list);
+			mutex_unlock(&ctx->uring_lock);
 		}
 		tctx->last = file;
 	}
@@ -8788,23 +8810,31 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
 static void io_uring_del_task_file(unsigned long index)
 {
 	struct io_uring_task *tctx = current->io_uring;
-	struct file *file;
+	struct io_tctx_node *node;
 
-	file = xa_erase(&tctx->xa, index);
-	if (!file)
+	node = xa_erase(&tctx->xa, index);
+	if (!node)
 		return;
 
-	if (tctx->last == file)
+	WARN_ON_ONCE(current != node->task);
+	WARN_ON_ONCE(list_empty(&node->ctx_node));
+
+	mutex_lock(&node->ctx->uring_lock);
+	list_del(&node->ctx_node);
+	mutex_unlock(&node->ctx->uring_lock);
+
+	if (tctx->last == node->file)
 		tctx->last = NULL;
-	fput(file);
+	fput(node->file);
+	kfree(node);
 }
 
 static void io_uring_clean_tctx(struct io_uring_task *tctx)
 {
-	struct file *file;
+	struct io_tctx_node *node;
 	unsigned long index;
 
-	xa_for_each(&tctx->xa, index, file)
+	xa_for_each(&tctx->xa, index, node)
 		io_uring_del_task_file(index);
 	if (tctx->io_wq) {
 		io_wq_put_and_exit(tctx->io_wq);
@@ -8815,13 +8845,13 @@ static void io_uring_clean_tctx(struct io_uring_task *tctx)
 void __io_uring_files_cancel(struct files_struct *files)
 {
 	struct io_uring_task *tctx = current->io_uring;
-	struct file *file;
+	struct io_tctx_node *node;
 	unsigned long index;
 
 	/* make sure overflow events are dropped */
 	atomic_inc(&tctx->in_idle);
-	xa_for_each(&tctx->xa, index, file)
-		io_uring_cancel_task_requests(file->private_data, files);
+	xa_for_each(&tctx->xa, index, node)
+		io_uring_cancel_task_requests(node->ctx, files);
 	atomic_dec(&tctx->in_idle);
 
 	if (files)
@@ -8884,11 +8914,11 @@ void __io_uring_task_cancel(void)
 	atomic_inc(&tctx->in_idle);
 
 	if (tctx->sqpoll) {
-		struct file *file;
+		struct io_tctx_node *node;
 		unsigned long index;
 
-		xa_for_each(&tctx->xa, index, file)
-			io_uring_cancel_sqpoll(file->private_data);
+		xa_for_each(&tctx->xa, index, node)
+			io_uring_cancel_sqpoll(node->ctx);
 	}
 
 	do {

From d56d938b4bef3e1421a42023cdcd6e13c1f50831 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sat, 6 Mar 2021 11:02:13 +0000
Subject: [PATCH 0300/1820] io_uring: do ctx initiated file note removal

Another preparation patch. When full quiesce is done on ctx exit, use
task_work infra to remove corresponding to the ctx io_uring->xa entries.
For that we use the back tctx map. Also use ->in_idle to prevent
removing it while we traversing ->xa on cancellation, just ignore it.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 46 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 9a2cff0662e0..8a4ab86ae64f 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -987,6 +987,7 @@ static const struct io_op_def io_op_defs[] = {
 	[IORING_OP_UNLINKAT] = {},
 };
 
+static void io_uring_del_task_file(unsigned long index);
 static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 					 struct task_struct *task,
 					 struct files_struct *files);
@@ -8536,10 +8537,33 @@ static bool io_run_ctx_fallback(struct io_ring_ctx *ctx)
 	return executed;
 }
 
+struct io_tctx_exit {
+	struct callback_head		task_work;
+	struct completion		completion;
+	unsigned long			index;
+};
+
+static void io_tctx_exit_cb(struct callback_head *cb)
+{
+	struct io_uring_task *tctx = current->io_uring;
+	struct io_tctx_exit *work;
+
+	work = container_of(cb, struct io_tctx_exit, task_work);
+	/*
+	 * When @in_idle, we're in cancellation and it's racy to remove the
+	 * node. It'll be removed by the end of cancellation, just ignore it.
+	 */
+	if (!atomic_read(&tctx->in_idle))
+		io_uring_del_task_file(work->index);
+	complete(&work->completion);
+}
+
 static void io_ring_exit_work(struct work_struct *work)
 {
-	struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx,
-					       exit_work);
+	struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work);
+	struct io_tctx_exit exit;
+	struct io_tctx_node *node;
+	int ret;
 
 	/*
 	 * If we're doing polled IO and end up having requests being
@@ -8550,6 +8574,26 @@ static void io_ring_exit_work(struct work_struct *work)
 	do {
 		io_uring_try_cancel_requests(ctx, NULL, NULL);
 	} while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20));
+
+	mutex_lock(&ctx->uring_lock);
+	while (!list_empty(&ctx->tctx_list)) {
+		node = list_first_entry(&ctx->tctx_list, struct io_tctx_node,
+					ctx_node);
+		exit.index = (unsigned long)node->file;
+		init_completion(&exit.completion);
+		init_task_work(&exit.task_work, io_tctx_exit_cb);
+		ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL);
+		if (WARN_ON_ONCE(ret))
+			continue;
+		wake_up_process(node->task);
+
+		mutex_unlock(&ctx->uring_lock);
+		wait_for_completion(&exit.completion);
+		cond_resched();
+		mutex_lock(&ctx->uring_lock);
+	}
+	mutex_unlock(&ctx->uring_lock);
+
 	io_ring_ctx_free(ctx);
 }
 

From eebd2e37e662617a6b8041db75205f0a262ce870 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sat, 6 Mar 2021 11:02:14 +0000
Subject: [PATCH 0301/1820] io_uring: don't take task ring-file notes

With ->flush() gone we're now leaving all uring file notes until the
task dies/execs, so the ctx will not be freed until all tasks that have
ever submit a request die. It was nicer with flush but not much, we
could have locked as described ctx in many cases.

Now we guarantee that ctx outlives all tctx in a sense that
io_ring_exit_work() waits for all tctxs to drop their corresponding
enties in ->xa, and ctx won't go away until then. Hence, additional
io_uring file reference (a.k.a. task file notes) are not needed anymore.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 8a4ab86ae64f..f448213267c8 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8821,11 +8821,9 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
 			node->file = file;
 			node->task = current;
 
-			get_file(file);
 			ret = xa_err(xa_store(&tctx->xa, (unsigned long)file,
 						node, GFP_KERNEL));
 			if (ret) {
-				fput(file);
 				kfree(node);
 				return ret;
 			}
@@ -8856,6 +8854,8 @@ static void io_uring_del_task_file(unsigned long index)
 	struct io_uring_task *tctx = current->io_uring;
 	struct io_tctx_node *node;
 
+	if (!tctx)
+		return;
 	node = xa_erase(&tctx->xa, index);
 	if (!node)
 		return;
@@ -8869,7 +8869,6 @@ static void io_uring_del_task_file(unsigned long index)
 
 	if (tctx->last == node->file)
 		tctx->last = NULL;
-	fput(node->file);
 	kfree(node);
 }
 

From baf186c4d345f5a105e63df01100936ad622f369 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sat, 6 Mar 2021 11:02:15 +0000
Subject: [PATCH 0302/1820] io_uring: index io_uring->xa by ctx not file

We don't use task file notes anymore, and no need left in indexing
task->io_uring->xa by file, and replace it with ctx. It's better
design-wise, especially since we keep a dangling file, and so have to
keep an eye on not dereferencing it.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c            | 24 +++++++++++-------------
 include/linux/io_uring.h |  2 +-
 2 files changed, 12 insertions(+), 14 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index f448213267c8..01a7fa4a4889 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -809,7 +809,6 @@ struct io_kiocb {
 struct io_tctx_node {
 	struct list_head	ctx_node;
 	struct task_struct	*task;
-	struct file		*file;
 	struct io_ring_ctx	*ctx;
 };
 
@@ -8540,7 +8539,7 @@ static bool io_run_ctx_fallback(struct io_ring_ctx *ctx)
 struct io_tctx_exit {
 	struct callback_head		task_work;
 	struct completion		completion;
-	unsigned long			index;
+	struct io_ring_ctx		*ctx;
 };
 
 static void io_tctx_exit_cb(struct callback_head *cb)
@@ -8554,7 +8553,7 @@ static void io_tctx_exit_cb(struct callback_head *cb)
 	 * node. It'll be removed by the end of cancellation, just ignore it.
 	 */
 	if (!atomic_read(&tctx->in_idle))
-		io_uring_del_task_file(work->index);
+		io_uring_del_task_file((unsigned long)work->ctx);
 	complete(&work->completion);
 }
 
@@ -8579,7 +8578,7 @@ static void io_ring_exit_work(struct work_struct *work)
 	while (!list_empty(&ctx->tctx_list)) {
 		node = list_first_entry(&ctx->tctx_list, struct io_tctx_node,
 					ctx_node);
-		exit.index = (unsigned long)node->file;
+		exit.ctx = ctx;
 		init_completion(&exit.completion);
 		init_task_work(&exit.task_work, io_tctx_exit_cb);
 		ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL);
@@ -8798,7 +8797,7 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
 /*
  * Note that this task has used io_uring. We use it for cancelation purposes.
  */
-static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
+static int io_uring_add_task_file(struct io_ring_ctx *ctx)
 {
 	struct io_uring_task *tctx = current->io_uring;
 	struct io_tctx_node *node;
@@ -8810,18 +8809,17 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
 			return ret;
 		tctx = current->io_uring;
 	}
-	if (tctx->last != file) {
-		void *old = xa_load(&tctx->xa, (unsigned long)file);
+	if (tctx->last != ctx) {
+		void *old = xa_load(&tctx->xa, (unsigned long)ctx);
 
 		if (!old) {
 			node = kmalloc(sizeof(*node), GFP_KERNEL);
 			if (!node)
 				return -ENOMEM;
 			node->ctx = ctx;
-			node->file = file;
 			node->task = current;
 
-			ret = xa_err(xa_store(&tctx->xa, (unsigned long)file,
+			ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx,
 						node, GFP_KERNEL));
 			if (ret) {
 				kfree(node);
@@ -8832,7 +8830,7 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
 			list_add(&node->ctx_node, &ctx->tctx_list);
 			mutex_unlock(&ctx->uring_lock);
 		}
-		tctx->last = file;
+		tctx->last = ctx;
 	}
 
 	/*
@@ -8867,7 +8865,7 @@ static void io_uring_del_task_file(unsigned long index)
 	list_del(&node->ctx_node);
 	mutex_unlock(&node->ctx->uring_lock);
 
-	if (tctx->last == node->file)
+	if (tctx->last == node->ctx)
 		tctx->last = NULL;
 	kfree(node);
 }
@@ -9166,7 +9164,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		}
 		submitted = to_submit;
 	} else if (to_submit) {
-		ret = io_uring_add_task_file(ctx, f.file);
+		ret = io_uring_add_task_file(ctx);
 		if (unlikely(ret))
 			goto out;
 		mutex_lock(&ctx->uring_lock);
@@ -9375,7 +9373,7 @@ static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file)
 	if (fd < 0)
 		return fd;
 
-	ret = io_uring_add_task_file(ctx, file);
+	ret = io_uring_add_task_file(ctx);
 	if (ret) {
 		put_unused_fd(fd);
 		return ret;
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 7cb7bd0e334c..9761a0ec9f95 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -18,7 +18,7 @@ struct io_uring_task {
 	/* submission side */
 	struct xarray		xa;
 	struct wait_queue_head	wait;
-	struct file		*last;
+	void			*last;
 	void			*io_wq;
 	struct percpu_counter	inflight;
 	atomic_t		in_idle;

From b5bb3a24f69da92e0ec2a301452364333e45be03 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sat, 6 Mar 2021 11:02:16 +0000
Subject: [PATCH 0303/1820] io_uring: warn when ring exit takes too long

We use system_unbound_wq to run io_ring_exit_work(), so it's hard to
monitor whether removal hang or not. Add WARN_ONCE to catch hangs.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 01a7fa4a4889..945e54690b81 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8560,6 +8560,7 @@ static void io_tctx_exit_cb(struct callback_head *cb)
 static void io_ring_exit_work(struct work_struct *work)
 {
 	struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work);
+	unsigned long timeout = jiffies + HZ * 60 * 5;
 	struct io_tctx_exit exit;
 	struct io_tctx_node *node;
 	int ret;
@@ -8572,10 +8573,14 @@ static void io_ring_exit_work(struct work_struct *work)
 	 */
 	do {
 		io_uring_try_cancel_requests(ctx, NULL, NULL);
+
+		WARN_ON_ONCE(time_after(jiffies, timeout));
 	} while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20));
 
 	mutex_lock(&ctx->uring_lock);
 	while (!list_empty(&ctx->tctx_list)) {
+		WARN_ON_ONCE(time_after(jiffies, timeout));
+
 		node = list_first_entry(&ctx->tctx_list, struct io_tctx_node,
 					ctx_node);
 		exit.ctx = ctx;

From 1b00764f09b6912d25e188d972a7764a457926ba Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sat, 6 Mar 2021 11:02:17 +0000
Subject: [PATCH 0304/1820] io_uring: cancel reqs of all iowq's on ring exit

io_ring_exit_work() have to cancel all requests, including those staying
in io-wq, however it tries only cancellation of current tctx, which is
NULL. If we've got task==NULL, use the ctx-to-tctx map to go over all
tctx/io-wq and try cancellations on them.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 42 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 39 insertions(+), 3 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 945e54690b81..8c74c7799960 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8688,19 +8688,55 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx,
 	}
 }
 
+static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
+{
+	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+	return req->ctx == data;
+}
+
+static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
+{
+	struct io_tctx_node *node;
+	enum io_wq_cancel cret;
+	bool ret = false;
+
+	mutex_lock(&ctx->uring_lock);
+	list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
+		struct io_uring_task *tctx = node->task->io_uring;
+
+		/*
+		 * io_wq will stay alive while we hold uring_lock, because it's
+		 * killed after ctx nodes, which requires to take the lock.
+		 */
+		if (!tctx || !tctx->io_wq)
+			continue;
+		cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true);
+		ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
+	}
+	mutex_unlock(&ctx->uring_lock);
+
+	return ret;
+}
+
 static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 					 struct task_struct *task,
 					 struct files_struct *files)
 {
 	struct io_task_cancel cancel = { .task = task, .files = files, };
-	struct task_struct *tctx_task = task ?: current;
-	struct io_uring_task *tctx = tctx_task->io_uring;
+	struct io_uring_task *tctx = task ? task->io_uring : NULL;
 
 	while (1) {
 		enum io_wq_cancel cret;
 		bool ret = false;
 
-		if (tctx && tctx->io_wq) {
+		if (!task) {
+			ret |= io_uring_try_cancel_iowq(ctx);
+		} else if (tctx && tctx->io_wq) {
+			/*
+			 * Cancels requests of all rings, not only @ctx, but
+			 * it's fine as the task is in exit/exec.
+			 */
 			cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb,
 					       &cancel, true);
 			ret |= (cret != IO_WQ_CANCEL_NOTFOUND);

From 678eeba481d8c161203382832a4379d507050aed Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sat, 6 Mar 2021 11:02:18 +0000
Subject: [PATCH 0305/1820] io-wq: warn on creating manager while exiting

Add a simple warning making sure that nobody tries to create a new
manager while we're under IO_WQ_BIT_EXIT. That can potentially happen
due to racy work submission after final put.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 1bfdb86336e4..1ab9324e602f 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -774,6 +774,8 @@ static int io_wq_fork_manager(struct io_wq *wq)
 	if (wq->manager)
 		return 0;
 
+	WARN_ON_ONCE(test_bit(IO_WQ_BIT_EXIT, &wq->state));
+
 	init_completion(&wq->worker_done);
 	atomic_set(&wq->worker_refs, 1);
 	tsk = create_io_thread(io_wq_manager, wq, NUMA_NO_NODE);

From 7c30f36a98ae488741178d69662e4f2baa53e7f6 Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Sun, 7 Mar 2021 11:54:28 +0100
Subject: [PATCH 0306/1820] io_uring: run __io_sq_thread() with the initial
 creds from io_uring_setup()

With IORING_SETUP_ATTACH_WQ we should let __io_sq_thread() use the
initial creds from each ctx.

Signed-off-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 8c74c7799960..4d3333ca27a3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -380,6 +380,7 @@ struct io_ring_ctx {
 	/* Only used for accounting purposes */
 	struct mm_struct	*mm_account;
 
+	const struct cred	*sq_creds;	/* cred used for __io_sq_thread() */
 	struct io_sq_data	*sq_data;	/* if using sq thread polling */
 
 	struct wait_queue_head	sqo_sq_wait;
@@ -6719,7 +6720,13 @@ static int io_sq_thread(void *data)
 		sqt_spin = false;
 		cap_entries = !list_is_singular(&sqd->ctx_list);
 		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
+			const struct cred *creds = NULL;
+
+			if (ctx->sq_creds != current_cred())
+				creds = override_creds(ctx->sq_creds);
 			ret = __io_sq_thread(ctx, cap_entries);
+			if (creds)
+				revert_creds(creds);
 			if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list)))
 				sqt_spin = true;
 		}
@@ -7152,6 +7159,8 @@ static void io_sq_thread_finish(struct io_ring_ctx *ctx)
 
 		io_put_sq_data(sqd);
 		ctx->sq_data = NULL;
+		if (ctx->sq_creds)
+			put_cred(ctx->sq_creds);
 	}
 }
 
@@ -7890,6 +7899,7 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 			goto err;
 		}
 
+		ctx->sq_creds = get_current_cred();
 		ctx->sq_data = sqd;
 		io_sq_thread_park(sqd);
 		mutex_lock(&sqd->ctx_lock);

From 041474885e9707a38fad081abe30159eb6d463f9 Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Sun, 7 Mar 2021 11:54:29 +0100
Subject: [PATCH 0307/1820] io_uring: kill io_sq_thread_fork() and return
 -EOWNERDEAD if the sq_thread is gone

This brings the behavior back in line with what 5.11 and earlier did,
and this is no longer needed with the improved handling of creds
not needing to do unshare().

Signed-off-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 31 +++----------------------------
 1 file changed, 3 insertions(+), 28 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 4d3333ca27a3..7cf96be691d8 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -336,7 +336,6 @@ struct io_ring_ctx {
 		unsigned int		drain_next: 1;
 		unsigned int		eventfd_async: 1;
 		unsigned int		restricted: 1;
-		unsigned int		sqo_exec: 1;
 
 		/*
 		 * Ring buffer of indices into array of io_uring_sqe, which is
@@ -6786,7 +6785,6 @@ static int io_sq_thread(void *data)
 
 	sqd->thread = NULL;
 	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
-		ctx->sqo_exec = 1;
 		io_ring_set_wakeup_flag(ctx);
 	}
 
@@ -7846,26 +7844,6 @@ void __io_uring_free(struct task_struct *tsk)
 	tsk->io_uring = NULL;
 }
 
-static int io_sq_thread_fork(struct io_sq_data *sqd, struct io_ring_ctx *ctx)
-{
-	struct task_struct *tsk;
-	int ret;
-
-	clear_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
-	reinit_completion(&sqd->parked);
-	ctx->sqo_exec = 0;
-	sqd->task_pid = current->pid;
-	tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE);
-	if (IS_ERR(tsk))
-		return PTR_ERR(tsk);
-	ret = io_uring_alloc_task_context(tsk, ctx);
-	if (ret)
-		set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
-	sqd->thread = tsk;
-	wake_up_new_task(tsk);
-	return ret;
-}
-
 static int io_sq_offload_create(struct io_ring_ctx *ctx,
 				struct io_uring_params *p)
 {
@@ -9199,13 +9177,10 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		io_cqring_overflow_flush(ctx, false, NULL, NULL);
 
-		if (unlikely(ctx->sqo_exec)) {
-			ret = io_sq_thread_fork(ctx->sq_data, ctx);
-			if (ret)
-				goto out;
-			ctx->sqo_exec = 0;
-		}
 		ret = -EOWNERDEAD;
+		if (unlikely(ctx->sq_data->thread == NULL)) {
+			goto out;
+		}
 		if (flags & IORING_ENTER_SQ_WAKEUP)
 			wake_up(&ctx->sq_data->wait);
 		if (flags & IORING_ENTER_SQ_WAIT) {

From 30b3f68715595dee7fe4d9bd91a2252c3becdf0a Mon Sep 17 00:00:00 2001
From: Caleb Connolly <caleb@connolly.tech>
Date: Sun, 7 Mar 2021 15:12:22 -0800
Subject: [PATCH 0308/1820] Input: s6sy761 - fix coordinate read bit shift

The touch coordinate register contains the following:

        byte 3             byte 2             byte 1
+--------+--------+ +-----------------+ +-----------------+
|        |        | |                 | |                 |
| X[3:0] | Y[3:0] | |     Y[11:4]     | |     X[11:4]     |
|        |        | |                 | |                 |
+--------+--------+ +-----------------+ +-----------------+

Bytes 2 and 1 need to be shifted left by 4 bits, the least significant
nibble of each is stored in byte 3. Currently they are only
being shifted by 3 causing the reported coordinates to be incorrect.

This matches downstream examples, and has been confirmed on my
device (OnePlus 7 Pro).

Fixes: 0145a7141e59 ("Input: add support for the Samsung S6SY761 touchscreen")
Signed-off-by: Caleb Connolly <caleb@connolly.tech>
Reviewed-by: Andi Shyti <andi@etezian.org>
Link: https://lore.kernel.org/r/20210305185710.225168-1-caleb@connolly.tech
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/s6sy761.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/touchscreen/s6sy761.c b/drivers/input/touchscreen/s6sy761.c
index b63d7fdf0cd2..85a1f465c097 100644
--- a/drivers/input/touchscreen/s6sy761.c
+++ b/drivers/input/touchscreen/s6sy761.c
@@ -145,8 +145,8 @@ static void s6sy761_report_coordinates(struct s6sy761_data *sdata,
 	u8 major = event[4];
 	u8 minor = event[5];
 	u8 z = event[6] & S6SY761_MASK_Z;
-	u16 x = (event[1] << 3) | ((event[3] & S6SY761_MASK_X) >> 4);
-	u16 y = (event[2] << 3) | (event[3] & S6SY761_MASK_Y);
+	u16 x = (event[1] << 4) | ((event[3] & S6SY761_MASK_X) >> 4);
+	u16 y = (event[2] << 4) | (event[3] & S6SY761_MASK_Y);
 
 	input_mt_slot(sdata->input, tid);
 

From 9f377622a484de0818c49ee01e0ab4eedf6acd81 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@redhat.com>
Date: Sat, 6 Mar 2021 12:04:38 +0800
Subject: [PATCH 0309/1820] erofs: fix bio->bi_max_vecs behavior change

Martin reported an issue that directory read could be hung on the
latest -rc kernel with some certain image. The root cause is that
commit baa2c7c97153 ("block: set .bi_max_vecs as actual allocated
vector number") changes .bi_max_vecs behavior. bio->bi_max_vecs
is set as actual allocated vector number rather than the requested
number now.

Let's avoid using .bi_max_vecs completely instead.

Link: https://lore.kernel.org/r/20210306040438.8084-1-hsiangkao@aol.com
Reported-by: Martin DEVERA <devik@eaxlabs.cz>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
[ Gao Xiang: note that <= 5.11 kernels are not impacted. ]
Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
---
 fs/erofs/data.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index f88851c5c250..1249e74b3bf0 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -129,6 +129,7 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 					      struct page *page,
 					      erofs_off_t *last_block,
 					      unsigned int nblocks,
+					      unsigned int *eblks,
 					      bool ra)
 {
 	struct inode *const inode = mapping->host;
@@ -145,8 +146,7 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 
 	/* note that for readpage case, bio also equals to NULL */
 	if (bio &&
-	    /* not continuous */
-	    *last_block + 1 != current_block) {
+	    (*last_block + 1 != current_block || !*eblks)) {
 submit_bio_retry:
 		submit_bio(bio);
 		bio = NULL;
@@ -216,7 +216,8 @@ submit_bio_retry:
 		if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE))
 			nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE);
 
-		bio = bio_alloc(GFP_NOIO, bio_max_segs(nblocks));
+		*eblks = bio_max_segs(nblocks);
+		bio = bio_alloc(GFP_NOIO, *eblks);
 
 		bio->bi_end_io = erofs_readendio;
 		bio_set_dev(bio, sb->s_bdev);
@@ -229,16 +230,8 @@ submit_bio_retry:
 	/* out of the extent or bio is full */
 	if (err < PAGE_SIZE)
 		goto submit_bio_retry;
-
+	--*eblks;
 	*last_block = current_block;
-
-	/* shift in advance in case of it followed by too many gaps */
-	if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) {
-		/* err should reassign to 0 after submitting */
-		err = 0;
-		goto submit_bio_out;
-	}
-
 	return bio;
 
 err_out:
@@ -252,7 +245,6 @@ has_updated:
 
 	/* if updated manually, continuous pages has a gap */
 	if (bio)
-submit_bio_out:
 		submit_bio(bio);
 	return err ? ERR_PTR(err) : NULL;
 }
@@ -264,23 +256,26 @@ submit_bio_out:
 static int erofs_raw_access_readpage(struct file *file, struct page *page)
 {
 	erofs_off_t last_block;
+	unsigned int eblks;
 	struct bio *bio;
 
 	trace_erofs_readpage(page, true);
 
 	bio = erofs_read_raw_page(NULL, page->mapping,
-				  page, &last_block, 1, false);
+				  page, &last_block, 1, &eblks, false);
 
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	DBG_BUGON(bio);	/* since we have only one bio -- must be NULL */
+	if (bio)
+		submit_bio(bio);
 	return 0;
 }
 
 static void erofs_raw_access_readahead(struct readahead_control *rac)
 {
 	erofs_off_t last_block;
+	unsigned int eblks;
 	struct bio *bio = NULL;
 	struct page *page;
 
@@ -291,7 +286,7 @@ static void erofs_raw_access_readahead(struct readahead_control *rac)
 		prefetchw(&page->flags);
 
 		bio = erofs_read_raw_page(bio, rac->mapping, page, &last_block,
-				readahead_count(rac), true);
+				readahead_count(rac), &eblks, true);
 
 		/* all the page errors are ignored when readahead */
 		if (IS_ERR(bio)) {
@@ -305,7 +300,6 @@ static void erofs_raw_access_readahead(struct readahead_control *rac)
 		put_page(page);
 	}
 
-	/* the rare case (end in gaps) */
 	if (bio)
 		submit_bio(bio);
 }

From 46eb1701c046cc18c032fa68f3c8ccbf24483ee4 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Tue, 23 Feb 2021 17:02:40 +0100
Subject: [PATCH 0310/1820] hrtimer: Update softirq_expires_next correctly
 after __hrtimer_get_next_event()

hrtimer_force_reprogram() and hrtimer_interrupt() invokes
__hrtimer_get_next_event() to find the earliest expiry time of hrtimer
bases. __hrtimer_get_next_event() does not update
cpu_base::[softirq_]_expires_next to preserve reprogramming logic. That
needs to be done at the callsites.

hrtimer_force_reprogram() updates cpu_base::softirq_expires_next only when
the first expiring timer is a softirq timer and the soft interrupt is not
activated. That's wrong because cpu_base::softirq_expires_next is left
stale when the first expiring timer of all bases is a timer which expires
in hard interrupt context. hrtimer_interrupt() does never update
cpu_base::softirq_expires_next which is wrong too.

That becomes a problem when clock_settime() sets CLOCK_REALTIME forward and
the first soft expiring timer is in the CLOCK_REALTIME_SOFT base. Setting
CLOCK_REALTIME forward moves the clock MONOTONIC based expiry time of that
timer before the stale cpu_base::softirq_expires_next.

cpu_base::softirq_expires_next is cached to make the check for raising the
soft interrupt fast. In the above case the soft interrupt won't be raised
until clock monotonic reaches the stale cpu_base::softirq_expires_next
value. That's incorrect, but what's worse it that if the softirq timer
becomes the first expiring timer of all clock bases after the hard expiry
timer has been handled the reprogramming of the clockevent from
hrtimer_interrupt() will result in an interrupt storm. That happens because
the reprogramming does not use cpu_base::softirq_expires_next, it uses
__hrtimer_get_next_event() which returns the actual expiry time. Once clock
MONOTONIC reaches cpu_base::softirq_expires_next the soft interrupt is
raised and the storm subsides.

Change the logic in hrtimer_force_reprogram() to evaluate the soft and hard
bases seperately, update softirq_expires_next and handle the case when a
soft expiring timer is the first of all bases by comparing the expiry times
and updating the required cpu base fields. Split this functionality into a
separate function to be able to use it in hrtimer_interrupt() as well
without copy paste.

Fixes: 5da70160462e ("hrtimer: Implement support for softirq based hrtimers")
Reported-by: Mikael Beckius <mikael.beckius@windriver.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Mikael Beckius <mikael.beckius@windriver.com>
Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210223160240.27518-1-anna-maria@linutronix.de
---
 kernel/time/hrtimer.c | 60 ++++++++++++++++++++++++++++---------------
 1 file changed, 39 insertions(+), 21 deletions(-)

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 743c852e10f2..788b9d137de4 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -546,8 +546,11 @@ static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base,
 }
 
 /*
- * Recomputes cpu_base::*next_timer and returns the earliest expires_next but
- * does not set cpu_base::*expires_next, that is done by hrtimer_reprogram.
+ * Recomputes cpu_base::*next_timer and returns the earliest expires_next
+ * but does not set cpu_base::*expires_next, that is done by
+ * hrtimer[_force]_reprogram and hrtimer_interrupt only. When updating
+ * cpu_base::*expires_next right away, reprogramming logic would no longer
+ * work.
  *
  * When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases,
  * those timers will get run whenever the softirq gets handled, at the end of
@@ -588,6 +591,37 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_
 	return expires_next;
 }
 
+static ktime_t hrtimer_update_next_event(struct hrtimer_cpu_base *cpu_base)
+{
+	ktime_t expires_next, soft = KTIME_MAX;
+
+	/*
+	 * If the soft interrupt has already been activated, ignore the
+	 * soft bases. They will be handled in the already raised soft
+	 * interrupt.
+	 */
+	if (!cpu_base->softirq_activated) {
+		soft = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT);
+		/*
+		 * Update the soft expiry time. clock_settime() might have
+		 * affected it.
+		 */
+		cpu_base->softirq_expires_next = soft;
+	}
+
+	expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_HARD);
+	/*
+	 * If a softirq timer is expiring first, update cpu_base->next_timer
+	 * and program the hardware with the soft expiry time.
+	 */
+	if (expires_next > soft) {
+		cpu_base->next_timer = cpu_base->softirq_next_timer;
+		expires_next = soft;
+	}
+
+	return expires_next;
+}
+
 static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
 {
 	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
@@ -628,23 +662,7 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 {
 	ktime_t expires_next;
 
-	/*
-	 * Find the current next expiration time.
-	 */
-	expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
-
-	if (cpu_base->next_timer && cpu_base->next_timer->is_soft) {
-		/*
-		 * When the softirq is activated, hrtimer has to be
-		 * programmed with the first hard hrtimer because soft
-		 * timer interrupt could occur too late.
-		 */
-		if (cpu_base->softirq_activated)
-			expires_next = __hrtimer_get_next_event(cpu_base,
-								HRTIMER_ACTIVE_HARD);
-		else
-			cpu_base->softirq_expires_next = expires_next;
-	}
+	expires_next = hrtimer_update_next_event(cpu_base);
 
 	if (skip_equal && expires_next == cpu_base->expires_next)
 		return;
@@ -1644,8 +1662,8 @@ retry:
 
 	__hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD);
 
-	/* Reevaluate the clock bases for the next expiry */
-	expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
+	/* Reevaluate the clock bases for the [soft] next expiry */
+	expires_next = hrtimer_update_next_event(cpu_base);
 	/*
 	 * Store the new expiry value so the migration code can verify
 	 * against it.

From 140a776833957539c84301dbdb4c3013876de118 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Mon, 8 Mar 2021 11:26:25 +0200
Subject: [PATCH 0311/1820] ARM: dts: Drop duplicate sha2md5_fck to fix
 clk_disable race

We have a duplicate legacy clock defined for sha2md5_fck that can
sometimes race with clk_disable() with the dts configured clock
for OMAP4_SHA2MD5_CLKCTRL when unused clocks are disabled during
boot causing an "Unhandled fault: imprecise external abort".

Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/boot/dts/omap44xx-clocks.dtsi | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/arch/arm/boot/dts/omap44xx-clocks.dtsi b/arch/arm/boot/dts/omap44xx-clocks.dtsi
index 532868591107..1f1c04d8f472 100644
--- a/arch/arm/boot/dts/omap44xx-clocks.dtsi
+++ b/arch/arm/boot/dts/omap44xx-clocks.dtsi
@@ -770,14 +770,6 @@
 		ti,max-div = <2>;
 	};
 
-	sha2md5_fck: sha2md5_fck@15c8 {
-		#clock-cells = <0>;
-		compatible = "ti,gate-clock";
-		clocks = <&l3_div_ck>;
-		ti,bit-shift = <1>;
-		reg = <0x15c8>;
-	};
-
 	usb_phy_cm_clk32k: usb_phy_cm_clk32k@640 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";

From 77335a040178a0456d4eabc8bf17a7ca3ee4a327 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Mon, 8 Mar 2021 11:30:45 +0200
Subject: [PATCH 0312/1820] ARM: dts: Fix moving mmc devices with aliases for
 omap4 & 5

Fix moving mmc devices with dts aliases as discussed on the lists.
Without this we now have internal eMMC mmc1 show up as mmc2 compared
to the earlier order of devices.

Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/boot/dts/omap4.dtsi | 5 +++++
 arch/arm/boot/dts/omap5.dtsi | 5 +++++
 2 files changed, 10 insertions(+)

diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 72e4f6481776..4a9f9496a867 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -22,6 +22,11 @@
 		i2c1 = &i2c2;
 		i2c2 = &i2c3;
 		i2c3 = &i2c4;
+		mmc0 = &mmc1;
+		mmc1 = &mmc2;
+		mmc2 = &mmc3;
+		mmc3 = &mmc4;
+		mmc4 = &mmc5;
 		serial0 = &uart1;
 		serial1 = &uart2;
 		serial2 = &uart3;
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index e025b7c9a357..ee821d0ab364 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -25,6 +25,11 @@
 		i2c2 = &i2c3;
 		i2c3 = &i2c4;
 		i2c4 = &i2c5;
+		mmc0 = &mmc1;
+		mmc1 = &mmc2;
+		mmc2 = &mmc3;
+		mmc3 = &mmc4;
+		mmc4 = &mmc5;
 		serial0 = &uart1;
 		serial1 = &uart2;
 		serial2 = &uart3;

From eba8e1af5a61e61e5d77e1dfe1e8e20735ebc9c6 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Tue, 23 Feb 2021 19:52:20 +0100
Subject: [PATCH 0313/1820] s390/time,idle: get rid of unsigned long long

Get rid of unsigned long long, and use unsigned long instead
everywhere. The usage of unsigned long long is a leftover from
31 bit kernel support.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/idle.h  | 12 ++++++------
 arch/s390/include/asm/timex.h | 36 +++++++++++++++++------------------
 arch/s390/kernel/idle.c       | 12 ++++++------
 arch/s390/kernel/time.c       | 28 +++++++++++++--------------
 arch/s390/kvm/interrupt.c     |  2 +-
 drivers/s390/cio/device_fsm.c |  2 +-
 6 files changed, 46 insertions(+), 46 deletions(-)

diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h
index b04f6a794cdf..5cea629c548e 100644
--- a/arch/s390/include/asm/idle.h
+++ b/arch/s390/include/asm/idle.h
@@ -14,12 +14,12 @@
 
 struct s390_idle_data {
 	seqcount_t seqcount;
-	unsigned long long idle_count;
-	unsigned long long idle_time;
-	unsigned long long clock_idle_enter;
-	unsigned long long clock_idle_exit;
-	unsigned long long timer_idle_enter;
-	unsigned long long timer_idle_exit;
+	unsigned long idle_count;
+	unsigned long idle_time;
+	unsigned long clock_idle_enter;
+	unsigned long clock_idle_exit;
+	unsigned long timer_idle_enter;
+	unsigned long timer_idle_exit;
 	unsigned long mt_cycles_enter[8];
 };
 
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index c4e23e925665..f6326c6d2abe 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -98,10 +98,10 @@ extern unsigned char ptff_function_mask[16];
 
 /* Query TOD offset result */
 struct ptff_qto {
-	unsigned long long physical_clock;
-	unsigned long long tod_offset;
-	unsigned long long logical_tod_offset;
-	unsigned long long tod_epoch_difference;
+	unsigned long physical_clock;
+	unsigned long tod_offset;
+	unsigned long logical_tod_offset;
+	unsigned long tod_epoch_difference;
 } __packed;
 
 static inline int ptff_query(unsigned int nr)
@@ -151,9 +151,9 @@ struct ptff_qui {
 	rc;								\
 })
 
-static inline unsigned long long local_tick_disable(void)
+static inline unsigned long local_tick_disable(void)
 {
-	unsigned long long old;
+	unsigned long old;
 
 	old = S390_lowcore.clock_comparator;
 	S390_lowcore.clock_comparator = clock_comparator_max;
@@ -161,7 +161,7 @@ static inline unsigned long long local_tick_disable(void)
 	return old;
 }
 
-static inline void local_tick_enable(unsigned long long comp)
+static inline void local_tick_enable(unsigned long comp)
 {
 	S390_lowcore.clock_comparator = comp;
 	set_clock_comparator(S390_lowcore.clock_comparator);
@@ -169,9 +169,9 @@ static inline void local_tick_enable(unsigned long long comp)
 
 #define CLOCK_TICK_RATE		1193180 /* Underlying HZ */
 
-typedef unsigned long long cycles_t;
+typedef unsigned long cycles_t;
 
-static inline unsigned long long get_tod_clock(void)
+static inline unsigned long get_tod_clock(void)
 {
 	union tod_clock clk;
 
@@ -179,10 +179,10 @@ static inline unsigned long long get_tod_clock(void)
 	return clk.tod;
 }
 
-static inline unsigned long long get_tod_clock_fast(void)
+static inline unsigned long get_tod_clock_fast(void)
 {
 #ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
-	unsigned long long clk;
+	unsigned long clk;
 
 	asm volatile("stckf %0" : "=Q" (clk) : : "cc");
 	return clk;
@@ -208,9 +208,9 @@ extern union tod_clock tod_clock_base;
  * Therefore preemption must be disabled, otherwise the returned
  * value is not guaranteed to be monotonic.
  */
-static inline unsigned long long get_tod_clock_monotonic(void)
+static inline unsigned long get_tod_clock_monotonic(void)
 {
-	unsigned long long tod;
+	unsigned long tod;
 
 	preempt_disable_notrace();
 	tod = get_tod_clock() - tod_clock_base.tod;
@@ -237,7 +237,7 @@ static inline unsigned long long get_tod_clock_monotonic(void)
  * -> ns = (th * 125) + ((tl * 125) >> 9);
  *
  */
-static inline unsigned long long tod_to_ns(unsigned long long todval)
+static inline unsigned long tod_to_ns(unsigned long todval)
 {
 	return ((todval >> 9) * 125) + (((todval & 0x1ff) * 125) >> 9);
 }
@@ -249,10 +249,10 @@ static inline unsigned long long tod_to_ns(unsigned long long todval)
  *
  * Returns: true if a is later than b
  */
-static inline int tod_after(unsigned long long a, unsigned long long b)
+static inline int tod_after(unsigned long a, unsigned long b)
 {
 	if (MACHINE_HAS_SCC)
-		return (long long) a > (long long) b;
+		return (long) a > (long) b;
 	return a > b;
 }
 
@@ -263,10 +263,10 @@ static inline int tod_after(unsigned long long a, unsigned long long b)
  *
  * Returns: true if a is later than b
  */
-static inline int tod_after_eq(unsigned long long a, unsigned long long b)
+static inline int tod_after_eq(unsigned long a, unsigned long b)
 {
 	if (MACHINE_HAS_SCC)
-		return (long long) a >= (long long) b;
+		return (long) a >= (long) b;
 	return a >= b;
 }
 
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 812073ea073e..4bf1ee293f2b 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -47,7 +47,7 @@ void account_idle_time_irq(void)
 void arch_cpu_idle(void)
 {
 	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
-	unsigned long long idle_time;
+	unsigned long idle_time;
 	unsigned long psw_mask;
 
 	/* Wait for external, I/O or machine check interrupt. */
@@ -73,7 +73,7 @@ static ssize_t show_idle_count(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
-	unsigned long long idle_count;
+	unsigned long idle_count;
 	unsigned int seq;
 
 	do {
@@ -82,14 +82,14 @@ static ssize_t show_idle_count(struct device *dev,
 		if (READ_ONCE(idle->clock_idle_enter))
 			idle_count++;
 	} while (read_seqcount_retry(&idle->seqcount, seq));
-	return sprintf(buf, "%llu\n", idle_count);
+	return sprintf(buf, "%lu\n", idle_count);
 }
 DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
 
 static ssize_t show_idle_time(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	unsigned long long now, idle_time, idle_enter, idle_exit, in_idle;
+	unsigned long now, idle_time, idle_enter, idle_exit, in_idle;
 	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
 	unsigned int seq;
 
@@ -109,14 +109,14 @@ static ssize_t show_idle_time(struct device *dev,
 		}
 	}
 	idle_time += in_idle;
-	return sprintf(buf, "%llu\n", idle_time >> 12);
+	return sprintf(buf, "%lu\n", idle_time >> 12);
 }
 DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
 
 u64 arch_cpu_idle_time(int cpu)
 {
 	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
-	unsigned long long now, idle_enter, idle_exit, in_idle;
+	unsigned long now, idle_enter, idle_exit, in_idle;
 	unsigned int seq;
 
 	do {
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 06bcfa636638..165da961f901 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -68,10 +68,10 @@ EXPORT_SYMBOL(s390_epoch_delta_notifier);
 
 unsigned char ptff_function_mask[16];
 
-static unsigned long long lpar_offset;
-static unsigned long long initial_leap_seconds;
-static unsigned long long tod_steering_end;
-static long long tod_steering_delta;
+static unsigned long lpar_offset;
+static unsigned long initial_leap_seconds;
+static unsigned long tod_steering_end;
+static long tod_steering_delta;
 
 /*
  * Get time offsets with PTFF
@@ -96,7 +96,7 @@ void __init time_early_init(void)
 
 	/* get initial leap seconds */
 	if (ptff_query(PTFF_QUI) && ptff(&qui, sizeof(qui), PTFF_QUI) == 0)
-		initial_leap_seconds = (unsigned long long)
+		initial_leap_seconds = (unsigned long)
 			((long) qui.old_leap * 4096000000L);
 }
 
@@ -222,7 +222,7 @@ void __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
 
 static u64 read_tod_clock(struct clocksource *cs)
 {
-	unsigned long long now, adj;
+	unsigned long now, adj;
 
 	preempt_disable(); /* protect from changes to steering parameters */
 	now = get_tod_clock();
@@ -362,7 +362,7 @@ static inline int check_sync_clock(void)
  * Apply clock delta to the global data structures.
  * This is called once on the CPU that performed the clock sync.
  */
-static void clock_sync_global(unsigned long long delta)
+static void clock_sync_global(unsigned long delta)
 {
 	unsigned long now, adj;
 	struct ptff_qto qto;
@@ -378,7 +378,7 @@ static void clock_sync_global(unsigned long long delta)
 			-(adj >> 15) : (adj >> 15);
 	tod_steering_delta += delta;
 	if ((abs(tod_steering_delta) >> 48) != 0)
-		panic("TOD clock sync offset %lli is too large to drift\n",
+		panic("TOD clock sync offset %li is too large to drift\n",
 		      tod_steering_delta);
 	tod_steering_end = now + (abs(tod_steering_delta) << 15);
 	vdso_data->arch_data.tod_steering_end = tod_steering_end;
@@ -394,7 +394,7 @@ static void clock_sync_global(unsigned long long delta)
  * Apply clock delta to the per-CPU data structures of this CPU.
  * This is called for each online CPU after the call to clock_sync_global.
  */
-static void clock_sync_local(unsigned long long delta)
+static void clock_sync_local(unsigned long delta)
 {
 	/* Add the delta to the clock comparator. */
 	if (S390_lowcore.clock_comparator != clock_comparator_max) {
@@ -418,7 +418,7 @@ static void __init time_init_wq(void)
 struct clock_sync_data {
 	atomic_t cpus;
 	int in_sync;
-	unsigned long long clock_delta;
+	unsigned long clock_delta;
 };
 
 /*
@@ -538,7 +538,7 @@ static int stpinfo_valid(void)
 static int stp_sync_clock(void *data)
 {
 	struct clock_sync_data *sync = data;
-	unsigned long long clock_delta, flags;
+	u64 clock_delta, flags;
 	static int first;
 	int rc;
 
@@ -720,8 +720,8 @@ static ssize_t ctn_id_show(struct device *dev,
 
 	mutex_lock(&stp_mutex);
 	if (stpinfo_valid())
-		ret = sprintf(buf, "%016llx\n",
-			      *(unsigned long long *) stp_info.ctnid);
+		ret = sprintf(buf, "%016lx\n",
+			      *(unsigned long *) stp_info.ctnid);
 	mutex_unlock(&stp_mutex);
 	return ret;
 }
@@ -794,7 +794,7 @@ static ssize_t leap_seconds_scheduled_show(struct device *dev,
 	if (!stzi.lsoib.p)
 		return sprintf(buf, "0,0\n");
 
-	return sprintf(buf, "%llu,%d\n",
+	return sprintf(buf, "%lu,%d\n",
 		       tod_to_ns(stzi.lsoib.nlsout - TOD_UNIX_EPOCH) / NSEC_PER_SEC,
 		       stzi.lsoib.nlso - stzi.lsoib.also);
 }
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index e3183bd05910..d548d60caed2 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1287,7 +1287,7 @@ static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
 			/* already expired? */
 			if (cputm >> 63)
 				return 0;
-			return min(sltime, tod_to_ns(cputm));
+			return min_t(u64, sltime, tod_to_ns(cputm));
 		}
 	} else if (cpu_timer_interrupts_enabled(vcpu)) {
 		sltime = kvm_s390_get_cpu_timer(vcpu);
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 6420b197bb05..05e136cfb8be 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -47,7 +47,7 @@ static void ccw_timeout_log(struct ccw_device *cdev)
 	orb = &private->orb;
 	cc = stsch(sch->schid, &schib);
 
-	printk(KERN_WARNING "cio: ccw device timeout occurred at %llx, "
+	printk(KERN_WARNING "cio: ccw device timeout occurred at %lx, "
 	       "device information:\n", get_tod_clock());
 	printk(KERN_WARNING "cio: orb:\n");
 	print_hex_dump(KERN_WARNING, "cio:  ", DUMP_PREFIX_NONE, 16, 1,

From f9d8cbf33e9fceee671a49760cdcfa4be6a55102 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 17 Feb 2021 12:47:41 +0100
Subject: [PATCH 0314/1820] s390/topology: remove always false if check

The cpumask being checked in cpu_group_map() must have at least one
cpu set; therefore remove the check.

Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/topology.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index e7ce447651b9..bfcc327acc6b 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -76,8 +76,6 @@ static void cpu_group_map(cpumask_t *dst, struct mask_info *info, unsigned int c
 			}
 			info = info->next;
 		}
-		if (cpumask_empty(&mask))
-			cpumask_copy(&mask, cpumask_of(cpu));
 		break;
 	case TOPOLOGY_MODE_PACKAGE:
 		cpumask_copy(&mask, cpu_present_mask);

From c41b20de1a7c9a41ceab293a6f08927312ada679 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Thu, 25 Feb 2021 14:28:52 +0100
Subject: [PATCH 0315/1820] s390/cpumf: remove 60 seconds read limit

Remove the 60 seconds read interval limit. Do not impose any limit
at all and allow read of complete counter sets.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/perf_cpum_cf_diag.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index db4877bbb9aa..5eebc912df5a 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -29,9 +29,7 @@
 #include <asm/perf_cpum_cf_diag.h>
 
 #define	CF_DIAG_CTRSET_DEF		0xfeef	/* Counter set header mark */
-#define CF_DIAG_MIN_INTERVAL		60	/* Minimum counter set read */
 						/* interval in seconds */
-static unsigned long cf_diag_interval = CF_DIAG_MIN_INTERVAL;
 static unsigned int cf_diag_cpu_speed;
 static debug_info_t *cf_diag_dbg;
 
@@ -729,7 +727,6 @@ static DEFINE_MUTEX(cf_diag_ctrset_mutex);
 static struct cf_diag_ctrset {
 	unsigned long ctrset;		/* Bit mask of counter set to read */
 	cpumask_t mask;			/* CPU mask to read from */
-	time64_t lastread;		/* Epoch counter set last read */
 } cf_diag_ctrset;
 
 static void cf_diag_ctrset_clear(void)
@@ -866,27 +863,16 @@ static int cf_diag_all_read(unsigned long arg)
 {
 	struct cf_diag_call_on_cpu_parm p;
 	cpumask_var_t mask;
-	time64_t now;
-	int rc = 0;
+	int rc;
 
 	debug_sprintf_event(cf_diag_dbg, 5, "%s\n", __func__);
 	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
 		return -ENOMEM;
-	now = ktime_get_seconds();
-	if (cf_diag_ctrset.lastread + cf_diag_interval > now) {
-		debug_sprintf_event(cf_diag_dbg, 5, "%s now %lld "
-				    " lastread %lld\n", __func__, now,
-				    cf_diag_ctrset.lastread);
-		rc = -EAGAIN;
-		goto out;
-	} else {
-		cf_diag_ctrset.lastread = now;
-	}
+
 	p.sets = cf_diag_ctrset.ctrset;
 	cpumask_and(mask, &cf_diag_ctrset.mask, cpu_online_mask);
 	on_each_cpu_mask(mask, cf_diag_cpu_read, &p, 1);
 	rc = cf_diag_all_copy(arg, mask);
-out:
 	free_cpumask_var(mask);
 	debug_sprintf_event(cf_diag_dbg, 5, "%s rc %d\n", __func__, rc);
 	return rc;

From 7449ca87312a5b0390b765be65a126e6e5451026 Mon Sep 17 00:00:00 2001
From: Alexander Egorenkov <egorenar@linux.ibm.com>
Date: Fri, 26 Feb 2021 11:21:05 +0100
Subject: [PATCH 0316/1820] s390/zcore: no need to check return value of
 debugfs_create functions

When calling debugfs functions, there is no need to ever check the
return value.  The function can work or not, but the code logic should
never do something different based on this.

See commit 7dd541a3fb34 ("s390: no need to check return value of debugfs_create functions").

Signed-off-by: Alexander Egorenkov <egorenar@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 drivers/s390/char/zcore.c | 18 +-----------------
 1 file changed, 1 insertion(+), 17 deletions(-)

diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index 1515fdc3c1ab..1bf507c00eb6 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -293,28 +293,12 @@ static int __init zcore_init(void)
 		goto fail;
 
 	zcore_dir = debugfs_create_dir("zcore" , NULL);
-	if (!zcore_dir) {
-		rc = -ENOMEM;
-		goto fail;
-	}
 	zcore_reipl_file = debugfs_create_file("reipl", S_IRUSR, zcore_dir,
 						NULL, &zcore_reipl_fops);
-	if (!zcore_reipl_file) {
-		rc = -ENOMEM;
-		goto fail_dir;
-	}
 	zcore_hsa_file = debugfs_create_file("hsa", S_IRUSR|S_IWUSR, zcore_dir,
 					     NULL, &zcore_hsa_fops);
-	if (!zcore_hsa_file) {
-		rc = -ENOMEM;
-		goto fail_reipl_file;
-	}
-	return 0;
 
-fail_reipl_file:
-	debugfs_remove(zcore_reipl_file);
-fail_dir:
-	debugfs_remove(zcore_dir);
+	return 0;
 fail:
 	diag308(DIAG308_REL_HSA, NULL);
 	return rc;

From dabdfac0e85c8c1e811b10c08742f49285e78a17 Mon Sep 17 00:00:00 2001
From: Alexander Egorenkov <egorenar@linux.ibm.com>
Date: Thu, 25 Feb 2021 14:28:52 +0100
Subject: [PATCH 0317/1820] s390/zcore: release dump save area on restart or
 power down

The zFCP/NVMe standalone dumper is supposed to release the dump save area
resource as soon as possible but might fail to do so, for instance, if it
crashes. To avoid this situation, register a reboot notifier and ensure
the dump save area resource is released on reboot or power down.

Signed-off-by: Alexander Egorenkov <egorenar@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 drivers/s390/char/zcore.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index 1bf507c00eb6..bd3c724bf695 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/debugfs.h>
+#include <linux/reboot.h>
 
 #include <asm/asm-offsets.h>
 #include <asm/ipl.h>
@@ -238,6 +239,28 @@ static int __init zcore_reipl_init(void)
 	return 0;
 }
 
+static int zcore_reboot_and_on_panic_handler(struct notifier_block *self,
+					     unsigned long	   event,
+					     void		   *data)
+{
+	if (hsa_available)
+		release_hsa();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block zcore_reboot_notifier = {
+	.notifier_call	= zcore_reboot_and_on_panic_handler,
+	/* we need to be notified before reipl and kdump */
+	.priority	= INT_MAX,
+};
+
+static struct notifier_block zcore_on_panic_notifier = {
+	.notifier_call	= zcore_reboot_and_on_panic_handler,
+	/* we need to be notified before reipl and kdump */
+	.priority	= INT_MAX,
+};
+
 static int __init zcore_init(void)
 {
 	unsigned char arch;
@@ -298,6 +321,9 @@ static int __init zcore_init(void)
 	zcore_hsa_file = debugfs_create_file("hsa", S_IRUSR|S_IWUSR, zcore_dir,
 					     NULL, &zcore_hsa_fops);
 
+	register_reboot_notifier(&zcore_reboot_notifier);
+	atomic_notifier_chain_register(&panic_notifier_list, &zcore_on_panic_notifier);
+
 	return 0;
 fail:
 	diag308(DIAG308_REL_HSA, NULL);

From 46b635b6abcf2ee106d36f2e84e942f56030c8f5 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 26 Feb 2021 15:00:56 +0100
Subject: [PATCH 0318/1820] s390/cpumf: rename header file to hwctrset.h

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Suggested-by: Hendrick Brueckner <brueckner@linux.ibm.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/uapi/asm/{perf_cpum_cf_diag.h => hwctrset.h} | 0
 arch/s390/kernel/perf_cpum_cf_diag.c                           | 2 +-
 2 files changed, 1 insertion(+), 1 deletion(-)
 rename arch/s390/include/uapi/asm/{perf_cpum_cf_diag.h => hwctrset.h} (100%)

diff --git a/arch/s390/include/uapi/asm/perf_cpum_cf_diag.h b/arch/s390/include/uapi/asm/hwctrset.h
similarity index 100%
rename from arch/s390/include/uapi/asm/perf_cpum_cf_diag.h
rename to arch/s390/include/uapi/asm/hwctrset.h
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index 5eebc912df5a..bc302b86ce28 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -26,7 +26,7 @@
 #include <asm/timex.h>
 #include <asm/debug.h>
 
-#include <asm/perf_cpum_cf_diag.h>
+#include <asm/hwctrset.h>
 
 #define	CF_DIAG_CTRSET_DEF		0xfeef	/* Counter set header mark */
 						/* interval in seconds */

From 51c44babdc19aaf882e1213325a0ba291573308f Mon Sep 17 00:00:00 2001
From: Wang Qing <wangqing@vivo.com>
Date: Mon, 1 Mar 2021 20:01:33 +0800
Subject: [PATCH 0319/1820] s390/cio: return -EFAULT if copy_to_user() fails

The copy_to_user() function returns the number of bytes remaining to be
copied, but we want to return -EFAULT if the copy doesn't complete.

Fixes: e01bcdd61320 ("vfio: ccw: realize VFIO_DEVICE_GET_REGION_INFO ioctl")
Signed-off-by: Wang Qing <wangqing@vivo.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Link: https://lore.kernel.org/r/1614600093-13992-1-git-send-email-wangqing@vivo.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_ops.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 68106be4ba7a..557d0b888cd3 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -543,7 +543,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 		if (ret)
 			return ret;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
 	}
 	case VFIO_DEVICE_GET_REGION_INFO:
 	{
@@ -561,7 +561,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 		if (ret)
 			return ret;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
 	}
 	case VFIO_DEVICE_GET_IRQ_INFO:
 	{

From 942df4be7ab40195e2a839e9de81951a5862bc5b Mon Sep 17 00:00:00 2001
From: Wang Qing <wangqing@vivo.com>
Date: Mon, 1 Mar 2021 20:08:21 +0800
Subject: [PATCH 0320/1820] s390/crypto: return -EFAULT if copy_to_user() fails

The copy_to_user() function returns the number of bytes remaining to be
copied, but we want to return -EFAULT if the copy doesn't complete.

Fixes: e06670c5fe3b ("s390: vfio-ap: implement VFIO_DEVICE_GET_INFO ioctl")
Signed-off-by: Wang Qing <wangqing@vivo.com>
Reviewed-by: Tony Krowiak <akrowiak@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Link: https://lore.kernel.org/r/1614600502-16714-1-git-send-email-wangqing@vivo.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 drivers/s390/crypto/vfio_ap_ops.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 41fc2e4135fe..1ffdd411201c 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -1286,7 +1286,7 @@ static int vfio_ap_mdev_get_device_info(unsigned long arg)
 	info.num_regions = 0;
 	info.num_irqs = 0;
 
-	return copy_to_user((void __user *)arg, &info, minsz);
+	return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
 }
 
 static ssize_t vfio_ap_mdev_ioctl(struct mdev_device *mdev,

From 1c0a9c7997325ef7a8f71fca2e1e6091e757c94b Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Thu, 25 Feb 2021 14:15:36 +0800
Subject: [PATCH 0321/1820] s390/cpumf: remove unneeded semicolon

Fix the following coccicheck warnings:

./arch/s390/kernel/perf_cpum_cf.c:272:2-3: Unneeded semicolon.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Link: https://lore.kernel.org/r/1614233736-87331-1-git-send-email-jiapeng.chong@linux.alibaba.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/perf_cpum_cf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 0eb1d1cc53a8..b3beef64d3d4 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -269,7 +269,7 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
 	case CPUMF_CTR_SET_MAX:
 		/* The counter could not be associated to a counter set */
 		return -EINVAL;
-	};
+	}
 
 	/* Initialize for using the CPU-measurement counter facility */
 	if (!atomic_inc_not_zero(&num_events)) {

From db232eb42c21b7bca8e46c7e74676754b8fe06ea Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 24 Aug 2020 21:56:16 -0700
Subject: [PATCH 0322/1820] s390/tty3270: avoid comma separated statements

Use semicolons and braces.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Link: https://lore.kernel.org/r/9988babd9cca4ac841961d9f0bbf5e49caa87659.1598331149.git.joe@perches.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 drivers/s390/char/tty3270.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c
index 15692449a1c3..307a80f85c07 100644
--- a/drivers/s390/char/tty3270.c
+++ b/drivers/s390/char/tty3270.c
@@ -424,8 +424,10 @@ tty3270_update(struct timer_list *t)
 			 * last output position matches the start address
 			 * of this line.
 			 */
-			if (s->string[1] == sba[0] && s->string[2] == sba[1])
-				str += 3, len -= 3;
+			if (s->string[1] == sba[0] && s->string[2] == sba[1]) {
+				str += 3;
+				len -= 3;
+			}
 			if (raw3270_request_add_data(wrq, str, len) != 0)
 				break;
 			list_del_init(&s->update);

From d9c48a948d29bcb22f4fe61a81b718ef6de561a0 Mon Sep 17 00:00:00 2001
From: Eric Farman <farman@linux.ibm.com>
Date: Mon, 1 Mar 2021 19:33:24 +0100
Subject: [PATCH 0323/1820] s390/cio: return -EFAULT if copy_to_user() fails

Fixes: 120e214e504f ("vfio: ccw: realize VFIO_DEVICE_G(S)ET_IRQ_INFO ioctls")
Signed-off-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_ops.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 557d0b888cd3..767ac41686fe 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -582,7 +582,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 		if (info.count == -1)
 			return -EINVAL;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
 	}
 	case VFIO_DEVICE_SET_IRQS:
 	{

From d0ed78e1780eb3738f9c106fbaff6a1181017cd3 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 1 Mar 2021 21:02:49 +0100
Subject: [PATCH 0324/1820] s390,alpha: make TMPFS_INODE64 available again

Both s390 and alpha have been switched to 64-bit ino_t with
commit 96c0a6a72d18 ("s390,alpha: switch to 64-bit ino_t").
Therefore enable TMPFS_INODE64 for both architectures again.

Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Link: https://lore.kernel.org/linux-mm/YCV7QiyoweJwvN+m@osiris/
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 fs/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/Kconfig b/fs/Kconfig
index 462253ae483a..a55bda4233bb 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -203,7 +203,7 @@ config TMPFS_XATTR
 
 config TMPFS_INODE64
 	bool "Use 64-bit ino_t by default in tmpfs"
-	depends on TMPFS && 64BIT && !(S390 || ALPHA)
+	depends on TMPFS && 64BIT
 	default n
 	help
 	  tmpfs has historically used only inode numbers as wide as an unsigned

From d50aa69d36be43fa8927fd8ef305c4af88b6b450 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 1 Mar 2021 21:48:16 +0100
Subject: [PATCH 0325/1820] s390: update defconfigs

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/configs/debug_defconfig    | 16 +++-------------
 arch/s390/configs/defconfig          | 11 ++---------
 arch/s390/configs/zfcpdump_defconfig |  1 -
 3 files changed, 5 insertions(+), 23 deletions(-)

diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 02056b024091..dc0b69058ac4 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -275,9 +275,9 @@ CONFIG_IP_VS_DH=m
 CONFIG_IP_VS_SH=m
 CONFIG_IP_VS_SED=m
 CONFIG_IP_VS_NQ=m
+CONFIG_IP_VS_TWOS=m
 CONFIG_IP_VS_FTP=m
 CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_IP_NF_IPTABLES=m
@@ -298,7 +298,6 @@ CONFIG_IP_NF_SECURITY=m
 CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_TABLES_IPV6=y
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
@@ -481,7 +480,6 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_VENDOR_AURORA is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_BROCADE is not set
 # CONFIG_NET_VENDOR_CADENCE is not set
@@ -581,7 +579,6 @@ CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
-# CONFIG_SURFACE_PLATFORMS is not set
 CONFIG_S390_CCW_IOMMU=y
 CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
@@ -635,6 +632,7 @@ CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_INODE64=y
 CONFIG_HUGETLBFS=y
 CONFIG_CONFIGFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -714,12 +712,8 @@ CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
@@ -731,7 +725,6 @@ CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4=m
@@ -796,12 +789,9 @@ CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
 CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
 CONFIG_SLUB_DEBUG_ON=y
 CONFIG_SLUB_STATS=y
-CONFIG_DEBUG_KMEMLEAK=y
-CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_VM=y
 CONFIG_DEBUG_VM_VMACACHE=y
-CONFIG_DEBUG_VM_RB=y
 CONFIG_DEBUG_VM_PGFLAGS=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
@@ -838,6 +828,7 @@ CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_FTRACE_STARTUP_TEST=y
 # CONFIG_EVENT_TRACE_STARTUP_TEST is not set
+CONFIG_DEBUG_ENTRY=y
 CONFIG_NOTIFIER_ERROR_INJECTION=m
 CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
 CONFIG_FAULT_INJECTION=y
@@ -861,4 +852,3 @@ CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_TEST_BITOPS=m
 CONFIG_TEST_BPF=m
-CONFIG_DEBUG_ENTRY=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index bac721a501da..320379da96d9 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -266,9 +266,9 @@ CONFIG_IP_VS_DH=m
 CONFIG_IP_VS_SH=m
 CONFIG_IP_VS_SED=m
 CONFIG_IP_VS_NQ=m
+CONFIG_IP_VS_TWOS=m
 CONFIG_IP_VS_FTP=m
 CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_IP_NF_IPTABLES=m
@@ -289,7 +289,6 @@ CONFIG_IP_NF_SECURITY=m
 CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_TABLES_IPV6=y
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
@@ -473,7 +472,6 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_VENDOR_AURORA is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_BROCADE is not set
 # CONFIG_NET_VENDOR_CADENCE is not set
@@ -573,7 +571,6 @@ CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
-# CONFIG_SURFACE_PLATFORMS is not set
 CONFIG_S390_CCW_IOMMU=y
 CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
@@ -623,6 +620,7 @@ CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_INODE64=y
 CONFIG_HUGETLBFS=y
 CONFIG_CONFIGFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -703,12 +701,8 @@ CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
@@ -720,7 +714,6 @@ CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index acf982a2ae4c..039fd499b4a9 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -61,7 +61,6 @@ CONFIG_RAW_DRIVER=y
 # CONFIG_HID is not set
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_VHOST_MENU is not set
-# CONFIG_SURFACE_PLATFORMS is not set
 # CONFIG_IOMMU_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set

From 78c7cccaab9d5f9ead44579d79dd7d13a05aec7e Mon Sep 17 00:00:00 2001
From: Alexander Egorenkov <egorenar@linux.ibm.com>
Date: Fri, 26 Feb 2021 09:40:47 +0100
Subject: [PATCH 0326/1820] s390: remove IBM_PARTITION and CONFIGFS_FS from
 zfcpdump defconfig

Remove by zfcpdump unused CONFIG_IBM_PARTITION and CONFIG_CONFIGFS_FS.

Signed-off-by: Alexander Egorenkov <egorenar@linux.ibm.com>
Reviewed-by: Steffen Maier <maier@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/configs/zfcpdump_defconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 039fd499b4a9..76123a4b26ab 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -26,7 +26,6 @@ CONFIG_CRASH_DUMP=y
 # CONFIG_SECCOMP is not set
 # CONFIG_GCC_PLUGINS is not set
 CONFIG_PARTITION_ADVANCED=y
-CONFIG_IBM_PARTITION=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_COMPACTION is not set
 # CONFIG_MIGRATION is not set
@@ -64,7 +63,6 @@ CONFIG_RAW_DRIVER=y
 # CONFIG_IOMMU_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set
-CONFIG_CONFIGFS_FS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_LSM="yama,loadpin,safesetid,integrity"

From 36b87cf302a4f13f8b4344bcf98f67405a145e2f Mon Sep 17 00:00:00 2001
From: Shou-Chieh Hsu <shouchieh@chromium.org>
Date: Tue, 2 Mar 2021 11:58:01 +0800
Subject: [PATCH 0327/1820] HID: google: add don USB id

Add 1 additional hammer-like device.

Signed-off-by: Shou-Chieh Hsu <shouchieh@chromium.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-google-hammer.c | 2 ++
 drivers/hid/hid-ids.h           | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c
index d9319622da44..e60c31dd05ff 100644
--- a/drivers/hid/hid-google-hammer.c
+++ b/drivers/hid/hid-google-hammer.c
@@ -573,6 +573,8 @@ static void hammer_remove(struct hid_device *hdev)
 }
 
 static const struct hid_device_id hammer_devices[] = {
+	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_DON) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index e42aaae3138f..0b4929258478 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -493,6 +493,7 @@
 #define USB_DEVICE_ID_GOOGLE_MASTERBALL	0x503c
 #define USB_DEVICE_ID_GOOGLE_MAGNEMITE	0x503d
 #define USB_DEVICE_ID_GOOGLE_MOONBALL	0x5044
+#define USB_DEVICE_ID_GOOGLE_DON	0x5050
 
 #define USB_VENDOR_ID_GOTOP		0x08f2
 #define USB_DEVICE_ID_SUPER_Q2		0x007f

From 9a0b44fbfea1932196a4879b44a37dd182e984c5 Mon Sep 17 00:00:00 2001
From: Luke D Jones <luke@ljones.dev>
Date: Fri, 19 Feb 2021 10:10:02 +1300
Subject: [PATCH 0328/1820] HID: asus: Add support for 2021 ASUS N-Key keyboard

Some new 2021 version of ASUS gamer laptops are using an updated
N-Key keyboard with the PID of 0x19b6. This version is using the
same init sequence and brightness control as the 0x1866 keyboard.

Signed-off-by: Luke D Jones <luke@ljones.dev>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-asus.c | 3 +++
 drivers/hid/hid-ids.h  | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 1dfe184ebf5a..2ab22b925941 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1221,6 +1221,9 @@ static const struct hid_device_id asus_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD),
 	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+	    USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD2),
+	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 		USB_DEVICE_ID_ASUSTEK_T100TA_KEYBOARD),
 	  QUIRK_T100_KEYBOARD | QUIRK_NO_CONSUMER_USAGES },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 0b4929258478..67fd8a2f5aba 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -194,6 +194,7 @@
 #define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD2 0x1837
 #define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD3 0x1822
 #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD	0x1866
+#define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD2	0x19b6
 #define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD	0x1869
 
 #define USB_VENDOR_ID_ATEN		0x0557

From fa8ba6e5dc0e78e409e503ddcfceef5dd96527f4 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 4 Mar 2021 05:19:57 -0800
Subject: [PATCH 0329/1820] HID: alps: fix error return code in
 alps_input_configured()

When input_register_device() fails, no error return code is assigned.
To fix this bug, ret is assigned with -ENOENT as error return code.

Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-alps.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c
index 3feaece13ade..6b665931147d 100644
--- a/drivers/hid/hid-alps.c
+++ b/drivers/hid/hid-alps.c
@@ -761,6 +761,7 @@ static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi)
 
 		if (input_register_device(data->input2)) {
 			input_free_device(input2);
+			ret = -ENOENT;
 			goto exit;
 		}
 	}

From 7a05293af39fc716d0f51c0164cbb727302396a2 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Wed, 3 Mar 2021 19:33:05 +0000
Subject: [PATCH 0330/1820] MIPS: boot/compressed: Copy DTB to aligned address

Since 5.12-rc1, the Device Tree blob must now be properly aligned.

Therefore, the decompress routine must be careful to copy the blob at
the next aligned address after the kernel image.

This commit fixes the kernel sometimes not booting with a Device Tree
blob appended to it.

Fixes: 79edff12060f ("scripts/dtc: Update to upstream version v1.6.0-51-g183df9e9c2b9")
Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/boot/compressed/decompress.c | 8 ++++++++
 arch/mips/kernel/vmlinux.lds.S         | 2 ++
 2 files changed, 10 insertions(+)

diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index e3946b06e840..3d70d15ada28 100644
--- a/arch/mips/boot/compressed/decompress.c
+++ b/arch/mips/boot/compressed/decompress.c
@@ -14,6 +14,7 @@
 
 #include <asm/addrspace.h>
 #include <asm/unaligned.h>
+#include <asm-generic/vmlinux.lds.h>
 
 /*
  * These two variables specify the free mem region
@@ -120,6 +121,13 @@ void decompress_kernel(unsigned long boot_heap_start)
 		/* last four bytes is always image size in little endian */
 		image_size = get_unaligned_le32((void *)&__image_end - 4);
 
+		/* The device tree's address must be properly aligned  */
+		image_size = ALIGN(image_size, STRUCT_ALIGNMENT);
+
+		puts("Copy device tree to address  ");
+		puthex(VMLINUX_LOAD_ADDRESS_ULL + image_size);
+		puts("\n");
+
 		/* copy dtb to where the booted kernel will expect it */
 		memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size,
 		       __appended_dtb, dtb_size);
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index c1c345be04ff..4b4e39b7c79b 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -145,6 +145,7 @@ SECTIONS
 	}
 
 #ifdef CONFIG_MIPS_ELF_APPENDED_DTB
+	STRUCT_ALIGN();
 	.appended_dtb : AT(ADDR(.appended_dtb) - LOAD_OFFSET) {
 		*(.appended_dtb)
 		KEEP(*(.appended_dtb))
@@ -172,6 +173,7 @@ SECTIONS
 #endif
 
 #ifdef CONFIG_MIPS_RAW_APPENDED_DTB
+	STRUCT_ALIGN();
 	__appended_dtb = .;
 	/* leave space for appended DTB */
 	. += 0x100000;

From 02fc409540303801994d076fcdb7064bd634dbf3 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Sun, 28 Feb 2021 09:33:19 +0800
Subject: [PATCH 0331/1820] cpufreq: qcom-hw: fix dereferencing freed memory
 'data'

Commit 67fc209b527d ("cpufreq: qcom-hw: drop devm_xxx() calls from
init/exit hooks") introduces an issue of dereferencing freed memory
'data'.  Fix it.

Fixes: 67fc209b527d ("cpufreq: qcom-hw: drop devm_xxx() calls from init/exit hooks")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/qcom-cpufreq-hw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index d3c23447b892..bee5d67a8227 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -374,7 +374,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 error:
 	kfree(data);
 unmap_base:
-	iounmap(data->base);
+	iounmap(base);
 release_region:
 	release_mem_region(res->start, resource_size(res));
 	return ret;

From 536eb97abeba857126ad055de5923fa592acef25 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Thu, 4 Mar 2021 10:04:23 +0000
Subject: [PATCH 0332/1820] cpufreq: qcom-hw: Fix return value check in
 qcom_cpufreq_hw_cpu_init()

In case of error, the function ioremap() returns NULL pointer
not ERR_PTR(). The IS_ERR() test in the return value check
should be replaced with NULL test.

Fixes: 67fc209b527d ("cpufreq: qcom-hw: drop devm_xxx() calls from init/exit hooks")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Acked-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/qcom-cpufreq-hw.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index bee5d67a8227..f86859bf76f1 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -317,9 +317,9 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	base = ioremap(res->start, resource_size(res));
-	if (IS_ERR(base)) {
+	if (!base) {
 		dev_err(dev, "failed to map resource %pR\n", res);
-		ret = PTR_ERR(base);
+		ret = -ENOMEM;
 		goto release_region;
 	}
 

From fbb31cb805fd3574d3be7defc06a7fd2fd9af7d2 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Thu, 18 Feb 2021 22:23:26 +0000
Subject: [PATCH 0333/1820] cpufreq: blacklist Arm Vexpress platforms in
 cpufreq-dt-platdev

Add "arm,vexpress" to cpufreq-dt-platdev blacklist since the actual
scaling is handled by the firmware cpufreq drivers(scpi, scmi and
vexpress-spc).

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/cpufreq-dt-platdev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 3ba2f716fe97..5e07065ec22f 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -103,6 +103,8 @@ static const struct of_device_id whitelist[] __initconst = {
 static const struct of_device_id blacklist[] __initconst = {
 	{ .compatible = "allwinner,sun50i-h6", },
 
+	{ .compatible = "arm,vexpress", },
+
 	{ .compatible = "calxeda,highbank", },
 	{ .compatible = "calxeda,ecx-2000", },
 

From 6c810cf20feef0d4338e9b424ab7f2644a8b353e Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@orcam.me.uk>
Date: Wed, 3 Mar 2021 02:16:04 +0100
Subject: [PATCH 0334/1820] crypto: mips/poly1305 - enable for all MIPS
 processors

The MIPS Poly1305 implementation is generic MIPS code written such as to
support down to the original MIPS I and MIPS III ISA for the 32-bit and
64-bit variant respectively.  Lift the current limitation then to enable
code for MIPSr1 ISA or newer processors only and have it available for
all MIPS processors.

Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Fixes: a11d055e7a64 ("crypto: mips/poly1305 - incorporate OpenSSL/CRYPTOGAMS optimized implementation")
Cc: stable@vger.kernel.org # v5.5+
Acked-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/crypto/Makefile | 4 ++--
 crypto/Kconfig            | 2 +-
 drivers/net/Kconfig       | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/mips/crypto/Makefile b/arch/mips/crypto/Makefile
index 8e1deaf00e0c..5e4105cccf9f 100644
--- a/arch/mips/crypto/Makefile
+++ b/arch/mips/crypto/Makefile
@@ -12,8 +12,8 @@ AFLAGS_chacha-core.o += -O2 # needed to fill branch delay slots
 obj-$(CONFIG_CRYPTO_POLY1305_MIPS) += poly1305-mips.o
 poly1305-mips-y := poly1305-core.o poly1305-glue.o
 
-perlasm-flavour-$(CONFIG_CPU_MIPS32) := o32
-perlasm-flavour-$(CONFIG_CPU_MIPS64) := 64
+perlasm-flavour-$(CONFIG_32BIT) := o32
+perlasm-flavour-$(CONFIG_64BIT) := 64
 
 quiet_cmd_perlasm = PERLASM $@
       cmd_perlasm = $(PERL) $(<) $(perlasm-flavour-y) $(@)
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 15c9c28d9f53..5809cc198fa7 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -767,7 +767,7 @@ config CRYPTO_POLY1305_X86_64
 
 config CRYPTO_POLY1305_MIPS
 	tristate "Poly1305 authenticator algorithm (MIPS optimized)"
-	depends on CPU_MIPS32 || (CPU_MIPS64 && 64BIT)
+	depends on MIPS
 	select CRYPTO_ARCH_HAVE_LIB_POLY1305
 
 config CRYPTO_MD4
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index b09bed554f26..bcd31f458d1a 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -94,7 +94,7 @@ config WIREGUARD
 	select CRYPTO_BLAKE2S_ARM if ARM
 	select CRYPTO_CURVE25519_NEON if ARM && KERNEL_MODE_NEON
 	select CRYPTO_CHACHA_MIPS if CPU_MIPS32_R2
-	select CRYPTO_POLY1305_MIPS if CPU_MIPS32 || (CPU_MIPS64 && 64BIT)
+	select CRYPTO_POLY1305_MIPS if MIPS
 	help
 	  WireGuard is a secure, fast, and easy to use replacement for IPSec
 	  that uses modern cryptography and clever networking tricks. It's

From 542104ee0cafe789cc07291b71818c143df8d623 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Wed, 24 Feb 2021 19:53:16 +0100
Subject: [PATCH 0335/1820] selftests: gpio: update .gitignore

The executable that we build for GPIO selftests was renamed to
gpio-mockup-cdev. Let's update .gitignore so that we don't show it
as an untracked file.

Fixes: 8bc395a6a2e2 ("selftests: gpio: rework and simplify test implementation")
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Kent Gibson <warthog618@gmail.com>
---
 tools/testing/selftests/gpio/.gitignore | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/gpio/.gitignore b/tools/testing/selftests/gpio/.gitignore
index 4c69408f3e84..a4969f7ee020 100644
--- a/tools/testing/selftests/gpio/.gitignore
+++ b/tools/testing/selftests/gpio/.gitignore
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-gpio-mockup-chardev
+gpio-mockup-cdev

From a6112998ee45514def58200a7914706c0703f3d7 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 1 Mar 2021 10:05:18 +0100
Subject: [PATCH 0336/1820] gpio: fix NULL-deref-on-deregistration regression

Fix a NULL-pointer deference when deregistering the gpio character
device that was introduced by the recent stub-driver hack. When the new
"driver" is unbound as part of deregistration, driver core clears the
driver-data pointer which is used to retrieve the struct gpio_device in
its release callback.

Fix this by using container_of() in the release callback as should have
been done all along.

Fixes: 4731210c09f5 ("gpiolib: Bind gpio_device to a driver to enable fw_devlink=on by default")
Cc: Saravana Kannan <saravanak@google.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reported-by: syzbot+d27b4c8adbbff70fbfde@syzkaller.appspotmail.com
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 drivers/gpio/gpiolib.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index adf55db080d8..6e0572515d02 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -474,7 +474,7 @@ EXPORT_SYMBOL_GPL(gpiochip_line_is_valid);
 
 static void gpiodevice_release(struct device *dev)
 {
-	struct gpio_device *gdev = dev_get_drvdata(dev);
+	struct gpio_device *gdev = container_of(dev, struct gpio_device, dev);
 
 	list_del(&gdev->list);
 	ida_free(&gpio_ida, gdev->id);
@@ -605,7 +605,6 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 		goto err_free_ida;
 
 	device_initialize(&gdev->dev);
-	dev_set_drvdata(&gdev->dev, gdev);
 	if (gc->parent && gc->parent->driver)
 		gdev->owner = gc->parent->driver->owner;
 	else if (gc->owner)

From cf25ef6b631c6fc6c0435fc91eba8734cca20511 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 1 Mar 2021 10:05:19 +0100
Subject: [PATCH 0337/1820] gpio: fix gpio-device list corruption

Make sure to hold the gpio_lock when removing the gpio device from the
gpio_devices list (when dropping the last reference) to avoid corrupting
the list when there are concurrent accesses.

Fixes: ff2b13592299 ("gpio: make the gpiochip a real device")
Cc: stable@vger.kernel.org      # 4.6
Reviewed-by: Saravana Kannan <saravanak@google.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 drivers/gpio/gpiolib.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 6e0572515d02..4253837f870b 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -475,8 +475,12 @@ EXPORT_SYMBOL_GPL(gpiochip_line_is_valid);
 static void gpiodevice_release(struct device *dev)
 {
 	struct gpio_device *gdev = container_of(dev, struct gpio_device, dev);
+	unsigned long flags;
 
+	spin_lock_irqsave(&gpio_lock, flags);
 	list_del(&gdev->list);
+	spin_unlock_irqrestore(&gpio_lock, flags);
+
 	ida_free(&gpio_ida, gdev->id);
 	kfree_const(gdev->label);
 	kfree(gdev->descs);

From 6e5d5791730b55a1f987e1db84b078b91eb49e99 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Tue, 23 Feb 2021 16:35:58 +0800
Subject: [PATCH 0338/1820] gpiolib: acpi: Add missing IRQF_ONESHOT

fixed the following coccicheck:
./drivers/gpio/gpiolib-acpi.c:176:7-27: ERROR: Threaded IRQ with no
primary handler requested without IRQF_ONESHOT

Make sure threaded IRQs without a primary handler are always request
with IRQF_ONESHOT

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/gpio/gpiolib-acpi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index e37a57d0a2f0..86efa2d9bf7f 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -174,7 +174,7 @@ static void acpi_gpiochip_request_irq(struct acpi_gpio_chip *acpi_gpio,
 	int ret, value;
 
 	ret = request_threaded_irq(event->irq, NULL, event->handler,
-				   event->irqflags, "ACPI:Event", event);
+				   event->irqflags | IRQF_ONESHOT, "ACPI:Event", event);
 	if (ret) {
 		dev_err(acpi_gpio->chip->parent,
 			"Failed to setup interrupt handler for %d\n",

From 62d5247d239d4b48762192a251c647d7c997616a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 25 Feb 2021 18:33:18 +0200
Subject: [PATCH 0339/1820] gpiolib: acpi: Add ACPI_GPIO_QUIRK_ABSOLUTE_NUMBER
 quirk

On some systems the ACPI tables has wrong pin number and instead of
having a relative one it provides an absolute one in the global GPIO
number space.

Add ACPI_GPIO_QUIRK_ABSOLUTE_NUMBER quirk to cope with such cases.

Fixes: ba8c90c61847 ("gpio: pca953x: Override IRQ for one of the expanders on Galileo Gen 2")
Depends-on: 0ea683931adb ("gpio: dwapb: Convert driver to using the GPIO-lib-based IRQ-chip")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib-acpi.c   | 7 ++++++-
 include/linux/gpio/consumer.h | 2 ++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 86efa2d9bf7f..0fa0127d50ec 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -677,6 +677,7 @@ static int acpi_populate_gpio_lookup(struct acpi_resource *ares, void *data)
 	if (!lookup->desc) {
 		const struct acpi_resource_gpio *agpio = &ares->data.gpio;
 		bool gpioint = agpio->connection_type == ACPI_RESOURCE_GPIO_TYPE_INT;
+		struct gpio_desc *desc;
 		u16 pin_index;
 
 		if (lookup->info.quirks & ACPI_GPIO_QUIRK_ONLY_GPIOIO && gpioint)
@@ -689,8 +690,12 @@ static int acpi_populate_gpio_lookup(struct acpi_resource *ares, void *data)
 		if (pin_index >= agpio->pin_table_length)
 			return 1;
 
-		lookup->desc = acpi_get_gpiod(agpio->resource_source.string_ptr,
+		if (lookup->info.quirks & ACPI_GPIO_QUIRK_ABSOLUTE_NUMBER)
+			desc = gpio_to_desc(agpio->pin_table[pin_index]);
+		else
+			desc = acpi_get_gpiod(agpio->resource_source.string_ptr,
 					      agpio->pin_table[pin_index]);
+		lookup->desc = desc;
 		lookup->info.pin_config = agpio->pin_config;
 		lookup->info.debounce = agpio->debounce_timeout;
 		lookup->info.gpioint = gpioint;
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index ef49307611d2..c73b25bc9213 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -674,6 +674,8 @@ struct acpi_gpio_mapping {
  * get GpioIo type explicitly, this quirk may be used.
  */
 #define ACPI_GPIO_QUIRK_ONLY_GPIOIO		BIT(1)
+/* Use given pin as an absolute GPIO number in the system */
+#define ACPI_GPIO_QUIRK_ABSOLUTE_NUMBER		BIT(2)
 
 	unsigned int quirks;
 };

From 809390219fb9c2421239afe5c9eb862d73978ba0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 25 Feb 2021 18:33:19 +0200
Subject: [PATCH 0340/1820] gpiolib: acpi: Allow to find GpioInt() resource by
 name and index

Currently only search by index is supported. However, in some cases
we might need to pass the quirks to the acpi_dev_gpio_irq_get().

For this, split out acpi_dev_gpio_irq_get_by() and replace
acpi_dev_gpio_irq_get() by calling above with NULL for name parameter.

Fixes: ba8c90c61847 ("gpio: pca953x: Override IRQ for one of the expanders on Galileo Gen 2")
Depends-on: 0ea683931adb ("gpio: dwapb: Convert driver to using the GPIO-lib-based IRQ-chip")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib-acpi.c | 12 ++++++++----
 include/linux/acpi.h        | 10 ++++++++--
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 0fa0127d50ec..1aacd2a5a1fd 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -945,8 +945,9 @@ struct gpio_desc *acpi_node_get_gpiod(struct fwnode_handle *fwnode,
 }
 
 /**
- * acpi_dev_gpio_irq_get() - Find GpioInt and translate it to Linux IRQ number
+ * acpi_dev_gpio_irq_get_by() - Find GpioInt and translate it to Linux IRQ number
  * @adev: pointer to a ACPI device to get IRQ from
+ * @name: optional name of GpioInt resource
  * @index: index of GpioInt resource (starting from %0)
  *
  * If the device has one or more GpioInt resources, this function can be
@@ -956,9 +957,12 @@ struct gpio_desc *acpi_node_get_gpiod(struct fwnode_handle *fwnode,
  * The function is idempotent, though each time it runs it will configure GPIO
  * pin direction according to the flags in GpioInt resource.
  *
+ * The function takes optional @name parameter. If the resource has a property
+ * name, then only those will be taken into account.
+ *
  * Return: Linux IRQ number (> %0) on success, negative errno on failure.
  */
-int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
+int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index)
 {
 	int idx, i;
 	unsigned int irq_flags;
@@ -968,7 +972,7 @@ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
 		struct acpi_gpio_info info;
 		struct gpio_desc *desc;
 
-		desc = acpi_get_gpiod_by_index(adev, NULL, i, &info);
+		desc = acpi_get_gpiod_by_index(adev, name, i, &info);
 
 		/* Ignore -EPROBE_DEFER, it only matters if idx matches */
 		if (IS_ERR(desc) && PTR_ERR(desc) != -EPROBE_DEFER)
@@ -1013,7 +1017,7 @@ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
 	}
 	return -ENOENT;
 }
-EXPORT_SYMBOL_GPL(acpi_dev_gpio_irq_get);
+EXPORT_SYMBOL_GPL(acpi_dev_gpio_irq_get_by);
 
 static acpi_status
 acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address,
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 9f432411e988..fcdaab723916 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1079,19 +1079,25 @@ void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const c
 #if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB)
 bool acpi_gpio_get_irq_resource(struct acpi_resource *ares,
 				struct acpi_resource_gpio **agpio);
-int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index);
+int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index);
 #else
 static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares,
 					      struct acpi_resource_gpio **agpio)
 {
 	return false;
 }
-static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
+static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev,
+					   const char *name, int index)
 {
 	return -ENXIO;
 }
 #endif
 
+static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
+{
+	return acpi_dev_gpio_irq_get_by(adev, NULL, index);
+}
+
 /* Device properties */
 
 #ifdef CONFIG_ACPI

From eb441337c7147514ab45036cadf09c3a71e4ce31 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 25 Feb 2021 18:33:20 +0200
Subject: [PATCH 0341/1820] gpio: pca953x: Set IRQ type when handle Intel
 Galileo Gen 2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The commit 0ea683931adb ("gpio: dwapb: Convert driver to using the
GPIO-lib-based IRQ-chip") indeliberately made a regression on how
IRQ line from GPIO I²C expander is handled. I.e. it reveals that
the quirk for Intel Galileo Gen 2 misses the part of setting IRQ type
which previously was predefined by gpio-dwapb driver. Now, we have to
reorganize the approach to call necessary parts, which can be done via
ACPI_GPIO_QUIRK_ABSOLUTE_NUMBER quirk.

Without this fix and with above mentioned change the kernel hangs
on the first IRQ event with:

    gpio gpiochip3: Persistence not supported for GPIO 1
    irq 32, desc: 62f8fb50, depth: 0, count: 0, unhandled: 0
    ->handle_irq():  41c7b0ab, handle_bad_irq+0x0/0x40
    ->irq_data.chip(): e03f1e72, 0xc2539218
    ->action(): 0ecc7e6f
    ->action->handler(): 8a3db21e, irq_default_primary_handler+0x0/0x10
       IRQ_NOPROBE set
    unexpected IRQ trap at vector 20

Fixes: ba8c90c61847 ("gpio: pca953x: Override IRQ for one of the expanders on Galileo Gen 2")
Depends-on: 0ea683931adb ("gpio: dwapb: Convert driver to using the GPIO-lib-based IRQ-chip")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-pca953x.c | 78 +++++++++++--------------------------
 1 file changed, 23 insertions(+), 55 deletions(-)

diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 5ea09fd01544..c91d05651596 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -113,8 +113,29 @@ MODULE_DEVICE_TABLE(i2c, pca953x_id);
 #ifdef CONFIG_GPIO_PCA953X_IRQ
 
 #include <linux/dmi.h>
-#include <linux/gpio.h>
-#include <linux/list.h>
+
+static const struct acpi_gpio_params pca953x_irq_gpios = { 0, 0, true };
+
+static const struct acpi_gpio_mapping pca953x_acpi_irq_gpios[] = {
+	{ "irq-gpios", &pca953x_irq_gpios, 1, ACPI_GPIO_QUIRK_ABSOLUTE_NUMBER },
+	{ }
+};
+
+static int pca953x_acpi_get_irq(struct device *dev)
+{
+	int ret;
+
+	ret = devm_acpi_dev_add_driver_gpios(dev, pca953x_acpi_irq_gpios);
+	if (ret)
+		dev_warn(dev, "can't add GPIO ACPI mapping\n");
+
+	ret = acpi_dev_gpio_irq_get_by(ACPI_COMPANION(dev), "irq-gpios", 0);
+	if (ret < 0)
+		return ret;
+
+	dev_info(dev, "ACPI interrupt quirk (IRQ %d)\n", ret);
+	return ret;
+}
 
 static const struct dmi_system_id pca953x_dmi_acpi_irq_info[] = {
 	{
@@ -133,59 +154,6 @@ static const struct dmi_system_id pca953x_dmi_acpi_irq_info[] = {
 	},
 	{}
 };
-
-#ifdef CONFIG_ACPI
-static int pca953x_acpi_get_pin(struct acpi_resource *ares, void *data)
-{
-	struct acpi_resource_gpio *agpio;
-	int *pin = data;
-
-	if (acpi_gpio_get_irq_resource(ares, &agpio))
-		*pin = agpio->pin_table[0];
-	return 1;
-}
-
-static int pca953x_acpi_find_pin(struct device *dev)
-{
-	struct acpi_device *adev = ACPI_COMPANION(dev);
-	int pin = -ENOENT, ret;
-	LIST_HEAD(r);
-
-	ret = acpi_dev_get_resources(adev, &r, pca953x_acpi_get_pin, &pin);
-	acpi_dev_free_resource_list(&r);
-	if (ret < 0)
-		return ret;
-
-	return pin;
-}
-#else
-static inline int pca953x_acpi_find_pin(struct device *dev) { return -ENXIO; }
-#endif
-
-static int pca953x_acpi_get_irq(struct device *dev)
-{
-	int pin, ret;
-
-	pin = pca953x_acpi_find_pin(dev);
-	if (pin < 0)
-		return pin;
-
-	dev_info(dev, "Applying ACPI interrupt quirk (GPIO %d)\n", pin);
-
-	if (!gpio_is_valid(pin))
-		return -EINVAL;
-
-	ret = gpio_request(pin, "pca953x interrupt");
-	if (ret)
-		return ret;
-
-	ret = gpio_to_irq(pin);
-
-	/* When pin is used as an IRQ, no need to keep it requested */
-	gpio_free(pin);
-
-	return ret;
-}
 #endif
 
 static const struct acpi_device_id pca953x_acpi_ids[] = {

From b41ba2ec54a70908067034f139aa23d0dd2985ce Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 5 Mar 2021 14:02:40 +0200
Subject: [PATCH 0342/1820] gpiolib: Read "gpio-line-names" from a firmware
 node

On STM32MP1, the GPIO banks are subnodes of pin-controller@50002000,
see arch/arm/boot/dts/stm32mp151.dtsi. The driver for
pin-controller@50002000 is in drivers/pinctrl/stm32/pinctrl-stm32.c
and iterates over all of its DT subnodes when registering each GPIO
bank gpiochip. Each gpiochip has:

  - gpio_chip.parent = dev,
    where dev is the device node of the pin controller
  - gpio_chip.of_node = np,
    which is the OF node of the GPIO bank

Therefore, dev_fwnode(chip->parent) != of_fwnode_handle(chip.of_node),
i.e. pin-controller@50002000 != pin-controller@50002000/gpio@5000*000.

The original code behaved correctly, as it extracted the "gpio-line-names"
from of_fwnode_handle(chip.of_node) = pin-controller@50002000/gpio@5000*000.

To achieve the same behaviour, read property from the firmware node.

Fixes: 7cba1a4d5e162 ("gpiolib: generalize devprop_gpiochip_set_names() for device properties")
Reported-by: Marek Vasut <marex@denx.de>
Reported-by: Roman Guskov <rguskov@dh-electronics.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Marek Vasut <marex@denx.de>
Reviewed-by: Marek Vasut <marex@denx.de>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 drivers/gpio/gpiolib.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 4253837f870b..7ec0822c0505 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -367,22 +367,18 @@ static int gpiochip_set_desc_names(struct gpio_chip *gc)
  *
  * Looks for device property "gpio-line-names" and if it exists assigns
  * GPIO line names for the chip. The memory allocated for the assigned
- * names belong to the underlying software node and should not be released
+ * names belong to the underlying firmware node and should not be released
  * by the caller.
  */
 static int devprop_gpiochip_set_names(struct gpio_chip *chip)
 {
 	struct gpio_device *gdev = chip->gpiodev;
-	struct device *dev = chip->parent;
+	struct fwnode_handle *fwnode = dev_fwnode(&gdev->dev);
 	const char **names;
 	int ret, i;
 	int count;
 
-	/* GPIO chip may not have a parent device whose properties we inspect. */
-	if (!dev)
-		return 0;
-
-	count = device_property_string_array_count(dev, "gpio-line-names");
+	count = fwnode_property_string_array_count(fwnode, "gpio-line-names");
 	if (count < 0)
 		return 0;
 
@@ -396,7 +392,7 @@ static int devprop_gpiochip_set_names(struct gpio_chip *chip)
 	if (!names)
 		return -ENOMEM;
 
-	ret = device_property_read_string_array(dev, "gpio-line-names",
+	ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
 						names, count);
 	if (ret < 0) {
 		dev_warn(&gdev->dev, "failed to read GPIO line names\n");

From 781e14eaa7d168dc07d2a2eea5c55831a5bb46f3 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Wed, 10 Feb 2021 16:06:33 +0200
Subject: [PATCH 0343/1820] thunderbolt: Initialize HopID IDAs in
 tb_switch_alloc()

If there is a failure before the tb_switch_add() is called the switch
object is released by tb_switch_release() but at that point HopID IDAs
have not yet been initialized. So we see splat like this:

BUG: spinlock bad magic on CPU#2, kworker/u8:5/115
...
Workqueue: thunderbolt0 tb_handle_hotplug
Call Trace:
 dump_stack+0x97/0xdc
 ? spin_bug+0x9a/0xa7
 do_raw_spin_lock+0x68/0x98
 _raw_spin_lock_irqsave+0x3f/0x5d
 ida_destroy+0x4f/0x127
 tb_switch_release+0x6d/0xfd
 device_release+0x2c/0x7d
 kobject_put+0x9b/0xbc
 tb_handle_hotplug+0x278/0x452
 process_one_work+0x1db/0x396
 worker_thread+0x216/0x375
 kthread+0x14d/0x155
 ? pr_cont_work+0x58/0x58
 ? kthread_blkcg+0x2e/0x2e
 ret_from_fork+0x1f/0x40

Fix this by always initializing HopID IDAs in tb_switch_alloc().

Fixes: 0b2863ac3cfd ("thunderbolt: Add functions for allocating and releasing HopIDs")
Cc: stable@vger.kernel.org
Reported-by: Chiranjeevi Rapolu <chiranjeevi.rapolu@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/switch.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index b63fecca6c2a..2a95b4ce06c0 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -768,12 +768,6 @@ static int tb_init_port(struct tb_port *port)
 
 	tb_dump_port(port->sw->tb, &port->config);
 
-	/* Control port does not need HopID allocation */
-	if (port->port) {
-		ida_init(&port->in_hopids);
-		ida_init(&port->out_hopids);
-	}
-
 	INIT_LIST_HEAD(&port->list);
 	return 0;
 
@@ -1842,10 +1836,8 @@ static void tb_switch_release(struct device *dev)
 	dma_port_free(sw->dma_port);
 
 	tb_switch_for_each_port(sw, port) {
-		if (!port->disabled) {
-			ida_destroy(&port->in_hopids);
-			ida_destroy(&port->out_hopids);
-		}
+		ida_destroy(&port->in_hopids);
+		ida_destroy(&port->out_hopids);
 	}
 
 	kfree(sw->uuid);
@@ -2025,6 +2017,12 @@ struct tb_switch *tb_switch_alloc(struct tb *tb, struct device *parent,
 		/* minimum setup for tb_find_cap and tb_drom_read to work */
 		sw->ports[i].sw = sw;
 		sw->ports[i].port = i;
+
+		/* Control port does not need HopID allocation */
+		if (i) {
+			ida_init(&sw->ports[i].in_hopids);
+			ida_init(&sw->ports[i].out_hopids);
+		}
 	}
 
 	ret = tb_switch_find_vse_cap(sw, TB_VSE_CAP_PLUG_EVENTS);

From c94732bda079ee66b5c3904cbb628d0cb218ab39 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Thu, 10 Dec 2020 14:57:10 +0200
Subject: [PATCH 0344/1820] thunderbolt: Increase runtime PM reference count on
 DP tunnel discovery

If the driver is unbound and then bound back it goes over the topology
and figure out the existing tunnels. However, if it finds DP tunnel it
should make sure the domain does not runtime suspend as otherwise it
will tear down the DP tunnel unexpectedly.

Fixes: 6ac6faee5d7d ("thunderbolt: Add runtime PM for Software CM")
Cc: stable@vger.kernel.org
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tb.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index 1f000ac1728b..c348b1fc0efc 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -138,6 +138,10 @@ static void tb_discover_tunnels(struct tb_switch *sw)
 				parent->boot = true;
 				parent = tb_switch_parent(parent);
 			}
+		} else if (tb_tunnel_is_dp(tunnel)) {
+			/* Keep the domain from powering down */
+			pm_runtime_get_sync(&tunnel->src_port->sw->dev);
+			pm_runtime_get_sync(&tunnel->dst_port->sw->dev);
 		}
 
 		list_add_tail(&tunnel->list, &tcm->tunnel_list);

From 350a5c4dd2452ea999cc5e1d4a8dbf12de2f97ef Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Sun, 7 Mar 2021 14:52:48 -0800
Subject: [PATCH 0345/1820] bpf: Dont allow vmlinux BTF to be used in
 map_create and prog_load.

The syzbot got FD of vmlinux BTF and passed it into map_create which caused
crash in btf_type_id_size() when it tried to access resolved_ids. The vmlinux
BTF doesn't have 'resolved_ids' and 'resolved_sizes' initialized to save
memory. To avoid such issues disallow using vmlinux BTF in prog_load and
map_create commands.

Fixes: 5329722057d4 ("bpf: Assign ID to vmlinux BTF and return extra info for BTF in GET_OBJ_INFO")
Reported-by: syzbot+8bab8ed346746e7540e8@syzkaller.appspotmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210307225248.79031-1-alexei.starovoitov@gmail.com
---
 kernel/bpf/syscall.c  | 5 +++++
 kernel/bpf/verifier.c | 4 ++++
 2 files changed, 9 insertions(+)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index c859bc46d06c..250503482cda 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -854,6 +854,11 @@ static int map_create(union bpf_attr *attr)
 			err = PTR_ERR(btf);
 			goto free_map;
 		}
+		if (btf_is_kernel(btf)) {
+			btf_put(btf);
+			err = -EACCES;
+			goto free_map;
+		}
 		map->btf = btf;
 
 		if (attr->btf_value_type_id) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c56e3fcb5f1a..4192a9e56654 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9056,6 +9056,10 @@ static int check_btf_info(struct bpf_verifier_env *env,
 	btf = btf_get_by_fd(attr->prog_btf_fd);
 	if (IS_ERR(btf))
 		return PTR_ERR(btf);
+	if (btf_is_kernel(btf)) {
+		btf_put(btf);
+		return -EACCES;
+	}
 	env->prog->aux->btf = btf;
 
 	err = check_btf_func(env, attr, uattr);

From df304c2d0dfd63c40561a8107a217e84fc3515e8 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Wed, 3 Mar 2021 13:49:26 +0000
Subject: [PATCH 0346/1820] arm64: cpufeatures: Fix handling of CONFIG_CMDLINE
 for idreg overrides

The built-in kernel commandline (CONFIG_CMDLINE) can be configured in
three different ways:

  1. CMDLINE_FORCE: Use CONFIG_CMDLINE instead of any bootloader args
  2. CMDLINE_EXTEND: Append the bootloader args to CONFIG_CMDLINE
  3. CMDLINE_FROM_BOOTLOADER: Only use CONFIG_CMDLINE if there aren't
     any bootloader args.

The early cmdline parsing to detect idreg overrides gets (2) and (3)
slightly wrong: in the case of (2) the bootloader args are parsed first
and in the case of (3) the CMDLINE is always parsed.

Fix these issues by moving the bootargs parsing out into a helper
function and following the same logic as that used by the EFI stub.

Reviewed-by: Marc Zyngier <maz@kernel.org>
Fixes: 33200303553d ("arm64: cpufeature: Add an early command-line cpufeature override facility")
Link: https://lore.kernel.org/r/20210303134927.18975-2-will@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/idreg-override.c | 50 +++++++++++++++++-------------
 1 file changed, 28 insertions(+), 22 deletions(-)

diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c
index dffb16682330..cc071712c6f9 100644
--- a/arch/arm64/kernel/idreg-override.c
+++ b/arch/arm64/kernel/idreg-override.c
@@ -163,33 +163,39 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases)
 	} while (1);
 }
 
+static __init const u8 *get_bootargs_cmdline(void)
+{
+	const u8 *prop;
+	void *fdt;
+	int node;
+
+	fdt = get_early_fdt_ptr();
+	if (!fdt)
+		return NULL;
+
+	node = fdt_path_offset(fdt, "/chosen");
+	if (node < 0)
+		return NULL;
+
+	prop = fdt_getprop(fdt, node, "bootargs", NULL);
+	if (!prop)
+		return NULL;
+
+	return strlen(prop) ? prop : NULL;
+}
+
 static __init void parse_cmdline(void)
 {
-	if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) {
-		const u8 *prop;
-		void *fdt;
-		int node;
+	const u8 *prop = get_bootargs_cmdline();
 
-		fdt = get_early_fdt_ptr();
-		if (!fdt)
-			goto out;
-
-		node = fdt_path_offset(fdt, "/chosen");
-		if (node < 0)
-			goto out;
-
-		prop = fdt_getprop(fdt, node, "bootargs", NULL);
-		if (!prop)
-			goto out;
-
-		__parse_cmdline(prop, true);
-
-		if (!IS_ENABLED(CONFIG_CMDLINE_EXTEND))
-			return;
+	if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) ||
+	    IS_ENABLED(CONFIG_CMDLINE_FORCE) ||
+	    !prop) {
+		__parse_cmdline(CONFIG_CMDLINE, true);
 	}
 
-out:
-	__parse_cmdline(CONFIG_CMDLINE, true);
+	if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && prop)
+		__parse_cmdline(prop, true);
 }
 
 /* Keep checkers quiet */

From cae118b6acc309539b33339e846cbb19187c164c Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Wed, 3 Mar 2021 13:49:27 +0000
Subject: [PATCH 0347/1820] arm64: Drop support for CMDLINE_EXTEND

The documented behaviour for CMDLINE_EXTEND is that the arguments from
the bootloader are appended to the built-in kernel command line. This
also matches the option parsing behaviour for the EFI stub and early ID
register overrides.

Bizarrely, the fdt behaviour is the other way around: appending the
built-in command line to the bootloader arguments, resulting in a
command-line that doesn't necessarily line-up with the parsing order and
definitely doesn't line-up with the documented behaviour.

As it turns out, there is a proposal [1] to replace CMDLINE_EXTEND with
CMDLINE_PREPEND and CMDLINE_APPEND options which should hopefully make
the intended behaviour much clearer. While we wait for those to land,
drop CMDLINE_EXTEND for now as there appears to be little enthusiasm for
changing the current FDT behaviour.

[1] https://lore.kernel.org/lkml/20190319232448.45964-2-danielwa@cisco.com/

Cc: Max Uvarov <muvarov@gmail.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Doug Anderson <dianders@chromium.org>
Cc: Tyler Hicks <tyhicks@linux.microsoft.com>
Cc: Frank Rowand <frowand.list@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/CAL_JsqJX=TCCs7=gg486r9TN4NYscMTCLNfqJF9crskKPq-bTg@mail.gmail.com
Link: https://lore.kernel.org/r/20210303134927.18975-3-will@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig                 | 6 ------
 arch/arm64/kernel/idreg-override.c | 5 +----
 2 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1f212b47a48a..f15418332d16 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1855,12 +1855,6 @@ config CMDLINE_FROM_BOOTLOADER
 	  the boot loader doesn't provide any, the default kernel command
 	  string provided in CMDLINE will be used.
 
-config CMDLINE_EXTEND
-	bool "Extend bootloader kernel arguments"
-	help
-	  The command-line arguments provided by the boot loader will be
-	  appended to the default kernel command string.
-
 config CMDLINE_FORCE
 	bool "Always use the default kernel command string"
 	help
diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c
index cc071712c6f9..83f1c4b92095 100644
--- a/arch/arm64/kernel/idreg-override.c
+++ b/arch/arm64/kernel/idreg-override.c
@@ -188,11 +188,8 @@ static __init void parse_cmdline(void)
 {
 	const u8 *prop = get_bootargs_cmdline();
 
-	if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) ||
-	    IS_ENABLED(CONFIG_CMDLINE_FORCE) ||
-	    !prop) {
+	if (IS_ENABLED(CONFIG_CMDLINE_FORCE) || !prop)
 		__parse_cmdline(CONFIG_CMDLINE, true);
-	}
 
 	if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && prop)
 		__parse_cmdline(prop, true);

From 07fb6dc327f108937881a096ec6e367a07a7395d Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Mon, 1 Mar 2021 10:36:32 +0530
Subject: [PATCH 0348/1820] arm64/mm: Drop redundant ARCH_WANT_HUGE_PMD_SHARE

There is already an ARCH_WANT_HUGE_PMD_SHARE which is being selected for
applicable configurations. Hence just drop the other redundant entry.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Link: https://lore.kernel.org/r/1614575192-21307-1-git-send-email-anshuman.khandual@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index f15418332d16..6f36732dc11a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1055,8 +1055,6 @@ config HW_PERF_EVENTS
 config SYS_SUPPORTS_HUGETLBFS
 	def_bool y
 
-config ARCH_WANT_HUGE_PMD_SHARE
-
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 

From 79cc2ed5a716544621b11a3f90550e5c7d314306 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Mon, 1 Mar 2021 16:55:14 +0530
Subject: [PATCH 0349/1820] arm64/mm: Drop THP conditionality from
 FORCE_MAX_ZONEORDER

Currently without THP being enabled, MAX_ORDER via FORCE_MAX_ZONEORDER gets
reduced to 11, which falls below HUGETLB_PAGE_ORDER for certain 16K and 64K
page size configurations. This is problematic which throws up the following
warning during boot as pageblock_order via HUGETLB_PAGE_ORDER order exceeds
MAX_ORDER.

WARNING: CPU: 7 PID: 127 at mm/vmstat.c:1092 __fragmentation_index+0x58/0x70
Modules linked in:
CPU: 7 PID: 127 Comm: kswapd0 Not tainted 5.12.0-rc1-00005-g0221e3101a1 #237
Hardware name: linux,dummy-virt (DT)
pstate: 20400005 (nzCv daif +PAN -UAO -TCO BTYPE=--)
pc : __fragmentation_index+0x58/0x70
lr : fragmentation_index+0x88/0xa8
sp : ffff800016ccfc00
x29: ffff800016ccfc00 x28: 0000000000000000
x27: ffff800011fd4000 x26: 0000000000000002
x25: ffff800016ccfda0 x24: 0000000000000002
x23: 0000000000000640 x22: ffff0005ffcb5b18
x21: 0000000000000002 x20: 000000000000000d
x19: ffff0005ffcb3980 x18: 0000000000000004
x17: 0000000000000001 x16: 0000000000000019
x15: ffff800011ca7fb8 x14: 00000000000002b3
x13: 0000000000000000 x12: 00000000000005e0
x11: 0000000000000003 x10: 0000000000000080
x9 : ffff800011c93948 x8 : 0000000000000000
x7 : 0000000000000000 x6 : 0000000000007000
x5 : 0000000000007944 x4 : 0000000000000032
x3 : 000000000000001c x2 : 000000000000000b
x1 : ffff800016ccfc10 x0 : 000000000000000d
Call trace:
__fragmentation_index+0x58/0x70
compaction_suitable+0x58/0x78
wakeup_kcompactd+0x8c/0xd8
balance_pgdat+0x570/0x5d0
kswapd+0x1e0/0x388
kthread+0x154/0x158
ret_from_fork+0x10/0x30

This solves the problem via keeping FORCE_MAX_ZONEORDER unchanged with or
without THP on 16K and 64K page size configurations, making sure that the
HUGETLB_PAGE_ORDER (and pageblock_order) would never exceed MAX_ORDER.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/1614597914-28565-1-git-send-email-anshuman.khandual@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 6f36732dc11a..5656e7aacd69 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1155,8 +1155,8 @@ config XEN
 
 config FORCE_MAX_ZONEORDER
 	int
-	default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
-	default "12" if (ARM64_16K_PAGES && TRANSPARENT_HUGEPAGE)
+	default "14" if ARM64_64K_PAGES
+	default "12" if ARM64_16K_PAGES
 	default "11"
 	help
 	  The kernel memory allocator divides physically contiguous memory

From 7c911f9de7abb89f46254d2fecb11dcb4a7a6c30 Mon Sep 17 00:00:00 2001
From: Benjamin Li <benl@squareup.com>
Date: Mon, 8 Mar 2021 15:09:15 +0200
Subject: [PATCH 0350/1820] interconnect: qcom: msm8939: remove rpm-ids from
 non-RPM nodes

Some nodes are incorrectly marked as RPM-controlled (they have RPM
master and slave ids assigned), but are actually controlled by the
application CPU instead. The RPM complains when we send requests for
resources that it can't control. Let's fix this by replacing the IDs,
with the default "-1" in which case no requests are sent.

See commit c497f9322af9 ("interconnect: qcom: msm8916: Remove rpm-ids
from non-RPM nodes") where this was done for msm8916.

Signed-off-by: Benjamin Li <benl@squareup.com>
Reviewed-by: Jun Nie <jun.nie@linaro.org>
Link: https://lore.kernel.org/r/20210205015205.22947-3-benl@squareup.com
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/qcom/msm8939.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/interconnect/qcom/msm8939.c b/drivers/interconnect/qcom/msm8939.c
index dfbec30ed149..20f31a1b4192 100644
--- a/drivers/interconnect/qcom/msm8939.c
+++ b/drivers/interconnect/qcom/msm8939.c
@@ -131,7 +131,7 @@ DEFINE_QNODE(mas_pcnoc_sdcc_1, MSM8939_MASTER_SDCC_1, 8, -1, -1, MSM8939_PNOC_IN
 DEFINE_QNODE(mas_pcnoc_sdcc_2, MSM8939_MASTER_SDCC_2, 8, -1, -1, MSM8939_PNOC_INT_1);
 DEFINE_QNODE(mas_qdss_bam, MSM8939_MASTER_QDSS_BAM, 8, -1, -1, MSM8939_SNOC_QDSS_INT);
 DEFINE_QNODE(mas_qdss_etr, MSM8939_MASTER_QDSS_ETR, 8, -1, -1, MSM8939_SNOC_QDSS_INT);
-DEFINE_QNODE(mas_snoc_cfg, MSM8939_MASTER_SNOC_CFG, 4, 20, -1, MSM8939_SLAVE_SRVC_SNOC);
+DEFINE_QNODE(mas_snoc_cfg, MSM8939_MASTER_SNOC_CFG, 4, -1, -1, MSM8939_SLAVE_SRVC_SNOC);
 DEFINE_QNODE(mas_spdm, MSM8939_MASTER_SPDM, 4, -1, -1, MSM8939_PNOC_MAS_0);
 DEFINE_QNODE(mas_tcu0, MSM8939_MASTER_TCU0, 16, -1, -1, MSM8939_SLAVE_EBI_CH0, MSM8939_BIMC_SNOC_MAS, MSM8939_SLAVE_AMPSS_L2);
 DEFINE_QNODE(mas_usb_hs1, MSM8939_MASTER_USB_HS1, 4, -1, -1, MSM8939_PNOC_MAS_1);
@@ -156,14 +156,14 @@ DEFINE_QNODE(pcnoc_snoc_mas, MSM8939_PNOC_SNOC_MAS, 8, 29, -1, MSM8939_PNOC_SNOC
 DEFINE_QNODE(pcnoc_snoc_slv, MSM8939_PNOC_SNOC_SLV, 8, -1, 45, MSM8939_SNOC_INT_0, MSM8939_SNOC_INT_BIMC, MSM8939_SNOC_INT_1);
 DEFINE_QNODE(qdss_int, MSM8939_SNOC_QDSS_INT, 8, -1, -1, MSM8939_SNOC_INT_0, MSM8939_SNOC_INT_BIMC);
 DEFINE_QNODE(slv_apps_l2, MSM8939_SLAVE_AMPSS_L2, 16, -1, -1, 0);
-DEFINE_QNODE(slv_apss, MSM8939_SLAVE_APSS, 4, -1, 20, 0);
+DEFINE_QNODE(slv_apss, MSM8939_SLAVE_APSS, 4, -1, -1, 0);
 DEFINE_QNODE(slv_audio, MSM8939_SLAVE_LPASS, 4, -1, -1, 0);
 DEFINE_QNODE(slv_bimc_cfg, MSM8939_SLAVE_BIMC_CFG, 4, -1, -1, 0);
 DEFINE_QNODE(slv_blsp_1, MSM8939_SLAVE_BLSP_1, 4, -1, -1, 0);
 DEFINE_QNODE(slv_boot_rom, MSM8939_SLAVE_BOOT_ROM, 4, -1, -1, 0);
 DEFINE_QNODE(slv_camera_cfg, MSM8939_SLAVE_CAMERA_CFG, 4, -1, -1, 0);
-DEFINE_QNODE(slv_cats_0, MSM8939_SLAVE_CATS_128, 16, -1, 106, 0);
-DEFINE_QNODE(slv_cats_1, MSM8939_SLAVE_OCMEM_64, 8, -1, 107, 0);
+DEFINE_QNODE(slv_cats_0, MSM8939_SLAVE_CATS_128, 16, -1, -1, 0);
+DEFINE_QNODE(slv_cats_1, MSM8939_SLAVE_OCMEM_64, 8, -1, -1, 0);
 DEFINE_QNODE(slv_clk_ctl, MSM8939_SLAVE_CLK_CTL, 4, -1, -1, 0);
 DEFINE_QNODE(slv_crypto_0_cfg, MSM8939_SLAVE_CRYPTO_0_CFG, 4, -1, -1, 0);
 DEFINE_QNODE(slv_dehr_cfg, MSM8939_SLAVE_DEHR_CFG, 4, -1, -1, 0);
@@ -187,20 +187,20 @@ DEFINE_QNODE(slv_sdcc_2, MSM8939_SLAVE_SDCC_2, 4, -1, -1, 0);
 DEFINE_QNODE(slv_security, MSM8939_SLAVE_SECURITY, 4, -1, -1, 0);
 DEFINE_QNODE(slv_snoc_cfg, MSM8939_SLAVE_SNOC_CFG, 4, -1, -1, 0);
 DEFINE_QNODE(slv_spdm, MSM8939_SLAVE_SPDM, 4, -1, -1, 0);
-DEFINE_QNODE(slv_srvc_snoc, MSM8939_SLAVE_SRVC_SNOC, 8, -1, 29, 0);
+DEFINE_QNODE(slv_srvc_snoc, MSM8939_SLAVE_SRVC_SNOC, 8, -1, -1, 0);
 DEFINE_QNODE(slv_tcsr, MSM8939_SLAVE_TCSR, 4, -1, -1, 0);
 DEFINE_QNODE(slv_tlmm, MSM8939_SLAVE_TLMM, 4, -1, -1, 0);
 DEFINE_QNODE(slv_usb_hs1, MSM8939_SLAVE_USB_HS1, 4, -1, -1, 0);
 DEFINE_QNODE(slv_usb_hs2, MSM8939_SLAVE_USB_HS2, 4, -1, -1, 0);
 DEFINE_QNODE(slv_venus_cfg, MSM8939_SLAVE_VENUS_CFG, 4, -1, -1, 0);
-DEFINE_QNODE(snoc_bimc_0_mas, MSM8939_SNOC_BIMC_0_MAS, 16, 3, -1, MSM8939_SNOC_BIMC_0_SLV);
-DEFINE_QNODE(snoc_bimc_0_slv, MSM8939_SNOC_BIMC_0_SLV, 16, -1, 24, MSM8939_SLAVE_EBI_CH0);
+DEFINE_QNODE(snoc_bimc_0_mas, MSM8939_SNOC_BIMC_0_MAS, 16, -1, -1, MSM8939_SNOC_BIMC_0_SLV);
+DEFINE_QNODE(snoc_bimc_0_slv, MSM8939_SNOC_BIMC_0_SLV, 16, -1, -1, MSM8939_SLAVE_EBI_CH0);
 DEFINE_QNODE(snoc_bimc_1_mas, MSM8939_SNOC_BIMC_1_MAS, 16, 76, -1, MSM8939_SNOC_BIMC_1_SLV);
 DEFINE_QNODE(snoc_bimc_1_slv, MSM8939_SNOC_BIMC_1_SLV, 16, -1, 104, MSM8939_SLAVE_EBI_CH0);
 DEFINE_QNODE(snoc_bimc_2_mas, MSM8939_SNOC_BIMC_2_MAS, 16, -1, -1, MSM8939_SNOC_BIMC_2_SLV);
 DEFINE_QNODE(snoc_bimc_2_slv, MSM8939_SNOC_BIMC_2_SLV, 16, -1, -1, MSM8939_SLAVE_EBI_CH0);
 DEFINE_QNODE(snoc_int_0, MSM8939_SNOC_INT_0, 8, 99, 130, MSM8939_SLAVE_QDSS_STM, MSM8939_SLAVE_IMEM, MSM8939_SNOC_PNOC_MAS);
-DEFINE_QNODE(snoc_int_1, MSM8939_SNOC_INT_1, 8, 100, 131, MSM8939_SLAVE_APSS, MSM8939_SLAVE_CATS_128, MSM8939_SLAVE_OCMEM_64);
+DEFINE_QNODE(snoc_int_1, MSM8939_SNOC_INT_1, 8, -1, -1, MSM8939_SLAVE_APSS, MSM8939_SLAVE_CATS_128, MSM8939_SLAVE_OCMEM_64);
 DEFINE_QNODE(snoc_int_bimc, MSM8939_SNOC_INT_BIMC, 8, 101, 132, MSM8939_SNOC_BIMC_1_MAS);
 DEFINE_QNODE(snoc_pcnoc_mas, MSM8939_SNOC_PNOC_MAS, 8, -1, -1, MSM8939_SNOC_PNOC_SLV);
 DEFINE_QNODE(snoc_pcnoc_slv, MSM8939_SNOC_PNOC_SLV, 8, -1, -1, MSM8939_PNOC_INT_0);

From 715ea61532e731c62392221238906704e63d75b6 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 8 Mar 2021 15:09:15 +0200
Subject: [PATCH 0351/1820] interconnect: core: fix error return code of
 icc_link_destroy()

When krealloc() fails and new is NULL, no error return code of
icc_link_destroy() is assigned.
To fix this bug, ret is assigned with -ENOMEM hen new is NULL.

Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Link: https://lore.kernel.org/r/20210306132857.17020-1-baijiaju1990@gmail.com
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index 5ad519c9f239..8a1e70e00876 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -942,6 +942,8 @@ int icc_link_destroy(struct icc_node *src, struct icc_node *dst)
 		       GFP_KERNEL);
 	if (new)
 		src->links = new;
+	else
+		ret = -ENOMEM;
 
 out:
 	mutex_unlock(&icc_lock);

From 78a81d88f60ba773cbe890205e1ee67f00502948 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 3 Mar 2021 15:17:12 +0100
Subject: [PATCH 0352/1820] x86/sev-es: Introduce ip_within_syscall_gap()
 helper

Introduce a helper to check whether an exception came from the syscall
gap and use it in the SEV-ES code. Extend the check to also cover the
compatibility SYSCALL entry path.

Fixes: 315562c9af3d5 ("x86/sev-es: Adjust #VC IST Stack on entering NMI handler")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: stable@vger.kernel.org # 5.10+
Link: https://lkml.kernel.org/r/20210303141716.29223-2-joro@8bytes.org
---
 arch/x86/entry/entry_64_compat.S |  2 ++
 arch/x86/include/asm/proto.h     |  1 +
 arch/x86/include/asm/ptrace.h    | 15 +++++++++++++++
 arch/x86/kernel/traps.c          |  3 +--
 4 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 541fdaf64045..0051cf5c792d 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -210,6 +210,8 @@ SYM_CODE_START(entry_SYSCALL_compat)
 	/* Switch to the kernel stack */
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
+SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL)
+
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER32_DS		/* pt_regs->ss */
 	pushq	%r8			/* pt_regs->sp */
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 2c35f1c01a2d..b6a9d51d1d79 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -25,6 +25,7 @@ void __end_SYSENTER_singlestep_region(void);
 void entry_SYSENTER_compat(void);
 void __end_entry_SYSENTER_compat(void);
 void entry_SYSCALL_compat(void);
+void entry_SYSCALL_compat_safe_stack(void);
 void entry_INT80_compat(void);
 #ifdef CONFIG_XEN_PV
 void xen_entry_INT80_compat(void);
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index d8324a236696..409f661481e1 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -94,6 +94,8 @@ struct pt_regs {
 #include <asm/paravirt_types.h>
 #endif
 
+#include <asm/proto.h>
+
 struct cpuinfo_x86;
 struct task_struct;
 
@@ -175,6 +177,19 @@ static inline bool any_64bit_mode(struct pt_regs *regs)
 #ifdef CONFIG_X86_64
 #define current_user_stack_pointer()	current_pt_regs()->sp
 #define compat_user_stack_pointer()	current_pt_regs()->sp
+
+static inline bool ip_within_syscall_gap(struct pt_regs *regs)
+{
+	bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
+		    regs->ip <  (unsigned long)entry_SYSCALL_64_safe_stack);
+
+#ifdef CONFIG_IA32_EMULATION
+	ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat &&
+		      regs->ip <  (unsigned long)entry_SYSCALL_compat_safe_stack);
+#endif
+
+	return ret;
+}
 #endif
 
 static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 7f5aec758f0e..ac1874a2a70e 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -694,8 +694,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r
 	 * In the SYSCALL entry path the RSP value comes from user-space - don't
 	 * trust it and switch to the current kernel stack
 	 */
-	if (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
-	    regs->ip <  (unsigned long)entry_SYSCALL_64_safe_stack) {
+	if (ip_within_syscall_gap(regs)) {
 		sp = this_cpu_read(cpu_current_top_of_stack);
 		goto sync;
 	}

From 2a2b09c867fdac63f430a45051e7bd0c46edc381 Mon Sep 17 00:00:00 2001
From: Douglas Gilbert <dgilbert@interlog.com>
Date: Sat, 9 Jan 2021 17:36:58 -0500
Subject: [PATCH 0353/1820] HID cp2112: fix support for multiple gpiochips

In lk 5.11.0-rc2 connecting a USB based Silicon Labs HID to I2C
bridge evaluation board (CP2112EK) causes this warning:
  gpio gpiochip0: (cp2112_gpio): detected irqchip that is shared
       with multiple gpiochips: please fix the driver

Simply copy what other gpio related drivers do to fix this
particular warning: replicate the struct irq_chip object in each
device instance rather than have a static object which makes that
object (incorrectly) shared by each device.

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-cp2112.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c
index 21e15627a461..477baa30889c 100644
--- a/drivers/hid/hid-cp2112.c
+++ b/drivers/hid/hid-cp2112.c
@@ -161,6 +161,7 @@ struct cp2112_device {
 	atomic_t read_avail;
 	atomic_t xfer_avail;
 	struct gpio_chip gc;
+	struct irq_chip irq;
 	u8 *in_out_buffer;
 	struct mutex lock;
 
@@ -1175,16 +1176,6 @@ static int cp2112_gpio_irq_type(struct irq_data *d, unsigned int type)
 	return 0;
 }
 
-static struct irq_chip cp2112_gpio_irqchip = {
-	.name = "cp2112-gpio",
-	.irq_startup = cp2112_gpio_irq_startup,
-	.irq_shutdown = cp2112_gpio_irq_shutdown,
-	.irq_ack = cp2112_gpio_irq_ack,
-	.irq_mask = cp2112_gpio_irq_mask,
-	.irq_unmask = cp2112_gpio_irq_unmask,
-	.irq_set_type = cp2112_gpio_irq_type,
-};
-
 static int __maybe_unused cp2112_allocate_irq(struct cp2112_device *dev,
 					      int pin)
 {
@@ -1339,8 +1330,17 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	dev->gc.can_sleep		= 1;
 	dev->gc.parent			= &hdev->dev;
 
+	dev->irq.name = "cp2112-gpio";
+	dev->irq.irq_startup = cp2112_gpio_irq_startup;
+	dev->irq.irq_shutdown = cp2112_gpio_irq_shutdown;
+	dev->irq.irq_ack = cp2112_gpio_irq_ack;
+	dev->irq.irq_mask = cp2112_gpio_irq_mask;
+	dev->irq.irq_unmask = cp2112_gpio_irq_unmask;
+	dev->irq.irq_set_type = cp2112_gpio_irq_type;
+	dev->irq.flags = IRQCHIP_MASK_ON_SUSPEND;
+
 	girq = &dev->gc.irq;
-	girq->chip = &cp2112_gpio_irqchip;
+	girq->chip = &dev->irq;
 	/* The event comes from the outside so no parent handler */
 	girq->parent_handler = NULL;
 	girq->num_parents = 0;

From e29c62ffb008829dc8bcc0a2ec438adc25a8255e Mon Sep 17 00:00:00 2001
From: Jiapeng Zhong <abaci-bugfix@linux.alibaba.com>
Date: Wed, 20 Jan 2021 15:34:30 +0800
Subject: [PATCH 0354/1820] HID: wacom: Assign boolean values to a bool
 variable

Fix the following coccicheck warnings:

./drivers/hid/wacom_wac.c:2536:2-6: WARNING: Assignment of
0/1 to bool variable.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Jiapeng Zhong <abaci-bugfix@linux.alibaba.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/wacom_wac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 44d715c12f6a..bdd9ba577150 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2533,7 +2533,7 @@ static void wacom_wac_finger_slot(struct wacom_wac *wacom_wac,
 	    !wacom_wac->shared->is_touch_on) {
 		if (!wacom_wac->shared->touch_down)
 			return;
-		prox = 0;
+		prox = false;
 	}
 
 	wacom_wac->hid_data.num_received++;

From ee2e3f50629f17b0752b55b2566c15ce8dafb557 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Sat, 6 Mar 2021 11:10:10 +0100
Subject: [PATCH 0355/1820] mount: fix mounting of detached mounts onto targets
 that reside on shared mounts

Creating a series of detached mounts, attaching them to the filesystem,
and unmounting them can be used to trigger an integer overflow in
ns->mounts causing the kernel to block any new mounts in count_mounts()
and returning ENOSPC because it falsely assumes that the maximum number
of mounts in the mount namespace has been reached, i.e. it thinks it
can't fit the new mounts into the mount namespace anymore.

Depending on the number of mounts in your system, this can be reproduced
on any kernel that supportes open_tree() and move_mount() by compiling
and running the following program:

  /* SPDX-License-Identifier: LGPL-2.1+ */

  #define _GNU_SOURCE
  #include <errno.h>
  #include <fcntl.h>
  #include <getopt.h>
  #include <limits.h>
  #include <stdbool.h>
  #include <stdio.h>
  #include <stdlib.h>
  #include <string.h>
  #include <sys/mount.h>
  #include <sys/stat.h>
  #include <sys/syscall.h>
  #include <sys/types.h>
  #include <unistd.h>

  /* open_tree() */
  #ifndef OPEN_TREE_CLONE
  #define OPEN_TREE_CLONE 1
  #endif

  #ifndef OPEN_TREE_CLOEXEC
  #define OPEN_TREE_CLOEXEC O_CLOEXEC
  #endif

  #ifndef __NR_open_tree
          #if defined __alpha__
                  #define __NR_open_tree 538
          #elif defined _MIPS_SIM
                  #if _MIPS_SIM == _MIPS_SIM_ABI32        /* o32 */
                          #define __NR_open_tree 4428
                  #endif
                  #if _MIPS_SIM == _MIPS_SIM_NABI32       /* n32 */
                          #define __NR_open_tree 6428
                  #endif
                  #if _MIPS_SIM == _MIPS_SIM_ABI64        /* n64 */
                          #define __NR_open_tree 5428
                  #endif
          #elif defined __ia64__
                  #define __NR_open_tree (428 + 1024)
          #else
                  #define __NR_open_tree 428
          #endif
  #endif

  /* move_mount() */
  #ifndef MOVE_MOUNT_F_EMPTY_PATH
  #define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
  #endif

  #ifndef __NR_move_mount
          #if defined __alpha__
                  #define __NR_move_mount 539
          #elif defined _MIPS_SIM
                  #if _MIPS_SIM == _MIPS_SIM_ABI32        /* o32 */
                          #define __NR_move_mount 4429
                  #endif
                  #if _MIPS_SIM == _MIPS_SIM_NABI32       /* n32 */
                          #define __NR_move_mount 6429
                  #endif
                  #if _MIPS_SIM == _MIPS_SIM_ABI64        /* n64 */
                          #define __NR_move_mount 5429
                  #endif
          #elif defined __ia64__
                  #define __NR_move_mount (428 + 1024)
          #else
                  #define __NR_move_mount 429
          #endif
  #endif

  static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)
  {
          return syscall(__NR_open_tree, dfd, filename, flags);
  }

  static inline int sys_move_mount(int from_dfd, const char *from_pathname, int to_dfd,
                                   const char *to_pathname, unsigned int flags)
  {
          return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd, to_pathname, flags);
  }

  static bool is_shared_mountpoint(const char *path)
  {
          bool shared = false;
          FILE *f = NULL;
          char *line = NULL;
          int i;
          size_t len = 0;

          f = fopen("/proc/self/mountinfo", "re");
          if (!f)
                  return 0;

          while (getline(&line, &len, f) > 0) {
                  char *slider1, *slider2;

                  for (slider1 = line, i = 0; slider1 && i < 4; i++)
                          slider1 = strchr(slider1 + 1, ' ');

                  if (!slider1)
                          continue;

                  slider2 = strchr(slider1 + 1, ' ');
                  if (!slider2)
                          continue;

                  *slider2 = '\0';
                  if (strcmp(slider1 + 1, path) == 0) {
                          /* This is the path. Is it shared? */
                          slider1 = strchr(slider2 + 1, ' ');
                          if (slider1 && strstr(slider1, "shared:")) {
                                  shared = true;
                                  break;
                          }
                  }
          }
          fclose(f);
          free(line);

          return shared;
  }

  static void usage(void)
  {
          const char *text = "mount-new [--recursive] <base-dir>\n";
          fprintf(stderr, "%s", text);
          _exit(EXIT_SUCCESS);
  }

  #define exit_usage(format, ...)                              \
          ({                                                   \
                  fprintf(stderr, format "\n", ##__VA_ARGS__); \
                  usage();                                     \
          })

  #define exit_log(format, ...)                                \
          ({                                                   \
                  fprintf(stderr, format "\n", ##__VA_ARGS__); \
                  exit(EXIT_FAILURE);                          \
          })

  static const struct option longopts[] = {
          {"help",        no_argument,            0,      'a'},
          { NULL,         no_argument,            0,       0 },
  };

  int main(int argc, char *argv[])
  {
          int exit_code = EXIT_SUCCESS, index = 0;
          int dfd, fd_tree, new_argc, ret;
          char *base_dir;
          char *const *new_argv;
          char target[PATH_MAX];

          while ((ret = getopt_long_only(argc, argv, "", longopts, &index)) != -1) {
                  switch (ret) {
                  case 'a':
                          /* fallthrough */
                  default:
                          usage();
                  }
          }

          new_argv = &argv[optind];
          new_argc = argc - optind;
          if (new_argc < 1)
                  exit_usage("Missing base directory\n");
          base_dir = new_argv[0];

          if (*base_dir != '/')
                  exit_log("Please specify an absolute path");

          /* Ensure that target is a shared mountpoint. */
          if (!is_shared_mountpoint(base_dir))
                  exit_log("Please ensure that \"%s\" is a shared mountpoint", base_dir);

          dfd = open(base_dir, O_RDONLY | O_DIRECTORY | O_CLOEXEC);
          if (dfd < 0)
                  exit_log("%m - Failed to open base directory \"%s\"", base_dir);

          ret = mkdirat(dfd, "detached-move-mount", 0755);
          if (ret < 0)
                  exit_log("%m - Failed to create required temporary directories");

          ret = snprintf(target, sizeof(target), "%s/detached-move-mount", base_dir);
          if (ret < 0 || (size_t)ret >= sizeof(target))
                  exit_log("%m - Failed to assemble target path");

          /*
           * Having a mount table with 10000 mounts is already quite excessive
           * and shoult account even for weird test systems.
           */
          for (size_t i = 0; i < 10000; i++) {
                  fd_tree = sys_open_tree(dfd, "detached-move-mount",
                                          OPEN_TREE_CLONE |
                                          OPEN_TREE_CLOEXEC |
                                          AT_EMPTY_PATH);
                  if (fd_tree < 0) {
                          fprintf(stderr, "%m - Failed to open %d(detached-move-mount)", dfd);
                          exit_code = EXIT_FAILURE;
                          break;
                  }

                  ret = sys_move_mount(fd_tree, "", dfd, "detached-move-mount", MOVE_MOUNT_F_EMPTY_PATH);
                  if (ret < 0) {
                          if (errno == ENOSPC)
                                  fprintf(stderr, "%m - Buggy mount counting");
                          else
                                  fprintf(stderr, "%m - Failed to attach mount to %d(detached-move-mount)", dfd);
                          exit_code = EXIT_FAILURE;
                          break;
                  }
                  close(fd_tree);

                  ret = umount2(target, MNT_DETACH);
                  if (ret < 0) {
                          fprintf(stderr, "%m - Failed to unmount %s", target);
                          exit_code = EXIT_FAILURE;
                          break;
                  }
          }

          (void)unlinkat(dfd, "detached-move-mount", AT_REMOVEDIR);
          close(dfd);

          exit(exit_code);
  }

and wait for the kernel to refuse any new mounts by returning ENOSPC.
How many iterations are needed depends on the number of mounts in your
system. Assuming you have something like 50 mounts on a standard system
it should be almost instantaneous.

The root cause of this is that detached mounts aren't handled correctly
when source and target mount are identical and reside on a shared mount
causing a broken mount tree where the detached source itself is
propagated which propagation prevents for regular bind-mounts and new
mounts. This ultimately leads to a miscalculation of the number of
mounts in the mount namespace.

Detached mounts created via
open_tree(fd, path, OPEN_TREE_CLONE)
are essentially like an unattached new mount, or an unattached
bind-mount. They can then later on be attached to the filesystem via
move_mount() which calls into attach_recursive_mount(). Part of
attaching it to the filesystem is making sure that mounts get correctly
propagated in case the destination mountpoint is MS_SHARED, i.e. is a
shared mountpoint. This is done by calling into propagate_mnt() which
walks the list of peers calling propagate_one() on each mount in this
list making sure it receives the propagation event.
The propagate_one() functions thereby skips both new mounts and bind
mounts to not propagate them "into themselves". Both are identified by
checking whether the mount is already attached to any mount namespace in
mnt->mnt_ns. The is what the IS_MNT_NEW() helper is responsible for.

However, detached mounts have an anonymous mount namespace attached to
them stashed in mnt->mnt_ns which means that IS_MNT_NEW() doesn't
realize they need to be skipped causing the mount to propagate "into
itself" breaking the mount table and causing a disconnect between the
number of mounts recorded as being beneath or reachable from the target
mountpoint and the number of mounts actually recorded/counted in
ns->mounts ultimately causing an overflow which in turn prevents any new
mounts via the ENOSPC issue.

So teach propagation to handle detached mounts by making it aware of
them. I've been tracking this issue down for the last couple of days and
then verifying that the fix is correct by
unmounting everything in my current mount table leaving only /proc and
/sys mounted and running the reproducer above overnight verifying the
number of mounts counted in ns->mounts. With this fix the counts are
correct and the ENOSPC issue can't be reproduced.

This change will only have an effect on mounts created with the new
mount API since detached mounts cannot be created with the old mount API
so regressions are extremely unlikely.

Link: https://lore.kernel.org/r/20210306101010.243666-1-christian.brauner@ubuntu.com
Fixes: 2db154b3ea8e ("vfs: syscall: Add move_mount(2) to move mounts around")
Cc: David Howells <dhowells@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Cc: <stable@vger.kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/pnode.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/pnode.h b/fs/pnode.h
index 26f74e092bd9..988f1aa9b02a 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -12,7 +12,7 @@
 
 #define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED)
 #define IS_MNT_SLAVE(m) ((m)->mnt_master)
-#define IS_MNT_NEW(m)  (!(m)->mnt_ns)
+#define IS_MNT_NEW(m)  (!(m)->mnt_ns || is_anon_ns((m)->mnt_ns))
 #define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
 #define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
 #define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)

From 769c18b254ca191b45047e1fcb3b2ce56fada0b6 Mon Sep 17 00:00:00 2001
From: Tal Lossos <tallossos@gmail.com>
Date: Sun, 7 Mar 2021 14:09:48 +0200
Subject: [PATCH 0356/1820] bpf: Change inode_storage's lookup_elem return
 value from NULL to -EBADF

bpf_fd_inode_storage_lookup_elem() returned NULL when getting a bad FD,
which caused -ENOENT in bpf_map_copy_value. -EBADF error is better than
-ENOENT for a bad FD behaviour.

The patch was partially contributed by CyberArk Software, Inc.

Fixes: 8ea636848aca ("bpf: Implement bpf_local_storage for inodes")
Signed-off-by: Tal Lossos <tallossos@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: KP Singh <kpsingh@kernel.org>
Link: https://lore.kernel.org/bpf/20210307120948.61414-1-tallossos@gmail.com
---
 kernel/bpf/bpf_inode_storage.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 6639640523c0..b58b2efb9b43 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -109,7 +109,7 @@ static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key)
 	fd = *(int *)key;
 	f = fget_raw(fd);
 	if (!f)
-		return NULL;
+		return ERR_PTR(-EBADF);
 
 	sdata = inode_storage_lookup(f->f_inode, map, true);
 	fput(f);

From a9e54f4b62dcfed4432a5a89b1cd5903737f6e83 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 28 Jan 2021 13:12:17 +0100
Subject: [PATCH 0357/1820] AMD_SFH: Removed unused activecontrolstatus member
 from the amd_mp2_dev struct

This value is only used once inside amd_mp2_get_sensor_num(),
so there is no need to store this in the amd_mp2_dev struct,
amd_mp2_get_sensor_num() can simple use a local variable for this.

Fixes: 4f567b9f8141 ("SFH: PCIe driver to add support of AMD sensor fusion hub")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Sandeep Singh <sandeep.singh@amd.com
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/amd-sfh-hid/amd_sfh_pcie.c | 6 ++++--
 drivers/hid/amd-sfh-hid/amd_sfh_pcie.h | 1 -
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index dbac16641662..f3cdb4ea33da 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -76,9 +76,11 @@ void amd_stop_all_sensors(struct amd_mp2_dev *privdata)
 int amd_mp2_get_sensor_num(struct amd_mp2_dev *privdata, u8 *sensor_id)
 {
 	int activestatus, num_of_sensors = 0;
+	u32 activecontrolstatus;
+
+	activecontrolstatus = readl(privdata->mmio + AMD_P2C_MSG3);
+	activestatus = activecontrolstatus >> 4;
 
-	privdata->activecontrolstatus = readl(privdata->mmio + AMD_P2C_MSG3);
-	activestatus = privdata->activecontrolstatus >> 4;
 	if (ACEL_EN  & activestatus)
 		sensor_id[num_of_sensors++] = accel_idx;
 
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h
index 8f8d19b2cfe5..489415f7c22c 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h
@@ -61,7 +61,6 @@ struct amd_mp2_dev {
 	struct pci_dev *pdev;
 	struct amdtp_cl_data *cl_data;
 	void __iomem *mmio;
-	u32 activecontrolstatus;
 };
 
 struct amd_mp2_sensor_info {

From 952f7d10c6b1685c6700fb24cf4ecbcf26ede77e Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 28 Jan 2021 13:12:18 +0100
Subject: [PATCH 0358/1820] AMD_SFH: Add sensor_mask module parameter

Add a sensor_mask module parameter which can be used to override the
sensor-mask read from the activestatus bits of the AMD_P2C_MSG3
registers. Some BIOS-es do not program the activestatus bits, leading
to the AMD-SFH driver not registering any HID devices even though the
laptop in question does actually have sensors.

While at it also fix the wrong indentation of the MAGNO_EN define.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=199715
BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1651886
Fixes: 4f567b9f8141 ("SFH: PCIe driver to add support of AMD sensor fusion hub")
Suggested-by: Richard Neumann <mail@richard-neumann.de>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Sandeep Singh <sandeep.singh@amd.com
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/amd-sfh-hid/amd_sfh_pcie.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index f3cdb4ea33da..ab0a9443e252 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -22,9 +22,13 @@
 
 #define ACEL_EN		BIT(0)
 #define GYRO_EN		BIT(1)
-#define MAGNO_EN		BIT(2)
+#define MAGNO_EN	BIT(2)
 #define ALS_EN		BIT(19)
 
+static int sensor_mask_override = -1;
+module_param_named(sensor_mask, sensor_mask_override, int, 0444);
+MODULE_PARM_DESC(sensor_mask, "override the detected sensors mask");
+
 void amd_start_sensor(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info info)
 {
 	union sfh_cmd_param cmd_param;
@@ -78,8 +82,12 @@ int amd_mp2_get_sensor_num(struct amd_mp2_dev *privdata, u8 *sensor_id)
 	int activestatus, num_of_sensors = 0;
 	u32 activecontrolstatus;
 
-	activecontrolstatus = readl(privdata->mmio + AMD_P2C_MSG3);
-	activestatus = activecontrolstatus >> 4;
+	if (sensor_mask_override >= 0) {
+		activestatus = sensor_mask_override;
+	} else {
+		activecontrolstatus = readl(privdata->mmio + AMD_P2C_MSG3);
+		activestatus = activecontrolstatus >> 4;
+	}
 
 	if (ACEL_EN  & activestatus)
 		sensor_id[num_of_sensors++] = accel_idx;

From 25615e454a0ec198254f17d2ed79b607cb755d0e Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 28 Jan 2021 13:12:19 +0100
Subject: [PATCH 0359/1820] AMD_SFH: Add DMI quirk table for BIOS-es which
 don't set the activestatus bits

Some BIOS-es do not initialize the activestatus bits of the AMD_P2C_MSG3
register. This cause the AMD_SFH driver to not register any sensors even
though the laptops in question do have sensors.

Add a DMI quirk-table for specifying sensor-mask overrides based on
DMI match, to make the sensors work OOTB on these laptop models.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=199715
BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1651886
Fixes: 4f567b9f8141 ("SFH: PCIe driver to add support of AMD sensor fusion hub")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Sandeep Singh <sandeep.singh@amd.com
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/amd-sfh-hid/amd_sfh_pcie.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index ab0a9443e252..ddecc84fd6f0 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -10,6 +10,7 @@
 #include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
+#include <linux/dmi.h>
 #include <linux/interrupt.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/module.h>
@@ -77,11 +78,34 @@ void amd_stop_all_sensors(struct amd_mp2_dev *privdata)
 	writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0);
 }
 
+static const struct dmi_system_id dmi_sensor_mask_overrides[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY x360 Convertible 13-ag0xxx"),
+		},
+		.driver_data = (void *)(ACEL_EN | MAGNO_EN),
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY x360 Convertible 15-cp0xxx"),
+		},
+		.driver_data = (void *)(ACEL_EN | MAGNO_EN),
+	},
+	{ }
+};
+
 int amd_mp2_get_sensor_num(struct amd_mp2_dev *privdata, u8 *sensor_id)
 {
 	int activestatus, num_of_sensors = 0;
+	const struct dmi_system_id *dmi_id;
 	u32 activecontrolstatus;
 
+	if (sensor_mask_override == -1) {
+		dmi_id = dmi_first_match(dmi_sensor_mask_overrides);
+		if (dmi_id)
+			sensor_mask_override = (long)dmi_id->driver_data;
+	}
+
 	if (sensor_mask_override >= 0) {
 		activestatus = sensor_mask_override;
 	} else {

From 28e96c1693ec1cdc963807611f8b5ad400431e82 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 8 Mar 2021 17:07:26 +0100
Subject: [PATCH 0360/1820] ALSA: hda: Drop the BATCH workaround for AMD
 controllers

The commit c02f77d32d2c ("ALSA: hda - Workaround for crackled sound on
AMD controller (1022:1457)") introduced a few workarounds for the
recent AMD HD-audio controller, and one of them is the forced BATCH
PCM mode so that PulseAudio avoids the timer-based scheduling.  This
was thought to cover for some badly working applications, but this
actually worsens for more others.  In total, this wasn't a good idea
to enforce it.

This is a partial revert of the commit above for dropping the PCM
BATCH enforcement part to recover from the regression again.

Fixes: c02f77d32d2c ("ALSA: hda - Workaround for crackled sound on AMD controller (1022:1457)")
BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=195303
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210308160726.22930-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_controller.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 9087981cd1f7..ca2f2ecd1488 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -609,13 +609,6 @@ static int azx_pcm_open(struct snd_pcm_substream *substream)
 				     20,
 				     178000000);
 
-	/* by some reason, the playback stream stalls on PulseAudio with
-	 * tsched=1 when a capture stream triggers.  Until we figure out the
-	 * real cause, disable tsched mode by telling the PCM info flag.
-	 */
-	if (chip->driver_caps & AZX_DCAPS_AMD_WORKAROUND)
-		runtime->hw.info |= SNDRV_PCM_INFO_BATCH;
-
 	if (chip->align_buffer_size)
 		/* constrain buffer sizes to be multiple of 128
 		   bytes. This is more efficient in terms of memory

From a0590473c5e6c4ef17c3132ad08fbad170f72d55 Mon Sep 17 00:00:00 2001
From: Timo Rothenpieler <timo@rothenpieler.org>
Date: Tue, 23 Feb 2021 15:19:01 +0100
Subject: [PATCH 0361/1820] nfs: fix PNFS_FLEXFILE_LAYOUT Kconfig default

This follows what was done in 8c2fabc6542d9d0f8b16bd1045c2eda59bdcde13.
With the default being m, it's impossible to build the module into the
kernel.

Signed-off-by: Timo Rothenpieler <timo@rothenpieler.org>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index e2a488d403a6..14a72224b657 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -127,7 +127,7 @@ config PNFS_BLOCK
 config PNFS_FLEXFILE_LAYOUT
 	tristate
 	depends on NFS_V4_1 && NFS_V3
-	default m
+	default NFS_V4
 
 config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
 	string "NFSv4.1 Implementation ID Domain"

From 7029e783027706b427bbfbdf8558252c1dac6fa0 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Sun, 3 Jan 2021 14:56:12 +0100
Subject: [PATCH 0362/1820] remoteproc: qcom: pil_info: avoid 64-bit division

On 32-bit machines with 64-bit resource_size_t, the driver causes
a link failure because of the 64-bit division:

arm-linux-gnueabi-ld: drivers/remoteproc/qcom_pil_info.o: in function `qcom_pil_info_store':
qcom_pil_info.c:(.text+0x1ec): undefined reference to `__aeabi_uldivmod'

Add a cast to an u32 to avoid this. If the resource exceeds 4GB,
there are bigger problems.

Fixes: 549b67da660d ("remoteproc: qcom: Introduce helper to store pil info in IMEM")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20210103135628.3702427-1-arnd@kernel.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/qcom_pil_info.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/qcom_pil_info.c b/drivers/remoteproc/qcom_pil_info.c
index 5521c4437ffa..7c007dd7b200 100644
--- a/drivers/remoteproc/qcom_pil_info.c
+++ b/drivers/remoteproc/qcom_pil_info.c
@@ -56,7 +56,7 @@ static int qcom_pil_info_init(void)
 	memset_io(base, 0, resource_size(&imem));
 
 	_reloc.base = base;
-	_reloc.num_entries = resource_size(&imem) / PIL_RELOC_ENTRY_SIZE;
+	_reloc.num_entries = (u32)resource_size(&imem) / PIL_RELOC_ENTRY_SIZE;
 
 	return 0;
 }

From 5f140174988edc739530ed9f2220e458a488b10a Mon Sep 17 00:00:00 2001
From: Mathieu Poirier <mathieu.poirier@linaro.org>
Date: Mon, 4 Jan 2021 10:16:18 -0700
Subject: [PATCH 0363/1820] MAINTAINERS: Add co-maintainer for remoteproc/RPMSG
 subsystems

After discussing with Bjorn, stepping forward to help with the
maintenance of the remoteproc and RPMSG subsystems.

Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: https://lore.kernel.org/r/20210104171618.2702461-1-mathieu.poirier@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index d92f85ca831d..b75658c9797c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15205,6 +15205,7 @@ F:	fs/reiserfs/
 REMOTE PROCESSOR (REMOTEPROC) SUBSYSTEM
 M:	Ohad Ben-Cohen <ohad@wizery.com>
 M:	Bjorn Andersson <bjorn.andersson@linaro.org>
+M:	Mathieu Poirier <mathieu.poirier@linaro.org>
 L:	linux-remoteproc@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc.git rproc-next
@@ -15218,6 +15219,7 @@ F:	include/linux/remoteproc/
 REMOTE PROCESSOR MESSAGING (RPMSG) SUBSYSTEM
 M:	Ohad Ben-Cohen <ohad@wizery.com>
 M:	Bjorn Andersson <bjorn.andersson@linaro.org>
+M:	Mathieu Poirier <mathieu.poirier@linaro.org>
 L:	linux-remoteproc@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc.git rpmsg-next

From e6d9423d31b2f9bdd0220fd0584e3bb6ed2c4e52 Mon Sep 17 00:00:00 2001
From: Dimitar Dimitrov <dimitar@dinux.eu>
Date: Wed, 30 Dec 2020 12:50:05 +0200
Subject: [PATCH 0364/1820] remoteproc: pru: Fix loading of GNU Binutils ELF

PRU port of GNU Binutils lacks support for separate address spaces.
PRU IRAM addresses are marked with artificial offset to differentiate
them from DRAM addresses. Hence remoteproc must mask IRAM addresses
coming from GNU ELF in order to get the true hardware address.

PRU firmware used for testing was the example in:
  https://github.com/dinuxbg/pru-gcc-examples/tree/master/blinking-led/pru

Signed-off-by: Dimitar Dimitrov <dimitar@dinux.eu>
Link: https://lore.kernel.org/r/20201230105005.30492-1-dimitar@dinux.eu
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/pru_rproc.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/remoteproc/pru_rproc.c b/drivers/remoteproc/pru_rproc.c
index 2667919d76b3..5fad787ba012 100644
--- a/drivers/remoteproc/pru_rproc.c
+++ b/drivers/remoteproc/pru_rproc.c
@@ -450,6 +450,24 @@ static void *pru_i_da_to_va(struct pru_rproc *pru, u32 da, size_t len)
 	if (len == 0)
 		return NULL;
 
+	/*
+	 * GNU binutils do not support multiple address spaces. The GNU
+	 * linker's default linker script places IRAM at an arbitrary high
+	 * offset, in order to differentiate it from DRAM. Hence we need to
+	 * strip the artificial offset in the IRAM addresses coming from the
+	 * ELF file.
+	 *
+	 * The TI proprietary linker would never set those higher IRAM address
+	 * bits anyway. PRU architecture limits the program counter to 16-bit
+	 * word-address range. This in turn corresponds to 18-bit IRAM
+	 * byte-address range for ELF.
+	 *
+	 * Two more bits are added just in case to make the final 20-bit mask.
+	 * Idea is to have a safeguard in case TI decides to add banking
+	 * in future SoCs.
+	 */
+	da &= 0xfffff;
+
 	if (da >= PRU_IRAM_DA &&
 	    da + len <= PRU_IRAM_DA + pru->mem_regions[PRU_IOMEM_IRAM].size) {
 		offset = da - PRU_IRAM_DA;

From 77e141266c8e72e4a586fe42eaab1b4b047655ed Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 8 Mar 2021 18:49:10 +0200
Subject: [PATCH 0365/1820] pinctrl: intel: Show the GPIO base calculation
 explicitly

During the split of intel_pinctrl_add_padgroups(), the _by_size() variant
missed the GPIO base calculations and hence made unable to retrieve proper
GPIO number.

Assign the gpio_base explicitly in _by_size() variant.

While at it, differentiate NOMAP case with the rest in _by_gpps() variant.

Fixes: 036e126c72eb ("pinctrl: intel: Split intel_pinctrl_add_padgroups() for better maintenance")
Reported-and-tested-by: Maximilian Luz <luzmaximilian@gmail.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 8085782cd8f9..7283203861ae 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1357,6 +1357,7 @@ static int intel_pinctrl_add_padgroups_by_gpps(struct intel_pinctrl *pctrl,
 				gpps[i].gpio_base = 0;
 				break;
 			case INTEL_GPIO_BASE_NOMAP:
+				break;
 			default:
 				break;
 		}
@@ -1393,6 +1394,7 @@ static int intel_pinctrl_add_padgroups_by_size(struct intel_pinctrl *pctrl,
 		gpps[i].size = min(gpp_size, npins);
 		npins -= gpps[i].size;
 
+		gpps[i].gpio_base = gpps[i].base;
 		gpps[i].padown_num = padown_num;
 
 		/*

From 6654111c893fec1516d83046d2b237e83e0d5967 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Sun, 7 Mar 2021 19:23:01 +0100
Subject: [PATCH 0366/1820] MIPS: vmlinux.lds.S: align raw appended dtb to 8
 bytes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The devicetree specification requires 8-byte alignment in
memory. This is now enforced by libfdt since commit 79edff12060f
("scripts/dtc: Update to upstream version v1.6.0-51-g183df9e9c2b9")
which included the upstream commit 5e735860c478 ("libfdt: Check for
8-byte address alignment in fdt_ro_probe_()").

This broke the MIPS raw appended DTBs which would be appended to
the image immediately following the initramfs section.  This ends
with a 32bit size, resulting in a 4-byte alignment of the DTB.

Fix by padding with zeroes to 8-bytes when MIPS_RAW_APPENDED_DTB
is defined.

Fixes: 79edff12060f ("scripts/dtc: Update to upstream version v1.6.0-51-g183df9e9c2b9")
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Frank Rowand <frowand.list@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/kernel/vmlinux.lds.S | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 4b4e39b7c79b..1234834cc4c4 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -173,7 +173,11 @@ SECTIONS
 #endif
 
 #ifdef CONFIG_MIPS_RAW_APPENDED_DTB
-	STRUCT_ALIGN();
+	.fill : {
+		FILL(0);
+		BYTE(0);
+		. = ALIGN(8);
+	}
 	__appended_dtb = .;
 	/* leave space for appended DTB */
 	. += 0x100000;

From eeb0753ba27b26f609e61f9950b14f1b934fe429 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Fri, 5 Mar 2021 10:54:57 +0530
Subject: [PATCH 0367/1820] arm64/mm: Fix pfn_valid() for ZONE_DEVICE based
 memory

pfn_valid() validates a pfn but basically it checks for a valid struct page
backing for that pfn. It should always return positive for memory ranges
backed with struct page mapping. But currently pfn_valid() fails for all
ZONE_DEVICE based memory types even though they have struct page mapping.

pfn_valid() asserts that there is a memblock entry for a given pfn without
MEMBLOCK_NOMAP flag being set. The problem with ZONE_DEVICE based memory is
that they do not have memblock entries. Hence memblock_is_map_memory() will
invariably fail via memblock_search() for a ZONE_DEVICE based address. This
eventually fails pfn_valid() which is wrong. memblock_is_map_memory() needs
to be skipped for such memory ranges. As ZONE_DEVICE memory gets hotplugged
into the system via memremap_pages() called from a driver, their respective
memory sections will not have SECTION_IS_EARLY set.

Normal hotplug memory will never have MEMBLOCK_NOMAP set in their memblock
regions. Because the flag MEMBLOCK_NOMAP was specifically designed and set
for firmware reserved memory regions. memblock_is_map_memory() can just be
skipped as its always going to be positive and that will be an optimization
for the normal hotplug memory. Like ZONE_DEVICE based memory, all normal
hotplugged memory too will not have SECTION_IS_EARLY set for their sections

Skipping memblock_is_map_memory() for all non early memory sections would
fix pfn_valid() problem for ZONE_DEVICE based memory and also improve its
performance for normal hotplug memory as well.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Acked-by: David Hildenbrand <david@redhat.com>
Fixes: 73b20c84d42d ("arm64: mm: implement pte_devmap support")
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/1614921898-4099-2-git-send-email-anshuman.khandual@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/init.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 0ace5e68efba..5920c527845a 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -230,6 +230,18 @@ int pfn_valid(unsigned long pfn)
 
 	if (!valid_section(__pfn_to_section(pfn)))
 		return 0;
+
+	/*
+	 * ZONE_DEVICE memory does not have the memblock entries.
+	 * memblock_is_map_memory() check for ZONE_DEVICE based
+	 * addresses will always fail. Even the normal hotplugged
+	 * memory will never have MEMBLOCK_NOMAP flag set in their
+	 * memblock entries. Skip memblock search for all non early
+	 * memory sections covering all of hotplug memory including
+	 * both normal and ZONE_DEVICE based.
+	 */
+	if (!early_section(__pfn_to_section(pfn)))
+		return pfn_section_valid(__pfn_to_section(pfn), pfn);
 #endif
 	return memblock_is_map_memory(addr);
 }

From 093bbe211ea566fa828536275e09ee9d75df1f25 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Fri, 5 Mar 2021 10:54:58 +0530
Subject: [PATCH 0368/1820] arm64/mm: Reorganize pfn_valid()

There are multiple instances of pfn_to_section_nr() and __pfn_to_section()
when CONFIG_SPARSEMEM is enabled. This can be optimized if memory section
is fetched earlier. This replaces the open coded PFN and ADDR conversion
with PFN_PHYS() and PHYS_PFN() helpers. While there, also add a comment.
This does not cause any functional change.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/1614921898-4099-3-git-send-email-anshuman.khandual@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/init.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 5920c527845a..3685e12aba9b 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -219,16 +219,26 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 int pfn_valid(unsigned long pfn)
 {
-	phys_addr_t addr = pfn << PAGE_SHIFT;
+	phys_addr_t addr = PFN_PHYS(pfn);
 
-	if ((addr >> PAGE_SHIFT) != pfn)
+	/*
+	 * Ensure the upper PAGE_SHIFT bits are clear in the
+	 * pfn. Else it might lead to false positives when
+	 * some of the upper bits are set, but the lower bits
+	 * match a valid pfn.
+	 */
+	if (PHYS_PFN(addr) != pfn)
 		return 0;
 
 #ifdef CONFIG_SPARSEMEM
+{
+	struct mem_section *ms;
+
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
 
-	if (!valid_section(__pfn_to_section(pfn)))
+	ms = __pfn_to_section(pfn);
+	if (!valid_section(ms))
 		return 0;
 
 	/*
@@ -240,8 +250,9 @@ int pfn_valid(unsigned long pfn)
 	 * memory sections covering all of hotplug memory including
 	 * both normal and ZONE_DEVICE based.
 	 */
-	if (!early_section(__pfn_to_section(pfn)))
-		return pfn_section_valid(__pfn_to_section(pfn), pfn);
+	if (!early_section(ms))
+		return pfn_section_valid(ms, pfn);
+}
 #endif
 	return memblock_is_map_memory(addr);
 }

From ad3dbe35c833c2d4d0bbf3f04c785d32f931e7c9 Mon Sep 17 00:00:00 2001
From: Frank Sorenson <sorenson@redhat.com>
Date: Mon, 8 Mar 2021 12:12:13 -0600
Subject: [PATCH 0369/1820] NFS: Correct size calculation for create reply
 length

CREATE requests return a post_op_fh3, rather than nfs_fh3. The
post_op_fh3 includes an extra word to indicate 'handle_follows'.

Without that additional word, create fails when full 64-byte
filehandles are in use.

Add NFS3_post_op_fh_sz, and correct the size calculation for
NFS3_createres_sz.

Signed-off-by: Frank Sorenson <sorenson@redhat.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs3xdr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index ca10072644ff..ed1c83738c30 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -36,6 +36,7 @@
 #define NFS3_pagepad_sz		(1) /* Page padding */
 #define NFS3_fhandle_sz		(1+16)
 #define NFS3_fh_sz		(NFS3_fhandle_sz)	/* shorthand */
+#define NFS3_post_op_fh_sz	(1+NFS3_fh_sz)
 #define NFS3_sattr_sz		(15)
 #define NFS3_filename_sz	(1+(NFS3_MAXNAMLEN>>2))
 #define NFS3_path_sz		(1+(NFS3_MAXPATHLEN>>2))
@@ -73,7 +74,7 @@
 #define NFS3_readlinkres_sz	(1+NFS3_post_op_attr_sz+1+NFS3_pagepad_sz)
 #define NFS3_readres_sz		(1+NFS3_post_op_attr_sz+3+NFS3_pagepad_sz)
 #define NFS3_writeres_sz	(1+NFS3_wcc_data_sz+4)
-#define NFS3_createres_sz	(1+NFS3_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
+#define NFS3_createres_sz	(1+NFS3_post_op_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
 #define NFS3_renameres_sz	(1+(2 * NFS3_wcc_data_sz))
 #define NFS3_linkres_sz		(1+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
 #define NFS3_readdirres_sz	(1+NFS3_post_op_attr_sz+2+NFS3_pagepad_sz)

From e7fb6465d4c8e767e39cbee72464e0060ab3d20c Mon Sep 17 00:00:00 2001
From: Georgi Valkov <gvalkov@abv.bg>
Date: Mon, 8 Mar 2021 10:30:38 -0800
Subject: [PATCH 0370/1820] libbpf: Fix INSTALL flag order

It was reported ([0]) that having optional -m flag between source and
destination arguments in install command breaks bpftools cross-build
on MacOS. Move -m to the front to fix this issue.

  [0] https://github.com/openwrt/openwrt/pull/3959

Fixes: 7110d80d53f4 ("libbpf: Makefile set specified permission mode")
Signed-off-by: Georgi Valkov <gvalkov@abv.bg>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210308183038.613432-1-andrii@kernel.org
---
 tools/lib/bpf/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 887a494ad5fc..e9eb6a6e80d2 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -215,7 +215,7 @@ define do_install
 	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
 	fi;						\
-	$(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2'
+	$(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
 endef
 
 install_lib: all_cmd

From bf9279cd63dcc144b2a3c4c76d8b6b4c30b05c22 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Fri, 5 Mar 2021 10:14:48 +0100
Subject: [PATCH 0371/1820] net: dsa: bcm_sf2: simplify optional reset handling

As of commit bb475230b8e5 ("reset: make optional functions really
optional"), the reset framework API calls use NULL pointers to describe
optional, non-present reset controls.

This allows to unconditionally return errors from
devm_reset_control_get_optional_exclusive.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 5ee8103b8e9c..f277df922fcd 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -406,7 +406,7 @@ static int bcm_sf2_sw_rst(struct bcm_sf2_priv *priv)
 	/* The watchdog reset does not work on 7278, we need to hit the
 	 * "external" reset line through the reset controller.
 	 */
-	if (priv->type == BCM7278_DEVICE_ID && !IS_ERR(priv->rcdev)) {
+	if (priv->type == BCM7278_DEVICE_ID) {
 		ret = reset_control_assert(priv->rcdev);
 		if (ret)
 			return ret;
@@ -1265,7 +1265,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 
 	priv->rcdev = devm_reset_control_get_optional_exclusive(&pdev->dev,
 								"switch");
-	if (PTR_ERR(priv->rcdev) == -EPROBE_DEFER)
+	if (IS_ERR(priv->rcdev))
 		return PTR_ERR(priv->rcdev);
 
 	/* Auto-detection using standard registers will not work, so
@@ -1426,7 +1426,7 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev)
 	bcm_sf2_mdio_unregister(priv);
 	clk_disable_unprepare(priv->clk_mdiv);
 	clk_disable_unprepare(priv->clk);
-	if (priv->type == BCM7278_DEVICE_ID && !IS_ERR(priv->rcdev))
+	if (priv->type == BCM7278_DEVICE_ID)
 		reset_control_assert(priv->rcdev);
 
 	return 0;

From a4813dc7baa4898f66c84ef68274bbbd1a0ae224 Mon Sep 17 00:00:00 2001
From: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Date: Sun, 7 Mar 2021 02:50:28 +0530
Subject: [PATCH 0372/1820] net: ethernet: chelsio: inline_crypto: Mundane
 typos fixed throughout the file chcr_ktls.c

Mundane typos fixes throughout the file.

s/establised/established/
s/availbale/available/
s/vaues/values/
s/Incase/In case/

Signed-off-by: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c    | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index 46a809f2aeca..169e10c91378 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -672,7 +672,7 @@ static int chcr_ktls_cpl_act_open_rpl(struct adapter *adap,
 	if (tx_info->pending_close) {
 		spin_unlock(&tx_info->lock);
 		if (!status) {
-			/* it's a late success, tcb status is establised,
+			/* it's a late success, tcb status is established,
 			 * mark it close.
 			 */
 			chcr_ktls_mark_tcb_close(tx_info);
@@ -930,7 +930,7 @@ chcr_ktls_get_tx_flits(u32 nr_frags, unsigned int key_ctx_len)
 }
 
 /*
- * chcr_ktls_check_tcp_options: To check if there is any TCP option availbale
+ * chcr_ktls_check_tcp_options: To check if there is any TCP option available
  * other than timestamp.
  * @skb - skb contains partial record..
  * return: 1 / 0
@@ -1115,7 +1115,7 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb,
 	}
 
 	if (unlikely(credits < ETHTXQ_STOP_THRES)) {
-		/* Credits are below the threshold vaues, stop the queue after
+		/* Credits are below the threshold values, stop the queue after
 		 * injecting the Work Request for this packet.
 		 */
 		chcr_eth_txq_stop(q);
@@ -2006,7 +2006,7 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* TCP segments can be in received either complete or partial.
 	 * chcr_end_part_handler will handle cases if complete record or end
-	 * part of the record is received. Incase of partial end part of record,
+	 * part of the record is received. In case of partial end part of record,
 	 * we will send the complete record again.
 	 */
 

From 492bbe7f8a43ff20bb9bfc6b98220dcfb7e5992f Mon Sep 17 00:00:00 2001
From: Grant Grundler <grundler@chromium.org>
Date: Sat, 6 Mar 2021 14:12:31 -0800
Subject: [PATCH 0373/1820] net: usb: cdc_ncm: emit dev_err on error paths

Several error paths in bind/probe code will only emit
output using dev_dbg. But if we are going to fail the
bind/probe, emit related output with "err" priority.

Signed-off-by: Grant Grundler <grundler@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 4087c9e33781..8acf30115428 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -851,17 +851,17 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 
 	/* check if we got everything */
 	if (!ctx->data) {
-		dev_dbg(&intf->dev, "CDC Union missing and no IAD found\n");
+		dev_err(&intf->dev, "CDC Union missing and no IAD found\n");
 		goto error;
 	}
 	if (cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting)) {
 		if (!ctx->mbim_desc) {
-			dev_dbg(&intf->dev, "MBIM functional descriptor missing\n");
+			dev_err(&intf->dev, "MBIM functional descriptor missing\n");
 			goto error;
 		}
 	} else {
 		if (!ctx->ether_desc || !ctx->func_desc) {
-			dev_dbg(&intf->dev, "NCM or ECM functional descriptors missing\n");
+			dev_err(&intf->dev, "NCM or ECM functional descriptors missing\n");
 			goto error;
 		}
 	}
@@ -870,7 +870,7 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	if (ctx->data != ctx->control) {
 		temp = usb_driver_claim_interface(driver, ctx->data, dev);
 		if (temp) {
-			dev_dbg(&intf->dev, "failed to claim data intf\n");
+			dev_err(&intf->dev, "failed to claim data intf\n");
 			goto error;
 		}
 	}
@@ -926,7 +926,7 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	if (ctx->ether_desc) {
 		temp = usbnet_get_ethernet_addr(dev, ctx->ether_desc->iMACAddress);
 		if (temp) {
-			dev_dbg(&intf->dev, "failed to get mac address\n");
+			dev_err(&intf->dev, "failed to get mac address\n");
 			goto error2;
 		}
 		dev_info(&intf->dev, "MAC-Address: %pM\n", dev->net->dev_addr);

From 4d8c79b7e9ff05030aad68421f7584b129933ba6 Mon Sep 17 00:00:00 2001
From: Grant Grundler <grundler@chromium.org>
Date: Sat, 6 Mar 2021 14:12:32 -0800
Subject: [PATCH 0374/1820] net: usb: log errors to dmesg/syslog

Errors in protocol should be logged when the driver aborts operations.
If the driver can carry on and "humor" the device, then emitting
the message as debug output level is fine.

Signed-off-by: Grant Grundler <grundler@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index b4c8080e6f87..f4f37ecfed58 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -887,7 +887,7 @@ int usbnet_open (struct net_device *net)
 
 	// insist peer be connected
 	if (info->check_connect && (retval = info->check_connect (dev)) < 0) {
-		netif_dbg(dev, ifup, dev->net, "can't open; %d\n", retval);
+		netif_err(dev, ifup, dev->net, "can't open; %d\n", retval);
 		goto done;
 	}
 

From 143c253f42bad20357e7e4432087aca747c43384 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Sun, 7 Mar 2021 00:40:12 -0800
Subject: [PATCH 0375/1820] net: hisilicon: hns: fix error return code of
 hns_nic_clear_all_rx_fetch()

When hns_assemble_skb() returns NULL to skb, no error return code of
hns_nic_clear_all_rx_fetch() is assigned.
To fix this bug, ret is assigned with -ENOMEM in this case.

Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hns_enet.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 5d7824d2b4d4..c66a7a51198e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1663,8 +1663,10 @@ static int hns_nic_clear_all_rx_fetch(struct net_device *ndev)
 			for (j = 0; j < fetch_num; j++) {
 				/* alloc one skb and init */
 				skb = hns_assemble_skb(ndev);
-				if (!skb)
+				if (!skb) {
+					ret = -ENOMEM;
 					goto out;
+				}
 				rd = &tx_ring_data(priv, skb->queue_mapping);
 				hns_nic_net_xmit_hw(ndev, skb, rd);
 

From 62765d39553cfd1ad340124fe1e280450e8c89e2 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Sun, 7 Mar 2021 01:12:56 -0800
Subject: [PATCH 0376/1820] net: wan: fix error return code of uhdlc_init()

When priv->rx_skbuff or priv->tx_skbuff is NULL, no error return code of
uhdlc_init() is assigned.
To fix this bug, ret is assigned with -ENOMEM in these cases.

Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/fsl_ucc_hdlc.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index dca97cd7c4e7..7eac6a3e1cde 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -204,14 +204,18 @@ static int uhdlc_init(struct ucc_hdlc_private *priv)
 	priv->rx_skbuff = kcalloc(priv->rx_ring_size,
 				  sizeof(*priv->rx_skbuff),
 				  GFP_KERNEL);
-	if (!priv->rx_skbuff)
+	if (!priv->rx_skbuff) {
+		ret = -ENOMEM;
 		goto free_ucc_pram;
+	}
 
 	priv->tx_skbuff = kcalloc(priv->tx_ring_size,
 				  sizeof(*priv->tx_skbuff),
 				  GFP_KERNEL);
-	if (!priv->tx_skbuff)
+	if (!priv->tx_skbuff) {
+		ret = -ENOMEM;
 		goto free_rx_skbuff;
+	}
 
 	priv->skb_curtx = 0;
 	priv->skb_dirtytx = 0;

From 03cbb87054c17b50a6ead63ed3ab02e094a785b1 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sun, 7 Mar 2021 12:21:56 +0200
Subject: [PATCH 0377/1820] net: dsa: fix switchdev objects on bridge master
 mistakenly being applied on ports

Tobias reports that after the blamed patch, VLAN objects being added to
a bridge device are being added to all slave ports instead (swp2, swp3).

ip link add br0 type bridge vlan_filtering 1
ip link set swp2 master br0
ip link set swp3 master br0
bridge vlan add dev br0 vid 100 self

This is because the fix was too broad: we made dsa_port_offloads_netdev
say "yes, I offload the br0 bridge" for all slave ports, but we didn't
add the checks whether the switchdev object was in fact meant for the
physical port or for the bridge itself. So we are reacting on events in
a way in which we shouldn't.

The reason why the fix was too broad is because the question itself,
"does this DSA port offload this netdev", was too broad in the first
place. The solution is to disambiguate the question and separate it into
two different functions, one to be called for each switchdev attribute /
object that has an orig_dev == net_bridge (dsa_port_offloads_bridge),
and the other for orig_dev == net_bridge_port (*_offloads_bridge_port).

In the case of VLAN objects on the bridge interface, this solves the
problem because we know that VLAN objects are per bridge port and not
per bridge. And when orig_dev is equal to the net_bridge, we offload it
as a bridge, but not as a bridge port; that's how we are able to skip
reacting on those events. Note that this is compatible with future plans
to have explicit offloading of VLAN objects on the bridge interface as a
bridge port (in DSA, this signifies that we should add that VLAN towards
the CPU port).

Fixes: 99b8202b179f ("net: dsa: fix SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING getting ignored")
Reported-by: Tobias Waldekranz <tobias@waldekranz.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Tobias Waldekranz <tobias@waldekranz.com>
Tested-by: Tobias Waldekranz <tobias@waldekranz.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa_priv.h | 25 +++++++++++---------
 net/dsa/slave.c    | 59 +++++++++++++++++++++++++++++++++-------------
 2 files changed, 57 insertions(+), 27 deletions(-)

diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 2eeaa42f2e08..9d4b0e9b1aa1 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -230,8 +230,8 @@ int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr);
 void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr);
 extern const struct phylink_mac_ops dsa_port_phylink_mac_ops;
 
-static inline bool dsa_port_offloads_netdev(struct dsa_port *dp,
-					    struct net_device *dev)
+static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp,
+						 struct net_device *dev)
 {
 	/* Switchdev offloading can be configured on: */
 
@@ -241,12 +241,6 @@ static inline bool dsa_port_offloads_netdev(struct dsa_port *dp,
 		 */
 		return true;
 
-	if (dp->bridge_dev == dev)
-		/* DSA ports connected to a bridge, and event was emitted
-		 * for the bridge.
-		 */
-		return true;
-
 	if (dp->lag_dev == dev)
 		/* DSA ports connected to a bridge via a LAG */
 		return true;
@@ -254,14 +248,23 @@ static inline bool dsa_port_offloads_netdev(struct dsa_port *dp,
 	return false;
 }
 
+static inline bool dsa_port_offloads_bridge(struct dsa_port *dp,
+					    struct net_device *bridge_dev)
+{
+	/* DSA ports connected to a bridge, and event was emitted
+	 * for the bridge.
+	 */
+	return dp->bridge_dev == bridge_dev;
+}
+
 /* Returns true if any port of this tree offloads the given net_device */
-static inline bool dsa_tree_offloads_netdev(struct dsa_switch_tree *dst,
-					    struct net_device *dev)
+static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst,
+						 struct net_device *dev)
 {
 	struct dsa_port *dp;
 
 	list_for_each_entry(dp, &dst->ports, list)
-		if (dsa_port_offloads_netdev(dp, dev))
+		if (dsa_port_offloads_bridge_port(dp, dev))
 			return true;
 
 	return false;
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 491e3761b5f4..992fcab4b552 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -278,28 +278,43 @@ static int dsa_slave_port_attr_set(struct net_device *dev,
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	int ret;
 
-	if (!dsa_port_offloads_netdev(dp, attr->orig_dev))
-		return -EOPNOTSUPP;
-
 	switch (attr->id) {
 	case SWITCHDEV_ATTR_ID_PORT_STP_STATE:
+		if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev))
+			return -EOPNOTSUPP;
+
 		ret = dsa_port_set_state(dp, attr->u.stp_state);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
+		if (!dsa_port_offloads_bridge(dp, attr->orig_dev))
+			return -EOPNOTSUPP;
+
 		ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering,
 					      extack);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME:
+		if (!dsa_port_offloads_bridge(dp, attr->orig_dev))
+			return -EOPNOTSUPP;
+
 		ret = dsa_port_ageing_time(dp, attr->u.ageing_time);
 		break;
 	case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+		if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev))
+			return -EOPNOTSUPP;
+
 		ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags,
 						extack);
 		break;
 	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
+		if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev))
+			return -EOPNOTSUPP;
+
 		ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER:
+		if (!dsa_port_offloads_bridge(dp, attr->orig_dev))
+			return -EOPNOTSUPP;
+
 		ret = dsa_port_mrouter(dp->cpu_dp, attr->u.mrouter, extack);
 		break;
 	default:
@@ -341,9 +356,6 @@ static int dsa_slave_vlan_add(struct net_device *dev,
 	struct switchdev_obj_port_vlan vlan;
 	int err;
 
-	if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
-		return -EOPNOTSUPP;
-
 	if (dsa_port_skip_vlan_configuration(dp)) {
 		NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN");
 		return 0;
@@ -391,27 +403,36 @@ static int dsa_slave_port_obj_add(struct net_device *dev,
 
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_ID_PORT_MDB:
-		if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+		if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
 			return -EOPNOTSUPP;
+
 		err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj));
 		break;
 	case SWITCHDEV_OBJ_ID_HOST_MDB:
+		if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
+			return -EOPNOTSUPP;
+
 		/* DSA can directly translate this to a normal MDB add,
 		 * but on the CPU port.
 		 */
 		err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj));
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
+			return -EOPNOTSUPP;
+
 		err = dsa_slave_vlan_add(dev, obj, extack);
 		break;
 	case SWITCHDEV_OBJ_ID_MRP:
-		if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+		if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
 			return -EOPNOTSUPP;
+
 		err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj));
 		break;
 	case SWITCHDEV_OBJ_ID_RING_ROLE_MRP:
-		if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+		if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
 			return -EOPNOTSUPP;
+
 		err = dsa_port_mrp_add_ring_role(dp,
 						 SWITCHDEV_OBJ_RING_ROLE_MRP(obj));
 		break;
@@ -431,9 +452,6 @@ static int dsa_slave_vlan_del(struct net_device *dev,
 	struct switchdev_obj_port_vlan *vlan;
 	int err;
 
-	if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
-		return -EOPNOTSUPP;
-
 	if (dsa_port_skip_vlan_configuration(dp))
 		return 0;
 
@@ -459,27 +477,36 @@ static int dsa_slave_port_obj_del(struct net_device *dev,
 
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_ID_PORT_MDB:
-		if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+		if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
 			return -EOPNOTSUPP;
+
 		err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj));
 		break;
 	case SWITCHDEV_OBJ_ID_HOST_MDB:
+		if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
+			return -EOPNOTSUPP;
+
 		/* DSA can directly translate this to a normal MDB add,
 		 * but on the CPU port.
 		 */
 		err = dsa_port_mdb_del(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj));
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
+			return -EOPNOTSUPP;
+
 		err = dsa_slave_vlan_del(dev, obj);
 		break;
 	case SWITCHDEV_OBJ_ID_MRP:
-		if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+		if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
 			return -EOPNOTSUPP;
+
 		err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj));
 		break;
 	case SWITCHDEV_OBJ_ID_RING_ROLE_MRP:
-		if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+		if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
 			return -EOPNOTSUPP;
+
 		err = dsa_port_mrp_del_ring_role(dp,
 						 SWITCHDEV_OBJ_RING_ROLE_MRP(obj));
 		break;
@@ -2298,7 +2325,7 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused,
 			 * other ports bridged with the LAG should be able to
 			 * autonomously forward towards it.
 			 */
-			if (dsa_tree_offloads_netdev(dp->ds->dst, dev))
+			if (dsa_tree_offloads_bridge_port(dp->ds->dst, dev))
 				return NOTIFY_DONE;
 		}
 

From ac88c531a5b38877eba2365a3f28f0c8b513dc33 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Sun, 7 Mar 2021 13:17:47 +0000
Subject: [PATCH 0378/1820] net: davicom: Fix regulator not turned off on
 failed probe

When the probe fails or requests to be defered, we must disable the
regulator that was previously enabled.

Fixes: 7994fe55a4a2 ("dm9000: Add regulator and reset support to dm9000")
Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/davicom/dm9000.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 3fdc70dab5c1..ae744826bb9e 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1449,7 +1449,7 @@ dm9000_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(dev, "failed to request reset gpio %d: %d\n",
 				reset_gpios, ret);
-			return -ENODEV;
+			goto out_regulator_disable;
 		}
 
 		/* According to manual PWRST# Low Period Min 1ms */
@@ -1461,8 +1461,10 @@ dm9000_probe(struct platform_device *pdev)
 
 	if (!pdata) {
 		pdata = dm9000_parse_dt(&pdev->dev);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
+		if (IS_ERR(pdata)) {
+			ret = PTR_ERR(pdata);
+			goto out_regulator_disable;
+		}
 	}
 
 	/* Init network device */
@@ -1703,6 +1705,10 @@ out:
 	dm9000_release_board(pdev, db);
 	free_netdev(ndev);
 
+out_regulator_disable:
+	if (!IS_ERR(power))
+		regulator_disable(power);
+
 	return ret;
 }
 

From cf9e60aa69ae6c40d3e3e4c94dd6c8de31674e9b Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Sun, 7 Mar 2021 13:17:48 +0000
Subject: [PATCH 0379/1820] net: davicom: Fix regulator not turned off on
 driver removal

We must disable the regulator that was enabled in the probe function.

Fixes: 7994fe55a4a2 ("dm9000: Add regulator and reset support to dm9000")
Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/davicom/dm9000.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index ae744826bb9e..a95e95ce9438 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -133,6 +133,8 @@ struct board_info {
 	u32		wake_state;
 
 	int		ip_summed;
+
+	struct regulator *power_supply;
 };
 
 /* debug code */
@@ -1481,6 +1483,8 @@ dm9000_probe(struct platform_device *pdev)
 
 	db->dev = &pdev->dev;
 	db->ndev = ndev;
+	if (!IS_ERR(power))
+		db->power_supply = power;
 
 	spin_lock_init(&db->lock);
 	mutex_init(&db->addr_lock);
@@ -1766,10 +1770,13 @@ static int
 dm9000_drv_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct board_info *dm = to_dm9000_board(ndev);
 
 	unregister_netdev(ndev);
-	dm9000_release_board(pdev, netdev_priv(ndev));
+	dm9000_release_board(pdev, dm);
 	free_netdev(ndev);		/* free device structure */
+	if (dm->power_supply)
+		regulator_disable(dm->power_supply);
 
 	dev_dbg(&pdev->dev, "released and freed device\n");
 	return 0;

From 2e2696223676d56db1a93acfca722c1b96cd552d Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Sun, 7 Mar 2021 13:17:49 +0000
Subject: [PATCH 0380/1820] net: davicom: Use platform_get_irq_optional()

The second IRQ line really is optional, so use
platform_get_irq_optional() to obtain it.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/davicom/dm9000.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index a95e95ce9438..252adfa5d837 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1507,7 +1507,7 @@ dm9000_probe(struct platform_device *pdev)
 		goto out;
 	}
 
-	db->irq_wake = platform_get_irq(pdev, 1);
+	db->irq_wake = platform_get_irq_optional(pdev, 1);
 	if (db->irq_wake >= 0) {
 		dev_dbg(db->dev, "wakeup irq %d\n", db->irq_wake);
 

From 1b2395dfff5bb40228a187f21f577cd90673d344 Mon Sep 17 00:00:00 2001
From: Alex Marginean <alexandru.marginean@nxp.com>
Date: Sun, 7 Mar 2021 15:23:38 +0200
Subject: [PATCH 0381/1820] net: enetc: set MAC RX FIFO to recommended value

On LS1028A, the MAC RX FIFO defaults to the value 2, which is too high
and may lead to RX lock-up under traffic at a rate higher than 6 Gbps.
Set it to 1 instead, as recommended by the hardware design team and by
later versions of the ENETC block guide.

Signed-off-by: Alex Marginean <alexandru.marginean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Reviewed-by: Jason Liu <jason.hui.liu@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc_hw.h | 2 ++
 drivers/net/ethernet/freescale/enetc/enetc_pf.c | 6 ++++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index de0d20b0f489..00938f7960a4 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -234,6 +234,8 @@ enum enetc_bdr_type {TX, RX};
 #define ENETC_PM0_MAXFRM	0x8014
 #define ENETC_SET_TX_MTU(val)	((val) << 16)
 #define ENETC_SET_MAXFRM(val)	((val) & 0xffff)
+#define ENETC_PM0_RX_FIFO	0x801c
+#define ENETC_PM0_RX_FIFO_VAL	1
 
 #define ENETC_PM_IMDIO_BASE	0x8030
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index ca02f033bea2..224fc37a6757 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -490,6 +490,12 @@ static void enetc_configure_port_mac(struct enetc_hw *hw)
 
 	enetc_port_wr(hw, ENETC_PM1_CMD_CFG, ENETC_PM0_CMD_PHY_TX_EN |
 		      ENETC_PM0_CMD_TXP	| ENETC_PM0_PROMISC);
+
+	/* On LS1028A, the MAC RX FIFO defaults to 2, which is too high
+	 * and may lead to RX lock-up under traffic. Set it to 1 instead,
+	 * as recommended by the hardware team.
+	 */
+	enetc_port_wr(hw, ENETC_PM0_RX_FIFO, ENETC_PM0_RX_FIFO_VAL);
 }
 
 static void enetc_mac_config(struct enetc_hw *hw, phy_interface_t phy_mode)

From 29d98f54a4fe1b6a9089bec8715a1b89ff9ad59c Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sun, 7 Mar 2021 15:23:39 +0200
Subject: [PATCH 0382/1820] net: enetc: allow hardware timestamping on TX
 queues with tc-etf enabled

The txtime is passed to the driver in skb->skb_mstamp_ns, which is
actually in a union with skb->tstamp (the place where software
timestamps are kept).

Since commit b50a5c70ffa4 ("net: allow simultaneous SW and HW transmit
timestamping"), __sock_recv_timestamp has some logic for making sure
that the two calls to skb_tstamp_tx:

skb_tx_timestamp(skb) # Software timestamp in the driver
-> skb_tstamp_tx(skb, NULL)

and

skb_tstamp_tx(skb, &shhwtstamps) # Hardware timestamp in the driver

will both do the right thing and in a race-free manner, meaning that
skb_tx_timestamp will deliver a cmsg with the software timestamp only,
and skb_tstamp_tx with a non-NULL hwtstamps argument will deliver a cmsg
with the hardware timestamp only.

Why are races even possible? Well, because although the software timestamp
skb->tstamp is private per skb, the hardware timestamp skb_hwtstamps(skb)
lives in skb_shinfo(skb), an area which is shared between skbs and their
clones. And skb_tstamp_tx works by cloning the packets when timestamping
them, therefore attempting to perform hardware timestamping on an skb's
clone will also change the hardware timestamp of the original skb. And
the original skb might have been yet again cloned for software
timestamping, at an earlier stage.

So the logic in __sock_recv_timestamp can't be as simple as saying
"does this skb have a hardware timestamp? if yes I'll send the hardware
timestamp to the socket, otherwise I'll send the software timestamp",
precisely because the hardware timestamp is shared.
Instead, it's quite the other way around: __sock_recv_timestamp says
"does this skb have a software timestamp? if yes, I'll send the software
timestamp, otherwise the hardware one". This works because the software
timestamp is not shared with clones.

But that means we have a problem when we attempt hardware timestamping
with skbs that don't have the skb->tstamp == 0. __sock_recv_timestamp
will say "oh, yeah, this must be some sort of odd clone" and will not
deliver the hardware timestamp to the socket. And this is exactly what
is happening when we have txtime enabled on the socket: as mentioned,
that is put in a union with skb->tstamp, so it is quite easy to mistake
it.

Do what other drivers do (intel igb/igc) and write zero to skb->tstamp
before taking the hardware timestamp. It's of no use to us now (we're
already on the TX confirmation path).

Fixes: 0d08c9ec7d6e ("enetc: add support time specific departure base on the qos etf")
Cc: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 30d7d4e83900..09471329f3a3 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -344,6 +344,12 @@ static void enetc_tstamp_tx(struct sk_buff *skb, u64 tstamp)
 	if (skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) {
 		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 		shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
+		/* Ensure skb_mstamp_ns, which might have been populated with
+		 * the txtime, is not mistaken for a software timestamp,
+		 * because this will prevent the dispatch of our hardware
+		 * timestamp to the socket.
+		 */
+		skb->tstamp = ktime_set(0, 0);
 		skb_tstamp_tx(skb, &shhwtstamps);
 	}
 }

From 2055a99da8a253a357bdfd359b3338ef3375a26c Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Sun, 7 Mar 2021 19:11:02 -0800
Subject: [PATCH 0383/1820] net: bonding: fix error return code of
 bond_neigh_init()

When slave is NULL or slave_ops->ndo_neigh_setup is NULL, no error
return code of bond_neigh_init() is assigned.
To fix this bug, ret is assigned with -EINVAL in these cases.

Fixes: 9e99bfefdbce ("bonding: fix bond_neigh_init()")
Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 74cbbb22470b..456315bef3a8 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3978,11 +3978,15 @@ static int bond_neigh_init(struct neighbour *n)
 
 	rcu_read_lock();
 	slave = bond_first_slave_rcu(bond);
-	if (!slave)
+	if (!slave) {
+		ret = -EINVAL;
 		goto out;
+	}
 	slave_ops = slave->dev->netdev_ops;
-	if (!slave_ops->ndo_neigh_setup)
+	if (!slave_ops->ndo_neigh_setup) {
+		ret = -EINVAL;
 		goto out;
+	}
 
 	/* TODO: find another way [1] to implement this.
 	 * Passing a zeroed structure is fragile,

From 69dd4503a7e6bae3389b8e028e5768008be8f2d7 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 16 Feb 2021 15:36:07 +0100
Subject: [PATCH 0384/1820] irqdomain: Remove debugfs_file from struct
 irq_domain

There's no need to keep around a dentry pointer to a simple file that
debugfs itself can look up when we need to remove it from the system.
So simplify the code by deleting the variable and cleaning up the logic
around the debugfs file.

Cc: Marc Zyngier <maz@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/YCvYV53ZdzQSWY6w@kroah.com
---
 include/linux/irqdomain.h | 4 ----
 kernel/irq/irqdomain.c    | 9 ++++-----
 2 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 42d196805f58..33cacc8af26d 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -150,7 +150,6 @@ struct irq_domain_chip_generic;
  *      setting up one or more generic chips for interrupt controllers
  *      drivers using the generic chip library which uses this pointer.
  * @parent: Pointer to parent irq_domain to support hierarchy irq_domains
- * @debugfs_file: dentry for the domain debugfs file
  *
  * Revmap data, used internally by irq_domain
  * @revmap_direct_max_irq: The largest hwirq that can be set for controllers that
@@ -174,9 +173,6 @@ struct irq_domain {
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 	struct irq_domain *parent;
 #endif
-#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
-	struct dentry		*debugfs_file;
-#endif
 
 	/* reverse map data. The linear map gets appended to the irq_domain */
 	irq_hw_number_t hwirq_max;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 288151393a06..d10ab1d689d5 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1898,16 +1898,15 @@ DEFINE_SHOW_ATTRIBUTE(irq_domain_debug);
 
 static void debugfs_add_domain_dir(struct irq_domain *d)
 {
-	if (!d->name || !domain_dir || d->debugfs_file)
+	if (!d->name || !domain_dir)
 		return;
-	d->debugfs_file = debugfs_create_file(d->name, 0444, domain_dir, d,
-					      &irq_domain_debug_fops);
+	debugfs_create_file(d->name, 0444, domain_dir, d,
+			    &irq_domain_debug_fops);
 }
 
 static void debugfs_remove_domain_dir(struct irq_domain *d)
 {
-	debugfs_remove(d->debugfs_file);
-	d->debugfs_file = NULL;
+	debugfs_remove(debugfs_lookup(d->name, domain_dir));
 }
 
 void __init irq_domain_debugfs_init(struct dentry *root)

From 3e895f4cbd158c31f1295d097a73ea4fe50f88f4 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 17 Feb 2021 18:10:35 +0000
Subject: [PATCH 0385/1820] ARM: ep93xx: Select GENERIC_IRQ_MULTI_HANDLER
 directly

ep93xx currently relies of CONFIG_ARM_VIC to select
GENERIC_IRQ_MULTI_HANDLER. Given that this is logically a platform
architecture property, add the selection of GENERIC_IRQ_MULTI_HANDLER
at the platform level.

Further patches will remove the selection from the irqchip side.

Reported-by: Marc Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Hector Martin <marcan@marcan.st>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 853aab5ab327..5da96f5df48f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -348,6 +348,7 @@ config ARCH_EP93XX
 	select ARM_AMBA
 	imply ARM_PATCH_PHYS_VIRT
 	select ARM_VIC
+	select GENERIC_IRQ_MULTI_HANDLER
 	select AUTO_ZRELADDR
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO

From a79f7051cccb6f3bcd3d2a0a058c7d5c79bb0371 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 17 Feb 2021 14:28:00 +0000
Subject: [PATCH 0386/1820] irqchip: Do not blindly select
 CONFIG_GENERIC_IRQ_MULTI_HANDLER

Implementing CONFIG_GENERIC_IRQ_MULTI_HANDLER is a decision that is
made at the architecture level, and shouldn't involve the irqchip
at all (we even provide a fallback helper when the option isn't
selected).

Drop all instances of such selection from non-arch code.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210217142800.2547737-1-maz@kernel.org
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Hector Martin <marcan@marcan.st>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 drivers/irqchip/Kconfig | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index e74fa206240a..15536e321df5 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -8,7 +8,6 @@ config IRQCHIP
 config ARM_GIC
 	bool
 	select IRQ_DOMAIN_HIERARCHY
-	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
 
 config ARM_GIC_PM
@@ -33,7 +32,6 @@ config GIC_NON_BANKED
 
 config ARM_GIC_V3
 	bool
-	select GENERIC_IRQ_MULTI_HANDLER
 	select IRQ_DOMAIN_HIERARCHY
 	select PARTITION_PERCPU
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
@@ -64,7 +62,6 @@ config ARM_NVIC
 config ARM_VIC
 	bool
 	select IRQ_DOMAIN
-	select GENERIC_IRQ_MULTI_HANDLER
 
 config ARM_VIC_NR
 	int
@@ -99,14 +96,12 @@ config ATMEL_AIC_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config ATMEL_AIC5_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config I8259
@@ -153,7 +148,6 @@ config DW_APB_ICTL
 config FARADAY_FTINTC010
 	bool
 	select IRQ_DOMAIN
-	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config HISILICON_IRQ_MBIGEN
@@ -169,7 +163,6 @@ config IMGPDC_IRQ
 config IXP4XX_IRQ
 	bool
 	select IRQ_DOMAIN
-	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config MADERA_IRQ
@@ -186,7 +179,6 @@ config CLPS711X_IRQCHIP
 	bool
 	depends on ARCH_CLPS711X
 	select IRQ_DOMAIN
-	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 	default y
 
@@ -205,7 +197,6 @@ config OMAP_IRQCHIP
 config ORION_IRQCHIP
 	bool
 	select IRQ_DOMAIN
-	select GENERIC_IRQ_MULTI_HANDLER
 
 config PIC32_EVIC
 	bool

From f0940f4b3284a00f38a5d42e6067c2aaa20e1f2e Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Wed, 3 Mar 2021 08:47:16 -0500
Subject: [PATCH 0387/1820] SUNRPC: Set memalloc_nofs_save() for sync tasks

We could recurse into NFS doing memory reclaim while sending a sync task,
which might result in a deadlock.  Set memalloc_nofs_save for sync task
execution.

Fixes: a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save() on all rpciod/xprtiod jobs")
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/sched.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index cf702a5f7fe5..39ed0e0afe6d 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -963,8 +963,11 @@ void rpc_execute(struct rpc_task *task)
 
 	rpc_set_active(task);
 	rpc_make_runnable(rpciod_workqueue, task);
-	if (!is_async)
+	if (!is_async) {
+		unsigned int pflags = memalloc_nofs_save();
 		__rpc_execute(task);
+		memalloc_nofs_restore(pflags);
+	}
 }
 
 static void rpc_async_schedule(struct work_struct *work)

From 82e7ca1334ab16e2e04fafded1cab9dfcdc11b40 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 8 Mar 2021 14:42:51 -0500
Subject: [PATCH 0388/1820] NFS: Don't revalidate the directory permissions on
 a lookup failure

There should be no reason to expect the directory permissions to change
just because the directory contents changed or a negative lookup timed
out. So let's avoid doing a full call to nfs_mark_for_revalidate() in
that case.
Furthermore, if this is a negative dentry, and we haven't actually done
a new lookup, then we have no reason yet to believe the directory has
changed at all. So let's remove the gratuitous directory inode
invalidation altogether when called from
nfs_lookup_revalidate_negative().

Reported-by: Geert Jansen <gerardu@amazon.com>
Fixes: 5ceb9d7fdaaf ("NFS: Refactor nfs_lookup_revalidate()")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/dir.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 19a9f434442f..08b162de627f 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1401,6 +1401,15 @@ out_force:
 	goto out;
 }
 
+static void nfs_mark_dir_for_revalidate(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	spin_lock(&inode->i_lock);
+	nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE;
+	spin_unlock(&inode->i_lock);
+}
+
 /*
  * We judge how long we want to trust negative
  * dentries by looking at the parent inode mtime.
@@ -1435,7 +1444,6 @@ nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry,
 			__func__, dentry);
 		return 1;
 	case 0:
-		nfs_mark_for_revalidate(dir);
 		if (inode && S_ISDIR(inode->i_mode)) {
 			/* Purge readdir caches. */
 			nfs_zap_caches(inode);
@@ -1525,6 +1533,13 @@ out:
 	nfs_free_fattr(fattr);
 	nfs_free_fhandle(fhandle);
 	nfs4_label_free(label);
+
+	/*
+	 * If the lookup failed despite the dentry change attribute being
+	 * a match, then we should revalidate the directory cache.
+	 */
+	if (!ret && nfs_verify_change_attribute(dir, dentry->d_time))
+		nfs_mark_dir_for_revalidate(dir);
 	return nfs_lookup_revalidate_done(dir, dentry, inode, ret);
 }
 
@@ -1567,7 +1582,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 		error = nfs_lookup_verify_inode(inode, flags);
 		if (error) {
 			if (error == -ESTALE)
-				nfs_zap_caches(dir);
+				nfs_mark_dir_for_revalidate(dir);
 			goto out_bad;
 		}
 		nfs_advise_use_readdirplus(dir);
@@ -2064,7 +2079,6 @@ out:
 	dput(parent);
 	return d;
 out_error:
-	nfs_mark_for_revalidate(dir);
 	d = ERR_PTR(error);
 	goto out;
 }

From 47397915ede0192235474b145ebcd81b37b03624 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 8 Mar 2021 14:42:52 -0500
Subject: [PATCH 0389/1820] NFS: Don't gratuitously clear the inode cache when
 lookup failed

The fact that the lookup revalidation failed, does not mean that the
inode contents have changed.

Fixes: 5ceb9d7fdaaf ("NFS: Refactor nfs_lookup_revalidate()")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/dir.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 08b162de627f..a91f324cca49 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1444,18 +1444,14 @@ nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry,
 			__func__, dentry);
 		return 1;
 	case 0:
-		if (inode && S_ISDIR(inode->i_mode)) {
-			/* Purge readdir caches. */
-			nfs_zap_caches(inode);
-			/*
-			 * We can't d_drop the root of a disconnected tree:
-			 * its d_hash is on the s_anon list and d_drop() would hide
-			 * it from shrink_dcache_for_unmount(), leading to busy
-			 * inodes on unmount and further oopses.
-			 */
-			if (IS_ROOT(dentry))
-				return 1;
-		}
+		/*
+		 * We can't d_drop the root of a disconnected tree:
+		 * its d_hash is on the s_anon list and d_drop() would hide
+		 * it from shrink_dcache_for_unmount(), leading to busy
+		 * inodes on unmount and further oopses.
+		 */
+		if (inode && IS_ROOT(dentry))
+			return 1;
 		dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n",
 				__func__, dentry);
 		return 0;

From fd6d3feed041e96b84680d0bfc1e7abc8f65de92 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 8 Mar 2021 14:42:53 -0500
Subject: [PATCH 0390/1820] NFS: Clean up function
 nfs_mark_dir_for_revalidate()

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/dir.c      | 4 +---
 fs/nfs/inode.c    | 2 +-
 fs/nfs/internal.h | 3 ++-
 3 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index a91f324cca49..02ac982846f4 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1403,10 +1403,8 @@ out_force:
 
 static void nfs_mark_dir_for_revalidate(struct inode *inode)
 {
-	struct nfs_inode *nfsi = NFS_I(inode);
-
 	spin_lock(&inode->i_lock);
-	nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE;
+	nfs_set_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE);
 	spin_unlock(&inode->i_lock);
 }
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 749bbea14d99..d21bfaac10b0 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -207,7 +207,7 @@ static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi)
 }
 #endif
 
-static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
+void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	bool have_delegation = NFS_PROTO(inode)->have_delegation(inode, FMODE_READ);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 25fb43b69e5a..7b644d6c09e4 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -411,7 +411,8 @@ extern int nfs_write_inode(struct inode *, struct writeback_control *);
 extern int nfs_drop_inode(struct inode *);
 extern void nfs_clear_inode(struct inode *);
 extern void nfs_evict_inode(struct inode *);
-void nfs_zap_acl_cache(struct inode *inode);
+extern void nfs_zap_acl_cache(struct inode *inode);
+extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags);
 extern bool nfs_check_cache_invalid(struct inode *, unsigned long);
 extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
 extern int nfs_wait_atomic_killable(atomic_t *p, unsigned int mode);

From ac46b3d768e4c2754f7b191b81e1bea582e11907 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 8 Mar 2021 14:42:54 -0500
Subject: [PATCH 0391/1820] NFS: Fix open coded versions of
 nfs_set_cache_invalid()

nfs_set_cache_invalid() has code to handle delegations, and other
optimisations, so let's use it when appropriate.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/dir.c    | 20 ++++++++++----------
 fs/nfs/inode.c  |  4 ++--
 fs/nfs/unlink.c |  6 +++---
 fs/nfs/write.c  |  8 ++++----
 4 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 02ac982846f4..fc4f490f2d78 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -81,8 +81,9 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir
 		spin_lock(&dir->i_lock);
 		if (list_empty(&nfsi->open_files) &&
 		    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
-			nfsi->cache_validity |= NFS_INO_INVALID_DATA |
-				NFS_INO_REVAL_FORCED;
+			nfs_set_cache_invalid(dir,
+					      NFS_INO_INVALID_DATA |
+						      NFS_INO_REVAL_FORCED);
 		list_add(&ctx->list, &nfsi->open_files);
 		spin_unlock(&dir->i_lock);
 		return ctx;
@@ -1700,10 +1701,9 @@ static void nfs_drop_nlink(struct inode *inode)
 	if (inode->i_nlink > 0)
 		drop_nlink(inode);
 	NFS_I(inode)->attr_gencount = nfs_inc_attr_generation_counter();
-	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_CHANGE
-		| NFS_INO_INVALID_CTIME
-		| NFS_INO_INVALID_OTHER
-		| NFS_INO_REVAL_FORCED;
+	nfs_set_cache_invalid(
+		inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME |
+			       NFS_INO_INVALID_OTHER | NFS_INO_REVAL_FORCED);
 	spin_unlock(&inode->i_lock);
 }
 
@@ -1715,7 +1715,7 @@ static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode)
 {
 	if (S_ISDIR(inode->i_mode))
 		/* drop any readdir cache as it could easily be old */
-		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
 
 	if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
 		nfs_complete_unlink(dentry, inode);
@@ -2481,9 +2481,9 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 	if (error == 0) {
 		spin_lock(&old_inode->i_lock);
 		NFS_I(old_inode)->attr_gencount = nfs_inc_attr_generation_counter();
-		NFS_I(old_inode)->cache_validity |= NFS_INO_INVALID_CHANGE
-			| NFS_INO_INVALID_CTIME
-			| NFS_INO_REVAL_FORCED;
+		nfs_set_cache_invalid(old_inode, NFS_INO_INVALID_CHANGE |
+							 NFS_INO_INVALID_CTIME |
+							 NFS_INO_REVAL_FORCED);
 		spin_unlock(&old_inode->i_lock);
 	}
 out:
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index d21bfaac10b0..eb1ae77f411a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1067,8 +1067,8 @@ void nfs_inode_attach_open_context(struct nfs_open_context *ctx)
 	spin_lock(&inode->i_lock);
 	if (list_empty(&nfsi->open_files) &&
 	    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
-		nfsi->cache_validity |= NFS_INO_INVALID_DATA |
-			NFS_INO_REVAL_FORCED;
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA |
+						     NFS_INO_REVAL_FORCED);
 	list_add_tail_rcu(&ctx->list, &nfsi->open_files);
 	spin_unlock(&inode->i_lock);
 }
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index b27ebdccef70..5fa11e1aca4c 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -500,9 +500,9 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 		spin_lock(&inode->i_lock);
 		NFS_I(inode)->attr_gencount = nfs_inc_attr_generation_counter();
-		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_CHANGE
-			| NFS_INO_INVALID_CTIME
-			| NFS_INO_REVAL_FORCED;
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE |
+						     NFS_INO_INVALID_CTIME |
+						     NFS_INO_REVAL_FORCED);
 		spin_unlock(&inode->i_lock);
 		d_move(dentry, sdentry);
 		break;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 82bdcb982186..f05a90338a76 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -303,9 +303,9 @@ static void nfs_set_pageerror(struct address_space *mapping)
 	nfs_zap_mapping(mapping->host, mapping);
 	/* Force file size revalidation */
 	spin_lock(&inode->i_lock);
-	NFS_I(inode)->cache_validity |= NFS_INO_REVAL_FORCED |
-					NFS_INO_REVAL_PAGECACHE |
-					NFS_INO_INVALID_SIZE;
+	nfs_set_cache_invalid(inode, NFS_INO_REVAL_FORCED |
+					     NFS_INO_REVAL_PAGECACHE |
+					     NFS_INO_INVALID_SIZE);
 	spin_unlock(&inode->i_lock);
 }
 
@@ -1604,7 +1604,7 @@ static int nfs_writeback_done(struct rpc_task *task,
 	/* Deal with the suid/sgid bit corner case */
 	if (nfs_should_remove_suid(inode)) {
 		spin_lock(&inode->i_lock);
-		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_OTHER;
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
 		spin_unlock(&inode->i_lock);
 	}
 	return 0;

From b6f80a2ebb97f184c4679518ac83074598bf9bf4 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 8 Mar 2021 14:42:55 -0500
Subject: [PATCH 0392/1820] NFS: Fix open coded versions of
 nfs_set_cache_invalid() in NFSv4

nfs_set_cache_invalid() has code to handle delegations, and other
optimisations, so let's use it when appropriate.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/inode.c     |  1 +
 fs/nfs/nfs42proc.c | 12 +++++++-----
 fs/nfs/nfs4proc.c  | 28 ++++++++++++----------------
 3 files changed, 20 insertions(+), 21 deletions(-)

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index eb1ae77f411a..a7fb076a5f44 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -229,6 +229,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 	if (flags & NFS_INO_INVALID_DATA)
 		nfs_fscache_invalidate(inode);
 }
+EXPORT_SYMBOL_GPL(nfs_set_cache_invalid);
 
 /*
  * Invalidate the local caches
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index f3fd935620fc..094024b0aca1 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -357,13 +357,15 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 	truncate_pagecache_range(dst_inode, pos_dst,
 				 pos_dst + res->write_res.count);
 	spin_lock(&dst_inode->i_lock);
-	NFS_I(dst_inode)->cache_validity |= (NFS_INO_REVAL_PAGECACHE |
-			NFS_INO_REVAL_FORCED | NFS_INO_INVALID_SIZE |
-			NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA);
+	nfs_set_cache_invalid(
+		dst_inode, NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED |
+				   NFS_INO_INVALID_SIZE | NFS_INO_INVALID_ATTR |
+				   NFS_INO_INVALID_DATA);
 	spin_unlock(&dst_inode->i_lock);
 	spin_lock(&src_inode->i_lock);
-	NFS_I(src_inode)->cache_validity |= (NFS_INO_REVAL_PAGECACHE |
-			NFS_INO_REVAL_FORCED | NFS_INO_INVALID_ATIME);
+	nfs_set_cache_invalid(src_inode, NFS_INO_REVAL_PAGECACHE |
+						 NFS_INO_REVAL_FORCED |
+						 NFS_INO_INVALID_ATIME);
 	spin_unlock(&src_inode->i_lock);
 	status = res->write_res.count;
 out:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 74bc5120013d..6d8fc56e5f45 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1169,14 +1169,14 @@ int nfs4_call_sync(struct rpc_clnt *clnt,
 static void
 nfs4_inc_nlink_locked(struct inode *inode)
 {
-	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_OTHER;
+	nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
 	inc_nlink(inode);
 }
 
 static void
 nfs4_dec_nlink_locked(struct inode *inode)
 {
-	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_OTHER;
+	nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
 	drop_nlink(inode);
 }
 
@@ -1187,35 +1187,31 @@ nfs4_update_changeattr_locked(struct inode *inode,
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 
-	nfsi->cache_validity |= NFS_INO_INVALID_CTIME
-		| NFS_INO_INVALID_MTIME
-		| cache_validity;
+	cache_validity |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME;
 
 	if (cinfo->atomic && cinfo->before == inode_peek_iversion_raw(inode)) {
 		nfsi->cache_validity &= ~NFS_INO_REVAL_PAGECACHE;
 		nfsi->attrtimeo_timestamp = jiffies;
 	} else {
 		if (S_ISDIR(inode->i_mode)) {
-			nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+			cache_validity |= NFS_INO_INVALID_DATA;
 			nfs_force_lookup_revalidate(inode);
 		} else {
 			if (!NFS_PROTO(inode)->have_delegation(inode,
 							       FMODE_READ))
-				nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE;
+				cache_validity |= NFS_INO_REVAL_PAGECACHE;
 		}
 
 		if (cinfo->before != inode_peek_iversion_raw(inode))
-			nfsi->cache_validity |= NFS_INO_INVALID_ACCESS |
-						NFS_INO_INVALID_ACL |
-						NFS_INO_INVALID_XATTR;
+			cache_validity |= NFS_INO_INVALID_ACCESS |
+					  NFS_INO_INVALID_ACL |
+					  NFS_INO_INVALID_XATTR;
 	}
 	inode_set_iversion_raw(inode, cinfo->after);
 	nfsi->read_cache_jiffies = timestamp;
 	nfsi->attr_gencount = nfs_inc_attr_generation_counter();
+	nfs_set_cache_invalid(inode, cache_validity);
 	nfsi->cache_validity &= ~NFS_INO_INVALID_CHANGE;
-
-	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
-		nfs_fscache_invalidate(inode);
 }
 
 void
@@ -5915,9 +5911,9 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	 * so mark the attribute cache invalid.
 	 */
 	spin_lock(&inode->i_lock);
-	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_CHANGE
-		| NFS_INO_INVALID_CTIME
-		| NFS_INO_REVAL_FORCED;
+	nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE |
+					     NFS_INO_INVALID_CTIME |
+					     NFS_INO_REVAL_FORCED);
 	spin_unlock(&inode->i_lock);
 	nfs_access_zap_cache(inode);
 	nfs_zap_acl_cache(inode);

From e5e35e754c28724d5c619f2ec805fd221f8d59ce Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Mon, 8 Mar 2021 15:59:18 +0100
Subject: [PATCH 0393/1820] bpf: BPF-helper for MTU checking add length input

The FIB lookup example[1] show how the IP-header field tot_len
(iph->tot_len) is used as input to perform the MTU check.

This patch extend the BPF-helper bpf_check_mtu() with the same ability
to provide the length as user parameter input, via mtu_len parameter.

This still needs to be done before the bpf_check_mtu() helper API
becomes frozen.

  [1] samples/bpf/xdp_fwd_kern.c

Fixes: 34b2021cc616 ("bpf: Add BPF-helper for MTU checking")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/161521555850.3515614.6533850861569774444.stgit@firesoul
---
 include/uapi/linux/bpf.h | 16 +++++++++++-----
 net/core/filter.c        | 12 ++++++++++--
 2 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 79c893310492..4ba4ef0ff63a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3850,7 +3850,7 @@ union bpf_attr {
  *
  * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
  *	Description
- *		Check ctx packet size against exceeding MTU of net device (based
+ *		Check packet size against exceeding MTU of net device (based
  *		on *ifindex*).  This helper will likely be used in combination
  *		with helpers that adjust/change the packet size.
  *
@@ -3867,6 +3867,14 @@ union bpf_attr {
  *		against the current net device.  This is practical if this isn't
  *		used prior to redirect.
  *
+ *		On input *mtu_len* must be a valid pointer, else verifier will
+ *		reject BPF program.  If the value *mtu_len* is initialized to
+ *		zero then the ctx packet size is use.  When value *mtu_len* is
+ *		provided as input this specify the L3 length that the MTU check
+ *		is done against. Remember XDP and TC length operate at L2, but
+ *		this value is L3 as this correlate to MTU and IP-header tot_len
+ *		values which are L3 (similar behavior as bpf_fib_lookup).
+ *
  *		The Linux kernel route table can configure MTUs on a more
  *		specific per route level, which is not provided by this helper.
  *		For route level MTU checks use the **bpf_fib_lookup**\ ()
@@ -3891,11 +3899,9 @@ union bpf_attr {
  *
  *		On return *mtu_len* pointer contains the MTU value of the net
  *		device.  Remember the net device configured MTU is the L3 size,
- *		which is returned here and XDP and TX length operate at L2.
+ *		which is returned here and XDP and TC length operate at L2.
  *		Helper take this into account for you, but remember when using
- *		MTU value in your BPF-code.  On input *mtu_len* must be a valid
- *		pointer and be initialized (to zero), else verifier will reject
- *		BPF program.
+ *		MTU value in your BPF-code.
  *
  *	Return
  *		* 0 on success, and populate MTU value in *mtu_len* pointer.
diff --git a/net/core/filter.c b/net/core/filter.c
index adfdad234674..9323d34d34cc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5658,7 +5658,7 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
 		return -EINVAL;
 
-	if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff))
+	if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len)))
 		return -EINVAL;
 
 	dev = __dev_via_ifindex(dev, ifindex);
@@ -5668,7 +5668,11 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	mtu = READ_ONCE(dev->mtu);
 
 	dev_len = mtu + dev->hard_header_len;
-	skb_len = skb->len + len_diff; /* minus result pass check */
+
+	/* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+	skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len;
+
+	skb_len += len_diff; /* minus result pass check */
 	if (skb_len <= dev_len) {
 		ret = BPF_MTU_CHK_RET_SUCCESS;
 		goto out;
@@ -5713,6 +5717,10 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
 	/* Add L2-header as dev MTU is L3 size */
 	dev_len = mtu + dev->hard_header_len;
 
+	/* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+	if (*mtu_len)
+		xdp_len = *mtu_len + dev->hard_header_len;
+
 	xdp_len += len_diff; /* minus result pass check */
 	if (xdp_len > dev_len)
 		ret = BPF_MTU_CHK_RET_FRAG_NEEDED;

From e5e010a3063ad801cb3f85793cbada9c2a654e40 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Mon, 8 Mar 2021 15:59:23 +0100
Subject: [PATCH 0394/1820] selftests/bpf: Tests using bpf_check_mtu BPF-helper
 input mtu_len param

Add tests that use mtu_len as input parameter in BPF-helper
bpf_check_mtu().

The BPF-helper is avail from both XDP and TC context. Add two tests
per context, one that tests below MTU and one that exceeds the MTU.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/161521556358.3515614.5915221479709358964.stgit@firesoul
---
 .../selftests/bpf/prog_tests/check_mtu.c      |  4 +
 .../selftests/bpf/progs/test_check_mtu.c      | 92 +++++++++++++++++++
 2 files changed, 96 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
index 36af1c138faf..b62a39315336 100644
--- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c
+++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
@@ -128,6 +128,8 @@ static void test_check_mtu_xdp(__u32 mtu, __u32 ifindex)
 	test_check_mtu_run_xdp(skel, skel->progs.xdp_use_helper, mtu);
 	test_check_mtu_run_xdp(skel, skel->progs.xdp_exceed_mtu, mtu);
 	test_check_mtu_run_xdp(skel, skel->progs.xdp_minus_delta, mtu);
+	test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len, mtu);
+	test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len_exceed, mtu);
 
 cleanup:
 	test_check_mtu__destroy(skel);
@@ -187,6 +189,8 @@ static void test_check_mtu_tc(__u32 mtu, __u32 ifindex)
 	test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu, mtu);
 	test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu_da, mtu);
 	test_check_mtu_run_tc(skel, skel->progs.tc_minus_delta, mtu);
+	test_check_mtu_run_tc(skel, skel->progs.tc_input_len, mtu);
+	test_check_mtu_run_tc(skel, skel->progs.tc_input_len_exceed, mtu);
 cleanup:
 	test_check_mtu__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c
index b7787b43f9db..c4a9bae96e75 100644
--- a/tools/testing/selftests/bpf/progs/test_check_mtu.c
+++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c
@@ -105,6 +105,54 @@ int xdp_minus_delta(struct xdp_md *ctx)
 	return retval;
 }
 
+SEC("xdp")
+int xdp_input_len(struct xdp_md *ctx)
+{
+	int retval = XDP_PASS; /* Expected retval on successful test */
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+	__u32 data_len = data_end - data;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input len is L3, like MTU and iph->tot_len.
+	 * Remember XDP data_len is L2.
+	 */
+	__u32 mtu_len = data_len - ETH_HLEN;
+
+	if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0))
+		retval = XDP_ABORTED;
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}
+
+SEC("xdp")
+int xdp_input_len_exceed(struct xdp_md *ctx)
+{
+	int retval = XDP_ABORTED; /* Fail */
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+	int err;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input length value is L3 size like MTU.
+	 */
+	__u32 mtu_len = GLOBAL_USER_MTU;
+
+	mtu_len += 1; /* Exceed with 1 */
+
+	err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0);
+	if (err == BPF_MTU_CHK_RET_FRAG_NEEDED)
+		retval = XDP_PASS ; /* Success in exceeding MTU check */
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}
+
 SEC("classifier")
 int tc_use_helper(struct __sk_buff *ctx)
 {
@@ -196,3 +244,47 @@ int tc_minus_delta(struct __sk_buff *ctx)
 	global_bpf_mtu_xdp = mtu_len;
 	return retval;
 }
+
+SEC("classifier")
+int tc_input_len(struct __sk_buff *ctx)
+{
+	int retval = BPF_OK; /* Expected retval on successful test */
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input length value is L3 size.
+	 */
+	__u32 mtu_len = GLOBAL_USER_MTU;
+
+	if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0))
+		retval = BPF_DROP;
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}
+
+SEC("classifier")
+int tc_input_len_exceed(struct __sk_buff *ctx)
+{
+	int retval = BPF_DROP; /* Fail */
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+	int err;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input length value is L3 size like MTU.
+	 */
+	__u32 mtu_len = GLOBAL_USER_MTU;
+
+	mtu_len += 1; /* Exceed with 1 */
+
+	err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0);
+	if (err == BPF_MTU_CHK_RET_FRAG_NEEDED)
+		retval = BPF_OK; /* Success in exceeding MTU check */
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}

From 27ab92d9996e4e003a726d22c56d780a1655d6b4 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Mon, 8 Mar 2021 10:00:04 +0100
Subject: [PATCH 0395/1820] mptcp: fix length of ADD_ADDR with port sub-option
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

in current Linux, MPTCP peers advertising endpoints with port numbers use
a sub-option length that wrongly accounts for the trailing TCP NOP. Also,
receivers will only process incoming ADD_ADDR with port having such wrong
sub-option length. Fix this, making ADD_ADDR compliant to RFC8684 §3.4.1.

this can be verified running tcpdump on the kselftests artifacts:

 unpatched kernel:
 [root@bottarga mptcp]# tcpdump -tnnr unpatched.pcap | grep add-addr
 reading from file unpatched.pcap, link-type LINUX_SLL (Linux cooked v1), snapshot length 65535
 IP 10.0.1.1.10000 > 10.0.1.2.53078: Flags [.], ack 101, win 509, options [nop,nop,TS val 214459678 ecr 521312851,mptcp add-addr v1 id 1 a00:201:2774:2d88:7436:85c3:17fd:101], length 0
 IP 10.0.1.2.53078 > 10.0.1.1.10000: Flags [.], ack 101, win 502, options [nop,nop,TS val 521312852 ecr 214459678,mptcp add-addr[bad opt]]

 patched kernel:
 [root@bottarga mptcp]# tcpdump -tnnr patched.pcap | grep add-addr
 reading from file patched.pcap, link-type LINUX_SLL (Linux cooked v1), snapshot length 65535
 IP 10.0.1.1.10000 > 10.0.1.2.38178: Flags [.], ack 101, win 509, options [nop,nop,TS val 3728873902 ecr 2732713192,mptcp add-addr v1 id 1 10.0.2.1:10100 hmac 0xbccdfcbe59292a1f,nop,nop], length 0
 IP 10.0.1.2.38178 > 10.0.1.1.10000: Flags [.], ack 101, win 502, options [nop,nop,TS val 2732713195 ecr 3728873902,mptcp add-addr v1-echo id 1 10.0.2.1:10100,nop,nop], length 0

Fixes: 22fb85ffaefb ("mptcp: add port support for ADD_ADDR suboption writing")
CC: stable@vger.kernel.org # 5.11+
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Acked-and-tested-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.h | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 91827d949766..e21a5bc36cf0 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -52,14 +52,15 @@
 #define TCPOLEN_MPTCP_DSS_MAP64		14
 #define TCPOLEN_MPTCP_DSS_CHECKSUM	2
 #define TCPOLEN_MPTCP_ADD_ADDR		16
-#define TCPOLEN_MPTCP_ADD_ADDR_PORT	20
+#define TCPOLEN_MPTCP_ADD_ADDR_PORT	18
 #define TCPOLEN_MPTCP_ADD_ADDR_BASE	8
-#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT	12
+#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT	10
 #define TCPOLEN_MPTCP_ADD_ADDR6		28
-#define TCPOLEN_MPTCP_ADD_ADDR6_PORT	32
+#define TCPOLEN_MPTCP_ADD_ADDR6_PORT	30
 #define TCPOLEN_MPTCP_ADD_ADDR6_BASE	20
-#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT	24
-#define TCPOLEN_MPTCP_PORT_LEN		4
+#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT	22
+#define TCPOLEN_MPTCP_PORT_LEN		2
+#define TCPOLEN_MPTCP_PORT_ALIGN	2
 #define TCPOLEN_MPTCP_RM_ADDR_BASE	4
 #define TCPOLEN_MPTCP_PRIO		3
 #define TCPOLEN_MPTCP_PRIO_ALIGN	4
@@ -701,8 +702,9 @@ static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port)
 		len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
 	if (!echo)
 		len += MPTCPOPT_THMAC_LEN;
+	/* account for 2 trailing 'nop' options */
 	if (port)
-		len += TCPOLEN_MPTCP_PORT_LEN;
+		len += TCPOLEN_MPTCP_PORT_LEN + TCPOLEN_MPTCP_PORT_ALIGN;
 
 	return len;
 }

From 179d0ba0c454057a65929c46af0d6ad986754781 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 8 Mar 2021 01:13:55 -0800
Subject: [PATCH 0396/1820] net: qrtr: fix error return code of qrtr_sendmsg()

When sock_alloc_send_skb() returns NULL to skb, no error return code of
qrtr_sendmsg() is assigned.
To fix this bug, rc is assigned with -ENOMEM in this case.

Fixes: 194ccc88297a ("net: qrtr: Support decoding incoming v2 packets")
Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 82d2eb8c21d1..edb6ac17ceca 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -958,8 +958,10 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	plen = (len + 3) & ~3;
 	skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_MAX_SIZE,
 				  msg->msg_flags & MSG_DONTWAIT, &rc);
-	if (!skb)
+	if (!skb) {
+		rc = -ENOMEM;
 		goto out_node;
+	}
 
 	skb_reserve(skb, QRTR_HDR_MAX_SIZE);
 

From 1019d7923d9d4cc878a1a85d4fc2d6619cfe1a6a Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Sun, 7 Mar 2021 22:25:28 -0500
Subject: [PATCH 0397/1820] atm: fix a typo in the struct description

phy_data means private PHY data not date

Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/atmdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 60cd25c0461b..9b02961d65ee 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -151,7 +151,7 @@ struct atm_dev {
 	const char	*type;		/* device type name */
 	int		number;		/* device index */
 	void		*dev_data;	/* per-device data */
-	void		*phy_data;	/* private PHY date */
+	void		*phy_data;	/* private PHY data */
 	unsigned long	flags;		/* device flags (ATM_DF_*) */
 	struct list_head local;		/* local ATM addresses */
 	struct list_head lecs;		/* LECS ATM addresses learned via ILMI */

From 3153724fc084d8ef640c611f269ddfb576d1dcb1 Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Sun, 7 Mar 2021 22:25:29 -0500
Subject: [PATCH 0398/1820] atm: uPD98402: fix incorrect allocation

dev->dev_data is set in zatm.c, calling zatm_start() will overwrite this
dev->dev_data in uPD98402_start() and a subsequent PRIV(dev)->lock
(i.e dev->phy_data->lock) will result in a null-ptr-dereference.

I believe this is a typo and what it actually want to do is to allocate
phy_data instead of dev_data.

Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/uPD98402.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/atm/uPD98402.c b/drivers/atm/uPD98402.c
index 7850758b5bb8..239852d85558 100644
--- a/drivers/atm/uPD98402.c
+++ b/drivers/atm/uPD98402.c
@@ -211,7 +211,7 @@ static void uPD98402_int(struct atm_dev *dev)
 static int uPD98402_start(struct atm_dev *dev)
 {
 	DPRINTK("phy_start\n");
-	if (!(dev->dev_data = kmalloc(sizeof(struct uPD98402_priv),GFP_KERNEL)))
+	if (!(dev->phy_data = kmalloc(sizeof(struct uPD98402_priv),GFP_KERNEL)))
 		return -ENOMEM;
 	spin_lock_init(&PRIV(dev)->lock);
 	memset(&PRIV(dev)->sonet_stats,0,sizeof(struct k_sonet_stats));

From 4416e98594dc04590ebc498fc4e530009535c511 Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Sun, 7 Mar 2021 22:25:30 -0500
Subject: [PATCH 0399/1820] atm: idt77252: fix null-ptr-dereference

this one is similar to the phy_data allocation fix in uPD98402, the
driver allocate the idt77105_priv and store to dev_data but later
dereference using dev->dev_data, which will cause null-ptr-dereference.

fix this issue by changing dev_data to phy_data so that PRIV(dev) can
work correctly.

Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/idt77105.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c
index 3c081b6171a8..bfca7b8a6f31 100644
--- a/drivers/atm/idt77105.c
+++ b/drivers/atm/idt77105.c
@@ -262,7 +262,7 @@ static int idt77105_start(struct atm_dev *dev)
 {
 	unsigned long flags;
 
-	if (!(dev->dev_data = kmalloc(sizeof(struct idt77105_priv),GFP_KERNEL)))
+	if (!(dev->phy_data = kmalloc(sizeof(struct idt77105_priv),GFP_KERNEL)))
 		return -ENOMEM;
 	PRIV(dev)->dev = dev;
 	spin_lock_irqsave(&idt77105_priv_lock, flags);
@@ -337,7 +337,7 @@ static int idt77105_stop(struct atm_dev *dev)
                 else
                     idt77105_all = walk->next;
 	        dev->phy = NULL;
-                dev->dev_data = NULL;
+                dev->phy_data = NULL;
                 kfree(walk);
                 break;
             }

From bf1bc694b6b0cf49756cb06f8f38501b9b2c5527 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Mon, 8 Mar 2021 12:00:47 -0300
Subject: [PATCH 0400/1820] cifs: print MIDs in decimal notation

The MIDs are mostly printed as decimal, so let's make it consistent.

Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cifs_debug.c | 2 +-
 fs/cifs/connect.c    | 4 ++--
 fs/cifs/smb2misc.c   | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 3aedc484e440..88a7958170ee 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -207,7 +207,7 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v)
 						from_kuid(&init_user_ns, cfile->uid),
 						cfile->dentry);
 #ifdef CONFIG_CIFS_DEBUG2
-					seq_printf(m, " 0x%llx\n", cfile->fid.mid);
+					seq_printf(m, " %llu\n", cfile->fid.mid);
 #else
 					seq_printf(m, "\n");
 #endif /* CIFS_DEBUG2 */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 68642e3d4270..eec8a2052da2 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -741,7 +741,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
 		spin_lock(&GlobalMid_Lock);
 		list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
 			mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-			cifs_dbg(FYI, "Clearing mid 0x%llx\n", mid_entry->mid);
+			cifs_dbg(FYI, "Clearing mid %llu\n", mid_entry->mid);
 			kref_get(&mid_entry->refcount);
 			mid_entry->mid_state = MID_SHUTDOWN;
 			list_move(&mid_entry->qhead, &dispose_list);
@@ -752,7 +752,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
 		/* now walk dispose list and issue callbacks */
 		list_for_each_safe(tmp, tmp2, &dispose_list) {
 			mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-			cifs_dbg(FYI, "Callback mid 0x%llx\n", mid_entry->mid);
+			cifs_dbg(FYI, "Callback mid %llu\n", mid_entry->mid);
 			list_del_init(&mid_entry->qhead);
 			mid_entry->callback(mid_entry);
 			cifs_mid_q_entry_release(mid_entry);
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 60d4bd1eae2b..6e0ea19e710b 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -767,7 +767,7 @@ smb2_cancelled_close_fid(struct work_struct *work)
 	int rc;
 
 	if (cancelled->mid)
-		cifs_tcon_dbg(VFS, "Close unmatched open for MID:%llx\n",
+		cifs_tcon_dbg(VFS, "Close unmatched open for MID:%llu\n",
 			      cancelled->mid);
 	else
 		cifs_tcon_dbg(VFS, "Close interrupted close\n");

From e3d100eae44b42f309c1366efb8397368f1cf8ed Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Mon, 8 Mar 2021 12:00:48 -0300
Subject: [PATCH 0401/1820] cifs: change noisy error message to FYI

A customer has reported that their dmesg were being flooded by

  CIFS: VFS: \\server Cancelling wait for mid xxx cmd: a
  CIFS: VFS: \\server Cancelling wait for mid yyy cmd: b
  CIFS: VFS: \\server Cancelling wait for mid zzz cmd: c

because some processes that were performing statfs(2) on the share had
been interrupted due to their automount setup when certain users
logged in and out.

Change it to FYI as they should be mostly informative rather than
error messages.

Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/transport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index e90a1d1380b0..15b72d2e8713 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -1207,7 +1207,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
 	}
 	if (rc != 0) {
 		for (; i < num_rqst; i++) {
-			cifs_server_dbg(VFS, "Cancelling wait for mid %llu cmd: %d\n",
+			cifs_server_dbg(FYI, "Cancelling wait for mid %llu cmd: %d\n",
 				 midQ[i]->mid, le16_to_cpu(midQ[i]->command));
 			send_cancel(server, &rqst[i], midQ[i]);
 			spin_lock(&GlobalMid_Lock);

From 14302ee3301b3a77b331cc14efb95bf7184c73cc Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Mon, 8 Mar 2021 12:00:49 -0300
Subject: [PATCH 0402/1820] cifs: return proper error code in statfs(2)

In cifs_statfs(), if server->ops->queryfs is not NULL, then we should
use its return value rather than always returning 0.  Instead, use rc
variable as it is properly set to 0 in case there is no
server->ops->queryfs.

Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
CC: <stable@vger.kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cifsfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index d43e935d2df4..099ad9f3660b 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -290,7 +290,7 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		rc = server->ops->queryfs(xid, tcon, cifs_sb, buf);
 
 	free_xid(xid);
-	return 0;
+	return rc;
 }
 
 static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len)

From 04ad69c342fc4de5bd23be9ef15ea7574fb1a87e Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Mon, 8 Mar 2021 12:00:50 -0300
Subject: [PATCH 0403/1820] cifs: do not send close in compound create+close
 requests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In case of interrupted syscalls, prevent sending CLOSE commands for
compound CREATE+CLOSE requests by introducing an
CIFS_CP_CREATE_CLOSE_OP flag to indicate lower layers that it should
not send a CLOSE command to the MIDs corresponding the compound
CREATE+CLOSE request.

A simple reproducer:

    #!/bin/bash

    mount //server/share /mnt -o username=foo,password=***
    tc qdisc add dev eth0 root netem delay 450ms
    stat -f /mnt &>/dev/null & pid=$!
    sleep 0.01
    kill $pid
    tc qdisc del dev eth0 root
    umount /mnt

Before patch:

    ...
    6 0.256893470 192.168.122.2 → 192.168.122.15 SMB2 402 Create Request File: ;GetInfo Request FS_INFO/FileFsFullSizeInformation;Close Request
    7 0.257144491 192.168.122.15 → 192.168.122.2 SMB2 498 Create Response File: ;GetInfo Response;Close Response
    9 0.260798209 192.168.122.2 → 192.168.122.15 SMB2 146 Close Request File:
   10 0.260841089 192.168.122.15 → 192.168.122.2 SMB2 130 Close Response, Error: STATUS_FILE_CLOSED

Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
CC: <stable@vger.kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cifsglob.h  | 19 ++++++++++---------
 fs/cifs/smb2inode.c |  1 +
 fs/cifs/smb2misc.c  |  8 ++++----
 fs/cifs/smb2ops.c   | 10 +++++-----
 fs/cifs/smb2proto.h |  3 +--
 fs/cifs/transport.c |  2 +-
 6 files changed, 22 insertions(+), 21 deletions(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 3de3c5908a72..31fc8695abd6 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -257,7 +257,7 @@ struct smb_version_operations {
 	/* verify the message */
 	int (*check_message)(char *, unsigned int, struct TCP_Server_Info *);
 	bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
-	int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *);
+	int (*handle_cancelled_mid)(struct mid_q_entry *, struct TCP_Server_Info *);
 	void (*downgrade_oplock)(struct TCP_Server_Info *server,
 				 struct cifsInodeInfo *cinode, __u32 oplock,
 				 unsigned int epoch, bool *purge_cache);
@@ -1705,16 +1705,17 @@ static inline bool is_retryable_error(int error)
 #define   CIFS_NO_RSP_BUF   0x040    /* no response buffer required */
 
 /* Type of request operation */
-#define   CIFS_ECHO_OP      0x080    /* echo request */
-#define   CIFS_OBREAK_OP   0x0100    /* oplock break request */
-#define   CIFS_NEG_OP      0x0200    /* negotiate request */
+#define   CIFS_ECHO_OP            0x080  /* echo request */
+#define   CIFS_OBREAK_OP          0x0100 /* oplock break request */
+#define   CIFS_NEG_OP             0x0200 /* negotiate request */
+#define   CIFS_CP_CREATE_CLOSE_OP 0x0400 /* compound create+close request */
 /* Lower bitmask values are reserved by others below. */
-#define   CIFS_SESS_OP     0x2000    /* session setup request */
-#define   CIFS_OP_MASK     0x2380    /* mask request type */
+#define   CIFS_SESS_OP            0x2000 /* session setup request */
+#define   CIFS_OP_MASK            0x2780 /* mask request type */
 
-#define   CIFS_HAS_CREDITS 0x0400    /* already has credits */
-#define   CIFS_TRANSFORM_REQ 0x0800    /* transform request before sending */
-#define   CIFS_NO_SRV_RSP    0x1000    /* there is no server response */
+#define   CIFS_HAS_CREDITS        0x0400 /* already has credits */
+#define   CIFS_TRANSFORM_REQ      0x0800 /* transform request before sending */
+#define   CIFS_NO_SRV_RSP         0x1000 /* there is no server response */
 
 /* Security Flags: indicate type of session setup needed */
 #define   CIFSSEC_MAY_SIGN	0x00001
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index 1f900b81c34a..a718dc77e604 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -358,6 +358,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	if (cfile)
 		goto after_close;
 	/* Close */
+	flags |= CIFS_CP_CREATE_CLOSE_OP;
 	rqst[num_rqst].rq_iov = &vars->close_iov[0];
 	rqst[num_rqst].rq_nvec = 1;
 	rc = SMB2_close_init(tcon, server,
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 6e0ea19e710b..b50164e2c88d 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -844,14 +844,14 @@ smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid,
 }
 
 int
-smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
+smb2_handle_cancelled_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server)
 {
-	struct smb2_sync_hdr *sync_hdr = (struct smb2_sync_hdr *)buffer;
-	struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
+	struct smb2_sync_hdr *sync_hdr = mid->resp_buf;
+	struct smb2_create_rsp *rsp = mid->resp_buf;
 	struct cifs_tcon *tcon;
 	int rc;
 
-	if (sync_hdr->Command != SMB2_CREATE ||
+	if ((mid->optype & CIFS_CP_CREATE_CLOSE_OP) || sync_hdr->Command != SMB2_CREATE ||
 	    sync_hdr->Status != STATUS_SUCCESS)
 		return 0;
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index f5087295424c..9bae7e8deb09 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1195,7 +1195,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 	struct TCP_Server_Info *server = cifs_pick_channel(ses);
 	__le16 *utf16_path = NULL;
 	int ea_name_len = strlen(ea_name);
-	int flags = 0;
+	int flags = CIFS_CP_CREATE_CLOSE_OP;
 	int len;
 	struct smb_rqst rqst[3];
 	int resp_buftype[3];
@@ -1573,7 +1573,7 @@ smb2_ioctl_query_info(const unsigned int xid,
 	struct smb_query_info qi;
 	struct smb_query_info __user *pqi;
 	int rc = 0;
-	int flags = 0;
+	int flags = CIFS_CP_CREATE_CLOSE_OP;
 	struct smb2_query_info_rsp *qi_rsp = NULL;
 	struct smb2_ioctl_rsp *io_rsp = NULL;
 	void *buffer = NULL;
@@ -2577,7 +2577,7 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	struct cifs_ses *ses = tcon->ses;
 	struct TCP_Server_Info *server = cifs_pick_channel(ses);
-	int flags = 0;
+	int flags = CIFS_CP_CREATE_CLOSE_OP;
 	struct smb_rqst rqst[3];
 	int resp_buftype[3];
 	struct kvec rsp_iov[3];
@@ -2975,7 +2975,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 	unsigned int sub_offset;
 	unsigned int print_len;
 	unsigned int print_offset;
-	int flags = 0;
+	int flags = CIFS_CP_CREATE_CLOSE_OP;
 	struct smb_rqst rqst[3];
 	int resp_buftype[3];
 	struct kvec rsp_iov[3];
@@ -3157,7 +3157,7 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_open_parms oparms;
 	struct cifs_fid fid;
 	struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses);
-	int flags = 0;
+	int flags = CIFS_CP_CREATE_CLOSE_OP;
 	struct smb_rqst rqst[3];
 	int resp_buftype[3];
 	struct kvec rsp_iov[3];
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 9565e27681a5..a2eb34a8d9c9 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -246,8 +246,7 @@ extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 extern int smb2_handle_cancelled_close(struct cifs_tcon *tcon,
 				       __u64 persistent_fid,
 				       __u64 volatile_fid);
-extern int smb2_handle_cancelled_mid(char *buffer,
-					struct TCP_Server_Info *server);
+extern int smb2_handle_cancelled_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server);
 void smb2_cancelled_close_fid(struct work_struct *work);
 extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_file_id, u64 volatile_file_id,
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 15b72d2e8713..007d99437c77 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -101,7 +101,7 @@ static void _cifs_mid_q_entry_release(struct kref *refcount)
 	if (midEntry->resp_buf && (midEntry->mid_flags & MID_WAIT_CANCELLED) &&
 	    midEntry->mid_state == MID_RESPONSE_RECEIVED &&
 	    server->ops->handle_cancelled_mid)
-		server->ops->handle_cancelled_mid(midEntry->resp_buf, server);
+		server->ops->handle_cancelled_mid(midEntry, server);
 
 	midEntry->mid_state = MID_FREE;
 	atomic_dec(&midCount);

From ab5eb336411f18fd449a1fb37d36a55ec422603f Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Thu, 25 Feb 2021 11:42:46 -0800
Subject: [PATCH 0404/1820] xtensa: move coprocessor_flush to the .text section

coprocessor_flush is not a part of fast exception handlers, but it uses
parts of fast coprocessor handling code that's why it's in the same
source file. It uses call0 opcode to invoke those parts so there are no
limitations on their relative location, but the rest of the code calls
coprocessor_flush with call8 and that doesn't work when vectors are
placed in a different gigabyte-aligned area than the rest of the kernel.

Move coprocessor_flush from the .exception.text section to the .text so
that it's reachable from the rest of the kernel with call8.

Cc: stable@vger.kernel.org
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/kernel/coprocessor.S | 64 ++++++++++++++++----------------
 1 file changed, 33 insertions(+), 31 deletions(-)

diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S
index c426b846beef..45cc0ae0af6f 100644
--- a/arch/xtensa/kernel/coprocessor.S
+++ b/arch/xtensa/kernel/coprocessor.S
@@ -99,37 +99,6 @@
 	LOAD_CP_REGS_TAB(6)
 	LOAD_CP_REGS_TAB(7)
 
-/*
- * coprocessor_flush(struct thread_info*, index)
- *                             a2        a3
- *
- * Save coprocessor registers for coprocessor 'index'.
- * The register values are saved to or loaded from the coprocessor area 
- * inside the task_info structure.
- *
- * Note that this function doesn't update the coprocessor_owner information!
- *
- */
-
-ENTRY(coprocessor_flush)
-
-	/* reserve 4 bytes on stack to save a0 */
-	abi_entry(4)
-
-	s32i	a0, a1, 0
-	movi	a0, .Lsave_cp_regs_jump_table
-	addx8	a3, a3, a0
-	l32i	a4, a3, 4
-	l32i	a3, a3, 0
-	add	a2, a2, a4
-	beqz	a3, 1f
-	callx0	a3
-1:	l32i	a0, a1, 0
-
-	abi_ret(4)
-
-ENDPROC(coprocessor_flush)
-
 /*
  * Entry condition:
  *
@@ -245,6 +214,39 @@ ENTRY(fast_coprocessor)
 
 ENDPROC(fast_coprocessor)
 
+	.text
+
+/*
+ * coprocessor_flush(struct thread_info*, index)
+ *                             a2        a3
+ *
+ * Save coprocessor registers for coprocessor 'index'.
+ * The register values are saved to or loaded from the coprocessor area
+ * inside the task_info structure.
+ *
+ * Note that this function doesn't update the coprocessor_owner information!
+ *
+ */
+
+ENTRY(coprocessor_flush)
+
+	/* reserve 4 bytes on stack to save a0 */
+	abi_entry(4)
+
+	s32i	a0, a1, 0
+	movi	a0, .Lsave_cp_regs_jump_table
+	addx8	a3, a3, a0
+	l32i	a4, a3, 4
+	l32i	a3, a3, 0
+	add	a2, a2, a4
+	beqz	a3, 1f
+	callx0	a3
+1:	l32i	a0, a1, 0
+
+	abi_ret(4)
+
+ENDPROC(coprocessor_flush)
+
 	.data
 
 ENTRY(coprocessor_owner)

From f15c5c11abfbf8909eb30598315ecbec2311cfdc Mon Sep 17 00:00:00 2001
From: Simeon Simeonoff <sim.simeonoff@gmail.com>
Date: Mon, 8 Mar 2021 20:48:35 +0200
Subject: [PATCH 0405/1820] ALSA: hda/ca0132: Add Sound BlasterX AE-5 Plus
 support

The new AE-5 Plus model has a different Subsystem ID compared to the
non-plus model. Adding the new id to the list of quirks.

Signed-off-by: Simeon Simeonoff <sim.simeonoff@gmail.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/998cafbe10b648f724ee33570553f2d780a38963.camel@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index c966f49fa942..b2b620f6c832 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -1309,6 +1309,7 @@ static const struct snd_pci_quirk ca0132_quirks[] = {
 	SND_PCI_QUIRK(0x1102, 0x0013, "Recon3D", QUIRK_R3D),
 	SND_PCI_QUIRK(0x1102, 0x0018, "Recon3D", QUIRK_R3D),
 	SND_PCI_QUIRK(0x1102, 0x0051, "Sound Blaster AE-5", QUIRK_AE5),
+	SND_PCI_QUIRK(0x1102, 0x0191, "Sound Blaster AE-5 Plus", QUIRK_AE5),
 	SND_PCI_QUIRK(0x1102, 0x0081, "Sound Blaster AE-7", QUIRK_AE7),
 	{}
 };

From 30dea07180de3aa0ad613af88431ef4e34b5ef68 Mon Sep 17 00:00:00 2001
From: Pavel Skripkin <paskripkin@gmail.com>
Date: Tue, 9 Mar 2021 01:30:36 +0300
Subject: [PATCH 0406/1820] ALSA: usb-audio: fix NULL ptr dereference in
 usb_audio_probe

syzbot reported null pointer dereference in usb_audio_probe.
The problem was in case, when quirk == NULL. It's not an
error condition, so quirk must be checked before dereferencing.

Call Trace:
 usb_probe_interface+0x315/0x7f0 drivers/usb/core/driver.c:396
 really_probe+0x291/0xe60 drivers/base/dd.c:554
 driver_probe_device+0x26b/0x3d0 drivers/base/dd.c:740
 __device_attach_driver+0x1d1/0x290 drivers/base/dd.c:846
 bus_for_each_drv+0x15f/0x1e0 drivers/base/bus.c:431
 __device_attach+0x228/0x4a0 drivers/base/dd.c:914
 bus_probe_device+0x1e4/0x290 drivers/base/bus.c:491
 device_add+0xbdb/0x1db0 drivers/base/core.c:3242
 usb_set_configuration+0x113f/0x1910 drivers/usb/core/message.c:2164
 usb_generic_driver_probe+0xba/0x100 drivers/usb/core/generic.c:238
 usb_probe_device+0xd9/0x2c0 drivers/usb/core/driver.c:293
 really_probe+0x291/0xe60 drivers/base/dd.c:554
 driver_probe_device+0x26b/0x3d0 drivers/base/dd.c:740
 __device_attach_driver+0x1d1/0x290 drivers/base/dd.c:846
 bus_for_each_drv+0x15f/0x1e0 drivers/base/bus.c:431
 __device_attach+0x228/0x4a0 drivers/base/dd.c:914
 bus_probe_device+0x1e4/0x290 drivers/base/bus.c:491
 device_add+0xbdb/0x1db0 drivers/base/core.c:3242
 usb_new_device.cold+0x721/0x1058 drivers/usb/core/hub.c:2555
 hub_port_connect drivers/usb/core/hub.c:5223 [inline]
 hub_port_connect_change drivers/usb/core/hub.c:5363 [inline]
 port_event drivers/usb/core/hub.c:5509 [inline]
 hub_event+0x2357/0x4320 drivers/usb/core/hub.c:5591
 process_one_work+0x98d/0x1600 kernel/workqueue.c:2275
 worker_thread+0x64c/0x1120 kernel/workqueue.c:2421
 kthread+0x3b1/0x4a0 kernel/kthread.c:292
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294

Reported-by: syzbot+719da9b149a931f5143f@syzkaller.appspotmail.com
Fixes: 9799110825db ("ALSA: usb-audio: Disable USB autosuspend properly in setup_disable_autosuspend()")
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/f1ebad6e721412843bd1b12584444c0a63c6b2fb.1615242183.git.paskripkin@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/card.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/usb/card.c b/sound/usb/card.c
index 08c794883299..3fd1743513b5 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -830,7 +830,8 @@ static int usb_audio_probe(struct usb_interface *intf,
 		snd_media_device_create(chip, intf);
 	}
 
-	chip->quirk_type = quirk->type;
+	if (quirk)
+		chip->quirk_type = quirk->type;
 
 	usb_chip[chip->index] = chip;
 	chip->intf[chip->num_interfaces] = intf;

From c5aa956eaeb05fe87e33433d7fd9f5e4d23c7416 Mon Sep 17 00:00:00 2001
From: Pavel Skripkin <paskripkin@gmail.com>
Date: Tue, 9 Mar 2021 01:30:57 +0300
Subject: [PATCH 0407/1820] ALSA: usb-audio: fix use after free in
 usb_audio_disconnect

The problem was in wrong "if" placement. chip->quirk_type is freed
in snd_card_free_when_closed(), but inside if statement it's accesed.

Fixes: 9799110825db ("ALSA: usb-audio: Disable USB autosuspend properly in setup_disable_autosuspend()")
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/16da19126ff461e5e64a9aec648cce28fb8ed73e.1615242183.git.paskripkin@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/card.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/usb/card.c b/sound/usb/card.c
index 3fd1743513b5..b6f4c0848e66 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -907,6 +907,9 @@ static void usb_audio_disconnect(struct usb_interface *intf)
 		}
 	}
 
+	if (chip->quirk_type & QUIRK_SETUP_DISABLE_AUTOSUSPEND)
+		usb_enable_autosuspend(interface_to_usbdev(intf));
+
 	chip->num_interfaces--;
 	if (chip->num_interfaces <= 0) {
 		usb_chip[chip->index] = NULL;
@@ -915,9 +918,6 @@ static void usb_audio_disconnect(struct usb_interface *intf)
 	} else {
 		mutex_unlock(&register_mutex);
 	}
-
-	if (chip->quirk_type & QUIRK_SETUP_DISABLE_AUTOSUSPEND)
-		usb_enable_autosuspend(interface_to_usbdev(intf));
 }
 
 /* lock the shutdown (disconnect) task and autoresume */

From ca667a33207daeaf9c62b106815728718def60ec Mon Sep 17 00:00:00 2001
From: Karan Singhal <karan.singhal@acuitybrands.com>
Date: Tue, 16 Feb 2021 11:03:10 -0500
Subject: [PATCH 0408/1820] USB: serial: cp210x: add ID for Acuity Brands
 nLight Air Adapter

IDs of nLight Air Adapter, Acuity Brands, Inc.:
vid: 10c4
pid: 88d8

Signed-off-by: Karan Singhal <karan.singhal@acuitybrands.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/cp210x.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 9e1c609792fb..afbc4f4ea21f 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -145,6 +145,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x8857) },	/* CEL EM357 ZigBee USB Stick */
 	{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
 	{ USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
+	{ USB_DEVICE(0x10C4, 0x88D8) }, /* Acuity Brands nLight Air Adapter */
 	{ USB_DEVICE(0x10C4, 0x88FB) }, /* CESINEL MEDCAL STII Network Analyzer */
 	{ USB_DEVICE(0x10C4, 0x8938) }, /* CESINEL MEDCAL S II Network Analyzer */
 	{ USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */

From 42213a0190b535093a604945db05a4225bf43885 Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sebastian.reichel@collabora.com>
Date: Tue, 23 Feb 2021 17:44:18 +0100
Subject: [PATCH 0409/1820] USB: serial: cp210x: add some more GE USB IDs

GE CS1000 has some more custom USB IDs for CP2102N; add them
to the driver to have working auto-probing.

Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/cp210x.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index afbc4f4ea21f..a373cd63b3a4 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -202,6 +202,8 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x1901, 0x0194) },	/* GE Healthcare Remote Alarm Box */
 	{ USB_DEVICE(0x1901, 0x0195) },	/* GE B850/B650/B450 CP2104 DP UART interface */
 	{ USB_DEVICE(0x1901, 0x0196) },	/* GE B850 CP2105 DP UART interface */
+	{ USB_DEVICE(0x1901, 0x0197) }, /* GE CS1000 Display serial interface */
+	{ USB_DEVICE(0x1901, 0x0198) }, /* GE CS1000 M.2 Key E serial interface */
 	{ USB_DEVICE(0x199B, 0xBA30) }, /* LORD WSDA-200-USB */
 	{ USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */
 	{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */

From f164f5d8a70245217bee89b246dc4fcfececa526 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Fri, 26 Feb 2021 11:08:26 +0100
Subject: [PATCH 0410/1820] USB: serial: xr: fix NULL-deref on disconnect

Claiming the sibling control interface is a bit more involved and
specifically requires adding support to USB-serial core for managing
either interface being unbound first, something which could otherwise
lead to a NULL-pointer dereference.

Similarly, additional infrastructure is also needed to handle suspend
properly.

Since the driver currently isn't actually using the control interface,
we can defer this for now by simply not claiming the control interface.

Fixes: c2d405aa86b4 ("USB: serial: add MaxLinear/Exar USB to Serial driver")
Reported-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Tested-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/xr_serial.c | 25 -------------------------
 1 file changed, 25 deletions(-)

diff --git a/drivers/usb/serial/xr_serial.c b/drivers/usb/serial/xr_serial.c
index 483d07dee19d..0ca04906da4b 100644
--- a/drivers/usb/serial/xr_serial.c
+++ b/drivers/usb/serial/xr_serial.c
@@ -545,37 +545,13 @@ static void xr_close(struct usb_serial_port *port)
 
 static int xr_probe(struct usb_serial *serial, const struct usb_device_id *id)
 {
-	struct usb_driver *driver = serial->type->usb_driver;
-	struct usb_interface *control_interface;
-	int ret;
-
 	/* Don't bind to control interface */
 	if (serial->interface->cur_altsetting->desc.bInterfaceNumber == 0)
 		return -ENODEV;
 
-	/* But claim the control interface during data interface probe */
-	control_interface = usb_ifnum_to_if(serial->dev, 0);
-	if (!control_interface)
-		return -ENODEV;
-
-	ret = usb_driver_claim_interface(driver, control_interface, NULL);
-	if (ret) {
-		dev_err(&serial->interface->dev, "Failed to claim control interface\n");
-		return ret;
-	}
-
 	return 0;
 }
 
-static void xr_disconnect(struct usb_serial *serial)
-{
-	struct usb_driver *driver = serial->type->usb_driver;
-	struct usb_interface *control_interface;
-
-	control_interface = usb_ifnum_to_if(serial->dev, 0);
-	usb_driver_release_interface(driver, control_interface);
-}
-
 static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x04e2, 0x1410) }, /* XR21V141X */
 	{ }
@@ -590,7 +566,6 @@ static struct usb_serial_driver xr_device = {
 	.id_table		= id_table,
 	.num_ports		= 1,
 	.probe			= xr_probe,
-	.disconnect		= xr_disconnect,
 	.open			= xr_open,
 	.close			= xr_close,
 	.break_ctl		= xr_break_ctl,

From 5563b3b6420362c8a1f468ca04afe6d5f0a8d0a3 Mon Sep 17 00:00:00 2001
From: Niv Sardi <xaiki@evilgiggle.com>
Date: Mon, 1 Mar 2021 17:16:12 -0300
Subject: [PATCH 0411/1820] USB: serial: ch341: add new Product ID

Add PID for CH340 that's found on cheap programmers.

The driver works flawlessly as soon as the new PID (0x9986) is added to it.
These look like ANU232MI but ship with a ch341 inside. They have no special
identifiers (mine only has the string "DB9D20130716" printed on the PCB and
nothing identifiable on the packaging. The merchant i bought it from
doesn't sell these anymore).

the lsusb -v output is:
Bus 001 Device 009: ID 9986:7523
Device Descriptor:
  bLength                18
  bDescriptorType         1
  bcdUSB               1.10
  bDeviceClass          255 Vendor Specific Class
  bDeviceSubClass         0
  bDeviceProtocol         0
  bMaxPacketSize0         8
  idVendor           0x9986
  idProduct          0x7523
  bcdDevice            2.54
  iManufacturer           0
  iProduct                0
  iSerial                 0
  bNumConfigurations      1
  Configuration Descriptor:
    bLength                 9
    bDescriptorType         2
    wTotalLength       0x0027
    bNumInterfaces          1
    bConfigurationValue     1
    iConfiguration          0
    bmAttributes         0x80
      (Bus Powered)
    MaxPower               96mA
    Interface Descriptor:
      bLength                 9
      bDescriptorType         4
      bInterfaceNumber        0
      bAlternateSetting       0
      bNumEndpoints           3
      bInterfaceClass       255 Vendor Specific Class
      bInterfaceSubClass      1
      bInterfaceProtocol      2
      iInterface              0
      Endpoint Descriptor:
        bLength                 7
        bDescriptorType         5
        bEndpointAddress     0x82  EP 2 IN
        bmAttributes            2
          Transfer Type            Bulk
          Synch Type               None
          Usage Type               Data
        wMaxPacketSize     0x0020  1x 32 bytes
        bInterval               0
      Endpoint Descriptor:
        bLength                 7
        bDescriptorType         5
        bEndpointAddress     0x02  EP 2 OUT
        bmAttributes            2
          Transfer Type            Bulk
          Synch Type               None
          Usage Type               Data
        wMaxPacketSize     0x0020  1x 32 bytes
        bInterval               0
      Endpoint Descriptor:
        bLength                 7
        bDescriptorType         5
        bEndpointAddress     0x81  EP 1 IN
        bmAttributes            3
          Transfer Type            Interrupt
          Synch Type               None
          Usage Type               Data
        wMaxPacketSize     0x0008  1x 8 bytes
        bInterval               1

Signed-off-by: Niv Sardi <xaiki@evilgiggle.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/ch341.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index 8d997b71056f..2db917eab799 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -86,6 +86,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x1a86, 0x7522) },
 	{ USB_DEVICE(0x1a86, 0x7523) },
 	{ USB_DEVICE(0x4348, 0x5523) },
+	{ USB_DEVICE(0x9986, 0x7523) },
 	{ },
 };
 MODULE_DEVICE_TABLE(usb, id_table);

From cfdc67acc785e01a8719eeb7012709d245564701 Mon Sep 17 00:00:00 2001
From: Pavel Skripkin <paskripkin@gmail.com>
Date: Tue, 2 Mar 2021 02:01:52 +0300
Subject: [PATCH 0412/1820] USB: serial: io_edgeport: fix memory leak in
 edge_startup

sysbot found memory leak in edge_startup().
The problem was that when an error was received from the usb_submit_urb(),
nothing was cleaned up.

Reported-by: syzbot+59f777bdcbdd7eea5305@syzkaller.appspotmail.com
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Fixes: 6e8cf7751f9f ("USB: add EPIC support to the io_edgeport driver")
Cc: stable@vger.kernel.org	# 2.6.21: c5c0c55598ce
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/io_edgeport.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c
index a493670c06e6..68401adcffde 100644
--- a/drivers/usb/serial/io_edgeport.c
+++ b/drivers/usb/serial/io_edgeport.c
@@ -3003,26 +3003,32 @@ static int edge_startup(struct usb_serial *serial)
 				response = -ENODEV;
 			}
 
-			usb_free_urb(edge_serial->interrupt_read_urb);
-			kfree(edge_serial->interrupt_in_buffer);
-
-			usb_free_urb(edge_serial->read_urb);
-			kfree(edge_serial->bulk_in_buffer);
-
-			kfree(edge_serial);
-
-			return response;
+			goto error;
 		}
 
 		/* start interrupt read for this edgeport this interrupt will
 		 * continue as long as the edgeport is connected */
 		response = usb_submit_urb(edge_serial->interrupt_read_urb,
 								GFP_KERNEL);
-		if (response)
+		if (response) {
 			dev_err(ddev, "%s - Error %d submitting control urb\n",
 				__func__, response);
+
+			goto error;
+		}
 	}
 	return response;
+
+error:
+	usb_free_urb(edge_serial->interrupt_read_urb);
+	kfree(edge_serial->interrupt_in_buffer);
+
+	usb_free_urb(edge_serial->read_urb);
+	kfree(edge_serial->bulk_in_buffer);
+
+	kfree(edge_serial);
+
+	return response;
 }
 
 

From 673433e7c288927f7244658788f203c660d7a6f6 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Sun, 7 Mar 2021 17:20:13 +0000
Subject: [PATCH 0413/1820] dt-bindings/irq: Add compatible string for the
 JZ4760B

Add the ingenic,jz4760b-intc compatible string with a fallback to the
ingenic,jz4760-intc compatible string.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210307172014.73481-1-paul@crapouillou.net
---
 .../devicetree/bindings/interrupt-controller/ingenic,intc.yaml   | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.yaml b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.yaml
index 0a046be8d1cd..0358a7739c8e 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.yaml
@@ -23,6 +23,7 @@ properties:
           - enum:
               - ingenic,jz4775-intc
               - ingenic,jz4770-intc
+              - ingenic,jz4760b-intc
           - const: ingenic,jz4760-intc
       - items:
           - const: ingenic,x1000-intc

From 5fbecd2389f48e1415799c63130d0cdce1cf3f60 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Sun, 7 Mar 2021 17:20:14 +0000
Subject: [PATCH 0414/1820] irqchip/ingenic: Add support for the JZ4760

Add support for the interrupt controller found in the JZ4760 SoC, which
works exactly like the one in the JZ4770.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210307172014.73481-2-paul@crapouillou.net
---
 drivers/irqchip/irq-ingenic-tcu.c | 1 +
 drivers/irqchip/irq-ingenic.c     | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/irqchip/irq-ingenic-tcu.c b/drivers/irqchip/irq-ingenic-tcu.c
index 7a7222d4c19c..b938d1d04d96 100644
--- a/drivers/irqchip/irq-ingenic-tcu.c
+++ b/drivers/irqchip/irq-ingenic-tcu.c
@@ -179,5 +179,6 @@ err_free_tcu:
 }
 IRQCHIP_DECLARE(jz4740_tcu_irq, "ingenic,jz4740-tcu", ingenic_tcu_irq_init);
 IRQCHIP_DECLARE(jz4725b_tcu_irq, "ingenic,jz4725b-tcu", ingenic_tcu_irq_init);
+IRQCHIP_DECLARE(jz4760_tcu_irq, "ingenic,jz4760-tcu", ingenic_tcu_irq_init);
 IRQCHIP_DECLARE(jz4770_tcu_irq, "ingenic,jz4770-tcu", ingenic_tcu_irq_init);
 IRQCHIP_DECLARE(x1000_tcu_irq, "ingenic,x1000-tcu", ingenic_tcu_irq_init);
diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c
index b61a8901ef72..ea36bb00be80 100644
--- a/drivers/irqchip/irq-ingenic.c
+++ b/drivers/irqchip/irq-ingenic.c
@@ -155,6 +155,7 @@ static int __init intc_2chip_of_init(struct device_node *node,
 {
 	return ingenic_intc_of_init(node, 2);
 }
+IRQCHIP_DECLARE(jz4760_intc, "ingenic,jz4760-intc", intc_2chip_of_init);
 IRQCHIP_DECLARE(jz4770_intc, "ingenic,jz4770-intc", intc_2chip_of_init);
 IRQCHIP_DECLARE(jz4775_intc, "ingenic,jz4775-intc", intc_2chip_of_init);
 IRQCHIP_DECLARE(jz4780_intc, "ingenic,jz4780-intc", intc_2chip_of_init);

From dbaee836d60a8e1b03e7d53a37893235662ba124 Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Fri, 5 Mar 2021 12:21:24 -0800
Subject: [PATCH 0415/1820] KVM: arm64: Don't use cbz/adr with external symbols

allmodconfig + CONFIG_LTO_CLANG_THIN=y fails to build due to following
linker errors:

  ld.lld: error: irqbypass.c:(function __guest_enter: .text+0x21CC):
  relocation R_AARCH64_CONDBR19 out of range: 2031220 is not in
  [-1048576, 1048575]; references hyp_panic
  >>> defined in vmlinux.o

  ld.lld: error: irqbypass.c:(function __guest_enter: .text+0x21E0):
  relocation R_AARCH64_ADR_PREL_LO21 out of range: 2031200 is not in
  [-1048576, 1048575]; references hyp_panic
  >>> defined in vmlinux.o

This is because with LTO, the compiler ends up placing hyp_panic()
more than 1MB away from __guest_enter(). Use an unconditional branch
and adr_l instead to fix the issue.

Link: https://github.com/ClangBuiltLinux/linux/issues/1317
Reported-by: Nathan Chancellor <nathan@kernel.org>
Suggested-by: Marc Zyngier <maz@kernel.org>
Suggested-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Will Deacon <will@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210305202124.3768527-1-samitolvanen@google.com
---
 arch/arm64/kvm/hyp/entry.S | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index 0c66a1d408fd..e831d3dfd50d 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -85,8 +85,10 @@ SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL)
 
 	// If the hyp context is loaded, go straight to hyp_panic
 	get_loaded_vcpu x0, x1
-	cbz	x0, hyp_panic
+	cbnz	x0, 1f
+	b	hyp_panic
 
+1:
 	// The hyp context is saved so make sure it is restored to allow
 	// hyp_panic to run at hyp and, subsequently, panic to run in the host.
 	// This makes use of __guest_exit to avoid duplication but sets the
@@ -94,7 +96,7 @@ SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL)
 	// current state is saved to the guest context but it will only be
 	// accurate if the guest had been completely restored.
 	adr_this_cpu x0, kvm_hyp_ctxt, x1
-	adr	x1, hyp_panic
+	adr_l	x1, hyp_panic
 	str	x1, [x0, #CPU_XREG_OFFSET(30)]
 
 	get_vcpu_ptr	x1, x0

From 774514bf977377c9137640a0310bd64eed0f7323 Mon Sep 17 00:00:00 2001
From: Yann Gautier <yann.gautier@foss.st.com>
Date: Thu, 25 Feb 2021 15:54:54 +0100
Subject: [PATCH 0416/1820] mmc: mmci: Add MMC_CAP_NEED_RSP_BUSY for the stm32
 variants

An issue has been observed on STM32MP157C-EV1 board, with an erase command
with secure erase argument, ending up waiting for ~4 hours before timeout.

The requested busy timeout from the mmc core ends up with 14784000ms (~4
hours), but the supported host->max_busy_timeout is 86767ms, which leads to
that the core switch to use an R1 response in favor of the R1B and polls
for busy with the host->card_busy() ops. In this case the polling doesn't
work as expected, as we never detects that the card stops signaling busy,
which leads to the following message:

 mmc1: Card stuck being busy! __mmc_poll_for_busy

The problem boils done to that the stm32 variants can't use R1 responses in
favor of R1B responses, as it leads to an internal state machine in the
controller to get stuck. To continue to process requests, it would need to
be reset.

To fix this problem, let's set MMC_CAP_NEED_RSP_BUSY for the stm32 variant,
which prevent the mmc core from switching to R1 responses. Additionally,
let's cap the cmd->busy_timeout to the host->max_busy_timeout, thus rely on
86767ms to be sufficient (~66 seconds was need for this test case).

Fixes: 94fe2580a2f3 ("mmc: core: Enable erase/discard/trim support for all mmc hosts")
Signed-off-by: Yann Gautier <yann.gautier@foss.st.com>
Link: https://lore.kernel.org/r/20210225145454.12780-1-yann.gautier@foss.st.com
Cc: stable@vger.kernel.org
[Ulf: Simplified the code and extended the commit message]
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/mmci.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 17dbc81c221e..984d35055156 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -1242,7 +1242,11 @@ mmci_start_command(struct mmci_host *host, struct mmc_command *cmd, u32 c)
 		if (!cmd->busy_timeout)
 			cmd->busy_timeout = 10 * MSEC_PER_SEC;
 
-		clks = (unsigned long long)cmd->busy_timeout * host->cclk;
+		if (cmd->busy_timeout > host->mmc->max_busy_timeout)
+			clks = (unsigned long long)host->mmc->max_busy_timeout * host->cclk;
+		else
+			clks = (unsigned long long)cmd->busy_timeout * host->cclk;
+
 		do_div(clks, MSEC_PER_SEC);
 		writel_relaxed(clks, host->base + MMCIDATATIMER);
 	}
@@ -2151,6 +2155,10 @@ static int mmci_probe(struct amba_device *dev,
 		mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
 	}
 
+	/* Variants with mandatory busy timeout in HW needs R1B responses. */
+	if (variant->busy_timeout)
+		mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
+
 	/* Prepare a CMD12 - needed to clear the DPSM on some variants. */
 	host->stop_abort.opcode = MMC_STOP_TRANSMISSION;
 	host->stop_abort.arg = 0;

From 66fbacccbab91e6e55d9c8f1fc0910a8eb6c81f7 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 3 Mar 2021 11:26:14 +0200
Subject: [PATCH 0417/1820] mmc: core: Fix partition switch time for eMMC

Avoid the following warning by always defining partition switch time:

 [    3.209874] mmc1: unspecified timeout for CMD6 - use generic
 [    3.222780] ------------[ cut here ]------------
 [    3.233363] WARNING: CPU: 1 PID: 111 at drivers/mmc/core/mmc_ops.c:575 __mmc_switch+0x200/0x204

Reported-by: Paul Fertser <fercerpav@gmail.com>
Fixes: 1c447116d017 ("mmc: mmc: Fix partition switch timeout for some eMMCs")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/168bbfd6-0c5b-5ace-ab41-402e7937c46e@intel.com
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/mmc.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 0d80b72ddde8..8741271d3971 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -423,10 +423,6 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 
 		/* EXT_CSD value is in units of 10ms, but we store in ms */
 		card->ext_csd.part_time = 10 * ext_csd[EXT_CSD_PART_SWITCH_TIME];
-		/* Some eMMC set the value too low so set a minimum */
-		if (card->ext_csd.part_time &&
-		    card->ext_csd.part_time < MMC_MIN_PART_SWITCH_TIME)
-			card->ext_csd.part_time = MMC_MIN_PART_SWITCH_TIME;
 
 		/* Sleep / awake timeout in 100ns units */
 		if (sa_shift > 0 && sa_shift <= 0x17)
@@ -616,6 +612,17 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		card->ext_csd.data_sector_size = 512;
 	}
 
+	/*
+	 * GENERIC_CMD6_TIME is to be used "unless a specific timeout is defined
+	 * when accessing a specific field", so use it here if there is no
+	 * PARTITION_SWITCH_TIME.
+	 */
+	if (!card->ext_csd.part_time)
+		card->ext_csd.part_time = card->ext_csd.generic_cmd6_time;
+	/* Some eMMC set the value too low so set a minimum */
+	if (card->ext_csd.part_time < MMC_MIN_PART_SWITCH_TIME)
+		card->ext_csd.part_time = MMC_MIN_PART_SWITCH_TIME;
+
 	/* eMMC v5 or later */
 	if (card->ext_csd.rev >= 7) {
 		memcpy(card->ext_csd.fwrev, &ext_csd[EXT_CSD_FIRMWARE_VERSION],

From f06391c45e83f9a731045deb23df7cc3814fd795 Mon Sep 17 00:00:00 2001
From: Frank Li <lznuaa@gmail.com>
Date: Wed, 3 Mar 2021 11:42:48 -0600
Subject: [PATCH 0418/1820] mmc: cqhci: Fix random crash when remove mmc
 module/card

[ 6684.493350] Unable to handle kernel paging request at virtual address ffff800011c5b0f0
[ 6684.498531] mmc0: card 0001 removed
[ 6684.501556] Mem abort info:
[ 6684.509681]   ESR = 0x96000047
[ 6684.512786]   EC = 0x25: DABT (current EL), IL = 32 bits
[ 6684.518394]   SET = 0, FnV = 0
[ 6684.521707]   EA = 0, S1PTW = 0
[ 6684.524998] Data abort info:
[ 6684.528236]   ISV = 0, ISS = 0x00000047
[ 6684.532986]   CM = 0, WnR = 1
[ 6684.536129] swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000081b22000
[ 6684.543923] [ffff800011c5b0f0] pgd=00000000bffff003, p4d=00000000bffff003, pud=00000000bfffe003, pmd=00000000900e1003, pte=0000000000000000
[ 6684.557915] Internal error: Oops: 96000047 [#1] PREEMPT SMP
[ 6684.564240] Modules linked in: sdhci_esdhc_imx(-) sdhci_pltfm sdhci cqhci mmc_block mmc_core fsl_jr_uio caam_jr caamkeyblob_desc caamhash_desc caamalg_desc crypto_engine rng_core authenc libdes crct10dif_ce flexcan can_dev caam error [last unloaded: mmc_core]
[ 6684.587281] CPU: 0 PID: 79138 Comm: kworker/0:3H Not tainted 5.10.9-01410-g3ba33182767b-dirty #10
[ 6684.596160] Hardware name: Freescale i.MX8DXL EVK (DT)
[ 6684.601320] Workqueue: kblockd blk_mq_run_work_fn

[ 6684.606094] pstate: 40000005 (nZcv daif -PAN -UAO -TCO BTYPE=--)
[ 6684.612286] pc : cqhci_request+0x148/0x4e8 [cqhci]
^GMessage from syslogd@  at Thu Jan  1 01:51:24 1970 ...[ 6684.617085] lr : cqhci_request+0x314/0x4e8 [cqhci]
[ 6684.626734] sp : ffff80001243b9f0
[ 6684.630049] x29: ffff80001243b9f0 x28: ffff00002c3dd000
[ 6684.635367] x27: 0000000000000001 x26: 0000000000000001
[ 6684.640690] x25: ffff00002c451000 x24: 000000000000000f
[ 6684.646007] x23: ffff000017e71c80 x22: ffff00002c451000
[ 6684.651326] x21: ffff00002c0f3550 x20: ffff00002c0f3550
[ 6684.656651] x19: ffff000017d46880 x18: ffff00002cea1500
[ 6684.661977] x17: 0000000000000000 x16: 0000000000000000
[ 6684.667294] x15: 000001ee628e3ed1 x14: 0000000000000278
[ 6684.672610] x13: 0000000000000001 x12: 0000000000000001
[ 6684.677927] x11: 0000000000000000 x10: 0000000000000000
[ 6684.683243] x9 : 000000000000002b x8 : 0000000000001000
[ 6684.688560] x7 : 0000000000000010 x6 : ffff00002c0f3678
[ 6684.693886] x5 : 000000000000000f x4 : ffff800011c5b000
[ 6684.699211] x3 : 000000000002d988 x2 : 0000000000000008
[ 6684.704537] x1 : 00000000000000f0 x0 : 0002d9880008102f
[ 6684.709854] Call trace:
[ 6684.712313]  cqhci_request+0x148/0x4e8 [cqhci]
[ 6684.716803]  mmc_cqe_start_req+0x58/0x68 [mmc_core]
[ 6684.721698]  mmc_blk_mq_issue_rq+0x460/0x810 [mmc_block]
[ 6684.727018]  mmc_mq_queue_rq+0x118/0x2b0 [mmc_block]

The problem occurs when cqhci_request() get called after cqhci_disable() as
it leads to access of allocated memory that has already been freed. Let's
fix the problem by calling cqhci_disable() a bit later in the remove path.

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Diagnosed-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/20210303174248.542175-1-Frank.Li@nxp.com
Fixes: f690f4409ddd ("mmc: mmc: Enable CQE's")
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/bus.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index c2e70b757dd1..4383c262b3f5 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -399,11 +399,6 @@ void mmc_remove_card(struct mmc_card *card)
 	mmc_remove_card_debugfs(card);
 #endif
 
-	if (host->cqe_enabled) {
-		host->cqe_ops->cqe_disable(host);
-		host->cqe_enabled = false;
-	}
-
 	if (mmc_card_present(card)) {
 		if (mmc_host_is_spi(card->host)) {
 			pr_info("%s: SPI card removed\n",
@@ -416,6 +411,10 @@ void mmc_remove_card(struct mmc_card *card)
 		of_node_put(card->dev.of_node);
 	}
 
+	if (host->cqe_enabled) {
+		host->cqe_ops->cqe_disable(host);
+		host->cqe_enabled = false;
+	}
+
 	put_device(&card->dev);
 }
-

From bd67b711bfaa02cf19e88aa2d9edae5c1c1d2739 Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Date: Mon, 8 Mar 2021 10:24:47 +0100
Subject: [PATCH 0419/1820] MIPS: kernel: Reserve exception base early to
 prevent corruption

BMIPS is one of the few platforms that do change the exception base.
After commit 2dcb39645441 ("memblock: do not start bottom-up allocations
with kernel_end") we started seeing BMIPS boards fail to boot with the
built-in FDT being corrupted.

Before the cited commit, early allocations would be in the [kernel_end,
RAM_END] range, but after commit they would be within [RAM_START +
PAGE_SIZE, RAM_END].

The custom exception base handler that is installed by
bmips_ebase_setup() done for BMIPS5000 CPUs ends-up trampling on the
memory region allocated by unflatten_and_copy_device_tree() thus
corrupting the FDT used by the kernel.

To fix this, we need to perform an early reservation of the custom
exception space. Additional we reserve the first 4k (1k for R3k) for
either normal exception vector space (legacy CPUs) or special vectors
like cache exceptions.

Huge thanks to Serge for analysing and proposing a solution to this
issue.

Fixes: 2dcb39645441 ("memblock: do not start bottom-up allocations with kernel_end")
Reported-by: Kamal Dasu <kdasu.kdev@gmail.com>
Debugged-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Tested-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/include/asm/traps.h    |  3 +++
 arch/mips/kernel/cpu-probe.c     |  6 ++++++
 arch/mips/kernel/cpu-r3k-probe.c |  3 +++
 arch/mips/kernel/traps.c         | 10 +++++-----
 4 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/arch/mips/include/asm/traps.h b/arch/mips/include/asm/traps.h
index 6aa8f126a43d..b710e76c9c65 100644
--- a/arch/mips/include/asm/traps.h
+++ b/arch/mips/include/asm/traps.h
@@ -24,8 +24,11 @@ extern void (*board_ebase_setup)(void);
 extern void (*board_cache_error_setup)(void);
 
 extern int register_nmi_notifier(struct notifier_block *nb);
+extern void reserve_exception_space(phys_addr_t addr, unsigned long size);
 extern char except_vec_nmi[];
 
+#define VECTORSPACING 0x100	/* for EI/VI mode */
+
 #define nmi_notifier(fn, pri)						\
 ({									\
 	static struct notifier_block fn##_nb = {			\
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 9a89637b4ecf..b71892064f27 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -26,6 +26,7 @@
 #include <asm/elf.h>
 #include <asm/pgtable-bits.h>
 #include <asm/spram.h>
+#include <asm/traps.h>
 #include <linux/uaccess.h>
 
 #include "fpu-probe.h"
@@ -1628,6 +1629,7 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 		c->cputype = CPU_BMIPS3300;
 		__cpu_name[cpu] = "Broadcom BMIPS3300";
 		set_elf_platform(cpu, "bmips3300");
+		reserve_exception_space(0x400, VECTORSPACING * 64);
 		break;
 	case PRID_IMP_BMIPS43XX: {
 		int rev = c->processor_id & PRID_REV_MASK;
@@ -1638,6 +1640,7 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 			__cpu_name[cpu] = "Broadcom BMIPS4380";
 			set_elf_platform(cpu, "bmips4380");
 			c->options |= MIPS_CPU_RIXI;
+			reserve_exception_space(0x400, VECTORSPACING * 64);
 		} else {
 			c->cputype = CPU_BMIPS4350;
 			__cpu_name[cpu] = "Broadcom BMIPS4350";
@@ -1654,6 +1657,7 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 			__cpu_name[cpu] = "Broadcom BMIPS5000";
 		set_elf_platform(cpu, "bmips5000");
 		c->options |= MIPS_CPU_ULRI | MIPS_CPU_RIXI;
+		reserve_exception_space(0x1000, VECTORSPACING * 64);
 		break;
 	}
 }
@@ -2133,6 +2137,8 @@ void cpu_probe(void)
 	if (cpu == 0)
 		__ua_limit = ~((1ull << cpu_vmbits) - 1);
 #endif
+
+	reserve_exception_space(0, 0x1000);
 }
 
 void cpu_report(void)
diff --git a/arch/mips/kernel/cpu-r3k-probe.c b/arch/mips/kernel/cpu-r3k-probe.c
index abdbbe8c5a43..af654771918c 100644
--- a/arch/mips/kernel/cpu-r3k-probe.c
+++ b/arch/mips/kernel/cpu-r3k-probe.c
@@ -21,6 +21,7 @@
 #include <asm/fpu.h>
 #include <asm/mipsregs.h>
 #include <asm/elf.h>
+#include <asm/traps.h>
 
 #include "fpu-probe.h"
 
@@ -158,6 +159,8 @@ void cpu_probe(void)
 		cpu_set_fpu_opts(c);
 	else
 		cpu_set_nofpu_opts(c);
+
+	reserve_exception_space(0, 0x400);
 }
 
 void cpu_report(void)
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index e0352958e2f7..808b8b61ded1 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2009,13 +2009,16 @@ void __noreturn nmi_exception_handler(struct pt_regs *regs)
 	nmi_exit();
 }
 
-#define VECTORSPACING 0x100	/* for EI/VI mode */
-
 unsigned long ebase;
 EXPORT_SYMBOL_GPL(ebase);
 unsigned long exception_handlers[32];
 unsigned long vi_handlers[64];
 
+void reserve_exception_space(phys_addr_t addr, unsigned long size)
+{
+	memblock_reserve(addr, size);
+}
+
 void __init *set_except_vector(int n, void *addr)
 {
 	unsigned long handler = (unsigned long) addr;
@@ -2367,10 +2370,7 @@ void __init trap_init(void)
 
 	if (!cpu_has_mips_r2_r6) {
 		ebase = CAC_BASE;
-		ebase_pa = virt_to_phys((void *)ebase);
 		vec_size = 0x400;
-
-		memblock_reserve(ebase_pa, vec_size);
 	} else {
 		if (cpu_has_veic || cpu_has_vint)
 			vec_size = 0x200 + VECTORSPACING*64;

From cea15316ceee2d4a51dfdecd79e08a438135416c Mon Sep 17 00:00:00 2001
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date: Thu, 4 Mar 2021 07:34:11 +0530
Subject: [PATCH 0420/1820] powerpc/64s: Fix instruction encoding for lis in
 ppc_function_entry()

'lis r2,N' is 'addis r2,0,N' and the instruction encoding in the macro
LIS_R2 is incorrect (it currently maps to 'addis r0,r2,N'). Fix the
same.

Fixes: c71b7eff426f ("powerpc: Add ABIv2 support to ppc_function_entry")
Cc: stable@vger.kernel.org # v3.16+
Reported-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210304020411.16796-1-naveen.n.rao@linux.vnet.ibm.com
---
 arch/powerpc/include/asm/code-patching.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index eacc9102c251..d5b3c3bb95b4 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -73,7 +73,7 @@ void __patch_exception(int exc, unsigned long addr);
 #endif
 
 #define OP_RT_RA_MASK	0xffff0000UL
-#define LIS_R2		0x3c020000UL
+#define LIS_R2		0x3c400000UL
 #define ADDIS_R2_R12	0x3c4c0000UL
 #define ADDI_R2_R2	0x38420000UL
 

From 545ac14c16b5dbd909d5a90ddf5b5a629a40fa94 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 3 Mar 2021 15:17:13 +0100
Subject: [PATCH 0421/1820] x86/sev-es: Check regs->sp is trusted before
 adjusting #VC IST stack

The code in the NMI handler to adjust the #VC handler IST stack is
needed in case an NMI hits when the #VC handler is still using its IST
stack.

But the check for this condition also needs to look if the regs->sp
value is trusted, meaning it was not set by user-space. Extend the check
to not use regs->sp when the NMI interrupted user-space code or the
SYSCALL gap.

Fixes: 315562c9af3d5 ("x86/sev-es: Adjust #VC IST Stack on entering NMI handler")
Reported-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: stable@vger.kernel.org # 5.10+
Link: https://lkml.kernel.org/r/20210303141716.29223-3-joro@8bytes.org
---
 arch/x86/kernel/sev-es.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c
index 84c1821819af..301f20f6d4dd 100644
--- a/arch/x86/kernel/sev-es.c
+++ b/arch/x86/kernel/sev-es.c
@@ -121,8 +121,18 @@ static void __init setup_vc_stacks(int cpu)
 	cea_set_pte((void *)vaddr, pa, PAGE_KERNEL);
 }
 
-static __always_inline bool on_vc_stack(unsigned long sp)
+static __always_inline bool on_vc_stack(struct pt_regs *regs)
 {
+	unsigned long sp = regs->sp;
+
+	/* User-mode RSP is not trusted */
+	if (user_mode(regs))
+		return false;
+
+	/* SYSCALL gap still has user-mode RSP */
+	if (ip_within_syscall_gap(regs))
+		return false;
+
 	return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
 }
 
@@ -144,7 +154,7 @@ void noinstr __sev_es_ist_enter(struct pt_regs *regs)
 	old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
 
 	/* Make room on the IST stack */
-	if (on_vc_stack(regs->sp))
+	if (on_vc_stack(regs))
 		new_ist = ALIGN_DOWN(regs->sp, 8) - sizeof(old_ist);
 	else
 		new_ist = old_ist - sizeof(old_ist);

From 62441a1fb53263bda349b6e5997c3cc5c120d89e Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 3 Mar 2021 15:17:15 +0100
Subject: [PATCH 0422/1820] x86/sev-es: Correctly track IRQ states in runtime
 #VC handler

Call irqentry_nmi_enter()/irqentry_nmi_exit() in the #VC handler to
correctly track the IRQ state during its execution.

Fixes: 0786138c78e79 ("x86/sev-es: Add a Runtime #VC Exception Handler")
Reported-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: stable@vger.kernel.org # v5.10+
Link: https://lkml.kernel.org/r/20210303141716.29223-5-joro@8bytes.org
---
 arch/x86/kernel/sev-es.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c
index 301f20f6d4dd..c3fd8fa79838 100644
--- a/arch/x86/kernel/sev-es.c
+++ b/arch/x86/kernel/sev-es.c
@@ -1258,13 +1258,12 @@ static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs)
 DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
 {
 	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
+	irqentry_state_t irq_state;
 	struct ghcb_state state;
 	struct es_em_ctxt ctxt;
 	enum es_result result;
 	struct ghcb *ghcb;
 
-	lockdep_assert_irqs_disabled();
-
 	/*
 	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
 	 */
@@ -1273,6 +1272,8 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
 		return;
 	}
 
+	irq_state = irqentry_nmi_enter(regs);
+	lockdep_assert_irqs_disabled();
 	instrumentation_begin();
 
 	/*
@@ -1335,6 +1336,7 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
 
 out:
 	instrumentation_end();
+	irqentry_nmi_exit(regs, irq_state);
 
 	return;
 

From bffe30dd9f1f3b2608a87ac909a224d6be472485 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 3 Mar 2021 15:17:16 +0100
Subject: [PATCH 0423/1820] x86/sev-es: Use __copy_from_user_inatomic()

The #VC handler must run in atomic context and cannot sleep. This is a
problem when it tries to fetch instruction bytes from user-space via
copy_from_user().

Introduce a insn_fetch_from_user_inatomic() helper which uses
__copy_from_user_inatomic() to safely copy the instruction bytes to
kernel memory in the #VC handler.

Fixes: 5e3427a7bc432 ("x86/sev-es: Handle instruction fetches from user-space")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: stable@vger.kernel.org # v5.10+
Link: https://lkml.kernel.org/r/20210303141716.29223-6-joro@8bytes.org
---
 arch/x86/include/asm/insn-eval.h |  2 +
 arch/x86/kernel/sev-es.c         |  2 +-
 arch/x86/lib/insn-eval.c         | 66 +++++++++++++++++++++++++-------
 3 files changed, 55 insertions(+), 15 deletions(-)

diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index a0f839aa144d..98b4dae5e8bc 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -23,6 +23,8 @@ unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx);
 int insn_get_code_seg_params(struct pt_regs *regs);
 int insn_fetch_from_user(struct pt_regs *regs,
 			 unsigned char buf[MAX_INSN_SIZE]);
+int insn_fetch_from_user_inatomic(struct pt_regs *regs,
+				  unsigned char buf[MAX_INSN_SIZE]);
 bool insn_decode(struct insn *insn, struct pt_regs *regs,
 		 unsigned char buf[MAX_INSN_SIZE], int buf_size);
 
diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c
index c3fd8fa79838..04a780abb512 100644
--- a/arch/x86/kernel/sev-es.c
+++ b/arch/x86/kernel/sev-es.c
@@ -258,7 +258,7 @@ static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
 	int res;
 
 	if (user_mode(ctxt->regs)) {
-		res = insn_fetch_from_user(ctxt->regs, buffer);
+		res = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
 		if (!res) {
 			ctxt->fi.vector     = X86_TRAP_PF;
 			ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 4229950a5d78..bb0b3fe1e0a0 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -1415,6 +1415,25 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
 	}
 }
 
+static unsigned long insn_get_effective_ip(struct pt_regs *regs)
+{
+	unsigned long seg_base = 0;
+
+	/*
+	 * If not in user-space long mode, a custom code segment could be in
+	 * use. This is true in protected mode (if the process defined a local
+	 * descriptor table), or virtual-8086 mode. In most of the cases
+	 * seg_base will be zero as in USER_CS.
+	 */
+	if (!user_64bit_mode(regs)) {
+		seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS);
+		if (seg_base == -1L)
+			return 0;
+	}
+
+	return seg_base + regs->ip;
+}
+
 /**
  * insn_fetch_from_user() - Copy instruction bytes from user-space memory
  * @regs:	Structure with register values as seen when entering kernel mode
@@ -1431,24 +1450,43 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
  */
 int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE])
 {
-	unsigned long seg_base = 0;
+	unsigned long ip;
 	int not_copied;
 
-	/*
-	 * If not in user-space long mode, a custom code segment could be in
-	 * use. This is true in protected mode (if the process defined a local
-	 * descriptor table), or virtual-8086 mode. In most of the cases
-	 * seg_base will be zero as in USER_CS.
-	 */
-	if (!user_64bit_mode(regs)) {
-		seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS);
-		if (seg_base == -1L)
-			return 0;
-	}
+	ip = insn_get_effective_ip(regs);
+	if (!ip)
+		return 0;
 
+	not_copied = copy_from_user(buf, (void __user *)ip, MAX_INSN_SIZE);
 
-	not_copied = copy_from_user(buf, (void __user *)(seg_base + regs->ip),
-				    MAX_INSN_SIZE);
+	return MAX_INSN_SIZE - not_copied;
+}
+
+/**
+ * insn_fetch_from_user_inatomic() - Copy instruction bytes from user-space memory
+ *                                   while in atomic code
+ * @regs:	Structure with register values as seen when entering kernel mode
+ * @buf:	Array to store the fetched instruction
+ *
+ * Gets the linear address of the instruction and copies the instruction bytes
+ * to the buf. This function must be used in atomic context.
+ *
+ * Returns:
+ *
+ * Number of instruction bytes copied.
+ *
+ * 0 if nothing was copied.
+ */
+int insn_fetch_from_user_inatomic(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE])
+{
+	unsigned long ip;
+	int not_copied;
+
+	ip = insn_get_effective_ip(regs);
+	if (!ip)
+		return 0;
+
+	not_copied = __copy_from_user_inatomic(buf, (void __user *)ip, MAX_INSN_SIZE);
 
 	return MAX_INSN_SIZE - not_copied;
 }

From 86c83365ab76e4b43cedd3ce07a07d32a4dc79ba Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Mon, 8 Mar 2021 17:10:23 +0100
Subject: [PATCH 0424/1820] arm64: kasan: fix page_alloc tagging with
 DEBUG_VIRTUAL

When CONFIG_DEBUG_VIRTUAL is enabled, the default page_to_virt() macro
implementation from include/linux/mm.h is used. That definition doesn't
account for KASAN tags, which leads to no tags on page_alloc allocations.

Provide an arm64-specific definition for page_to_virt() when
CONFIG_DEBUG_VIRTUAL is enabled that takes care of KASAN tags.

Fixes: 2813b9c02962 ("kasan, mm, arm64: tag non slab memory allocated via pagealloc")
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/4b55b35202706223d3118230701c6a59749d9b72.1615219501.git.andreyknvl@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index c759faf7a1ff..0aabc3be9a75 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -328,6 +328,11 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
 #if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
+#define page_to_virt(x)	({						\
+	__typeof__(x) __page = x;					\
+	void *__addr = __va(page_to_phys(__page));			\
+	(void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\
+})
 #define virt_to_page(x)		pfn_to_page(virt_to_pfn(x))
 #else
 #define page_to_virt(x)	({						\

From 4aa5e002034f0701c3335379fd6c22d7f3338cce Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Mon, 8 Mar 2021 10:51:51 -0500
Subject: [PATCH 0425/1820] Revert "nfsd4: remove check_conflicting_opens
 warning"

This reverts commit 50747dd5e47b "nfsd4: remove check_conflicting_opens
warning", as a prerequisite for reverting 94415b06eb8a, which has a
serious bug.

Cc: stable@vger.kernel.org
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4state.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 61552e89bd89..482e241c9639 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4952,6 +4952,7 @@ static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
 		writes--;
 	if (fp->fi_fds[O_RDWR])
 		writes--;
+	WARN_ON_ONCE(writes < 0);
 	if (writes > 0)
 		return -EAGAIN;
 	spin_lock(&fp->fi_lock);

From 6ee65a773096ab3f39d9b00311ac983be5bdeb7c Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Mon, 8 Mar 2021 10:52:29 -0500
Subject: [PATCH 0426/1820] Revert "nfsd4: a client's own opens needn't prevent
 delegations"

This reverts commit 94415b06eb8aed13481646026dc995f04a3a534a.

That commit claimed to allow a client to get a read delegation when it
was the only writer.  Actually it allowed a client to get a read
delegation when *any* client has a write open!

The main problem is that it's depending on nfs4_clnt_odstate structures
that are actually only maintained for pnfs exports.

This causes clients to miss writes performed by other clients, even when
there have been intervening closes and opens, violating close-to-open
cache consistency.

We can do this a different way, but first we should just revert this.

I've added pynfs 4.1 test DELEG19 to test for this, as I should have
done originally!

Cc: stable@vger.kernel.org
Reported-by: Timo Rothenpieler <timo@rothenpieler.org>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/locks.c          |  3 ---
 fs/nfsd/nfs4state.c | 54 ++++++++++++---------------------------------
 2 files changed, 14 insertions(+), 43 deletions(-)

diff --git a/fs/locks.c b/fs/locks.c
index 99ca97e81b7a..6125d2de39b8 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1808,9 +1808,6 @@ check_conflicting_open(struct file *filp, const long arg, int flags)
 
 	if (flags & FL_LAYOUT)
 		return 0;
-	if (flags & FL_DELEG)
-		/* We leave these checks to the caller. */
-		return 0;
 
 	if (arg == F_RDLCK)
 		return inode_is_open_for_write(inode) ? -EAGAIN : 0;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 482e241c9639..97447a64bad0 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4940,32 +4940,6 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
 	return fl;
 }
 
-static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
-						struct nfs4_file *fp)
-{
-	struct nfs4_clnt_odstate *co;
-	struct file *f = fp->fi_deleg_file->nf_file;
-	struct inode *ino = locks_inode(f);
-	int writes = atomic_read(&ino->i_writecount);
-
-	if (fp->fi_fds[O_WRONLY])
-		writes--;
-	if (fp->fi_fds[O_RDWR])
-		writes--;
-	WARN_ON_ONCE(writes < 0);
-	if (writes > 0)
-		return -EAGAIN;
-	spin_lock(&fp->fi_lock);
-	list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) {
-		if (co->co_client != clp) {
-			spin_unlock(&fp->fi_lock);
-			return -EAGAIN;
-		}
-	}
-	spin_unlock(&fp->fi_lock);
-	return 0;
-}
-
 static struct nfs4_delegation *
 nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 		    struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate)
@@ -4985,12 +4959,9 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 
 	nf = find_readable_file(fp);
 	if (!nf) {
-		/*
-		 * We probably could attempt another open and get a read
-		 * delegation, but for now, don't bother until the
-		 * client actually sends us one.
-		 */
-		return ERR_PTR(-EAGAIN);
+		/* We should always have a readable file here */
+		WARN_ON_ONCE(1);
+		return ERR_PTR(-EBADF);
 	}
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
@@ -5020,19 +4991,11 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 	if (!fl)
 		goto out_clnt_odstate;
 
-	status = nfsd4_check_conflicting_opens(clp, fp);
-	if (status) {
-		locks_free_lock(fl);
-		goto out_clnt_odstate;
-	}
 	status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL);
 	if (fl)
 		locks_free_lock(fl);
 	if (status)
 		goto out_clnt_odstate;
-	status = nfsd4_check_conflicting_opens(clp, fp);
-	if (status)
-		goto out_clnt_odstate;
 
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
@@ -5114,6 +5077,17 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
 				goto out_no_deleg;
 			if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED))
 				goto out_no_deleg;
+			/*
+			 * Also, if the file was opened for write or
+			 * create, there's a good chance the client's
+			 * about to write to it, resulting in an
+			 * immediate recall (since we don't support
+			 * write delegations):
+			 */
+			if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
+				goto out_no_deleg;
+			if (open->op_create == NFS4_OPEN_CREATE)
+				goto out_no_deleg;
 			break;
 		default:
 			goto out_no_deleg;

From 5808fecc572391867fcd929662b29c12e6d08d81 Mon Sep 17 00:00:00 2001
From: Ritesh Harjani <riteshh@linux.ibm.com>
Date: Tue, 9 Mar 2021 09:29:11 -0800
Subject: [PATCH 0427/1820] iomap: Fix negative assignment to unsigned
 sis->pages in iomap_swapfile_activate

In case if isi.nr_pages is 0, we are making sis->pages (which is
unsigned int) a huge value in iomap_swapfile_activate() by assigning -1.
This could cause a kernel crash in kernel v4.18 (with below signature).
Or could lead to unknown issues on latest kernel if the fake big swap gets
used.

Fix this issue by returning -EINVAL in case of nr_pages is 0, since it
is anyway a invalid swapfile. Looks like this issue will be hit when
we have pagesize < blocksize type of configuration.

I was able to hit the issue in case of a tiny swap file with below
test script.
https://raw.githubusercontent.com/riteshharjani/LinuxStudy/master/scripts/swap-issue.sh

kernel crash analysis on v4.18
==============================
On v4.18 kernel, it causes a kernel panic, since sis->pages becomes
a huge value and isi.nr_extents is 0. When 0 is returned it is
considered as a swapfile over NFS and SWP_FILE is set (sis->flags |= SWP_FILE).
Then when swapoff was getting called it was calling a_ops->swap_deactivate()
if (sis->flags & SWP_FILE) is true. Since a_ops->swap_deactivate() is
NULL in case of XFS, it causes below panic.

Panic signature on v4.18 kernel:
=======================================
root@qemu:/home/qemu# [ 8291.723351] XFS (loop2): Unmounting Filesystem
[ 8292.123104] XFS (loop2): Mounting V5 Filesystem
[ 8292.132451] XFS (loop2): Ending clean mount
[ 8292.263362] Adding 4294967232k swap on /mnt1/test/swapfile.  Priority:-2 extents:1 across:274877906880k
[ 8292.277834] Unable to handle kernel paging request for instruction fetch
[ 8292.278677] Faulting instruction address: 0x00000000
cpu 0x19: Vector: 400 (Instruction Access) at [c0000009dd5b7ad0]
    pc: 0000000000000000
    lr: c0000000003eb9dc: destroy_swap_extents+0xfc/0x120
    sp: c0000009dd5b7d50
   msr: 8000000040009033
  current = 0xc0000009b6710080
  paca    = 0xc00000003ffcb280   irqmask: 0x03   irq_happened: 0x01
    pid   = 5604, comm = swapoff
Linux version 4.18.0 (riteshh@xxxxxxx) (gcc version 8.4.0 (Ubuntu 8.4.0-1ubuntu1~18.04)) #57 SMP Wed Mar 3 01:33:04 CST 2021
enter ? for help
[link register   ] c0000000003eb9dc destroy_swap_extents+0xfc/0x120
[c0000009dd5b7d50] c0000000025a7058 proc_poll_event+0x0/0x4 (unreliable)
[c0000009dd5b7da0] c0000000003f0498 sys_swapoff+0x3f8/0x910
[c0000009dd5b7e30] c00000000000bbe4 system_call+0x5c/0x70
Exception: c01 (System Call) at 00007ffff7d208d8

Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com>
[djwong: rework the comment to provide more details]
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/iomap/swapfile.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c
index a648dbf6991e..a5e478de1417 100644
--- a/fs/iomap/swapfile.c
+++ b/fs/iomap/swapfile.c
@@ -170,6 +170,16 @@ int iomap_swapfile_activate(struct swap_info_struct *sis,
 			return ret;
 	}
 
+	/*
+	 * If this swapfile doesn't contain even a single page-aligned
+	 * contiguous range of blocks, reject this useless swapfile to
+	 * prevent confusion later on.
+	 */
+	if (isi.nr_pages == 0) {
+		pr_warn("swapon: Cannot find a single usable page in file.\n");
+		return -EINVAL;
+	}
+
 	*pagespan = 1 + isi.highest_ppage - isi.lowest_ppage;
 	sis->max = isi.nr_pages;
 	sis->pages = isi.nr_pages - 1;

From b5a08423da9da59c7f38ed8dbb6dd6cbbe9024a4 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 2 Mar 2021 09:32:52 -0800
Subject: [PATCH 0428/1820] xfs: fix quota accounting when a mount is idmapped

Nowadays, we indirectly use the idmap-aware helper functions in the VFS
to set the initial uid and gid of a file being created.  Unfortunately,
we didn't convert the quota code, which means we attach the wrong dquots
to files created on an idmapped mount.

Fixes: f736d93d76d3 ("xfs: support idmapped mounts")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/xfs_inode.c   | 14 ++++++++------
 fs/xfs/xfs_symlink.c |  3 ++-
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 46a861d55e48..f93370bd7b1e 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1007,9 +1007,10 @@ xfs_create(
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
-	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
-					XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
-					&udqp, &gdqp, &pdqp);
+	error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns),
+			fsgid_into_mnt(mnt_userns), prid,
+			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
+			&udqp, &gdqp, &pdqp);
 	if (error)
 		return error;
 
@@ -1157,9 +1158,10 @@ xfs_create_tmpfile(
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
-	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
-				XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
-				&udqp, &gdqp, &pdqp);
+	error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns),
+			fsgid_into_mnt(mnt_userns), prid,
+			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
+			&udqp, &gdqp, &pdqp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 1379013d74b8..7f368b10ded1 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -182,7 +182,8 @@ xfs_symlink(
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
-	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
+	error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns),
+			fsgid_into_mnt(mnt_userns), prid,
 			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
 			&udqp, &gdqp, &pdqp);
 	if (error)

From 01dc9262ff5797b675c32c0c6bc682777d23de05 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 3 Mar 2021 16:45:05 +0000
Subject: [PATCH 0429/1820] KVM: arm64: Ensure I-cache isolation between vcpus
 of a same VM

It recently became apparent that the ARMv8 architecture has interesting
rules regarding attributes being used when fetching instructions
if the MMU is off at Stage-1.

In this situation, the CPU is allowed to fetch from the PoC and
allocate into the I-cache (unless the memory is mapped with
the XN attribute at Stage-2).

If we transpose this to vcpus sharing a single physical CPU,
it is possible for a vcpu running with its MMU off to influence
another vcpu running with its MMU on, as the latter is expected to
fetch from the PoU (and self-patching code doesn't flush below that
level).

In order to solve this, reuse the vcpu-private TLB invalidation
code to apply the same policy to the I-cache, nuking it every time
the vcpu runs on a physical CPU that ran another vcpu of the same
VM in the past.

This involve renaming __kvm_tlb_flush_local_vmid() to
__kvm_flush_cpu_context(), and inserting a local i-cache invalidation
there.

Cc: stable@vger.kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20210303164505.68492-1-maz@kernel.org
---
 arch/arm64/include/asm/kvm_asm.h   | 4 ++--
 arch/arm64/kvm/arm.c               | 7 ++++++-
 arch/arm64/kvm/hyp/nvhe/hyp-main.c | 6 +++---
 arch/arm64/kvm/hyp/nvhe/tlb.c      | 3 ++-
 arch/arm64/kvm/hyp/vhe/tlb.c       | 3 ++-
 5 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 9c0e396dd03f..a7ab84f781f7 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -47,7 +47,7 @@
 #define __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context		2
 #define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa		3
 #define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid		4
-#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_local_vmid	5
+#define __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context		5
 #define __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff		6
 #define __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs			7
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config		8
@@ -183,10 +183,10 @@ DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #define __bp_harden_hyp_vecs	CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
 
 extern void __kvm_flush_vm_context(void);
+extern void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
 				     int level);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
-extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index bb85da1d5880..a391b984dd05 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -385,11 +385,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
 	/*
+	 * We guarantee that both TLBs and I-cache are private to each
+	 * vcpu. If detecting that a vcpu from the same VM has
+	 * previously run on the same physical CPU, call into the
+	 * hypervisor code to nuke the relevant contexts.
+	 *
 	 * We might get preempted before the vCPU actually runs, but
 	 * over-invalidation doesn't affect correctness.
 	 */
 	if (*last_ran != vcpu->vcpu_id) {
-		kvm_call_hyp(__kvm_tlb_flush_local_vmid, mmu);
+		kvm_call_hyp(__kvm_flush_cpu_context, mmu);
 		*last_ran = vcpu->vcpu_id;
 	}
 
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 8f129968204e..936328207bde 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -46,11 +46,11 @@ static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
 	__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
 }
 
-static void handle___kvm_tlb_flush_local_vmid(struct kvm_cpu_context *host_ctxt)
+static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
 
-	__kvm_tlb_flush_local_vmid(kern_hyp_va(mmu));
+	__kvm_flush_cpu_context(kern_hyp_va(mmu));
 }
 
 static void handle___kvm_timer_set_cntvoff(struct kvm_cpu_context *host_ctxt)
@@ -115,7 +115,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_flush_vm_context),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),
-	HANDLE_FUNC(__kvm_tlb_flush_local_vmid),
+	HANDLE_FUNC(__kvm_flush_cpu_context),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
 	HANDLE_FUNC(__kvm_enable_ssbs),
 	HANDLE_FUNC(__vgic_v3_get_gic_config),
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index fbde89a2c6e8..229b06748c20 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -123,7 +123,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
@@ -131,6 +131,7 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
+	asm volatile("ic iallu");
 	dsb(nsh);
 	isb();
 
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index fd7895945bbc..66f17349f0c3 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -127,7 +127,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
@@ -135,6 +135,7 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
+	asm volatile("ic iallu");
 	dsb(nsh);
 	isb();
 

From 614c9750173e412663728215152cc6d12bcb3425 Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <kolga@netapp.com>
Date: Tue, 9 Mar 2021 09:41:14 -0500
Subject: [PATCH 0430/1820] NFSD: fix dest to src mount in inter-server COPY

A cleanup of the inter SSC copy needs to call fput() of the source
file handle to make sure that file structure is freed as well as
drop the reference on the superblock to unmount the source server.

Fixes: 36e1e5ba90fb ("NFSD: Fix use-after-free warning when doing inter-server copy")
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Dai Ngo <dai.ngo@oracle.com>
---
 fs/nfsd/nfs4proc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index acdb3cd806a1..dd9f38d072dd 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1302,7 +1302,7 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src,
 			struct nfsd_file *dst)
 {
 	nfs42_ssc_close(src->nf_file);
-	/* 'src' is freed by nfsd4_do_async_copy */
+	fput(src->nf_file);
 	nfsd_file_put(dst);
 	mntput(ss_mnt);
 }

From 53cb245454df5b13d7063162afd7a785aed6ebf2 Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Fri, 15 Jan 2021 18:43:56 +0100
Subject: [PATCH 0431/1820] NFSv4.2: fix return value of
 _nfs4_get_security_label()

An xattr 'get' handler is expected to return the length of the value on
success, yet _nfs4_get_security_label() (and consequently also
nfs4_xattr_get_nfs4_label(), which is used as an xattr handler) returns
just 0 on success.

Fix this by returning label.len instead, which contains the length of
the result.

Fixes: aa9c2669626c ("NFS: Client implementation of Labeled-NFS")
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Reviewed-by: James Morris <jamorris@linux.microsoft.com>
Reviewed-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6d8fc56e5f45..1002c4f66f3f 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5965,7 +5965,7 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf,
 		return ret;
 	if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL))
 		return -ENOENT;
-	return 0;
+	return label.len;
 }
 
 static int nfs4_get_security_label(struct inode *inode, void *buf,

From f7d9d4854519fdf4d45c70a4d953438cd88e7e58 Mon Sep 17 00:00:00 2001
From: Xie He <xie.he.0141@gmail.com>
Date: Sun, 7 Mar 2021 03:33:07 -0800
Subject: [PATCH 0432/1820] net: lapbether: Remove netif_start_queue /
 netif_stop_queue

For the devices in this driver, the default qdisc is "noqueue",
because their "tx_queue_len" is 0.

In function "__dev_queue_xmit" in "net/core/dev.c", devices with the
"noqueue" qdisc are specially handled. Packets are transmitted without
being queued after a "dev->flags & IFF_UP" check. However, it's possible
that even if this check succeeds, "ops->ndo_stop" may still have already
been called. This is because in "__dev_close_many", "ops->ndo_stop" is
called before clearing the "IFF_UP" flag.

If we call "netif_stop_queue" in "ops->ndo_stop", then it's possible in
"__dev_queue_xmit", it sees the "IFF_UP" flag is present, and then it
checks "netif_xmit_stopped" and finds that the queue is already stopped.
In this case, it will complain that:
"Virtual device ... asks to queue packet!"

To prevent "__dev_queue_xmit" from generating this complaint, we should
not call "netif_stop_queue" in "ops->ndo_stop".

We also don't need to call "netif_start_queue" in "ops->ndo_open",
because after a netdev is allocated and registered, the
"__QUEUE_STATE_DRV_XOFF" flag is initially not set, so there is no need
to call "netif_start_queue" to clear it.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Xie He <xie.he.0141@gmail.com>
Acked-by: Martin Schiller <ms@dev.tdt.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/lapbether.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 605fe555e157..c3372498f4f1 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -292,7 +292,6 @@ static int lapbeth_open(struct net_device *dev)
 		return -ENODEV;
 	}
 
-	netif_start_queue(dev);
 	return 0;
 }
 
@@ -300,8 +299,6 @@ static int lapbeth_close(struct net_device *dev)
 {
 	int err;
 
-	netif_stop_queue(dev);
-
 	if ((err = lapb_unregister(dev)) != LAPB_OK)
 		pr_err("lapb_unregister error: %d\n", err);
 

From 993bdde94547887faaad4a97f0b0480a6da271c3 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 28 Feb 2021 15:10:25 +0900
Subject: [PATCH 0433/1820] kbuild: add image_name to no-sync-config-targets

'make image_name' needs include/config/auto.conf to show the correct
output because KBUILD_IMAGE depends on CONFIG options, but should not
attempt to resync the configuration.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 Makefile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 31dcdb3d61fa..3f9f44eac27f 100644
--- a/Makefile
+++ b/Makefile
@@ -264,7 +264,8 @@ no-dot-config-targets := $(clean-targets) \
 			 $(version_h) headers headers_% archheaders archscripts \
 			 %asm-generic kernelversion %src-pkg dt_binding_check \
 			 outputmakefile
-no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease
+no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease \
+			  image_name
 single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/
 
 config-build	:=

From b3d9fc1436808a4ef9927e558b3415e728e710c5 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Wed, 3 Mar 2021 11:43:14 +0100
Subject: [PATCH 0434/1820] kbuild: dummy-tools: fix inverted tests for gcc

There is a test in Kconfig which takes inverted value of a compiler
check:
* config CC_HAS_INT128
        def_bool !$(cc-option,$(m64-flag) -D__SIZEOF_INT128__=0)

This results in CC_HAS_INT128 not being in super-config generated by
dummy-tools. So take this into account in the gcc script.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/dummy-tools/gcc | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/scripts/dummy-tools/gcc b/scripts/dummy-tools/gcc
index 5c113cad5601..0d0589cf8184 100755
--- a/scripts/dummy-tools/gcc
+++ b/scripts/dummy-tools/gcc
@@ -85,3 +85,8 @@ if arg_contain -print-file-name=plugin "$@"; then
 	echo $plugin_dir
 	exit 0
 fi
+
+# inverted return value
+if arg_contain -D__SIZEOF_INT128__=0 "$@"; then
+	exit 1
+fi

From 1f09af062556f0610c08e2f3d680a8b8bc40dd48 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bernhard=20Rosenkr=C3=A4nzer?= <bero@lindev.ch>
Date: Tue, 2 Mar 2021 23:12:11 +0100
Subject: [PATCH 0435/1820] kbuild: Fix ld-version.sh script if LLD was built
 with LLD_VENDOR
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If LLD was built with -DLLD_VENDOR="xyz", ld.lld --version output
will prefix LLD_VENDOR. Since LLD_VENDOR can contain spaces, the
LLD identifier isn't guaranteed to be $2 either.

Adjust the version checker to handle such versions of lld.

Link: https://lore.kernel.org/lkml/20210302221211.1620858-1-bero@lindev.ch/
Signed-off-by: Bernhard Rosenkränzer <bero@lindev.ch>
[masahiro yamada: refactor the code]
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/ld-version.sh | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/scripts/ld-version.sh b/scripts/ld-version.sh
index a463273509b5..30debf78aa09 100755
--- a/scripts/ld-version.sh
+++ b/scripts/ld-version.sh
@@ -44,14 +44,20 @@ if [ "$1" = GNU -a "$2" = ld ]; then
 elif [ "$1" = GNU -a "$2" = gold ]; then
 	echo "gold linker is not supported as it is not capable of linking the kernel proper." >&2
 	exit 1
-elif [ "$1" = LLD ]; then
-	version=$2
-	min_version=$lld_min_version
-	name=LLD
-	disp_name=LLD
 else
-	echo "$orig_args: unknown linker" >&2
-	exit 1
+	while [ $# -gt 1 -a "$1" != "LLD" ]; do
+		shift
+	done
+
+	if [ "$1" = LLD ]; then
+		version=$2
+		min_version=$lld_min_version
+		name=LLD
+		disp_name=LLD
+	else
+		echo "$orig_args: unknown linker" >&2
+		exit 1
+	fi
 fi
 
 # Some distributions append a package release number, as in 2.34-4.fc32

From 05a68ce5fa51a83c360381630f823545c5757aa2 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 9 Mar 2021 10:50:28 -0800
Subject: [PATCH 0436/1820] bpf: Don't do bpf_cgroup_storage_set() for
 kuprobe/tp programs

For kuprobe and tracepoint bpf programs, kernel calls
trace_call_bpf() which calls BPF_PROG_RUN_ARRAY_CHECK()
to run the program array. Currently, BPF_PROG_RUN_ARRAY_CHECK()
also calls bpf_cgroup_storage_set() to set percpu
cgroup local storage with NULL value. This is
due to Commit 394e40a29788 ("bpf: extend bpf_prog_array to store
pointers to the cgroup storage") which modified
__BPF_PROG_RUN_ARRAY() to call bpf_cgroup_storage_set()
and this macro is also used by BPF_PROG_RUN_ARRAY_CHECK().

kuprobe and tracepoint programs are not allowed to call
bpf_get_local_storage() helper hence does not
access percpu cgroup local storage. Let us
change BPF_PROG_RUN_ARRAY_CHECK() not to
modify percpu cgroup local storage.

The issue is observed when I tried to debug [1] where
percpu data is overwritten due to
  preempt_disable -> migration_disable
change. This patch does not completely fix the above issue,
which will be addressed separately, e.g., multiple cgroup
prog runs may preempt each other. But it does fix
any potential issue caused by tracing program
overwriting percpu cgroup storage:
 - in a busy system, a tracing program is to run between
   bpf_cgroup_storage_set() and the cgroup prog run.
 - a kprobe program is triggered by a helper in cgroup prog
   before bpf_get_local_storage() is called.

 [1] https://lore.kernel.org/bpf/CAKH8qBuXCfUz=w8L+Fj74OaUpbosO29niYwTki7e3Ag044_aww@mail.gmail.com/T

Fixes: 394e40a29788 ("bpf: extend bpf_prog_array to store pointers to the cgroup storage")
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Roman Gushchin <guro@fb.com>
Link: https://lore.kernel.org/bpf/20210309185028.3763817-1-yhs@fb.com
---
 include/linux/bpf.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index cccaef1088ea..d7e0f479a5b0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1093,7 +1093,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 		_ret;							\
 	 })
 
-#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null)	\
+#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null, set_cg_storage)	\
 	({						\
 		struct bpf_prog_array_item *_item;	\
 		struct bpf_prog *_prog;			\
@@ -1106,7 +1106,8 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 			goto _out;			\
 		_item = &_array->items[0];		\
 		while ((_prog = READ_ONCE(_item->prog))) {		\
-			bpf_cgroup_storage_set(_item->cgroup_storage);	\
+			if (set_cg_storage)		\
+				bpf_cgroup_storage_set(_item->cgroup_storage);	\
 			_ret &= func(_prog, ctx);	\
 			_item++;			\
 		}					\
@@ -1153,10 +1154,10 @@ _out:							\
 	})
 
 #define BPF_PROG_RUN_ARRAY(array, ctx, func)		\
-	__BPF_PROG_RUN_ARRAY(array, ctx, func, false)
+	__BPF_PROG_RUN_ARRAY(array, ctx, func, false, true)
 
 #define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func)	\
-	__BPF_PROG_RUN_ARRAY(array, ctx, func, true)
+	__BPF_PROG_RUN_ARRAY(array, ctx, func, true, false)
 
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);

From eeb05595d22c19c8f814ff893dcf88ec277a2365 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 8 Mar 2021 12:35:01 +0000
Subject: [PATCH 0437/1820] umem: fix error return code in mm_pci_probe()

Fix to return negative error code -ENOMEM from the blk_alloc_queue()
and dma_alloc_coherent() error handling cases instead of 0, as done
elsewhere in this function.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Link: https://lore.kernel.org/r/20210308123501.2573816-1-weiyongjun1@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/umem.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 982732dbe82e..664280f23bee 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -877,6 +877,7 @@ static int mm_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (card->mm_pages[0].desc == NULL ||
 	    card->mm_pages[1].desc == NULL) {
 		dev_printk(KERN_ERR, &card->dev->dev, "alloc failed\n");
+		ret = -ENOMEM;
 		goto failed_alloc;
 	}
 	reset_page(&card->mm_pages[0]);
@@ -888,8 +889,10 @@ static int mm_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	spin_lock_init(&card->lock);
 
 	card->queue = blk_alloc_queue(NUMA_NO_NODE);
-	if (!card->queue)
+	if (!card->queue) {
+		ret = -ENOMEM;
 		goto failed_alloc;
+	}
 
 	tasklet_init(&card->tasklet, process_page, (unsigned long)card);
 

From 7aed41cff35a9aaf3431b8c0c23daa7d8bb77cd3 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue, 9 Mar 2021 17:53:15 +1100
Subject: [PATCH 0438/1820] powerpc/64s: Use symbolic macros for function entry
 encoding

In ppc_function_entry() we look for a specific set of instructions by
masking the instructions and comparing with a known value. Currently
those known values are just literal hex values, and we recently
discovered one of them was wrong.

Instead construct the values using the existing constants we have for
defining various fields of instructions.

Suggested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20210309071544.515303-1-mpe@ellerman.id.au
---
 arch/powerpc/include/asm/code-patching.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index d5b3c3bb95b4..f1d029bf906e 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -73,9 +73,10 @@ void __patch_exception(int exc, unsigned long addr);
 #endif
 
 #define OP_RT_RA_MASK	0xffff0000UL
-#define LIS_R2		0x3c400000UL
-#define ADDIS_R2_R12	0x3c4c0000UL
-#define ADDI_R2_R2	0x38420000UL
+#define LIS_R2		(PPC_INST_ADDIS | __PPC_RT(R2))
+#define ADDIS_R2_R12	(PPC_INST_ADDIS | __PPC_RT(R2) | __PPC_RA(R12))
+#define ADDI_R2_R2	(PPC_INST_ADDI  | __PPC_RT(R2) | __PPC_RA(R2))
+
 
 static inline unsigned long ppc_function_entry(void *func)
 {

From 73ac79881804eed2e9d76ecdd1018037f8510cb1 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Mon, 8 Mar 2021 18:55:30 +1000
Subject: [PATCH 0439/1820] powerpc: Fix inverted SET_FULL_REGS bitop

This bit operation was inverted and set the low bit rather than
cleared it, breaking the ability to ptrace non-volatile GPRs after
exec. Fix.

Only affects 64e and 32-bit.

Fixes: feb9df3462e6 ("powerpc/64s: Always has full regs, so remove remnant checks")
Cc: stable@vger.kernel.org # v5.8+
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210308085530.3191843-1-npiggin@gmail.com
---
 arch/powerpc/include/asm/ptrace.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 975ba260006a..1499e928ea6a 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -195,7 +195,7 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
 #define TRAP_FLAGS_MASK		0x11
 #define TRAP(regs)		((regs)->trap & ~TRAP_FLAGS_MASK)
 #define FULL_REGS(regs)		(((regs)->trap & 1) == 0)
-#define SET_FULL_REGS(regs)	((regs)->trap |= 1)
+#define SET_FULL_REGS(regs)	((regs)->trap &= ~1)
 #endif
 #define CHECK_FULL_REGS(regs)	BUG_ON(!FULL_REGS(regs))
 #define NV_REG_POISON		0xdeadbeefdeadbeefUL
@@ -210,7 +210,7 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
 #define TRAP_FLAGS_MASK		0x1F
 #define TRAP(regs)		((regs)->trap & ~TRAP_FLAGS_MASK)
 #define FULL_REGS(regs)		(((regs)->trap & 1) == 0)
-#define SET_FULL_REGS(regs)	((regs)->trap |= 1)
+#define SET_FULL_REGS(regs)	((regs)->trap &= ~1)
 #define IS_CRITICAL_EXC(regs)	(((regs)->trap & 2) != 0)
 #define IS_MCHECK_EXC(regs)	(((regs)->trap & 4) != 0)
 #define IS_DEBUG_EXC(regs)	(((regs)->trap & 8) != 0)

From c080a173301ffc62cb6c76308c803c7fee05517a Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Thu, 25 Feb 2021 14:09:59 +1100
Subject: [PATCH 0440/1820] powerpc/64s/exception: Clean up a missed SRR
 specifier

Nick's patch cleaning up the SRR specifiers in exception-64s.S missed
a single instance of EXC_HV_OR_STD. Clean that up.

Caught by clang's integrated assembler.

Fixes: 3f7fbd97d07d ("powerpc/64s/exception: Clean up SRR specifiers")
Signed-off-by: Daniel Axtens <dja@axtens.net>
Acked-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210225031006.1204774-2-dja@axtens.net
---
 arch/powerpc/kernel/exceptions-64s.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 60d3051a8bc8..8082b690e874 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -466,7 +466,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
 
 	ld	r10,PACAKMSR(r13)	/* get MSR value for kernel */
 	/* MSR[RI] is clear iff using SRR regs */
-	.if IHSRR == EXC_HV_OR_STD
+	.if IHSRR_IF_HVMODE
 	BEGIN_FTR_SECTION
 	xori	r10,r10,MSR_RI
 	END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)

From de920fc64cbaa031f947e9be964bda05fd090380 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 8 Mar 2021 17:56:47 -0800
Subject: [PATCH 0441/1820] bpf, x86: Use kvmalloc_array instead kmalloc_array
 in bpf_jit_comp

x86 bpf_jit_comp.c used kmalloc_array to store jited addresses
for each bpf insn. With a large bpf program, we have see the
following allocation failures in our production server:

    page allocation failure: order:5, mode:0x40cc0(GFP_KERNEL|__GFP_COMP),
                             nodemask=(null),cpuset=/,mems_allowed=0"
    Call Trace:
    dump_stack+0x50/0x70
    warn_alloc.cold.120+0x72/0xd2
    ? __alloc_pages_direct_compact+0x157/0x160
    __alloc_pages_slowpath+0xcdb/0xd00
    ? get_page_from_freelist+0xe44/0x1600
    ? vunmap_page_range+0x1ba/0x340
    __alloc_pages_nodemask+0x2c9/0x320
    kmalloc_order+0x18/0x80
    kmalloc_order_trace+0x1d/0xa0
    bpf_int_jit_compile+0x1e2/0x484
    ? kmalloc_order_trace+0x1d/0xa0
    bpf_prog_select_runtime+0xc3/0x150
    bpf_prog_load+0x480/0x720
    ? __mod_memcg_lruvec_state+0x21/0x100
    __do_sys_bpf+0xc31/0x2040
    ? close_pdeo+0x86/0xe0
    do_syscall_64+0x42/0x110
    entry_SYSCALL_64_after_hwframe+0x44/0xa9
    RIP: 0033:0x7f2f300f7fa9
    Code: Bad RIP value.

Dumped assembly:

    ffffffff810b6d70 <bpf_int_jit_compile>:
    ; {
    ffffffff810b6d70: e8 eb a5 b4 00        callq   0xffffffff81c01360 <__fentry__>
    ffffffff810b6d75: 41 57                 pushq   %r15
    ...
    ffffffff810b6f39: e9 72 fe ff ff        jmp     0xffffffff810b6db0 <bpf_int_jit_compile+0x40>
    ;       addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
    ffffffff810b6f3e: 8b 45 0c              movl    12(%rbp), %eax
    ;       return __kmalloc(bytes, flags);
    ffffffff810b6f41: be c0 0c 00 00        movl    $3264, %esi
    ;       addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
    ffffffff810b6f46: 8d 78 01              leal    1(%rax), %edi
    ;       if (unlikely(check_mul_overflow(n, size, &bytes)))
    ffffffff810b6f49: 48 c1 e7 02           shlq    $2, %rdi
    ;       return __kmalloc(bytes, flags);
    ffffffff810b6f4d: e8 8e 0c 1d 00        callq   0xffffffff81287be0 <__kmalloc>
    ;       if (!addrs) {
    ffffffff810b6f52: 48 85 c0              testq   %rax, %rax

Change kmalloc_array() to kvmalloc_array() to avoid potential
allocation error for big bpf programs.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210309015647.3657852-1-yhs@fb.com
---
 arch/x86/net/bpf_jit_comp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 6926d0ca6c71..747bba0a584a 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2225,7 +2225,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		padding = true;
 		goto skip_init_addrs;
 	}
-	addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
+	addrs = kvmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
 	if (!addrs) {
 		prog = orig_prog;
 		goto out_addrs;
@@ -2317,7 +2317,7 @@ out_image:
 		if (image)
 			bpf_prog_fill_jited_linfo(prog, addrs + 1);
 out_addrs:
-		kfree(addrs);
+		kvfree(addrs);
 		kfree(jit_data);
 		prog->aux->jit_data = NULL;
 	}

From 286a8624d7f9c6505cd568d947772eb59646514b Mon Sep 17 00:00:00 2001
From: George McCollister <george.mccollister@gmail.com>
Date: Mon, 8 Mar 2021 17:38:22 -0600
Subject: [PATCH 0442/1820] net: dsa: xrs700x: check if partner is same as port
 in hsr join

Don't assign dp to partner if it's the same port that xrs700x_hsr_join
was called with. The partner port is supposed to be the other port in
the HSR/PRP redundant pair not the same port. This fixes an issue
observed in testing where forwarding between redundant HSR ports on this
switch didn't work depending on the order the ports were added to the
hsr device.

Fixes: bd62e6f5e6a9 ("net: dsa: xrs700x: add HSR offloading support")
Signed-off-by: George McCollister <george.mccollister@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/xrs700x/xrs700x.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c
index f025f968f96d..fde6e99274b6 100644
--- a/drivers/net/dsa/xrs700x/xrs700x.c
+++ b/drivers/net/dsa/xrs700x/xrs700x.c
@@ -528,7 +528,10 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port,
 		return -EOPNOTSUPP;
 
 	dsa_hsr_foreach_port(dp, ds, hsr) {
-		partner = dp;
+		if (dp->index != port) {
+			partner = dp;
+			break;
+		}
 	}
 
 	/* We can't enable redundancy on the switch until both
@@ -582,7 +585,10 @@ static int xrs700x_hsr_leave(struct dsa_switch *ds, int port,
 	unsigned int val;
 
 	dsa_hsr_foreach_port(dp, ds, hsr) {
-		partner = dp;
+		if (dp->index != port) {
+			partner = dp;
+			break;
+		}
 	}
 
 	if (!partner)

From 924a9bc362a5223cd448ca08c3dde21235adc310 Mon Sep 17 00:00:00 2001
From: Balazs Nemeth <bnemeth@redhat.com>
Date: Tue, 9 Mar 2021 12:31:00 +0100
Subject: [PATCH 0443/1820] net: check if protocol extracted by
 virtio_net_hdr_set_proto is correct

For gso packets, virtio_net_hdr_set_proto sets the protocol (if it isn't
set) based on the type in the virtio net hdr, but the skb could contain
anything since it could come from packet_snd through a raw socket. If
there is a mismatch between what virtio_net_hdr_set_proto sets and
the actual protocol, then the skb could be handled incorrectly later
on.

An example where this poses an issue is with the subsequent call to
skb_flow_dissect_flow_keys_basic which relies on skb->protocol being set
correctly. A specially crafted packet could fool
skb_flow_dissect_flow_keys_basic preventing EINVAL to be returned.

Avoid blindly trusting the information provided by the virtio net header
by checking that the protocol in the packet actually matches the
protocol set by virtio_net_hdr_set_proto. Note that since the protocol
is only checked if skb->dev implements header_ops->parse_protocol,
packets from devices without the implementation are not checked at this
stage.

Fixes: 9274124f023b ("net: stricter validation of untrusted gso packets")
Signed-off-by: Balazs Nemeth <bnemeth@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index e8a924eeea3d..6b5fcfa1e555 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -79,8 +79,13 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		if (gso_type && skb->network_header) {
 			struct flow_keys_basic keys;
 
-			if (!skb->protocol)
+			if (!skb->protocol) {
+				__be16 protocol = dev_parse_header_protocol(skb);
+
 				virtio_net_hdr_set_proto(skb, hdr);
+				if (protocol && protocol != skb->protocol)
+					return -EINVAL;
+			}
 retry:
 			if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
 							      NULL, 0, 0, 0,

From d348ede32e99d3a04863e9f9b28d224456118c27 Mon Sep 17 00:00:00 2001
From: Balazs Nemeth <bnemeth@redhat.com>
Date: Tue, 9 Mar 2021 12:31:01 +0100
Subject: [PATCH 0444/1820] net: avoid infinite loop in mpls_gso_segment when
 mpls_hlen == 0

A packet with skb_inner_network_header(skb) == skb_network_header(skb)
and ETH_P_MPLS_UC will prevent mpls_gso_segment from pulling any headers
from the packet. Subsequently, the call to skb_mac_gso_segment will
again call mpls_gso_segment with the same packet leading to an infinite
loop. In addition, ensure that the header length is a multiple of four,
which should hold irrespective of the number of stacked labels.

Signed-off-by: Balazs Nemeth <bnemeth@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/mpls_gso.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index b1690149b6fa..1482259de9b5 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -14,6 +14,7 @@
 #include <linux/netdev_features.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
+#include <net/mpls.h>
 
 static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 				       netdev_features_t features)
@@ -27,6 +28,8 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 
 	skb_reset_network_header(skb);
 	mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb);
+	if (unlikely(!mpls_hlen || mpls_hlen % MPLS_HLEN))
+		goto out;
 	if (unlikely(!pskb_may_pull(skb, mpls_hlen)))
 		goto out;
 

From e7a36d27f6b9f389e41d8189a8a08919c6835732 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Tue, 9 Mar 2021 17:52:18 +0100
Subject: [PATCH 0445/1820] s390/qeth: fix memory leak after failed TX Buffer
 allocation

When qeth_alloc_qdio_queues() fails to allocate one of the buffers that
back an Output Queue, the 'out_freeoutqbufs' path will free all
previously allocated buffers for this queue. But it misses to free the
half-finished queue struct itself.

Move the buffer allocation into qeth_alloc_output_queue(), and deal with
such errors internally.

Fixes: 0da9581ddb0f ("qeth: exploit asynchronous delivery of storage blocks")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 35 +++++++++++++++----------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index b71b8902d1c4..f7bc0ca6909b 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2634,15 +2634,28 @@ static void qeth_free_output_queue(struct qeth_qdio_out_q *q)
 static struct qeth_qdio_out_q *qeth_alloc_output_queue(void)
 {
 	struct qeth_qdio_out_q *q = kzalloc(sizeof(*q), GFP_KERNEL);
+	unsigned int i;
 
 	if (!q)
 		return NULL;
 
-	if (qdio_alloc_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q)) {
-		kfree(q);
-		return NULL;
+	if (qdio_alloc_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q))
+		goto err_qdio_bufs;
+
+	for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++) {
+		if (qeth_init_qdio_out_buf(q, i))
+			goto err_out_bufs;
 	}
+
 	return q;
+
+err_out_bufs:
+	while (i > 0)
+		kmem_cache_free(qeth_qdio_outbuf_cache, q->bufs[--i]);
+	qdio_free_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q);
+err_qdio_bufs:
+	kfree(q);
+	return NULL;
 }
 
 static void qeth_tx_completion_timer(struct timer_list *timer)
@@ -2655,7 +2668,7 @@ static void qeth_tx_completion_timer(struct timer_list *timer)
 
 static int qeth_alloc_qdio_queues(struct qeth_card *card)
 {
-	int i, j;
+	unsigned int i;
 
 	QETH_CARD_TEXT(card, 2, "allcqdbf");
 
@@ -2689,13 +2702,6 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card)
 		queue->coalesce_usecs = QETH_TX_COALESCE_USECS;
 		queue->max_coalesced_frames = QETH_TX_MAX_COALESCED_FRAMES;
 		queue->priority = QETH_QIB_PQUE_PRIO_DEFAULT;
-
-		/* give outbound qeth_qdio_buffers their qdio_buffers */
-		for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) {
-			WARN_ON(queue->bufs[j]);
-			if (qeth_init_qdio_out_buf(queue, j))
-				goto out_freeoutqbufs;
-		}
 	}
 
 	/* completion */
@@ -2704,13 +2710,6 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card)
 
 	return 0;
 
-out_freeoutqbufs:
-	while (j > 0) {
-		--j;
-		kmem_cache_free(qeth_qdio_outbuf_cache,
-				card->qdio.out_qs[i]->bufs[j]);
-		card->qdio.out_qs[i]->bufs[j] = NULL;
-	}
 out_freeoutq:
 	while (i > 0) {
 		qeth_free_output_queue(card->qdio.out_qs[--i]);

From c20383ad1656b0f6354dd50e4acd894f9d94090d Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Tue, 9 Mar 2021 17:52:19 +0100
Subject: [PATCH 0446/1820] s390/qeth: improve completion of pending TX buffers

The current design attaches a pending TX buffer to a custom
single-linked list, which is anchored at the buffer's slot on the
TX ring. The buffer is then checked for final completion whenever
this slot is processed during a subsequent TX NAPI poll cycle.

But if there's insufficient traffic on the ring, we might never make
enough progress to get back to this ring slot and discover the pending
buffer's final TX completion. In particular if this missing TX
completion blocks the application from sending further traffic.

So convert the custom single-linked list code to a per-queue list_head,
and scan this list on every TX NAPI cycle.

Fixes: 0da9581ddb0f ("qeth: exploit asynchronous delivery of storage blocks")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  3 +-
 drivers/s390/net/qeth_core_main.c | 69 +++++++++++++------------------
 2 files changed, 30 insertions(+), 42 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index a1da83b0b0ef..91acff493612 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -436,7 +436,7 @@ struct qeth_qdio_out_buffer {
 	int is_header[QDIO_MAX_ELEMENTS_PER_BUFFER];
 
 	struct qeth_qdio_out_q *q;
-	struct qeth_qdio_out_buffer *next_pending;
+	struct list_head list_entry;
 };
 
 struct qeth_card;
@@ -500,6 +500,7 @@ struct qeth_qdio_out_q {
 	struct qdio_buffer *qdio_bufs[QDIO_MAX_BUFFERS_PER_Q];
 	struct qeth_qdio_out_buffer *bufs[QDIO_MAX_BUFFERS_PER_Q];
 	struct qdio_outbuf_state *bufstates; /* convenience pointer */
+	struct list_head pending_bufs;
 	struct qeth_out_q_stats stats;
 	spinlock_t lock;
 	unsigned int priority;
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index f7bc0ca6909b..3763cd6d14f8 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -73,8 +73,6 @@ static void qeth_free_qdio_queues(struct qeth_card *card);
 static void qeth_notify_skbs(struct qeth_qdio_out_q *queue,
 		struct qeth_qdio_out_buffer *buf,
 		enum iucv_tx_notify notification);
-static void qeth_tx_complete_buf(struct qeth_qdio_out_buffer *buf, bool error,
-				 int budget);
 
 static void qeth_close_dev_handler(struct work_struct *work)
 {
@@ -465,41 +463,6 @@ static enum iucv_tx_notify qeth_compute_cq_notification(int sbalf15,
 	return n;
 }
 
-static void qeth_cleanup_handled_pending(struct qeth_qdio_out_q *q, int bidx,
-					 int forced_cleanup)
-{
-	if (q->card->options.cq != QETH_CQ_ENABLED)
-		return;
-
-	if (q->bufs[bidx]->next_pending != NULL) {
-		struct qeth_qdio_out_buffer *head = q->bufs[bidx];
-		struct qeth_qdio_out_buffer *c = q->bufs[bidx]->next_pending;
-
-		while (c) {
-			if (forced_cleanup ||
-			    atomic_read(&c->state) == QETH_QDIO_BUF_EMPTY) {
-				struct qeth_qdio_out_buffer *f = c;
-
-				QETH_CARD_TEXT(f->q->card, 5, "fp");
-				QETH_CARD_TEXT_(f->q->card, 5, "%lx", (long) f);
-				/* release here to avoid interleaving between
-				   outbound tasklet and inbound tasklet
-				   regarding notifications and lifecycle */
-				qeth_tx_complete_buf(c, forced_cleanup, 0);
-
-				c = f->next_pending;
-				WARN_ON_ONCE(head->next_pending != f);
-				head->next_pending = c;
-				kmem_cache_free(qeth_qdio_outbuf_cache, f);
-			} else {
-				head = c;
-				c = c->next_pending;
-			}
-
-		}
-	}
-}
-
 static void qeth_qdio_handle_aob(struct qeth_card *card,
 				 unsigned long phys_aob_addr)
 {
@@ -537,7 +500,7 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 		qeth_notify_skbs(buffer->q, buffer, notification);
 
 		/* Free dangling allocations. The attached skbs are handled by
-		 * qeth_cleanup_handled_pending().
+		 * qeth_tx_complete_pending_bufs().
 		 */
 		for (i = 0;
 		     i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card);
@@ -1488,14 +1451,35 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
 	atomic_set(&buf->state, QETH_QDIO_BUF_EMPTY);
 }
 
+static void qeth_tx_complete_pending_bufs(struct qeth_card *card,
+					  struct qeth_qdio_out_q *queue,
+					  bool drain)
+{
+	struct qeth_qdio_out_buffer *buf, *tmp;
+
+	list_for_each_entry_safe(buf, tmp, &queue->pending_bufs, list_entry) {
+		if (drain || atomic_read(&buf->state) == QETH_QDIO_BUF_EMPTY) {
+			QETH_CARD_TEXT(card, 5, "fp");
+			QETH_CARD_TEXT_(card, 5, "%lx", (long) buf);
+
+			qeth_tx_complete_buf(buf, drain, 0);
+
+			list_del(&buf->list_entry);
+			kmem_cache_free(qeth_qdio_outbuf_cache, buf);
+		}
+	}
+}
+
 static void qeth_drain_output_queue(struct qeth_qdio_out_q *q, bool free)
 {
 	int j;
 
+	qeth_tx_complete_pending_bufs(q->card, q, true);
+
 	for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) {
 		if (!q->bufs[j])
 			continue;
-		qeth_cleanup_handled_pending(q, j, 1);
+
 		qeth_clear_output_buffer(q, q->bufs[j], true, 0);
 		if (free) {
 			kmem_cache_free(qeth_qdio_outbuf_cache, q->bufs[j]);
@@ -2615,7 +2599,6 @@ static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx)
 	skb_queue_head_init(&newbuf->skb_list);
 	lockdep_set_class(&newbuf->skb_list.lock, &qdio_out_skb_queue_key);
 	newbuf->q = q;
-	newbuf->next_pending = q->bufs[bidx];
 	atomic_set(&newbuf->state, QETH_QDIO_BUF_EMPTY);
 	q->bufs[bidx] = newbuf;
 	return 0;
@@ -2697,6 +2680,7 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card)
 		card->qdio.out_qs[i] = queue;
 		queue->card = card;
 		queue->queue_no = i;
+		INIT_LIST_HEAD(&queue->pending_bufs);
 		spin_lock_init(&queue->lock);
 		timer_setup(&queue->timer, qeth_tx_completion_timer, 0);
 		queue->coalesce_usecs = QETH_TX_COALESCE_USECS;
@@ -6106,6 +6090,8 @@ static void qeth_iqd_tx_complete(struct qeth_qdio_out_q *queue,
 					qeth_schedule_recovery(card);
 				}
 
+				list_add(&buffer->list_entry,
+					 &queue->pending_bufs);
 				/* Skip clearing the buffer: */
 				return;
 			case QETH_QDIO_BUF_QAOB_OK:
@@ -6161,6 +6147,8 @@ static int qeth_tx_poll(struct napi_struct *napi, int budget)
 		unsigned int bytes = 0;
 		int completed;
 
+		qeth_tx_complete_pending_bufs(card, queue, false);
+
 		if (qeth_out_queue_is_empty(queue)) {
 			napi_complete(napi);
 			return 0;
@@ -6193,7 +6181,6 @@ static int qeth_tx_poll(struct napi_struct *napi, int budget)
 
 			qeth_handle_send_error(card, buffer, error);
 			qeth_iqd_tx_complete(queue, bidx, error, budget);
-			qeth_cleanup_handled_pending(queue, bidx, false);
 		}
 
 		netdev_tx_completed_queue(txq, packets, bytes);

From 3e83d467a08e25b27c44c885f511624a71c84f7c Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Tue, 9 Mar 2021 17:52:20 +0100
Subject: [PATCH 0447/1820] s390/qeth: schedule TX NAPI on QAOB completion

When a QAOB notifies us that a pending TX buffer has been delivered, the
actual TX completion processing by qeth_tx_complete_pending_bufs()
is done within the context of a TX NAPI instance. We shouldn't rely on
this instance being scheduled by some other TX event, but just do it
ourselves.

qeth_qdio_handle_aob() is called from qeth_poll(), ie. our main NAPI
instance. To avoid touching the TX queue's NAPI instance
before/after it is (un-)registered, reorder the code in qeth_open()
and qeth_stop() accordingly.

Fixes: 0da9581ddb0f ("qeth: exploit asynchronous delivery of storage blocks")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 3763cd6d14f8..d0a56afec028 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -470,6 +470,7 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 	struct qaob *aob;
 	struct qeth_qdio_out_buffer *buffer;
 	enum iucv_tx_notify notification;
+	struct qeth_qdio_out_q *queue;
 	unsigned int i;
 
 	aob = (struct qaob *) phys_to_virt(phys_aob_addr);
@@ -512,7 +513,9 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 			buffer->is_header[i] = 0;
 		}
 
+		queue = buffer->q;
 		atomic_set(&buffer->state, QETH_QDIO_BUF_EMPTY);
+		napi_schedule(&queue->napi);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -7235,9 +7238,7 @@ int qeth_open(struct net_device *dev)
 	card->data.state = CH_STATE_UP;
 	netif_tx_start_all_queues(dev);
 
-	napi_enable(&card->napi);
 	local_bh_disable();
-	napi_schedule(&card->napi);
 	if (IS_IQD(card)) {
 		struct qeth_qdio_out_q *queue;
 		unsigned int i;
@@ -7249,8 +7250,12 @@ int qeth_open(struct net_device *dev)
 			napi_schedule(&queue->napi);
 		}
 	}
+
+	napi_enable(&card->napi);
+	napi_schedule(&card->napi);
 	/* kick-start the NAPI softirq: */
 	local_bh_enable();
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(qeth_open);
@@ -7260,6 +7265,11 @@ int qeth_stop(struct net_device *dev)
 	struct qeth_card *card = dev->ml_priv;
 
 	QETH_CARD_TEXT(card, 4, "qethstop");
+
+	napi_disable(&card->napi);
+	cancel_delayed_work_sync(&card->buffer_reclaim_work);
+	qdio_stop_irq(CARD_DDEV(card));
+
 	if (IS_IQD(card)) {
 		struct qeth_qdio_out_q *queue;
 		unsigned int i;
@@ -7280,10 +7290,6 @@ int qeth_stop(struct net_device *dev)
 		netif_tx_disable(dev);
 	}
 
-	napi_disable(&card->napi);
-	cancel_delayed_work_sync(&card->buffer_reclaim_work);
-	qdio_stop_irq(CARD_DDEV(card));
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(qeth_stop);

From 7eefda7f353ef86ad82a2dc8329e8a3538c08ab6 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Tue, 9 Mar 2021 17:52:21 +0100
Subject: [PATCH 0448/1820] s390/qeth: fix notification for pending buffers
 during teardown

The cited commit reworked the state machine for pending TX buffers.
In qeth_iqd_tx_complete() it turned PENDING into a transient state, and
uses NEED_QAOB for buffers that get parked while waiting for their QAOB
completion.

But it missed to adjust the check in qeth_tx_complete_buf(). So if
qeth_tx_complete_pending_bufs() is called during teardown to drain
the parked TX buffers, we no longer raise a notification for af_iucv.

Instead of updating the checked state, just move this code into
qeth_tx_complete_pending_bufs() itself. This also gets rid of the
special-case in the common TX completion path.

Fixes: 8908f36d20d8 ("s390/qeth: fix af_iucv notification race")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index d0a56afec028..a814698387bc 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1390,9 +1390,6 @@ static void qeth_tx_complete_buf(struct qeth_qdio_out_buffer *buf, bool error,
 	struct qeth_qdio_out_q *queue = buf->q;
 	struct sk_buff *skb;
 
-	if (atomic_read(&buf->state) == QETH_QDIO_BUF_PENDING)
-		qeth_notify_skbs(queue, buf, TX_NOTIFY_GENERALERROR);
-
 	/* Empty buffer? */
 	if (buf->next_element_to_fill == 0)
 		return;
@@ -1465,6 +1462,9 @@ static void qeth_tx_complete_pending_bufs(struct qeth_card *card,
 			QETH_CARD_TEXT(card, 5, "fp");
 			QETH_CARD_TEXT_(card, 5, "%lx", (long) buf);
 
+			if (drain)
+				qeth_notify_skbs(queue, buf,
+						 TX_NOTIFY_GENERALERROR);
 			qeth_tx_complete_buf(buf, drain, 0);
 
 			list_del(&buf->list_entry);

From bd73758803c2eedc037c2268b65a19542a832594 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Tue, 9 Mar 2021 08:39:39 +0000
Subject: [PATCH 0449/1820] powerpc: Fix missing declaration of
 [en/dis]able_kernel_vsx()

Add stub instances of enable_kernel_vsx() and disable_kernel_vsx()
when CONFIG_VSX is not set, to avoid following build failure.

  CC [M]  drivers/gpu/drm/amd/amdgpu/../display/dc/calcs/dcn_calcs.o
  In file included from ./drivers/gpu/drm/amd/amdgpu/../display/dc/dm_services_types.h:29,
                   from ./drivers/gpu/drm/amd/amdgpu/../display/dc/dm_services.h:37,
                   from drivers/gpu/drm/amd/amdgpu/../display/dc/calcs/dcn_calcs.c:27:
  drivers/gpu/drm/amd/amdgpu/../display/dc/calcs/dcn_calcs.c: In function 'dcn_bw_apply_registry_override':
  ./drivers/gpu/drm/amd/amdgpu/../display/dc/os_types.h:64:3: error: implicit declaration of function 'enable_kernel_vsx'; did you mean 'enable_kernel_fp'? [-Werror=implicit-function-declaration]
     64 |   enable_kernel_vsx(); \
        |   ^~~~~~~~~~~~~~~~~
  drivers/gpu/drm/amd/amdgpu/../display/dc/calcs/dcn_calcs.c:640:2: note: in expansion of macro 'DC_FP_START'
    640 |  DC_FP_START();
        |  ^~~~~~~~~~~
  ./drivers/gpu/drm/amd/amdgpu/../display/dc/os_types.h:75:3: error: implicit declaration of function 'disable_kernel_vsx'; did you mean 'disable_kernel_fp'? [-Werror=implicit-function-declaration]
     75 |   disable_kernel_vsx(); \
        |   ^~~~~~~~~~~~~~~~~~
  drivers/gpu/drm/amd/amdgpu/../display/dc/calcs/dcn_calcs.c:676:2: note: in expansion of macro 'DC_FP_END'
    676 |  DC_FP_END();
        |  ^~~~~~~~~
  cc1: some warnings being treated as errors
  make[5]: *** [drivers/gpu/drm/amd/amdgpu/../display/dc/calcs/dcn_calcs.o] Error 1

This works because the caller is checking if VSX is available using
cpu_has_feature():

  #define DC_FP_START() { \
  	if (cpu_has_feature(CPU_FTR_VSX_COMP)) { \
  		preempt_disable(); \
  		enable_kernel_vsx(); \
  	} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) { \
  		preempt_disable(); \
  		enable_kernel_altivec(); \
  	} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) { \
  		preempt_disable(); \
  		enable_kernel_fp(); \
  	} \

When CONFIG_VSX is not selected, cpu_has_feature(CPU_FTR_VSX_COMP)
constant folds to 'false' so the call to enable_kernel_vsx() is
discarded and the build succeeds.

Fixes: 16a9dea110a6 ("amdgpu: Enable initial DCN support on POWER")
Cc: stable@vger.kernel.org # v5.6+
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
[mpe: Incorporate some discussion comments into the change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/8d7d285a027e9d21f5ff7f850fa71a2655b0c4af.1615279170.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/include/asm/switch_to.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index fdab93428372..9d1fbd8be1c7 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -71,6 +71,16 @@ static inline void disable_kernel_vsx(void)
 {
 	msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
 }
+#else
+static inline void enable_kernel_vsx(void)
+{
+	BUILD_BUG();
+}
+
+static inline void disable_kernel_vsx(void)
+{
+	BUILD_BUG();
+}
 #endif
 
 #ifdef CONFIG_SPE

From e5e8b80d352ec999d2bba3ea584f541c83f4ca3f Mon Sep 17 00:00:00 2001
From: Rob Gardner <rob.gardner@oracle.com>
Date: Sun, 28 Feb 2021 22:48:16 -0700
Subject: [PATCH 0450/1820] sparc64: Fix opcode filtering in handling of no
 fault loads

is_no_fault_exception() has two bugs which were discovered via random
opcode testing with stress-ng. Both are caused by improper filtering
of opcodes.

The first bug can be triggered by a floating point store with a no-fault
ASI, for instance "sta %f0, [%g0] #ASI_PNF", opcode C1A01040.

The code first tests op3[5] (0x1000000), which denotes a floating
point instruction, and then tests op3[2] (0x200000), which denotes a
store instruction. But these bits are not mutually exclusive, and the
above mentioned opcode has both bits set. The intent is to filter out
stores, so the test for stores must be done first in order to have
any effect.

The second bug can be triggered by a floating point load with one of
the invalid ASI values 0x8e or 0x8f, which pass this check in
is_no_fault_exception():
     if ((asi & 0xf2) == ASI_PNF)

An example instruction is "ldqa [%l7 + %o7] #ASI 0x8f, %f38",
opcode CF95D1EF. Asi values greater than 0x8b (ASI_SNFL) are fatal
in handle_ldf_stq(), and is_no_fault_exception() must not allow these
invalid asi values to make it that far.

In both of these cases, handle_ldf_stq() reacts by calling
sun4v_data_access_exception() or spitfire_data_access_exception(),
which call is_no_fault_exception() and results in an infinite
recursion.

Signed-off-by: Rob Gardner <rob.gardner@oracle.com>
Tested-by: Anatoly Pugachev <matorola@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/kernel/traps_64.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index d92e5eaa4c1d..a850dccd78ea 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -275,14 +275,13 @@ bool is_no_fault_exception(struct pt_regs *regs)
 			asi = (regs->tstate >> 24); /* saved %asi       */
 		else
 			asi = (insn >> 5);	    /* immediate asi    */
-		if ((asi & 0xf2) == ASI_PNF) {
-			if (insn & 0x1000000) {     /* op3[5:4]=3       */
-				handle_ldf_stq(insn, regs);
-				return true;
-			} else if (insn & 0x200000) { /* op3[2], stores */
+		if ((asi & 0xf6) == ASI_PNF) {
+			if (insn & 0x200000)        /* op3[2], stores   */
 				return false;
-			}
-			handle_ld_nf(insn, regs);
+			if (insn & 0x1000000)       /* op3[5:4]=3 (fp)  */
+				handle_ldf_stq(insn, regs);
+			else
+				handle_ld_nf(insn, regs);
 			return true;
 		}
 	}

From 69264b4a43aff7307283e2bae29e9305ab6b7d47 Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Mon, 8 Mar 2021 09:51:26 +0000
Subject: [PATCH 0451/1820] sparc: sparc64_defconfig: remove duplicate CONFIGs

After my patch there is CONFIG_ATA defined twice.
Remove the duplicate one.
Same problem for CONFIG_HAPPYMEAL, except I added as builtin for boot
test with NFS.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Fixes: a57cdeb369ef ("sparc: sparc64_defconfig: add necessary configs for qemu")
Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/configs/sparc64_defconfig | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index 148f44b33890..12a4fb0bd52a 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -93,7 +93,7 @@ CONFIG_NETDEVICES=y
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=m
 CONFIG_SUNLANCE=m
-CONFIG_HAPPYMEAL=m
+CONFIG_HAPPYMEAL=y
 CONFIG_SUNGEM=m
 CONFIG_SUNVNET=m
 CONFIG_LDMVSW=m
@@ -234,9 +234,7 @@ CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRC16=m
 CONFIG_LIBCRC32C=m
 CONFIG_VCC=m
-CONFIG_ATA=y
 CONFIG_PATA_CMD64X=y
-CONFIG_HAPPYMEAL=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_DEVTMPFS=y

From 6dd4879f59b0a0679ed8c3ebaff3d79f37930778 Mon Sep 17 00:00:00 2001
From: Heinrich Schuchardt <xypron.glpk@gmx.de>
Date: Sat, 6 Mar 2021 06:48:01 +0100
Subject: [PATCH 0452/1820] RISC-V: correct enum sbi_ext_rfence_fid

The constants in enum sbi_ext_rfence_fid should match the SBI
specification. See
https://github.com/riscv/riscv-sbi-doc/blob/master/riscv-sbi.adoc#78-function-listing

| Function Name               | FID | EID
| sbi_remote_fence_i          |   0 | 0x52464E43
| sbi_remote_sfence_vma       |   1 | 0x52464E43
| sbi_remote_sfence_vma_asid  |   2 | 0x52464E43
| sbi_remote_hfence_gvma_vmid |   3 | 0x52464E43
| sbi_remote_hfence_gvma      |   4 | 0x52464E43
| sbi_remote_hfence_vvma_asid |   5 | 0x52464E43
| sbi_remote_hfence_vvma      |   6 | 0x52464E43

Fixes: ecbacc2a3efd ("RISC-V: Add SBI v0.2 extension definitions")
Reported-by: Sean Anderson <seanga2@gmail.com>
Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Atish Patra <atish.patra@wdc.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/include/asm/sbi.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 99895d9c3bdd..d7027411dde8 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -51,10 +51,10 @@ enum sbi_ext_rfence_fid {
 	SBI_EXT_RFENCE_REMOTE_FENCE_I = 0,
 	SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
 	SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
-	SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
 	SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID,
-	SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
+	SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
 	SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID,
+	SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
 };
 
 enum sbi_ext_hsm_fid {

From 030f1dfa855054db5d845eca7f04c8cfda1c9f51 Mon Sep 17 00:00:00 2001
From: Nanyong Sun <sunnanyong@huawei.com>
Date: Fri, 5 Mar 2021 19:33:24 +0800
Subject: [PATCH 0453/1820] riscv: traps: Fix no prototype warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix all W=1 compilation warnings:'no previous prototype for' in arch/riscv/kernel/traps.c:
arch/riscv/kernel/traps.c:96:15: warning: no previous prototype for ‘do_trap_unknown’ [-Wmissing-prototypes]
   96 | DO_ERROR_INFO(do_trap_unknown,
      |               ^~~~~~~~~~~~~~~
arch/riscv/kernel/traps.c:91:27: note: in definition of macro ‘DO_ERROR_INFO’
   91 | asmlinkage __visible void name(struct pt_regs *regs)   \
      |                           ^~~~
arch/riscv/kernel/traps.c:98:15: warning: no previous prototype for ‘do_trap_insn_misaligned’ [-Wmissing-prototypes]
   98 | DO_ERROR_INFO(do_trap_insn_misaligned,
      |               ^~~~~~~~~~~~~~~~~~~~~~~
arch/riscv/kernel/traps.c:91:27: note: in definition of macro ‘DO_ERROR_INFO’
   91 | asmlinkage __visible void name(struct pt_regs *regs)   \
      |                           ^~~~
arch/riscv/kernel/traps.c:100:15: warning: no previous prototype for ‘do_trap_insn_fault’ [-Wmissing-prototypes]
...

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Nanyong Sun <sunnanyong@huawei.com>
[Palmer: fix checkpatch warnings]
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/include/asm/asm-prototypes.h | 16 ++++++++++++++++
 arch/riscv/kernel/traps.c               |  1 +
 2 files changed, 17 insertions(+)

diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index 27e005fca584..2a652b0c987d 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -9,4 +9,20 @@ long long __lshrti3(long long a, int b);
 long long __ashrti3(long long a, int b);
 long long __ashlti3(long long a, int b);
 
+
+#define DECLARE_DO_ERROR_INFO(name)	asmlinkage void name(struct pt_regs *regs)
+
+DECLARE_DO_ERROR_INFO(do_trap_unknown);
+DECLARE_DO_ERROR_INFO(do_trap_insn_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_insn_fault);
+DECLARE_DO_ERROR_INFO(do_trap_insn_illegal);
+DECLARE_DO_ERROR_INFO(do_trap_load_fault);
+DECLARE_DO_ERROR_INFO(do_trap_load_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_store_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_store_fault);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_u);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
+DECLARE_DO_ERROR_INFO(do_trap_break);
+
 #endif /* _ASM_RISCV_PROTOTYPES_H */
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 3ed2c23601a0..0879b5df11b9 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/irq.h>
 
+#include <asm/asm-prototypes.h>
 #include <asm/bug.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>

From 004570c3796bfe454a9cdfb9ab5d3ea48371fe48 Mon Sep 17 00:00:00 2001
From: Nanyong Sun <sunnanyong@huawei.com>
Date: Fri, 5 Mar 2021 19:33:25 +0800
Subject: [PATCH 0454/1820] riscv: irq: Fix no prototype warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following W=1 kernel compilation warning:
arch/riscv/kernel/irq.c:19:13: warning: no previous prototype for ‘init_IRQ’ [-Wmissing-prototypes]
   19 | void __init init_IRQ(void)
      |             ^~~~~~~~

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Nanyong Sun <sunnanyong@huawei.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/include/asm/irq.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h
index 9807ad164015..e4c435509983 100644
--- a/arch/riscv/include/asm/irq.h
+++ b/arch/riscv/include/asm/irq.h
@@ -12,4 +12,6 @@
 
 #include <asm-generic/irq.h>
 
+extern void __init init_IRQ(void);
+
 #endif /* _ASM_RISCV_IRQ_H */

From 56a6c37f6e3994cba01609768f5a215c85bd2f85 Mon Sep 17 00:00:00 2001
From: Nanyong Sun <sunnanyong@huawei.com>
Date: Fri, 5 Mar 2021 19:33:26 +0800
Subject: [PATCH 0455/1820] riscv: sbi: Fix comment of __sbi_set_timer_v01

Fix the comment of __sbi_set_timer_v01, the function name in comment
is missing '__'

Signed-off-by: Nanyong Sun <sunnanyong@huawei.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/kernel/sbi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index f4a7db3d309e..d3bf756321a5 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -116,7 +116,7 @@ void sbi_clear_ipi(void)
 EXPORT_SYMBOL(sbi_clear_ipi);
 
 /**
- * sbi_set_timer_v01() - Program the timer for next timer event.
+ * __sbi_set_timer_v01() - Program the timer for next timer event.
  * @stime_value: The value after which next timer event should fire.
  *
  * Return: None

From e06f4ce1d4c63799eff9d3544b3f7468d5409f3e Mon Sep 17 00:00:00 2001
From: Nanyong Sun <sunnanyong@huawei.com>
Date: Fri, 5 Mar 2021 19:33:27 +0800
Subject: [PATCH 0456/1820] riscv: ptrace: Fix no prototype warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following W=1 kernel compilation warnings:
arch/riscv/kernel/ftrace.c:186:6: warning: no previous prototype for ‘prepare_ftrace_return’ [-Wmissing-prototypes]
  186 | void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
      |      ^~~~~~~~~~~~~~~~~~~~~
arch/riscv/kernel/ptrace.c:239:15: warning: no previous prototype for ‘do_syscall_trace_enter’ [-Wmissing-prototypes]
  239 | __visible int do_syscall_trace_enter(struct pt_regs *regs)
      |               ^~~~~~~~~~~~~~~~~~~~~~
arch/riscv/kernel/ptrace.c:262:16: warning: no previous prototype for ‘do_syscall_trace_exit’ [-Wmissing-prototypes]
  262 | __visible void do_syscall_trace_exit(struct pt_regs *regs)
      |                ^~~~~~~~~~~~~~~~~~~~~

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Nanyong Sun <sunnanyong@huawei.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/include/asm/ptrace.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
index cb4abb639e8d..09ad4e923510 100644
--- a/arch/riscv/include/asm/ptrace.h
+++ b/arch/riscv/include/asm/ptrace.h
@@ -119,6 +119,11 @@ extern int regs_query_register_offset(const char *name);
 extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 					       unsigned int n);
 
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer);
+int do_syscall_trace_enter(struct pt_regs *regs);
+void do_syscall_trace_exit(struct pt_regs *regs);
+
 /**
  * regs_get_register() - get register value from its offset
  * @regs:	pt_regs from which register value is gotten

From db2a8f9256e9a2a931edb83622d81ca73c6c8c6a Mon Sep 17 00:00:00 2001
From: Nanyong Sun <sunnanyong@huawei.com>
Date: Fri, 5 Mar 2021 19:33:28 +0800
Subject: [PATCH 0457/1820] riscv: time: Fix no prototype for time_init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following W=1 compilation warning:
arch/riscv/kernel/time.c:16:13: warning: no previous prototype for ‘time_init’ [-Wmissing-prototypes]
   16 | void __init time_init(void)
      |             ^~~~~~~~~

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Nanyong Sun <sunnanyong@huawei.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/include/asm/timex.h | 2 ++
 arch/riscv/kernel/time.c       | 1 +
 2 files changed, 3 insertions(+)

diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
index 81de51e6aa32..507cae273bc6 100644
--- a/arch/riscv/include/asm/timex.h
+++ b/arch/riscv/include/asm/timex.h
@@ -88,4 +88,6 @@ static inline int read_current_timer(unsigned long *timer_val)
 	return 0;
 }
 
+extern void time_init(void);
+
 #endif /* _ASM_RISCV_TIMEX_H */
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
index 8a5cf99c0776..1b432264f7ef 100644
--- a/arch/riscv/kernel/time.c
+++ b/arch/riscv/kernel/time.c
@@ -9,6 +9,7 @@
 #include <linux/delay.h>
 #include <asm/sbi.h>
 #include <asm/processor.h>
+#include <asm/timex.h>
 
 unsigned long riscv_timebase;
 EXPORT_SYMBOL_GPL(riscv_timebase);

From a6a58ecf98c3f6d95123ee3e66ccb6f7672c6e68 Mon Sep 17 00:00:00 2001
From: Nanyong Sun <sunnanyong@huawei.com>
Date: Fri, 5 Mar 2021 19:33:29 +0800
Subject: [PATCH 0458/1820] riscv: syscall_table: Reduce W=1 compilation
 warnings noise
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Building riscv syscall table with W=1 throws the warning as
following pattern:
arch/riscv/kernel/syscall_table.c:14:36: warning: initialized field overwritten [-Woverride-init]
   14 | #define __SYSCALL(nr, call) [nr] = (call),
      |                                    ^
./include/uapi/asm-generic/unistd.h:29:37: note: in expansion of macro ‘__SYSCALL’
   29 | #define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys)
      |                                     ^~~~~~~~~
./include/uapi/asm-generic/unistd.h:34:1: note: in expansion of macro ‘__SC_COMP’
   34 | __SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup)
      | ^~~~~~~~~
arch/riscv/kernel/syscall_table.c:14:36: note: (near initialization for ‘sys_call_table[0]’)
   14 | #define __SYSCALL(nr, call) [nr] = (call),
      |                                    ^
./include/uapi/asm-generic/unistd.h:29:37: note: in expansion of macro ‘__SYSCALL’
   29 | #define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys)
      |                                     ^~~~~~~~~
./include/uapi/asm-generic/unistd.h:34:1: note: in expansion of macro ‘__SC_COMP’
   34 | __SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup)
      | ^~~~~~~~~
arch/riscv/kernel/syscall_table.c:14:36: warning: initialized field overwritten [-Woverride-init]
...

Since we intentionally build the syscall tables this way,ignore the warning.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Nanyong Sun <sunnanyong@huawei.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/kernel/Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 3dc0abde988a..647a47f5484a 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -8,6 +8,7 @@ CFLAGS_REMOVE_ftrace.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_patch.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
 endif
+CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
 
 extra-y += head.o
 extra-y += vmlinux.lds

From 86b276c1ddedfbcc0be708e73d82ce1fb2298768 Mon Sep 17 00:00:00 2001
From: Nanyong Sun <sunnanyong@huawei.com>
Date: Fri, 5 Mar 2021 19:33:30 +0800
Subject: [PATCH 0459/1820] riscv: process: Fix no prototype for show_regs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Include header file to fix the following W=1 compilation warning:
arch/riscv/kernel/process.c:78:6: warning: no previous prototype for ‘show_regs’ [-Wmissing-prototypes]
   78 | void show_regs(struct pt_regs *regs)
      |      ^~~~~~~~~

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Nanyong Sun <sunnanyong@huawei.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/kernel/process.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 6f728e731bed..f9cd57c9c67d 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -10,6 +10,7 @@
 #include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/tick.h>
 #include <linux/ptrace.h>

From 288f6775a08913e9cb5f5ae0a43c105b725be0c8 Mon Sep 17 00:00:00 2001
From: Nanyong Sun <sunnanyong@huawei.com>
Date: Fri, 5 Mar 2021 19:33:31 +0800
Subject: [PATCH 0460/1820] riscv: ftrace: Use ftrace_get_regs helper

Use ftrace_get_regs() helper call to get pt_regs from ftrace_regs struct,
this makes the code simpler.

Signed-off-by: Nanyong Sun <sunnanyong@huawei.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/kernel/probes/ftrace.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c
index e6372490aa0b..2dfb33fdac74 100644
--- a/arch/riscv/kernel/probes/ftrace.c
+++ b/arch/riscv/kernel/probes/ftrace.c
@@ -4,37 +4,39 @@
 
 /* Ftrace callback handler for kprobes -- called under preepmt disabed */
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-			   struct ftrace_ops *ops, struct ftrace_regs *regs)
+			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
 	struct kprobe *p;
+	struct pt_regs *regs;
 	struct kprobe_ctlblk *kcb;
 
 	p = get_kprobe((kprobe_opcode_t *)ip);
 	if (unlikely(!p) || kprobe_disabled(p))
 		return;
 
+	regs = ftrace_get_regs(fregs);
 	kcb = get_kprobe_ctlblk();
 	if (kprobe_running()) {
 		kprobes_inc_nmissed_count(p);
 	} else {
-		unsigned long orig_ip = instruction_pointer(&(regs->regs));
+		unsigned long orig_ip = instruction_pointer(regs);
 
-		instruction_pointer_set(&(regs->regs), ip);
+		instruction_pointer_set(regs, ip);
 
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		if (!p->pre_handler || !p->pre_handler(p, &(regs->regs))) {
+		if (!p->pre_handler || !p->pre_handler(p, regs)) {
 			/*
 			 * Emulate singlestep (and also recover regs->pc)
 			 * as if there is a nop
 			 */
-			instruction_pointer_set(&(regs->regs),
+			instruction_pointer_set(regs,
 				(unsigned long)p->addr + MCOUNT_INSN_SIZE);
 			if (unlikely(p->post_handler)) {
 				kcb->kprobe_status = KPROBE_HIT_SSDONE;
-				p->post_handler(p, &(regs->regs), 0);
+				p->post_handler(p, regs, 0);
 			}
-			instruction_pointer_set(&(regs->regs), orig_ip);
+			instruction_pointer_set(regs, orig_ip);
 		}
 
 		/*

From 0d7588ab9ef98bad3b52ad0b91291e8258853cc1 Mon Sep 17 00:00:00 2001
From: Nanyong Sun <sunnanyong@huawei.com>
Date: Fri, 5 Mar 2021 19:33:32 +0800
Subject: [PATCH 0461/1820] riscv: process: Fix no prototype for
 arch_dup_task_struct
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following W=1 compilation warning:
arch/riscv/kernel/process.c:114:5: warning: no previous prototype for ‘arch_dup_task_struct’ [-Wmissing-prototypes]
  114 | int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
      |     ^~~~~~~~~~~~~~~~~~~~

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Nanyong Sun <sunnanyong@huawei.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/include/asm/processor.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 3a240037bde2..021ed64ee608 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -71,6 +71,7 @@ int riscv_of_processor_hartid(struct device_node *node);
 int riscv_of_parent_hartid(struct device_node *node);
 
 extern void riscv_fill_hwcap(void);
+extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 
 #endif /* __ASSEMBLY__ */
 

From 2d8aaa1720c6128ce263a2afcd3f8ee2e5551af8 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 8 Mar 2021 11:40:30 -0800
Subject: [PATCH 0462/1820] Input: n64joy - fix return value check in
 n64joy_probe()

In case of error, the function devm_platform_ioremap_resource()
returns ERR_PTR() and never returns NULL. The NULL test in the
return value check should be replaced with IS_ERR().

Fixes: 3bdffa8ffb45 ("Input: Add N64 controller driver")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Lauri Kasanen <cand@gmx.com>
Link: https://lore.kernel.org/r/20210308122856.2177071-1-weiyongjun1@huawei.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/n64joy.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/joystick/n64joy.c b/drivers/input/joystick/n64joy.c
index 8bcc529942bc..9dbca366613e 100644
--- a/drivers/input/joystick/n64joy.c
+++ b/drivers/input/joystick/n64joy.c
@@ -252,8 +252,8 @@ static int __init n64joy_probe(struct platform_device *pdev)
 	mutex_init(&priv->n64joy_mutex);
 
 	priv->reg_base = devm_platform_ioremap_resource(pdev, 0);
-	if (!priv->reg_base) {
-		err = -EINVAL;
+	if (IS_ERR(priv->reg_base)) {
+		err = PTR_ERR(priv->reg_base);
 		goto fail;
 	}
 

From 16db6b532fa4e0397bf33e04368408fd15f0dd90 Mon Sep 17 00:00:00 2001
From: Oded Gabbay <ogabbay@kernel.org>
Date: Tue, 16 Feb 2021 21:49:30 +0200
Subject: [PATCH 0463/1820] habanalabs: mark hl_eq_inc_ptr() as static

hl_eq_inc_ptr() is not called from anywhere outside irq.c so mark
it as static

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/misc/habanalabs/common/irq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c
index de53fb5f978a..44a0522b59b9 100644
--- a/drivers/misc/habanalabs/common/irq.c
+++ b/drivers/misc/habanalabs/common/irq.c
@@ -47,7 +47,7 @@ inline u32 hl_cq_inc_ptr(u32 ptr)
  * Increment ptr by 1. If it reaches the number of event queue
  * entries, set it to 0
  */
-inline u32 hl_eq_inc_ptr(u32 ptr)
+static inline u32 hl_eq_inc_ptr(u32 ptr)
 {
 	ptr++;
 	if (unlikely(ptr == HL_EQ_LENGTH))

From bd0c48e53d2fadcc7f62056c46a05718370b7939 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 16 Feb 2021 16:08:28 +0100
Subject: [PATCH 0464/1820] drivers: habanalabs: remove unused dentry pointer
 for debugfs files

The dentry for the created debugfs file was being saved, but never used
anywhere.  As the pointer isn't needed for anything, and the debugfs
files are being properly removed by removing the parent directory,
remove the saved pointer as well, saving a tiny bit of memory and logic.

Cc: Oded Gabbay <ogabbay@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Tomer Tayar <ttayar@habana.ai>
Cc: Moti Haimovski <mhaimovski@habana.ai>
Cc: Omer Shpigelman <oshpigelman@habana.ai>
Cc: Ofir Bitton <obitton@habana.ai>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/misc/habanalabs/common/debugfs.c    | 5 +----
 drivers/misc/habanalabs/common/habanalabs.h | 2 --
 2 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
index df847a6d19f4..9f19bee7b592 100644
--- a/drivers/misc/habanalabs/common/debugfs.c
+++ b/drivers/misc/habanalabs/common/debugfs.c
@@ -992,7 +992,6 @@ void hl_debugfs_add_device(struct hl_device *hdev)
 	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
 	int count = ARRAY_SIZE(hl_debugfs_list);
 	struct hl_debugfs_entry *entry;
-	struct dentry *ent;
 	int i;
 
 	dev_entry->hdev = hdev;
@@ -1105,13 +1104,11 @@ void hl_debugfs_add_device(struct hl_device *hdev)
 				&hl_security_violations_fops);
 
 	for (i = 0, entry = dev_entry->entry_arr ; i < count ; i++, entry++) {
-
-		ent = debugfs_create_file(hl_debugfs_list[i].name,
+		debugfs_create_file(hl_debugfs_list[i].name,
 					0444,
 					dev_entry->root,
 					entry,
 					&hl_debugfs_fops);
-		entry->dent = ent;
 		entry->info_ent = &hl_debugfs_list[i];
 		entry->dev_entry = dev_entry;
 	}
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index d933878b24d1..4b321e4f8059 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -1465,12 +1465,10 @@ struct hl_info_list {
 
 /**
  * struct hl_debugfs_entry - debugfs dentry wrapper.
- * @dent: base debugfs entry structure.
  * @info_ent: dentry realted ops.
  * @dev_entry: ASIC specific debugfs manager.
  */
 struct hl_debugfs_entry {
-	struct dentry			*dent;
 	const struct hl_info_list	*info_ent;
 	struct hl_dbg_device_entry	*dev_entry;
 };

From 27ac5aada024e0821c86540ad18f37edadd77d5e Mon Sep 17 00:00:00 2001
From: Tomer Tayar <ttayar@habana.ai>
Date: Fri, 19 Feb 2021 14:05:33 +0200
Subject: [PATCH 0465/1820] habanalabs: Call put_pid() when releasing control
 device

The refcount of the "hl_fpriv" structure is not used for the control
device, and thus hl_hpriv_put() is not called when releasing this
device.
This results with no call to put_pid(), so add it explicitly in
hl_device_release_ctrl().

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/misc/habanalabs/common/device.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 15fcb5c31c4b..9ecd805f0e88 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -117,6 +117,8 @@ static int hl_device_release_ctrl(struct inode *inode, struct file *filp)
 	list_del(&hpriv->dev_node);
 	mutex_unlock(&hdev->fpriv_list_lock);
 
+	put_pid(hpriv->taskpid);
+
 	kfree(hpriv);
 
 	return 0;

From ffd123fe839700366ea79b19ac3683bf56817372 Mon Sep 17 00:00:00 2001
From: Tomer Tayar <ttayar@habana.ai>
Date: Mon, 1 Feb 2021 19:44:34 +0200
Subject: [PATCH 0466/1820] habanalabs: Disable file operations after device is
 removed

A device can be removed from the PCI subsystem while a process holds the
file descriptor opened.
In such a case, the driver attempts to kill the process, but as it is
still possible that the process will be alive after this step, the
device removal will complete, and we will end up with a process object
that points to a device object which was already released.

To prevent the usage of this released device object, disable the
following file operations for this process object, and avoid the cleanup
steps when the file descriptor is eventually closed.
The latter is just a best effort, as memory leak will occur.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/misc/habanalabs/common/device.c       | 40 ++++++++++++++++---
 .../misc/habanalabs/common/habanalabs_ioctl.c | 12 ++++++
 2 files changed, 46 insertions(+), 6 deletions(-)

diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 9ecd805f0e88..334009e83823 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -93,12 +93,19 @@ void hl_hpriv_put(struct hl_fpriv *hpriv)
 static int hl_device_release(struct inode *inode, struct file *filp)
 {
 	struct hl_fpriv *hpriv = filp->private_data;
+	struct hl_device *hdev = hpriv->hdev;
+
+	filp->private_data = NULL;
+
+	if (!hdev) {
+		pr_crit("Closing FD after device was removed. Memory leak will occur and it is advised to reboot.\n");
+		put_pid(hpriv->taskpid);
+		return 0;
+	}
 
 	hl_cb_mgr_fini(hpriv->hdev, &hpriv->cb_mgr);
 	hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);
 
-	filp->private_data = NULL;
-
 	hl_hpriv_put(hpriv);
 
 	return 0;
@@ -107,16 +114,19 @@ static int hl_device_release(struct inode *inode, struct file *filp)
 static int hl_device_release_ctrl(struct inode *inode, struct file *filp)
 {
 	struct hl_fpriv *hpriv = filp->private_data;
-	struct hl_device *hdev;
+	struct hl_device *hdev = hpriv->hdev;
 
 	filp->private_data = NULL;
 
-	hdev = hpriv->hdev;
+	if (!hdev) {
+		pr_err("Closing FD after device was removed\n");
+		goto out;
+	}
 
 	mutex_lock(&hdev->fpriv_list_lock);
 	list_del(&hpriv->dev_node);
 	mutex_unlock(&hdev->fpriv_list_lock);
-
+out:
 	put_pid(hpriv->taskpid);
 
 	kfree(hpriv);
@@ -136,8 +146,14 @@ static int hl_device_release_ctrl(struct inode *inode, struct file *filp)
 static int hl_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct hl_fpriv *hpriv = filp->private_data;
+	struct hl_device *hdev = hpriv->hdev;
 	unsigned long vm_pgoff;
 
+	if (!hdev) {
+		pr_err_ratelimited("Trying to mmap after device was removed! Please close FD\n");
+		return -ENODEV;
+	}
+
 	vm_pgoff = vma->vm_pgoff;
 	vma->vm_pgoff = HL_MMAP_OFFSET_VALUE_GET(vm_pgoff);
 
@@ -885,6 +901,16 @@ wait_for_processes:
 	return -EBUSY;
 }
 
+static void device_disable_open_processes(struct hl_device *hdev)
+{
+	struct hl_fpriv *hpriv;
+
+	mutex_lock(&hdev->fpriv_list_lock);
+	list_for_each_entry(hpriv, &hdev->fpriv_list, dev_node)
+		hpriv->hdev = NULL;
+	mutex_unlock(&hdev->fpriv_list_lock);
+}
+
 /*
  * hl_device_reset - reset the device
  *
@@ -1558,8 +1584,10 @@ void hl_device_fini(struct hl_device *hdev)
 		HL_PENDING_RESET_LONG_SEC);
 
 	rc = device_kill_open_processes(hdev, HL_PENDING_RESET_LONG_SEC);
-	if (rc)
+	if (rc) {
 		dev_crit(hdev->dev, "Failed to kill all open processes\n");
+		device_disable_open_processes(hdev);
+	}
 
 	hl_cb_pool_fini(hdev);
 
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index 03af61cecd37..083a30969c5f 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -5,6 +5,8 @@
  * All Rights Reserved.
  */
 
+#define pr_fmt(fmt)	"habanalabs: " fmt
+
 #include <uapi/misc/habanalabs.h>
 #include "habanalabs.h"
 
@@ -682,6 +684,11 @@ long hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 	const struct hl_ioctl_desc *ioctl = NULL;
 	unsigned int nr = _IOC_NR(cmd);
 
+	if (!hdev) {
+		pr_err_ratelimited("Sending ioctl after device was removed! Please close FD\n");
+		return -ENODEV;
+	}
+
 	if ((nr >= HL_COMMAND_START) && (nr < HL_COMMAND_END)) {
 		ioctl = &hl_ioctls[nr];
 	} else {
@@ -700,6 +707,11 @@ long hl_ioctl_control(struct file *filep, unsigned int cmd, unsigned long arg)
 	const struct hl_ioctl_desc *ioctl = NULL;
 	unsigned int nr = _IOC_NR(cmd);
 
+	if (!hdev) {
+		pr_err_ratelimited("Sending ioctl after device was removed! Please close FD\n");
+		return -ENODEV;
+	}
+
 	if (nr == _IOC_NR(HL_IOCTL_INFO)) {
 		ioctl = &hl_ioctls_control[nr];
 	} else {

From 15097e9338ed3de2f5c5904d3dc776ef1b650edc Mon Sep 17 00:00:00 2001
From: farah kassabri <fkassabri@habana.ai>
Date: Sun, 28 Feb 2021 11:06:14 +0200
Subject: [PATCH 0467/1820] habanalabs: fix debugfs address translation

when user uses virtual addresses to access dram through debugfs,
driver translate this address to physical and use it
for the access through the pcie bar.
in case dram page size is different than the dmmu
page size, we need to have special treatment
for adding the page offset to the actual address, which
is to use the dram page size mask to fetch the page offset
from the virtual address, instead of the dmmu last hop shift.

Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/misc/habanalabs/common/mmu/mmu.c | 38 ++++++++++++++++--------
 1 file changed, 26 insertions(+), 12 deletions(-)

diff --git a/drivers/misc/habanalabs/common/mmu/mmu.c b/drivers/misc/habanalabs/common/mmu/mmu.c
index 71703a32350f..93c9e5f587e1 100644
--- a/drivers/misc/habanalabs/common/mmu/mmu.c
+++ b/drivers/misc/habanalabs/common/mmu/mmu.c
@@ -499,18 +499,32 @@ static void hl_mmu_pa_page_with_offset(struct hl_ctx *ctx, u64 virt_addr,
 	else /* HL_VA_RANGE_TYPE_DRAM */
 		p = &prop->dmmu;
 
-	/*
-	 * find the correct hop shift field in hl_mmu_properties structure
-	 * in order to determine the right maks for the page offset.
-	 */
-	hop0_shift_off = offsetof(struct hl_mmu_properties, hop0_shift);
-	p = (char *)p + hop0_shift_off;
-	p = (char *)p + ((hops->used_hops - 1) * sizeof(u64));
-	hop_shift = *(u64 *)p;
-	offset_mask = (1ull << hop_shift) - 1;
-	addr_mask = ~(offset_mask);
-	*phys_addr = (tmp_phys_addr & addr_mask) |
-					(virt_addr & offset_mask);
+	if ((hops->range_type == HL_VA_RANGE_TYPE_DRAM) &&
+			!is_power_of_2(prop->dram_page_size)) {
+		u32 bit;
+		u64 page_offset_mask;
+		u64 phys_addr_mask;
+
+		bit = __ffs64((u64)prop->dram_page_size);
+		page_offset_mask = ((1ull << bit) - 1);
+		phys_addr_mask = ~page_offset_mask;
+		*phys_addr = (tmp_phys_addr & phys_addr_mask) |
+				(virt_addr & page_offset_mask);
+	} else {
+		/*
+		 * find the correct hop shift field in hl_mmu_properties
+		 * structure in order to determine the right masks
+		 * for the page offset.
+		 */
+		hop0_shift_off = offsetof(struct hl_mmu_properties, hop0_shift);
+		p = (char *)p + hop0_shift_off;
+		p = (char *)p + ((hops->used_hops - 1) * sizeof(u64));
+		hop_shift = *(u64 *)p;
+		offset_mask = (1ull << hop_shift) - 1;
+		addr_mask = ~(offset_mask);
+		*phys_addr = (tmp_phys_addr & addr_mask) |
+				(virt_addr & offset_mask);
+	}
 }
 
 int hl_mmu_va_to_pa(struct hl_ctx *ctx, u64 virt_addr, u64 *phys_addr)

From 51f24030358bdeeb9e75a38618dd029c5a53beeb Mon Sep 17 00:00:00 2001
From: Shuo Liu <shuo.a.liu@intel.com>
Date: Sun, 21 Feb 2021 21:43:38 +0800
Subject: [PATCH 0468/1820] cpu/hotplug: Fix build error of using
 {add,remove}_cpu() with !CONFIG_SMP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

279dcf693ac7 ("virt: acrn: Introduce an interface for Service VM to
control vCPU") introduced {add,remove}_cpu() usage and it hit below
error with !CONFIG_SMP:

../drivers/virt/acrn/hsm.c: In function ‘remove_cpu_store’:
../drivers/virt/acrn/hsm.c:389:3: error: implicit declaration of function ‘remove_cpu’; [-Werror=implicit-function-declaration]
   remove_cpu(cpu);

../drivers/virt/acrn/hsm.c:402:2: error: implicit declaration of function ‘add_cpu’; [-Werror=implicit-function-declaration]
   add_cpu(cpu);

Add add_cpu() function prototypes with !CONFIG_SMP and remove_cpu() with
!CONFIG_HOTPLUG_CPU for such usage.

Fixes: 279dcf693ac7 ("virt: acrn: Introduce an interface for Service VM to control vCPU")
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Qais Yousef <qais.yousef@arm.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Qais Yousef <qais.yousef@arm.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Signed-off-by: Shuo Liu <shuo.a.liu@intel.com>
Link: https://lore.kernel.org/r/20210221134339.57851-1-shuo.a.liu@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/cpu.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 3aaa0687e8df..94a578a96202 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -108,6 +108,8 @@ static inline void cpu_maps_update_done(void)
 {
 }
 
+static inline int add_cpu(unsigned int cpu) { return 0;}
+
 #endif /* CONFIG_SMP */
 extern struct bus_type cpu_subsys;
 
@@ -137,6 +139,7 @@ static inline int  cpus_read_trylock(void) { return true; }
 static inline void lockdep_assert_cpus_held(void) { }
 static inline void cpu_hotplug_disable(void) { }
 static inline void cpu_hotplug_enable(void) { }
+static inline int remove_cpu(unsigned int cpu) { return -EPERM; }
 static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { }
 #endif	/* !CONFIG_HOTPLUG_CPU */
 

From e54b78886949e16301e8ac3cc4b2b43969bfe5fa Mon Sep 17 00:00:00 2001
From: Shuo Liu <shuo.a.liu@intel.com>
Date: Sun, 21 Feb 2021 21:43:39 +0800
Subject: [PATCH 0469/1820] virt: acrn: Make remove_cpu sysfs invisible with
 !CONFIG_HOTPLUG_CPU

Without cpu hotplug support, vCPU cannot be removed from a Service VM.
Don't expose remove_cpu sysfs when CONFIG_HOTPLUG_CPU disabled.

Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Qais Yousef <qais.yousef@arm.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Signed-off-by: Shuo Liu <shuo.a.liu@intel.com>
Link: https://lore.kernel.org/r/20210221134339.57851-2-shuo.a.liu@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/acrn/hsm.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c
index 1f6b7c54a1a4..6996ea6219e5 100644
--- a/drivers/virt/acrn/hsm.c
+++ b/drivers/virt/acrn/hsm.c
@@ -404,6 +404,14 @@ fail_remove:
 }
 static DEVICE_ATTR_WO(remove_cpu);
 
+static umode_t acrn_attr_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+       if (a == &dev_attr_remove_cpu.attr)
+               return IS_ENABLED(CONFIG_HOTPLUG_CPU) ? a->mode : 0;
+
+       return a->mode;
+}
+
 static struct attribute *acrn_attrs[] = {
 	&dev_attr_remove_cpu.attr,
 	NULL
@@ -411,6 +419,7 @@ static struct attribute *acrn_attrs[] = {
 
 static struct attribute_group acrn_attr_group = {
 	.attrs = acrn_attrs,
+	.is_visible = acrn_attr_visible,
 };
 
 static const struct attribute_group *acrn_attr_groups[] = {

From dcf9625f2adf33cf3ea14c72b436b7c212807e51 Mon Sep 17 00:00:00 2001
From: Yejune Deng <yejune.deng@gmail.com>
Date: Sun, 21 Feb 2021 21:33:06 +0800
Subject: [PATCH 0470/1820] virt: acrn: Use vfs_poll() instead of f_op->poll()

Use a more advanced function vfs_poll() in acrn_irqfd_assign().
At the same time, modify the definition of events.

Signed-off-by: Yejune Deng <yejune.deng@gmail.com>
Signed-off-by: Shuo Liu <shuo.a.liu@intel.com>
Link: https://lore.kernel.org/r/20210221133306.33530-1-shuo.a.liu@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/acrn/irqfd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/virt/acrn/irqfd.c b/drivers/virt/acrn/irqfd.c
index a8766d528e29..98d6e9b18f9e 100644
--- a/drivers/virt/acrn/irqfd.c
+++ b/drivers/virt/acrn/irqfd.c
@@ -112,7 +112,7 @@ static int acrn_irqfd_assign(struct acrn_vm *vm, struct acrn_irqfd *args)
 {
 	struct eventfd_ctx *eventfd = NULL;
 	struct hsm_irqfd *irqfd, *tmp;
-	unsigned int events;
+	__poll_t events;
 	struct fd f;
 	int ret = 0;
 
@@ -158,7 +158,7 @@ static int acrn_irqfd_assign(struct acrn_vm *vm, struct acrn_irqfd *args)
 	mutex_unlock(&vm->irqfds_lock);
 
 	/* Check the pending event in this stage */
-	events = f.file->f_op->poll(f.file, &irqfd->pt);
+	events = vfs_poll(f.file, &irqfd->pt);
 
 	if (events & POLLIN)
 		acrn_irqfd_inject(irqfd);

From 7c36194558cf49a86a53b5f60db8046c5e3013ae Mon Sep 17 00:00:00 2001
From: Julian Braha <julianbraha@gmail.com>
Date: Mon, 22 Feb 2021 13:06:07 -0500
Subject: [PATCH 0471/1820] staging: rtl8192e: fix kconfig dependency on CRYPTO

When RTLLIB_CRYPTO_TKIP is enabled and CRYPTO is disabled,
Kbuild gives the following warning:

WARNING: unmet direct dependencies detected for CRYPTO_MICHAEL_MIC
  Depends on [n]: CRYPTO [=n]
  Selected by [m]:
  - RTLLIB_CRYPTO_TKIP [=m] && STAGING [=y] && RTLLIB [=m]

WARNING: unmet direct dependencies detected for CRYPTO_LIB_ARC4
  Depends on [n]: CRYPTO [=n]
  Selected by [m]:
  - RTLLIB_CRYPTO_TKIP [=m] && STAGING [=y] && RTLLIB [=m]
  - RTLLIB_CRYPTO_WEP [=m] && STAGING [=y] && RTLLIB [=m]

This is because RTLLIB_CRYPTO_TKIP selects CRYPTO_MICHAEL_MIC and
CRYPTO_LIB_ARC4, without depending on or selecting CRYPTO,
despite those config options being subordinate to CRYPTO.

Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Julian Braha <julianbraha@gmail.com>
Link: https://lore.kernel.org/r/20210222180607.399753-1-julianbraha@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/staging/rtl8192e/Kconfig b/drivers/staging/rtl8192e/Kconfig
index 963a2ffbc1fb..39f5a6a7346a 100644
--- a/drivers/staging/rtl8192e/Kconfig
+++ b/drivers/staging/rtl8192e/Kconfig
@@ -27,6 +27,7 @@ config RTLLIB_CRYPTO_CCMP
 config RTLLIB_CRYPTO_TKIP
 	tristate "Support for rtllib TKIP crypto"
 	depends on RTLLIB
+	select CRYPTO
 	select CRYPTO_LIB_ARC4
 	select CRYPTO_MICHAEL_MIC
 	default y

From d660f4f42ccea50262c6ee90c8e7ad19a69fb225 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 24 Feb 2021 11:45:59 +0300
Subject: [PATCH 0472/1820] staging: rtl8712: unterminated string leads to read
 overflow

The memdup_user() function does not necessarily return a NUL terminated
string so this can lead to a read overflow.  Switch from memdup_user()
to strndup_user() to fix this bug.

Fixes: c6dc001f2add ("staging: r8712u: Merging Realtek's latest (v2.6.6). Various fixes.")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Link: https://lore.kernel.org/r/YDYSR+1rj26NRhvb@mwanda
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8712/rtl871x_ioctl_linux.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8712/rtl871x_ioctl_linux.c b/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
index 81de5a9e6b67..60dd798a6e51 100644
--- a/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
+++ b/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
@@ -924,7 +924,7 @@ static int r871x_wx_set_priv(struct net_device *dev,
 	struct iw_point *dwrq = (struct iw_point *)awrq;
 
 	len = dwrq->length;
-	ext = memdup_user(dwrq->pointer, len);
+	ext = strndup_user(dwrq->pointer, len);
 	if (IS_ERR(ext))
 		return PTR_ERR(ext);
 

From 8687bf9ef9551bcf93897e33364d121667b1aadf Mon Sep 17 00:00:00 2001
From: Lee Gibson <leegib@gmail.com>
Date: Fri, 26 Feb 2021 14:51:57 +0000
Subject: [PATCH 0473/1820] staging: rtl8192e: Fix possible buffer overflow in
 _rtl92e_wx_set_scan

Function _rtl92e_wx_set_scan calls memcpy without checking the length.
A user could control that length and trigger a buffer overflow.
Fix by checking the length is within the maximum allowed size.

Reviewed-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Lee Gibson <leegib@gmail.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210226145157.424065-1-leegib@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtl8192e/rtl_wx.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c b/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
index 16bcee13f64b..407effde5e71 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c
@@ -406,9 +406,10 @@ static int _rtl92e_wx_set_scan(struct net_device *dev,
 		struct iw_scan_req *req = (struct iw_scan_req *)b;
 
 		if (req->essid_len) {
-			ieee->current_network.ssid_len = req->essid_len;
-			memcpy(ieee->current_network.ssid, req->essid,
-			       req->essid_len);
+			int len = min_t(int, req->essid_len, IW_ESSID_MAX_SIZE);
+
+			ieee->current_network.ssid_len = len;
+			memcpy(ieee->current_network.ssid, req->essid, len);
 		}
 	}
 

From b93c1e3981af19527beee1c10a2bef67a228c48c Mon Sep 17 00:00:00 2001
From: Lee Gibson <leegib@gmail.com>
Date: Mon, 1 Mar 2021 13:26:48 +0000
Subject: [PATCH 0474/1820] staging: rtl8712: Fix possible buffer overflow in
 r8712_sitesurvey_cmd

Function r8712_sitesurvey_cmd calls memcpy without checking the length.
A user could control that length and trigger a buffer overflow.
Fix by checking the length is within the maximum allowed size.

Signed-off-by: Lee Gibson <leegib@gmail.com>
Link: https://lore.kernel.org/r/20210301132648.420296-1-leegib@gmail.com
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8712/rtl871x_cmd.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8712/rtl871x_cmd.c b/drivers/staging/rtl8712/rtl871x_cmd.c
index 18116469bd31..75716f59044d 100644
--- a/drivers/staging/rtl8712/rtl871x_cmd.c
+++ b/drivers/staging/rtl8712/rtl871x_cmd.c
@@ -192,8 +192,10 @@ u8 r8712_sitesurvey_cmd(struct _adapter *padapter,
 	psurveyPara->ss_ssidlen = 0;
 	memset(psurveyPara->ss_ssid, 0, IW_ESSID_MAX_SIZE + 1);
 	if (pssid && pssid->SsidLength) {
-		memcpy(psurveyPara->ss_ssid, pssid->Ssid, pssid->SsidLength);
-		psurveyPara->ss_ssidlen = cpu_to_le32(pssid->SsidLength);
+		int len = min_t(int, pssid->SsidLength, IW_ESSID_MAX_SIZE);
+
+		memcpy(psurveyPara->ss_ssid, pssid->Ssid, len);
+		psurveyPara->ss_ssidlen = cpu_to_le32(len);
 	}
 	set_fwstate(pmlmepriv, _FW_UNDER_SURVEY);
 	r8712_enqueue_cmd(pcmdpriv, ph2c);

From e163b9823a0b08c3bb8dc4f5b4b5c221c24ec3e5 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 2 Mar 2021 14:19:39 +0300
Subject: [PATCH 0475/1820] staging: ks7010: prevent buffer overflow in
 ks_wlan_set_scan()

The user can specify a "req->essid_len" of up to 255 but if it's
over IW_ESSID_MAX_SIZE (32) that can lead to memory corruption.

Fixes: 13a9930d15b4 ("staging: ks7010: add driver from Nanonote extra-repository")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/YD4fS8+HmM/Qmrw6@mwanda
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/ks7010/ks_wlan_net.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/ks7010/ks_wlan_net.c b/drivers/staging/ks7010/ks_wlan_net.c
index dc09cc6e1c47..09e7b4cd0138 100644
--- a/drivers/staging/ks7010/ks_wlan_net.c
+++ b/drivers/staging/ks7010/ks_wlan_net.c
@@ -1120,6 +1120,7 @@ static int ks_wlan_set_scan(struct net_device *dev,
 {
 	struct ks_wlan_private *priv = netdev_priv(dev);
 	struct iw_scan_req *req = NULL;
+	int len;
 
 	if (priv->sleep_mode == SLP_SLEEP)
 		return -EPERM;
@@ -1129,8 +1130,9 @@ static int ks_wlan_set_scan(struct net_device *dev,
 	if (wrqu->data.length == sizeof(struct iw_scan_req) &&
 	    wrqu->data.flags & IW_SCAN_THIS_ESSID) {
 		req = (struct iw_scan_req *)extra;
-		priv->scan_ssid_len = req->essid_len;
-		memcpy(priv->scan_ssid, req->essid, priv->scan_ssid_len);
+		len = min_t(int, req->essid_len, IW_ESSID_MAX_SIZE);
+		priv->scan_ssid_len = len;
+		memcpy(priv->scan_ssid, req->essid, len);
 	} else {
 		priv->scan_ssid_len = 0;
 	}

From 25317f428a78fde71b2bf3f24d05850f08a73a52 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:42 +0000
Subject: [PATCH 0476/1820] staging: comedi: addi_apci_1032: Fix endian problem
 for COS sample

The Change-Of-State (COS) subdevice supports Comedi asynchronous
commands to read 16-bit change-of-state values.  However, the interrupt
handler is calling `comedi_buf_write_samples()` with the address of a
32-bit integer `&s->state`.  On bigendian architectures, it will copy 2
bytes from the wrong end of the 32-bit integer.  Fix it by transferring
the value via a 16-bit integer.

Fixes: 6bb45f2b0c86 ("staging: comedi: addi_apci_1032: use comedi_buf_write_samples()")
Cc: <stable@vger.kernel.org> # 3.19+
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-2-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/addi_apci_1032.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/addi_apci_1032.c b/drivers/staging/comedi/drivers/addi_apci_1032.c
index 35b75f0c9200..81a246fbcc01 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1032.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1032.c
@@ -260,6 +260,7 @@ static irqreturn_t apci1032_interrupt(int irq, void *d)
 	struct apci1032_private *devpriv = dev->private;
 	struct comedi_subdevice *s = dev->read_subdev;
 	unsigned int ctrl;
+	unsigned short val;
 
 	/* check interrupt is from this device */
 	if ((inl(devpriv->amcc_iobase + AMCC_OP_REG_INTCSR) &
@@ -275,7 +276,8 @@ static irqreturn_t apci1032_interrupt(int irq, void *d)
 	outl(ctrl & ~APCI1032_CTRL_INT_ENA, dev->iobase + APCI1032_CTRL_REG);
 
 	s->state = inl(dev->iobase + APCI1032_STATUS_REG) & 0xffff;
-	comedi_buf_write_samples(s, &s->state, 1);
+	val = s->state;
+	comedi_buf_write_samples(s, &val, 1);
 	comedi_handle_events(dev, s);
 
 	/* enable the interrupt */

From ac0bbf55ed3be75fde1f8907e91ecd2fd589bde3 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:43 +0000
Subject: [PATCH 0477/1820] staging: comedi: addi_apci_1500: Fix endian problem
 for command sample

The digital input subdevice supports Comedi asynchronous commands that
read interrupt status information.  This uses 16-bit Comedi samples (of
which only the bottom 8 bits contain status information).  However, the
interrupt handler is calling `comedi_buf_write_samples()` with the
address of a 32-bit variable `unsigned int status`.  On a bigendian
machine, this will copy 2 bytes from the wrong end of the variable.  Fix
it by changing the type of the variable to `unsigned short`.

Fixes: a8c66b684efa ("staging: comedi: addi_apci_1500: rewrite the subdevice support functions")
Cc: <stable@vger.kernel.org> #4.0+
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-3-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../staging/comedi/drivers/addi_apci_1500.c    | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/staging/comedi/drivers/addi_apci_1500.c b/drivers/staging/comedi/drivers/addi_apci_1500.c
index 11efb21555e3..b04c15dcfb57 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1500.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1500.c
@@ -208,7 +208,7 @@ static irqreturn_t apci1500_interrupt(int irq, void *d)
 	struct comedi_device *dev = d;
 	struct apci1500_private *devpriv = dev->private;
 	struct comedi_subdevice *s = dev->read_subdev;
-	unsigned int status = 0;
+	unsigned short status = 0;
 	unsigned int val;
 
 	val = inl(devpriv->amcc + AMCC_OP_REG_INTCSR);
@@ -238,14 +238,14 @@ static irqreturn_t apci1500_interrupt(int irq, void *d)
 	 *
 	 *    Mask     Meaning
 	 * ----------  ------------------------------------------
-	 * 0x00000001  Event 1 has occurred
-	 * 0x00000010  Event 2 has occurred
-	 * 0x00000100  Counter/timer 1 has run down (not implemented)
-	 * 0x00001000  Counter/timer 2 has run down (not implemented)
-	 * 0x00010000  Counter 3 has run down (not implemented)
-	 * 0x00100000  Watchdog has run down (not implemented)
-	 * 0x01000000  Voltage error
-	 * 0x10000000  Short-circuit error
+	 * 0b00000001  Event 1 has occurred
+	 * 0b00000010  Event 2 has occurred
+	 * 0b00000100  Counter/timer 1 has run down (not implemented)
+	 * 0b00001000  Counter/timer 2 has run down (not implemented)
+	 * 0b00010000  Counter 3 has run down (not implemented)
+	 * 0b00100000  Watchdog has run down (not implemented)
+	 * 0b01000000  Voltage error
+	 * 0b10000000  Short-circuit error
 	 */
 	comedi_buf_write_samples(s, &status, 1);
 	comedi_handle_events(dev, s);

From b2e78630f733a76508b53ba680528ca39c890e82 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:44 +0000
Subject: [PATCH 0478/1820] staging: comedi: adv_pci1710: Fix endian problem
 for AI command data

The analog input subdevice supports Comedi asynchronous commands that
use Comedi's 16-bit sample format.  However, the calls to
`comedi_buf_write_samples()` are passing the address of a 32-bit integer
variable.  On bigendian machines, this will copy 2 bytes from the wrong
end of the 32-bit value.  Fix it by changing the type of the variables
holding the sample value to `unsigned short`.  The type of the `val`
parameter of `pci1710_ai_read_sample()` is changed to `unsigned short *`
accordingly.  The type of the `val` variable in `pci1710_ai_insn_read()`
is also changed to `unsigned short` since its address is passed to
`pci1710_ai_read_sample()`.

Fixes: a9c3a015c12f ("staging: comedi: adv_pci1710: use comedi_buf_write_samples()")
Cc: <stable@vger.kernel.org> # 4.0+
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-4-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/adv_pci1710.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/comedi/drivers/adv_pci1710.c b/drivers/staging/comedi/drivers/adv_pci1710.c
index 692893c7e5c3..090607760be6 100644
--- a/drivers/staging/comedi/drivers/adv_pci1710.c
+++ b/drivers/staging/comedi/drivers/adv_pci1710.c
@@ -300,11 +300,11 @@ static int pci1710_ai_eoc(struct comedi_device *dev,
 static int pci1710_ai_read_sample(struct comedi_device *dev,
 				  struct comedi_subdevice *s,
 				  unsigned int cur_chan,
-				  unsigned int *val)
+				  unsigned short *val)
 {
 	const struct boardtype *board = dev->board_ptr;
 	struct pci1710_private *devpriv = dev->private;
-	unsigned int sample;
+	unsigned short sample;
 	unsigned int chan;
 
 	sample = inw(dev->iobase + PCI171X_AD_DATA_REG);
@@ -345,7 +345,7 @@ static int pci1710_ai_insn_read(struct comedi_device *dev,
 	pci1710_ai_setup_chanlist(dev, s, &insn->chanspec, 1, 1);
 
 	for (i = 0; i < insn->n; i++) {
-		unsigned int val;
+		unsigned short val;
 
 		/* start conversion */
 		outw(0, dev->iobase + PCI171X_SOFTTRG_REG);
@@ -395,7 +395,7 @@ static void pci1710_handle_every_sample(struct comedi_device *dev,
 {
 	struct comedi_cmd *cmd = &s->async->cmd;
 	unsigned int status;
-	unsigned int val;
+	unsigned short val;
 	int ret;
 
 	status = inw(dev->iobase + PCI171X_STATUS_REG);
@@ -455,7 +455,7 @@ static void pci1710_handle_fifo(struct comedi_device *dev,
 	}
 
 	for (i = 0; i < devpriv->max_samples; i++) {
-		unsigned int val;
+		unsigned short val;
 		int ret;
 
 		ret = pci1710_ai_read_sample(dev, s, s->async->cur_chan, &val);

From 1c0f20b78781b9ca50dc3ecfd396d0db5b141890 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:45 +0000
Subject: [PATCH 0479/1820] staging: comedi: das6402: Fix endian problem for AI
 command data

The analog input subdevice supports Comedi asynchronous commands that
use Comedi's 16-bit sample format.  However, the call to
`comedi_buf_write_samples()` is passing the address of a 32-bit integer
variable.  On bigendian machines, this will copy 2 bytes from the wrong
end of the 32-bit value.  Fix it by changing the type of the variable
holding the sample value to `unsigned short`.

Fixes: d1d24cb65ee3 ("staging: comedi: das6402: read analog input samples in interrupt handler")
Cc: <stable@vger.kernel.org> # 3.19+
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-5-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/das6402.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/das6402.c b/drivers/staging/comedi/drivers/das6402.c
index 04e224f8b779..96f4107b8054 100644
--- a/drivers/staging/comedi/drivers/das6402.c
+++ b/drivers/staging/comedi/drivers/das6402.c
@@ -186,7 +186,7 @@ static irqreturn_t das6402_interrupt(int irq, void *d)
 	if (status & DAS6402_STATUS_FFULL) {
 		async->events |= COMEDI_CB_OVERFLOW;
 	} else if (status & DAS6402_STATUS_FFNE) {
-		unsigned int val;
+		unsigned short val;
 
 		val = das6402_ai_read_sample(dev, s);
 		comedi_buf_write_samples(s, &val, 1);

From 459b1e8c8fe97fcba0bd1b623471713dce2c5eaf Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:46 +0000
Subject: [PATCH 0480/1820] staging: comedi: das800: Fix endian problem for AI
 command data

The analog input subdevice supports Comedi asynchronous commands that
use Comedi's 16-bit sample format.  However, the call to
`comedi_buf_write_samples()` is passing the address of a 32-bit integer
variable.  On bigendian machines, this will copy 2 bytes from the wrong
end of the 32-bit value.  Fix it by changing the type of the variable
holding the sample value to `unsigned short`.

Fixes: ad9eb43c93d8 ("staging: comedi: das800: use comedi_buf_write_samples()")
Cc: <stable@vger.kernel.org> # 3.19+
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-6-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/das800.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/das800.c b/drivers/staging/comedi/drivers/das800.c
index 4ea100ff6930..2881808d6606 100644
--- a/drivers/staging/comedi/drivers/das800.c
+++ b/drivers/staging/comedi/drivers/das800.c
@@ -427,7 +427,7 @@ static irqreturn_t das800_interrupt(int irq, void *d)
 	struct comedi_cmd *cmd;
 	unsigned long irq_flags;
 	unsigned int status;
-	unsigned int val;
+	unsigned short val;
 	bool fifo_empty;
 	bool fifo_overflow;
 	int i;

From 54999c0d94b3c26625f896f8e3460bc029821578 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:47 +0000
Subject: [PATCH 0481/1820] staging: comedi: dmm32at: Fix endian problem for AI
 command data

The analog input subdevice supports Comedi asynchronous commands that
use Comedi's 16-bit sample format.  However, the call to
`comedi_buf_write_samples()` is passing the address of a 32-bit integer
variable.  On bigendian machines, this will copy 2 bytes from the wrong
end of the 32-bit value.  Fix it by changing the type of the variable
holding the sample value to `unsigned short`.

[Note: the bug was introduced in commit 1700529b24cc ("staging: comedi:
dmm32at: use comedi_buf_write_samples()") but the patch applies better
to the later (but in the same kernel release) commit 0c0eadadcbe6e
("staging: comedi: dmm32at: introduce dmm32_ai_get_sample()").]

Fixes: 0c0eadadcbe6e ("staging: comedi: dmm32at: introduce dmm32_ai_get_sample()")
Cc: <stable@vger.kernel.org> # 3.19+
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-7-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/dmm32at.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/dmm32at.c b/drivers/staging/comedi/drivers/dmm32at.c
index 17e6018918bb..56682f01242f 100644
--- a/drivers/staging/comedi/drivers/dmm32at.c
+++ b/drivers/staging/comedi/drivers/dmm32at.c
@@ -404,7 +404,7 @@ static irqreturn_t dmm32at_isr(int irq, void *d)
 {
 	struct comedi_device *dev = d;
 	unsigned char intstat;
-	unsigned int val;
+	unsigned short val;
 	int i;
 
 	if (!dev->attached) {

From b39dfcced399d31e7c4b7341693b18e01c8f655e Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:48 +0000
Subject: [PATCH 0482/1820] staging: comedi: me4000: Fix endian problem for AI
 command data

The analog input subdevice supports Comedi asynchronous commands that
use Comedi's 16-bit sample format.  However, the calls to
`comedi_buf_write_samples()` are passing the address of a 32-bit integer
variable.  On bigendian machines, this will copy 2 bytes from the wrong
end of the 32-bit value.  Fix it by changing the type of the variable
holding the sample value to `unsigned short`.

Fixes: de88924f67d1 ("staging: comedi: me4000: use comedi_buf_write_samples()")
Cc: <stable@vger.kernel.org> # 3.19+
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-8-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/me4000.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/me4000.c b/drivers/staging/comedi/drivers/me4000.c
index 726e40dc17b6..0d3d4cafce2e 100644
--- a/drivers/staging/comedi/drivers/me4000.c
+++ b/drivers/staging/comedi/drivers/me4000.c
@@ -924,7 +924,7 @@ static irqreturn_t me4000_ai_isr(int irq, void *dev_id)
 	struct comedi_subdevice *s = dev->read_subdev;
 	int i;
 	int c = 0;
-	unsigned int lval;
+	unsigned short lval;
 
 	if (!dev->attached)
 		return IRQ_NONE;

From a084303a645896e834883f2c5170d044410dfdb3 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:49 +0000
Subject: [PATCH 0483/1820] staging: comedi: pcl711: Fix endian problem for AI
 command data

The analog input subdevice supports Comedi asynchronous commands that
use Comedi's 16-bit sample format.  However, the call to
`comedi_buf_write_samples()` is passing the address of a 32-bit integer
variable.  On bigendian machines, this will copy 2 bytes from the wrong
end of the 32-bit value.  Fix it by changing the type of the variable
holding the sample value to `unsigned short`.

Fixes: 1f44c034de2e ("staging: comedi: pcl711: use comedi_buf_write_samples()")
Cc: <stable@vger.kernel.org> # 3.19+
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-9-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/pcl711.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/pcl711.c b/drivers/staging/comedi/drivers/pcl711.c
index 2dbf69e30965..bd6f42fe9e3c 100644
--- a/drivers/staging/comedi/drivers/pcl711.c
+++ b/drivers/staging/comedi/drivers/pcl711.c
@@ -184,7 +184,7 @@ static irqreturn_t pcl711_interrupt(int irq, void *d)
 	struct comedi_device *dev = d;
 	struct comedi_subdevice *s = dev->read_subdev;
 	struct comedi_cmd *cmd = &s->async->cmd;
-	unsigned int data;
+	unsigned short data;
 
 	if (!dev->attached) {
 		dev_err(dev->class_dev, "spurious interrupt\n");

From 148e34fd33d53740642db523724226de14ee5281 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:50 +0000
Subject: [PATCH 0484/1820] staging: comedi: pcl818: Fix endian problem for AI
 command data

The analog input subdevice supports Comedi asynchronous commands that
use Comedi's 16-bit sample format.  However, the call to
`comedi_buf_write_samples()` is passing the address of a 32-bit integer
parameter.  On bigendian machines, this will copy 2 bytes from the wrong
end of the 32-bit value.  Fix it by changing the type of the parameter
holding the sample value to `unsigned short`.

[Note: the bug was introduced in commit edf4537bcbf5 ("staging: comedi:
pcl818: use comedi_buf_write_samples()") but the patch applies better to
commit d615416de615 ("staging: comedi: pcl818: introduce
pcl818_ai_write_sample()").]

Fixes: d615416de615 ("staging: comedi: pcl818: introduce pcl818_ai_write_sample()")
Cc: <stable@vger.kernel.org> # 4.0+
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-10-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/pcl818.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/pcl818.c b/drivers/staging/comedi/drivers/pcl818.c
index 63e3011158f2..f4b4a686c710 100644
--- a/drivers/staging/comedi/drivers/pcl818.c
+++ b/drivers/staging/comedi/drivers/pcl818.c
@@ -423,7 +423,7 @@ static int pcl818_ai_eoc(struct comedi_device *dev,
 
 static bool pcl818_ai_write_sample(struct comedi_device *dev,
 				   struct comedi_subdevice *s,
-				   unsigned int chan, unsigned int val)
+				   unsigned int chan, unsigned short val)
 {
 	struct pcl818_private *devpriv = dev->private;
 	struct comedi_cmd *cmd = &s->async->cmd;

From 8536749d4952649ada4a88396079e6ec69c1fc9f Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:51 +0000
Subject: [PATCH 0485/1820] staging: comedi: amplc_pc236_common: Use 16-bit 0
 for interrupt data

The Amplicon PC36AT/PCI236 common driver has an "interrupt" subdevice
that supports Comedi asynchronous commands, placing a value in the
Comedi buffer for each interrupt.  The subdevice uses Comedi's 16-bit
sample format but the interrupt handler is calling
`comedi_buf_write_samples()` with the address of a 32-bit integer
`&s->state`.  On bigendian machines, this will copy 2 bytes from the
wrong end of the 32-bit integer.  This isn't really a problem since
`s->state` will always be 0 for this subdevice, but clean it up by using
a 16-bit variable initialized to 0 to pass the value.

Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-11-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/amplc_pc236_common.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/amplc_pc236_common.c b/drivers/staging/comedi/drivers/amplc_pc236_common.c
index 043752663188..981d281e87a1 100644
--- a/drivers/staging/comedi/drivers/amplc_pc236_common.c
+++ b/drivers/staging/comedi/drivers/amplc_pc236_common.c
@@ -126,7 +126,9 @@ static irqreturn_t pc236_interrupt(int irq, void *d)
 
 	handled = pc236_intr_check(dev);
 	if (dev->attached && handled) {
-		comedi_buf_write_samples(s, &s->state, 1);
+		unsigned short val = 0;
+
+		comedi_buf_write_samples(s, &val, 1);
 		comedi_handle_events(dev, s);
 	}
 	return IRQ_RETVAL(handled);

From a1acdbc55403d94ac8dddcb0311360bc6dae659f Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:52 +0000
Subject: [PATCH 0486/1820] staging: comedi: comedi_parport: Use 16-bit 0 for
 interrupt data

The comedi_parport driver has an "interrupt" subdevice that supports
Comedi asynchronous commands, placing a value in the Comedi buffer for
each interrupt.  The subdevice uses Comedi's 16-bit sample format but
the interrupt handler is calling `comedi_buf_write_samples()` with the
address of a 32-bit integer `&s->state`.  On bigendian machines, this
will copy 2 bytes from the wrong end of the 32-bit integer.  This isn't
really a problem since `s->state` will always be 0 for this subdevice,
but clean it up by using a 16-bit variable initialized to 0 to pass the
value.

Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-12-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/comedi_parport.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/comedi_parport.c b/drivers/staging/comedi/drivers/comedi_parport.c
index 9361b2dcf949..5338b5eea440 100644
--- a/drivers/staging/comedi/drivers/comedi_parport.c
+++ b/drivers/staging/comedi/drivers/comedi_parport.c
@@ -210,12 +210,13 @@ static irqreturn_t parport_interrupt(int irq, void *d)
 	struct comedi_device *dev = d;
 	struct comedi_subdevice *s = dev->read_subdev;
 	unsigned int ctrl;
+	unsigned short val = 0;
 
 	ctrl = inb(dev->iobase + PARPORT_CTRL_REG);
 	if (!(ctrl & PARPORT_CTRL_IRQ_ENA))
 		return IRQ_NONE;
 
-	comedi_buf_write_samples(s, &s->state, 1);
+	comedi_buf_write_samples(s, &val, 1);
 	comedi_handle_events(dev, s);
 
 	return IRQ_HANDLED;

From 33444638ae54fa2eb8e9269d70ce2d5bc8b52751 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:53 +0000
Subject: [PATCH 0487/1820] staging: comedi: ni_6527: Use 16-bit 0 for
 interrupt data

The ni_6527 driver has an "interrupt" subdevice that supports Comedi
asynchronous commands, placing a value in the Comedi buffer for each
interrupt.  The subdevice uses Comedi's 16-bit sample format but the
interrupt handler is calling `comedi_buf_write_samples()` with the
address of a 32-bit integer `&s->state`.  On bigendian machines, this
will copy 2 bytes from the wrong end of the 32-bit integer.  This isn't
really a problem since `s->state` will always be 0 for this subdevice,
but clean it up by using a 16-bit variable initialized to 0 to pass the
value.

Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-13-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/ni_6527.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/ni_6527.c b/drivers/staging/comedi/drivers/ni_6527.c
index 99e744172f4d..f1a45cf7342a 100644
--- a/drivers/staging/comedi/drivers/ni_6527.c
+++ b/drivers/staging/comedi/drivers/ni_6527.c
@@ -195,7 +195,9 @@ static irqreturn_t ni6527_interrupt(int irq, void *d)
 		return IRQ_NONE;
 
 	if (status & NI6527_STATUS_EDGE) {
-		comedi_buf_write_samples(s, &s->state, 1);
+		unsigned short val = 0;
+
+		comedi_buf_write_samples(s, &val, 1);
 		comedi_handle_events(dev, s);
 	}
 

From 5ff1c08c28c331eee1ac6a02e8e3eabb329fa953 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:54 +0000
Subject: [PATCH 0488/1820] staging: comedi: ni_65xx: Use 16-bit 0 for
 interrupt data

The ni_65xx driver has an "interrupt" subdevice that supports Comedi
asynchronous commands, placing a value in the Comedi buffer for each
interrupt.  The subdevice uses Comedi's 16-bit sample format but the
interrupt handler is calling `comedi_buf_write_samples()` with the
address of a 32-bit integer `&s->state`.  On bigendian machines, this
will copy 2 bytes from the wrong end of the 32-bit integer.  This isn't
really a problem since `s->state` will always be 0 for this subdevice,
but clean it up by using a 16-bit variable initialized to 0 to pass the
value.

Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-14-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/ni_65xx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/ni_65xx.c b/drivers/staging/comedi/drivers/ni_65xx.c
index eb3f9f7109da..7cd8497420f2 100644
--- a/drivers/staging/comedi/drivers/ni_65xx.c
+++ b/drivers/staging/comedi/drivers/ni_65xx.c
@@ -472,6 +472,7 @@ static irqreturn_t ni_65xx_interrupt(int irq, void *d)
 	struct comedi_device *dev = d;
 	struct comedi_subdevice *s = dev->read_subdev;
 	unsigned int status;
+	unsigned short val = 0;
 
 	status = readb(dev->mmio + NI_65XX_STATUS_REG);
 	if ((status & NI_65XX_STATUS_INT) == 0)
@@ -482,7 +483,7 @@ static irqreturn_t ni_65xx_interrupt(int irq, void *d)
 	writeb(NI_65XX_CLR_EDGE_INT | NI_65XX_CLR_OVERFLOW_INT,
 	       dev->mmio + NI_65XX_CLR_REG);
 
-	comedi_buf_write_samples(s, &s->state, 1);
+	comedi_buf_write_samples(s, &val, 1);
 	comedi_handle_events(dev, s);
 
 	return IRQ_HANDLED;

From fd3ce6557da0e7557a451ee56fc8f5700d3bd08f Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 23 Feb 2021 14:30:55 +0000
Subject: [PATCH 0489/1820] staging: comedi: pcl726: Use 16-bit 0 for interrupt
 data

The pcl726 driver has an "interrupt" subdevice that supports Comedi
asynchronous commands, placing a value in the Comedi buffer for each
interrupt.  The subdevice uses Comedi's 16-bit sample format but the
interrupt handler is calling `comedi_buf_write_samples()` with the
address of a 32-bit integer `&s->state`.  On bigendian machines, this
will copy 2 bytes from the wrong end of the 32-bit integer.  This isn't
really a problem since `s->state` will always be 0 for this subdevice,
but clean it up by using a 16-bit variable initialized to 0 to pass the
value.

Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20210223143055.257402-15-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/pcl726.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/pcl726.c b/drivers/staging/comedi/drivers/pcl726.c
index 64eb649c9813..88f25d7e76f7 100644
--- a/drivers/staging/comedi/drivers/pcl726.c
+++ b/drivers/staging/comedi/drivers/pcl726.c
@@ -220,9 +220,11 @@ static irqreturn_t pcl726_interrupt(int irq, void *d)
 	struct pcl726_private *devpriv = dev->private;
 
 	if (devpriv->cmd_running) {
+		unsigned short val = 0;
+
 		pcl726_intr_cancel(dev, s);
 
-		comedi_buf_write_samples(s, &s->state, 1);
+		comedi_buf_write_samples(s, &val, 1);
 		comedi_handle_events(dev, s);
 	}
 

From 87107518d7a93fec6cdb2559588862afeee800fb Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 5 Mar 2021 11:12:49 +0300
Subject: [PATCH 0490/1820] staging: rtl8192u: fix ->ssid overflow in
 r8192_wx_set_scan()

We need to cap len at IW_ESSID_MAX_SIZE (32) to avoid memory corruption.
This can be controlled by the user via the ioctl.

Fixes: 5f53d8ca3d5d ("Staging: add rtl8192SU wireless usb driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/YEHoAWMOSZBUw91F@mwanda
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192u/r8192U_wx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8192u/r8192U_wx.c b/drivers/staging/rtl8192u/r8192U_wx.c
index d853586705fc..77bf88696a84 100644
--- a/drivers/staging/rtl8192u/r8192U_wx.c
+++ b/drivers/staging/rtl8192u/r8192U_wx.c
@@ -331,8 +331,10 @@ static int r8192_wx_set_scan(struct net_device *dev, struct iw_request_info *a,
 		struct iw_scan_req *req = (struct iw_scan_req *)b;
 
 		if (req->essid_len) {
-			ieee->current_network.ssid_len = req->essid_len;
-			memcpy(ieee->current_network.ssid, req->essid, req->essid_len);
+			int len = min_t(int, req->essid_len, IW_ESSID_MAX_SIZE);
+
+			ieee->current_network.ssid_len = len;
+			memcpy(ieee->current_network.ssid, req->essid, len);
 		}
 	}
 

From d4ac640322b06095128a5c45ba4a1e80929fe7f3 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 5 Mar 2021 11:56:32 +0300
Subject: [PATCH 0491/1820] staging: rtl8188eu: fix potential memory corruption
 in rtw_check_beacon_data()

The "ie_len" is a value in the 1-255 range that comes from the user.  We
have to cap it to ensure that it's not too large or it could lead to
memory corruption.

Fixes: 9a7fe54ddc3a ("staging: r8188eu: Add source files for new driver - part 1")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/YEHyQCrFZKTXyT7J@mwanda
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8188eu/core/rtw_ap.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/staging/rtl8188eu/core/rtw_ap.c b/drivers/staging/rtl8188eu/core/rtw_ap.c
index fa1e34a0d456..182bb944c9b3 100644
--- a/drivers/staging/rtl8188eu/core/rtw_ap.c
+++ b/drivers/staging/rtl8188eu/core/rtw_ap.c
@@ -791,6 +791,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf,  int len)
 	p = rtw_get_ie(ie + _BEACON_IE_OFFSET_, WLAN_EID_SSID, &ie_len,
 		       pbss_network->ie_length - _BEACON_IE_OFFSET_);
 	if (p && ie_len > 0) {
+		ie_len = min_t(int, ie_len, sizeof(pbss_network->ssid.ssid));
 		memset(&pbss_network->ssid, 0, sizeof(struct ndis_802_11_ssid));
 		memcpy(pbss_network->ssid.ssid, p + 2, ie_len);
 		pbss_network->ssid.ssid_length = ie_len;
@@ -811,6 +812,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf,  int len)
 	p = rtw_get_ie(ie + _BEACON_IE_OFFSET_, WLAN_EID_SUPP_RATES, &ie_len,
 		       pbss_network->ie_length - _BEACON_IE_OFFSET_);
 	if (p) {
+		ie_len = min_t(int, ie_len, NDIS_802_11_LENGTH_RATES_EX);
 		memcpy(supportRate, p + 2, ie_len);
 		supportRateNum = ie_len;
 	}
@@ -819,6 +821,8 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf,  int len)
 	p = rtw_get_ie(ie + _BEACON_IE_OFFSET_, WLAN_EID_EXT_SUPP_RATES,
 		       &ie_len, pbss_network->ie_length - _BEACON_IE_OFFSET_);
 	if (p) {
+		ie_len = min_t(int, ie_len,
+			       NDIS_802_11_LENGTH_RATES_EX - supportRateNum);
 		memcpy(supportRate + supportRateNum, p + 2, ie_len);
 		supportRateNum += ie_len;
 	}
@@ -934,6 +938,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf,  int len)
 
 		pht_cap->mcs.rx_mask[0] = 0xff;
 		pht_cap->mcs.rx_mask[1] = 0x0;
+		ie_len = min_t(int, ie_len, sizeof(pmlmepriv->htpriv.ht_cap));
 		memcpy(&pmlmepriv->htpriv.ht_cap, p + 2, ie_len);
 	}
 

From 74b6b20df8cfe90ada777d621b54c32e69e27cd7 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 5 Mar 2021 11:58:03 +0300
Subject: [PATCH 0492/1820] staging: rtl8188eu: prevent ->ssid overflow in
 rtw_wx_set_scan()

This code has a check to prevent read overflow but it needs another
check to prevent writing beyond the end of the ->ssid[] array.

Fixes: a2c60d42d97c ("staging: r8188eu: Add files for new driver - part 16")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/YEHymwsnHewzoam7@mwanda
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8188eu/os_dep/ioctl_linux.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
index bf22f130d3e1..58954b88a817 100644
--- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
+++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
@@ -1133,9 +1133,11 @@ static int rtw_wx_set_scan(struct net_device *dev, struct iw_request_info *a,
 						break;
 					}
 					sec_len = *(pos++); len -= 1;
-					if (sec_len > 0 && sec_len <= len) {
+					if (sec_len > 0 &&
+					    sec_len <= len &&
+					    sec_len <= 32) {
 						ssid[ssid_index].ssid_length = sec_len;
-						memcpy(ssid[ssid_index].ssid, pos, ssid[ssid_index].ssid_length);
+						memcpy(ssid[ssid_index].ssid, pos, sec_len);
 						ssid_index++;
 					}
 					pos += sec_len;

From 16d7586dccf83785819f5b66f4d20fac9bfcd644 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 9 Mar 2021 15:51:56 +0100
Subject: [PATCH 0493/1820] Revert "staging: wfx: remove unused included header
 files"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 314fd52f01ead9528a5cda5a868425bb736d93a2.

It turns .h files into non-stand-alone when building, which might cause
problems in the long-run.

Reported-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Cc: Muhammad Usama Anjum <musamaanjum@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/wfx/bh.c              | 1 +
 drivers/staging/wfx/bh.h              | 4 ++++
 drivers/staging/wfx/bus.h             | 3 +++
 drivers/staging/wfx/bus_sdio.c        | 6 ++++++
 drivers/staging/wfx/bus_spi.c         | 7 +++++++
 drivers/staging/wfx/data_rx.c         | 5 +++++
 drivers/staging/wfx/data_tx.c         | 5 +++++
 drivers/staging/wfx/data_tx.h         | 3 +++
 drivers/staging/wfx/debug.c           | 6 ++++++
 drivers/staging/wfx/fwio.c            | 2 ++
 drivers/staging/wfx/hif_api_cmd.h     | 4 ++++
 drivers/staging/wfx/hif_api_general.h | 9 +++++++++
 drivers/staging/wfx/hif_tx.c          | 4 ++++
 drivers/staging/wfx/hif_tx_mib.c      | 5 +++++
 drivers/staging/wfx/hwio.c            | 3 +++
 drivers/staging/wfx/hwio.h            | 2 ++
 drivers/staging/wfx/key.c             | 2 ++
 drivers/staging/wfx/key.h             | 2 ++
 drivers/staging/wfx/main.c            | 7 +++++++
 drivers/staging/wfx/main.h            | 3 +++
 drivers/staging/wfx/queue.c           | 4 ++++
 drivers/staging/wfx/queue.h           | 3 +++
 drivers/staging/wfx/scan.h            | 2 ++
 drivers/staging/wfx/sta.c             | 6 ++++++
 drivers/staging/wfx/sta.h             | 2 ++
 drivers/staging/wfx/traces.h          | 3 +++
 drivers/staging/wfx/wfx.h             | 3 +++
 27 files changed, 106 insertions(+)

diff --git a/drivers/staging/wfx/bh.c b/drivers/staging/wfx/bh.c
index cd6bcfdfbe9a..ed53d0b45592 100644
--- a/drivers/staging/wfx/bh.c
+++ b/drivers/staging/wfx/bh.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2017-2020, Silicon Laboratories, Inc.
  * Copyright (c) 2010, ST-Ericsson
  */
+#include <linux/gpio/consumer.h>
 #include <net/mac80211.h>
 
 #include "bh.h"
diff --git a/drivers/staging/wfx/bh.h b/drivers/staging/wfx/bh.h
index 92ef3298d4ac..78c49329e22a 100644
--- a/drivers/staging/wfx/bh.h
+++ b/drivers/staging/wfx/bh.h
@@ -8,6 +8,10 @@
 #ifndef WFX_BH_H
 #define WFX_BH_H
 
+#include <linux/atomic.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+
 struct wfx_dev;
 
 struct wfx_hif {
diff --git a/drivers/staging/wfx/bus.h b/drivers/staging/wfx/bus.h
index ea3911485307..ca04b3da6204 100644
--- a/drivers/staging/wfx/bus.h
+++ b/drivers/staging/wfx/bus.h
@@ -8,6 +8,9 @@
 #ifndef WFX_BUS_H
 #define WFX_BUS_H
 
+#include <linux/mmc/sdio_func.h>
+#include <linux/spi/spi.h>
+
 #define WFX_REG_CONFIG        0x0
 #define WFX_REG_CONTROL       0x1
 #define WFX_REG_IN_OUT_QUEUE  0x2
diff --git a/drivers/staging/wfx/bus_sdio.c b/drivers/staging/wfx/bus_sdio.c
index 588edce44854..e06d7e1ebe9c 100644
--- a/drivers/staging/wfx/bus_sdio.c
+++ b/drivers/staging/wfx/bus_sdio.c
@@ -5,13 +5,19 @@
  * Copyright (c) 2017-2020, Silicon Laboratories, Inc.
  * Copyright (c) 2010, ST-Ericsson
  */
+#include <linux/module.h>
 #include <linux/mmc/sdio.h>
 #include <linux/mmc/sdio_func.h>
 #include <linux/mmc/card.h>
+#include <linux/interrupt.h>
 #include <linux/of_irq.h>
+#include <linux/irq.h>
 
 #include "bus.h"
 #include "wfx.h"
+#include "hwio.h"
+#include "main.h"
+#include "bh.h"
 
 static const struct wfx_platform_data wfx_sdio_pdata = {
 	.file_fw = "wfm_wf200",
diff --git a/drivers/staging/wfx/bus_spi.c b/drivers/staging/wfx/bus_spi.c
index f89855abe9f8..a99125d1a30d 100644
--- a/drivers/staging/wfx/bus_spi.c
+++ b/drivers/staging/wfx/bus_spi.c
@@ -6,12 +6,19 @@
  * Copyright (c) 2011, Sagrad Inc.
  * Copyright (c) 2010, ST-Ericsson
  */
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 #include <linux/spi/spi.h>
+#include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/of.h>
 
 #include "bus.h"
 #include "wfx.h"
+#include "hwio.h"
+#include "main.h"
+#include "bh.h"
 
 #define SET_WRITE 0x7FFF        /* usage: and operation */
 #define SET_READ 0x8000         /* usage: or operation */
diff --git a/drivers/staging/wfx/data_rx.c b/drivers/staging/wfx/data_rx.c
index 2cfa16279220..385f2d42a0e2 100644
--- a/drivers/staging/wfx/data_rx.c
+++ b/drivers/staging/wfx/data_rx.c
@@ -5,8 +5,13 @@
  * Copyright (c) 2017-2020, Silicon Laboratories, Inc.
  * Copyright (c) 2010, ST-Ericsson
  */
+#include <linux/etherdevice.h>
+#include <net/mac80211.h>
+
 #include "data_rx.h"
 #include "wfx.h"
+#include "bh.h"
+#include "sta.h"
 
 static void wfx_rx_handle_ba(struct wfx_vif *wvif, struct ieee80211_mgmt *mgmt)
 {
diff --git a/drivers/staging/wfx/data_tx.c b/drivers/staging/wfx/data_tx.c
index 76f26e3c4381..77fb104efdec 100644
--- a/drivers/staging/wfx/data_tx.c
+++ b/drivers/staging/wfx/data_tx.c
@@ -6,9 +6,14 @@
  * Copyright (c) 2010, ST-Ericsson
  */
 #include <net/mac80211.h>
+#include <linux/etherdevice.h>
 
+#include "data_tx.h"
 #include "wfx.h"
+#include "bh.h"
 #include "sta.h"
+#include "queue.h"
+#include "debug.h"
 #include "traces.h"
 #include "hif_tx_mib.h"
 
diff --git a/drivers/staging/wfx/data_tx.h b/drivers/staging/wfx/data_tx.h
index 6b3020097efa..401363d6b563 100644
--- a/drivers/staging/wfx/data_tx.h
+++ b/drivers/staging/wfx/data_tx.h
@@ -8,6 +8,9 @@
 #ifndef WFX_DATA_TX_H
 #define WFX_DATA_TX_H
 
+#include <linux/list.h>
+#include <net/mac80211.h>
+
 #include "hif_api_cmd.h"
 #include "hif_api_mib.h"
 
diff --git a/drivers/staging/wfx/debug.c b/drivers/staging/wfx/debug.c
index 3e87d13eb358..eedada78c25f 100644
--- a/drivers/staging/wfx/debug.c
+++ b/drivers/staging/wfx/debug.c
@@ -5,9 +5,15 @@
  * Copyright (c) 2017-2020, Silicon Laboratories, Inc.
  * Copyright (c) 2010, ST-Ericsson
  */
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/crc32.h>
+
 #include "debug.h"
 #include "wfx.h"
 #include "sta.h"
+#include "main.h"
+#include "hif_tx.h"
 #include "hif_tx_mib.h"
 
 #define CREATE_TRACE_POINTS
diff --git a/drivers/staging/wfx/fwio.c b/drivers/staging/wfx/fwio.c
index 1bb9054871c4..1b8aec02d169 100644
--- a/drivers/staging/wfx/fwio.c
+++ b/drivers/staging/wfx/fwio.c
@@ -6,6 +6,8 @@
  * Copyright (c) 2010, ST-Ericsson
  */
 #include <linux/firmware.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
 #include <linux/bitfield.h>
 
 #include "fwio.h"
diff --git a/drivers/staging/wfx/hif_api_cmd.h b/drivers/staging/wfx/hif_api_cmd.h
index 8b671c9ab97c..58c9bb036011 100644
--- a/drivers/staging/wfx/hif_api_cmd.h
+++ b/drivers/staging/wfx/hif_api_cmd.h
@@ -8,6 +8,10 @@
 #ifndef WFX_HIF_API_CMD_H
 #define WFX_HIF_API_CMD_H
 
+#include <linux/ieee80211.h>
+
+#include "hif_api_general.h"
+
 enum hif_requests_ids {
 	HIF_REQ_ID_RESET                = 0x0a,
 	HIF_REQ_ID_READ_MIB             = 0x05,
diff --git a/drivers/staging/wfx/hif_api_general.h b/drivers/staging/wfx/hif_api_general.h
index 70b253d0265d..24188945718d 100644
--- a/drivers/staging/wfx/hif_api_general.h
+++ b/drivers/staging/wfx/hif_api_general.h
@@ -8,6 +8,15 @@
 #ifndef WFX_HIF_API_GENERAL_H
 #define WFX_HIF_API_GENERAL_H
 
+#ifdef __KERNEL__
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#else
+#include <net/ethernet.h>
+#include <stdint.h>
+#define __packed __attribute__((__packed__))
+#endif
+
 #define HIF_ID_IS_INDICATION      0x80
 #define HIF_COUNTER_MAX           7
 
diff --git a/drivers/staging/wfx/hif_tx.c b/drivers/staging/wfx/hif_tx.c
index 17dc13321978..63b437261eb7 100644
--- a/drivers/staging/wfx/hif_tx.c
+++ b/drivers/staging/wfx/hif_tx.c
@@ -6,7 +6,11 @@
  * Copyright (c) 2017-2020, Silicon Laboratories, Inc.
  * Copyright (c) 2010, ST-Ericsson
  */
+#include <linux/etherdevice.h>
+
+#include "hif_tx.h"
 #include "wfx.h"
+#include "bh.h"
 #include "hwio.h"
 #include "debug.h"
 #include "sta.h"
diff --git a/drivers/staging/wfx/hif_tx_mib.c b/drivers/staging/wfx/hif_tx_mib.c
index 6432ed86505c..1926cf1b62be 100644
--- a/drivers/staging/wfx/hif_tx_mib.c
+++ b/drivers/staging/wfx/hif_tx_mib.c
@@ -6,8 +6,13 @@
  * Copyright (c) 2010, ST-Ericsson
  * Copyright (C) 2010, ST-Ericsson SA
  */
+
+#include <linux/etherdevice.h>
+
 #include "wfx.h"
+#include "hif_tx.h"
 #include "hif_tx_mib.h"
+#include "hif_api_mib.h"
 
 int hif_set_output_power(struct wfx_vif *wvif, int val)
 {
diff --git a/drivers/staging/wfx/hwio.c b/drivers/staging/wfx/hwio.c
index 089bb41be149..36fbc5b5d64c 100644
--- a/drivers/staging/wfx/hwio.c
+++ b/drivers/staging/wfx/hwio.c
@@ -5,10 +5,13 @@
  * Copyright (c) 2017-2020, Silicon Laboratories, Inc.
  * Copyright (c) 2010, ST-Ericsson
  */
+#include <linux/kernel.h>
+#include <linux/delay.h>
 #include <linux/slab.h>
 
 #include "hwio.h"
 #include "wfx.h"
+#include "bus.h"
 #include "traces.h"
 
 /*
diff --git a/drivers/staging/wfx/hwio.h b/drivers/staging/wfx/hwio.h
index 8bb9bcfc3182..0b8e4f7157df 100644
--- a/drivers/staging/wfx/hwio.h
+++ b/drivers/staging/wfx/hwio.h
@@ -8,6 +8,8 @@
 #ifndef WFX_HWIO_H
 #define WFX_HWIO_H
 
+#include <linux/types.h>
+
 struct wfx_dev;
 
 int wfx_data_read(struct wfx_dev *wdev, void *buf, size_t buf_len);
diff --git a/drivers/staging/wfx/key.c b/drivers/staging/wfx/key.c
index c93d07dcdc10..2ab82bed4c1b 100644
--- a/drivers/staging/wfx/key.c
+++ b/drivers/staging/wfx/key.c
@@ -5,10 +5,12 @@
  * Copyright (c) 2017-2020, Silicon Laboratories, Inc.
  * Copyright (c) 2010, ST-Ericsson
  */
+#include <linux/etherdevice.h>
 #include <net/mac80211.h>
 
 #include "key.h"
 #include "wfx.h"
+#include "hif_tx_mib.h"
 
 static int wfx_alloc_key(struct wfx_dev *wdev)
 {
diff --git a/drivers/staging/wfx/key.h b/drivers/staging/wfx/key.h
index 4dc9feadaba2..70a44d0ca35e 100644
--- a/drivers/staging/wfx/key.h
+++ b/drivers/staging/wfx/key.h
@@ -8,6 +8,8 @@
 #ifndef WFX_KEY_H
 #define WFX_KEY_H
 
+#include <net/mac80211.h>
+
 struct wfx_dev;
 struct wfx_vif;
 
diff --git a/drivers/staging/wfx/main.c b/drivers/staging/wfx/main.c
index b9ea9a93fe1a..e7bc1988124a 100644
--- a/drivers/staging/wfx/main.c
+++ b/drivers/staging/wfx/main.c
@@ -10,21 +10,28 @@
  * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
  * Copyright (c) 2004-2006 Jean-Baptiste Note <jbnote@gmail.com>, et al.
  */
+#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
+#include <linux/gpio/consumer.h>
 #include <linux/mmc/sdio_func.h>
 #include <linux/spi/spi.h>
+#include <linux/etherdevice.h>
 #include <linux/firmware.h>
 
+#include "main.h"
 #include "wfx.h"
 #include "fwio.h"
 #include "hwio.h"
 #include "bus.h"
+#include "bh.h"
 #include "sta.h"
 #include "key.h"
 #include "scan.h"
 #include "debug.h"
+#include "data_tx.h"
 #include "hif_tx_mib.h"
+#include "hif_api_cmd.h"
 
 #define WFX_PDS_MAX_SIZE 1500
 
diff --git a/drivers/staging/wfx/main.h b/drivers/staging/wfx/main.h
index 086bcc041b90..a0db322383a3 100644
--- a/drivers/staging/wfx/main.h
+++ b/drivers/staging/wfx/main.h
@@ -10,8 +10,11 @@
 #ifndef WFX_MAIN_H
 #define WFX_MAIN_H
 
+#include <linux/device.h>
 #include <linux/gpio/consumer.h>
 
+#include "hif_api_general.h"
+
 struct wfx_dev;
 struct hwbus_ops;
 
diff --git a/drivers/staging/wfx/queue.c b/drivers/staging/wfx/queue.c
index 3bddf282a4ce..31c37f69c295 100644
--- a/drivers/staging/wfx/queue.c
+++ b/drivers/staging/wfx/queue.c
@@ -5,9 +5,13 @@
  * Copyright (c) 2017-2020, Silicon Laboratories, Inc.
  * Copyright (c) 2010, ST-Ericsson
  */
+#include <linux/sched.h>
 #include <net/mac80211.h>
 
+#include "queue.h"
 #include "wfx.h"
+#include "sta.h"
+#include "data_tx.h"
 #include "traces.h"
 
 void wfx_tx_lock(struct wfx_dev *wdev)
diff --git a/drivers/staging/wfx/queue.h b/drivers/staging/wfx/queue.h
index e43aa9dfbc45..80ba19455ef3 100644
--- a/drivers/staging/wfx/queue.h
+++ b/drivers/staging/wfx/queue.h
@@ -8,6 +8,9 @@
 #ifndef WFX_QUEUE_H
 #define WFX_QUEUE_H
 
+#include <linux/skbuff.h>
+#include <linux/atomic.h>
+
 struct wfx_dev;
 struct wfx_vif;
 
diff --git a/drivers/staging/wfx/scan.h b/drivers/staging/wfx/scan.h
index e5b7eef78858..c7496a766478 100644
--- a/drivers/staging/wfx/scan.h
+++ b/drivers/staging/wfx/scan.h
@@ -8,6 +8,8 @@
 #ifndef WFX_SCAN_H
 #define WFX_SCAN_H
 
+#include <net/mac80211.h>
+
 struct wfx_dev;
 struct wfx_vif;
 
diff --git a/drivers/staging/wfx/sta.c b/drivers/staging/wfx/sta.c
index 5585f9e876e1..196779a1b89a 100644
--- a/drivers/staging/wfx/sta.c
+++ b/drivers/staging/wfx/sta.c
@@ -5,11 +5,17 @@
  * Copyright (c) 2017-2020, Silicon Laboratories, Inc.
  * Copyright (c) 2010, ST-Ericsson
  */
+#include <linux/etherdevice.h>
 #include <net/mac80211.h>
 
 #include "sta.h"
 #include "wfx.h"
+#include "fwio.h"
+#include "bh.h"
+#include "key.h"
 #include "scan.h"
+#include "debug.h"
+#include "hif_tx.h"
 #include "hif_tx_mib.h"
 
 #define HIF_MAX_ARP_IP_ADDRTABLE_ENTRIES 2
diff --git a/drivers/staging/wfx/sta.h b/drivers/staging/wfx/sta.h
index a3fb9fc93fa4..d7b5df5ea4e6 100644
--- a/drivers/staging/wfx/sta.h
+++ b/drivers/staging/wfx/sta.h
@@ -8,6 +8,8 @@
 #ifndef WFX_STA_H
 #define WFX_STA_H
 
+#include <net/mac80211.h>
+
 struct wfx_dev;
 struct wfx_vif;
 
diff --git a/drivers/staging/wfx/traces.h b/drivers/staging/wfx/traces.h
index afe1074e09b3..e34c7a538c65 100644
--- a/drivers/staging/wfx/traces.h
+++ b/drivers/staging/wfx/traces.h
@@ -12,8 +12,11 @@
 #define _WFX_TRACE_H
 
 #include <linux/tracepoint.h>
+#include <net/mac80211.h>
 
 #include "bus.h"
+#include "hif_api_cmd.h"
+#include "hif_api_mib.h"
 
 /* The hell below need some explanations. For each symbolic number, we need to
  * define it with TRACE_DEFINE_ENUM() and in a list for __print_symbolic.
diff --git a/drivers/staging/wfx/wfx.h b/drivers/staging/wfx/wfx.h
index a185b82795c4..94898680ccde 100644
--- a/drivers/staging/wfx/wfx.h
+++ b/drivers/staging/wfx/wfx.h
@@ -10,6 +10,9 @@
 #ifndef WFX_H
 #define WFX_H
 
+#include <linux/completion.h>
+#include <linux/workqueue.h>
+#include <linux/mutex.h>
 #include <linux/nospec.h>
 #include <net/mac80211.h>
 

From 1487e7bae809d73461940a6ef8c1ffc7c4faa0d3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 19 Feb 2021 14:33:06 +0100
Subject: [PATCH 0494/1820] leds: trigger: Fix error path to not unlock the
 unlocked mutex
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ttyname is allocated before the mutex is taken, so it must not be
unlocked in the error path.

Fixes: fd4a641ac88f ("leds: trigger: implement a tty trigger")
Reported-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20210219133307.4840-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/leds/trigger/ledtrig-tty.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-tty.c b/drivers/leds/trigger/ledtrig-tty.c
index d2ab6ab080ac..af61281dc6a1 100644
--- a/drivers/leds/trigger/ledtrig-tty.c
+++ b/drivers/leds/trigger/ledtrig-tty.c
@@ -51,10 +51,8 @@ static ssize_t ttyname_store(struct device *dev,
 
 	if (size) {
 		ttyname = kmemdup_nul(buf, size, GFP_KERNEL);
-		if (!ttyname) {
-			ret = -ENOMEM;
-			goto out_unlock;
-		}
+		if (!ttyname)
+			return -ENOMEM;
 	} else {
 		ttyname = NULL;
 	}
@@ -69,7 +67,6 @@ static ssize_t ttyname_store(struct device *dev,
 
 	trigger_data->ttyname = ttyname;
 
-out_unlock:
 	mutex_unlock(&trigger_data->mutex);
 
 	if (ttyname && !running)

From ba8a86e4dadb332c41454f02e27d28321e0f03d5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 19 Feb 2021 14:33:07 +0100
Subject: [PATCH 0495/1820] leds: trigger/tty: Use led_set_brightness_sync()
 from workqueue
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

led_set_brightness() involves scheduling a workqueue. As here the led's
brightness setting is done in context of the trigger's workqueue this is
unjustified overhead and it's more sensible to use
led_set_brightness_sync().

Fixes: fd4a641ac88f ("leds: trigger: implement a tty trigger")
Reported-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20210219133307.4840-3-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/leds/trigger/ledtrig-tty.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-tty.c b/drivers/leds/trigger/ledtrig-tty.c
index af61281dc6a1..f62db7e520b5 100644
--- a/drivers/leds/trigger/ledtrig-tty.c
+++ b/drivers/leds/trigger/ledtrig-tty.c
@@ -122,12 +122,12 @@ static void ledtrig_tty_work(struct work_struct *work)
 
 	if (icount.rx != trigger_data->rx ||
 	    icount.tx != trigger_data->tx) {
-		led_set_brightness(trigger_data->led_cdev, LED_ON);
+		led_set_brightness_sync(trigger_data->led_cdev, LED_ON);
 
 		trigger_data->rx = icount.rx;
 		trigger_data->tx = icount.tx;
 	} else {
-		led_set_brightness(trigger_data->led_cdev, LED_OFF);
+		led_set_brightness_sync(trigger_data->led_cdev, LED_OFF);
 	}
 
 out:

From 2334de198fed3da72e9785ecdd691d101aa96e77 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Wed, 17 Feb 2021 11:06:08 +0300
Subject: [PATCH 0496/1820] Revert "serial: max310x: rework RX interrupt
 handling"

This reverts commit fce3c5c1a2d9cd888f2987662ce17c0c651916b2.

FIFO is triggered 4 intervals after receiving a byte, it's good
when we don't care about the time of reception, but are only
interested in the presence of any activity on the line.
Unfortunately, this method is not suitable for all tasks,
for example, the RS-485 protocol will not work properly,
since the state machine must track the request-response time
and after the timeout expires, a decision is made that the device
on the line is not responding.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Link: https://lore.kernel.org/r/20210217080608.31192-1-shc_work@mail.ru
Fixes: fce3c5c1a2d9 ("serial: max310x: rework RX interrupt handling")
Cc: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/max310x.c | 29 +++++------------------------
 1 file changed, 5 insertions(+), 24 deletions(-)

diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 9795b2e8b0b2..1b61d26bb7af 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -1056,9 +1056,9 @@ static int max310x_startup(struct uart_port *port)
 	max310x_port_update(port, MAX310X_MODE1_REG,
 			    MAX310X_MODE1_TRNSCVCTRL_BIT, 0);
 
-	/* Reset FIFOs */
-	max310x_port_write(port, MAX310X_MODE2_REG,
-			   MAX310X_MODE2_FIFORST_BIT);
+	/* Configure MODE2 register & Reset FIFOs*/
+	val = MAX310X_MODE2_RXEMPTINV_BIT | MAX310X_MODE2_FIFORST_BIT;
+	max310x_port_write(port, MAX310X_MODE2_REG, val);
 	max310x_port_update(port, MAX310X_MODE2_REG,
 			    MAX310X_MODE2_FIFORST_BIT, 0);
 
@@ -1086,27 +1086,8 @@ static int max310x_startup(struct uart_port *port)
 	/* Clear IRQ status register */
 	max310x_port_read(port, MAX310X_IRQSTS_REG);
 
-	/*
-	 * Let's ask for an interrupt after a timeout equivalent to
-	 * the receiving time of 4 characters after the last character
-	 * has been received.
-	 */
-	max310x_port_write(port, MAX310X_RXTO_REG, 4);
-
-	/*
-	 * Make sure we also get RX interrupts when the RX FIFO is
-	 * filling up quickly, so get an interrupt when half of the RX
-	 * FIFO has been filled in.
-	 */
-	max310x_port_write(port, MAX310X_FIFOTRIGLVL_REG,
-			   MAX310X_FIFOTRIGLVL_RX(MAX310X_FIFO_SIZE / 2));
-
-	/* Enable RX timeout interrupt in LSR */
-	max310x_port_write(port, MAX310X_LSR_IRQEN_REG,
-			   MAX310X_LSR_RXTO_BIT);
-
-	/* Enable LSR, RX FIFO trigger, CTS change interrupts */
-	val = MAX310X_IRQ_LSR_BIT  | MAX310X_IRQ_RXFIFO_BIT | MAX310X_IRQ_TXEMPTY_BIT;
+	/* Enable RX, TX, CTS change interrupts */
+	val = MAX310X_IRQ_RXEMPTY_BIT | MAX310X_IRQ_TXEMPTY_BIT;
 	max310x_port_write(port, MAX310X_IRQEN_REG, val | MAX310X_IRQ_CTS_BIT);
 
 	return 0;

From c776b77a279c327fe9e7710e71a3400766554255 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Thu, 4 Mar 2021 17:18:02 +0100
Subject: [PATCH 0497/1820] Revert "drivers:tty:pty: Fix a race causing data
 loss on close"

This reverts commit 33d4ae98859873ddd49e22e4ca724387548b3d89.

Pierre-Louis writes:

	Our SOF/audio CI shows an across-the-board regression when we try v5.12-rc1,
	specifically on pause/resume tests with an interactive terminal running 'aplay
	-i' commands managed by expect to simulate the user pressing the space bar to
	pause/unpause. It turns out the processes are not longer killed and the audio
	devices remain busy (see publicly available test results listed below).

	git bisect points to commit 33d4ae9885987 ("drivers:tty:pty: Fix a race
	causing data loss on close"). Reverting the patch fixes the issue on all test
	devices.

	Further analysis with Corey Minyard points to a problem where a slave tty will
	not get a SIGHUP when the master is closed.

So revert this for now:

Reported-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/00154592-c5ee-aaba-956e-b265473b53bc@linux.intel.com
Cc: Corey Minyard <cminyard@mvista.com>
Cc: Jiri Slaby <jirislaby@kernel.org>
Cc: Mark Brown <broonie@kernel.org>,
Fixes: 33d4ae988598 ("drivers:tty:pty: Fix a race causing data loss on close")
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/pty.c    | 15 ++-------------
 drivers/tty/tty_io.c |  5 ++---
 2 files changed, 4 insertions(+), 16 deletions(-)

diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 8b2797b6ee44..5e2374580e27 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -66,8 +66,7 @@ static void pty_close(struct tty_struct *tty, struct file *filp)
 	wake_up_interruptible(&tty->link->read_wait);
 	wake_up_interruptible(&tty->link->write_wait);
 	if (tty->driver->subtype == PTY_TYPE_MASTER) {
-		struct file *f;
-
+		set_bit(TTY_OTHER_CLOSED, &tty->flags);
 #ifdef CONFIG_UNIX98_PTYS
 		if (tty->driver == ptm_driver) {
 			mutex_lock(&devpts_mutex);
@@ -76,17 +75,7 @@ static void pty_close(struct tty_struct *tty, struct file *filp)
 			mutex_unlock(&devpts_mutex);
 		}
 #endif
-
-		/*
-		 * This hack is required because a program can open a
-		 * pty and redirect a console to it, but if the pty is
-		 * closed and the console is not released, then the
-		 * slave side will never close.  So release the
-		 * redirect when the master closes.
-		 */
-		f = tty_release_redirect(tty->link);
-		if (f)
-			fput(f);
+		tty_vhangup(tty->link);
 	}
 }
 
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 74733ec8f565..391bada4cedb 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -544,9 +544,7 @@ EXPORT_SYMBOL_GPL(tty_wakeup);
  *	@tty: tty device
  *
  *	This is available to the pty code so if the master closes, if the
- *	slave is a redirect it can release the redirect.  It returns the
- *	filp for the redirect, which must be fput when the operations on
- *	the tty are completed.
+ *	slave is a redirect it can release the redirect.
  */
 struct file *tty_release_redirect(struct tty_struct *tty)
 {
@@ -561,6 +559,7 @@ struct file *tty_release_redirect(struct tty_struct *tty)
 
 	return f;
 }
+EXPORT_SYMBOL_GPL(tty_release_redirect);
 
 /**
  *	__tty_hangup		-	actual handler for hangup events

From 4d8654e81db7346f915eca9f1aff18f385cab621 Mon Sep 17 00:00:00 2001
From: Yorick de Wid <ydewid@gmail.com>
Date: Sat, 13 Feb 2021 15:49:02 +0100
Subject: [PATCH 0498/1820] Goodix Fingerprint device is not a modem

The CDC ACM driver is false matching the Goodix Fingerprint device
against the USB_CDC_ACM_PROTO_AT_V25TER.

The Goodix Fingerprint device is a biometrics sensor that should be
handled in user-space. libfprint has some support for Goodix
fingerprint sensors, although not for this particular one. It is
possible that the vendor allocates a PID per OEM (Lenovo, Dell etc).
If this happens to be the case then more devices from the same vendor
could potentially match the ACM modem module table.

Signed-off-by: Yorick de Wid <ydewid@gmail.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210213144901.53199-1-ydewid@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 37f824b59daa..39ddb5585ded 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1935,6 +1935,11 @@ static const struct usb_device_id acm_ids[] = {
 	.driver_info = SEND_ZERO_PACKET,
 	},
 
+	/* Exclude Goodix Fingerprint Reader */
+	{ USB_DEVICE(0x27c6, 0x5395),
+	.driver_info = IGNORE_DEVICE,
+	},
+
 	/* control interfaces without any protocol set */
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
 		USB_CDC_PROTO_NONE) },

From 1edbff9c80ed32071fffa7dbaaea507fdb21ff2d Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Mon, 1 Mar 2021 15:57:45 +0800
Subject: [PATCH 0499/1820] usb: dwc3: qcom: add ACPI device id for sc8180x

It enables USB Host support for sc8180x ACPI boot, both the standalone
one and the one behind URS (USB Role Switch).  And they share the
the same dwc3_acpi_pdata with sdm845.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Link: https://lore.kernel.org/r/20210301075745.20544-1-shawn.guo@linaro.org
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-qcom.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index 846a47be6df7..d8850f9ccb62 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -938,6 +938,8 @@ static const struct dwc3_acpi_pdata sdm845_acpi_urs_pdata = {
 static const struct acpi_device_id dwc3_qcom_acpi_match[] = {
 	{ "QCOM2430", (unsigned long)&sdm845_acpi_pdata },
 	{ "QCOM0304", (unsigned long)&sdm845_acpi_urs_pdata },
+	{ "QCOM0497", (unsigned long)&sdm845_acpi_urs_pdata },
+	{ "QCOM04A6", (unsigned long)&sdm845_acpi_pdata },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, dwc3_qcom_acpi_match);

From 650bf52208d804ad5ee449c58102f8dc43175573 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 15 Feb 2021 15:57:16 +0000
Subject: [PATCH 0500/1820] USB: gadget: u_ether: Fix a configfs return code

If the string is invalid, this should return -EINVAL instead of 0.

Fixes: 73517cf49bd4 ("usb: gadget: add RNDIS configfs options for class/subclass/protocol")
Cc: stable <stable@vger.kernel.org>
Acked-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Link: https://lore.kernel.org/r/YCqZ3P53yyIg5cn7@mwanda
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether_configfs.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h
index 3dfb460908fa..f558c3139ebe 100644
--- a/drivers/usb/gadget/function/u_ether_configfs.h
+++ b/drivers/usb/gadget/function/u_ether_configfs.h
@@ -182,12 +182,11 @@ out:									\
 						size_t len)		\
 	{								\
 		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);	\
-		int ret;						\
+		int ret = -EINVAL;					\
 		u8 val;							\
 									\
 		mutex_lock(&opts->lock);				\
-		ret = sscanf(page, "%02hhx", &val);			\
-		if (ret > 0) {						\
+		if (sscanf(page, "%02hhx", &val) > 0) {			\
 			opts->_n_ = val;				\
 			ret = len;					\
 		}							\

From 789ea77310f0200c84002884ffd628e2baf3ad8a Mon Sep 17 00:00:00 2001
From: Ruslan Bilovol <ruslan.bilovol@gmail.com>
Date: Mon, 1 Mar 2021 13:49:31 +0200
Subject: [PATCH 0501/1820] usb: gadget: f_uac2: always increase endpoint
 max_packet_size by one audio slot

As per UAC2 Audio Data Formats spec (2.3.1.1 USB Packets),
if the sampling rate is a constant, the allowable variation
of number of audio slots per virtual frame is +/- 1 audio slot.

It means that endpoint should be able to accept/send +1 audio
slot.

Previous endpoint max_packet_size calculation code
was adding sometimes +1 audio slot due to DIV_ROUND_UP
behaviour which was rounding up to closest integer.
However this doesn't work if the numbers are divisible.

It had no any impact with Linux hosts which ignore
this issue, but in case of more strict Windows it
caused rejected enumeration

Thus always add +1 audio slot to endpoint's max packet size

Fixes: 913e4a90b6f9 ("usb: gadget: f_uac2: finalize wMaxPacketSize according to bandwidth")
Cc: Peter Chen <peter.chen@freescale.com>
Cc: <stable@vger.kernel.org> #v4.3+
Signed-off-by: Ruslan Bilovol <ruslan.bilovol@gmail.com>
Link: https://lore.kernel.org/r/1614599375-8803-2-git-send-email-ruslan.bilovol@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_uac2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index 5d960b6603b6..6f03e944e0e3 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -478,7 +478,7 @@ static int set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts,
 	}
 
 	max_size_bw = num_channels(chmask) * ssize *
-		DIV_ROUND_UP(srate, factor / (1 << (ep_desc->bInterval - 1)));
+		((srate / (factor / (1 << (ep_desc->bInterval - 1)))) + 1);
 	ep_desc->wMaxPacketSize = cpu_to_le16(min_t(u16, max_size_bw,
 						    max_size_ep));
 

From cc2ac63d4cf72104e0e7f58bb846121f0f51bb19 Mon Sep 17 00:00:00 2001
From: Ruslan Bilovol <ruslan.bilovol@gmail.com>
Date: Mon, 1 Mar 2021 13:49:32 +0200
Subject: [PATCH 0502/1820] usb: gadget: f_uac1: stop playback on function
 disable

There is missing playback stop/cleanup in case of
gadget's ->disable callback that happens on
events like USB host resetting or gadget disconnection

Fixes: 0591bc236015 ("usb: gadget: add f_uac1 variant based on a new u_audio api")
Cc: <stable@vger.kernel.org> # 4.13+
Signed-off-by: Ruslan Bilovol <ruslan.bilovol@gmail.com>
Link: https://lore.kernel.org/r/1614599375-8803-3-git-send-email-ruslan.bilovol@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_uac1.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/gadget/function/f_uac1.c b/drivers/usb/gadget/function/f_uac1.c
index 00d346965f7a..560382e0a8f3 100644
--- a/drivers/usb/gadget/function/f_uac1.c
+++ b/drivers/usb/gadget/function/f_uac1.c
@@ -499,6 +499,7 @@ static void f_audio_disable(struct usb_function *f)
 	uac1->as_out_alt = 0;
 	uac1->as_in_alt = 0;
 
+	u_audio_stop_playback(&uac1->g_audio);
 	u_audio_stop_capture(&uac1->g_audio);
 }
 

From 2664deb0930643149d61cddbb66ada527ae180bd Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <mka@chromium.org>
Date: Tue, 2 Mar 2021 10:37:03 -0800
Subject: [PATCH 0503/1820] usb: dwc3: qcom: Honor wakeup enabled/disabled
 state

The dwc3-qcom currently enables wakeup interrupts unconditionally
when suspending, however this should not be done when wakeup is
disabled (e.g. through the sysfs attribute power/wakeup). Only
enable wakeup interrupts when device_may_wakeup() returns true.

Fixes: a4333c3a6ba9 ("usb: dwc3: Add Qualcomm DWC3 glue driver")
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210302103659.v2.1.I44954d9e1169f2cf5c44e6454d357c75ddfa99a2@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-qcom.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index d8850f9ccb62..730e8d6a2aa6 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -358,8 +358,10 @@ static int dwc3_qcom_suspend(struct dwc3_qcom *qcom)
 	if (ret)
 		dev_warn(qcom->dev, "failed to disable interconnect: %d\n", ret);
 
+	if (device_may_wakeup(qcom->dev))
+		dwc3_qcom_enable_interrupts(qcom);
+
 	qcom->is_suspended = true;
-	dwc3_qcom_enable_interrupts(qcom);
 
 	return 0;
 }
@@ -372,7 +374,8 @@ static int dwc3_qcom_resume(struct dwc3_qcom *qcom)
 	if (!qcom->is_suspended)
 		return 0;
 
-	dwc3_qcom_disable_interrupts(qcom);
+	if (device_may_wakeup(qcom->dev))
+		dwc3_qcom_disable_interrupts(qcom);
 
 	for (i = 0; i < qcom->num_clocks; i++) {
 		ret = clk_prepare_enable(qcom->clks[i]);

From b1d25e6ee57c2605845595b6c61340d734253eb3 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Mon, 8 Mar 2021 10:55:38 +0900
Subject: [PATCH 0504/1820] usb: renesas_usbhs: Clear PIPECFG for re-enabling
 pipe with other EPNUM

According to the datasheet, this controller has a restriction
which "set an endpoint number so that combinations of the DIR bit and
the EPNUM bits do not overlap.". However, since the udc core driver is
possible to assign a bulk pipe as an interrupt endpoint, an endpoint
number may not match the pipe number. After that, when user rebinds
another gadget driver, this driver broke the restriction because
the driver didn't clear any configuration in usb_ep_disable().

Example:
 # modprobe g_ncm
 Then, EP3 = pipe 3, EP4 = pipe 4, EP5 = pipe 6
 # rmmod g_ncm
 # modprobe g_hid
 Then, EP3 = pipe 6, EP4 = pipe 7.
 So, pipe 3 and pipe 6 are set as EP3.

So, clear PIPECFG register in usbhs_pipe_free().

Fixes: dfb87b8bfe09 ("usb: renesas_usbhs: gadget: fix re-enabling pipe without re-connecting")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/1615168538-26101-1-git-send-email-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/renesas_usbhs/pipe.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/renesas_usbhs/pipe.c b/drivers/usb/renesas_usbhs/pipe.c
index e7334b7fb3a6..75fff2e4cbc6 100644
--- a/drivers/usb/renesas_usbhs/pipe.c
+++ b/drivers/usb/renesas_usbhs/pipe.c
@@ -746,6 +746,8 @@ struct usbhs_pipe *usbhs_pipe_malloc(struct usbhs_priv *priv,
 
 void usbhs_pipe_free(struct usbhs_pipe *pipe)
 {
+	usbhsp_pipe_select(pipe);
+	usbhsp_pipe_cfg_set(pipe, 0xFFFF, 0);
 	usbhsp_put_pipe(pipe);
 }
 

From 414c20df7d401bcf1cb6c13d2dd944fb53ae4acf Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Fri, 5 Mar 2021 03:49:27 +0000
Subject: [PATCH 0505/1820] USB: gadget: udc: s3c2410_udc: fix return value
 check in s3c2410_udc_probe()

In case of error, the function devm_platform_ioremap_resource()
returns ERR_PTR() and never returns NULL. The NULL test in the
return value check should be replaced with IS_ERR().

Fixes: 188db4435ac6 ("usb: gadget: s3c: use platform resources")
Cc: stable <stable@vger.kernel.org>
Reported-by: Hulk Robot <hulkci@huawei.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Link: https://lore.kernel.org/r/20210305034927.3232386-1-weiyongjun1@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/s3c2410_udc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/udc/s3c2410_udc.c b/drivers/usb/gadget/udc/s3c2410_udc.c
index f1ea51476add..1d3ebb07ccd4 100644
--- a/drivers/usb/gadget/udc/s3c2410_udc.c
+++ b/drivers/usb/gadget/udc/s3c2410_udc.c
@@ -1773,8 +1773,8 @@ static int s3c2410_udc_probe(struct platform_device *pdev)
 	udc_info = dev_get_platdata(&pdev->dev);
 
 	base_addr = devm_platform_ioremap_resource(pdev, 0);
-	if (!base_addr) {
-		retval = -ENOMEM;
+	if (IS_ERR(base_addr)) {
+		retval = PTR_ERR(base_addr);
 		goto err_mem;
 	}
 

From 9de2c43acf37a17dc4c69ff78bb099b80fb74325 Mon Sep 17 00:00:00 2001
From: Pete Zaitcev <zaitcev@redhat.com>
Date: Wed, 3 Mar 2021 22:10:53 -0600
Subject: [PATCH 0506/1820] USB: usblp: fix a hang in poll() if disconnected

Apparently an application that opens a device and calls select()
on it, will hang if the decice is disconnected. It's a little
surprising that we had this bug for 15 years, but apparently
nobody ever uses select() with a printer: only write() and read(),
and those work fine. Well, you can also select() with a timeout.

The fix is modeled after devio.c. A few other drivers check the
condition first, then do not add the wait queue in case the
device is disconnected. We doubt that's completely race-free.
So, this patch adds the process first, then locks properly
and checks for the disconnect.

Reviewed-by: Zqiang <qiang.zhang@windriver.com>
Signed-off-by: Pete Zaitcev <zaitcev@redhat.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210303221053.1cf3313e@suzdal.zaitcev.lan
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/usblp.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index c9f6e9758288..f27b4aecff3d 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -494,16 +494,24 @@ static int usblp_release(struct inode *inode, struct file *file)
 /* No kernel lock - fine */
 static __poll_t usblp_poll(struct file *file, struct poll_table_struct *wait)
 {
-	__poll_t ret;
+	struct usblp *usblp = file->private_data;
+	__poll_t ret = 0;
 	unsigned long flags;
 
-	struct usblp *usblp = file->private_data;
 	/* Should we check file->f_mode & FMODE_WRITE before poll_wait()? */
 	poll_wait(file, &usblp->rwait, wait);
 	poll_wait(file, &usblp->wwait, wait);
+
+	mutex_lock(&usblp->mut);
+	if (!usblp->present)
+		ret |= EPOLLHUP;
+	mutex_unlock(&usblp->mut);
+
 	spin_lock_irqsave(&usblp->lock, flags);
-	ret = ((usblp->bidir && usblp->rcomplete) ? EPOLLIN  | EPOLLRDNORM : 0) |
-	   ((usblp->no_paper || usblp->wcomplete) ? EPOLLOUT | EPOLLWRNORM : 0);
+	if (usblp->bidir && usblp->rcomplete)
+		ret |= EPOLLIN  | EPOLLRDNORM;
+	if (usblp->no_paper || usblp->wcomplete)
+		ret |= EPOLLOUT | EPOLLWRNORM;
 	spin_unlock_irqrestore(&usblp->lock, flags);
 	return ret;
 }

From 1cffb1c66499a9db9a735473778abf8427d16287 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Fri, 12 Feb 2021 23:55:19 +0300
Subject: [PATCH 0507/1820] usb: dwc3: qcom: Add missing DWC3 OF node refcount
 decrement

of_get_child_by_name() increments the reference counter of the OF node it
managed to find. So after the code is done using the device node, the
refcount must be decremented. Add missing of_node_put() invocation then
to the dwc3_qcom_of_register_core() method, since DWC3 OF node is being
used only there.

Fixes: a4333c3a6ba9 ("usb: dwc3: Add Qualcomm DWC3 glue driver")
Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Link: https://lore.kernel.org/r/20210212205521.14280-1-Sergey.Semin@baikalelectronics.ru
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-qcom.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index 730e8d6a2aa6..fcaf04483ad0 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -653,16 +653,19 @@ static int dwc3_qcom_of_register_core(struct platform_device *pdev)
 	ret = of_platform_populate(np, NULL, NULL, dev);
 	if (ret) {
 		dev_err(dev, "failed to register dwc3 core - %d\n", ret);
-		return ret;
+		goto node_put;
 	}
 
 	qcom->dwc3 = of_find_device_by_node(dwc3_np);
 	if (!qcom->dwc3) {
+		ret = -ENODEV;
 		dev_err(dev, "failed to get dwc3 platform device\n");
-		return -ENODEV;
 	}
 
-	return 0;
+node_put:
+	of_node_put(dwc3_np);
+
+	return ret;
 }
 
 static struct platform_device *

From a758b7c4c6f21f8e117fc8097c56fd9967363c15 Mon Sep 17 00:00:00 2001
From: Yejune Deng <yejune.deng@gmail.com>
Date: Wed, 10 Mar 2021 15:49:01 +0800
Subject: [PATCH 0508/1820] virt: acrn: Use EPOLLIN instead of POLLIN

This fixes the following sparse warning:
"sparse warnings: (new ones prefixed by >>)"
>> drivers/virt/acrn/irqfd.c:163:13: sparse: sparse: restricted __poll_t
 degrades to integer

Fixes: dcf9625f2adf ("virt: acrn: Use vfs_poll() instead of f_op->poll()")
Reported-by: kernel test robot <lkp@intel.com>
Acked-by: Shuo Liu <shuo.a.liu@intel.com>
Signed-off-by: Yejune Deng <yejune.deng@gmail.com>
Link: https://lore.kernel.org/r/20210310074901.7486-1-yejune.deng@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/acrn/irqfd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/virt/acrn/irqfd.c b/drivers/virt/acrn/irqfd.c
index 98d6e9b18f9e..df5184979b28 100644
--- a/drivers/virt/acrn/irqfd.c
+++ b/drivers/virt/acrn/irqfd.c
@@ -160,7 +160,7 @@ static int acrn_irqfd_assign(struct acrn_vm *vm, struct acrn_irqfd *args)
 	/* Check the pending event in this stage */
 	events = vfs_poll(f.file, &irqfd->pt);
 
-	if (events & POLLIN)
+	if (events & EPOLLIN)
 		acrn_irqfd_inject(irqfd);
 
 	fdput(f);

From d5b0e0677bfd5efd17c5bbb00156931f0d41cb85 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 8 Mar 2021 09:38:12 +0100
Subject: [PATCH 0509/1820] u64_stats,lockdep: Fix u64_stats_init() vs lockdep

Jakub reported that:

    static struct net_device *rtl8139_init_board(struct pci_dev *pdev)
    {
	    ...
	    u64_stats_init(&tp->rx_stats.syncp);
	    u64_stats_init(&tp->tx_stats.syncp);
	    ...
    }

results in lockdep getting confused between the RX and TX stats lock.
This is because u64_stats_init() is an inline calling seqcount_init(),
which is a macro using a static variable to generate a lockdep class.

By wrapping that in an inline, we negate the effect of the macro and
fold the static key variable, hence the confusion.

Fix by also making u64_stats_init() a macro for the case where it
matters, leaving the other case an inline for argument validation
etc.

Reported-by: Jakub Kicinski <kuba@kernel.org>
Debugged-by: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: "Erhard F." <erhard_f@mailbox.org>
Link: https://lkml.kernel.org/r/YEXicy6+9MksdLZh@hirez.programming.kicks-ass.net
---
 include/linux/u64_stats_sync.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h
index c6abb79501b3..e81856c0ba13 100644
--- a/include/linux/u64_stats_sync.h
+++ b/include/linux/u64_stats_sync.h
@@ -115,12 +115,13 @@ static inline void u64_stats_inc(u64_stats_t *p)
 }
 #endif
 
+#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
+#define u64_stats_init(syncp)	seqcount_init(&(syncp)->seq)
+#else
 static inline void u64_stats_init(struct u64_stats_sync *syncp)
 {
-#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
-	seqcount_init(&syncp->seq);
-#endif
 }
+#endif
 
 static inline void u64_stats_update_begin(struct u64_stats_sync *syncp)
 {

From 4817a52b306136c8b2b2271d8770401441e4cf79 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 9 Mar 2021 15:21:18 +0100
Subject: [PATCH 0510/1820] seqlock,lockdep: Fix seqcount_latch_init()

seqcount_init() must be a macro in order to preserve the static
variable that is used for the lockdep key. Don't then wrap it in an
inline function, which destroys that.

Luckily there aren't many users of this function, but fix it before it
becomes a problem.

Fixes: 80793c3471d9 ("seqlock: Introduce seqcount_latch_t")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/YEeFEbNUVkZaXDp4@hirez.programming.kicks-ass.net
---
 include/linux/seqlock.h | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 2f7bb92b4c9e..f61e34fbaaea 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -664,10 +664,7 @@ typedef struct {
  * seqcount_latch_init() - runtime initializer for seqcount_latch_t
  * @s: Pointer to the seqcount_latch_t instance
  */
-static inline void seqcount_latch_init(seqcount_latch_t *s)
-{
-	seqcount_init(&s->seqcount);
-}
+#define seqcount_latch_init(s) seqcount_init(&(s)->seqcount)
 
 /**
  * raw_read_seqcount_latch() - pick even/odd latch data copy

From d15dfd31384ba3cb93150e5f87661a76fa419f74 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Tue, 9 Mar 2021 12:26:01 +0000
Subject: [PATCH 0511/1820] arm64: mte: Map hotplugged memory as Normal Tagged

In a system supporting MTE, the linear map must allow reading/writing
allocation tags by setting the memory type as Normal Tagged. Currently,
this is only handled for memory present at boot. Hotplugged memory uses
Normal non-Tagged memory.

Introduce pgprot_mhp() for hotplugged memory and use it in
add_memory_resource(). The arm64 code maps pgprot_mhp() to
pgprot_tagged().

Note that ZONE_DEVICE memory should not be mapped as Tagged and
therefore setting the memory type in arch_add_memory() is not feasible.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Fixes: 0178dc761368 ("arm64: mte: Use Normal Tagged attributes for the linear map")
Reported-by: Patrick Daly <pdaly@codeaurora.org>
Tested-by: Patrick Daly <pdaly@codeaurora.org>
Link: https://lore.kernel.org/r/1614745263-27827-1-git-send-email-pdaly@codeaurora.org
Cc: <stable@vger.kernel.org> # 5.10.x
Cc: Will Deacon <will@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Link: https://lore.kernel.org/r/20210309122601.5543-1-catalin.marinas@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable-prot.h | 1 -
 arch/arm64/include/asm/pgtable.h      | 3 +++
 arch/arm64/mm/mmu.c                   | 3 ++-
 include/linux/pgtable.h               | 4 ++++
 mm/memory_hotplug.c                   | 2 +-
 5 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 046be789fbb4..9a65fb528110 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -66,7 +66,6 @@ extern bool arm64_use_ng_mappings;
 #define _PAGE_DEFAULT		(_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
 
 #define PAGE_KERNEL		__pgprot(PROT_NORMAL)
-#define PAGE_KERNEL_TAGGED	__pgprot(PROT_NORMAL_TAGGED)
 #define PAGE_KERNEL_RO		__pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
 #define PAGE_KERNEL_ROX		__pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(PROT_NORMAL & ~PTE_PXN)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index e17b96d0e4b5..47027796c2f9 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -486,6 +486,9 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
 #define pgprot_device(prot) \
 	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN)
+#define pgprot_tagged(prot) \
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_TAGGED))
+#define pgprot_mhp	pgprot_tagged
 /*
  * DMA allocations for non-coherent devices use what the Arm architecture calls
  * "Normal non-cacheable" memory, which permits speculation, unaligned accesses
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 3802cfbdd20d..9c8aa1b44cd5 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -512,7 +512,8 @@ static void __init map_mem(pgd_t *pgdp)
 		 * if MTE is present. Otherwise, it has the same attributes as
 		 * PAGE_KERNEL.
 		 */
-		__map_memblock(pgdp, start, end, PAGE_KERNEL_TAGGED, flags);
+		__map_memblock(pgdp, start, end, pgprot_tagged(PAGE_KERNEL),
+			       flags);
 	}
 
 	/*
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index cdfc4e9f253e..5e772392a379 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -904,6 +904,10 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
 #define pgprot_device pgprot_noncached
 #endif
 
+#ifndef pgprot_mhp
+#define pgprot_mhp(prot)	(prot)
+#endif
+
 #ifdef CONFIG_MMU
 #ifndef pgprot_modify
 #define pgprot_modify pgprot_modify
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 5ba51a8bdaeb..0cdbbfbc5757 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1072,7 +1072,7 @@ static int online_memory_block(struct memory_block *mem, void *arg)
  */
 int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 {
-	struct mhp_params params = { .pgprot = PAGE_KERNEL };
+	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
 	u64 start, size;
 	bool new_node = false;
 	int ret;

From 07e644885bf6727a48db109fad053cb43f3c9859 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 9 Mar 2021 19:03:04 +0000
Subject: [PATCH 0512/1820] kselftest: arm64: Fix exit code of sve-ptrace

We track if sve-ptrace encountered a failure in a variable but don't
actually use that value when we exit the program, do so.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20210309190304.39169-1-broonie@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 tools/testing/selftests/arm64/fp/sve-ptrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
index b2282be6f938..612d3899614a 100644
--- a/tools/testing/selftests/arm64/fp/sve-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -332,5 +332,5 @@ int main(void)
 
 	ksft_print_cnts();
 
-	return 0;
+	return ret;
 }

From 26f55386f964cefa92ab7ccbed68f1a313074215 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Wed, 10 Mar 2021 11:23:10 +0530
Subject: [PATCH 0513/1820] arm64/mm: Fix __enable_mmu() for new TGRAN range
 values

As per ARM ARM DDI 0487G.a, when FEAT_LPA2 is implemented, ID_AA64MMFR0_EL1
might contain a range of values to describe supported translation granules
(4K and 16K pages sizes in particular) instead of just enabled or disabled
values. This changes __enable_mmu() function to handle complete acceptable
range of values (depending on whether the field is signed or unsigned) now
represented with ID_AA64MMFR0_TGRAN_SUPPORTED_[MIN..MAX] pair. While here,
also fix similar situations in EFI stub and KVM as well.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: kvmarm@lists.cs.columbia.edu
Cc: linux-efi@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Acked-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Link: https://lore.kernel.org/r/1615355590-21102-1-git-send-email-anshuman.khandual@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/sysreg.h           | 20 ++++++++++++++------
 arch/arm64/kernel/head.S                  |  6 ++++--
 arch/arm64/kvm/reset.c                    | 10 ++++++----
 drivers/firmware/efi/libstub/arm64-stub.c |  2 +-
 4 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index dfd4edbfe360..d4a5fca984c3 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -796,6 +796,11 @@
 #define ID_AA64MMFR0_PARANGE_48		0x5
 #define ID_AA64MMFR0_PARANGE_52		0x6
 
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT	0x0
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE	0x1
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN	0x2
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MAX	0x7
+
 #ifdef CONFIG_ARM64_PA_BITS_52
 #define ID_AA64MMFR0_PARANGE_MAX	ID_AA64MMFR0_PARANGE_52
 #else
@@ -961,14 +966,17 @@
 #define ID_PFR1_PROGMOD_SHIFT		0
 
 #if defined(CONFIG_ARM64_4K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT	ID_AA64MMFR0_TGRAN4_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN4_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SHIFT		ID_AA64MMFR0_TGRAN4_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_TGRAN4_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX	0x7
 #elif defined(CONFIG_ARM64_16K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT	ID_AA64MMFR0_TGRAN16_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN16_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SHIFT		ID_AA64MMFR0_TGRAN16_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_TGRAN16_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX	0xF
 #elif defined(CONFIG_ARM64_64K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT	ID_AA64MMFR0_TGRAN64_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN64_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SHIFT		ID_AA64MMFR0_TGRAN64_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_TGRAN64_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX	0x7
 #endif
 
 #define MVFR2_FPMISC_SHIFT		4
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 66b0e0b66e31..8b469f164091 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -655,8 +655,10 @@ SYM_FUNC_END(__secondary_too_slow)
 SYM_FUNC_START(__enable_mmu)
 	mrs	x2, ID_AA64MMFR0_EL1
 	ubfx	x2, x2, #ID_AA64MMFR0_TGRAN_SHIFT, 4
-	cmp	x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
-	b.ne	__no_granule_support
+	cmp     x2, #ID_AA64MMFR0_TGRAN_SUPPORTED_MIN
+	b.lt    __no_granule_support
+	cmp     x2, #ID_AA64MMFR0_TGRAN_SUPPORTED_MAX
+	b.gt    __no_granule_support
 	update_early_cpu_boot_status 0, x2, x3
 	adrp	x2, idmap_pg_dir
 	phys_to_ttbr x1, x1
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 47f3f035f3ea..e81c7ec9e102 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -311,16 +311,18 @@ int kvm_set_ipa_limit(void)
 	}
 
 	switch (cpuid_feature_extract_unsigned_field(mmfr0, tgran_2)) {
-	default:
-	case 1:
+	case ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE:
 		kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
 		return -EINVAL;
-	case 0:
+	case ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT:
 		kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n");
 		break;
-	case 2:
+	case ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN ... ID_AA64MMFR0_TGRAN_2_SUPPORTED_MAX:
 		kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n");
 		break;
+	default:
+		kvm_err("Unsupported value for TGRAN_2, giving up\n");
+		return -EINVAL;
 	}
 
 	kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange);
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index b69d63143e0d..7bf0a7acae5e 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -24,7 +24,7 @@ efi_status_t check_platform_features(void)
 		return EFI_SUCCESS;
 
 	tg = (read_cpuid(ID_AA64MMFR0_EL1) >> ID_AA64MMFR0_TGRAN_SHIFT) & 0xf;
-	if (tg != ID_AA64MMFR0_TGRAN_SUPPORTED) {
+	if (tg < ID_AA64MMFR0_TGRAN_SUPPORTED_MIN || tg > ID_AA64MMFR0_TGRAN_SUPPORTED_MAX) {
 		if (IS_ENABLED(CONFIG_ARM64_64K_PAGES))
 			efi_err("This 64 KB granular kernel is not supported by your CPU\n");
 		else

From 7bb8bc6eb550116c504fb25af8678b9d7ca2abc5 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 9 Mar 2021 17:44:12 -0700
Subject: [PATCH 0514/1820] arm64: perf: Fix 64-bit event counter read
 truncation

Commit 0fdf1bb75953 ("arm64: perf: Avoid PMXEV* indirection") changed
armv8pmu_read_evcntr() to return a u32 instead of u64. The result is
silent truncation of the event counter when using 64-bit counters. Given
the offending commit appears to have passed thru several folks, it seems
likely this was a bad rebase after v8.5 PMU 64-bit counters landed.

Cc: Alexandru Elisei <alexandru.elisei@arm.com>
Cc: Julien Thierry <julien.thierry.kdev@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: <stable@vger.kernel.org>
Fixes: 0fdf1bb75953 ("arm64: perf: Avoid PMXEV* indirection")
Signed-off-by: Rob Herring <robh@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Link: https://lore.kernel.org/r/20210310004412.1450128-1-robh@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/perf_event.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 7d2318f80955..4658fcf88c2b 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -460,7 +460,7 @@ static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
 	return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
 }
 
-static inline u32 armv8pmu_read_evcntr(int idx)
+static inline u64 armv8pmu_read_evcntr(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
 

From 13661fc48461282e43fe8f76bf5bf449b3d40687 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 10 Mar 2021 12:28:07 +0100
Subject: [PATCH 0515/1820] ALSA: hda: Flush pending unsolicited events before
 suspend

The HD-audio controller driver processes the unsolicited events via
its work asynchronously, and this might be pending when the system
goes to suspend.  When a lengthy event handling like ELD byte reads is
running, this might trigger unexpected accesses among suspend/resume
procedure, typically seen with Nvidia driver that still requires the
handling via unsolicited event verbs for ELD updates.

This patch adds the flush of unsol_work to assure that pending events
are processed before going into suspend.

Buglink: https://bugzilla.suse.com/show_bug.cgi?id=1182377
Reported-and-tested-by: Abhishek Sahu <abhsahu@nvidia.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210310112809.9215-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_intel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 5b492c3f816c..5eea130dcf0a 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1026,6 +1026,8 @@ static int azx_prepare(struct device *dev)
 	chip = card->private_data;
 	chip->pm_prepared = 1;
 
+	flush_work(&azx_bus(chip)->unsol_work);
+
 	/* HDA controller always requires different WAKEEN for runtime suspend
 	 * and system suspend, so don't use direct-complete here.
 	 */

From 5ff9dde42e8c72ed8102eb8cb62e03f9dc2103ab Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 10 Mar 2021 12:28:08 +0100
Subject: [PATCH 0516/1820] ALSA: hda: Avoid spurious unsol event handling
 during S3/S4

When HD-audio bus receives unsolicited events during its system
suspend/resume (S3 and S4) phase, the controller driver may still try
to process events although the codec chips are already (or yet)
powered down.  This might screw up the codec communication, resulting
in CORB/RIRB errors.  Such events should be rather skipped, as the
codec chip status such as the jack status will be fully refreshed at
the system resume time.

Since we're tracking the system suspend/resume state in codec
power.power_state field, let's add the check in the common unsol event
handler entry point to filter out such events.

BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1182377
Tested-by: Abhishek Sahu <abhsahu@nvidia.com>
Cc: <stable@vger.kernel.org> # 183ab39eb0ea: ALSA: hda: Initialize power_state
Link: https://lore.kernel.org/r/20210310112809.9215-3-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_bind.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c
index 6a8564566375..17a25e453f60 100644
--- a/sound/pci/hda/hda_bind.c
+++ b/sound/pci/hda/hda_bind.c
@@ -47,6 +47,10 @@ static void hda_codec_unsol_event(struct hdac_device *dev, unsigned int ev)
 	if (codec->bus->shutdown)
 		return;
 
+	/* ignore unsol events during system suspend/resume */
+	if (codec->core.dev.power.power_state.event != PM_EVENT_ON)
+		return;
+
 	if (codec->patch_ops.unsol_event)
 		codec->patch_ops.unsol_event(codec, ev);
 }

From eea46a0879bcca23e15071f9968c0f6e6596e470 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 10 Mar 2021 12:28:09 +0100
Subject: [PATCH 0517/1820] ALSA: hda/hdmi: Cancel pending works before suspend

The per_pin->work might be still floating at the suspend, and this may
hit the access to the hardware at an unexpected timing.  Cancel the
work properly at the suspend callback for avoiding the buggy access.

Note that the bug doesn't trigger easily in the recent kernels since
the work is queued only when the repoll count is set, and usually it's
only at the resume callback, but it's still possible to hit in
theory.

BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1182377
Reported-and-tested-by: Abhishek Sahu <abhsahu@nvidia.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210310112809.9215-4-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_hdmi.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index e6d0843ee9df..45ae845e82df 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2480,6 +2480,18 @@ static void generic_hdmi_free(struct hda_codec *codec)
 }
 
 #ifdef CONFIG_PM
+static int generic_hdmi_suspend(struct hda_codec *codec)
+{
+	struct hdmi_spec *spec = codec->spec;
+	int pin_idx;
+
+	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
+		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
+		cancel_delayed_work_sync(&per_pin->work);
+	}
+	return 0;
+}
+
 static int generic_hdmi_resume(struct hda_codec *codec)
 {
 	struct hdmi_spec *spec = codec->spec;
@@ -2503,6 +2515,7 @@ static const struct hda_codec_ops generic_hdmi_patch_ops = {
 	.build_controls		= generic_hdmi_build_controls,
 	.unsol_event		= hdmi_unsol_event,
 #ifdef CONFIG_PM
+	.suspend		= generic_hdmi_suspend,
 	.resume			= generic_hdmi_resume,
 #endif
 };

From b410ed2a8572d41c68bd9208555610e4b07d0703 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 8 Mar 2021 17:11:43 +0200
Subject: [PATCH 0518/1820] perf auxtrace: Fix auxtrace queue conflict

The only requirement of an auxtrace queue is that the buffers are in
time order.  That is achieved by making separate queues for separate
perf buffer or AUX area buffer mmaps.

That generally means a separate queue per cpu for per-cpu contexts, and
a separate queue per thread for per-task contexts.

When buffers are added to a queue, perf checks that the buffer cpu and
thread id (tid) match the queue cpu and thread id.

However, generally, that need not be true, and perf will queue buffers
correctly anyway, so the check is not needed.

In addition, the check gets erroneously hit when using sample mode to
trace multiple threads.

Consequently, fix that case by removing the check.

Fixes: e502789302a6 ("perf auxtrace: Add helpers for queuing AUX area tracing data")
Reported-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20210308151143.18338-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/auxtrace.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 953f4afacd3b..5b6ccb90b397 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -298,10 +298,6 @@ static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues,
 		queue->set = true;
 		queue->tid = buffer->tid;
 		queue->cpu = buffer->cpu;
-	} else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
-		pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
-		       queue->cpu, queue->tid, buffer->cpu, buffer->tid);
-		return -EINVAL;
 	}
 
 	buffer->buffer_nr = queues->next_buffer_nr++;

From c3d59cfde9cc1fa699eb6bf0d3ce4156354e3a98 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 9 Mar 2021 12:04:47 +0100
Subject: [PATCH 0519/1820] perf synthetic-events: Fix uninitialized
 'kernel_thread' variable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

perf build fails on 5.12.0rc2 on s390 with this error message:

util/synthetic-events.c: In function
				‘__event__synthesize_thread.part.0.isra’:
util/synthetic-events.c:787:19: error: ‘kernel_thread’ may be
    used uninitialized in this function [-Werror=maybe-uninitialized]
    787 |   if (_pid == pid && !kernel_thread) {
        |       ~~~~~~~~~~~~^~~~~~~~~~~~~~~~~

The build succeeds using command 'make DEBUG=y'.

The variable kernel_thread is set by this function sequence:

__event__synthesize_thread()
|    defines bool kernel_thread; as local variable and calls
+--> perf_event__prepare_comm(..., &kernel_thread)
     +--> perf_event__get_comm_ids(..., bool *kernel);
          On return of this function variable kernel is always
          set to true or false.

To prevent this compile error, assign variable kernel_thread
a value when it is defined.

Output after:

  [root@m35lp76 perf]# make  util/synthetic-events.o
  ....
   CC       util/synthetic-events.o
  [root@m35lp76 perf]#

Fixes: c1b907953b2cd9ff ("perf tools: Skip PERF_RECORD_MMAP event synthesis for kernel threads")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: http://lore.kernel.org/lkml/20210309110447.834292-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/synthetic-events.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index b698046ec2db..5dd451695f33 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -758,7 +758,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 	for (i = 0; i < n; i++) {
 		char *end;
 		pid_t _pid;
-		bool kernel_thread;
+		bool kernel_thread = false;
 
 		_pid = strtol(dirent[i]->d_name, &end, 10);
 		if (*end)

From 49f2675f5b4d5d0af22c963f9f6152abb1bb15aa Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 10 Mar 2021 09:18:30 -0300
Subject: [PATCH 0520/1820] tools headers UAPI: Sync linux/kvm.h with the
 kernel sources

To pick the changes in:

  30b5c851af7991ad ("KVM: x86/xen: Add support for vCPU runstate information")

That don't cause any change in tooling as it doesn't introduce any new
ioctl, just parameters to existing one.

This silences this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h'
  diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/kvm.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 8b281f722e5b..f6afee209620 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1154,6 +1154,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR	(1 << 0)
 #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL	(1 << 1)
 #define KVM_XEN_HVM_CONFIG_SHARED_INFO		(1 << 2)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE		(1 << 3)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1621,12 +1622,24 @@ struct kvm_xen_vcpu_attr {
 	union {
 		__u64 gpa;
 		__u64 pad[8];
+		struct {
+			__u64 state;
+			__u64 state_entry_time;
+			__u64 time_running;
+			__u64 time_runnable;
+			__u64 time_blocked;
+			__u64 time_offline;
+		} runstate;
 	} u;
 };
 
 /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
 #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO	0x0
 #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO	0x1
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR	0x2
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT	0x3
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA	0x4
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST	0x5
 
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {

From 2a76f6de07906f0bb5f2a13fb02845db1695cc29 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 9 Mar 2021 15:49:45 -0800
Subject: [PATCH 0521/1820] perf synthetic events: Avoid write of uninitialized
 memory when generating PERF_RECORD_MMAP* records

Account for alignment bytes in the zero-ing memset.

Fixes: 1a853e36871b533c ("perf record: Allow specifying a pid to record")
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20210309234945.419254-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/synthetic-events.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 5dd451695f33..dff178103ce5 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -424,7 +424,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 
 	while (!io.eof) {
 		static const char anonstr[] = "//anon";
-		size_t size;
+		size_t size, aligned_size;
 
 		/* ensure null termination since stack will be reused. */
 		event->mmap2.filename[0] = '\0';
@@ -484,11 +484,12 @@ out:
 		}
 
 		size = strlen(event->mmap2.filename) + 1;
-		size = PERF_ALIGN(size, sizeof(u64));
+		aligned_size = PERF_ALIGN(size, sizeof(u64));
 		event->mmap2.len -= event->mmap.start;
 		event->mmap2.header.size = (sizeof(event->mmap2) -
-					(sizeof(event->mmap2.filename) - size));
-		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+					(sizeof(event->mmap2.filename) - aligned_size));
+		memset(event->mmap2.filename + size, 0, machine->id_hdr_size +
+			(aligned_size - size));
 		event->mmap2.header.size += machine->id_hdr_size;
 		event->mmap2.pid = tgid;
 		event->mmap2.tid = pid;

From fbc102fb4ccfaebf1f9c178bb78cc76108e954e7 Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Mon, 15 Feb 2021 11:48:13 +0800
Subject: [PATCH 0522/1820] regulator: mt6315: Return REGULATOR_MODE_INVALID
 for invalid mode

-EINVAL is not a valid return value for .of_map_mode, return
REGULATOR_MODE_INVALID instead.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Link: https://lore.kernel.org/r/20210215034813.45510-1-axel.lin@ingics.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/mt6315-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/mt6315-regulator.c b/drivers/regulator/mt6315-regulator.c
index d49a1534d8e9..fc7654624dd6 100644
--- a/drivers/regulator/mt6315-regulator.c
+++ b/drivers/regulator/mt6315-regulator.c
@@ -69,7 +69,7 @@ static unsigned int mt6315_map_mode(u32 mode)
 	case MT6315_BUCK_MODE_LP:
 		return REGULATOR_MODE_IDLE;
 	default:
-		return -EINVAL;
+		return REGULATOR_MODE_INVALID;
 	}
 }
 

From 5fe5f17dc59e508cae1ec2a898a0801f54aeeaae Mon Sep 17 00:00:00 2001
From: Frieder Schrempf <frieder.schrempf@kontron.de>
Date: Mon, 22 Feb 2021 16:08:04 +0100
Subject: [PATCH 0523/1820] regulator: pca9450: Fix return value when failing
 to get sd-vsel GPIO

This fixes the return value of pca9450_i2c_probe() to use the correct
error code when getting the sd-vsel GPIO fails.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Link: https://lore.kernel.org/r/20210222150809.208942-1-frieder.schrempf@kontron.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pca9450-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c
index 833d398c6aa2..89b806be399f 100644
--- a/drivers/regulator/pca9450-regulator.c
+++ b/drivers/regulator/pca9450-regulator.c
@@ -814,7 +814,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c,
 
 	if (IS_ERR(pca9450->sd_vsel_gpio)) {
 		dev_err(&i2c->dev, "Failed to get SD_VSEL GPIO\n");
-		return ret;
+		return PTR_ERR(pca9450->sd_vsel_gpio);
 	}
 
 	dev_info(&i2c->dev, "%s probed.\n",

From e610e072c87a30658479a7b4c51e1801cb3f450c Mon Sep 17 00:00:00 2001
From: satya priya <skakit@codeaurora.org>
Date: Wed, 24 Feb 2021 14:03:08 +0530
Subject: [PATCH 0524/1820] regulator: qcom-rpmh: Correct the pmic5_hfsmps515
 buck

Correct the REGULATOR_LINEAR_RANGE and n_voltges for
pmic5_hfsmps515 buck.

Signed-off-by: satya priya <skakit@codeaurora.org>
Link: https://lore.kernel.org/r/1614155592-14060-4-git-send-email-skakit@codeaurora.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/qcom-rpmh-regulator.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
index 79a554f1029d..36542c3b5e1b 100644
--- a/drivers/regulator/qcom-rpmh-regulator.c
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -726,8 +726,8 @@ static const struct rpmh_vreg_hw_data pmic5_ftsmps510 = {
 static const struct rpmh_vreg_hw_data pmic5_hfsmps515 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(2800000, 0, 4, 16000),
-	.n_voltages = 5,
+	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 235, 16000),
+	.n_voltages = 236,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
 };

From dfe03bca8db4957d4b60614ff7df4d136ba90f37 Mon Sep 17 00:00:00 2001
From: satya priya <skakit@codeaurora.org>
Date: Wed, 24 Feb 2021 14:03:11 +0530
Subject: [PATCH 0525/1820] regulator: qcom-rpmh: Use correct buck for S1C
 regulator

Use correct buck, that is, pmic5_hfsmps515 for S1C regulator
of PM8350C PMIC.

Signed-off-by: satya priya <skakit@codeaurora.org>
Link: https://lore.kernel.org/r/1614155592-14060-7-git-send-email-skakit@codeaurora.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/qcom-rpmh-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
index 36542c3b5e1b..65a108c9121f 100644
--- a/drivers/regulator/qcom-rpmh-regulator.c
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -901,7 +901,7 @@ static const struct rpmh_vreg_init_data pm8350_vreg_data[] = {
 };
 
 static const struct rpmh_vreg_init_data pm8350c_vreg_data[] = {
-	RPMH_VREG("smps1",  "smp%s1",  &pmic5_hfsmps510, "vdd-s1"),
+	RPMH_VREG("smps1",  "smp%s1",  &pmic5_hfsmps515, "vdd-s1"),
 	RPMH_VREG("smps2",  "smp%s2",  &pmic5_ftsmps510, "vdd-s2"),
 	RPMH_VREG("smps3",  "smp%s3",  &pmic5_ftsmps510, "vdd-s3"),
 	RPMH_VREG("smps4",  "smp%s4",  &pmic5_ftsmps510, "vdd-s4"),

From 98b94b6e38ca0c4eeb29949c656f6a315000c23e Mon Sep 17 00:00:00 2001
From: Frieder Schrempf <frieder.schrempf@kontron.de>
Date: Mon, 22 Feb 2021 12:52:20 +0100
Subject: [PATCH 0526/1820] regulator: pca9450: Clear PRESET_EN bit to fix
 BUCK1/2/3 voltage setting

The driver uses the DVS registers PCA9450_REG_BUCKxOUT_DVS0 to set the
voltage for the buck regulators 1, 2 and 3. This has no effect as the
PRESET_EN bit is set by default and therefore the preset values are used
instead, which are set to 850 mV.

To fix this we clear the PRESET_EN bit at time of initialization.

Fixes: 0935ff5f1f0a ("regulator: pca9450: add pca9450 pmic driver")
Cc: <stable@vger.kernel.org>
Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Link: https://lore.kernel.org/r/20210222115229.166620-1-frieder.schrempf@kontron.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pca9450-regulator.c | 8 ++++++++
 include/linux/regulator/pca9450.h     | 3 +++
 2 files changed, 11 insertions(+)

diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c
index 89b806be399f..2f7ee212cb8c 100644
--- a/drivers/regulator/pca9450-regulator.c
+++ b/drivers/regulator/pca9450-regulator.c
@@ -797,6 +797,14 @@ static int pca9450_i2c_probe(struct i2c_client *i2c,
 		return ret;
 	}
 
+	/* Clear PRESET_EN bit in BUCK123_DVS to use DVS registers */
+	ret = regmap_clear_bits(pca9450->regmap, PCA9450_REG_BUCK123_DVS,
+				BUCK123_PRESET_EN);
+	if (ret) {
+		dev_err(&i2c->dev, "Failed to clear PRESET_EN bit: %d\n", ret);
+		return ret;
+	}
+
 	/* Set reset behavior on assertion of WDOG_B signal */
 	ret = regmap_update_bits(pca9450->regmap, PCA9450_REG_RESET_CTRL,
 				WDOG_B_CFG_MASK, WDOG_B_CFG_COLD_LDO12);
diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h
index ccdb5320a240..71902f41c919 100644
--- a/include/linux/regulator/pca9450.h
+++ b/include/linux/regulator/pca9450.h
@@ -147,6 +147,9 @@ enum {
 #define BUCK6_FPWM			0x04
 #define BUCK6_ENMODE_MASK		0x03
 
+/* PCA9450_REG_BUCK123_PRESET_EN bit */
+#define BUCK123_PRESET_EN		0x80
+
 /* PCA9450_BUCK1OUT_DVS0 bits */
 #define BUCK1OUT_DVS0_MASK		0x7F
 #define BUCK1OUT_DVS0_DEFAULT		0x14

From e9e7fce0384b43f9b6c42dee1a79c0a1c332f326 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Fri, 5 Mar 2021 03:49:30 +0000
Subject: [PATCH 0527/1820] regulator: rt4831: Fix return value check in
 rt4831_regulator_probe()

In case of error, the function dev_get_regmap() returns NULL
pointer not ERR_PTR(). The IS_ERR() test in the return value
check should be replaced with NULL test.

Fixes: 9351ab8b0cb6 ("regulator: rt4831: Adds support for Richtek RT4831 DSV regulator")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Link: https://lore.kernel.org/r/20210305034930.3236099-1-weiyongjun1@huawei.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/rt4831-regulator.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/regulator/rt4831-regulator.c b/drivers/regulator/rt4831-regulator.c
index 3d4695ded629..e3aaac90d238 100644
--- a/drivers/regulator/rt4831-regulator.c
+++ b/drivers/regulator/rt4831-regulator.c
@@ -153,9 +153,9 @@ static int rt4831_regulator_probe(struct platform_device *pdev)
 	int i, ret;
 
 	regmap = dev_get_regmap(pdev->dev.parent, NULL);
-	if (IS_ERR(regmap)) {
+	if (!regmap) {
 		dev_err(&pdev->dev, "Failed to init regmap\n");
-		return PTR_ERR(regmap);
+		return -ENODEV;
 	}
 
 	/* Configure DSV mode to normal by default */

From 9e0bdaa9fcb8c64efc1487a7fba07722e7bc515e Mon Sep 17 00:00:00 2001
From: Jack Yu <jack.yu@realtek.com>
Date: Mon, 22 Feb 2021 17:00:56 +0800
Subject: [PATCH 0528/1820] ASoC: rt1015: fix i2c communication error

Remove 0x100 cache re-sync to solve i2c communication error.

Signed-off-by: Jack Yu <jack.yu@realtek.com>
Link: https://lore.kernel.org/r/20210222090057.29532-1-jack.yu@realtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt1015.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/rt1015.c b/sound/soc/codecs/rt1015.c
index 37b5795b00d1..90767490af82 100644
--- a/sound/soc/codecs/rt1015.c
+++ b/sound/soc/codecs/rt1015.c
@@ -209,6 +209,7 @@ static bool rt1015_volatile_register(struct device *dev, unsigned int reg)
 	case RT1015_VENDOR_ID:
 	case RT1015_DEVICE_ID:
 	case RT1015_PRO_ALT:
+	case RT1015_MAN_I2C:
 	case RT1015_DAC3:
 	case RT1015_VBAT_TEST_OUT1:
 	case RT1015_VBAT_TEST_OUT2:

From 0d2b6e398975bcc6a29f1d466229a312dde71b53 Mon Sep 17 00:00:00 2001
From: Jack Yu <jack.yu@realtek.com>
Date: Mon, 22 Feb 2021 17:00:57 +0800
Subject: [PATCH 0529/1820] ASoC: rt1015: enable BCLK detection after
 calibration

Enable BCLK detection after calibration.

Signed-off-by: Jack Yu <jack.yu@realtek.com>
Link: https://lore.kernel.org/r/20210222090057.29532-2-jack.yu@realtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt1015.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/rt1015.c b/sound/soc/codecs/rt1015.c
index 90767490af82..844e4079d176 100644
--- a/sound/soc/codecs/rt1015.c
+++ b/sound/soc/codecs/rt1015.c
@@ -514,6 +514,7 @@ static void rt1015_calibrate(struct rt1015_priv *rt1015)
 	msleep(300);
 	regmap_write(regmap, RT1015_PWR_STATE_CTRL, 0x0008);
 	regmap_write(regmap, RT1015_SYS_RST1, 0x05F5);
+	regmap_write(regmap, RT1015_CLK_DET, 0x8000);
 
 	regcache_cache_bypass(regmap, false);
 	regcache_mark_dirty(regmap);

From 0c0a5883783540a56e6a5dbf5868f045dbeaa888 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 15 Feb 2021 16:33:13 +0000
Subject: [PATCH 0530/1820] ASoC: codecs: lpass-rx-macro: Fix uninitialized
 variable ec_tx

There is potential read of the uninitialized variable ec_tx if the call
to snd_soc_component_read fails or returns an unrecognized w->name. To
avoid this corner case, initialize ec_tx to -1 so that it is caught
later when ec_tx is bounds checked.

Addresses-Coverity: ("Uninitialized scalar variable")
Fixes: 4f692926f562 ("ASoC: codecs: lpass-rx-macro: add dapm widgets and route")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Link: https://lore.kernel.org/r/20210215163313.84026-1-colin.king@canonical.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/lpass-rx-macro.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c
index c9c21d22c2c4..8c04b3b2c907 100644
--- a/sound/soc/codecs/lpass-rx-macro.c
+++ b/sound/soc/codecs/lpass-rx-macro.c
@@ -2895,7 +2895,7 @@ static int rx_macro_enable_echo(struct snd_soc_dapm_widget *w,
 {
 	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
 	u16 val, ec_hq_reg;
-	int ec_tx;
+	int ec_tx = -1;
 
 	val = snd_soc_component_read(component,
 			CDC_RX_INP_MUX_RX_MIX_CFG4);

From 87263968516fb9507d6215d53f44052627fae8d8 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Tue, 16 Feb 2021 14:42:21 +0300
Subject: [PATCH 0531/1820] ASoC: fsl_ssi: Fix TDM slot setup for I2S mode

When using the driver in I2S TDM mode, the _fsl_ssi_set_dai_fmt()
function rewrites the number of slots previously set by the
fsl_ssi_set_dai_tdm_slot() function to 2 by default.
To fix this, let's use the saved slot count value or, if TDM
is not used and the slot count is not set, proceed as before.

Fixes: 4f14f5c11db1 ("ASoC: fsl_ssi: Fix number of words per frame for I2S-slave mode")
Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Acked-by: Nicolin Chen <nicoleotsuka@gmail.com>
Link: https://lore.kernel.org/r/20210216114221.26635-1-shc_work@mail.ru
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_ssi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 57811743c294..ad8af3f450e2 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -878,6 +878,7 @@ static int fsl_ssi_hw_free(struct snd_pcm_substream *substream,
 static int _fsl_ssi_set_dai_fmt(struct fsl_ssi *ssi, unsigned int fmt)
 {
 	u32 strcr = 0, scr = 0, stcr, srcr, mask;
+	unsigned int slots;
 
 	ssi->dai_fmt = fmt;
 
@@ -909,10 +910,11 @@ static int _fsl_ssi_set_dai_fmt(struct fsl_ssi *ssi, unsigned int fmt)
 			return -EINVAL;
 		}
 
+		slots = ssi->slots ? : 2;
 		regmap_update_bits(ssi->regs, REG_SSI_STCCR,
-				   SSI_SxCCR_DC_MASK, SSI_SxCCR_DC(2));
+				   SSI_SxCCR_DC_MASK, SSI_SxCCR_DC(slots));
 		regmap_update_bits(ssi->regs, REG_SSI_SRCCR,
-				   SSI_SxCCR_DC_MASK, SSI_SxCCR_DC(2));
+				   SSI_SxCCR_DC_MASK, SSI_SxCCR_DC(slots));
 
 		/* Data on rising edge of bclk, frame low, 1clk before data */
 		strcr |= SSI_STCR_TFSI | SSI_STCR_TSCKP | SSI_STCR_TEFS;

From d917b5dde660b11abd757bf99a29353c36880b2c Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 15 Feb 2021 15:21:15 +0100
Subject: [PATCH 0532/1820] ASoC: rt5670: Remove 'OUT Channel Switch' control

The "OUT Channel Switch" control is a left over from code copied from
thr rt5640 codec driver.

With the rt5640 codec driver the output volume controls have 2 pairs of
mute bits:
bit 7, 15: Mute Control for Spk/Headphone/Line Output Port
bit 6, 14: Mute Control for Spk/Headphone/Line Volume Channel

Bits 7 and 15 are normal mute bits on the rt5670/5672 which are
controlled by 2 dapm widgets:
	SND_SOC_DAPM_SWITCH("LOUT L Playback", SND_SOC_NOPM, 0, 0,
			    &lout_l_enable_control),
	SND_SOC_DAPM_SWITCH("LOUT R Playback", SND_SOC_NOPM, 0, 0,
			    &lout_r_enable_control),

But on the 5670/5672 bit 6 is always reserved, where as bit 14 is
"LOUT Differential Mode" on the 5670 and also reserved on the 5672.

So the "OUT Channel Switch" control which is controlling bits 6+14
of the "LINE Output Control" register is bogus -> remove it.

This should not cause any issues for userspace. AFAICT the rt567x codecs
are only used on x86/ACPI devices and the UCM profiles used there do not
use the "OUT Channel Switch" control.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210215142118.308516-2-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5670.c | 2 --
 sound/soc/codecs/rt5670.h | 4 ----
 2 files changed, 6 deletions(-)

diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c
index c29317ea5df2..2e799e21dbda 100644
--- a/sound/soc/codecs/rt5670.c
+++ b/sound/soc/codecs/rt5670.c
@@ -637,8 +637,6 @@ static const struct snd_kcontrol_new rt5670_snd_controls[] = {
 		RT5670_L_VOL_SFT, RT5670_R_VOL_SFT,
 		39, 1, out_vol_tlv),
 	/* OUTPUT Control */
-	SOC_DOUBLE("OUT Channel Switch", RT5670_LOUT1,
-		RT5670_VOL_L_SFT, RT5670_VOL_R_SFT, 1, 1),
 	SOC_DOUBLE_TLV("OUT Playback Volume", RT5670_LOUT1,
 		RT5670_L_VOL_SFT, RT5670_R_VOL_SFT, 39, 1, out_vol_tlv),
 	/* DAC Digital Volume */
diff --git a/sound/soc/codecs/rt5670.h b/sound/soc/codecs/rt5670.h
index 56b13fe6bd3c..f9c4db156c80 100644
--- a/sound/soc/codecs/rt5670.h
+++ b/sound/soc/codecs/rt5670.h
@@ -212,12 +212,8 @@
 /* global definition */
 #define RT5670_L_MUTE				(0x1 << 15)
 #define RT5670_L_MUTE_SFT			15
-#define RT5670_VOL_L_MUTE			(0x1 << 14)
-#define RT5670_VOL_L_SFT			14
 #define RT5670_R_MUTE				(0x1 << 7)
 #define RT5670_R_MUTE_SFT			7
-#define RT5670_VOL_R_MUTE			(0x1 << 6)
-#define RT5670_VOL_R_SFT			6
 #define RT5670_L_VOL_MASK			(0x3f << 8)
 #define RT5670_L_VOL_SFT			8
 #define RT5670_R_VOL_MASK			(0x3f)

From caba8d764770b6824391c5bf3c3eba6e51b69330 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 15 Feb 2021 15:21:16 +0100
Subject: [PATCH 0533/1820] ASoC: rt5670: Remove 'HP Playback Switch' control

The RT5670_L_MUTE_SFT and RT5670_R_MUTE_SFT bits (bits 15 and 7) of the
RT5670_HP_VOL register are set / unset by the headphones deplop code
run by rt5670_hp_event() on SND_SOC_DAPM_POST_PMU / SND_SOC_DAPM_PRE_PMD.

So we should not also export a control to userspace which toggles these
same bits.

This should not cause any issues for userspace. AFAICT the rt567x codecs
are only used on x86/ACPI devices and the UCM profiles used there do not
use the "HP Playback Switch" control.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210215142118.308516-3-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5670.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c
index 2e799e21dbda..932e4cd1e9a6 100644
--- a/sound/soc/codecs/rt5670.c
+++ b/sound/soc/codecs/rt5670.c
@@ -631,8 +631,6 @@ static SOC_ENUM_SINGLE_DECL(rt5670_if2_adc_enum, RT5670_DIG_INF1_DATA,
 
 static const struct snd_kcontrol_new rt5670_snd_controls[] = {
 	/* Headphone Output Volume */
-	SOC_DOUBLE("HP Playback Switch", RT5670_HP_VOL,
-		RT5670_L_MUTE_SFT, RT5670_R_MUTE_SFT, 1, 1),
 	SOC_DOUBLE_TLV("HP Playback Volume", RT5670_HP_VOL,
 		RT5670_L_VOL_SFT, RT5670_R_VOL_SFT,
 		39, 1, out_vol_tlv),

From 02aa946ef3762aa456d87cc55606667942b3f354 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 15 Feb 2021 15:21:17 +0100
Subject: [PATCH 0534/1820] ASoC: rt5670: Remove ADC vol-ctrl mute bits poking
 from Sto1 ADC mixer settings

The SND_SOC_DAPM_MIXER declaration for "Sto1 ADC MIXL" and "Sto1 ADC MIXR"
was using the mute bits from the RT5670_STO1_ADC_DIG_VOL control as mixer
master mute bits.

But these bits are already exposed to userspace as controls as part of the
"ADC Capture Volume" / "ADC Capture Switch" control pair:

        SOC_DOUBLE("ADC Capture Switch", RT5670_STO1_ADC_DIG_VOL,
                RT5670_L_MUTE_SFT, RT5670_R_MUTE_SFT, 1, 1),
        SOC_DOUBLE_TLV("ADC Capture Volume", RT5670_STO1_ADC_DIG_VOL,
                        RT5670_L_VOL_SFT, RT5670_R_VOL_SFT,
                        127, 0, adc_vol_tlv),

Both the fact that the mute bits belong to the same reg as the vol-ctrl
and the "Digital Mixer Path" diagram in the datasheet clearly shows that
these mute bits are not part of the mixer and having 2 separate controls
poking at the same bits is a bad idea.

Remove the master-mute bits settings from the  "Sto1 ADC MIXL" and
"Sto1 ADC MIXR" DAPM widget declarations, avoiding these bits getting
poked from 2 different places.

This should not cause any issues for userspace. AFAICT the rt567x codecs
are only used on x86/ACPI devices and the UCM profiles used there already
set the "ADC Capture Switch" as needed.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210215142118.308516-4-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5670.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c
index 932e4cd1e9a6..2f015c24c637 100644
--- a/sound/soc/codecs/rt5670.c
+++ b/sound/soc/codecs/rt5670.c
@@ -1652,12 +1652,10 @@ static const struct snd_soc_dapm_widget rt5670_dapm_widgets[] = {
 			    RT5670_PWR_ADC_S1F_BIT, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("ADC Stereo2 Filter", RT5670_PWR_DIG2,
 			    RT5670_PWR_ADC_S2F_BIT, 0, NULL, 0),
-	SND_SOC_DAPM_MIXER("Sto1 ADC MIXL", RT5670_STO1_ADC_DIG_VOL,
-			   RT5670_L_MUTE_SFT, 1, rt5670_sto1_adc_l_mix,
-			   ARRAY_SIZE(rt5670_sto1_adc_l_mix)),
-	SND_SOC_DAPM_MIXER("Sto1 ADC MIXR", RT5670_STO1_ADC_DIG_VOL,
-			   RT5670_R_MUTE_SFT, 1, rt5670_sto1_adc_r_mix,
-			   ARRAY_SIZE(rt5670_sto1_adc_r_mix)),
+	SND_SOC_DAPM_MIXER("Sto1 ADC MIXL", SND_SOC_NOPM, 0, 0,
+			   rt5670_sto1_adc_l_mix, ARRAY_SIZE(rt5670_sto1_adc_l_mix)),
+	SND_SOC_DAPM_MIXER("Sto1 ADC MIXR", SND_SOC_NOPM, 0, 0,
+			   rt5670_sto1_adc_r_mix, ARRAY_SIZE(rt5670_sto1_adc_r_mix)),
 	SND_SOC_DAPM_MIXER("Sto2 ADC MIXL", SND_SOC_NOPM, 0, 0,
 			   rt5670_sto2_adc_l_mix,
 			   ARRAY_SIZE(rt5670_sto2_adc_l_mix)),

From 42121c2645d229d348399ad278b6c3fd224bd6a2 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 15 Feb 2021 15:21:18 +0100
Subject: [PATCH 0535/1820] ASoC: rt5670: Add emulated 'DAC1 Playback Switch'
 control

For reliable output-mute LED control we need a "DAC1 Playback Switch"
control. The "DAC Playback volume" control is the only control in the
path from the DAC1 data input to the speaker output, so the UCM profile
for the speaker output will have its PlaybackMixerElem set to "DAC1".

But userspace (pulseaudio) will set the "DAC1 Playback Volume" control to
its softest setting (which is not fully muted) while still showing the
speaker as being enabled at a low volume in the UI.

If we were to set the SNDRV_CTL_ELEM_ACCESS_SPK_LED on the "DAC1 Playback
Volume" control, this would mean then what pressing KEY_VOLUMEDOWN the
speaker-mute LED (embedded in the volume-mute toggle key) would light
while the UI is still showing the speaker as being enabled at a low
volume, meaning that the UI and the LED are out of sync.

Only after an _extra_ KEY_VOLUMEDOWN press would the UI show the
speaker as being muted.

The path from DAC1 data input to the speaker output does have
a digital mixer with DAC1's data as one of its inputs direclty after
the "DAC1 Playback Volume" control.

This commit adds an emulated "DAC1 Playback Switch" control by:

1. Declaring the enable flag for that mixers DAC1 input as well as the
"DAC1 Playback Switch" control both as SND_SOC_NOPM controls.

2. Storing the settings of both controls as driver-private data

3. Only clearing the mute flag for the DAC1 input of that mixer if the
stored values indicate both controls are enabled.

This is a preparation patch for adding "audio-mute" LED trigger support.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210215142118.308516-5-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5670.c | 96 +++++++++++++++++++++++++++++++++++++--
 sound/soc/codecs/rt5670.h |  5 ++
 2 files changed, 97 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c
index 2f015c24c637..4063aac2a443 100644
--- a/sound/soc/codecs/rt5670.c
+++ b/sound/soc/codecs/rt5670.c
@@ -629,6 +629,56 @@ static SOC_ENUM_SINGLE_DECL(rt5670_if2_dac_enum, RT5670_DIG_INF1_DATA,
 static SOC_ENUM_SINGLE_DECL(rt5670_if2_adc_enum, RT5670_DIG_INF1_DATA,
 				RT5670_IF2_ADC_SEL_SFT, rt5670_data_select);
 
+/*
+ * For reliable output-mute LED control we need a "DAC1 Playback Switch" control.
+ * We emulate this by only clearing the RT5670_M_DAC1_L/_R AD_DA_MIXER register
+ * bits when both our emulated DAC1 Playback Switch control and the DAC1 MIXL/R
+ * DAPM-mixer DAC1 input are enabled.
+ */
+static void rt5670_update_ad_da_mixer_dac1_m_bits(struct rt5670_priv *rt5670)
+{
+	int val = RT5670_M_DAC1_L | RT5670_M_DAC1_R;
+
+	if (rt5670->dac1_mixl_dac1_switch && rt5670->dac1_playback_switch_l)
+		val &= ~RT5670_M_DAC1_L;
+
+	if (rt5670->dac1_mixr_dac1_switch && rt5670->dac1_playback_switch_r)
+		val &= ~RT5670_M_DAC1_R;
+
+	regmap_update_bits(rt5670->regmap, RT5670_AD_DA_MIXER,
+			   RT5670_M_DAC1_L | RT5670_M_DAC1_R, val);
+}
+
+static int rt5670_dac1_playback_switch_get(struct snd_kcontrol *kcontrol,
+					   struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
+	struct rt5670_priv *rt5670 = snd_soc_component_get_drvdata(component);
+
+	ucontrol->value.integer.value[0] = rt5670->dac1_playback_switch_l;
+	ucontrol->value.integer.value[1] = rt5670->dac1_playback_switch_r;
+
+	return 0;
+}
+
+static int rt5670_dac1_playback_switch_put(struct snd_kcontrol *kcontrol,
+					   struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
+	struct rt5670_priv *rt5670 = snd_soc_component_get_drvdata(component);
+
+	if (rt5670->dac1_playback_switch_l == ucontrol->value.integer.value[0] &&
+	    rt5670->dac1_playback_switch_r == ucontrol->value.integer.value[1])
+		return 0;
+
+	rt5670->dac1_playback_switch_l = ucontrol->value.integer.value[0];
+	rt5670->dac1_playback_switch_r = ucontrol->value.integer.value[1];
+
+	rt5670_update_ad_da_mixer_dac1_m_bits(rt5670);
+
+	return 1;
+}
+
 static const struct snd_kcontrol_new rt5670_snd_controls[] = {
 	/* Headphone Output Volume */
 	SOC_DOUBLE_TLV("HP Playback Volume", RT5670_HP_VOL,
@@ -640,6 +690,8 @@ static const struct snd_kcontrol_new rt5670_snd_controls[] = {
 	/* DAC Digital Volume */
 	SOC_DOUBLE("DAC2 Playback Switch", RT5670_DAC_CTRL,
 		RT5670_M_DAC_L2_VOL_SFT, RT5670_M_DAC_R2_VOL_SFT, 1, 1),
+	SOC_DOUBLE_EXT("DAC1 Playback Switch", SND_SOC_NOPM, 0, 1, 1, 0,
+			rt5670_dac1_playback_switch_get, rt5670_dac1_playback_switch_put),
 	SOC_DOUBLE_TLV("DAC1 Playback Volume", RT5670_DAC1_DIG_VOL,
 			RT5670_L_VOL_SFT, RT5670_R_VOL_SFT,
 			175, 0, dac_vol_tlv),
@@ -909,18 +961,44 @@ static const struct snd_kcontrol_new rt5670_mono_adc_r_mix[] = {
 			RT5670_M_MONO_ADC_R2_SFT, 1, 1),
 };
 
+/* See comment above rt5670_update_ad_da_mixer_dac1_m_bits() */
+static int rt5670_put_dac1_mix_dac1_switch(struct snd_kcontrol *kcontrol,
+					   struct snd_ctl_elem_value *ucontrol)
+{
+	struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value;
+	struct snd_soc_component *component = snd_soc_dapm_kcontrol_component(kcontrol);
+	struct rt5670_priv *rt5670 = snd_soc_component_get_drvdata(component);
+	int ret;
+
+	if (mc->shift == 0)
+		rt5670->dac1_mixl_dac1_switch = ucontrol->value.integer.value[0];
+	else
+		rt5670->dac1_mixr_dac1_switch = ucontrol->value.integer.value[0];
+
+	/* Apply the update (if any) */
+	ret = snd_soc_dapm_put_volsw(kcontrol, ucontrol);
+	if (ret == 0)
+		return 0;
+
+	rt5670_update_ad_da_mixer_dac1_m_bits(rt5670);
+
+	return 1;
+}
+
+#define SOC_DAPM_SINGLE_RT5670_DAC1_SW(name, shift) \
+	SOC_SINGLE_EXT(name, SND_SOC_NOPM, shift, 1, 0, \
+		       snd_soc_dapm_get_volsw, rt5670_put_dac1_mix_dac1_switch)
+
 static const struct snd_kcontrol_new rt5670_dac_l_mix[] = {
 	SOC_DAPM_SINGLE("Stereo ADC Switch", RT5670_AD_DA_MIXER,
 			RT5670_M_ADCMIX_L_SFT, 1, 1),
-	SOC_DAPM_SINGLE("DAC1 Switch", RT5670_AD_DA_MIXER,
-			RT5670_M_DAC1_L_SFT, 1, 1),
+	SOC_DAPM_SINGLE_RT5670_DAC1_SW("DAC1 Switch", 0),
 };
 
 static const struct snd_kcontrol_new rt5670_dac_r_mix[] = {
 	SOC_DAPM_SINGLE("Stereo ADC Switch", RT5670_AD_DA_MIXER,
 			RT5670_M_ADCMIX_R_SFT, 1, 1),
-	SOC_DAPM_SINGLE("DAC1 Switch", RT5670_AD_DA_MIXER,
-			RT5670_M_DAC1_R_SFT, 1, 1),
+	SOC_DAPM_SINGLE_RT5670_DAC1_SW("DAC1 Switch", 1),
 };
 
 static const struct snd_kcontrol_new rt5670_sto_dac_l_mix[] = {
@@ -2993,6 +3071,16 @@ static int rt5670_i2c_probe(struct i2c_client *i2c,
 		dev_info(&i2c->dev, "quirk JD mode 3\n");
 	}
 
+	/*
+	 * Enable the emulated "DAC1 Playback Switch" by default to avoid
+	 * muting the output with older UCM profiles.
+	 */
+	rt5670->dac1_playback_switch_l = true;
+	rt5670->dac1_playback_switch_r = true;
+	/* The Power-On-Reset values for the DAC1 mixer have the DAC1 input enabled. */
+	rt5670->dac1_mixl_dac1_switch = true;
+	rt5670->dac1_mixr_dac1_switch = true;
+
 	rt5670->regmap = devm_regmap_init_i2c(i2c, &rt5670_regmap);
 	if (IS_ERR(rt5670->regmap)) {
 		ret = PTR_ERR(rt5670->regmap);
diff --git a/sound/soc/codecs/rt5670.h b/sound/soc/codecs/rt5670.h
index f9c4db156c80..6fb3c369ee98 100644
--- a/sound/soc/codecs/rt5670.h
+++ b/sound/soc/codecs/rt5670.h
@@ -2013,6 +2013,11 @@ struct rt5670_priv {
 	int dsp_rate;
 	int jack_type;
 	int jack_type_saved;
+
+	bool dac1_mixl_dac1_switch;
+	bool dac1_mixr_dac1_switch;
+	bool dac1_playback_switch_l;
+	bool dac1_playback_switch_r;
 };
 
 void rt5670_jack_suspend(struct snd_soc_component *component);

From 4ec5b96775a88dd9b1c3ba1d23c43c478cab95a2 Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@nxp.com>
Date: Wed, 24 Feb 2021 14:57:51 +0800
Subject: [PATCH 0536/1820] ASoC: ak4458: Add MODULE_DEVICE_TABLE

Add missed MODULE_DEVICE_TABLE for the driver can be loaded
automatically at boot.

Fixes: 08660086eff9 ("ASoC: ak4458: Add support for AK4458 DAC driver")
Cc: <stable@vger.kernel.org>
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Link: https://lore.kernel.org/r/1614149872-25510-1-git-send-email-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/ak4458.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/ak4458.c b/sound/soc/codecs/ak4458.c
index 472caad17012..85a1d00894a9 100644
--- a/sound/soc/codecs/ak4458.c
+++ b/sound/soc/codecs/ak4458.c
@@ -812,6 +812,7 @@ static const struct of_device_id ak4458_of_match[] = {
 	{ .compatible = "asahi-kasei,ak4497", .data = &ak4497_drvdata},
 	{ },
 };
+MODULE_DEVICE_TABLE(of, ak4458_of_match);
 
 static struct i2c_driver ak4458_i2c_driver = {
 	.driver = {

From 80cffd2468ddb850e678f17841fc356930b2304a Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@nxp.com>
Date: Wed, 24 Feb 2021 14:57:52 +0800
Subject: [PATCH 0537/1820] ASoC: ak5558: Add MODULE_DEVICE_TABLE

Add missed MODULE_DEVICE_TABLE for the driver can be loaded
automatically at boot.

Fixes: 920884777480 ("ASoC: ak5558: Add support for AK5558 ADC driver")
Cc: <stable@vger.kernel.org>
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Link: https://lore.kernel.org/r/1614149872-25510-2-git-send-email-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/ak5558.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/ak5558.c b/sound/soc/codecs/ak5558.c
index 8a32b0139cb0..85bdd0534180 100644
--- a/sound/soc/codecs/ak5558.c
+++ b/sound/soc/codecs/ak5558.c
@@ -419,6 +419,7 @@ static const struct of_device_id ak5558_i2c_dt_ids[] __maybe_unused = {
 	{ .compatible = "asahi-kasei,ak5558"},
 	{ }
 };
+MODULE_DEVICE_TABLE(of, ak5558_i2c_dt_ids);
 
 static struct i2c_driver ak5558_i2c_driver = {
 	.driver = {

From ca08ddfd961d2a17208d9182e0ee5791b39bd8bf Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 24 Feb 2021 11:50:52 +0100
Subject: [PATCH 0538/1820] ASoC: Intel: bytcr_rt5640: Fix HP Pavilion x2
 10-p0XX OVCD current threshold

When I added the quirk for the "HP Pavilion x2 10-p0XX" I copied the
byt_rt5640_quirk_table[] entry for the HP Pavilion x2 10-k0XX / 10-n0XX
models since these use almost the same settings.

While doing this I accidentally also copied and kept the non-standard
OVCD_TH_1500UA setting used on those models. This too low threshold is
causing headsets to often be seen as headphones (without a headset-mic)
and when correctly identified it is causing ghost play/pause
button-presses to get detected.

Correct the HP Pavilion x2 10-p0XX quirk to use the default OVCD_TH_2000UA
setting, fixing these problems.

Fixes: fbdae7d6d04d ("ASoC: Intel: bytcr_rt5640: Fix HP Pavilion x2 Detachable quirks")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210224105052.42116-1-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5640.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 782f2b4d72ad..5d48cc359c3d 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -581,7 +581,7 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 		},
 		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
 					BYT_RT5640_JD_SRC_JD1_IN4P |
-					BYT_RT5640_OVCD_TH_1500UA |
+					BYT_RT5640_OVCD_TH_2000UA |
 					BYT_RT5640_OVCD_SF_0P75 |
 					BYT_RT5640_MCLK_EN),
 	},

From cfa26ed1f9f885c2fd8f53ca492989d1e16d0199 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 26 Feb 2021 15:38:13 +0100
Subject: [PATCH 0539/1820] ASoC: rt5640: Fix dac- and adc- vol-tlv values
 being off by a factor of 10

The adc_vol_tlv volume-control has a range from -17.625 dB to +30 dB,
not -176.25 dB to + 300 dB. This wrong scale is esp. a problem in userspace
apps which translate the dB scale to a linear scale. With the logarithmic
dB scale being of by a factor of 10 we loose all precision in the lower
area of the range when apps translate things to a linear scale.

E.g. the 0 dB default, which corresponds with a value of 47 of the
0 - 127 range for the control, would be shown as 0/100 in alsa-mixer.

Since the centi-dB values used in the TLV struct cannot represent the
0.375 dB step size used by these controls, change the TLV definition
for them to specify a min and max value instead of min + stepsize.

Note this mirrors commit 3f31f7d9b540 ("ASoC: rt5670: Fix dac- and adc-
vol-tlv values being off by a factor of 10") which made the exact same
change to the rt5670 codec driver.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210226143817.84287-2-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5640.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index 1414ad15d01c..a5674c227b3a 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -339,9 +339,9 @@ static bool rt5640_readable_register(struct device *dev, unsigned int reg)
 }
 
 static const DECLARE_TLV_DB_SCALE(out_vol_tlv, -4650, 150, 0);
-static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0);
+static const DECLARE_TLV_DB_MINMAX(dac_vol_tlv, -6562, 0);
 static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -3450, 150, 0);
-static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0);
+static const DECLARE_TLV_DB_MINMAX(adc_vol_tlv, -1762, 3000);
 static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0);
 
 /* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */

From eee51df776bd6cac10a76b2779a9fdee3f622b2b Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 26 Feb 2021 15:38:14 +0100
Subject: [PATCH 0540/1820] ASoC: rt5651: Fix dac- and adc- vol-tlv values
 being off by a factor of 10

The adc_vol_tlv volume-control has a range from -17.625 dB to +30 dB,
not -176.25 dB to + 300 dB. This wrong scale is esp. a problem in userspace
apps which translate the dB scale to a linear scale. With the logarithmic
dB scale being of by a factor of 10 we loose all precision in the lower
area of the range when apps translate things to a linear scale.

E.g. the 0 dB default, which corresponds with a value of 47 of the
0 - 127 range for the control, would be shown as 0/100 in alsa-mixer.

Since the centi-dB values used in the TLV struct cannot represent the
0.375 dB step size used by these controls, change the TLV definition
for them to specify a min and max value instead of min + stepsize.

Note this mirrors commit 3f31f7d9b540 ("ASoC: rt5670: Fix dac- and adc-
vol-tlv values being off by a factor of 10") which made the exact same
change to the rt5670 codec driver.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210226143817.84287-3-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5651.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/rt5651.c b/sound/soc/codecs/rt5651.c
index d198e191fb0c..e59fdc81dbd4 100644
--- a/sound/soc/codecs/rt5651.c
+++ b/sound/soc/codecs/rt5651.c
@@ -285,9 +285,9 @@ static bool rt5651_readable_register(struct device *dev, unsigned int reg)
 }
 
 static const DECLARE_TLV_DB_SCALE(out_vol_tlv, -4650, 150, 0);
-static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0);
+static const DECLARE_TLV_DB_MINMAX(dac_vol_tlv, -6562, 0);
 static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -3450, 150, 0);
-static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0);
+static const DECLARE_TLV_DB_MINMAX(adc_vol_tlv, -1762, 3000);
 static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0);
 
 /* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */

From f86f58e3594fb0ab1993d833d3b9a2496f3c928c Mon Sep 17 00:00:00 2001
From: Benjamin Rood <benjaminjrood@gmail.com>
Date: Fri, 19 Feb 2021 13:33:08 -0500
Subject: [PATCH 0541/1820] ASoC: sgtl5000: set DAP_AVC_CTRL register to
 correct default value on probe

According to the SGTL5000 datasheet [1], the DAP_AVC_CTRL register has
the following bit field definitions:

| BITS  | FIELD       | RW | RESET | DEFINITION                        |
| 15    | RSVD        | RO | 0x0   | Reserved                          |
| 14    | RSVD        | RW | 0x1   | Reserved                          |
| 13:12 | MAX_GAIN    | RW | 0x1   | Max Gain of AVC in expander mode  |
| 11:10 | RSVD        | RO | 0x0   | Reserved                          |
| 9:8   | LBI_RESP    | RW | 0x1   | Integrator Response               |
| 7:6   | RSVD        | RO | 0x0   | Reserved                          |
| 5     | HARD_LMT_EN | RW | 0x0   | Enable hard limiter mode          |
| 4:1   | RSVD        | RO | 0x0   | Reserved                          |
| 0     | EN          | RW | 0x0   | Enable/Disable AVC                |

The original default value written to the DAP_AVC_CTRL register during
sgtl5000_i2c_probe() was 0x0510.  This would incorrectly write values to
bits 4 and 10, which are defined as RESERVED.  It would also not set
bits 12 and 14 to their correct RESET values of 0x1, and instead set
them to 0x0.  While the DAP_AVC module is effectively disabled because
the EN bit is 0, this default value is still writing invalid values to
registers that are marked as read-only and RESERVED as well as not
setting bits 12 and 14 to their correct default values as defined by the
datasheet.

The correct value that should be written to the DAP_AVC_CTRL register is
0x5100, which configures the register bits to the default values defined
by the datasheet, and prevents any writes to bits defined as
'read-only'.  Generally speaking, it is best practice to NOT attempt to
write values to registers/bits defined as RESERVED, as it generally
produces unwanted/undefined behavior, or errors.

Also, all credit for this patch should go to my colleague Dan MacDonald
<dmacdonald@curbellmedical.com> for finding this error in the first
place.

[1] https://www.nxp.com/docs/en/data-sheet/SGTL5000.pdf

Signed-off-by: Benjamin Rood <benjaminjrood@gmail.com>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Link: https://lore.kernel.org/r/20210219183308.GA2117@ubuntu-dev
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/sgtl5000.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index 73551e36695e..6d9bb256a2cf 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -71,7 +71,7 @@ static const struct reg_default sgtl5000_reg_defaults[] = {
 	{ SGTL5000_DAP_EQ_BASS_BAND4,		0x002f },
 	{ SGTL5000_DAP_MAIN_CHAN,		0x8000 },
 	{ SGTL5000_DAP_MIX_CHAN,		0x0000 },
-	{ SGTL5000_DAP_AVC_CTRL,		0x0510 },
+	{ SGTL5000_DAP_AVC_CTRL,		0x5100 },
 	{ SGTL5000_DAP_AVC_THRESHOLD,		0x1473 },
 	{ SGTL5000_DAP_AVC_ATTACK,		0x0028 },
 	{ SGTL5000_DAP_AVC_DECAY,		0x0050 },

From bb18c678754ce1514100fb4c0bf6113b5af36c48 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 28 Feb 2021 17:04:41 +0100
Subject: [PATCH 0542/1820] ASoC: es8316: Simplify adc_pga_gain_tlv table

Most steps in this table are steps of 3dB (300 centi-dB), so we can
simplify the table.

This not only reduces the amount of space it takes inside the kernel,
this also makes alsa-lib's mixer code actually accept the table, where
as before this change alsa-lib saw the "ADC PGA Gain" control as a
control without a dB scale.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210228160441.241110-1-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es8316.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/sound/soc/codecs/es8316.c b/sound/soc/codecs/es8316.c
index d632055370e0..067757d1d70a 100644
--- a/sound/soc/codecs/es8316.c
+++ b/sound/soc/codecs/es8316.c
@@ -63,13 +63,8 @@ static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(adc_pga_gain_tlv,
 	1, 1, TLV_DB_SCALE_ITEM(0, 0, 0),
 	2, 2, TLV_DB_SCALE_ITEM(250, 0, 0),
 	3, 3, TLV_DB_SCALE_ITEM(450, 0, 0),
-	4, 4, TLV_DB_SCALE_ITEM(700, 0, 0),
-	5, 5, TLV_DB_SCALE_ITEM(1000, 0, 0),
-	6, 6, TLV_DB_SCALE_ITEM(1300, 0, 0),
-	7, 7, TLV_DB_SCALE_ITEM(1600, 0, 0),
-	8, 8, TLV_DB_SCALE_ITEM(1800, 0, 0),
-	9, 9, TLV_DB_SCALE_ITEM(2100, 0, 0),
-	10, 10, TLV_DB_SCALE_ITEM(2400, 0, 0),
+	4, 7, TLV_DB_SCALE_ITEM(700, 300, 0),
+	8, 10, TLV_DB_SCALE_ITEM(1800, 300, 0),
 );
 
 static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(hpout_vol_tlv,

From 5bb0ecddb2a7f638d65e457f3da9fa334c967b14 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 1 Mar 2021 18:34:10 -0600
Subject: [PATCH 0543/1820] ASoC: SOF: Intel: unregister DMIC device on probe
 error

We only unregister the platform device during the .remove operation,
but if the probe fails we will never reach this sequence.

Suggested-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Fixes: dd96daca6c83e ("ASoC: SOF: Intel: Add APL/CNL HW DSP support")
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20210302003410.1178535-1-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index 1d29b1fd6a94..0c096db07322 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -897,6 +897,7 @@ free_streams:
 /* dsp_unmap: not currently used */
 	iounmap(sdev->bar[HDA_DSP_BAR]);
 hdac_bus_unmap:
+	platform_device_unregister(hdev->dmic_dev);
 	iounmap(bus->remap_addr);
 	hda_codec_i915_exit(sdev);
 err:

From 7de14d581dbed57c2b3c6afffa2c3fdc6955a3cd Mon Sep 17 00:00:00 2001
From: Jon Hunter <jonathanh@nvidia.com>
Date: Wed, 3 Mar 2021 11:55:26 +0000
Subject: [PATCH 0544/1820] ASoC: soc-core: Prevent warning if no DMI table is
 present

Many systems do not use ACPI and hence do not provide a DMI table. On
non-ACPI systems a warning, such as the following, is printed on boot.

 WARNING KERN tegra-audio-graph-card sound: ASoC: no DMI vendor name!

The variable 'dmi_available' is not exported and so currently cannot be
used by kernel modules without adding an accessor. However, it is
possible to use the function is_acpi_device_node() to determine if the
sound card is an ACPI device and hence indicate if we expect a DMI table
to be present. Therefore, call is_acpi_device_node() to see if we are
using ACPI and only parse the DMI table if we are booting with ACPI.

Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Link: https://lore.kernel.org/r/20210303115526.419458-1-jonathanh@nvidia.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index f6d4e99b590c..0cffc9527e28 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -31,6 +31,7 @@
 #include <linux/of.h>
 #include <linux/of_graph.h>
 #include <linux/dmi.h>
+#include <linux/acpi.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -1573,6 +1574,9 @@ int snd_soc_set_dmi_name(struct snd_soc_card *card, const char *flavour)
 	if (card->long_name)
 		return 0; /* long name already set by driver or from DMI */
 
+	if (!is_acpi_device_node(card->dev->fwnode))
+		return 0;
+
 	/* make up dmi long name as: vendor-product-version-board */
 	vendor = dmi_get_system_info(DMI_BOARD_VENDOR);
 	if (!vendor || !is_dmi_valid(vendor)) {

From e793c965519b8b7f2fea51a48398405e2a501729 Mon Sep 17 00:00:00 2001
From: Lucas Tanure <tanureal@opensource.cirrus.com>
Date: Fri, 5 Mar 2021 17:34:28 +0000
Subject: [PATCH 0545/1820] ASoC: cs42l42: Fix Bitclock polarity inversion

The driver was setting bit clock polarity opposite to intended polarity.
Also simplify the code by grouping ADC and DAC clock configurations into
a single field.

Signed-off-by: Lucas Tanure <tanureal@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20210305173442.195740-2-tanureal@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs42l42.c | 20 ++++++++------------
 sound/soc/codecs/cs42l42.h | 11 ++++++-----
 2 files changed, 14 insertions(+), 17 deletions(-)

diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c
index 210fcbedf241..df0d5fec0287 100644
--- a/sound/soc/codecs/cs42l42.c
+++ b/sound/soc/codecs/cs42l42.c
@@ -797,27 +797,23 @@ static int cs42l42_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 	/* Bitclock/frame inversion */
 	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
 	case SND_SOC_DAIFMT_NB_NF:
+		asp_cfg_val |= CS42L42_ASP_SCPOL_NOR << CS42L42_ASP_SCPOL_SHIFT;
 		break;
 	case SND_SOC_DAIFMT_NB_IF:
-		asp_cfg_val |= CS42L42_ASP_POL_INV <<
-				CS42L42_ASP_LCPOL_IN_SHIFT;
+		asp_cfg_val |= CS42L42_ASP_SCPOL_NOR << CS42L42_ASP_SCPOL_SHIFT;
+		asp_cfg_val |= CS42L42_ASP_LCPOL_INV << CS42L42_ASP_LCPOL_SHIFT;
 		break;
 	case SND_SOC_DAIFMT_IB_NF:
-		asp_cfg_val |= CS42L42_ASP_POL_INV <<
-				CS42L42_ASP_SCPOL_IN_DAC_SHIFT;
 		break;
 	case SND_SOC_DAIFMT_IB_IF:
-		asp_cfg_val |= CS42L42_ASP_POL_INV <<
-				CS42L42_ASP_LCPOL_IN_SHIFT;
-		asp_cfg_val |= CS42L42_ASP_POL_INV <<
-				CS42L42_ASP_SCPOL_IN_DAC_SHIFT;
+		asp_cfg_val |= CS42L42_ASP_LCPOL_INV << CS42L42_ASP_LCPOL_SHIFT;
 		break;
 	}
 
-	snd_soc_component_update_bits(component, CS42L42_ASP_CLK_CFG,
-				CS42L42_ASP_MODE_MASK |
-				CS42L42_ASP_SCPOL_IN_DAC_MASK |
-				CS42L42_ASP_LCPOL_IN_MASK, asp_cfg_val);
+	snd_soc_component_update_bits(component, CS42L42_ASP_CLK_CFG, CS42L42_ASP_MODE_MASK |
+								      CS42L42_ASP_SCPOL_MASK |
+								      CS42L42_ASP_LCPOL_MASK,
+								      asp_cfg_val);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/cs42l42.h b/sound/soc/codecs/cs42l42.h
index 9e3cc528dcff..1f0d67c95a9a 100644
--- a/sound/soc/codecs/cs42l42.h
+++ b/sound/soc/codecs/cs42l42.h
@@ -258,11 +258,12 @@
 #define CS42L42_ASP_SLAVE_MODE		0x00
 #define CS42L42_ASP_MODE_SHIFT		4
 #define CS42L42_ASP_MODE_MASK		(1 << CS42L42_ASP_MODE_SHIFT)
-#define CS42L42_ASP_SCPOL_IN_DAC_SHIFT	2
-#define CS42L42_ASP_SCPOL_IN_DAC_MASK	(1 << CS42L42_ASP_SCPOL_IN_DAC_SHIFT)
-#define CS42L42_ASP_LCPOL_IN_SHIFT	0
-#define CS42L42_ASP_LCPOL_IN_MASK	(1 << CS42L42_ASP_LCPOL_IN_SHIFT)
-#define CS42L42_ASP_POL_INV		1
+#define CS42L42_ASP_SCPOL_SHIFT		2
+#define CS42L42_ASP_SCPOL_MASK		(3 << CS42L42_ASP_SCPOL_SHIFT)
+#define CS42L42_ASP_SCPOL_NOR		3
+#define CS42L42_ASP_LCPOL_SHIFT		0
+#define CS42L42_ASP_LCPOL_MASK		(3 << CS42L42_ASP_LCPOL_SHIFT)
+#define CS42L42_ASP_LCPOL_INV		3
 
 #define CS42L42_ASP_FRM_CFG		(CS42L42_PAGE_12 + 0x08)
 #define CS42L42_ASP_STP_SHIFT		4

From 2bdc4f5c6838f7c3feb4fe68e4edbeea158ec0a2 Mon Sep 17 00:00:00 2001
From: Lucas Tanure <tanureal@opensource.cirrus.com>
Date: Fri, 5 Mar 2021 17:34:29 +0000
Subject: [PATCH 0546/1820] ASoC: cs42l42: Fix channel width support

Remove the hard coded 32 bits width and replace with the correct width
calculated by params_width.

Signed-off-by: Lucas Tanure <tanureal@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20210305173442.195740-3-tanureal@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs42l42.c | 47 ++++++++++++++++++--------------------
 sound/soc/codecs/cs42l42.h |  1 -
 2 files changed, 22 insertions(+), 26 deletions(-)

diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c
index df0d5fec0287..4f9ad9547929 100644
--- a/sound/soc/codecs/cs42l42.c
+++ b/sound/soc/codecs/cs42l42.c
@@ -691,24 +691,6 @@ static int cs42l42_pll_config(struct snd_soc_component *component)
 					CS42L42_CLK_OASRC_SEL_MASK,
 					CS42L42_CLK_OASRC_SEL_12 <<
 					CS42L42_CLK_OASRC_SEL_SHIFT);
-			/* channel 1 on low LRCLK, 32 bit */
-			snd_soc_component_update_bits(component,
-					CS42L42_ASP_RX_DAI0_CH1_AP_RES,
-					CS42L42_ASP_RX_CH_AP_MASK |
-					CS42L42_ASP_RX_CH_RES_MASK,
-					(CS42L42_ASP_RX_CH_AP_LOW <<
-					CS42L42_ASP_RX_CH_AP_SHIFT) |
-					(CS42L42_ASP_RX_CH_RES_32 <<
-					CS42L42_ASP_RX_CH_RES_SHIFT));
-			/* Channel 2 on high LRCLK, 32 bit */
-			snd_soc_component_update_bits(component,
-					CS42L42_ASP_RX_DAI0_CH2_AP_RES,
-					CS42L42_ASP_RX_CH_AP_MASK |
-					CS42L42_ASP_RX_CH_RES_MASK,
-					(CS42L42_ASP_RX_CH_AP_HI <<
-					CS42L42_ASP_RX_CH_AP_SHIFT) |
-					(CS42L42_ASP_RX_CH_RES_32 <<
-					CS42L42_ASP_RX_CH_RES_SHIFT));
 			if (pll_ratio_table[i].mclk_src_sel == 0) {
 				/* Pass the clock straight through */
 				snd_soc_component_update_bits(component,
@@ -824,14 +806,29 @@ static int cs42l42_pcm_hw_params(struct snd_pcm_substream *substream,
 {
 	struct snd_soc_component *component = dai->component;
 	struct cs42l42_private *cs42l42 = snd_soc_component_get_drvdata(component);
-	int retval;
+	unsigned int width = (params_width(params) / 8) - 1;
+	unsigned int val = 0;
 
 	cs42l42->srate = params_rate(params);
-	cs42l42->swidth = params_width(params);
 
-	retval = cs42l42_pll_config(component);
+	switch(substream->stream) {
+	case SNDRV_PCM_STREAM_PLAYBACK:
+		val |= width << CS42L42_ASP_RX_CH_RES_SHIFT;
+		/* channel 1 on low LRCLK */
+		snd_soc_component_update_bits(component, CS42L42_ASP_RX_DAI0_CH1_AP_RES,
+							 CS42L42_ASP_RX_CH_AP_MASK |
+							 CS42L42_ASP_RX_CH_RES_MASK, val);
+		/* Channel 2 on high LRCLK */
+		val |= CS42L42_ASP_RX_CH_AP_HI << CS42L42_ASP_RX_CH_AP_SHIFT;
+		snd_soc_component_update_bits(component, CS42L42_ASP_RX_DAI0_CH2_AP_RES,
+							 CS42L42_ASP_RX_CH_AP_MASK |
+							 CS42L42_ASP_RX_CH_RES_MASK, val);
+		break;
+	default:
+		break;
+	}
 
-	return retval;
+	return cs42l42_pll_config(component);
 }
 
 static int cs42l42_set_sysclk(struct snd_soc_dai *dai,
@@ -896,9 +893,9 @@ static int cs42l42_mute(struct snd_soc_dai *dai, int mute, int direction)
 	return 0;
 }
 
-#define CS42L42_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S18_3LE | \
-			SNDRV_PCM_FMTBIT_S20_3LE | SNDRV_PCM_FMTBIT_S24_LE | \
-			SNDRV_PCM_FMTBIT_S32_LE)
+#define CS42L42_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
+			 SNDRV_PCM_FMTBIT_S24_LE |\
+			 SNDRV_PCM_FMTBIT_S32_LE )
 
 
 static const struct snd_soc_dai_ops cs42l42_ops = {
diff --git a/sound/soc/codecs/cs42l42.h b/sound/soc/codecs/cs42l42.h
index 1f0d67c95a9a..9b017b76828a 100644
--- a/sound/soc/codecs/cs42l42.h
+++ b/sound/soc/codecs/cs42l42.h
@@ -757,7 +757,6 @@ struct  cs42l42_private {
 	struct completion pdn_done;
 	u32 sclk;
 	u32 srate;
-	u32 swidth;
 	u8 plug_state;
 	u8 hs_type;
 	u8 ts_inv;

From 72d904763ae6a8576e7ad034f9da4f0e3c44bf24 Mon Sep 17 00:00:00 2001
From: Lucas Tanure <tanureal@opensource.cirrus.com>
Date: Fri, 5 Mar 2021 17:34:30 +0000
Subject: [PATCH 0547/1820] ASoC: cs42l42: Fix mixer volume control

The minimum value is 0x3f (-63dB), which also is mute

Signed-off-by: Lucas Tanure <tanureal@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20210305173442.195740-4-tanureal@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs42l42.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c
index 4f9ad9547929..d5078ce79fad 100644
--- a/sound/soc/codecs/cs42l42.c
+++ b/sound/soc/codecs/cs42l42.c
@@ -401,7 +401,7 @@ static const struct regmap_config cs42l42_regmap = {
 };
 
 static DECLARE_TLV_DB_SCALE(adc_tlv, -9600, 100, false);
-static DECLARE_TLV_DB_SCALE(mixer_tlv, -6200, 100, false);
+static DECLARE_TLV_DB_SCALE(mixer_tlv, -6300, 100, true);
 
 static const char * const cs42l42_hpf_freq_text[] = {
 	"1.86Hz", "120Hz", "235Hz", "466Hz"
@@ -458,7 +458,7 @@ static const struct snd_kcontrol_new cs42l42_snd_controls[] = {
 				CS42L42_DAC_HPF_EN_SHIFT, true, false),
 	SOC_DOUBLE_R_TLV("Mixer Volume", CS42L42_MIXER_CHA_VOL,
 			 CS42L42_MIXER_CHB_VOL, CS42L42_MIXER_CH_VOL_SHIFT,
-				0x3e, 1, mixer_tlv)
+				0x3f, 1, mixer_tlv)
 };
 
 static int cs42l42_hpdrv_evt(struct snd_soc_dapm_widget *w,

From 15013240fcf791691f99c884802099db34c099b9 Mon Sep 17 00:00:00 2001
From: Lucas Tanure <tanureal@opensource.cirrus.com>
Date: Fri, 5 Mar 2021 17:34:31 +0000
Subject: [PATCH 0548/1820] ASoC: cs42l42: Don't enable/disable regulator at
 Bias Level

dev_pm_ops already enable/disable the codec if not in use

Signed-off-by: Lucas Tanure <tanureal@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20210305173442.195740-5-tanureal@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs42l42.c | 38 --------------------------------------
 1 file changed, 38 deletions(-)

diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c
index d5078ce79fad..eee3fc320030 100644
--- a/sound/soc/codecs/cs42l42.c
+++ b/sound/soc/codecs/cs42l42.c
@@ -511,43 +511,6 @@ static const struct snd_soc_dapm_route cs42l42_audio_map[] = {
 	{"HP", NULL, "HPDRV"}
 };
 
-static int cs42l42_set_bias_level(struct snd_soc_component *component,
-					enum snd_soc_bias_level level)
-{
-	struct cs42l42_private *cs42l42 = snd_soc_component_get_drvdata(component);
-	int ret;
-
-	switch (level) {
-	case SND_SOC_BIAS_ON:
-		break;
-	case SND_SOC_BIAS_PREPARE:
-		break;
-	case SND_SOC_BIAS_STANDBY:
-		if (snd_soc_component_get_bias_level(component) == SND_SOC_BIAS_OFF) {
-			regcache_cache_only(cs42l42->regmap, false);
-			regcache_sync(cs42l42->regmap);
-			ret = regulator_bulk_enable(
-						ARRAY_SIZE(cs42l42->supplies),
-						cs42l42->supplies);
-			if (ret != 0) {
-				dev_err(component->dev,
-					"Failed to enable regulators: %d\n",
-					ret);
-				return ret;
-			}
-		}
-		break;
-	case SND_SOC_BIAS_OFF:
-
-		regcache_cache_only(cs42l42->regmap, true);
-		regulator_bulk_disable(ARRAY_SIZE(cs42l42->supplies),
-						    cs42l42->supplies);
-		break;
-	}
-
-	return 0;
-}
-
 static int cs42l42_component_probe(struct snd_soc_component *component)
 {
 	struct cs42l42_private *cs42l42 =
@@ -560,7 +523,6 @@ static int cs42l42_component_probe(struct snd_soc_component *component)
 
 static const struct snd_soc_component_driver soc_component_dev_cs42l42 = {
 	.probe			= cs42l42_component_probe,
-	.set_bias_level		= cs42l42_set_bias_level,
 	.dapm_widgets		= cs42l42_dapm_widgets,
 	.num_dapm_widgets	= ARRAY_SIZE(cs42l42_dapm_widgets),
 	.dapm_routes		= cs42l42_audio_map,

From 19325cfea04446bc79b36bffd4978af15f46a00e Mon Sep 17 00:00:00 2001
From: Lucas Tanure <tanureal@opensource.cirrus.com>
Date: Fri, 5 Mar 2021 17:34:32 +0000
Subject: [PATCH 0549/1820] ASoC: cs42l42: Always wait at least 3ms after reset

This delay is part of the power-up sequence defined in the datasheet.
A runtime_resume is a power-up so must also include the delay.

Signed-off-by: Lucas Tanure <tanureal@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20210305173442.195740-6-tanureal@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs42l42.c | 3 ++-
 sound/soc/codecs/cs42l42.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c
index eee3fc320030..811b7b1c9732 100644
--- a/sound/soc/codecs/cs42l42.c
+++ b/sound/soc/codecs/cs42l42.c
@@ -1756,7 +1756,7 @@ static int cs42l42_i2c_probe(struct i2c_client *i2c_client,
 		dev_dbg(&i2c_client->dev, "Found reset GPIO\n");
 		gpiod_set_value_cansleep(cs42l42->reset_gpio, 1);
 	}
-	mdelay(3);
+	usleep_range(CS42L42_BOOT_TIME_US, CS42L42_BOOT_TIME_US * 2);
 
 	/* Request IRQ */
 	ret = devm_request_threaded_irq(&i2c_client->dev,
@@ -1881,6 +1881,7 @@ static int cs42l42_runtime_resume(struct device *dev)
 	}
 
 	gpiod_set_value_cansleep(cs42l42->reset_gpio, 1);
+	usleep_range(CS42L42_BOOT_TIME_US, CS42L42_BOOT_TIME_US * 2);
 
 	regcache_cache_only(cs42l42->regmap, false);
 	regcache_sync(cs42l42->regmap);
diff --git a/sound/soc/codecs/cs42l42.h b/sound/soc/codecs/cs42l42.h
index 9b017b76828a..866d7c873e3c 100644
--- a/sound/soc/codecs/cs42l42.h
+++ b/sound/soc/codecs/cs42l42.h
@@ -740,6 +740,7 @@
 #define CS42L42_FRAC2_VAL(val)	(((val) & 0xff0000) >> 16)
 
 #define CS42L42_NUM_SUPPLIES	5
+#define CS42L42_BOOT_TIME_US	3000
 
 static const char *const cs42l42_supply_names[CS42L42_NUM_SUPPLIES] = {
 	"VA",

From 5346f0e80b7160c91fb599d4545fd12560c286ed Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 4 Mar 2021 16:56:46 -0500
Subject: [PATCH 0550/1820] ASoC: codecs: lpass-va-macro: mute/unmute all
 active decimators

An interface can have multiple decimators enabled, so loop over all active
decimators. Otherwise only one channel will be unmuted, and other channels
will be zero. This fixes recording from dual DMIC as a single two channel
stream.

Also remove the now unused "active_decimator" field.

Fixes: 908e6b1df26e ("ASoC: codecs: lpass-va-macro: Add support to VA Macro")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20210304215646.17956-1-jonathan@marek.ca
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/lpass-va-macro.c | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/sound/soc/codecs/lpass-va-macro.c b/sound/soc/codecs/lpass-va-macro.c
index 91e6890d6efc..3d6976a3d9e4 100644
--- a/sound/soc/codecs/lpass-va-macro.c
+++ b/sound/soc/codecs/lpass-va-macro.c
@@ -189,7 +189,6 @@ struct va_macro {
 	struct device *dev;
 	unsigned long active_ch_mask[VA_MACRO_MAX_DAIS];
 	unsigned long active_ch_cnt[VA_MACRO_MAX_DAIS];
-	unsigned long active_decimator[VA_MACRO_MAX_DAIS];
 	u16 dmic_clk_div;
 
 	int dec_mode[VA_MACRO_NUM_DECIMATORS];
@@ -549,11 +548,9 @@ static int va_macro_tx_mixer_put(struct snd_kcontrol *kcontrol,
 	if (enable) {
 		set_bit(dec_id, &va->active_ch_mask[dai_id]);
 		va->active_ch_cnt[dai_id]++;
-		va->active_decimator[dai_id] = dec_id;
 	} else {
 		clear_bit(dec_id, &va->active_ch_mask[dai_id]);
 		va->active_ch_cnt[dai_id]--;
-		va->active_decimator[dai_id] = -1;
 	}
 
 	snd_soc_dapm_mixer_update_power(widget->dapm, kcontrol, enable, update);
@@ -880,18 +877,19 @@ static int va_macro_digital_mute(struct snd_soc_dai *dai, int mute, int stream)
 	struct va_macro *va = snd_soc_component_get_drvdata(component);
 	u16 tx_vol_ctl_reg, decimator;
 
-	decimator = va->active_decimator[dai->id];
-
-	tx_vol_ctl_reg = CDC_VA_TX0_TX_PATH_CTL +
-				VA_MACRO_TX_PATH_OFFSET * decimator;
-	if (mute)
-		snd_soc_component_update_bits(component, tx_vol_ctl_reg,
-					      CDC_VA_TX_PATH_PGA_MUTE_EN_MASK,
-					      CDC_VA_TX_PATH_PGA_MUTE_EN);
-	else
-		snd_soc_component_update_bits(component, tx_vol_ctl_reg,
-					      CDC_VA_TX_PATH_PGA_MUTE_EN_MASK,
-					      CDC_VA_TX_PATH_PGA_MUTE_DISABLE);
+	for_each_set_bit(decimator, &va->active_ch_mask[dai->id],
+			 VA_MACRO_DEC_MAX) {
+		tx_vol_ctl_reg = CDC_VA_TX0_TX_PATH_CTL +
+					VA_MACRO_TX_PATH_OFFSET * decimator;
+		if (mute)
+			snd_soc_component_update_bits(component, tx_vol_ctl_reg,
+					CDC_VA_TX_PATH_PGA_MUTE_EN_MASK,
+					CDC_VA_TX_PATH_PGA_MUTE_EN);
+		else
+			snd_soc_component_update_bits(component, tx_vol_ctl_reg,
+					CDC_VA_TX_PATH_PGA_MUTE_EN_MASK,
+					CDC_VA_TX_PATH_PGA_MUTE_DISABLE);
+	}
 
 	return 0;
 }

From e4b8b7c916038c1ffcba2c4ce92d5523c4cc2f46 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 4 Mar 2021 19:50:48 -0500
Subject: [PATCH 0551/1820] ASoC: codecs: lpass-wsa-macro: fix RX MIX input
 controls

Attempting to use the RX MIX path at 48kHz plays at 96kHz, because these
controls are incorrectly toggling the first bit of the register, which
is part of the FS_RATE field.

Fix the problem by using the same method used by the "WSA RX_MIX EC0_MUX"
control, which is to use SND_SOC_NOPM as the register and use an enum in
the shift field instead.

Fixes: 2c4066e5d428 ("ASoC: codecs: lpass-wsa-macro: add dapm widgets and route")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20210305005049.24726-1-jonathan@marek.ca
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/lpass-wsa-macro.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/sound/soc/codecs/lpass-wsa-macro.c b/sound/soc/codecs/lpass-wsa-macro.c
index 5ebcd935ba89..9ca49a165f69 100644
--- a/sound/soc/codecs/lpass-wsa-macro.c
+++ b/sound/soc/codecs/lpass-wsa-macro.c
@@ -1211,14 +1211,16 @@ static int wsa_macro_enable_mix_path(struct snd_soc_dapm_widget *w,
 				     struct snd_kcontrol *kcontrol, int event)
 {
 	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
-	u16 gain_reg;
+	u16 path_reg, gain_reg;
 	int val;
 
-	switch (w->reg) {
-	case CDC_WSA_RX0_RX_PATH_MIX_CTL:
+	switch (w->shift) {
+	case WSA_MACRO_RX_MIX0:
+		path_reg = CDC_WSA_RX0_RX_PATH_MIX_CTL;
 		gain_reg = CDC_WSA_RX0_RX_VOL_MIX_CTL;
 		break;
-	case CDC_WSA_RX1_RX_PATH_MIX_CTL:
+	case WSA_MACRO_RX_MIX1:
+		path_reg = CDC_WSA_RX1_RX_PATH_MIX_CTL;
 		gain_reg = CDC_WSA_RX1_RX_VOL_MIX_CTL;
 		break;
 	default:
@@ -1231,7 +1233,7 @@ static int wsa_macro_enable_mix_path(struct snd_soc_dapm_widget *w,
 		snd_soc_component_write(component, gain_reg, val);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
-		snd_soc_component_update_bits(component, w->reg,
+		snd_soc_component_update_bits(component, path_reg,
 					      CDC_WSA_RX_PATH_MIX_CLK_EN_MASK,
 					      CDC_WSA_RX_PATH_MIX_CLK_DISABLE);
 		break;
@@ -2068,14 +2070,14 @@ static const struct snd_soc_dapm_widget wsa_macro_dapm_widgets[] = {
 	SND_SOC_DAPM_MUX("WSA_RX0 INP0", SND_SOC_NOPM, 0, 0, &rx0_prim_inp0_mux),
 	SND_SOC_DAPM_MUX("WSA_RX0 INP1", SND_SOC_NOPM, 0, 0, &rx0_prim_inp1_mux),
 	SND_SOC_DAPM_MUX("WSA_RX0 INP2", SND_SOC_NOPM, 0, 0, &rx0_prim_inp2_mux),
-	SND_SOC_DAPM_MUX_E("WSA_RX0 MIX INP", CDC_WSA_RX0_RX_PATH_MIX_CTL,
-			   0, 0, &rx0_mix_mux, wsa_macro_enable_mix_path,
+	SND_SOC_DAPM_MUX_E("WSA_RX0 MIX INP", SND_SOC_NOPM, WSA_MACRO_RX_MIX0,
+			   0, &rx0_mix_mux, wsa_macro_enable_mix_path,
 			   SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
 	SND_SOC_DAPM_MUX("WSA_RX1 INP0", SND_SOC_NOPM, 0, 0, &rx1_prim_inp0_mux),
 	SND_SOC_DAPM_MUX("WSA_RX1 INP1", SND_SOC_NOPM, 0, 0, &rx1_prim_inp1_mux),
 	SND_SOC_DAPM_MUX("WSA_RX1 INP2", SND_SOC_NOPM, 0, 0, &rx1_prim_inp2_mux),
-	SND_SOC_DAPM_MUX_E("WSA_RX1 MIX INP", CDC_WSA_RX1_RX_PATH_MIX_CTL,
-			   0, 0, &rx1_mix_mux, wsa_macro_enable_mix_path,
+	SND_SOC_DAPM_MUX_E("WSA_RX1 MIX INP", SND_SOC_NOPM, WSA_MACRO_RX_MIX1,
+			   0, &rx1_mix_mux, wsa_macro_enable_mix_path,
 			   SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
 
 	SND_SOC_DAPM_MIXER_E("WSA_RX INT0 MIX", SND_SOC_NOPM, 0, 0, NULL, 0,

From ac101985cad3912e484295bd0ec22d117fee9f17 Mon Sep 17 00:00:00 2001
From: Peter Robinson <pbrobinson@gmail.com>
Date: Sun, 7 Mar 2021 16:23:37 +0000
Subject: [PATCH 0552/1820] ASoC: remove remnants of sirf prima/atlas audio
 codec

In 61fbeb5 the sirf prima/atlas drivers were removed. This cleans
up a stray header and some Kconfig entries for the codec that
were missed in the process.

Fixes: 61fbeb5dcb3d (ASoC: remove sirf prima/atlas drivers)
Signed-off-by: Peter Robinson <pbrobinson@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Mark Brown <broonie@kernel.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20210307162338.1160604-1-pbrobinson@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/Kconfig            |   5 --
 sound/soc/codecs/sirf-audio-codec.h | 124 ----------------------------
 2 files changed, 129 deletions(-)
 delete mode 100644 sound/soc/codecs/sirf-audio-codec.h

diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index e4cf14e66a51..1c87b42606c9 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -186,7 +186,6 @@ config SND_SOC_ALL_CODECS
 	imply SND_SOC_SI476X
 	imply SND_SOC_SIMPLE_AMPLIFIER
 	imply SND_SOC_SIMPLE_MUX
-	imply SND_SOC_SIRF_AUDIO_CODEC
 	imply SND_SOC_SPDIF
 	imply SND_SOC_SSM2305
 	imply SND_SOC_SSM2518
@@ -1279,10 +1278,6 @@ config SND_SOC_SIMPLE_MUX
 	tristate "Simple Audio Mux"
 	select GPIOLIB
 
-config SND_SOC_SIRF_AUDIO_CODEC
-	tristate "SiRF SoC internal audio codec"
-	select REGMAP_MMIO
-
 config SND_SOC_SPDIF
 	tristate "S/PDIF CODEC"
 
diff --git a/sound/soc/codecs/sirf-audio-codec.h b/sound/soc/codecs/sirf-audio-codec.h
deleted file mode 100644
index a7fe2680f4c7..000000000000
--- a/sound/soc/codecs/sirf-audio-codec.h
+++ /dev/null
@@ -1,124 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * SiRF inner codec controllers define
- *
- * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company.
- */
-
-#ifndef _SIRF_AUDIO_CODEC_H
-#define _SIRF_AUDIO_CODEC_H
-
-
-#define AUDIO_IC_CODEC_PWR			(0x00E0)
-#define AUDIO_IC_CODEC_CTRL0			(0x00E4)
-#define AUDIO_IC_CODEC_CTRL1			(0x00E8)
-#define AUDIO_IC_CODEC_CTRL2			(0x00EC)
-#define AUDIO_IC_CODEC_CTRL3			(0x00F0)
-
-#define MICBIASEN		(1 << 3)
-
-#define IC_RDACEN		(1 << 0)
-#define IC_LDACEN		(1 << 1)
-#define IC_HSREN		(1 << 2)
-#define IC_HSLEN		(1 << 3)
-#define IC_SPEN			(1 << 4)
-#define IC_CPEN			(1 << 5)
-
-#define IC_HPRSELR		(1 << 6)
-#define IC_HPLSELR		(1 << 7)
-#define IC_HPRSELL		(1 << 8)
-#define IC_HPLSELL		(1 << 9)
-#define IC_SPSELR		(1 << 10)
-#define IC_SPSELL		(1 << 11)
-
-#define IC_MONOR		(1 << 12)
-#define IC_MONOL		(1 << 13)
-
-#define IC_RXOSRSEL		(1 << 28)
-#define IC_CPFREQ		(1 << 29)
-#define IC_HSINVEN		(1 << 30)
-
-#define IC_MICINREN		(1 << 0)
-#define IC_MICINLEN		(1 << 1)
-#define IC_MICIN1SEL		(1 << 2)
-#define IC_MICIN2SEL		(1 << 3)
-#define IC_MICDIFSEL		(1 << 4)
-#define	IC_LINEIN1SEL		(1 << 5)
-#define	IC_LINEIN2SEL		(1 << 6)
-#define	IC_RADCEN		(1 << 7)
-#define	IC_LADCEN		(1 << 8)
-#define	IC_ALM			(1 << 9)
-
-#define IC_DIGMICEN             (1 << 22)
-#define IC_DIGMICFREQ           (1 << 23)
-#define IC_ADC14B_12            (1 << 24)
-#define IC_FIRDAC_HSL_EN        (1 << 25)
-#define IC_FIRDAC_HSR_EN        (1 << 26)
-#define IC_FIRDAC_LOUT_EN       (1 << 27)
-#define IC_POR                  (1 << 28)
-#define IC_CODEC_CLK_EN         (1 << 29)
-#define IC_HP_3DB_BOOST         (1 << 30)
-
-#define IC_ADC_LEFT_GAIN_SHIFT	16
-#define IC_ADC_RIGHT_GAIN_SHIFT 10
-#define IC_ADC_GAIN_MASK	0x3F
-#define IC_MIC_MAX_GAIN		0x39
-
-#define IC_RXPGAR_MASK		0x3F
-#define IC_RXPGAR_SHIFT		14
-#define IC_RXPGAL_MASK		0x3F
-#define IC_RXPGAL_SHIFT		21
-#define IC_RXPGAR		0x7B
-#define IC_RXPGAL		0x7B
-
-#define AUDIO_PORT_TX_FIFO_LEVEL_CHECK_MASK     0x3F
-#define AUDIO_PORT_TX_FIFO_SC_OFFSET    0
-#define AUDIO_PORT_TX_FIFO_LC_OFFSET    10
-#define AUDIO_PORT_TX_FIFO_HC_OFFSET    20
-
-#define TX_FIFO_SC(x)           (((x) & AUDIO_PORT_TX_FIFO_LEVEL_CHECK_MASK) \
-				<< AUDIO_PORT_TX_FIFO_SC_OFFSET)
-#define TX_FIFO_LC(x)           (((x) & AUDIO_PORT_TX_FIFO_LEVEL_CHECK_MASK) \
-				<< AUDIO_PORT_TX_FIFO_LC_OFFSET)
-#define TX_FIFO_HC(x)           (((x) & AUDIO_PORT_TX_FIFO_LEVEL_CHECK_MASK) \
-				<< AUDIO_PORT_TX_FIFO_HC_OFFSET)
-
-#define AUDIO_PORT_RX_FIFO_LEVEL_CHECK_MASK     0x0F
-#define AUDIO_PORT_RX_FIFO_SC_OFFSET    0
-#define AUDIO_PORT_RX_FIFO_LC_OFFSET    10
-#define AUDIO_PORT_RX_FIFO_HC_OFFSET    20
-
-#define RX_FIFO_SC(x)           (((x) & AUDIO_PORT_RX_FIFO_LEVEL_CHECK_MASK) \
-				<< AUDIO_PORT_RX_FIFO_SC_OFFSET)
-#define RX_FIFO_LC(x)           (((x) & AUDIO_PORT_RX_FIFO_LEVEL_CHECK_MASK) \
-				<< AUDIO_PORT_RX_FIFO_LC_OFFSET)
-#define RX_FIFO_HC(x)           (((x) & AUDIO_PORT_RX_FIFO_LEVEL_CHECK_MASK) \
-				<< AUDIO_PORT_RX_FIFO_HC_OFFSET)
-#define AUDIO_PORT_IC_CODEC_TX_CTRL		(0x00F4)
-#define AUDIO_PORT_IC_CODEC_RX_CTRL		(0x00F8)
-
-#define AUDIO_PORT_IC_TXFIFO_OP			(0x00FC)
-#define AUDIO_PORT_IC_TXFIFO_LEV_CHK		(0x0100)
-#define AUDIO_PORT_IC_TXFIFO_STS		(0x0104)
-#define AUDIO_PORT_IC_TXFIFO_INT		(0x0108)
-#define AUDIO_PORT_IC_TXFIFO_INT_MSK		(0x010C)
-
-#define AUDIO_PORT_IC_RXFIFO_OP			(0x0110)
-#define AUDIO_PORT_IC_RXFIFO_LEV_CHK		(0x0114)
-#define AUDIO_PORT_IC_RXFIFO_STS		(0x0118)
-#define AUDIO_PORT_IC_RXFIFO_INT		(0x011C)
-#define AUDIO_PORT_IC_RXFIFO_INT_MSK		(0x0120)
-
-#define AUDIO_FIFO_START		(1 << 0)
-#define AUDIO_FIFO_RESET		(1 << 1)
-
-#define AUDIO_FIFO_FULL			(1 << 0)
-#define AUDIO_FIFO_EMPTY		(1 << 1)
-#define AUDIO_FIFO_OFLOW		(1 << 2)
-#define AUDIO_FIFO_UFLOW		(1 << 3)
-
-#define IC_TX_ENABLE		(0x03)
-#define IC_RX_ENABLE_MONO	(0x01)
-#define IC_RX_ENABLE_STEREO	(0x03)
-
-#endif /*__SIRF_AUDIO_CODEC_H*/

From 1c668e1c0a0f74472469cd514f40c9012b324c31 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 9 Mar 2021 14:21:27 +0000
Subject: [PATCH 0553/1820] ASoC: qcom: sdm845: Fix array out of bounds access

Static analysis Coverity had detected a potential array out-of-bounds
write issue due to the fact that MAX AFE port Id was set to 16 instead
of using AFE_PORT_MAX macro.

Fix this by properly using AFE_PORT_MAX macro.

Fixes: 1b93a8843147 ("ASoC: qcom: sdm845: handle soundwire stream")
Reported-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20210309142129.14182-2-srinivas.kandagatla@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/sdm845.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
index 6c2760e27ea6..1e2c2d0902ea 100644
--- a/sound/soc/qcom/sdm845.c
+++ b/sound/soc/qcom/sdm845.c
@@ -33,12 +33,12 @@
 struct sdm845_snd_data {
 	struct snd_soc_jack jack;
 	bool jack_setup;
-	bool stream_prepared[SLIM_MAX_RX_PORTS];
+	bool stream_prepared[AFE_PORT_MAX];
 	struct snd_soc_card *card;
 	uint32_t pri_mi2s_clk_count;
 	uint32_t sec_mi2s_clk_count;
 	uint32_t quat_tdm_clk_count;
-	struct sdw_stream_runtime *sruntime[SLIM_MAX_RX_PORTS];
+	struct sdw_stream_runtime *sruntime[AFE_PORT_MAX];
 };
 
 static unsigned int tdm_slot_offset[8] = {0, 4, 8, 12, 16, 20, 24, 28};

From 4800fe6ea1022eb240215b1743d2541adad8efc7 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 9 Mar 2021 14:21:28 +0000
Subject: [PATCH 0554/1820] ASoC: qcom: sdm845: Fix array out of range on rx
 slim channels

WCD934x has only 13 RX SLIM ports however we are setting it as 16
in set_channel_map, this will lead to array out of bounds error!

Orignally caught by enabling USBAN array out of bounds check:

Fixes: 5caf64c633a3 ("ASoC: qcom: sdm845: add support to DB845c and Lenovo Yoga")
Reported-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20210309142129.14182-3-srinivas.kandagatla@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/sdm845.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
index 1e2c2d0902ea..153e9b2de0b5 100644
--- a/sound/soc/qcom/sdm845.c
+++ b/sound/soc/qcom/sdm845.c
@@ -27,7 +27,7 @@
 #define SPK_TDM_RX_MASK         0x03
 #define NUM_TDM_SLOTS           8
 #define SLIM_MAX_TX_PORTS 16
-#define SLIM_MAX_RX_PORTS 16
+#define SLIM_MAX_RX_PORTS 13
 #define WCD934X_DEFAULT_MCLK_RATE	9600000
 
 struct sdm845_snd_data {

From 3bb4852d598f0275ed5996a059df55be7318ac2f Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 9 Mar 2021 14:21:29 +0000
Subject: [PATCH 0555/1820] ASoC: codecs: wcd934x: add a sanity check in set
 channel map

set channel map can be passed with a channel maps, however if
the number of channels that are passed are more than the actual
supported channels then we would be accessing array out of bounds.

So add a sanity check to validate these numbers!

Fixes: a61f3b4f476e ("ASoC: wcd934x: add support to wcd9340/wcd9341 codec")
Reported-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20210309142129.14182-4-srinivas.kandagatla@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wcd934x.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c
index 40f682f5dab8..d18ae5e3ee80 100644
--- a/sound/soc/codecs/wcd934x.c
+++ b/sound/soc/codecs/wcd934x.c
@@ -1873,6 +1873,12 @@ static int wcd934x_set_channel_map(struct snd_soc_dai *dai,
 
 	wcd = snd_soc_component_get_drvdata(dai->component);
 
+	if (tx_num > WCD934X_TX_MAX || rx_num > WCD934X_RX_MAX) {
+		dev_err(wcd->dev, "Invalid tx %d or rx %d channel count\n",
+			tx_num, rx_num);
+		return -EINVAL;
+	}
+
 	if (!tx_slot || !rx_slot) {
 		dev_err(wcd->dev, "Invalid tx_slot=%p, rx_slot=%p\n",
 			tx_slot, rx_slot);

From fd8299181995093948ec6ca75432e797b4a39143 Mon Sep 17 00:00:00 2001
From: Pan Xiuli <xiuli.pan@linux.intel.com>
Date: Mon, 8 Mar 2021 18:41:27 -0600
Subject: [PATCH 0556/1820] ASoC: SOF: intel: fix wrong poll bits in dsp power
 down

The ADSPCS_SPA is Set Power Active bit. To check if DSP is powered
down, we need to check ADSPCS_CPA, the Current Power Active bit.

Fixes: 747503b1813a3 ("ASoC: SOF: Intel: Add Intel specific HDA DSP HW operations")
Reviewed-by: Rander Wang <rander.wang@intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Pan Xiuli <xiuli.pan@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210309004127.4940-1-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda-dsp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c
index 5788fe356960..c3b757cf01a0 100644
--- a/sound/soc/sof/intel/hda-dsp.c
+++ b/sound/soc/sof/intel/hda-dsp.c
@@ -207,7 +207,7 @@ int hda_dsp_core_power_down(struct snd_sof_dev *sdev, unsigned int core_mask)
 
 	ret = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR,
 				HDA_DSP_REG_ADSPCS, adspcs,
-				!(adspcs & HDA_DSP_ADSPCS_SPA_MASK(core_mask)),
+				!(adspcs & HDA_DSP_ADSPCS_CPA_MASK(core_mask)),
 				HDA_DSP_REG_POLL_INTERVAL_US,
 				HDA_DSP_PD_TIMEOUT * USEC_PER_MSEC);
 	if (ret < 0)

From 9e77d96b8e2724ed00380189f7b0ded61113b39f Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Sat, 6 Mar 2021 17:18:31 +0100
Subject: [PATCH 0557/1820] xen/events: reset affinity of 2-level event when
 tearing it down

When creating a new event channel with 2-level events the affinity
needs to be reset initially in order to avoid using an old affinity
from earlier usage of the event channel port. So when tearing an event
channel down reset all affinity bits.

The same applies to the affinity when onlining a vcpu: all old
affinity settings for this vcpu must be reset. As percpu events get
initialized before the percpu event channel hook is called,
resetting of the affinities happens after offlining a vcpu (this is
working, as initial percpu memory is zeroed out).

Cc: stable@vger.kernel.org
Reported-by: Julien Grall <julien@xen.org>
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Julien Grall <jgrall@amazon.com>
Link: https://lore.kernel.org/r/20210306161833.4552-2-jgross@suse.com
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/events/events_2l.c       | 15 +++++++++++++++
 drivers/xen/events/events_base.c     |  1 +
 drivers/xen/events/events_internal.h |  8 ++++++++
 3 files changed, 24 insertions(+)

diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c
index da87f3a1e351..a7f413c5c190 100644
--- a/drivers/xen/events/events_2l.c
+++ b/drivers/xen/events/events_2l.c
@@ -47,6 +47,11 @@ static unsigned evtchn_2l_max_channels(void)
 	return EVTCHN_2L_NR_CHANNELS;
 }
 
+static void evtchn_2l_remove(evtchn_port_t evtchn, unsigned int cpu)
+{
+	clear_bit(evtchn, BM(per_cpu(cpu_evtchn_mask, cpu)));
+}
+
 static void evtchn_2l_bind_to_cpu(evtchn_port_t evtchn, unsigned int cpu,
 				  unsigned int old_cpu)
 {
@@ -355,9 +360,18 @@ static void evtchn_2l_resume(void)
 				EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD);
 }
 
+static int evtchn_2l_percpu_deinit(unsigned int cpu)
+{
+	memset(per_cpu(cpu_evtchn_mask, cpu), 0, sizeof(xen_ulong_t) *
+			EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD);
+
+	return 0;
+}
+
 static const struct evtchn_ops evtchn_ops_2l = {
 	.max_channels      = evtchn_2l_max_channels,
 	.nr_channels       = evtchn_2l_max_channels,
+	.remove            = evtchn_2l_remove,
 	.bind_to_cpu       = evtchn_2l_bind_to_cpu,
 	.clear_pending     = evtchn_2l_clear_pending,
 	.set_pending       = evtchn_2l_set_pending,
@@ -367,6 +381,7 @@ static const struct evtchn_ops evtchn_ops_2l = {
 	.unmask            = evtchn_2l_unmask,
 	.handle_events     = evtchn_2l_handle_events,
 	.resume	           = evtchn_2l_resume,
+	.percpu_deinit     = evtchn_2l_percpu_deinit,
 };
 
 void __init xen_evtchn_2l_init(void)
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index adb7260e94b2..7e23808892a7 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -377,6 +377,7 @@ static int xen_irq_info_pirq_setup(unsigned irq,
 static void xen_irq_info_cleanup(struct irq_info *info)
 {
 	set_evtchn_to_irq(info->evtchn, -1);
+	xen_evtchn_port_remove(info->evtchn, info->cpu);
 	info->evtchn = 0;
 	channels_on_cpu_dec(info);
 }
diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h
index 0a97c0549db7..18a4090d0709 100644
--- a/drivers/xen/events/events_internal.h
+++ b/drivers/xen/events/events_internal.h
@@ -14,6 +14,7 @@ struct evtchn_ops {
 	unsigned (*nr_channels)(void);
 
 	int (*setup)(evtchn_port_t port);
+	void (*remove)(evtchn_port_t port, unsigned int cpu);
 	void (*bind_to_cpu)(evtchn_port_t evtchn, unsigned int cpu,
 			    unsigned int old_cpu);
 
@@ -54,6 +55,13 @@ static inline int xen_evtchn_port_setup(evtchn_port_t evtchn)
 	return 0;
 }
 
+static inline void xen_evtchn_port_remove(evtchn_port_t evtchn,
+					  unsigned int cpu)
+{
+	if (evtchn_ops->remove)
+		evtchn_ops->remove(evtchn, cpu);
+}
+
 static inline void xen_evtchn_port_bind_to_cpu(evtchn_port_t evtchn,
 					       unsigned int cpu,
 					       unsigned int old_cpu)

From 5d5f2919273d1089a00556cad68e7f462f3dd2eb Mon Sep 17 00:00:00 2001
From: Lars Povlsen <lars.povlsen@microchip.com>
Date: Wed, 3 Feb 2021 13:38:25 +0100
Subject: [PATCH 0558/1820] pinctrl: microchip-sgpio: Fix wrong register offset
 for IRQ trigger

This patch fixes using a wrong register offset when configuring an IRQ
trigger type.

Fixes: be2dc859abd4 ("pinctrl: pinctrl-microchip-sgpio: Add irq support (for sparx5)")
Reported-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Lars Povlsen <lars.povlsen@microchip.com>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20210203123825.611576-1-lars.povlsen@microchip.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-microchip-sgpio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-microchip-sgpio.c b/drivers/pinctrl/pinctrl-microchip-sgpio.c
index f35edb0eac40..c12fa57ebd12 100644
--- a/drivers/pinctrl/pinctrl-microchip-sgpio.c
+++ b/drivers/pinctrl/pinctrl-microchip-sgpio.c
@@ -572,7 +572,7 @@ static void microchip_sgpio_irq_settype(struct irq_data *data,
 	/* Type value spread over 2 registers sets: low, high bit */
 	sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER, addr.bit,
 			 BIT(addr.port), (!!(type & 0x1)) << addr.port);
-	sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER + SGPIO_MAX_BITS, addr.bit,
+	sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER, SGPIO_MAX_BITS + addr.bit,
 			 BIT(addr.port), (!!(type & 0x2)) << addr.port);
 
 	if (type == SGPIO_INT_TRG_LEVEL)

From c971af25cda94afe71617790826a86253e88eab0 Mon Sep 17 00:00:00 2001
From: Wang Panzhenzhuan <randy.wang@rock-chips.com>
Date: Tue, 23 Feb 2021 18:07:25 +0800
Subject: [PATCH 0559/1820] pinctrl: rockchip: fix restore error in resume

The restore in resume should match to suspend which only set for RK3288
SoCs pinctrl.

Fixes: 8dca933127024 ("pinctrl: rockchip: save and restore gpio6_c6 pinmux in suspend/resume")
Reviewed-by: Jianqun Xu <jay.xu@rock-chips.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Wang Panzhenzhuan <randy.wang@rock-chips.com>
Signed-off-by: Jianqun Xu <jay.xu@rock-chips.com>
Link: https://lore.kernel.org/r/20210223100725.269240-1-jay.xu@rock-chips.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-rockchip.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index aa1a1c850d05..53a0badc6b03 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -3727,12 +3727,15 @@ static int __maybe_unused rockchip_pinctrl_suspend(struct device *dev)
 static int __maybe_unused rockchip_pinctrl_resume(struct device *dev)
 {
 	struct rockchip_pinctrl *info = dev_get_drvdata(dev);
-	int ret = regmap_write(info->regmap_base, RK3288_GRF_GPIO6C_IOMUX,
-			       rk3288_grf_gpio6c_iomux |
-			       GPIO6C6_SEL_WRITE_ENABLE);
+	int ret;
 
-	if (ret)
-		return ret;
+	if (info->ctrl->type == RK3288) {
+		ret = regmap_write(info->regmap_base, RK3288_GRF_GPIO6C_IOMUX,
+				   rk3288_grf_gpio6c_iomux |
+				   GPIO6C6_SEL_WRITE_ENABLE);
+		if (ret)
+			return ret;
+	}
 
 	return pinctrl_force_default(info->pctl_dev);
 }

From 8891123f9cbb9c1ee531e5a87fa116f0af685c48 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Mon, 1 Mar 2021 17:30:11 +0300
Subject: [PATCH 0560/1820] software node: Fix node registration

Software node can not be registered before its parent.

Fixes: 80488a6b1d3c ("software node: Add support for static node descriptors")
Cc: 5.10+ <stable@vger.kernel.org> # 5.10+
Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/swnode.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index 37179a8b1ceb..74db8c971db7 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -938,6 +938,9 @@ int software_node_register(const struct software_node *node)
 	if (software_node_to_swnode(node))
 		return -EEXIST;
 
+	if (node->parent && !parent)
+		return -EINVAL;
+
 	return PTR_ERR_OR_ZERO(swnode_register(node, parent, 0));
 }
 EXPORT_SYMBOL_GPL(software_node_register);

From 2a92c90f2ecca4475d6050f2f938a1755a8954cc Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Mon, 1 Mar 2021 17:30:12 +0300
Subject: [PATCH 0561/1820] software node: Fix device_add_software_node()

The function device_add_software_node() was meant to
register the node supplied to it, but only if that node
wasn't already registered. Right now the function attempts
to always register the node. That will cause a failure with
nodes that are already registered.

Fixing that by incrementing the reference count of the nodes
that have already been registered, and only registering the
new nodes. Also, clarifying the behaviour in the function
documentation.

Fixes: e68d0119e328 ("software node: Introduce device_add_software_node()")
Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/swnode.c    | 26 +++++++++++++++++---------
 include/linux/property.h |  2 +-
 2 files changed, 18 insertions(+), 10 deletions(-)

diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index 74db8c971db7..fa3719ef80e4 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -1005,25 +1005,33 @@ EXPORT_SYMBOL_GPL(fwnode_remove_software_node);
 /**
  * device_add_software_node - Assign software node to a device
  * @dev: The device the software node is meant for.
- * @swnode: The software node.
+ * @node: The software node.
  *
- * This function will register @swnode and make it the secondary firmware node
- * pointer of @dev. If @dev has no primary node, then @swnode will become the primary
- * node.
+ * This function will make @node the secondary firmware node pointer of @dev. If
+ * @dev has no primary node, then @node will become the primary node. The
+ * function will register @node automatically if it wasn't already registered.
  */
-int device_add_software_node(struct device *dev, const struct software_node *swnode)
+int device_add_software_node(struct device *dev, const struct software_node *node)
 {
+	struct swnode *swnode;
 	int ret;
 
 	/* Only one software node per device. */
 	if (dev_to_swnode(dev))
 		return -EBUSY;
 
-	ret = software_node_register(swnode);
-	if (ret)
-		return ret;
+	swnode = software_node_to_swnode(node);
+	if (swnode) {
+		kobject_get(&swnode->kobj);
+	} else {
+		ret = software_node_register(node);
+		if (ret)
+			return ret;
 
-	set_secondary_fwnode(dev, software_node_fwnode(swnode));
+		swnode = software_node_to_swnode(node);
+	}
+
+	set_secondary_fwnode(dev, &swnode->fwnode);
 
 	return 0;
 }
diff --git a/include/linux/property.h b/include/linux/property.h
index dafccfce0262..dd4687b56239 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -488,7 +488,7 @@ fwnode_create_software_node(const struct property_entry *properties,
 			    const struct fwnode_handle *parent);
 void fwnode_remove_software_node(struct fwnode_handle *fwnode);
 
-int device_add_software_node(struct device *dev, const struct software_node *swnode);
+int device_add_software_node(struct device *dev, const struct software_node *node);
 void device_remove_software_node(struct device *dev);
 
 int device_create_managed_software_node(struct device *dev,

From 05962f95f9ac7af25fea037ef51b37c0eccb5590 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 6 Mar 2021 13:58:48 -0700
Subject: [PATCH 0562/1820] io_uring: SQPOLL parking fixes

We keep running into weird dependency issues between the sqd lock and
the parking state. Disentangle the SQPOLL thread from the last bits of
the kthread parking inheritance, and just replace the parking state,
and two associated locks, with a single rw mutex. The SQPOLL thread
keeps the mutex for read all the time, except if someone has marked us
needing to park. Then we drop/re-acquire and try again.

This greatly simplifies the parking state machine (by just getting rid
of it), and makes it a lot more obvious how it works - if you need to
modify the ctx list, then you simply park the thread which will grab
the lock for writing.

Fold in fix from Hillf Danton on not setting STOP on a fatal signal.

Fixes: e54945ae947f ("io_uring: SQPOLL stop error handling fixes")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 133 +++++++++++++-------------------------------------
 1 file changed, 34 insertions(+), 99 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 7cf96be691d8..2a3542b487ff 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -258,12 +258,11 @@ enum {
 
 struct io_sq_data {
 	refcount_t		refs;
-	struct mutex		lock;
+	struct rw_semaphore	rw_lock;
 
 	/* ctx's that are using this sqd */
 	struct list_head	ctx_list;
 	struct list_head	ctx_new_list;
-	struct mutex		ctx_lock;
 
 	struct task_struct	*thread;
 	struct wait_queue_head	wait;
@@ -274,7 +273,6 @@ struct io_sq_data {
 
 	unsigned long		state;
 	struct completion	startup;
-	struct completion	parked;
 	struct completion	exited;
 };
 
@@ -6638,45 +6636,6 @@ static void io_sqd_init_new(struct io_sq_data *sqd)
 	io_sqd_update_thread_idle(sqd);
 }
 
-static bool io_sq_thread_should_stop(struct io_sq_data *sqd)
-{
-	return test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
-}
-
-static bool io_sq_thread_should_park(struct io_sq_data *sqd)
-{
-	return test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
-}
-
-static void io_sq_thread_parkme(struct io_sq_data *sqd)
-{
-	for (;;) {
-		/*
-		 * TASK_PARKED is a special state; we must serialize against
-		 * possible pending wakeups to avoid store-store collisions on
-		 * task->state.
-		 *
-		 * Such a collision might possibly result in the task state
-		 * changin from TASK_PARKED and us failing the
-		 * wait_task_inactive() in kthread_park().
-		 */
-		set_special_state(TASK_PARKED);
-		if (!test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state))
-			break;
-
-		/*
-		 * Thread is going to call schedule(), do not preempt it,
-		 * or the caller of kthread_park() may spend more time in
-		 * wait_task_inactive().
-		 */
-		preempt_disable();
-		complete(&sqd->parked);
-		schedule_preempt_disabled();
-		preempt_enable();
-	}
-	__set_current_state(TASK_RUNNING);
-}
-
 static int io_sq_thread(void *data)
 {
 	struct io_sq_data *sqd = data;
@@ -6697,17 +6656,16 @@ static int io_sq_thread(void *data)
 
 	wait_for_completion(&sqd->startup);
 
-	while (!io_sq_thread_should_stop(sqd)) {
+	down_read(&sqd->rw_lock);
+
+	while (!test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)) {
 		int ret;
 		bool cap_entries, sqt_spin, needs_sched;
 
-		/*
-		 * Any changes to the sqd lists are synchronized through the
-		 * thread parking. This synchronizes the thread vs users,
-		 * the users are synchronized on the sqd->ctx_lock.
-		 */
-		if (io_sq_thread_should_park(sqd)) {
-			io_sq_thread_parkme(sqd);
+		if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) {
+			up_read(&sqd->rw_lock);
+			cond_resched();
+			down_read(&sqd->rw_lock);
 			continue;
 		}
 		if (unlikely(!list_empty(&sqd->ctx_new_list))) {
@@ -6752,12 +6710,14 @@ static int io_sq_thread(void *data)
 			}
 		}
 
-		if (needs_sched && !io_sq_thread_should_park(sqd)) {
+		if (needs_sched && !test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) {
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				io_ring_set_wakeup_flag(ctx);
 
+			up_read(&sqd->rw_lock);
 			schedule();
 			try_to_freeze();
+			down_read(&sqd->rw_lock);
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				io_ring_clear_wakeup_flag(ctx);
 		}
@@ -6768,28 +6728,16 @@ static int io_sq_thread(void *data)
 
 	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 		io_uring_cancel_sqpoll(ctx);
+	up_read(&sqd->rw_lock);
 
 	io_run_task_work();
 
-	/*
-	 * Ensure that we park properly if racing with someone trying to park
-	 * while we're exiting. If we fail to grab the lock, check park and
-	 * park if necessary. The ordering with the park bit and the lock
-	 * ensures that we catch this reliably.
-	 */
-	if (!mutex_trylock(&sqd->lock)) {
-		if (io_sq_thread_should_park(sqd))
-			io_sq_thread_parkme(sqd);
-		mutex_lock(&sqd->lock);
-	}
-
+	down_write(&sqd->rw_lock);
 	sqd->thread = NULL;
-	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
+	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 		io_ring_set_wakeup_flag(ctx);
-	}
-
+	up_write(&sqd->rw_lock);
 	complete(&sqd->exited);
-	mutex_unlock(&sqd->lock);
 	do_exit(0);
 }
 
@@ -7088,44 +7036,40 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 }
 
 static void io_sq_thread_unpark(struct io_sq_data *sqd)
-	__releases(&sqd->lock)
+	__releases(&sqd->rw_lock)
 {
 	if (sqd->thread == current)
 		return;
 	clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
-	if (sqd->thread)
-		wake_up_state(sqd->thread, TASK_PARKED);
-	mutex_unlock(&sqd->lock);
+	up_write(&sqd->rw_lock);
 }
 
 static void io_sq_thread_park(struct io_sq_data *sqd)
-	__acquires(&sqd->lock)
+	__acquires(&sqd->rw_lock)
 {
 	if (sqd->thread == current)
 		return;
 	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
-	mutex_lock(&sqd->lock);
-	if (sqd->thread) {
+	down_write(&sqd->rw_lock);
+	/* set again for consistency, in case concurrent parks are happening */
+	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
+	if (sqd->thread)
 		wake_up_process(sqd->thread);
-		wait_for_completion(&sqd->parked);
-	}
 }
 
 static void io_sq_thread_stop(struct io_sq_data *sqd)
 {
 	if (test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state))
 		return;
-	mutex_lock(&sqd->lock);
-	if (sqd->thread) {
-		set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
-		WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state));
-		wake_up_process(sqd->thread);
-		mutex_unlock(&sqd->lock);
-		wait_for_completion(&sqd->exited);
-		WARN_ON_ONCE(sqd->thread);
-	} else {
-		mutex_unlock(&sqd->lock);
+	down_write(&sqd->rw_lock);
+	if (!sqd->thread) {
+		up_write(&sqd->rw_lock);
+		return;
 	}
+	set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
+	wake_up_process(sqd->thread);
+	up_write(&sqd->rw_lock);
+	wait_for_completion(&sqd->exited);
 }
 
 static void io_put_sq_data(struct io_sq_data *sqd)
@@ -7142,18 +7086,13 @@ static void io_sq_thread_finish(struct io_ring_ctx *ctx)
 
 	if (sqd) {
 		complete(&sqd->startup);
-		if (sqd->thread) {
+		if (sqd->thread)
 			wait_for_completion(&ctx->sq_thread_comp);
-			io_sq_thread_park(sqd);
-		}
 
-		mutex_lock(&sqd->ctx_lock);
+		io_sq_thread_park(sqd);
 		list_del(&ctx->sqd_list);
 		io_sqd_update_thread_idle(sqd);
-		mutex_unlock(&sqd->ctx_lock);
-
-		if (sqd->thread)
-			io_sq_thread_unpark(sqd);
+		io_sq_thread_unpark(sqd);
 
 		io_put_sq_data(sqd);
 		ctx->sq_data = NULL;
@@ -7202,11 +7141,9 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p)
 	refcount_set(&sqd->refs, 1);
 	INIT_LIST_HEAD(&sqd->ctx_list);
 	INIT_LIST_HEAD(&sqd->ctx_new_list);
-	mutex_init(&sqd->ctx_lock);
-	mutex_init(&sqd->lock);
+	init_rwsem(&sqd->rw_lock);
 	init_waitqueue_head(&sqd->wait);
 	init_completion(&sqd->startup);
-	init_completion(&sqd->parked);
 	init_completion(&sqd->exited);
 	return sqd;
 }
@@ -7880,9 +7817,7 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 		ctx->sq_creds = get_current_cred();
 		ctx->sq_data = sqd;
 		io_sq_thread_park(sqd);
-		mutex_lock(&sqd->ctx_lock);
 		list_add(&ctx->sqd_list, &sqd->ctx_new_list);
-		mutex_unlock(&sqd->ctx_lock);
 		io_sq_thread_unpark(sqd);
 
 		ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);

From f458dd8441e56d122ddf1d8e2af0b6ee62f52af9 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Mon, 8 Mar 2021 12:14:14 +0000
Subject: [PATCH 0563/1820] io_uring: fix unrelated ctx reqs cancellation

io-wq now is per-task, so cancellations now should match against
request's ctx.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2a3542b487ff..d4f018f5838d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -5573,22 +5573,30 @@ add:
 	return 0;
 }
 
+struct io_cancel_data {
+	struct io_ring_ctx *ctx;
+	u64 user_data;
+};
+
 static bool io_cancel_cb(struct io_wq_work *work, void *data)
 {
 	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+	struct io_cancel_data *cd = data;
 
-	return req->user_data == (unsigned long) data;
+	return req->ctx == cd->ctx && req->user_data == cd->user_data;
 }
 
-static int io_async_cancel_one(struct io_uring_task *tctx, void *sqe_addr)
+static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data,
+			       struct io_ring_ctx *ctx)
 {
+	struct io_cancel_data data = { .ctx = ctx, .user_data = user_data, };
 	enum io_wq_cancel cancel_ret;
 	int ret = 0;
 
-	if (!tctx->io_wq)
+	if (!tctx || !tctx->io_wq)
 		return -ENOENT;
 
-	cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, sqe_addr, false);
+	cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, &data, false);
 	switch (cancel_ret) {
 	case IO_WQ_CANCEL_OK:
 		ret = 0;
@@ -5611,8 +5619,7 @@ static void io_async_find_and_cancel(struct io_ring_ctx *ctx,
 	unsigned long flags;
 	int ret;
 
-	ret = io_async_cancel_one(req->task->io_uring,
-					(void *) (unsigned long) sqe_addr);
+	ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx);
 	if (ret != -ENOENT) {
 		spin_lock_irqsave(&ctx->completion_lock, flags);
 		goto done;

From 0298ef969a110ca03654f0cea9b50e3f3b331acc Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Mon, 8 Mar 2021 13:20:57 +0000
Subject: [PATCH 0564/1820] io_uring: clean R_DISABLED startup mess

There are enough of problems with IORING_SETUP_R_DISABLED, including the
burden of checking and kicking off the SQO task all over the codebase --
for exit/cancel/etc.

Rework it, always start the thread but don't do submit unless the flag
is gone, that's much easier.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 25 ++++++-------------------
 1 file changed, 6 insertions(+), 19 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index d4f018f5838d..3f6db813d670 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6606,7 +6606,8 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
 		if (!list_empty(&ctx->iopoll_list))
 			io_do_iopoll(ctx, &nr_events, 0);
 
-		if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)))
+		if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) &&
+		    !(ctx->flags & IORING_SETUP_R_DISABLED))
 			ret = io_submit_sqes(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
 	}
@@ -7861,6 +7862,7 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 		wake_up_new_task(tsk);
 		if (ret)
 			goto err;
+		complete(&sqd->startup);
 	} else if (p->flags & IORING_SETUP_SQ_AFF) {
 		/* Can't have SQ_AFF without SQPOLL */
 		ret = -EINVAL;
@@ -7873,15 +7875,6 @@ err:
 	return ret;
 }
 
-static void io_sq_offload_start(struct io_ring_ctx *ctx)
-{
-	struct io_sq_data *sqd = ctx->sq_data;
-
-	ctx->flags &= ~IORING_SETUP_R_DISABLED;
-	if (ctx->flags & IORING_SETUP_SQPOLL)
-		complete(&sqd->startup);
-}
-
 static inline void __io_unaccount_mem(struct user_struct *user,
 				      unsigned long nr_pages)
 {
@@ -8742,11 +8735,6 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
 	struct task_struct *task = current;
 
 	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
-		/* never started, nothing to cancel */
-		if (ctx->flags & IORING_SETUP_R_DISABLED) {
-			io_sq_offload_start(ctx);
-			return;
-		}
 		io_sq_thread_park(ctx->sq_data);
 		task = ctx->sq_data->thread;
 		if (task)
@@ -9449,9 +9437,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 	if (ret)
 		goto err;
 
-	if (!(p->flags & IORING_SETUP_R_DISABLED))
-		io_sq_offload_start(ctx);
-
 	memset(&p->sq_off, 0, sizeof(p->sq_off));
 	p->sq_off.head = offsetof(struct io_rings, sq.head);
 	p->sq_off.tail = offsetof(struct io_rings, sq.tail);
@@ -9668,7 +9653,9 @@ static int io_register_enable_rings(struct io_ring_ctx *ctx)
 	if (ctx->restrictions.registered)
 		ctx->restricted = 1;
 
-	io_sq_offload_start(ctx);
+	ctx->flags &= ~IORING_SETUP_R_DISABLED;
+	if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait))
+		wake_up(&ctx->sq_data->wait);
 	return 0;
 }
 

From 61cf93700fe6359552848ed5e3becba6cd760efa Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 8 Mar 2021 14:16:16 +0000
Subject: [PATCH 0565/1820] io_uring: Convert personality_idr to XArray

You can't call idr_remove() from within a idr_for_each() callback,
but you can call xa_erase() from an xa_for_each() loop, so switch the
entire personality_idr from the IDR to the XArray.  This manifests as a
use-after-free as idr_for_each() attempts to walk the rest of the node
after removing the last entry from it.

Fixes: 071698e13ac6 ("io_uring: allow registering credentials")
Cc: stable@vger.kernel.org # 5.6+
Reported-by: yangerkun <yangerkun@huawei.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
[Pavel: rebased (creds load was moved into io_init_req())]
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/7ccff36e1375f2b0ebf73d957f037b43becc0dde.1615212806.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 47 ++++++++++++++++++++++++-----------------------
 1 file changed, 24 insertions(+), 23 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3f6db813d670..84eb499368a4 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -406,7 +406,8 @@ struct io_ring_ctx {
 
 	struct idr		io_buffer_idr;
 
-	struct idr		personality_idr;
+	struct xarray		personalities;
+	u32			pers_next;
 
 	struct {
 		unsigned		cached_cq_tail;
@@ -1137,7 +1138,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	init_completion(&ctx->ref_comp);
 	init_completion(&ctx->sq_thread_comp);
 	idr_init(&ctx->io_buffer_idr);
-	idr_init(&ctx->personality_idr);
+	xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
 	mutex_init(&ctx->uring_lock);
 	init_waitqueue_head(&ctx->wait);
 	spin_lock_init(&ctx->completion_lock);
@@ -6337,7 +6338,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	req->work.list.next = NULL;
 	personality = READ_ONCE(sqe->personality);
 	if (personality) {
-		req->work.creds = idr_find(&ctx->personality_idr, personality);
+		req->work.creds = xa_load(&ctx->personalities, personality);
 		if (!req->work.creds)
 			return -EINVAL;
 		get_cred(req->work.creds);
@@ -8355,7 +8356,6 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	mutex_unlock(&ctx->uring_lock);
 	io_eventfd_unregister(ctx);
 	io_destroy_buffers(ctx);
-	idr_destroy(&ctx->personality_idr);
 
 #if defined(CONFIG_UNIX)
 	if (ctx->ring_sock) {
@@ -8420,7 +8420,7 @@ static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
 {
 	const struct cred *creds;
 
-	creds = idr_remove(&ctx->personality_idr, id);
+	creds = xa_erase(&ctx->personalities, id);
 	if (creds) {
 		put_cred(creds);
 		return 0;
@@ -8429,14 +8429,6 @@ static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
 	return -EINVAL;
 }
 
-static int io_remove_personalities(int id, void *p, void *data)
-{
-	struct io_ring_ctx *ctx = data;
-
-	io_unregister_personality(ctx, id);
-	return 0;
-}
-
 static bool io_run_ctx_fallback(struct io_ring_ctx *ctx)
 {
 	struct callback_head *work, *next;
@@ -8526,13 +8518,17 @@ static void io_ring_exit_work(struct work_struct *work)
 
 static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 {
+	unsigned long index;
+	struct creds *creds;
+
 	mutex_lock(&ctx->uring_lock);
 	percpu_ref_kill(&ctx->refs);
 	/* if force is set, the ring is going away. always drop after that */
 	ctx->cq_overflow_flushed = 1;
 	if (ctx->rings)
 		__io_cqring_overflow_flush(ctx, true, NULL, NULL);
-	idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx);
+	xa_for_each(&ctx->personalities, index, creds)
+		io_unregister_personality(ctx, index);
 	mutex_unlock(&ctx->uring_lock);
 
 	io_kill_timeouts(ctx, NULL, NULL);
@@ -9162,10 +9158,9 @@ out_fput:
 }
 
 #ifdef CONFIG_PROC_FS
-static int io_uring_show_cred(int id, void *p, void *data)
+static int io_uring_show_cred(struct seq_file *m, unsigned int id,
+		const struct cred *cred)
 {
-	const struct cred *cred = p;
-	struct seq_file *m = data;
 	struct user_namespace *uns = seq_user_ns(m);
 	struct group_info *gi;
 	kernel_cap_t cap;
@@ -9233,9 +9228,13 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 		seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf,
 						(unsigned int) buf->len);
 	}
-	if (has_lock && !idr_is_empty(&ctx->personality_idr)) {
+	if (has_lock && !xa_empty(&ctx->personalities)) {
+		unsigned long index;
+		const struct cred *cred;
+
 		seq_printf(m, "Personalities:\n");
-		idr_for_each(&ctx->personality_idr, io_uring_show_cred, m);
+		xa_for_each(&ctx->personalities, index, cred)
+			io_uring_show_cred(m, index, cred);
 	}
 	seq_printf(m, "PollList:\n");
 	spin_lock_irq(&ctx->completion_lock);
@@ -9564,14 +9563,16 @@ out:
 static int io_register_personality(struct io_ring_ctx *ctx)
 {
 	const struct cred *creds;
+	u32 id;
 	int ret;
 
 	creds = get_current_cred();
 
-	ret = idr_alloc_cyclic(&ctx->personality_idr, (void *) creds, 1,
-				USHRT_MAX, GFP_KERNEL);
-	if (ret < 0)
-		put_cred(creds);
+	ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds,
+			XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL);
+	if (!ret)
+		return id;
+	put_cred(creds);
 	return ret;
 }
 

From cc20e3fec682700b673fcd286e6bef8e9da947e2 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 8 Mar 2021 09:34:43 -0700
Subject: [PATCH 0566/1820] io-wq: remove unused 'user' member of io_wq

Previous patches killed the last user of this, now it's just a dead member
in the struct. Get rid of it.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 1ab9324e602f..c2e7031f6d09 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -110,7 +110,6 @@ struct io_wq {
 	io_wq_work_fn *do_work;
 
 	struct task_struct *manager;
-	struct user_struct *user;
 
 	struct io_wq_hash *hash;
 

From 97a73a0f9fbfb2be682fd037814576dbfa0e0da8 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Mon, 8 Mar 2021 17:30:54 +0000
Subject: [PATCH 0567/1820] io_uring: fix io_sq_offload_create error handling

Don't set IO_SQ_THREAD_SHOULD_STOP when io_sq_offload_create() has
failed on io_uring_alloc_task_context() but leave everything to
io_sq_thread_finish(), because currently io_sq_thread_finish()
hangs on trying to park it. That's great it stalls there, because
otherwise the following io_sq_thread_stop() would be skipped on
IO_SQ_THREAD_SHOULD_STOP check and the sqo would race for sqd with
freeing ctx.

A simple error injection gives something like this.

[  245.463955] INFO: task sqpoll-test-hang:523 blocked for more than 122 seconds.
[  245.463983] Call Trace:
[  245.463990]  __schedule+0x36b/0x950
[  245.464005]  schedule+0x68/0xe0
[  245.464013]  schedule_timeout+0x209/0x2a0
[  245.464032]  wait_for_completion+0x8b/0xf0
[  245.464043]  io_sq_thread_finish+0x44/0x1a0
[  245.464049]  io_uring_setup+0x9ea/0xc80
[  245.464058]  __x64_sys_io_uring_setup+0x16/0x20
[  245.464064]  do_syscall_64+0x38/0x50
[  245.464073]  entry_SYSCALL_64_after_hwframe+0x44/0xae

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 84eb499368a4..3299807894ec 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7856,10 +7856,9 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 			ret = PTR_ERR(tsk);
 			goto err;
 		}
-		ret = io_uring_alloc_task_context(tsk, ctx);
-		if (ret)
-			set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
+
 		sqd->thread = tsk;
+		ret = io_uring_alloc_task_context(tsk, ctx);
 		wake_up_new_task(tsk);
 		if (ret)
 			goto err;

From 33cc89a9fc248a486857381584cc6b67d9405fab Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 9 Mar 2021 00:37:58 +0000
Subject: [PATCH 0568/1820] io_uring: add io_disarm_next() helper

A preparation patch placing all preparations before extracting a next
request into a separate helper io_disarm_next().

Also, don't spuriously do ev_posted in a rare case where REQ_F_FAIL_LINK
is set but there are no requests linked (i.e. after cancelling a linked
timeout or setting IOSQE_IO_LINK on a last request of a submission
batch).

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/44ecff68d6b47e1c4e6b891bdde1ddc08cfc3590.1615250156.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 68 ++++++++++++++++++++++++++-------------------------
 1 file changed, 35 insertions(+), 33 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3299807894ec..cc9a2cc95608 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1705,15 +1705,11 @@ static inline void io_remove_next_linked(struct io_kiocb *req)
 	nxt->link = NULL;
 }
 
-static void io_kill_linked_timeout(struct io_kiocb *req)
+static bool io_kill_linked_timeout(struct io_kiocb *req)
+	__must_hold(&req->ctx->completion_lock)
 {
-	struct io_ring_ctx *ctx = req->ctx;
-	struct io_kiocb *link;
+	struct io_kiocb *link = req->link;
 	bool cancelled = false;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ctx->completion_lock, flags);
-	link = req->link;
 
 	/*
 	 * Can happen if a linked timeout fired and link had been like
@@ -1728,50 +1724,48 @@ static void io_kill_linked_timeout(struct io_kiocb *req)
 		ret = hrtimer_try_to_cancel(&io->timer);
 		if (ret != -1) {
 			io_cqring_fill_event(link, -ECANCELED);
-			io_commit_cqring(ctx);
+			io_put_req_deferred(link, 1);
 			cancelled = true;
 		}
 	}
 	req->flags &= ~REQ_F_LINK_TIMEOUT;
-	spin_unlock_irqrestore(&ctx->completion_lock, flags);
-
-	if (cancelled) {
-		io_cqring_ev_posted(ctx);
-		io_put_req(link);
-	}
+	return cancelled;
 }
 
-
 static void io_fail_links(struct io_kiocb *req)
+	__must_hold(&req->ctx->completion_lock)
 {
-	struct io_kiocb *link, *nxt;
-	struct io_ring_ctx *ctx = req->ctx;
-	unsigned long flags;
+	struct io_kiocb *nxt, *link = req->link;
 
-	spin_lock_irqsave(&ctx->completion_lock, flags);
-	link = req->link;
 	req->link = NULL;
-
 	while (link) {
 		nxt = link->link;
 		link->link = NULL;
 
 		trace_io_uring_fail_link(req, link);
 		io_cqring_fill_event(link, -ECANCELED);
-
 		io_put_req_deferred(link, 2);
 		link = nxt;
 	}
-	io_commit_cqring(ctx);
-	spin_unlock_irqrestore(&ctx->completion_lock, flags);
+}
 
-	io_cqring_ev_posted(ctx);
+static bool io_disarm_next(struct io_kiocb *req)
+	__must_hold(&req->ctx->completion_lock)
+{
+	bool posted = false;
+
+	if (likely(req->flags & REQ_F_LINK_TIMEOUT))
+		posted = io_kill_linked_timeout(req);
+	if (unlikely(req->flags & REQ_F_FAIL_LINK)) {
+		posted |= (req->link != NULL);
+		io_fail_links(req);
+	}
+	return posted;
 }
 
 static struct io_kiocb *__io_req_find_next(struct io_kiocb *req)
 {
-	if (req->flags & REQ_F_LINK_TIMEOUT)
-		io_kill_linked_timeout(req);
+	struct io_kiocb *nxt;
 
 	/*
 	 * If LINK is set, we have dependent requests in this chain. If we
@@ -1779,14 +1773,22 @@ static struct io_kiocb *__io_req_find_next(struct io_kiocb *req)
 	 * dependencies to the next request. In case of failure, fail the rest
 	 * of the chain.
 	 */
-	if (likely(!(req->flags & REQ_F_FAIL_LINK))) {
-		struct io_kiocb *nxt = req->link;
+	if (req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_FAIL_LINK)) {
+		struct io_ring_ctx *ctx = req->ctx;
+		unsigned long flags;
+		bool posted;
 
-		req->link = NULL;
-		return nxt;
+		spin_lock_irqsave(&ctx->completion_lock, flags);
+		posted = io_disarm_next(req);
+		if (posted)
+			io_commit_cqring(req->ctx);
+		spin_unlock_irqrestore(&ctx->completion_lock, flags);
+		if (posted)
+			io_cqring_ev_posted(ctx);
 	}
-	io_fail_links(req);
-	return NULL;
+	nxt = req->link;
+	req->link = NULL;
+	return nxt;
 }
 
 static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req)

From 7a612350a989866510dc5c874fd8ffe1f37555d2 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 9 Mar 2021 00:37:59 +0000
Subject: [PATCH 0569/1820] io_uring: fix complete_post races for linked req

Calling io_queue_next() after spin_unlock in io_req_complete_post()
races with the other side extracting and reusing this request. Hand
coded parts of io_req_find_next() considering that io_disarm_next()
and io_req_task_queue() have (and safe) to be called with
completion_lock held.

It already does io_commit_cqring() and io_cqring_ev_posted(), so just
reuse it for post io_disarm_next().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/5672a62f3150ee7c55849f40c0037655c4f2840f.1615250156.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index cc9a2cc95608..f7153483a3ac 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -985,6 +985,7 @@ static const struct io_op_def io_op_defs[] = {
 	[IORING_OP_UNLINKAT] = {},
 };
 
+static bool io_disarm_next(struct io_kiocb *req);
 static void io_uring_del_task_file(unsigned long index);
 static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 					 struct task_struct *task,
@@ -1525,15 +1526,14 @@ static void io_cqring_fill_event(struct io_kiocb *req, long res)
 	__io_cqring_fill_event(req, res, 0);
 }
 
-static inline void io_req_complete_post(struct io_kiocb *req, long res,
-					unsigned int cflags)
+static void io_req_complete_post(struct io_kiocb *req, long res,
+				 unsigned int cflags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ctx->completion_lock, flags);
 	__io_cqring_fill_event(req, res, cflags);
-	io_commit_cqring(ctx);
 	/*
 	 * If we're the last reference to this request, add to our locked
 	 * free_list cache.
@@ -1541,19 +1541,26 @@ static inline void io_req_complete_post(struct io_kiocb *req, long res,
 	if (refcount_dec_and_test(&req->refs)) {
 		struct io_comp_state *cs = &ctx->submit_state.comp;
 
+		if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
+			if (req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_FAIL_LINK))
+				io_disarm_next(req);
+			if (req->link) {
+				io_req_task_queue(req->link);
+				req->link = NULL;
+			}
+		}
 		io_dismantle_req(req);
 		io_put_task(req->task, 1);
 		list_add(&req->compl.list, &cs->locked_free_list);
 		cs->locked_free_nr++;
 	} else
 		req = NULL;
+	io_commit_cqring(ctx);
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
-
 	io_cqring_ev_posted(ctx);
-	if (req) {
-		io_queue_next(req);
+
+	if (req)
 		percpu_ref_put(&ctx->refs);
-	}
 }
 
 static void io_req_complete_state(struct io_kiocb *req, long res,

From 70e35125093b05b0e607ba1f5358ddf76946756c Mon Sep 17 00:00:00 2001
From: yangerkun <yangerkun@huawei.com>
Date: Tue, 9 Mar 2021 11:04:10 +0800
Subject: [PATCH 0570/1820] io-wq: fix ref leak for req in case of exit
 cancelations

do_work such as io_wq_submit_work that cancel the work may leave a ref of
req as 1 if we have links. Fix it by call io_run_cancel.

Fixes: 4fb6ac326204 ("io-wq: improve manager/worker handling over exec")
Signed-off-by: yangerkun <yangerkun@huawei.com>
Link: https://lore.kernel.org/r/20210309030410.3294078-1-yangerkun@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index c2e7031f6d09..3d7060ba547a 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -799,8 +799,7 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
 	/* Can only happen if manager creation fails after exec */
 	if (io_wq_fork_manager(wqe->wq) ||
 	    test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state)) {
-		work->flags |= IO_WQ_WORK_CANCEL;
-		wqe->wq->do_work(work);
+		io_run_cancel(work, wqe);
 		return;
 	}
 

From 93e68e036c2fc1ce18e784418e4e19975a5882b4 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 9 Mar 2021 07:02:21 -0700
Subject: [PATCH 0571/1820] io_uring: move all io_kiocb init early in
 io_init_req()

If we hit an error path in the function, make sure that the io_kiocb is
fully initialized at that point so that freeing the request always sees
a valid state.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index f7153483a3ac..0f18e4a7bd08 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6327,6 +6327,9 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	refcount_set(&req->refs, 2);
 	req->task = current;
 	req->result = 0;
+	req->work.list.next = NULL;
+	req->work.creds = NULL;
+	req->work.flags = 0;
 
 	/* enforce forwards compatibility on users */
 	if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) {
@@ -6344,17 +6347,13 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	    !io_op_defs[req->opcode].buffer_select)
 		return -EOPNOTSUPP;
 
-	req->work.list.next = NULL;
 	personality = READ_ONCE(sqe->personality);
 	if (personality) {
 		req->work.creds = xa_load(&ctx->personalities, personality);
 		if (!req->work.creds)
 			return -EINVAL;
 		get_cred(req->work.creds);
-	} else {
-		req->work.creds = NULL;
 	}
-	req->work.flags = 0;
 	state = &ctx->submit_state;
 
 	/*

From 5199328a0d415b3e372633096b1b92f36b8ac9e5 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Tue, 9 Mar 2021 14:30:41 +0800
Subject: [PATCH 0572/1820] io_uring: remove unneeded variable 'ret'

Fix the following coccicheck warning:
./fs/io_uring.c:8984:5-8: Unneeded variable: "ret". Return "0" on line
8998

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Link: https://lore.kernel.org/r/1615271441-33649-1-git-send-email-yang.lee@linux.alibaba.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 0f18e4a7bd08..6325f32ef6a3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -9022,7 +9022,6 @@ static unsigned long io_uring_nommu_get_unmapped_area(struct file *file,
 
 static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
 {
-	int ret = 0;
 	DEFINE_WAIT(wait);
 
 	do {
@@ -9036,7 +9035,7 @@ static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
 	} while (!signal_pending(current));
 
 	finish_wait(&ctx->sqo_sq_wait, &wait);
-	return ret;
+	return 0;
 }
 
 static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz,

From e8f98f24549d62cc54bf608c815904a56d4437bc Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 9 Mar 2021 16:32:13 -0700
Subject: [PATCH 0573/1820] io_uring: always wait for sqd exited when stopping
 SQPOLL thread

We have a tiny race where io_put_sq_data() calls io_sq_thead_stop()
and finds the thread gone, but the thread has indeed not fully
exited or called complete() yet. Close it up by always having
io_sq_thread_stop() wait on completion of the exit event.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 6325f32ef6a3..62f998bf2ce8 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7079,12 +7079,9 @@ static void io_sq_thread_stop(struct io_sq_data *sqd)
 	if (test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state))
 		return;
 	down_write(&sqd->rw_lock);
-	if (!sqd->thread) {
-		up_write(&sqd->rw_lock);
-		return;
-	}
 	set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
-	wake_up_process(sqd->thread);
+	if (sqd->thread)
+		wake_up_process(sqd->thread);
 	up_write(&sqd->rw_lock);
 	wait_for_completion(&sqd->exited);
 }
@@ -7849,9 +7846,9 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 
 			ret = -EINVAL;
 			if (cpu >= nr_cpu_ids)
-				goto err;
+				goto err_sqpoll;
 			if (!cpu_online(cpu))
-				goto err;
+				goto err_sqpoll;
 
 			sqd->sq_cpu = cpu;
 		} else {
@@ -7862,7 +7859,7 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 		tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE);
 		if (IS_ERR(tsk)) {
 			ret = PTR_ERR(tsk);
-			goto err;
+			goto err_sqpoll;
 		}
 
 		sqd->thread = tsk;
@@ -7881,6 +7878,9 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 err:
 	io_sq_thread_finish(ctx);
 	return ret;
+err_sqpoll:
+	complete(&ctx->sq_data->exited);
+	goto err;
 }
 
 static inline void __io_unaccount_mem(struct user_struct *user,

From e22bc9b481a90d7898984ea17621f04a653e2cd1 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 9 Mar 2021 19:49:02 -0700
Subject: [PATCH 0574/1820] kernel: make IO threads unfreezable by default

The io-wq threads were already marked as no-freeze, but the manager was
not. On resume, we perpetually have signal_pending() being true, and
hence the manager will loop and spin 100% of the time.

Just mark the tasks created by create_io_thread() as PF_NOFREEZE by
default, and remove any knowledge of it in io-wq and io_uring.

Reported-by: Kevin Locke <kevin@kevinlocke.name>
Tested-by: Kevin Locke <kevin@kevinlocke.name>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c    | 3 +--
 fs/io_uring.c | 1 -
 kernel/fork.c | 1 +
 3 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 3d7060ba547a..0ae9ecadf295 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -591,7 +591,7 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
 	tsk->pf_io_worker = worker;
 	worker->task = tsk;
 	set_cpus_allowed_ptr(tsk, cpumask_of_node(wqe->node));
-	tsk->flags |= PF_NOFREEZE | PF_NO_SETAFFINITY;
+	tsk->flags |= PF_NO_SETAFFINITY;
 
 	raw_spin_lock_irq(&wqe->lock);
 	hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
@@ -709,7 +709,6 @@ static int io_wq_manager(void *data)
 		set_current_state(TASK_INTERRUPTIBLE);
 		io_wq_check_workers(wq);
 		schedule_timeout(HZ);
-		try_to_freeze();
 		if (fatal_signal_pending(current))
 			set_bit(IO_WQ_BIT_EXIT, &wq->state);
 	} while (!test_bit(IO_WQ_BIT_EXIT, &wq->state));
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 62f998bf2ce8..14165e18020c 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6733,7 +6733,6 @@ static int io_sq_thread(void *data)
 
 			up_read(&sqd->rw_lock);
 			schedule();
-			try_to_freeze();
 			down_read(&sqd->rw_lock);
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				io_ring_clear_wakeup_flag(ctx);
diff --git a/kernel/fork.c b/kernel/fork.c
index d3171e8e88e5..72e444cd0ffe 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2436,6 +2436,7 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 	if (!IS_ERR(tsk)) {
 		sigfillset(&tsk->blocked);
 		sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
+		tsk->flags |= PF_NOFREEZE;
 	}
 	return tsk;
 }

From 78d7f6ba82edb7f8763390982be29051c4216772 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 10 Mar 2021 13:13:53 +0000
Subject: [PATCH 0575/1820] io_uring: fix invalid ctx->sq_thread_idle

We have to set ctx->sq_thread_idle before adding a ring to an SQ task,
otherwise sqd races for seeing zero and accounting it as such.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 14165e18020c..7072c0eb22c1 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7829,14 +7829,14 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 
 		ctx->sq_creds = get_current_cred();
 		ctx->sq_data = sqd;
-		io_sq_thread_park(sqd);
-		list_add(&ctx->sqd_list, &sqd->ctx_new_list);
-		io_sq_thread_unpark(sqd);
-
 		ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
 		if (!ctx->sq_thread_idle)
 			ctx->sq_thread_idle = HZ;
 
+		io_sq_thread_park(sqd);
+		list_add(&ctx->sqd_list, &sqd->ctx_new_list);
+		io_sq_thread_unpark(sqd);
+
 		if (sqd->thread)
 			return 0;
 

From 7d41e8543d809c3c900d1212d6ea887eb284b69a Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 10 Mar 2021 13:13:54 +0000
Subject: [PATCH 0576/1820] io_uring: remove indirect ctx into sqo injection

We use ->ctx_new_list to notify sqo about new ctx pending, then sqo
should stop and splice it to its sqd->ctx_list, paired with
->sq_thread_comp.

The last one is broken because nobody reinitialises it, and trying to
fix it would only add more complexity and bugs. And the first isn't
really needed as is done under park(), that protects from races well.
Add ctx into sqd->ctx_list directly (under park()), it's much simpler
and allows to kill both, ctx_new_list and sq_thread_comp.

note: apparently there is no real problem at the moment, because
sq_thread_comp is used only by io_sq_thread_finish() followed by
parking, where list_del(&ctx->sqd_list) removes it well regardless
whether it's in the new or the active list.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 28 +++-------------------------
 1 file changed, 3 insertions(+), 25 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 7072c0eb22c1..5c045a9f7ffe 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -262,7 +262,6 @@ struct io_sq_data {
 
 	/* ctx's that are using this sqd */
 	struct list_head	ctx_list;
-	struct list_head	ctx_new_list;
 
 	struct task_struct	*thread;
 	struct wait_queue_head	wait;
@@ -398,7 +397,6 @@ struct io_ring_ctx {
 	struct user_struct	*user;
 
 	struct completion	ref_comp;
-	struct completion	sq_thread_comp;
 
 #if defined(CONFIG_UNIX)
 	struct socket		*ring_sock;
@@ -1137,7 +1135,6 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	init_waitqueue_head(&ctx->cq_wait);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
 	init_completion(&ctx->ref_comp);
-	init_completion(&ctx->sq_thread_comp);
 	idr_init(&ctx->io_buffer_idr);
 	xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
 	mutex_init(&ctx->uring_lock);
@@ -6640,19 +6637,6 @@ static void io_sqd_update_thread_idle(struct io_sq_data *sqd)
 	sqd->sq_thread_idle = sq_thread_idle;
 }
 
-static void io_sqd_init_new(struct io_sq_data *sqd)
-{
-	struct io_ring_ctx *ctx;
-
-	while (!list_empty(&sqd->ctx_new_list)) {
-		ctx = list_first_entry(&sqd->ctx_new_list, struct io_ring_ctx, sqd_list);
-		list_move_tail(&ctx->sqd_list, &sqd->ctx_list);
-		complete(&ctx->sq_thread_comp);
-	}
-
-	io_sqd_update_thread_idle(sqd);
-}
-
 static int io_sq_thread(void *data)
 {
 	struct io_sq_data *sqd = data;
@@ -6683,11 +6667,8 @@ static int io_sq_thread(void *data)
 			up_read(&sqd->rw_lock);
 			cond_resched();
 			down_read(&sqd->rw_lock);
-			continue;
-		}
-		if (unlikely(!list_empty(&sqd->ctx_new_list))) {
-			io_sqd_init_new(sqd);
 			timeout = jiffies + sqd->sq_thread_idle;
+			continue;
 		}
 		if (fatal_signal_pending(current))
 			break;
@@ -7099,9 +7080,6 @@ static void io_sq_thread_finish(struct io_ring_ctx *ctx)
 
 	if (sqd) {
 		complete(&sqd->startup);
-		if (sqd->thread)
-			wait_for_completion(&ctx->sq_thread_comp);
-
 		io_sq_thread_park(sqd);
 		list_del(&ctx->sqd_list);
 		io_sqd_update_thread_idle(sqd);
@@ -7153,7 +7131,6 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p)
 
 	refcount_set(&sqd->refs, 1);
 	INIT_LIST_HEAD(&sqd->ctx_list);
-	INIT_LIST_HEAD(&sqd->ctx_new_list);
 	init_rwsem(&sqd->rw_lock);
 	init_waitqueue_head(&sqd->wait);
 	init_completion(&sqd->startup);
@@ -7834,7 +7811,8 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 			ctx->sq_thread_idle = HZ;
 
 		io_sq_thread_park(sqd);
-		list_add(&ctx->sqd_list, &sqd->ctx_new_list);
+		list_add(&ctx->sqd_list, &sqd->ctx_list);
+		io_sqd_update_thread_idle(sqd);
 		io_sq_thread_unpark(sqd);
 
 		if (sqd->thread)

From faa44c69daf9ccbd5b8a1aee13e0e0d037c0be17 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@wdc.com>
Date: Wed, 10 Mar 2021 18:09:19 +0900
Subject: [PATCH 0577/1820] block: Fix REQ_OP_ZONE_RESET_ALL handling

Similarly to a single zone reset operation (REQ_OP_ZONE_RESET), execute
REQ_OP_ZONE_RESET_ALL operations with REQ_SYNC set.

Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 833978c02e60..8b9f3fc5a690 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -240,7 +240,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 		 */
 		if (op == REQ_OP_ZONE_RESET &&
 		    blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
-			bio->bi_opf = REQ_OP_ZONE_RESET_ALL;
+			bio->bi_opf = REQ_OP_ZONE_RESET_ALL | REQ_SYNC;
 			break;
 		}
 

From df66617bfe87487190a60783d26175b65d2502ce Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Tue, 9 Mar 2021 19:30:17 -0800
Subject: [PATCH 0578/1820] block: rsxx: fix error return code of
 rsxx_pci_probe()

When create_singlethread_workqueue returns NULL to card->event_wq, no
error return code of rsxx_pci_probe() is assigned.

To fix this bug, st is assigned with -ENOMEM in this case.

Fixes: 8722ff8cdbfa ("block: IBM RamSan 70/80 device driver")
Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Link: https://lore.kernel.org/r/20210310033017.4023-1-baijiaju1990@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/rsxx/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 5ac1881396af..227e1be4c6f9 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -871,6 +871,7 @@ static int rsxx_pci_probe(struct pci_dev *dev,
 	card->event_wq = create_singlethread_workqueue(DRIVER_NAME"_event");
 	if (!card->event_wq) {
 		dev_err(CARD_TO_DEV(card), "Failed card event setup.\n");
+		st = -ENOMEM;
 		goto failed_event_handler;
 	}
 

From 221c3a09ddf70a0a51715e6c2878d8305e95c558 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 11 Apr 2018 19:05:03 +0300
Subject: [PATCH 0579/1820] ARM: dts: at91-sama5d27_som1: fix phy address to 7

Fix the phy address to 7 for Ethernet PHY on SAMA5D27 SOM1. No
connection established if phy address 0 is used.

The board uses the 24 pins version of the KSZ8081RNA part, KSZ8081RNA
pin 16 REFCLK as PHYAD bit [2] has weak internal pull-down.  But at
reset, connected to PD09 of the MPU it's connected with an internal
pull-up forming PHYAD[2:0] = 7.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Fixes: 2f61929eb10a ("ARM: dts: at91: at91-sama5d27_som1: fix PHY ID")
Cc: Ludovic Desroches <ludovic.desroches@microchip.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Cc: <stable@vger.kernel.org> # 4.14+
---
 arch/arm/boot/dts/at91-sama5d27_som1.dtsi | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
index 1b1163858b1d..e3251f3e3eaa 100644
--- a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
+++ b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
@@ -84,8 +84,8 @@
 				pinctrl-0 = <&pinctrl_macb0_default>;
 				phy-mode = "rmii";
 
-				ethernet-phy@0 {
-					reg = <0x0>;
+				ethernet-phy@7 {
+					reg = <0x7>;
 					interrupt-parent = <&pioA>;
 					interrupts = <PIN_PD31 IRQ_TYPE_LEVEL_LOW>;
 					pinctrl-names = "default";

From 664979bba8169d775959452def968d1a7c03901f Mon Sep 17 00:00:00 2001
From: Federico Pellegrin <fede@evolware.org>
Date: Sun, 7 Feb 2021 06:00:22 +0100
Subject: [PATCH 0580/1820] ARM: dts: at91: sam9x60: fix mux-mask for PA7 so it
 can be set to A, B and C

According to the datasheet PA7 can be set to either function A, B or
C (see table 6-2 of DS60001579D). The previous value would permit just
configuring with function C.

Signed-off-by: Federico Pellegrin <fede@evolware.org>
Fixes: 1e5f532c2737 ("ARM: dts: at91: sam9x60: add device tree for soc and board")
Cc: <stable@vger.kernel.org> # 5.6+
Cc: Sandeep Sheriker Mallikarjun <sandeepsheriker.mallikarjun@microchip.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@microchip.com>
---
 arch/arm/boot/dts/at91-sam9x60ek.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/at91-sam9x60ek.dts b/arch/arm/boot/dts/at91-sam9x60ek.dts
index 73b6b1f89de9..4c40ae571154 100644
--- a/arch/arm/boot/dts/at91-sam9x60ek.dts
+++ b/arch/arm/boot/dts/at91-sam9x60ek.dts
@@ -336,7 +336,7 @@
 &pinctrl {
 	atmel,mux-mask = <
 			 /*	A	B	C	*/
-			 0xFFFFFE7F 0xC0E0397F 0xEF00019D	/* pioA */
+			 0xFFFFFEFF 0xC0E039FF 0xEF00019D	/* pioA */
 			 0x03FFFFFF 0x02FC7E68 0x00780000	/* pioB */
 			 0xffffffff 0xF83FFFFF 0xB800F3FC	/* pioC */
 			 0x003FFFFF 0x003F8000 0x00000000	/* pioD */

From 2c69c8a1736eace8de491d480e6e577a27c2087c Mon Sep 17 00:00:00 2001
From: Nicolas Ferre <nicolas.ferre@microchip.com>
Date: Wed, 10 Mar 2021 16:20:06 +0100
Subject: [PATCH 0581/1820] ARM: dts: at91: sam9x60: fix mux-mask to match
 product's datasheet

Fix the whole mux-mask table according to datasheet for the sam9x60
product.  Too much functions for pins were disabled leading to
misunderstandings when enabling more peripherals or taking this table
as an example for another board.
Take advantage of this fix to move the mux-mask in the SoC file where it
belongs and use lower case letters for hex numbers like everywhere in
the file.

Signed-off-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Fixes: 1e5f532c2737 ("ARM: dts: at91: sam9x60: add device tree for soc and board")
Cc: <stable@vger.kernel.org> # 5.6+
Cc: Sandeep Sheriker Mallikarjun <sandeepsheriker.mallikarjun@microchip.com>
Reviewed-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Link: https://lore.kernel.org/r/20210310152006.15018-1-nicolas.ferre@microchip.com
---
 arch/arm/boot/dts/at91-sam9x60ek.dts | 8 --------
 arch/arm/boot/dts/sam9x60.dtsi       | 9 +++++++++
 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/arch/arm/boot/dts/at91-sam9x60ek.dts b/arch/arm/boot/dts/at91-sam9x60ek.dts
index 4c40ae571154..775ceb3acb6c 100644
--- a/arch/arm/boot/dts/at91-sam9x60ek.dts
+++ b/arch/arm/boot/dts/at91-sam9x60ek.dts
@@ -334,14 +334,6 @@
 };
 
 &pinctrl {
-	atmel,mux-mask = <
-			 /*	A	B	C	*/
-			 0xFFFFFEFF 0xC0E039FF 0xEF00019D	/* pioA */
-			 0x03FFFFFF 0x02FC7E68 0x00780000	/* pioB */
-			 0xffffffff 0xF83FFFFF 0xB800F3FC	/* pioC */
-			 0x003FFFFF 0x003F8000 0x00000000	/* pioD */
-			 >;
-
 	adc {
 		pinctrl_adc_default: adc_default {
 			atmel,pins = <AT91_PIOB 15 AT91_PERIPH_A AT91_PINCTRL_NONE>;
diff --git a/arch/arm/boot/dts/sam9x60.dtsi b/arch/arm/boot/dts/sam9x60.dtsi
index 84066c1298df..ec45ced3cde6 100644
--- a/arch/arm/boot/dts/sam9x60.dtsi
+++ b/arch/arm/boot/dts/sam9x60.dtsi
@@ -606,6 +606,15 @@
 				compatible = "microchip,sam9x60-pinctrl", "atmel,at91sam9x5-pinctrl", "atmel,at91rm9200-pinctrl", "simple-bus";
 				ranges = <0xfffff400 0xfffff400 0x800>;
 
+				/* mux-mask corresponding to sam9x60 SoC in TFBGA228L package */
+				atmel,mux-mask = <
+						 /*	A	B	C	*/
+						 0xffffffff 0xffe03fff 0xef00019d	/* pioA */
+						 0x03ffffff 0x02fc7e7f 0x00780000	/* pioB */
+						 0xffffffff 0xffffffff 0xf83fffff	/* pioC */
+						 0x003fffff 0x003f8000 0x00000000	/* pioD */
+						 >;
+
 				pioA: gpio@fffff400 {
 					compatible = "microchip,sam9x60-gpio", "atmel,at91sam9x5-gpio", "atmel,at91rm9200-gpio";
 					reg = <0xfffff400 0x200>;

From c8e2fe13d1d1f3a02842b7b909d4e4846a4b6a2c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 9 Mar 2021 09:10:19 -0800
Subject: [PATCH 0582/1820] x86/perf: Use RET0 as default for guest_get_msrs to
 handle "no PMU" case

Initialize x86_pmu.guest_get_msrs to return 0/NULL to handle the "nop"
case.  Patching in perf_guest_get_msrs_nop() during setup does not work
if there is no PMU, as setup bails before updating the static calls,
leaving x86_pmu.guest_get_msrs NULL and thus a complete nop.  Ultimately,
this causes VMX abort on VM-Exit due to KVM putting random garbage from
the stack into the MSR load list.

Add a comment in KVM to note that nr_msrs is valid if and only if the
return value is non-NULL.

Fixes: abd562df94d1 ("x86/perf: Use static_call for x86_pmu.guest_get_msrs")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reported-by: syzbot+cce9ef2dd25246f815ee@syzkaller.appspotmail.com
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210309171019.1125243-1-seanjc@google.com
---
 arch/x86/events/core.c | 15 ++++++---------
 arch/x86/kvm/vmx/vmx.c |  2 +-
 2 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 6ddeed3cd2ac..18df17129695 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -81,7 +81,11 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_swap_task_ctx, *x86_pmu.swap_task_ctx);
 DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs,   *x86_pmu.drain_pebs);
 DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases);
 
-DEFINE_STATIC_CALL_NULL(x86_pmu_guest_get_msrs,  *x86_pmu.guest_get_msrs);
+/*
+ * This one is magic, it will get called even when PMU init fails (because
+ * there is no PMU), in which case it should simply return NULL.
+ */
+DEFINE_STATIC_CALL_RET0(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs);
 
 u64 __read_mostly hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
@@ -1944,13 +1948,6 @@ static void _x86_pmu_read(struct perf_event *event)
 	x86_perf_event_update(event);
 }
 
-static inline struct perf_guest_switch_msr *
-perf_guest_get_msrs_nop(int *nr)
-{
-	*nr = 0;
-	return NULL;
-}
-
 static int __init init_hw_perf_events(void)
 {
 	struct x86_pmu_quirk *quirk;
@@ -2025,7 +2022,7 @@ static int __init init_hw_perf_events(void)
 		x86_pmu.read = _x86_pmu_read;
 
 	if (!x86_pmu.guest_get_msrs)
-		x86_pmu.guest_get_msrs = perf_guest_get_msrs_nop;
+		x86_pmu.guest_get_msrs = (void *)&__static_call_return0;
 
 	x86_pmu_static_call_update();
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 50810d471462..32cf8287d4a7 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6580,8 +6580,8 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 	int i, nr_msrs;
 	struct perf_guest_switch_msr *msrs;
 
+	/* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */
 	msrs = perf_guest_get_msrs(&nr_msrs);
-
 	if (!msrs)
 		return;
 

From 1201d68f4781141411e734315f22457e6ea2cfcb Mon Sep 17 00:00:00 2001
From: Shuo Liu <shuo.a.liu@intel.com>
Date: Wed, 10 Mar 2021 23:37:08 +0800
Subject: [PATCH 0583/1820] virt: acrn: Correct type casting of argument of
 copy_from_user()

hsm.c:336:50: warning: incorrect type in argument 2 (different address spaces)
hsm.c:336:50:    expected void const [noderef] __user *from
hsm.c:336:50:    got void *

This patch fixes above sparse warning.

Fixes: 3d679d5aec64 ("virt: acrn: Introduce interfaces to query C-states and P-states allowed by hypervisor")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Shuo Liu <shuo.a.liu@intel.com>
Link: https://lore.kernel.org/r/20210310153708.17451-1-shuo.a.liu@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/acrn/hsm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c
index 6996ea6219e5..130e12b8652a 100644
--- a/drivers/virt/acrn/hsm.c
+++ b/drivers/virt/acrn/hsm.c
@@ -333,7 +333,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd,
 		acrn_ioreq_request_clear(vm);
 		break;
 	case ACRN_IOCTL_PM_GET_CPU_STATE:
-		if (copy_from_user(&cstate_cmd, (void *)ioctl_param,
+		if (copy_from_user(&cstate_cmd, (void __user *)ioctl_param,
 				   sizeof(cstate_cmd)))
 			return -EFAULT;
 

From 20c40794eb85ea29852d7bc37c55713802a543d6 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 12 Feb 2021 22:26:58 +0300
Subject: [PATCH 0584/1820] misc: fastrpc: restrict user apps from sending
 kernel RPC messages

Verify that user applications are not using the kernel RPC message
handle to restrict them from directly attaching to guest OS on the
remote subsystem. This is a port of CVE-2019-2308 fix.

Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method")
Cc: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Cc: Jonathan Marek <jonathan@marek.ca>
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20210212192658.3476137-1-dmitry.baryshkov@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/fastrpc.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index f12e909034ac..beda610e6b30 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -950,6 +950,11 @@ static int fastrpc_internal_invoke(struct fastrpc_user *fl,  u32 kernel,
 	if (!fl->cctx->rpdev)
 		return -EPIPE;
 
+	if (handle == FASTRPC_INIT_HANDLE && !kernel) {
+		dev_warn_ratelimited(fl->sctx->dev, "user app trying to send a kernel RPC message (%d)\n",  handle);
+		return -EPERM;
+	}
+
 	ctx = fastrpc_context_alloc(fl, kernel, sc, args);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);

From 65527a51c66f4edfa28602643d7dd4fa366eb826 Mon Sep 17 00:00:00 2001
From: Shile Zhang <shile.zhang@linux.alibaba.com>
Date: Thu, 18 Feb 2021 20:31:16 +0800
Subject: [PATCH 0585/1820] misc/pvpanic: Export module FDT device table

Export the module FDT device table to ensure the FDT compatible strings
are listed in the module alias. This help the pvpanic driver can be
loaded on boot automatically not only the ACPI device, but also the FDT
device.

Fixes: 46f934c9a12fc ("misc/pvpanic: add support to get pvpanic device info FDT")
Signed-off-by: Shile Zhang <shile.zhang@linux.alibaba.com>
Link: https://lore.kernel.org/r/20210218123116.207751-1-shile.zhang@linux.alibaba.com
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/pvpanic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/misc/pvpanic.c b/drivers/misc/pvpanic.c
index 9f350e05ef68..f1655f5ca016 100644
--- a/drivers/misc/pvpanic.c
+++ b/drivers/misc/pvpanic.c
@@ -140,6 +140,7 @@ static const struct of_device_id pvpanic_mmio_match[] = {
 	{ .compatible = "qemu,pvpanic-mmio", },
 	{}
 };
+MODULE_DEVICE_TABLE(of, pvpanic_mmio_match);
 
 static const struct acpi_device_id pvpanic_device_ids[] = {
 	{ "QEMU0001", 0 },

From 9b1ea29bc0d7b94d420f96a0f4121403efc3dd85 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 10 Mar 2021 10:18:04 -0800
Subject: [PATCH 0586/1820] Revert "mm, slub: consider rest of partial list if
 acquire_slab() fails"

This reverts commit 8ff60eb052eeba95cfb3efe16b08c9199f8121cf.

The kernel test robot reports a huge performance regression due to the
commit, and the reason seems fairly straightforward: when there is
contention on the page list (which is what causes acquire_slab() to
fail), we do _not_ want to just loop and try again, because that will
transfer the contention to the 'n->list_lock' spinlock we hold, and
just make things even worse.

This is admittedly likely a problem only on big machines - the kernel
test robot report comes from a 96-thread dual socket Intel Xeon Gold
6252 setup, but the regression there really is quite noticeable:

   -47.9% regression of stress-ng.rawpkt.ops_per_sec

and the commit that was marked as being fixed (7ced37197196: "slub:
Acquire_slab() avoid loop") actually did the loop exit early very
intentionally (the hint being that "avoid loop" part of that commit
message), exactly to avoid this issue.

The correct thing to do may be to pick some kind of reasonable middle
ground: instead of breaking out of the loop on the very first sign of
contention, or trying over and over and over again, the right thing may
be to re-try _once_, and then give up on the second failure (or pick
your favorite value for "once"..).

Reported-by: kernel test robot <oliver.sang@intel.com>
Link: https://lore.kernel.org/lkml/20210301080404.GF12822@xsang-OptiPlex-9020/
Cc: Jann Horn <jannh@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/slub.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/slub.c b/mm/slub.c
index e26c274b4657..3021ce9bf1b3 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1993,7 +1993,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 
 		t = acquire_slab(s, n, page, object == NULL, &objects);
 		if (!t)
-			continue; /* cmpxchg raced */
+			break;
 
 		available += objects;
 		if (!object) {

From 47ccc8fc2c9c94558b27b6f9e2582df32d29e6e8 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Sun, 7 Mar 2021 20:53:26 -0700
Subject: [PATCH 0587/1820] usbip: fix stub_dev to check for stream socket

Fix usbip_sockfd_store() to validate the passed in file descriptor is
a stream socket. If the file descriptor passed was a SOCK_DGRAM socket,
sock_recvmsg() can't detect end of stream.

Cc: stable@vger.kernel.org
Suggested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/e942d2bd03afb8e8552bd2a5d84e18d17670d521.1615171203.git.skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/stub_dev.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index 2305d425e6c9..90c105469a07 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -69,8 +69,16 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 		}
 
 		socket = sockfd_lookup(sockfd, &err);
-		if (!socket)
+		if (!socket) {
+			dev_err(dev, "failed to lookup sock");
 			goto err;
+		}
+
+		if (socket->type != SOCK_STREAM) {
+			dev_err(dev, "Expecting SOCK_STREAM - found %d",
+				socket->type);
+			goto sock_err;
+		}
 
 		sdev->ud.tcp_socket = socket;
 		sdev->ud.sockfd = sockfd;
@@ -100,6 +108,8 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 
 	return count;
 
+sock_err:
+	sockfd_put(socket);
 err:
 	spin_unlock_irq(&sdev->ud.lock);
 	return -EINVAL;

From f55a0571690c4aae03180e001522538c0927432f Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Sun, 7 Mar 2021 20:53:27 -0700
Subject: [PATCH 0588/1820] usbip: fix vhci_hcd to check for stream socket

Fix attach_store() to validate the passed in file descriptor is a
stream socket. If the file descriptor passed was a SOCK_DGRAM socket,
sock_recvmsg() can't detect end of stream.

Cc: stable@vger.kernel.org
Suggested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/52712aa308915bda02cece1589e04ee8b401d1f3.1615171203.git.skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/vhci_sysfs.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c
index 96e5371dc335..1e1ae9bd06ab 100644
--- a/drivers/usb/usbip/vhci_sysfs.c
+++ b/drivers/usb/usbip/vhci_sysfs.c
@@ -349,8 +349,16 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr,
 
 	/* Extract socket from fd. */
 	socket = sockfd_lookup(sockfd, &err);
-	if (!socket)
+	if (!socket) {
+		dev_err(dev, "failed to lookup sock");
 		return -EINVAL;
+	}
+	if (socket->type != SOCK_STREAM) {
+		dev_err(dev, "Expecting SOCK_STREAM - found %d",
+			socket->type);
+		sockfd_put(socket);
+		return -EINVAL;
+	}
 
 	/* now need lock until setting vdev status as used */
 

From 6801854be94fe8819b3894979875ea31482f5658 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Sun, 7 Mar 2021 20:53:28 -0700
Subject: [PATCH 0589/1820] usbip: fix vudc to check for stream socket

Fix usbip_sockfd_store() to validate the passed in file descriptor is
a stream socket. If the file descriptor passed was a SOCK_DGRAM socket,
sock_recvmsg() can't detect end of stream.

Cc: stable@vger.kernel.org
Suggested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/387a670316002324113ac7ea1e8b53f4085d0c95.1615171203.git.skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/vudc_sysfs.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/usb/usbip/vudc_sysfs.c b/drivers/usb/usbip/vudc_sysfs.c
index 100f680c572a..83a0c59a3de8 100644
--- a/drivers/usb/usbip/vudc_sysfs.c
+++ b/drivers/usb/usbip/vudc_sysfs.c
@@ -138,6 +138,13 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 			goto unlock_ud;
 		}
 
+		if (socket->type != SOCK_STREAM) {
+			dev_err(dev, "Expecting SOCK_STREAM - found %d",
+				socket->type);
+			ret = -EINVAL;
+			goto sock_err;
+		}
+
 		udc->ud.tcp_socket = socket;
 
 		spin_unlock_irq(&udc->ud.lock);
@@ -177,6 +184,8 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 
 	return count;
 
+sock_err:
+	sockfd_put(socket);
 unlock_ud:
 	spin_unlock_irq(&udc->ud.lock);
 unlock:

From 9380afd6df70e24eacbdbde33afc6a3950965d22 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Sun, 7 Mar 2021 20:53:29 -0700
Subject: [PATCH 0590/1820] usbip: fix stub_dev usbip_sockfd_store() races
 leading to gpf

usbip_sockfd_store() is invoked when user requests attach (import)
detach (unimport) usb device from usbip host. vhci_hcd sends import
request and usbip_sockfd_store() exports the device if it is free
for export.

Export and unexport are governed by local state and shared state
- Shared state (usbip device status, sockfd) - sockfd and Device
  status are used to determine if stub should be brought up or shut
  down.
- Local state (tcp_socket, rx and tx thread task_struct ptrs)
  A valid tcp_socket controls rx and tx thread operations while the
  device is in exported state.
- While the device is exported, device status is marked used and socket,
  sockfd, and thread pointers are valid.

Export sequence (stub-up) includes validating the socket and creating
receive (rx) and transmit (tx) threads to talk to the client to provide
access to the exported device. rx and tx threads depends on local and
shared state to be correct and in sync.

Unexport (stub-down) sequence shuts the socket down and stops the rx and
tx threads. Stub-down sequence relies on local and shared states to be
in sync.

There are races in updating the local and shared status in the current
stub-up sequence resulting in crashes. These stem from starting rx and
tx threads before local and global state is updated correctly to be in
sync.

1. Doesn't handle kthread_create() error and saves invalid ptr in local
   state that drives rx and tx threads.
2. Updates tcp_socket and sockfd,  starts stub_rx and stub_tx threads
   before updating usbip_device status to SDEV_ST_USED. This opens up a
   race condition between the threads and usbip_sockfd_store() stub up
   and down handling.

Fix the above problems:
- Stop using kthread_get_run() macro to create/start threads.
- Create threads and get task struct reference.
- Add kthread_create() failure handling and bail out.
- Hold usbip_device lock to update local and shared states after
  creating rx and tx threads.
- Update usbip_device status to SDEV_ST_USED.
- Update usbip_device tcp_socket, sockfd, tcp_rx, and tcp_tx
- Start threads after usbip_device (tcp_socket, sockfd, tcp_rx, tcp_tx,
  and status) is complete.

Credit goes to syzbot and Tetsuo Handa for finding and root-causing the
kthread_get_run() improper error handling problem and others. This is a
hard problem to find and debug since the races aren't seen in a normal
case. Fuzzing forces the race window to be small enough for the
kthread_get_run() error path bug and starting threads before updating the
local and shared state bug in the stub-up sequence.

Tested with syzbot reproducer:
- https://syzkaller.appspot.com/text?tag=ReproC&x=14801034d00000

Fixes: 9720b4bc76a83807 ("staging/usbip: convert to kthread")
Cc: stable@vger.kernel.org
Reported-by: syzbot <syzbot+a93fba6d384346a761e3@syzkaller.appspotmail.com>
Reported-by: syzbot <syzbot+bf1a360e305ee719e364@syzkaller.appspotmail.com>
Reported-by: syzbot <syzbot+95ce4b142579611ef0a9@syzkaller.appspotmail.com>
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/268a0668144d5ff36ec7d87fdfa90faf583b7ccc.1615171203.git.skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/stub_dev.c | 36 +++++++++++++++++++++++++++---------
 1 file changed, 27 insertions(+), 9 deletions(-)

diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index 90c105469a07..8f1de1fbbeed 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -46,6 +46,8 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 	int sockfd = 0;
 	struct socket *socket;
 	int rv;
+	struct task_struct *tcp_rx = NULL;
+	struct task_struct *tcp_tx = NULL;
 
 	if (!sdev) {
 		dev_err(dev, "sdev is null\n");
@@ -80,20 +82,36 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 			goto sock_err;
 		}
 
+		/* unlock and create threads and get tasks */
+		spin_unlock_irq(&sdev->ud.lock);
+		tcp_rx = kthread_create(stub_rx_loop, &sdev->ud, "stub_rx");
+		if (IS_ERR(tcp_rx)) {
+			sockfd_put(socket);
+			return -EINVAL;
+		}
+		tcp_tx = kthread_create(stub_tx_loop, &sdev->ud, "stub_tx");
+		if (IS_ERR(tcp_tx)) {
+			kthread_stop(tcp_rx);
+			sockfd_put(socket);
+			return -EINVAL;
+		}
+
+		/* get task structs now */
+		get_task_struct(tcp_rx);
+		get_task_struct(tcp_tx);
+
+		/* lock and update sdev->ud state */
+		spin_lock_irq(&sdev->ud.lock);
 		sdev->ud.tcp_socket = socket;
 		sdev->ud.sockfd = sockfd;
-
-		spin_unlock_irq(&sdev->ud.lock);
-
-		sdev->ud.tcp_rx = kthread_get_run(stub_rx_loop, &sdev->ud,
-						  "stub_rx");
-		sdev->ud.tcp_tx = kthread_get_run(stub_tx_loop, &sdev->ud,
-						  "stub_tx");
-
-		spin_lock_irq(&sdev->ud.lock);
+		sdev->ud.tcp_rx = tcp_rx;
+		sdev->ud.tcp_tx = tcp_tx;
 		sdev->ud.status = SDEV_ST_USED;
 		spin_unlock_irq(&sdev->ud.lock);
 
+		wake_up_process(sdev->ud.tcp_rx);
+		wake_up_process(sdev->ud.tcp_tx);
+
 	} else {
 		dev_info(dev, "stub down\n");
 

From 718ad9693e3656120064b715fe931f43a6201e67 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Sun, 7 Mar 2021 20:53:30 -0700
Subject: [PATCH 0591/1820] usbip: fix vhci_hcd attach_store() races leading to
 gpf

attach_store() is invoked when user requests import (attach) a device
from usbip host.

Attach and detach are governed by local state and shared state
- Shared state (usbip device status) - Device status is used to manage
  the attach and detach operations on import-able devices.
- Local state (tcp_socket, rx and tx thread task_struct ptrs)
  A valid tcp_socket controls rx and tx thread operations while the
  device is in exported state.
- Device has to be in the right state to be attached and detached.

Attach sequence includes validating the socket and creating receive (rx)
and transmit (tx) threads to talk to the host to get access to the
imported device. rx and tx threads depends on local and shared state to
be correct and in sync.

Detach sequence shuts the socket down and stops the rx and tx threads.
Detach sequence relies on local and shared states to be in sync.

There are races in updating the local and shared status in the current
attach sequence resulting in crashes. These stem from starting rx and
tx threads before local and global state is updated correctly to be in
sync.

1. Doesn't handle kthread_create() error and saves invalid ptr in local
   state that drives rx and tx threads.
2. Updates tcp_socket and sockfd,  starts stub_rx and stub_tx threads
   before updating usbip_device status to VDEV_ST_NOTASSIGNED. This opens
   up a race condition between the threads, port connect, and detach
   handling.

Fix the above problems:
- Stop using kthread_get_run() macro to create/start threads.
- Create threads and get task struct reference.
- Add kthread_create() failure handling and bail out.
- Hold vhci and usbip_device locks to update local and shared states after
  creating rx and tx threads.
- Update usbip_device status to VDEV_ST_NOTASSIGNED.
- Update usbip_device tcp_socket, sockfd, tcp_rx, and tcp_tx
- Start threads after usbip_device (tcp_socket, sockfd, tcp_rx, tcp_tx,
  and status) is complete.

Credit goes to syzbot and Tetsuo Handa for finding and root-causing the
kthread_get_run() improper error handling problem and others. This is
hard problem to find and debug since the races aren't seen in a normal
case. Fuzzing forces the race window to be small enough for the
kthread_get_run() error path bug and starting threads before updating the
local and shared state bug in the attach sequence.
- Update usbip_device tcp_rx and tcp_tx pointers holding vhci and
  usbip_device locks.

Tested with syzbot reproducer:
- https://syzkaller.appspot.com/text?tag=ReproC&x=14801034d00000

Fixes: 9720b4bc76a83807 ("staging/usbip: convert to kthread")
Cc: stable@vger.kernel.org
Reported-by: syzbot <syzbot+a93fba6d384346a761e3@syzkaller.appspotmail.com>
Reported-by: syzbot <syzbot+bf1a360e305ee719e364@syzkaller.appspotmail.com>
Reported-by: syzbot <syzbot+95ce4b142579611ef0a9@syzkaller.appspotmail.com>
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/bb434bd5d7a64fbec38b5ecfb838a6baef6eb12b.1615171203.git.skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/vhci_sysfs.c | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c
index 1e1ae9bd06ab..c4b4256e5dad 100644
--- a/drivers/usb/usbip/vhci_sysfs.c
+++ b/drivers/usb/usbip/vhci_sysfs.c
@@ -312,6 +312,8 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr,
 	struct vhci *vhci;
 	int err;
 	unsigned long flags;
+	struct task_struct *tcp_rx = NULL;
+	struct task_struct *tcp_tx = NULL;
 
 	/*
 	 * @rhport: port number of vhci_hcd
@@ -360,9 +362,24 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 	}
 
-	/* now need lock until setting vdev status as used */
+	/* create threads before locking */
+	tcp_rx = kthread_create(vhci_rx_loop, &vdev->ud, "vhci_rx");
+	if (IS_ERR(tcp_rx)) {
+		sockfd_put(socket);
+		return -EINVAL;
+	}
+	tcp_tx = kthread_create(vhci_tx_loop, &vdev->ud, "vhci_tx");
+	if (IS_ERR(tcp_tx)) {
+		kthread_stop(tcp_rx);
+		sockfd_put(socket);
+		return -EINVAL;
+	}
 
-	/* begin a lock */
+	/* get task structs now */
+	get_task_struct(tcp_rx);
+	get_task_struct(tcp_tx);
+
+	/* now begin lock until setting vdev status set */
 	spin_lock_irqsave(&vhci->lock, flags);
 	spin_lock(&vdev->ud.lock);
 
@@ -372,6 +389,8 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr,
 		spin_unlock_irqrestore(&vhci->lock, flags);
 
 		sockfd_put(socket);
+		kthread_stop_put(tcp_rx);
+		kthread_stop_put(tcp_tx);
 
 		dev_err(dev, "port %d already used\n", rhport);
 		/*
@@ -390,6 +409,8 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr,
 	vdev->speed         = speed;
 	vdev->ud.sockfd     = sockfd;
 	vdev->ud.tcp_socket = socket;
+	vdev->ud.tcp_rx     = tcp_rx;
+	vdev->ud.tcp_tx     = tcp_tx;
 	vdev->ud.status     = VDEV_ST_NOTASSIGNED;
 	usbip_kcov_handle_init(&vdev->ud);
 
@@ -397,8 +418,8 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr,
 	spin_unlock_irqrestore(&vhci->lock, flags);
 	/* end the lock */
 
-	vdev->ud.tcp_rx = kthread_get_run(vhci_rx_loop, &vdev->ud, "vhci_rx");
-	vdev->ud.tcp_tx = kthread_get_run(vhci_tx_loop, &vdev->ud, "vhci_tx");
+	wake_up_process(vdev->ud.tcp_rx);
+	wake_up_process(vdev->ud.tcp_tx);
 
 	rh_port_connect(vdev, speed);
 

From 46613c9dfa964c0c60b5385dbdf5aaa18be52a9c Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Sun, 7 Mar 2021 20:53:31 -0700
Subject: [PATCH 0592/1820] usbip: fix vudc usbip_sockfd_store races leading to
 gpf

usbip_sockfd_store() is invoked when user requests attach (import)
detach (unimport) usb gadget device from usbip host. vhci_hcd sends
import request and usbip_sockfd_store() exports the device if it is
free for export.

Export and unexport are governed by local state and shared state
- Shared state (usbip device status, sockfd) - sockfd and Device
  status are used to determine if stub should be brought up or shut
  down. Device status is shared between host and client.
- Local state (tcp_socket, rx and tx thread task_struct ptrs)
  A valid tcp_socket controls rx and tx thread operations while the
  device is in exported state.
- While the device is exported, device status is marked used and socket,
  sockfd, and thread pointers are valid.

Export sequence (stub-up) includes validating the socket and creating
receive (rx) and transmit (tx) threads to talk to the client to provide
access to the exported device. rx and tx threads depends on local and
shared state to be correct and in sync.

Unexport (stub-down) sequence shuts the socket down and stops the rx and
tx threads. Stub-down sequence relies on local and shared states to be
in sync.

There are races in updating the local and shared status in the current
stub-up sequence resulting in crashes. These stem from starting rx and
tx threads before local and global state is updated correctly to be in
sync.

1. Doesn't handle kthread_create() error and saves invalid ptr in local
   state that drives rx and tx threads.
2. Updates tcp_socket and sockfd,  starts stub_rx and stub_tx threads
   before updating usbip_device status to SDEV_ST_USED. This opens up a
   race condition between the threads and usbip_sockfd_store() stub up
   and down handling.

Fix the above problems:
- Stop using kthread_get_run() macro to create/start threads.
- Create threads and get task struct reference.
- Add kthread_create() failure handling and bail out.
- Hold usbip_device lock to update local and shared states after
  creating rx and tx threads.
- Update usbip_device status to SDEV_ST_USED.
- Update usbip_device tcp_socket, sockfd, tcp_rx, and tcp_tx
- Start threads after usbip_device (tcp_socket, sockfd, tcp_rx, tcp_tx,
  and status) is complete.

Credit goes to syzbot and Tetsuo Handa for finding and root-causing the
kthread_get_run() improper error handling problem and others. This is a
hard problem to find and debug since the races aren't seen in a normal
case. Fuzzing forces the race window to be small enough for the
kthread_get_run() error path bug and starting threads before updating the
local and shared state bug in the stub-up sequence.

Fixes: 9720b4bc76a83807 ("staging/usbip: convert to kthread")
Cc: stable@vger.kernel.org
Reported-by: syzbot <syzbot+a93fba6d384346a761e3@syzkaller.appspotmail.com>
Reported-by: syzbot <syzbot+bf1a360e305ee719e364@syzkaller.appspotmail.com>
Reported-by: syzbot <syzbot+95ce4b142579611ef0a9@syzkaller.appspotmail.com>
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/b1c08b983ffa185449c9f0f7d1021dc8c8454b60.1615171203.git.skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/vudc_sysfs.c | 42 +++++++++++++++++++++++++++-------
 1 file changed, 34 insertions(+), 8 deletions(-)

diff --git a/drivers/usb/usbip/vudc_sysfs.c b/drivers/usb/usbip/vudc_sysfs.c
index 83a0c59a3de8..a3ec39fc6177 100644
--- a/drivers/usb/usbip/vudc_sysfs.c
+++ b/drivers/usb/usbip/vudc_sysfs.c
@@ -90,8 +90,9 @@ unlock:
 }
 static BIN_ATTR_RO(dev_desc, sizeof(struct usb_device_descriptor));
 
-static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *attr,
-		     const char *in, size_t count)
+static ssize_t usbip_sockfd_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *in, size_t count)
 {
 	struct vudc *udc = (struct vudc *) dev_get_drvdata(dev);
 	int rv;
@@ -100,6 +101,8 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 	struct socket *socket;
 	unsigned long flags;
 	int ret;
+	struct task_struct *tcp_rx = NULL;
+	struct task_struct *tcp_tx = NULL;
 
 	rv = kstrtoint(in, 0, &sockfd);
 	if (rv != 0)
@@ -145,24 +148,47 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 			goto sock_err;
 		}
 
-		udc->ud.tcp_socket = socket;
-
+		/* unlock and create threads and get tasks */
 		spin_unlock_irq(&udc->ud.lock);
 		spin_unlock_irqrestore(&udc->lock, flags);
 
-		udc->ud.tcp_rx = kthread_get_run(&v_rx_loop,
-						    &udc->ud, "vudc_rx");
-		udc->ud.tcp_tx = kthread_get_run(&v_tx_loop,
-						    &udc->ud, "vudc_tx");
+		tcp_rx = kthread_create(&v_rx_loop, &udc->ud, "vudc_rx");
+		if (IS_ERR(tcp_rx)) {
+			sockfd_put(socket);
+			return -EINVAL;
+		}
+		tcp_tx = kthread_create(&v_tx_loop, &udc->ud, "vudc_tx");
+		if (IS_ERR(tcp_tx)) {
+			kthread_stop(tcp_rx);
+			sockfd_put(socket);
+			return -EINVAL;
+		}
 
+		/* get task structs now */
+		get_task_struct(tcp_rx);
+		get_task_struct(tcp_tx);
+
+		/* lock and update udc->ud state */
 		spin_lock_irqsave(&udc->lock, flags);
 		spin_lock_irq(&udc->ud.lock);
+
+		udc->ud.tcp_socket = socket;
+		udc->ud.tcp_rx = tcp_rx;
+		udc->ud.tcp_rx = tcp_tx;
 		udc->ud.status = SDEV_ST_USED;
+
 		spin_unlock_irq(&udc->ud.lock);
 
 		ktime_get_ts64(&udc->start_time);
 		v_start_timer(udc);
 		udc->connected = 1;
+
+		spin_unlock_irqrestore(&udc->lock, flags);
+
+		wake_up_process(udc->ud.tcp_rx);
+		wake_up_process(udc->ud.tcp_tx);
+		return count;
+
 	} else {
 		if (!udc->connected) {
 			dev_err(dev, "Device not connected");

From 5115daa675ccf70497fe56e8916cf738d8212c10 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 12 Jan 2021 13:29:14 +0200
Subject: [PATCH 0593/1820] net/mlx5e: Enforce minimum value check for ICOSQ
 size

The ICOSQ size should not go below MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE.
Enforce this where it's missing.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ec2fcb2a2977..5c8ffa8da6f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2368,8 +2368,9 @@ static u8 mlx5e_build_icosq_log_wq_sz(struct mlx5e_params *params,
 {
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		return order_base_2(MLX5E_UMR_WQEBBS) +
-			mlx5e_get_rq_log_wq_sz(rqp->rqc);
+		return max_t(u8, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE,
+			     order_base_2(MLX5E_UMR_WQEBBS) +
+			     mlx5e_get_rq_log_wq_sz(rqp->rqc));
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
 	}

From d5dd03b26ba49c4ffe67ee1937add82293c19794 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 12 Jan 2021 13:21:17 +0200
Subject: [PATCH 0594/1820] net/mlx5e: RX, Mind the MPWQE gaps when calculating
 offsets

Since cited patch, MLX5E_REQUIRED_WQE_MTTS is not a power of two.
Hence, usage of MLX5E_LOG_ALIGNED_MPWQE_PPW should be replaced,
as it lost some accuracy. Use the designated macro to calculate
the number of required MTTs.

This makes sure the solution in cited patch works properly.

While here, un-inline mlx5e_get_mpwqe_offset(), and remove the
unused RQ parameter.

Fixes: c3c9402373fe ("net/mlx5e: Add resiliency in Striding RQ mode for packets larger than MTU")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 7 ++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 4 ++--
 3 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 7435fe6829b6..304b296fe8b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -92,14 +92,15 @@ struct page_pool;
 				    MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT : 0)
 #define MLX5_MPWRQ_PAGES_PER_WQE		BIT(MLX5_MPWRQ_WQE_PAGE_ORDER)
 
-#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
+#define MLX5_ALIGN_MTTS(mtts)		(ALIGN(mtts, 8))
+#define MLX5_ALIGNED_MTTS_OCTW(mtts)	((mtts) / 2)
+#define MLX5_MTT_OCTW(mtts)		(MLX5_ALIGNED_MTTS_OCTW(MLX5_ALIGN_MTTS(mtts)))
 /* Add another page to MLX5E_REQUIRED_WQE_MTTS as a buffer between
  * WQEs, This page will absorb write overflow by the hardware, when
  * receiving packets larger than MTU. These oversize packets are
  * dropped by the driver at a later stage.
  */
-#define MLX5E_REQUIRED_WQE_MTTS		(ALIGN(MLX5_MPWRQ_PAGES_PER_WQE + 1, 8))
-#define MLX5E_LOG_ALIGNED_MPWQE_PPW	(ilog2(MLX5E_REQUIRED_WQE_MTTS))
+#define MLX5E_REQUIRED_WQE_MTTS		(MLX5_ALIGN_MTTS(MLX5_MPWRQ_PAGES_PER_WQE + 1))
 #define MLX5E_REQUIRED_MTTS(wqes)	(wqes * MLX5E_REQUIRED_WQE_MTTS)
 #define MLX5E_MAX_RQ_NUM_MTTS	\
 	((1 << 16) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5c8ffa8da6f0..831f5495ff39 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -334,9 +334,9 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
 				     rq->wqe_overflow.addr);
 }
 
-static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
+static u64 mlx5e_get_mpwqe_offset(u16 wqe_ix)
 {
-	return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT;
+	return MLX5E_REQUIRED_MTTS(wqe_ix) << PAGE_SHIFT;
 }
 
 static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
@@ -577,7 +577,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 				mlx5_wq_ll_get_wqe(&rq->mpwqe.wq, i);
 			u32 byte_count =
 				rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz;
-			u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i);
+			u64 dma_offset = mlx5e_get_mpwqe_offset(i);
 
 			wqe->data[0].addr = cpu_to_be64(dma_offset + rq->buff.headroom);
 			wqe->data[0].byte_count = cpu_to_be32(byte_count);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1b6ad94ebb10..249d8905e644 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -500,7 +500,6 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	struct mlx5e_icosq *sq = rq->icosq;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5e_umr_wqe *umr_wqe;
-	u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1);
 	u16 pi;
 	int err;
 	int i;
@@ -531,7 +530,8 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	umr_wqe->ctrl.opmod_idx_opcode =
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			    MLX5_OPCODE_UMR);
-	umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
+	umr_wqe->uctrl.xlt_offset =
+		cpu_to_be16(MLX5_ALIGNED_MTTS_OCTW(MLX5E_REQUIRED_MTTS(ix)));
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
 		.wqe_type   = MLX5E_ICOSQ_WQE_UMR_RX,

From 354521eebd02db45168b9c8c3795078f90c327b7 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Sun, 28 Feb 2021 18:40:18 +0200
Subject: [PATCH 0595/1820] net/mlx5e: Accumulate port PTP TX stats with other
 channels stats

In addition to .get_ethtool_stats, add port PTP TX stats to
.ndo_get_stats64.

Fixes: 145e5637d941 ("net/mlx5e: Add TX PTP port object support")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 831f5495ff39..9e2a30dc5e4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3811,6 +3811,15 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
 		for (j = 0; j < priv->max_opened_tc; j++) {
 			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
 
+			s->tx_packets    += sq_stats->packets;
+			s->tx_bytes      += sq_stats->bytes;
+			s->tx_dropped    += sq_stats->dropped;
+		}
+	}
+	if (priv->port_ptp_opened) {
+		for (i = 0; i < priv->max_opened_tc; i++) {
+			struct mlx5e_sq_stats *sq_stats = &priv->port_ptp_stats.sq[i];
+
 			s->tx_packets    += sq_stats->packets;
 			s->tx_bytes      += sq_stats->bytes;
 			s->tx_dropped    += sq_stats->dropped;

From 1c2cdf0b603a3b0c763288ad92e9f3f1555925cf Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Tue, 12 Jan 2021 13:34:29 +0200
Subject: [PATCH 0596/1820] net/mlx5e: Set PTP channel pointer explicitly to
 NULL

When closing the PTP channel, set its pointer explicitly to NULL. PTP
channel is opened on demand, the code verify the pointer validity before
access. Nullify it when closing the PTP channel to avoid unexpected
behavior.

Fixes: 145e5637d941 ("net/mlx5e: Add TX PTP port object support")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9e2a30dc5e4f..66d23cd275c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2503,8 +2503,10 @@ void mlx5e_close_channels(struct mlx5e_channels *chs)
 {
 	int i;
 
-	if (chs->port_ptp)
+	if (chs->port_ptp) {
 		mlx5e_port_ptp_close(chs->port_ptp);
+		chs->port_ptp = NULL;
+	}
 
 	for (i = 0; i < chs->num; i++)
 		mlx5e_close_channel(chs->c[i]);

From e5eb01344e9b09bb9d255b9727449186f7168df8 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Thu, 11 Feb 2021 15:51:11 +0200
Subject: [PATCH 0597/1820] net/mlx5e: When changing XDP program without reset,
 take refs for XSK RQs

Each RQ (including XSK RQs) takes a reference to the XDP program. When
an XDP program is attached or detached, the channels and queues are
recreated, however, there is a special flow for changing an active XDP
program to another one. In that flow, channels and queues stay alive,
but the refcounts of the old and new XDP programs are adjusted. This
flow didn't increment refcount by the number of active XSK RQs, and this
commit fixes it.

Fixes: db05815b36cb ("net/mlx5e: Add XSK zero-copy support")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 66d23cd275c1..6b761fb8d269 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4695,8 +4695,10 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 		struct mlx5e_channel *c = priv->channels.c[i];
 
 		mlx5e_rq_replace_xdp_prog(&c->rq, prog);
-		if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+		if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) {
+			bpf_prog_inc(prog);
 			mlx5e_rq_replace_xdp_prog(&c->xskrq, prog);
+		}
 	}
 
 unlock:

From 74640f09735f935437bd8df9fe61a66f03eabb34 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Fri, 29 Jan 2021 14:04:34 +0200
Subject: [PATCH 0598/1820] net/mlx5e: Revert parameters on errors when
 changing PTP state without reset

Port timestamping for PTP can be enabled/disabled while the channels are
closed. In that case mlx5e_safe_switch_channels is skipped, and the
preactivate hook is called directly. However, if that hook returns an
error, the channel parameters must be reverted back to their old values.
This commit adds missing handling on this case.

Fixes: 145e5637d941 ("net/mlx5e: Add TX PTP port object support")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index abdf721bb264..0e059d5c57ac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -2014,8 +2014,13 @@ static int set_pflag_tx_port_ts(struct net_device *netdev, bool enable)
 	 */
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		struct mlx5e_params old_params;
+
+		old_params = priv->channels.params;
 		priv->channels.params = new_channels.params;
 		err = mlx5e_num_channels_changed(priv);
+		if (err)
+			priv->channels.params = old_params;
 		goto out;
 	}
 

From 385d40b042e60aa0b677d7b400a0fefb44bcbaf4 Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@nvidia.com>
Date: Tue, 16 Feb 2021 13:39:18 +0200
Subject: [PATCH 0599/1820] net/mlx5e: Don't match on Geneve options in case
 option masks are all zero

The cited change added offload support for Geneve options without verifying
the validity of the options masks, this caused offload of rules with match
on Geneve options with class,type and data masks which are zero to fail.

Fix by ignoring the match on Geneve options in case option masks are
all zero.

Fixes: 9272e3df3023 ("net/mlx5e: Geneve, Add support for encap/decap flows offload")
Signed-off-by: Maor Dickman <maord@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Oz Shlomo <ozsh@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
index e472ed0eacfb..7ed3f9f79f11 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
@@ -227,6 +227,10 @@ static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv,
 	option_key = (struct geneve_opt *)&enc_opts.key->data[0];
 	option_mask = (struct geneve_opt *)&enc_opts.mask->data[0];
 
+	if (option_mask->opt_class == 0 && option_mask->type == 0 &&
+	    !memchr_inv(option_mask->opt_data, 0, option_mask->length * 4))
+		return 0;
+
 	if (option_key->length > max_tlv_option_data_len) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Matching on GENEVE options: unsupported option len");

From 55affa97d6758b6aeab0bc68f4884c4b5a6828af Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Mon, 1 Mar 2021 17:54:21 +0200
Subject: [PATCH 0600/1820] net/mlx5: Fix turn-off PPS command

Fix a bug of uninitialized pin index when trying to turn off PPS out.

Fixes: de19cd6cc977 ("net/mlx5: Move some PPS logic into helper functions")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Eran Ben Elisha <eranbe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index b0e129d0f6d8..1e7f26b240de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -495,15 +495,15 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 		return -EINVAL;
 
 	field_select = MLX5_MTPPS_FS_ENABLE;
+	pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, rq->perout.index);
+	if (pin < 0)
+		return -EBUSY;
+
 	if (on) {
 		bool rt_mode = mlx5_real_time_mode(mdev);
 		u32 nsec;
 		s64 sec;
 
-		pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, rq->perout.index);
-		if (pin < 0)
-			return -EBUSY;
-
 		pin_mode = MLX5_PIN_MODE_OUT;
 		pattern = MLX5_OUT_PATTERN_PERIODIC;
 		ts.tv_sec = rq->perout.period.sec;

From 1e74152ed065ef491c30ccbbe119992e3e5200be Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@nvidia.com>
Date: Tue, 2 Mar 2021 11:31:08 +0200
Subject: [PATCH 0601/1820] net/mlx5e: Check correct ip_version in
 decapsulation route resolution

flow_attr->ip_version has the matching that should be done inner/outer.
When working with chains, decapsulation is done on chain0 and next chain
match on outer header which is the original inner which could be ipv4.
So in tunnel route resolution we cannot use that to know which ip version
we are at so save tun_ip_version when parsing the tunnel match and use
that.

Fixes: a508728a4c8b ("net/mlx5e: VF tunnel RX traffic offloading")
Signed-off-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Dmytro Linkin <dlinkin@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c       | 8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c | 3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h           | 1 +
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index f8075a604605..172e0474f2e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -685,14 +685,14 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv,
 	u16 vport_num;
 	int err = 0;
 
-	if (flow_attr->ip_version == 4) {
+	if (flow_attr->tun_ip_version == 4) {
 		/* Addresses are swapped for decap */
 		attr.fl.fl4.saddr = esw_attr->rx_tun_attr->dst_ip.v4;
 		attr.fl.fl4.daddr = esw_attr->rx_tun_attr->src_ip.v4;
 		err = mlx5e_route_lookup_ipv4_get(priv, priv->netdev, &attr);
 	}
 #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
-	else if (flow_attr->ip_version == 6) {
+	else if (flow_attr->tun_ip_version == 6) {
 		/* Addresses are swapped for decap */
 		attr.fl.fl6.saddr = esw_attr->rx_tun_attr->dst_ip.v6;
 		attr.fl.fl6.daddr = esw_attr->rx_tun_attr->src_ip.v6;
@@ -718,10 +718,10 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv,
 	esw_attr->rx_tun_attr->decap_vport = vport_num;
 
 out:
-	if (flow_attr->ip_version == 4)
+	if (flow_attr->tun_ip_version == 4)
 		mlx5e_route_lookup_ipv4_put(&attr);
 #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
-	else if (flow_attr->ip_version == 6)
+	else if (flow_attr->tun_ip_version == 6)
 		mlx5e_route_lookup_ipv6_put(&attr);
 #endif
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index 6a116335bb21..7f7b0f6dcdf9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -89,6 +89,7 @@ int mlx5e_tc_set_attr_rx_tun(struct mlx5e_tc_flow *flow,
 	 * required to establish routing.
 	 */
 	flow_flag_set(flow, TUN_RX);
+	flow->attr->tun_ip_version = ip_version;
 	return 0;
 }
 
@@ -1091,7 +1092,7 @@ int mlx5e_attach_decap_route(struct mlx5e_priv *priv,
 	if (err || !esw_attr->rx_tun_attr->decap_vport)
 		goto out;
 
-	key.ip_version = attr->ip_version;
+	key.ip_version = attr->tun_ip_version;
 	if (key.ip_version == 4)
 		key.endpoint_ip.v4 = esw_attr->rx_tun_attr->dst_ip.v4;
 	else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 89003ae7775a..25c091795bcd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -79,6 +79,7 @@ struct mlx5_flow_attr {
 	u8 inner_match_level;
 	u8 outer_match_level;
 	u8 ip_version;
+	u8 tun_ip_version;
 	u32 flags;
 	union {
 		struct mlx5_esw_flow_attr esw_attr[0];

From f574531a0b77261478408e9c8f70d96dc701a35a Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@nvidia.com>
Date: Mon, 1 Mar 2021 13:07:08 +0200
Subject: [PATCH 0602/1820] net/mlx5: Disable VF tunnel TX offload if
 ignore_flow_level isn't supported

VF tunnel TX traffic offload is adding flow which forward to flow
tables with lower level, which isn't support on all FW versions
and may cause firmware to fail with syndrome.

Fixed by enabling VF tunnel TX offload only if flow table capability
ignore_flow_level is enabled.

Fixes: 10742efc20a4 ("net/mlx5e: VF tunnel TX traffic offloading")
Signed-off-by: Maor Dickman <maord@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 94cb0217b4f3..8694b83968b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -551,7 +551,8 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
 
 	if (!mlx5_eswitch_termtbl_required(esw, attr, flow_act, spec) &&
 	    MLX5_CAP_GEN(esw_attr->in_mdev, reg_c_preserve) &&
-	    mlx5_eswitch_vport_match_metadata_enabled(esw))
+	    mlx5_eswitch_vport_match_metadata_enabled(esw) &&
+	    MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level))
 		attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE;
 
 	if (attr->dest_ft) {

From 469549e4778a1e5ac4a7c6659c4b1a75a648bfdf Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@nvidia.com>
Date: Wed, 10 Feb 2021 10:33:13 +0200
Subject: [PATCH 0603/1820] net/mlx5e: Fix error flow in change profile

Move priv memset from init to cleanup to avoid double priv cleanup
that can happen on profile change if also roolback fails.
Add missing cleanup flow in mlx5e_netdev_attach_profile().

Fixes: c4d7eb57687f ("net/mxl5e: Add change profile method")
Signed-off-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 41 +++++++++++--------
 .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c |  3 +-
 2 files changed, 26 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6b761fb8d269..33b418796e43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5488,8 +5488,6 @@ int mlx5e_priv_init(struct mlx5e_priv *priv,
 		    struct net_device *netdev,
 		    struct mlx5_core_dev *mdev)
 {
-	memset(priv, 0, sizeof(*priv));
-
 	/* priv init */
 	priv->mdev        = mdev;
 	priv->netdev      = netdev;
@@ -5522,12 +5520,18 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv)
 {
 	int i;
 
+	/* bail if change profile failed and also rollback failed */
+	if (!priv->mdev)
+		return;
+
 	destroy_workqueue(priv->wq);
 	free_cpumask_var(priv->scratchpad.cpumask);
 
 	for (i = 0; i < priv->htb.max_qos_sqs; i++)
 		kfree(priv->htb.qos_sq_stats[i]);
 	kvfree(priv->htb.qos_sq_stats);
+
+	memset(priv, 0, sizeof(*priv));
 }
 
 struct net_device *
@@ -5644,11 +5648,10 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv)
 }
 
 static int
-mlx5e_netdev_attach_profile(struct mlx5e_priv *priv,
+mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev,
 			    const struct mlx5e_profile *new_profile, void *new_ppriv)
 {
-	struct net_device *netdev = priv->netdev;
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_priv *priv = netdev_priv(netdev);
 	int err;
 
 	err = mlx5e_priv_init(priv, netdev, mdev);
@@ -5661,10 +5664,16 @@ mlx5e_netdev_attach_profile(struct mlx5e_priv *priv,
 	priv->ppriv = new_ppriv;
 	err = new_profile->init(priv->mdev, priv->netdev);
 	if (err)
-		return err;
+		goto priv_cleanup;
 	err = mlx5e_attach_netdev(priv);
 	if (err)
-		new_profile->cleanup(priv);
+		goto profile_cleanup;
+	return err;
+
+profile_cleanup:
+	new_profile->cleanup(priv);
+priv_cleanup:
+	mlx5e_priv_cleanup(priv);
 	return err;
 }
 
@@ -5673,13 +5682,14 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv,
 {
 	unsigned int new_max_nch = mlx5e_calc_max_nch(priv, new_profile);
 	const struct mlx5e_profile *orig_profile = priv->profile;
+	struct net_device *netdev = priv->netdev;
+	struct mlx5_core_dev *mdev = priv->mdev;
 	void *orig_ppriv = priv->ppriv;
 	int err, rollback_err;
 
 	/* sanity */
 	if (new_max_nch != priv->max_nch) {
-		netdev_warn(priv->netdev,
-			    "%s: Replacing profile with different max channels\n",
+		netdev_warn(netdev, "%s: Replacing profile with different max channels\n",
 			    __func__);
 		return -EINVAL;
 	}
@@ -5689,22 +5699,19 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv,
 	priv->profile->cleanup(priv);
 	mlx5e_priv_cleanup(priv);
 
-	err = mlx5e_netdev_attach_profile(priv, new_profile, new_ppriv);
+	err = mlx5e_netdev_attach_profile(netdev, mdev, new_profile, new_ppriv);
 	if (err) { /* roll back to original profile */
-		netdev_warn(priv->netdev, "%s: new profile init failed, %d\n",
-			    __func__, err);
+		netdev_warn(netdev, "%s: new profile init failed, %d\n", __func__, err);
 		goto rollback;
 	}
 
 	return 0;
 
 rollback:
-	rollback_err = mlx5e_netdev_attach_profile(priv, orig_profile, orig_ppriv);
-	if (rollback_err) {
-		netdev_err(priv->netdev,
-			   "%s: failed to rollback to orig profile, %d\n",
+	rollback_err = mlx5e_netdev_attach_profile(netdev, mdev, orig_profile, orig_ppriv);
+	if (rollback_err)
+		netdev_err(netdev, "%s: failed to rollback to orig profile, %d\n",
 			   __func__, rollback_err);
-	}
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 1eeca45cfcdf..756fa0401ab7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -694,6 +694,7 @@ static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev)
 static void mlx5_rdma_netdev_free(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5i_priv *ipriv = priv->ppriv;
 	const struct mlx5e_profile *profile = priv->profile;
 
@@ -702,7 +703,7 @@ static void mlx5_rdma_netdev_free(struct net_device *netdev)
 
 	if (!ipriv->sub_interface) {
 		mlx5i_pkey_qpn_ht_cleanup(netdev);
-		mlx5e_destroy_mdev_resources(priv->mdev);
+		mlx5e_destroy_mdev_resources(mdev);
 	}
 }
 

From 4806f1e2fee84c053cb68cd5be5817170bf0aab6 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Wed, 3 Mar 2021 14:36:16 +0200
Subject: [PATCH 0604/1820] net/mlx5: Set QP timestamp mode to default

QPs which don't care from timestamp mode, should set the ts_format
to default, otherwise the QP creation could be failed if the timestamp
mode is not supported.

Fixes: 2fe8d4b87802 ("RDMA/mlx5: Fail QP creation if the device can not support the CQE TS")
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c        | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c      | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c | 1 +
 include/linux/mlx5/qp.h                                    | 7 +++++++
 4 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 80da50e12915..bd66ab2af5b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -575,6 +575,7 @@ static int mlx5_fpga_conn_create_qp(struct mlx5_fpga_conn *conn,
 	MLX5_SET(qpc, qpc, log_sq_size, ilog2(conn->qp.sq.size));
 	MLX5_SET(qpc, qpc, cqn_snd, conn->cq.mcq.cqn);
 	MLX5_SET(qpc, qpc, cqn_rcv, conn->cq.mcq.cqn);
+	MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(mdev));
 	MLX5_SET64(qpc, qpc, dbr_addr, conn->qp.wq_ctrl.db.dma);
 	if (MLX5_CAP_GEN(mdev, cqe_version) == 1)
 		MLX5_SET(qpc, qpc, user_index, 0xFFFFFF);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 756fa0401ab7..6f7cef47e04c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -233,6 +233,7 @@ int mlx5i_create_underlay_qp(struct mlx5e_priv *priv)
 	}
 
 	qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+	MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(priv->mdev));
 	MLX5_SET(qpc, qpc, st, MLX5_QP_ST_UD);
 	MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
 	MLX5_SET(qpc, qpc, ulp_stateless_offload_mode,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 83c4c877d558..8a6a56f9dc4e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -169,6 +169,7 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 	MLX5_SET(qpc, qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt));
 	MLX5_SET(qpc, qpc, rq_type, MLX5_NON_ZERO_RQ);
 	MLX5_SET(qpc, qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt));
+	MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(mdev));
 	MLX5_SET64(qpc, qpc, dbr_addr, dr_qp->wq_ctrl.db.dma);
 	if (MLX5_CAP_GEN(mdev, cqe_version) == 1)
 		MLX5_SET(qpc, qpc, user_index, 0xFFFFFF);
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index d75ef8aa8fac..b7deb790f257 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -547,4 +547,11 @@ static inline const char *mlx5_qp_state_str(int state)
 	}
 }
 
+static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev)
+{
+	return !MLX5_CAP_ROCE(dev, qp_ts_format) ?
+		       MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING :
+		       MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT;
+}
+
 #endif /* MLX5_QP_H */

From 8256c69b2d9c35e94d0e424184c0d27b59bdee12 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Wed, 3 Mar 2021 14:39:20 +0200
Subject: [PATCH 0605/1820] RDMA/mlx5: Fix timestamp default mode

1. Don't set the ts_format bit to default when it reserved - device is
   running in the old mode (free running).
2. XRC doesn't have a CQ therefore the ts format in the QP
   context should be default / free running.
3. Set ts_format to WQ.

Fixes: 2fe8d4b87802 ("RDMA/mlx5: Fail QP creation if the device can not support the CQE TS")
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index ec4b3f6a8222..f5a52a6fae43 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1078,7 +1078,7 @@ static int _create_kernel_qp(struct mlx5_ib_dev *dev,
 
 	qpc = MLX5_ADDR_OF(create_qp_in, *in, qpc);
 	MLX5_SET(qpc, qpc, uar_page, uar_index);
-	MLX5_SET(qpc, qpc, ts_format, MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT);
+	MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(dev->mdev));
 	MLX5_SET(qpc, qpc, log_page_size, qp->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
 
 	/* Set "fast registration enabled" for all kernel QPs */
@@ -1188,7 +1188,8 @@ static int get_rq_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq)
 		}
 		return MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING;
 	}
-	return MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT;
+	return fr_supported ? MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING :
+			      MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT;
 }
 
 static int get_sq_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq)
@@ -1206,7 +1207,8 @@ static int get_sq_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq)
 		}
 		return MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING;
 	}
-	return MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT;
+	return fr_supported ? MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING :
+			      MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT;
 }
 
 static int get_qp_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq,
@@ -1217,7 +1219,8 @@ static int get_qp_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq,
 			MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING ||
 		MLX5_CAP_ROCE(dev->mdev, qp_ts_format) ==
 			MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME;
-	int ts_format = MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT;
+	int ts_format = fr_supported ? MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING :
+				       MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT;
 
 	if (recv_cq &&
 	    recv_cq->create_flags & IB_UVERBS_CQ_FLAGS_TIMESTAMP_COMPLETION)
@@ -1930,6 +1933,7 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (qp->flags & IB_QP_CREATE_MANAGED_RECV)
 		MLX5_SET(qpc, qpc, cd_slave_receive, 1);
 
+	MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(dev->mdev));
 	MLX5_SET(qpc, qpc, rq_type, MLX5_SRQ_RQ);
 	MLX5_SET(qpc, qpc, no_sq, 1);
 	MLX5_SET(qpc, qpc, cqn_rcv, to_mcq(devr->c0)->mcq.cqn);
@@ -4873,6 +4877,7 @@ static int  create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd,
 	struct mlx5_ib_dev *dev;
 	int has_net_offloads;
 	__be64 *rq_pas0;
+	int ts_format;
 	void *in;
 	void *rqc;
 	void *wq;
@@ -4881,6 +4886,10 @@ static int  create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd,
 
 	dev = to_mdev(pd->device);
 
+	ts_format = get_rq_ts_format(dev, to_mcq(init_attr->cq));
+	if (ts_format < 0)
+		return ts_format;
+
 	inlen = MLX5_ST_SZ_BYTES(create_rq_in) + sizeof(u64) * rwq->rq_num_pas;
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
@@ -4890,6 +4899,7 @@ static int  create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd,
 	rqc = MLX5_ADDR_OF(create_rq_in, in, ctx);
 	MLX5_SET(rqc,  rqc, mem_rq_type,
 		 MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_INLINE);
+	MLX5_SET(rqc, rqc, ts_format, ts_format);
 	MLX5_SET(rqc, rqc, user_index, rwq->user_index);
 	MLX5_SET(rqc,  rqc, cqn, to_mcq(init_attr->cq)->mcq.cqn);
 	MLX5_SET(rqc,  rqc, state, MLX5_RQC_STATE_RST);

From 8b90d897823b28a51811931f3bdc79f8df79407e Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Wed, 17 Feb 2021 08:23:29 +0200
Subject: [PATCH 0606/1820] net/mlx5e: E-switch, Fix rate calculation division

do_div() returns reminder, while cited patch wanted to use
quotient.
Fix it by using quotient.

Fixes: 0e22bfb7c046 ("net/mlx5e: E-switch, Fix rate calculation for overflow")
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Maor Dickman <maord@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 0da69b98f38f..0cacf46dc950 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4445,7 +4445,8 @@ static int apply_police_params(struct mlx5e_priv *priv, u64 rate,
 	 */
 	if (rate) {
 		rate = (rate * BITS_PER_BYTE) + 500000;
-		rate_mbps = max_t(u64, do_div(rate, 1000000), 1);
+		do_div(rate, 1000000);
+		rate_mbps = max_t(u32, rate, 1);
 	}
 
 	err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps);

From 6a3717544ce9ee8a2058fbc75c67060515435937 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 26 Feb 2021 10:15:16 +0200
Subject: [PATCH 0607/1820] net/mlx5: SF, Correct vhca context size

Fix vhca context size as defined by device interface specification.

Fixes: f3196bb0f14c ("net/mlx5: Introduce vhca state event notifier")
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h    | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h
index 1daf5a122ba3..4fc870140d71 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h
@@ -20,7 +20,7 @@ struct mlx5_ifc_vhca_state_context_bits {
 
 	u8         sw_function_id[0x20];
 
-	u8         reserved_at_40[0x80];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_query_vhca_state_out_bits {

From 6fa37d66ef2dc850ff18b2a057a84cd7ca8499bb Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 2 Feb 2021 12:21:04 +0200
Subject: [PATCH 0608/1820] net/mlx5: SF: Fix memory leak of work item

Cited patch in the fixes tag missed to free the allocated work.
Fix it by freeing the work after work execution.

Fixes: f3196bb0f14c ("net/mlx5: Introduce vhca state event notifier")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
index af2f2dd9db25..f1c2068d4f2a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
@@ -94,6 +94,7 @@ static void mlx5_vhca_state_work_handler(struct work_struct *_work)
 	struct mlx5_core_dev *dev = notifier->dev;
 
 	mlx5_vhca_event_notify(dev, &work->event);
+	kfree(work);
 }
 
 static int

From dc694f11a7593b7fd5aabe15a0e6c8fd2de24ebf Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 11 Feb 2021 15:41:35 +0200
Subject: [PATCH 0609/1820] net/mlx5: SF: Fix error flow of SFs allocation flow

When SF id is unavailable, code jumps to wrong label that accesses
sw id array outside of its range.
Hence, when SF id is not allocated, avoid accessing such array.

Fixes: 8f0105418668 ("net/mlx5: SF, Add port add delete functionality")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
index 58b6be0b03d7..0914909806cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -64,7 +64,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum)
 	}
 	if (sw_id == -ENOSPC) {
 		err = -ENOSPC;
-		goto err;
+		goto exist_err;
 	}
 
 	hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, sw_id);

From 84076c4c800d1be77199a139d65b8b136a61422e Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Sat, 6 Feb 2021 22:11:52 +0200
Subject: [PATCH 0610/1820] net/mlx5: DR, Fix potential shift wrapping of
 32-bit value in STEv1 getter

Fix 32-bit variable shift wrapping in dr_ste_v1_get_miss_addr.

Fixes: a6098129c781 ("net/mlx5: DR, Add STEv1 setters and getters")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
index 4088d6e51508..9143ec326ebf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
@@ -264,8 +264,8 @@ static void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr)
 static u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p)
 {
 	u64 index =
-		(MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6) |
-		 MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_39_32) << 26);
+		((u64)MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6) |
+		 ((u64)MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_39_32)) << 26);
 
 	return index << 6;
 }

From c4c877b2732466b4c63217baad05c96f775912c7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 10 Mar 2021 01:38:09 +0100
Subject: [PATCH 0611/1820] net: Consolidate common blackhole dst ops

Move generic blackhole dst ops to the core and use them from both
ipv4_dst_blackhole_ops and ip6_dst_blackhole_ops where possible. No
functional change otherwise. We need these also in other locations
and having to define them over and over again is not great.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 11 +++++++++++
 net/core/dst.c    | 38 ++++++++++++++++++++++++++++++++++++++
 net/ipv4/route.c  | 45 ++++++++-------------------------------------
 net/ipv6/route.c  | 36 +++++++++---------------------------
 4 files changed, 66 insertions(+), 64 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 26f134ad3a25..75b1e734e9c2 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -550,4 +550,15 @@ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
 		dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
 }
 
+struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie);
+void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb, u32 mtu, bool confirm_neigh);
+void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+			    struct sk_buff *skb);
+u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old);
+struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
+					     struct sk_buff *skb,
+					     const void *daddr);
+unsigned int dst_blackhole_mtu(const struct dst_entry *dst);
+
 #endif /* _NET_DST_H */
diff --git a/net/core/dst.c b/net/core/dst.c
index 0c01bd8d9d81..5f6315601776 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -237,6 +237,44 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 }
 EXPORT_SYMBOL(__dst_destroy_metrics_generic);
 
+struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie)
+{
+	return NULL;
+}
+
+u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old)
+{
+	return NULL;
+}
+
+struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
+					     struct sk_buff *skb,
+					     const void *daddr)
+{
+	return NULL;
+}
+
+void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_update_pmtu);
+
+void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+			    struct sk_buff *skb)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_redirect);
+
+unsigned int dst_blackhole_mtu(const struct dst_entry *dst)
+{
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	return mtu ? : dst->dev->mtu;
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_mtu);
+
 static struct dst_ops md_dst_ops = {
 	.family =		AF_UNSPEC,
 };
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 02d81d79deeb..bba150fdd265 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2687,44 +2687,15 @@ out:
 	return rth;
 }
 
-static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
-{
-	return NULL;
-}
-
-static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
-{
-	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
-
-	return mtu ? : dst->dev->mtu;
-}
-
-static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					  struct sk_buff *skb, u32 mtu,
-					  bool confirm_neigh)
-{
-}
-
-static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
-				       struct sk_buff *skb)
-{
-}
-
-static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst,
-					  unsigned long old)
-{
-	return NULL;
-}
-
 static struct dst_ops ipv4_dst_blackhole_ops = {
-	.family			=	AF_INET,
-	.check			=	ipv4_blackhole_dst_check,
-	.mtu			=	ipv4_blackhole_mtu,
-	.default_advmss		=	ipv4_default_advmss,
-	.update_pmtu		=	ipv4_rt_blackhole_update_pmtu,
-	.redirect		=	ipv4_rt_blackhole_redirect,
-	.cow_metrics		=	ipv4_rt_blackhole_cow_metrics,
-	.neigh_lookup		=	ipv4_neigh_lookup,
+	.family			= AF_INET,
+	.default_advmss		= ipv4_default_advmss,
+	.neigh_lookup		= ipv4_neigh_lookup,
+	.check			= dst_blackhole_check,
+	.cow_metrics		= dst_blackhole_cow_metrics,
+	.update_pmtu		= dst_blackhole_update_pmtu,
+	.redirect		= dst_blackhole_redirect,
+	.mtu			= dst_blackhole_mtu,
 };
 
 struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1536f4948e86..1056b0229ffd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -260,34 +260,16 @@ static struct dst_ops ip6_dst_ops_template = {
 	.confirm_neigh		=	ip6_confirm_neigh,
 };
 
-static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
-{
-	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
-
-	return mtu ? : dst->dev->mtu;
-}
-
-static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					 struct sk_buff *skb, u32 mtu,
-					 bool confirm_neigh)
-{
-}
-
-static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
-				      struct sk_buff *skb)
-{
-}
-
 static struct dst_ops ip6_dst_blackhole_ops = {
-	.family			=	AF_INET6,
-	.destroy		=	ip6_dst_destroy,
-	.check			=	ip6_dst_check,
-	.mtu			=	ip6_blackhole_mtu,
-	.default_advmss		=	ip6_default_advmss,
-	.update_pmtu		=	ip6_rt_blackhole_update_pmtu,
-	.redirect		=	ip6_rt_blackhole_redirect,
-	.cow_metrics		=	dst_cow_metrics_generic,
-	.neigh_lookup		=	ip6_dst_neigh_lookup,
+	.family			= AF_INET6,
+	.default_advmss		= ip6_default_advmss,
+	.neigh_lookup		= ip6_dst_neigh_lookup,
+	.check			= ip6_dst_check,
+	.destroy		= ip6_dst_destroy,
+	.cow_metrics		= dst_cow_metrics_generic,
+	.update_pmtu		= dst_blackhole_update_pmtu,
+	.redirect		= dst_blackhole_redirect,
+	.mtu			= dst_blackhole_mtu,
 };
 
 static const u32 ip6_template_metrics[RTAX_MAX] = {

From a188bb5638d41aa99090ebf2f85d3505ab13fba5 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 10 Mar 2021 01:38:10 +0100
Subject: [PATCH 0612/1820] net, bpf: Fix ip6ip6 crash with collect_md
 populated skbs

I ran into a crash where setting up a ip6ip6 tunnel device which was /not/
set to collect_md mode was receiving collect_md populated skbs for xmit.

The BPF prog was populating the skb via bpf_skb_set_tunnel_key() which is
assigning special metadata dst entry and then redirecting the skb to the
device, taking ip6_tnl_start_xmit() -> ipxip6_tnl_xmit() -> ip6_tnl_xmit()
and in the latter it performs a neigh lookup based on skb_dst(skb) where
we trigger a NULL pointer dereference on dst->ops->neigh_lookup() since
the md_dst_ops do not populate neigh_lookup callback with a fake handler.

Transform the md_dst_ops into generic dst_blackhole_ops that can also be
reused elsewhere when needed, and use them for the metadata dst entries as
callback ops.

Also, remove the dst_md_discard{,_out}() ops and rely on dst_discard{,_out}()
from dst_init() which free the skb the same way modulo the splat. Given we
will be able to recover just fine from there, avoid any potential splats
iff this gets ever triggered in future (or worse, panic on warns when set).

Fixes: f38a9eb1f77b ("dst: Metadata destinations")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dst.c | 31 +++++++++----------------------
 1 file changed, 9 insertions(+), 22 deletions(-)

diff --git a/net/core/dst.c b/net/core/dst.c
index 5f6315601776..fb3bcba87744 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -275,37 +275,24 @@ unsigned int dst_blackhole_mtu(const struct dst_entry *dst)
 }
 EXPORT_SYMBOL_GPL(dst_blackhole_mtu);
 
-static struct dst_ops md_dst_ops = {
-	.family =		AF_UNSPEC,
+static struct dst_ops dst_blackhole_ops = {
+	.family		= AF_UNSPEC,
+	.neigh_lookup	= dst_blackhole_neigh_lookup,
+	.check		= dst_blackhole_check,
+	.cow_metrics	= dst_blackhole_cow_metrics,
+	.update_pmtu	= dst_blackhole_update_pmtu,
+	.redirect	= dst_blackhole_redirect,
+	.mtu		= dst_blackhole_mtu,
 };
 
-static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
-{
-	WARN_ONCE(1, "Attempting to call output on metadata dst\n");
-	kfree_skb(skb);
-	return 0;
-}
-
-static int dst_md_discard(struct sk_buff *skb)
-{
-	WARN_ONCE(1, "Attempting to call input on metadata dst\n");
-	kfree_skb(skb);
-	return 0;
-}
-
 static void __metadata_dst_init(struct metadata_dst *md_dst,
 				enum metadata_type type, u8 optslen)
-
 {
 	struct dst_entry *dst;
 
 	dst = &md_dst->dst;
-	dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE,
+	dst_init(dst, &dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE,
 		 DST_METADATA | DST_NOCOUNT);
-
-	dst->input = dst_md_discard;
-	dst->output = dst_md_discard_out;
-
 	memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
 	md_dst->type = type;
 }

From 28259bac7f1dde06d8ba324e222bbec9d4e92f2b Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 9 Mar 2021 18:20:35 -0800
Subject: [PATCH 0613/1820] ipv6: fix suspecious RCU usage warning

Syzbot reported the suspecious RCU usage in nexthop_fib6_nh() when
called from ipv6_route_seq_show(). The reason is ipv6_route_seq_start()
calls rcu_read_lock_bh(), while nexthop_fib6_nh() calls
rcu_dereference_rtnl().
The fix proposed is to add a variant of nexthop_fib6_nh() to use
rcu_dereference_bh_rtnl() for ipv6_route_seq_show().

The reported trace is as follows:
./include/net/nexthop.h:416 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
2 locks held by syz-executor.0/17895:
     at: seq_read+0x71/0x12a0 fs/seq_file.c:169
     at: seq_file_net include/linux/seq_file_net.h:19 [inline]
     at: ipv6_route_seq_start+0xaf/0x300 net/ipv6/ip6_fib.c:2616

stack backtrace:
CPU: 1 PID: 17895 Comm: syz-executor.0 Not tainted 4.15.0-syzkaller #0
Call Trace:
 [<ffffffff849edf9e>] __dump_stack lib/dump_stack.c:17 [inline]
 [<ffffffff849edf9e>] dump_stack+0xd8/0x147 lib/dump_stack.c:53
 [<ffffffff8480b7fa>] lockdep_rcu_suspicious+0x153/0x15d kernel/locking/lockdep.c:5745
 [<ffffffff8459ada6>] nexthop_fib6_nh include/net/nexthop.h:416 [inline]
 [<ffffffff8459ada6>] ipv6_route_native_seq_show net/ipv6/ip6_fib.c:2488 [inline]
 [<ffffffff8459ada6>] ipv6_route_seq_show+0x436/0x7a0 net/ipv6/ip6_fib.c:2673
 [<ffffffff81c556df>] seq_read+0xccf/0x12a0 fs/seq_file.c:276
 [<ffffffff81dbc62c>] proc_reg_read+0x10c/0x1d0 fs/proc/inode.c:231
 [<ffffffff81bc28ae>] do_loop_readv_writev fs/read_write.c:714 [inline]
 [<ffffffff81bc28ae>] do_loop_readv_writev fs/read_write.c:701 [inline]
 [<ffffffff81bc28ae>] do_iter_read+0x49e/0x660 fs/read_write.c:935
 [<ffffffff81bc81ab>] vfs_readv+0xfb/0x170 fs/read_write.c:997
 [<ffffffff81c88847>] kernel_readv fs/splice.c:361 [inline]
 [<ffffffff81c88847>] default_file_splice_read+0x487/0x9c0 fs/splice.c:416
 [<ffffffff81c86189>] do_splice_to+0x129/0x190 fs/splice.c:879
 [<ffffffff81c86f66>] splice_direct_to_actor+0x256/0x890 fs/splice.c:951
 [<ffffffff81c8777d>] do_splice_direct+0x1dd/0x2b0 fs/splice.c:1060
 [<ffffffff81bc4747>] do_sendfile+0x597/0xce0 fs/read_write.c:1459
 [<ffffffff81bca205>] SYSC_sendfile64 fs/read_write.c:1520 [inline]
 [<ffffffff81bca205>] SyS_sendfile64+0x155/0x170 fs/read_write.c:1506
 [<ffffffff81015fcf>] do_syscall_64+0x1ff/0x310 arch/x86/entry/common.c:305
 [<ffffffff84a00076>] entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: f88d8ea67fbdb ("ipv6: Plumb support for nexthop object in a fib6_info")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Cc: David Ahern <dsahern@kernel.org>
Cc: Ido Schimmel <idosch@idosch.org>
Cc: Petr Machata <petrm@nvidia.com>
Cc: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/nexthop.h | 24 ++++++++++++++++++++++++
 net/ipv6/ip6_fib.c    |  2 +-
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index 7bc057aee40b..a10a319d7eb2 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -410,6 +410,7 @@ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel)
 int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
 		       struct netlink_ext_ack *extack);
 
+/* Caller should either hold rcu_read_lock(), or RTNL. */
 static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh)
 {
 	struct nh_info *nhi;
@@ -430,6 +431,29 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh)
 	return NULL;
 }
 
+/* Variant of nexthop_fib6_nh().
+ * Caller should either hold rcu_read_lock_bh(), or RTNL.
+ */
+static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh)
+{
+	struct nh_info *nhi;
+
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_bh_rtnl(nh->nh_grp);
+		nh = nexthop_mpath_select(nh_grp, 0);
+		if (!nh)
+			return NULL;
+	}
+
+	nhi = rcu_dereference_bh_rtnl(nh->nh_info);
+	if (nhi->family == AF_INET6)
+		return &nhi->fib6_nh;
+
+	return NULL;
+}
+
 static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i)
 {
 	struct fib6_nh *fib6_nh;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ef9d022e693f..679699e953f1 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2486,7 +2486,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v)
 	const struct net_device *dev;
 
 	if (rt->nh)
-		fib6_nh = nexthop_fib6_nh(rt->nh);
+		fib6_nh = nexthop_fib6_nh_bh(rt->nh);
 
 	seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);
 

From a2f8d988698d7d3645b045f4940415b045140b81 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 10 Dec 2020 01:18:40 -0500
Subject: [PATCH 0614/1820] drm/amdgpu/display: simplify backlight setting

Avoid the extra wrapper function.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 20 ++++---------------
 1 file changed, 4 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 3e1fd1e7d09f..78720a25c13f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3185,19 +3185,6 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm)
 #endif
 }
 
-static int set_backlight_via_aux(struct dc_link *link, uint32_t brightness)
-{
-	bool rc;
-
-	if (!link)
-		return 1;
-
-	rc = dc_link_set_backlight_level_nits(link, true, brightness,
-					      AUX_BL_DEFAULT_TRANSITION_TIME_MS);
-
-	return rc ? 0 : 1;
-}
-
 static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps,
 				unsigned *min, unsigned *max)
 {
@@ -3260,9 +3247,10 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd)
 	brightness = convert_brightness_from_user(&caps, bd->props.brightness);
 	// Change brightness based on AUX property
 	if (caps.aux_support)
-		return set_backlight_via_aux(link, brightness);
-
-	rc = dc_link_set_backlight_level(dm->backlight_link, brightness, 0);
+		rc = dc_link_set_backlight_level_nits(link, true, brightness,
+						      AUX_BL_DEFAULT_TRANSITION_TIME_MS);
+	else
+		rc = dc_link_set_backlight_level(dm->backlight_link, brightness, 0);
 
 	return rc ? 0 : 1;
 }

From dfd8b7fbd985ec1cf76fe10f2875a50b10833740 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 10 Dec 2020 01:20:08 -0500
Subject: [PATCH 0615/1820] drm/amdgpu/display: don't assert in set backlight
 function

It just spams the logs.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index fa5059f71727..bd0101013ec8 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -2602,7 +2602,6 @@ bool dc_link_set_backlight_level(const struct dc_link *link,
 			if (pipe_ctx->plane_state == NULL)
 				frame_ramp = 0;
 		} else {
-			ASSERT(false);
 			return false;
 		}
 

From 0ad3e64eb46d8c47de3af552e282894e3893e973 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 10 Dec 2020 01:45:12 -0500
Subject: [PATCH 0616/1820] drm/amdgpu/display: handle aux backlight in
 backlight_get_brightness

Need to fetch it via aux.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 24 +++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 78720a25c13f..0bc9a06b3f15 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3258,11 +3258,27 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd)
 static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd)
 {
 	struct amdgpu_display_manager *dm = bl_get_data(bd);
-	int ret = dc_link_get_backlight_level(dm->backlight_link);
+	struct amdgpu_dm_backlight_caps caps;
 
-	if (ret == DC_ERROR_UNEXPECTED)
-		return bd->props.brightness;
-	return convert_brightness_to_user(&dm->backlight_caps, ret);
+	amdgpu_dm_update_backlight_caps(dm);
+	caps = dm->backlight_caps;
+
+	if (caps.aux_support) {
+		struct dc_link *link = (struct dc_link *)dm->backlight_link;
+		u32 avg, peak;
+		bool rc;
+
+		rc = dc_link_get_backlight_level_nits(link, &avg, &peak);
+		if (!rc)
+			return bd->props.brightness;
+		return convert_brightness_to_user(&caps, avg);
+	} else {
+		int ret = dc_link_get_backlight_level(dm->backlight_link);
+
+		if (ret == DC_ERROR_UNEXPECTED)
+			return bd->props.brightness;
+		return convert_brightness_to_user(&caps, ret);
+	}
 }
 
 static const struct backlight_ops amdgpu_dm_backlight_ops = {

From 7a46f05e5e163c00e41892e671294286e53fe15c Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 3 Feb 2021 13:42:41 +0100
Subject: [PATCH 0617/1820] drm/amd/display: Add a backlight module option

There seem devices that don't work with the aux channel backlight
control.  For allowing such users to test with the other backlight
control method, provide a new module option, aux_backlight, to specify
enabling or disabling the aux backport support explicitly.  As
default, the aux support is detected by the hardware capability.

v2: make the backlight option generic in case we add future
backlight types (Alex)

BugLink: https://bugzilla.opensuse.org/show_bug.cgi?id=1180749
BugLink: https://gitlab.freedesktop.org/drm/amd/-/issues/1438
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h               | 1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c           | 4 ++++
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 5 +++++
 3 files changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index b6879d97c9c9..49267eb64302 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -180,6 +180,7 @@ extern uint amdgpu_smu_memory_pool_size;
 extern uint amdgpu_dc_feature_mask;
 extern uint amdgpu_dc_debug_mask;
 extern uint amdgpu_dm_abm_level;
+extern int amdgpu_backlight;
 extern struct amdgpu_mgpu_info mgpu_info;
 extern int amdgpu_ras_enable;
 extern uint amdgpu_ras_mask;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 4575192d9b08..b26e2fd1c538 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -781,6 +781,10 @@ uint amdgpu_dm_abm_level;
 MODULE_PARM_DESC(abmlevel, "ABM level (0 = off (default), 1-4 = backlight reduction level) ");
 module_param_named(abmlevel, amdgpu_dm_abm_level, uint, 0444);
 
+int amdgpu_backlight = -1;
+MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (default))");
+module_param_named(backlight, amdgpu_backlight, bint, 0444);
+
 /**
  * DOC: tmz (int)
  * Trusted Memory Zone (TMZ) is a method to protect data being written
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 0bc9a06b3f15..0523be612a48 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2267,6 +2267,11 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 	    caps->ext_caps->bits.hdr_aux_backlight_control == 1)
 		caps->aux_support = true;
 
+	if (amdgpu_backlight == 0)
+		caps->aux_support = false;
+	else if (amdgpu_backlight == 1)
+		caps->aux_support = true;
+
 	/* From the specification (CTA-861-G), for calculating the maximum
 	 * luminance we need to use:
 	 *	Luminance = 50*2**(CV/32)

From 15e8b95d5f7509e0b09289be8c422c459c9f0412 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Holger=20Hoffst=C3=A4tte?= <holger@applied-asynchrony.com>
Date: Fri, 5 Mar 2021 12:39:21 +0100
Subject: [PATCH 0618/1820] drm/amd/display: Fix nested FPU context in
 dcn21_validate_bandwidth()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 41401ac67791 added FPU wrappers to dcn21_validate_bandwidth(),
which was correct. Unfortunately a nested function alredy contained
DC_FP_START()/DC_FP_END() calls, which results in nested FPU context
enter/exit and complaints by kernel_fpu_begin_mask().
This can be observed e.g. with 5.10.20, which backported 41401ac67791
and now emits the following warning on boot:

WARNING: CPU: 6 PID: 858 at arch/x86/kernel/fpu/core.c:129 kernel_fpu_begin_mask+0xa5/0xc0
Call Trace:
 dcn21_calculate_wm+0x47/0xa90 [amdgpu]
 dcn21_validate_bandwidth_fp+0x15d/0x2b0 [amdgpu]
 dcn21_validate_bandwidth+0x29/0x40 [amdgpu]
 dc_validate_global_state+0x3c7/0x4c0 [amdgpu]

The warning is emitted due to the additional DC_FP_START/END calls in
patch_bounding_box(), which is inlined into dcn21_calculate_wm(),
its only caller. Removing the calls brings the code in line with
dcn20 and makes the warning disappear.

Fixes: 41401ac67791 ("drm/amd/display: Add FPU wrappers to dcn21_validate_bandwidth()")
Signed-off-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index 072f8c880924..68be73fe2e23 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -1062,8 +1062,6 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s
 {
 	int i;
 
-	DC_FP_START();
-
 	if (dc->bb_overrides.sr_exit_time_ns) {
 		for (i = 0; i < WM_SET_COUNT; i++) {
 			  dc->clk_mgr->bw_params->wm_table.entries[i].sr_exit_time_us =
@@ -1088,8 +1086,6 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s
 				dc->bb_overrides.dram_clock_change_latency_ns / 1000.0;
 		}
 	}
-
-	DC_FP_END();
 }
 
 void dcn21_calculate_wm(

From 680174cfd1e1cea70a8f30ccb44d8fbdf996018e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Holger=20Hoffst=C3=A4tte?= <holger@applied-asynchrony.com>
Date: Fri, 5 Mar 2021 15:23:18 +0100
Subject: [PATCH 0619/1820] drm/amdgpu/display: use GFP_ATOMIC in
 dcn21_validate_bandwidth_fp()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After fixing nested FPU contexts caused by 41401ac67791 we're still seeing
complaints about spurious kernel_fpu_end(). As it turns out this was
already fixed for dcn20 in commit f41ed88cbd ("drm/amdgpu/display:
use GFP_ATOMIC in dcn20_validate_bandwidth_internal") but never moved
forward to dcn21.

Signed-off-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index 68be73fe2e23..94ee2cab26b7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -1335,7 +1335,7 @@ static noinline bool dcn21_validate_bandwidth_fp(struct dc *dc,
 	int vlevel = 0;
 	int pipe_split_from[MAX_PIPES];
 	int pipe_cnt = 0;
-	display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL);
+	display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC);
 	DC_LOGGER_INIT(dc->ctx->logger);
 
 	BW_VAL_TRACE_COUNT();

From 7afa0033d6f7fb8a84798ef99d1117661c4e696c Mon Sep 17 00:00:00 2001
From: Qingqing Zhuo <qingqing.zhuo@amd.com>
Date: Fri, 19 Feb 2021 17:17:50 -0500
Subject: [PATCH 0620/1820] drm/amd/display: Enable pflip interrupt upon pipe
 enable

[Why]
pflip interrupt would not be enabled promptly if a pipe is disabled
and re-enabled, causing flip_done timeout error during DP
compliance tests

[How]
Enable pflip interrupt upon pipe enablement

Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c     |  1 +
 drivers/gpu/drm/amd/display/dc/dc.h                   |  1 +
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c     | 11 +++++++++++
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h     |  6 ++++++
 .../gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c |  7 +++++++
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c     |  1 +
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c    |  6 ++++++
 drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c     |  1 +
 drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c     |  1 +
 drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h          |  2 ++
 10 files changed, 37 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 0523be612a48..573cf17262da 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4725,6 +4725,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	dc_plane_state->global_alpha_value = plane_info.global_alpha_value;
 	dc_plane_state->dcc = plane_info.dcc;
 	dc_plane_state->layer_index = plane_info.layer_index; // Always returns 0
+	dc_plane_state->flip_int_enabled = true;
 
 	/*
 	 * Always set input transfer function, since plane state is refreshed
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 4eee3a55fa30..18ed0d3f247e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -887,6 +887,7 @@ struct dc_plane_state {
 	int layer_index;
 
 	union surface_update_flags update_flags;
+	bool flip_int_enabled;
 	/* private to DC core */
 	struct dc_plane_status status;
 	struct dc_context *ctx;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index 9e796dfeac20..714c71a5fbde 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -1257,6 +1257,16 @@ void hubp1_soft_reset(struct hubp *hubp, bool reset)
 	REG_UPDATE(DCHUBP_CNTL, HUBP_DISABLE, reset ? 1 : 0);
 }
 
+void hubp1_set_flip_int(struct hubp *hubp)
+{
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+
+	REG_UPDATE(DCSURF_SURFACE_FLIP_INTERRUPT,
+		SURFACE_FLIP_INT_MASK, 1);
+
+	return;
+}
+
 void hubp1_init(struct hubp *hubp)
 {
 	//do nothing
@@ -1290,6 +1300,7 @@ static const struct hubp_funcs dcn10_hubp_funcs = {
 	.dmdata_load = NULL,
 	.hubp_soft_reset = hubp1_soft_reset,
 	.hubp_in_blank = hubp1_in_blank,
+	.hubp_set_flip_int = hubp1_set_flip_int,
 };
 
 /*****************************************/
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
index a9a6ed7f4f99..e2f2f6995935 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -74,6 +74,7 @@
 	SRI(DCSURF_SURFACE_EARLIEST_INUSE_C, HUBPREQ, id),\
 	SRI(DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C, HUBPREQ, id),\
 	SRI(DCSURF_SURFACE_CONTROL, HUBPREQ, id),\
+	SRI(DCSURF_SURFACE_FLIP_INTERRUPT, HUBPREQ, id),\
 	SRI(HUBPRET_CONTROL, HUBPRET, id),\
 	SRI(DCN_EXPANSION_MODE, HUBPREQ, id),\
 	SRI(DCHUBP_REQ_SIZE_CONFIG, HUBP, id),\
@@ -183,6 +184,7 @@
 	uint32_t DCSURF_SURFACE_EARLIEST_INUSE_C; \
 	uint32_t DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C; \
 	uint32_t DCSURF_SURFACE_CONTROL; \
+	uint32_t DCSURF_SURFACE_FLIP_INTERRUPT; \
 	uint32_t HUBPRET_CONTROL; \
 	uint32_t DCN_EXPANSION_MODE; \
 	uint32_t DCHUBP_REQ_SIZE_CONFIG; \
@@ -332,6 +334,7 @@
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_META_SURFACE_TMZ_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_EN, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_64B_BLK, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_FLIP_INTERRUPT, SURFACE_FLIP_INT_MASK, mask_sh),\
 	HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\
 	HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\
 	HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\
@@ -531,6 +534,7 @@
 	type PRIMARY_SURFACE_DCC_IND_64B_BLK;\
 	type SECONDARY_SURFACE_DCC_EN;\
 	type SECONDARY_SURFACE_DCC_IND_64B_BLK;\
+	type SURFACE_FLIP_INT_MASK;\
 	type DET_BUF_PLANE1_BASE_ADDRESS;\
 	type CROSSBAR_SRC_CB_B;\
 	type CROSSBAR_SRC_CR_R;\
@@ -777,4 +781,6 @@ void hubp1_read_state_common(struct hubp *hubp);
 bool hubp1_in_blank(struct hubp *hubp);
 void hubp1_soft_reset(struct hubp *hubp, bool reset);
 
+void hubp1_set_flip_int(struct hubp *hubp);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 89912bb5014f..9ba5c624770d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2196,6 +2196,13 @@ static void dcn10_enable_plane(
 	if (dc->debug.sanity_checks) {
 		hws->funcs.verify_allow_pstate_change_high(dc);
 	}
+
+	if (!pipe_ctx->top_pipe
+		&& pipe_ctx->plane_state
+		&& pipe_ctx->plane_state->flip_int_enabled
+		&& pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int)
+			pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int(pipe_ctx->plane_res.hubp);
+
 }
 
 void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
index 0df0da2e6a4d..bec7059f6d5d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -1597,6 +1597,7 @@ static struct hubp_funcs dcn20_hubp_funcs = {
 	.validate_dml_output = hubp2_validate_dml_output,
 	.hubp_in_blank = hubp1_in_blank,
 	.hubp_soft_reset = hubp1_soft_reset,
+	.hubp_set_flip_int = hubp1_set_flip_int,
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 0726fb435e2a..5342c309b78c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1146,6 +1146,12 @@ void dcn20_enable_plane(
 		pipe_ctx->plane_res.hubp->funcs->hubp_set_vm_system_aperture_settings(pipe_ctx->plane_res.hubp, &apt);
 	}
 
+	if (!pipe_ctx->top_pipe
+		&& pipe_ctx->plane_state
+		&& pipe_ctx->plane_state->flip_int_enabled
+		&& pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int)
+			pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int(pipe_ctx->plane_res.hubp);
+
 //	if (dc->debug.sanity_checks) {
 //		dcn10_verify_allow_pstate_change_high(dc);
 //	}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
index f9045852728f..b0c9180b808f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
@@ -838,6 +838,7 @@ static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_set_flip_control_surface_gsl = hubp2_set_flip_control_surface_gsl,
 	.hubp_init = hubp21_init,
 	.validate_dml_output = hubp21_validate_dml_output,
+	.hubp_set_flip_int = hubp1_set_flip_int,
 };
 
 bool hubp21_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
index 88ffa9ff1ed1..f24612523248 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
@@ -511,6 +511,7 @@ static struct hubp_funcs dcn30_hubp_funcs = {
 	.hubp_init = hubp3_init,
 	.hubp_in_blank = hubp1_in_blank,
 	.hubp_soft_reset = hubp1_soft_reset,
+	.hubp_set_flip_int = hubp1_set_flip_int,
 };
 
 bool hubp3_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 22f3f643ed1b..346dcd87dc10 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -191,6 +191,8 @@ struct hubp_funcs {
 	bool (*hubp_in_blank)(struct hubp *hubp);
 	void (*hubp_soft_reset)(struct hubp *hubp, bool reset);
 
+	void (*hubp_set_flip_int)(struct hubp *hubp);
+
 };
 
 #endif

From b0075d114c33580f5c9fa9cee8e13d06db41471b Mon Sep 17 00:00:00 2001
From: Sung Lee <sung.lee@amd.com>
Date: Fri, 26 Feb 2021 13:20:43 -0500
Subject: [PATCH 0621/1820] drm/amd/display: Revert dram_clock_change_latency
 for DCN2.1

[WHY & HOW]
Using values provided by DF for latency may cause hangs in
multi display configurations. Revert change to previous value.

Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Sung Lee <sung.lee@amd.com>
Reviewed-by: Haonan Wang <Haonan.Wang2@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index 94ee2cab26b7..173488ab787a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -296,7 +296,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = {
 	.num_banks = 8,
 	.num_chans = 4,
 	.vmm_page_size_bytes = 4096,
-	.dram_clock_change_latency_us = 11.72,
+	.dram_clock_change_latency_us = 23.84,
 	.return_bus_width_bytes = 64,
 	.dispclk_dppclk_vco_speed_mhz = 3600,
 	.xfc_bus_transport_time_us = 4,

From d2c91285958a3e77db99c352c136af4243f8f529 Mon Sep 17 00:00:00 2001
From: Dillon Varone <dillon.varone@amd.com>
Date: Fri, 19 Feb 2021 18:15:30 -0500
Subject: [PATCH 0622/1820] drm/amd/display: Enabled pipe harvesting in dcn30

[Why & How]
Ported logic from dcn21 for reading in pipe fusing to dcn30.
Supported configurations are 1 and 6 pipes. Invalid fusing
will revert to 1 pipe being enabled.

Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Dillon Varone <dillon.varone@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dcn30/dcn30_resource.c | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index 8d0f663489ac..fb7f1dea3c46 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -2508,6 +2508,19 @@ static const struct resource_funcs dcn30_res_pool_funcs = {
 	.patch_unknown_plane_state = dcn20_patch_unknown_plane_state,
 };
 
+#define CTX ctx
+
+#define REG(reg_name) \
+	(DCN_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name)
+
+static uint32_t read_pipe_fuses(struct dc_context *ctx)
+{
+	uint32_t value = REG_READ(CC_DC_PIPE_DIS);
+	/* Support for max 6 pipes */
+	value = value & 0x3f;
+	return value;
+}
+
 static bool dcn30_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
@@ -2517,6 +2530,15 @@ static bool dcn30_resource_construct(
 	struct dc_context *ctx = dc->ctx;
 	struct irq_service_init_data init_data;
 	struct ddc_service_init_data ddc_init_data;
+	uint32_t pipe_fuses = read_pipe_fuses(ctx);
+	uint32_t num_pipes = 0;
+
+	if (!(pipe_fuses == 0 || pipe_fuses == 0x3e)) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: Unexpected fuse recipe for navi2x !\n");
+		/* fault to single pipe */
+		pipe_fuses = 0x3e;
+	}
 
 	DC_FP_START();
 
@@ -2650,6 +2672,15 @@ static bool dcn30_resource_construct(
 	/* PP Lib and SMU interfaces */
 	init_soc_bounding_box(dc, pool);
 
+	num_pipes = dcn3_0_ip.max_num_dpp;
+
+	for (i = 0; i < dcn3_0_ip.max_num_dpp; i++)
+		if (pipe_fuses & 1 << i)
+			num_pipes--;
+
+	dcn3_0_ip.max_num_dpp = num_pipes;
+	dcn3_0_ip.max_num_otg = num_pipes;
+
 	dml_init_instance(&dc->dml, &dcn3_0_soc, &dcn3_0_ip, DML_PROJECT_DCN30);
 
 	/* IRQ */

From eda29602f1a8b2b32d8c8c354232d9d1ee1c064d Mon Sep 17 00:00:00 2001
From: Zhan Liu <zhan.liu@amd.com>
Date: Mon, 8 Mar 2021 20:28:22 -0500
Subject: [PATCH 0623/1820] drm/amdgpu/display: Use wm_table.entries for dcn301
 calculate_wm

[Why]
For DGPU Navi, the wm_table.nv_entries are used. These entires are not
populated for DCN301 Vangogh APU, but instead wm_table.entries are.

[How]
Use DCN21 Renoir style wm calculations.

Signed-off-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Zhan Liu <zhan.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Zhan Liu <zhan.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/dcn301/dcn301_resource.c   | 96 ++++++++++++++++++-
 1 file changed, 95 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
index 5d4b2c60192e..c494235016e0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
@@ -1619,12 +1619,106 @@ static void dcn301_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *b
 	dml_init_instance(&dc->dml, &dcn3_01_soc, &dcn3_01_ip, DML_PROJECT_DCN30);
 }
 
+static void calculate_wm_set_for_vlevel(
+		int vlevel,
+		struct wm_range_table_entry *table_entry,
+		struct dcn_watermarks *wm_set,
+		struct display_mode_lib *dml,
+		display_e2e_pipe_params_st *pipes,
+		int pipe_cnt)
+{
+	double dram_clock_change_latency_cached = dml->soc.dram_clock_change_latency_us;
+
+	ASSERT(vlevel < dml->soc.num_states);
+	/* only pipe 0 is read for voltage and dcf/soc clocks */
+	pipes[0].clks_cfg.voltage = vlevel;
+	pipes[0].clks_cfg.dcfclk_mhz = dml->soc.clock_limits[vlevel].dcfclk_mhz;
+	pipes[0].clks_cfg.socclk_mhz = dml->soc.clock_limits[vlevel].socclk_mhz;
+
+	dml->soc.dram_clock_change_latency_us = table_entry->pstate_latency_us;
+	dml->soc.sr_exit_time_us = table_entry->sr_exit_time_us;
+	dml->soc.sr_enter_plus_exit_time_us = table_entry->sr_enter_plus_exit_time_us;
+
+	wm_set->urgent_ns = get_wm_urgent(dml, pipes, pipe_cnt) * 1000;
+	wm_set->cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(dml, pipes, pipe_cnt) * 1000;
+	wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000;
+	wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000;
+	wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000;
+	wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000;
+	wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000;
+	wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000;
+	dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached;
+
+}
+
+static void dcn301_calculate_wm_and_dlg(
+		struct dc *dc, struct dc_state *context,
+		display_e2e_pipe_params_st *pipes,
+		int pipe_cnt,
+		int vlevel_req)
+{
+	int i, pipe_idx;
+	int vlevel, vlevel_max;
+	struct wm_range_table_entry *table_entry;
+	struct clk_bw_params *bw_params = dc->clk_mgr->bw_params;
+
+	ASSERT(bw_params);
+
+	vlevel_max = bw_params->clk_table.num_entries - 1;
+
+	/* WM Set D */
+	table_entry = &bw_params->wm_table.entries[WM_D];
+	if (table_entry->wm_type == WM_TYPE_RETRAINING)
+		vlevel = 0;
+	else
+		vlevel = vlevel_max;
+	calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.d,
+						&context->bw_ctx.dml, pipes, pipe_cnt);
+	/* WM Set C */
+	table_entry = &bw_params->wm_table.entries[WM_C];
+	vlevel = min(max(vlevel_req, 2), vlevel_max);
+	calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.c,
+						&context->bw_ctx.dml, pipes, pipe_cnt);
+	/* WM Set B */
+	table_entry = &bw_params->wm_table.entries[WM_B];
+	vlevel = min(max(vlevel_req, 1), vlevel_max);
+	calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.b,
+						&context->bw_ctx.dml, pipes, pipe_cnt);
+
+	/* WM Set A */
+	table_entry = &bw_params->wm_table.entries[WM_A];
+	vlevel = min(vlevel_req, vlevel_max);
+	calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.a,
+						&context->bw_ctx.dml, pipes, pipe_cnt);
+
+	for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) {
+		if (!context->res_ctx.pipe_ctx[i].stream)
+			continue;
+
+		pipes[pipe_idx].clks_cfg.dispclk_mhz = get_dispclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt);
+		pipes[pipe_idx].clks_cfg.dppclk_mhz = get_dppclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
+
+		if (dc->config.forced_clocks) {
+			pipes[pipe_idx].clks_cfg.dispclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dispclk_mhz;
+			pipes[pipe_idx].clks_cfg.dppclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dppclk_mhz;
+		}
+		if (dc->debug.min_disp_clk_khz > pipes[pipe_idx].clks_cfg.dispclk_mhz * 1000)
+			pipes[pipe_idx].clks_cfg.dispclk_mhz = dc->debug.min_disp_clk_khz / 1000.0;
+		if (dc->debug.min_dpp_clk_khz > pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000)
+			pipes[pipe_idx].clks_cfg.dppclk_mhz = dc->debug.min_dpp_clk_khz / 1000.0;
+
+		pipe_idx++;
+	}
+
+	dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);
+}
+
 static struct resource_funcs dcn301_res_pool_funcs = {
 	.destroy = dcn301_destroy_resource_pool,
 	.link_enc_create = dcn301_link_encoder_create,
 	.panel_cntl_create = dcn301_panel_cntl_create,
 	.validate_bandwidth = dcn30_validate_bandwidth,
-	.calculate_wm_and_dlg = dcn30_calculate_wm_and_dlg,
+	.calculate_wm_and_dlg = dcn301_calculate_wm_and_dlg,
 	.populate_dml_pipes = dcn30_populate_dml_pipes_from_context,
 	.acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer,
 	.add_stream_to_ctx = dcn30_add_stream_to_ctx,

From 521f04f9e3ffc73ef96c776035f8a0a31b4cdd81 Mon Sep 17 00:00:00 2001
From: Nirmoy Das <nirmoy.das@amd.com>
Date: Mon, 8 Mar 2021 15:22:22 +0100
Subject: [PATCH 0624/1820] drm/amdgpu: fb BO should be ttm_bo_type_device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

FB BO should not be ttm_bo_type_kernel type and
amdgpufb_create_pinned_object() pins the FB BO anyway.

Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 51cd49c6f38f..24010cacf7d0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -146,7 +146,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 	size = mode_cmd->pitches[0] * height;
 	aligned_size = ALIGN(size, PAGE_SIZE);
 	ret = amdgpu_gem_object_create(adev, aligned_size, 0, domain, flags,
-				       ttm_bo_type_kernel, NULL, &gobj);
+				       ttm_bo_type_device, NULL, &gobj);
 	if (ret) {
 		pr_err("failed to allocate framebuffer (%d)\n", aligned_size);
 		return -ENOMEM;

From 50ceb1fe7acd50831180f4b5597bf7b39e8059c8 Mon Sep 17 00:00:00 2001
From: Kenneth Feng <kenneth.feng@amd.com>
Date: Tue, 9 Mar 2021 21:10:16 +0800
Subject: [PATCH 0625/1820] drm/amd/pm: bug fix for pcie dpm

Currently the pcie dpm has two problems.
1. Only the high dpm level speed/width can be overrided
if the requested values are out of the pcie capability.
2. The high dpm level is always overrided though sometimes
it's not necesarry.

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 .../drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 48 ++++++++++++++
 .../drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c | 66 +++++++++++++++++++
 .../drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c | 48 ++++++++------
 3 files changed, 141 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
index 29c99642d22d..22b636e2b89b 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@@ -1505,6 +1505,48 @@ static int vega10_populate_single_lclk_level(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
+static int vega10_override_pcie_parameters(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+	struct vega10_hwmgr *data =
+			(struct vega10_hwmgr *)(hwmgr->backend);
+	uint32_t pcie_gen = 0, pcie_width = 0;
+	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+	int i;
+
+	if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4)
+		pcie_gen = 3;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
+		pcie_gen = 2;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2)
+		pcie_gen = 1;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1)
+		pcie_gen = 0;
+
+	if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
+		pcie_width = 6;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12)
+		pcie_width = 5;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8)
+		pcie_width = 4;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4)
+		pcie_width = 3;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2)
+		pcie_width = 2;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1)
+		pcie_width = 1;
+
+	for (i = 0; i < NUM_LINK_LEVELS; i++) {
+		if (pp_table->PcieGenSpeed[i] > pcie_gen)
+			pp_table->PcieGenSpeed[i] = pcie_gen;
+
+		if (pp_table->PcieLaneCount[i] > pcie_width)
+			pp_table->PcieLaneCount[i] = pcie_width;
+	}
+
+	return 0;
+}
+
 static int vega10_populate_smc_link_levels(struct pp_hwmgr *hwmgr)
 {
 	int result = -1;
@@ -2556,6 +2598,11 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr)
 			"Failed to initialize Link Level!",
 			return result);
 
+	result = vega10_override_pcie_parameters(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to override pcie parameters!",
+			return result);
+
 	result = vega10_populate_all_graphic_levels(hwmgr);
 	PP_ASSERT_WITH_CODE(!result,
 			"Failed to initialize Graphics Level!",
@@ -2922,6 +2969,7 @@ static int vega10_start_dpm(struct pp_hwmgr *hwmgr, uint32_t bitmap)
 	return 0;
 }
 
+
 static int vega10_enable_disable_PCC_limit_feature(struct pp_hwmgr *hwmgr, bool enable)
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
index c0753029a8e2..43e01d880f7c 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
@@ -481,6 +481,67 @@ static void vega12_init_dpm_state(struct vega12_dpm_state *dpm_state)
 	dpm_state->hard_max_level = 0xffff;
 }
 
+static int vega12_override_pcie_parameters(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+	uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg, pcie_gen_arg, pcie_width_arg;
+	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+	int i;
+	int ret;
+
+	if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4)
+		pcie_gen = 3;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
+		pcie_gen = 2;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2)
+		pcie_gen = 1;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1)
+		pcie_gen = 0;
+
+	if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
+		pcie_width = 6;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12)
+		pcie_width = 5;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8)
+		pcie_width = 4;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4)
+		pcie_width = 3;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2)
+		pcie_width = 2;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1)
+		pcie_width = 1;
+
+	/* Bit 31:16: LCLK DPM level. 0 is DPM0, and 1 is DPM1
+	 * Bit 15:8:  PCIE GEN, 0 to 3 corresponds to GEN1 to GEN4
+	 * Bit 7:0:   PCIE lane width, 1 to 7 corresponds is x1 to x32
+	 */
+	for (i = 0; i < NUM_LINK_LEVELS; i++) {
+		pcie_gen_arg = (pp_table->PcieGenSpeed[i] > pcie_gen) ? pcie_gen :
+			pp_table->PcieGenSpeed[i];
+		pcie_width_arg = (pp_table->PcieLaneCount[i] > pcie_width) ? pcie_width :
+			pp_table->PcieLaneCount[i];
+
+		if (pcie_gen_arg != pp_table->PcieGenSpeed[i] || pcie_width_arg !=
+		    pp_table->PcieLaneCount[i]) {
+			smu_pcie_arg = (i << 16) | (pcie_gen_arg << 8) | pcie_width_arg;
+			ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+				PPSMC_MSG_OverridePcieParameters, smu_pcie_arg,
+				NULL);
+			PP_ASSERT_WITH_CODE(!ret,
+				"[OverridePcieParameters] Attempt to override pcie params failed!",
+				return ret);
+		}
+
+		/* update the pptable */
+		pp_table->PcieGenSpeed[i] = pcie_gen_arg;
+		pp_table->PcieLaneCount[i] = pcie_width_arg;
+	}
+
+	return 0;
+}
+
 static int vega12_get_number_of_dpm_level(struct pp_hwmgr *hwmgr,
 		PPCLK_e clk_id, uint32_t *num_of_levels)
 {
@@ -968,6 +1029,11 @@ static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 			"Failed to enable all smu features!",
 			return result);
 
+	result = vega12_override_pcie_parameters(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"[EnableDPMTasks] Failed to override pcie parameters!",
+			return result);
+
 	tmp_result = vega12_power_control_set_level(hwmgr);
 	PP_ASSERT_WITH_CODE(!tmp_result,
 			"Failed to power control set level!",
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
index 87811b005b85..f19964c69a00 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
@@ -831,7 +831,9 @@ static int vega20_override_pcie_parameters(struct pp_hwmgr *hwmgr)
 	struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
 	struct vega20_hwmgr *data =
 			(struct vega20_hwmgr *)(hwmgr->backend);
-	uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg;
+	uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg, pcie_gen_arg, pcie_width_arg;
+	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+	int i;
 	int ret;
 
 	if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4)
@@ -860,17 +862,27 @@ static int vega20_override_pcie_parameters(struct pp_hwmgr *hwmgr)
 	 * Bit 15:8:  PCIE GEN, 0 to 3 corresponds to GEN1 to GEN4
 	 * Bit 7:0:   PCIE lane width, 1 to 7 corresponds is x1 to x32
 	 */
-	smu_pcie_arg = (1 << 16) | (pcie_gen << 8) | pcie_width;
-	ret = smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_OverridePcieParameters, smu_pcie_arg,
-			NULL);
-	PP_ASSERT_WITH_CODE(!ret,
-		"[OverridePcieParameters] Attempt to override pcie params failed!",
-		return ret);
+	for (i = 0; i < NUM_LINK_LEVELS; i++) {
+		pcie_gen_arg = (pp_table->PcieGenSpeed[i] > pcie_gen) ? pcie_gen :
+			pp_table->PcieGenSpeed[i];
+		pcie_width_arg = (pp_table->PcieLaneCount[i] > pcie_width) ? pcie_width :
+			pp_table->PcieLaneCount[i];
 
-	data->pcie_parameters_override = true;
-	data->pcie_gen_level1 = pcie_gen;
-	data->pcie_width_level1 = pcie_width;
+		if (pcie_gen_arg != pp_table->PcieGenSpeed[i] || pcie_width_arg !=
+		    pp_table->PcieLaneCount[i]) {
+			smu_pcie_arg = (i << 16) | (pcie_gen_arg << 8) | pcie_width_arg;
+			ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+				PPSMC_MSG_OverridePcieParameters, smu_pcie_arg,
+				NULL);
+			PP_ASSERT_WITH_CODE(!ret,
+				"[OverridePcieParameters] Attempt to override pcie params failed!",
+				return ret);
+		}
+
+		/* update the pptable */
+		pp_table->PcieGenSpeed[i] = pcie_gen_arg;
+		pp_table->PcieLaneCount[i] = pcie_width_arg;
+	}
 
 	return 0;
 }
@@ -3319,9 +3331,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 			data->od8_settings.od8_settings_array;
 	OverDriveTable_t *od_table =
 			&(data->smc_state_table.overdrive_table);
-	struct phm_ppt_v3_information *pptable_information =
-		(struct phm_ppt_v3_information *)hwmgr->pptable;
-	PPTable_t *pptable = (PPTable_t *)pptable_information->smc_pptable;
+	PPTable_t *pptable = &(data->smc_state_table.pp_table);
 	struct pp_clock_levels_with_latency clocks;
 	struct vega20_single_dpm_table *fclk_dpm_table =
 			&(data->dpm_table.fclk_table);
@@ -3420,13 +3430,9 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		current_lane_width =
 			vega20_get_current_pcie_link_width_level(hwmgr);
 		for (i = 0; i < NUM_LINK_LEVELS; i++) {
-			if (i == 1 && data->pcie_parameters_override) {
-				gen_speed = data->pcie_gen_level1;
-				lane_width = data->pcie_width_level1;
-			} else {
-				gen_speed = pptable->PcieGenSpeed[i];
-				lane_width = pptable->PcieLaneCount[i];
-			}
+			gen_speed = pptable->PcieGenSpeed[i];
+			lane_width = pptable->PcieLaneCount[i];
+
 			size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i,
 					(gen_speed == 0) ? "2.5GT/s," :
 					(gen_speed == 1) ? "5.0GT/s," :

From 48123d068fcb584838ce29912660c5e9490bad0e Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Fri, 5 Mar 2021 14:21:26 +0800
Subject: [PATCH 0626/1820] drm/amd/pm: correct the watermark settings for
 Polaris

The "/ 10" should be applied to the right-hand operand instead of
the left-hand one.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Noticed-by: Georgios Toptsidis <gtoptsid@gmail.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index c57dc9ae81f2..a2681fe875ed 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -5216,10 +5216,10 @@ static int smu7_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 		for (j = 0; j < dep_sclk_table->count; j++) {
 			valid_entry = false;
 			for (k = 0; k < watermarks->num_wm_sets; k++) {
-				if (dep_sclk_table->entries[i].clk / 10 >= watermarks->wm_clk_ranges[k].wm_min_eng_clk_in_khz &&
-				    dep_sclk_table->entries[i].clk / 10 < watermarks->wm_clk_ranges[k].wm_max_eng_clk_in_khz &&
-				    dep_mclk_table->entries[i].clk / 10 >= watermarks->wm_clk_ranges[k].wm_min_mem_clk_in_khz &&
-				    dep_mclk_table->entries[i].clk / 10 < watermarks->wm_clk_ranges[k].wm_max_mem_clk_in_khz) {
+				if (dep_sclk_table->entries[i].clk >= watermarks->wm_clk_ranges[k].wm_min_eng_clk_in_khz / 10 &&
+				    dep_sclk_table->entries[i].clk < watermarks->wm_clk_ranges[k].wm_max_eng_clk_in_khz / 10 &&
+				    dep_mclk_table->entries[i].clk >= watermarks->wm_clk_ranges[k].wm_min_mem_clk_in_khz / 10 &&
+				    dep_mclk_table->entries[i].clk < watermarks->wm_clk_ranges[k].wm_max_mem_clk_in_khz / 10) {
 					valid_entry = true;
 					table->DisplayWatermark[i][j] = watermarks->wm_clk_ranges[k].wm_set_id;
 					break;

From a25955ba123499d7db520175c6be59c29f9215e3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Mon, 8 Mar 2021 19:35:14 +0100
Subject: [PATCH 0627/1820] drm/radeon: also init GEM funcs in
 radeon_gem_prime_import_sg_table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Otherwise we will run into a NULL ptr deref.

Signed-off-by: Christian König <christian.koenig@amd.com>
Bug: https://bugzilla.kernel.org/show_bug.cgi?id=212137
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 5.11.x
---
 drivers/gpu/drm/radeon/radeon.h       | 2 ++
 drivers/gpu/drm/radeon/radeon_gem.c   | 4 ++--
 drivers/gpu/drm/radeon/radeon_prime.c | 2 ++
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index f09989bdce98..3effc8c71494 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -574,6 +574,8 @@ struct radeon_gem {
 	struct list_head	objects;
 };
 
+extern const struct drm_gem_object_funcs radeon_gem_object_funcs;
+
 int radeon_gem_init(struct radeon_device *rdev);
 void radeon_gem_fini(struct radeon_device *rdev);
 int radeon_gem_object_create(struct radeon_device *rdev, unsigned long size,
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 941826923247..db14a82a2e4b 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -43,7 +43,7 @@ struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj);
 int radeon_gem_prime_pin(struct drm_gem_object *obj);
 void radeon_gem_prime_unpin(struct drm_gem_object *obj);
 
-static const struct drm_gem_object_funcs radeon_gem_object_funcs;
+const struct drm_gem_object_funcs radeon_gem_object_funcs;
 
 static void radeon_gem_object_free(struct drm_gem_object *gobj)
 {
@@ -227,7 +227,7 @@ static int radeon_gem_handle_lockup(struct radeon_device *rdev, int r)
 	return r;
 }
 
-static const struct drm_gem_object_funcs radeon_gem_object_funcs = {
+const struct drm_gem_object_funcs radeon_gem_object_funcs = {
 	.free = radeon_gem_object_free,
 	.open = radeon_gem_object_open,
 	.close = radeon_gem_object_close,
diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c
index ab29eb9e8667..42a87948e28c 100644
--- a/drivers/gpu/drm/radeon/radeon_prime.c
+++ b/drivers/gpu/drm/radeon/radeon_prime.c
@@ -56,6 +56,8 @@ struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev,
 	if (ret)
 		return ERR_PTR(ret);
 
+	bo->tbo.base.funcs = &radeon_gem_object_funcs;
+
 	mutex_lock(&rdev->gem.mutex);
 	list_add_tail(&bo->list, &rdev->gem.objects);
 	mutex_unlock(&rdev->gem.mutex);

From cba2afb65cb05c3d197d17323fee4e3c9edef9cd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Mon, 8 Mar 2021 19:22:13 +0100
Subject: [PATCH 0628/1820] drm/radeon: fix AGP dependency
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When AGP is compiled as module radeon must be compiled as module as
well.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 8bf103de1594..19fc4ce62a94 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -225,6 +225,7 @@ source "drivers/gpu/drm/arm/Kconfig"
 config DRM_RADEON
 	tristate "ATI Radeon"
 	depends on DRM && PCI && MMU
+	depends on AGP || !AGP
 	select FW_LOADER
         select DRM_KMS_HELPER
         select DRM_TTM

From a5cb3c1a36376c25cd25fd3e99918dc48ac420bb Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 9 Mar 2021 22:58:47 -0500
Subject: [PATCH 0629/1820] drm/amdgpu: fix S0ix handling when the
 CONFIG_AMD_PMC=m

Need to check the module variant as well.

Acked-by: Prike Liang <Prike.Liang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 36a741d63ddc..2e9b16fb3fcd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -903,7 +903,7 @@ void amdgpu_acpi_fini(struct amdgpu_device *adev)
  */
 bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev)
 {
-#if defined(CONFIG_AMD_PMC)
+#if defined(CONFIG_AMD_PMC) || defined(CONFIG_AMD_PMC_MODULE)
 	if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) {
 		if (adev->flags & AMD_IS_APU)
 			return true;

From 25da4618af240fbec6112401498301a6f2bc9702 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Sat, 6 Mar 2021 17:18:32 +0100
Subject: [PATCH 0630/1820] xen/events: don't unmask an event channel when an
 eoi is pending

An event channel should be kept masked when an eoi is pending for it.
When being migrated to another cpu it might be unmasked, though.

In order to avoid this keep three different flags for each event channel
to be able to distinguish "normal" masking/unmasking from eoi related
masking/unmasking and temporary masking. The event channel should only
be able to generate an interrupt if all flags are cleared.

Cc: stable@vger.kernel.org
Fixes: 54c9de89895e ("xen/events: add a new "late EOI" evtchn framework")
Reported-by: Julien Grall <julien@xen.org>
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Julien Grall <jgrall@amazon.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Tested-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Link: https://lore.kernel.org/r/20210306161833.4552-3-jgross@suse.com

[boris -- corrected Fixed tag format]

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/events/events_2l.c       |   7 --
 drivers/xen/events/events_base.c     | 101 +++++++++++++++++++++------
 drivers/xen/events/events_fifo.c     |   7 --
 drivers/xen/events/events_internal.h |   6 --
 4 files changed, 80 insertions(+), 41 deletions(-)

diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c
index a7f413c5c190..b8f2f971c2f0 100644
--- a/drivers/xen/events/events_2l.c
+++ b/drivers/xen/events/events_2l.c
@@ -77,12 +77,6 @@ static bool evtchn_2l_is_pending(evtchn_port_t port)
 	return sync_test_bit(port, BM(&s->evtchn_pending[0]));
 }
 
-static bool evtchn_2l_test_and_set_mask(evtchn_port_t port)
-{
-	struct shared_info *s = HYPERVISOR_shared_info;
-	return sync_test_and_set_bit(port, BM(&s->evtchn_mask[0]));
-}
-
 static void evtchn_2l_mask(evtchn_port_t port)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
@@ -376,7 +370,6 @@ static const struct evtchn_ops evtchn_ops_2l = {
 	.clear_pending     = evtchn_2l_clear_pending,
 	.set_pending       = evtchn_2l_set_pending,
 	.is_pending        = evtchn_2l_is_pending,
-	.test_and_set_mask = evtchn_2l_test_and_set_mask,
 	.mask              = evtchn_2l_mask,
 	.unmask            = evtchn_2l_unmask,
 	.handle_events     = evtchn_2l_handle_events,
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 7e23808892a7..b27c012c86b5 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -98,13 +98,18 @@ struct irq_info {
 	short refcnt;
 	u8 spurious_cnt;
 	u8 is_accounted;
-	enum xen_irq_type type; /* type */
+	short type;		/* type: IRQT_* */
+	u8 mask_reason;		/* Why is event channel masked */
+#define EVT_MASK_REASON_EXPLICIT	0x01
+#define EVT_MASK_REASON_TEMPORARY	0x02
+#define EVT_MASK_REASON_EOI_PENDING	0x04
 	unsigned irq;
 	evtchn_port_t evtchn;   /* event channel */
 	unsigned short cpu;     /* cpu bound */
 	unsigned short eoi_cpu; /* EOI must happen on this cpu-1 */
 	unsigned int irq_epoch; /* If eoi_cpu valid: irq_epoch of event */
 	u64 eoi_time;           /* Time in jiffies when to EOI. */
+	spinlock_t lock;
 
 	union {
 		unsigned short virq;
@@ -154,6 +159,7 @@ static DEFINE_RWLOCK(evtchn_rwlock);
  *   evtchn_rwlock
  *     IRQ-desc lock
  *       percpu eoi_list_lock
+ *         irq_info->lock
  */
 
 static LIST_HEAD(xen_irq_list_head);
@@ -304,6 +310,8 @@ static int xen_irq_info_common_setup(struct irq_info *info,
 	info->irq = irq;
 	info->evtchn = evtchn;
 	info->cpu = cpu;
+	info->mask_reason = EVT_MASK_REASON_EXPLICIT;
+	spin_lock_init(&info->lock);
 
 	ret = set_evtchn_to_irq(evtchn, irq);
 	if (ret < 0)
@@ -459,6 +467,34 @@ unsigned int cpu_from_evtchn(evtchn_port_t evtchn)
 	return ret;
 }
 
+static void do_mask(struct irq_info *info, u8 reason)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->lock, flags);
+
+	if (!info->mask_reason)
+		mask_evtchn(info->evtchn);
+
+	info->mask_reason |= reason;
+
+	spin_unlock_irqrestore(&info->lock, flags);
+}
+
+static void do_unmask(struct irq_info *info, u8 reason)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->lock, flags);
+
+	info->mask_reason &= ~reason;
+
+	if (!info->mask_reason)
+		unmask_evtchn(info->evtchn);
+
+	spin_unlock_irqrestore(&info->lock, flags);
+}
+
 #ifdef CONFIG_X86
 static bool pirq_check_eoi_map(unsigned irq)
 {
@@ -605,7 +641,7 @@ static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious)
 	}
 
 	info->eoi_time = 0;
-	unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_EOI_PENDING);
 }
 
 static void xen_irq_lateeoi_worker(struct work_struct *work)
@@ -850,7 +886,8 @@ static unsigned int __startup_pirq(unsigned int irq)
 		goto err;
 
 out:
-	unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_EXPLICIT);
+
 	eoi_pirq(irq_get_irq_data(irq));
 
 	return 0;
@@ -877,7 +914,7 @@ static void shutdown_pirq(struct irq_data *data)
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
-	mask_evtchn(evtchn);
+	do_mask(info, EVT_MASK_REASON_EXPLICIT);
 	xen_evtchn_close(evtchn);
 	xen_irq_info_cleanup(info);
 }
@@ -1721,10 +1758,10 @@ void rebind_evtchn_irq(evtchn_port_t evtchn, int irq)
 }
 
 /* Rebind an evtchn so that it gets delivered to a specific cpu */
-static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu)
+static int xen_rebind_evtchn_to_cpu(struct irq_info *info, unsigned int tcpu)
 {
 	struct evtchn_bind_vcpu bind_vcpu;
-	int masked;
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return -1;
@@ -1740,7 +1777,7 @@ static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu)
 	 * Mask the event while changing the VCPU binding to prevent
 	 * it being delivered on an unexpected VCPU.
 	 */
-	masked = test_and_set_mask(evtchn);
+	do_mask(info, EVT_MASK_REASON_TEMPORARY);
 
 	/*
 	 * If this fails, it usually just indicates that we're dealing with a
@@ -1750,8 +1787,7 @@ static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu)
 	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
 		bind_evtchn_to_cpu(evtchn, tcpu, false);
 
-	if (!masked)
-		unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 
 	return 0;
 }
@@ -1790,7 +1826,7 @@ static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 	unsigned int tcpu = select_target_cpu(dest);
 	int ret;
 
-	ret = xen_rebind_evtchn_to_cpu(evtchn_from_irq(data->irq), tcpu);
+	ret = xen_rebind_evtchn_to_cpu(info_for_irq(data->irq), tcpu);
 	if (!ret)
 		irq_data_update_effective_affinity(data, cpumask_of(tcpu));
 
@@ -1799,18 +1835,20 @@ static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 
 static void enable_dynirq(struct irq_data *data)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		unmask_evtchn(evtchn);
+		do_unmask(info, EVT_MASK_REASON_EXPLICIT);
 }
 
 static void disable_dynirq(struct irq_data *data)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		mask_evtchn(evtchn);
+		do_mask(info, EVT_MASK_REASON_EXPLICIT);
 }
 
 static void ack_dynirq(struct irq_data *data)
@@ -1829,18 +1867,39 @@ static void mask_ack_dynirq(struct irq_data *data)
 	ack_dynirq(data);
 }
 
+static void lateeoi_ack_dynirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
+
+	if (VALID_EVTCHN(evtchn)) {
+		do_mask(info, EVT_MASK_REASON_EOI_PENDING);
+		clear_evtchn(evtchn);
+	}
+}
+
+static void lateeoi_mask_ack_dynirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
+
+	if (VALID_EVTCHN(evtchn)) {
+		do_mask(info, EVT_MASK_REASON_EXPLICIT);
+		clear_evtchn(evtchn);
+	}
+}
+
 static int retrigger_dynirq(struct irq_data *data)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
-	int masked;
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return 0;
 
-	masked = test_and_set_mask(evtchn);
+	do_mask(info, EVT_MASK_REASON_TEMPORARY);
 	set_evtchn(evtchn);
-	if (!masked)
-		unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 
 	return 1;
 }
@@ -2054,8 +2113,8 @@ static struct irq_chip xen_lateeoi_chip __read_mostly = {
 	.irq_mask		= disable_dynirq,
 	.irq_unmask		= enable_dynirq,
 
-	.irq_ack		= mask_ack_dynirq,
-	.irq_mask_ack		= mask_ack_dynirq,
+	.irq_ack		= lateeoi_ack_dynirq,
+	.irq_mask_ack		= lateeoi_mask_ack_dynirq,
 
 	.irq_set_affinity	= set_affinity_irq,
 	.irq_retrigger		= retrigger_dynirq,
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index b234f1766810..ad9fe51d3fb3 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -209,12 +209,6 @@ static bool evtchn_fifo_is_pending(evtchn_port_t port)
 	return sync_test_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
 }
 
-static bool evtchn_fifo_test_and_set_mask(evtchn_port_t port)
-{
-	event_word_t *word = event_word_from_port(port);
-	return sync_test_and_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
-}
-
 static void evtchn_fifo_mask(evtchn_port_t port)
 {
 	event_word_t *word = event_word_from_port(port);
@@ -423,7 +417,6 @@ static const struct evtchn_ops evtchn_ops_fifo = {
 	.clear_pending     = evtchn_fifo_clear_pending,
 	.set_pending       = evtchn_fifo_set_pending,
 	.is_pending        = evtchn_fifo_is_pending,
-	.test_and_set_mask = evtchn_fifo_test_and_set_mask,
 	.mask              = evtchn_fifo_mask,
 	.unmask            = evtchn_fifo_unmask,
 	.handle_events     = evtchn_fifo_handle_events,
diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h
index 18a4090d0709..4d3398eff9cd 100644
--- a/drivers/xen/events/events_internal.h
+++ b/drivers/xen/events/events_internal.h
@@ -21,7 +21,6 @@ struct evtchn_ops {
 	void (*clear_pending)(evtchn_port_t port);
 	void (*set_pending)(evtchn_port_t port);
 	bool (*is_pending)(evtchn_port_t port);
-	bool (*test_and_set_mask)(evtchn_port_t port);
 	void (*mask)(evtchn_port_t port);
 	void (*unmask)(evtchn_port_t port);
 
@@ -84,11 +83,6 @@ static inline bool test_evtchn(evtchn_port_t port)
 	return evtchn_ops->is_pending(port);
 }
 
-static inline bool test_and_set_mask(evtchn_port_t port)
-{
-	return evtchn_ops->test_and_set_mask(port);
-}
-
 static inline void mask_evtchn(evtchn_port_t port)
 {
 	return evtchn_ops->mask(port);

From b6622798bc50b625a1e62f82c7190df40c1f5b21 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Sat, 6 Mar 2021 17:18:33 +0100
Subject: [PATCH 0631/1820] xen/events: avoid handling the same event on two
 cpus at the same time

When changing the cpu affinity of an event it can happen today that
(with some unlucky timing) the same event will be handled on the old
and the new cpu at the same time.

Avoid that by adding an "event active" flag to the per-event data and
call the handler only if this flag isn't set.

Cc: stable@vger.kernel.org
Reported-by: Julien Grall <julien@xen.org>
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Julien Grall <jgrall@amazon.com>
Link: https://lore.kernel.org/r/20210306161833.4552-4-jgross@suse.com
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/events/events_base.c | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index b27c012c86b5..8236e2364eeb 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -103,6 +103,7 @@ struct irq_info {
 #define EVT_MASK_REASON_EXPLICIT	0x01
 #define EVT_MASK_REASON_TEMPORARY	0x02
 #define EVT_MASK_REASON_EOI_PENDING	0x04
+	u8 is_active;		/* Is event just being handled? */
 	unsigned irq;
 	evtchn_port_t evtchn;   /* event channel */
 	unsigned short cpu;     /* cpu bound */
@@ -810,6 +811,12 @@ static void xen_evtchn_close(evtchn_port_t port)
 		BUG();
 }
 
+static void event_handler_exit(struct irq_info *info)
+{
+	smp_store_release(&info->is_active, 0);
+	clear_evtchn(info->evtchn);
+}
+
 static void pirq_query_unmask(int irq)
 {
 	struct physdev_irq_status_query irq_status;
@@ -828,14 +835,15 @@ static void pirq_query_unmask(int irq)
 
 static void eoi_pirq(struct irq_data *data)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 	struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
 	int rc = 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
-	clear_evtchn(evtchn);
+	event_handler_exit(info);
 
 	if (pirq_needs_eoi(data->irq)) {
 		rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
@@ -1666,6 +1674,8 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl)
 	}
 
 	info = info_for_irq(irq);
+	if (xchg_acquire(&info->is_active, 1))
+		return;
 
 	dev = (info->type == IRQT_EVTCHN) ? info->u.interdomain : NULL;
 	if (dev)
@@ -1853,12 +1863,11 @@ static void disable_dynirq(struct irq_data *data)
 
 static void ack_dynirq(struct irq_data *data)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
-	if (!VALID_EVTCHN(evtchn))
-		return;
-
-	clear_evtchn(evtchn);
+	if (VALID_EVTCHN(evtchn))
+		event_handler_exit(info);
 }
 
 static void mask_ack_dynirq(struct irq_data *data)
@@ -1874,7 +1883,7 @@ static void lateeoi_ack_dynirq(struct irq_data *data)
 
 	if (VALID_EVTCHN(evtchn)) {
 		do_mask(info, EVT_MASK_REASON_EOI_PENDING);
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 	}
 }
 
@@ -1885,7 +1894,7 @@ static void lateeoi_mask_ack_dynirq(struct irq_data *data)
 
 	if (VALID_EVTCHN(evtchn)) {
 		do_mask(info, EVT_MASK_REASON_EXPLICIT);
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 	}
 }
 
@@ -1998,10 +2007,11 @@ static void restore_cpu_ipis(unsigned int cpu)
 /* Clear an irq's pending state, in preparation for polling on it */
 void xen_clear_irq_pending(int irq)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(irq);
+	struct irq_info *info = info_for_irq(irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 }
 EXPORT_SYMBOL(xen_clear_irq_pending);
 void xen_set_irq_pending(int irq)

From 0f9b05b9a01a4cf6b6bdf904faacf4796e2aa232 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@suse.com>
Date: Tue, 9 Mar 2021 18:00:44 +0100
Subject: [PATCH 0632/1820] Xen: drop exports of
 {set,clear}_foreign_p2m_mapping()

They're only used internally, and the layering violation they contain
(x86) or imply (Arm) of calling HYPERVISOR_grant_table_op() strongly
advise against any (uncontrolled) use from a module. The functions also
never had users except the ones from drivers/xen/grant-table.c forever
since their introduction in 3.15.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Link: https://lore.kernel.org/r/746a5cd6-1446-eda4-8b23-03c1cac30b8d@suse.com
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/arm/xen/p2m.c | 2 --
 arch/x86/xen/p2m.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c
index acb464547a54..5316cf36cb57 100644
--- a/arch/arm/xen/p2m.c
+++ b/arch/arm/xen/p2m.c
@@ -130,7 +130,6 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
 
 int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 			      struct gnttab_unmap_grant_ref *kunmap_ops,
@@ -145,7 +144,6 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);
 
 bool __set_phys_to_machine_multi(unsigned long pfn,
 		unsigned long mfn, unsigned long nr_pages)
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index a3cc33091f46..e912992e0b77 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -776,7 +776,6 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 out:
 	return ret;
 }
-EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
 
 int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 			      struct gnttab_unmap_grant_ref *kunmap_ops,
@@ -802,7 +801,6 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);
 
 #ifdef CONFIG_XEN_DEBUG_FS
 #include <linux/debugfs.h>

From 36caa3fedf06d377bd08bc91b50c93fb9022f5ec Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@suse.com>
Date: Wed, 10 Mar 2021 11:45:00 +0100
Subject: [PATCH 0633/1820] Xen/gntdev: don't needlessly allocate
 k{,un}map_ops[]

They're needed only in the not-auto-translate (i.e. PV) case; there's no
point in allocating memory that's never going to get accessed.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/180d50cb-5531-8952-4bf0-d65c554638ed@suse.com
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/gntdev.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 5447c5156b2e..b60ebd8bdb26 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -136,17 +136,20 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 	add->grants    = kvcalloc(count, sizeof(add->grants[0]), GFP_KERNEL);
 	add->map_ops   = kvcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
 	add->unmap_ops = kvcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
-	add->kmap_ops  = kvcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
-	add->kunmap_ops = kvcalloc(count,
-				   sizeof(add->kunmap_ops[0]), GFP_KERNEL);
 	add->pages     = kvcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
 	if (NULL == add->grants    ||
 	    NULL == add->map_ops   ||
 	    NULL == add->unmap_ops ||
-	    NULL == add->kmap_ops  ||
-	    NULL == add->kunmap_ops ||
 	    NULL == add->pages)
 		goto err;
+	if (use_ptemod) {
+		add->kmap_ops   = kvcalloc(count, sizeof(add->kmap_ops[0]),
+					   GFP_KERNEL);
+		add->kunmap_ops = kvcalloc(count, sizeof(add->kunmap_ops[0]),
+					   GFP_KERNEL);
+		if (NULL == add->kmap_ops || NULL == add->kunmap_ops)
+			goto err;
+	}
 
 #ifdef CONFIG_XEN_GRANT_DMA_ALLOC
 	add->dma_flags = dma_flags;
@@ -185,8 +188,10 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 	for (i = 0; i < count; i++) {
 		add->map_ops[i].handle = -1;
 		add->unmap_ops[i].handle = -1;
-		add->kmap_ops[i].handle = -1;
-		add->kunmap_ops[i].handle = -1;
+		if (use_ptemod) {
+			add->kmap_ops[i].handle = -1;
+			add->kunmap_ops[i].handle = -1;
+		}
 	}
 
 	add->index = 0;
@@ -332,8 +337,8 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 	}
 
 	pr_debug("map %d+%d\n", map->index, map->count);
-	err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL,
-			map->pages, map->count);
+	err = gnttab_map_refs(map->map_ops, map->kmap_ops, map->pages,
+			map->count);
 
 	for (i = 0; i < map->count; i++) {
 		if (map->map_ops[i].status == GNTST_okay)

From bce21a2b48ede7cbcab92db18bc956daf1d5c246 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@suse.com>
Date: Wed, 10 Mar 2021 11:45:26 +0100
Subject: [PATCH 0634/1820] Xen/gnttab: introduce common
 INVALID_GRANT_{HANDLE,REF}

It's not helpful if every driver has to cook its own. Generalize
xenbus'es INVALID_GRANT_HANDLE and pcifront's INVALID_GRANT_REF (which
shouldn't have expanded to zero to begin with). Use the constants in
p2m.c and gntdev.c right away, and update field types where necessary so
they would match with the constants' types (albeit without touching
struct ioctl_gntdev_grant_ref's ref field, as that's part of the public
interface of the kernel and would require introducing a dependency on
Xen's grant_table.h public header).

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/db7c38a5-0d75-d5d1-19de-e5fe9f0b9c48@suse.com
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/arm/xen/p2m.c         |  3 ++-
 arch/x86/xen/p2m.c         |  4 ++--
 drivers/pci/xen-pcifront.c |  4 ++--
 drivers/xen/gntdev.c       | 24 +++++++++++++-----------
 include/xen/grant_table.h  |  7 +++++++
 include/xen/xenbus.h       |  1 -
 6 files changed, 26 insertions(+), 17 deletions(-)

diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c
index 5316cf36cb57..84a1cea1f43b 100644
--- a/arch/arm/xen/p2m.c
+++ b/arch/arm/xen/p2m.c
@@ -11,6 +11,7 @@
 
 #include <xen/xen.h>
 #include <xen/interface/memory.h>
+#include <xen/grant_table.h>
 #include <xen/page.h>
 #include <xen/swiotlb-xen.h>
 
@@ -109,7 +110,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 		map_ops[i].status = GNTST_general_error;
 		unmap.host_addr = map_ops[i].host_addr,
 		unmap.handle = map_ops[i].handle;
-		map_ops[i].handle = ~0;
+		map_ops[i].handle = INVALID_GRANT_HANDLE;
 		if (map_ops[i].flags & GNTMAP_device_map)
 			unmap.dev_bus_addr = map_ops[i].dev_bus_addr;
 		else
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index e912992e0b77..17d80f751fcb 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -741,7 +741,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 		map_ops[i].status = GNTST_general_error;
 		unmap[0].host_addr = map_ops[i].host_addr,
 		unmap[0].handle = map_ops[i].handle;
-		map_ops[i].handle = ~0;
+		map_ops[i].handle = INVALID_GRANT_HANDLE;
 		if (map_ops[i].flags & GNTMAP_device_map)
 			unmap[0].dev_bus_addr = map_ops[i].dev_bus_addr;
 		else
@@ -751,7 +751,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 			kmap_ops[i].status = GNTST_general_error;
 			unmap[1].host_addr = kmap_ops[i].host_addr,
 			unmap[1].handle = kmap_ops[i].handle;
-			kmap_ops[i].handle = ~0;
+			kmap_ops[i].handle = INVALID_GRANT_HANDLE;
 			if (kmap_ops[i].flags & GNTMAP_device_map)
 				unmap[1].dev_bus_addr = kmap_ops[i].dev_bus_addr;
 			else
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index c6fe0cfec0f6..2d7502648219 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -26,7 +26,7 @@
 #include <xen/platform_pci.h>
 
 #include <asm/xen/swiotlb-xen.h>
-#define INVALID_GRANT_REF (0)
+
 #define INVALID_EVTCHN    (-1)
 
 struct pci_bus_entry {
@@ -42,7 +42,7 @@ struct pcifront_device {
 	struct list_head root_buses;
 
 	int evtchn;
-	int gnt_ref;
+	grant_ref_t gnt_ref;
 
 	int irq;
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index b60ebd8bdb26..ebfd3e7b20d4 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -186,11 +186,11 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 		goto err;
 
 	for (i = 0; i < count; i++) {
-		add->map_ops[i].handle = -1;
-		add->unmap_ops[i].handle = -1;
+		add->map_ops[i].handle = INVALID_GRANT_HANDLE;
+		add->unmap_ops[i].handle = INVALID_GRANT_HANDLE;
 		if (use_ptemod) {
-			add->kmap_ops[i].handle = -1;
-			add->kunmap_ops[i].handle = -1;
+			add->kmap_ops[i].handle = INVALID_GRANT_HANDLE;
+			add->kunmap_ops[i].handle = INVALID_GRANT_HANDLE;
 		}
 	}
 
@@ -279,7 +279,7 @@ static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data)
 			  map->grants[pgnr].ref,
 			  map->grants[pgnr].domid);
 	gnttab_set_unmap_op(&map->unmap_ops[pgnr], pte_maddr, flags,
-			    -1 /* handle */);
+			    INVALID_GRANT_HANDLE);
 	return 0;
 }
 
@@ -297,7 +297,7 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 
 	if (!use_ptemod) {
 		/* Note: it could already be mapped */
-		if (map->map_ops[0].handle != -1)
+		if (map->map_ops[0].handle != INVALID_GRANT_HANDLE)
 			return 0;
 		for (i = 0; i < map->count; i++) {
 			unsigned long addr = (unsigned long)
@@ -306,7 +306,7 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 				map->grants[i].ref,
 				map->grants[i].domid);
 			gnttab_set_unmap_op(&map->unmap_ops[i], addr,
-				map->flags, -1 /* handle */);
+				map->flags, INVALID_GRANT_HANDLE);
 		}
 	} else {
 		/*
@@ -332,7 +332,7 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 				map->grants[i].ref,
 				map->grants[i].domid);
 			gnttab_set_unmap_op(&map->kunmap_ops[i], address,
-				flags, -1);
+				flags, INVALID_GRANT_HANDLE);
 		}
 	}
 
@@ -390,7 +390,7 @@ static int __unmap_grant_pages(struct gntdev_grant_map *map, int offset,
 		pr_debug("unmap handle=%d st=%d\n",
 			map->unmap_ops[offset+i].handle,
 			map->unmap_ops[offset+i].status);
-		map->unmap_ops[offset+i].handle = -1;
+		map->unmap_ops[offset+i].handle = INVALID_GRANT_HANDLE;
 	}
 	return err;
 }
@@ -406,13 +406,15 @@ static int unmap_grant_pages(struct gntdev_grant_map *map, int offset,
 	 * already unmapped some of the grants. Only unmap valid ranges.
 	 */
 	while (pages && !err) {
-		while (pages && map->unmap_ops[offset].handle == -1) {
+		while (pages &&
+		       map->unmap_ops[offset].handle == INVALID_GRANT_HANDLE) {
 			offset++;
 			pages--;
 		}
 		range = 0;
 		while (range < pages) {
-			if (map->unmap_ops[offset+range].handle == -1)
+			if (map->unmap_ops[offset + range].handle ==
+			    INVALID_GRANT_HANDLE)
 				break;
 			range++;
 		}
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index 0b1182a3cf41..cb854df031ce 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -50,6 +50,13 @@
 #include <linux/page-flags.h>
 #include <linux/kernel.h>
 
+/*
+ * Technically there's no reliably invalid grant reference or grant handle,
+ * so pick the value that is the most unlikely one to be observed valid.
+ */
+#define INVALID_GRANT_REF          ((grant_ref_t)-1)
+#define INVALID_GRANT_HANDLE       ((grant_handle_t)-1)
+
 #define GNTTAB_RESERVED_XENSTORE 1
 
 /* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index 0b1386073d49..b94074c82772 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -51,7 +51,6 @@
 
 #define XENBUS_MAX_RING_GRANT_ORDER 4
 #define XENBUS_MAX_RING_GRANTS      (1U << XENBUS_MAX_RING_GRANT_ORDER)
-#define INVALID_GRANT_HANDLE       (~0U)
 
 /* Register callback to watch this node. */
 struct xenbus_watch

From f1d20d8643e54dcde242fd2c8748063ed75702a8 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@suse.com>
Date: Wed, 10 Mar 2021 11:46:13 +0100
Subject: [PATCH 0635/1820] Xen/gntdev: don't needlessly use kvcalloc()

Requesting zeroed memory when all of it will be overwritten subsequently
by all ones is a waste of processing bandwidth. In fact, rather than
recording zeroed ->grants[], fill that array too with more appropriate
"invalid" indicators.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/9a726be2-4893-8ffe-0ef1-b70dd1c229b1@suse.com
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/gntdev.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index ebfd3e7b20d4..f01d58c7a042 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -133,9 +133,12 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 	if (NULL == add)
 		return NULL;
 
-	add->grants    = kvcalloc(count, sizeof(add->grants[0]), GFP_KERNEL);
-	add->map_ops   = kvcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
-	add->unmap_ops = kvcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
+	add->grants    = kvmalloc_array(count, sizeof(add->grants[0]),
+					GFP_KERNEL);
+	add->map_ops   = kvmalloc_array(count, sizeof(add->map_ops[0]),
+					GFP_KERNEL);
+	add->unmap_ops = kvmalloc_array(count, sizeof(add->unmap_ops[0]),
+					GFP_KERNEL);
 	add->pages     = kvcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
 	if (NULL == add->grants    ||
 	    NULL == add->map_ops   ||
@@ -143,10 +146,10 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 	    NULL == add->pages)
 		goto err;
 	if (use_ptemod) {
-		add->kmap_ops   = kvcalloc(count, sizeof(add->kmap_ops[0]),
-					   GFP_KERNEL);
-		add->kunmap_ops = kvcalloc(count, sizeof(add->kunmap_ops[0]),
-					   GFP_KERNEL);
+		add->kmap_ops   = kvmalloc_array(count, sizeof(add->kmap_ops[0]),
+						 GFP_KERNEL);
+		add->kunmap_ops = kvmalloc_array(count, sizeof(add->kunmap_ops[0]),
+						 GFP_KERNEL);
 		if (NULL == add->kmap_ops || NULL == add->kunmap_ops)
 			goto err;
 	}
@@ -186,6 +189,8 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 		goto err;
 
 	for (i = 0; i < count; i++) {
+		add->grants[i].domid = DOMID_INVALID;
+		add->grants[i].ref = INVALID_GRANT_REF;
 		add->map_ops[i].handle = INVALID_GRANT_HANDLE;
 		add->unmap_ops[i].handle = INVALID_GRANT_HANDLE;
 		if (use_ptemod) {

From 2a9be38099e338f597c14d3cb851849b01db05f6 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 4 Mar 2021 14:48:16 -0500
Subject: [PATCH 0636/1820] pinctrl: qcom: lpass lpi: use default
 pullup/strength values

If these fields are not set in dts, the driver will use these variables
uninitialized to set the fields. Not only will it set garbage values for
these fields, but it can overflow into other fields and break those.

In the current sm8250 dts, the dmic01 entries do not have a pullup setting,
and might not work without this change.

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: 6e261d1090d6 ("pinctrl: qcom: Add sm8250 lpass lpi pinctrl driver")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20210304194816.3843-1-jonathan@marek.ca
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-lpass-lpi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
index 369ee20a7ea9..2f19ab4db720 100644
--- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
@@ -392,7 +392,7 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group,
 			  unsigned long *configs, unsigned int nconfs)
 {
 	struct lpi_pinctrl *pctrl = dev_get_drvdata(pctldev->dev);
-	unsigned int param, arg, pullup, strength;
+	unsigned int param, arg, pullup = LPI_GPIO_BIAS_DISABLE, strength = 2;
 	bool value, output_enabled = false;
 	const struct lpi_pingroup *g;
 	unsigned long sval;

From 9398e9c0b1d44eeb700e9e766c02bcc765c82570 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 10 Mar 2021 12:28:01 +0200
Subject: [PATCH 0637/1820] drop_monitor: Perform cleanup upon probe
 registration failure

In the rare case that drop_monitor fails to register its probe on the
'napi_poll' tracepoint, it will not deactivate its hysteresis timer as
part of the error path. If the hysteresis timer was armed by the shortly
lived 'kfree_skb' probe and user space retries to initiate tracing, a
warning will be emitted for trying to initialize an active object [1].

Fix this by properly undoing all the operations that were done prior to
probe registration, in both software and hardware code paths.

Note that syzkaller managed to fail probe registration by injecting a
slab allocation failure [2].

[1]
ODEBUG: init active (active state 0) object type: timer_list hint: sched_send_work+0x0/0x60 include/linux/list.h:135
WARNING: CPU: 1 PID: 8649 at lib/debugobjects.c:505 debug_print_object+0x16e/0x250 lib/debugobjects.c:505
Modules linked in:
CPU: 1 PID: 8649 Comm: syz-executor.0 Not tainted 5.11.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:debug_print_object+0x16e/0x250 lib/debugobjects.c:505
[...]
Call Trace:
 __debug_object_init+0x524/0xd10 lib/debugobjects.c:588
 debug_timer_init kernel/time/timer.c:722 [inline]
 debug_init kernel/time/timer.c:770 [inline]
 init_timer_key+0x2d/0x340 kernel/time/timer.c:814
 net_dm_trace_on_set net/core/drop_monitor.c:1111 [inline]
 set_all_monitor_traces net/core/drop_monitor.c:1188 [inline]
 net_dm_monitor_start net/core/drop_monitor.c:1295 [inline]
 net_dm_cmd_trace+0x720/0x1220 net/core/drop_monitor.c:1339
 genl_family_rcv_msg_doit+0x228/0x320 net/netlink/genetlink.c:739
 genl_family_rcv_msg net/netlink/genetlink.c:783 [inline]
 genl_rcv_msg+0x328/0x580 net/netlink/genetlink.c:800
 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2502
 genl_rcv+0x24/0x40 net/netlink/genetlink.c:811
 netlink_unicast_kernel net/netlink/af_netlink.c:1312 [inline]
 netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1338
 netlink_sendmsg+0x856/0xd90 net/netlink/af_netlink.c:1927
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x6e8/0x810 net/socket.c:2348
 ___sys_sendmsg+0xf3/0x170 net/socket.c:2402
 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2435
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xae

[2]
 FAULT_INJECTION: forcing a failure.
 name failslab, interval 1, probability 0, space 0, times 1
 CPU: 1 PID: 8645 Comm: syz-executor.0 Not tainted 5.11.0-syzkaller #0
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
 Call Trace:
  dump_stack+0xfa/0x151
  should_fail.cold+0x5/0xa
  should_failslab+0x5/0x10
  __kmalloc+0x72/0x3f0
  tracepoint_add_func+0x378/0x990
  tracepoint_probe_register+0x9c/0xe0
  net_dm_cmd_trace+0x7fc/0x1220
  genl_family_rcv_msg_doit+0x228/0x320
  genl_rcv_msg+0x328/0x580
  netlink_rcv_skb+0x153/0x420
  genl_rcv+0x24/0x40
  netlink_unicast+0x533/0x7d0
  netlink_sendmsg+0x856/0xd90
  sock_sendmsg+0xcf/0x120
  ____sys_sendmsg+0x6e8/0x810
  ___sys_sendmsg+0xf3/0x170
  __sys_sendmsg+0xe5/0x1b0
  do_syscall_64+0x2d/0x70
  entry_SYSCALL_64_after_hwframe+0x44/0xae

Fixes: 70c69274f354 ("drop_monitor: Initialize timer and work item upon tracing enable")
Fixes: 8ee2267ad33e ("drop_monitor: Convert to using devlink tracepoint")
Reported-by: syzbot+779559d6503f3a56213d@syzkaller.appspotmail.com
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/drop_monitor.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 571f191c06d9..db65ce62b625 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -1053,6 +1053,20 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack)
 	return 0;
 
 err_module_put:
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu);
+		struct sk_buff *skb;
+
+		del_timer_sync(&hw_data->send_timer);
+		cancel_work_sync(&hw_data->dm_alert_work);
+		while ((skb = __skb_dequeue(&hw_data->drop_queue))) {
+			struct devlink_trap_metadata *hw_metadata;
+
+			hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata;
+			net_dm_hw_metadata_free(hw_metadata);
+			consume_skb(skb);
+		}
+	}
 	module_put(THIS_MODULE);
 	return rc;
 }
@@ -1134,6 +1148,15 @@ static int net_dm_trace_on_set(struct netlink_ext_ack *extack)
 err_unregister_trace:
 	unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL);
 err_module_put:
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu);
+		struct sk_buff *skb;
+
+		del_timer_sync(&data->send_timer);
+		cancel_work_sync(&data->dm_alert_work);
+		while ((skb = __skb_dequeue(&data->drop_queue)))
+			consume_skb(skb);
+	}
 	module_put(THIS_MODULE);
 	return rc;
 }

From dd4fa1dae9f4847cc1fd78ca468ad69e16e5db3e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 10 Mar 2021 01:56:36 -0800
Subject: [PATCH 0638/1820] macvlan: macvlan_count_rx() needs to be aware of
 preemption

macvlan_count_rx() can be called from process context, it is thus
necessary to disable preemption before calling u64_stats_update_begin()

syzbot was able to spot this on 32bit arch:

WARNING: CPU: 1 PID: 4632 at include/linux/seqlock.h:271 __seqprop_assert include/linux/seqlock.h:271 [inline]
WARNING: CPU: 1 PID: 4632 at include/linux/seqlock.h:271 __seqprop_assert.constprop.0+0xf0/0x11c include/linux/seqlock.h:269
Modules linked in:
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 4632 Comm: kworker/1:3 Not tainted 5.12.0-rc2-syzkaller #0
Hardware name: ARM-Versatile Express
Workqueue: events macvlan_process_broadcast
Backtrace:
[<82740468>] (dump_backtrace) from [<827406dc>] (show_stack+0x18/0x1c arch/arm/kernel/traps.c:252)
 r7:00000080 r6:60000093 r5:00000000 r4:8422a3c4
[<827406c4>] (show_stack) from [<82751b58>] (__dump_stack lib/dump_stack.c:79 [inline])
[<827406c4>] (show_stack) from [<82751b58>] (dump_stack+0xb8/0xe8 lib/dump_stack.c:120)
[<82751aa0>] (dump_stack) from [<82741270>] (panic+0x130/0x378 kernel/panic.c:231)
 r7:830209b4 r6:84069ea4 r5:00000000 r4:844350d0
[<82741140>] (panic) from [<80244924>] (__warn+0xb0/0x164 kernel/panic.c:605)
 r3:8404ec8c r2:00000000 r1:00000000 r0:830209b4
 r7:0000010f
[<80244874>] (__warn) from [<82741520>] (warn_slowpath_fmt+0x68/0xd4 kernel/panic.c:628)
 r7:81363f70 r6:0000010f r5:83018e50 r4:00000000
[<827414bc>] (warn_slowpath_fmt) from [<81363f70>] (__seqprop_assert include/linux/seqlock.h:271 [inline])
[<827414bc>] (warn_slowpath_fmt) from [<81363f70>] (__seqprop_assert.constprop.0+0xf0/0x11c include/linux/seqlock.h:269)
 r8:5a109000 r7:0000000f r6:a568dac0 r5:89802300 r4:00000001
[<81363e80>] (__seqprop_assert.constprop.0) from [<81364af0>] (u64_stats_update_begin include/linux/u64_stats_sync.h:128 [inline])
[<81363e80>] (__seqprop_assert.constprop.0) from [<81364af0>] (macvlan_count_rx include/linux/if_macvlan.h:47 [inline])
[<81363e80>] (__seqprop_assert.constprop.0) from [<81364af0>] (macvlan_broadcast+0x154/0x26c drivers/net/macvlan.c:291)
 r5:89802300 r4:8a927740
[<8136499c>] (macvlan_broadcast) from [<81365020>] (macvlan_process_broadcast+0x258/0x2d0 drivers/net/macvlan.c:317)
 r10:81364f78 r9:8a86d000 r8:8a9c7e7c r7:8413aa5c r6:00000000 r5:00000000
 r4:89802840
[<81364dc8>] (macvlan_process_broadcast) from [<802696a4>] (process_one_work+0x2d4/0x998 kernel/workqueue.c:2275)
 r10:00000008 r9:8404ec98 r8:84367a02 r7:ddfe6400 r6:ddfe2d40 r5:898dac80
 r4:8a86d43c
[<802693d0>] (process_one_work) from [<80269dcc>] (worker_thread+0x64/0x54c kernel/workqueue.c:2421)
 r10:00000008 r9:8a9c6000 r8:84006d00 r7:ddfe2d78 r6:898dac94 r5:ddfe2d40
 r4:898dac80
[<80269d68>] (worker_thread) from [<80271f40>] (kthread+0x184/0x1a4 kernel/kthread.c:292)
 r10:85247e64 r9:898dac80 r8:80269d68 r7:00000000 r6:8a9c6000 r5:89a2ee40
 r4:8a97bd00
[<80271dbc>] (kthread) from [<80200114>] (ret_from_fork+0x14/0x20 arch/arm/kernel/entry-common.S:158)
Exception stack(0x8a9c7fb0 to 0x8a9c7ff8)

Fixes: 412ca1550cbe ("macvlan: Move broadcasts into a work queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_macvlan.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 96556c64c95d..10c94a3936ca 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -43,13 +43,14 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
 	if (likely(success)) {
 		struct vlan_pcpu_stats *pcpu_stats;
 
-		pcpu_stats = this_cpu_ptr(vlan->pcpu_stats);
+		pcpu_stats = get_cpu_ptr(vlan->pcpu_stats);
 		u64_stats_update_begin(&pcpu_stats->syncp);
 		pcpu_stats->rx_packets++;
 		pcpu_stats->rx_bytes += len;
 		if (multicast)
 			pcpu_stats->rx_multicast++;
 		u64_stats_update_end(&pcpu_stats->syncp);
+		put_cpu_ptr(vlan->pcpu_stats);
 	} else {
 		this_cpu_inc(vlan->pcpu_stats->rx_errors);
 	}

From 0571a753cb07982cc82f4a5115e0b321da89e1f3 Mon Sep 17 00:00:00 2001
From: Pavel Andrianov <andrianov@ispras.ru>
Date: Wed, 10 Mar 2021 11:10:46 +0300
Subject: [PATCH 0639/1820] net: pxa168_eth: Fix a potential data race in
 pxa168_eth_remove

pxa168_eth_remove() firstly calls unregister_netdev(),
then cancels a timeout work. unregister_netdev() shuts down a device
interface and removes it from the kernel tables. If the timeout occurs
in parallel, the timeout work (pxa168_eth_tx_timeout_task) performs stop
and open of the device. It may lead to an inconsistent state and memory
leaks.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Pavel Andrianov <andrianov@ispras.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/pxa168_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index d1e4d42e497d..3712e1786091 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1544,8 +1544,8 @@ static int pxa168_eth_remove(struct platform_device *pdev)
 	clk_disable_unprepare(pep->clk);
 	mdiobus_unregister(pep->smi_bus);
 	mdiobus_free(pep->smi_bus);
-	unregister_netdev(dev);
 	cancel_work_sync(&pep->tx_timeout_task);
+	unregister_netdev(dev);
 	free_netdev(dev);
 	return 0;
 }

From 8373a0fe9c7160a55482effa8a3f725efd3f8434 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Wed, 10 Mar 2021 13:51:59 +0100
Subject: [PATCH 0640/1820] net: dsa: bcm_sf2: use 2 Gbps IMP port link on
 BCM4908
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

BCM4908 uses 2 Gbps link between switch and the Ethernet interface.
Without this BCM4908 devices were able to achieve only 2 x ~895 Mb/s.
This allows handling e.g. NAT traffic with 940 Mb/s.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index f277df922fcd..4dedd6e0b11b 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -114,7 +114,10 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 		/* Force link status for IMP port */
 		reg = core_readl(priv, offset);
 		reg |= (MII_SW_OR | LINK_STS);
-		reg &= ~GMII_SPEED_UP_2G;
+		if (priv->type == BCM4908_DEVICE_ID)
+			reg |= GMII_SPEED_UP_2G;
+		else
+			reg &= ~GMII_SPEED_UP_2G;
 		core_writel(priv, reg, offset);
 
 		/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */

From e323d865b36134e8c5c82c834df89109a5c60dab Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 10 Mar 2021 08:26:41 -0800
Subject: [PATCH 0641/1820] net: sched: validate stab values

iproute2 package is well behaved, but malicious user space can
provide illegal shift values and trigger UBSAN reports.

Add stab parameter to red_check_params() to validate user input.

syzbot reported:

UBSAN: shift-out-of-bounds in ./include/net/red.h:312:18
shift exponent 111 is too large for 64-bit type 'long unsigned int'
CPU: 1 PID: 14662 Comm: syz-executor.3 Not tainted 5.12.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:79 [inline]
 dump_stack+0x141/0x1d7 lib/dump_stack.c:120
 ubsan_epilogue+0xb/0x5a lib/ubsan.c:148
 __ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:327
 red_calc_qavg_from_idle_time include/net/red.h:312 [inline]
 red_calc_qavg include/net/red.h:353 [inline]
 choke_enqueue.cold+0x18/0x3dd net/sched/sch_choke.c:221
 __dev_xmit_skb net/core/dev.c:3837 [inline]
 __dev_queue_xmit+0x1943/0x2e00 net/core/dev.c:4150
 neigh_hh_output include/net/neighbour.h:499 [inline]
 neigh_output include/net/neighbour.h:508 [inline]
 ip6_finish_output2+0x911/0x1700 net/ipv6/ip6_output.c:117
 __ip6_finish_output net/ipv6/ip6_output.c:182 [inline]
 __ip6_finish_output+0x4c1/0xe10 net/ipv6/ip6_output.c:161
 ip6_finish_output+0x35/0x200 net/ipv6/ip6_output.c:192
 NF_HOOK_COND include/linux/netfilter.h:290 [inline]
 ip6_output+0x1e4/0x530 net/ipv6/ip6_output.c:215
 dst_output include/net/dst.h:448 [inline]
 NF_HOOK include/linux/netfilter.h:301 [inline]
 NF_HOOK include/linux/netfilter.h:295 [inline]
 ip6_xmit+0x127e/0x1eb0 net/ipv6/ip6_output.c:320
 inet6_csk_xmit+0x358/0x630 net/ipv6/inet6_connection_sock.c:135
 dccp_transmit_skb+0x973/0x12c0 net/dccp/output.c:138
 dccp_send_reset+0x21b/0x2b0 net/dccp/output.c:535
 dccp_finish_passive_close net/dccp/proto.c:123 [inline]
 dccp_finish_passive_close+0xed/0x140 net/dccp/proto.c:118
 dccp_terminate_connection net/dccp/proto.c:958 [inline]
 dccp_close+0xb3c/0xe60 net/dccp/proto.c:1028
 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431
 inet6_release+0x4c/0x70 net/ipv6/af_inet6.c:478
 __sock_release+0xcd/0x280 net/socket.c:599
 sock_close+0x18/0x20 net/socket.c:1258
 __fput+0x288/0x920 fs/file_table.c:280
 task_work_run+0xdd/0x1a0 kernel/task_work.c:140
 tracehook_notify_resume include/linux/tracehook.h:189 [inline]

Fixes: 8afa10cbe281 ("net_sched: red: Avoid illegal values")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/red.h     | 10 +++++++++-
 net/sched/sch_choke.c |  7 ++++---
 net/sched/sch_gred.c  |  2 +-
 net/sched/sch_red.c   |  7 +++++--
 net/sched/sch_sfq.c   |  2 +-
 5 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/include/net/red.h b/include/net/red.h
index 932f0d79d60c..9e6647c4ccd1 100644
--- a/include/net/red.h
+++ b/include/net/red.h
@@ -168,7 +168,8 @@ static inline void red_set_vars(struct red_vars *v)
 	v->qcount	= -1;
 }
 
-static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_log)
+static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog,
+				    u8 Scell_log, u8 *stab)
 {
 	if (fls(qth_min) + Wlog > 32)
 		return false;
@@ -178,6 +179,13 @@ static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_
 		return false;
 	if (qth_max < qth_min)
 		return false;
+	if (stab) {
+		int i;
+
+		for (i = 0; i < RED_STAB_SIZE; i++)
+			if (stab[i] >= 32)
+				return false;
+	}
 	return true;
 }
 
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 50f680f03a54..2adbd945bf15 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -345,6 +345,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt,
 	struct sk_buff **old = NULL;
 	unsigned int mask;
 	u32 max_P;
+	u8 *stab;
 
 	if (opt == NULL)
 		return -EINVAL;
@@ -361,8 +362,8 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt,
 	max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0;
 
 	ctl = nla_data(tb[TCA_CHOKE_PARMS]);
-
-	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log))
+	stab = nla_data(tb[TCA_CHOKE_STAB]);
+	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab))
 		return -EINVAL;
 
 	if (ctl->limit > CHOKE_MAX_QUEUE)
@@ -412,7 +413,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt,
 
 	red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
 		      ctl->Plog, ctl->Scell_log,
-		      nla_data(tb[TCA_CHOKE_STAB]),
+		      stab,
 		      max_P);
 	red_set_vars(&q->vars);
 
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index e0bc77533acc..f4132dc25ac0 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -480,7 +480,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp,
 	struct gred_sched *table = qdisc_priv(sch);
 	struct gred_sched_data *q = table->tab[dp];
 
-	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) {
+	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) {
 		NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters");
 		return -EINVAL;
 	}
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index b4ae34d7aa96..40adf1f07a82 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -242,6 +242,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb,
 	unsigned char flags;
 	int err;
 	u32 max_P;
+	u8 *stab;
 
 	if (tb[TCA_RED_PARMS] == NULL ||
 	    tb[TCA_RED_STAB] == NULL)
@@ -250,7 +251,9 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb,
 	max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0;
 
 	ctl = nla_data(tb[TCA_RED_PARMS]);
-	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log))
+	stab = nla_data(tb[TCA_RED_STAB]);
+	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog,
+			      ctl->Scell_log, stab))
 		return -EINVAL;
 
 	err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS,
@@ -288,7 +291,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb,
 	red_set_parms(&q->parms,
 		      ctl->qth_min, ctl->qth_max, ctl->Wlog,
 		      ctl->Plog, ctl->Scell_log,
-		      nla_data(tb[TCA_RED_STAB]),
+		      stab,
 		      max_P);
 	red_set_vars(&q->vars);
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index b25e51440623..066754a18569 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -647,7 +647,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	}
 
 	if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max,
-					ctl_v1->Wlog, ctl_v1->Scell_log))
+					ctl_v1->Wlog, ctl_v1->Scell_log, NULL))
 		return -EINVAL;
 	if (ctl_v1 && ctl_v1->qth_min) {
 		p = kmalloc(sizeof(*p), GFP_KERNEL);

From d45c36bafb94e72fdb6dee437279b61b6d97e706 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 10 Mar 2021 10:46:10 -0800
Subject: [PATCH 0642/1820] net: dsa: b53: VLAN filtering is global to all
 users

The bcm_sf2 driver uses the b53 driver as a library but does not make
usre of the b53_setup() function, this made it fail to inherit the
vlan_filtering_is_global attribute. Fix this by moving the assignment to
b53_switch_alloc() which is used by bcm_sf2.

Fixes: 7228b23e68f7 ("net: dsa: b53: Let DSA handle mismatched VLAN filtering settings")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index a162499bcafc..eb443721c58e 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1105,13 +1105,6 @@ static int b53_setup(struct dsa_switch *ds)
 			b53_disable_port(ds, port);
 	}
 
-	/* Let DSA handle the case were multiple bridges span the same switch
-	 * device and different VLAN awareness settings are requested, which
-	 * would be breaking filtering semantics for any of the other bridge
-	 * devices. (not hardware supported)
-	 */
-	ds->vlan_filtering_is_global = true;
-
 	return b53_setup_devlink_resources(ds);
 }
 
@@ -2664,6 +2657,13 @@ struct b53_device *b53_switch_alloc(struct device *base,
 	ds->ops = &b53_switch_ops;
 	ds->untag_bridge_pvid = true;
 	dev->vlan_enabled = true;
+	/* Let DSA handle the case were multiple bridges span the same switch
+	 * device and different VLAN awareness settings are requested, which
+	 * would be breaking filtering semantics for any of the other bridge
+	 * devices. (not hardware supported)
+	 */
+	ds->vlan_filtering_is_global = true;
+
 	mutex_init(&dev->reg_mutex);
 	mutex_init(&dev->stats_mutex);
 

From 07abd8db9358751107cc46d1cdbd44a92c76a934 Mon Sep 17 00:00:00 2001
From: Rajendra Nayak <rnayak@codeaurora.org>
Date: Tue, 2 Mar 2021 10:51:50 +0530
Subject: [PATCH 0643/1820] pinctrl: qcom: sc7280: Fix SDC_QDSD_PINGROUP and
 UFS_RESET offsets

The offsets for SDC_QDSD_PINGROUP and UFS_RESET were off by 0x100000
due to an issue in the scripts generating the data.

Fixes: ecb454594c43: ("pinctrl: qcom: Add sc7280 pinctrl driver")
Reported-by: Veerabhadrarao Badiganti <vbadigan@codeaurora.org>
Signed-off-by: Rajendra Nayak <rnayak@codeaurora.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Link: https://lore.kernel.org/r/1614662511-26519-1-git-send-email-rnayak@codeaurora.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-sc7280.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280.c b/drivers/pinctrl/qcom/pinctrl-sc7280.c
index 8daccd530285..49c434788304 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7280.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7280.c
@@ -1439,14 +1439,14 @@ static const struct msm_pingroup sc7280_groups[] = {
 	[172] = PINGROUP(172, qdss, _, _, _, _, _, _, _, _),
 	[173] = PINGROUP(173, qdss, _, _, _, _, _, _, _, _),
 	[174] = PINGROUP(174, qdss, _, _, _, _, _, _, _, _),
-	[175] = UFS_RESET(ufs_reset, 0x1be000),
-	[176] = SDC_QDSD_PINGROUP(sdc1_rclk, 0x1b3000, 15, 0),
-	[177] = SDC_QDSD_PINGROUP(sdc1_clk, 0x1b3000, 13, 6),
-	[178] = SDC_QDSD_PINGROUP(sdc1_cmd, 0x1b3000, 11, 3),
-	[179] = SDC_QDSD_PINGROUP(sdc1_data, 0x1b3000, 9, 0),
-	[180] = SDC_QDSD_PINGROUP(sdc2_clk, 0x1b4000, 14, 6),
-	[181] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x1b4000, 11, 3),
-	[182] = SDC_QDSD_PINGROUP(sdc2_data, 0x1b4000, 9, 0),
+	[175] = UFS_RESET(ufs_reset, 0xbe000),
+	[176] = SDC_QDSD_PINGROUP(sdc1_rclk, 0xb3000, 15, 0),
+	[177] = SDC_QDSD_PINGROUP(sdc1_clk, 0xb3000, 13, 6),
+	[178] = SDC_QDSD_PINGROUP(sdc1_cmd, 0xb3000, 11, 3),
+	[179] = SDC_QDSD_PINGROUP(sdc1_data, 0xb3000, 9, 0),
+	[180] = SDC_QDSD_PINGROUP(sdc2_clk, 0xb4000, 14, 6),
+	[181] = SDC_QDSD_PINGROUP(sdc2_cmd, 0xb4000, 11, 3),
+	[182] = SDC_QDSD_PINGROUP(sdc2_data, 0xb4000, 9, 0),
 };
 
 static const struct msm_pinctrl_soc_data sc7280_pinctrl = {

From d0f9f47c07fe52b34e2ff8590cf09e0a9d8d6f99 Mon Sep 17 00:00:00 2001
From: Rajendra Nayak <rnayak@codeaurora.org>
Date: Tue, 2 Mar 2021 10:51:51 +0530
Subject: [PATCH 0644/1820] pinctrl: qcom: sc7280: Fix SDC1_RCLK configurations

Fix SDC1_RCLK configurations which are in a different register so fix the
offset from 0xb3000 to 0xb3004.

Fixes: ecb454594c43: ("pinctrl: qcom: Add sc7280 pinctrl driver")
Reported-by: Veerabhadrarao Badiganti <vbadigan@codeaurora.org>
Signed-off-by: Rajendra Nayak <rnayak@codeaurora.org>
Acked-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Link: https://lore.kernel.org/r/1614662511-26519-2-git-send-email-rnayak@codeaurora.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-sc7280.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280.c b/drivers/pinctrl/qcom/pinctrl-sc7280.c
index 49c434788304..9d41abfca37e 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7280.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7280.c
@@ -1440,7 +1440,7 @@ static const struct msm_pingroup sc7280_groups[] = {
 	[173] = PINGROUP(173, qdss, _, _, _, _, _, _, _, _),
 	[174] = PINGROUP(174, qdss, _, _, _, _, _, _, _, _),
 	[175] = UFS_RESET(ufs_reset, 0xbe000),
-	[176] = SDC_QDSD_PINGROUP(sdc1_rclk, 0xb3000, 15, 0),
+	[176] = SDC_QDSD_PINGROUP(sdc1_rclk, 0xb3004, 0, 6),
 	[177] = SDC_QDSD_PINGROUP(sdc1_clk, 0xb3000, 13, 6),
 	[178] = SDC_QDSD_PINGROUP(sdc1_cmd, 0xb3000, 11, 3),
 	[179] = SDC_QDSD_PINGROUP(sdc1_data, 0xb3000, 9, 0),

From 47142ed6c34d544ae9f0463e58d482289cbe0d46 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 10 Mar 2021 14:17:58 -0800
Subject: [PATCH 0645/1820] net: dsa: bcm_sf2: Qualify phydev->dev_flags based
 on port

Similar to commit 92696286f3bb37ba50e4bd8d1beb24afb759a799 ("net:
bcmgenet: Set phydev->dev_flags only for internal PHYs") we need to
qualify the phydev->dev_flags based on whether the port is connected to
an internal or external PHY otherwise we risk having a flags collision
with a completely different interpretation depending on the driver.

Fixes: aa9aef77c761 ("net: dsa: bcm_sf2: communicate integrated PHY revision to PHY driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 4dedd6e0b11b..ba5d546d06aa 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -588,8 +588,10 @@ static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port)
 	 * in bits 15:8 and the patch level in bits 7:0 which is exactly what
 	 * the REG_PHY_REVISION register layout is.
 	 */
-
-	return priv->hw_params.gphy_rev;
+	if (priv->int_phy_mask & BIT(port))
+		return priv->hw_params.gphy_rev;
+	else
+		return 0;
 }
 
 static void bcm_sf2_sw_validate(struct dsa_switch *ds, int port,

From ce6ed1c4c9876c2880f52f18c41ef2a30d070bc5 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Thu, 4 Mar 2021 20:37:08 +0900
Subject: [PATCH 0646/1820] kbuild: rebuild GCC plugins when the compiler is
 upgraded

Linus reported a build error due to the GCC plugin incompatibility
when the compiler is upgraded. [1]

GCC plugins are tied to a particular GCC version. So, they must be
rebuilt when the compiler is upgraded.

This seems to be a long-standing flaw since the initial support of
GCC plugins.

Extend commit 8b59cd81dc5e ("kbuild: ensure full rebuild when the
compiler is updated"), so that GCC plugins are covered by the
compiler upgrade detection.

[1]: https://lore.kernel.org/lkml/CAHk-=wieoN5ttOy7SnsGwZv+Fni3R6m-Ut=oxih6bbZ28G+4dw@mail.gmail.com/

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
---
 Makefile                         |  1 +
 include/linux/compiler-version.h | 14 ++++++++++++++
 include/linux/kconfig.h          |  2 --
 init/Kconfig                     |  8 ++++----
 scripts/gcc-plugins/Makefile     |  1 +
 5 files changed, 20 insertions(+), 6 deletions(-)
 create mode 100644 include/linux/compiler-version.h

diff --git a/Makefile b/Makefile
index 3f9f44eac27f..10bb0a62cc7d 100644
--- a/Makefile
+++ b/Makefile
@@ -479,6 +479,7 @@ USERINCLUDE    := \
 		-I$(objtree)/arch/$(SRCARCH)/include/generated/uapi \
 		-I$(srctree)/include/uapi \
 		-I$(objtree)/include/generated/uapi \
+                -include $(srctree)/include/linux/compiler-version.h \
                 -include $(srctree)/include/linux/kconfig.h
 
 # Use LINUXINCLUDE when you must reference the include/ directory.
diff --git a/include/linux/compiler-version.h b/include/linux/compiler-version.h
new file mode 100644
index 000000000000..2b2972c77c62
--- /dev/null
+++ b/include/linux/compiler-version.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifdef  __LINUX_COMPILER_VERSION_H
+#error "Please do not include <linux/compiler-version.h>. This is done by the build system."
+#endif
+#define __LINUX_COMPILER_VERSION_H
+
+/*
+ * This header exists to force full rebuild when the compiler is upgraded.
+ *
+ * When fixdep scans this, it will find this string "CONFIG_CC_VERSION_TEXT"
+ * and add dependency on include/config/cc/version/text.h, which is touched
+ * by Kconfig when the version string from the compiler changes.
+ */
diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h
index e78e17a76dc9..24a59cb06963 100644
--- a/include/linux/kconfig.h
+++ b/include/linux/kconfig.h
@@ -2,8 +2,6 @@
 #ifndef __LINUX_KCONFIG_H
 #define __LINUX_KCONFIG_H
 
-/* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */
-
 #include <generated/autoconf.h>
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
diff --git a/init/Kconfig b/init/Kconfig
index 22946fe5ded9..30c849094c28 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -20,10 +20,10 @@ config CC_VERSION_TEXT
 	    When the compiler is updated, Kconfig will be invoked.
 
 	  - Ensure full rebuild when the compiler is updated
-	    include/linux/kconfig.h contains this option in the comment line so
-	    fixdep adds include/config/cc/version/text.h into the auto-generated
-	    dependency. When the compiler is updated, syncconfig will touch it
-	    and then every file will be rebuilt.
+	    include/linux/compiler-version.h contains this option in the comment
+	    line so fixdep adds include/config/cc/version/text.h into the
+	    auto-generated dependency. When the compiler is updated, syncconfig
+	    will touch it and then every file will be rebuilt.
 
 config CC_IS_GCC
 	def_bool $(success,test "$(cc-name)" = GCC)
diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile
index b5487cce69e8..1952d3bb80c6 100644
--- a/scripts/gcc-plugins/Makefile
+++ b/scripts/gcc-plugins/Makefile
@@ -22,6 +22,7 @@ always-y += $(GCC_PLUGIN)
 GCC_PLUGINS_DIR = $(shell $(CC) -print-file-name=plugin)
 
 plugin_cxxflags	= -Wp,-MMD,$(depfile) $(KBUILD_HOSTCXXFLAGS) -fPIC \
+		  -include $(srctree)/include/linux/compiler-version.h \
 		   -I $(GCC_PLUGINS_DIR)/include -I $(obj) -std=gnu++11 \
 		   -fno-rtti -fno-exceptions -fasynchronous-unwind-tables \
 		   -ggdb -Wno-narrowing -Wno-unused-variable \

From 2eab791f940b98d0bdd4d1e8c4857f3dec3c7d04 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 8 Mar 2021 07:28:20 +0100
Subject: [PATCH 0647/1820] kbuild: dummy-tools: support MPROFILE_KERNEL checks
 for ppc

ppc64le checks for -mprofile-kernel to define MPROFILE_KERNEL Kconfig.
Kconfig calls arch/powerpc/tools/gcc-check-mprofile-kernel.sh for that
purpose. This script performs two checks:
1) build with -mprofile-kernel should contain "_mcount"
2) build with -mprofile-kernel with a function marked as "notrace"
   should not produce "_mcount"

So support this in dummy-tools' gcc, so that we have MPROFILE_KERNEL
always true.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/dummy-tools/gcc | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/scripts/dummy-tools/gcc b/scripts/dummy-tools/gcc
index 0d0589cf8184..7b10332b23ba 100755
--- a/scripts/dummy-tools/gcc
+++ b/scripts/dummy-tools/gcc
@@ -73,6 +73,15 @@ if arg_contain -S "$@"; then
 		echo "%gs"
 		exit 0
 	fi
+
+	# For arch/powerpc/tools/gcc-check-mprofile-kernel.sh
+	if arg_contain -m64 "$@" && arg_contain -mlittle-endian "$@" &&
+		arg_contain -mprofile-kernel "$@"; then
+		if ! test -t 0 && ! grep -q notrace; then
+			echo "_mcount"
+		fi
+		exit 0
+	fi
 fi
 
 # To set GCC_PLUGINS

From bf3c255150619b71badb328c4dab48401a7ed62d Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Mon, 8 Mar 2021 10:46:56 -0800
Subject: [PATCH 0648/1820] kbuild: Allow LTO to be selected with KASAN_HW_TAGS

While LTO with KASAN is normally not useful, hardware tag-based KASAN
can be used also in production kernels with ARM64_MTE. Therefore, allow
KASAN_HW_TAGS to be selected together with HAS_LTO_CLANG.

Reported-by: Alistair Delva <adelva@google.com>
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 arch/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index 2bb30673d8e6..2e7139b39e8f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -638,7 +638,7 @@ config HAS_LTO_CLANG
 	depends on $(success,$(AR) --help | head -n 1 | grep -qi llvm)
 	depends on ARCH_SUPPORTS_LTO_CLANG
 	depends on !FTRACE_MCOUNT_USE_RECORDMCOUNT
-	depends on !KASAN
+	depends on !KASAN || KASAN_HW_TAGS
 	depends on !GCOV_KERNEL
 	help
 	  The compiler and Kconfig options support building with Clang's

From f9bc754be475582e2cc44296f7de0aaedbdbefeb Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Wed, 10 Mar 2021 01:25:45 +0900
Subject: [PATCH 0649/1820] kbuild: dummy-tools: adjust to
 scripts/cc-version.sh

Commit aec6c60a01d3 ("kbuild: check the minimum compiler version in
Kconfig") changed how the script detects the compiler version.

Get 'make CROSS_COMPILE=scripts/dummy-tools/' back working again.

Fixes: aec6c60a01d3 ("kbuild: check the minimum compiler version in Kconfig")
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: Miguel Ojeda <ojeda@kernel.org>
---
 scripts/dummy-tools/gcc | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/dummy-tools/gcc b/scripts/dummy-tools/gcc
index 7b10332b23ba..39e65fee59bd 100755
--- a/scripts/dummy-tools/gcc
+++ b/scripts/dummy-tools/gcc
@@ -57,9 +57,9 @@ if arg_contain --version "$@"; then
 fi
 
 if arg_contain -E "$@"; then
-	# For scripts/gcc-version.sh; This emulates GCC 20.0.0
+	# For scripts/cc-version.sh; This emulates GCC 20.0.0
 	if arg_contain - "$@"; then
-		sed 's/^__GNUC__$/20/; s/^__GNUC_MINOR__$/0/; s/^__GNUC_PATCHLEVEL__$/0/'
+		sed -n '/^GCC/{s/__GNUC__/20/; s/__GNUC_MINOR__/0/; s/__GNUC_PATCHLEVEL__/0/; p;}'
 		exit 0
 	else
 		echo "no input files" >&2

From 64bfc99429a5c9613fffb0e54f2f8c2ddc8c1d04 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Wed, 10 Mar 2021 20:08:24 +0900
Subject: [PATCH 0650/1820] kbuild: remove unneeded -O option to dtc

This piece of code converts the target suffix to the dtc -O option:

    *.dtb      ->  -O dtb
    *.dt.yaml  ->  -O yaml

Commit ce88c9c79455 ("kbuild: Add support to build overlays (%.dtbo)")
added the third case:

    *.dtbo     ->  -O dtbo

This works thanks to commit 163f0469bf2e ("dtc: Allow overlays to have
.dtbo extension") in the upstream DTC, which has already been pulled in
the kernel.

However, I think it is a bit odd because "dtbo" is not a format name.
At least, it does not show up in the help message of dtc.

$ scripts/dtc/dtc --help
  [ snip ]
  -O, --out-format <arg>
        Output formats are:
                dts - device tree source text
                dtb - device tree blob
                yaml - device tree encoded as YAML
                asm - assembler source

So, I am not a big fan of the second hunk of that change:

        } else if (streq(outform, "dtbo")) {
                dt_to_blob(outf, dti, outversion);

Anyway, we did not need to do this in Makefile in the first place.

guess_type_by_name() had already understood ".yaml" before commit
4f0e3a57d6eb ("kbuild: Add support for DT binding schema checks"),
and now does ".dtbo" as well.

Makefile does not need to duplicate the same logic. Let's leave it
to dtc.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Rob Herring <robh@kernel.org>
---
 scripts/Makefile.lib | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index eee59184de64..90a4e04cd8f5 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -327,7 +327,7 @@ $(obj)/%.dtb.S: $(obj)/%.dtb FORCE
 
 quiet_cmd_dtc = DTC     $@
 cmd_dtc = $(HOSTCC) -E $(dtc_cpp_flags) -x assembler-with-cpp -o $(dtc-tmp) $< ; \
-	$(DTC) -O $(patsubst .%,%,$(suffix $@)) -o $@ -b 0 \
+	$(DTC) -o $@ -b 0 \
 		$(addprefix -i,$(dir $<) $(DTC_INCLUDE)) $(DTC_FLAGS) \
 		-d $(depfile).dtc.tmp $(dtc-tmp) ; \
 	cat $(depfile).pre.tmp $(depfile).dtc.tmp > $(depfile)

From 4c273d23c44ad49c73353737b303e78585a4503f Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Wed, 10 Mar 2021 22:54:22 +0900
Subject: [PATCH 0651/1820] kbuild: remove LLVM=1 test from HAS_LTO_CLANG

As Documentation/kbuild/llvm.rst notes, LLVM=1 switches the default of
tools, but you can still override CC, LD, etc. individually. This LLVM=1
check is unneeded because each tool is already checked separately.

"make CC=clang LD=ld.lld NM=llvm-nm AR=llvm-ar LLVM_IAS=1 menuconfig"
should be able to enable Clang LTO.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
---
 arch/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index 2e7139b39e8f..ecfd3520b676 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -632,7 +632,6 @@ config HAS_LTO_CLANG
 	def_bool y
 	# Clang >= 11: https://github.com/ClangBuiltLinux/linux/issues/510
 	depends on CC_IS_CLANG && CLANG_VERSION >= 110000 && LD_IS_LLD
-	depends on $(success,test $(LLVM) -eq 1)
 	depends on $(success,test $(LLVM_IAS) -eq 1)
 	depends on $(success,$(NM) --help | head -n 1 | grep -qi llvm)
 	depends on $(success,$(AR) --help | head -n 1 | grep -qi llvm)

From 285a65f1a10f87088cefd6c7ea6ff26b143339b3 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Thu, 11 Mar 2021 15:30:54 +0900
Subject: [PATCH 0652/1820] kbuild: remove meaningless parameter to $(call
 if_changed_rule,dtc)

This is a remnant of commit 78046fabe6e7 ("kbuild: determine the output
format of DTC by the target suffix").

The parameter "yaml" is meaningless because cmd_dtc no loner takes $(2).

Reported-by: Rob Herring <robh@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/Makefile.lib | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 90a4e04cd8f5..8cd67b1b6d15 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -352,7 +352,7 @@ define rule_dtc
 endef
 
 $(obj)/%.dt.yaml: $(src)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE
-	$(call if_changed_rule,dtc,yaml)
+	$(call if_changed_rule,dtc)
 
 dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp)
 

From 874a52f9b693ed8bf7a92b3592a547ce8a684e6f Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Sat, 27 Feb 2021 23:46:25 -0500
Subject: [PATCH 0653/1820] drm/fb-helper: only unmap if buffer not null

drm_fbdev_cleanup() can be called when fb_helper->buffer is null, hence
fb_helper->buffer should be checked before calling
drm_client_buffer_vunmap(). This buffer is also checked in
drm_client_framebuffer_delete(), so we should also do the same thing for
drm_client_buffer_vunmap().

[  199.128742] RIP: 0010:drm_client_buffer_vunmap+0xd/0x20
[  199.129031] Code: 43 18 48 8b 53 20 49 89 45 00 49 89 55 08 5b 44 89 e0 41 5c 41 5d 41 5e 5d
c3 0f 1f 00 53 48 89 fb 48 8d 7f 10 e8 73 7d a1 ff <48> 8b 7b 10 48 8d 73 18 5b e9 75 53 fc ff 0
f 1f 44 00 00 48 b8 00
[  199.130041] RSP: 0018:ffff888103f3fc88 EFLAGS: 00010282
[  199.130329] RAX: 0000000000000001 RBX: 0000000000000000 RCX: ffffffff8214d46d
[  199.130733] RDX: 1ffffffff079c6b9 RSI: 0000000000000246 RDI: ffffffff83ce35c8
[  199.131119] RBP: ffff888103d25458 R08: 0000000000000001 R09: fffffbfff0791761
[  199.131505] R10: ffffffff83c8bb07 R11: fffffbfff0791760 R12: 0000000000000000
[  199.131891] R13: ffff888103d25468 R14: ffff888103d25418 R15: ffff888103f18120
[  199.132277] FS:  00007f36fdcbb6a0(0000) GS:ffff88815b400000(0000) knlGS:0000000000000000
[  199.132721] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  199.133033] CR2: 0000000000000010 CR3: 0000000103d26000 CR4: 00000000000006f0
[  199.133420] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  199.133807] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  199.134195] Call Trace:
[  199.134333]  drm_fbdev_cleanup+0x179/0x1a0
[  199.134562]  drm_fbdev_client_unregister+0x2b/0x40
[  199.134828]  drm_client_dev_unregister+0xa8/0x180
[  199.135088]  drm_dev_unregister+0x61/0x110
[  199.135315]  mgag200_pci_remove+0x38/0x52 [mgag200]
[  199.135586]  pci_device_remove+0x62/0xe0
[  199.135806]  device_release_driver_internal+0x148/0x270
[  199.136094]  driver_detach+0x76/0xe0
[  199.136294]  bus_remove_driver+0x7e/0x100
[  199.136521]  pci_unregister_driver+0x28/0xf0
[  199.136759]  __x64_sys_delete_module+0x268/0x300
[  199.137016]  ? __ia32_sys_delete_module+0x300/0x300
[  199.137285]  ? call_rcu+0x3e4/0x580
[  199.137481]  ? fpregs_assert_state_consistent+0x4d/0x60
[  199.137767]  ? exit_to_user_mode_prepare+0x2f/0x130
[  199.138037]  do_syscall_64+0x33/0x40
[  199.138237]  entry_SYSCALL_64_after_hwframe+0x44/0xae
[  199.138517] RIP: 0033:0x7f36fdc3dcf7

Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Fixes: 763aea17bf57 ("drm/fb-helper: Unmap client buffer during shutdown")
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: dri-devel@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v5.11+
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20210228044625.171151-1-ztong0001@gmail.com
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/drm_fb_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index b9a616737c0e..f6baa2046124 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -2048,7 +2048,7 @@ static void drm_fbdev_cleanup(struct drm_fb_helper *fb_helper)
 
 	if (shadow)
 		vfree(shadow);
-	else
+	else if (fb_helper->buffer)
 		drm_client_buffer_vunmap(fb_helper->buffer);
 
 	drm_client_framebuffer_delete(fb_helper->buffer);

From e8dd3506dcf380d4cbe983422dfed1909011b02a Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Thu, 4 Feb 2021 15:57:05 +0100
Subject: [PATCH 0654/1820] drm/qxl: unpin release objects

Balances the qxl_create_bo(..., pinned=true, ...);
call in qxl_release_bo_alloc().

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: http://patchwork.freedesktop.org/patch/msgid/20210204145712.1531203-5-kraxel@redhat.com
(cherry picked from commit 65ffea3c6e738f37bb15ff3ee480415c793df893)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/qxl/qxl_release.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 0fcfc952d5e9..93b5f7ab055d 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -347,6 +347,7 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
 
 	mutex_lock(&qdev->release_mutex);
 	if (qdev->current_release_bo_offset[cur_idx] + 1 >= releases_per_bo[cur_idx]) {
+		qxl_bo_unpin(qdev->current_release_bo[cur_idx]);
 		qxl_bo_unref(&qdev->current_release_bo[cur_idx]);
 		qdev->current_release_bo_offset[cur_idx] = 0;
 		qdev->current_release_bo[cur_idx] = NULL;

From e998d3c8cba93ab4075d6bcc56b1d4451d85efe5 Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Wed, 17 Feb 2021 13:32:06 +0100
Subject: [PATCH 0655/1820] drm/qxl: fix lockdep issue in
 qxl_alloc_release_reserved

Call qxl_bo_unpin (which does a reservation) without holding the
release_mutex lock.  Fixes lockdep (correctly) warning on a possible
deadlock.

Fixes: e8dd3506dcf3 ("drm/qxl: unpin release objects")
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: http://patchwork.freedesktop.org/patch/msgid/20210217123213.2199186-5-kraxel@redhat.com
(cherry picked from commit 19089b760e56c97458c272e90e43da761b05cf12)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/qxl/qxl_release.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 93b5f7ab055d..b372455e2729 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -321,7 +321,7 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
 				       int type, struct qxl_release **release,
 				       struct qxl_bo **rbo)
 {
-	struct qxl_bo *bo;
+	struct qxl_bo *bo, *free_bo = NULL;
 	int idr_ret;
 	int ret = 0;
 	union qxl_release_info *info;
@@ -347,8 +347,7 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
 
 	mutex_lock(&qdev->release_mutex);
 	if (qdev->current_release_bo_offset[cur_idx] + 1 >= releases_per_bo[cur_idx]) {
-		qxl_bo_unpin(qdev->current_release_bo[cur_idx]);
-		qxl_bo_unref(&qdev->current_release_bo[cur_idx]);
+		free_bo = qdev->current_release_bo[cur_idx];
 		qdev->current_release_bo_offset[cur_idx] = 0;
 		qdev->current_release_bo[cur_idx] = NULL;
 	}
@@ -356,6 +355,10 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
 		ret = qxl_release_bo_alloc(qdev, &qdev->current_release_bo[cur_idx]);
 		if (ret) {
 			mutex_unlock(&qdev->release_mutex);
+			if (free_bo) {
+				qxl_bo_unpin(free_bo);
+				qxl_bo_unref(&free_bo);
+			}
 			qxl_release_free(qdev, *release);
 			return ret;
 		}
@@ -371,6 +374,10 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
 		*rbo = bo;
 
 	mutex_unlock(&qdev->release_mutex);
+	if (free_bo) {
+		qxl_bo_unpin(free_bo);
+		qxl_bo_unref(&free_bo);
+	}
 
 	ret = qxl_release_list_add(*release, bo);
 	qxl_bo_unref(&bo);

From 39a3898abf4dfb8702929832836b1f785b1c2bc4 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 24 Feb 2021 13:55:28 -0800
Subject: [PATCH 0656/1820] fbdev: atyfb: always declare aty_{ld,st}_lcd()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The previously added stubs for aty_{ld,}st_lcd() make it
so that these functions are used regardless of the config
options that were guarding them, so remove the #ifdef/#endif
lines and make their declarations always visible.
This fixes build warnings that were reported by clang:

   drivers/video/fbdev/aty/atyfb_base.c:180:6: warning: no previous prototype for function 'aty_st_lcd' [-Wmissing-prototypes]
   void aty_st_lcd(int index, u32 val, const struct atyfb_par *par)
        ^
   drivers/video/fbdev/aty/atyfb_base.c:180:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
   void aty_st_lcd(int index, u32 val, const struct atyfb_par *par)

   drivers/video/fbdev/aty/atyfb_base.c:183:5: warning: no previous prototype for function 'aty_ld_lcd' [-Wmissing-prototypes]
   u32 aty_ld_lcd(int index, const struct atyfb_par *par)
       ^
   drivers/video/fbdev/aty/atyfb_base.c:183:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
   u32 aty_ld_lcd(int index, const struct atyfb_par *par)

They should not be marked as static since they are used in
mach64_ct.c.

Fixes: bfa5782b9caa ("fbdev: atyfb: add stubs for aty_{ld,st}_lcd()")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: linux-fbdev@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: David Airlie <airlied@linux.ie>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210224215528.822-1-rdunlap@infradead.org
Acked-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/video/fbdev/aty/atyfb.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/video/fbdev/aty/atyfb.h b/drivers/video/fbdev/aty/atyfb.h
index 551372f9b9aa..465f55beb97f 100644
--- a/drivers/video/fbdev/aty/atyfb.h
+++ b/drivers/video/fbdev/aty/atyfb.h
@@ -287,11 +287,8 @@ static inline void aty_st_8(int regindex, u8 val, const struct atyfb_par *par)
 #endif
 }
 
-#if defined(CONFIG_PMAC_BACKLIGHT) || defined (CONFIG_FB_ATY_GENERIC_LCD) || \
-defined (CONFIG_FB_ATY_BACKLIGHT)
 extern void aty_st_lcd(int index, u32 val, const struct atyfb_par *par);
 extern u32 aty_ld_lcd(int index, const struct atyfb_par *par);
-#endif
 
     /*
      *  DAC operations

From b266409310c6b3c523d824616bc3328026b4ee63 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 26 Feb 2021 09:30:08 -0800
Subject: [PATCH 0657/1820] fbdev: atyfb: use LCD management functions for
 PPC_PMAC also
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Include PPC_PMAC in the configs that use aty_ld_lcd() and
aty_st_lcd() implementations so that the PM code may work
correctly for PPC_PMAC.

Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: linux-fbdev@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: David Airlie <airlied@linux.ie>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210226173008.18236-1-rdunlap@infradead.org
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/video/fbdev/aty/atyfb_base.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c
index e946903a86c2..1aef3d6ebd88 100644
--- a/drivers/video/fbdev/aty/atyfb_base.c
+++ b/drivers/video/fbdev/aty/atyfb_base.c
@@ -133,7 +133,7 @@
 #define PRINTKE(fmt, args...)	printk(KERN_ERR "atyfb: " fmt, ## args)
 
 #if defined(CONFIG_PMAC_BACKLIGHT) || defined(CONFIG_FB_ATY_GENERIC_LCD) || \
-defined(CONFIG_FB_ATY_BACKLIGHT)
+defined(CONFIG_FB_ATY_BACKLIGHT) || defined (CONFIG_PPC_PMAC)
 static const u32 lt_lcd_regs[] = {
 	CNFG_PANEL_LG,
 	LCD_GEN_CNTL_LG,
@@ -175,8 +175,8 @@ u32 aty_ld_lcd(int index, const struct atyfb_par *par)
 		return aty_ld_le32(LCD_DATA, par);
 	}
 }
-#else /* defined(CONFIG_PMAC_BACKLIGHT) || defined(CONFIG_FB_ATY_BACKLIGHT) \
-	 defined(CONFIG_FB_ATY_GENERIC_LCD) */
+#else /* defined(CONFIG_PMAC_BACKLIGHT) || defined(CONFIG_FB_ATY_BACKLIGHT) ||
+	 defined(CONFIG_FB_ATY_GENERIC_LCD) || defined(CONFIG_PPC_PMAC) */
 void aty_st_lcd(int index, u32 val, const struct atyfb_par *par)
 { }
 
@@ -184,7 +184,8 @@ u32 aty_ld_lcd(int index, const struct atyfb_par *par)
 {
 	return 0;
 }
-#endif /* defined(CONFIG_PMAC_BACKLIGHT) || defined (CONFIG_FB_ATY_GENERIC_LCD) */
+#endif /* defined(CONFIG_PMAC_BACKLIGHT) || defined(CONFIG_FB_ATY_BACKLIGHT) ||
+	  defined (CONFIG_FB_ATY_GENERIC_LCD) || defined(CONFIG_PPC_PMAC) */
 
 #ifdef CONFIG_FB_ATY_GENERIC_LCD
 /*

From 301469c121bfe4a243460ed0b6abf391139c6bb1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pavel=20Turinsk=C3=BD?= <ledoian@kam.mff.cuni.cz>
Date: Sun, 28 Feb 2021 17:36:58 +0100
Subject: [PATCH 0658/1820] MAINTAINERS: update drm bug reporting URL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The original bugzilla seems to be read-only now, linking to the gitlab
for new bugs.

Signed-off-by: Pavel Turinský <ledoian@kam.mff.cuni.cz>
Cc: trivial@kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210228163658.54962-1-ledoian@kam.mff.cuni.cz
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d92f85ca831d..f5f8e8966668 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5835,7 +5835,7 @@ M:	David Airlie <airlied@linux.ie>
 M:	Daniel Vetter <daniel@ffwll.ch>
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
-B:	https://bugs.freedesktop.org/
+B:	https://gitlab.freedesktop.org/drm
 C:	irc://chat.freenode.net/dri-devel
 T:	git git://anongit.freedesktop.org/drm/drm
 F:	Documentation/devicetree/bindings/display/

From 659ab7a49cbebe0deffcbe1f9560e82006b21817 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Wed, 3 Mar 2021 14:32:29 +0100
Subject: [PATCH 0659/1820] drm: Use USB controller's DMA mask when importing
 dmabufs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

USB devices cannot perform DMA and hence have no dma_mask set in their
device structure. Therefore importing dmabuf into a USB-based driver
fails, which breaks joining and mirroring of display in X11.

For USB devices, pick the associated USB controller as attachment device.
This allows the DRM import helpers to perform the DMA setup. If the DMA
controller does not support DMA transfers, we're out of luck and cannot
import. Our current USB-based DRM drivers don't use DMA, so the actual
DMA device is not important.

Tested by joining/mirroring displays of udl and radeon under Gnome/X11.

v8:
	* release dmadev if device initialization fails (Noralf)
	* fix commit description (Noralf)
v7:
	* fix use-before-init bug in gm12u320 (Dan)
v6:
	* implement workaround in DRM drivers and hold reference to
	  DMA device while USB device is in use
	* remove dev_is_usb() (Greg)
	* collapse USB helper into usb_intf_get_dma_device() (Alan)
	* integrate Daniel's TODO statement (Daniel)
	* fix typos (Greg)
v5:
	* provide a helper for USB interfaces (Alan)
	* add FIXME item to documentation and TODO list (Daniel)
v4:
	* implement workaround with USB helper functions (Greg)
	* use struct usb_device->bus->sysdev as DMA device (Takashi)
v3:
	* drop gem_create_object
	* use DMA mask of USB controller, if any (Daniel, Christian, Noralf)
v2:
	* move fix to importer side (Christian, Daniel)
	* update SHMEM and CMA helpers for new PRIME callbacks

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: 6eb0233ec2d0 ("usb: don't inherity DMA properties for USB devices")
Tested-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Noralf Trønnes <noralf@tronnes.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: <stable@vger.kernel.org> # v5.10+
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20210303133229.3288-1-tzimmermann@suse.de
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 Documentation/gpu/todo.rst      | 21 ++++++++++++++++
 drivers/gpu/drm/tiny/gm12u320.c | 44 +++++++++++++++++++++++++++------
 drivers/gpu/drm/udl/udl_drv.c   | 17 +++++++++++++
 drivers/gpu/drm/udl/udl_drv.h   |  1 +
 drivers/gpu/drm/udl/udl_main.c  | 10 ++++++++
 drivers/usb/core/usb.c          | 32 ++++++++++++++++++++++++
 include/linux/usb.h             |  2 ++
 7 files changed, 119 insertions(+), 8 deletions(-)

diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst
index 40ccac61137e..22ce801e3a8d 100644
--- a/Documentation/gpu/todo.rst
+++ b/Documentation/gpu/todo.rst
@@ -613,6 +613,27 @@ Some of these date from the very introduction of KMS in 2008 ...
 
 Level: Intermediate
 
+Remove automatic page mapping from dma-buf importing
+----------------------------------------------------
+
+When importing dma-bufs, the dma-buf and PRIME frameworks automatically map
+imported pages into the importer's DMA area. drm_gem_prime_fd_to_handle() and
+drm_gem_prime_handle_to_fd() require that importers call dma_buf_attach()
+even if they never do actual device DMA, but only CPU access through
+dma_buf_vmap(). This is a problem for USB devices, which do not support DMA
+operations.
+
+To fix the issue, automatic page mappings should be removed from the
+buffer-sharing code. Fixing this is a bit more involved, since the import/export
+cache is also tied to &drm_gem_object.import_attach. Meanwhile we paper over
+this problem for USB devices by fishing out the USB host controller device, as
+long as that supports DMA. Otherwise importing can still needlessly fail.
+
+Contact: Thomas Zimmermann <tzimmermann@suse.de>, Daniel Vetter
+
+Level: Advanced
+
+
 Better Testing
 ==============
 
diff --git a/drivers/gpu/drm/tiny/gm12u320.c b/drivers/gpu/drm/tiny/gm12u320.c
index 33f65f4626e5..23866a54e3f9 100644
--- a/drivers/gpu/drm/tiny/gm12u320.c
+++ b/drivers/gpu/drm/tiny/gm12u320.c
@@ -83,6 +83,7 @@ MODULE_PARM_DESC(eco_mode, "Turn on Eco mode (less bright, more silent)");
 
 struct gm12u320_device {
 	struct drm_device	         dev;
+	struct device                   *dmadev;
 	struct drm_simple_display_pipe   pipe;
 	struct drm_connector	         conn;
 	unsigned char                   *cmd_buf;
@@ -601,6 +602,22 @@ static const uint64_t gm12u320_pipe_modifiers[] = {
 	DRM_FORMAT_MOD_INVALID
 };
 
+/*
+ * FIXME: Dma-buf sharing requires DMA support by the importing device.
+ *        This function is a workaround to make USB devices work as well.
+ *        See todo.rst for how to fix the issue in the dma-buf framework.
+ */
+static struct drm_gem_object *gm12u320_gem_prime_import(struct drm_device *dev,
+							struct dma_buf *dma_buf)
+{
+	struct gm12u320_device *gm12u320 = to_gm12u320(dev);
+
+	if (!gm12u320->dmadev)
+		return ERR_PTR(-ENODEV);
+
+	return drm_gem_prime_import_dev(dev, dma_buf, gm12u320->dmadev);
+}
+
 DEFINE_DRM_GEM_FOPS(gm12u320_fops);
 
 static const struct drm_driver gm12u320_drm_driver = {
@@ -614,6 +631,7 @@ static const struct drm_driver gm12u320_drm_driver = {
 
 	.fops		 = &gm12u320_fops,
 	DRM_GEM_SHMEM_DRIVER_OPS,
+	.gem_prime_import = gm12u320_gem_prime_import,
 };
 
 static const struct drm_mode_config_funcs gm12u320_mode_config_funcs = {
@@ -640,15 +658,18 @@ static int gm12u320_usb_probe(struct usb_interface *interface,
 				      struct gm12u320_device, dev);
 	if (IS_ERR(gm12u320))
 		return PTR_ERR(gm12u320);
+	dev = &gm12u320->dev;
+
+	gm12u320->dmadev = usb_intf_get_dma_device(to_usb_interface(dev->dev));
+	if (!gm12u320->dmadev)
+		drm_warn(dev, "buffer sharing not supported"); /* not an error */
 
 	INIT_DELAYED_WORK(&gm12u320->fb_update.work, gm12u320_fb_update_work);
 	mutex_init(&gm12u320->fb_update.lock);
 
-	dev = &gm12u320->dev;
-
 	ret = drmm_mode_config_init(dev);
 	if (ret)
-		return ret;
+		goto err_put_device;
 
 	dev->mode_config.min_width = GM12U320_USER_WIDTH;
 	dev->mode_config.max_width = GM12U320_USER_WIDTH;
@@ -658,15 +679,15 @@ static int gm12u320_usb_probe(struct usb_interface *interface,
 
 	ret = gm12u320_usb_alloc(gm12u320);
 	if (ret)
-		return ret;
+		goto err_put_device;
 
 	ret = gm12u320_set_ecomode(gm12u320);
 	if (ret)
-		return ret;
+		goto err_put_device;
 
 	ret = gm12u320_conn_init(gm12u320);
 	if (ret)
-		return ret;
+		goto err_put_device;
 
 	ret = drm_simple_display_pipe_init(&gm12u320->dev,
 					   &gm12u320->pipe,
@@ -676,24 +697,31 @@ static int gm12u320_usb_probe(struct usb_interface *interface,
 					   gm12u320_pipe_modifiers,
 					   &gm12u320->conn);
 	if (ret)
-		return ret;
+		goto err_put_device;
 
 	drm_mode_config_reset(dev);
 
 	usb_set_intfdata(interface, dev);
 	ret = drm_dev_register(dev, 0);
 	if (ret)
-		return ret;
+		goto err_put_device;
 
 	drm_fbdev_generic_setup(dev, 0);
 
 	return 0;
+
+err_put_device:
+	put_device(gm12u320->dmadev);
+	return ret;
 }
 
 static void gm12u320_usb_disconnect(struct usb_interface *interface)
 {
 	struct drm_device *dev = usb_get_intfdata(interface);
+	struct gm12u320_device *gm12u320 = to_gm12u320(dev);
 
+	put_device(gm12u320->dmadev);
+	gm12u320->dmadev = NULL;
 	drm_dev_unplug(dev);
 	drm_atomic_helper_shutdown(dev);
 }
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 9269092697d8..5703277c6f52 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -32,6 +32,22 @@ static int udl_usb_resume(struct usb_interface *interface)
 	return drm_mode_config_helper_resume(dev);
 }
 
+/*
+ * FIXME: Dma-buf sharing requires DMA support by the importing device.
+ *        This function is a workaround to make USB devices work as well.
+ *        See todo.rst for how to fix the issue in the dma-buf framework.
+ */
+static struct drm_gem_object *udl_driver_gem_prime_import(struct drm_device *dev,
+							  struct dma_buf *dma_buf)
+{
+	struct udl_device *udl = to_udl(dev);
+
+	if (!udl->dmadev)
+		return ERR_PTR(-ENODEV);
+
+	return drm_gem_prime_import_dev(dev, dma_buf, udl->dmadev);
+}
+
 DEFINE_DRM_GEM_FOPS(udl_driver_fops);
 
 static const struct drm_driver driver = {
@@ -40,6 +56,7 @@ static const struct drm_driver driver = {
 	/* GEM hooks */
 	.fops = &udl_driver_fops,
 	DRM_GEM_SHMEM_DRIVER_OPS,
+	.gem_prime_import = udl_driver_gem_prime_import,
 
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 875e73551ae9..cc16a13316e4 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -50,6 +50,7 @@ struct urb_list {
 struct udl_device {
 	struct drm_device drm;
 	struct device *dev;
+	struct device *dmadev;
 
 	struct drm_simple_display_pipe display_pipe;
 
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index 0e2a376cb075..853f147036f6 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -315,6 +315,10 @@ int udl_init(struct udl_device *udl)
 
 	DRM_DEBUG("\n");
 
+	udl->dmadev = usb_intf_get_dma_device(to_usb_interface(dev->dev));
+	if (!udl->dmadev)
+		drm_warn(dev, "buffer sharing not supported"); /* not an error */
+
 	mutex_init(&udl->gem_lock);
 
 	if (!udl_parse_vendor_descriptor(udl)) {
@@ -343,12 +347,18 @@ int udl_init(struct udl_device *udl)
 err:
 	if (udl->urbs.count)
 		udl_free_urb_list(dev);
+	put_device(udl->dmadev);
 	DRM_ERROR("%d\n", ret);
 	return ret;
 }
 
 int udl_drop_usb(struct drm_device *dev)
 {
+	struct udl_device *udl = to_udl(dev);
+
 	udl_free_urb_list(dev);
+	put_device(udl->dmadev);
+	udl->dmadev = NULL;
+
 	return 0;
 }
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index 8f07b0516100..a566bb494e24 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -748,6 +748,38 @@ void usb_put_intf(struct usb_interface *intf)
 }
 EXPORT_SYMBOL_GPL(usb_put_intf);
 
+/**
+ * usb_intf_get_dma_device - acquire a reference on the usb interface's DMA endpoint
+ * @intf: the usb interface
+ *
+ * While a USB device cannot perform DMA operations by itself, many USB
+ * controllers can. A call to usb_intf_get_dma_device() returns the DMA endpoint
+ * for the given USB interface, if any. The returned device structure must be
+ * released with put_device().
+ *
+ * See also usb_get_dma_device().
+ *
+ * Returns: A reference to the usb interface's DMA endpoint; or NULL if none
+ *          exists.
+ */
+struct device *usb_intf_get_dma_device(struct usb_interface *intf)
+{
+	struct usb_device *udev = interface_to_usbdev(intf);
+	struct device *dmadev;
+
+	if (!udev->bus)
+		return NULL;
+
+	dmadev = get_device(udev->bus->sysdev);
+	if (!dmadev || !dmadev->dma_mask) {
+		put_device(dmadev);
+		return NULL;
+	}
+
+	return dmadev;
+}
+EXPORT_SYMBOL_GPL(usb_intf_get_dma_device);
+
 /*			USB device locking
  *
  * USB devices and interfaces are locked using the semaphore in their
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 7d72c4e0713c..d6a41841b93e 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -746,6 +746,8 @@ extern int usb_lock_device_for_reset(struct usb_device *udev,
 extern int usb_reset_device(struct usb_device *dev);
 extern void usb_queue_reset_device(struct usb_interface *dev);
 
+extern struct device *usb_intf_get_dma_device(struct usb_interface *intf);
+
 #ifdef CONFIG_ACPI
 extern int usb_acpi_set_power_state(struct usb_device *hdev, int index,
 	bool enable);

From d228f8d8749994eb5c52636090709109120ed339 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Wed, 3 Mar 2021 15:47:14 +0100
Subject: [PATCH 0660/1820] drm/ttm: soften TTM warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

QXL indeed unrefs pinned BOs and the warnings are spamming peoples log files.

Make sure we warn only once until the QXL driver is fixed.

Signed-off-by: Christian König <christian.koenig@amd.com>
References: https://lore.kernel.org/lkml/YD+eYcMMcdlXB8PY@alley/
Link: https://patchwork.freedesktop.org/patch/422834/
Reviewed-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 20a25660b35b..101a68dc615b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -136,7 +136,8 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo,
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_resource_manager *man;
 
-	dma_resv_assert_held(bo->base.resv);
+	if (!bo->deleted)
+		dma_resv_assert_held(bo->base.resv);
 
 	if (bo->pin_count) {
 		ttm_bo_del_from_lru(bo);
@@ -508,8 +509,11 @@ static void ttm_bo_release(struct kref *kref)
 		 * Make pinned bos immediately available to
 		 * shrinkers, now that they are queued for
 		 * destruction.
+		 *
+		 * FIXME: QXL is triggering this. Can be removed when the
+		 * driver is fixed.
 		 */
-		if (WARN_ON(bo->pin_count)) {
+		if (WARN_ON_ONCE(bo->pin_count)) {
 			bo->pin_count = 0;
 			ttm_bo_move_to_lru_tail(bo, &bo->mem, NULL);
 		}

From ca63d76fd2319db984f2875992643f900caf2c72 Mon Sep 17 00:00:00 2001
From: Anthony DeRossi <ajderossi@gmail.com>
Date: Tue, 2 Mar 2021 17:17:25 -0800
Subject: [PATCH 0661/1820] drm/ttm: Fix TTM page pool accounting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Freed pages are not subtracted from the allocated_pages counter in
ttm_pool_type_fini(), causing a leak in the count on device removal.
The next shrinker invocation loops forever trying to free pages that are
no longer in the pool:

  rcu: INFO: rcu_sched self-detected stall on CPU
  rcu:  3-....: (9998 ticks this GP) idle=54e/1/0x4000000000000000 softirq=434857/434857 fqs=2237
    (t=10001 jiffies g=2194533 q=49211)
  NMI backtrace for cpu 3
  CPU: 3 PID: 1034 Comm: kswapd0 Tainted: P           O      5.11.0-com #1
  Hardware name: System manufacturer System Product Name/PRIME X570-PRO, BIOS 1405 11/19/2019
  Call Trace:
   <IRQ>
   ...
   </IRQ>
   sysvec_apic_timer_interrupt+0x77/0x80
   asm_sysvec_apic_timer_interrupt+0x12/0x20
  RIP: 0010:mutex_unlock+0x16/0x20
  Code: e7 48 8b 70 10 e8 7a 53 77 ff eb aa e8 43 6c ff ff 0f 1f 00 65 48 8b 14 25 00 6d 01 00 31 c9 48 89 d0 f0 48 0f b1 0f 48 39 c2 <74> 05 e9 e3 fe ff ff c3 66 90 48 8b 47 20 48 85 c0 74 0f 8b 50 10
  RSP: 0018:ffffbdb840797be8 EFLAGS: 00000246
  RAX: ffff9ff445a41c00 RBX: ffffffffc02a9ef8 RCX: 0000000000000000
  RDX: ffff9ff445a41c00 RSI: ffffbdb840797c78 RDI: ffffffffc02a9ac0
  RBP: 0000000000000080 R08: 0000000000000000 R09: ffffbdb840797c80
  R10: 0000000000000000 R11: fffffffffffffff5 R12: 0000000000000000
  R13: 0000000000000000 R14: 0000000000000084 R15: ffffffffc02a9a60
   ttm_pool_shrink+0x7d/0x90 [ttm]
   ttm_pool_shrinker_scan+0x5/0x20 [ttm]
   do_shrink_slab+0x13a/0x1a0
...

debugfs shows the incorrect total:

  $ cat /sys/kernel/debug/dri/0/ttm_page_pool
            --- 0--- --- 1--- --- 2--- --- 3--- --- 4--- --- 5--- --- 6--- --- 7--- --- 8--- --- 9--- ---10---
  wc      :        0        0        0        0        0        0        0        0        0        0        0
  uc      :        0        0        0        0        0        0        0        0        0        0        0
  wc 32   :        0        0        0        0        0        0        0        0        0        0        0
  uc 32   :        0        0        0        0        0        0        0        0        0        0        0
  DMA uc  :        0        0        0        0        0        0        0        0        0        0        0
  DMA wc  :        0        0        0        0        0        0        0        0        0        0        0
  DMA     :        0        0        0        0        0        0        0        0        0        0        0

  total   :     3029 of  8244261

Using ttm_pool_type_take() to remove pages from the pool before freeing
them correctly accounts for the freed pages.

Fixes: d099fc8f540a ("drm/ttm: new TT backend allocation pool v3")
Signed-off-by: Anthony DeRossi <ajderossi@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210303011723.22512-1-ajderossi@gmail.com
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/ttm/ttm_pool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 6e27cb1bf48b..4eb6efb8b8c0 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -268,13 +268,13 @@ static void ttm_pool_type_init(struct ttm_pool_type *pt, struct ttm_pool *pool,
 /* Remove a pool_type from the global shrinker list and free all pages */
 static void ttm_pool_type_fini(struct ttm_pool_type *pt)
 {
-	struct page *p, *tmp;
+	struct page *p;
 
 	mutex_lock(&shrinker_lock);
 	list_del(&pt->shrinker_list);
 	mutex_unlock(&shrinker_lock);
 
-	list_for_each_entry_safe(p, tmp, &pt->pages, lru)
+	while ((p = ttm_pool_type_take(pt)))
 		ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
 }
 

From 738acd49eb018feb873e0fac8f9517493f6ce2c7 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 4 Mar 2021 09:49:28 +0000
Subject: [PATCH 0662/1820] qxl: Fix uninitialised struct field head.surface_id

The surface_id struct field in head is not being initialized and
static analysis warns that this is being passed through to
dev->monitors_config->heads[i] on an assignment. Clear up this
warning by initializing it to zero.

Addresses-Coverity: ("Uninitialized scalar variable")
Fixes: a6d3c4d79822 ("qxl: hook monitors_config updates into crtc, not encoder.")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20210304094928.2280722-1-colin.king@canonical.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/qxl/qxl_display.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 012bce0cdb65..10738e04c09b 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -328,6 +328,7 @@ static void qxl_crtc_update_monitors_config(struct drm_crtc *crtc,
 
 	head.id = i;
 	head.flags = 0;
+	head.surface_id = 0;
 	oldcount = qdev->monitors_config->count;
 	if (crtc->state->active) {
 		struct drm_display_mode *mode = &crtc->mode;

From d611b4a0907cece060699f2fd347c492451cd2aa Mon Sep 17 00:00:00 2001
From: Neil Roberts <nroberts@igalia.com>
Date: Tue, 23 Feb 2021 16:51:24 +0100
Subject: [PATCH 0663/1820] drm/shmem-helper: Check for purged buffers in fault
 handler

When a buffer is madvised as not needed and then purged, any attempts to
access the buffer from user-space should cause a bus fault. This patch
adds a check for that.

Cc: stable@vger.kernel.org
Fixes: 17acb9f35ed7 ("drm/shmem: Add madvise state and purge helpers")
Signed-off-by: Neil Roberts <nroberts@igalia.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Signed-off-by: Steven Price <steven.price@arm.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210223155125.199577-2-nroberts@igalia.com
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/drm_gem_shmem_helper.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 9825c378dfa6..b26139b1dc35 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -525,14 +525,24 @@ static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf)
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
 	loff_t num_pages = obj->size >> PAGE_SHIFT;
+	vm_fault_t ret;
 	struct page *page;
 
-	if (vmf->pgoff >= num_pages || WARN_ON_ONCE(!shmem->pages))
-		return VM_FAULT_SIGBUS;
+	mutex_lock(&shmem->pages_lock);
 
-	page = shmem->pages[vmf->pgoff];
+	if (vmf->pgoff >= num_pages ||
+	    WARN_ON_ONCE(!shmem->pages) ||
+	    shmem->madv < 0) {
+		ret = VM_FAULT_SIGBUS;
+	} else {
+		page = shmem->pages[vmf->pgoff];
 
-	return vmf_insert_page(vma, vmf->address, page);
+		ret = vmf_insert_page(vma, vmf->address, page);
+	}
+
+	mutex_unlock(&shmem->pages_lock);
+
+	return ret;
 }
 
 static void drm_gem_shmem_vm_open(struct vm_area_struct *vma)

From 11d5a4745e00e73745774671dbf2fb07bd6e2363 Mon Sep 17 00:00:00 2001
From: Neil Roberts <nroberts@igalia.com>
Date: Tue, 23 Feb 2021 16:51:25 +0100
Subject: [PATCH 0664/1820] drm/shmem-helper: Don't remove the offset in
 vm_area_struct pgoff

When mmapping the shmem, it would previously adjust the pgoff in the
vm_area_struct to remove the fake offset that is added to be able to
identify the buffer. This patch removes the adjustment and makes the
fault handler use the vm_fault address to calculate the page offset
instead. Although using this address is apparently discouraged, several
DRM drivers seem to be doing it anyway.

The problem with removing the pgoff is that it prevents
drm_vma_node_unmap from working because that searches the mapping tree
by address. That doesn't work because all of the mappings are at offset
0. drm_vma_node_unmap is being used by the shmem helpers when purging
the buffer.

This fixes a bug in Panfrost which is using drm_gem_shmem_purge. Without
this the mapping for the purged buffer can still be accessed which might
mean it would access random pages from other buffers

v2: Don't check whether the unsigned page_offset is less than 0.

Cc: stable@vger.kernel.org
Fixes: 17acb9f35ed7 ("drm/shmem: Add madvise state and purge helpers")
Signed-off-by: Neil Roberts <nroberts@igalia.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Signed-off-by: Steven Price <steven.price@arm.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210223155125.199577-3-nroberts@igalia.com
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/drm_gem_shmem_helper.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index b26139b1dc35..5b5c095e86a9 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -527,15 +527,19 @@ static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf)
 	loff_t num_pages = obj->size >> PAGE_SHIFT;
 	vm_fault_t ret;
 	struct page *page;
+	pgoff_t page_offset;
+
+	/* We don't use vmf->pgoff since that has the fake offset */
+	page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
 	mutex_lock(&shmem->pages_lock);
 
-	if (vmf->pgoff >= num_pages ||
+	if (page_offset >= num_pages ||
 	    WARN_ON_ONCE(!shmem->pages) ||
 	    shmem->madv < 0) {
 		ret = VM_FAULT_SIGBUS;
 	} else {
-		page = shmem->pages[vmf->pgoff];
+		page = shmem->pages[page_offset];
 
 		ret = vmf_insert_page(vma, vmf->address, page);
 	}
@@ -591,9 +595,6 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	struct drm_gem_shmem_object *shmem;
 	int ret;
 
-	/* Remove the fake offset */
-	vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
-
 	if (obj->import_attach) {
 		/* Drop the reference drm_gem_mmap_obj() acquired.*/
 		drm_gem_object_put(obj);

From fa0c16caf3d73ab4d2e5d6fa2ef2394dbec91791 Mon Sep 17 00:00:00 2001
From: Artem Lapkin <art@khadas.com>
Date: Tue, 2 Mar 2021 12:22:02 +0800
Subject: [PATCH 0665/1820] drm: meson_drv add shutdown function

Problem: random stucks on reboot stage about 1/20 stuck/reboots
// debug kernel log
[    4.496660] reboot: kernel restart prepare CMD:(null)
[    4.498114] meson_ee_pwrc c883c000.system-controller:power-controller: shutdown begin
[    4.503949] meson_ee_pwrc c883c000.system-controller:power-controller: shutdown domain 0:VPU...
...STUCK...

Solution: add shutdown function to meson_drm driver
// debug kernel log
[    5.231896] reboot: kernel restart prepare CMD:(null)
[    5.246135] [drm:meson_drv_shutdown]
...
[    5.259271] meson_ee_pwrc c883c000.system-controller:power-controller: shutdown begin
[    5.274688] meson_ee_pwrc c883c000.system-controller:power-controller: shutdown domain 0:VPU...
[    5.338331] reboot: Restarting system
[    5.358293] psci: PSCI_0_2_FN_SYSTEM_RESET reboot_mode:0 cmd:(null)
bl31 reboot reason: 0xd
bl31 reboot reason: 0x0
system cmd  1.
...REBOOT...

Tested: on VIM1 VIM2 VIM3 VIM3L khadas sbcs - 1000+ successful reboots
and Odroid boards, WeTek Play2 (GXBB)

Fixes: bbbe775ec5b5 ("drm: Add support for Amlogic Meson Graphic Controller")
Signed-off-by: Artem Lapkin <art@khadas.com>
Tested-by: Christian Hewitt <christianshewitt@gmail.com>
Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210302042202.3728113-1-art@khadas.com
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/meson/meson_drv.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 42c5d3246cfc..453d8b4c5763 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -482,6 +482,16 @@ static int meson_probe_remote(struct platform_device *pdev,
 	return count;
 }
 
+static void meson_drv_shutdown(struct platform_device *pdev)
+{
+	struct meson_drm *priv = dev_get_drvdata(&pdev->dev);
+	struct drm_device *drm = priv->drm;
+
+	DRM_DEBUG_DRIVER("\n");
+	drm_kms_helper_poll_fini(drm);
+	drm_atomic_helper_shutdown(drm);
+}
+
 static int meson_drv_probe(struct platform_device *pdev)
 {
 	struct component_match *match = NULL;
@@ -553,6 +563,7 @@ static const struct dev_pm_ops meson_drv_pm_ops = {
 
 static struct platform_driver meson_drm_platform_driver = {
 	.probe      = meson_drv_probe,
+	.shutdown   = meson_drv_shutdown,
 	.driver     = {
 		.name	= "meson-drm",
 		.of_match_table = dt_match,

From 64e194e278673bceb68fb2dde7dbc3d812bfceb3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Noralf=20Tr=C3=B8nnes?= <noralf@tronnes.org>
Date: Fri, 19 Feb 2021 13:22:03 +0100
Subject: [PATCH 0666/1820] drm/shmem-helpers: vunmap: Don't put pages for
 dma-buf
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

dma-buf importing was reworked in commit 7d2cd72a9aa3
("drm/shmem-helpers: Simplify dma-buf importing"). Before that commit
drm_gem_shmem_prime_import_sg_table() did set ->pages_use_count=1 and
drm_gem_shmem_vunmap_locked() could call drm_gem_shmem_put_pages()
unconditionally. Now without the use count set, put pages is called also
on dma-bufs. Fix this by only putting pages if it's not imported.

Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Fixes: 7d2cd72a9aa3 ("drm/shmem-helpers: Simplify dma-buf importing")
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Tested-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20210219122203.51130-1-noralf@tronnes.org
(cherry picked from commit cdea72518a2b38207146e92e1c9e2fac15975679)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/drm_gem_shmem_helper.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 5b5c095e86a9..6d625cee7a6a 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -357,13 +357,14 @@ static void drm_gem_shmem_vunmap_locked(struct drm_gem_shmem_object *shmem,
 	if (--shmem->vmap_use_count > 0)
 		return;
 
-	if (obj->import_attach)
+	if (obj->import_attach) {
 		dma_buf_vunmap(obj->import_attach->dmabuf, map);
-	else
+	} else {
 		vunmap(shmem->vaddr);
+		drm_gem_shmem_put_pages(shmem);
+	}
 
 	shmem->vaddr = NULL;
-	drm_gem_shmem_put_pages(shmem);
 }
 
 /*

From de066e116306baf3a6a62691ac63cfc0b1dabddb Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 22 Feb 2021 11:06:43 +0100
Subject: [PATCH 0667/1820] drm/compat: Clear bounce structures

Some of them have gaps, or fields we don't clear. Native ioctl code
does full copies plus zero-extends on size mismatch, so nothing can
leak. But compat is more hand-rolled so need to be careful.

None of these matter for performance, so just memset.

Also I didn't fix up the CONFIG_DRM_LEGACY or CONFIG_DRM_AGP ioctl, those
are security holes anyway.

Acked-by: Maxime Ripard <mripard@kernel.org>
Reported-by: syzbot+620cf21140fc7e772a5d@syzkaller.appspotmail.com # vblank ioctl
Cc: syzbot+620cf21140fc7e772a5d@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210222100643.400935-1-daniel.vetter@ffwll.ch
(cherry picked from commit e926c474ebee404441c838d18224cd6f246a71b7)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/drm_ioc32.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c
index f86448ab1fe0..dc734d4828a1 100644
--- a/drivers/gpu/drm/drm_ioc32.c
+++ b/drivers/gpu/drm/drm_ioc32.c
@@ -99,6 +99,8 @@ static int compat_drm_version(struct file *file, unsigned int cmd,
 	if (copy_from_user(&v32, (void __user *)arg, sizeof(v32)))
 		return -EFAULT;
 
+	memset(&v, 0, sizeof(v));
+
 	v = (struct drm_version) {
 		.name_len = v32.name_len,
 		.name = compat_ptr(v32.name),
@@ -137,6 +139,9 @@ static int compat_drm_getunique(struct file *file, unsigned int cmd,
 
 	if (copy_from_user(&uq32, (void __user *)arg, sizeof(uq32)))
 		return -EFAULT;
+
+	memset(&uq, 0, sizeof(uq));
+
 	uq = (struct drm_unique){
 		.unique_len = uq32.unique_len,
 		.unique = compat_ptr(uq32.unique),
@@ -265,6 +270,8 @@ static int compat_drm_getclient(struct file *file, unsigned int cmd,
 	if (copy_from_user(&c32, argp, sizeof(c32)))
 		return -EFAULT;
 
+	memset(&client, 0, sizeof(client));
+
 	client.idx = c32.idx;
 
 	err = drm_ioctl_kernel(file, drm_getclient, &client, 0);
@@ -852,6 +859,8 @@ static int compat_drm_wait_vblank(struct file *file, unsigned int cmd,
 	if (copy_from_user(&req32, argp, sizeof(req32)))
 		return -EFAULT;
 
+	memset(&req, 0, sizeof(req));
+
 	req.request.type = req32.request.type;
 	req.request.sequence = req32.request.sequence;
 	req.request.signal = req32.request.signal;
@@ -889,6 +898,8 @@ static int compat_drm_mode_addfb2(struct file *file, unsigned int cmd,
 	struct drm_mode_fb_cmd2 req64;
 	int err;
 
+	memset(&req64, 0, sizeof(req64));
+
 	if (copy_from_user(&req64, argp,
 			   offsetof(drm_mode_fb_cmd232_t, modifier)))
 		return -EFAULT;

From f09f9f93afad770a04b35235a0aa465fcc8d6e3d Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Fri, 26 Feb 2021 11:37:47 +0100
Subject: [PATCH 0668/1820] media: rc: compile rc-cec.c into rc-core

The rc-cec keymap is unusual in that it can't be built as a module,
instead it is registered directly in rc-main.c if CONFIG_MEDIA_CEC_RC
is set. This is because it can be called from drm_dp_cec_set_edid() via
cec_register_adapter() in an asynchronous context, and it is not
allowed to use request_module() to load rc-cec.ko in that case. Trying to
do so results in a 'WARN_ON_ONCE(wait && current_is_async())'.

Since this keymap is only used if CONFIG_MEDIA_CEC_RC is set, we
just compile this keymap into the rc-core module and never as a
separate module.

Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Fixes: 2c6d1fffa1d9 (drm: add support for DisplayPort CEC-Tunneling-over-AUX)
Reported-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/rc/Makefile         |  1 +
 drivers/media/rc/keymaps/Makefile |  1 -
 drivers/media/rc/keymaps/rc-cec.c | 28 +++++++++++-----------------
 drivers/media/rc/rc-main.c        |  6 ++++++
 include/media/rc-map.h            |  7 +++++++
 5 files changed, 25 insertions(+), 18 deletions(-)

diff --git a/drivers/media/rc/Makefile b/drivers/media/rc/Makefile
index 5bb2932ab119..ff6a8fc4c38e 100644
--- a/drivers/media/rc/Makefile
+++ b/drivers/media/rc/Makefile
@@ -5,6 +5,7 @@ obj-y += keymaps/
 obj-$(CONFIG_RC_CORE) += rc-core.o
 rc-core-y := rc-main.o rc-ir-raw.o
 rc-core-$(CONFIG_LIRC) += lirc_dev.o
+rc-core-$(CONFIG_MEDIA_CEC_RC) += keymaps/rc-cec.o
 rc-core-$(CONFIG_BPF_LIRC_MODE2) += bpf-lirc.o
 obj-$(CONFIG_IR_NEC_DECODER) += ir-nec-decoder.o
 obj-$(CONFIG_IR_RC5_DECODER) += ir-rc5-decoder.o
diff --git a/drivers/media/rc/keymaps/Makefile b/drivers/media/rc/keymaps/Makefile
index b252a1d2ebd6..cc6662e1903f 100644
--- a/drivers/media/rc/keymaps/Makefile
+++ b/drivers/media/rc/keymaps/Makefile
@@ -21,7 +21,6 @@ obj-$(CONFIG_RC_MAP) += rc-adstech-dvb-t-pci.o \
 			rc-behold.o \
 			rc-behold-columbus.o \
 			rc-budget-ci-old.o \
-			rc-cec.o \
 			rc-cinergy-1400.o \
 			rc-cinergy.o \
 			rc-d680-dmb.o \
diff --git a/drivers/media/rc/keymaps/rc-cec.c b/drivers/media/rc/keymaps/rc-cec.c
index 3e3bd11092b4..068e22aeac8c 100644
--- a/drivers/media/rc/keymaps/rc-cec.c
+++ b/drivers/media/rc/keymaps/rc-cec.c
@@ -1,5 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /* Keytable for the CEC remote control
+ *
+ * This keymap is unusual in that it can't be built as a module,
+ * instead it is registered directly in rc-main.c if CONFIG_MEDIA_CEC_RC
+ * is set. This is because it can be called from drm_dp_cec_set_edid() via
+ * cec_register_adapter() in an asynchronous context, and it is not
+ * allowed to use request_module() to load rc-cec.ko in that case.
+ *
+ * Since this keymap is only used if CONFIG_MEDIA_CEC_RC is set, we
+ * just compile this keymap into the rc-core module and never as a
+ * separate module.
  *
  * Copyright (c) 2015 by Kamil Debski
  */
@@ -152,7 +162,7 @@ static struct rc_map_table cec[] = {
 	/* 0x77-0xff: Reserved */
 };
 
-static struct rc_map_list cec_map = {
+struct rc_map_list cec_map = {
 	.map = {
 		.scan		= cec,
 		.size		= ARRAY_SIZE(cec),
@@ -160,19 +170,3 @@ static struct rc_map_list cec_map = {
 		.name		= RC_MAP_CEC,
 	}
 };
-
-static int __init init_rc_map_cec(void)
-{
-	return rc_map_register(&cec_map);
-}
-
-static void __exit exit_rc_map_cec(void)
-{
-	rc_map_unregister(&cec_map);
-}
-
-module_init(init_rc_map_cec);
-module_exit(exit_rc_map_cec);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Kamil Debski");
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 1fd62c1dac76..8e88dc8ea6c5 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -2069,6 +2069,9 @@ static int __init rc_core_init(void)
 
 	led_trigger_register_simple("rc-feedback", &led_feedback);
 	rc_map_register(&empty_map);
+#ifdef CONFIG_MEDIA_CEC_RC
+	rc_map_register(&cec_map);
+#endif
 
 	return 0;
 }
@@ -2078,6 +2081,9 @@ static void __exit rc_core_exit(void)
 	lirc_dev_exit();
 	class_unregister(&rc_class);
 	led_trigger_unregister_simple(led_feedback);
+#ifdef CONFIG_MEDIA_CEC_RC
+	rc_map_unregister(&cec_map);
+#endif
 	rc_map_unregister(&empty_map);
 }
 
diff --git a/include/media/rc-map.h b/include/media/rc-map.h
index 999b750bc6b8..30f138ebab6f 100644
--- a/include/media/rc-map.h
+++ b/include/media/rc-map.h
@@ -175,6 +175,13 @@ struct rc_map_list {
 	struct rc_map map;
 };
 
+#ifdef CONFIG_MEDIA_CEC_RC
+/*
+ * rc_map_list from rc-cec.c
+ */
+extern struct rc_map_list cec_map;
+#endif
+
 /* Routines from rc-map.c */
 
 /**

From 8a7e27fd5cd696ba564a3f62cedef7269cfd0723 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maxtram95@gmail.com>
Date: Fri, 5 Feb 2021 23:51:39 +0100
Subject: [PATCH 0669/1820] media: usbtv: Fix deadlock on suspend

usbtv doesn't support power management, so on system suspend the
.disconnect callback of the driver is called. The teardown sequence
includes a call to snd_card_free. Its implementation waits until the
refcount of the sound card device drops to zero, however, if its file is
open, snd_card_file_add takes a reference, which can't be dropped during
the suspend, because the userspace processes are already frozen at this
point. snd_card_free waits for completion forever, leading to a hang on
suspend.

This commit fixes this deadlock condition by replacing snd_card_free
with snd_card_free_when_closed, that doesn't wait until all references
are released, allowing suspend to progress.

Fixes: 63ddf68de52e ("[media] usbtv: add audio support")
Signed-off-by: Maxim Mikityanskiy <maxtram95@gmail.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/usb/usbtv/usbtv-audio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/usbtv/usbtv-audio.c b/drivers/media/usb/usbtv/usbtv-audio.c
index b57e94fb1977..333bd305a4f9 100644
--- a/drivers/media/usb/usbtv/usbtv-audio.c
+++ b/drivers/media/usb/usbtv/usbtv-audio.c
@@ -371,7 +371,7 @@ void usbtv_audio_free(struct usbtv *usbtv)
 	cancel_work_sync(&usbtv->snd_trigger);
 
 	if (usbtv->snd && usbtv->udev) {
-		snd_card_free(usbtv->snd);
+		snd_card_free_when_closed(usbtv->snd);
 		usbtv->snd = NULL;
 	}
 }

From ac8d82f586c8692b501cb974604a71ef0e22a04c Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 1 Mar 2021 13:08:27 +0100
Subject: [PATCH 0670/1820] media: v4l: vsp1: Fix bru null pointer access

RZ/G2L SoC has only BRS. This patch fixes null pointer access,when only
BRS is enabled.

Fixes: cbb7fa49c7466("media: v4l: vsp1: Rename BRU to BRx")
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_drm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index 86d5e3f4b1ff..f6d2f47a4058 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -245,7 +245,7 @@ static int vsp1_du_pipeline_setup_brx(struct vsp1_device *vsp1,
 		brx = &vsp1->bru->entity;
 	else if (pipe->brx && !drm_pipe->force_brx_release)
 		brx = pipe->brx;
-	else if (!vsp1->bru->entity.pipe)
+	else if (vsp1_feature(vsp1, VSP1_HAS_BRU) && !vsp1->bru->entity.pipe)
 		brx = &vsp1->bru->entity;
 	else
 		brx = &vsp1->brs->entity;

From 6732f313938027a910e1f7351951ff52c0329e70 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 1 Mar 2021 13:08:28 +0100
Subject: [PATCH 0671/1820] media: v4l: vsp1: Fix uif null pointer access

RZ/G2L SoC has no UIF. This patch fixes null pointer access, when UIF
module is not used.

Fixes: 5e824f989e6e8("media: v4l: vsp1: Integrate DISCOM in display pipeline")
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_drm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index f6d2f47a4058..06f74d410973 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -462,9 +462,9 @@ static int vsp1_du_pipeline_setup_inputs(struct vsp1_device *vsp1,
 	 * make sure it is present in the pipeline's list of entities if it
 	 * wasn't already.
 	 */
-	if (!use_uif) {
+	if (drm_pipe->uif && !use_uif) {
 		drm_pipe->uif->pipe = NULL;
-	} else if (!drm_pipe->uif->pipe) {
+	} else if (drm_pipe->uif && !drm_pipe->uif->pipe) {
 		drm_pipe->uif->pipe = pipe;
 		list_add_tail(&drm_pipe->uif->list_pipe, &pipe->entities);
 	}

From 2025a48cfd92d541c5ee47deee97f8a46d00c4ac Mon Sep 17 00:00:00 2001
From: Dafna Hirschfeld <dafna.hirschfeld@collabora.com>
Date: Mon, 1 Mar 2021 18:18:35 +0100
Subject: [PATCH 0672/1820] media: rkisp1: params: fix wrong bits settings

The histogram mode is set using 'rkisp1_params_set_bits'.
Only the bits of the mode should be the value argument for
that function. Otherwise bits outside the mode mask are
turned on which is not what was intended.

Fixes: bae1155cf579 ("media: staging: rkisp1: add output device for parameters")
Signed-off-by: Dafna Hirschfeld <dafna.hirschfeld@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/platform/rockchip/rkisp1/rkisp1-params.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c
index aa5f45749543..a60c302ef267 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c
@@ -1288,7 +1288,6 @@ static void rkisp1_params_config_parameter(struct rkisp1_params *params)
 	memset(hst.hist_weight, 0x01, sizeof(hst.hist_weight));
 	rkisp1_hst_config(params, &hst);
 	rkisp1_param_set_bits(params, RKISP1_CIF_ISP_HIST_PROP,
-			      ~RKISP1_CIF_ISP_HIST_PROP_MODE_MASK |
 			      rkisp1_hst_params_default_config.mode);
 
 	/* set the  range */

From e6ad55988b968bd4c54fd182d0bd3d7fcb969779 Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Date: Wed, 3 Mar 2021 14:47:17 -0800
Subject: [PATCH 0673/1820] nvme: set max_zone_append_sectors
 nvme_revalidate_zones

The chunk_sectors value affects max_zone_append_sectors.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Tested-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/zns.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index c7e3ec561ba0..bc2f344f0ae0 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -9,7 +9,13 @@
 
 int nvme_revalidate_zones(struct nvme_ns *ns)
 {
-	return blk_revalidate_disk_zones(ns->disk, NULL);
+	struct request_queue *q = ns->queue;
+	int ret;
+
+	ret = blk_revalidate_disk_zones(ns->disk, NULL);
+	if (!ret)
+		blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
+	return ret;
 }
 
 static int nvme_set_max_append(struct nvme_ctrl *ctrl)
@@ -107,7 +113,6 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1);
 	blk_queue_max_active_zones(q, le32_to_cpu(id->mar) + 1);
-	blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
 free_data:
 	kfree(id);
 	return status;

From d95c1f4179a7f3ea8aa728ed00252a8ed0f8158f Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 26 Feb 2021 08:17:25 +0100
Subject: [PATCH 0674/1820] nvme: simplify error logic in nvme_validate_ns()

We only should remove namespaces when we get fatal error back from
the device or when the namespace IDs have changed.
So instead of painfully masking out error numbers which might indicate
that the error should be ignored we could use an NVME status code
to indicated when the namespace should be removed.
That simplifies the final logic and makes it less error-prone.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e68a8c4ac5a6..e084120c3453 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1440,7 +1440,7 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 		goto out_free_id;
 	}
 
-	error = -ENODEV;
+	error = NVME_SC_INVALID_NS | NVME_SC_DNR;
 	if ((*id)->ncap == 0) /* namespace not allocated or attached */
 		goto out_free_id;
 
@@ -4038,7 +4038,7 @@ static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid)
 static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_ids *ids)
 {
 	struct nvme_id_ns *id;
-	int ret = -ENODEV;
+	int ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
 
 	if (test_bit(NVME_NS_DEAD, &ns->flags))
 		goto out;
@@ -4047,7 +4047,7 @@ static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_ids *ids)
 	if (ret)
 		goto out;
 
-	ret = -ENODEV;
+	ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
 	if (!nvme_ns_ids_equal(&ns->head->ids, ids)) {
 		dev_err(ns->ctrl->device,
 			"identifiers changed for nsid %d\n", ns->head->ns_id);
@@ -4065,7 +4065,7 @@ out:
 	 *
 	 * TODO: we should probably schedule a delayed retry here.
 	 */
-	if (ret && ret != -ENOMEM && !(ret > 0 && !(ret & NVME_SC_DNR)))
+	if (ret > 0 && (ret & NVME_SC_DNR))
 		nvme_ns_remove(ns);
 }
 

From d3589381987ec879b03f8ce3039df57e87f05901 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 26 Feb 2021 08:17:26 +0100
Subject: [PATCH 0675/1820] nvme: add NVME_REQ_CANCELLED flag in
 nvme_cancel_request()

NVME_REQ_CANCELLED is translated into -EINTR in nvme_submit_sync_cmd(),
so we should be setting this flags during nvme_cancel_request() to
ensure that the callers to nvme_submit_sync_cmd() will get the correct
error code when the controller is reset.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chao Leng <lengchao@huawei.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e084120c3453..63bb1da0861e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -380,6 +380,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 		return true;
 
 	nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
+	nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 	blk_mq_complete_request(req);
 	return true;
 }

From 3c7aafbc8d3d4d90430dfa126847a796c3e4ecfc Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 26 Feb 2021 08:17:27 +0100
Subject: [PATCH 0676/1820] nvme-fc: set NVME_REQ_CANCELLED in
 nvme_fc_terminate_exchange()

nvme_fc_terminate_exchange() is being called when exchanges are
being deleted, and as such we should be setting the NVME_REQ_CANCELLED
flag to have identical behaviour on all transports.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/fc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 20dadd86e981..ef12a619daec 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2443,6 +2443,7 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
 
+	op->nreq.flags |= NVME_REQ_CANCELLED;
 	__nvme_fc_abort_op(ctrl, op);
 	return true;
 }

From ae3afe6308b43bbf49953101d4ba2c1c481133a8 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 26 Feb 2021 08:17:28 +0100
Subject: [PATCH 0677/1820] nvme-fc: return NVME_SC_HOST_ABORTED_CMD when a
 command has been aborted

When a command has been aborted we should return NVME_SC_HOST_ABORTED_CMD
to be consistent with the other transports.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/fc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index ef12a619daec..97e3424c7b03 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1956,7 +1956,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 				sizeof(op->rsp_iu), DMA_FROM_DEVICE);
 
 	if (opstate == FCPOP_STATE_ABORTED)
-		status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+		status = cpu_to_le16(NVME_SC_HOST_ABORTED_CMD << 1);
 	else if (freq->status) {
 		status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
 		dev_info(ctrl->ctrl.device,

From f20ef34d71abc1fc56b322aaa251f90f94320140 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Mon, 8 Mar 2021 16:51:26 -0800
Subject: [PATCH 0678/1820] nvme-fc: fix racing controller reset and create
 association

Recent patch to prevent calling __nvme_fc_abort_outstanding_ios in
interrupt context results in a possible race condition. A controller
reset results in errored io completions, which schedules error
work. The change of error work to a work element allows it to fire
after the ctrl state transition to NVME_CTRL_CONNECTING, causing
any outstanding io (used to initialize the controller) to fail and
cause problems for connect_work.

Add a state check to only schedule error work if not in the RESETTING
state.

Fixes: 19fce0470f05 ("nvme-fc: avoid calling _nvme_fc_abort_outstanding_ios from interrupt context")
Signed-off-by: Nigel Kirkland <nkirkland2304@gmail.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/fc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 97e3424c7b03..73d073748389 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2055,7 +2055,7 @@ done:
 		nvme_fc_complete_rq(rq);
 
 check_error:
-	if (terminate_assoc)
+	if (terminate_assoc && ctrl->ctrl.state != NVME_CTRL_RESETTING)
 		queue_work(nvme_reset_wq, &ctrl->ioerr_work);
 }
 

From 0ec84df4953bd42c6583a555773f1d4996a061eb Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Date: Mon, 8 Mar 2021 20:58:21 -0800
Subject: [PATCH 0679/1820] nvme-core: check ctrl css before setting up zns

Ensure multiple Command Sets are supported before starting to setup a
ZNS namespace.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
[hch: move the check around a bit]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 63bb1da0861e..82ad5eef9d0c 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4096,6 +4096,12 @@ static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 				nsid);
 			break;
 		}
+		if (!nvme_multi_css(ctrl)) {
+			dev_warn(ctrl->device,
+				"command set not reported for nsid: %d\n",
+				ns->head->ns_id);
+			break;
+		}
 		nvme_alloc_ns(ctrl, nsid, &ids);
 		break;
 	default:

From abec6561fc4e0fbb19591a0b35676d8c783b5493 Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Wed, 10 Mar 2021 21:44:13 -0800
Subject: [PATCH 0680/1820] nvme-rdma: Fix a use after free in
 nvmet_rdma_write_data_done

In nvmet_rdma_write_data_done, rsp is recoverd by wc->wr_cqe and freed by
nvmet_rdma_release_rsp(). But after that, pr_info() used the freed
chunk's member object and could leak the freed chunk address with
wc->wr_cqe by computing the offset.

Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/rdma.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 06b6b742bb21..6c1f3ab7649c 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -802,9 +802,8 @@ static void nvmet_rdma_write_data_done(struct ib_cq *cq, struct ib_wc *wc)
 		nvmet_req_uninit(&rsp->req);
 		nvmet_rdma_release_rsp(rsp);
 		if (wc->status != IB_WC_WR_FLUSH_ERR) {
-			pr_info("RDMA WRITE for CQE 0x%p failed with status %s (%d).\n",
-				wc->wr_cqe, ib_wc_status_msg(wc->status),
-				wc->status);
+			pr_info("RDMA WRITE for CQE failed with status %s (%d).\n",
+				ib_wc_status_msg(wc->status), wc->status);
 			nvmet_rdma_error_comp(queue);
 		}
 		return;

From abbb5f5929ec6c52574c430c5475c158a65c2a8c Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmtrmonakhov@yandex-team.ru>
Date: Wed, 10 Mar 2021 12:06:41 +0000
Subject: [PATCH 0681/1820] nvme-pci: add the DISABLE_WRITE_ZEROES quirk for a
 Samsung PM1725a

This adds a quirk for Samsung PM1725a drive which fixes timeouts and
I/O errors due to the fact that the controller does not properly
handle the Write Zeroes command, dmesg log:

nvme nvme0: I/O 528 QID 10 timeout, aborting
nvme nvme0: I/O 529 QID 10 timeout, aborting
nvme nvme0: I/O 530 QID 10 timeout, aborting
nvme nvme0: I/O 531 QID 10 timeout, aborting
nvme nvme0: I/O 532 QID 10 timeout, aborting
nvme nvme0: I/O 533 QID 10 timeout, aborting
nvme nvme0: I/O 534 QID 10 timeout, aborting
nvme nvme0: I/O 535 QID 10 timeout, aborting
nvme nvme0: Abort status: 0x0
nvme nvme0: Abort status: 0x0
nvme nvme0: Abort status: 0x0
nvme nvme0: Abort status: 0x0
nvme nvme0: Abort status: 0x0
nvme nvme0: Abort status: 0x0
nvme nvme0: Abort status: 0x0
nvme nvme0: Abort status: 0x0
nvme nvme0: I/O 528 QID 10 timeout, reset controller
nvme nvme0: controller is down; will reset: CSTS=0x3, PCI_STATUS=0x10
nvme nvme0: Device not ready; aborting reset, CSTS=0x3
nvme nvme0: Device not ready; aborting reset, CSTS=0x3
nvme nvme0: Removing after probe failure status: -19
nvme0n1: detected capacity change from 6251233968 to 0
blk_update_request: I/O error, dev nvme0n1, sector 32776 op 0x1:(WRITE) flags 0x3000 phys_seg 6 prio class 0
blk_update_request: I/O error, dev nvme0n1, sector 113319936 op 0x9:(WRITE_ZEROES) flags 0x800 phys_seg 0 prio class 0
Buffer I/O error on dev nvme0n1p2, logical block 1, lost async page write
blk_update_request: I/O error, dev nvme0n1, sector 113319680 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0
Buffer I/O error on dev nvme0n1p2, logical block 2, lost async page write
blk_update_request: I/O error, dev nvme0n1, sector 113319424 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0
Buffer I/O error on dev nvme0n1p2, logical block 3, lost async page write
blk_update_request: I/O error, dev nvme0n1, sector 113319168 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0
Buffer I/O error on dev nvme0n1p2, logical block 4, lost async page write
blk_update_request: I/O error, dev nvme0n1, sector 113318912 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0
Buffer I/O error on dev nvme0n1p2, logical block 5, lost async page write
blk_update_request: I/O error, dev nvme0n1, sector 113318656 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0
Buffer I/O error on dev nvme0n1p2, logical block 6, lost async page write
blk_update_request: I/O error, dev nvme0n1, sector 113318400 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0
blk_update_request: I/O error, dev nvme0n1, sector 113318144 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0
blk_update_request: I/O error, dev nvme0n1, sector 113317888 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0

Signed-off-by: Dmitry Monakhov <dmtrmonakhov@yandex-team.ru>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/pci.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 17ab3320d28b..7249ae74f71f 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3246,6 +3246,7 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE(0x144d, 0xa822),   /* Samsung PM1725a */
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
+				NVME_QUIRK_DISABLE_WRITE_ZEROES|
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x1987, 0x5016),	/* Phison E16 */
 		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },

From 14fbbc8297728e880070f7b077b3301a8c698ef9 Mon Sep 17 00:00:00 2001
From: Daiyue Zhang <zhangdaiyue1@huawei.com>
Date: Mon, 1 Mar 2021 14:10:53 +0800
Subject: [PATCH 0682/1820] configfs: fix a use-after-free in
 __configfs_open_file

Commit b0841eefd969 ("configfs: provide exclusion between IO and removals")
uses ->frag_dead to mark the fragment state, thus no bothering with extra
refcount on config_item when opening a file. The configfs_get_config_item
was removed in __configfs_open_file, but not with config_item_put. So the
refcount on config_item will lost its balance, causing use-after-free
issues in some occasions like this:

Test:
1. Mount configfs on /config with read-only items:
drwxrwx--- 289 root   root            0 2021-04-01 11:55 /config
drwxr-xr-x   2 root   root            0 2021-04-01 11:54 /config/a
--w--w--w-   1 root   root         4096 2021-04-01 11:53 /config/a/1.txt
......

2. Then run:
for file in /config
do
echo $file
grep -R 'key' $file
done

3. __configfs_open_file will be called in parallel, the first one
got called will do:
if (file->f_mode & FMODE_READ) {
	if (!(inode->i_mode & S_IRUGO))
		goto out_put_module;
			config_item_put(buffer->item);
				kref_put()
					package_details_release()
						kfree()

the other one will run into use-after-free issues like this:
BUG: KASAN: use-after-free in __configfs_open_file+0x1bc/0x3b0
Read of size 8 at addr fffffff155f02480 by task grep/13096
CPU: 0 PID: 13096 Comm: grep VIP: 00 Tainted: G        W       4.14.116-kasan #1
TGID: 13096 Comm: grep
Call trace:
dump_stack+0x118/0x160
kasan_report+0x22c/0x294
__asan_load8+0x80/0x88
__configfs_open_file+0x1bc/0x3b0
configfs_open_file+0x28/0x34
do_dentry_open+0x2cc/0x5c0
vfs_open+0x80/0xe0
path_openat+0xd8c/0x2988
do_filp_open+0x1c4/0x2fc
do_sys_open+0x23c/0x404
SyS_openat+0x38/0x48

Allocated by task 2138:
kasan_kmalloc+0xe0/0x1ac
kmem_cache_alloc_trace+0x334/0x394
packages_make_item+0x4c/0x180
configfs_mkdir+0x358/0x740
vfs_mkdir2+0x1bc/0x2e8
SyS_mkdirat+0x154/0x23c
el0_svc_naked+0x34/0x38

Freed by task 13096:
kasan_slab_free+0xb8/0x194
kfree+0x13c/0x910
package_details_release+0x524/0x56c
kref_put+0xc4/0x104
config_item_put+0x24/0x34
__configfs_open_file+0x35c/0x3b0
configfs_open_file+0x28/0x34
do_dentry_open+0x2cc/0x5c0
vfs_open+0x80/0xe0
path_openat+0xd8c/0x2988
do_filp_open+0x1c4/0x2fc
do_sys_open+0x23c/0x404
SyS_openat+0x38/0x48
el0_svc_naked+0x34/0x38

To fix this issue, remove the config_item_put in
__configfs_open_file to balance the refcount of config_item.

Fixes: b0841eefd969 ("configfs: provide exclusion between IO and removals")
Signed-off-by: Daiyue Zhang <zhangdaiyue1@huawei.com>
Signed-off-by: Yi Chen <chenyi77@huawei.com>
Signed-off-by: Ge Qiu <qiuge@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/configfs/file.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index 1f0270229d7b..da8351d1e455 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -378,7 +378,7 @@ static int __configfs_open_file(struct inode *inode, struct file *file, int type
 
 	attr = to_attr(dentry);
 	if (!attr)
-		goto out_put_item;
+		goto out_free_buffer;
 
 	if (type & CONFIGFS_ITEM_BIN_ATTR) {
 		buffer->bin_attr = to_bin_attr(dentry);
@@ -391,7 +391,7 @@ static int __configfs_open_file(struct inode *inode, struct file *file, int type
 	/* Grab the module reference for this attribute if we have one */
 	error = -ENODEV;
 	if (!try_module_get(buffer->owner))
-		goto out_put_item;
+		goto out_free_buffer;
 
 	error = -EACCES;
 	if (!buffer->item->ci_type)
@@ -435,8 +435,6 @@ static int __configfs_open_file(struct inode *inode, struct file *file, int type
 
 out_put_module:
 	module_put(buffer->owner);
-out_put_item:
-	config_item_put(buffer->item);
 out_free_buffer:
 	up_read(&frag->frag_sem);
 	kfree(buffer);

From 2fb164f0ce95e504e2688b4f984893c29ebd19ab Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Tue, 9 Mar 2021 01:01:07 +0100
Subject: [PATCH 0683/1820] mtd: rawnand: mtk: Fix WAITRDY break condition and
 timeout

This fixes NAND_OP_WAITRDY_INSTR operation in the driver. Without this
change the driver waits till the system is busy, but we should wait till
the busy flag is cleared. The readl_poll_timeout() function gets a break
condition, not a wait condition.

In addition fix the timeout. The timeout_ms is given in ms, but the
readl_poll_timeout() function takes the timeout in us. Multiple the
given timeout by 1000 to convert it.

Without this change, the driver does not work at all, it doesn't even
identify the NAND chip.

Fixes: 5197360f9e09 ("mtd: rawnand: mtk: Convert the driver to exec_op()")
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20210309000107.1368404-1-hauke@hauke-m.de
---
 drivers/mtd/nand/raw/mtk_nand.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index 57f1f1708994..5c5c92132287 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -488,8 +488,8 @@ static int mtk_nfc_exec_instr(struct nand_chip *chip,
 		return 0;
 	case NAND_OP_WAITRDY_INSTR:
 		return readl_poll_timeout(nfc->regs + NFI_STA, status,
-					  status & STA_BUSY, 20,
-					  instr->ctx.waitrdy.timeout_ms);
+					  !(status & STA_BUSY), 20,
+					  instr->ctx.waitrdy.timeout_ms * 1000);
 	default:
 		break;
 	}

From a4a251f8c23518899d2078c320cf9ce2fa459c9f Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stf_xl@wp.pl>
Date: Thu, 11 Mar 2021 13:53:50 +0200
Subject: [PATCH 0684/1820] usb: xhci: do not perform Soft Retry for some xHCI
 hosts

On some systems rt2800usb and mt7601u devices are unable to operate since
commit f8f80be501aa ("xhci: Use soft retry to recover faster from
transaction errors")

Seems that some xHCI controllers can not perform Soft Retry correctly,
affecting those devices.

To avoid the problem add xhci->quirks flag that restore pre soft retry
xhci behaviour for affected xHCI controllers. Currently those are
AMD_PROMONTORYA_4 and AMD_PROMONTORYA_2, since it was confirmed
by the users: on those xHCI hosts issue happen and is gone after
disabling Soft Retry.

[minor commit message rewording for checkpatch -Mathias]

Fixes: f8f80be501aa ("xhci: Use soft retry to recover faster from transaction errors")
Cc: <stable@vger.kernel.org> # 4.20+
Reported-by: Bernhard <bernhard.gebetsberger@gmx.at>
Tested-by: Bernhard <bernhard.gebetsberger@gmx.at>
Signed-off-by: Stanislaw Gruszka <stf_xl@wp.pl>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202541
Link: https://lore.kernel.org/r/20210311115353.2137560-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-pci.c  | 5 +++++
 drivers/usb/host/xhci-ring.c | 3 ++-
 drivers/usb/host/xhci.h      | 1 +
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 84da8406d5b4..1f989a49c8c6 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -295,6 +295,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	     pdev->device == 0x9026)
 		xhci->quirks |= XHCI_RESET_PLL_ON_DISCONNECT;
 
+	if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+	    (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_2 ||
+	     pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4))
+		xhci->quirks |= XHCI_NO_SOFT_RETRY;
+
 	if (xhci->quirks & XHCI_RESET_ON_RESUME)
 		xhci_dbg_trace(xhci, trace_xhci_dbg_quirks,
 				"QUIRK: Resetting on resume");
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 5e548a1c93ab..ce38076901e2 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -2484,7 +2484,8 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td,
 		remaining	= 0;
 		break;
 	case COMP_USB_TRANSACTION_ERROR:
-		if ((ep_ring->err_count++ > MAX_SOFT_RETRY) ||
+		if (xhci->quirks & XHCI_NO_SOFT_RETRY ||
+		    (ep_ring->err_count++ > MAX_SOFT_RETRY) ||
 		    le32_to_cpu(slot_ctx->tt_info) & TT_SLOT)
 			break;
 
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index d41de5dc0452..ca822ad3b65b 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1891,6 +1891,7 @@ struct xhci_hcd {
 #define XHCI_SKIP_PHY_INIT	BIT_ULL(37)
 #define XHCI_DISABLE_SPARSE	BIT_ULL(38)
 #define XHCI_SG_TRB_CACHE_SIZE_QUIRK	BIT_ULL(39)
+#define XHCI_NO_SOFT_RETRY	BIT_ULL(40)
 
 	unsigned int		num_active_eps;
 	unsigned int		limit_active_eps;

From 253f588c70f66184b1f3a9bbb428b49bbda73e80 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Thu, 11 Mar 2021 13:53:51 +0200
Subject: [PATCH 0685/1820] xhci: Improve detection of device initiated wake
 signal.

A xHC USB 3 port might miss the first wake signal from a USB 3 device
if the port LFPS reveiver isn't enabled fast enough after xHC resume.

xHC host will anyway be resumed by a PME# signal, but will go back to
suspend if no port activity is seen.
The device resends the U3 LFPS wake signal after a 100ms delay, but
by then host is already suspended, starting all over from the
beginning of this issue.

USB 3 specs say U3 wake LFPS signal is sent for max 10ms, then device
needs to delay 100ms before resending the wake.

Don't suspend immediately if port activity isn't detected in resume.
Instead add a retry. If there is no port activity then delay for 120ms,
and re-check for port activity.

Cc: <stable@vger.kernel.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20210311115353.2137560-3-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index bd27bd670104..48a68fcf2b36 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1088,6 +1088,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 	struct usb_hcd		*secondary_hcd;
 	int			retval = 0;
 	bool			comp_timer_running = false;
+	bool			pending_portevent = false;
 
 	if (!hcd->state)
 		return 0;
@@ -1226,13 +1227,22 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 
  done:
 	if (retval == 0) {
-		/* Resume root hubs only when have pending events. */
-		if (xhci_pending_portevent(xhci)) {
+		/*
+		 * Resume roothubs only if there are pending events.
+		 * USB 3 devices resend U3 LFPS wake after a 100ms delay if
+		 * the first wake signalling failed, give it that chance.
+		 */
+		pending_portevent = xhci_pending_portevent(xhci);
+		if (!pending_portevent) {
+			msleep(120);
+			pending_portevent = xhci_pending_portevent(xhci);
+		}
+
+		if (pending_portevent) {
 			usb_hcd_resume_root_hub(xhci->shared_hcd);
 			usb_hcd_resume_root_hub(hcd);
 		}
 	}
-
 	/*
 	 * If system is subject to the Quirk, Compliance Mode Timer needs to
 	 * be re-initialized Always after a system resume. Ports are subject

From b71c669ad8390dd1c866298319ff89fe68b45653 Mon Sep 17 00:00:00 2001
From: Forest Crossman <cyrozap@gmail.com>
Date: Thu, 11 Mar 2021 13:53:52 +0200
Subject: [PATCH 0686/1820] usb: xhci: Fix ASMedia ASM1042A and ASM3242 DMA
 addressing

I've confirmed that both the ASMedia ASM1042A and ASM3242 have the same
problem as the ASM1142 and ASM2142/ASM3142, where they lose some of the
upper bits of 64-bit DMA addresses. As with the other chips, this can
cause problems on systems where the upper bits matter, and adding the
XHCI_NO_64BIT_SUPPORT quirk completely fixes the issue.

Cc: stable@vger.kernel.org
Signed-off-by: Forest Crossman <cyrozap@gmail.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20210311115353.2137560-4-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-pci.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 1f989a49c8c6..5bbccc9a0179 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -66,6 +66,7 @@
 #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI		0x1142
 #define PCI_DEVICE_ID_ASMEDIA_1142_XHCI			0x1242
 #define PCI_DEVICE_ID_ASMEDIA_2142_XHCI			0x2142
+#define PCI_DEVICE_ID_ASMEDIA_3242_XHCI			0x3242
 
 static const char hcd_name[] = "xhci_hcd";
 
@@ -276,11 +277,14 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
-		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI)
+		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI) {
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+		xhci->quirks |= XHCI_NO_64BIT_SUPPORT;
+	}
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
 	    (pdev->device == PCI_DEVICE_ID_ASMEDIA_1142_XHCI ||
-	     pdev->device == PCI_DEVICE_ID_ASMEDIA_2142_XHCI))
+	     pdev->device == PCI_DEVICE_ID_ASMEDIA_2142_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_ASMEDIA_3242_XHCI))
 		xhci->quirks |= XHCI_NO_64BIT_SUPPORT;
 
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&

From d26c00e7276fc92b18c253d69e872f6b03832bad Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Thu, 11 Mar 2021 13:53:53 +0200
Subject: [PATCH 0687/1820] xhci: Fix repeated xhci wake after suspend due to
 uncleared internal wake state

If port terminations are detected in suspend, but link never reaches U0
then xHCI may have an internal uncleared wake state that will cause an
immediate wake after suspend.

This wake state is normally cleared when driver clears the PORT_CSC bit,
which is set after a device is enabled and in U0.

Write 1 to clear PORT_CSC for ports that don't have anything connected
when suspending. This makes sure any pending internal wake states in
xHCI are cleared.

Cc: stable@vger.kernel.org
Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20210311115353.2137560-5-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 62 ++++++++++++++++++++---------------------
 1 file changed, 30 insertions(+), 32 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 48a68fcf2b36..1975016f46bf 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -883,44 +883,42 @@ static void xhci_clear_command_ring(struct xhci_hcd *xhci)
 	xhci_set_cmd_ring_deq(xhci);
 }
 
-static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
+/*
+ * Disable port wake bits if do_wakeup is not set.
+ *
+ * Also clear a possible internal port wake state left hanging for ports that
+ * detected termination but never successfully enumerated (trained to 0U).
+ * Internal wake causes immediate xHCI wake after suspend. PORT_CSC write done
+ * at enumeration clears this wake, force one here as well for unconnected ports
+ */
+
+static void xhci_disable_hub_port_wake(struct xhci_hcd *xhci,
+				       struct xhci_hub *rhub,
+				       bool do_wakeup)
 {
-	struct xhci_port **ports;
-	int port_index;
 	unsigned long flags;
 	u32 t1, t2, portsc;
+	int i;
 
 	spin_lock_irqsave(&xhci->lock, flags);
 
-	/* disable usb3 ports Wake bits */
-	port_index = xhci->usb3_rhub.num_ports;
-	ports = xhci->usb3_rhub.ports;
-	while (port_index--) {
-		t1 = readl(ports[port_index]->addr);
-		portsc = t1;
-		t1 = xhci_port_state_to_neutral(t1);
-		t2 = t1 & ~PORT_WAKE_BITS;
-		if (t1 != t2) {
-			writel(t2, ports[port_index]->addr);
-			xhci_dbg(xhci, "disable wake bits port %d-%d, portsc: 0x%x, write: 0x%x\n",
-				 xhci->usb3_rhub.hcd->self.busnum,
-				 port_index + 1, portsc, t2);
-		}
-	}
+	for (i = 0; i < rhub->num_ports; i++) {
+		portsc = readl(rhub->ports[i]->addr);
+		t1 = xhci_port_state_to_neutral(portsc);
+		t2 = t1;
+
+		/* clear wake bits if do_wake is not set */
+		if (!do_wakeup)
+			t2 &= ~PORT_WAKE_BITS;
+
+		/* Don't touch csc bit if connected or connect change is set */
+		if (!(portsc & (PORT_CSC | PORT_CONNECT)))
+			t2 |= PORT_CSC;
 
-	/* disable usb2 ports Wake bits */
-	port_index = xhci->usb2_rhub.num_ports;
-	ports = xhci->usb2_rhub.ports;
-	while (port_index--) {
-		t1 = readl(ports[port_index]->addr);
-		portsc = t1;
-		t1 = xhci_port_state_to_neutral(t1);
-		t2 = t1 & ~PORT_WAKE_BITS;
 		if (t1 != t2) {
-			writel(t2, ports[port_index]->addr);
-			xhci_dbg(xhci, "disable wake bits port %d-%d, portsc: 0x%x, write: 0x%x\n",
-				 xhci->usb2_rhub.hcd->self.busnum,
-				 port_index + 1, portsc, t2);
+			writel(t2, rhub->ports[i]->addr);
+			xhci_dbg(xhci, "config port %d-%d wake bits, portsc: 0x%x, write: 0x%x\n",
+				 rhub->hcd->self.busnum, i + 1, portsc, t2);
 		}
 	}
 	spin_unlock_irqrestore(&xhci->lock, flags);
@@ -983,8 +981,8 @@ int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup)
 		return -EINVAL;
 
 	/* Clear root port wake on bits if wakeup not allowed. */
-	if (!do_wakeup)
-		xhci_disable_port_wake_on_bits(xhci);
+	xhci_disable_hub_port_wake(xhci, &xhci->usb3_rhub, do_wakeup);
+	xhci_disable_hub_port_wake(xhci, &xhci->usb2_rhub, do_wakeup);
 
 	if (!HCD_HW_ACCESSIBLE(hcd))
 		return 0;

From 7ba8f2b2d652cd8d8a2ab61f4be66973e70f9f88 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 10 Mar 2021 18:15:11 +0100
Subject: [PATCH 0688/1820] arm64: mm: use a 48-bit ID map when possible on
 52-bit VA builds

52-bit VA kernels can run on hardware that is only 48-bit capable, but
configure the ID map as 52-bit by default. This was not a problem until
recently, because the special T0SZ value for a 52-bit VA space was never
programmed into the TCR register anwyay, and because a 52-bit ID map
happens to use the same number of translation levels as a 48-bit one.

This behavior was changed by commit 1401bef703a4 ("arm64: mm: Always update
TCR_EL1 from __cpu_set_tcr_t0sz()"), which causes the unsupported T0SZ
value for a 52-bit VA to be programmed into TCR_EL1. While some hardware
simply ignores this, Mark reports that Amberwing systems choke on this,
resulting in a broken boot. But even before that commit, the unsupported
idmap_t0sz value was exposed to KVM and used to program TCR_EL2 incorrectly
as well.

Given that we already have to deal with address spaces being either 48-bit
or 52-bit in size, the cleanest approach seems to be to simply default to
a 48-bit VA ID map, and only switch to a 52-bit one if the placement of the
kernel in DRAM requires it. This is guaranteed not to happen unless the
system is actually 52-bit VA capable.

Fixes: 90ec95cda91a ("arm64: mm: Introduce VA_BITS_MIN")
Reported-by: Mark Salter <msalter@redhat.com>
Link: http://lore.kernel.org/r/20210310003216.410037-1-msalter@redhat.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20210310171515.416643-2-ardb@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/mmu_context.h | 5 +----
 arch/arm64/kernel/head.S             | 2 +-
 arch/arm64/mm/mmu.c                  | 2 +-
 3 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 70ce8c1d2b07..0f467d550f27 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -65,10 +65,7 @@ extern u64 idmap_ptrs_per_pgd;
 
 static inline bool __cpu_uses_extended_idmap(void)
 {
-	if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52))
-		return false;
-
-	return unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS));
+	return unlikely(idmap_t0sz != TCR_T0SZ(vabits_actual));
 }
 
 /*
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 8b469f164091..840bda1869e9 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -319,7 +319,7 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
 	 */
 	adrp	x5, __idmap_text_end
 	clz	x5, x5
-	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
+	cmp	x5, TCR_T0SZ(VA_BITS_MIN) // default T0SZ small enough?
 	b.ge	1f			// .. then skip VA range extension
 
 	adr_l	x6, idmap_t0sz
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 9c8aa1b44cd5..7484ea4f6ba0 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -40,7 +40,7 @@
 #define NO_BLOCK_MAPPINGS	BIT(0)
 #define NO_CONT_MAPPINGS	BIT(1)
 
-u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
+u64 idmap_t0sz = TCR_T0SZ(VA_BITS_MIN);
 u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
 
 u64 __section(".mmuoff.data.write") vabits_actual;

From 30b2675761b8a1a2b6ef56b535ef51b789bb7150 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 10 Mar 2021 18:15:12 +0100
Subject: [PATCH 0689/1820] arm64: mm: remove unused
 __cpu_uses_extended_idmap[_level()]

These routines lost all existing users during the latest merge window so
we can remove them. This avoids the need to fix them in the context of
fixing a regression related to the ID map on 52-bit VA kernels.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20210310171515.416643-3-ardb@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/mmu_context.h | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 0f467d550f27..bd02e99b1a4c 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -63,20 +63,6 @@ static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
 extern u64 idmap_t0sz;
 extern u64 idmap_ptrs_per_pgd;
 
-static inline bool __cpu_uses_extended_idmap(void)
-{
-	return unlikely(idmap_t0sz != TCR_T0SZ(vabits_actual));
-}
-
-/*
- * True if the extended ID map requires an extra level of translation table
- * to be configured.
- */
-static inline bool __cpu_uses_extended_idmap_level(void)
-{
-	return ARM64_HW_PGTABLE_LEVELS(64 - idmap_t0sz) > CONFIG_PGTABLE_LEVELS;
-}
-
 /*
  * Ensure TCR.T0SZ is set to the provided value.
  */

From d450293c55005a3b0a25d209e981ac425483fead Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Thu, 11 Mar 2021 10:05:58 +0800
Subject: [PATCH 0690/1820] regulator: mt6315: Fix off-by-one for .n_voltages

The valid selector is 0 ~ 0xbf, so the .n_voltages should be 0xc0.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Link: https://lore.kernel.org/r/20210311020558.579597-1-axel.lin@ingics.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/mt6315-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/mt6315-regulator.c b/drivers/regulator/mt6315-regulator.c
index fc7654624dd6..9edc34981ee0 100644
--- a/drivers/regulator/mt6315-regulator.c
+++ b/drivers/regulator/mt6315-regulator.c
@@ -41,7 +41,7 @@ struct mt6315_chip {
 		.type = REGULATOR_VOLTAGE,			\
 		.id = _bid,					\
 		.owner = THIS_MODULE,				\
-		.n_voltages = 0xbf,				\
+		.n_voltages = 0xc0,				\
 		.linear_ranges = mt_volt_range1,		\
 		.n_linear_ranges = ARRAY_SIZE(mt_volt_range1),	\
 		.vsel_reg = _vsel,				\

From ea94191e584b146878f0b7fd4b767500d7aae870 Mon Sep 17 00:00:00 2001
From: Meng Li <Meng.Li@windriver.com>
Date: Thu, 11 Mar 2021 17:12:20 +0800
Subject: [PATCH 0691/1820] spi: cadence: set cqspi to the driver_data field of
 struct device

When initialize cadence qspi controller, it is need to set cqspi
to the driver_data field of struct device, because it will be
used in function cqspi_remove/suspend/resume(). Otherwise, there
will be a crash trace as below when invoking these finctions.

Fixes: 31fb632b5d43 ("spi: Move cadence-quadspi driver to drivers/spi/")
Cc: stable@vger.kernel.org
Signed-off-by: Meng Li <Meng.Li@windriver.com>
Link: https://lore.kernel.org/r/20210311091220.3615-1-Meng.Li@windriver.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-cadence-quadspi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 442cc7c53a47..52ddb3255d88 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1433,6 +1433,7 @@ static int cqspi_probe(struct platform_device *pdev)
 	cqspi = spi_master_get_devdata(master);
 
 	cqspi->pdev = pdev;
+	platform_set_drvdata(pdev, cqspi);
 
 	/* Obtain configuration from OF. */
 	ret = cqspi_of_get_pdata(cqspi);

From a8affc03a9b375e19bc81573de0c9108317d78c7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 11 Mar 2021 12:01:37 +0100
Subject: [PATCH 0692/1820] block: rename BIO_MAX_PAGES to BIO_MAX_VECS

Ever since the addition of multipage bio_vecs BIO_MAX_PAGES has been
horribly confusingly misnamed.  Rename it to BIO_MAX_VECS to stop
confusing users of the bio API.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20210311110137.1132391-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c                    | 14 +++++++-------
 block/blk-crypto-fallback.c    |  2 +-
 block/blk-lib.c                |  2 +-
 block/blk-map.c                |  2 +-
 block/bounce.c                 |  6 +++---
 drivers/block/drbd/drbd_int.h  |  2 +-
 drivers/md/bcache/super.c      |  2 +-
 drivers/md/dm-crypt.c          |  8 ++++----
 drivers/md/dm-writecache.c     |  4 ++--
 drivers/md/raid5-cache.c       |  4 ++--
 drivers/md/raid5-ppl.c         |  2 +-
 drivers/nvme/target/passthru.c |  6 +++---
 fs/block_dev.c                 |  6 +++---
 fs/btrfs/extent_io.c           |  2 +-
 fs/btrfs/scrub.c               |  2 +-
 fs/crypto/bio.c                |  6 +++---
 fs/erofs/zdata.c               |  2 +-
 fs/ext4/page-io.c              |  2 +-
 fs/f2fs/checkpoint.c           |  2 +-
 fs/f2fs/data.c                 |  4 ++--
 fs/f2fs/segment.c              |  2 +-
 fs/f2fs/segment.h              |  4 ++--
 fs/f2fs/super.c                |  4 ++--
 fs/gfs2/lops.c                 |  2 +-
 fs/iomap/buffered-io.c         |  4 ++--
 fs/iomap/direct-io.c           |  4 ++--
 fs/mpage.c                     |  2 +-
 fs/nilfs2/segbuf.c             |  2 +-
 fs/squashfs/block.c            |  2 +-
 fs/zonefs/super.c              |  2 +-
 include/linux/bio.h            |  4 ++--
 31 files changed, 56 insertions(+), 56 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index a1c4d2900c7a..26b7f721cda8 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -33,7 +33,7 @@ static struct biovec_slab {
 	{ .nr_vecs = 16, .name = "biovec-16" },
 	{ .nr_vecs = 64, .name = "biovec-64" },
 	{ .nr_vecs = 128, .name = "biovec-128" },
-	{ .nr_vecs = BIO_MAX_PAGES, .name = "biovec-max" },
+	{ .nr_vecs = BIO_MAX_VECS, .name = "biovec-max" },
 };
 
 static struct biovec_slab *biovec_slab(unsigned short nr_vecs)
@@ -46,7 +46,7 @@ static struct biovec_slab *biovec_slab(unsigned short nr_vecs)
 		return &bvec_slabs[1];
 	case 65 ... 128:
 		return &bvec_slabs[2];
-	case 129 ... BIO_MAX_PAGES:
+	case 129 ... BIO_MAX_VECS:
 		return &bvec_slabs[3];
 	default:
 		BUG();
@@ -151,9 +151,9 @@ out:
 
 void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs)
 {
-	BIO_BUG_ON(nr_vecs > BIO_MAX_PAGES);
+	BIO_BUG_ON(nr_vecs > BIO_MAX_VECS);
 
-	if (nr_vecs == BIO_MAX_PAGES)
+	if (nr_vecs == BIO_MAX_VECS)
 		mempool_free(bv, pool);
 	else if (nr_vecs > BIO_INLINE_VECS)
 		kmem_cache_free(biovec_slab(nr_vecs)->slab, bv);
@@ -186,15 +186,15 @@ struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
 	/*
 	 * Try a slab allocation first for all smaller allocations.  If that
 	 * fails and __GFP_DIRECT_RECLAIM is set retry with the mempool.
-	 * The mempool is sized to handle up to BIO_MAX_PAGES entries.
+	 * The mempool is sized to handle up to BIO_MAX_VECS entries.
 	 */
-	if (*nr_vecs < BIO_MAX_PAGES) {
+	if (*nr_vecs < BIO_MAX_VECS) {
 		struct bio_vec *bvl;
 
 		bvl = kmem_cache_alloc(bvs->slab, bvec_alloc_gfp(gfp_mask));
 		if (likely(bvl) || !(gfp_mask & __GFP_DIRECT_RECLAIM))
 			return bvl;
-		*nr_vecs = BIO_MAX_PAGES;
+		*nr_vecs = BIO_MAX_VECS;
 	}
 
 	return mempool_alloc(pool, gfp_mask);
diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
index c176b7af56a7..c322176a1e09 100644
--- a/block/blk-crypto-fallback.c
+++ b/block/blk-crypto-fallback.c
@@ -219,7 +219,7 @@ static bool blk_crypto_split_bio_if_needed(struct bio **bio_ptr)
 
 	bio_for_each_segment(bv, bio, iter) {
 		num_sectors += bv.bv_len >> SECTOR_SHIFT;
-		if (++i == BIO_MAX_PAGES)
+		if (++i == BIO_MAX_VECS)
 			break;
 	}
 	if (num_sectors < bio_sectors(bio)) {
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 752f9c722062..7b256131b20b 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -296,7 +296,7 @@ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects)
 {
 	sector_t pages = DIV_ROUND_UP_SECTOR_T(nr_sects, PAGE_SIZE / 512);
 
-	return min(pages, (sector_t)BIO_MAX_PAGES);
+	return min(pages, (sector_t)BIO_MAX_VECS);
 }
 
 static int __blkdev_issue_zero_pages(struct block_device *bdev,
diff --git a/block/blk-map.c b/block/blk-map.c
index 369e204d14d0..1ffef782fcf2 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -249,7 +249,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 	if (!iov_iter_count(iter))
 		return -EINVAL;
 
-	bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_PAGES));
+	bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_VECS));
 	if (!bio)
 		return -ENOMEM;
 	bio->bi_opf |= req_op(rq);
diff --git a/block/bounce.c b/block/bounce.c
index 87983a35079c..6c441f4f1cd4 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -229,10 +229,10 @@ static struct bio *bounce_clone_bio(struct bio *bio_src)
 	 *  - The point of cloning the biovec is to produce a bio with a biovec
 	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
 	 *
-	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
+	 *  - The original bio could've had more than BIO_MAX_VECS biovecs; if
 	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
 	 *    But the clone should succeed as long as the number of biovecs we
-	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
+	 *    actually need to allocate is fewer than BIO_MAX_VECS.
 	 *
 	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
 	 *    that does not own the bio - reason being drivers don't use it for
@@ -299,7 +299,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	int sectors = 0;
 
 	bio_for_each_segment(from, *bio_orig, iter) {
-		if (i++ < BIO_MAX_PAGES)
+		if (i++ < BIO_MAX_VECS)
 			sectors += from.bv_len >> 9;
 		if (page_to_pfn(from.bv_page) > q->limits.bounce_pfn)
 			bounce = true;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 7d9cc433b758..5d9181382ce1 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1324,7 +1324,7 @@ struct bm_extent {
  * A followup commit may allow even bigger BIO sizes,
  * once we thought that through. */
 #define DRBD_MAX_BIO_SIZE (1U << 20)
-#if DRBD_MAX_BIO_SIZE > (BIO_MAX_PAGES << PAGE_SHIFT)
+#if DRBD_MAX_BIO_SIZE > (BIO_MAX_VECS << PAGE_SHIFT)
 #error Architecture not supported: DRBD_MAX_BIO_SIZE > BIO_MAX_SIZE
 #endif
 #define DRBD_MAX_BIO_SIZE_SAFE (1U << 12)       /* Works always = 4k */
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 71691f32959b..03e1fe4de53d 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -965,7 +965,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	q->limits.max_hw_sectors	= UINT_MAX;
 	q->limits.max_sectors		= UINT_MAX;
 	q->limits.max_segment_size	= UINT_MAX;
-	q->limits.max_segments		= BIO_MAX_PAGES;
+	q->limits.max_segments		= BIO_MAX_VECS;
 	blk_queue_max_discard_sectors(q, UINT_MAX);
 	q->limits.discard_granularity	= 512;
 	q->limits.io_min		= block_size;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 11c105ecd165..b0ab080f2567 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -229,7 +229,7 @@ static DEFINE_SPINLOCK(dm_crypt_clients_lock);
 static unsigned dm_crypt_clients_n = 0;
 static volatile unsigned long dm_crypt_pages_per_client;
 #define DM_CRYPT_MEMORY_PERCENT			2
-#define DM_CRYPT_MIN_PAGES_PER_CLIENT		(BIO_MAX_PAGES * 16)
+#define DM_CRYPT_MIN_PAGES_PER_CLIENT		(BIO_MAX_VECS * 16)
 
 static void clone_init(struct dm_crypt_io *, struct bio *);
 static void kcryptd_queue_crypt(struct dm_crypt_io *io);
@@ -3246,7 +3246,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start + additional_req_size,
 		      ARCH_KMALLOC_MINALIGN);
 
-	ret = mempool_init(&cc->page_pool, BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc);
+	ret = mempool_init(&cc->page_pool, BIO_MAX_VECS, crypt_page_alloc, crypt_page_free, cc);
 	if (ret) {
 		ti->error = "Cannot allocate page mempool";
 		goto bad;
@@ -3373,9 +3373,9 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 	/*
 	 * Check if bio is too large, split as needed.
 	 */
-	if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_PAGES << PAGE_SHIFT)) &&
+	if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_VECS << PAGE_SHIFT)) &&
 	    (bio_data_dir(bio) == WRITE || cc->on_disk_tag_size))
-		dm_accept_partial_bio(bio, ((BIO_MAX_PAGES << PAGE_SHIFT) >> SECTOR_SHIFT));
+		dm_accept_partial_bio(bio, ((BIO_MAX_VECS << PAGE_SHIFT) >> SECTOR_SHIFT));
 
 	/*
 	 * Ensure that bio is a multiple of internal sector encryption size
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 844c4be11768..4f72b6f66c3a 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -1892,10 +1892,10 @@ restart:
 			list_add(&g->lru, &wbl.list);
 			wbl.size++;
 			g->write_in_progress = true;
-			g->wc_list_contiguous = BIO_MAX_PAGES;
+			g->wc_list_contiguous = BIO_MAX_VECS;
 			f = g;
 			e->wc_list_contiguous++;
-			if (unlikely(e->wc_list_contiguous == BIO_MAX_PAGES)) {
+			if (unlikely(e->wc_list_contiguous == BIO_MAX_VECS)) {
 				if (unlikely(wc->writeback_all)) {
 					next_node = rb_next(&f->rb_node);
 					if (likely(next_node))
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 4337ae0e6af2..0b5dcaabbc15 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -735,7 +735,7 @@ static void r5l_submit_current_io(struct r5l_log *log)
 
 static struct bio *r5l_bio_alloc(struct r5l_log *log)
 {
-	struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, &log->bs);
+	struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS, &log->bs);
 
 	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	bio_set_dev(bio, log->rdev->bdev);
@@ -1634,7 +1634,7 @@ static int r5l_recovery_allocate_ra_pool(struct r5l_log *log,
 {
 	struct page *page;
 
-	ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_PAGES, &log->bs);
+	ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_VECS, &log->bs);
 	if (!ctx->ra_bio)
 		return -ENOMEM;
 
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index e8c118e05dfd..3ddc2aa0b530 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -496,7 +496,7 @@ static void ppl_submit_iounit(struct ppl_io_unit *io)
 		if (!bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0)) {
 			struct bio *prev = bio;
 
-			bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES,
+			bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS,
 					       &ppl_conf->bs);
 			bio->bi_opf = prev->bi_opf;
 			bio->bi_write_hint = prev->bi_write_hint;
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 26c587ccd152..2798944899b7 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -50,9 +50,9 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
 
 	/*
 	 * nvmet_passthru_map_sg is limitted to using a single bio so limit
-	 * the mdts based on BIO_MAX_PAGES as well
+	 * the mdts based on BIO_MAX_VECS as well
 	 */
-	max_hw_sectors = min_not_zero(BIO_MAX_PAGES << (PAGE_SHIFT - 9),
+	max_hw_sectors = min_not_zero(BIO_MAX_VECS << (PAGE_SHIFT - 9),
 				      max_hw_sectors);
 
 	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
@@ -191,7 +191,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
 	struct bio *bio;
 	int i;
 
-	if (req->sg_cnt > BIO_MAX_PAGES)
+	if (req->sg_cnt > BIO_MAX_VECS)
 		return -EINVAL;
 
 	if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) {
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 03166b3dea4d..92ed7d5df677 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -432,7 +432,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		dio->size += bio->bi_iter.bi_size;
 		pos += bio->bi_iter.bi_size;
 
-		nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_PAGES);
+		nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
 		if (!nr_pages) {
 			bool polled = false;
 
@@ -500,8 +500,8 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	if (!iov_iter_count(iter))
 		return 0;
 
-	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_PAGES + 1);
-	if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_PAGES)
+	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
+	if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS)
 		return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
 
 	return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4dfb3ead1175..db8cb98c020c 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3048,7 +3048,7 @@ struct bio *btrfs_bio_alloc(u64 first_byte)
 {
 	struct bio *bio;
 
-	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &btrfs_bioset);
+	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_VECS, &btrfs_bioset);
 	bio->bi_iter.bi_sector = first_byte >> 9;
 	btrfs_io_bio_init(btrfs_io_bio(bio));
 	return bio;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 582df11d298a..6daa4309c974 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1428,7 +1428,7 @@ static void scrub_recheck_block_on_raid56(struct btrfs_fs_info *fs_info,
 	if (!first_page->dev->bdev)
 		goto out;
 
-	bio = btrfs_io_bio_alloc(BIO_MAX_PAGES);
+	bio = btrfs_io_bio_alloc(BIO_MAX_VECS);
 	bio_set_dev(bio, first_page->dev->bdev);
 
 	for (page_num = 0; page_num < sblock->page_count; page_num++) {
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
index b048a0e38516..68a2de6b5a9b 100644
--- a/fs/crypto/bio.c
+++ b/fs/crypto/bio.c
@@ -52,7 +52,7 @@ static int fscrypt_zeroout_range_inline_crypt(const struct inode *inode,
 	int num_pages = 0;
 
 	/* This always succeeds since __GFP_DIRECT_RECLAIM is set. */
-	bio = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
+	bio = bio_alloc(GFP_NOFS, BIO_MAX_VECS);
 
 	while (len) {
 		unsigned int blocks_this_page = min(len, blocks_per_page);
@@ -74,7 +74,7 @@ static int fscrypt_zeroout_range_inline_crypt(const struct inode *inode,
 		len -= blocks_this_page;
 		lblk += blocks_this_page;
 		pblk += blocks_this_page;
-		if (num_pages == BIO_MAX_PAGES || !len ||
+		if (num_pages == BIO_MAX_VECS || !len ||
 		    !fscrypt_mergeable_bio(bio, inode, lblk)) {
 			err = submit_bio_wait(bio);
 			if (err)
@@ -126,7 +126,7 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
 		return fscrypt_zeroout_range_inline_crypt(inode, lblk, pblk,
 							  len);
 
-	BUILD_BUG_ON(ARRAY_SIZE(pages) > BIO_MAX_PAGES);
+	BUILD_BUG_ON(ARRAY_SIZE(pages) > BIO_MAX_VECS);
 	nr_pages = min_t(unsigned int, ARRAY_SIZE(pages),
 			 (len + blocks_per_page - 1) >> blocks_per_page_bits);
 
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 6cb356c4217b..3851e1a64f73 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1235,7 +1235,7 @@ submit_bio_retry:
 			}
 
 			if (!bio) {
-				bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
+				bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS);
 
 				bio->bi_end_io = z_erofs_decompressqueue_endio;
 				bio_set_dev(bio, sb->s_bdev);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 03a44a0de86a..f038d578d8d8 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -398,7 +398,7 @@ static void io_submit_init_bio(struct ext4_io_submit *io,
 	 * bio_alloc will _always_ be able to allocate a bio if
 	 * __GFP_DIRECT_RECLAIM is set, see comments for bio_alloc_bioset().
 	 */
-	bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
+	bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS);
 	fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio_set_dev(bio, bh->b_bdev);
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 174a0819ad96..be5415a0dbbc 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -292,7 +292,7 @@ void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
 	f2fs_put_page(page, 0);
 
 	if (readahead)
-		f2fs_ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true);
+		f2fs_ra_meta_pages(sbi, index, BIO_MAX_VECS, META_POR, true);
 }
 
 static int __f2fs_write_meta_page(struct page *page,
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 7c95818639a6..4e5257c763d0 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -857,7 +857,7 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
 		f2fs_submit_merged_ipu_write(fio->sbi, &bio, NULL);
 alloc_new:
 	if (!bio) {
-		bio = __bio_alloc(fio, BIO_MAX_PAGES);
+		bio = __bio_alloc(fio, BIO_MAX_VECS);
 		__attach_io_flag(fio);
 		f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
 				       fio->page->index, fio, GFP_NOIO);
@@ -932,7 +932,7 @@ alloc_new:
 			fio->retry = true;
 			goto skip;
 		}
-		io->bio = __bio_alloc(fio, BIO_MAX_PAGES);
+		io->bio = __bio_alloc(fio, BIO_MAX_VECS);
 		f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host,
 				       bio_page->index, fio, GFP_NOIO);
 		io->fio = *fio;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 993004f06a77..c2866561263e 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -4381,7 +4381,7 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
 	block_t total_node_blocks = 0;
 
 	do {
-		readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
+		readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_VECS,
 							META_SIT, true);
 
 		start = start_blk * sit_i->sents_per_block;
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 229814b4f4a6..e9a7a637d688 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -851,7 +851,7 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 	else if (type == NODE)
 		return 8 * sbi->blocks_per_seg;
 	else if (type == META)
-		return 8 * BIO_MAX_PAGES;
+		return 8 * BIO_MAX_VECS;
 	else
 		return 0;
 }
@@ -868,7 +868,7 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
 		return 0;
 
 	nr_to_write = wbc->nr_to_write;
-	desired = BIO_MAX_PAGES;
+	desired = BIO_MAX_VECS;
 	if (type == NODE)
 		desired <<= 1;
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 7069793752f1..82592b19b4e0 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -753,9 +753,9 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 		case Opt_io_size_bits:
 			if (args->from && match_int(args, &arg))
 				return -EINVAL;
-			if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_PAGES)) {
+			if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_VECS)) {
 				f2fs_warn(sbi, "Not support %d, larger than %d",
-					  1 << arg, BIO_MAX_PAGES);
+					  1 << arg, BIO_MAX_VECS);
 				return -EINVAL;
 			}
 			F2FS_OPTION(sbi).write_io_size_bits = arg;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index dc1b93a877c6..a82f4747aa8d 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -267,7 +267,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno,
 				      bio_end_io_t *end_io)
 {
 	struct super_block *sb = sdp->sd_vfs;
-	struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
+	struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS);
 
 	bio->bi_iter.bi_sector = blkno << sdp->sd_fsb2bb_shift;
 	bio_set_dev(bio, sb->s_bdev);
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 7ffcd7ef33d4..414769a6ad11 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1221,7 +1221,7 @@ iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc,
 	struct iomap_ioend *ioend;
 	struct bio *bio;
 
-	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &iomap_ioend_bioset);
+	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_VECS, &iomap_ioend_bioset);
 	bio_set_dev(bio, wpc->iomap.bdev);
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
@@ -1252,7 +1252,7 @@ iomap_chain_bio(struct bio *prev)
 {
 	struct bio *new;
 
-	new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
+	new = bio_alloc(GFP_NOFS, BIO_MAX_VECS);
 	bio_copy_dev(new, prev);/* also copies over blkcg information */
 	new->bi_iter.bi_sector = bio_end_sector(prev);
 	new->bi_opf = prev->bi_opf;
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index e2c4991833b8..bdd0d89bbf0a 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -296,7 +296,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 	 */
 	bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua);
 
-	nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_PAGES);
+	nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS);
 	do {
 		size_t n;
 		if (dio->error) {
@@ -338,7 +338,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 		copied += n;
 
 		nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter,
-						 BIO_MAX_PAGES);
+						 BIO_MAX_VECS);
 		iomap_dio_submit_bio(dio, iomap, bio, pos);
 		pos += n;
 	} while (nr_pages);
diff --git a/fs/mpage.c b/fs/mpage.c
index 961234d68779..334e7d09aa65 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -616,7 +616,7 @@ alloc_new:
 				goto out;
 		}
 		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
-				BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH);
+				BIO_MAX_VECS, GFP_NOFS|__GFP_HIGH);
 		if (bio == NULL)
 			goto confused;
 
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 1e75417bfe6e..56872e93823d 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -399,7 +399,7 @@ static void nilfs_segbuf_prepare_write(struct nilfs_segment_buffer *segbuf,
 {
 	wi->bio = NULL;
 	wi->rest_blocks = segbuf->sb_sum.nblocks;
-	wi->max_pages = BIO_MAX_PAGES;
+	wi->max_pages = BIO_MAX_VECS;
 	wi->nr_vecs = min(wi->max_pages, wi->rest_blocks);
 	wi->start = wi->end = 0;
 	wi->blocknr = segbuf->sb_pseg_start;
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 45f44425d856..b9e87ebb1060 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -87,7 +87,7 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length,
 	int error, i;
 	struct bio *bio;
 
-	if (page_count <= BIO_MAX_PAGES)
+	if (page_count <= BIO_MAX_VECS)
 		bio = bio_alloc(GFP_NOIO, page_count);
 	else
 		bio = bio_kmalloc(GFP_NOIO, page_count);
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index b6ff4a21abac..0fe76f376dee 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -684,7 +684,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
 	iov_iter_truncate(from, max);
 
-	nr_pages = iov_iter_npages(from, BIO_MAX_PAGES);
+	nr_pages = iov_iter_npages(from, BIO_MAX_VECS);
 	if (!nr_pages)
 		return 0;
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 983ed2fe7c85..d0246c92a6e8 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -20,11 +20,11 @@
 #define BIO_BUG_ON
 #endif
 
-#define BIO_MAX_PAGES		256U
+#define BIO_MAX_VECS		256U
 
 static inline unsigned int bio_max_segs(unsigned int nr_segs)
 {
-	return min(nr_segs, BIO_MAX_PAGES);
+	return min(nr_segs, BIO_MAX_VECS);
 }
 
 #define bio_prio(bio)			(bio)->bi_ioprio

From f053cf7aa66cd9d592b0fc967f4d887c2abff1b7 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 2 Mar 2021 12:04:19 -0800
Subject: [PATCH 0693/1820] ext4: fix error handling in
 ext4_end_enable_verity()

ext4 didn't properly clean up if verity failed to be enabled on a file:

- It left verity metadata (pages past EOF) in the page cache, which
  would be exposed to userspace if the file was later extended.

- It didn't truncate the verity metadata at all (either from cache or
  from disk) if an error occurred while setting the verity bit.

Fix these bugs by adding a call to truncate_inode_pages() and ensuring
that we truncate the verity metadata (both from cache and from disk) in
all error paths.  Also rework the code to cleanly separate the success
path from the error paths, which makes it much easier to understand.

Reported-by: Yunlei He <heyunlei@hihonor.com>
Fixes: c93d8f885809 ("ext4: add basic fs-verity support")
Cc: stable@vger.kernel.org # v5.4+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Link: https://lore.kernel.org/r/20210302200420.137977-2-ebiggers@kernel.org
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/verity.c | 93 +++++++++++++++++++++++++++++-------------------
 1 file changed, 57 insertions(+), 36 deletions(-)

diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index 5b7ba8f71153..00e3cbde472e 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -201,55 +201,76 @@ static int ext4_end_enable_verity(struct file *filp, const void *desc,
 	struct inode *inode = file_inode(filp);
 	const int credits = 2; /* superblock and inode for ext4_orphan_del() */
 	handle_t *handle;
+	struct ext4_iloc iloc;
 	int err = 0;
-	int err2;
-
-	if (desc != NULL) {
-		/* Succeeded; write the verity descriptor. */
-		err = ext4_write_verity_descriptor(inode, desc, desc_size,
-						   merkle_tree_size);
-
-		/* Write all pages before clearing VERITY_IN_PROGRESS. */
-		if (!err)
-			err = filemap_write_and_wait(inode->i_mapping);
-	}
-
-	/* If we failed, truncate anything we wrote past i_size. */
-	if (desc == NULL || err)
-		ext4_truncate(inode);
 
 	/*
-	 * We must always clean up by clearing EXT4_STATE_VERITY_IN_PROGRESS and
-	 * deleting the inode from the orphan list, even if something failed.
-	 * If everything succeeded, we'll also set the verity bit in the same
-	 * transaction.
+	 * If an error already occurred (which fs/verity/ signals by passing
+	 * desc == NULL), then only clean-up is needed.
 	 */
+	if (desc == NULL)
+		goto cleanup;
 
-	ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+	/* Append the verity descriptor. */
+	err = ext4_write_verity_descriptor(inode, desc, desc_size,
+					   merkle_tree_size);
+	if (err)
+		goto cleanup;
+
+	/*
+	 * Write all pages (both data and verity metadata).  Note that this must
+	 * happen before clearing EXT4_STATE_VERITY_IN_PROGRESS; otherwise pages
+	 * beyond i_size won't be written properly.  For crash consistency, this
+	 * also must happen before the verity inode flag gets persisted.
+	 */
+	err = filemap_write_and_wait(inode->i_mapping);
+	if (err)
+		goto cleanup;
+
+	/*
+	 * Finally, set the verity inode flag and remove the inode from the
+	 * orphan list (in a single transaction).
+	 */
 
 	handle = ext4_journal_start(inode, EXT4_HT_INODE, credits);
 	if (IS_ERR(handle)) {
-		ext4_orphan_del(NULL, inode);
-		return PTR_ERR(handle);
+		err = PTR_ERR(handle);
+		goto cleanup;
 	}
 
-	err2 = ext4_orphan_del(handle, inode);
-	if (err2)
-		goto out_stop;
+	err = ext4_orphan_del(handle, inode);
+	if (err)
+		goto stop_and_cleanup;
 
-	if (desc != NULL && !err) {
-		struct ext4_iloc iloc;
+	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		goto stop_and_cleanup;
+
+	ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
+	ext4_set_inode_flags(inode, false);
+	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+	if (err)
+		goto stop_and_cleanup;
 
-		err = ext4_reserve_inode_write(handle, inode, &iloc);
-		if (err)
-			goto out_stop;
-		ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
-		ext4_set_inode_flags(inode, false);
-		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-	}
-out_stop:
 	ext4_journal_stop(handle);
-	return err ?: err2;
+
+	ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+	return 0;
+
+stop_and_cleanup:
+	ext4_journal_stop(handle);
+cleanup:
+	/*
+	 * Verity failed to be enabled, so clean up by truncating any verity
+	 * metadata that was written beyond i_size (both from cache and from
+	 * disk), removing the inode from the orphan list (if it wasn't done
+	 * already), and clearing EXT4_STATE_VERITY_IN_PROGRESS.
+	 */
+	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	ext4_truncate(inode);
+	ext4_orphan_del(NULL, inode);
+	ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+	return err;
 }
 
 static int ext4_get_verity_descriptor_location(struct inode *inode,

From b4250dd868d1b42c0a65de11ef3afbee67ba5d2f Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <kolga@netapp.com>
Date: Thu, 11 Mar 2021 10:55:00 -0500
Subject: [PATCH 0694/1820] NFSD: fix error handling in NFSv4.0 callbacks

When the server tries to do a callback and a client fails it due to
authentication problems, we need the server to set callback down
flag in RENEW so that client can recover.

Suggested-by: Bruce Fields <bfields@redhat.com>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Benjamin Coddington <bcodding@redhat.com>
Link: https://lore.kernel.org/linux-nfs/FB84E90A-1A03-48B3-8BF7-D9D10AC2C9FE@oracle.com/T/#t
---
 fs/nfsd/nfs4callback.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 052be5bf9ef5..7325592b456e 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1189,6 +1189,7 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
 		switch (task->tk_status) {
 		case -EIO:
 		case -ETIMEDOUT:
+		case -EACCES:
 			nfsd4_mark_cb_down(clp, task->tk_status);
 		}
 		break;

From 9922f50f7178496e709d3d064920b5031f0d9061 Mon Sep 17 00:00:00 2001
From: Srinivasa Rao Mandadapu <srivasam@codeaurora.org>
Date: Thu, 11 Mar 2021 21:15:57 +0530
Subject: [PATCH 0695/1820] ASoC: qcom: lpass-cpu: Fix lpass dai ids parse

The max boundary check while parsing dai ids makes
sound card registration fail after common up dai ids.

Fixes: cd3484f7f138 ("ASoC: qcom: Fix broken support to MI2S TERTIARY and QUATERNARY")

Signed-off-by: Srinivasa Rao Mandadapu <srivasam@codeaurora.org>
Link: https://lore.kernel.org/r/20210311154557.24978-1-srivasam@codeaurora.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/lpass-cpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c
index c642e5f8f28c..be360a402b67 100644
--- a/sound/soc/qcom/lpass-cpu.c
+++ b/sound/soc/qcom/lpass-cpu.c
@@ -739,7 +739,7 @@ static void of_lpass_cpu_parse_dai_data(struct device *dev,
 
 	for_each_child_of_node(dev->of_node, node) {
 		ret = of_property_read_u32(node, "reg", &id);
-		if (ret || id < 0 || id >= data->variant->num_dai) {
+		if (ret || id < 0) {
 			dev_err(dev, "valid dai id not found: %d\n", ret);
 			continue;
 		}

From 5c2469e0a22e035d52f3ba768151cc75e3d4a1cd Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 11 Mar 2021 10:17:56 -0700
Subject: [PATCH 0696/1820] io_uring: force creation of separate context for
 ATTACH_WQ and non-threads

Earlier kernels had SQPOLL threads that could share across anything, as
we grabbed the context we needed on a per-ring basis. This is no longer
the case, so only allow attaching directly if we're in the same thread
group. That is the common use case. For non-group tasks, just setup a
new context and thread as we would've done if sharing wasn't set. This
isn't 100% ideal in terms of CPU utilization for the forked and share
case, but hopefully that isn't much of a concern. If it is, there are
plans in motion for how to improve that. Most importantly, we want to
avoid app side regressions where sharing worked before and now doesn't.
With this patch, functionality is equivalent to previous kernels that
supported IORING_SETUP_ATTACH_WQ with SQPOLL.

Reported-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5c045a9f7ffe..472eab7359f2 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -269,6 +269,7 @@ struct io_sq_data {
 	unsigned		sq_thread_idle;
 	int			sq_cpu;
 	pid_t			task_pid;
+	pid_t			task_tgid;
 
 	unsigned long		state;
 	struct completion	startup;
@@ -7112,6 +7113,10 @@ static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p)
 		fdput(f);
 		return ERR_PTR(-EINVAL);
 	}
+	if (sqd->task_tgid != current->tgid) {
+		fdput(f);
+		return ERR_PTR(-EPERM);
+	}
 
 	refcount_inc(&sqd->refs);
 	fdput(f);
@@ -7122,8 +7127,14 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p)
 {
 	struct io_sq_data *sqd;
 
-	if (p->flags & IORING_SETUP_ATTACH_WQ)
-		return io_attach_sq_data(p);
+	if (p->flags & IORING_SETUP_ATTACH_WQ) {
+		sqd = io_attach_sq_data(p);
+		if (!IS_ERR(sqd))
+			return sqd;
+		/* fall through for EPERM case, setup new sqd/task */
+		if (PTR_ERR(sqd) != -EPERM)
+			return sqd;
+	}
 
 	sqd = kzalloc(sizeof(*sqd), GFP_KERNEL);
 	if (!sqd)
@@ -7833,6 +7844,7 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 		}
 
 		sqd->task_pid = current->pid;
+		sqd->task_tgid = current->tgid;
 		tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE);
 		if (IS_ERR(tsk)) {
 			ret = PTR_ERR(tsk);

From 22053df0a3647560e6aa11cb6ddcb0da04f505cc Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Thu, 11 Mar 2021 16:20:24 +0200
Subject: [PATCH 0697/1820] RDMA/mlx5: Fix typo in destroy_mkey inbox

Set mkey_index to the correct place when preparing the destroy_mkey inbox,
this will fix the following syndrome:

 mlx5_core 0000:08:00.0: mlx5_cmd_check:782:(pid 980716): DEALLOC_PD(0x801)
 op_mod(0x0) failed, status bad resource state(0x9), syndrome (0x31b635)

Link: https://lore.kernel.org/r/20210311142024.1282004-1-leon@kernel.org
Fixes: 1368ead04c36 ("RDMA/mlx5: Use strict get/set operations for obj_id")
Reviewed-by: Ido Kalir <idok@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/devx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index de3c2fc6f361..07b8350929cd 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1116,7 +1116,7 @@ static void devx_obj_build_destroy_cmd(void *in, void *out, void *din,
 	case MLX5_CMD_OP_CREATE_MKEY:
 		MLX5_SET(destroy_mkey_in, din, opcode,
 			 MLX5_CMD_OP_DESTROY_MKEY);
-		MLX5_SET(destroy_mkey_in, in, mkey_index, *obj_id);
+		MLX5_SET(destroy_mkey_in, din, mkey_index, *obj_id);
 		break;
 	case MLX5_CMD_OP_CREATE_CQ:
 		MLX5_SET(destroy_cq_in, din, opcode, MLX5_CMD_OP_DESTROY_CQ);

From 6da262378c99b17b1a1ac2e42aa65acc1bd471c7 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Tue, 20 Oct 2020 16:34:00 +0300
Subject: [PATCH 0698/1820] igc: reinit_locked() should be called with
 rtnl_lock

This commit applies to the igc_reset_task the same changes that
were applied to the igb driver in commit 024a8168b749 ("igb:
reinit_locked() should be called with rtnl_lock")
and fix possible race in reset subtask.

Fixes: 0507ef8a0372 ("igc: Add transmit and receive fastpath and interrupt handlers")
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Dvora Fuxbrumer <dvorax.fuxbrumer@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 7ac9597ddb84..4d989ebc9713 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3831,10 +3831,19 @@ static void igc_reset_task(struct work_struct *work)
 
 	adapter = container_of(work, struct igc_adapter, reset_task);
 
+	rtnl_lock();
+	/* If we're already down or resetting, just bail */
+	if (test_bit(__IGC_DOWN, &adapter->state) ||
+	    test_bit(__IGC_RESETTING, &adapter->state)) {
+		rtnl_unlock();
+		return;
+	}
+
 	igc_rings_dump(adapter);
 	igc_regs_dump(adapter);
 	netdev_err(adapter->netdev, "Reset adapter\n");
 	igc_reinit_locked(adapter);
+	rtnl_unlock();
 }
 
 /**

From 8876529465c368beafd51a70f79d7a738f2aadf4 Mon Sep 17 00:00:00 2001
From: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Date: Sat, 20 Feb 2021 00:36:47 +0800
Subject: [PATCH 0699/1820] igc: Fix Pause Frame Advertising

Fix Pause Frame Advertising when getting the advertisement via ethtool.
Remove setting the "advertising" bit in link_ksettings during default
case when Tx and Rx are in off state with Auto Negotiate off.

Below is the original output of advertisement link during Tx and Rx off:
Advertised pause frame use: Symmetric Receive-only

Expected output:
Advertised pause frame use: No

Fixes: 8c5ad0dae93c ("igc: Add ethtool support")
Signed-off-by: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Reviewed-by: Malli C <mallikarjuna.chilakala@intel.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Dvora Fuxbrumer <dvorax.fuxbrumer@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 824a6c454bca..67a4aed45fc2 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1725,9 +1725,7 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 						     Asym_Pause);
 		break;
 	default:
-		ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
-		ethtool_link_ksettings_add_link_mode(cmd, advertising,
-						     Asym_Pause);
+		break;
 	}
 
 	status = pm_runtime_suspended(&adapter->pdev->dev) ?

From 9a4a1cdc5ab52118c1f2b216f4240830b6528d32 Mon Sep 17 00:00:00 2001
From: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Date: Sat, 20 Feb 2021 00:36:48 +0800
Subject: [PATCH 0700/1820] igc: Fix Supported Pause Frame Link Setting

The Supported Pause Frame always display "No" even though the Advertised
pause frame showing the correct setting based on the pause parameters via
ethtool. Set bit in link_ksettings to "Supported" for Pause Frame.

Before output:
Supported pause frame use: No

Expected output:
Supported pause frame use: Symmetric

Fixes: 8c5ad0dae93c ("igc: Add ethtool support")
Signed-off-by: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Reviewed-by: Malli C <mallikarjuna.chilakala@intel.com>
Tested-by: Dvora Fuxbrumer <dvorax.fuxbrumer@linux.intel.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 67a4aed45fc2..8722294ab90c 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1711,6 +1711,9 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 						     Autoneg);
 	}
 
+	/* Set pause flow control settings */
+	ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
+
 	switch (hw->fc.requested_mode) {
 	case igc_fc_full:
 		ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);

From fc9e5020971d57d7d0b3fef9e2ab2108fcb5588b Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 9 Mar 2021 22:42:56 -0800
Subject: [PATCH 0701/1820] igc: Fix igc_ptp_rx_pktstamp()

The comment describing the timestamps layout in the packet buffer is
wrong and the code is actually retrieving the timestamp in Timer 1
reference instead of Timer 0. This hasn't been a big issue so far
because hardware is configured to report both timestamps using Timer 0
(see IGC_SRRCTL register configuration in igc_ptp_enable_rx_timestamp()
helper). This patch fixes the comment and the code so we retrieve the
timestamp in Timer 0 reference as expected.

This patch also takes the opportunity to get rid of the hw.mac.type check
since it is not required.

Fixes: 81b055205e8ba ("igc: Add support for RX timestamping")
Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Signed-off-by: Vedang Patel <vedang.patel@intel.com>
Signed-off-by: Jithu Joseph <jithu.joseph@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Dvora Fuxbrumer <dvorax.fuxbrumer@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h     |  2 +-
 drivers/net/ethernet/intel/igc/igc_ptp.c | 68 +++++++++++++-----------
 2 files changed, 39 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 5d2809dfd06a..1b08a7dc7bc4 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -547,7 +547,7 @@ void igc_ptp_init(struct igc_adapter *adapter);
 void igc_ptp_reset(struct igc_adapter *adapter);
 void igc_ptp_suspend(struct igc_adapter *adapter);
 void igc_ptp_stop(struct igc_adapter *adapter);
-void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va,
+void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va,
 			 struct sk_buff *skb);
 int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
 int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index ac0b9c85da7c..545f4d0e67cf 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -152,46 +152,54 @@ static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter,
 }
 
 /**
- * igc_ptp_rx_pktstamp - retrieve Rx per packet timestamp
+ * igc_ptp_rx_pktstamp - Retrieve timestamp from Rx packet buffer
  * @q_vector: Pointer to interrupt specific structure
  * @va: Pointer to address containing Rx buffer
  * @skb: Buffer containing timestamp and packet
  *
- * This function is meant to retrieve the first timestamp from the
- * first buffer of an incoming frame. The value is stored in little
- * endian format starting on byte 0. There's a second timestamp
- * starting on byte 8.
- **/
-void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va,
+ * This function retrieves the timestamp saved in the beginning of packet
+ * buffer. While two timestamps are available, one in timer0 reference and the
+ * other in timer1 reference, this function considers only the timestamp in
+ * timer0 reference.
+ */
+void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va,
 			 struct sk_buff *skb)
 {
 	struct igc_adapter *adapter = q_vector->adapter;
-	__le64 *regval = (__le64 *)va;
-	int adjust = 0;
+	u64 regval;
+	int adjust;
 
-	/* The timestamp is recorded in little endian format.
-	 * DWORD: | 0          | 1           | 2          | 3
-	 * Field: | Timer0 Low | Timer0 High | Timer1 Low | Timer1 High
+	/* Timestamps are saved in little endian at the beginning of the packet
+	 * buffer following the layout:
+	 *
+	 * DWORD: | 0              | 1              | 2              | 3              |
+	 * Field: | Timer1 SYSTIML | Timer1 SYSTIMH | Timer0 SYSTIML | Timer0 SYSTIMH |
+	 *
+	 * SYSTIML holds the nanoseconds part while SYSTIMH holds the seconds
+	 * part of the timestamp.
 	 */
-	igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb),
-				   le64_to_cpu(regval[0]));
+	regval = le32_to_cpu(va[2]);
+	regval |= (u64)le32_to_cpu(va[3]) << 32;
+	igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval);
 
-	/* adjust timestamp for the RX latency based on link speed */
-	if (adapter->hw.mac.type == igc_i225) {
-		switch (adapter->link_speed) {
-		case SPEED_10:
-			adjust = IGC_I225_RX_LATENCY_10;
-			break;
-		case SPEED_100:
-			adjust = IGC_I225_RX_LATENCY_100;
-			break;
-		case SPEED_1000:
-			adjust = IGC_I225_RX_LATENCY_1000;
-			break;
-		case SPEED_2500:
-			adjust = IGC_I225_RX_LATENCY_2500;
-			break;
-		}
+	/* Adjust timestamp for the RX latency based on link speed */
+	switch (adapter->link_speed) {
+	case SPEED_10:
+		adjust = IGC_I225_RX_LATENCY_10;
+		break;
+	case SPEED_100:
+		adjust = IGC_I225_RX_LATENCY_100;
+		break;
+	case SPEED_1000:
+		adjust = IGC_I225_RX_LATENCY_1000;
+		break;
+	case SPEED_2500:
+		adjust = IGC_I225_RX_LATENCY_2500;
+		break;
+	default:
+		adjust = 0;
+		netdev_warn_once(adapter->netdev, "Imprecise timestamp\n");
+		break;
 	}
 	skb_hwtstamps(skb)->hwtstamp =
 		ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust);

From 21f857f0321d0d0ea9b1a758bd55dc63d1cb2437 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Wed, 21 Oct 2020 14:59:37 +0300
Subject: [PATCH 0702/1820] e1000e: add rtnl_lock() to e1000_reset_task

A possible race condition was found in e1000_reset_task,
after discovering a similar issue in igb driver via
commit 024a8168b749 ("igb: reinit_locked() should be called
with rtnl_lock").

Added rtnl_lock() and rtnl_unlock() to avoid this.

Fixes: bc7f75fa9788 ("[E1000E]: New pci-express e1000 driver (currently for ICH9 devices only)")
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Tested-by: Dvora Fuxbrumer <dvorax.fuxbrumer@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/netdev.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index e9b82c209c2d..a0948002ddf8 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -5974,15 +5974,19 @@ static void e1000_reset_task(struct work_struct *work)
 	struct e1000_adapter *adapter;
 	adapter = container_of(work, struct e1000_adapter, reset_task);
 
+	rtnl_lock();
 	/* don't run the task if already down */
-	if (test_bit(__E1000_DOWN, &adapter->state))
+	if (test_bit(__E1000_DOWN, &adapter->state)) {
+		rtnl_unlock();
 		return;
+	}
 
 	if (!(adapter->flags & FLAG_RESTART_NOW)) {
 		e1000e_dump(adapter);
 		e_err("Reset adapter unexpectedly\n");
 	}
 	e1000e_reinit_locked(adapter);
+	rtnl_unlock();
 }
 
 /**

From b52912b8293f2c496f42583e65599aee606a0c18 Mon Sep 17 00:00:00 2001
From: Dinghao Liu <dinghao.liu@zju.edu.cn>
Date: Sun, 28 Feb 2021 17:44:23 +0800
Subject: [PATCH 0703/1820] e1000e: Fix error handling in
 e1000_set_d0_lplu_state_82571

There is one e1e_wphy() call in e1000_set_d0_lplu_state_82571
that we have caught its return value but lack further handling.
Check and terminate the execution flow just like other e1e_wphy()
in this function.

Fixes: bc7f75fa9788 ("[E1000E]: New pci-express e1000 driver (currently for ICH9 devices only)")
Signed-off-by: Dinghao Liu <dinghao.liu@zju.edu.cn>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Dvora Fuxbrumer <dvorax.fuxbrumer@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/82571.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c
index 88faf05e23ba..0b1e890dd583 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.c
+++ b/drivers/net/ethernet/intel/e1000e/82571.c
@@ -899,6 +899,8 @@ static s32 e1000_set_d0_lplu_state_82571(struct e1000_hw *hw, bool active)
 	} else {
 		data &= ~IGP02E1000_PM_D0_LPLU;
 		ret_val = e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, data);
+		if (ret_val)
+			return ret_val;
 		/* LPLU and SmartSpeed are mutually exclusive.  LPLU is used
 		 * during Dx states where the power conservation is most
 		 * important.  During driver activity we should enable

From d052d1d685f5125249ab4ff887562c88ba959638 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 11 Mar 2021 10:49:20 -0700
Subject: [PATCH 0704/1820] io_uring: perform IOPOLL reaping if canceler is
 thread itself

We bypass IOPOLL completion polling (and reaping) for the SQPOLL thread,
but if it's the thread itself invoking cancelations, then we still need
to perform it or no one will.

Fixes: 9936c7c2bc76 ("io_uring: deduplicate core cancellations sequence")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 472eab7359f2..49f85f49e1c3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8658,7 +8658,8 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 		}
 
 		/* SQPOLL thread does its own polling */
-		if (!(ctx->flags & IORING_SETUP_SQPOLL) && !files) {
+		if ((!(ctx->flags & IORING_SETUP_SQPOLL) && !files) ||
+		    (ctx->sq_data && ctx->sq_data->thread == current)) {
 			while (!list_empty_careful(&ctx->iopoll_list)) {
 				io_iopoll_try_reap_events(ctx);
 				ret = true;

From 4f8be1f53bf615102d103c0509ffa9596f65b718 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Thu, 28 Jan 2021 17:36:38 -0500
Subject: [PATCH 0705/1820] nfs: we don't support removing system.nfs4_acl

The NFSv4 protocol doesn't have any notion of reomoving an attribute, so
removexattr(path,"system.nfs4_acl") doesn't make sense.

There's no documented return value.  Arguably it could be EOPNOTSUPP but
I'm a little worried an application might take that to mean that we
don't support ACLs or xattrs.  How about EINVAL?

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1002c4f66f3f..c65c4b41e2c1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5889,6 +5889,9 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
 	int ret, i;
 
+	/* You can't remove system.nfs4_acl: */
+	if (buflen == 0)
+		return -EINVAL;
 	if (!nfs4_server_supports_acls(server))
 		return -EOPNOTSUPP;
 	if (npages > ARRAY_SIZE(pages))

From 9ec491447b90ad6a4056a9656b13f0b3a1e83043 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Thu, 11 Mar 2021 16:19:17 +0100
Subject: [PATCH 0706/1820] block: Suppress uevent for hidden device when
 removed

register_disk() suppress uevents for devices with the GENHD_FL_HIDDEN
but enables uevents at the end again in order to announce disk after
possible partitions are created.

When the device is removed the uevents are still on and user land sees
'remove' messages for devices which were never 'add'ed to the system.

  KERNEL[95481.571887] remove   /devices/virtual/nvme-fabrics/ctl/nvme5/nvme0c5n1 (block)

Let's suppress the uevents for GENHD_FL_HIDDEN by not enabling the
uevents at all.

Signed-off-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin Wilck <mwilck@suse.com>
Link: https://lore.kernel.org/r/20210311151917.136091-1-dwagner@suse.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/block/genhd.c b/block/genhd.c
index c55e8f0fced1..8c8f543572e6 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -534,10 +534,8 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 		kobject_create_and_add("holders", &ddev->kobj);
 	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
 
-	if (disk->flags & GENHD_FL_HIDDEN) {
-		dev_set_uevent_suppress(ddev, 0);
+	if (disk->flags & GENHD_FL_HIDDEN)
 		return;
-	}
 
 	disk_scan_partitions(disk);
 

From e5113505904ea1c1c0e1f92c1cfa91fbf4da1694 Mon Sep 17 00:00:00 2001
From: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Date: Thu, 11 Mar 2021 16:25:46 +0900
Subject: [PATCH 0707/1820] block: Discard page cache of zone reset target
 range

When zone reset ioctl and data read race for a same zone on zoned block
devices, the data read leaves stale page cache even though the zone
reset ioctl zero clears all the zone data on the device. To avoid
non-zero data read from the stale page cache after zone reset, discard
page cache of reset target zones in blkdev_zone_mgmt_ioctl(). Introduce
the helper function blkdev_truncate_zone_range() to discard the page
cache. Ensure the page cache discarded by calling the helper function
before and after zone reset in same manner as fallocate does.

This patch can be applied back to the stable kernel version v5.10.y.
Rework is needed for older stable kernels.

Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Fixes: 3ed05a987e0f ("blk-zoned: implement ioctls")
Cc: <stable@vger.kernel.org> # 5.10+
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20210311072546.678999-1-shinichiro.kawasaki@wdc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c | 38 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 36 insertions(+), 2 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 8b9f3fc5a690..c0276b42d9fb 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -318,6 +318,22 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	return 0;
 }
 
+static int blkdev_truncate_zone_range(struct block_device *bdev, fmode_t mode,
+				      const struct blk_zone_range *zrange)
+{
+	loff_t start, end;
+
+	if (zrange->sector + zrange->nr_sectors <= zrange->sector ||
+	    zrange->sector + zrange->nr_sectors > get_capacity(bdev->bd_disk))
+		/* Out of range */
+		return -EINVAL;
+
+	start = zrange->sector << SECTOR_SHIFT;
+	end = ((zrange->sector + zrange->nr_sectors) << SECTOR_SHIFT) - 1;
+
+	return truncate_bdev_range(bdev, mode, start, end);
+}
+
 /*
  * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
  * Called from blkdev_ioctl.
@@ -329,6 +345,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
 	struct request_queue *q;
 	struct blk_zone_range zrange;
 	enum req_opf op;
+	int ret;
 
 	if (!argp)
 		return -EINVAL;
@@ -352,6 +369,11 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
 	switch (cmd) {
 	case BLKRESETZONE:
 		op = REQ_OP_ZONE_RESET;
+
+		/* Invalidate the page cache, including dirty pages. */
+		ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
+		if (ret)
+			return ret;
 		break;
 	case BLKOPENZONE:
 		op = REQ_OP_ZONE_OPEN;
@@ -366,8 +388,20 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
 		return -ENOTTY;
 	}
 
-	return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
-				GFP_KERNEL);
+	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
+			       GFP_KERNEL);
+
+	/*
+	 * Invalidate the page cache again for zone reset: writes can only be
+	 * direct for zoned devices so concurrent writes would not add any page
+	 * to the page cache after/during reset. The page cache may be filled
+	 * again due to concurrent reads though and dropping the pages for
+	 * these is fine.
+	 */
+	if (!ret && cmd == BLKRESETZONE)
+		ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
+
+	return ret;
 }
 
 static inline unsigned long *blk_alloc_zone_bitmap(int node,

From bade4be69a6ea6f38c5894468ede10ee60b6f7a0 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 11 Mar 2021 13:25:01 -0500
Subject: [PATCH 0708/1820] svcrdma: Revert "svcrdma: Reduce Receive doorbell
 rate"

I tested commit 43042b90cae1 ("svcrdma: Reduce Receive doorbell
rate") with mlx4 (IB) and software iWARP and didn't find any
issues. However, I recently got my hardware iWARP setup back on
line (FastLinQ) and it's crashing hard on this commit (confirmed
via bisect).

The failure mode is complex.
 - After a connection is established, the first Receive completes
   normally.
 - But the second and third Receives have garbage in their Receive
   buffers. The server responds with ERR_VERS as a result.
 - When the client tears down the connection to retry, a couple
   of posted Receives flush twice, and that corrupts the recv_ctxt
   free list.
 - __svc_rdma_free then faults or loops infinitely while destroying
   the xprt's recv_ctxts.

Since 43042b90cae1 ("svcrdma: Reduce Receive doorbell rate") does
not fix a bug but is a scalability enhancement, it's safe and
appropriate to revert it while working on a replacement.

Fixes: 43042b90cae1 ("svcrdma: Reduce Receive doorbell rate")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h         |  1 -
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 82 ++++++++++++-------------
 2 files changed, 39 insertions(+), 44 deletions(-)

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 7c693b31965e..1e76ed688044 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -104,7 +104,6 @@ struct svcxprt_rdma {
 
 	wait_queue_head_t    sc_send_wait;	/* SQ exhaustion waitlist */
 	unsigned long	     sc_flags;
-	u32		     sc_pending_recvs;
 	struct list_head     sc_read_complete_q;
 	struct work_struct   sc_work;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 6d28f23ceb35..7d34290e2ff8 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -266,46 +266,33 @@ void svc_rdma_release_rqst(struct svc_rqst *rqstp)
 		svc_rdma_recv_ctxt_put(rdma, ctxt);
 }
 
-static bool svc_rdma_refresh_recvs(struct svcxprt_rdma *rdma,
-				   unsigned int wanted, bool temp)
+static int __svc_rdma_post_recv(struct svcxprt_rdma *rdma,
+				struct svc_rdma_recv_ctxt *ctxt)
 {
-	const struct ib_recv_wr *bad_wr = NULL;
-	struct svc_rdma_recv_ctxt *ctxt;
-	struct ib_recv_wr *recv_chain;
 	int ret;
 
-	recv_chain = NULL;
-	while (wanted--) {
-		ctxt = svc_rdma_recv_ctxt_get(rdma);
-		if (!ctxt)
-			break;
-
-		trace_svcrdma_post_recv(ctxt);
-		ctxt->rc_temp = temp;
-		ctxt->rc_recv_wr.next = recv_chain;
-		recv_chain = &ctxt->rc_recv_wr;
-		rdma->sc_pending_recvs++;
-	}
-	if (!recv_chain)
-		return false;
-
-	ret = ib_post_recv(rdma->sc_qp, recv_chain, &bad_wr);
+	trace_svcrdma_post_recv(ctxt);
+	ret = ib_post_recv(rdma->sc_qp, &ctxt->rc_recv_wr, NULL);
 	if (ret)
 		goto err_post;
-	return true;
+	return 0;
 
 err_post:
-	while (bad_wr) {
-		ctxt = container_of(bad_wr, struct svc_rdma_recv_ctxt,
-				    rc_recv_wr);
-		bad_wr = bad_wr->next;
-		svc_rdma_recv_ctxt_put(rdma, ctxt);
-	}
-
 	trace_svcrdma_rq_post_err(rdma, ret);
-	/* Since we're destroying the xprt, no need to reset
-	 * sc_pending_recvs. */
-	return false;
+	svc_rdma_recv_ctxt_put(rdma, ctxt);
+	return ret;
+}
+
+static int svc_rdma_post_recv(struct svcxprt_rdma *rdma)
+{
+	struct svc_rdma_recv_ctxt *ctxt;
+
+	if (test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags))
+		return 0;
+	ctxt = svc_rdma_recv_ctxt_get(rdma);
+	if (!ctxt)
+		return -ENOMEM;
+	return __svc_rdma_post_recv(rdma, ctxt);
 }
 
 /**
@@ -316,7 +303,20 @@ err_post:
  */
 bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma)
 {
-	return svc_rdma_refresh_recvs(rdma, rdma->sc_max_requests, true);
+	struct svc_rdma_recv_ctxt *ctxt;
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < rdma->sc_max_requests; i++) {
+		ctxt = svc_rdma_recv_ctxt_get(rdma);
+		if (!ctxt)
+			return false;
+		ctxt->rc_temp = true;
+		ret = __svc_rdma_post_recv(rdma, ctxt);
+		if (ret)
+			return false;
+	}
+	return true;
 }
 
 /**
@@ -324,6 +324,8 @@ bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma)
  * @cq: Completion Queue context
  * @wc: Work Completion object
  *
+ * NB: The svc_xprt/svcxprt_rdma is pinned whenever it's possible that
+ * the Receive completion handler could be running.
  */
 static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 {
@@ -331,8 +333,6 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	struct ib_cqe *cqe = wc->wr_cqe;
 	struct svc_rdma_recv_ctxt *ctxt;
 
-	rdma->sc_pending_recvs--;
-
 	/* WARNING: Only wc->wr_cqe and wc->status are reliable */
 	ctxt = container_of(cqe, struct svc_rdma_recv_ctxt, rc_cqe);
 
@@ -340,6 +340,9 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	if (wc->status != IB_WC_SUCCESS)
 		goto flushed;
 
+	if (svc_rdma_post_recv(rdma))
+		goto post_err;
+
 	/* All wc fields are now known to be valid */
 	ctxt->rc_byte_len = wc->byte_len;
 
@@ -350,18 +353,11 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	spin_unlock(&rdma->sc_rq_dto_lock);
 	if (!test_bit(RDMAXPRT_CONN_PENDING, &rdma->sc_flags))
 		svc_xprt_enqueue(&rdma->sc_xprt);
-
-	if (!test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags) &&
-	    rdma->sc_pending_recvs < rdma->sc_max_requests)
-		if (!svc_rdma_refresh_recvs(rdma, RPCRDMA_MAX_RECV_BATCH,
-					    false))
-			goto post_err;
-
 	return;
 
 flushed:
-	svc_rdma_recv_ctxt_put(rdma, ctxt);
 post_err:
+	svc_rdma_recv_ctxt_put(rdma, ctxt);
 	set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
 	svc_xprt_enqueue(&rdma->sc_xprt);
 }

From 7421b1a4d10c633ca5f14c8236d3e2c1de07e52b Mon Sep 17 00:00:00 2001
From: David Gow <davidgow@google.com>
Date: Mon, 22 Feb 2021 21:49:30 -0800
Subject: [PATCH 0709/1820] kunit: tool: Fix a python tuple typing error

The first argument to namedtuple() should match the name of the type,
which wasn't the case for KconfigEntryBase.

Fixing this is enough to make mypy show no python typing errors again.

Fixes 97752c39bd ("kunit: kunit_tool: Allow .kunitconfig to disable config items")
Signed-off-by: David Gow <davidgow@google.com>
Reviewed-by: Daniel Latypov <dlatypov@google.com>
Acked-by: Brendan Higgins <brendanhiggins@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/kunit/kunit_config.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/kunit/kunit_config.py b/tools/testing/kunit/kunit_config.py
index 0b550cbd667d..1e2683dcc0e7 100644
--- a/tools/testing/kunit/kunit_config.py
+++ b/tools/testing/kunit/kunit_config.py
@@ -13,7 +13,7 @@ from typing import List, Set
 CONFIG_IS_NOT_SET_PATTERN = r'^# CONFIG_(\w+) is not set$'
 CONFIG_PATTERN = r'^CONFIG_(\w+)=(\S+|".*")$'
 
-KconfigEntryBase = collections.namedtuple('KconfigEntry', ['name', 'value'])
+KconfigEntryBase = collections.namedtuple('KconfigEntryBase', ['name', 'value'])
 
 class KconfigEntry(KconfigEntryBase):
 

From 7fd53f41f771d250eb08db08650940f017e37c26 Mon Sep 17 00:00:00 2001
From: David Gow <davidgow@google.com>
Date: Mon, 8 Feb 2021 23:10:34 -0800
Subject: [PATCH 0710/1820] kunit: tool: Disable PAGE_POISONING under
 --alltests

kunit_tool maintains a list of config options which are broken under
UML, which we exclude from an otherwise 'make ARCH=um allyesconfig'
build used to run all tests with the --alltests option.

Something in UML allyesconfig is causing segfaults when page poisining
is enabled (and is poisoning with a non-zero value). Previously, this
didn't occur, as allyesconfig enabled the CONFIG_PAGE_POISONING_ZERO
option, which worked around the problem by zeroing memory. This option
has since been removed, and memory is now poisoned with 0xAA, which
triggers segfaults in many different codepaths, preventing UML from
booting.

Note that we have to disable both CONFIG_PAGE_POISONING and
CONFIG_DEBUG_PAGEALLOC, as the latter will 'select' the former on
architectures (such as UML) which don't implement __kernel_map_pages().

Ideally, we'd fix this properly by tracking down the real root cause,
but since this is breaking KUnit's --alltests feature, it's worth
disabling there in the meantime so the kernel can boot to the point
where tests can actually run.

Fixes: f289041ed4cf ("mm, page_poison: remove CONFIG_PAGE_POISONING_ZERO")
Signed-off-by: David Gow <davidgow@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Brendan Higgins <brendanhiggins@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/kunit/configs/broken_on_uml.config | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/kunit/configs/broken_on_uml.config b/tools/testing/kunit/configs/broken_on_uml.config
index a7f0603d33f6..690870043ac0 100644
--- a/tools/testing/kunit/configs/broken_on_uml.config
+++ b/tools/testing/kunit/configs/broken_on_uml.config
@@ -40,3 +40,5 @@
 # CONFIG_RESET_BRCMSTB_RESCAL is not set
 # CONFIG_RESET_INTEL_GW is not set
 # CONFIG_ADI_AXI_ADC is not set
+# CONFIG_DEBUG_PAGEALLOC is not set
+# CONFIG_PAGE_POISONING is not set

From 0b736881c8f1a6cd912f7a9162b9e097b28c1c30 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Tue, 9 Mar 2021 12:09:26 +0000
Subject: [PATCH 0711/1820] powerpc/traps: unrecoverable_exception() is not an
 interrupt handler

unrecoverable_exception() is called from interrupt handlers or
after an interrupt handler has failed.

Make it a standard function to avoid doubling the actions
performed on interrupt entry (e.g.: user time accounting).

Fixes: 3a96570ffceb ("powerpc: convert interrupt handlers to use wrappers")
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/ae96c59fa2cb7f24a8929c58cfa2c909cb8ff1f1.1615291471.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/include/asm/interrupt.h | 3 ++-
 arch/powerpc/kernel/interrupt.c      | 1 -
 arch/powerpc/kernel/traps.c          | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index aedfba29e43a..e8d09a841373 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -410,7 +410,6 @@ DECLARE_INTERRUPT_HANDLER(altivec_assist_exception);
 DECLARE_INTERRUPT_HANDLER(CacheLockingException);
 DECLARE_INTERRUPT_HANDLER(SPEFloatingPointException);
 DECLARE_INTERRUPT_HANDLER(SPEFloatingPointRoundException);
-DECLARE_INTERRUPT_HANDLER(unrecoverable_exception);
 DECLARE_INTERRUPT_HANDLER(WatchdogException);
 DECLARE_INTERRUPT_HANDLER(kernel_bad_stack);
 
@@ -437,6 +436,8 @@ DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode);
 
 DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
 
+void unrecoverable_exception(struct pt_regs *regs);
+
 void replay_system_reset(void);
 void replay_soft_interrupts(void);
 
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 2ef3c4051bb9..c475a229a42a 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -436,7 +436,6 @@ again:
 	return ret;
 }
 
-void unrecoverable_exception(struct pt_regs *regs);
 void preempt_schedule_irq(void);
 
 notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 1583fd1c6010..a44a30b0688c 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -2170,7 +2170,7 @@ DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException)
  * in the MSR is 0.  This indicates that SRR0/1 are live, and that
  * we therefore lost state by taking this exception.
  */
-DEFINE_INTERRUPT_HANDLER(unrecoverable_exception)
+void unrecoverable_exception(struct pt_regs *regs)
 {
 	pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
 		 regs->trap, regs->nip, regs->msr);

From b80350f393703fa2e733921430276c98bbc092de Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Thu, 11 Mar 2021 10:57:36 +0800
Subject: [PATCH 0712/1820] net: sock: simplify tw proto registration

Introduce the new function tw_prot_init (inspired by
req_prot_init) to simplify "proto_register" function.

tw_prot_cleanup will take care of a partially initialized
timewait_sock_ops.

Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 44 ++++++++++++++++++++++++++++----------------
 1 file changed, 28 insertions(+), 16 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 0ed98f20448a..cc31b601ae10 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3440,6 +3440,32 @@ static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot)
 	twsk_prot->twsk_slab = NULL;
 }
 
+static int tw_prot_init(const struct proto *prot)
+{
+	struct timewait_sock_ops *twsk_prot = prot->twsk_prot;
+
+	if (!twsk_prot)
+		return 0;
+
+	twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s",
+					      prot->name);
+	if (!twsk_prot->twsk_slab_name)
+		return -ENOMEM;
+
+	twsk_prot->twsk_slab =
+		kmem_cache_create(twsk_prot->twsk_slab_name,
+				  twsk_prot->twsk_obj_size, 0,
+				  SLAB_ACCOUNT | prot->slab_flags,
+				  NULL);
+	if (!twsk_prot->twsk_slab) {
+		pr_crit("%s: Can't create timewait sock SLAB cache!\n",
+			prot->name);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
 {
 	if (!rsk_prot)
@@ -3496,22 +3522,8 @@ int proto_register(struct proto *prot, int alloc_slab)
 		if (req_prot_init(prot))
 			goto out_free_request_sock_slab;
 
-		if (prot->twsk_prot != NULL) {
-			prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name);
-
-			if (prot->twsk_prot->twsk_slab_name == NULL)
-				goto out_free_request_sock_slab;
-
-			prot->twsk_prot->twsk_slab =
-				kmem_cache_create(prot->twsk_prot->twsk_slab_name,
-						  prot->twsk_prot->twsk_obj_size,
-						  0,
-						  SLAB_ACCOUNT |
-						  prot->slab_flags,
-						  NULL);
-			if (prot->twsk_prot->twsk_slab == NULL)
-				goto out_free_timewait_sock_slab;
-		}
+		if (tw_prot_init(prot))
+			goto out_free_timewait_sock_slab;
 	}
 
 	mutex_lock(&proto_list_mutex);

From a829f033e966d5e4aa27c3ef2b381f51734e4a7f Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Tue, 2 Mar 2021 11:42:13 +0000
Subject: [PATCH 0713/1820] drm/i915: Wedge the GPU if command parser setup
 fails

Commit 311a50e76a33 ("drm/i915: Add support for mandatory cmdparsing")
introduced mandatory command parsing but setup failures were not
translated into wedging the GPU which was probably the intent.

Possible errors come in two categories. Either the sanity check on
internal tables has failed, which should be caught in CI unless an
affected platform would be missed in testing; or memory allocation failure
happened during driver load, which should be extremely unlikely but for
correctness should still be handled.

v2:
 * Tidy coding style. (Chris)

[airlied: cherry-picked to avoid rc1 base]
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Fixes: 311a50e76a33 ("drm/i915: Add support for mandatory cmdparsing")
Cc: Jon Bloomfield <jon.bloomfield@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris.p.wilson@intel.com>
Reviewed-by: Chris Wilson <chris.p.wilson@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210302114213.1102223-1-tvrtko.ursulin@linux.intel.com
(cherry picked from commit 5a1a659762d35a6dc51047c9127c011303c77b7f)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c |  7 ++++++-
 drivers/gpu/drm/i915/i915_cmd_parser.c    | 19 +++++++++++++------
 drivers/gpu/drm/i915/i915_drv.h           |  2 +-
 3 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index fb1b1d096975..9cf555d6842b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -713,9 +713,12 @@ static int engine_setup_common(struct intel_engine_cs *engine)
 		goto err_status;
 	}
 
+	err = intel_engine_init_cmd_parser(engine);
+	if (err)
+		goto err_cmd_parser;
+
 	intel_engine_init_active(engine, ENGINE_PHYSICAL);
 	intel_engine_init_execlists(engine);
-	intel_engine_init_cmd_parser(engine);
 	intel_engine_init__pm(engine);
 	intel_engine_init_retire(engine);
 
@@ -732,6 +735,8 @@ static int engine_setup_common(struct intel_engine_cs *engine)
 
 	return 0;
 
+err_cmd_parser:
+	intel_breadcrumbs_free(engine->breadcrumbs);
 err_status:
 	cleanup_status_page(engine);
 	return err;
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index ced9a96d7c34..5f86f5b2caf6 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -940,7 +940,7 @@ static void fini_hash_table(struct intel_engine_cs *engine)
  * struct intel_engine_cs based on whether the platform requires software
  * command parsing.
  */
-void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
+int intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 {
 	const struct drm_i915_cmd_table *cmd_tables;
 	int cmd_table_count;
@@ -948,7 +948,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 
 	if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) &&
 					  engine->class == COPY_ENGINE_CLASS))
-		return;
+		return 0;
 
 	switch (engine->class) {
 	case RENDER_CLASS:
@@ -1013,19 +1013,19 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 		break;
 	default:
 		MISSING_CASE(engine->class);
-		return;
+		goto out;
 	}
 
 	if (!validate_cmds_sorted(engine, cmd_tables, cmd_table_count)) {
 		drm_err(&engine->i915->drm,
 			"%s: command descriptions are not sorted\n",
 			engine->name);
-		return;
+		goto out;
 	}
 	if (!validate_regs_sorted(engine)) {
 		drm_err(&engine->i915->drm,
 			"%s: registers are not sorted\n", engine->name);
-		return;
+		goto out;
 	}
 
 	ret = init_hash_table(engine, cmd_tables, cmd_table_count);
@@ -1033,10 +1033,17 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 		drm_err(&engine->i915->drm,
 			"%s: initialised failed!\n", engine->name);
 		fini_hash_table(engine);
-		return;
+		goto out;
 	}
 
 	engine->flags |= I915_ENGINE_USING_CMD_PARSER;
+
+out:
+	if (intel_engine_requires_cmd_parser(engine) &&
+	    !intel_engine_using_cmd_parser(engine))
+		return -EINVAL;
+
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 26d69d06aa6d..cb62ddba2035 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1952,7 +1952,7 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
 
 /* i915_cmd_parser.c */
 int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
-void intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
+int intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
 int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 			    struct i915_vma *batch,

From 4042160c2e5433e0759782c402292a90b5bf458d Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Thu, 11 Mar 2021 14:35:27 +1000
Subject: [PATCH 0714/1820] drm/nouveau: fix dma syncing for loops (v2)

The index variable should only be increased in one place.

Noticed this while trying to track down another oops.

v2: use while loop.

Fixes: f295c8cfec83 ("drm/nouveau: fix dma syncing warning with debugging on.")
Signed-off-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210311043527.5376-1-airlied@gmail.com
---
 drivers/gpu/drm/nouveau/nouveau_bo.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 2375711877cf..fabb314a0b2f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -556,7 +556,8 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo)
 	if (nvbo->force_coherent)
 		return;
 
-	for (i = 0; i < ttm_dma->num_pages; ++i) {
+	i = 0;
+	while (i < ttm_dma->num_pages) {
 		struct page *p = ttm_dma->pages[i];
 		size_t num_pages = 1;
 
@@ -587,7 +588,8 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo)
 	if (nvbo->force_coherent)
 		return;
 
-	for (i = 0; i < ttm_dma->num_pages; ++i) {
+	i = 0;
+	while (i < ttm_dma->num_pages) {
 		struct page *p = ttm_dma->pages[i];
 		size_t num_pages = 1;
 

From db74623a3850db99cb9692fda9e836a56b74198d Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Wed, 10 Mar 2021 20:01:40 -0800
Subject: [PATCH 0715/1820] net/qlcnic: Fix a use after free in
 qlcnic_83xx_get_minidump_template

In qlcnic_83xx_get_minidump_template, fw_dump->tmpl_hdr was freed by
vfree(). But unfortunately, it is used when extended is true.

Fixes: 7061b2bdd620e ("qlogic: Deletion of unnecessary checks before two function calls")
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
index 7760a3394e93..7ecb3dfe30bd 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
@@ -1425,6 +1425,7 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter)
 
 	if (fw_dump->tmpl_hdr == NULL || current_version > prev_version) {
 		vfree(fw_dump->tmpl_hdr);
+		fw_dump->tmpl_hdr = NULL;
 
 		if (qlcnic_83xx_md_check_extended_dump_capability(adapter))
 			extended = !qlcnic_83xx_extend_md_capab(adapter);
@@ -1443,6 +1444,8 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter)
 			struct qlcnic_83xx_dump_template_hdr *hdr;
 
 			hdr = fw_dump->tmpl_hdr;
+			if (!hdr)
+				return;
 			hdr->drv_cap_mask = 0x1f;
 			fw_dump->cap_mask = 0x1f;
 			dev_info(&pdev->dev,

From 0c9fdcdba68208270ae85d39600ea97da1718344 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Thu, 14 Jan 2021 19:29:28 +0800
Subject: [PATCH 0716/1820] soc: qcom: geni: shield geni_icc_get() for ACPI
 boot

Currently, GENI devices like i2c-qcom-geni fails to probe in ACPI boot,
if interconnect support is enabled.  That's because interconnect driver
only supports DT right now.  As interconnect is not necessarily required
for basic function of GENI devices, let's shield geni_icc_get() call,
and then all other ICC calls become nop due to NULL icc_path, so that
GENI devices keep working for ACPI boot.

Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Link: https://lore.kernel.org/r/20210114112928.11368-1-shawn.guo@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/soc/qcom/qcom-geni-se.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/soc/qcom/qcom-geni-se.c b/drivers/soc/qcom/qcom-geni-se.c
index f42954e2c98e..c7c03ccfe888 100644
--- a/drivers/soc/qcom/qcom-geni-se.c
+++ b/drivers/soc/qcom/qcom-geni-se.c
@@ -760,6 +760,9 @@ int geni_icc_get(struct geni_se *se, const char *icc_ddr)
 	int i, err;
 	const char *icc_names[] = {"qup-core", "qup-config", icc_ddr};
 
+	if (has_acpi_companion(se->dev))
+		return 0;
+
 	for (i = 0; i < ARRAY_SIZE(se->icc_paths); i++) {
 		if (!icc_names[i])
 			continue;

From a9f81244d2e33e6dfcef120fefd30c96b3f7cdb0 Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Wed, 10 Mar 2021 23:27:35 -0500
Subject: [PATCH 0717/1820] mISDN: fix crash in fritzpci

setup_fritz() in avmfritz.c might fail with -EIO and in this case the
isac.type and isac.write_reg is not initialized and remains 0(NULL).
A subsequent call to isac_release() will dereference isac->write_reg and
crash.

[    1.737444] BUG: kernel NULL pointer dereference, address: 0000000000000000
[    1.737809] #PF: supervisor instruction fetch in kernel mode
[    1.738106] #PF: error_code(0x0010) - not-present page
[    1.738378] PGD 0 P4D 0
[    1.738515] Oops: 0010 [#1] SMP NOPTI
[    1.738711] CPU: 0 PID: 180 Comm: systemd-udevd Not tainted 5.12.0-rc2+ #78
[    1.739077] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-48-gd9c812dda519-p
rebuilt.qemu.org 04/01/2014
[    1.739664] RIP: 0010:0x0
[    1.739807] Code: Unable to access opcode bytes at RIP 0xffffffffffffffd6.
[    1.740200] RSP: 0018:ffffc9000027ba10 EFLAGS: 00010202
[    1.740478] RAX: 0000000000000000 RBX: ffff888102f41840 RCX: 0000000000000027
[    1.740853] RDX: 00000000000000ff RSI: 0000000000000020 RDI: ffff888102f41800
[    1.741226] RBP: ffffc9000027ba20 R08: ffff88817bc18440 R09: ffffc9000027b808
[    1.741600] R10: 0000000000000001 R11: 0000000000000001 R12: ffff888102f41840
[    1.741976] R13: 00000000fffffffb R14: ffff888102f41800 R15: ffff8881008b0000
[    1.742351] FS:  00007fda3a38a8c0(0000) GS:ffff88817bc00000(0000) knlGS:0000000000000000
[    1.742774] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    1.743076] CR2: ffffffffffffffd6 CR3: 00000001021ec000 CR4: 00000000000006f0
[    1.743452] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[    1.743828] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[    1.744206] Call Trace:
[    1.744339]  isac_release+0xcc/0xe0 [mISDNipac]
[    1.744582]  fritzpci_probe.cold+0x282/0x739 [avmfritz]
[    1.744861]  local_pci_probe+0x48/0x80
[    1.745063]  pci_device_probe+0x10f/0x1c0
[    1.745278]  really_probe+0xfb/0x420
[    1.745471]  driver_probe_device+0xe9/0x160
[    1.745693]  device_driver_attach+0x5d/0x70
[    1.745917]  __driver_attach+0x8f/0x150
[    1.746123]  ? device_driver_attach+0x70/0x70
[    1.746354]  bus_for_each_dev+0x7e/0xc0
[    1.746560]  driver_attach+0x1e/0x20
[    1.746751]  bus_add_driver+0x152/0x1f0
[    1.746957]  driver_register+0x74/0xd0
[    1.747157]  ? 0xffffffffc00d8000
[    1.747334]  __pci_register_driver+0x54/0x60
[    1.747562]  AVM_init+0x36/0x1000 [avmfritz]
[    1.747791]  do_one_initcall+0x48/0x1d0
[    1.747997]  ? __cond_resched+0x19/0x30
[    1.748206]  ? kmem_cache_alloc_trace+0x390/0x440
[    1.748458]  ? do_init_module+0x28/0x250
[    1.748669]  do_init_module+0x62/0x250
[    1.748870]  load_module+0x23ee/0x26a0
[    1.749073]  __do_sys_finit_module+0xc2/0x120
[    1.749307]  ? __do_sys_finit_module+0xc2/0x120
[    1.749549]  __x64_sys_finit_module+0x1a/0x20
[    1.749782]  do_syscall_64+0x38/0x90

Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hardware/mISDN/mISDNipac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c
index ec475087fbf9..39f841b42488 100644
--- a/drivers/isdn/hardware/mISDN/mISDNipac.c
+++ b/drivers/isdn/hardware/mISDN/mISDNipac.c
@@ -694,7 +694,7 @@ isac_release(struct isac_hw *isac)
 {
 	if (isac->type & IPAC_TYPE_ISACX)
 		WriteISAC(isac, ISACX_MASK, 0xff);
-	else
+	else if (isac->type != 0)
 		WriteISAC(isac, ISAC_MASK, 0xff);
 	if (isac->dch.timer.function != NULL) {
 		del_timer(&isac->dch.timer);

From 7a1468ba0e02eee24ae1353e8933793a27198e20 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 10 Mar 2021 20:53:42 -0800
Subject: [PATCH 0718/1820] net: phy: broadcom: Add power down exit reset state
 delay

Per the datasheet, when we clear the power down bit, the PHY remains in
an internal reset state for 40us and then resume normal operation.
Account for that delay to avoid any issues in the future if
genphy_resume() changes.

Fixes: fe26821fa614 ("net: phy: broadcom: Wire suspend/resume for BCM54810")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/broadcom.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index fa0be591ae79..ad51f1889435 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -399,6 +399,11 @@ static int bcm54xx_resume(struct phy_device *phydev)
 	if (ret < 0)
 		return ret;
 
+	/* Upon exiting power down, the PHY remains in an internal reset state
+	 * for 40us
+	 */
+	fsleep(40);
+
 	return bcm54xx_config_init(phydev);
 }
 

From 93bde210c4341e79f0cd9cb160d889f4577e40b1 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@nvidia.com>
Date: Thu, 11 Mar 2021 16:42:05 +0200
Subject: [PATCH 0719/1820] sch_htb: Fix select_queue for non-offload mode

htb_select_queue assumes it's always the offload mode, and it ends up in
calling ndo_setup_tc without any checks. It may lead to a NULL pointer
dereference if ndo_setup_tc is not implemented, or to an error returned
from the driver, which will prevent attaching qdiscs to HTB classes in
the non-offload mode.

This commit fixes the bug by adding the missing check to
htb_select_queue. In the non-offload mode it will return sch->dev_queue,
mimicking tc_modify_qdisc's behavior for the case where select_queue is
not implemented.

Reported-by: syzbot+b53a709f04722ca12a3c@syzkaller.appspotmail.com
Fixes: d03b195b5aa0 ("sch_htb: Hierarchical QoS hardware offload")
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_htb.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index dff3adf5a915..b23203159996 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1340,8 +1340,12 @@ htb_select_queue(struct Qdisc *sch, struct tcmsg *tcm)
 {
 	struct net_device *dev = qdisc_dev(sch);
 	struct tc_htb_qopt_offload offload_opt;
+	struct htb_sched *q = qdisc_priv(sch);
 	int err;
 
+	if (!q->offload)
+		return sch->dev_queue;
+
 	offload_opt = (struct tc_htb_qopt_offload) {
 		.command = TC_HTB_LEAF_QUERY_QUEUE,
 		.classid = TC_H_MIN(tcm->tcm_parent),

From fb3a3e37de337ec2941c71ff0bcb83e701f3c9f4 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@nvidia.com>
Date: Thu, 11 Mar 2021 16:42:06 +0200
Subject: [PATCH 0720/1820] sch_htb: Fix offload cleanup in htb_destroy on
 htb_init failure

htb_init may fail to do the offload if it's not supported or if a
runtime error happens when allocating direct qdiscs. In those cases
TC_HTB_CREATE command is not sent to the driver, however, htb_destroy
gets called anyway and attempts to send TC_HTB_DESTROY.

It shouldn't happen, because the driver didn't receive TC_HTB_CREATE,
and also because the driver may not support ndo_setup_tc at all, while
q->offload is true, and htb_destroy mistakenly thinks the offload is
supported. Trying to call ndo_setup_tc in the latter case will lead to a
NULL pointer dereference.

This commit fixes the issues with htb_destroy by deferring assignment of
q->offload until after the TC_HTB_CREATE command. The necessary cleanup
of the offload entities is already done in htb_init.

Reported-by: syzbot+b53a709f04722ca12a3c@syzkaller.appspotmail.com
Fixes: d03b195b5aa0 ("sch_htb: Hierarchical QoS hardware offload")
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_htb.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index b23203159996..62e12cb41a3e 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1020,6 +1020,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt,
 	struct nlattr *tb[TCA_HTB_MAX + 1];
 	struct tc_htb_glob *gopt;
 	unsigned int ntx;
+	bool offload;
 	int err;
 
 	qdisc_watchdog_init(&q->watchdog, sch);
@@ -1044,9 +1045,9 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt,
 	if (gopt->version != HTB_VER >> 16)
 		return -EINVAL;
 
-	q->offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]);
+	offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]);
 
-	if (q->offload) {
+	if (offload) {
 		if (sch->parent != TC_H_ROOT)
 			return -EOPNOTSUPP;
 
@@ -1076,7 +1077,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt,
 		q->rate2quantum = 1;
 	q->defcls = gopt->defcls;
 
-	if (!q->offload)
+	if (!offload)
 		return 0;
 
 	for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) {
@@ -1107,12 +1108,14 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt,
 	if (err)
 		goto err_free_qdiscs;
 
+	/* Defer this assignment, so that htb_destroy skips offload-related
+	 * parts (especially calling ndo_setup_tc) on errors.
+	 */
+	q->offload = true;
+
 	return 0;
 
 err_free_qdiscs:
-	/* TC_HTB_CREATE call failed, avoid any further calls to the driver. */
-	q->offload = false;
-
 	for (ntx = 0; ntx < q->num_direct_qdiscs && q->direct_qdiscs[ntx];
 	     ntx++)
 		qdisc_put(q->direct_qdiscs[ntx]);

From 606a5d4227e4610399c61086ac55c46068a90b03 Mon Sep 17 00:00:00 2001
From: Beata Michalska <beata.michalska@arm.com>
Date: Thu, 4 Mar 2021 15:07:34 +0000
Subject: [PATCH 0721/1820] opp: Don't drop extra references to OPPs
 accidentally

We are required to call dev_pm_opp_put() from outside of the
opp_table->lock as debugfs removal needs to happen lock-less to avoid
circular dependency issues.

commit cf1fac943c63 ("opp: Reduce the size of critical section in
_opp_kref_release()") tried to fix that introducing a new routine
_opp_get_next() which keeps returning OPPs that can be freed by the
callers and this routine shall be called without holding the
opp_table->lock.

Though the commit overlooked the fact that the OPPs can be referenced by
other users as well and this routine will end up dropping references
which were taken by other users and hence freeing the OPPs prematurely.

In effect, other users of the OPPs will end up having invalid pointers
at hand. We didn't see any crash reports earlier as the exact situation
never happened, though it is certainly possible.

We need a way to mark which OPPs are no longer referenced by the OPP
core, so we don't drop extra references to them accidentally.

This commit adds another OPP flag, "removed", which is used to track
this. And now we should never end up dropping extra references to the
OPPs.

Cc: v5.11+ <stable@vger.kernel.org> # v5.11+
Fixes: cf1fac943c63 ("opp: Reduce the size of critical section in _opp_kref_release()")
Signed-off-by: Beata Michalska <beata.michalska@arm.com>
[ Viresh: Almost rewrote entire patch, added new "removed" field,
	  rewrote commit log and added the correct Fixes tag. ]
Co-developed-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/opp/core.c | 48 ++++++++++++++++++++++++----------------------
 drivers/opp/opp.h  |  2 ++
 2 files changed, 27 insertions(+), 23 deletions(-)

diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index c2689386a906..1556998425d5 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -1492,7 +1492,11 @@ static struct dev_pm_opp *_opp_get_next(struct opp_table *opp_table,
 
 	mutex_lock(&opp_table->lock);
 	list_for_each_entry(temp, &opp_table->opp_list, node) {
-		if (dynamic == temp->dynamic) {
+		/*
+		 * Refcount must be dropped only once for each OPP by OPP core,
+		 * do that with help of "removed" flag.
+		 */
+		if (!temp->removed && dynamic == temp->dynamic) {
 			opp = temp;
 			break;
 		}
@@ -1502,10 +1506,27 @@ static struct dev_pm_opp *_opp_get_next(struct opp_table *opp_table,
 	return opp;
 }
 
-bool _opp_remove_all_static(struct opp_table *opp_table)
+/*
+ * Can't call dev_pm_opp_put() from under the lock as debugfs removal needs to
+ * happen lock less to avoid circular dependency issues. This routine must be
+ * called without the opp_table->lock held.
+ */
+static void _opp_remove_all(struct opp_table *opp_table, bool dynamic)
 {
 	struct dev_pm_opp *opp;
 
+	while ((opp = _opp_get_next(opp_table, dynamic))) {
+		opp->removed = true;
+		dev_pm_opp_put(opp);
+
+		/* Drop the references taken by dev_pm_opp_add() */
+		if (dynamic)
+			dev_pm_opp_put_opp_table(opp_table);
+	}
+}
+
+bool _opp_remove_all_static(struct opp_table *opp_table)
+{
 	mutex_lock(&opp_table->lock);
 
 	if (!opp_table->parsed_static_opps) {
@@ -1520,13 +1541,7 @@ bool _opp_remove_all_static(struct opp_table *opp_table)
 
 	mutex_unlock(&opp_table->lock);
 
-	/*
-	 * Can't remove the OPP from under the lock, debugfs removal needs to
-	 * happen lock less to avoid circular dependency issues.
-	 */
-	while ((opp = _opp_get_next(opp_table, false)))
-		dev_pm_opp_put(opp);
-
+	_opp_remove_all(opp_table, false);
 	return true;
 }
 
@@ -1539,25 +1554,12 @@ bool _opp_remove_all_static(struct opp_table *opp_table)
 void dev_pm_opp_remove_all_dynamic(struct device *dev)
 {
 	struct opp_table *opp_table;
-	struct dev_pm_opp *opp;
-	int count = 0;
 
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table))
 		return;
 
-	/*
-	 * Can't remove the OPP from under the lock, debugfs removal needs to
-	 * happen lock less to avoid circular dependency issues.
-	 */
-	while ((opp = _opp_get_next(opp_table, true))) {
-		dev_pm_opp_put(opp);
-		count++;
-	}
-
-	/* Drop the references taken by dev_pm_opp_add() */
-	while (count--)
-		dev_pm_opp_put_opp_table(opp_table);
+	_opp_remove_all(opp_table, true);
 
 	/* Drop the reference taken by _find_opp_table() */
 	dev_pm_opp_put_opp_table(opp_table);
diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index 50fb9dced3c5..407c3bfe51d9 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -56,6 +56,7 @@ extern struct list_head opp_tables, lazy_opp_tables;
  * @dynamic:	not-created from static DT entries.
  * @turbo:	true if turbo (boost) OPP
  * @suspend:	true if suspend OPP
+ * @removed:	flag indicating that OPP's reference is dropped by OPP core.
  * @pstate: Device's power domain's performance state.
  * @rate:	Frequency in hertz
  * @level:	Performance level
@@ -78,6 +79,7 @@ struct dev_pm_opp {
 	bool dynamic;
 	bool turbo;
 	bool suspend;
+	bool removed;
 	unsigned int pstate;
 	unsigned long rate;
 	unsigned int level;

From ba08abca66d46381df60842f64f70099d5482b92 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 8 Mar 2021 15:46:04 +0100
Subject: [PATCH 0722/1820] objtool,x86: Fix uaccess PUSHF/POPF validation

Commit ab234a260b1f ("x86/pv: Rework arch_local_irq_restore() to not
use popf") replaced "push %reg; popf" with something like: "test
$0x200, %reg; jz 1f; sti; 1:", which breaks the pushf/popf symmetry
that commit ea24213d8088 ("objtool: Add UACCESS validation") relies
on.

The result is:

  drivers/gpu/drm/amd/amdgpu/si.o: warning: objtool: si_common_hw_init()+0xf36: PUSHF stack exhausted

Meanwhile, commit c9c324dc22aa ("objtool: Support stack layout changes
in alternatives") makes that we can actually use stack-ops in
alternatives, which means we can revert 1ff865e343c2 ("x86,smap: Fix
smap_{save,restore}() alternatives").

That in turn means we can limit the PUSHF/POPF handling of
ea24213d8088 to those instructions that are in alternatives.

Fixes: ab234a260b1f ("x86/pv: Rework arch_local_irq_restore() to not use popf")
Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/YEY4rIbQYa5fnnEp@hirez.programming.kicks-ass.net
---
 arch/x86/include/asm/smap.h | 10 ++++------
 tools/objtool/check.c       |  3 +++
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 8b58d6975d5d..0bc9b0895f33 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -58,9 +58,8 @@ static __always_inline unsigned long smap_save(void)
 	unsigned long flags;
 
 	asm volatile ("# smap_save\n\t"
-		      ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
-		      "pushf; pop %0; " __ASM_CLAC "\n\t"
-		      "1:"
+		      ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC "\n\t",
+				  X86_FEATURE_SMAP)
 		      : "=rm" (flags) : : "memory", "cc");
 
 	return flags;
@@ -69,9 +68,8 @@ static __always_inline unsigned long smap_save(void)
 static __always_inline void smap_restore(unsigned long flags)
 {
 	asm volatile ("# smap_restore\n\t"
-		      ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
-		      "push %0; popf\n\t"
-		      "1:"
+		      ALTERNATIVE("", "push %0; popf\n\t",
+				  X86_FEATURE_SMAP)
 		      : : "g" (flags) : "memory", "cc");
 }
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 068cdb41f76f..5e5388a38e2a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -2442,6 +2442,9 @@ static int handle_insn_ops(struct instruction *insn, struct insn_state *state)
 		if (update_cfi_state(insn, &state->cfi, op))
 			return 1;
 
+		if (!insn->alt_group)
+			continue;
+
 		if (op->dest.type == OP_DEST_PUSHF) {
 			if (!state->uaccess_stack) {
 				state->uaccess_stack = 1;

From 3875721e825cf3ab05fc1a52b6cbd76c8d16da51 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Fri, 12 Mar 2021 08:04:23 +0000
Subject: [PATCH 0723/1820] gpiolib: Fix error return code in
 gpiolib_dev_init()

Fix to return a negative error code from the error handling
case instead of 0, as done elsewhere in this function.

Fixes: 4731210c09f5 ("gpiolib: Bind gpio_device to a driver to enable fw_devlink=on by default")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 drivers/gpio/gpiolib.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 7ec0822c0505..6635e4ec60ce 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -4256,7 +4256,8 @@ static int __init gpiolib_dev_init(void)
 		return ret;
 	}
 
-	if (driver_register(&gpio_stub_drv) < 0) {
+	ret = driver_register(&gpio_stub_drv);
+	if (ret < 0) {
 		pr_err("gpiolib: could not register GPIO stub driver\n");
 		bus_unregister(&gpio_bus_type);
 		return ret;

From c8e3866836528a4ba3b0535834f03768d74f7d8e Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Fri, 12 Mar 2021 08:04:21 +0000
Subject: [PATCH 0724/1820] perf/arm_dmc620_pmu: Fix error return code in
 dmc620_pmu_device_probe()

Fix to return negative error code -ENOMEM from the error handling
case instead of 0, as done elsewhere in this function.

Fixes: 53c218da220c ("driver/perf: Add PMU driver for the ARM DMC-620 memory controller")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Link: https://lore.kernel.org/r/20210312080421.277562-1-weiyongjun1@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/perf/arm_dmc620_pmu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c
index 66ad5b3ece19..f2a85500258d 100644
--- a/drivers/perf/arm_dmc620_pmu.c
+++ b/drivers/perf/arm_dmc620_pmu.c
@@ -681,6 +681,7 @@ static int dmc620_pmu_device_probe(struct platform_device *pdev)
 	if (!name) {
 		dev_err(&pdev->dev,
 			  "Create name failed, PMU @%pa\n", &res->start);
+		ret = -ENOMEM;
 		goto out_teardown_dev;
 	}
 

From 2bf44e0ee95f39cc54ea1b942f0a027e0181ca4e Mon Sep 17 00:00:00 2001
From: Hui Wang <hui.wang@canonical.com>
Date: Fri, 12 Mar 2021 12:14:08 +0800
Subject: [PATCH 0725/1820] ALSA: hda: generic: Fix the micmute led init state

Recently we found the micmute led init state is not correct after
freshly installing the ubuntu linux on a Lenovo AIO machine. The
internal mic is not muted, but the micmute led is on and led mode is
'follow mute'. If we mute internal mic, the led is keeping on, then
unmute the internal mic, the led is off. And from then on, the
micmute led will work correctly.

So the micmute led init state is not correct. The led is controlled
by codec gpio (ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), in the
patch_realtek, the gpio data is set to 0x4 initially and the led is
on with this data. In the hda_generic, the led_value is set to
0 initially, suppose users set the 'capture switch' to on from
user space and the micmute led should change to be off with this
operation, but the check "if (val == spec->micmute_led.led_value)" in
the call_micmute_led_update() will skip the led setting.

To guarantee the led state will be set by the 1st time of changing
"Capture Switch", set -1 to the init led_value.

Cc: <stable@vger.kernel.org>
Signed-off-by: Hui Wang <hui.wang@canonical.com>
Link: https://lore.kernel.org/r/20210312041408.3776-1-hui.wang@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_generic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 8b7c5508f368..f5cba7afd1c6 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -4065,7 +4065,7 @@ static int add_micmute_led_hook(struct hda_codec *codec)
 
 	spec->micmute_led.led_mode = MICMUTE_LED_FOLLOW_MUTE;
 	spec->micmute_led.capture = 0;
-	spec->micmute_led.led_value = 0;
+	spec->micmute_led.led_value = -1;
 	spec->micmute_led.old_hook = spec->cap_sync_hook;
 	spec->cap_sync_hook = update_micmute_led;
 	if (!snd_hda_gen_add_kctl(spec, NULL, &micmute_led_mode_ctl))

From dd7b836d6bc935df95c826f69ff4d051f5561604 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Fri, 12 Mar 2021 18:34:07 +0900
Subject: [PATCH 0726/1820] ALSA: dice: fix null pointer dereference when node
 is disconnected

When node is removed from IEEE 1394 bus, any transaction fails to the node.
In the case, ALSA dice driver doesn't stop isochronous contexts even if
they are running. As a result, null pointer dereference occurs in callback
from the running context.

This commit fixes the bug to release isochronous contexts always.

Cc: <stable@vger.kernel.org> # v5.4 or later
Fixes: e9f21129b8d8 ("ALSA: dice: support AMDTP domain")
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Link: https://lore.kernel.org/r/20210312093407.23437-1-o-takashi@sakamocchi.jp
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/firewire/dice/dice-stream.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/sound/firewire/dice/dice-stream.c b/sound/firewire/dice/dice-stream.c
index 8e0c0380b4c4..1a14c083e8ce 100644
--- a/sound/firewire/dice/dice-stream.c
+++ b/sound/firewire/dice/dice-stream.c
@@ -493,11 +493,10 @@ void snd_dice_stream_stop_duplex(struct snd_dice *dice)
 	struct reg_params tx_params, rx_params;
 
 	if (dice->substreams_counter == 0) {
-		if (get_register_params(dice, &tx_params, &rx_params) >= 0) {
-			amdtp_domain_stop(&dice->domain);
+		if (get_register_params(dice, &tx_params, &rx_params) >= 0)
 			finish_session(dice, &tx_params, &rx_params);
-		}
 
+		amdtp_domain_stop(&dice->domain);
 		release_resources(dice);
 	}
 }

From d5bf630f355d8c532bef2347cf90e8ae60a5f1bd Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Fri, 12 Mar 2021 07:58:54 -0500
Subject: [PATCH 0727/1820] gfs2: bypass signal_our_withdraw if no journal

Before this patch, function signal_our_withdraw referenced the journal
inode immediately. But corrupt file systems may have some invalid
journals, in which case our attempt to read it in will withdraw and the
resulting signal_our_withdraw would dereference the NULL value.

This patch adds a check to signal_our_withdraw so that if the journal
has not yet been initialized, it simply returns and does the old-style
withdraw.

Thanks, Andy Price, for his analysis.

Reported-by: syzbot+50a8a9cf8127f2c6f5df@syzkaller.appspotmail.com
Fixes: 601ef0d52e96 ("gfs2: Force withdraw to replay journals and wait for it to finish")
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/util.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 58743315cda9..4f034b87b427 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -119,17 +119,22 @@ void gfs2_freeze_unlock(struct gfs2_holder *freeze_gh)
 static void signal_our_withdraw(struct gfs2_sbd *sdp)
 {
 	struct gfs2_glock *live_gl = sdp->sd_live_gh.gh_gl;
-	struct inode *inode = sdp->sd_jdesc->jd_inode;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_glock *i_gl = ip->i_gl;
-	u64 no_formal_ino = ip->i_no_formal_ino;
+	struct inode *inode;
+	struct gfs2_inode *ip;
+	struct gfs2_glock *i_gl;
+	u64 no_formal_ino;
 	int log_write_allowed = test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
 	int ret = 0;
 	int tries;
 
-	if (test_bit(SDF_NORECOVERY, &sdp->sd_flags))
+	if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) || !sdp->sd_jdesc)
 		return;
 
+	inode = sdp->sd_jdesc->jd_inode;
+	ip = GFS2_I(inode);
+	i_gl = ip->i_gl;
+	no_formal_ino = ip->i_no_formal_ino;
+
 	/* Prevent any glock dq until withdraw recovery is complete */
 	set_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
 	/*

From e1915f76a8981f0a750cf56515df42582a37c4b0 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 11 Mar 2021 23:29:35 +0000
Subject: [PATCH 0728/1820] io_uring: cancel deferred requests in try_cancel

As io_uring_cancel_files() and others let SQO to run between
io_uring_try_cancel_requests(), SQO may generate new deferred requests,
so it's safer to try to cancel them in it.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 49f85f49e1c3..56f3d8f408c9 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8577,11 +8577,11 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data)
 	return ret;
 }
 
-static void io_cancel_defer_files(struct io_ring_ctx *ctx,
+static bool io_cancel_defer_files(struct io_ring_ctx *ctx,
 				  struct task_struct *task,
 				  struct files_struct *files)
 {
-	struct io_defer_entry *de = NULL;
+	struct io_defer_entry *de;
 	LIST_HEAD(list);
 
 	spin_lock_irq(&ctx->completion_lock);
@@ -8592,6 +8592,8 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx,
 		}
 	}
 	spin_unlock_irq(&ctx->completion_lock);
+	if (list_empty(&list))
+		return false;
 
 	while (!list_empty(&list)) {
 		de = list_first_entry(&list, struct io_defer_entry, list);
@@ -8601,6 +8603,7 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx,
 		io_req_complete(de->req, -ECANCELED);
 		kfree(de);
 	}
+	return true;
 }
 
 static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
@@ -8666,6 +8669,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 			}
 		}
 
+		ret |= io_cancel_defer_files(ctx, task, files);
 		ret |= io_poll_remove_all(ctx, task, files);
 		ret |= io_kill_timeouts(ctx, task, files);
 		ret |= io_run_task_work();
@@ -8734,8 +8738,6 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
 			atomic_inc(&task->io_uring->in_idle);
 	}
 
-	io_cancel_defer_files(ctx, task, files);
-
 	io_uring_cancel_files(ctx, task, files);
 	if (!files)
 		io_uring_try_cancel_requests(ctx, task, NULL);

From 0df8ea602b3fe80819a34361027ad40485e78909 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 11 Mar 2021 23:29:36 +0000
Subject: [PATCH 0729/1820] io_uring: remove useless ->startup completion

We always do complete(&sqd->startup) almost right after sqd->thread
creation, either in the success path or in io_sq_thread_finish(). It's
specifically created not started for us to be able to set some stuff
like sqd->thread and io_uring_alloc_task_context() before following
right after wake_up_new_task().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 56f3d8f408c9..6349374d715d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -272,7 +272,6 @@ struct io_sq_data {
 	pid_t			task_tgid;
 
 	unsigned long		state;
-	struct completion	startup;
 	struct completion	exited;
 };
 
@@ -6656,8 +6655,6 @@ static int io_sq_thread(void *data)
 		set_cpus_allowed_ptr(current, cpu_online_mask);
 	current->flags |= PF_NO_SETAFFINITY;
 
-	wait_for_completion(&sqd->startup);
-
 	down_read(&sqd->rw_lock);
 
 	while (!test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)) {
@@ -7080,7 +7077,6 @@ static void io_sq_thread_finish(struct io_ring_ctx *ctx)
 	struct io_sq_data *sqd = ctx->sq_data;
 
 	if (sqd) {
-		complete(&sqd->startup);
 		io_sq_thread_park(sqd);
 		list_del(&ctx->sqd_list);
 		io_sqd_update_thread_idle(sqd);
@@ -7144,7 +7140,6 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p)
 	INIT_LIST_HEAD(&sqd->ctx_list);
 	init_rwsem(&sqd->rw_lock);
 	init_waitqueue_head(&sqd->wait);
-	init_completion(&sqd->startup);
 	init_completion(&sqd->exited);
 	return sqd;
 }
@@ -7856,7 +7851,6 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 		wake_up_new_task(tsk);
 		if (ret)
 			goto err;
-		complete(&sqd->startup);
 	} else if (p->flags & IORING_SETUP_SQ_AFF) {
 		/* Can't have SQ_AFF without SQPOLL */
 		ret = -EINVAL;

From 8d06b9633a66f41fed520f6eebd163189518ba79 Mon Sep 17 00:00:00 2001
From: Jiaxin Yu <jiaxin.yu@mediatek.com>
Date: Fri, 12 Mar 2021 10:26:45 +0800
Subject: [PATCH 0730/1820] ASoC: mediatek: mt8192: fix tdm out data is valid
 on rising edge

This patch correct tdm out bck inverse register to AUDIO_TOP_CON3[3].

Signed-off-by: Jiaxin Yu <jiaxin.yu@mediatek.com>
Link: https://lore.kernel.org/r/1615516005-781-1-git-send-email-jiaxin.yu@mediatek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/mediatek/mt8192/mt8192-dai-tdm.c | 4 +++-
 sound/soc/mediatek/mt8192/mt8192-reg.h     | 8 +++++---
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/sound/soc/mediatek/mt8192/mt8192-dai-tdm.c b/sound/soc/mediatek/mt8192/mt8192-dai-tdm.c
index f5de1d769679..f3bebed2428a 100644
--- a/sound/soc/mediatek/mt8192/mt8192-dai-tdm.c
+++ b/sound/soc/mediatek/mt8192/mt8192-dai-tdm.c
@@ -555,7 +555,9 @@ static int mtk_dai_tdm_hw_params(struct snd_pcm_substream *substream,
 
 	/* set tdm */
 	if (tdm_priv->bck_invert)
-		tdm_con |= 1 << BCK_INVERSE_SFT;
+		regmap_update_bits(afe->regmap, AUDIO_TOP_CON3,
+				   BCK_INVERSE_MASK_SFT,
+				   0x1 << BCK_INVERSE_SFT);
 
 	if (tdm_priv->lck_invert)
 		tdm_con |= 1 << LRCK_INVERSE_SFT;
diff --git a/sound/soc/mediatek/mt8192/mt8192-reg.h b/sound/soc/mediatek/mt8192/mt8192-reg.h
index 562f25c79c34..b9fb80d4afec 100644
--- a/sound/soc/mediatek/mt8192/mt8192-reg.h
+++ b/sound/soc/mediatek/mt8192/mt8192-reg.h
@@ -21,6 +21,11 @@ enum {
 /*****************************************************************************
  *                  R E G I S T E R       D E F I N I T I O N
  *****************************************************************************/
+/* AUDIO_TOP_CON3 */
+#define BCK_INVERSE_SFT                              3
+#define BCK_INVERSE_MASK                             0x1
+#define BCK_INVERSE_MASK_SFT                         (0x1 << 3)
+
 /* AFE_DAC_CON0 */
 #define VUL12_ON_SFT                                   31
 #define VUL12_ON_MASK                                  0x1
@@ -2079,9 +2084,6 @@ enum {
 #define TDM_EN_SFT                                     0
 #define TDM_EN_MASK                                    0x1
 #define TDM_EN_MASK_SFT                                (0x1 << 0)
-#define BCK_INVERSE_SFT                                1
-#define BCK_INVERSE_MASK                               0x1
-#define BCK_INVERSE_MASK_SFT                           (0x1 << 1)
 #define LRCK_INVERSE_SFT                               2
 #define LRCK_INVERSE_MASK                              0x1
 #define LRCK_INVERSE_MASK_SFT                          (0x1 << 2)

From 0efc4976e3da40b09c592b21f722022d8f12a16b Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Fri, 12 Mar 2021 08:47:47 -0500
Subject: [PATCH 0731/1820] gfs2: bypass log flush if the journal is not live

Patch fe3e397668775 ("gfs2: Rework the log space allocation logic")
changed gfs2_log_flush to reserve a set of journal blocks in case no
transaction is active.  However, gfs2_log_flush also gets called in
cases where we don't have an active journal, for example, for spectator
mounts.  In that case, trying to reserve blocks would sleep forever, but
we want gfs2_log_flush to be a no-op instead.

Fixes: fe3e397668775 ("gfs2: Rework the log space allocation logic")
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/log.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 760af666576c..6410281546f9 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -1036,7 +1036,7 @@ repeat:
 	 * Do this check while holding the log_flush_lock to prevent new
 	 * buffers from being added to the ail via gfs2_pin()
 	 */
-	if (gfs2_withdrawn(sdp))
+	if (gfs2_withdrawn(sdp) || !test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
 		goto out;
 
 	/* Log might have been flushed while we waited for the flush lock */

From fac245216b68cdfccf3e2a8d20d6710b750bf20f Mon Sep 17 00:00:00 2001
From: Vineet Gupta <vgupta@synopsys.com>
Date: Thu, 11 Feb 2021 16:43:53 -0800
Subject: [PATCH 0732/1820] ARC: haps: bump memory to 1 GB

Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
---
 arch/arc/boot/dts/haps_hs.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arc/boot/dts/haps_hs.dts b/arch/arc/boot/dts/haps_hs.dts
index 60d578e2781f..76ad527a0847 100644
--- a/arch/arc/boot/dts/haps_hs.dts
+++ b/arch/arc/boot/dts/haps_hs.dts
@@ -16,7 +16,7 @@
 	memory {
 		device_type = "memory";
 		/* CONFIG_LINUX_RAM_BASE needs to match low mem start */
-		reg = <0x0 0x80000000 0x0 0x20000000	/* 512 MB low mem */
+		reg = <0x0 0x80000000 0x0 0x40000000	/* 1 GB low mem */
 		       0x1 0x00000000 0x0 0x40000000>;	/* 1 GB highmem */
 	};
 

From 7d717558dd5ef10d28866750d5c24ff892ea3778 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 11 Mar 2021 10:00:15 +0000
Subject: [PATCH 0733/1820] KVM: arm64: Reject VM creation when the default IPA
 size is unsupported

KVM/arm64 has forever used a 40bit default IPA space, partially
due to its 32bit heritage (where the only choice is 40bit).

However, there are implementations in the wild that have a *cough*
much smaller *cough* IPA space, which leads to a misprogramming of
VTCR_EL2, and a guest that is stuck on its first memory access
if userspace dares to ask for the default IPA setting (which most
VMMs do).

Instead, blundly reject the creation of such VM, as we can't
satisfy the requirements from userspace (with a one-off warning).
Also clarify the boot warning, and document that the VM creation
will fail when an unsupported IPA size is provided.

Although this is an ABI change, it doesn't really change much
for userspace:

- the guest couldn't run before this change, but no error was
  returned. At least userspace knows what is happening.

- a memory slot that was accepted because it did fit the default
  IPA space now doesn't even get a chance to be registered.

The other thing that is left doing is to convince userspace to
actually use the IPA space setting instead of relying on the
antiquated default.

Fixes: 233a7cb23531 ("kvm: arm64: Allow tuning the physical address size for VM")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Reviewed-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20210311100016.3830038-2-maz@kernel.org
---
 Documentation/virt/kvm/api.rst |  3 +++
 arch/arm64/kvm/reset.c         | 12 ++++++++----
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 1a2b5210cdbf..38e327d4b479 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -182,6 +182,9 @@ is dependent on the CPU capability and the kernel configuration. The limit can
 be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION
 ioctl() at run-time.
 
+Creation of the VM will fail if the requested IPA size (whether it is
+implicit or explicit) is unsupported on the host.
+
 Please note that configuring the IPA size does not affect the capability
 exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects
 size of the address translated by the stage2 level (guest physical to
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 47f3f035f3ea..9d3d09a89894 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -324,10 +324,9 @@ int kvm_set_ipa_limit(void)
 	}
 
 	kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange);
-	WARN(kvm_ipa_limit < KVM_PHYS_SHIFT,
-	     "KVM IPA Size Limit (%d bits) is smaller than default size\n",
-	     kvm_ipa_limit);
-	kvm_info("IPA Size Limit: %d bits\n", kvm_ipa_limit);
+	kvm_info("IPA Size Limit: %d bits%s\n", kvm_ipa_limit,
+		 ((kvm_ipa_limit < KVM_PHYS_SHIFT) ?
+		  " (Reduced IPA size, limited VM/VMM compatibility)" : ""));
 
 	return 0;
 }
@@ -356,6 +355,11 @@ int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
 			return -EINVAL;
 	} else {
 		phys_shift = KVM_PHYS_SHIFT;
+		if (phys_shift > kvm_ipa_limit) {
+			pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n",
+				     current->comm);
+			return -EINVAL;
+		}
 	}
 
 	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);

From 262b003d059c6671601a19057e9fe1a5e7f23722 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 11 Mar 2021 10:00:16 +0000
Subject: [PATCH 0734/1820] KVM: arm64: Fix exclusive limit for IPA size

When registering a memslot, we check the size and location of that
memslot against the IPA size to ensure that we can provide guest
access to the whole of the memory.

Unfortunately, this check rejects memslot that end-up at the exact
limit of the addressing capability for a given IPA size. For example,
it refuses the creation of a 2GB memslot at 0x8000000 with a 32bit
IPA space.

Fix it by relaxing the check to accept a memslot reaching the
limit of the IPA space.

Fixes: c3058d5da222 ("arm/arm64: KVM: Ensure memslots are within KVM_PHYS_SIZE")
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Reviewed-by: Andrew Jones <drjones@redhat.com>
Link: https://lore.kernel.org/r/20210311100016.3830038-3-maz@kernel.org
---
 arch/arm64/kvm/mmu.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 77cb2d28f2a4..8711894db8c2 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1312,8 +1312,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	 * Prevent userspace from creating a memory region outside of the IPA
 	 * space addressable by the KVM guest IPA space.
 	 */
-	if (memslot->base_gfn + memslot->npages >=
-	    (kvm_phys_size(kvm) >> PAGE_SHIFT))
+	if ((memslot->base_gfn + memslot->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT))
 		return -EFAULT;
 
 	mmap_read_lock(current->mm);

From ed0907e3bdcfc7fe1c1756a480451e757b207a69 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 5 Feb 2021 10:09:04 +0100
Subject: [PATCH 0735/1820] ice: fix napi work done reporting in xsk path

Fix the wrong napi work done reporting in the xsk path of the ice
driver. The code in the main Rx processing loop was written to assume
that the buffer allocation code returns true if all allocations where
successful and false if not. In contrast with all other Intel NIC xsk
drivers, the ice_alloc_rx_bufs_zc() has the inverted logic messing up
the work done reporting in the napi loop.

This can be fixed either by inverting the return value from
ice_alloc_rx_bufs_zc() in the function that uses this in an incorrect
way, or by changing the return value of ice_alloc_rx_bufs_zc(). We
chose the latter as it makes all the xsk allocation functions for
Intel NICs behave in the same way. My guess is that it was this
unexpected discrepancy that gave rise to this bug in the first place.

Fixes: 5bb0c4b5eb61 ("ice, xsk: Move Rx allocation out of while-loop")
Reported-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c |  6 ++++--
 drivers/net/ethernet/intel/ice/ice_xsk.c  | 10 +++++-----
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 3124a3bf519a..952e41a1e001 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -418,6 +418,8 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	writel(0, ring->tail);
 
 	if (ring->xsk_pool) {
+		bool ok;
+
 		if (!xsk_buff_can_alloc(ring->xsk_pool, num_bufs)) {
 			dev_warn(dev, "XSK buffer pool does not provide enough addresses to fill %d buffers on Rx ring %d\n",
 				 num_bufs, ring->q_index);
@@ -426,8 +428,8 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 			return 0;
 		}
 
-		err = ice_alloc_rx_bufs_zc(ring, num_bufs);
-		if (err)
+		ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
+		if (!ok)
 			dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n",
 				 ring->q_index, pf_q);
 		return 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 83f3c9574ed1..9f94d9159acd 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -358,18 +358,18 @@ xsk_pool_if_up:
  * This function allocates a number of Rx buffers from the fill ring
  * or the internal recycle mechanism and places them on the Rx ring.
  *
- * Returns false if all allocations were successful, true if any fail.
+ * Returns true if all allocations were successful, false if any fail.
  */
 bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count)
 {
 	union ice_32b_rx_flex_desc *rx_desc;
 	u16 ntu = rx_ring->next_to_use;
 	struct ice_rx_buf *rx_buf;
-	bool ret = false;
+	bool ok = true;
 	dma_addr_t dma;
 
 	if (!count)
-		return false;
+		return true;
 
 	rx_desc = ICE_RX_DESC(rx_ring, ntu);
 	rx_buf = &rx_ring->rx_buf[ntu];
@@ -377,7 +377,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count)
 	do {
 		rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool);
 		if (!rx_buf->xdp) {
-			ret = true;
+			ok = false;
 			break;
 		}
 
@@ -402,7 +402,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count)
 		ice_release_rx_desc(rx_ring, ntu);
 	}
 
-	return ret;
+	return ok;
 }
 
 /**

From a86606268ec0c809f341cda3771ae53460e064ab Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 3 Mar 2021 16:39:26 +0100
Subject: [PATCH 0736/1820] i40e: move headroom initialization to
 i40e_configure_rx_ring

i40e_rx_offset(), that is supposed to initialize the Rx buffer headroom,
relies on I40E_RXR_FLAGS_BUILD_SKB_ENABLED flag.

Currently, the callsite of mentioned function is placed incorrectly
within i40e_setup_rx_descriptors() where Rx ring's build skb flag is not
set yet. This causes the XDP_REDIRECT to be partially broken due to
inability to create xdp_frame in the headroom space, as the headroom is
0.

For the record, below is the call graph:

i40e_vsi_open
 i40e_vsi_setup_rx_resources
  i40e_setup_rx_descriptors
   i40e_rx_offset() <-- sets offset to 0 as build_skb flag is set below

 i40e_vsi_configure_rx
  i40e_configure_rx_ring
   set_ring_build_skb_enabled(ring) <-- set build_skb flag

Fix this by moving i40e_rx_offset() to i40e_configure_rx_ring() after
the flag setting.

Fixes: f7bb0d71d658 ("i40e: store the result of i40e_rx_offset() onto i40e_ring")
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Co-developed-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 13 +++++++++++++
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 12 ------------
 2 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 353deae139f9..17f3b800640e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3258,6 +3258,17 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 	return 0;
 }
 
+/**
+ * i40e_rx_offset - Return expected offset into page to access data
+ * @rx_ring: Ring we are requesting offset of
+ *
+ * Returns the offset value for ring into the data buffer.
+ */
+static unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
+{
+	return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
+}
+
 /**
  * i40e_configure_rx_ring - Configure a receive ring context
  * @ring: The Rx ring to configure
@@ -3369,6 +3380,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	else
 		set_ring_build_skb_enabled(ring);
 
+	ring->rx_offset = i40e_rx_offset(ring);
+
 	/* cache tail for quicker writes, and clear the reg before use */
 	ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
 	writel(0, ring->tail);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 627794b31e33..5747a99122fb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1569,17 +1569,6 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring)
 	}
 }
 
-/**
- * i40e_rx_offset - Return expected offset into page to access data
- * @rx_ring: Ring we are requesting offset of
- *
- * Returns the offset value for ring into the data buffer.
- */
-static unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
-{
-	return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
-}
-
 /**
  * i40e_setup_rx_descriptors - Allocate Rx descriptors
  * @rx_ring: Rx descriptor ring (for a specific queue) to setup
@@ -1608,7 +1597,6 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
-	rx_ring->rx_offset = i40e_rx_offset(rx_ring);
 
 	/* XDP RX-queue info only needed for RX rings exposed to XDP */
 	if (rx_ring->vsi->type == I40E_VSI_MAIN) {

From 89861c485c6a384e298fb78660d6a773339e42b1 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 3 Mar 2021 16:39:27 +0100
Subject: [PATCH 0737/1820] ice: move headroom initialization to
 ice_setup_rx_ctx

ice_rx_offset(), that is supposed to initialize the Rx buffer headroom,
relies on ICE_RX_FLAGS_RING_BUILD_SKB flag as well as XDP prog presence.

Currently, the callsite of mentioned function is placed incorrectly
within ice_setup_rx_ring() where Rx ring's build skb flag is not
set yet. This causes the XDP_REDIRECT to be partially broken due to
inability to create xdp_frame in the headroom space, as the headroom is
0.

Fix this by moving ice_rx_offset() to ice_setup_rx_ctx() after the flag
setting.

Fixes: f1b1f409bf79 ("ice: store the result of ice_rx_offset() onto ice_ring")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c | 18 ++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_txrx.c | 17 -----------------
 2 files changed, 18 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 952e41a1e001..1148d768f8ed 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -274,6 +274,22 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
 	tlan_ctx->legacy_int = ICE_TX_LEGACY;
 }
 
+/**
+ * ice_rx_offset - Return expected offset into page to access data
+ * @rx_ring: Ring we are requesting offset of
+ *
+ * Returns the offset value for ring into the data buffer.
+ */
+static unsigned int ice_rx_offset(struct ice_ring *rx_ring)
+{
+	if (ice_ring_uses_build_skb(rx_ring))
+		return ICE_SKB_PAD;
+	else if (ice_is_xdp_ena_vsi(rx_ring->vsi))
+		return XDP_PACKET_HEADROOM;
+
+	return 0;
+}
+
 /**
  * ice_setup_rx_ctx - Configure a receive ring context
  * @ring: The Rx ring to configure
@@ -413,6 +429,8 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	else
 		ice_set_ring_build_skb_ena(ring);
 
+	ring->rx_offset = ice_rx_offset(ring);
+
 	/* init queue specific tail register */
 	ring->tail = hw->hw_addr + QRX_TAIL(pf_q);
 	writel(0, ring->tail);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index b7dc25da1202..b91dcfd12727 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -443,22 +443,6 @@ void ice_free_rx_ring(struct ice_ring *rx_ring)
 	}
 }
 
-/**
- * ice_rx_offset - Return expected offset into page to access data
- * @rx_ring: Ring we are requesting offset of
- *
- * Returns the offset value for ring into the data buffer.
- */
-static unsigned int ice_rx_offset(struct ice_ring *rx_ring)
-{
-	if (ice_ring_uses_build_skb(rx_ring))
-		return ICE_SKB_PAD;
-	else if (ice_is_xdp_ena_vsi(rx_ring->vsi))
-		return XDP_PACKET_HEADROOM;
-
-	return 0;
-}
-
 /**
  * ice_setup_rx_ring - Allocate the Rx descriptors
  * @rx_ring: the Rx ring to set up
@@ -493,7 +477,6 @@ int ice_setup_rx_ring(struct ice_ring *rx_ring)
 
 	rx_ring->next_to_use = 0;
 	rx_ring->next_to_clean = 0;
-	rx_ring->rx_offset = ice_rx_offset(rx_ring);
 
 	if (ice_is_xdp_ena_vsi(rx_ring->vsi))
 		WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog);

From 76064573b121a376fe54a2799ee6b5bb91632a1f Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 3 Mar 2021 16:39:28 +0100
Subject: [PATCH 0738/1820] ixgbe: move headroom initialization to
 ixgbe_configure_rx_ring

ixgbe_rx_offset(), that is supposed to initialize the Rx buffer headroom,
relies on __IXGBE_RX_BUILD_SKB_ENABLED flag.

Currently, the callsite of mentioned function is placed incorrectly
within ixgbe_setup_rx_resources() where Rx ring's build skb flag is not
set yet. This causes the XDP_REDIRECT to be partially broken due to
inability to create xdp_frame in the headroom space, as the headroom is
0.

Fix this by moving ixgbe_rx_offset() to ixgbe_configure_rx_ring() after
the flag setting, which happens to be set in ixgbe_set_rx_buffer_len.

Fixes: c0d4e9d223c5 ("ixgbe: store the result of ixgbe_rx_offset() onto ixgbe_ring")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Vishakha Jambekar <vishakha.jambekar@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 9f3f12e2ccf2..03d9aad516d4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -4118,6 +4118,8 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 #endif
 	}
 
+	ring->rx_offset = ixgbe_rx_offset(ring);
+
 	if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) {
 		u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
 
@@ -6578,7 +6580,6 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
 
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
-	rx_ring->rx_offset = ixgbe_rx_offset(rx_ring);
 
 	/* XDP RX-queue info */
 	if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev,

From 26984fbf3ad9d1c1fb56a0c1e0cdf9fa3b806f0c Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 11 Mar 2021 23:29:37 +0000
Subject: [PATCH 0739/1820] io_uring: prevent racy sqd->thread checks

SQPOLL thread to which we're trying to attach may be going away, it's
not nice but a more serious problem is if io_sq_offload_create() sees
sqd->thread==NULL, and tries to init it with a new thread. There are
tons of ways it can be exploited or fail.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 6349374d715d..cdec59510433 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7119,14 +7119,18 @@ static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p)
 	return sqd;
 }
 
-static struct io_sq_data *io_get_sq_data(struct io_uring_params *p)
+static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
+					 bool *attached)
 {
 	struct io_sq_data *sqd;
 
+	*attached = false;
 	if (p->flags & IORING_SETUP_ATTACH_WQ) {
 		sqd = io_attach_sq_data(p);
-		if (!IS_ERR(sqd))
+		if (!IS_ERR(sqd)) {
+			*attached = true;
 			return sqd;
+		}
 		/* fall through for EPERM case, setup new sqd/task */
 		if (PTR_ERR(sqd) != -EPERM)
 			return sqd;
@@ -7799,12 +7803,13 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		struct task_struct *tsk;
 		struct io_sq_data *sqd;
+		bool attached;
 
 		ret = -EPERM;
 		if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE))
 			goto err;
 
-		sqd = io_get_sq_data(p);
+		sqd = io_get_sq_data(p, &attached);
 		if (IS_ERR(sqd)) {
 			ret = PTR_ERR(sqd);
 			goto err;
@@ -7816,13 +7821,24 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 		if (!ctx->sq_thread_idle)
 			ctx->sq_thread_idle = HZ;
 
+		ret = 0;
 		io_sq_thread_park(sqd);
-		list_add(&ctx->sqd_list, &sqd->ctx_list);
-		io_sqd_update_thread_idle(sqd);
+		/* don't attach to a dying SQPOLL thread, would be racy */
+		if (attached && !sqd->thread) {
+			ret = -ENXIO;
+		} else {
+			list_add(&ctx->sqd_list, &sqd->ctx_list);
+			io_sqd_update_thread_idle(sqd);
+		}
 		io_sq_thread_unpark(sqd);
 
-		if (sqd->thread)
+		if (ret < 0) {
+			io_put_sq_data(sqd);
+			ctx->sq_data = NULL;
+			return ret;
+		} else if (attached) {
 			return 0;
+		}
 
 		if (p->flags & IORING_SETUP_SQ_AFF) {
 			int cpu = p->sq_thread_cpu;

From 521d6a737a31c08dbab204a95cd4fb5bee725f0f Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 11 Mar 2021 23:29:38 +0000
Subject: [PATCH 0740/1820] io_uring: cancel sqpoll via task_work

1) The first problem is io_uring_cancel_sqpoll() ->
io_uring_cancel_task_requests() basically doing park(); park(); and so
hanging.

2) Another one is more subtle, when the master task is doing cancellations,
but SQPOLL task submits in-between the end of the cancellation but
before finish() requests taking a ref to the ctx, and so eternally
locking it up.

3) Yet another is a dying SQPOLL task doing io_uring_cancel_sqpoll() and
same io_uring_cancel_sqpoll() from the owner task, they race for
tctx->wait events. And there probably more of them.

Instead do SQPOLL cancellations from within SQPOLL task context via
task_work, see io_sqpoll_cancel_sync(). With that we don't need temporal
park()/unpark() during cancellation, which is ugly, subtle and anyway
doesn't allow to do io_run_task_work() properly.

io_uring_cancel_sqpoll() is called only from SQPOLL task context and
under sqd locking, so all parking is removed from there. And so,
io_sq_thread_[un]park() and io_sq_thread_stop() are not used now by
SQPOLL task, and that spare us from some headache.

Also remove ctx->sqd_list early to avoid 2). And kill tctx->sqpoll,
which is not used anymore.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 151 ++++++++++++++++++++++++--------------------------
 1 file changed, 71 insertions(+), 80 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index cdec59510433..70286b393c0e 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6665,6 +6665,7 @@ static int io_sq_thread(void *data)
 			up_read(&sqd->rw_lock);
 			cond_resched();
 			down_read(&sqd->rw_lock);
+			io_run_task_work();
 			timeout = jiffies + sqd->sq_thread_idle;
 			continue;
 		}
@@ -6720,18 +6721,22 @@ static int io_sq_thread(void *data)
 		finish_wait(&sqd->wait, &wait);
 		timeout = jiffies + sqd->sq_thread_idle;
 	}
+	up_read(&sqd->rw_lock);
+	down_write(&sqd->rw_lock);
+	/*
+	 * someone may have parked and added a cancellation task_work, run
+	 * it first because we don't want it in io_uring_cancel_sqpoll()
+	 */
+	io_run_task_work();
 
 	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 		io_uring_cancel_sqpoll(ctx);
-	up_read(&sqd->rw_lock);
-
-	io_run_task_work();
-
-	down_write(&sqd->rw_lock);
 	sqd->thread = NULL;
 	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 		io_ring_set_wakeup_flag(ctx);
 	up_write(&sqd->rw_lock);
+
+	io_run_task_work();
 	complete(&sqd->exited);
 	do_exit(0);
 }
@@ -7033,8 +7038,8 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 static void io_sq_thread_unpark(struct io_sq_data *sqd)
 	__releases(&sqd->rw_lock)
 {
-	if (sqd->thread == current)
-		return;
+	WARN_ON_ONCE(sqd->thread == current);
+
 	clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
 	up_write(&sqd->rw_lock);
 }
@@ -7042,8 +7047,8 @@ static void io_sq_thread_unpark(struct io_sq_data *sqd)
 static void io_sq_thread_park(struct io_sq_data *sqd)
 	__acquires(&sqd->rw_lock)
 {
-	if (sqd->thread == current)
-		return;
+	WARN_ON_ONCE(sqd->thread == current);
+
 	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
 	down_write(&sqd->rw_lock);
 	/* set again for consistency, in case concurrent parks are happening */
@@ -7054,8 +7059,8 @@ static void io_sq_thread_park(struct io_sq_data *sqd)
 
 static void io_sq_thread_stop(struct io_sq_data *sqd)
 {
-	if (test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state))
-		return;
+	WARN_ON_ONCE(sqd->thread == current);
+
 	down_write(&sqd->rw_lock);
 	set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
 	if (sqd->thread)
@@ -7078,7 +7083,7 @@ static void io_sq_thread_finish(struct io_ring_ctx *ctx)
 
 	if (sqd) {
 		io_sq_thread_park(sqd);
-		list_del(&ctx->sqd_list);
+		list_del_init(&ctx->sqd_list);
 		io_sqd_update_thread_idle(sqd);
 		io_sq_thread_unpark(sqd);
 
@@ -7760,7 +7765,6 @@ static int io_uring_alloc_task_context(struct task_struct *task,
 	init_waitqueue_head(&tctx->wait);
 	tctx->last = NULL;
 	atomic_set(&tctx->in_idle, 0);
-	tctx->sqpoll = false;
 	task->io_uring = tctx;
 	spin_lock_init(&tctx->task_lock);
 	INIT_WQ_LIST(&tctx->task_list);
@@ -8719,45 +8723,14 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 
 		io_uring_try_cancel_requests(ctx, task, files);
 
-		if (ctx->sq_data)
-			io_sq_thread_unpark(ctx->sq_data);
 		prepare_to_wait(&task->io_uring->wait, &wait,
 				TASK_UNINTERRUPTIBLE);
 		if (inflight == io_uring_count_inflight(ctx, task, files))
 			schedule();
 		finish_wait(&task->io_uring->wait, &wait);
-		if (ctx->sq_data)
-			io_sq_thread_park(ctx->sq_data);
 	}
 }
 
-/*
- * We need to iteratively cancel requests, in case a request has dependent
- * hard links. These persist even for failure of cancelations, hence keep
- * looping until none are found.
- */
-static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
-					  struct files_struct *files)
-{
-	struct task_struct *task = current;
-
-	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
-		io_sq_thread_park(ctx->sq_data);
-		task = ctx->sq_data->thread;
-		if (task)
-			atomic_inc(&task->io_uring->in_idle);
-	}
-
-	io_uring_cancel_files(ctx, task, files);
-	if (!files)
-		io_uring_try_cancel_requests(ctx, task, NULL);
-
-	if (task)
-		atomic_dec(&task->io_uring->in_idle);
-	if (ctx->sq_data)
-		io_sq_thread_unpark(ctx->sq_data);
-}
-
 /*
  * Note that this task has used io_uring. We use it for cancelation purposes.
  */
@@ -8796,15 +8769,6 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx)
 		}
 		tctx->last = ctx;
 	}
-
-	/*
-	 * This is race safe in that the task itself is doing this, hence it
-	 * cannot be going through the exit/cancel paths at the same time.
-	 * This cannot be modified while exit/cancel is running.
-	 */
-	if (!tctx->sqpoll && (ctx->flags & IORING_SETUP_SQPOLL))
-		tctx->sqpoll = true;
-
 	return 0;
 }
 
@@ -8847,6 +8811,44 @@ static void io_uring_clean_tctx(struct io_uring_task *tctx)
 	}
 }
 
+static s64 tctx_inflight(struct io_uring_task *tctx)
+{
+	return percpu_counter_sum(&tctx->inflight);
+}
+
+static void io_sqpoll_cancel_cb(struct callback_head *cb)
+{
+	struct io_tctx_exit *work = container_of(cb, struct io_tctx_exit, task_work);
+	struct io_ring_ctx *ctx = work->ctx;
+	struct io_sq_data *sqd = ctx->sq_data;
+
+	if (sqd->thread)
+		io_uring_cancel_sqpoll(ctx);
+	complete(&work->completion);
+}
+
+static void io_sqpoll_cancel_sync(struct io_ring_ctx *ctx)
+{
+	struct io_sq_data *sqd = ctx->sq_data;
+	struct io_tctx_exit work = { .ctx = ctx, };
+	struct task_struct *task;
+
+	io_sq_thread_park(sqd);
+	list_del_init(&ctx->sqd_list);
+	io_sqd_update_thread_idle(sqd);
+	task = sqd->thread;
+	if (task) {
+		init_completion(&work.completion);
+		init_task_work(&work.task_work, io_sqpoll_cancel_cb);
+		WARN_ON_ONCE(task_work_add(task, &work.task_work, TWA_SIGNAL));
+		wake_up_process(task);
+	}
+	io_sq_thread_unpark(sqd);
+
+	if (task)
+		wait_for_completion(&work.completion);
+}
+
 void __io_uring_files_cancel(struct files_struct *files)
 {
 	struct io_uring_task *tctx = current->io_uring;
@@ -8855,41 +8857,40 @@ void __io_uring_files_cancel(struct files_struct *files)
 
 	/* make sure overflow events are dropped */
 	atomic_inc(&tctx->in_idle);
-	xa_for_each(&tctx->xa, index, node)
-		io_uring_cancel_task_requests(node->ctx, files);
+	xa_for_each(&tctx->xa, index, node) {
+		struct io_ring_ctx *ctx = node->ctx;
+
+		if (ctx->sq_data) {
+			io_sqpoll_cancel_sync(ctx);
+			continue;
+		}
+		io_uring_cancel_files(ctx, current, files);
+		if (!files)
+			io_uring_try_cancel_requests(ctx, current, NULL);
+	}
 	atomic_dec(&tctx->in_idle);
 
 	if (files)
 		io_uring_clean_tctx(tctx);
 }
 
-static s64 tctx_inflight(struct io_uring_task *tctx)
-{
-	return percpu_counter_sum(&tctx->inflight);
-}
-
+/* should only be called by SQPOLL task */
 static void io_uring_cancel_sqpoll(struct io_ring_ctx *ctx)
 {
 	struct io_sq_data *sqd = ctx->sq_data;
-	struct io_uring_task *tctx;
+	struct io_uring_task *tctx = current->io_uring;
 	s64 inflight;
 	DEFINE_WAIT(wait);
 
-	if (!sqd)
-		return;
-	io_sq_thread_park(sqd);
-	if (!sqd->thread || !sqd->thread->io_uring) {
-		io_sq_thread_unpark(sqd);
-		return;
-	}
-	tctx = ctx->sq_data->thread->io_uring;
+	WARN_ON_ONCE(!sqd || ctx->sq_data->thread != current);
+
 	atomic_inc(&tctx->in_idle);
 	do {
 		/* read completions before cancelations */
 		inflight = tctx_inflight(tctx);
 		if (!inflight)
 			break;
-		io_uring_cancel_task_requests(ctx, NULL);
+		io_uring_try_cancel_requests(ctx, current, NULL);
 
 		prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
 		/*
@@ -8902,7 +8903,6 @@ static void io_uring_cancel_sqpoll(struct io_ring_ctx *ctx)
 		finish_wait(&tctx->wait, &wait);
 	} while (1);
 	atomic_dec(&tctx->in_idle);
-	io_sq_thread_unpark(sqd);
 }
 
 /*
@@ -8917,15 +8917,6 @@ void __io_uring_task_cancel(void)
 
 	/* make sure overflow events are dropped */
 	atomic_inc(&tctx->in_idle);
-
-	if (tctx->sqpoll) {
-		struct io_tctx_node *node;
-		unsigned long index;
-
-		xa_for_each(&tctx->xa, index, node)
-			io_uring_cancel_sqpoll(node->ctx);
-	}
-
 	do {
 		/* read completions before cancelations */
 		inflight = tctx_inflight(tctx);

From 58f99373834151e1ca7edc49bc5578d9d40db099 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Fri, 12 Mar 2021 16:25:55 +0000
Subject: [PATCH 0741/1820] io_uring: fix OP_ASYNC_CANCEL across tasks

IORING_OP_ASYNC_CANCEL tries io-wq cancellation only for current task.
If it fails go over tctx_list and try it out for every single tctx.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 41 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 40 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 70286b393c0e..a4bce17af506 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -5667,8 +5667,47 @@ static int io_async_cancel_prep(struct io_kiocb *req,
 static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
+	u64 sqe_addr = req->cancel.addr;
+	struct io_tctx_node *node;
+	int ret;
 
-	io_async_find_and_cancel(ctx, req, req->cancel.addr, 0);
+	/* tasks should wait for their io-wq threads, so safe w/o sync */
+	ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx);
+	spin_lock_irq(&ctx->completion_lock);
+	if (ret != -ENOENT)
+		goto done;
+	ret = io_timeout_cancel(ctx, sqe_addr);
+	if (ret != -ENOENT)
+		goto done;
+	ret = io_poll_cancel(ctx, sqe_addr);
+	if (ret != -ENOENT)
+		goto done;
+	spin_unlock_irq(&ctx->completion_lock);
+
+	/* slow path, try all io-wq's */
+	io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+	ret = -ENOENT;
+	list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
+		struct io_uring_task *tctx = node->task->io_uring;
+
+		if (!tctx || !tctx->io_wq)
+			continue;
+		ret = io_async_cancel_one(tctx, req->cancel.addr, ctx);
+		if (ret != -ENOENT)
+			break;
+	}
+	io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+
+	spin_lock_irq(&ctx->completion_lock);
+done:
+	io_cqring_fill_event(req, ret);
+	io_commit_cqring(ctx);
+	spin_unlock_irq(&ctx->completion_lock);
+	io_cqring_ev_posted(ctx);
+
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_put_req(req);
 	return 0;
 }
 

From 98dfb02aa22280bd8833836d1b00ab0488fa951f Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Thu, 21 Jan 2021 13:54:23 -0800
Subject: [PATCH 0742/1820] igb: avoid premature Rx buffer reuse

Igb needs a similar fix as commit 75aab4e10ae6a ("i40e: avoid
premature Rx buffer reuse")

The page recycle code, incorrectly, relied on that a page fragment
could not be freed inside xdp_do_redirect(). This assumption leads to
that page fragments that are used by the stack/XDP redirect can be
reused and overwritten.

To avoid this, store the page count prior invoking xdp_do_redirect().

Longer explanation:

Intel NICs have a recycle mechanism. The main idea is that a page is
split into two parts. One part is owned by the driver, one part might
be owned by someone else, such as the stack.

t0: Page is allocated, and put on the Rx ring
              +---------------
used by NIC ->| upper buffer
(rx_buffer)   +---------------
              | lower buffer
              +---------------
  page count  == USHRT_MAX
  rx_buffer->pagecnt_bias == USHRT_MAX

t1: Buffer is received, and passed to the stack (e.g.)
              +---------------
              | upper buff (skb)
              +---------------
used by NIC ->| lower buffer
(rx_buffer)   +---------------
  page count  == USHRT_MAX
  rx_buffer->pagecnt_bias == USHRT_MAX - 1

t2: Buffer is received, and redirected
              +---------------
              | upper buff (skb)
              +---------------
used by NIC ->| lower buffer
(rx_buffer)   +---------------

Now, prior calling xdp_do_redirect():
  page count  == USHRT_MAX
  rx_buffer->pagecnt_bias == USHRT_MAX - 2

This means that buffer *cannot* be flipped/reused, because the skb is
still using it.

The problem arises when xdp_do_redirect() actually frees the
segment. Then we get:
  page count  == USHRT_MAX - 1
  rx_buffer->pagecnt_bias == USHRT_MAX - 2

From a recycle perspective, the buffer can be flipped and reused,
which means that the skb data area is passed to the Rx HW ring!

To work around this, the page count is stored prior calling
xdp_do_redirect().

Fixes: 9cbc948b5a20 ("igb: add XDP support")
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Tested-by: Vishakha Jambekar <vishakha.jambekar@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 878b31d534ec..d3b37761f637 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -8214,7 +8214,8 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring,
 	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
 }
 
-static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer)
+static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
+				  int rx_buf_pgcnt)
 {
 	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
 	struct page *page = rx_buffer->page;
@@ -8225,7 +8226,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer)
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely((page_ref_count(page) - pagecnt_bias) > 1))
+	if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1))
 		return false;
 #else
 #define IGB_LAST_OFFSET \
@@ -8614,11 +8615,17 @@ static unsigned int igb_rx_offset(struct igb_ring *rx_ring)
 }
 
 static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring,
-					       const unsigned int size)
+					       const unsigned int size, int *rx_buf_pgcnt)
 {
 	struct igb_rx_buffer *rx_buffer;
 
 	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+	*rx_buf_pgcnt =
+#if (PAGE_SIZE < 8192)
+		page_count(rx_buffer->page);
+#else
+		0;
+#endif
 	prefetchw(rx_buffer->page);
 
 	/* we are reusing so sync this buffer for CPU use */
@@ -8634,9 +8641,9 @@ static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring,
 }
 
 static void igb_put_rx_buffer(struct igb_ring *rx_ring,
-			      struct igb_rx_buffer *rx_buffer)
+			      struct igb_rx_buffer *rx_buffer, int rx_buf_pgcnt)
 {
-	if (igb_can_reuse_rx_page(rx_buffer)) {
+	if (igb_can_reuse_rx_page(rx_buffer, rx_buf_pgcnt)) {
 		/* hand second half of page back to the ring */
 		igb_reuse_rx_page(rx_ring, rx_buffer);
 	} else {
@@ -8664,6 +8671,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	unsigned int xdp_xmit = 0;
 	struct xdp_buff xdp;
 	u32 frame_sz = 0;
+	int rx_buf_pgcnt;
 
 	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
 #if (PAGE_SIZE < 8192)
@@ -8693,7 +8701,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		 */
 		dma_rmb();
 
-		rx_buffer = igb_get_rx_buffer(rx_ring, size);
+		rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt);
 
 		/* retrieve a buffer from the ring */
 		if (!skb) {
@@ -8736,7 +8744,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 			break;
 		}
 
-		igb_put_rx_buffer(rx_ring, rx_buffer);
+		igb_put_rx_buffer(rx_ring, rx_buffer, rx_buf_pgcnt);
 		cleaned_count++;
 
 		/* fetch next buffer in frame if non-eop */

From 6fcd9cbc6a903f48eebaa14657aeccb003f69a3d Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <musamaanjum@gmail.com>
Date: Sat, 6 Mar 2021 00:11:23 +0500
Subject: [PATCH 0743/1820] kvm: x86: annotate RCU pointers

This patch adds the annotation to fix the following sparse errors:
arch/x86/kvm//x86.c:8147:15: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//x86.c:8147:15:    struct kvm_apic_map [noderef] __rcu *
arch/x86/kvm//x86.c:8147:15:    struct kvm_apic_map *
arch/x86/kvm//x86.c:10628:16: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//x86.c:10628:16:    struct kvm_apic_map [noderef] __rcu *
arch/x86/kvm//x86.c:10628:16:    struct kvm_apic_map *
arch/x86/kvm//x86.c:10629:15: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//x86.c:10629:15:    struct kvm_pmu_event_filter [noderef] __rcu *
arch/x86/kvm//x86.c:10629:15:    struct kvm_pmu_event_filter *
arch/x86/kvm//lapic.c:267:15: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//lapic.c:267:15:    struct kvm_apic_map [noderef] __rcu *
arch/x86/kvm//lapic.c:267:15:    struct kvm_apic_map *
arch/x86/kvm//lapic.c:269:9: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//lapic.c:269:9:    struct kvm_apic_map [noderef] __rcu *
arch/x86/kvm//lapic.c:269:9:    struct kvm_apic_map *
arch/x86/kvm//lapic.c:637:15: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//lapic.c:637:15:    struct kvm_apic_map [noderef] __rcu *
arch/x86/kvm//lapic.c:637:15:    struct kvm_apic_map *
arch/x86/kvm//lapic.c:994:15: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//lapic.c:994:15:    struct kvm_apic_map [noderef] __rcu *
arch/x86/kvm//lapic.c:994:15:    struct kvm_apic_map *
arch/x86/kvm//lapic.c:1036:15: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//lapic.c:1036:15:    struct kvm_apic_map [noderef] __rcu *
arch/x86/kvm//lapic.c:1036:15:    struct kvm_apic_map *
arch/x86/kvm//lapic.c:1173:15: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//lapic.c:1173:15:    struct kvm_apic_map [noderef] __rcu *
arch/x86/kvm//lapic.c:1173:15:    struct kvm_apic_map *
arch/x86/kvm//pmu.c:190:18: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//pmu.c:190:18:    struct kvm_pmu_event_filter [noderef] __rcu *
arch/x86/kvm//pmu.c:190:18:    struct kvm_pmu_event_filter *
arch/x86/kvm//pmu.c:251:18: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//pmu.c:251:18:    struct kvm_pmu_event_filter [noderef] __rcu *
arch/x86/kvm//pmu.c:251:18:    struct kvm_pmu_event_filter *
arch/x86/kvm//pmu.c:522:18: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//pmu.c:522:18:    struct kvm_pmu_event_filter [noderef] __rcu *
arch/x86/kvm//pmu.c:522:18:    struct kvm_pmu_event_filter *
arch/x86/kvm//pmu.c:522:18: error: incompatible types in comparison expression (different address spaces):
arch/x86/kvm//pmu.c:522:18:    struct kvm_pmu_event_filter [noderef] __rcu *
arch/x86/kvm//pmu.c:522:18:    struct kvm_pmu_event_filter *

Signed-off-by: Muhammad Usama Anjum <musamaanjum@gmail.com>
Message-Id: <20210305191123.GA497469@LEGION>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 877a4025d8da..9bc091ecaaeb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -963,7 +963,7 @@ struct kvm_arch {
 	struct kvm_pit *vpit;
 	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
-	struct kvm_apic_map *apic_map;
+	struct kvm_apic_map __rcu *apic_map;
 	atomic_t apic_map_dirty;
 
 	bool apic_access_page_done;
@@ -1036,7 +1036,7 @@ struct kvm_arch {
 
 	bool bus_lock_detection_enabled;
 
-	struct kvm_pmu_event_filter *pmu_event_filter;
+	struct kvm_pmu_event_filter __rcu *pmu_event_filter;
 	struct task_struct *nx_lpage_recovery_thread;
 
 #ifdef CONFIG_X86_64

From d7eb79c6290c7ae4561418544072e0a3266e7384 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpengli@tencent.com>
Date: Wed, 24 Feb 2021 09:37:29 +0800
Subject: [PATCH 0744/1820] KVM: kvmclock: Fix vCPUs > 64 can't be
 online/hotpluged

# lscpu
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                88
On-line CPU(s) list:   0-63
Off-line CPU(s) list:  64-87

# cat /proc/cmdline
BOOT_IMAGE=/vmlinuz-5.10.0-rc3-tlinux2-0050+ root=/dev/mapper/cl-root ro
rd.lvm.lv=cl/root rhgb quiet console=ttyS0 LANG=en_US .UTF-8 no-kvmclock-vsyscall

# echo 1 > /sys/devices/system/cpu/cpu76/online
-bash: echo: write error: Cannot allocate memory

The per-cpu vsyscall pvclock data pointer assigns either an element of the
static array hv_clock_boot (#vCPU <= 64) or dynamically allocated memory
hvclock_mem (vCPU > 64), the dynamically memory will not be allocated if
kvmclock vsyscall is disabled, this can result in cpu hotpluged fails in
kvmclock_setup_percpu() which returns -ENOMEM. It's broken for no-vsyscall
and sometimes you end up with vsyscall disabled if the host does something
strange. This patch fixes it by allocating this dynamically memory
unconditionally even if vsyscall is disabled.

Fixes: 6a1cac56f4 ("x86/kvm: Use __bss_decrypted attribute in shared variables")
Reported-by: Zelin Deng <zelin.deng@linux.alibaba.com>
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: stable@vger.kernel.org#v4.19-rc5+
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Message-Id: <1614130683-24137-1-git-send-email-wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kernel/kvmclock.c | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index aa593743acf6..1fc0962c89c0 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -268,21 +268,20 @@ static void __init kvmclock_init_mem(void)
 
 static int __init kvm_setup_vsyscall_timeinfo(void)
 {
-#ifdef CONFIG_X86_64
-	u8 flags;
-
-	if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall)
-		return 0;
-
-	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
-	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
-		return 0;
-
-	kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
-#endif
-
 	kvmclock_init_mem();
 
+#ifdef CONFIG_X86_64
+	if (per_cpu(hv_clock_per_cpu, 0) && kvmclock_vsyscall) {
+		u8 flags;
+
+		flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
+		if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+			return 0;
+
+		kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
+	}
+#endif
+
 	return 0;
 }
 early_initcall(kvm_setup_vsyscall_timeinfo);

From 8df9f1af2eced9720f71cf310275d81c1bf07a06 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 9 Mar 2021 16:30:29 -0800
Subject: [PATCH 0745/1820] KVM: x86/mmu: Skip !MMU-present SPTEs when removing
 SP in exclusive mode

If mmu_lock is held for write, don't bother setting !PRESENT SPTEs to
REMOVED_SPTE when recursively zapping SPTEs as part of shadow page
removal.  The concurrent write protections provided by REMOVED_SPTE are
not needed, there are no backing page side effects to record, and MMIO
SPTEs can be left as is since they are protected by the memslot
generation, not by ensuring that the MMIO SPTE is unreachable (which
is racy with respect to lockless walks regardless of zapping behavior).

Skipping !PRESENT drastically reduces the number of updates needed to
tear down sparsely populated MMUs, e.g. when tearing down a 6gb VM that
didn't touch much memory, 6929/7168 (~96.6%) of SPTEs were '0' and could
be skipped.

Avoiding the write itself is likely close to a wash, but avoiding
__handle_changed_spte() is a clear-cut win as that involves saving and
restoring all non-volatile GPRs (it's a subtly big function), as well as
several conditional branches before bailing out.

Cc: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210310003029.1250571-1-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/tdp_mmu.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index c926c6b899a1..d78915019b08 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -337,7 +337,18 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
 				cpu_relax();
 			}
 		} else {
+			/*
+			 * If the SPTE is not MMU-present, there is no backing
+			 * page associated with the SPTE and so no side effects
+			 * that need to be recorded, and exclusive ownership of
+			 * mmu_lock ensures the SPTE can't be made present.
+			 * Note, zapping MMIO SPTEs is also unnecessary as they
+			 * are guarded by the memslots generation, not by being
+			 * unreachable.
+			 */
 			old_child_spte = READ_ONCE(*sptep);
+			if (!is_shadow_present_pte(old_child_spte))
+				continue;
 
 			/*
 			 * Marking the SPTE as a removed SPTE is not

From 35737d2db2f4567106c90060ad110b27cb354fa4 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpengli@tencent.com>
Date: Thu, 4 Mar 2021 08:35:18 +0800
Subject: [PATCH 0746/1820] KVM: LAPIC: Advancing the timer expiration on guest
 initiated write

Advancing the timer expiration should only be necessary on guest initiated
writes. When we cancel the timer and clear .pending during state restore,
clear expired_tscdeadline as well.

Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Message-Id: <1614818118-965-1-git-send-email-wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/lapic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index cb8ebfaccfb6..cc369b9ad8f1 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2604,6 +2604,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 
 	apic_update_ppr(apic);
 	hrtimer_cancel(&apic->lapic_timer.timer);
+	apic->lapic_timer.expired_tscdeadline = 0;
 	apic_update_lvtt(apic);
 	apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
 	update_divide_count(apic);

From 080bfa1e6d928a5d1f185cc44e5f3c251df06df5 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 12 Mar 2021 12:15:03 -0800
Subject: [PATCH 0747/1820] Revert "net: bonding: fix error return code of
 bond_neigh_init()"

This reverts commit 2055a99da8a253a357bdfd359b3338ef3375a26c.

This change rejects legitimate configurations.

A slave doesn't need to exist nor implement ndo_slave_setup.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 456315bef3a8..74cbbb22470b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3978,15 +3978,11 @@ static int bond_neigh_init(struct neighbour *n)
 
 	rcu_read_lock();
 	slave = bond_first_slave_rcu(bond);
-	if (!slave) {
-		ret = -EINVAL;
+	if (!slave)
 		goto out;
-	}
 	slave_ops = slave->dev->netdev_ops;
-	if (!slave_ops->ndo_neigh_setup) {
-		ret = -EINVAL;
+	if (!slave_ops->ndo_neigh_setup)
 		goto out;
-	}
 
 	/* TODO: find another way [1] to implement this.
 	 * Passing a zeroed structure is fragile,

From f4f9fc29e56b6fa9d7fa65ec51d3c82aff99c99b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 12 Mar 2021 20:55:36 +0100
Subject: [PATCH 0748/1820] nvme: fix the nsid value to print in
 nvme_validate_or_alloc_ns

ns can be NULL at this point, and my move of the check from
the original patch by Chaitanya broke this.

Fixes: 0ec84df4953b ("nvme-core: check ctrl css before setting up zns")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/nvme/host/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 82ad5eef9d0c..a5653892d773 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4099,7 +4099,7 @@ static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		if (!nvme_multi_css(ctrl)) {
 			dev_warn(ctrl->device,
 				"command set not reported for nsid: %d\n",
-				ns->head->ns_id);
+				nsid);
 			break;
 		}
 		nvme_alloc_ns(ctrl, nsid, &ids);

From f211ac154577ec9ccf07c15f18a6abf0d9bdb4ab Mon Sep 17 00:00:00 2001
From: liuyacan <yacanliu@163.com>
Date: Fri, 12 Mar 2021 00:32:25 +0800
Subject: [PATCH 0749/1820] net: correct sk_acceptq_is_full()

The "backlog" argument in listen() specifies
the maximom length of pending connections,
so the accept queue should be considered full
if there are exactly "backlog" elements.

Signed-off-by: liuyacan <yacanliu@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 636810ddcd9b..0b6266fd6bf6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -936,7 +936,7 @@ static inline void sk_acceptq_added(struct sock *sk)
 
 static inline bool sk_acceptq_is_full(const struct sock *sk)
 {
-	return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog);
+	return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog);
 }
 
 /*

From 3b0c2d3eaa83da259d7726192cf55a137769012f Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 12 Mar 2021 15:07:09 -0600
Subject: [PATCH 0750/1820] Revert 95ebabde382c ("capabilities: Don't allow
 writing ambiguous v3 file capabilities")

It turns out that there are in fact userspace implementations that
care and this recent change caused a regression.

https://github.com/containers/buildah/issues/3071

As the motivation for the original change was future development,
and the impact is existing real world code just revert this change
and allow the ambiguity in v3 file caps.

Cc: stable@vger.kernel.org
Fixes: 95ebabde382c ("capabilities: Don't allow writing ambiguous v3 file capabilities")
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 security/commoncap.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/security/commoncap.c b/security/commoncap.c
index 28f4d25480df..1c519c875217 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -543,8 +543,7 @@ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry,
 	__u32 magic, nsmagic;
 	struct inode *inode = d_backing_inode(dentry);
 	struct user_namespace *task_ns = current_user_ns(),
-		*fs_ns = inode->i_sb->s_user_ns,
-		*ancestor;
+		*fs_ns = inode->i_sb->s_user_ns;
 	kuid_t rootid;
 	size_t newsize;
 
@@ -567,15 +566,6 @@ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry,
 	if (nsrootid == -1)
 		return -EINVAL;
 
-	/*
-	 * Do not allow allow adding a v3 filesystem capability xattr
-	 * if the rootid field is ambiguous.
-	 */
-	for (ancestor = task_ns->parent; ancestor; ancestor = ancestor->parent) {
-		if (from_kuid(ancestor, rootid) == 0)
-			return -EINVAL;
-	}
-
 	newsize = sizeof(struct vfs_ns_cap_data);
 	nscap = kmalloc(newsize, GFP_ATOMIC);
 	if (!nscap)

From 59cd4f19267a0aab87a8c07e4426eb7187ee548d Mon Sep 17 00:00:00 2001
From: Robert Hancock <robert.hancock@calian.com>
Date: Thu, 11 Mar 2021 14:05:18 -0600
Subject: [PATCH 0751/1820] net: axienet: Fix probe error cleanup

The driver did not always clean up all allocated resources when probe
failed. Fix the probe cleanup path to clean up everything that was
allocated.

Fixes: 57baf8cc70ea ("net: axienet: Handle deferred probe on clock properly")
Signed-off-by: Robert Hancock <robert.hancock@calian.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/xilinx/xilinx_axienet_main.c | 37 +++++++++++++------
 1 file changed, 25 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 3a8775e0ca55..5d677db0aee5 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1880,7 +1880,7 @@ static int axienet_probe(struct platform_device *pdev)
 	if (IS_ERR(lp->regs)) {
 		dev_err(&pdev->dev, "could not map Axi Ethernet regs.\n");
 		ret = PTR_ERR(lp->regs);
-		goto free_netdev;
+		goto cleanup_clk;
 	}
 	lp->regs_start = ethres->start;
 
@@ -1958,18 +1958,18 @@ static int axienet_probe(struct platform_device *pdev)
 			break;
 		default:
 			ret = -EINVAL;
-			goto free_netdev;
+			goto cleanup_clk;
 		}
 	} else {
 		ret = of_get_phy_mode(pdev->dev.of_node, &lp->phy_mode);
 		if (ret)
-			goto free_netdev;
+			goto cleanup_clk;
 	}
 	if (lp->switch_x_sgmii && lp->phy_mode != PHY_INTERFACE_MODE_SGMII &&
 	    lp->phy_mode != PHY_INTERFACE_MODE_1000BASEX) {
 		dev_err(&pdev->dev, "xlnx,switch-x-sgmii only supported with SGMII or 1000BaseX\n");
 		ret = -EINVAL;
-		goto free_netdev;
+		goto cleanup_clk;
 	}
 
 	/* Find the DMA node, map the DMA registers, and decode the DMA IRQs */
@@ -1982,7 +1982,7 @@ static int axienet_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev,
 				"unable to get DMA resource\n");
 			of_node_put(np);
-			goto free_netdev;
+			goto cleanup_clk;
 		}
 		lp->dma_regs = devm_ioremap_resource(&pdev->dev,
 						     &dmares);
@@ -2002,12 +2002,12 @@ static int axienet_probe(struct platform_device *pdev)
 	if (IS_ERR(lp->dma_regs)) {
 		dev_err(&pdev->dev, "could not map DMA regs\n");
 		ret = PTR_ERR(lp->dma_regs);
-		goto free_netdev;
+		goto cleanup_clk;
 	}
 	if ((lp->rx_irq <= 0) || (lp->tx_irq <= 0)) {
 		dev_err(&pdev->dev, "could not determine irqs\n");
 		ret = -ENOMEM;
-		goto free_netdev;
+		goto cleanup_clk;
 	}
 
 	/* Autodetect the need for 64-bit DMA pointers.
@@ -2037,7 +2037,7 @@ static int axienet_probe(struct platform_device *pdev)
 	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(addr_width));
 	if (ret) {
 		dev_err(&pdev->dev, "No suitable DMA available\n");
-		goto free_netdev;
+		goto cleanup_clk;
 	}
 
 	/* Check for Ethernet core IRQ (optional) */
@@ -2068,12 +2068,12 @@ static int axienet_probe(struct platform_device *pdev)
 		if (!lp->phy_node) {
 			dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n");
 			ret = -EINVAL;
-			goto free_netdev;
+			goto cleanup_mdio;
 		}
 		lp->pcs_phy = of_mdio_find_device(lp->phy_node);
 		if (!lp->pcs_phy) {
 			ret = -EPROBE_DEFER;
-			goto free_netdev;
+			goto cleanup_mdio;
 		}
 		lp->phylink_config.pcs_poll = true;
 	}
@@ -2087,17 +2087,30 @@ static int axienet_probe(struct platform_device *pdev)
 	if (IS_ERR(lp->phylink)) {
 		ret = PTR_ERR(lp->phylink);
 		dev_err(&pdev->dev, "phylink_create error (%i)\n", ret);
-		goto free_netdev;
+		goto cleanup_mdio;
 	}
 
 	ret = register_netdev(lp->ndev);
 	if (ret) {
 		dev_err(lp->dev, "register_netdev() error (%i)\n", ret);
-		goto free_netdev;
+		goto cleanup_phylink;
 	}
 
 	return 0;
 
+cleanup_phylink:
+	phylink_destroy(lp->phylink);
+
+cleanup_mdio:
+	if (lp->pcs_phy)
+		put_device(&lp->pcs_phy->dev);
+	if (lp->mii_bus)
+		axienet_mdio_teardown(lp);
+	of_node_put(lp->phy_node);
+
+cleanup_clk:
+	clk_disable_unprepare(lp->clk);
+
 free_netdev:
 	free_netdev(ndev);
 

From 6897087323a2fde46df32917462750c069668b2f Mon Sep 17 00:00:00 2001
From: Dylan Hung <dylan_hung@aspeedtech.com>
Date: Fri, 12 Mar 2021 11:04:05 +1030
Subject: [PATCH 0752/1820] ftgmac100: Restart MAC HW once

The interrupt handler may set the flag to reset the mac in the future,
but that flag is not cleared once the reset has occurred.

Fixes: 10cbd6407609 ("ftgmac100: Rework NAPI & interrupts handling")
Signed-off-by: Dylan Hung <dylan_hung@aspeedtech.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/faraday/ftgmac100.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 88bfe2107938..04421aec2dfd 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1337,6 +1337,7 @@ static int ftgmac100_poll(struct napi_struct *napi, int budget)
 	 */
 	if (unlikely(priv->need_mac_restart)) {
 		ftgmac100_start_hw(priv);
+		priv->need_mac_restart = false;
 
 		/* Re-enable "bad" interrupts */
 		iowrite32(FTGMAC100_INT_BAD,

From b1dd9bf688b0dcc5a34dca660de46c7570bd9243 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 11 Mar 2021 16:52:50 -0800
Subject: [PATCH 0753/1820] net: phy: broadcom: Fix RGMII delays for BCM50160
 and BCM50610M

The PHY driver entry for BCM50160 and BCM50610M calls
bcm54xx_config_init() but does not call bcm54xx_config_clock_delay() in
order to configuration appropriate clock delays on the PHY, fix that.

Fixes: 733336262b28 ("net: phy: Allow BCM5481x PHYs to setup internal TX/RX clock delay")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/broadcom.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index ad51f1889435..82fe5f43f0e9 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -342,6 +342,10 @@ static int bcm54xx_config_init(struct phy_device *phydev)
 	bcm54xx_adjust_rxrefclk(phydev);
 
 	switch (BRCM_PHY_MODEL(phydev)) {
+	case PHY_ID_BCM50610:
+	case PHY_ID_BCM50610M:
+		err = bcm54xx_config_clock_delay(phydev);
+		break;
 	case PHY_ID_BCM54210E:
 		err = bcm54210e_config_init(phydev);
 		break;

From 2e5de7e0c8d2caa860e133ef71fc94671cb8e0bf Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 12 Mar 2021 10:41:12 +0300
Subject: [PATCH 0754/1820] mptcp: fix bit MPTCP_PUSH_PENDING tests

The MPTCP_PUSH_PENDING define is 6 and these tests should be testing if
BIT(6) is set.

Fixes: c2e6048fa1cf ("mptcp: fix race in release_cb")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 76958570ae7f..1590b9d4cde2 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2968,7 +2968,7 @@ static void mptcp_release_cb(struct sock *sk)
 	for (;;) {
 		flags = 0;
 		if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags))
-			flags |= MPTCP_PUSH_PENDING;
+			flags |= BIT(MPTCP_PUSH_PENDING);
 		if (!flags)
 			break;
 
@@ -2981,7 +2981,7 @@ static void mptcp_release_cb(struct sock *sk)
 		 */
 
 		spin_unlock_bh(&sk->sk_lock.slock);
-		if (flags & MPTCP_PUSH_PENDING)
+		if (flags & BIT(MPTCP_PUSH_PENDING))
 			__mptcp_push_pending(sk, 0);
 
 		cond_resched();

From c3b8e07909dbe67b0d580416c1a5257643a73be7 Mon Sep 17 00:00:00 2001
From: Ilya Lipnitskiy <ilya.lipnitskiy@gmail.com>
Date: Fri, 12 Mar 2021 00:07:03 -0800
Subject: [PATCH 0755/1820] net: dsa: mt7530: setup core clock even in TRGMII
 mode

A recent change to MIPS ralink reset logic made it so mt7530 actually
resets the switch on platforms such as mt7621 (where bit 2 is the reset
line for the switch). That exposed an issue where the switch would not
function properly in TRGMII mode after a reset.

Reconfigure core clock in TRGMII mode to fix the issue.

Tested on Ubiquiti ER-X (MT7621) with TRGMII mode enabled.

Fixes: 3f9ef7785a9c ("MIPS: ralink: manage low reset lines")
Signed-off-by: Ilya Lipnitskiy <ilya.lipnitskiy@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c | 46 +++++++++++++++++++---------------------
 1 file changed, 22 insertions(+), 24 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index f06f5fa2f898..9871d7cff93a 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -436,34 +436,32 @@ mt7530_pad_clk_setup(struct dsa_switch *ds, phy_interface_t interface)
 			     TD_DM_DRVP(8) | TD_DM_DRVN(8));
 
 	/* Setup core clock for MT7530 */
-	if (!trgint) {
-		/* Disable MT7530 core clock */
-		core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
+	/* Disable MT7530 core clock */
+	core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
 
-		/* Disable PLL, since phy_device has not yet been created
-		 * provided for phy_[read,write]_mmd_indirect is called, we
-		 * provide our own core_write_mmd_indirect to complete this
-		 * function.
-		 */
-		core_write_mmd_indirect(priv,
-					CORE_GSWPLL_GRP1,
-					MDIO_MMD_VEND2,
-					0);
+	/* Disable PLL, since phy_device has not yet been created
+	 * provided for phy_[read,write]_mmd_indirect is called, we
+	 * provide our own core_write_mmd_indirect to complete this
+	 * function.
+	 */
+	core_write_mmd_indirect(priv,
+				CORE_GSWPLL_GRP1,
+				MDIO_MMD_VEND2,
+				0);
 
-		/* Set core clock into 500Mhz */
-		core_write(priv, CORE_GSWPLL_GRP2,
-			   RG_GSWPLL_POSDIV_500M(1) |
-			   RG_GSWPLL_FBKDIV_500M(25));
+	/* Set core clock into 500Mhz */
+	core_write(priv, CORE_GSWPLL_GRP2,
+		   RG_GSWPLL_POSDIV_500M(1) |
+		   RG_GSWPLL_FBKDIV_500M(25));
 
-		/* Enable PLL */
-		core_write(priv, CORE_GSWPLL_GRP1,
-			   RG_GSWPLL_EN_PRE |
-			   RG_GSWPLL_POSDIV_200M(2) |
-			   RG_GSWPLL_FBKDIV_200M(32));
+	/* Enable PLL */
+	core_write(priv, CORE_GSWPLL_GRP1,
+		   RG_GSWPLL_EN_PRE |
+		   RG_GSWPLL_POSDIV_200M(2) |
+		   RG_GSWPLL_FBKDIV_200M(32));
 
-		/* Enable MT7530 core clock */
-		core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
-	}
+	/* Enable MT7530 core clock */
+	core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
 
 	/* Setup the MT7530 TRGMII Tx Clock */
 	core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);

From a673321aa74fc5604643d6a4653684c0bc9fa617 Mon Sep 17 00:00:00 2001
From: Mat Martineau <mathew.j.martineau@linux.intel.com>
Date: Fri, 12 Mar 2021 16:43:52 -0800
Subject: [PATCH 0756/1820] selftests: mptcp: Restore packet capture option in
 join tests

The join self tests previously used the '-c' command line option to
enable creation of pcap files for the tests that run, but the change to
allow running a subset of the join tests made overlapping use of that
option.

Restore the capture functionality with '-c' and move the syncookie test
option to '-k'.

Fixes: 1002b89f23ea ("selftests: mptcp: add command line arguments for mptcp_join.sh")
Acked-and-tested-by: Geliang Tang <geliangtang@gmail.com>
Co-developed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 30 ++++++++++++-------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 964db9ed544f..ad32240fbfda 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -11,6 +11,7 @@ ksft_skip=4
 timeout=30
 mptcp_connect=""
 capture=0
+do_all_tests=1
 
 TEST_COUNT=0
 
@@ -121,12 +122,6 @@ reset_with_add_addr_timeout()
 		-j DROP
 }
 
-for arg in "$@"; do
-	if [ "$arg" = "-c" ]; then
-		capture=1
-	fi
-done
-
 ip -Version > /dev/null 2>&1
 if [ $? -ne 0 ];then
 	echo "SKIP: Could not run test without ip tool"
@@ -1221,7 +1216,8 @@ usage()
 	echo "  -4 v4mapped_tests"
 	echo "  -b backup_tests"
 	echo "  -p add_addr_ports_tests"
-	echo "  -c syncookies_tests"
+	echo "  -k syncookies_tests"
+	echo "  -c capture pcap files"
 	echo "  -h help"
 }
 
@@ -1235,12 +1231,24 @@ make_file "$cin" "client" 1
 make_file "$sin" "server" 1
 trap cleanup EXIT
 
-if [ -z $1 ]; then
+for arg in "$@"; do
+	# check for "capture" arg before launching tests
+	if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"c"[0-9a-zA-Z]*$ ]]; then
+		capture=1
+	fi
+
+	# exception for the capture option, the rest means: a part of the tests
+	if [ "${arg}" != "-c" ]; then
+		do_all_tests=0
+	fi
+done
+
+if [ $do_all_tests -eq 1 ]; then
 	all_tests
 	exit $ret
 fi
 
-while getopts 'fsltra64bpch' opt; do
+while getopts 'fsltra64bpkch' opt; do
 	case $opt in
 		f)
 			subflows_tests
@@ -1272,9 +1280,11 @@ while getopts 'fsltra64bpch' opt; do
 		p)
 			add_addr_ports_tests
 			;;
-		c)
+		k)
 			syncookies_tests
 			;;
+		c)
+			;;
 		h | *)
 			usage
 			;;

From 6afa455e6153bcbde879dd408f7ac83668b0ac4a Mon Sep 17 00:00:00 2001
From: Lijun Pan <ljp@linux.ibm.com>
Date: Fri, 12 Mar 2021 12:45:30 -0600
Subject: [PATCH 0757/1820] ibmvnic: update MAINTAINERS

Tom wrote most of the driver code and his experience is valuable to us.
Add him as a Reviewer so that patches will be Cc'ed and reviewed by him.

Signed-off-by: Lijun Pan <ljp@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index f2e34ede1ab3..6acc3b839187 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8521,6 +8521,7 @@ IBM Power SRIOV Virtual NIC Device Driver
 M:	Dany Madden <drt@linux.ibm.com>
 M:	Lijun Pan <ljp@linux.ibm.com>
 M:	Sukadev Bhattiprolu <sukadev@linux.ibm.com>
+R:	Thomas Falcon <tlfalcon@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/ibm/ibmvnic.*

From bcbcf50f521843445c9ea320a0569874f88c4b7a Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 13 Mar 2021 04:38:14 +0900
Subject: [PATCH 0758/1820] kbuild: fix ld-version.sh to not be affected by
 locale

ld-version.sh checks the output from $(LD) --version, but it has a
problem on some locales.

For example, in Italian:

  $ LC_MESSAGES=it_IT.UTF-8 ld --version | head -n 1
  ld di GNU (GNU Binutils for Debian) 2.35.2

This makes ld-version.sh fail because it expects "GNU ld" for the
BFD linker case.

Add LC_ALL=C to override the user's locale.

BTW, setting LC_MESSAGES=C (or LANG=C) is not enough because it is
ineffective if LC_ALL is set on the user's environment.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=212105
Reported-by: Marco Scardovi
Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Recensito-da: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/ld-version.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/ld-version.sh b/scripts/ld-version.sh
index 30debf78aa09..1bf3aadde9de 100755
--- a/scripts/ld-version.sh
+++ b/scripts/ld-version.sh
@@ -29,7 +29,7 @@ orig_args="$@"
 # Get the first line of the --version output.
 IFS='
 '
-set -- $("$@" --version)
+set -- $(LC_ALL=C "$@" --version)
 
 # Split the line on spaces.
 IFS=' '

From 15b2219facadec583c24523eed40fa45865f859f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 12 Mar 2021 20:20:42 -0700
Subject: [PATCH 0759/1820] kernel: freezer should treat PF_IO_WORKER like
 PF_KTHREAD for freezing

Don't send fake signals to PF_IO_WORKER threads, they don't accept
signals. Just treat them like kthreads in this regard, all they need
is a wakeup as no forced kernel/user transition is needed.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/freezer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/freezer.c b/kernel/freezer.c
index dc520f01f99d..1a2d57d1327c 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -134,7 +134,7 @@ bool freeze_task(struct task_struct *p)
 		return false;
 	}
 
-	if (!(p->flags & PF_KTHREAD))
+	if (!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))
 		fake_signal_wake_up(p);
 	else
 		wake_up_state(p, TASK_INTERRUPTIBLE);

From 16efa4fce3b7af17bb45d635c3e89992d721e0f3 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 12 Mar 2021 20:26:13 -0700
Subject: [PATCH 0760/1820] io_uring: allow IO worker threads to be frozen

With the freezer using the proper signaling to notify us of when it's
time to freeze a thread, we can re-enable normal freezer usage for the
IO threads. Ensure that SQPOLL, io-wq, and the io-wq manager call
try_to_freeze() appropriately, and remove the default setting of
PF_NOFREEZE from create_io_thread().

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c    | 6 +++++-
 fs/io_uring.c | 1 +
 kernel/fork.c | 1 -
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 0ae9ecadf295..e05f996d088f 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -488,6 +488,8 @@ static int io_wqe_worker(void *data)
 	set_task_comm(current, buf);
 
 	while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
+		long ret;
+
 		set_current_state(TASK_INTERRUPTIBLE);
 loop:
 		raw_spin_lock_irq(&wqe->lock);
@@ -498,7 +500,8 @@ loop:
 		__io_worker_idle(wqe, worker);
 		raw_spin_unlock_irq(&wqe->lock);
 		io_flush_signals();
-		if (schedule_timeout(WORKER_IDLE_TIMEOUT))
+		ret = schedule_timeout(WORKER_IDLE_TIMEOUT);
+		if (try_to_freeze() || ret)
 			continue;
 		if (fatal_signal_pending(current))
 			break;
@@ -709,6 +712,7 @@ static int io_wq_manager(void *data)
 		set_current_state(TASK_INTERRUPTIBLE);
 		io_wq_check_workers(wq);
 		schedule_timeout(HZ);
+		try_to_freeze();
 		if (fatal_signal_pending(current))
 			set_bit(IO_WQ_BIT_EXIT, &wq->state);
 	} while (!test_bit(IO_WQ_BIT_EXIT, &wq->state));
diff --git a/fs/io_uring.c b/fs/io_uring.c
index a4bce17af506..05adc4887ef3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6752,6 +6752,7 @@ static int io_sq_thread(void *data)
 
 			up_read(&sqd->rw_lock);
 			schedule();
+			try_to_freeze();
 			down_read(&sqd->rw_lock);
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				io_ring_clear_wakeup_flag(ctx);
diff --git a/kernel/fork.c b/kernel/fork.c
index 72e444cd0ffe..d3171e8e88e5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2436,7 +2436,6 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 	if (!IS_ERR(tsk)) {
 		sigfillset(&tsk->blocked);
 		sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
-		tsk->flags |= PF_NOFREEZE;
 	}
 	return tsk;
 }

From d0dcd90b7f472691de122515eb0d1765808b6d91 Mon Sep 17 00:00:00 2001
From: Pawel Laszczak <pawell@cadence.com>
Date: Mon, 8 Mar 2021 08:31:03 +0100
Subject: [PATCH 0761/1820] usb: cdnsp: Fixes incorrect value in ISOC TRB

Fixes issue with priority of operator. Operator "|" priority is
higher then "? :".
To improve the readability the operator "? :" has been replaced with
"if ()" statement.

Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver")
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Pawel Laszczak <pawell@cadence.com>
Signed-off-by: Peter Chen <peter.chen@kernel.org>
---
 drivers/usb/cdns3/cdnsp-ring.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
index f9170d177a89..5f0513c96c04 100644
--- a/drivers/usb/cdns3/cdnsp-ring.c
+++ b/drivers/usb/cdns3/cdnsp-ring.c
@@ -2197,7 +2197,10 @@ static int cdnsp_queue_isoc_tx(struct cdnsp_device *pdev,
 	 * inverted in the first TDs isoc TRB.
 	 */
 	field = TRB_TYPE(TRB_ISOC) | TRB_TLBPC(last_burst_pkt) |
-		start_cycle ? 0 : 1 | TRB_SIA | TRB_TBC(burst_count);
+		TRB_SIA | TRB_TBC(burst_count);
+
+	if (!start_cycle)
+		field |= TRB_CYCLE;
 
 	/* Fill the rest of the TRB fields, and remaining normal TRBs. */
 	for (i = 0; i < trbs_per_td; i++) {

From 34dc2efb39a231280fd6696a59bbe712bf3c5c4a Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 12 Mar 2021 21:07:01 -0800
Subject: [PATCH 0762/1820] memblock: fix section mismatch warning

The inlining logic in clang-13 is rewritten to often not inline some
functions that were inlined by all earlier compilers.

In case of the memblock interfaces, this exposed a harmless bug of a
missing __init annotation:

WARNING: modpost: vmlinux.o(.text+0x507c0a): Section mismatch in reference from the function memblock_bottom_up() to the variable .meminit.data:memblock
The function memblock_bottom_up() references
the variable __meminitdata memblock.
This is often because memblock_bottom_up lacks a __meminitdata
annotation or the annotation of memblock is wrong.

Interestingly, these annotations were present originally, but got removed
with the explanation that the __init annotation prevents the function from
getting inlined.  I checked this again and found that while this is the
case with clang, gcc (version 7 through 10, did not test others) does
inline the functions regardless.

As the previous change was apparently intended to help the clang builds,
reverting it to help the newer clang versions seems appropriate as well.
gcc builds don't seem to care either way.

Link: https://lkml.kernel.org/r/20210225133808.2188581-1-arnd@kernel.org
Fixes: 5bdba520c1b3 ("mm: memblock: drop __init from memblock functions to make it inline")
Reference: 2cfb3665e864 ("include/linux/memblock.h: add __init to memblock_set_bottom_up()")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Faiyaz Mohammed <faiyazm@codeaurora.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Aslan Bakirov <aslan@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memblock.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index c88bc24e31aa..d13e3cd938b4 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -460,7 +460,7 @@ static inline void memblock_free_late(phys_addr_t base, phys_addr_t size)
 /*
  * Set the allocation direction to bottom-up or top-down.
  */
-static inline void memblock_set_bottom_up(bool enable)
+static inline __init void memblock_set_bottom_up(bool enable)
 {
 	memblock.bottom_up = enable;
 }
@@ -470,7 +470,7 @@ static inline void memblock_set_bottom_up(bool enable)
  * if this is true, that said, memblock will allocate memory
  * in bottom-up direction.
  */
-static inline bool memblock_bottom_up(void)
+static inline __init bool memblock_bottom_up(void)
 {
 	return memblock.bottom_up;
 }

From cbf78d85079cee662c45749ef4f744d41be85d48 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 12 Mar 2021 21:07:04 -0800
Subject: [PATCH 0763/1820] stop_machine: mark helpers __always_inline

With clang-13, some functions only get partially inlined, with a
specialized version referring to a global variable.  This triggers a
harmless build-time check for the intel-rng driver:

WARNING: modpost: drivers/char/hw_random/intel-rng.o(.text+0xe): Section mismatch in reference from the function stop_machine() to the function .init.text:intel_rng_hw_init()
The function stop_machine() references
the function __init intel_rng_hw_init().
This is often because stop_machine lacks a __init
annotation or the annotation of intel_rng_hw_init is wrong.

In this instance, an easy workaround is to force the stop_machine()
function to be inline, along with related interfaces that did not show the
same behavior at the moment, but theoretically could.

The combination of the two patches listed below triggers the behavior in
clang-13, but individually these commits are correct.

Link: https://lkml.kernel.org/r/20210225130153.1956990-1-arnd@kernel.org
Fixes: fe5595c07400 ("stop_machine: Provide stop_machine_cpuslocked()")
Fixes: ee527cd3a20c ("Use stop_machine_run in the Intel RNG driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/stop_machine.h | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 30577c3aecf8..46fb3ebdd16e 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -128,7 +128,7 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 				   const struct cpumask *cpus);
 #else	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
 
-static inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data,
+static __always_inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data,
 					  const struct cpumask *cpus)
 {
 	unsigned long flags;
@@ -139,14 +139,15 @@ static inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data,
 	return ret;
 }
 
-static inline int stop_machine(cpu_stop_fn_t fn, void *data,
-			       const struct cpumask *cpus)
+static __always_inline int
+stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
 {
 	return stop_machine_cpuslocked(fn, data, cpus);
 }
 
-static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
-						 const struct cpumask *cpus)
+static __always_inline int
+stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
+			       const struct cpumask *cpus)
 {
 	return stop_machine(fn, data, cpus);
 }

From ea29b20a828511de3348334e529a3d046a180416 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Fri, 12 Mar 2021 21:07:08 -0800
Subject: [PATCH 0764/1820] init/Kconfig: make COMPILE_TEST depend on HAS_IOMEM

I read the commit log of the following two:

- bc083a64b6c0 ("init/Kconfig: make COMPILE_TEST depend on !UML")
- 334ef6ed06fa ("init/Kconfig: make COMPILE_TEST depend on !S390")

Both are talking about HAS_IOMEM dependency missing in many drivers.

So, 'depends on HAS_IOMEM' seems the direct, sensible solution to me.

This does not change the behavior of UML. UML still cannot enable
COMPILE_TEST because it does not provide HAS_IOMEM.

The current dependency for S390 is too strong. Under the condition of
CONFIG_PCI=y, S390 provides HAS_IOMEM, hence can enable COMPILE_TEST.

I also removed the meaningless 'default n'.

Link: https://lkml.kernel.org/r/20210224140809.1067582-1-masahiroy@kernel.org
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Arnd Bergmann <arnd@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: KP Singh <kpsingh@google.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Quentin Perret <qperret@google.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: "Enrico Weigelt, metux IT consult" <lkml@metux.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 init/Kconfig | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 22946fe5ded9..8f8a497aafe0 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -119,8 +119,7 @@ config INIT_ENV_ARG_LIMIT
 
 config COMPILE_TEST
 	bool "Compile also drivers which will not load"
-	depends on !UML && !S390
-	default n
+	depends on HAS_IOMEM
 	help
 	  Some drivers can be compiled on a different platform than they are
 	  intended to be run on. Despite they cannot be loaded there (or even

From 0740a50b9baa4472cfb12442df4b39e2712a64a4 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Fri, 12 Mar 2021 21:07:12 -0800
Subject: [PATCH 0765/1820] mm/page_alloc.c: refactor initialization of struct
 page for holes in memory layout
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There could be struct pages that are not backed by actual physical memory.
This can happen when the actual memory bank is not a multiple of
SECTION_SIZE or when an architecture does not register memory holes
reserved by the firmware as memblock.memory.

Such pages are currently initialized using init_unavailable_mem() function
that iterates through PFNs in holes in memblock.memory and if there is a
struct page corresponding to a PFN, the fields of this page are set to
default values and it is marked as Reserved.

init_unavailable_mem() does not take into account zone and node the page
belongs to and sets both zone and node links in struct page to zero.

Before commit 73a6e474cb37 ("mm: memmap_init: iterate over memblock
regions rather that check each PFN") the holes inside a zone were
re-initialized during memmap_init() and got their zone/node links right.
However, after that commit nothing updates the struct pages representing
such holes.

On a system that has firmware reserved holes in a zone above ZONE_DMA, for
instance in a configuration below:

	# grep -A1 E820 /proc/iomem
	7a17b000-7a216fff : Unknown E820 type
	7a217000-7bffffff : System RAM

unset zone link in struct page will trigger

	VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);

in set_pfnblock_flags_mask() when called with a struct page from a range
other than E820_TYPE_RAM because there are pages in the range of
ZONE_DMA32 but the unset zone link in struct page makes them appear as a
part of ZONE_DMA.

Interleave initialization of the unavailable pages with the normal
initialization of memory map, so that zone and node information will be
properly set on struct pages that are not backed by the actual memory.

With this change the pages for holes inside a zone will get proper
zone/node links and the pages that are not spanned by any node will get
links to the adjacent zone/node.  The holes between nodes will be
prepended to the zone/node above the hole and the trailing pages in the
last section that will be appended to the zone/node below.

[akpm@linux-foundation.org: don't initialize static to zero, use %llu for u64]

Link: https://lkml.kernel.org/r/20210225224351.7356-2-rppt@kernel.org
Fixes: 73a6e474cb37 ("mm: memmap_init: iterate over memblock regions rather that check each PFN")
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Reported-by: Qian Cai <cai@lca.pw>
Reported-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Łukasz Majczak <lma@semihalf.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: "Sarvela, Tomi P" <tomi.p.sarvela@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 158 +++++++++++++++++++++++-------------------------
 1 file changed, 75 insertions(+), 83 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3e4b29ee2b1e..d4580e4215d8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6259,12 +6259,65 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 	}
 }
 
+#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
+/*
+ * Only struct pages that correspond to ranges defined by memblock.memory
+ * are zeroed and initialized by going through __init_single_page() during
+ * memmap_init_zone().
+ *
+ * But, there could be struct pages that correspond to holes in
+ * memblock.memory. This can happen because of the following reasons:
+ * - physical memory bank size is not necessarily the exact multiple of the
+ *   arbitrary section size
+ * - early reserved memory may not be listed in memblock.memory
+ * - memory layouts defined with memmap= kernel parameter may not align
+ *   nicely with memmap sections
+ *
+ * Explicitly initialize those struct pages so that:
+ * - PG_Reserved is set
+ * - zone and node links point to zone and node that span the page if the
+ *   hole is in the middle of a zone
+ * - zone and node links point to adjacent zone/node if the hole falls on
+ *   the zone boundary; the pages in such holes will be prepended to the
+ *   zone/node above the hole except for the trailing pages in the last
+ *   section that will be appended to the zone/node below.
+ */
+static u64 __meminit init_unavailable_range(unsigned long spfn,
+					    unsigned long epfn,
+					    int zone, int node)
+{
+	unsigned long pfn;
+	u64 pgcnt = 0;
+
+	for (pfn = spfn; pfn < epfn; pfn++) {
+		if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
+			pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
+				+ pageblock_nr_pages - 1;
+			continue;
+		}
+		__init_single_page(pfn_to_page(pfn), pfn, zone, node);
+		__SetPageReserved(pfn_to_page(pfn));
+		pgcnt++;
+	}
+
+	return pgcnt;
+}
+#else
+static inline u64 init_unavailable_range(unsigned long spfn, unsigned long epfn,
+					 int zone, int node)
+{
+	return 0;
+}
+#endif
+
 void __meminit __weak memmap_init_zone(struct zone *zone)
 {
 	unsigned long zone_start_pfn = zone->zone_start_pfn;
 	unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages;
 	int i, nid = zone_to_nid(zone), zone_id = zone_idx(zone);
+	static unsigned long hole_pfn;
 	unsigned long start_pfn, end_pfn;
+	u64 pgcnt = 0;
 
 	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
 		start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn);
@@ -6274,7 +6327,29 @@ void __meminit __weak memmap_init_zone(struct zone *zone)
 			memmap_init_range(end_pfn - start_pfn, nid,
 					zone_id, start_pfn, zone_end_pfn,
 					MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
+
+		if (hole_pfn < start_pfn)
+			pgcnt += init_unavailable_range(hole_pfn, start_pfn,
+							zone_id, nid);
+		hole_pfn = end_pfn;
 	}
+
+#ifdef CONFIG_SPARSEMEM
+	/*
+	 * Initialize the hole in the range [zone_end_pfn, section_end].
+	 * If zone boundary falls in the middle of a section, this hole
+	 * will be re-initialized during the call to this function for the
+	 * higher zone.
+	 */
+	end_pfn = round_up(zone_end_pfn, PAGES_PER_SECTION);
+	if (hole_pfn < end_pfn)
+		pgcnt += init_unavailable_range(hole_pfn, end_pfn,
+						zone_id, nid);
+#endif
+
+	if (pgcnt)
+		pr_info("  %s zone: %llu pages in unavailable ranges\n",
+			zone->name, pgcnt);
 }
 
 static int zone_batchsize(struct zone *zone)
@@ -7071,88 +7146,6 @@ void __init free_area_init_memoryless_node(int nid)
 	free_area_init_node(nid);
 }
 
-#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
-/*
- * Initialize all valid struct pages in the range [spfn, epfn) and mark them
- * PageReserved(). Return the number of struct pages that were initialized.
- */
-static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn)
-{
-	unsigned long pfn;
-	u64 pgcnt = 0;
-
-	for (pfn = spfn; pfn < epfn; pfn++) {
-		if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
-			pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
-				+ pageblock_nr_pages - 1;
-			continue;
-		}
-		/*
-		 * Use a fake node/zone (0) for now. Some of these pages
-		 * (in memblock.reserved but not in memblock.memory) will
-		 * get re-initialized via reserve_bootmem_region() later.
-		 */
-		__init_single_page(pfn_to_page(pfn), pfn, 0, 0);
-		__SetPageReserved(pfn_to_page(pfn));
-		pgcnt++;
-	}
-
-	return pgcnt;
-}
-
-/*
- * Only struct pages that are backed by physical memory are zeroed and
- * initialized by going through __init_single_page(). But, there are some
- * struct pages which are reserved in memblock allocator and their fields
- * may be accessed (for example page_to_pfn() on some configuration accesses
- * flags). We must explicitly initialize those struct pages.
- *
- * This function also addresses a similar issue where struct pages are left
- * uninitialized because the physical address range is not covered by
- * memblock.memory or memblock.reserved. That could happen when memblock
- * layout is manually configured via memmap=, or when the highest physical
- * address (max_pfn) does not end on a section boundary.
- */
-static void __init init_unavailable_mem(void)
-{
-	phys_addr_t start, end;
-	u64 i, pgcnt;
-	phys_addr_t next = 0;
-
-	/*
-	 * Loop through unavailable ranges not covered by memblock.memory.
-	 */
-	pgcnt = 0;
-	for_each_mem_range(i, &start, &end) {
-		if (next < start)
-			pgcnt += init_unavailable_range(PFN_DOWN(next),
-							PFN_UP(start));
-		next = end;
-	}
-
-	/*
-	 * Early sections always have a fully populated memmap for the whole
-	 * section - see pfn_valid(). If the last section has holes at the
-	 * end and that section is marked "online", the memmap will be
-	 * considered initialized. Make sure that memmap has a well defined
-	 * state.
-	 */
-	pgcnt += init_unavailable_range(PFN_DOWN(next),
-					round_up(max_pfn, PAGES_PER_SECTION));
-
-	/*
-	 * Struct pages that do not have backing memory. This could be because
-	 * firmware is using some of this memory, or for some other reasons.
-	 */
-	if (pgcnt)
-		pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt);
-}
-#else
-static inline void __init init_unavailable_mem(void)
-{
-}
-#endif /* !CONFIG_FLAT_NODE_MEM_MAP */
-
 #if MAX_NUMNODES > 1
 /*
  * Figure out the number of possible node ids.
@@ -7576,7 +7569,6 @@ void __init free_area_init(unsigned long *max_zone_pfn)
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
 	setup_nr_node_ids();
-	init_unavailable_mem();
 	for_each_online_node(nid) {
 		pg_data_t *pgdat = NODE_DATA(nid);
 		free_area_init_node(nid);

From 82e69a121be4b1597ce758534816a8ee04c8b761 Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Fri, 12 Mar 2021 21:07:15 -0800
Subject: [PATCH 0766/1820] mm/fork: clear PASID for new mm

When a new mm is created, its PASID should be cleared, i.e.  the PASID is
initialized to its init state 0 on both ARM and X86.

This patch was part of the series introducing mm->pasid, but got lost
along the way [1].  It still makes sense to have it, because each address
space has a different PASID.  And the IOMMU code in
iommu_sva_alloc_pasid() expects the pasid field of a new mm struct to be
cleared.

[1] https://lore.kernel.org/linux-iommu/YDgh53AcQHT+T3L0@otcwcpicx3.sc.intel.com/

Link: https://lkml.kernel.org/r/20210302103837.2562625-1-jean-philippe@linaro.org
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Cc: Jacob Pan <jacob.jun.pan@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm_types.h | 1 +
 kernel/fork.c            | 8 ++++++++
 2 files changed, 9 insertions(+)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0974ad501a47..6613b26a8894 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -23,6 +23,7 @@
 #endif
 #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
 
+#define INIT_PASID	0
 
 struct address_space;
 struct mem_cgroup;
diff --git a/kernel/fork.c b/kernel/fork.c
index d3171e8e88e5..54cc905e5fe0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -994,6 +994,13 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
 #endif
 }
 
+static void mm_init_pasid(struct mm_struct *mm)
+{
+#ifdef CONFIG_IOMMU_SUPPORT
+	mm->pasid = INIT_PASID;
+#endif
+}
+
 static void mm_init_uprobes_state(struct mm_struct *mm)
 {
 #ifdef CONFIG_UPROBES
@@ -1024,6 +1031,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm_init_cpumask(mm);
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	mm_init_pasid(mm);
 	RCU_INIT_POINTER(mm->exe_file, NULL);
 	mmu_notifier_subscriptions_init(mm);
 	init_tlb_flush_pending(mm);

From 2103cf9c3f3ba002feab8bfd9c5528ce676cf65a Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 12 Mar 2021 21:07:18 -0800
Subject: [PATCH 0767/1820] hugetlb: dedup the code to add a new file_region

Patch series "mm/hugetlb: Early cow on fork, and a few cleanups", v5.

As reported by Gal [1], we still miss the code clip to handle early cow
for hugetlb case, which is true.  Again, it still feels odd to fork()
after using a few huge pages, especially if they're privately mapped to
me..  However I do agree with Gal and Jason in that we should still have
that since that'll complete the early cow on fork effort at least, and
it'll still fix issues where buffers are not well under control and not
easy to apply MADV_DONTFORK.

The first two patches (1-2) are some cleanups I noticed when reading into
the hugetlb reserve map code.  I think it's good to have but they're not
necessary for fixing the fork issue.

The last two patches (3-4) are the real fix.

I tested this with a fork() after some vfio-pci assignment, so I'm pretty
sure the page copy path could trigger well (page will be accounted right
after the fork()), but I didn't do data check since the card I assigned is
some random nic.

  https://github.com/xzpeter/linux/tree/fork-cow-pin-huge

[1] https://lore.kernel.org/lkml/27564187-4a08-f187-5a84-3df50009f6ca@amazon.com/

Introduce hugetlb_resv_map_add() helper to add a new file_region rather
than duplication the similar code twice in add_reservation_in_range().

Link: https://lkml.kernel.org/r/20210217233547.93892-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20210217233547.93892-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Gal Pressman <galpress@amazon.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Wei Zhang <wzam@amazon.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jann Horn <jannh@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Kirill Shutemov <kirill@shutemov.name>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: Roland Scheidegger <sroland@vmware.com>
Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/hugetlb.c | 51 +++++++++++++++++++++++++++------------------------
 1 file changed, 27 insertions(+), 24 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8fb42c6dd74b..e92a176dbb91 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -331,6 +331,24 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
 	}
 }
 
+static inline long
+hugetlb_resv_map_add(struct resv_map *map, struct file_region *rg, long from,
+		     long to, struct hstate *h, struct hugetlb_cgroup *cg,
+		     long *regions_needed)
+{
+	struct file_region *nrg;
+
+	if (!regions_needed) {
+		nrg = get_file_region_entry_from_cache(map, from, to);
+		record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg);
+		list_add(&nrg->link, rg->link.prev);
+		coalesce_file_region(map, nrg);
+	} else
+		*regions_needed += 1;
+
+	return to - from;
+}
+
 /*
  * Must be called with resv->lock held.
  *
@@ -346,7 +364,7 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
 	long add = 0;
 	struct list_head *head = &resv->regions;
 	long last_accounted_offset = f;
-	struct file_region *rg = NULL, *trg = NULL, *nrg = NULL;
+	struct file_region *rg = NULL, *trg = NULL;
 
 	if (regions_needed)
 		*regions_needed = 0;
@@ -375,18 +393,11 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
 		/* Add an entry for last_accounted_offset -> rg->from, and
 		 * update last_accounted_offset.
 		 */
-		if (rg->from > last_accounted_offset) {
-			add += rg->from - last_accounted_offset;
-			if (!regions_needed) {
-				nrg = get_file_region_entry_from_cache(
-					resv, last_accounted_offset, rg->from);
-				record_hugetlb_cgroup_uncharge_info(h_cg, h,
-								    resv, nrg);
-				list_add(&nrg->link, rg->link.prev);
-				coalesce_file_region(resv, nrg);
-			} else
-				*regions_needed += 1;
-		}
+		if (rg->from > last_accounted_offset)
+			add += hugetlb_resv_map_add(resv, rg,
+						    last_accounted_offset,
+						    rg->from, h, h_cg,
+						    regions_needed);
 
 		last_accounted_offset = rg->to;
 	}
@@ -394,17 +405,9 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
 	/* Handle the case where our range extends beyond
 	 * last_accounted_offset.
 	 */
-	if (last_accounted_offset < t) {
-		add += t - last_accounted_offset;
-		if (!regions_needed) {
-			nrg = get_file_region_entry_from_cache(
-				resv, last_accounted_offset, t);
-			record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg);
-			list_add(&nrg->link, rg->link.prev);
-			coalesce_file_region(resv, nrg);
-		} else
-			*regions_needed += 1;
-	}
+	if (last_accounted_offset < t)
+		add += hugetlb_resv_map_add(resv, rg, last_accounted_offset,
+					    t, h, h_cg, regions_needed);
 
 	VM_BUG_ON(add < 0);
 	return add;

From ca7e0457efefca9eeee8c42a89a7f450651d555b Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 12 Mar 2021 21:07:22 -0800
Subject: [PATCH 0768/1820] hugetlb: break earlier in
 add_reservation_in_range() when we can

All the regions maintained in hugetlb reserved map is inclusive on "from"
but exclusive on "to".  We can break earlier even if rg->from==t because
it already means no possible intersection.

This does not need a Fixes in all cases because when it happens
(rg->from==t) we'll not break out of the loop while we should, however the
next thing we'd do is still add the last file_region we'd need and quit
the loop in the next round.  So this change is not a bugfix (since the old
code should still run okay iiuc), but we'd better still touch it up to
make it logically sane.

Link: https://lkml.kernel.org/r/20210217233547.93892-3-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Gal Pressman <galpress@amazon.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kirill Shutemov <kirill@shutemov.name>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Roland Scheidegger <sroland@vmware.com>
Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Cc: Wei Zhang <wzam@amazon.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/hugetlb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e92a176dbb91..b905143a523e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -387,7 +387,7 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
 		/* When we find a region that starts beyond our range, we've
 		 * finished.
 		 */
-		if (rg->from > t)
+		if (rg->from >= t)
 			break;
 
 		/* Add an entry for last_accounted_offset -> rg->from, and

From 97a7e4733b9b221d012ae68fcd3b3251febf6341 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 12 Mar 2021 21:07:26 -0800
Subject: [PATCH 0769/1820] mm: introduce page_needs_cow_for_dma() for deciding
 whether cow

We've got quite a few places (pte, pmd, pud) that explicitly checked
against whether we should break the cow right now during fork().  It's
easier to provide a helper, especially before we work the same thing on
hugetlbfs.

Since we'll reference is_cow_mapping() in mm.h, move it there too.
Actually it suites mm.h more since internal.h is mm/ only, but mm.h is
exported to the whole kernel.  With that we should expect another patch to
use is_cow_mapping() whenever we can across the kernel since we do use it
quite a lot but it's always done with raw code against VM_* flags.

Link: https://lkml.kernel.org/r/20210217233547.93892-4-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Gal Pressman <galpress@amazon.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Kirill Shutemov <kirill@shutemov.name>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Roland Scheidegger <sroland@vmware.com>
Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Cc: Wei Zhang <wzam@amazon.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 21 +++++++++++++++++++++
 mm/huge_memory.c   |  8 ++------
 mm/internal.h      |  5 -----
 mm/memory.c        |  8 +-------
 4 files changed, 24 insertions(+), 18 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 77e64e3eac80..64a71bf20536 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1300,6 +1300,27 @@ static inline bool page_maybe_dma_pinned(struct page *page)
 		GUP_PIN_COUNTING_BIAS;
 }
 
+static inline bool is_cow_mapping(vm_flags_t flags)
+{
+	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
+}
+
+/*
+ * This should most likely only be called during fork() to see whether we
+ * should break the cow immediately for a page on the src mm.
+ */
+static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
+					  struct page *page)
+{
+	if (!is_cow_mapping(vma->vm_flags))
+		return false;
+
+	if (!atomic_read(&vma->vm_mm->has_pinned))
+		return false;
+
+	return page_maybe_dma_pinned(page);
+}
+
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
 #define SECTION_IN_PAGE_FLAGS
 #endif
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 395c75111d33..da1d63a41aec 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1100,9 +1100,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 * best effort that the pinned pages won't be replaced by another
 	 * random page during the coming copy-on-write.
 	 */
-	if (unlikely(is_cow_mapping(vma->vm_flags) &&
-		     atomic_read(&src_mm->has_pinned) &&
-		     page_maybe_dma_pinned(src_page))) {
+	if (unlikely(page_needs_cow_for_dma(vma, src_page))) {
 		pte_free(dst_mm, pgtable);
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
@@ -1214,9 +1212,7 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	}
 
 	/* Please refer to comments in copy_huge_pmd() */
-	if (unlikely(is_cow_mapping(vma->vm_flags) &&
-		     atomic_read(&src_mm->has_pinned) &&
-		     page_maybe_dma_pinned(pud_page(pud)))) {
+	if (unlikely(page_needs_cow_for_dma(vma, pud_page(pud)))) {
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
 		__split_huge_pud(vma, src_pud, addr);
diff --git a/mm/internal.h b/mm/internal.h
index 9902648f2206..1432feec62df 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -296,11 +296,6 @@ static inline unsigned int buddy_order(struct page *page)
  */
 #define buddy_order_unsafe(page)	READ_ONCE(page_private(page))
 
-static inline bool is_cow_mapping(vm_flags_t flags)
-{
-	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
-}
-
 /*
  * These three helpers classifies VMAs for virtual memory accounting.
  */
diff --git a/mm/memory.c b/mm/memory.c
index c8e357627318..523230005db1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -809,12 +809,8 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 		  pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
 		  struct page **prealloc, pte_t pte, struct page *page)
 {
-	struct mm_struct *src_mm = src_vma->vm_mm;
 	struct page *new_page;
 
-	if (!is_cow_mapping(src_vma->vm_flags))
-		return 1;
-
 	/*
 	 * What we want to do is to check whether this page may
 	 * have been pinned by the parent process.  If so,
@@ -828,9 +824,7 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 	 * the page count. That might give false positives for
 	 * for pinning, but it will work correctly.
 	 */
-	if (likely(!atomic_read(&src_mm->has_pinned)))
-		return 1;
-	if (likely(!page_maybe_dma_pinned(page)))
+	if (likely(!page_needs_cow_for_dma(src_vma, page)))
 		return 1;
 
 	new_page = *prealloc;

From ca6eb14d6453bea85ac66fa4c6ab75dfe93eaf45 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 12 Mar 2021 21:07:30 -0800
Subject: [PATCH 0770/1820] mm: use is_cow_mapping() across tree where proper

After is_cow_mapping() is exported in mm.h, replace some manual checks
elsewhere throughout the tree but start to use the new helper.

Link: https://lkml.kernel.org/r/20210217233547.93892-5-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Jason Gunthorpe <jgg@ziepe.ca>
Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Cc: Roland Scheidegger <sroland@vmware.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Gal Pressman <galpress@amazon.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Kirill Shutemov <kirill@shutemov.name>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Wei Zhang <wzam@amazon.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c | 4 +---
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c   | 2 +-
 fs/proc/task_mmu.c                         | 2 --
 mm/hugetlb.c                               | 4 +---
 4 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
index 0a900afc66ff..45c9c6a7f1d6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
@@ -500,8 +500,6 @@ vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf,
 	vm_fault_t ret;
 	pgoff_t fault_page_size;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
-	bool is_cow_mapping =
-		(vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
 	switch (pe_size) {
 	case PE_SIZE_PMD:
@@ -518,7 +516,7 @@ vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf,
 	}
 
 	/* Always do write dirty-tracking and COW on PTE level. */
-	if (write && (READ_ONCE(vbo->dirty) || is_cow_mapping))
+	if (write && (READ_ONCE(vbo->dirty) || is_cow_mapping(vma->vm_flags)))
 		return VM_FAULT_FALLBACK;
 
 	ret = ttm_bo_vm_reserve(bo, vmf);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
index 3c03b1746661..cb9975889e2f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
@@ -49,7 +49,7 @@ int vmw_mmap(struct file *filp, struct vm_area_struct *vma)
 	vma->vm_ops = &vmw_vm_ops;
 
 	/* Use VM_PFNMAP rather than VM_MIXEDMAP if not a COW mapping */
-	if ((vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) != VM_MAYWRITE)
+	if (!is_cow_mapping(vma->vm_flags))
 		vma->vm_flags = (vma->vm_flags & ~VM_MIXEDMAP) | VM_PFNMAP;
 
 	return 0;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 3cec6fbef725..e862cab69583 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1036,8 +1036,6 @@ struct clear_refs_private {
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
 
-#define is_cow_mapping(flags) (((flags) & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE)
-
 static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 {
 	struct page *page;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b905143a523e..7786267da2fe 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3734,15 +3734,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	pte_t *src_pte, *dst_pte, entry, dst_entry;
 	struct page *ptepage;
 	unsigned long addr;
-	int cow;
+	bool cow = is_cow_mapping(vma->vm_flags);
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	struct mmu_notifier_range range;
 	int ret = 0;
 
-	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
-
 	if (cow) {
 		mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src,
 					vma->vm_start,

From 4eae4efa2c299f85b7ebfbeeda56c19c5eba2768 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 12 Mar 2021 21:07:33 -0800
Subject: [PATCH 0771/1820] hugetlb: do early cow when page pinned on src mm

This is the last missing piece of the COW-during-fork effort when there're
pinned pages found.  One can reference 70e806e4e645 ("mm: Do early cow for
pinned pages during fork() for ptes", 2020-09-27) for more information,
since we do similar things here rather than pte this time, but just for
hugetlb.

Note that after Jason's recent work on 57efa1fe5957 ("mm/gup: prevent
gup_fast from racing with COW during fork", 2020-12-15) which is safer and
easier to understand, we're safe now within the whole copy_page_range()
against gup-fast, we don't need the wr-protect trick that proposed in
70e806e4e645 anymore.

Link: https://lkml.kernel.org/r/20210217233547.93892-6-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Gal Pressman <galpress@amazon.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Kirill Shutemov <kirill@shutemov.name>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Roland Scheidegger <sroland@vmware.com>
Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Cc: Wei Zhang <wzam@amazon.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/hugetlb.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 62 insertions(+), 4 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7786267da2fe..5b1ab1f427c5 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3728,6 +3728,18 @@ static bool is_hugetlb_entry_hwpoisoned(pte_t pte)
 		return false;
 }
 
+static void
+hugetlb_install_page(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr,
+		     struct page *new_page)
+{
+	__SetPageUptodate(new_page);
+	set_huge_pte_at(vma->vm_mm, addr, ptep, make_huge_pte(vma, new_page, 1));
+	hugepage_add_new_anon_rmap(new_page, vma, addr);
+	hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm);
+	ClearHPageRestoreReserve(new_page);
+	SetHPageMigratable(new_page);
+}
+
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			    struct vm_area_struct *vma)
 {
@@ -3737,6 +3749,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	bool cow = is_cow_mapping(vma->vm_flags);
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
+	unsigned long npages = pages_per_huge_page(h);
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	struct mmu_notifier_range range;
 	int ret = 0;
@@ -3785,6 +3798,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 		entry = huge_ptep_get(src_pte);
 		dst_entry = huge_ptep_get(dst_pte);
+again:
 		if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) {
 			/*
 			 * Skip if src entry none.  Also, skip in the
@@ -3808,6 +3822,52 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			}
 			set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
 		} else {
+			entry = huge_ptep_get(src_pte);
+			ptepage = pte_page(entry);
+			get_page(ptepage);
+
+			/*
+			 * This is a rare case where we see pinned hugetlb
+			 * pages while they're prone to COW.  We need to do the
+			 * COW earlier during fork.
+			 *
+			 * When pre-allocating the page or copying data, we
+			 * need to be without the pgtable locks since we could
+			 * sleep during the process.
+			 */
+			if (unlikely(page_needs_cow_for_dma(vma, ptepage))) {
+				pte_t src_pte_old = entry;
+				struct page *new;
+
+				spin_unlock(src_ptl);
+				spin_unlock(dst_ptl);
+				/* Do not use reserve as it's private owned */
+				new = alloc_huge_page(vma, addr, 1);
+				if (IS_ERR(new)) {
+					put_page(ptepage);
+					ret = PTR_ERR(new);
+					break;
+				}
+				copy_user_huge_page(new, ptepage, addr, vma,
+						    npages);
+				put_page(ptepage);
+
+				/* Install the new huge page if src pte stable */
+				dst_ptl = huge_pte_lock(h, dst, dst_pte);
+				src_ptl = huge_pte_lockptr(h, src, src_pte);
+				spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+				entry = huge_ptep_get(src_pte);
+				if (!pte_same(src_pte_old, entry)) {
+					put_page(new);
+					/* dst_entry won't change as in child */
+					goto again;
+				}
+				hugetlb_install_page(vma, dst_pte, addr, new);
+				spin_unlock(src_ptl);
+				spin_unlock(dst_ptl);
+				continue;
+			}
+
 			if (cow) {
 				/*
 				 * No need to notify as we are downgrading page
@@ -3818,12 +3878,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 				 */
 				huge_ptep_set_wrprotect(src, addr, src_pte);
 			}
-			entry = huge_ptep_get(src_pte);
-			ptepage = pte_page(entry);
-			get_page(ptepage);
+
 			page_dup_rmap(ptepage, true);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
-			hugetlb_count_add(pages_per_huge_page(h), dst);
+			hugetlb_count_add(npages, dst);
 		}
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);

From 184cee516f3e24019a08ac8eb5c7cf04c00933cb Mon Sep 17 00:00:00 2001
From: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Date: Fri, 12 Mar 2021 21:07:37 -0800
Subject: [PATCH 0772/1820] mm/highmem.c: fix zero_user_segments() with start >
 end

zero_user_segments() is used from __block_write_begin_int(), for example
like the following

	zero_user_segments(page, 4096, 1024, 512, 918)

But new the zero_user_segments() implementation for for HIGHMEM +
TRANSPARENT_HUGEPAGE doesn't handle "start > end" case correctly, and hits
BUG_ON().  (we can fix __block_write_begin_int() instead though, it is the
old and multiple usage)

Also it calls kmap_atomic() unnecessarily while start == end == 0.

Link: https://lkml.kernel.org/r/87v9ab60r4.fsf@mail.parknet.co.jp
Fixes: 0060ef3b4e6d ("mm: support THPs in zero_user_segments")
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/highmem.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/mm/highmem.c b/mm/highmem.c
index 874b732b120c..86f2b9495f9c 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -368,20 +368,24 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
 
 	BUG_ON(end1 > page_size(page) || end2 > page_size(page));
 
+	if (start1 >= end1)
+		start1 = end1 = 0;
+	if (start2 >= end2)
+		start2 = end2 = 0;
+
 	for (i = 0; i < compound_nr(page); i++) {
 		void *kaddr = NULL;
 
-		if (start1 < PAGE_SIZE || start2 < PAGE_SIZE)
-			kaddr = kmap_atomic(page + i);
-
 		if (start1 >= PAGE_SIZE) {
 			start1 -= PAGE_SIZE;
 			end1 -= PAGE_SIZE;
 		} else {
 			unsigned this_end = min_t(unsigned, end1, PAGE_SIZE);
 
-			if (end1 > start1)
+			if (end1 > start1) {
+				kaddr = kmap_atomic(page + i);
 				memset(kaddr + start1, 0, this_end - start1);
+			}
 			end1 -= this_end;
 			start1 = 0;
 		}
@@ -392,8 +396,11 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
 		} else {
 			unsigned this_end = min_t(unsigned, end2, PAGE_SIZE);
 
-			if (end2 > start2)
+			if (end2 > start2) {
+				if (!kaddr)
+					kaddr = kmap_atomic(page + i);
 				memset(kaddr + start2, 0, this_end - start2);
+			}
 			end2 -= this_end;
 			start2 = 0;
 		}

From e7850f4d844e0acfac7e570af611d89deade3146 Mon Sep 17 00:00:00 2001
From: Lior Ribak <liorribak@gmail.com>
Date: Fri, 12 Mar 2021 21:07:41 -0800
Subject: [PATCH 0773/1820] binfmt_misc: fix possible deadlock in
 bm_register_write

There is a deadlock in bm_register_write:

First, in the begining of the function, a lock is taken on the binfmt_misc
root inode with inode_lock(d_inode(root)).

Then, if the user used the MISC_FMT_OPEN_FILE flag, the function will call
open_exec on the user-provided interpreter.

open_exec will call a path lookup, and if the path lookup process includes
the root of binfmt_misc, it will try to take a shared lock on its inode
again, but it is already locked, and the code will get stuck in a deadlock

To reproduce the bug:
$ echo ":iiiii:E::ii::/proc/sys/fs/binfmt_misc/bla:F" > /proc/sys/fs/binfmt_misc/register

backtrace of where the lock occurs (#5):
0  schedule () at ./arch/x86/include/asm/current.h:15
1  0xffffffff81b51237 in rwsem_down_read_slowpath (sem=0xffff888003b202e0, count=<optimized out>, state=state@entry=2) at kernel/locking/rwsem.c:992
2  0xffffffff81b5150a in __down_read_common (state=2, sem=<optimized out>) at kernel/locking/rwsem.c:1213
3  __down_read (sem=<optimized out>) at kernel/locking/rwsem.c:1222
4  down_read (sem=<optimized out>) at kernel/locking/rwsem.c:1355
5  0xffffffff811ee22a in inode_lock_shared (inode=<optimized out>) at ./include/linux/fs.h:783
6  open_last_lookups (op=0xffffc9000022fe34, file=0xffff888004098600, nd=0xffffc9000022fd10) at fs/namei.c:3177
7  path_openat (nd=nd@entry=0xffffc9000022fd10, op=op@entry=0xffffc9000022fe34, flags=flags@entry=65) at fs/namei.c:3366
8  0xffffffff811efe1c in do_filp_open (dfd=<optimized out>, pathname=pathname@entry=0xffff8880031b9000, op=op@entry=0xffffc9000022fe34) at fs/namei.c:3396
9  0xffffffff811e493f in do_open_execat (fd=fd@entry=-100, name=name@entry=0xffff8880031b9000, flags=<optimized out>, flags@entry=0) at fs/exec.c:913
10 0xffffffff811e4a92 in open_exec (name=<optimized out>) at fs/exec.c:948
11 0xffffffff8124aa84 in bm_register_write (file=<optimized out>, buffer=<optimized out>, count=19, ppos=<optimized out>) at fs/binfmt_misc.c:682
12 0xffffffff811decd2 in vfs_write (file=file@entry=0xffff888004098500, buf=buf@entry=0xa758d0 ":iiiii:E::ii::i:CF
", count=count@entry=19, pos=pos@entry=0xffffc9000022ff10) at fs/read_write.c:603
13 0xffffffff811defda in ksys_write (fd=<optimized out>, buf=0xa758d0 ":iiiii:E::ii::i:CF
", count=19) at fs/read_write.c:658
14 0xffffffff81b49813 in do_syscall_64 (nr=<optimized out>, regs=0xffffc9000022ff58) at arch/x86/entry/common.c:46
15 0xffffffff81c0007c in entry_SYSCALL_64 () at arch/x86/entry/entry_64.S:120

To solve the issue, the open_exec call is moved to before the write
lock is taken by bm_register_write

Link: https://lkml.kernel.org/r/20210228224414.95962-1-liorribak@gmail.com
Fixes: 948b701a607f1 ("binfmt_misc: add persistent opened binary handler for containers")
Signed-off-by: Lior Ribak <liorribak@gmail.com>
Acked-by: Helge Deller <deller@gmx.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_misc.c | 29 ++++++++++++++---------------
 1 file changed, 14 insertions(+), 15 deletions(-)

diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index c457334de43f..e1eae7ea823a 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -649,12 +649,24 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 	struct super_block *sb = file_inode(file)->i_sb;
 	struct dentry *root = sb->s_root, *dentry;
 	int err = 0;
+	struct file *f = NULL;
 
 	e = create_entry(buffer, count);
 
 	if (IS_ERR(e))
 		return PTR_ERR(e);
 
+	if (e->flags & MISC_FMT_OPEN_FILE) {
+		f = open_exec(e->interpreter);
+		if (IS_ERR(f)) {
+			pr_notice("register: failed to install interpreter file %s\n",
+				 e->interpreter);
+			kfree(e);
+			return PTR_ERR(f);
+		}
+		e->interp_file = f;
+	}
+
 	inode_lock(d_inode(root));
 	dentry = lookup_one_len(e->name, root, strlen(e->name));
 	err = PTR_ERR(dentry);
@@ -678,21 +690,6 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 		goto out2;
 	}
 
-	if (e->flags & MISC_FMT_OPEN_FILE) {
-		struct file *f;
-
-		f = open_exec(e->interpreter);
-		if (IS_ERR(f)) {
-			err = PTR_ERR(f);
-			pr_notice("register: failed to install interpreter file %s\n", e->interpreter);
-			simple_release_fs(&bm_mnt, &entry_count);
-			iput(inode);
-			inode = NULL;
-			goto out2;
-		}
-		e->interp_file = f;
-	}
-
 	e->dentry = dget(dentry);
 	inode->i_private = e;
 	inode->i_fop = &bm_entry_operations;
@@ -709,6 +706,8 @@ out:
 	inode_unlock(d_inode(root));
 
 	if (err) {
+		if (f)
+			filp_close(f, NULL);
 		kfree(e);
 		return err;
 	}

From f0b15b6081291367634a8f3c557f7a68fdaa35e4 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Fri, 12 Mar 2021 21:07:44 -0800
Subject: [PATCH 0774/1820] MAINTAINERS: exclude uapi directories in API/ABI
 section

Commit 7b4693e644cb ("MAINTAINERS: add uapi directories to API/ABI
section") added include/uapi/ and arch/*/include/uapi/ so that patches
modifying them CC linux-api.  However that was already done in the past
and resulted in too much noise and thus later removed, as explained in
b14fd334ff3d ("MAINTAINERS: trim the file triggers for ABI/API")

To prevent another round of addition and removal in the future, change the
entries to X: (explicit exclusion) for documentation purposes, although
they are not subdirectories of broader included directories, as there is
apparently no defined way to add plain comments in subsystem sections.

Link: https://lkml.kernel.org/r/20210301100255.25229-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Michael Kerrisk (man-pages) <mtk.manpages@gmail.com>
Acked-by: Michael Kerrisk (man-pages) <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 72e5b9db5050..1b3c05666071 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -261,8 +261,8 @@ ABI/API
 L:	linux-api@vger.kernel.org
 F:	include/linux/syscalls.h
 F:	kernel/sys_ni.c
-F:	include/uapi/
-F:	arch/*/include/uapi/
+X:	include/uapi/
+X:	arch/*/include/uapi/
 
 ABIT UGURU 1,2 HARDWARE MONITOR DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>

From 97e4910232fa1f81e806aa60c25a0450276d99a2 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 12 Mar 2021 21:07:47 -0800
Subject: [PATCH 0775/1820] linux/compiler-clang.h: define HAVE_BUILTIN_BSWAP*

Separating compiler-clang.h from compiler-gcc.h inadventently dropped the
definitions of the three HAVE_BUILTIN_BSWAP macros, which requires falling
back to the open-coded version and hoping that the compiler detects it.

Since all versions of clang support the __builtin_bswap interfaces, add
back the flags and have the headers pick these up automatically.

This results in a 4% improvement of compilation speed for arm defconfig.

Note: it might also be worth revisiting which architectures set
CONFIG_ARCH_USE_BUILTIN_BSWAP for one compiler or the other, today this is
set on six architectures (arm32, csky, mips, powerpc, s390, x86), while
another ten architectures define custom helpers (alpha, arc, ia64, m68k,
mips, nios2, parisc, sh, sparc, xtensa), and the rest (arm64, h8300,
hexagon, microblaze, nds32, openrisc, riscv) just get the unoptimized
version and rely on the compiler to detect it.

A long time ago, the compiler builtins were architecture specific, but
nowadays, all compilers that are able to build the kernel have correct
implementations of them, though some may not be as optimized as the inline
asm versions.

The patch that dropped the optimization landed in v4.19, so as discussed
it would be fairly safe to backport this revert to stable kernels to the
4.19/5.4/5.10 stable kernels, but there is a remaining risk for
regressions, and it has no known side-effects besides compile speed.

Link: https://lkml.kernel.org/r/20210226161151.2629097-1-arnd@kernel.org
Link: https://lore.kernel.org/lkml/20210225164513.3667778-1-arnd@kernel.org/
Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Miguel Ojeda <ojeda@kernel.org>
Acked-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Guo Ren <guoren@kernel.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Sami Tolvanen <samitolvanen@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Arvind Sankar <nivedita@alum.mit.edu>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler-clang.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 04c0a5a717f7..d217c382b02d 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -31,6 +31,12 @@
 #define __no_sanitize_thread
 #endif
 
+#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP)
+#define __HAVE_BUILTIN_BSWAP32__
+#define __HAVE_BUILTIN_BSWAP64__
+#define __HAVE_BUILTIN_BSWAP16__
+#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
+
 #if __has_feature(undefined_behavior_sanitizer)
 /* GCC does not have __SANITIZE_UNDEFINED__ */
 #define __no_sanitize_undefined \

From 702b16d724a61cb97461f403d7a2da29324471b3 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Fri, 12 Mar 2021 21:07:50 -0800
Subject: [PATCH 0776/1820] kfence: fix printk format for ptrdiff_t

Use %td for ptrdiff_t.

Link: https://lkml.kernel.org/r/3abbe4c9-16ad-c168-a90f-087978ccd8f7@csgroup.eu
Link: https://lkml.kernel.org/r/20210303121157.3430807-1-elver@google.com
Signed-off-by: Marco Elver <elver@google.com>
Reported-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Alexander Potapenko <glider@google.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/kfence/report.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/mm/kfence/report.c b/mm/kfence/report.c
index ab83d5a59bb1..519f037720f5 100644
--- a/mm/kfence/report.c
+++ b/mm/kfence/report.c
@@ -116,12 +116,12 @@ void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *met
 	lockdep_assert_held(&meta->lock);
 
 	if (meta->state == KFENCE_OBJECT_UNUSED) {
-		seq_con_printf(seq, "kfence-#%zd unused\n", meta - kfence_metadata);
+		seq_con_printf(seq, "kfence-#%td unused\n", meta - kfence_metadata);
 		return;
 	}
 
 	seq_con_printf(seq,
-		       "kfence-#%zd [0x%p-0x%p"
+		       "kfence-#%td [0x%p-0x%p"
 		       ", size=%d, cache=%s] allocated by task %d:\n",
 		       meta - kfence_metadata, (void *)start, (void *)(start + size - 1), size,
 		       (cache && cache->name) ? cache->name : "<destroyed>", meta->alloc_track.pid);
@@ -204,7 +204,7 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r
 
 		pr_err("BUG: KFENCE: out-of-bounds %s in %pS\n\n", get_access_type(is_write),
 		       (void *)stack_entries[skipnr]);
-		pr_err("Out-of-bounds %s at 0x%p (%luB %s of kfence-#%zd):\n",
+		pr_err("Out-of-bounds %s at 0x%p (%luB %s of kfence-#%td):\n",
 		       get_access_type(is_write), (void *)address,
 		       left_of_object ? meta->addr - address : address - meta->addr,
 		       left_of_object ? "left" : "right", object_index);
@@ -213,14 +213,14 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r
 	case KFENCE_ERROR_UAF:
 		pr_err("BUG: KFENCE: use-after-free %s in %pS\n\n", get_access_type(is_write),
 		       (void *)stack_entries[skipnr]);
-		pr_err("Use-after-free %s at 0x%p (in kfence-#%zd):\n",
+		pr_err("Use-after-free %s at 0x%p (in kfence-#%td):\n",
 		       get_access_type(is_write), (void *)address, object_index);
 		break;
 	case KFENCE_ERROR_CORRUPTION:
 		pr_err("BUG: KFENCE: memory corruption in %pS\n\n", (void *)stack_entries[skipnr]);
 		pr_err("Corrupted memory at 0x%p ", (void *)address);
 		print_diff_canary(address, 16, meta);
-		pr_cont(" (in kfence-#%zd):\n", object_index);
+		pr_cont(" (in kfence-#%td):\n", object_index);
 		break;
 	case KFENCE_ERROR_INVALID:
 		pr_err("BUG: KFENCE: invalid %s in %pS\n\n", get_access_type(is_write),
@@ -230,7 +230,7 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r
 		break;
 	case KFENCE_ERROR_INVALID_FREE:
 		pr_err("BUG: KFENCE: invalid free in %pS\n\n", (void *)stack_entries[skipnr]);
-		pr_err("Invalid free of 0x%p (in kfence-#%zd):\n", (void *)address,
+		pr_err("Invalid free of 0x%p (in kfence-#%td):\n", (void *)address,
 		       object_index);
 		break;
 	}

From df3ae2c9941d38106afd67d7816b58f6dc7405e8 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Fri, 12 Mar 2021 21:07:53 -0800
Subject: [PATCH 0777/1820] kfence, slab: fix cache_alloc_debugcheck_after()
 for bulk allocations

cache_alloc_debugcheck_after() performs checks on an object, including
adjusting the returned pointer.  None of this should apply to KFENCE
objects.  While for non-bulk allocations, the checks are skipped when we
allocate via KFENCE, for bulk allocations cache_alloc_debugcheck_after()
is called via cache_alloc_debugcheck_after_bulk().

Fix it by skipping cache_alloc_debugcheck_after() for KFENCE objects.

Link: https://lkml.kernel.org/r/20210304205256.2162309-1-elver@google.com
Signed-off-by: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/slab.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/slab.c b/mm/slab.c
index 51fd424e0d6d..ae651bf540b7 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2992,7 +2992,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 				gfp_t flags, void *objp, unsigned long caller)
 {
 	WARN_ON_ONCE(cachep->ctor && (flags & __GFP_ZERO));
-	if (!objp)
+	if (!objp || is_kfence_address(objp))
 		return objp;
 	if (cachep->flags & SLAB_POISON) {
 		check_poison_obj(cachep, objp);

From 0aa41cae92c1e2e61ae5b3a2dde8e674172e40ac Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Fri, 12 Mar 2021 21:08:00 -0800
Subject: [PATCH 0778/1820] kfence: fix reports if constant function prefixes
 exist

Some architectures prefix all functions with a constant string ('.' on
ppc64).  Add ARCH_FUNC_PREFIX, which may optionally be defined in
<asm/kfence.h>, so that get_stack_skipnr() can work properly.

Link: https://lkml.kernel.org/r/f036c53d-7e81-763c-47f4-6024c6c5f058@csgroup.eu
Link: https://lkml.kernel.org/r/20210304144000.1148590-1-elver@google.com
Signed-off-by: Marco Elver <elver@google.com>
Reported-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/kfence/report.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/mm/kfence/report.c b/mm/kfence/report.c
index 519f037720f5..e3f71451ad9e 100644
--- a/mm/kfence/report.c
+++ b/mm/kfence/report.c
@@ -20,6 +20,11 @@
 
 #include "kfence.h"
 
+/* May be overridden by <asm/kfence.h>. */
+#ifndef ARCH_FUNC_PREFIX
+#define ARCH_FUNC_PREFIX ""
+#endif
+
 extern bool no_hash_pointers;
 
 /* Helper function to either print to a seq_file or to console. */
@@ -67,8 +72,9 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
 	for (skipnr = 0; skipnr < num_entries; skipnr++) {
 		int len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skipnr]);
 
-		if (str_has_prefix(buf, "kfence_") || str_has_prefix(buf, "__kfence_") ||
-		    !strncmp(buf, "__slab_free", len)) {
+		if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfence_") ||
+		    str_has_prefix(buf, ARCH_FUNC_PREFIX "__kfence_") ||
+		    !strncmp(buf, ARCH_FUNC_PREFIX "__slab_free", len)) {
 			/*
 			 * In case of tail calls from any of the below
 			 * to any of the above.
@@ -77,10 +83,10 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
 		}
 
 		/* Also the *_bulk() variants by only checking prefixes. */
-		if (str_has_prefix(buf, "kfree") ||
-		    str_has_prefix(buf, "kmem_cache_free") ||
-		    str_has_prefix(buf, "__kmalloc") ||
-		    str_has_prefix(buf, "kmem_cache_alloc"))
+		if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfree") ||
+		    str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_free") ||
+		    str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmalloc") ||
+		    str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_alloc"))
 			goto found;
 	}
 	if (fallback < num_entries)

From 149fc787353f65b7e72e05e7b75d34863266c3e2 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 12 Mar 2021 21:08:03 -0800
Subject: [PATCH 0779/1820] include/linux/sched/mm.h: use rcu_dereference in
 in_vfork()

Fix a sparse warning by using rcu_dereference().  Technically this is a
bug and a sufficiently aggressive compiler could reload the `real_parent'
pointer outside the protection of the rcu lock (and access freed memory),
but I think it's pretty unlikely to happen.

Link: https://lkml.kernel.org/r/20210221194207.1351703-1-willy@infradead.org
Fixes: b18dc5f291c0 ("mm, oom: skip vforked tasks from being selected")
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched/mm.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 1ae08b8462a4..90b2a0bce11c 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -140,7 +140,8 @@ static inline bool in_vfork(struct task_struct *tsk)
 	 * another oom-unkillable task does this it should blame itself.
 	 */
 	rcu_read_lock();
-	ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm;
+	ret = tsk->vfork_done &&
+			rcu_dereference(tsk->real_parent)->mm == tsk->mm;
 	rcu_read_unlock();
 
 	return ret;

From 96cfe2c0fd23ea7c2368d14f769d287e7ae1082e Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Fri, 12 Mar 2021 21:08:06 -0800
Subject: [PATCH 0780/1820] mm/madvise: replace ptrace attach requirement for
 process_madvise

process_madvise currently requires ptrace attach capability.
PTRACE_MODE_ATTACH gives one process complete control over another
process.  It effectively removes the security boundary between the two
processes (in one direction).  Granting ptrace attach capability even to a
system process is considered dangerous since it creates an attack surface.
This severely limits the usage of this API.

The operations process_madvise can perform do not affect the correctness
of the operation of the target process; they only affect where the data is
physically located (and therefore, how fast it can be accessed).  What we
want is the ability for one process to influence another process in order
to optimize performance across the entire system while leaving the
security boundary intact.

Replace PTRACE_MODE_ATTACH with a combination of PTRACE_MODE_READ and
CAP_SYS_NICE.  PTRACE_MODE_READ to prevent leaking ASLR metadata and
CAP_SYS_NICE for influencing process performance.

Link: https://lkml.kernel.org/r/20210303185807.2160264-1-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jeff Vander Stoep <jeffv@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: <stable@vger.kernel.org>	[5.10+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/madvise.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/mm/madvise.c b/mm/madvise.c
index df692d2e35d4..01fef79ac761 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1198,12 +1198,22 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
 		goto release_task;
 	}
 
-	mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS);
+	/* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */
+	mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
 	if (IS_ERR_OR_NULL(mm)) {
 		ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
 		goto release_task;
 	}
 
+	/*
+	 * Require CAP_SYS_NICE for influencing process performance. Note that
+	 * only non-destructive hints are currently supported.
+	 */
+	if (!capable(CAP_SYS_NICE)) {
+		ret = -EPERM;
+		goto release_mm;
+	}
+
 	total_len = iov_iter_count(&iter);
 
 	while (iov_iter_count(&iter)) {
@@ -1218,6 +1228,7 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
 	if (ret == 0)
 		ret = total_len - iov_iter_count(&iter);
 
+release_mm:
 	mmput(mm);
 release_task:
 	put_task_struct(task);

From f9d79e8dce4077d3c6ab739c808169dfa99af9ef Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Fri, 12 Mar 2021 21:08:10 -0800
Subject: [PATCH 0781/1820] kasan, mm: fix crash with HW_TAGS and
 DEBUG_PAGEALLOC

Currently, kasan_free_nondeferred_pages()->kasan_free_pages() is called
after debug_pagealloc_unmap_pages(). This causes a crash when
debug_pagealloc is enabled, as HW_TAGS KASAN can't set tags on an
unmapped page.

This patch puts kasan_free_nondeferred_pages() before
debug_pagealloc_unmap_pages() and arch_free_page(), which can also make
the page unavailable.

Link: https://lkml.kernel.org/r/24cd7db274090f0e5bc3adcdc7399243668e3171.1614987311.git.andreyknvl@google.com
Fixes: 94ab5b61ee16 ("kasan, arm64: enable CONFIG_KASAN_HW_TAGS")
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d4580e4215d8..3cd1c0ce4d06 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1281,6 +1281,12 @@ static __always_inline bool free_pages_prepare(struct page *page,
 
 	kernel_poison_pages(page, 1 << order);
 
+	/*
+	 * With hardware tag-based KASAN, memory tags must be set before the
+	 * page becomes unavailable via debug_pagealloc or arch_free_page.
+	 */
+	kasan_free_nondeferred_pages(page, order);
+
 	/*
 	 * arch_free_page() can make the page's contents inaccessible.  s390
 	 * does this.  So nothing which can access the page's contents should
@@ -1290,8 +1296,6 @@ static __always_inline bool free_pages_prepare(struct page *page,
 
 	debug_pagealloc_unmap_pages(page, 1 << order);
 
-	kasan_free_nondeferred_pages(page, order);
-
 	return true;
 }
 

From d9b571c885a8974fbb7d4ee639dbc643fd000f9e Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Fri, 12 Mar 2021 21:08:13 -0800
Subject: [PATCH 0782/1820] kasan: fix KASAN_STACK dependency for HW_TAGS

There's a runtime failure when running HW_TAGS-enabled kernel built with
GCC on hardware that doesn't support MTE.  GCC-built kernels always have
CONFIG_KASAN_STACK enabled, even though stack instrumentation isn't
supported by HW_TAGS.  Having that config enabled causes KASAN to issue
MTE-only instructions to unpoison kernel stacks, which causes the failure.

Fix the issue by disallowing CONFIG_KASAN_STACK when HW_TAGS is used.

(The commit that introduced CONFIG_KASAN_HW_TAGS specified proper
 dependency for CONFIG_KASAN_STACK_ENABLE but not for CONFIG_KASAN_STACK.)

Link: https://lkml.kernel.org/r/59e75426241dbb5611277758c8d4d6f5f9298dac.1615215441.git.andreyknvl@google.com
Fixes: 6a63a63ff1ac ("kasan: introduce CONFIG_KASAN_HW_TAGS")
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reported-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: <stable@vger.kernel.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/Kconfig.kasan | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 624ae1df7984..fba9909e31b7 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -156,6 +156,7 @@ config KASAN_STACK_ENABLE
 
 config KASAN_STACK
 	int
+	depends on KASAN_GENERIC || KASAN_SW_TAGS
 	default 1 if KASAN_STACK_ENABLE || CC_IS_GCC
 	default 0
 

From 6ce64428d62026a10cb5d80138ff2f90cc21d367 Mon Sep 17 00:00:00 2001
From: Nadav Amit <namit@vmware.com>
Date: Fri, 12 Mar 2021 21:08:17 -0800
Subject: [PATCH 0783/1820] mm/userfaultfd: fix memory corruption due to
 writeprotect
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Userfaultfd self-test fails occasionally, indicating a memory corruption.

Analyzing this problem indicates that there is a real bug since mmap_lock
is only taken for read in mwriteprotect_range() and defers flushes, and
since there is insufficient consideration of concurrent deferred TLB
flushes in wp_page_copy().  Although the PTE is flushed from the TLBs in
wp_page_copy(), this flush takes place after the copy has already been
performed, and therefore changes of the page are possible between the time
of the copy and the time in which the PTE is flushed.

To make matters worse, memory-unprotection using userfaultfd also poses a
problem.  Although memory unprotection is logically a promotion of PTE
permissions, and therefore should not require a TLB flush, the current
userrfaultfd code might actually cause a demotion of the architectural PTE
permission: when userfaultfd_writeprotect() unprotects memory region, it
unintentionally *clears* the RW-bit if it was already set.  Note that this
unprotecting a PTE that is not write-protected is a valid use-case: the
userfaultfd monitor might ask to unprotect a region that holds both
write-protected and write-unprotected PTEs.

The scenario that happens in selftests/vm/userfaultfd is as follows:

cpu0				cpu1			cpu2
----				----			----
							[ Writable PTE
							  cached in TLB ]
userfaultfd_writeprotect()
[ write-*unprotect* ]
mwriteprotect_range()
mmap_read_lock()
change_protection()

change_protection_range()
...
change_pte_range()
[ *clear* “write”-bit ]
[ defer TLB flushes ]
				[ page-fault ]
				...
				wp_page_copy()
				 cow_user_page()
				  [ copy page ]
							[ write to old
							  page ]
				...
				 set_pte_at_notify()

A similar scenario can happen:

cpu0		cpu1		cpu2		cpu3
----		----		----		----
						[ Writable PTE
				  		  cached in TLB ]
userfaultfd_writeprotect()
[ write-protect ]
[ deferred TLB flush ]
		userfaultfd_writeprotect()
		[ write-unprotect ]
		[ deferred TLB flush]
				[ page-fault ]
				wp_page_copy()
				 cow_user_page()
				 [ copy page ]
				 ...		[ write to page ]
				set_pte_at_notify()

This race exists since commit 292924b26024 ("userfaultfd: wp: apply
_PAGE_UFFD_WP bit").  Yet, as Yu Zhao pointed, these races became apparent
since commit 09854ba94c6a ("mm: do_wp_page() simplification") which made
wp_page_copy() more likely to take place, specifically if page_count(page)
> 1.

To resolve the aforementioned races, check whether there are pending
flushes on uffd-write-protected VMAs, and if there are, perform a flush
before doing the COW.

Further optimizations will follow to avoid during uffd-write-unprotect
unnecassary PTE write-protection and TLB flushes.

Link: https://lkml.kernel.org/r/20210304095423.3825684-1-namit@vmware.com
Fixes: 09854ba94c6a ("mm: do_wp_page() simplification")
Signed-off-by: Nadav Amit <namit@vmware.com>
Suggested-by: Yu Zhao <yuzhao@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Tested-by: Peter Xu <peterx@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <stable@vger.kernel.org>	[5.9+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memory.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/mm/memory.c b/mm/memory.c
index 523230005db1..5efa07fb6cdc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3097,6 +3097,14 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 		return handle_userfault(vmf, VM_UFFD_WP);
 	}
 
+	/*
+	 * Userfaultfd write-protect can defer flushes. Ensure the TLB
+	 * is flushed in this case before copying.
+	 */
+	if (unlikely(userfaultfd_wp(vmf->vma) &&
+		     mm_tlb_flush_pending(vmf->vma->vm_mm)))
+		flush_tlb_page(vmf->vma, vmf->address);
+
 	vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
 	if (!vmf->page) {
 		/*

From 0ceb1ace4a2778e34a5414e5349712ae4dc41d85 Mon Sep 17 00:00:00 2001
From: Sergei Trofimovich <slyfox@gentoo.org>
Date: Fri, 12 Mar 2021 21:08:23 -0800
Subject: [PATCH 0784/1820] ia64: fix ia64_syscall_get_set_arguments() for
 break-based syscalls

In https://bugs.gentoo.org/769614 Dmitry noticed that
`ptrace(PTRACE_GET_SYSCALL_INFO)` does not work for syscalls called via
glibc's syscall() wrapper.

ia64 has two ways to call syscalls from userspace: via `break` and via
`eps` instructions.

The difference is in stack layout:

1. `eps` creates simple stack frame: no locals, in{0..7} == out{0..8}
2. `break` uses userspace stack frame: may be locals (glibc provides
   one), in{0..7} == out{0..8}.

Both work fine in syscall handling cde itself.

But `ptrace(PTRACE_GET_SYSCALL_INFO)` uses unwind mechanism to
re-extract syscall arguments but it does not account for locals.

The change always skips locals registers. It should not change `eps`
path as kernel's handler already enforces locals=0 and fixes `break`.

Tested on v5.10 on rx3600 machine (ia64 9040 CPU).

Link: https://lkml.kernel.org/r/20210221002554.333076-1-slyfox@gentoo.org
Link: https://bugs.gentoo.org/769614
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Reported-by: Dmitry V. Levin <ldv@altlinux.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/kernel/ptrace.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index c3490ee2daa5..e14f5653393a 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -2013,27 +2013,39 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data)
 {
 	struct syscall_get_set_args *args = data;
 	struct pt_regs *pt = args->regs;
-	unsigned long *krbs, cfm, ndirty;
+	unsigned long *krbs, cfm, ndirty, nlocals, nouts;
 	int i, count;
 
 	if (unw_unwind_to_user(info) < 0)
 		return;
 
+	/*
+	 * We get here via a few paths:
+	 * - break instruction: cfm is shared with caller.
+	 *   syscall args are in out= regs, locals are non-empty.
+	 * - epsinstruction: cfm is set by br.call
+	 *   locals don't exist.
+	 *
+	 * For both cases argguments are reachable in cfm.sof - cfm.sol.
+	 * CFM: [ ... | sor: 17..14 | sol : 13..7 | sof : 6..0 ]
+	 */
 	cfm = pt->cr_ifs;
+	nlocals = (cfm >> 7) & 0x7f; /* aka sol */
+	nouts = (cfm & 0x7f) - nlocals; /* aka sof - sol */
 	krbs = (unsigned long *)info->task + IA64_RBS_OFFSET/8;
 	ndirty = ia64_rse_num_regs(krbs, krbs + (pt->loadrs >> 19));
 
 	count = 0;
 	if (in_syscall(pt))
-		count = min_t(int, args->n, cfm & 0x7f);
+		count = min_t(int, args->n, nouts);
 
+	/* Iterate over outs. */
 	for (i = 0; i < count; i++) {
+		int j = ndirty + nlocals + i + args->i;
 		if (args->rw)
-			*ia64_rse_skip_regs(krbs, ndirty + i + args->i) =
-				args->args[i];
+			*ia64_rse_skip_regs(krbs, j) = args->args[i];
 		else
-			args->args[i] = *ia64_rse_skip_regs(krbs,
-				ndirty + i + args->i);
+			args->args[i] = *ia64_rse_skip_regs(krbs, j);
 	}
 
 	if (!args->rw) {

From 61bf318eac2c13356f7bd1c6a05421ef504ccc8a Mon Sep 17 00:00:00 2001
From: Sergei Trofimovich <slyfox@gentoo.org>
Date: Fri, 12 Mar 2021 21:08:27 -0800
Subject: [PATCH 0785/1820] ia64: fix ptrace(PTRACE_SYSCALL_INFO_EXIT) sign

In https://bugs.gentoo.org/769614 Dmitry noticed that
`ptrace(PTRACE_GET_SYSCALL_INFO)` does not return error sign properly.

The bug is in mismatch between get/set errors:

static inline long syscall_get_error(struct task_struct *task,
                                     struct pt_regs *regs)
{
        return regs->r10 == -1 ? regs->r8:0;
}

static inline long syscall_get_return_value(struct task_struct *task,
                                            struct pt_regs *regs)
{
        return regs->r8;
}

static inline void syscall_set_return_value(struct task_struct *task,
                                            struct pt_regs *regs,
                                            int error, long val)
{
        if (error) {
                /* error < 0, but ia64 uses > 0 return value */
                regs->r8 = -error;
                regs->r10 = -1;
        } else {
                regs->r8 = val;
                regs->r10 = 0;
        }
}

Tested on v5.10 on rx3600 machine (ia64 9040 CPU).

Link: https://lkml.kernel.org/r/20210221002554.333076-2-slyfox@gentoo.org
Link: https://bugs.gentoo.org/769614
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Reported-by: Dmitry V. Levin <ldv@altlinux.org>
Reviewed-by: Dmitry V. Levin <ldv@altlinux.org>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/include/asm/syscall.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h
index 6c6f16e409a8..0d23c0049301 100644
--- a/arch/ia64/include/asm/syscall.h
+++ b/arch/ia64/include/asm/syscall.h
@@ -32,7 +32,7 @@ static inline void syscall_rollback(struct task_struct *task,
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
-	return regs->r10 == -1 ? regs->r8:0;
+	return regs->r10 == -1 ? -regs->r8:0;
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,

From be6c8982e4ab9a41907555f601b711a7e2a17d4c Mon Sep 17 00:00:00 2001
From: Zhou Guanghui <zhouguanghui1@huawei.com>
Date: Fri, 12 Mar 2021 21:08:30 -0800
Subject: [PATCH 0786/1820] mm/memcg: rename mem_cgroup_split_huge_fixup to
 split_page_memcg and add nr_pages argument

Rename mem_cgroup_split_huge_fixup to split_page_memcg and explicitly pass
in page number argument.

In this way, the interface name is more common and can be used by
potential users.  In addition, the complete info(memcg and flag) of the
memcg needs to be set to the tail pages.

Link: https://lkml.kernel.org/r/20210304074053.65527-2-zhouguanghui1@huawei.com
Signed-off-by: Zhou Guanghui <zhouguanghui1@huawei.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Tianhong Ding <dingtianhong@huawei.com>
Cc: Weilong Chen <chenweilong@huawei.com>
Cc: Rui Xiang <rui.xiang@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  6 ++----
 mm/huge_memory.c           |  2 +-
 mm/memcontrol.c            | 15 ++++++---------
 3 files changed, 9 insertions(+), 14 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e6dc793d587d..0c04d39a7967 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1061,9 +1061,7 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 	rcu_read_unlock();
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-void mem_cgroup_split_huge_fixup(struct page *head);
-#endif
+void split_page_memcg(struct page *head, unsigned int nr);
 
 #else /* CONFIG_MEMCG */
 
@@ -1400,7 +1398,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 	return 0;
 }
 
-static inline void mem_cgroup_split_huge_fixup(struct page *head)
+static inline void split_page_memcg(struct page *head, unsigned int nr)
 {
 }
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index da1d63a41aec..ae907a9c2050 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2467,7 +2467,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	int i;
 
 	/* complete memcg works before add pages to LRU */
-	mem_cgroup_split_huge_fixup(head);
+	split_page_memcg(head, nr);
 
 	if (PageAnon(head) && PageSwapCache(head)) {
 		swp_entry_t entry = { .val = page_private(head) };
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 845eec01ef9d..e064ac0d850a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3287,24 +3287,21 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
 
 #endif /* CONFIG_MEMCG_KMEM */
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
- * Because page_memcg(head) is not set on compound tails, set it now.
+ * Because page_memcg(head) is not set on tails, set it now.
  */
-void mem_cgroup_split_huge_fixup(struct page *head)
+void split_page_memcg(struct page *head, unsigned int nr)
 {
 	struct mem_cgroup *memcg = page_memcg(head);
 	int i;
 
-	if (mem_cgroup_disabled())
+	if (mem_cgroup_disabled() || !memcg)
 		return;
 
-	for (i = 1; i < HPAGE_PMD_NR; i++) {
-		css_get(&memcg->css);
-		head[i].memcg_data = (unsigned long)memcg;
-	}
+	for (i = 1; i < nr; i++)
+		head[i].memcg_data = head->memcg_data;
+	css_get_many(&memcg->css, nr - 1);
 }
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #ifdef CONFIG_MEMCG_SWAP
 /**

From e1baddf8475b06cc56f4bafecf9a32a124343d9f Mon Sep 17 00:00:00 2001
From: Zhou Guanghui <zhouguanghui1@huawei.com>
Date: Fri, 12 Mar 2021 21:08:33 -0800
Subject: [PATCH 0787/1820] mm/memcg: set memcg when splitting page

As described in the split_page() comment, for the non-compound high order
page, the sub-pages must be freed individually.  If the memcg of the first
page is valid, the tail pages cannot be uncharged when be freed.

For example, when alloc_pages_exact is used to allocate 1MB continuous
physical memory, 2MB is charged(kmemcg is enabled and __GFP_ACCOUNT is
set).  When make_alloc_exact free the unused 1MB and free_pages_exact free
the applied 1MB, actually, only 4KB(one page) is uncharged.

Therefore, the memcg of the tail page needs to be set when splitting a
page.

Michel:

There are at least two explicit users of __GFP_ACCOUNT with
alloc_exact_pages added recently.  See 7efe8ef274024 ("KVM: arm64:
Allocate stage-2 pgd pages with GFP_KERNEL_ACCOUNT") and c419621873713
("KVM: s390: Add memcg accounting to KVM allocations"), so this is not
just a theoretical issue.

Link: https://lkml.kernel.org/r/20210304074053.65527-3-zhouguanghui1@huawei.com
Signed-off-by: Zhou Guanghui <zhouguanghui1@huawei.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Rui Xiang <rui.xiang@huawei.com>
Cc: Tianhong Ding <dingtianhong@huawei.com>
Cc: Weilong Chen <chenweilong@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3cd1c0ce4d06..cfc72873961d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3314,6 +3314,7 @@ void split_page(struct page *page, unsigned int order)
 	for (i = 1; i < (1 << order); i++)
 		set_page_refcounted(page + i);
 	split_page_owner(page, 1 << order);
+	split_page_memcg(page, 1 << order);
 }
 EXPORT_SYMBOL_GPL(split_page);
 

From 57e0076e6575a7b7cef620a0bd2ee2549ef77818 Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Fri, 12 Mar 2021 21:08:38 -0800
Subject: [PATCH 0788/1820] zram: fix return value on writeback_store

writeback_store's return value is overwritten by submit_bio_wait's return
value.  Thus, writeback_store will return zero since there was no IO
error.  In the end, write syscall from userspace will see the zero as
return value, which could make the process stall to keep trying the write
until it will succeed.

Link: https://lkml.kernel.org/r/20210312173949.2197662-1-minchan@kernel.org
Fixes: 3b82a051c101("drivers/block/zram/zram_drv.c: fix error return codes not being returned in writeback_store")
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Colin Ian King <colin.king@canonical.com>
Cc: John Dias <joaodias@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/block/zram/zram_drv.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index a711a2e2a794..63bbefdffc81 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -627,7 +627,7 @@ static ssize_t writeback_store(struct device *dev,
 	struct bio_vec bio_vec;
 	struct page *page;
 	ssize_t ret = len;
-	int mode;
+	int mode, err;
 	unsigned long blk_idx = 0;
 
 	if (sysfs_streq(buf, "idle"))
@@ -728,12 +728,17 @@ static ssize_t writeback_store(struct device *dev,
 		 * XXX: A single page IO would be inefficient for write
 		 * but it would be not bad as starter.
 		 */
-		ret = submit_bio_wait(&bio);
-		if (ret) {
+		err = submit_bio_wait(&bio);
+		if (err) {
 			zram_slot_lock(zram, index);
 			zram_clear_flag(zram, index, ZRAM_UNDER_WB);
 			zram_clear_flag(zram, index, ZRAM_IDLE);
 			zram_slot_unlock(zram, index);
+			/*
+			 * Return last IO error unless every IO were
+			 * not suceeded.
+			 */
+			ret = err;
 			continue;
 		}
 

From 2766f1821600cc7562bae2128ad0b163f744c5d9 Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Fri, 12 Mar 2021 21:08:41 -0800
Subject: [PATCH 0789/1820] zram: fix broken page writeback

commit 0d8359620d9b ("zram: support page writeback") introduced two
problems.  It overwrites writeback_store's return value as kstrtol's
return value, which makes return value zero so user could see zero as
return value of write syscall even though it wrote data successfully.

It also breaks index value in the loop in that it doesn't increase the
index any longer.  It means it can write only first starting block index
so user couldn't write all idle pages in the zram so lose memory saving
chance.

This patch fixes those issues.

Link: https://lkml.kernel.org/r/20210312173949.2197662-2-minchan@kernel.org
Fixes: 0d8359620d9b("zram: support page writeback")
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reported-by: Amos Bianchi <amosbianchi@google.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: John Dias <joaodias@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/block/zram/zram_drv.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 63bbefdffc81..cf8deecc39ef 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -638,8 +638,8 @@ static ssize_t writeback_store(struct device *dev,
 		if (strncmp(buf, PAGE_WB_SIG, sizeof(PAGE_WB_SIG) - 1))
 			return -EINVAL;
 
-		ret = kstrtol(buf + sizeof(PAGE_WB_SIG) - 1, 10, &index);
-		if (ret || index >= nr_pages)
+		if (kstrtol(buf + sizeof(PAGE_WB_SIG) - 1, 10, &index) ||
+				index >= nr_pages)
 			return -EINVAL;
 
 		nr_pages = 1;
@@ -663,7 +663,7 @@ static ssize_t writeback_store(struct device *dev,
 		goto release_init_lock;
 	}
 
-	while (nr_pages--) {
+	for (; nr_pages != 0; index++, nr_pages--) {
 		struct bio_vec bvec;
 
 		bvec.bv_page = page;

From c9b86db274d229a1ab47a4e8e11fa9775fd21cbb Mon Sep 17 00:00:00 2001
From: Taniya Das <tdas@codeaurora.org>
Date: Wed, 10 Mar 2021 23:48:03 +0530
Subject: [PATCH 0790/1820] clk: qcom: rpmh: Update the XO clock source for
 SC7280

The bi_tcxo clock source for SC7280 requires a div 4 to derive 19.2MHz
from the xo_board. Thus update the same.

Fixes: fff2b9a65162 ("clk: qcom: rpmh: Add support for RPMH clocks on SC7280")
Signed-off-by: Taniya Das <tdas@codeaurora.org>
Link: https://lore.kernel.org/r/1615400283-20100-1-git-send-email-tdas@codeaurora.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/clk-rpmh.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c
index 91dc390a583b..c623ce900406 100644
--- a/drivers/clk/qcom/clk-rpmh.c
+++ b/drivers/clk/qcom/clk-rpmh.c
@@ -510,9 +510,12 @@ static const struct clk_rpmh_desc clk_rpmh_sm8350 = {
 	.num_clks = ARRAY_SIZE(sm8350_rpmh_clocks),
 };
 
+/* Resource name must match resource id present in cmd-db */
+DEFINE_CLK_RPMH_ARC(sc7280, bi_tcxo, bi_tcxo_ao, "xo.lvl", 0x3, 4);
+
 static struct clk_hw *sc7280_rpmh_clocks[] = {
-	[RPMH_CXO_CLK]      = &sdm845_bi_tcxo.hw,
-	[RPMH_CXO_CLK_A]    = &sdm845_bi_tcxo_ao.hw,
+	[RPMH_CXO_CLK]      = &sc7280_bi_tcxo.hw,
+	[RPMH_CXO_CLK_A]    = &sc7280_bi_tcxo_ao.hw,
 	[RPMH_LN_BB_CLK2]   = &sdm845_ln_bb_clk2.hw,
 	[RPMH_LN_BB_CLK2_A] = &sdm845_ln_bb_clk2_ao.hw,
 	[RPMH_RF_CLK1]      = &sdm845_rf_clk1.hw,

From 0ae67123eafd056cc0e27ab27b0d3c5e4bdaf916 Mon Sep 17 00:00:00 2001
From: Marijn Suijten <marijn.suijten@somainline.org>
Date: Wed, 3 Mar 2021 00:41:06 +0100
Subject: [PATCH 0791/1820] clk: qcom: rcg2: Rectify clk_gfx3d rate rounding
 without mux division

In case the mux is not divided parent_req was mistakenly not assigned to
leading __clk_determine_rate to determine the best frequency setting for
a requested rate of 0, resulting in the msm8996 platform not booting.
Rectify this by refactoring the logic to unconditionally assign to
parent_req.rate with the clock rate the caller is expecting.

Fixes: 7cbb78a99db6 ("clk: qcom: rcg2: Stop hardcoding gfx3d pingpong parent numbers")
Reported-by: Konrad Dybcio <konrad.dybcio@somainline.org>
Tested-by: Konrad Dybcio <konrad.dybcio@somainline.org>
Reviewed-By: AngeloGioacchino Del Regno <angelogioacchino.delregno@somainline.org>
Signed-off-by: Marijn Suijten <marijn.suijten@somainline.org>
Link: https://lore.kernel.org/r/20210302234106.3418665-1-marijn.suijten@somainline.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/clk-rcg2.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index 42f13a2d1cc1..05ff3b0d233e 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -730,7 +730,8 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw,
 	struct clk_rate_request parent_req = { };
 	struct clk_rcg2_gfx3d *cgfx = to_clk_rcg2_gfx3d(hw);
 	struct clk_hw *xo, *p0, *p1, *p2;
-	unsigned long request, p0_rate;
+	unsigned long p0_rate;
+	u8 mux_div = cgfx->div;
 	int ret;
 
 	p0 = cgfx->hws[0];
@@ -750,14 +751,15 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw,
 		return 0;
 	}
 
-	request = req->rate;
-	if (cgfx->div > 1)
-		parent_req.rate = request = request * cgfx->div;
+	if (mux_div == 0)
+		mux_div = 1;
+
+	parent_req.rate = req->rate * mux_div;
 
 	/* This has to be a fixed rate PLL */
 	p0_rate = clk_hw_get_rate(p0);
 
-	if (request == p0_rate) {
+	if (parent_req.rate == p0_rate) {
 		req->rate = req->best_parent_rate = p0_rate;
 		req->best_parent_hw = p0;
 		return 0;
@@ -765,7 +767,7 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw,
 
 	if (req->best_parent_hw == p0) {
 		/* Are we going back to a previously used rate? */
-		if (clk_hw_get_rate(p2) == request)
+		if (clk_hw_get_rate(p2) == parent_req.rate)
 			req->best_parent_hw = p2;
 		else
 			req->best_parent_hw = p1;
@@ -780,8 +782,7 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw,
 		return ret;
 
 	req->rate = req->best_parent_rate = parent_req.rate;
-	if (cgfx->div > 1)
-		req->rate /= cgfx->div;
+	req->rate /= mux_div;
 
 	return 0;
 }

From 148ddaa89d4a0a927c4353398096cc33687755c1 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Wed, 24 Feb 2021 09:50:25 -0800
Subject: [PATCH 0792/1820] clk: qcom: gcc-sc7180: Use floor ops for the
 correct sdcc1 clk

While picking commit a8cd989e1a57 ("mmc: sdhci-msm: Warn about
overclocking SD/MMC") back to my tree I was surprised that it was
reporting warnings.  I thought I fixed those!  Looking closer at the
fix, I see that I totally bungled it (or at least I halfway bungled
it).  The SD card clock got fixed (and that was the one I was really
focused on fixing), but I totally adjusted the wrong clock for eMMC.
Sigh.  Let's fix my dumb mistake.

Now both SD and eMMC have floor for the "apps" clock.

This doesn't matter a lot for the final clock rate for HS400 eMMC but
could matter if someone happens to put some slower eMMC on a sc7180.
We also transition through some of these lower rates sometimes and
having them wrong could cause problems during these transitions.
These were the messages I was seeing at boot:
  mmc1: Card appears overclocked; req 52000000 Hz, actual 100000000 Hz
  mmc1: Card appears overclocked; req 52000000 Hz, actual 100000000 Hz
  mmc1: Card appears overclocked; req 104000000 Hz, actual 192000000 Hz

Fixes: 6d37a8d19283 ("clk: qcom: gcc-sc7180: Use floor ops for sdcc clks")
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20210224095013.1.I2e2ba4978cfca06520dfb5d757768f9c42140f7c@changeid
Reviewed-by: Taniya Das <tdas@codeaurora.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/gcc-sc7180.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/qcom/gcc-sc7180.c b/drivers/clk/qcom/gcc-sc7180.c
index 88e896abb663..da8b627ca156 100644
--- a/drivers/clk/qcom/gcc-sc7180.c
+++ b/drivers/clk/qcom/gcc-sc7180.c
@@ -620,7 +620,7 @@ static struct clk_rcg2 gcc_sdcc1_apps_clk_src = {
 		.name = "gcc_sdcc1_apps_clk_src",
 		.parent_data = gcc_parent_data_1,
 		.num_parents = 5,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_floor_ops,
 	},
 };
 
@@ -642,7 +642,7 @@ static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = {
 		.name = "gcc_sdcc1_ice_core_clk_src",
 		.parent_data = gcc_parent_data_0,
 		.num_parents = 4,
-		.ops = &clk_rcg2_floor_ops,
+		.ops = &clk_rcg2_ops,
 	},
 };
 

From 3a9ef3e11c5d33e5cb355b4aad1a4caad2407541 Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@linaro.org>
Date: Fri, 12 Mar 2021 09:12:48 -0600
Subject: [PATCH 0793/1820] net: ipa: terminate message handler arrays

When a QMI handle is initialized, an array of message handler
structures is provided, defining how any received message should
be handled based on its type and message ID.  The QMI core code
traverses this array when a message arrives and calls the function
associated with the (type, msg_id) found in the array.

The array is supposed to be terminated with an empty (all zero)
entry though.  Without it, an unsupported message will cause
the QMI core code to go past the end of the array.

Fix this bug, by properly terminating the message handler arrays
provided when QMI handles are set up by the IPA driver.

Fixes: 530f9216a9537 ("soc: qcom: ipa: AP/modem communications")
Reported-by: Sujit Kautkar <sujitka@chromium.org>
Signed-off-by: Alex Elder <elder@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipa/ipa_qmi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c
index 2fc64483f275..e594bf3b600f 100644
--- a/drivers/net/ipa/ipa_qmi.c
+++ b/drivers/net/ipa/ipa_qmi.c
@@ -249,6 +249,7 @@ static const struct qmi_msg_handler ipa_server_msg_handlers[] = {
 		.decoded_size	= IPA_QMI_DRIVER_INIT_COMPLETE_REQ_SZ,
 		.fn		= ipa_server_driver_init_complete,
 	},
+	{ },
 };
 
 /* Handle an INIT_DRIVER response message from the modem. */
@@ -269,6 +270,7 @@ static const struct qmi_msg_handler ipa_client_msg_handlers[] = {
 		.decoded_size	= IPA_QMI_INIT_DRIVER_RSP_SZ,
 		.fn		= ipa_client_init_driver,
 	},
+	{ },
 };
 
 /* Return a pointer to an init modem driver request structure, which contains

From ad236ccde19a93309cba25fb8c9e789b9c69397c Mon Sep 17 00:00:00 2001
From: Eva Dengler <eva.dengler@fau.de>
Date: Sat, 13 Mar 2021 01:04:13 +0100
Subject: [PATCH 0794/1820] devlink: fix typo in documentation

This commit fixes three spelling typos in devlink-dpipe.rst and
devlink-port.rst.

Signed-off-by: Eva Dengler <eva.dengler@fau.de>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/devlink/devlink-dpipe.rst | 2 +-
 Documentation/networking/devlink/devlink-port.rst  | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/networking/devlink/devlink-dpipe.rst b/Documentation/networking/devlink/devlink-dpipe.rst
index 468fe1001b74..af37f250df43 100644
--- a/Documentation/networking/devlink/devlink-dpipe.rst
+++ b/Documentation/networking/devlink/devlink-dpipe.rst
@@ -52,7 +52,7 @@ purposes as a standard complementary tool. The system's view from
 ``devlink-dpipe`` should change according to the changes done by the
 standard configuration tools.
 
-For example, it’s quiet common to  implement Access Control Lists (ACL)
+For example, it’s quite common to  implement Access Control Lists (ACL)
 using Ternary Content Addressable Memory (TCAM). The TCAM memory can be
 divided into TCAM regions. Complex TC filters can have multiple rules with
 different priorities and different lookup keys. On the other hand hardware
diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst
index e99b41599465..ab790e7980b8 100644
--- a/Documentation/networking/devlink/devlink-port.rst
+++ b/Documentation/networking/devlink/devlink-port.rst
@@ -151,7 +151,7 @@ representor netdevice.
 -------------
 A subfunction devlink port is created but it is not active yet. That means the
 entities are created on devlink side, the e-switch port representor is created,
-but the subfunction device itself it not created. A user might use e-switch port
+but the subfunction device itself is not created. A user might use e-switch port
 representor to do settings, putting it into bridge, adding TC rules, etc. A user
 might as well configure the hardware address (such as MAC address) of the
 subfunction while subfunction is inactive.
@@ -173,7 +173,7 @@ Terms and Definitions
    * - Term
      - Definitions
    * - ``PCI device``
-     - A physical PCI device having one or more PCI bus consists of one or
+     - A physical PCI device having one or more PCI buses consists of one or
        more PCI controllers.
    * - ``PCI controller``
      -  A controller consists of potentially multiple physical functions,

From e1c86210fe27428399643861b81b080eccd79f87 Mon Sep 17 00:00:00 2001
From: Xiaoliang Yu <yxl_22@outlook.com>
Date: Sat, 13 Mar 2021 07:54:53 +0800
Subject: [PATCH 0795/1820] ALSA: hda/realtek: Apply headset-mic quirks for
 Xiaomi Redmibook Air

There is another fix for headset-mic problem on Redmibook (1d72:1602),
it also works on Redmibook Air (1d72:1947), which has the same issue.

Signed-off-by: Xiaoliang Yu <yxl_22@outlook.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/TYBP286MB02856DC016849DEA0F9B6A37EE6F9@TYBP286MB0285.JPNP286.PROD.OUTLOOK.COM
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b47504fa8dfd..c6d916177d5c 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -8243,6 +8243,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */
 	SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802),
 	SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X),

From da98b54d02981de5b07d8044b2a632bf6ba3ac45 Mon Sep 17 00:00:00 2001
From: Tang Bin <tangbin@cmss.chinamobile.com>
Date: Mon, 22 Feb 2021 13:57:24 +0800
Subject: [PATCH 0796/1820] virtio-mmio: Use to_virtio_mmio_device() to simply
 code

The file virtio_mmio.c has defined the function to_virtio_mmio_device,
so use it instead of container_of() to simply code.

Signed-off-by: Tang Bin <tangbin@cmss.chinamobile.com>
Link: https://lore.kernel.org/r/20210222055724.220-1-tangbin@cmss.chinamobile.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_mmio.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index a286d22b6551..56128b9c46eb 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -548,8 +548,7 @@ static void virtio_mmio_release_dev(struct device *_d)
 {
 	struct virtio_device *vdev =
 			container_of(_d, struct virtio_device, dev);
-	struct virtio_mmio_device *vm_dev =
-			container_of(vdev, struct virtio_mmio_device, vdev);
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 	struct platform_device *pdev = vm_dev->pdev;
 
 	devm_kfree(&pdev->dev, vm_dev);

From bc22ed2ea1121f9d9ba3f85c524cb857d54a2d00 Mon Sep 17 00:00:00 2001
From: Xianting Tian <xianting_tian@126.com>
Date: Sat, 20 Feb 2021 11:28:18 -0500
Subject: [PATCH 0797/1820] virtio: remove export for virtio_config_{enable,
 disable}

virtio_config_enable(), virtio_config_disable() are only used inside
drivers/virtio/virtio.c, so it doesn't need export the symbols.

Signed-off-by: Xianting Tian <xianting_tian@126.com>
Link: https://lore.kernel.org/r/1613838498-8791-1-git-send-email-xianting_tian@126.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
---
 drivers/virtio/virtio.c | 6 ++----
 include/linux/virtio.h  | 2 --
 2 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 42e09cc1b8ac..4b15c00c0a0a 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -141,15 +141,14 @@ void virtio_config_changed(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(virtio_config_changed);
 
-void virtio_config_disable(struct virtio_device *dev)
+static void virtio_config_disable(struct virtio_device *dev)
 {
 	spin_lock_irq(&dev->config_lock);
 	dev->config_enabled = false;
 	spin_unlock_irq(&dev->config_lock);
 }
-EXPORT_SYMBOL_GPL(virtio_config_disable);
 
-void virtio_config_enable(struct virtio_device *dev)
+static void virtio_config_enable(struct virtio_device *dev)
 {
 	spin_lock_irq(&dev->config_lock);
 	dev->config_enabled = true;
@@ -158,7 +157,6 @@ void virtio_config_enable(struct virtio_device *dev)
 	dev->config_change_pending = false;
 	spin_unlock_irq(&dev->config_lock);
 }
-EXPORT_SYMBOL_GPL(virtio_config_enable);
 
 void virtio_add_status(struct virtio_device *dev, unsigned int status)
 {
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 55ea329fe72a..b1894e0323fa 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -132,8 +132,6 @@ bool is_virtio_device(struct device *dev);
 void virtio_break_device(struct virtio_device *dev);
 
 void virtio_config_changed(struct virtio_device *dev);
-void virtio_config_disable(struct virtio_device *dev);
-void virtio_config_enable(struct virtio_device *dev);
 int virtio_finalize_features(struct virtio_device *dev);
 #ifdef CONFIG_PM_SLEEP
 int virtio_device_freeze(struct virtio_device *dev);

From aa443ac20445ad79afc9aa589727e5d9ee88dc2f Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Sat, 13 Feb 2021 20:39:51 +0200
Subject: [PATCH 0798/1820] vdpa_sim: Skip typecasting from void*

Typecasting from void* to virtio_net_config* is not needed.
Remove it.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Link: https://lore.kernel.org/r/20210213183951.248324-1-parav@nvidia.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
index 702be74877d2..a1ab6163f7d1 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
@@ -110,8 +110,7 @@ out:
 
 static void vdpasim_net_get_config(struct vdpasim *vdpasim, void *config)
 {
-	struct virtio_net_config *net_config =
-		(struct virtio_net_config *)config;
+	struct virtio_net_config *net_config = config;
 
 	net_config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
 	net_config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP);

From 4c050286bb202cffd5467c1cba982dff391d62e1 Mon Sep 17 00:00:00 2001
From: Gautam Dawar <gdawar.xilinx@gmail.com>
Date: Wed, 24 Feb 2021 17:18:45 +0530
Subject: [PATCH 0799/1820] vhost_vdpa: fix the missing
 irq_bypass_unregister_producer() invocation

When qemu with vhost-vdpa netdevice is run for the first time,
it works well. But after the VM is powered off, the next qemu run
causes kernel panic due to a NULL pointer dereference in
irq_bypass_register_producer().

When the VM is powered off, vhost_vdpa_clean_irq() misses on calling
irq_bypass_unregister_producer() for irq 0 because of the existing check.

This leaves stale producer nodes, which are reset in
vhost_vring_call_reset() when vhost_dev_init() is invoked during the
second qemu run.

As the node member of struct irq_bypass_producer is also initialized
to zero, traversal on the producers list causes crash due to NULL
pointer dereference.

Fixes: 2cf1ba9a4d15c ("vhost_vdpa: implement IRQ offloading in vhost_vdpa")
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=211711
Signed-off-by: Gautam Dawar <gdawar.xilinx@gmail.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20210224114845.104173-1-gdawar.xilinx@gmail.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vdpa.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index ef688c8c0e0e..dfdd8e4a8b08 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -900,14 +900,10 @@ err:
 
 static void vhost_vdpa_clean_irq(struct vhost_vdpa *v)
 {
-	struct vhost_virtqueue *vq;
 	int i;
 
-	for (i = 0; i < v->nvqs; i++) {
-		vq = &v->vqs[i];
-		if (vq->call_ctx.producer.irq)
-			irq_bypass_unregister_producer(&vq->call_ctx.producer);
-	}
+	for (i = 0; i < v->nvqs; i++)
+		vhost_vdpa_unsetup_vq_irq(v, i);
 }
 
 static int vhost_vdpa_release(struct inode *inode, struct file *filep)

From 08c18b63d9656e0389087d1956d2b37fd7019172 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Tue, 9 Mar 2021 06:19:30 +0000
Subject: [PATCH 0800/1820] powerpc/vdso32: Add missing _restgpr_31_x to fix
 build failure

With some defconfig including CONFIG_CC_OPTIMIZE_FOR_SIZE,
(for instance mvme5100_defconfig and ps3_defconfig), gcc 5
generates a call to _restgpr_31_x.

Until recently it went unnoticed, but
commit 42ed6d56ade2 ("powerpc/vdso: Block R_PPC_REL24 relocations")
made it rise to the surface.

Provide that function (copied from lib/crtsavres.S) in
gettimeofday.S

Fixes: ab037dd87a2f ("powerpc/vdso: Switch VDSO to generic C implementation.")
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/a7aa198a88bcd33c6e35e99f70f86c7b7f2f9440.1615270757.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/kernel/vdso32/gettimeofday.S | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index a6e29f880e0e..d21d08140a5e 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -65,3 +65,14 @@ V_FUNCTION_END(__kernel_clock_getres)
 V_FUNCTION_BEGIN(__kernel_time)
 	cvdso_call_time __c_kernel_time
 V_FUNCTION_END(__kernel_time)
+
+/* Routines for restoring integer registers, called by the compiler.  */
+/* Called with r11 pointing to the stack header word of the caller of the */
+/* function, just beyond the end of the integer restore area.  */
+_GLOBAL(_restgpr_31_x)
+_GLOBAL(_rest32gpr_31_x)
+	lwz	r0,4(r11)
+	lwz	r31,-4(r11)
+	mtlr	r0
+	mr	r1,r11
+	blr

From eed5fae00593ab9d261a0c1ffc1bdb786a87a55a Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Wed, 10 Mar 2021 12:10:34 +0000
Subject: [PATCH 0801/1820] powerpc: Force inlining of cpu_has_feature() to
 avoid build failure

The code relies on constant folding of cpu_has_feature() based
on possible and always true values as defined per
CPU_FTRS_ALWAYS and CPU_FTRS_POSSIBLE.

Build failure is encountered with for instance
book3e_all_defconfig on kisskb in the AMDGPU driver which uses
cpu_has_feature(CPU_FTR_VSX_COMP) to decide whether calling
kernel_enable_vsx() or not.

The failure is due to cpu_has_feature() not being inlined with
that configuration with gcc 4.9.

In the same way as commit acdad8fb4a15 ("powerpc: Force inlining of
mmu_has_feature to fix build failure"), for inlining of
cpu_has_feature().

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/b231dfa040ce4cc37f702f5c3a595fdeabfe0462.1615378209.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/include/asm/cpu_has_feature.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h
index 7897d16e0990..727d4b321937 100644
--- a/arch/powerpc/include/asm/cpu_has_feature.h
+++ b/arch/powerpc/include/asm/cpu_has_feature.h
@@ -7,7 +7,7 @@
 #include <linux/bug.h>
 #include <asm/cputable.h>
 
-static inline bool early_cpu_has_feature(unsigned long feature)
+static __always_inline bool early_cpu_has_feature(unsigned long feature)
 {
 	return !!((CPU_FTRS_ALWAYS & feature) ||
 		  (CPU_FTRS_POSSIBLE & cur_cpu_spec->cpu_features & feature));
@@ -46,7 +46,7 @@ static __always_inline bool cpu_has_feature(unsigned long feature)
 	return static_branch_likely(&cpu_feature_keys[i]);
 }
 #else
-static inline bool cpu_has_feature(unsigned long feature)
+static __always_inline bool cpu_has_feature(unsigned long feature)
 {
 	return early_cpu_has_feature(feature);
 }

From 9e15c3a0ced5a61f320b989072c24983cb1620c1 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 13 Mar 2021 12:29:43 -0700
Subject: [PATCH 0802/1820] io_uring: convert io_buffer_idr to XArray

Like we did for the personality idr, convert the IO buffer idr to use
XArray. This avoids a use-after-free on removal of entries, since idr
doesn't like doing so from inside an iterator, and it nicely reduces
the amount of code we need to support this feature.

Fixes: 5a2e745d4d43 ("io_uring: buffer registration infrastructure")
Cc: stable@vger.kernel.org
Cc: Matthew Wilcox <willy@infradead.org>
Cc: yangerkun <yangerkun@huawei.com>
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 43 +++++++++++++++----------------------------
 1 file changed, 15 insertions(+), 28 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 05adc4887ef3..58d62dd9f8e4 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -402,7 +402,7 @@ struct io_ring_ctx {
 	struct socket		*ring_sock;
 #endif
 
-	struct idr		io_buffer_idr;
+	struct xarray		io_buffers;
 
 	struct xarray		personalities;
 	u32			pers_next;
@@ -1135,7 +1135,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	init_waitqueue_head(&ctx->cq_wait);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
 	init_completion(&ctx->ref_comp);
-	idr_init(&ctx->io_buffer_idr);
+	xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1);
 	xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
 	mutex_init(&ctx->uring_lock);
 	init_waitqueue_head(&ctx->wait);
@@ -2843,7 +2843,7 @@ static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
 
 	lockdep_assert_held(&req->ctx->uring_lock);
 
-	head = idr_find(&req->ctx->io_buffer_idr, bgid);
+	head = xa_load(&req->ctx->io_buffers, bgid);
 	if (head) {
 		if (!list_empty(&head->list)) {
 			kbuf = list_last_entry(&head->list, struct io_buffer,
@@ -2851,7 +2851,7 @@ static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
 			list_del(&kbuf->list);
 		} else {
 			kbuf = head;
-			idr_remove(&req->ctx->io_buffer_idr, bgid);
+			xa_erase(&req->ctx->io_buffers, bgid);
 		}
 		if (*len > kbuf->len)
 			*len = kbuf->len;
@@ -3892,7 +3892,7 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf,
 	}
 	i++;
 	kfree(buf);
-	idr_remove(&ctx->io_buffer_idr, bgid);
+	xa_erase(&ctx->io_buffers, bgid);
 
 	return i;
 }
@@ -3910,7 +3910,7 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
 	lockdep_assert_held(&ctx->uring_lock);
 
 	ret = -ENOENT;
-	head = idr_find(&ctx->io_buffer_idr, p->bgid);
+	head = xa_load(&ctx->io_buffers, p->bgid);
 	if (head)
 		ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs);
 	if (ret < 0)
@@ -3993,21 +3993,14 @@ static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
 
 	lockdep_assert_held(&ctx->uring_lock);
 
-	list = head = idr_find(&ctx->io_buffer_idr, p->bgid);
+	list = head = xa_load(&ctx->io_buffers, p->bgid);
 
 	ret = io_add_buffers(p, &head);
-	if (ret < 0)
-		goto out;
-
-	if (!list) {
-		ret = idr_alloc(&ctx->io_buffer_idr, head, p->bgid, p->bgid + 1,
-					GFP_KERNEL);
-		if (ret < 0) {
+	if (ret >= 0 && !list) {
+		ret = xa_insert(&ctx->io_buffers, p->bgid, head, GFP_KERNEL);
+		if (ret < 0)
 			__io_remove_buffers(ctx, head, p->bgid, -1U);
-			goto out;
-		}
 	}
-out:
 	if (ret < 0)
 		req_set_fail_links(req);
 
@@ -8333,19 +8326,13 @@ static int io_eventfd_unregister(struct io_ring_ctx *ctx)
 	return -ENXIO;
 }
 
-static int __io_destroy_buffers(int id, void *p, void *data)
-{
-	struct io_ring_ctx *ctx = data;
-	struct io_buffer *buf = p;
-
-	__io_remove_buffers(ctx, buf, id, -1U);
-	return 0;
-}
-
 static void io_destroy_buffers(struct io_ring_ctx *ctx)
 {
-	idr_for_each(&ctx->io_buffer_idr, __io_destroy_buffers, ctx);
-	idr_destroy(&ctx->io_buffer_idr);
+	struct io_buffer *buf;
+	unsigned long index;
+
+	xa_for_each(&ctx->io_buffers, index, buf)
+		__io_remove_buffers(ctx, buf, index, -1U);
 }
 
 static void io_req_cache_free(struct list_head *list, struct task_struct *tsk)

From 6577b9a551aedb86bca6d4438c28386361845108 Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Sun, 14 Mar 2021 14:08:36 -0400
Subject: [PATCH 0803/1820] net: arcnet: com20020 fix error handling

There are two issues when handling error case in com20020pci_probe()

1. priv might be not initialized yet when calling com20020pci_remove()
from com20020pci_probe(), since the priv is set at the very last but it
can jump to error handling in the middle and priv remains NULL.
2. memory leak - the net device is allocated in alloc_arcdev but not
properly released if error happens in the middle of the big for loop

[    1.529110] BUG: kernel NULL pointer dereference, address: 0000000000000008
[    1.531447] RIP: 0010:com20020pci_remove+0x15/0x60 [com20020_pci]
[    1.536805] Call Trace:
[    1.536939]  com20020pci_probe+0x3f2/0x48c [com20020_pci]
[    1.537226]  local_pci_probe+0x48/0x80
[    1.539918]  com20020pci_init+0x3f/0x1000 [com20020_pci]

Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/arcnet/com20020-pci.c | 34 +++++++++++++++++--------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c
index 8bdc44b7e09a..3c8f665c1558 100644
--- a/drivers/net/arcnet/com20020-pci.c
+++ b/drivers/net/arcnet/com20020-pci.c
@@ -127,6 +127,8 @@ static int com20020pci_probe(struct pci_dev *pdev,
 	int i, ioaddr, ret;
 	struct resource *r;
 
+	ret = 0;
+
 	if (pci_enable_device(pdev))
 		return -EIO;
 
@@ -139,6 +141,8 @@ static int com20020pci_probe(struct pci_dev *pdev,
 	priv->ci = ci;
 	mm = &ci->misc_map;
 
+	pci_set_drvdata(pdev, priv);
+
 	INIT_LIST_HEAD(&priv->list_dev);
 
 	if (mm->size) {
@@ -161,7 +165,7 @@ static int com20020pci_probe(struct pci_dev *pdev,
 		dev = alloc_arcdev(device);
 		if (!dev) {
 			ret = -ENOMEM;
-			goto out_port;
+			break;
 		}
 		dev->dev_port = i;
 
@@ -178,7 +182,7 @@ static int com20020pci_probe(struct pci_dev *pdev,
 			pr_err("IO region %xh-%xh already allocated\n",
 			       ioaddr, ioaddr + cm->size - 1);
 			ret = -EBUSY;
-			goto out_port;
+			goto err_free_arcdev;
 		}
 
 		/* Dummy access after Reset
@@ -216,18 +220,18 @@ static int com20020pci_probe(struct pci_dev *pdev,
 		if (arcnet_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) {
 			pr_err("IO address %Xh is empty!\n", ioaddr);
 			ret = -EIO;
-			goto out_port;
+			goto err_free_arcdev;
 		}
 		if (com20020_check(dev)) {
 			ret = -EIO;
-			goto out_port;
+			goto err_free_arcdev;
 		}
 
 		card = devm_kzalloc(&pdev->dev, sizeof(struct com20020_dev),
 				    GFP_KERNEL);
 		if (!card) {
 			ret = -ENOMEM;
-			goto out_port;
+			goto err_free_arcdev;
 		}
 
 		card->index = i;
@@ -253,29 +257,29 @@ static int com20020pci_probe(struct pci_dev *pdev,
 
 		ret = devm_led_classdev_register(&pdev->dev, &card->tx_led);
 		if (ret)
-			goto out_port;
+			goto err_free_arcdev;
 
 		ret = devm_led_classdev_register(&pdev->dev, &card->recon_led);
 		if (ret)
-			goto out_port;
+			goto err_free_arcdev;
 
 		dev_set_drvdata(&dev->dev, card);
 
 		ret = com20020_found(dev, IRQF_SHARED);
 		if (ret)
-			goto out_port;
+			goto err_free_arcdev;
 
 		devm_arcnet_led_init(dev, dev->dev_id, i);
 
 		list_add(&card->list, &priv->list_dev);
+		continue;
+
+err_free_arcdev:
+		free_arcdev(dev);
+		break;
 	}
-
-	pci_set_drvdata(pdev, priv);
-
-	return 0;
-
-out_port:
-	com20020pci_remove(pdev);
+	if (ret)
+		com20020pci_remove(pdev);
 	return ret;
 }
 

From 50535249f624d0072cd885bcdce4e4b6fb770160 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 12 Mar 2021 08:59:48 -0800
Subject: [PATCH 0804/1820] net: qrtr: fix a kernel-infoleak in qrtr_recvmsg()

struct sockaddr_qrtr has a 2-byte hole, and qrtr_recvmsg() currently
does not clear it before copying kernel data to user space.

It might be too late to name the hole since sockaddr_qrtr structure is uapi.

BUG: KMSAN: kernel-infoleak in kmsan_copy_to_user+0x9c/0xb0 mm/kmsan/kmsan_hooks.c:249
CPU: 0 PID: 29705 Comm: syz-executor.3 Not tainted 5.11.0-rc7-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:79 [inline]
 dump_stack+0x21c/0x280 lib/dump_stack.c:120
 kmsan_report+0xfb/0x1e0 mm/kmsan/kmsan_report.c:118
 kmsan_internal_check_memory+0x202/0x520 mm/kmsan/kmsan.c:402
 kmsan_copy_to_user+0x9c/0xb0 mm/kmsan/kmsan_hooks.c:249
 instrument_copy_to_user include/linux/instrumented.h:121 [inline]
 _copy_to_user+0x1ac/0x270 lib/usercopy.c:33
 copy_to_user include/linux/uaccess.h:209 [inline]
 move_addr_to_user+0x3a2/0x640 net/socket.c:237
 ____sys_recvmsg+0x696/0xd50 net/socket.c:2575
 ___sys_recvmsg net/socket.c:2610 [inline]
 do_recvmmsg+0xa97/0x22d0 net/socket.c:2710
 __sys_recvmmsg net/socket.c:2789 [inline]
 __do_sys_recvmmsg net/socket.c:2812 [inline]
 __se_sys_recvmmsg+0x24a/0x410 net/socket.c:2805
 __x64_sys_recvmmsg+0x62/0x80 net/socket.c:2805
 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x465f69
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f43659d6188 EFLAGS: 00000246 ORIG_RAX: 000000000000012b
RAX: ffffffffffffffda RBX: 000000000056bf60 RCX: 0000000000465f69
RDX: 0000000000000008 RSI: 0000000020003e40 RDI: 0000000000000003
RBP: 00000000004bfa8f R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000010060 R11: 0000000000000246 R12: 000000000056bf60
R13: 0000000000a9fb1f R14: 00007f43659d6300 R15: 0000000000022000

Local variable ----addr@____sys_recvmsg created at:
 ____sys_recvmsg+0x168/0xd50 net/socket.c:2550
 ____sys_recvmsg+0x168/0xd50 net/socket.c:2550

Bytes 2-3 of 12 are uninitialized
Memory access of size 12 starts at ffff88817c627b40
Data copied to user address 0000000020000140

Fixes: bdabad3e363d ("net: Add Qualcomm IPC router")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Courtney Cavin <courtney.cavin@sonymobile.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index edb6ac17ceca..dfc820ee553a 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -1058,6 +1058,11 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg,
 	rc = copied;
 
 	if (addr) {
+		/* There is an anonymous 2-byte hole after sq_family,
+		 * make sure to clear it.
+		 */
+		memset(addr, 0, sizeof(*addr));
+
 		addr->sq_family = AF_QIPCRTR;
 		addr->sq_node = cb->src_node;
 		addr->sq_port = cb->src_port;

From a25f822285420486f5da434efc8d940d42a83bce Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@pm.me>
Date: Fri, 12 Mar 2021 20:08:57 +0000
Subject: [PATCH 0805/1820] flow_dissector: fix byteorder of dissected ICMP ID

flow_dissector_key_icmp::id is of type u16 (CPU byteorder),
ICMP header has its ID field in network byteorder obviously.
Sparse says:

net/core/flow_dissector.c:178:43: warning: restricted __be16 degrades to integer

Convert ID value to CPU byteorder when storing it into
flow_dissector_key_icmp.

Fixes: 5dec597e5cd0 ("flow_dissector: extract more ICMP information")
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2ef2224b3bff..a96a4f5de0ce 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -176,7 +176,7 @@ void skb_flow_get_icmp_tci(const struct sk_buff *skb,
 	 * avoid confusion with packets without such field
 	 */
 	if (icmp_has_id(ih->type))
-		key_icmp->id = ih->un.echo.id ? : 1;
+		key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1;
 	else
 		key_icmp->id = 0;
 }

From c995f12ad8842dbf5cfed113fb52cdd083f5afd1 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Sun, 14 Mar 2021 23:51:14 +0300
Subject: [PATCH 0806/1820] prctl: fix PR_SET_MM_AUXV kernel stack leak

Doing a

	prctl(PR_SET_MM, PR_SET_MM_AUXV, addr, 1);

will copy 1 byte from userspace to (quite big) on-stack array
and then stash everything to mm->saved_auxv.
AT_NULL terminator will be inserted at the very end.

/proc/*/auxv handler will find that AT_NULL terminator
and copy original stack contents to userspace.

This devious scheme requires CAP_SYS_RESOURCE.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/sys.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sys.c b/kernel/sys.c
index b09fe21e88ff..2e2e3f378d97 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2079,7 +2079,7 @@ static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr,
 	 * up to the caller to provide sane values here, otherwise userspace
 	 * tools which use this vector might be unhappy.
 	 */
-	unsigned long user_auxv[AT_VECTOR_SIZE];
+	unsigned long user_auxv[AT_VECTOR_SIZE] = {};
 
 	if (len > sizeof(user_auxv))
 		return -EINVAL;

From 1e28eed17697bcf343c6743f0028cc3b5dd88bf0 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 14 Mar 2021 14:41:02 -0700
Subject: [PATCH 0807/1820] Linux 5.12-rc3

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 10bb0a62cc7d..a28bb374663d 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Frozen Wasteland
 
 # *DOCUMENTATION*

From beb691e69f4dec7bfe8b81b509848acfd1f0dbf9 Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Fri, 12 Mar 2021 15:09:13 +0100
Subject: [PATCH 0808/1820] vhost: Fix vhost_vq_reset()

vhost_reset_is_le() is vhost_init_is_le(), and in the case of
cross-endian legacy, vhost_init_is_le() depends on vq->user_be.

vq->user_be is set by vhost_disable_cross_endian().

But in vhost_vq_reset(), we have:

    vhost_reset_is_le(vq);
    vhost_disable_cross_endian(vq);

And so user_be is used before being set.

To fix that, reverse the lines order as there is no other dependency
between them.

Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Link: https://lore.kernel.org/r/20210312140913.788592-1-lvivier@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vhost.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a262e12c6dc2..5ccb0705beae 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -332,8 +332,8 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->error_ctx = NULL;
 	vq->kick = NULL;
 	vq->log_ctx = NULL;
-	vhost_reset_is_le(vq);
 	vhost_disable_cross_endian(vq);
+	vhost_reset_is_le(vq);
 	vq->busyloop_timeout = 0;
 	vq->umem = NULL;
 	vq->iotlb = NULL;

From f6bbf0010ba004f5e90c7aefdebc0ee4bd3283b9 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Thu, 11 Mar 2021 14:52:56 +0100
Subject: [PATCH 0809/1820] vhost-vdpa: fix use-after-free of v->config_ctx

When the 'v->config_ctx' eventfd_ctx reference is released we didn't
set it to NULL. So if the same character device (e.g. /dev/vhost-vdpa-0)
is re-opened, the 'v->config_ctx' is invalid and calling again
vhost_vdpa_config_put() causes use-after-free issues like the
following refcount_t underflow:

    refcount_t: underflow; use-after-free.
    WARNING: CPU: 2 PID: 872 at lib/refcount.c:28 refcount_warn_saturate+0xae/0xf0
    RIP: 0010:refcount_warn_saturate+0xae/0xf0
    Call Trace:
     eventfd_ctx_put+0x5b/0x70
     vhost_vdpa_release+0xcd/0x150 [vhost_vdpa]
     __fput+0x8e/0x240
     ____fput+0xe/0x10
     task_work_run+0x66/0xa0
     exit_to_user_mode_prepare+0x118/0x120
     syscall_exit_to_user_mode+0x21/0x50
     ? __x64_sys_close+0x12/0x40
     do_syscall_64+0x45/0x50
     entry_SYSCALL_64_after_hwframe+0x44/0xae

Fixes: 776f395004d8 ("vhost_vdpa: Support config interrupt in vdpa")
Cc: lingshan.zhu@intel.com
Cc: stable@vger.kernel.org
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://lore.kernel.org/r/20210311135257.109460-2-sgarzare@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Zhu Lingshan <lingshan.zhu@intel.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vhost/vdpa.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index dfdd8e4a8b08..4fc768813c4a 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -308,8 +308,10 @@ static long vhost_vdpa_get_vring_num(struct vhost_vdpa *v, u16 __user *argp)
 
 static void vhost_vdpa_config_put(struct vhost_vdpa *v)
 {
-	if (v->config_ctx)
+	if (v->config_ctx) {
 		eventfd_ctx_put(v->config_ctx);
+		v->config_ctx = NULL;
+	}
 }
 
 static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp)

From 0bde59c1723a29e294765c96dbe5c7fb639c2f96 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Thu, 11 Mar 2021 14:52:57 +0100
Subject: [PATCH 0810/1820] vhost-vdpa: set v->config_ctx to NULL if
 eventfd_ctx_fdget() fails

In vhost_vdpa_set_config_call() if eventfd_ctx_fdget() fails the
'v->config_ctx' contains an error instead of a valid pointer.

Since we consider 'v->config_ctx' valid if it is not NULL, we should
set it to NULL in this case to avoid to use an invalid pointer in
other functions such as vhost_vdpa_config_put().

Fixes: 776f395004d8 ("vhost_vdpa: Support config interrupt in vdpa")
Cc: lingshan.zhu@intel.com
Cc: stable@vger.kernel.org
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://lore.kernel.org/r/20210311135257.109460-3-sgarzare@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vhost/vdpa.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 4fc768813c4a..e0a27e336293 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -331,8 +331,12 @@ static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp)
 	if (!IS_ERR_OR_NULL(ctx))
 		eventfd_ctx_put(ctx);
 
-	if (IS_ERR(v->config_ctx))
-		return PTR_ERR(v->config_ctx);
+	if (IS_ERR(v->config_ctx)) {
+		long ret = PTR_ERR(v->config_ctx);
+
+		v->config_ctx = NULL;
+		return ret;
+	}
 
 	v->vdpa->config->set_config_cb(v->vdpa, &cb);
 

From 5171317dfd9afcf729799d31fffdbb9e71e45402 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 10 Mar 2021 10:22:27 +0000
Subject: [PATCH 0811/1820] cifs: update new ACE pointer after
 populate_new_aces.

After the fix for retaining externally set ACEs with cifsacl and
modefromsid,idsfromsid, there was an issue in populating the
inherited ACEs after setting the ACEs introduced by these two modes.
Fixed this by updating the ACE pointer again after the call to
populate_new_aces.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Reviewed-by: Rohith Surabattula <rohiths@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cifsacl.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 9d29eb9660c2..2be22a5c690f 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1118,7 +1118,6 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl,
 	/* Retain old ACEs which we can retain */
 	for (i = 0; i < src_num_aces; ++i) {
 		pntace = (struct cifs_ace *) (acl_base + size);
-		pnntace = (struct cifs_ace *) (nacl_base + nsize);
 
 		if (!new_aces_set && (pntace->flags & INHERITED_ACE)) {
 			/* Place the new ACEs in between existing explicit and inherited */
@@ -1131,14 +1130,18 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl,
 		}
 
 		/* If it's any one of the ACE we're replacing, skip! */
-		if ((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
+		if (!mode_from_sid &&
+				((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
 				(compare_sids(&pntace->sid, pownersid) == 0) ||
 				(compare_sids(&pntace->sid, pgrpsid) == 0) ||
 				(compare_sids(&pntace->sid, &sid_everyone) == 0) ||
-				(compare_sids(&pntace->sid, &sid_authusers) == 0)) {
+				(compare_sids(&pntace->sid, &sid_authusers) == 0))) {
 			goto next_ace;
 		}
 
+		/* update the pointer to the next ACE to populate*/
+		pnntace = (struct cifs_ace *) (nacl_base + nsize);
+
 		nsize += cifs_copy_ace(pnntace, pntace, NULL);
 		num_aces++;
 

From 05946d4b7a7349ae58bfa2d51ae832e64a394c2d Mon Sep 17 00:00:00 2001
From: Vincent Whitchurch <vincent.whitchurch@axis.com>
Date: Wed, 10 Mar 2021 13:20:40 +0100
Subject: [PATCH 0812/1820] cifs: Fix preauth hash corruption

smb311_update_preauth_hash() uses the shash in server->secmech without
appropriate locking, and this can lead to sessions corrupting each
other's preauth hashes.

The following script can easily trigger the problem:

	#!/bin/sh -e

	NMOUNTS=10
	for i in $(seq $NMOUNTS);
		mkdir -p /tmp/mnt$i
		umount /tmp/mnt$i 2>/dev/null || :
	done
	while :; do
		for i in $(seq $NMOUNTS); do
			mount -t cifs //192.168.0.1/test /tmp/mnt$i -o ... &
		done
		wait
		for i in $(seq $NMOUNTS); do
			umount /tmp/mnt$i
		done
	done

Usually within seconds this leads to one or more of the mounts failing
with the following errors, and a "Bad SMB2 signature for message" is
seen in the server logs:

 CIFS: VFS: \\192.168.0.1 failed to connect to IPC (rc=-13)
 CIFS: VFS: cifs_mount failed w/return code = -13

Fix it by holding the server mutex just like in the other places where
the shashes are used.

Fixes: 8bd68c6e47abff34e4 ("CIFS: implement v3.11 preauth integrity")
Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com>
CC: <stable@vger.kernel.org>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/transport.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 007d99437c77..c1725b55f364 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -1196,9 +1196,12 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
 	/*
 	 * Compounding is never used during session establish.
 	 */
-	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP))
+	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP)) {
+		mutex_lock(&server->srv_mutex);
 		smb311_update_preauth_hash(ses, rqst[0].rq_iov,
 					   rqst[0].rq_nvec);
+		mutex_unlock(&server->srv_mutex);
+	}
 
 	for (i = 0; i < num_rqst; i++) {
 		rc = wait_for_response(server, midQ[i]);
@@ -1266,7 +1269,9 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
 			.iov_base = resp_iov[0].iov_base,
 			.iov_len = resp_iov[0].iov_len
 		};
+		mutex_lock(&server->srv_mutex);
 		smb311_update_preauth_hash(ses, &iov, 1);
+		mutex_unlock(&server->srv_mutex);
 	}
 
 out:

From c9570d4a5efd04479b3cd09c39b571eb031d94f4 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Thu, 31 Dec 2020 09:52:52 +0100
Subject: [PATCH 0813/1820] extcon: Add stubs for
 extcon_register_notifier_all() functions

Add stubs for extcon_register_notifier_all() function for !CONFIG_EXTCON
case.  This is useful for compile testing and for drivers which use
EXTCON but do not require it (therefore do not depend on CONFIG_EXTCON).

Fixes: 815429b39d94 ("extcon: Add new extcon_register_notifier_all() to monitor all external connectors")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 include/linux/extcon.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/include/linux/extcon.h b/include/linux/extcon.h
index fd183fb9c20f..0c19010da77f 100644
--- a/include/linux/extcon.h
+++ b/include/linux/extcon.h
@@ -271,6 +271,29 @@ static inline  void devm_extcon_unregister_notifier(struct device *dev,
 				struct extcon_dev *edev, unsigned int id,
 				struct notifier_block *nb) { }
 
+static inline int extcon_register_notifier_all(struct extcon_dev *edev,
+					       struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int extcon_unregister_notifier_all(struct extcon_dev *edev,
+						 struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int devm_extcon_register_notifier_all(struct device *dev,
+						    struct extcon_dev *edev,
+						    struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline void devm_extcon_unregister_notifier_all(struct device *dev,
+						       struct extcon_dev *edev,
+						       struct notifier_block *nb) { }
+
 static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name)
 {
 	return ERR_PTR(-ENODEV);

From d3bdd1c3140724967ca4136755538fa7c05c2b4e Mon Sep 17 00:00:00 2001
From: Dinghao Liu <dinghao.liu@zju.edu.cn>
Date: Tue, 19 Jan 2021 16:10:55 +0800
Subject: [PATCH 0814/1820] extcon: Fix error handling in extcon_dev_register

When devm_kcalloc() fails, we should execute device_unregister()
to unregister edev->dev from system.

Fixes: 046050f6e623e ("extcon: Update the prototype of extcon_register_notifier() with enum extcon")
Signed-off-by: Dinghao Liu <dinghao.liu@zju.edu.cn>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/extcon/extcon.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index 0a6438cbb3f3..e7a9561a826d 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -1241,6 +1241,7 @@ int extcon_dev_register(struct extcon_dev *edev)
 				sizeof(*edev->nh), GFP_KERNEL);
 	if (!edev->nh) {
 		ret = -ENOMEM;
+		device_unregister(&edev->dev);
 		goto err_dev;
 	}
 

From e2c1b0ff38c961d49ce34efda48fa45eb1cb5f19 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Thu, 4 Feb 2021 17:38:46 -0800
Subject: [PATCH 0815/1820] ARM: imx: avic: Convert to using IRQCHIP_DECLARE

Using IRQCHIP_DECLARE lets fw_devlink know that it should not wait for
these interrupt controllers to be populated as struct devices. Without
this change, fw_devlink=on will make the consumers of these interrupt
controllers wait for the struct device to be added and thereby block the
consumers' probes forever. Converting to IRQCHIP_DECLARE addresses boot
issues on imx25 with fw_devlink=on that were reported by Martin.

This also removes a lot of boilerplate code.

Fixes: e590474768f1 ("driver core: Set fw_devlink=on by default")
Reported-by: Martin Kaiser <martin@kaiser.cx>
Signed-off-by: Saravana Kannan <saravanak@google.com>
Tested-by: Martin Kaiser <martin@kaiser.cx>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm/mach-imx/avic.c       | 16 +++++++++++++++-
 arch/arm/mach-imx/common.h     |  1 -
 arch/arm/mach-imx/mach-imx1.c  | 11 -----------
 arch/arm/mach-imx/mach-imx25.c | 12 ------------
 arch/arm/mach-imx/mach-imx27.c | 12 ------------
 arch/arm/mach-imx/mach-imx31.c |  1 -
 arch/arm/mach-imx/mach-imx35.c |  1 -
 arch/arm/mach-imx/mm-imx3.c    | 24 ------------------------
 8 files changed, 15 insertions(+), 63 deletions(-)

diff --git a/arch/arm/mach-imx/avic.c b/arch/arm/mach-imx/avic.c
index 322caa21bcb3..21bce4049cec 100644
--- a/arch/arm/mach-imx/avic.c
+++ b/arch/arm/mach-imx/avic.c
@@ -7,6 +7,7 @@
 #include <linux/module.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
+#include <linux/irqchip.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -162,7 +163,7 @@ static void __exception_irq_entry avic_handle_irq(struct pt_regs *regs)
  * interrupts. It registers the interrupt enable and disable functions
  * to the kernel for each interrupt source.
  */
-void __init mxc_init_irq(void __iomem *irqbase)
+static void __init mxc_init_irq(void __iomem *irqbase)
 {
 	struct device_node *np;
 	int irq_base;
@@ -220,3 +221,16 @@ void __init mxc_init_irq(void __iomem *irqbase)
 
 	printk(KERN_INFO "MXC IRQ initialized\n");
 }
+
+static int __init imx_avic_init(struct device_node *node,
+			       struct device_node *parent)
+{
+	void __iomem *avic_base;
+
+	avic_base = of_iomap(node, 0);
+	BUG_ON(!avic_base);
+	mxc_init_irq(avic_base);
+	return 0;
+}
+
+IRQCHIP_DECLARE(imx_avic, "fsl,avic", imx_avic_init);
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index 2b004cc4f95e..474dedb73bc7 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -22,7 +22,6 @@ void mx35_map_io(void);
 void imx21_init_early(void);
 void imx31_init_early(void);
 void imx35_init_early(void);
-void mxc_init_irq(void __iomem *);
 void mx31_init_irq(void);
 void mx35_init_irq(void);
 void mxc_set_cpu_type(unsigned int type);
diff --git a/arch/arm/mach-imx/mach-imx1.c b/arch/arm/mach-imx/mach-imx1.c
index 32df3b8012f9..8eca92d66a2e 100644
--- a/arch/arm/mach-imx/mach-imx1.c
+++ b/arch/arm/mach-imx/mach-imx1.c
@@ -17,16 +17,6 @@ static void __init imx1_init_early(void)
 	mxc_set_cpu_type(MXC_CPU_MX1);
 }
 
-static void __init imx1_init_irq(void)
-{
-	void __iomem *avic_addr;
-
-	avic_addr = ioremap(MX1_AVIC_ADDR, SZ_4K);
-	WARN_ON(!avic_addr);
-
-	mxc_init_irq(avic_addr);
-}
-
 static const char * const imx1_dt_board_compat[] __initconst = {
 	"fsl,imx1",
 	NULL
@@ -34,7 +24,6 @@ static const char * const imx1_dt_board_compat[] __initconst = {
 
 DT_MACHINE_START(IMX1_DT, "Freescale i.MX1 (Device Tree Support)")
 	.init_early	= imx1_init_early,
-	.init_irq	= imx1_init_irq,
 	.dt_compat	= imx1_dt_board_compat,
 	.restart	= mxc_restart,
 MACHINE_END
diff --git a/arch/arm/mach-imx/mach-imx25.c b/arch/arm/mach-imx/mach-imx25.c
index 95de48a1aa7d..51927bd08aef 100644
--- a/arch/arm/mach-imx/mach-imx25.c
+++ b/arch/arm/mach-imx/mach-imx25.c
@@ -22,17 +22,6 @@ static void __init imx25_dt_init(void)
 	imx_aips_allow_unprivileged_access("fsl,imx25-aips");
 }
 
-static void __init mx25_init_irq(void)
-{
-	struct device_node *np;
-	void __iomem *avic_base;
-
-	np = of_find_compatible_node(NULL, NULL, "fsl,avic");
-	avic_base = of_iomap(np, 0);
-	BUG_ON(!avic_base);
-	mxc_init_irq(avic_base);
-}
-
 static const char * const imx25_dt_board_compat[] __initconst = {
 	"fsl,imx25",
 	NULL
@@ -42,6 +31,5 @@ DT_MACHINE_START(IMX25_DT, "Freescale i.MX25 (Device Tree Support)")
 	.init_early	= imx25_init_early,
 	.init_machine	= imx25_dt_init,
 	.init_late      = imx25_pm_init,
-	.init_irq	= mx25_init_irq,
 	.dt_compat	= imx25_dt_board_compat,
 MACHINE_END
diff --git a/arch/arm/mach-imx/mach-imx27.c b/arch/arm/mach-imx/mach-imx27.c
index 262422a9c196..e325c9468105 100644
--- a/arch/arm/mach-imx/mach-imx27.c
+++ b/arch/arm/mach-imx/mach-imx27.c
@@ -56,17 +56,6 @@ static void __init imx27_init_early(void)
 	mxc_set_cpu_type(MXC_CPU_MX27);
 }
 
-static void __init mx27_init_irq(void)
-{
-	void __iomem *avic_base;
-	struct device_node *np;
-
-	np = of_find_compatible_node(NULL, NULL, "fsl,avic");
-	avic_base = of_iomap(np, 0);
-	BUG_ON(!avic_base);
-	mxc_init_irq(avic_base);
-}
-
 static const char * const imx27_dt_board_compat[] __initconst = {
 	"fsl,imx27",
 	NULL
@@ -75,7 +64,6 @@ static const char * const imx27_dt_board_compat[] __initconst = {
 DT_MACHINE_START(IMX27_DT, "Freescale i.MX27 (Device Tree Support)")
 	.map_io		= mx27_map_io,
 	.init_early	= imx27_init_early,
-	.init_irq	= mx27_init_irq,
 	.init_late	= imx27_pm_init,
 	.dt_compat	= imx27_dt_board_compat,
 MACHINE_END
diff --git a/arch/arm/mach-imx/mach-imx31.c b/arch/arm/mach-imx/mach-imx31.c
index dc69dfe600df..e9a1092b6093 100644
--- a/arch/arm/mach-imx/mach-imx31.c
+++ b/arch/arm/mach-imx/mach-imx31.c
@@ -14,6 +14,5 @@ static const char * const imx31_dt_board_compat[] __initconst = {
 DT_MACHINE_START(IMX31_DT, "Freescale i.MX31 (Device Tree Support)")
 	.map_io		= mx31_map_io,
 	.init_early	= imx31_init_early,
-	.init_irq	= mx31_init_irq,
 	.dt_compat	= imx31_dt_board_compat,
 MACHINE_END
diff --git a/arch/arm/mach-imx/mach-imx35.c b/arch/arm/mach-imx/mach-imx35.c
index ec5c3068715c..0fc08218b77d 100644
--- a/arch/arm/mach-imx/mach-imx35.c
+++ b/arch/arm/mach-imx/mach-imx35.c
@@ -27,6 +27,5 @@ DT_MACHINE_START(IMX35_DT, "Freescale i.MX35 (Device Tree Support)")
 	.l2c_aux_mask	= ~0,
 	.map_io		= mx35_map_io,
 	.init_early	= imx35_init_early,
-	.init_irq	= mx35_init_irq,
 	.dt_compat	= imx35_dt_board_compat,
 MACHINE_END
diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c
index 5056438e5b42..28db97289ee8 100644
--- a/arch/arm/mach-imx/mm-imx3.c
+++ b/arch/arm/mach-imx/mm-imx3.c
@@ -109,18 +109,6 @@ void __init imx31_init_early(void)
 	mx3_ccm_base = of_iomap(np, 0);
 	BUG_ON(!mx3_ccm_base);
 }
-
-void __init mx31_init_irq(void)
-{
-	void __iomem *avic_base;
-	struct device_node *np;
-
-	np = of_find_compatible_node(NULL, NULL, "fsl,imx31-avic");
-	avic_base = of_iomap(np, 0);
-	BUG_ON(!avic_base);
-
-	mxc_init_irq(avic_base);
-}
 #endif /* ifdef CONFIG_SOC_IMX31 */
 
 #ifdef CONFIG_SOC_IMX35
@@ -158,16 +146,4 @@ void __init imx35_init_early(void)
 	mx3_ccm_base = of_iomap(np, 0);
 	BUG_ON(!mx3_ccm_base);
 }
-
-void __init mx35_init_irq(void)
-{
-	void __iomem *avic_base;
-	struct device_node *np;
-
-	np = of_find_compatible_node(NULL, NULL, "fsl,imx35-avic");
-	avic_base = of_iomap(np, 0);
-	BUG_ON(!avic_base);
-
-	mxc_init_irq(avic_base);
-}
 #endif /* ifdef CONFIG_SOC_IMX35 */

From 9c3a16f88385e671b63a0de7b82b85e604a80f42 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Horia=20Geant=C4=83?= <horia.geanta@nxp.com>
Date: Sun, 7 Mar 2021 22:47:35 +0200
Subject: [PATCH 0816/1820] arm64: dts: ls1046a: mark crypto engine dma
 coherent
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Crypto engine (CAAM) on LS1046A platform is configured HW-coherent,
mark accordingly the DT node.

As reported by Greg and Sascha, and explained by Robin, lack of
"dma-coherent" property for an IP that is configured HW-coherent
can lead to problems, e.g. on v5.11:

> kernel BUG at drivers/crypto/caam/jr.c:247!
> Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
> Modules linked in:
> CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.11.0-20210225-3-00039-g434215968816-dirty #12
> Hardware name: TQ TQMLS1046A SoM on Arkona AT1130 (C300) board (DT)
> pstate: 60000005 (nZCv daif -PAN -UAO -TCO BTYPE=--)
> pc : caam_jr_dequeue+0x98/0x57c
> lr : caam_jr_dequeue+0x98/0x57c
> sp : ffff800010003d50
> x29: ffff800010003d50 x28: ffff8000118d4000
> x27: ffff8000118d4328 x26: 00000000000001f0
> x25: ffff0008022be480 x24: ffff0008022c6410
> x23: 00000000000001f1 x22: ffff8000118d4329
> x21: 0000000000004d80 x20: 00000000000001f1
> x19: 0000000000000001 x18: 0000000000000020
> x17: 0000000000000000 x16: 0000000000000015
> x15: ffff800011690230 x14: 2e2e2e2e2e2e2e2e
> x13: 2e2e2e2e2e2e2020 x12: 3030303030303030
> x11: ffff800011700a38 x10: 00000000fffff000
> x9 : ffff8000100ada30 x8 : ffff8000116a8a38
> x7 : 0000000000000001 x6 : 0000000000000000
> x5 : 0000000000000000 x4 : 0000000000000000
> x3 : 00000000ffffffff x2 : 0000000000000000
> x1 : 0000000000000000 x0 : 0000000000001800
> Call trace:
>  caam_jr_dequeue+0x98/0x57c
>  tasklet_action_common.constprop.0+0x164/0x18c
>  tasklet_action+0x44/0x54
>  __do_softirq+0x160/0x454
>  __irq_exit_rcu+0x164/0x16c
>  irq_exit+0x1c/0x30
>  __handle_domain_irq+0xc0/0x13c
>  gic_handle_irq+0x5c/0xf0
>  el1_irq+0xb4/0x180
>  arch_cpu_idle+0x18/0x30
>  default_idle_call+0x3c/0x1c0
>  do_idle+0x23c/0x274
>  cpu_startup_entry+0x34/0x70
>  rest_init+0xdc/0xec
>  arch_call_rest_init+0x1c/0x28
>  start_kernel+0x4ac/0x4e4
> Code: 91392021 912c2000 d377d8c6 97f24d96 (d4210000)

Cc: <stable@vger.kernel.org> # v4.10+
Fixes: 8126d88162a5 ("arm64: dts: add QorIQ LS1046A SoC support")
Link: https://lore.kernel.org/linux-crypto/fe6faa24-d8f7-d18f-adfa-44fa0caa1598@arm.com
Reported-by: Greg Ungerer <gerg@kernel.org>
Reported-by: Sascha Hauer <s.hauer@pengutronix.de>
Tested-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Horia Geantă <horia.geanta@nxp.com>
Acked-by: Greg Ungerer <gerg@kernel.org>
Acked-by: Li Yang <leoyang.li@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
index 1d6dfd189c7f..39458305e333 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
@@ -354,6 +354,7 @@
 			ranges = <0x0 0x00 0x1700000 0x100000>;
 			reg = <0x00 0x1700000 0x0 0x100000>;
 			interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+			dma-coherent;
 
 			sec_jr0: jr@10000 {
 				compatible = "fsl,sec-v5.4-job-ring",

From 4fb3a074755b7737c4081cffe0ccfa08c2f2d29d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Horia=20Geant=C4=83?= <horia.geanta@nxp.com>
Date: Sun, 7 Mar 2021 22:47:36 +0200
Subject: [PATCH 0817/1820] arm64: dts: ls1043a: mark crypto engine dma
 coherent
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Crypto engine (CAAM) on LS1043A platform is configured HW-coherent,
mark accordingly the DT node.

Lack of "dma-coherent" property for an IP that is configured HW-coherent
can lead to problems, similar to what has been reported for LS1046A.

Cc: <stable@vger.kernel.org> # v4.8+
Fixes: 63dac35b58f4 ("arm64: dts: ls1043a: add crypto node")
Link: https://lore.kernel.org/linux-crypto/fe6faa24-d8f7-d18f-adfa-44fa0caa1598@arm.com
Signed-off-by: Horia Geantă <horia.geanta@nxp.com>
Acked-by: Li Yang <leoyang.li@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index 5a8a1dc4262d..28c51e521cb2 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -348,6 +348,7 @@
 			ranges = <0x0 0x00 0x1700000 0x100000>;
 			reg = <0x00 0x1700000 0x0 0x100000>;
 			interrupts = <0 75 0x4>;
+			dma-coherent;
 
 			sec_jr0: jr@10000 {
 				compatible = "fsl,sec-v5.4-job-ring",

From ba8da03fa7dff59d9400250aebd38f94cde3cb0f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Horia=20Geant=C4=83?= <horia.geanta@nxp.com>
Date: Sun, 7 Mar 2021 22:47:37 +0200
Subject: [PATCH 0818/1820] arm64: dts: ls1012a: mark crypto engine dma
 coherent
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Crypto engine (CAAM) on LS1012A platform is configured HW-coherent,
mark accordingly the DT node.

Lack of "dma-coherent" property for an IP that is configured HW-coherent
can lead to problems, similar to what has been reported for LS1046A.

Cc: <stable@vger.kernel.org> # v4.12+
Fixes: 85b85c569507 ("arm64: dts: ls1012a: add crypto node")
Signed-off-by: Horia Geantă <horia.geanta@nxp.com>
Acked-by: Li Yang <leoyang.li@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
index 7de6b376d792..9058cfa4980f 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
@@ -198,6 +198,7 @@
 			ranges = <0x0 0x00 0x1700000 0x100000>;
 			reg = <0x00 0x1700000 0x0 0x100000>;
 			interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+			dma-coherent;
 
 			sec_jr0: jr@10000 {
 				compatible = "fsl,sec-v5.4-job-ring",

From 412627f6ffe32211863e1dcd76dab98c90556fc7 Mon Sep 17 00:00:00 2001
From: Teresa Remmet <t.remmet@phytec.de>
Date: Thu, 11 Mar 2021 07:14:45 +0100
Subject: [PATCH 0819/1820] arm64: dts: imx8mp-phyboard-pollux-rdk: Add missing
 pinctrl entry

Add missing pinctrl-names for i2c gpio recovery mode.

Fixes: 88f7f6bcca37 ("arm64: dts: freescale: Add support for phyBOARD-Pollux-i.MX8MP")
Signed-off-by: Teresa Remmet <t.remmet@phytec.de>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts | 2 +-
 arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi        | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
index 0e1a6d953389..122c95ddad30 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
@@ -35,7 +35,7 @@
 
 &i2c2 {
 	clock-frequency = <400000>;
-	pinctrl-names = "default";
+	pinctrl-names = "default", "gpio";
 	pinctrl-0 = <&pinctrl_i2c2>;
 	pinctrl-1 = <&pinctrl_i2c2_gpio>;
 	sda-gpios = <&gpio5 17 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
index 44a8c2337cee..f3965ec5b31d 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
@@ -67,7 +67,7 @@
 
 &i2c1 {
 	clock-frequency = <400000>;
-	pinctrl-names = "default";
+	pinctrl-names = "default", "gpio";
 	pinctrl-0 = <&pinctrl_i2c1>;
 	pinctrl-1 = <&pinctrl_i2c1_gpio>;
 	sda-gpios = <&gpio5 15 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;

From 69cbbf6be5d5c25deeddd9450ae538e769480dc3 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@gmail.com>
Date: Fri, 12 Mar 2021 08:37:46 -0300
Subject: [PATCH 0820/1820] ARM: imx6ul-14x14-evk: Do not reset the Ethernet
 PHYs independently

The imx6ul-evk board designer took the bad decision to tie the
two Ethernet PHY reset lines together. This prevents one Ethernet
interface to work while the other one is brought down. For example:

 # ifconfig eth0 down
 # [  279.386551] fec 2188000.ethernet eth1: Link is Down

Bringing eth0 interface down also causes eth1 to be down.

The Ethernet reset lines comes from the IO expander and both come in
logic level 0 by default.

To fix this issue, remove the Ethernet PHY reset descriptions from
its respective PHY nodes and force both Ethernet PHY lines to be at
logic level 1 via gpio-hog.

Fixes: 2db7e78bf02b ("ARM: dts: imx6ul-14x14-evk: Describe the KSZ8081 reset")
Reported-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Signed-off-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm/boot/dts/imx6ul-14x14-evk.dtsi | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
index c593597b2119..5a1e10def6ef 100644
--- a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
+++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
@@ -210,9 +210,6 @@
 			micrel,led-mode = <1>;
 			clocks = <&clks IMX6UL_CLK_ENET_REF>;
 			clock-names = "rmii-ref";
-			reset-gpios = <&gpio_spi 1 GPIO_ACTIVE_LOW>;
-			reset-assert-us = <10000>;
-			reset-deassert-us = <100>;
 
 		};
 
@@ -222,9 +219,6 @@
 			micrel,led-mode = <1>;
 			clocks = <&clks IMX6UL_CLK_ENET2_REF>;
 			clock-names = "rmii-ref";
-			reset-gpios = <&gpio_spi 2 GPIO_ACTIVE_LOW>;
-			reset-assert-us = <10000>;
-			reset-deassert-us = <100>;
 		};
 	};
 };
@@ -243,6 +237,22 @@
 	status = "okay";
 };
 
+&gpio_spi {
+	eth0-phy-hog {
+		gpio-hog;
+		gpios = <1 GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "eth0-phy";
+	};
+
+	eth1-phy-hog {
+		gpio-hog;
+		gpios = <2 GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "eth1-phy";
+	};
+};
+
 &i2c1 {
 	clock-frequency = <100000>;
 	pinctrl-names = "default";

From 0710442a88d1c646d37ac83c52de85f456e99171 Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@linaro.org>
Date: Sun, 14 Mar 2021 20:26:50 -0500
Subject: [PATCH 0821/1820] arm64: csum: cast to the proper type

The last line of ip_fast_csum() calls csum_fold(), forcing the
type of the argument passed to be u32.  But csum_fold() takes a
__wsum argument (which is __u32 __bitwise for arm64).  As long
as we're forcing the cast, cast it to the right type.

Signed-off-by: Alex Elder <elder@linaro.org>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20210315012650.1221328-1-elder@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/checksum.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index 93a161b3bf3f..dc52b733675d 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -37,7 +37,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	} while (--n > 0);
 
 	sum += ((sum >> 32) | (sum << 32));
-	return csum_fold((__force u32)(sum >> 32));
+	return csum_fold((__force __wsum)(sum >> 32));
 }
 #define ip_fast_csum ip_fast_csum
 

From e40647762fb5881360874e08e03e972d58d63c42 Mon Sep 17 00:00:00 2001
From: Jin Yao <yao.jin@linux.intel.com>
Date: Wed, 10 Mar 2021 13:11:38 +0800
Subject: [PATCH 0822/1820] perf pmu: Validate raw event with sysfs exported
 format bits

A raw PMU event (eventsel+umask) in the form of rNNN is supported
by perf but lacks of checking for the validity of raw encoding.

For example, bit 16 and bit 17 are not valid on KBL but perf doesn't
report warning when encoding with these bits.

Before:

  # ./perf stat -e cpu/r031234/ -a -- sleep 1

   Performance counter stats for 'system wide':

                   0      cpu/r031234/

         1.003798924 seconds time elapsed

It may silently measure the wrong event!

The kernel supported bits have been exported through
/sys/devices/<pmu>/format/. Perf collects the information to
'struct perf_pmu_format' and links it to 'pmu->format' list.

The 'struct perf_pmu_format' has a bitmap which records the
valid bits for this format. For example,

  root@kbl-ppc:/sys/devices/cpu/format# cat umask
  config:8-15

The valid bits (bit8-bit15) are recorded in bitmap of format 'umask'.

We collect total valid bits of all formats, save to a local variable
'masks' and reverse it. Now '~masks' represents total invalid bits.

bits = config & ~masks;

The set bits in 'bits' indicate the invalid bits used in config.
Finally we use bitmap_scnprintf to report the invalid bits.

Some architectures may not export supported bits through sysfs,
so if masks is 0, perf_pmu__warn_invalid_config directly returns.

After:

Single event without name:

  # ./perf stat -e cpu/r031234/ -a -- sleep 1
  WARNING: event 'N/A' not valid (bits 16-17 of config '31234' not supported by kernel)!

   Performance counter stats for 'system wide':

                   0      cpu/r031234/

         1.001597373 seconds time elapsed

Multiple events with names:

  # ./perf stat -e cpu/rf01234,name=aaa/,cpu/r031234,name=bbb/ -a -- sleep 1
  WARNING: event 'aaa' not valid (bits 20,22 of config 'f01234' not supported by kernel)!
  WARNING: event 'bbb' not valid (bits 16-17 of config '31234' not supported by kernel)!

   Performance counter stats for 'system wide':

                   0      aaa
                   0      bbb

         1.001573787 seconds time elapsed

Warnings are reported for invalid bits.

Co-developed-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210310051138.12154-1-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c |  3 +++
 tools/perf/util/pmu.c          | 33 +++++++++++++++++++++++++++++++++
 tools/perf/util/pmu.h          |  3 +++
 3 files changed, 39 insertions(+)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 42c84adeb2fb..c0c0fab22cb8 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -356,6 +356,9 @@ __add_event(struct list_head *list, int *idx,
 	struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) :
 			       cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
 
+	if (pmu && attr->type == PERF_TYPE_RAW)
+		perf_pmu__warn_invalid_config(pmu, attr->config, name);
+
 	if (init_attr)
 		event_attr_init(attr);
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 44ef28302fc7..46fd0f998484 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1812,3 +1812,36 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu)
 
 	return nr_caps;
 }
+
+void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
+				   char *name)
+{
+	struct perf_pmu_format *format;
+	__u64 masks = 0, bits;
+	char buf[100];
+	unsigned int i;
+
+	list_for_each_entry(format, &pmu->format, list)	{
+		if (format->value != PERF_PMU_FORMAT_VALUE_CONFIG)
+			continue;
+
+		for_each_set_bit(i, format->bits, PERF_PMU_FORMAT_BITS)
+			masks |= 1ULL << i;
+	}
+
+	/*
+	 * Kernel doesn't export any valid format bits.
+	 */
+	if (masks == 0)
+		return;
+
+	bits = config & ~masks;
+	if (bits == 0)
+		return;
+
+	bitmap_scnprintf((unsigned long *)&bits, sizeof(bits) * 8, buf, sizeof(buf));
+
+	pr_warning("WARNING: event '%s' not valid (bits %s of config "
+		   "'%llx' not supported by kernel)!\n",
+		   name ?: "N/A", buf, config);
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 8164388478c6..160b0f561771 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -123,4 +123,7 @@ int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 
 int perf_pmu__caps_parse(struct perf_pmu *pmu);
 
+void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
+				   char *name);
+
 #endif /* __PMU_H */

From 62dd0f98a0e5668424270b47a0c2e973795faba7 Mon Sep 17 00:00:00 2001
From: Andrew Price <anprice@redhat.com>
Date: Mon, 15 Mar 2021 12:24:00 +0000
Subject: [PATCH 0823/1820] gfs2: Flag a withdraw if init_threads() fails

Interrupting mount with ^C quickly enough can cause the kthread_run()
calls in gfs2's init_threads() to fail and the error path leads to a
deadlock on the s_umount rwsem. The abridged chain of events is:

  [mount path]
  get_tree_bdev()
    sget_fc()
      alloc_super()
        down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); [acquired]
    gfs2_fill_super()
      gfs2_make_fs_rw()
        init_threads()
          kthread_run()
            ( Interrupted )
      [Error path]
      gfs2_gl_hash_clear()
        flush_workqueue(glock_workqueue)
          wait_for_completion()

  [workqueue context]
  glock_work_func()
    run_queue()
      do_xmote()
        freeze_go_sync()
          freeze_super()
            down_write(&sb->s_umount) [deadlock]

In freeze_go_sync() there is a gfs2_withdrawn() check that we can use to
make sure freeze_super() is not called in the error path, so add a
gfs2_withdraw_delayed() call when init_threads() fails.

Ref: https://bugzilla.kernel.org/show_bug.cgi?id=212231

Reported-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: Andrew Price <anprice@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/super.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 97076d3f562f..9e91c9d92bd6 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -162,8 +162,10 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 	int error;
 
 	error = init_threads(sdp);
-	if (error)
+	if (error) {
+		gfs2_withdraw_delayed(sdp);
 		return error;
+	}
 
 	j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
 	if (gfs2_withdrawn(sdp)) {

From 6c5403173a13a08ff61dbdafa4c0ed4a9dedbfe0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Fri, 12 Mar 2021 09:34:39 +0100
Subject: [PATCH 0824/1820] drm/ttm: make ttm_bo_unpin more defensive
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We seem to have some more driver bugs than thought.

Signed-off-by: Christian König <christian.koenig@amd.com>
Fixes: deb0814b43f3 ("drm/ttm: add ttm_bo_pin()/ttm_bo_unpin() v2")
Acked-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210312093810.2202-1-christian.koenig@amd.com
---
 include/drm/ttm/ttm_bo_api.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index e17be324d95f..b8ca13664fa2 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -612,9 +612,11 @@ static inline void ttm_bo_pin(struct ttm_buffer_object *bo)
 static inline void ttm_bo_unpin(struct ttm_buffer_object *bo)
 {
 	dma_resv_assert_held(bo->base.resv);
-	WARN_ON_ONCE(!bo->pin_count);
 	WARN_ON_ONCE(!kref_read(&bo->kref));
-	--bo->pin_count;
+	if (bo->pin_count)
+		--bo->pin_count;
+	else
+		WARN_ON_ONCE(true);
 }
 
 int ttm_mem_evict_first(struct ttm_bo_device *bdev,

From efe814a471e0e58f28f1efaf430c8784a4f36626 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sun, 14 Mar 2021 20:57:08 +0000
Subject: [PATCH 0825/1820] io_uring: fix ->flags races by linked timeouts

It's racy to modify req->flags from a not owning context, e.g. linked
timeout calling req_set_fail_links() for the master request might race
with that request setting/clearing flags while being executed
concurrently. Just remove req_set_fail_links(prev) from
io_link_timeout_fn(), io_async_find_and_cancel() and functions down the
line take care of setting the fail bit.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 58d62dd9f8e4..217f72d50ff5 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6197,7 +6197,6 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer)
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 
 	if (prev) {
-		req_set_fail_links(prev);
 		io_async_find_and_cancel(ctx, req, prev->user_data, -ETIME);
 		io_put_req_deferred(prev, 1);
 	} else {

From 180f829fe4026bd192447d261e712b6cb84f6202 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sun, 14 Mar 2021 20:57:09 +0000
Subject: [PATCH 0826/1820] io_uring: fix complete_post use ctx after free

If io_req_complete_post() put not a final ref, we can't rely on the
request's ctx ref, and so ctx may potentially be freed while
complete_post() is in io_cqring_ev_posted()/etc.

In that case get an additional ctx reference, and put it in the end, so
protecting following io_cqring_ev_posted(). And also prolong ctx
lifetime until spin_unlock happens, as we do with mutexes, so added
percpu_ref_get() doesn't race with ctx free.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 217f72d50ff5..f8a683607b25 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1550,14 +1550,17 @@ static void io_req_complete_post(struct io_kiocb *req, long res,
 		io_put_task(req->task, 1);
 		list_add(&req->compl.list, &cs->locked_free_list);
 		cs->locked_free_nr++;
-	} else
-		req = NULL;
+	} else {
+		if (!percpu_ref_tryget(&ctx->refs))
+			req = NULL;
+	}
 	io_commit_cqring(ctx);
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
-	io_cqring_ev_posted(ctx);
 
-	if (req)
+	if (req) {
+		io_cqring_ev_posted(ctx);
 		percpu_ref_put(&ctx->refs);
+	}
 }
 
 static void io_req_complete_state(struct io_kiocb *req, long res,
@@ -8373,11 +8376,13 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 {
 	/*
 	 * Some may use context even when all refs and requests have been put,
-	 * and they are free to do so while still holding uring_lock, see
-	 * __io_req_task_submit(). Wait for them to finish.
+	 * and they are free to do so while still holding uring_lock or
+	 * completion_lock, see __io_req_task_submit(). Wait for them to finish.
 	 */
 	mutex_lock(&ctx->uring_lock);
 	mutex_unlock(&ctx->uring_lock);
+	spin_lock_irq(&ctx->completion_lock);
+	spin_unlock_irq(&ctx->completion_lock);
 
 	io_sq_thread_finish(ctx);
 	io_sqe_buffers_unregister(ctx);

From 09a6f4efaa6536e760385f949e24078fd78305ad Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sun, 14 Mar 2021 20:57:10 +0000
Subject: [PATCH 0827/1820] io_uring: replace sqd rw_semaphore with mutex

The only user of read-locking of sqd->rw_lock is sq_thread itself, which
is by definition alone, so we don't really need rw_semaphore, but mutex
will do. Replace it with a mutex, and kill read-to-write upgrading and
extra task_work handling in io_sq_thread().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 36 ++++++++++++++----------------------
 1 file changed, 14 insertions(+), 22 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index f8a683607b25..6de779aafd33 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -258,7 +258,7 @@ enum {
 
 struct io_sq_data {
 	refcount_t		refs;
-	struct rw_semaphore	rw_lock;
+	struct mutex		lock;
 
 	/* ctx's that are using this sqd */
 	struct list_head	ctx_list;
@@ -6689,16 +6689,15 @@ static int io_sq_thread(void *data)
 		set_cpus_allowed_ptr(current, cpu_online_mask);
 	current->flags |= PF_NO_SETAFFINITY;
 
-	down_read(&sqd->rw_lock);
-
+	mutex_lock(&sqd->lock);
 	while (!test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)) {
 		int ret;
 		bool cap_entries, sqt_spin, needs_sched;
 
 		if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) {
-			up_read(&sqd->rw_lock);
+			mutex_unlock(&sqd->lock);
 			cond_resched();
-			down_read(&sqd->rw_lock);
+			mutex_lock(&sqd->lock);
 			io_run_task_work();
 			timeout = jiffies + sqd->sq_thread_idle;
 			continue;
@@ -6745,10 +6744,10 @@ static int io_sq_thread(void *data)
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				io_ring_set_wakeup_flag(ctx);
 
-			up_read(&sqd->rw_lock);
+			mutex_unlock(&sqd->lock);
 			schedule();
 			try_to_freeze();
-			down_read(&sqd->rw_lock);
+			mutex_lock(&sqd->lock);
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				io_ring_clear_wakeup_flag(ctx);
 		}
@@ -6756,20 +6755,13 @@ static int io_sq_thread(void *data)
 		finish_wait(&sqd->wait, &wait);
 		timeout = jiffies + sqd->sq_thread_idle;
 	}
-	up_read(&sqd->rw_lock);
-	down_write(&sqd->rw_lock);
-	/*
-	 * someone may have parked and added a cancellation task_work, run
-	 * it first because we don't want it in io_uring_cancel_sqpoll()
-	 */
-	io_run_task_work();
 
 	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 		io_uring_cancel_sqpoll(ctx);
 	sqd->thread = NULL;
 	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 		io_ring_set_wakeup_flag(ctx);
-	up_write(&sqd->rw_lock);
+	mutex_unlock(&sqd->lock);
 
 	io_run_task_work();
 	complete(&sqd->exited);
@@ -7071,21 +7063,21 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 }
 
 static void io_sq_thread_unpark(struct io_sq_data *sqd)
-	__releases(&sqd->rw_lock)
+	__releases(&sqd->lock)
 {
 	WARN_ON_ONCE(sqd->thread == current);
 
 	clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
-	up_write(&sqd->rw_lock);
+	mutex_unlock(&sqd->lock);
 }
 
 static void io_sq_thread_park(struct io_sq_data *sqd)
-	__acquires(&sqd->rw_lock)
+	__acquires(&sqd->lock)
 {
 	WARN_ON_ONCE(sqd->thread == current);
 
 	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
-	down_write(&sqd->rw_lock);
+	mutex_lock(&sqd->lock);
 	/* set again for consistency, in case concurrent parks are happening */
 	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
 	if (sqd->thread)
@@ -7096,11 +7088,11 @@ static void io_sq_thread_stop(struct io_sq_data *sqd)
 {
 	WARN_ON_ONCE(sqd->thread == current);
 
-	down_write(&sqd->rw_lock);
+	mutex_lock(&sqd->lock);
 	set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
 	if (sqd->thread)
 		wake_up_process(sqd->thread);
-	up_write(&sqd->rw_lock);
+	mutex_unlock(&sqd->lock);
 	wait_for_completion(&sqd->exited);
 }
 
@@ -7182,7 +7174,7 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
 
 	refcount_set(&sqd->refs, 1);
 	INIT_LIST_HEAD(&sqd->ctx_list);
-	init_rwsem(&sqd->rw_lock);
+	mutex_init(&sqd->lock);
 	init_waitqueue_head(&sqd->wait);
 	init_completion(&sqd->exited);
 	return sqd;

From f6d54255f4235448d4bbe442362d4caa62da97d5 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sun, 14 Mar 2021 20:57:11 +0000
Subject: [PATCH 0828/1820] io_uring: halt SQO submission on ctx exit

io_sq_thread_finish() is called in io_ring_ctx_free(), so SQPOLL task is
potentially running submitting new requests. It's not a disaster because
of using a "try" variant of percpu_ref_get, but is far from nice.

Remove ctx from the sqd ctx list earlier, before cancellation loop, so
SQPOLL can't find it and so won't submit new requests.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 6de779aafd33..b87012a21775 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8564,6 +8564,14 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 		io_unregister_personality(ctx, index);
 	mutex_unlock(&ctx->uring_lock);
 
+	/* prevent SQPOLL from submitting new requests */
+	if (ctx->sq_data) {
+		io_sq_thread_park(ctx->sq_data);
+		list_del_init(&ctx->sqd_list);
+		io_sqd_update_thread_idle(ctx->sq_data);
+		io_sq_thread_unpark(ctx->sq_data);
+	}
+
 	io_kill_timeouts(ctx, NULL, NULL);
 	io_poll_remove_all(ctx, NULL, NULL);
 

From 9e138a48345427fa42f6076396ea069cebf3c08f Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sun, 14 Mar 2021 20:57:12 +0000
Subject: [PATCH 0829/1820] io_uring: fix concurrent parking

If io_sq_thread_park() of one task got rescheduled right after
set_bit(), before it gets back to mutex_lock() there can happen
park()/unpark() by another task with SQPOLL locking again and
continuing running never seeing that first set_bit(SHOULD_PARK),
so won't even try to put the mutex down for parking.

It will get parked eventually when SQPOLL drops the lock for reschedule,
but may be problematic and will get in the way of further fixes.

Account number of tasks waiting for parking with a new atomic variable
park_pending and adjust SHOULD_PARK accordingly. It doesn't entirely
replaces SHOULD_PARK bit with this atomic var because it's convenient
to have it as a bit in the state and will help to do optimisations
later.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index b87012a21775..70ceb8ed5950 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -258,6 +258,7 @@ enum {
 
 struct io_sq_data {
 	refcount_t		refs;
+	atomic_t		park_pending;
 	struct mutex		lock;
 
 	/* ctx's that are using this sqd */
@@ -7067,7 +7068,13 @@ static void io_sq_thread_unpark(struct io_sq_data *sqd)
 {
 	WARN_ON_ONCE(sqd->thread == current);
 
+	/*
+	 * Do the dance but not conditional clear_bit() because it'd race with
+	 * other threads incrementing park_pending and setting the bit.
+	 */
 	clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
+	if (atomic_dec_return(&sqd->park_pending))
+		set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
 	mutex_unlock(&sqd->lock);
 }
 
@@ -7076,10 +7083,9 @@ static void io_sq_thread_park(struct io_sq_data *sqd)
 {
 	WARN_ON_ONCE(sqd->thread == current);
 
+	atomic_inc(&sqd->park_pending);
 	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
 	mutex_lock(&sqd->lock);
-	/* set again for consistency, in case concurrent parks are happening */
-	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
 	if (sqd->thread)
 		wake_up_process(sqd->thread);
 }
@@ -7099,6 +7105,8 @@ static void io_sq_thread_stop(struct io_sq_data *sqd)
 static void io_put_sq_data(struct io_sq_data *sqd)
 {
 	if (refcount_dec_and_test(&sqd->refs)) {
+		WARN_ON_ONCE(atomic_read(&sqd->park_pending));
+
 		io_sq_thread_stop(sqd);
 		kfree(sqd);
 	}
@@ -7172,6 +7180,7 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
 	if (!sqd)
 		return ERR_PTR(-ENOMEM);
 
+	atomic_set(&sqd->park_pending, 0);
 	refcount_set(&sqd->refs, 1);
 	INIT_LIST_HEAD(&sqd->ctx_list);
 	mutex_init(&sqd->lock);

From 9b46571142e47503ed4f3ae3be5ed3968d8cb9cc Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Mon, 15 Mar 2021 14:23:07 +0000
Subject: [PATCH 0830/1820] io_uring: add generic callback_head helpers

We already have helpers to run/add callback_head but taking ctx and
working with ctx->exit_task_work. Extract generic versions of them
implemented in terms of struct callback_head, it will be used later.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 62 ++++++++++++++++++++++++++++++---------------------
 1 file changed, 36 insertions(+), 26 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 70ceb8ed5950..5c2de43b99f5 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1929,17 +1929,44 @@ static int io_req_task_work_add(struct io_kiocb *req)
 	return ret;
 }
 
+static bool io_run_task_work_head(struct callback_head **work_head)
+{
+	struct callback_head *work, *next;
+	bool executed = false;
+
+	do {
+		work = xchg(work_head, NULL);
+		if (!work)
+			break;
+
+		do {
+			next = work->next;
+			work->func(work);
+			work = next;
+			cond_resched();
+		} while (work);
+		executed = true;
+	} while (1);
+
+	return executed;
+}
+
+static void io_task_work_add_head(struct callback_head **work_head,
+				  struct callback_head *task_work)
+{
+	struct callback_head *head;
+
+	do {
+		head = READ_ONCE(*work_head);
+		task_work->next = head;
+	} while (cmpxchg(work_head, head, task_work) != head);
+}
+
 static void io_req_task_work_add_fallback(struct io_kiocb *req,
 					  task_work_func_t cb)
 {
-	struct io_ring_ctx *ctx = req->ctx;
-	struct callback_head *head;
-
 	init_task_work(&req->task_work, cb);
-	do {
-		head = READ_ONCE(ctx->exit_task_work);
-		req->task_work.next = head;
-	} while (cmpxchg(&ctx->exit_task_work, head, &req->task_work) != head);
+	io_task_work_add_head(&req->ctx->exit_task_work, &req->task_work);
 }
 
 static void __io_req_task_cancel(struct io_kiocb *req, int error)
@@ -8471,26 +8498,9 @@ static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
 	return -EINVAL;
 }
 
-static bool io_run_ctx_fallback(struct io_ring_ctx *ctx)
+static inline bool io_run_ctx_fallback(struct io_ring_ctx *ctx)
 {
-	struct callback_head *work, *next;
-	bool executed = false;
-
-	do {
-		work = xchg(&ctx->exit_task_work, NULL);
-		if (!work)
-			break;
-
-		do {
-			next = work->next;
-			work->func(work);
-			work = next;
-			cond_resched();
-		} while (work);
-		executed = true;
-	} while (1);
-
-	return executed;
+	return io_run_task_work_head(&ctx->exit_task_work);
 }
 
 struct io_tctx_exit {

From b7f5a0bfe2061b2c7b2164de06fa4072d7373a45 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Mon, 15 Mar 2021 14:23:08 +0000
Subject: [PATCH 0831/1820] io_uring: fix sqpoll cancellation via task_work

Running sqpoll cancellations via task_work_run() is a bad idea because
it depends on other task works to be run, but those may be locked in
currently running task_work_run() because of how it's (splicing the list
in batches).

Enqueue and run them through a separate callback head, namely
struct io_sq_data::park_task_work. As a nice bonus we now precisely
control where it's run, that's much safer than guessing where it can
happen as it was before.

Reported-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5c2de43b99f5..5f4e312111ea 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -274,6 +274,7 @@ struct io_sq_data {
 
 	unsigned long		state;
 	struct completion	exited;
+	struct callback_head	*park_task_work;
 };
 
 #define IO_IOPOLL_BATCH			8
@@ -6727,6 +6728,7 @@ static int io_sq_thread(void *data)
 			cond_resched();
 			mutex_lock(&sqd->lock);
 			io_run_task_work();
+			io_run_task_work_head(&sqd->park_task_work);
 			timeout = jiffies + sqd->sq_thread_idle;
 			continue;
 		}
@@ -6781,6 +6783,7 @@ static int io_sq_thread(void *data)
 		}
 
 		finish_wait(&sqd->wait, &wait);
+		io_run_task_work_head(&sqd->park_task_work);
 		timeout = jiffies + sqd->sq_thread_idle;
 	}
 
@@ -6792,6 +6795,7 @@ static int io_sq_thread(void *data)
 	mutex_unlock(&sqd->lock);
 
 	io_run_task_work();
+	io_run_task_work_head(&sqd->park_task_work);
 	complete(&sqd->exited);
 	do_exit(0);
 }
@@ -8890,7 +8894,7 @@ static void io_sqpoll_cancel_sync(struct io_ring_ctx *ctx)
 	if (task) {
 		init_completion(&work.completion);
 		init_task_work(&work.task_work, io_sqpoll_cancel_cb);
-		WARN_ON_ONCE(task_work_add(task, &work.task_work, TWA_SIGNAL));
+		io_task_work_add_head(&sqd->park_task_work, &work.task_work);
 		wake_up_process(task);
 	}
 	io_sq_thread_unpark(sqd);

From 3b6e7088afc919f5b52e4d2de8501ad34d35b09b Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 12 Mar 2021 14:02:40 +0100
Subject: [PATCH 0832/1820] regulator: bd9571mwv: Fix AVS and DVFS voltage
 range

According to Table 30 ("DVFS_MoniVDAC [6:0] Setting Table") in the
BD9571MWV-M Datasheet Rev. 002, the valid voltage range is 600..1100 mV
(settings 0x3c..0x6e).  While the lower limit is taken into account (by
setting regulator_desc.linear_min_sel to 0x3c), the upper limit is not.

Fix this by reducing regulator_desc.n_voltages from 0x80 to 0x6f.

Fixes: e85c5a153fe237f2 ("regulator: Add ROHM BD9571MWV-M PMIC regulator driver")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20210312130242.3390038-2-geert+renesas@glider.be
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bd9571mwv-regulator.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c
index 7b0cd08db446..13393cdc6be1 100644
--- a/drivers/regulator/bd9571mwv-regulator.c
+++ b/drivers/regulator/bd9571mwv-regulator.c
@@ -125,7 +125,7 @@ static const struct regulator_ops vid_ops = {
 
 static const struct regulator_desc regulators[] = {
 	BD9571MWV_REG("VD09", "vd09", VD09, avs_ops, 0, 0x7f,
-		      0x80, 600000, 10000, 0x3c),
+		      0x6f, 600000, 10000, 0x3c),
 	BD9571MWV_REG("VD18", "vd18", VD18, vid_ops, BD9571MWV_VD18_VID, 0xf,
 		      16, 1625000, 25000, 0),
 	BD9571MWV_REG("VD25", "vd25", VD25, vid_ops, BD9571MWV_VD25_VID, 0xf,
@@ -134,7 +134,7 @@ static const struct regulator_desc regulators[] = {
 		      11, 2800000, 100000, 0),
 	BD9571MWV_REG("DVFS", "dvfs", DVFS, reg_ops,
 		      BD9571MWV_DVFS_MONIVDAC, 0x7f,
-		      0x80, 600000, 10000, 0x3c),
+		      0x6f, 600000, 10000, 0x3c),
 };
 
 #ifdef CONFIG_PM_SLEEP

From 9cbc23f7d51fb0b1363bdfdd0b770aa7b5982f2f Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 12 Mar 2021 14:02:41 +0100
Subject: [PATCH 0833/1820] regulator: bd9571mwv: Fix regulator name printed on
 registration failure

If a regulator fails to register, the driver prints an error message
like:

    bd9571mwv-regulator bd9571mwv-regulator.6.auto: failed to register bd9571mwv-regulator regulator

However, the platform device's name is already printed as part of
dev_err(), and does not allow the user to distinguish among the various
regulators that are part of the PMIC.

Fix this by printing regulator_desc.name instead, to change the message
like:

    bd9571mwv-regulator bd9571mwv-regulator.6.auto: failed to register DVFS regulator

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Link: https://lore.kernel.org/r/20210312130242.3390038-3-geert+renesas@glider.be
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bd9571mwv-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c
index 13393cdc6be1..a4d406022587 100644
--- a/drivers/regulator/bd9571mwv-regulator.c
+++ b/drivers/regulator/bd9571mwv-regulator.c
@@ -301,7 +301,7 @@ static int bd9571mwv_regulator_probe(struct platform_device *pdev)
 					       &config);
 		if (IS_ERR(rdev)) {
 			dev_err(&pdev->dev, "failed to register %s regulator\n",
-				pdev->name);
+				regulators[i].name);
 			return PTR_ERR(rdev);
 		}
 	}

From 1deceabbdc0dd3162def1e26acb2e57a93275909 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 12 Mar 2021 14:02:42 +0100
Subject: [PATCH 0834/1820] regulator: bd9571mwv: Convert device attribute to
 sysfs_emit()

Convert the "backup_mode" device attribute from sprintf() to
sysfs_emit(), as the latter is aware of the PAGE_SIZE buffer.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20210312130242.3390038-4-geert+renesas@glider.be
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bd9571mwv-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c
index a4d406022587..ba020a45f238 100644
--- a/drivers/regulator/bd9571mwv-regulator.c
+++ b/drivers/regulator/bd9571mwv-regulator.c
@@ -174,7 +174,7 @@ static ssize_t backup_mode_show(struct device *dev,
 {
 	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%s\n", bdreg->bkup_mode_enabled ? "on" : "off");
+	return sysfs_emit(buf, "%s\n", bdreg->bkup_mode_enabled ? "on" : "off");
 }
 
 static ssize_t backup_mode_store(struct device *dev,

From d336f7ebc65007f5831e2297e6f3383ae8dbf8ed Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 2 Mar 2021 09:32:53 -0800
Subject: [PATCH 0835/1820] xfs: force log and push AIL to clear pinned inodes
 when aborting mount

If we allocate quota inodes in the process of mounting a filesystem but
then decide to abort the mount, it's possible that the quota inodes are
sitting around pinned by the log.  Now that inode reclaim relies on the
AIL to flush inodes, we have to force the log and push the AIL in
between releasing the quota inodes and kicking off reclaim to tear down
all the incore inodes.  Do this by extracting the bits we need from the
unmount path and reusing them.  As an added bonus, failed writes during
a failed mount will not retry forever now.

This was originally found during a fuzz test of metadata directories
(xfs/1546), but the actual symptom was that reclaim hung up on the quota
inodes.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/xfs_mount.c | 90 +++++++++++++++++++++++-----------------------
 1 file changed, 44 insertions(+), 46 deletions(-)

diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 52370d0a3f43..1c97b155a8ee 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -634,6 +634,47 @@ xfs_check_summary_counts(
 	return xfs_initialize_perag_data(mp, mp->m_sb.sb_agcount);
 }
 
+/*
+ * Flush and reclaim dirty inodes in preparation for unmount. Inodes and
+ * internal inode structures can be sitting in the CIL and AIL at this point,
+ * so we need to unpin them, write them back and/or reclaim them before unmount
+ * can proceed.
+ *
+ * An inode cluster that has been freed can have its buffer still pinned in
+ * memory because the transaction is still sitting in a iclog. The stale inodes
+ * on that buffer will be pinned to the buffer until the transaction hits the
+ * disk and the callbacks run. Pushing the AIL will skip the stale inodes and
+ * may never see the pinned buffer, so nothing will push out the iclog and
+ * unpin the buffer.
+ *
+ * Hence we need to force the log to unpin everything first. However, log
+ * forces don't wait for the discards they issue to complete, so we have to
+ * explicitly wait for them to complete here as well.
+ *
+ * Then we can tell the world we are unmounting so that error handling knows
+ * that the filesystem is going away and we should error out anything that we
+ * have been retrying in the background.  This will prevent never-ending
+ * retries in AIL pushing from hanging the unmount.
+ *
+ * Finally, we can push the AIL to clean all the remaining dirty objects, then
+ * reclaim the remaining inodes that are still in memory at this point in time.
+ */
+static void
+xfs_unmount_flush_inodes(
+	struct xfs_mount	*mp)
+{
+	xfs_log_force(mp, XFS_LOG_SYNC);
+	xfs_extent_busy_wait_all(mp);
+	flush_workqueue(xfs_discard_wq);
+
+	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
+
+	xfs_ail_push_all_sync(mp->m_ail);
+	cancel_delayed_work_sync(&mp->m_reclaim_work);
+	xfs_reclaim_inodes(mp);
+	xfs_health_unmount(mp);
+}
+
 /*
  * This function does the following on an initial mount of a file system:
  *	- reads the superblock from disk and init the mount struct
@@ -1008,7 +1049,7 @@ xfs_mountfs(
 	/* Clean out dquots that might be in memory after quotacheck. */
 	xfs_qm_unmount(mp);
 	/*
-	 * Cancel all delayed reclaim work and reclaim the inodes directly.
+	 * Flush all inode reclamation work and flush the log.
 	 * We have to do this /after/ rtunmount and qm_unmount because those
 	 * two will have scheduled delayed reclaim for the rt/quota inodes.
 	 *
@@ -1018,11 +1059,8 @@ xfs_mountfs(
 	 * qm_unmount_quotas and therefore rely on qm_unmount to release the
 	 * quota inodes.
 	 */
-	cancel_delayed_work_sync(&mp->m_reclaim_work);
-	xfs_reclaim_inodes(mp);
-	xfs_health_unmount(mp);
+	xfs_unmount_flush_inodes(mp);
  out_log_dealloc:
-	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
 	xfs_log_mount_cancel(mp);
  out_fail_wait:
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
@@ -1063,47 +1101,7 @@ xfs_unmountfs(
 	xfs_rtunmount_inodes(mp);
 	xfs_irele(mp->m_rootip);
 
-	/*
-	 * We can potentially deadlock here if we have an inode cluster
-	 * that has been freed has its buffer still pinned in memory because
-	 * the transaction is still sitting in a iclog. The stale inodes
-	 * on that buffer will be pinned to the buffer until the
-	 * transaction hits the disk and the callbacks run. Pushing the AIL will
-	 * skip the stale inodes and may never see the pinned buffer, so
-	 * nothing will push out the iclog and unpin the buffer. Hence we
-	 * need to force the log here to ensure all items are flushed into the
-	 * AIL before we go any further.
-	 */
-	xfs_log_force(mp, XFS_LOG_SYNC);
-
-	/*
-	 * Wait for all busy extents to be freed, including completion of
-	 * any discard operation.
-	 */
-	xfs_extent_busy_wait_all(mp);
-	flush_workqueue(xfs_discard_wq);
-
-	/*
-	 * We now need to tell the world we are unmounting. This will allow
-	 * us to detect that the filesystem is going away and we should error
-	 * out anything that we have been retrying in the background. This will
-	 * prevent neverending retries in AIL pushing from hanging the unmount.
-	 */
-	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
-
-	/*
-	 * Flush all pending changes from the AIL.
-	 */
-	xfs_ail_push_all_sync(mp->m_ail);
-
-	/*
-	 * Reclaim all inodes. At this point there should be no dirty inodes and
-	 * none should be pinned or locked. Stop background inode reclaim here
-	 * if it is still running.
-	 */
-	cancel_delayed_work_sync(&mp->m_reclaim_work);
-	xfs_reclaim_inodes(mp);
-	xfs_health_unmount(mp);
+	xfs_unmount_flush_inodes(mp);
 
 	xfs_qm_unmount(mp);
 

From 08a204387e8063ba7375481281701137bd553dee Mon Sep 17 00:00:00 2001
From: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Date: Tue, 9 Mar 2021 09:45:51 -0800
Subject: [PATCH 0836/1820] docs: ABI: Fix the spelling oustanding to
 outstanding in the file sysfs-fs-xfs

s/oustanding/outstanding/

Signed-off-by: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 Documentation/ABI/testing/sysfs-fs-xfs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/ABI/testing/sysfs-fs-xfs b/Documentation/ABI/testing/sysfs-fs-xfs
index ea0cc8c42093..f704925f6fe9 100644
--- a/Documentation/ABI/testing/sysfs-fs-xfs
+++ b/Documentation/ABI/testing/sysfs-fs-xfs
@@ -33,7 +33,7 @@ Contact:	xfs@oss.sgi.com
 Description:
 		The current state of the log write grant head. It
 		represents the total log reservation of all currently
-		oustanding transactions, including regrants due to
+		outstanding transactions, including regrants due to
 		rolling transactions. The grant head is exported in
 		"cycle:bytes" format.
 Users:		xfstests

From 8723d5ba8bdae1c41be7a6fc8469dc9aa551e7d0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 14 Mar 2021 10:59:39 -0700
Subject: [PATCH 0837/1820] xfs: also reject BULKSTAT_SINGLE in a mount user
 namespace

BULKSTAT_SINGLE exposed the ondisk uids/gids just like bulkstat, and can
be called on any inode, including ones not visible in the current mount.

Fixes: f736d93d76d3 ("xfs: support idmapped mounts")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_itable.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index ca310a125d1e..3498b97fb06d 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -168,6 +168,12 @@ xfs_bulkstat_one(
 	};
 	int			error;
 
+	if (breq->mnt_userns != &init_user_ns) {
+		xfs_warn_ratelimited(breq->mp,
+			"bulkstat not supported inside of idmapped mounts.");
+		return -EINVAL;
+	}
+
 	ASSERT(breq->icount == 1);
 
 	bc.buf = kmem_zalloc(sizeof(struct xfs_bulkstat),

From d2dcc8ed8ec650a793e81d8b2222146eb6ddd84f Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 8 Mar 2021 17:20:17 +0800
Subject: [PATCH 0838/1820] btrfs: fix wrong offset to zero out range beyond
 i_size

[BUG]
The test generic/091 fails , with the following output:

  fsx -N 10000 -o 128000 -l 500000 -r PSIZE -t BSIZE -w BSIZE -Z -W
  mapped writes DISABLED
  Seed set to 1
  main: filesystem does not support fallocate mode FALLOC_FL_COLLAPSE_RANGE, disabling!
  main: filesystem does not support fallocate mode FALLOC_FL_INSERT_RANGE, disabling!
  skipping zero size read
  truncating to largest ever: 0xe400
  copying to largest ever: 0x1f400
  cloning to largest ever: 0x70000
  cloning to largest ever: 0x77000
  fallocating to largest ever: 0x7a120
  Mapped Read: non-zero data past EOF (0x3a7ff) page offset 0x800 is 0xf2e1 <<<
  ...

[CAUSE]
In commit c28ea613fafa ("btrfs: subpage: fix the false data csum mismatch error")
end_bio_extent_readpage() changes to only zero the range inside the bvec
for incoming subpage support.

But that commit is using incorrect offset to calculate the start.

For subpage, we can have a case that the whole bvec is beyond isize,
thus we need to calculate the correct offset.

But the offending commit is using @end (bvec end), other than @start
(bvec start) to calculate the start offset.

This means, we only zero the last byte of the bvec, not from the isize.
This stupid bug makes the range beyond isize is not properly zeroed, and
failed above test.

[FIX]
Use correct @start to calculate the range start.

Reported-by: kernel test robot <oliver.sang@intel.com>
Fixes: c28ea613fafa ("btrfs: subpage: fix the false data csum mismatch error")
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4671c99d468d..f3d7be975c3a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3020,7 +3020,7 @@ readpage_ok:
 			 */
 			if (page->index == end_index && i_size <= end) {
 				u32 zero_start = max(offset_in_page(i_size),
-						     offset_in_page(end));
+						     offset_in_page(start));
 
 				zero_user_segment(page, zero_start,
 						  offset_in_page(end) + 1);

From fbf48bb0b197e6894a04c714728c952af7153bf3 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 3 Mar 2021 18:41:51 +0800
Subject: [PATCH 0839/1820] btrfs: track qgroup released data in own variable
 in insert_prealloc_file_extent

There is a piece of weird code in insert_prealloc_file_extent(), which
looks like:

	ret = btrfs_qgroup_release_data(inode, file_offset, len);
	if (ret < 0)
		return ERR_PTR(ret);
	if (trans) {
		ret = insert_reserved_file_extent(trans, inode,
						  file_offset, &stack_fi,
						  true, ret);
	...
	}
	extent_info.is_new_extent = true;
	extent_info.qgroup_reserved = ret;
	...

Note how the variable @ret is abused here, and if anyone is adding code
just after btrfs_qgroup_release_data() call, it's super easy to
overwrite the @ret and cause tons of qgroup related bugs.

Fix such abuse by introducing new variable @qgroup_released, so that we
won't reuse the existing variable @ret.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c35b724a5611..77182be403c5 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9873,6 +9873,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 	struct btrfs_path *path;
 	u64 start = ins->objectid;
 	u64 len = ins->offset;
+	int qgroup_released;
 	int ret;
 
 	memset(&stack_fi, 0, sizeof(stack_fi));
@@ -9885,14 +9886,14 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 	btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE);
 	/* Encryption and other encoding is reserved and all 0 */
 
-	ret = btrfs_qgroup_release_data(inode, file_offset, len);
-	if (ret < 0)
-		return ERR_PTR(ret);
+	qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len);
+	if (qgroup_released < 0)
+		return ERR_PTR(qgroup_released);
 
 	if (trans) {
 		ret = insert_reserved_file_extent(trans, inode,
 						  file_offset, &stack_fi,
-						  true, ret);
+						  true, qgroup_released);
 		if (ret)
 			return ERR_PTR(ret);
 		return trans;
@@ -9905,7 +9906,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 	extent_info.file_offset = file_offset;
 	extent_info.extent_buf = (char *)&stack_fi;
 	extent_info.is_new_extent = true;
-	extent_info.qgroup_reserved = ret;
+	extent_info.qgroup_reserved = qgroup_released;
 	extent_info.insertions = 0;
 
 	path = btrfs_alloc_path();

From a3ee79bd8fe17812d2305ccc4bf81bfeab395576 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 3 Mar 2021 18:41:52 +0800
Subject: [PATCH 0840/1820] btrfs: fix qgroup data rsv leak caused by falloc
 failure

[BUG]
When running fsstress with only falloc workload, and a very low qgroup
limit set, we can get qgroup data rsv leak at unmount time.

 BTRFS warning (device dm-0): qgroup 0/5 has unreleased space, type 0 rsv 20480
 BTRFS error (device dm-0): qgroup reserved space leaked

The minimal reproducer looks like:

  #!/bin/bash
  dev=/dev/test/test
  mnt="/mnt/btrfs"
  fsstress=~/xfstests-dev/ltp/fsstress
  runtime=8

  workload()
  {
          umount $dev &> /dev/null
          umount $mnt &> /dev/null
          mkfs.btrfs -f $dev > /dev/null
          mount $dev $mnt

          btrfs quota en $mnt
          btrfs quota rescan -w $mnt
          btrfs qgroup limit 16m 0/5 $mnt

          $fsstress -w -z -f creat=10 -f fallocate=10 -p 2 -n 100 \
  		-d $mnt -v > /tmp/fsstress

          umount $mnt
          if dmesg | grep leak ; then
		echo "!!! FAILED !!!"
  		exit 1
          fi
  }

  for (( i=0; i < $runtime; i++)); do
          echo "=== $i/$runtime==="
          workload
  done

Normally it would fail before round 4.

[CAUSE]
In function insert_prealloc_file_extent(), we first call
btrfs_qgroup_release_data() to know how many bytes are reserved for
qgroup data rsv.

Then use that @qgroup_released number to continue our work.

But after we call btrfs_qgroup_release_data(), we should either queue
@qgroup_released to delayed ref or free them manually in error path.

Unfortunately, we lack the error handling to free the released bytes,
leaking qgroup data rsv.

All the error handling function outside won't help at all, as we have
released the range, meaning in inode io tree, the EXTENT_QGROUP_RESERVED
bit is already cleared, thus all btrfs_qgroup_free_data() call won't
free any data rsv.

[FIX]
Add free_qgroup tag to manually free the released qgroup data rsv.

Reported-by: Nikolay Borisov <nborisov@suse.com>
Reported-by: David Sterba <dsterba@suse.cz>
Fixes: 9729f10a608f ("btrfs: inode: move qgroup reserved space release to the callers of insert_reserved_file_extent()")
CC: stable@vger.kernel.org # 5.10+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 77182be403c5..ea5ede619220 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9895,7 +9895,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 						  file_offset, &stack_fi,
 						  true, qgroup_released);
 		if (ret)
-			return ERR_PTR(ret);
+			goto free_qgroup;
 		return trans;
 	}
 
@@ -9910,17 +9910,31 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 	extent_info.insertions = 0;
 
 	path = btrfs_alloc_path();
-	if (!path)
-		return ERR_PTR(-ENOMEM);
+	if (!path) {
+		ret = -ENOMEM;
+		goto free_qgroup;
+	}
 
 	ret = btrfs_replace_file_extents(&inode->vfs_inode, path, file_offset,
 				     file_offset + len - 1, &extent_info,
 				     &trans);
 	btrfs_free_path(path);
 	if (ret)
-		return ERR_PTR(ret);
-
+		goto free_qgroup;
 	return trans;
+
+free_qgroup:
+	/*
+	 * We have released qgroup data range at the beginning of the function,
+	 * and normally qgroup_released bytes will be freed when committing
+	 * transaction.
+	 * But if we error out early, we have to free what we have released
+	 * or we leak qgroup data reservation.
+	 */
+	btrfs_qgroup_free_refroot(inode->root->fs_info,
+			inode->root->root_key.objectid, qgroup_released,
+			BTRFS_QGROUP_RSV_DATA);
+	return ERR_PTR(ret);
 }
 
 static int __btrfs_prealloc_file_range(struct inode *inode, int mode,

From e3d3b4157610164b0ec43d968b0dfedfe7c68992 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 11 Mar 2021 15:13:30 +0000
Subject: [PATCH 0841/1820] btrfs: zoned: fix linked list corruption after log
 root tree allocation failure

When using a zoned filesystem, while syncing the log, if we fail to
allocate the root node for the log root tree, we are not removing the
log context we allocated on stack from the list of log contexts of the
log root tree. This means after the return from btrfs_sync_log() we get
a corrupted linked list.

Fix this by allocating the node before adding our stack allocated context
to the list of log contexts of the log root tree.

Fixes: 3ddebf27fcd3a9 ("btrfs: zoned: reorder log node allocation on zoned filesystem")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 2f1acc9aea9e..92a368627791 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3169,10 +3169,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 
 	mutex_lock(&log_root_tree->log_mutex);
 
-	index2 = log_root_tree->log_transid % 2;
-	list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
-	root_log_ctx.log_transid = log_root_tree->log_transid;
-
 	if (btrfs_is_zoned(fs_info)) {
 		if (!log_root_tree->node) {
 			ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
@@ -3183,6 +3179,10 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		}
 	}
 
+	index2 = log_root_tree->log_transid % 2;
+	list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
+	root_log_ctx.log_transid = log_root_tree->log_transid;
+
 	/*
 	 * Now we are safe to update the log_root_tree because we're under the
 	 * log_mutex, and we're a current writer so we're holding the commit

From 31254dc9566221429d2cfb45fd5737985d70f2b6 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 9 Mar 2021 11:22:14 +0800
Subject: [PATCH 0842/1820] selftests/bpf: Set gopt opt_class to 0 if get
 tunnel opt failed

When fixing the bpf test_tunnel.sh geneve failure. I only fixed the IPv4
part but forgot the IPv6 issue. Similar with the IPv4 fixes 557c223b643a
("selftests/bpf: No need to drop the packet when there is no geneve opt"),
when there is no tunnel option and bpf_skb_get_tunnel_opt() returns error,
there is no need to drop the packets and break all geneve rx traffic.
Just set opt_class to 0 and keep returning TC_ACT_OK at the end.

Fixes: 557c223b643a ("selftests/bpf: No need to drop the packet when there is no geneve opt")
Fixes: 933a741e3b82 ("selftests/bpf: bpf tunnel test.")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: William Tu <u9012063@gmail.com>
Link: https://lore.kernel.org/bpf/20210309032214.2112438-1-liuhangbin@gmail.com
---
 tools/testing/selftests/bpf/progs/test_tunnel_kern.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 9afe947cfae9..ba6eadfec565 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -508,10 +508,8 @@ int _ip6geneve_get_tunnel(struct __sk_buff *skb)
 	}
 
 	ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
-	if (ret < 0) {
-		ERROR(ret);
-		return TC_ACT_SHOT;
-	}
+	if (ret < 0)
+		gopt.opt_class = 0;
 
 	bpf_trace_printk(fmt, sizeof(fmt),
 			key.tunnel_id, key.remote_ipv4, gopt.opt_class);

From 64fcbb6158ecc684d84c64424830a9c37c77c5b9 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 2 Mar 2021 10:26:45 +0000
Subject: [PATCH 0843/1820] afs: Fix accessing YFS xattrs on a non-YFS server

If someone attempts to access YFS-related xattrs (e.g. afs.yfs.acl) on a
file on a non-YFS AFS server (such as OpenAFS), then the kernel will jump
to a NULL function pointer because the afs_fetch_acl_operation descriptor
doesn't point to a function for issuing an operation on a non-YFS
server[1].

Fix this by making afs_wait_for_operation() check that the issue_afs_rpc
method is set before jumping to it and setting -ENOTSUPP if not.  This fix
also covers other potential operations that also only exist on YFS servers.

afs_xattr_get/set_yfs() then need to translate -ENOTSUPP to -ENODATA as the
former error is internal to the kernel.

The bug shows up as an oops like the following:

	BUG: kernel NULL pointer dereference, address: 0000000000000000
	[...]
	Code: Unable to access opcode bytes at RIP 0xffffffffffffffd6.
	[...]
	Call Trace:
	 afs_wait_for_operation+0x83/0x1b0 [kafs]
	 afs_xattr_get_yfs+0xe6/0x270 [kafs]
	 __vfs_getxattr+0x59/0x80
	 vfs_getxattr+0x11c/0x140
	 getxattr+0x181/0x250
	 ? __check_object_size+0x13f/0x150
	 ? __fput+0x16d/0x250
	 __x64_sys_fgetxattr+0x64/0xb0
	 do_syscall_64+0x49/0xc0
	 entry_SYSCALL_64_after_hwframe+0x44/0xa9
	RIP: 0033:0x7fb120a9defe

This was triggered with "cp -a" which attempts to copy xattrs, including
afs ones, but is easier to reproduce with getfattr, e.g.:

	getfattr -d -m ".*" /afs/openafs.org/

Fixes: e49c7b2f6de7 ("afs: Build an abstraction around an "operation" concept")
Reported-by: Gaja Sophie Peters <gaja.peters@math.uni-hamburg.de>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Gaja Sophie Peters <gaja.peters@math.uni-hamburg.de>
Reviewed-by: Marc Dionne <marc.dionne@auristor.com>
Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
cc: linux-afs@lists.infradead.org
Link: http://lists.infradead.org/pipermail/linux-afs/2021-March/003498.html [1]
Link: http://lists.infradead.org/pipermail/linux-afs/2021-March/003566.html # v1
Link: http://lists.infradead.org/pipermail/linux-afs/2021-March/003572.html # v2
---
 fs/afs/fs_operation.c | 7 +++++--
 fs/afs/xattr.c        | 8 +++++++-
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index 97cab12b0a6c..71c58723763d 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -181,10 +181,13 @@ void afs_wait_for_operation(struct afs_operation *op)
 		if (test_bit(AFS_SERVER_FL_IS_YFS, &op->server->flags) &&
 		    op->ops->issue_yfs_rpc)
 			op->ops->issue_yfs_rpc(op);
-		else
+		else if (op->ops->issue_afs_rpc)
 			op->ops->issue_afs_rpc(op);
+		else
+			op->ac.error = -ENOTSUPP;
 
-		op->error = afs_wait_for_call_to_complete(op->call, &op->ac);
+		if (op->call)
+			op->error = afs_wait_for_call_to_complete(op->call, &op->ac);
 	}
 
 	switch (op->error) {
diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c
index c629caae5002..4934e325a14a 100644
--- a/fs/afs/xattr.c
+++ b/fs/afs/xattr.c
@@ -231,6 +231,8 @@ static int afs_xattr_get_yfs(const struct xattr_handler *handler,
 			else
 				ret = -ERANGE;
 		}
+	} else if (ret == -ENOTSUPP) {
+		ret = -ENODATA;
 	}
 
 error_yacl:
@@ -256,6 +258,7 @@ static int afs_xattr_set_yfs(const struct xattr_handler *handler,
 {
 	struct afs_operation *op;
 	struct afs_vnode *vnode = AFS_FS_I(inode);
+	int ret;
 
 	if (flags == XATTR_CREATE ||
 	    strcmp(name, "acl") != 0)
@@ -270,7 +273,10 @@ static int afs_xattr_set_yfs(const struct xattr_handler *handler,
 		return afs_put_operation(op);
 
 	op->ops = &yfs_store_opaque_acl2_operation;
-	return afs_do_sync_operation(op);
+	ret = afs_do_sync_operation(op);
+	if (ret == -ENOTSUPP)
+		ret = -ENODATA;
+	return ret;
 }
 
 static const struct xattr_handler afs_xattr_yfs_handler = {

From a7889c6320b9200e3fe415238f546db677310fa9 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 9 Mar 2021 08:27:39 +0000
Subject: [PATCH 0844/1820] afs: Stop listxattr() from listing "afs.*"
 attributes

afs_listxattr() lists all the available special afs xattrs (i.e. those in
the "afs.*" space), no matter what type of server we're dealing with.  But
OpenAFS servers, for example, cannot deal with some of the extra-capable
attributes that AuriStor (YFS) servers provide.  Unfortunately, the
presence of the afs.yfs.* attributes causes errors[1] for anything that
tries to read them if the server is of the wrong type.

Fix the problem by removing afs_listxattr() so that none of the special
xattrs are listed (AFS doesn't support xattrs).  It does mean, however,
that getfattr won't list them, though they can still be accessed with
getxattr() and setxattr().

This can be tested with something like:

	getfattr -d -m ".*" /afs/example.com/path/to/file

With this change, none of the afs.* attributes should be visible.

Changes:
ver #2:
 - Hide all of the afs.* xattrs, not just the ACL ones.

Fixes: ae46578b963f ("afs: Get YFS ACLs and information through xattrs")
Reported-by: Gaja Sophie Peters <gaja.peters@math.uni-hamburg.de>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Gaja Sophie Peters <gaja.peters@math.uni-hamburg.de>
Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
Reviewed-by: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
Link: http://lists.infradead.org/pipermail/linux-afs/2021-March/003502.html [1]
Link: http://lists.infradead.org/pipermail/linux-afs/2021-March/003567.html # v1
Link: http://lists.infradead.org/pipermail/linux-afs/2021-March/003573.html # v2
---
 fs/afs/dir.c      |  1 -
 fs/afs/file.c     |  1 -
 fs/afs/inode.c    |  1 -
 fs/afs/internal.h |  1 -
 fs/afs/mntpt.c    |  1 -
 fs/afs/xattr.c    | 23 -----------------------
 6 files changed, 28 deletions(-)

diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 714fcca9af99..17548c1faf02 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -70,7 +70,6 @@ const struct inode_operations afs_dir_inode_operations = {
 	.permission	= afs_permission,
 	.getattr	= afs_getattr,
 	.setattr	= afs_setattr,
-	.listxattr	= afs_listxattr,
 };
 
 const struct address_space_operations afs_dir_aops = {
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 85f5adf21aa0..960b64268623 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -43,7 +43,6 @@ const struct inode_operations afs_file_inode_operations = {
 	.getattr	= afs_getattr,
 	.setattr	= afs_setattr,
 	.permission	= afs_permission,
-	.listxattr	= afs_listxattr,
 };
 
 const struct address_space_operations afs_fs_aops = {
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 1156b2df28d3..12be88716e4c 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -27,7 +27,6 @@
 
 static const struct inode_operations afs_symlink_inode_operations = {
 	.get_link	= page_get_link,
-	.listxattr	= afs_listxattr,
 };
 
 static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *parent_vnode)
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index b626e38e9ab5..1627b1872812 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -1509,7 +1509,6 @@ extern int afs_launder_page(struct page *);
  * xattr.c
  */
 extern const struct xattr_handler *afs_xattr_handlers[];
-extern ssize_t afs_listxattr(struct dentry *, char *, size_t);
 
 /*
  * yfsclient.c
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 052dab2f5c03..bbb2c210d139 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -32,7 +32,6 @@ const struct inode_operations afs_mntpt_inode_operations = {
 	.lookup		= afs_mntpt_lookup,
 	.readlink	= page_readlink,
 	.getattr	= afs_getattr,
-	.listxattr	= afs_listxattr,
 };
 
 const struct inode_operations afs_autocell_inode_operations = {
diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c
index 4934e325a14a..7751b0b3f81d 100644
--- a/fs/afs/xattr.c
+++ b/fs/afs/xattr.c
@@ -11,29 +11,6 @@
 #include <linux/xattr.h>
 #include "internal.h"
 
-static const char afs_xattr_list[] =
-	"afs.acl\0"
-	"afs.cell\0"
-	"afs.fid\0"
-	"afs.volume\0"
-	"afs.yfs.acl\0"
-	"afs.yfs.acl_inherited\0"
-	"afs.yfs.acl_num_cleaned\0"
-	"afs.yfs.vol_acl";
-
-/*
- * Retrieve a list of the supported xattrs.
- */
-ssize_t afs_listxattr(struct dentry *dentry, char *buffer, size_t size)
-{
-	if (size == 0)
-		return sizeof(afs_xattr_list);
-	if (size < sizeof(afs_xattr_list))
-		return -ERANGE;
-	memcpy(buffer, afs_xattr_list, sizeof(afs_xattr_list));
-	return sizeof(afs_xattr_list);
-}
-
 /*
  * Deal with the result of a successful fetch ACL operation.
  */

From abe7034b9a8d57737e80cc16d60ed3666990bdbf Mon Sep 17 00:00:00 2001
From: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Date: Mon, 8 Mar 2021 14:24:11 +1300
Subject: [PATCH 0845/1820] Revert "netfilter: x_tables: Update remaining
 dereference to RCU"

This reverts commit 443d6e86f821a165fae3fc3fc13086d27ac140b1.

This (and the following) patch basically re-implemented the RCU
mechanisms of patch 784544739a25. That patch was replaced because of the
performance problems that it created when replacing tables. Now, we have
the same issue: the call to synchronize_rcu() makes replacing tables
slower by as much as an order of magnitude.

Revert these patches and fix the issue in a different way.

Signed-off-by: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/arp_tables.c | 2 +-
 net/ipv4/netfilter/ip_tables.c  | 2 +-
 net/ipv6/netfilter/ip6_tables.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index c576a63d09db..563b62b76a5f 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1379,7 +1379,7 @@ static int compat_get_entries(struct net *net,
 	xt_compat_lock(NFPROTO_ARP);
 	t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = xt_table_get_private_protected(t);
+		const struct xt_table_info *private = t->private;
 		struct xt_table_info info;
 
 		ret = compat_table_info(private, &info);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index e8f6f9d86237..6e2851f8d3a3 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1589,7 +1589,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr,
 	xt_compat_lock(AF_INET);
 	t = xt_find_table_lock(net, AF_INET, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = xt_table_get_private_protected(t);
+		const struct xt_table_info *private = t->private;
 		struct xt_table_info info;
 		ret = compat_table_info(private, &info);
 		if (!ret && get.size == info.size)
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 0d453fa9e327..c4f532f4d311 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1598,7 +1598,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr,
 	xt_compat_lock(AF_INET6);
 	t = xt_find_table_lock(net, AF_INET6, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = xt_table_get_private_protected(t);
+		const struct xt_table_info *private = t->private;
 		struct xt_table_info info;
 		ret = compat_table_info(private, &info);
 		if (!ret && get.size == info.size)

From d3d40f237480abf3268956daf18cdc56edd32834 Mon Sep 17 00:00:00 2001
From: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Date: Mon, 8 Mar 2021 14:24:12 +1300
Subject: [PATCH 0846/1820] Revert "netfilter: x_tables: Switch synchronization
 to RCU"

This reverts commit cc00bcaa589914096edef7fb87ca5cee4a166b5c.

This (and the preceding) patch basically re-implemented the RCU
mechanisms of patch 784544739a25. That patch was replaced because of the
performance problems that it created when replacing tables. Now, we have
the same issue: the call to synchronize_rcu() makes replacing tables
slower by as much as an order of magnitude.

Prior to using RCU a script calling "iptables" approx. 200 times was
taking 1.16s. With RCU this increased to 11.59s.

Revert these patches and fix the issue in a different way.

Signed-off-by: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/x_tables.h |  5 +--
 net/ipv4/netfilter/arp_tables.c    | 14 ++++-----
 net/ipv4/netfilter/ip_tables.c     | 14 ++++-----
 net/ipv6/netfilter/ip6_tables.c    | 14 ++++-----
 net/netfilter/x_tables.c           | 49 +++++++++++++++++++++---------
 5 files changed, 56 insertions(+), 40 deletions(-)

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 8ebb64193757..5deb099d156d 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -227,7 +227,7 @@ struct xt_table {
 	unsigned int valid_hooks;
 
 	/* Man behind the curtain... */
-	struct xt_table_info __rcu *private;
+	struct xt_table_info *private;
 
 	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
 	struct module *me;
@@ -448,9 +448,6 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu)
 
 struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *);
 
-struct xt_table_info
-*xt_table_get_private_protected(const struct xt_table *table);
-
 #ifdef CONFIG_COMPAT
 #include <net/compat.h>
 
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 563b62b76a5f..d1e04d2b5170 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -203,7 +203,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = rcu_access_pointer(table->private);
+	private = READ_ONCE(table->private); /* Address dependency. */
 	cpu     = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct arpt_entry **)private->jumpstack[cpu];
@@ -649,7 +649,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = xt_table_get_private_protected(table);
+	const struct xt_table_info *private = table->private;
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	 * (other than comefrom, which userspace doesn't care
@@ -673,7 +673,7 @@ static int copy_entries_to_user(unsigned int total_size,
 	unsigned int off, num;
 	const struct arpt_entry *e;
 	struct xt_counters *counters;
-	struct xt_table_info *private = xt_table_get_private_protected(table);
+	struct xt_table_info *private = table->private;
 	int ret = 0;
 	void *loc_cpu_entry;
 
@@ -807,7 +807,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
 	t = xt_request_find_table_lock(net, NFPROTO_ARP, name);
 	if (!IS_ERR(t)) {
 		struct arpt_getinfo info;
-		const struct xt_table_info *private = xt_table_get_private_protected(t);
+		const struct xt_table_info *private = t->private;
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
@@ -860,7 +860,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr,
 
 	t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = xt_table_get_private_protected(t);
+		const struct xt_table_info *private = t->private;
 
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
@@ -1017,7 +1017,7 @@ static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 	}
 
 	local_bh_disable();
-	private = xt_table_get_private_protected(t);
+	private = t->private;
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
@@ -1330,7 +1330,7 @@ static int compat_copy_entries_to_user(unsigned int total_size,
 				       void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = xt_table_get_private_protected(table);
+	const struct xt_table_info *private = table->private;
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 6e2851f8d3a3..f15bc21d7301 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -258,7 +258,7 @@ ipt_do_table(struct sk_buff *skb,
 	WARN_ON(!(table->valid_hooks & (1 << hook)));
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = rcu_access_pointer(table->private);
+	private = READ_ONCE(table->private); /* Address dependency. */
 	cpu        = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct ipt_entry **)private->jumpstack[cpu];
@@ -791,7 +791,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = xt_table_get_private_protected(table);
+	const struct xt_table_info *private = table->private;
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	   (other than comefrom, which userspace doesn't care
@@ -815,7 +815,7 @@ copy_entries_to_user(unsigned int total_size,
 	unsigned int off, num;
 	const struct ipt_entry *e;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = xt_table_get_private_protected(table);
+	const struct xt_table_info *private = table->private;
 	int ret = 0;
 	const void *loc_cpu_entry;
 
@@ -964,7 +964,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
 	t = xt_request_find_table_lock(net, AF_INET, name);
 	if (!IS_ERR(t)) {
 		struct ipt_getinfo info;
-		const struct xt_table_info *private = xt_table_get_private_protected(t);
+		const struct xt_table_info *private = t->private;
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
@@ -1018,7 +1018,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr,
 
 	t = xt_find_table_lock(net, AF_INET, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = xt_table_get_private_protected(t);
+		const struct xt_table_info *private = t->private;
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
 						   t, uptr->entrytable);
@@ -1173,7 +1173,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 	}
 
 	local_bh_disable();
-	private = xt_table_get_private_protected(t);
+	private = t->private;
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
@@ -1543,7 +1543,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
 			    void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = xt_table_get_private_protected(table);
+	const struct xt_table_info *private = table->private;
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index c4f532f4d311..2e2119bfcf13 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -280,7 +280,7 @@ ip6t_do_table(struct sk_buff *skb,
 
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = rcu_access_pointer(table->private);
+	private = READ_ONCE(table->private); /* Address dependency. */
 	cpu        = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct ip6t_entry **)private->jumpstack[cpu];
@@ -807,7 +807,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = xt_table_get_private_protected(table);
+	const struct xt_table_info *private = table->private;
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	   (other than comefrom, which userspace doesn't care
@@ -831,7 +831,7 @@ copy_entries_to_user(unsigned int total_size,
 	unsigned int off, num;
 	const struct ip6t_entry *e;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = xt_table_get_private_protected(table);
+	const struct xt_table_info *private = table->private;
 	int ret = 0;
 	const void *loc_cpu_entry;
 
@@ -980,7 +980,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
 	t = xt_request_find_table_lock(net, AF_INET6, name);
 	if (!IS_ERR(t)) {
 		struct ip6t_getinfo info;
-		const struct xt_table_info *private = xt_table_get_private_protected(t);
+		const struct xt_table_info *private = t->private;
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
@@ -1035,7 +1035,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr,
 
 	t = xt_find_table_lock(net, AF_INET6, get.name);
 	if (!IS_ERR(t)) {
-		struct xt_table_info *private = xt_table_get_private_protected(t);
+		struct xt_table_info *private = t->private;
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
 						   t, uptr->entrytable);
@@ -1189,7 +1189,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 	}
 
 	local_bh_disable();
-	private = xt_table_get_private_protected(t);
+	private = t->private;
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
@@ -1552,7 +1552,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
 			    void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = xt_table_get_private_protected(table);
+	const struct xt_table_info *private = table->private;
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index bce6ca203d46..7df3aef39c5c 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1351,14 +1351,6 @@ struct xt_counters *xt_counters_alloc(unsigned int counters)
 }
 EXPORT_SYMBOL(xt_counters_alloc);
 
-struct xt_table_info
-*xt_table_get_private_protected(const struct xt_table *table)
-{
-	return rcu_dereference_protected(table->private,
-					 mutex_is_locked(&xt[table->af].mutex));
-}
-EXPORT_SYMBOL(xt_table_get_private_protected);
-
 struct xt_table_info *
 xt_replace_table(struct xt_table *table,
 	      unsigned int num_counters,
@@ -1366,6 +1358,7 @@ xt_replace_table(struct xt_table *table,
 	      int *error)
 {
 	struct xt_table_info *private;
+	unsigned int cpu;
 	int ret;
 
 	ret = xt_jumpstack_alloc(newinfo);
@@ -1375,20 +1368,47 @@ xt_replace_table(struct xt_table *table,
 	}
 
 	/* Do the substitution. */
-	private = xt_table_get_private_protected(table);
+	local_bh_disable();
+	private = table->private;
 
 	/* Check inside lock: is the old number correct? */
 	if (num_counters != private->number) {
 		pr_debug("num_counters != table->private->number (%u/%u)\n",
 			 num_counters, private->number);
+		local_bh_enable();
 		*error = -EAGAIN;
 		return NULL;
 	}
 
 	newinfo->initial_entries = private->initial_entries;
+	/*
+	 * Ensure contents of newinfo are visible before assigning to
+	 * private.
+	 */
+	smp_wmb();
+	table->private = newinfo;
 
-	rcu_assign_pointer(table->private, newinfo);
-	synchronize_rcu();
+	/* make sure all cpus see new ->private value */
+	smp_wmb();
+
+	/*
+	 * Even though table entries have now been swapped, other CPU's
+	 * may still be using the old entries...
+	 */
+	local_bh_enable();
+
+	/* ... so wait for even xt_recseq on all cpus */
+	for_each_possible_cpu(cpu) {
+		seqcount_t *s = &per_cpu(xt_recseq, cpu);
+		u32 seq = raw_read_seqcount(s);
+
+		if (seq & 1) {
+			do {
+				cond_resched();
+				cpu_relax();
+			} while (seq == raw_read_seqcount(s));
+		}
+	}
 
 	audit_log_nfcfg(table->name, table->af, private->number,
 			!private->number ? AUDIT_XT_OP_REGISTER :
@@ -1424,12 +1444,12 @@ struct xt_table *xt_register_table(struct net *net,
 	}
 
 	/* Simplifies replace_table code. */
-	rcu_assign_pointer(table->private, bootstrap);
+	table->private = bootstrap;
 
 	if (!xt_replace_table(table, 0, newinfo, &ret))
 		goto unlock;
 
-	private = xt_table_get_private_protected(table);
+	private = table->private;
 	pr_debug("table->private->number = %u\n", private->number);
 
 	/* save number of initial entries */
@@ -1452,8 +1472,7 @@ void *xt_unregister_table(struct xt_table *table)
 	struct xt_table_info *private;
 
 	mutex_lock(&xt[table->af].mutex);
-	private = xt_table_get_private_protected(table);
-	RCU_INIT_POINTER(table->private, NULL);
+	private = table->private;
 	list_del(&table->list);
 	mutex_unlock(&xt[table->af].mutex);
 	audit_log_nfcfg(table->name, table->af, private->number,

From 175e476b8cdf2a4de7432583b49c871345e4f8a1 Mon Sep 17 00:00:00 2001
From: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Date: Mon, 8 Mar 2021 14:24:13 +1300
Subject: [PATCH 0847/1820] netfilter: x_tables: Use correct memory barriers.

When a new table value was assigned, it was followed by a write memory
barrier. This ensured that all writes before this point would complete
before any writes after this point. However, to determine whether the
rules are unused, the sequence counter is read. To ensure that all
writes have been done before these reads, a full memory barrier is
needed, not just a write memory barrier. The same argument applies when
incrementing the counter, before the rules are read.

Changing to using smp_mb() instead of smp_wmb() fixes the kernel panic
reported in cc00bcaa5899 (which is still present), while still
maintaining the same speed of replacing tables.

The smb_mb() barriers potentially slow the packet path, however testing
has shown no measurable change in performance on a 4-core MIPS64
platform.

Fixes: 7f5c6d4f665b ("netfilter: get rid of atomic ops in fast path")
Signed-off-by: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/x_tables.h | 2 +-
 net/netfilter/x_tables.c           | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 5deb099d156d..8ec48466410a 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -376,7 +376,7 @@ static inline unsigned int xt_write_recseq_begin(void)
 	 * since addend is most likely 1
 	 */
 	__this_cpu_add(xt_recseq.sequence, addend);
-	smp_wmb();
+	smp_mb();
 
 	return addend;
 }
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 7df3aef39c5c..6bd31a7a27fc 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1389,7 +1389,7 @@ xt_replace_table(struct xt_table *table,
 	table->private = newinfo;
 
 	/* make sure all cpus see new ->private value */
-	smp_wmb();
+	smp_mb();
 
 	/*
 	 * Even though table entries have now been swapped, other CPU's

From b58f33d49e426dc66e98ed73afb5d97b15a25f2d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 15 Mar 2021 11:31:09 +0100
Subject: [PATCH 0848/1820] netfilter: ctnetlink: fix dump of the expect mask
 attribute

Before this change, the mask is never included in the netlink message, so
"conntrack -E expect" always prints 0.0.0.0.

In older kernels the l3num callback struct was passed as argument, based
on tuple->src.l3num. After the l3num indirection got removed, the call
chain is based on m.src.l3num, but this value is 0xffff.

Init l3num to the correct value.

Fixes: f957be9d349a3 ("netfilter: conntrack: remove ctnetlink callbacks from l3 protocol trackers")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 1469365bac7e..1d519b0e51a5 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2962,6 +2962,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb,
 	memset(&m, 0xFF, sizeof(m));
 	memcpy(&m.src.u3, &mask->src.u3, sizeof(m.src.u3));
 	m.src.u.all = mask->src.u.all;
+	m.src.l3num = tuple->src.l3num;
 	m.dst.protonum = tuple->dst.protonum;
 
 	nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK);

From 73076790e25717b7d452c2eab0bfb118826e5b61 Mon Sep 17 00:00:00 2001
From: Sung Lee <sung.lee@amd.com>
Date: Thu, 4 Feb 2021 08:21:15 -0500
Subject: [PATCH 0849/1820] drm/amd/display: Copy over soc values before
 bounding box creation

[Why]
With certain fclock overclocks, state 1 may be chosen
as the closest clock level. This may result in this state
being empty if not populated beforehand, resulting in
black screens and screen corruption.

[How]
Copy over all soc states to clock_limits before bounding
box creation to avoid any cases with empty states.

Fixes: f2459c52c84449 ("drm/amd/display: Add Bounding Box State for Low DF PState but High Voltage State")
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1514
Signed-off-by: Sung Lee <sung.lee@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Qingqing Zhuo <Qingqing.Zhuo@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index 173488ab787a..4a3df13c9e49 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -1595,6 +1595,11 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 	dcn2_1_soc.num_chans = bw_params->num_channels;
 
 	ASSERT(clk_table->num_entries);
+	/* Copy dcn2_1_soc.clock_limits to clock_limits to avoid copying over null states later */
+	for (i = 0; i < dcn2_1_soc.num_states + 1; i++) {
+		clock_limits[i] = dcn2_1_soc.clock_limits[i];
+	}
+
 	for (i = 0; i < clk_table->num_entries; i++) {
 		/* loop backwards*/
 		for (closest_clk_lvl = 0, j = dcn2_1_soc.num_states - 1; j >= 0; j--) {

From c79f01b6eb5dc708573002fb3ba270918bcd1d32 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Wed, 10 Mar 2021 14:26:48 +0100
Subject: [PATCH 0850/1820] s390/cpumf: disable preemption when accessing
 per-cpu variable

The following BUG message was triggered repeatedly when complete counter
sets are extracted from the CPUMF:

BUG: using smp_processor_id() in preemptible [00000000]
     code: psvc-readsets/7759
 caller is cf_diag_needspace+0x2c/0x100
 CPU: 7 PID: 7759 Comm: psvc-readsets Not tainted 5.12.0
 Hardware name: IBM 3906 M03 703 (LPAR)
 Call Trace:
  [<00000000c7043f78>] show_stack+0x90/0xf8
  [<00000000c705776a>] dump_stack+0xba/0x108
  [<00000000c705d91c>] check_preemption_disabled+0xec/0xf0
  [<00000000c63eb1c4>] cf_diag_needspace+0x2c/0x100
  [<00000000c63ecbcc>] cf_diag_ioctl_start+0x10c/0x240
  [<00000000c63ece9a>] cf_diag_ioctl+0x19a/0x238
  [<00000000c675f3f4>] __s390x_sys_ioctl+0xc4/0x100
  [<00000000c63ca762>] do_syscall+0x82/0xd0
  [<00000000c705bdd8>] __do_syscall+0xc0/0xd8
  [<00000000c706d532>] system_call+0x72/0x98
 2 locks held by psvc-readsets/7759:
  #0: 00000000c75a57c0 (cpu_hotplug_lock){++++}-{0:0},
      at: cf_diag_ioctl+0x44/0x238
  #1: 00000000c75a3078 (cf_diag_ctrset_mutex){+.+.}-{3:3},
	            at: cf_diag_ioctl+0x54/0x238

This issue is a missing get_cpu_ptr/put_cpu_ptr pair in function
cf_diag_needspace. Add it.

Fixes: cf6acb8bdb1d ("s390/cpumf: Add support for complete counter set extraction")
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/perf_cpum_cf_diag.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index bc302b86ce28..2e3e7edbe3a0 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -968,7 +968,7 @@ static int cf_diag_all_start(void)
  */
 static size_t cf_diag_needspace(unsigned int sets)
 {
-	struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+	struct cpu_cf_events *cpuhw = get_cpu_ptr(&cpu_cf_events);
 	size_t bytes = 0;
 	int i;
 
@@ -984,6 +984,7 @@ static size_t cf_diag_needspace(unsigned int sets)
 		     sizeof(((struct s390_ctrset_cpudata *)0)->no_sets));
 	debug_sprintf_event(cf_diag_dbg, 5, "%s bytes %ld\n", __func__,
 			    bytes);
+	put_cpu_ptr(&cpu_cf_events);
 	return bytes;
 }
 

From d54cb7d54877d529bc1e0e1f47a3dd082f73add3 Mon Sep 17 00:00:00 2001
From: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Date: Wed, 10 Mar 2021 14:23:37 +0100
Subject: [PATCH 0851/1820] s390/vtime: fix increased steal time accounting

Commit 152e9b8676c6e ("s390/vtime: steal time exponential moving average")
inadvertently changed the input value for account_steal_time() from
"cputime_to_nsecs(steal)" to just "steal", resulting in broken increased
steal time accounting.

Fix this by changing it back to "cputime_to_nsecs(steal)".

Fixes: 152e9b8676c6e ("s390/vtime: steal time exponential moving average")
Cc: <stable@vger.kernel.org> # 5.1
Reported-by: Sabine Forkel <sabine.forkel@de.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/vtime.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 73c7afcc0527..f216a1b2f825 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -214,7 +214,7 @@ void vtime_flush(struct task_struct *tsk)
 	avg_steal = S390_lowcore.avg_steal_timer / 2;
 	if ((s64) steal > 0) {
 		S390_lowcore.steal_timer = 0;
-		account_steal_time(steal);
+		account_steal_time(cputime_to_nsecs(steal));
 		avg_steal += steal;
 	}
 	S390_lowcore.avg_steal_timer = avg_steal;

From 0b13525c20febcfecccf6fc1db5969727401317d Mon Sep 17 00:00:00 2001
From: Niklas Schnelle <schnelle@linux.ibm.com>
Date: Wed, 10 Mar 2021 13:46:26 +0100
Subject: [PATCH 0852/1820] s390/pci: fix leak of PCI device structure

In commit 05bc1be6db4b2 ("s390/pci: create zPCI bus") we removed the
pci_dev_put() call matching the earlier pci_get_slot() done as part of
__zpci_event_availability(). This was based on the wrong understanding
that the device_put() done as part of pci_destroy_device() would counter
the pci_get_slot() when it only counters the initial reference. This
same understanding and existing bad example also lead to not doing
a pci_dev_put() in zpci_remove_device().

Since releasing the PCI devices, unlike releasing the PCI slot, does not
print any debug message for testing I added one in pci_release_dev().
This revealed that we are indeed leaking the PCI device on PCI
hotunplug. Further testing also revealed another missing pci_dev_put() in
disable_slot().

Fix this by adding the missing pci_dev_put() in disable_slot() and fix
zpci_remove_device() with the correct pci_dev_put() calls. Also instead
of calling pci_get_slot() in __zpci_event_availability() to determine if
a PCI device is registered and then doing the same again in
zpci_remove_device() do this once in zpci_remove_device() which makes
sure that the pdev in __zpci_event_availability() is only used for the
result of pci_scan_single_device() which does not need a reference count
decremnt as its ownership goes to the PCI bus.

Also move the check if zdev->zbus->bus is set into zpci_remove_device()
since it may be that we're removing a device with devfn != 0 which never
had a PCI bus. So we can still set the pdev->error_state to indicate
that the device is not usable anymore, add a flag to set the error state.

Fixes: 05bc1be6db4b2 ("s390/pci: create zPCI bus")
Cc: <stable@vger.kernel.org> # 5.8+: e1bff843cde6 s390/pci: remove superfluous zdev->zbus check
Cc: <stable@vger.kernel.org> # 5.8+: ba764dd703fe s390/pci: refactor zpci_create_device()
Cc: <stable@vger.kernel.org> # 5.8+
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/pci.h        |  2 +-
 arch/s390/pci/pci.c                | 28 ++++++++++++++++++++++++----
 arch/s390/pci/pci_event.c          | 18 ++++++------------
 drivers/pci/hotplug/s390_pci_hpc.c |  3 ++-
 4 files changed, 33 insertions(+), 18 deletions(-)

diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 053fe8b8dec7..a75d94a9bcb2 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -202,7 +202,7 @@ extern unsigned int s390_pci_no_rid;
 ----------------------------------------------------------------------------- */
 /* Base stuff */
 int zpci_create_device(u32 fid, u32 fh, enum zpci_state state);
-void zpci_remove_device(struct zpci_dev *zdev);
+void zpci_remove_device(struct zpci_dev *zdev, bool set_error);
 int zpci_enable_device(struct zpci_dev *);
 int zpci_disable_device(struct zpci_dev *);
 int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64);
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 600881d894dd..91064077526d 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -682,16 +682,36 @@ int zpci_disable_device(struct zpci_dev *zdev)
 }
 EXPORT_SYMBOL_GPL(zpci_disable_device);
 
-void zpci_remove_device(struct zpci_dev *zdev)
+/* zpci_remove_device - Removes the given zdev from the PCI core
+ * @zdev: the zdev to be removed from the PCI core
+ * @set_error: if true the device's error state is set to permanent failure
+ *
+ * Sets a zPCI device to a configured but offline state; the zPCI
+ * device is still accessible through its hotplug slot and the zPCI
+ * API but is removed from the common code PCI bus, making it
+ * no longer available to drivers.
+ */
+void zpci_remove_device(struct zpci_dev *zdev, bool set_error)
 {
 	struct zpci_bus *zbus = zdev->zbus;
 	struct pci_dev *pdev;
 
+	if (!zdev->zbus->bus)
+		return;
+
 	pdev = pci_get_slot(zbus->bus, zdev->devfn);
 	if (pdev) {
-		if (pdev->is_virtfn)
-			return zpci_iov_remove_virtfn(pdev, zdev->vfn);
+		if (set_error)
+			pdev->error_state = pci_channel_io_perm_failure;
+		if (pdev->is_virtfn) {
+			zpci_iov_remove_virtfn(pdev, zdev->vfn);
+			/* balance pci_get_slot */
+			pci_dev_put(pdev);
+			return;
+		}
 		pci_stop_and_remove_bus_device_locked(pdev);
+		/* balance pci_get_slot */
+		pci_dev_put(pdev);
 	}
 }
 
@@ -765,7 +785,7 @@ void zpci_release_device(struct kref *kref)
 	struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref);
 
 	if (zdev->zbus->bus)
-		zpci_remove_device(zdev);
+		zpci_remove_device(zdev, false);
 
 	switch (zdev->state) {
 	case ZPCI_FN_STATE_ONLINE:
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index b4162da4e8a2..ac0c65cdd69d 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -76,13 +76,10 @@ void zpci_event_error(void *data)
 static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 {
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
-	struct pci_dev *pdev = NULL;
 	enum zpci_state state;
+	struct pci_dev *pdev;
 	int ret;
 
-	if (zdev && zdev->zbus->bus)
-		pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
-
 	zpci_err("avail CCDF:\n");
 	zpci_err_hex(ccdf, sizeof(*ccdf));
 
@@ -124,8 +121,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 	case 0x0303: /* Deconfiguration requested */
 		if (!zdev)
 			break;
-		if (pdev)
-			zpci_remove_device(zdev);
+		zpci_remove_device(zdev, false);
 
 		ret = zpci_disable_device(zdev);
 		if (ret)
@@ -140,12 +136,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 	case 0x0304: /* Configured -> Standby|Reserved */
 		if (!zdev)
 			break;
-		if (pdev) {
-			/* Give the driver a hint that the function is
-			 * already unusable. */
-			pdev->error_state = pci_channel_io_perm_failure;
-			zpci_remove_device(zdev);
-		}
+		/* Give the driver a hint that the function is
+		 * already unusable.
+		 */
+		zpci_remove_device(zdev, true);
 
 		zdev->fh = ccdf->fh;
 		zpci_disable_device(zdev);
diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c
index c9e790c74051..a047c421debe 100644
--- a/drivers/pci/hotplug/s390_pci_hpc.c
+++ b/drivers/pci/hotplug/s390_pci_hpc.c
@@ -93,8 +93,9 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
 		pci_dev_put(pdev);
 		return -EBUSY;
 	}
+	pci_dev_put(pdev);
 
-	zpci_remove_device(zdev);
+	zpci_remove_device(zdev, false);
 
 	rc = zpci_disable_device(zdev);
 	if (rc)

From bf0ffea336b493c0a8c8bc27b46683ecf1e8f294 Mon Sep 17 00:00:00 2001
From: Xie He <xie.he.0141@gmail.com>
Date: Sun, 14 Mar 2021 04:21:01 -0700
Subject: [PATCH 0853/1820] net: hdlc_x25: Prevent racing between "x25_close"
 and "x25_xmit"/"x25_rx"

"x25_close" is called by "hdlc_close" in "hdlc.c", which is called by
hardware drivers' "ndo_stop" function.
"x25_xmit" is called by "hdlc_start_xmit" in "hdlc.c", which is hardware
drivers' "ndo_start_xmit" function.
"x25_rx" is called by "hdlc_rcv" in "hdlc.c", which receives HDLC frames
from "net/core/dev.c".

"x25_close" races with "x25_xmit" and "x25_rx" because their callers race.

However, we need to ensure that the LAPB APIs called in "x25_xmit" and
"x25_rx" are called before "lapb_unregister" is called in "x25_close".

This patch adds locking to ensure when "x25_xmit" and "x25_rx" are doing
their work, "lapb_unregister" is not yet called in "x25_close".

Reasons for not solving the racing between "x25_close" and "x25_xmit" by
calling "netif_tx_disable" in "x25_close":
1. We still need to solve the racing between "x25_close" and "x25_rx";
2. The design of the HDLC subsystem assumes the HDLC hardware drivers
have full control over the TX queue, and the HDLC protocol drivers (like
this driver) have no control. Controlling the queue here in the protocol
driver may interfere with hardware drivers' control of the queue.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Xie He <xie.he.0141@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/hdlc_x25.c | 44 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 42 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c
index 4aaa6388b9ee..5a6a945f6c81 100644
--- a/drivers/net/wan/hdlc_x25.c
+++ b/drivers/net/wan/hdlc_x25.c
@@ -23,6 +23,8 @@
 
 struct x25_state {
 	x25_hdlc_proto settings;
+	bool up;
+	spinlock_t up_lock; /* Protects "up" */
 };
 
 static int x25_ioctl(struct net_device *dev, struct ifreq *ifr);
@@ -104,6 +106,8 @@ static void x25_data_transmit(struct net_device *dev, struct sk_buff *skb)
 
 static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	hdlc_device *hdlc = dev_to_hdlc(dev);
+	struct x25_state *x25st = state(hdlc);
 	int result;
 
 	/* There should be a pseudo header of 1 byte added by upper layers.
@@ -114,11 +118,19 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
+	spin_lock_bh(&x25st->up_lock);
+	if (!x25st->up) {
+		spin_unlock_bh(&x25st->up_lock);
+		kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
 	switch (skb->data[0]) {
 	case X25_IFACE_DATA:	/* Data to be transmitted */
 		skb_pull(skb, 1);
 		if ((result = lapb_data_request(dev, skb)) != LAPB_OK)
 			dev_kfree_skb(skb);
+		spin_unlock_bh(&x25st->up_lock);
 		return NETDEV_TX_OK;
 
 	case X25_IFACE_CONNECT:
@@ -147,6 +159,7 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
 		break;
 	}
 
+	spin_unlock_bh(&x25st->up_lock);
 	dev_kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
@@ -164,6 +177,7 @@ static int x25_open(struct net_device *dev)
 		.data_transmit = x25_data_transmit,
 	};
 	hdlc_device *hdlc = dev_to_hdlc(dev);
+	struct x25_state *x25st = state(hdlc);
 	struct lapb_parms_struct params;
 	int result;
 
@@ -190,6 +204,10 @@ static int x25_open(struct net_device *dev)
 	if (result != LAPB_OK)
 		return -EINVAL;
 
+	spin_lock_bh(&x25st->up_lock);
+	x25st->up = true;
+	spin_unlock_bh(&x25st->up_lock);
+
 	return 0;
 }
 
@@ -197,6 +215,13 @@ static int x25_open(struct net_device *dev)
 
 static void x25_close(struct net_device *dev)
 {
+	hdlc_device *hdlc = dev_to_hdlc(dev);
+	struct x25_state *x25st = state(hdlc);
+
+	spin_lock_bh(&x25st->up_lock);
+	x25st->up = false;
+	spin_unlock_bh(&x25st->up_lock);
+
 	lapb_unregister(dev);
 }
 
@@ -205,15 +230,28 @@ static void x25_close(struct net_device *dev)
 static int x25_rx(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
+	hdlc_device *hdlc = dev_to_hdlc(dev);
+	struct x25_state *x25st = state(hdlc);
 
 	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
 		dev->stats.rx_dropped++;
 		return NET_RX_DROP;
 	}
 
-	if (lapb_data_received(dev, skb) == LAPB_OK)
-		return NET_RX_SUCCESS;
+	spin_lock_bh(&x25st->up_lock);
+	if (!x25st->up) {
+		spin_unlock_bh(&x25st->up_lock);
+		kfree_skb(skb);
+		dev->stats.rx_dropped++;
+		return NET_RX_DROP;
+	}
 
+	if (lapb_data_received(dev, skb) == LAPB_OK) {
+		spin_unlock_bh(&x25st->up_lock);
+		return NET_RX_SUCCESS;
+	}
+
+	spin_unlock_bh(&x25st->up_lock);
 	dev->stats.rx_errors++;
 	dev_kfree_skb_any(skb);
 	return NET_RX_DROP;
@@ -298,6 +336,8 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr)
 			return result;
 
 		memcpy(&state(hdlc)->settings, &new_settings, size);
+		state(hdlc)->up = false;
+		spin_lock_init(&state(hdlc)->up_lock);
 
 		/* There's no header_ops so hard_header_len should be 0. */
 		dev->hard_header_len = 0;

From b95bc12e0412d14d5fc764f0b82631c7bcaf1959 Mon Sep 17 00:00:00 2001
From: Xiaoliang Yu <yxl_22@outlook.com>
Date: Tue, 16 Mar 2021 00:49:00 +0800
Subject: [PATCH 0854/1820] ALSA: hda/realtek: apply pin quirk for
 XiaomiNotebook Pro

Built-in microphone and combojack on Xiaomi Notebook Pro (1d72:1701) needs
to be fixed, the existing quirk for Dell works well on that machine.

Signed-off-by: Xiaoliang Yu <yxl_22@outlook.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/OS0P286MB02749B9E13920E6899902CD8EE6C9@OS0P286MB0274.JPNP286.PROD.OUTLOOK.COM
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c6d916177d5c..345a447aba81 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -8242,6 +8242,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1b35, 0x1237, "CZC L101", ALC269_FIXUP_CZC_L101),
 	SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */
 	SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE),

From d82c6c1aaccd2877b6082cebcb1746a13648a16d Mon Sep 17 00:00:00 2001
From: Ong Boon Leong <boon.leong.ong@intel.com>
Date: Mon, 15 Mar 2021 12:33:42 +0800
Subject: [PATCH 0855/1820] net: phylink: Fix phylink_err() function name error
 in phylink_major_config

if pl->mac_ops->mac_finish() failed, phylink_err should use
"mac_finish" instead of "mac_prepare".

Fixes: b7ad14c2fe2d4 ("net: phylink: re-implement interface configuration with PCS")
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 053c92e02cd8..dc2800beacc3 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -476,7 +476,7 @@ static void phylink_major_config(struct phylink *pl, bool restart,
 		err = pl->mac_ops->mac_finish(pl->config, pl->cur_link_an_mode,
 					      state->interface);
 		if (err < 0)
-			phylink_err(pl, "mac_prepare failed: %pe\n",
+			phylink_err(pl, "mac_finish failed: %pe\n",
 				    ERR_PTR(err));
 	}
 }

From 0217ed2848e8538bcf9172d97ed2eeb4a26041bb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 15 Mar 2021 03:06:58 -0700
Subject: [PATCH 0856/1820] tipc: better validate user input in
 tipc_nl_retrieve_key()

Before calling tipc_aead_key_size(ptr), we need to ensure
we have enough data to dereference ptr->keylen.

We probably also want to make sure tipc_aead_key_size()
wont overflow with malicious ptr->keylen values.

Syzbot reported:

BUG: KMSAN: uninit-value in __tipc_nl_node_set_key net/tipc/node.c:2971 [inline]
BUG: KMSAN: uninit-value in tipc_nl_node_set_key+0x9bf/0x13b0 net/tipc/node.c:3023
CPU: 0 PID: 21060 Comm: syz-executor.5 Not tainted 5.11.0-rc7-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:79 [inline]
 dump_stack+0x21c/0x280 lib/dump_stack.c:120
 kmsan_report+0xfb/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x5f/0xa0 mm/kmsan/kmsan_instr.c:197
 __tipc_nl_node_set_key net/tipc/node.c:2971 [inline]
 tipc_nl_node_set_key+0x9bf/0x13b0 net/tipc/node.c:3023
 genl_family_rcv_msg_doit net/netlink/genetlink.c:739 [inline]
 genl_family_rcv_msg net/netlink/genetlink.c:783 [inline]
 genl_rcv_msg+0x1319/0x1610 net/netlink/genetlink.c:800
 netlink_rcv_skb+0x6fa/0x810 net/netlink/af_netlink.c:2494
 genl_rcv+0x63/0x80 net/netlink/genetlink.c:811
 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline]
 netlink_unicast+0x11d6/0x14a0 net/netlink/af_netlink.c:1330
 netlink_sendmsg+0x1740/0x1840 net/netlink/af_netlink.c:1919
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg net/socket.c:672 [inline]
 ____sys_sendmsg+0xcfc/0x12f0 net/socket.c:2345
 ___sys_sendmsg net/socket.c:2399 [inline]
 __sys_sendmsg+0x714/0x830 net/socket.c:2432
 __compat_sys_sendmsg net/compat.c:347 [inline]
 __do_compat_sys_sendmsg net/compat.c:354 [inline]
 __se_compat_sys_sendmsg+0xa7/0xc0 net/compat.c:351
 __ia32_compat_sys_sendmsg+0x4a/0x70 net/compat.c:351
 do_syscall_32_irqs_on arch/x86/entry/common.c:79 [inline]
 __do_fast_syscall_32+0x102/0x160 arch/x86/entry/common.c:141
 do_fast_syscall_32+0x6a/0xc0 arch/x86/entry/common.c:166
 do_SYSENTER_32+0x73/0x90 arch/x86/entry/common.c:209
 entry_SYSENTER_compat_after_hwframe+0x4d/0x5c
RIP: 0023:0xf7f60549
Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d b4 26 00 00 00 00 8d b4 26 00 00 00 00
RSP: 002b:00000000f555a5fc EFLAGS: 00000296 ORIG_RAX: 0000000000000172
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000020000200
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:121 [inline]
 kmsan_internal_poison_shadow+0x5c/0xf0 mm/kmsan/kmsan.c:104
 kmsan_slab_alloc+0x8d/0xe0 mm/kmsan/kmsan_hooks.c:76
 slab_alloc_node mm/slub.c:2907 [inline]
 __kmalloc_node_track_caller+0xa37/0x1430 mm/slub.c:4527
 __kmalloc_reserve net/core/skbuff.c:142 [inline]
 __alloc_skb+0x2f8/0xb30 net/core/skbuff.c:210
 alloc_skb include/linux/skbuff.h:1099 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1176 [inline]
 netlink_sendmsg+0xdbc/0x1840 net/netlink/af_netlink.c:1894
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg net/socket.c:672 [inline]
 ____sys_sendmsg+0xcfc/0x12f0 net/socket.c:2345
 ___sys_sendmsg net/socket.c:2399 [inline]
 __sys_sendmsg+0x714/0x830 net/socket.c:2432
 __compat_sys_sendmsg net/compat.c:347 [inline]
 __do_compat_sys_sendmsg net/compat.c:354 [inline]
 __se_compat_sys_sendmsg+0xa7/0xc0 net/compat.c:351
 __ia32_compat_sys_sendmsg+0x4a/0x70 net/compat.c:351
 do_syscall_32_irqs_on arch/x86/entry/common.c:79 [inline]
 __do_fast_syscall_32+0x102/0x160 arch/x86/entry/common.c:141
 do_fast_syscall_32+0x6a/0xc0 arch/x86/entry/common.c:166
 do_SYSENTER_32+0x73/0x90 arch/x86/entry/common.c:209
 entry_SYSENTER_compat_after_hwframe+0x4d/0x5c

Fixes: e1f32190cf7d ("tipc: add support for AEAD key setting via netlink")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tuong Lien <tuong.t.lien@dektech.com.au>
Cc: Jon Maloy <jmaloy@redhat.com>
Cc: Ying Xue <ying.xue@windriver.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 008670d1f43e..136338b85504 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -2895,17 +2895,22 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb,
 
 #ifdef CONFIG_TIPC_CRYPTO
 static int tipc_nl_retrieve_key(struct nlattr **attrs,
-				struct tipc_aead_key **key)
+				struct tipc_aead_key **pkey)
 {
 	struct nlattr *attr = attrs[TIPC_NLA_NODE_KEY];
+	struct tipc_aead_key *key;
 
 	if (!attr)
 		return -ENODATA;
 
-	*key = (struct tipc_aead_key *)nla_data(attr);
-	if (nla_len(attr) < tipc_aead_key_size(*key))
+	if (nla_len(attr) < sizeof(*key))
+		return -EINVAL;
+	key = (struct tipc_aead_key *)nla_data(attr);
+	if (key->keylen > TIPC_AEAD_KEYLEN_MAX ||
+	    nla_len(attr) < tipc_aead_key_size(key))
 		return -EINVAL;
 
+	*pkey = key;
 	return 0;
 }
 

From 7233da86697efef41288f8b713c10c2499cffe85 Mon Sep 17 00:00:00 2001
From: Alexander Ovechkin <ovov@yandex-team.ru>
Date: Mon, 15 Mar 2021 14:05:45 +0300
Subject: [PATCH 0857/1820] tcp: relookup sock for RST+ACK packets handled by
 obsolete req sock

Currently tcp_check_req can be called with obsolete req socket for which big
socket have been already created (because of CPU race or early demux
assigning req socket to multiple packets in gro batch).

Commit e0f9759f530bf789e984 ("tcp: try to keep packet if SYN_RCV race
is lost") added retry in case when tcp_check_req is called for PSH|ACK packet.
But if client sends RST+ACK immediatly after connection being
established (it is performing healthcheck, for example) retry does not
occur. In that case tcp_check_req tries to close req socket,
leaving big socket active.

Fixes: e0f9759f530 ("tcp: try to keep packet if SYN_RCV race is lost")
Signed-off-by: Alexander Ovechkin <ovov@yandex-team.ru>
Reported-by: Oleg Senin <olegsenin@yandex-team.ru>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h | 2 +-
 net/ipv4/inet_connection_sock.c    | 7 +++++--
 net/ipv4/tcp_minisocks.c           | 7 +++++--
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 10a625760de9..3c8c59471bc1 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -282,7 +282,7 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
 	return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog;
 }
 
-void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
+bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
 void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req);
 
 static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 6bd7ca09af03..fd472eae4f5c 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -705,12 +705,15 @@ static bool reqsk_queue_unlink(struct request_sock *req)
 	return found;
 }
 
-void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
+bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
 {
-	if (reqsk_queue_unlink(req)) {
+	bool unlinked = reqsk_queue_unlink(req);
+
+	if (unlinked) {
 		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
 		reqsk_put(req);
 	}
+	return unlinked;
 }
 EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 0055ae0a3bf8..7513ba45553d 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -804,8 +804,11 @@ embryonic_reset:
 		tcp_reset(sk, skb);
 	}
 	if (!fastopen) {
-		inet_csk_reqsk_queue_drop(sk, req);
-		__NET_INC_STATS(sock_net(sk), LINUX_MIB_EMBRYONICRSTS);
+		bool unlinked = inet_csk_reqsk_queue_drop(sk, req);
+
+		if (unlinked)
+			__NET_INC_STATS(sock_net(sk), LINUX_MIB_EMBRYONICRSTS);
+		*req_stolen = !unlinked;
 	}
 	return NULL;
 }

From 13832ae2755395b2585500c85b64f5109a44227e Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Mon, 15 Mar 2021 11:41:16 +0100
Subject: [PATCH 0858/1820] mptcp: fix ADD_ADDR HMAC in case port is specified
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, Linux computes the HMAC contained in ADD_ADDR sub-option using
the Address Id and the IP Address, and hardcodes a destination port equal
to zero. This is not ok for ADD_ADDR with port: ensure to account for the
endpoint port when computing the HMAC, in compliance with RFC8684 §3.4.1.

Fixes: 22fb85ffaefb ("mptcp: add port support for ADD_ADDR suboption writing")
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Acked-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/options.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 444a38681e93..89a4225ed321 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -567,15 +567,15 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 }
 
 static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id,
-				  struct in_addr *addr)
+				  struct in_addr *addr, u16 port)
 {
 	u8 hmac[SHA256_DIGEST_SIZE];
 	u8 msg[7];
 
 	msg[0] = addr_id;
 	memcpy(&msg[1], &addr->s_addr, 4);
-	msg[5] = 0;
-	msg[6] = 0;
+	msg[5] = port >> 8;
+	msg[6] = port & 0xFF;
 
 	mptcp_crypto_hmac_sha(key1, key2, msg, 7, hmac);
 
@@ -584,15 +584,15 @@ static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id,
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
-				   struct in6_addr *addr)
+				   struct in6_addr *addr, u16 port)
 {
 	u8 hmac[SHA256_DIGEST_SIZE];
 	u8 msg[19];
 
 	msg[0] = addr_id;
 	memcpy(&msg[1], &addr->s6_addr, 16);
-	msg[17] = 0;
-	msg[18] = 0;
+	msg[17] = port >> 8;
+	msg[18] = port & 0xFF;
 
 	mptcp_crypto_hmac_sha(key1, key2, msg, 19, hmac);
 
@@ -646,7 +646,8 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 			opts->ahmac = add_addr_generate_hmac(msk->local_key,
 							     msk->remote_key,
 							     opts->addr_id,
-							     &opts->addr);
+							     &opts->addr,
+							     opts->port);
 		}
 	}
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
@@ -657,7 +658,8 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 			opts->ahmac = add_addr6_generate_hmac(msk->local_key,
 							      msk->remote_key,
 							      opts->addr_id,
-							      &opts->addr6);
+							      &opts->addr6,
+							      opts->port);
 		}
 	}
 #endif
@@ -962,12 +964,14 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
 	if (mp_opt->family == MPTCP_ADDR_IPVERSION_4)
 		hmac = add_addr_generate_hmac(msk->remote_key,
 					      msk->local_key,
-					      mp_opt->addr_id, &mp_opt->addr);
+					      mp_opt->addr_id, &mp_opt->addr,
+					      mp_opt->port);
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	else
 		hmac = add_addr6_generate_hmac(msk->remote_key,
 					       msk->local_key,
-					       mp_opt->addr_id, &mp_opt->addr6);
+					       mp_opt->addr_id, &mp_opt->addr6,
+					       mp_opt->port);
 #endif
 
 	pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n",

From 7a1adbd2399023177508836c2b13a6c723035409 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Wed, 13 Jan 2021 17:02:53 +0000
Subject: [PATCH 0859/1820] drm: rcar-du: Use drmm_encoder_alloc() to manage
 encoder

The encoder allocation was converted to a DRM managed resource at the
same time as the addition of a new helper drmm_encoder_alloc() which
simplifies the same process.

Convert the custom drm managed resource allocation of the encoder
with the helper to simplify the implementation, and prevent hitting a
WARN_ON() due to the handling the drm_encoder_init() call directly
without registering a .destroy() function op.

Fixes: f5f16725edbc ("drm: rcar-du: Use DRM-managed allocation for encoders")
Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
---
 drivers/gpu/drm/rcar-du/rcar_du_encoder.c | 31 +++++------------------
 1 file changed, 6 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
index ba8c6038cd63..ca3761772211 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
@@ -48,21 +48,12 @@ static unsigned int rcar_du_encoder_count_ports(struct device_node *node)
 static const struct drm_encoder_funcs rcar_du_encoder_funcs = {
 };
 
-static void rcar_du_encoder_release(struct drm_device *dev, void *res)
-{
-	struct rcar_du_encoder *renc = res;
-
-	drm_encoder_cleanup(&renc->base);
-	kfree(renc);
-}
-
 int rcar_du_encoder_init(struct rcar_du_device *rcdu,
 			 enum rcar_du_output output,
 			 struct device_node *enc_node)
 {
 	struct rcar_du_encoder *renc;
 	struct drm_bridge *bridge;
-	int ret;
 
 	/*
 	 * Locate the DRM bridge from the DT node. For the DPAD outputs, if the
@@ -101,26 +92,16 @@ int rcar_du_encoder_init(struct rcar_du_device *rcdu,
 			return -ENOLINK;
 	}
 
-	renc = kzalloc(sizeof(*renc), GFP_KERNEL);
-	if (renc == NULL)
-		return -ENOMEM;
-
-	renc->output = output;
-
 	dev_dbg(rcdu->dev, "initializing encoder %pOF for output %u\n",
 		enc_node, output);
 
-	ret = drm_encoder_init(&rcdu->ddev, &renc->base, &rcar_du_encoder_funcs,
-			       DRM_MODE_ENCODER_NONE, NULL);
-	if (ret < 0) {
-		kfree(renc);
-		return ret;
-	}
+	renc = drmm_encoder_alloc(&rcdu->ddev, struct rcar_du_encoder, base,
+				  &rcar_du_encoder_funcs, DRM_MODE_ENCODER_NONE,
+				  NULL);
+	if (!renc)
+		return -ENOMEM;
 
-	ret = drmm_add_action_or_reset(&rcdu->ddev, rcar_du_encoder_release,
-				       renc);
-	if (ret)
-		return ret;
+	renc->output = output;
 
 	/*
 	 * Attach the bridge to the encoder. The bridge will create the

From febb0cc847e7efd0b2b6cabf9f0e82b13dbadbec Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.ibm.com>
Date: Wed, 10 Mar 2021 19:22:12 -0600
Subject: [PATCH 0860/1820] scsi: ibmvfc: Free channel_setup_buf during device
 tear down

The buffer for negotiating channel setup is DMA allocated at device probe
time. However, the remove path fails to free this allocation which will
prevent the hypervisor from releasing the virtual device in the case of a
hotplug remove.

Fix this issue by freeing the buffer allocation in ibmvfc_free_mem().

Link: https://lore.kernel.org/r/20210311012212.428068-1-tyreld@linux.ibm.com
Fixes: e95eef3fc0bc ("scsi: ibmvfc: Implement channel enquiry and setup commands")
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ibmvscsi/ibmvfc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 338e29d3e025..6a92891ac488 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -5784,6 +5784,8 @@ static void ibmvfc_free_mem(struct ibmvfc_host *vhost)
 			  vhost->disc_buf_dma);
 	dma_free_coherent(vhost->dev, sizeof(*vhost->login_buf),
 			  vhost->login_buf, vhost->login_buf_dma);
+	dma_free_coherent(vhost->dev, sizeof(*vhost->channel_setup_buf),
+			  vhost->channel_setup_buf, vhost->channel_setup_dma);
 	dma_pool_destroy(vhost->sg_pool);
 	ibmvfc_free_queue(vhost, async_q);
 	LEAVE;

From 2bb817712e2f77486d6ee17e7efaf91997a685f8 Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Wed, 10 Mar 2021 22:30:05 -0800
Subject: [PATCH 0861/1820] scsi: myrs: Fix a double free in myrs_cleanup()

In myrs_cleanup(), cs->mmio_base will be freed twice by iounmap().

Link: https://lore.kernel.org/r/20210311063005.9963-1-lyl2019@mail.ustc.edu.cn
Fixes: 77266186397c ("scsi: myrs: Add Mylex RAID controller (SCSI interface)")
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/myrs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c
index 4adf9ded296a..329fd025c718 100644
--- a/drivers/scsi/myrs.c
+++ b/drivers/scsi/myrs.c
@@ -2273,12 +2273,12 @@ static void myrs_cleanup(struct myrs_hba *cs)
 	if (cs->mmio_base) {
 		cs->disable_intr(cs);
 		iounmap(cs->mmio_base);
+		cs->mmio_base = NULL;
 	}
 	if (cs->irq)
 		free_irq(cs->irq, cs);
 	if (cs->io_addr)
 		release_region(cs->io_addr, 0x80);
-	iounmap(cs->mmio_base);
 	pci_set_drvdata(pdev, NULL);
 	pci_disable_device(pdev);
 	scsi_host_put(cs->host);

From c8c165dea4c8f5ad67b1240861e4f6c5395fa4ac Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Wed, 10 Mar 2021 22:46:36 -0800
Subject: [PATCH 0862/1820] scsi: st: Fix a use after free in st_open()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In st_open(), if STp->in_use is true, STp will be freed by
scsi_tape_put(). However, STp is still used by DEBC_printk() after. It is
better to DEBC_printk() before scsi_tape_put().

Link: https://lore.kernel.org/r/20210311064636.10522-1-lyl2019@mail.ustc.edu.cn
Acked-by: Kai Mäkisara <kai.makisara@kolumbus.fi>
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/st.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 841ad2fc369a..9ca536aae784 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -1269,8 +1269,8 @@ static int st_open(struct inode *inode, struct file *filp)
 	spin_lock(&st_use_lock);
 	if (STp->in_use) {
 		spin_unlock(&st_use_lock);
-		scsi_tape_put(STp);
 		DEBC_printk(STp, "Device already in use.\n");
+		scsi_tape_put(STp);
 		return (-EBUSY);
 	}
 

From 5999b9e5b1f8a2f5417b755130919b3ac96f5550 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Sun, 14 Mar 2021 18:32:46 +0300
Subject: [PATCH 0863/1820] scsi: qla2xxx: Fix broken #endif placement

Only half of the file is under include guard because terminating #endif
is placed too early.

Link: https://lore.kernel.org/r/YE4snvoW1SuwcXAn@localhost.localdomain
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_target.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 10e5e6c8087d..01620f3eab39 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -116,7 +116,6 @@
 	(min(1270, ((ql) > 0) ? (QLA_TGT_DATASEGS_PER_CMD_24XX + \
 		QLA_TGT_DATASEGS_PER_CONT_24XX*((ql) - 1)) : 0))
 #endif
-#endif
 
 #define GET_TARGET_ID(ha, iocb) ((HAS_EXTENDED_IDS(ha))			\
 			 ? le16_to_cpu((iocb)->u.isp2x.target.extended)	\
@@ -244,6 +243,7 @@ struct ctio_to_2xxx {
 #ifndef CTIO_RET_TYPE
 #define CTIO_RET_TYPE	0x17		/* CTIO return entry */
 #define ATIO_TYPE7 0x06 /* Accept target I/O entry for 24xx */
+#endif
 
 struct fcp_hdr {
 	uint8_t  r_ctl;

From 19f1bc7edf0f97186810e13a88f5b62069d89097 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 12 Mar 2021 10:42:11 +0300
Subject: [PATCH 0864/1820] scsi: lpfc: Fix some error codes in debugfs

If copy_from_user() or kstrtoull() fail then the correct behavior is to
return a negative error code.

Link: https://lore.kernel.org/r/YEsbU/UxYypVrC7/@mwanda
Fixes: f9bb2da11db8 ("[SCSI] lpfc 8.3.27: T10 additions for SLI4")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_debugfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index bc79a017e1a2..46a8f2d1d2b8 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -2421,7 +2421,7 @@ lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf,
 	memset(dstbuf, 0, 33);
 	size = (nbytes < 32) ? nbytes : 32;
 	if (copy_from_user(dstbuf, buf, size))
-		return 0;
+		return -EFAULT;
 
 	if (dent == phba->debug_InjErrLBA) {
 		if ((dstbuf[0] == 'o') && (dstbuf[1] == 'f') &&
@@ -2430,7 +2430,7 @@ lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf,
 	}
 
 	if ((tmp == 0) && (kstrtoull(dstbuf, 0, &tmp)))
-		return 0;
+		return -EINVAL;
 
 	if (dent == phba->debug_writeGuard)
 		phba->lpfc_injerr_wgrd_cnt = (uint32_t)tmp;

From ca6883393f0fa7f13ec8b860dbcef423a759c4a2 Mon Sep 17 00:00:00 2001
From: Jeremy Szu <jeremy.szu@canonical.com>
Date: Tue, 16 Mar 2021 14:54:50 +0800
Subject: [PATCH 0865/1820] ALSA: hda/realtek: fix mute/micmute LEDs for HP 840
 G8

The HP EliteBook 840 G8 Notebook PC is using ALC285 codec which is
using 0x04 to control mute LED and 0x01 to control micmute LED.
Therefore, add a quirk to make it works.

Signed-off-by: Jeremy Szu <jeremy.szu@canonical.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210316065452.75659-1-jeremy.szu@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 345a447aba81..f06bcb1ac4f9 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -8048,6 +8048,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),
+	SND_PCI_QUIRK(0x103c, 0x884c, "HP EliteBook 840 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),

From 3a5ca857079ea022e0b1b17fc154f7ad7dbc150f Mon Sep 17 00:00:00 2001
From: Martin Willi <martin@strongswan.org>
Date: Tue, 2 Mar 2021 13:24:23 +0100
Subject: [PATCH 0866/1820] can: dev: Move device back to init netns on owning
 netns delete

When a non-initial netns is destroyed, the usual policy is to delete
all virtual network interfaces contained, but move physical interfaces
back to the initial netns. This keeps the physical interface visible
on the system.

CAN devices are somewhat special, as they define rtnl_link_ops even
if they are physical devices. If a CAN interface is moved into a
non-initial netns, destroying that netns lets the interface vanish
instead of moving it back to the initial netns. default_device_exit()
skips CAN interfaces due to having rtnl_link_ops set. Reproducer:

  ip netns add foo
  ip link set can0 netns foo
  ip netns delete foo

WARNING: CPU: 1 PID: 84 at net/core/dev.c:11030 ops_exit_list+0x38/0x60
CPU: 1 PID: 84 Comm: kworker/u4:2 Not tainted 5.10.19 #1
Workqueue: netns cleanup_net
[<c010e700>] (unwind_backtrace) from [<c010a1d8>] (show_stack+0x10/0x14)
[<c010a1d8>] (show_stack) from [<c086dc10>] (dump_stack+0x94/0xa8)
[<c086dc10>] (dump_stack) from [<c086b938>] (__warn+0xb8/0x114)
[<c086b938>] (__warn) from [<c086ba10>] (warn_slowpath_fmt+0x7c/0xac)
[<c086ba10>] (warn_slowpath_fmt) from [<c0629f20>] (ops_exit_list+0x38/0x60)
[<c0629f20>] (ops_exit_list) from [<c062a5c4>] (cleanup_net+0x230/0x380)
[<c062a5c4>] (cleanup_net) from [<c0142c20>] (process_one_work+0x1d8/0x438)
[<c0142c20>] (process_one_work) from [<c0142ee4>] (worker_thread+0x64/0x5a8)
[<c0142ee4>] (worker_thread) from [<c0148a98>] (kthread+0x148/0x14c)
[<c0148a98>] (kthread) from [<c0100148>] (ret_from_fork+0x14/0x2c)

To properly restore physical CAN devices to the initial netns on owning
netns exit, introduce a flag on rtnl_link_ops that can be set by drivers.
For CAN devices setting this flag, default_device_exit() considers them
non-virtual, applying the usual namespace move.

The issue was introduced in the commit mentioned below, as at that time
CAN devices did not have a dellink() operation.

Fixes: e008b5fc8dc7 ("net: Simplfy default_device_exit and improve batching.")
Link: https://lore.kernel.org/r/20210302122423.872326-1-martin@strongswan.org
Signed-off-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev/netlink.c | 1 +
 include/net/rtnetlink.h       | 2 ++
 net/core/dev.c                | 2 +-
 3 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index 867f6be31230..f5d79e6e5483 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -355,6 +355,7 @@ static void can_dellink(struct net_device *dev, struct list_head *head)
 
 struct rtnl_link_ops can_link_ops __read_mostly = {
 	.kind		= "can",
+	.netns_refund	= true,
 	.maxtype	= IFLA_CAN_MAX,
 	.policy		= can_policy,
 	.setup		= can_setup,
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index e2091bb2b3a8..4da61c950e93 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -33,6 +33,7 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh)
  *
  *	@list: Used internally
  *	@kind: Identifier
+ *	@netns_refund: Physical device, move to init_net on netns exit
  *	@maxtype: Highest device specific netlink attribute number
  *	@policy: Netlink policy for device specific attribute validation
  *	@validate: Optional validation function for netlink/changelink parameters
@@ -64,6 +65,7 @@ struct rtnl_link_ops {
 	size_t			priv_size;
 	void			(*setup)(struct net_device *dev);
 
+	bool			netns_refund;
 	unsigned int		maxtype;
 	const struct nla_policy	*policy;
 	int			(*validate)(struct nlattr *tb[],
diff --git a/net/core/dev.c b/net/core/dev.c
index 6c5967e80132..a142a207fc1d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11346,7 +11346,7 @@ static void __net_exit default_device_exit(struct net *net)
 			continue;
 
 		/* Leave virtual devices for the generic cleanup */
-		if (dev->rtnl_link_ops)
+		if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund)
 			continue;
 
 		/* Push remaining network devices to init_net */

From e4912459bd5edd493b61bc7c3a5d9b2eb17f5a89 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 18 Feb 2021 21:58:36 +0100
Subject: [PATCH 0867/1820] can: isotp: isotp_setsockopt(): only allow to set
 low level TX flags for CAN-FD

CAN-FD frames have struct canfd_frame::flags, while classic CAN frames
don't.

This patch refuses to set TX flags (struct
can_isotp_ll_options::tx_flags) on non CAN-FD isotp sockets.

Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol")
Link: https://lore.kernel.org/r/20210218215434.1708249-2-mkl@pengutronix.de
Cc: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/isotp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/can/isotp.c b/net/can/isotp.c
index 3ef7f78e553b..e32d446c121e 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1228,7 +1228,8 @@ static int isotp_setsockopt(struct socket *sock, int level, int optname,
 			if (ll.mtu != CAN_MTU && ll.mtu != CANFD_MTU)
 				return -EINVAL;
 
-			if (ll.mtu == CAN_MTU && ll.tx_dl > CAN_MAX_DLEN)
+			if (ll.mtu == CAN_MTU &&
+			    (ll.tx_dl > CAN_MAX_DLEN || ll.tx_flags != 0))
 				return -EINVAL;
 
 			memcpy(&so->ll, &ll, sizeof(ll));

From d4eb538e1f48b3cf7bb6cb9eb39fe3e9e8a701f7 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 18 Feb 2021 21:24:20 +0100
Subject: [PATCH 0868/1820] can: isotp: TX-path: ensure that CAN frame flags
 are initialized

The previous patch ensures that the TX flags (struct
can_isotp_ll_options::tx_flags) are 0 for classic CAN frames or a user
configured value for CAN-FD frames.

This patch sets the CAN frames flags unconditionally to the ISO-TP TX
flags, so that they are initialized to a proper value. Otherwise when
running "candump -x" on a classical CAN ISO-TP stream shows wrongly
set "B" and "E" flags.

| $ candump any,0:0,#FFFFFFFF -extA
| [...]
| can0  TX B E  713   [8]  2B 0A 0B 0C 0D 0E 0F 00
| can0  TX B E  713   [8]  2C 01 02 03 04 05 06 07
| can0  TX B E  713   [8]  2D 08 09 0A 0B 0C 0D 0E
| can0  TX B E  713   [8]  2E 0F 00 01 02 03 04 05

Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol")
Link: https://lore.kernel.org/r/20210218215434.1708249-2-mkl@pengutronix.de
Cc: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/isotp.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/can/isotp.c b/net/can/isotp.c
index e32d446c121e..430976485d95 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -215,8 +215,7 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus)
 	if (ae)
 		ncf->data[0] = so->opt.ext_address;
 
-	if (so->ll.mtu == CANFD_MTU)
-		ncf->flags = so->ll.tx_flags;
+	ncf->flags = so->ll.tx_flags;
 
 	can_send_ret = can_send(nskb, 1);
 	if (can_send_ret)
@@ -790,8 +789,7 @@ isotp_tx_burst:
 		so->tx.sn %= 16;
 		so->tx.bs++;
 
-		if (so->ll.mtu == CANFD_MTU)
-			cf->flags = so->ll.tx_flags;
+		cf->flags = so->ll.tx_flags;
 
 		skb->dev = dev;
 		can_skb_set_owner(skb, sk);
@@ -939,8 +937,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	}
 
 	/* send the first or only CAN frame */
-	if (so->ll.mtu == CANFD_MTU)
-		cf->flags = so->ll.tx_flags;
+	cf->flags = so->ll.tx_flags;
 
 	skb->dev = dev;
 	skb->sk = sk;

From 59ec7b89ed3e921cd0625a8c83f31a30d485fdf8 Mon Sep 17 00:00:00 2001
From: Stephane Grosjean <s.grosjean@peak-system.com>
Date: Tue, 9 Mar 2021 09:21:27 +0100
Subject: [PATCH 0869/1820] can: peak_usb: add forgotten supported devices

Since the peak_usb driver also supports the CAN-USB interfaces
"PCAN-USB X6" and "PCAN-Chip USB" from PEAK-System GmbH, this patch adds
their names to the list of explicitly supported devices.

Fixes: ea8b65b596d7 ("can: usb: Add support of PCAN-Chip USB stamp module")
Fixes: f00b534ded60 ("can: peak: Add support for PCAN-USB X6 USB interface")
Link: https://lore.kernel.org/r/20210309082128.23125-3-s.grosjean@peak-system.com
Signed-off-by: Stephane Grosjean <s.grosjean@peak-system.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/peak_usb/pcan_usb_fd.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index f347ecc79aef..f1d018218c93 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -18,6 +18,8 @@
 
 MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB FD adapter");
 MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro FD adapter");
+MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-Chip USB");
+MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB X6 adapter");
 
 #define PCAN_USBPROFD_CHANNEL_COUNT	2
 #define PCAN_USBFD_CHANNEL_COUNT	1

From 47c5e474bc1e1061fb037d13b5000b38967eb070 Mon Sep 17 00:00:00 2001
From: Angelo Dureghello <angelo@kernel-space.org>
Date: Tue, 16 Mar 2021 00:15:10 +0100
Subject: [PATCH 0870/1820] can: flexcan: flexcan_chip_freeze(): fix chip
 freeze for missing bitrate

For cases when flexcan is built-in, bitrate is still not set at
registering. So flexcan_chip_freeze() generates:

[    1.860000] *** ZERO DIVIDE ***   FORMAT=4
[    1.860000] Current process id is 1
[    1.860000] BAD KERNEL TRAP: 00000000
[    1.860000] PC: [<402e70c8>] flexcan_chip_freeze+0x1a/0xa8

To allow chip freeze, using an hardcoded timeout when bitrate is still
not set.

Fixes: ec15e27cc890 ("can: flexcan: enable RX FIFO after FRZ/HALT valid")
Link: https://lore.kernel.org/r/20210315231510.650593-1-angelo@kernel-space.org
Signed-off-by: Angelo Dureghello <angelo@kernel-space.org>
[mkl: use if instead of ? operator]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 134c05757a3b..57f3635ad8d7 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -697,9 +697,15 @@ static int flexcan_chip_disable(struct flexcan_priv *priv)
 static int flexcan_chip_freeze(struct flexcan_priv *priv)
 {
 	struct flexcan_regs __iomem *regs = priv->regs;
-	unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate;
+	unsigned int timeout;
+	u32 bitrate = priv->can.bittiming.bitrate;
 	u32 reg;
 
+	if (bitrate)
+		timeout = 1000 * 1000 * 10 / bitrate;
+	else
+		timeout = FLEXCAN_TIMEOUT_US / 10;
+
 	reg = priv->read(&regs->mcr);
 	reg |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT;
 	priv->write(reg, &regs->mcr);

From 7c6e6bce08f918b64459415f58061d4d6df44994 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Tue, 9 Mar 2021 10:17:23 +0100
Subject: [PATCH 0871/1820] can: kvaser_pciefd: Always disable bus load
 reporting

Under certain circumstances, when switching from Kvaser's linuxcan driver
(kvpciefd) to the SocketCAN driver (kvaser_pciefd), the bus load reporting
is not disabled.
This is flooding the kernel log with prints like:
[3485.574677] kvaser_pciefd 0000:02:00.0: Received unexpected packet type 0x00000009

Always put the controller in the expected state, instead of assuming that
bus load reporting is inactive.

Note: If bus load reporting is enabled when the driver is loaded, you will
      still get a number of bus load packages (and printouts), before it is
      disabled.

Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices")
Link: https://lore.kernel.org/r/20210309091724.31262-1-jimmyassarsson@gmail.com
Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/kvaser_pciefd.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index 37e05010ca91..74d9899fc904 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -57,6 +57,7 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices");
 #define KVASER_PCIEFD_KCAN_STAT_REG 0x418
 #define KVASER_PCIEFD_KCAN_MODE_REG 0x41c
 #define KVASER_PCIEFD_KCAN_BTRN_REG 0x420
+#define KVASER_PCIEFD_KCAN_BUS_LOAD_REG 0x424
 #define KVASER_PCIEFD_KCAN_BTRD_REG 0x428
 #define KVASER_PCIEFD_KCAN_PWM_REG 0x430
 /* Loopback control register */
@@ -949,6 +950,9 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		timer_setup(&can->bec_poll_timer, kvaser_pciefd_bec_poll_timer,
 			    0);
 
+		/* Disable Bus load reporting */
+		iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_BUS_LOAD_REG);
+
 		tx_npackets = ioread32(can->reg_base +
 				       KVASER_PCIEFD_KCAN_TX_NPACKETS_REG);
 		if (((tx_npackets >> KVASER_PCIEFD_KCAN_TX_NPACKETS_MAX_SHIFT) &

From 7507479c46b120c37ef83e59be7683a526e98e1a Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Tue, 9 Mar 2021 10:17:24 +0100
Subject: [PATCH 0872/1820] can: kvaser_usb: Add support for USBcan Pro 4xHS

Add support for Kvaser USBcan Pro 4xHS.

Link: https://lore.kernel.org/r/20210309091724.31262-2-jimmyassarsson@gmail.com
Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/Kconfig                      | 1 +
 drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index c1e5d5b570b6..538f4d9adb91 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -73,6 +73,7 @@ config CAN_KVASER_USB
 	    - Kvaser Memorator Pro 5xHS
 	    - Kvaser USBcan Light 4xHS
 	    - Kvaser USBcan Pro 2xHS v2
+	    - Kvaser USBcan Pro 4xHS
 	    - Kvaser USBcan Pro 5xHS
 	    - Kvaser U100
 	    - Kvaser U100P
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 2b7efd296758..4e97da8434ab 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -86,8 +86,9 @@
 #define USB_U100_PRODUCT_ID			273
 #define USB_U100P_PRODUCT_ID			274
 #define USB_U100S_PRODUCT_ID			275
+#define USB_USBCAN_PRO_4HS_PRODUCT_ID		276
 #define USB_HYDRA_PRODUCT_ID_END \
-	USB_U100S_PRODUCT_ID
+	USB_USBCAN_PRO_4HS_PRODUCT_ID
 
 static inline bool kvaser_is_leaf(const struct usb_device_id *id)
 {
@@ -193,6 +194,7 @@ static const struct usb_device_id kvaser_usb_table[] = {
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100P_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100S_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_4HS_PRODUCT_ID) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, kvaser_usb_table);

From 0429d6d89f97ebff4f17f13f5b5069c66bde8138 Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Sun, 28 Feb 2021 21:45:11 -0500
Subject: [PATCH 0873/1820] can: c_can_pci: c_can_pci_remove(): fix
 use-after-free

There is a UAF in c_can_pci_remove(). dev is released by
free_c_can_dev() and is used by pci_iounmap(pdev, priv->base) later.
To fix this issue, save the mmio address before releasing dev.

Fixes: 5b92da0443c2 ("c_can_pci: generic module for C_CAN/D_CAN on PCI")
Link: https://lore.kernel.org/r/20210301024512.539039-1-ztong0001@gmail.com
Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/c_can/c_can_pci.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/c_can/c_can_pci.c b/drivers/net/can/c_can/c_can_pci.c
index 406b4847e5dc..7efb60b50876 100644
--- a/drivers/net/can/c_can/c_can_pci.c
+++ b/drivers/net/can/c_can/c_can_pci.c
@@ -239,12 +239,13 @@ static void c_can_pci_remove(struct pci_dev *pdev)
 {
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct c_can_priv *priv = netdev_priv(dev);
+	void __iomem *addr = priv->base;
 
 	unregister_c_can_dev(dev);
 
 	free_c_can_dev(dev);
 
-	pci_iounmap(pdev, priv->base);
+	pci_iounmap(pdev, addr);
 	pci_disable_msi(pdev);
 	pci_clear_master(pdev);
 	pci_release_regions(pdev);

From 6e2fe01dd6f98da6cae8b07cd5cfa67abc70d97d Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Mon, 1 Mar 2021 21:55:40 -0500
Subject: [PATCH 0874/1820] can: c_can: move runtime PM enable/disable to
 c_can_platform
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently doing modprobe c_can_pci will make the kernel complain:

    Unbalanced pm_runtime_enable!

this is caused by pm_runtime_enable() called before pm is initialized.

This fix is similar to 227619c3ff7c, move those pm_enable/disable code
to c_can_platform.

Fixes: 4cdd34b26826 ("can: c_can: Add runtime PM support to Bosch C_CAN/D_CAN controller")
Link: http://lore.kernel.org/r/20210302025542.987600-1-ztong0001@gmail.com
Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/c_can/c_can.c          | 24 +-----------------------
 drivers/net/can/c_can/c_can_platform.c |  6 +++++-
 2 files changed, 6 insertions(+), 24 deletions(-)

diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index ef474bae47a1..6958830cb983 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -212,18 +212,6 @@ static const struct can_bittiming_const c_can_bittiming_const = {
 	.brp_inc = 1,
 };
 
-static inline void c_can_pm_runtime_enable(const struct c_can_priv *priv)
-{
-	if (priv->device)
-		pm_runtime_enable(priv->device);
-}
-
-static inline void c_can_pm_runtime_disable(const struct c_can_priv *priv)
-{
-	if (priv->device)
-		pm_runtime_disable(priv->device);
-}
-
 static inline void c_can_pm_runtime_get_sync(const struct c_can_priv *priv)
 {
 	if (priv->device)
@@ -1335,7 +1323,6 @@ static const struct net_device_ops c_can_netdev_ops = {
 
 int register_c_can_dev(struct net_device *dev)
 {
-	struct c_can_priv *priv = netdev_priv(dev);
 	int err;
 
 	/* Deactivate pins to prevent DRA7 DCAN IP from being
@@ -1345,28 +1332,19 @@ int register_c_can_dev(struct net_device *dev)
 	 */
 	pinctrl_pm_select_sleep_state(dev->dev.parent);
 
-	c_can_pm_runtime_enable(priv);
-
 	dev->flags |= IFF_ECHO;	/* we support local echo */
 	dev->netdev_ops = &c_can_netdev_ops;
 
 	err = register_candev(dev);
-	if (err)
-		c_can_pm_runtime_disable(priv);
-	else
+	if (!err)
 		devm_can_led_init(dev);
-
 	return err;
 }
 EXPORT_SYMBOL_GPL(register_c_can_dev);
 
 void unregister_c_can_dev(struct net_device *dev)
 {
-	struct c_can_priv *priv = netdev_priv(dev);
-
 	unregister_candev(dev);
-
-	c_can_pm_runtime_disable(priv);
 }
 EXPORT_SYMBOL_GPL(unregister_c_can_dev);
 
diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index 05f425ceb53a..47b251b1607c 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -29,6 +29,7 @@
 #include <linux/list.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/clk.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -386,6 +387,7 @@ static int c_can_plat_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, dev);
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
+	pm_runtime_enable(priv->device);
 	ret = register_c_can_dev(dev);
 	if (ret) {
 		dev_err(&pdev->dev, "registering %s failed (err=%d)\n",
@@ -398,6 +400,7 @@ static int c_can_plat_probe(struct platform_device *pdev)
 	return 0;
 
 exit_free_device:
+	pm_runtime_disable(priv->device);
 	free_c_can_dev(dev);
 exit:
 	dev_err(&pdev->dev, "probe failed\n");
@@ -408,9 +411,10 @@ exit:
 static int c_can_plat_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
+	struct c_can_priv *priv = netdev_priv(dev);
 
 	unregister_c_can_dev(dev);
-
+	pm_runtime_disable(priv->device);
 	free_c_can_dev(dev);
 
 	return 0;

From c0e399f3baf42279f48991554240af8c457535d1 Mon Sep 17 00:00:00 2001
From: Torin Cooper-Bennun <torin@maxiluxsystems.com>
Date: Wed, 3 Mar 2021 10:31:52 +0000
Subject: [PATCH 0875/1820] can: m_can: m_can_do_rx_poll(): fix extraneous msg
 loss warning

Message loss from RX FIFO 0 is already handled in
m_can_handle_lost_msg(), with netdev output included.

Removing this warning also improves driver performance under heavy
load, where m_can_do_rx_poll() may be called many times before this
interrupt is cleared, causing this message to be output many
times (thanks Mariusz Madej for this report).

Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support")
Link: https://lore.kernel.org/r/20210303103151.3760532-1-torin@maxiluxsystems.com
Reported-by: Mariusz Madej <mariusz.madej@xtrack.com>
Signed-off-by: Torin Cooper-Bennun <torin@maxiluxsystems.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 3752520a7d4b..d783c46cac16 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -501,9 +501,6 @@ static int m_can_do_rx_poll(struct net_device *dev, int quota)
 	}
 
 	while ((rxfs & RXFS_FFL_MASK) && (quota > 0)) {
-		if (rxfs & RXFS_RFL)
-			netdev_warn(dev, "Rx FIFO 0 Message Lost\n");
-
 		m_can_read_fifo(dev, rxfs);
 
 		quota--;

From e98d9ee64ee2cc9b1d1a8e26610ec4d0392ebe50 Mon Sep 17 00:00:00 2001
From: Torin Cooper-Bennun <torin@maxiluxsystems.com>
Date: Wed, 3 Mar 2021 14:43:51 +0000
Subject: [PATCH 0876/1820] can: m_can: m_can_rx_peripheral(): fix RX being
 blocked by errors

For M_CAN peripherals, m_can_rx_handler() was called with quota = 1,
which caused any error handling to block RX from taking place until
the next time the IRQ handler is called. This had been observed to
cause RX to be blocked indefinitely in some cases.

This is fixed by calling m_can_rx_handler with a sensibly high quota.

Fixes: f524f829b75a ("can: m_can: Create a m_can platform framework")
Link: https://lore.kernel.org/r/20210303144350.4093750-1-torin@maxiluxsystems.com
Suggested-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Torin Cooper-Bennun <torin@maxiluxsystems.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index d783c46cac16..0c8d36bc668c 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -873,7 +873,7 @@ static int m_can_rx_peripheral(struct net_device *dev)
 {
 	struct m_can_classdev *cdev = netdev_priv(dev);
 
-	m_can_rx_handler(dev, 1);
+	m_can_rx_handler(dev, M_CAN_NAPI_WEIGHT);
 
 	m_can_enable_all_interrupts(cdev);
 

From e7d66cf799390166e90f9a5715f2eede4fe06d51 Mon Sep 17 00:00:00 2001
From: Jeremy Szu <jeremy.szu@canonical.com>
Date: Tue, 16 Mar 2021 15:46:24 +0800
Subject: [PATCH 0877/1820] ALSA: hda/realtek: fix mute/micmute LEDs for HP 440
 G8

The HP EliteBook 840 G8 Notebook PC is using ALC236 codec which is
using 0x02 to control mute LED and 0x01 to control micmute LED.
Therefore, add a quirk to make it works.

Signed-off-by: Jeremy Szu <jeremy.szu@canonical.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210316074626.79895-1-jeremy.szu@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f06bcb1ac4f9..145d6cf4939e 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4225,6 +4225,12 @@ static void alc_fixup_hp_gpio_led(struct hda_codec *codec,
 	}
 }
 
+static void alc236_fixup_hp_gpio_led(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	alc_fixup_hp_gpio_led(codec, action, 0x02, 0x01);
+}
+
 static void alc269_fixup_hp_gpio_led(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
@@ -6381,6 +6387,7 @@ enum {
 	ALC294_FIXUP_ASUS_GX502_VERBS,
 	ALC285_FIXUP_HP_GPIO_LED,
 	ALC285_FIXUP_HP_MUTE_LED,
+	ALC236_FIXUP_HP_GPIO_LED,
 	ALC236_FIXUP_HP_MUTE_LED,
 	ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
 	ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
@@ -7616,6 +7623,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc285_fixup_hp_mute_led,
 	},
+	[ALC236_FIXUP_HP_GPIO_LED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc236_fixup_hp_gpio_led,
+	},
 	[ALC236_FIXUP_HP_MUTE_LED] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc236_fixup_hp_mute_led,
@@ -8045,6 +8056,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8783, "HP ZBook Fury 15 G7 Mobile Workstation",
 		      ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),

From 1601ea068b886da1f8f8d4e18b9403e9e24adef6 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@wdc.com>
Date: Mon, 15 Mar 2021 12:43:55 +0900
Subject: [PATCH 0878/1820] zonefs: prevent use of seq files as swap file

The sequential write constraint of sequential zone file prevent their
use as swap files. Only allow conventional zone files to be used as swap
files.

Fixes: 8dcc1a9d90c1 ("fs: New zonefs file system")
Cc: <stable@vger.kernel.org>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
---
 fs/zonefs/super.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 0fe76f376dee..a3d074f98660 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -165,6 +165,21 @@ static int zonefs_writepages(struct address_space *mapping,
 	return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
 }
 
+static int zonefs_swap_activate(struct swap_info_struct *sis,
+				struct file *swap_file, sector_t *span)
+{
+	struct inode *inode = file_inode(swap_file);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+	if (zi->i_ztype != ZONEFS_ZTYPE_CNV) {
+		zonefs_err(inode->i_sb,
+			   "swap file: not a conventional zone file\n");
+		return -EINVAL;
+	}
+
+	return iomap_swapfile_activate(sis, swap_file, span, &zonefs_iomap_ops);
+}
+
 static const struct address_space_operations zonefs_file_aops = {
 	.readpage		= zonefs_readpage,
 	.readahead		= zonefs_readahead,
@@ -177,6 +192,7 @@ static const struct address_space_operations zonefs_file_aops = {
 	.is_partially_uptodate	= iomap_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
 	.direct_IO		= noop_direct_IO,
+	.swap_activate		= zonefs_swap_activate,
 };
 
 static void zonefs_update_stats(struct inode *inode, loff_t new_isize)

From ebfd68cd0c1e81267c757332385cb96df30dacce Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@wdc.com>
Date: Wed, 10 Mar 2021 15:20:28 +0900
Subject: [PATCH 0879/1820] zonefs: Fix O_APPEND async write handling

zonefs updates the size of a sequential zone file inode only on
completion of direct writes. When executing asynchronous append writes
(with a file open with O_APPEND or using RWF_APPEND), the use of the
current inode size in generic_write_checks() to set an iocb offset thus
leads to unaligned write if an application issues an append write
operation with another write already being executed.

Fix this problem by introducing zonefs_write_checks() as a modified
version of generic_write_checks() using the file inode wp_offset for an
append write iocb offset. Also introduce zonefs_write_check_limits() to
replace generic_write_check_limits() call. This zonefs special helper
makes sure that the maximum file limit used is the maximum size of the
file being accessed.

Since zonefs_write_checks() already truncates the iov_iter, the calls
to iov_iter_truncate() in zonefs_file_dio_write() and
zonefs_file_buffered_write() are removed.

Fixes: 8dcc1a9d90c1 ("fs: New zonefs file system")
Cc: <stable@vger.kernel.org>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
---
 fs/zonefs/super.c | 78 +++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 68 insertions(+), 10 deletions(-)

diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index a3d074f98660..3427c99abb4d 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -743,6 +743,68 @@ out_release:
 	return ret;
 }
 
+/*
+ * Do not exceed the LFS limits nor the file zone size. If pos is under the
+ * limit it becomes a short access. If it exceeds the limit, return -EFBIG.
+ */
+static loff_t zonefs_write_check_limits(struct file *file, loff_t pos,
+					loff_t count)
+{
+	struct inode *inode = file_inode(file);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	loff_t limit = rlimit(RLIMIT_FSIZE);
+	loff_t max_size = zi->i_max_size;
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		count = min(count, limit - pos);
+	}
+
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = min_t(loff_t, MAX_NON_LFS, max_size);
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+
+	return min(count, max_size - pos);
+}
+
+static ssize_t zonefs_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	loff_t count;
+
+	if (IS_SWAPFILE(inode))
+		return -ETXTBSY;
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+		return -EINVAL;
+
+	if (iocb->ki_flags & IOCB_APPEND) {
+		if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
+			return -EINVAL;
+		mutex_lock(&zi->i_truncate_mutex);
+		iocb->ki_pos = zi->i_wpoffset;
+		mutex_unlock(&zi->i_truncate_mutex);
+	}
+
+	count = zonefs_write_check_limits(file, iocb->ki_pos,
+					  iov_iter_count(from));
+	if (count < 0)
+		return count;
+
+	iov_iter_truncate(from, count);
+	return iov_iter_count(from);
+}
+
 /*
  * Handle direct writes. For sequential zone files, this is the only possible
  * write path. For these files, check that the user is issuing writes
@@ -760,8 +822,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 	struct super_block *sb = inode->i_sb;
 	bool sync = is_sync_kiocb(iocb);
 	bool append = false;
-	size_t count;
-	ssize_t ret;
+	ssize_t ret, count;
 
 	/*
 	 * For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
@@ -779,12 +840,11 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 		inode_lock(inode);
 	}
 
-	ret = generic_write_checks(iocb, from);
-	if (ret <= 0)
+	count = zonefs_write_checks(iocb, from);
+	if (count <= 0) {
+		ret = count;
 		goto inode_unlock;
-
-	iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
-	count = iov_iter_count(from);
+	}
 
 	if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
 		ret = -EINVAL;
@@ -844,12 +904,10 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
 		inode_lock(inode);
 	}
 
-	ret = generic_write_checks(iocb, from);
+	ret = zonefs_write_checks(iocb, from);
 	if (ret <= 0)
 		goto inode_unlock;
 
-	iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
-
 	ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops);
 	if (ret > 0)
 		iocb->ki_pos += ret;

From 6cb59afe9e5b45a035bd6b97da6593743feefc72 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 15 Mar 2021 20:44:30 +0200
Subject: [PATCH 0880/1820] gpiolib: Assign fwnode to parent's if no primary
 one provided

In case when the properties are supplied in the secondary fwnode
(for example, built-in device properties) the fwnode pointer left
unassigned. This makes unable to retrieve them.

Assign fwnode to parent's if no primary one provided.

Fixes: 7cba1a4d5e16 ("gpiolib: generalize devprop_gpiochip_set_names() for device properties")
Fixes: 2afa97e9868f ("gpiolib: Read "gpio-line-names" from a firmware node")
Reported-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Tested-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 drivers/gpio/gpiolib.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 6635e4ec60ce..6367646dce83 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -571,6 +571,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 			       struct lock_class_key *lock_key,
 			       struct lock_class_key *request_key)
 {
+	struct fwnode_handle *fwnode = gc->parent ? dev_fwnode(gc->parent) : NULL;
 	unsigned long	flags;
 	int		ret = 0;
 	unsigned	i;
@@ -594,6 +595,12 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 
 	of_gpio_dev_init(gc, gdev);
 
+	/*
+	 * Assign fwnode depending on the result of the previous calls,
+	 * if none of them succeed, assign it to the parent's one.
+	 */
+	gdev->dev.fwnode = dev_fwnode(&gdev->dev) ?: fwnode;
+
 	gdev->id = ida_alloc(&gpio_ida, GFP_KERNEL);
 	if (gdev->id < 0) {
 		ret = gdev->id;

From d9bb77d51e668a1a6d4530c1ea471574d0ce465f Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 15 Mar 2021 13:39:14 +0800
Subject: [PATCH 0881/1820] btrfs: subpage: fix wild pointer access during
 metadata read failure

[BUG]
When running fstests for btrfs subpage read-write test, it has a very
high chance to crash at generic/475 with the following stack:

 BTRFS warning (device dm-8): direct IO failed ino 510 rw 1,34817 sector 0xcdf0 len 94208 err no 10
 Unable to handle kernel paging request at virtual address ffff80001157e7c0
 CPU: 2 PID: 687125 Comm: kworker/u12:4 Tainted: G        WC        5.12.0-rc2-custom+ #5
 Hardware name: Khadas VIM3 (DT)
 Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs]
 pc : queued_spin_lock_slowpath+0x1a0/0x390
 lr : do_raw_spin_lock+0xc4/0x11c
 Call trace:
  queued_spin_lock_slowpath+0x1a0/0x390
  _raw_spin_lock+0x68/0x84
  btree_readahead_hook+0x38/0xc0 [btrfs]
  end_bio_extent_readpage+0x504/0x5f4 [btrfs]
  bio_endio+0x170/0x1a4
  end_workqueue_fn+0x3c/0x60 [btrfs]
  btrfs_work_helper+0x1b0/0x1b4 [btrfs]
  process_one_work+0x22c/0x430
  worker_thread+0x70/0x3a0
  kthread+0x13c/0x140
  ret_from_fork+0x10/0x30
 Code: 910020e0 8b0200c2 f861d884 aa0203e1 (f8246827)

[CAUSE]
In end_bio_extent_readpage(), if we hit an error during read, we will
handle the error differently for data and metadata.
For data we queue a repair, while for metadata, we record the error and
let the caller choose what to do.

But the code is still using page->private to grab extent buffer, which
no longer points to extent buffer for subpage metadata pages.

Thus this wild pointer access leads to above crash.

[FIX]
Introduce a helper, find_extent_buffer_readpage(), to grab extent
buffer.

The difference against find_extent_buffer_nospinlock() is:

- Also handles regular sectorsize == PAGE_SIZE case
- No extent buffer refs increase/decrease
  As extent buffer under IO must have non-zero refs, so this is safe

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f3d7be975c3a..0d00a9cd123a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2885,6 +2885,35 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
 		btrfs_subpage_end_reader(fs_info, page, start, len);
 }
 
+/*
+ * Find extent buffer for a givne bytenr.
+ *
+ * This is for end_bio_extent_readpage(), thus we can't do any unsafe locking
+ * in endio context.
+ */
+static struct extent_buffer *find_extent_buffer_readpage(
+		struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
+{
+	struct extent_buffer *eb;
+
+	/*
+	 * For regular sectorsize, we can use page->private to grab extent
+	 * buffer
+	 */
+	if (fs_info->sectorsize == PAGE_SIZE) {
+		ASSERT(PagePrivate(page) && page->private);
+		return (struct extent_buffer *)page->private;
+	}
+
+	/* For subpage case, we need to lookup buffer radix tree */
+	rcu_read_lock();
+	eb = radix_tree_lookup(&fs_info->buffer_radix,
+			       bytenr >> fs_info->sectorsize_bits);
+	rcu_read_unlock();
+	ASSERT(eb);
+	return eb;
+}
+
 /*
  * after a readpage IO is done, we need to:
  * clear the uptodate bits on error
@@ -2996,7 +3025,7 @@ static void end_bio_extent_readpage(struct bio *bio)
 		} else {
 			struct extent_buffer *eb;
 
-			eb = (struct extent_buffer *)page->private;
+			eb = find_extent_buffer_readpage(fs_info, page, start);
 			set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 			eb->read_mirror = mirror;
 			atomic_dec(&eb->io_pages);

From 60484cd9d50117017cf53d5310c6cd629600dc69 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 15 Mar 2021 13:39:15 +0800
Subject: [PATCH 0882/1820] btrfs: subpage: make readahead work properly

In readahead infrastructure, we are using a lot of hard coded PAGE_SHIFT
while we're not doing anything specific to PAGE_SIZE.

One of the most affected part is the radix tree operation of
btrfs_fs_info::reada_tree.

If using PAGE_SHIFT, subpage metadata readahead is broken and does no
help reading metadata ahead.

Fix the problem by using btrfs_fs_info::sectorsize_bits so that
readahead could work for subpage.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/reada.c | 35 ++++++++++++++++++-----------------
 1 file changed, 18 insertions(+), 17 deletions(-)

diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 20fd4aa48a8c..06713a8fe26b 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -209,7 +209,7 @@ int btree_readahead_hook(struct extent_buffer *eb, int err)
 	/* find extent */
 	spin_lock(&fs_info->reada_lock);
 	re = radix_tree_lookup(&fs_info->reada_tree,
-			       eb->start >> PAGE_SHIFT);
+			       eb->start >> fs_info->sectorsize_bits);
 	if (re)
 		re->refcnt++;
 	spin_unlock(&fs_info->reada_lock);
@@ -240,7 +240,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
 	zone = NULL;
 	spin_lock(&fs_info->reada_lock);
 	ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
-				     logical >> PAGE_SHIFT, 1);
+				     logical >> fs_info->sectorsize_bits, 1);
 	if (ret == 1 && logical >= zone->start && logical <= zone->end) {
 		kref_get(&zone->refcnt);
 		spin_unlock(&fs_info->reada_lock);
@@ -283,13 +283,13 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
 
 	spin_lock(&fs_info->reada_lock);
 	ret = radix_tree_insert(&dev->reada_zones,
-				(unsigned long)(zone->end >> PAGE_SHIFT),
-				zone);
+			(unsigned long)(zone->end >> fs_info->sectorsize_bits),
+			zone);
 
 	if (ret == -EEXIST) {
 		kfree(zone);
 		ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
-					     logical >> PAGE_SHIFT, 1);
+					logical >> fs_info->sectorsize_bits, 1);
 		if (ret == 1 && logical >= zone->start && logical <= zone->end)
 			kref_get(&zone->refcnt);
 		else
@@ -315,7 +315,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 	u64 length;
 	int real_stripes;
 	int nzones = 0;
-	unsigned long index = logical >> PAGE_SHIFT;
+	unsigned long index = logical >> fs_info->sectorsize_bits;
 	int dev_replace_is_ongoing;
 	int have_zone = 0;
 
@@ -497,7 +497,7 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
 			     struct reada_extent *re)
 {
 	int i;
-	unsigned long index = re->logical >> PAGE_SHIFT;
+	unsigned long index = re->logical >> fs_info->sectorsize_bits;
 
 	spin_lock(&fs_info->reada_lock);
 	if (--re->refcnt) {
@@ -538,11 +538,12 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
 static void reada_zone_release(struct kref *kref)
 {
 	struct reada_zone *zone = container_of(kref, struct reada_zone, refcnt);
+	struct btrfs_fs_info *fs_info = zone->device->fs_info;
 
-	lockdep_assert_held(&zone->device->fs_info->reada_lock);
+	lockdep_assert_held(&fs_info->reada_lock);
 
 	radix_tree_delete(&zone->device->reada_zones,
-			  zone->end >> PAGE_SHIFT);
+			  zone->end >> fs_info->sectorsize_bits);
 
 	kfree(zone);
 }
@@ -593,7 +594,7 @@ static int reada_add_block(struct reada_control *rc, u64 logical,
 static void reada_peer_zones_set_lock(struct reada_zone *zone, int lock)
 {
 	int i;
-	unsigned long index = zone->end >> PAGE_SHIFT;
+	unsigned long index = zone->end >> zone->device->fs_info->sectorsize_bits;
 
 	for (i = 0; i < zone->ndevs; ++i) {
 		struct reada_zone *peer;
@@ -628,7 +629,7 @@ static int reada_pick_zone(struct btrfs_device *dev)
 					     (void **)&zone, index, 1);
 		if (ret == 0)
 			break;
-		index = (zone->end >> PAGE_SHIFT) + 1;
+		index = (zone->end >> dev->fs_info->sectorsize_bits) + 1;
 		if (zone->locked) {
 			if (zone->elems > top_locked_elems) {
 				top_locked_elems = zone->elems;
@@ -709,7 +710,7 @@ static int reada_start_machine_dev(struct btrfs_device *dev)
 	 * plugging to speed things up
 	 */
 	ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re,
-				     dev->reada_next >> PAGE_SHIFT, 1);
+				dev->reada_next >> fs_info->sectorsize_bits, 1);
 	if (ret == 0 || re->logical > dev->reada_curr_zone->end) {
 		ret = reada_pick_zone(dev);
 		if (!ret) {
@@ -718,7 +719,7 @@ static int reada_start_machine_dev(struct btrfs_device *dev)
 		}
 		re = NULL;
 		ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re,
-					dev->reada_next >> PAGE_SHIFT, 1);
+				dev->reada_next >> fs_info->sectorsize_bits, 1);
 	}
 	if (ret == 0) {
 		spin_unlock(&fs_info->reada_lock);
@@ -885,7 +886,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 				pr_cont(" curr off %llu",
 					device->reada_next - zone->start);
 			pr_cont("\n");
-			index = (zone->end >> PAGE_SHIFT) + 1;
+			index = (zone->end >> fs_info->sectorsize_bits) + 1;
 		}
 		cnt = 0;
 		index = 0;
@@ -910,7 +911,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 				}
 			}
 			pr_cont("\n");
-			index = (re->logical >> PAGE_SHIFT) + 1;
+			index = (re->logical >> fs_info->sectorsize_bits) + 1;
 			if (++cnt > 15)
 				break;
 		}
@@ -926,7 +927,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 		if (ret == 0)
 			break;
 		if (!re->scheduled) {
-			index = (re->logical >> PAGE_SHIFT) + 1;
+			index = (re->logical >> fs_info->sectorsize_bits) + 1;
 			continue;
 		}
 		pr_debug("re: logical %llu size %u list empty %d scheduled %d",
@@ -942,7 +943,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 			}
 		}
 		pr_cont("\n");
-		index = (re->logical >> PAGE_SHIFT) + 1;
+		index = (re->logical >> fs_info->sectorsize_bits) + 1;
 	}
 	spin_unlock(&fs_info->reada_lock);
 }

From f8d70fd6a5a7a38a95eb8021e00d2e547f88efec Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Sat, 13 Mar 2021 14:58:02 +0100
Subject: [PATCH 0883/1820] MAINTAINERS: move some real subsystems off of the
 staging mailing list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The VME and Android drivers still have their MAINTAINERS entries
pointing to the "driverdevel" mailing list, due to them having their
codebase move out of the drivers/staging/ directory, but no one
remembered to change the mailing list entries.

Move them both to linux-kernel for lack of a more specific place at the
moment.  These are both low-volume areas of the kernel, so this
shouldn't be an issue.

Cc: Martyn Welch <martyn@welchs.me.uk>
Cc: Manohar Vanga <manohar.vanga@gmail.com>
Cc: Arve Hjønnevåg <arve@android.com>
Cc: Todd Kjos <tkjos@android.com>
Cc: Martijn Coenen <maco@android.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Christian Brauner <christian@brauner.io>
Cc: Hridya Valsaraju <hridya@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Reported-by: Konstantin Ryabitsev <konstantin@linuxfoundation.org>
Link: https://lore.kernel.org/r/YEzE6u6U1jkBatmr@kroah.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index aa84121c5611..d7c25c0fc08a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1181,7 +1181,7 @@ M:	Joel Fernandes <joel@joelfernandes.org>
 M:	Christian Brauner <christian@brauner.io>
 M:	Hridya Valsaraju <hridya@google.com>
 M:	Suren Baghdasaryan <surenb@google.com>
-L:	devel@driverdev.osuosl.org
+L:	linux-kernel@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging.git
 F:	drivers/android/
@@ -19135,7 +19135,7 @@ VME SUBSYSTEM
 M:	Martyn Welch <martyn@welchs.me.uk>
 M:	Manohar Vanga <manohar.vanga@gmail.com>
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-L:	devel@driverdev.osuosl.org
+L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
 F:	Documentation/driver-api/vme.rst

From 1cbd44666216278bbb6a55bcb6b9283702171c77 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Sun, 7 Mar 2021 06:06:28 +0200
Subject: [PATCH 0884/1820] dmaengine: xilinx: dpdma: Fix descriptor issuing on
 video group

When multiple channels are part of a video group, the transfer is
triggered only when all channels in the group are ready. The logic to do
so is incorrect, as it causes the descriptors for all channels but the
last one in a group to not being pushed to the hardware. Fix it.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://lore.kernel.org/r/20210307040629.29308-2-laurent.pinchart@ideasonboard.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xilinx_dpdma.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
index 55df63dead8d..d504112c609e 100644
--- a/drivers/dma/xilinx/xilinx_dpdma.c
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -839,6 +839,7 @@ static void xilinx_dpdma_chan_queue_transfer(struct xilinx_dpdma_chan *chan)
 	struct xilinx_dpdma_tx_desc *desc;
 	struct virt_dma_desc *vdesc;
 	u32 reg, channels;
+	bool first_frame;
 
 	lockdep_assert_held(&chan->lock);
 
@@ -852,14 +853,6 @@ static void xilinx_dpdma_chan_queue_transfer(struct xilinx_dpdma_chan *chan)
 		chan->running = true;
 	}
 
-	if (chan->video_group)
-		channels = xilinx_dpdma_chan_video_group_ready(chan);
-	else
-		channels = BIT(chan->id);
-
-	if (!channels)
-		return;
-
 	vdesc = vchan_next_desc(&chan->vchan);
 	if (!vdesc)
 		return;
@@ -884,13 +877,26 @@ static void xilinx_dpdma_chan_queue_transfer(struct xilinx_dpdma_chan *chan)
 			    FIELD_PREP(XILINX_DPDMA_CH_DESC_START_ADDRE_MASK,
 				       upper_32_bits(sw_desc->dma_addr)));
 
-	if (chan->first_frame)
+	first_frame = chan->first_frame;
+	chan->first_frame = false;
+
+	if (chan->video_group) {
+		channels = xilinx_dpdma_chan_video_group_ready(chan);
+		/*
+		 * Trigger the transfer only when all channels in the group are
+		 * ready.
+		 */
+		if (!channels)
+			return;
+	} else {
+		channels = BIT(chan->id);
+	}
+
+	if (first_frame)
 		reg = XILINX_DPDMA_GBL_TRIG_MASK(channels);
 	else
 		reg = XILINX_DPDMA_GBL_RETRIG_MASK(channels);
 
-	chan->first_frame = false;
-
 	dpdma_write(xdev->reg, XILINX_DPDMA_GBL, reg);
 }
 

From 868833fbffbe51c487df4f95d4de9194264a4b30 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Sun, 7 Mar 2021 06:06:29 +0200
Subject: [PATCH 0885/1820] dmaengine: xilinx: dpdma: Fix race condition in
 done IRQ

The active descriptor pointer is accessed from different contexts,
including different interrupt handlers, and its access must be protected
by the channel's lock. This wasn't done in the done IRQ handler. Fix it.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://lore.kernel.org/r/20210307040629.29308-3-laurent.pinchart@ideasonboard.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xilinx_dpdma.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
index d504112c609e..70b29bd079c9 100644
--- a/drivers/dma/xilinx/xilinx_dpdma.c
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -1048,13 +1048,14 @@ static int xilinx_dpdma_chan_stop(struct xilinx_dpdma_chan *chan)
  */
 static void xilinx_dpdma_chan_done_irq(struct xilinx_dpdma_chan *chan)
 {
-	struct xilinx_dpdma_tx_desc *active = chan->desc.active;
+	struct xilinx_dpdma_tx_desc *active;
 	unsigned long flags;
 
 	spin_lock_irqsave(&chan->lock, flags);
 
 	xilinx_dpdma_debugfs_desc_done_irq(chan);
 
+	active = chan->desc.active;
 	if (active)
 		vchan_cyclic_callback(&active->vdesc);
 	else

From e06da9ea3e3f6746a849edeae1d09ee821f5c2ce Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 16 Mar 2021 11:23:11 +0100
Subject: [PATCH 0886/1820] MAINTAINERS: move the staging subsystem to
 lists.linux.dev

The drivers/staging/ tree has a new mailing list,
linux-staging@lists.linux.dev, so move the MAINTAINER entry to point to
it so that we get patches sent to the proper place.

There was no need to specify a list for the hikey9xx driver, the tools
pick up the "base" list for drivers/staging/* so remove that line to
make the file simpler.

Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/20210316102311.182375-1-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d7c25c0fc08a..9e876927c60d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8116,7 +8116,6 @@ F:	drivers/crypto/hisilicon/sec2/sec_main.c
 
 HISILICON STAGING DRIVERS FOR HIKEY 960/970
 M:	Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
-L:	devel@driverdev.osuosl.org
 S:	Maintained
 F:	drivers/staging/hikey9xx/
 
@@ -17040,7 +17039,7 @@ F:	drivers/staging/vt665?/
 
 STAGING SUBSYSTEM
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-L:	devel@driverdev.osuosl.org
+L:	linux-staging@lists.linux.dev
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging.git
 F:	drivers/staging/

From 2e5848a3d86f03024ae096478bdb892ab3d79131 Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Mon, 15 Mar 2021 15:59:14 -0400
Subject: [PATCH 0887/1820] staging: comedi: cb_pcidas: fix request_irq() warn

request_irq() wont accept a name which contains slash so we need to
repalce it with something else -- otherwise it will trigger a warning
and the entry in /proc/irq/ will not be created
since the .name might be used by userspace and we don't want to break
userspace, so we are changing the parameters passed to request_irq()

[    1.630764] name 'pci-das1602/16'
[    1.630950] WARNING: CPU: 0 PID: 181 at fs/proc/generic.c:180 __xlate_proc_name+0x93/0xb0
[    1.634009] RIP: 0010:__xlate_proc_name+0x93/0xb0
[    1.639441] Call Trace:
[    1.639976]  proc_mkdir+0x18/0x20
[    1.641946]  request_threaded_irq+0xfe/0x160
[    1.642186]  cb_pcidas_auto_attach+0xf4/0x610 [cb_pcidas]

Suggested-by: Ian Abbott <abbotti@mev.co.uk>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Link: https://lore.kernel.org/r/20210315195914.4801-1-ztong0001@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/cb_pcidas.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/cb_pcidas.c b/drivers/staging/comedi/drivers/cb_pcidas.c
index d740c4782775..2f20bd56ec6c 100644
--- a/drivers/staging/comedi/drivers/cb_pcidas.c
+++ b/drivers/staging/comedi/drivers/cb_pcidas.c
@@ -1281,7 +1281,7 @@ static int cb_pcidas_auto_attach(struct comedi_device *dev,
 	     devpriv->amcc + AMCC_OP_REG_INTCSR);
 
 	ret = request_irq(pcidev->irq, cb_pcidas_interrupt, IRQF_SHARED,
-			  dev->board_name, dev);
+			  "cb_pcidas", dev);
 	if (ret) {
 		dev_dbg(dev->class_dev, "unable to allocate irq %d\n",
 			pcidev->irq);

From d2d106fe3badfc3bf0dd3899d1c3f210c7203eab Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Mon, 15 Mar 2021 15:58:12 -0400
Subject: [PATCH 0888/1820] staging: comedi: cb_pcidas64: fix request_irq()
 warn

request_irq() wont accept a name which contains slash so we need to
repalce it with something else -- otherwise it will trigger a warning
and the entry in /proc/irq/ will not be created
since the .name might be used by userspace and we don't want to break
userspace, so we are changing the parameters passed to request_irq()

[    1.565966] name 'pci-das6402/16'
[    1.566149] WARNING: CPU: 0 PID: 184 at fs/proc/generic.c:180 __xlate_proc_name+0x93/0xb0
[    1.568923] RIP: 0010:__xlate_proc_name+0x93/0xb0
[    1.574200] Call Trace:
[    1.574722]  proc_mkdir+0x18/0x20
[    1.576629]  request_threaded_irq+0xfe/0x160
[    1.576859]  auto_attach+0x60a/0xc40 [cb_pcidas64]

Suggested-by: Ian Abbott <abbotti@mev.co.uk>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Link: https://lore.kernel.org/r/20210315195814.4692-1-ztong0001@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/comedi/drivers/cb_pcidas64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/comedi/drivers/cb_pcidas64.c b/drivers/staging/comedi/drivers/cb_pcidas64.c
index fa987bb0e7cd..6d3ba399a7f0 100644
--- a/drivers/staging/comedi/drivers/cb_pcidas64.c
+++ b/drivers/staging/comedi/drivers/cb_pcidas64.c
@@ -4035,7 +4035,7 @@ static int auto_attach(struct comedi_device *dev,
 	init_stc_registers(dev);
 
 	retval = request_irq(pcidev->irq, handle_interrupt, IRQF_SHARED,
-			     dev->board_name, dev);
+			     "cb_pcidas64", dev);
 	if (retval) {
 		dev_dbg(dev->class_dev, "unable to allocate irq %u\n",
 			pcidev->irq);

From 1a096ae46e21b73f83a581e617f76326c1de592d Mon Sep 17 00:00:00 2001
From: Jackie Liu <jackieliu2113@gmail.com>
Date: Tue, 16 Mar 2021 09:24:53 +0800
Subject: [PATCH 0889/1820] perf top: Fix BPF support related crash with
 perf_event_paranoid=3 + kptr_restrict

After installing the libelf-dev package and compiling perf, if we have
kptr_restrict=2 and perf_event_paranoid=3 'perf top' will crash because
the value of /proc/kallsyms cannot be obtained, which leads to
info->jited_ksyms == NULL. In order to solve this problem, Add a
check before use.

Also plug some leaks on the error path.

Suggested-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: jackie liu <liuyun01@kylinos.cn>
Link: http://lore.kernel.org/lkml/20210316012453.1156-1-liuyun01@kylinos.cn
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf-event.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 57d58c81a5f8..cdecda1ddd36 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -196,25 +196,32 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
 	}
 
 	if (info_linear->info_len < offsetof(struct bpf_prog_info, prog_tags)) {
+		free(info_linear);
 		pr_debug("%s: the kernel is too old, aborting\n", __func__);
 		return -2;
 	}
 
 	info = &info_linear->info;
+	if (!info->jited_ksyms) {
+		free(info_linear);
+		return -1;
+	}
 
 	/* number of ksyms, func_lengths, and tags should match */
 	sub_prog_cnt = info->nr_jited_ksyms;
 	if (sub_prog_cnt != info->nr_prog_tags ||
-	    sub_prog_cnt != info->nr_jited_func_lens)
+	    sub_prog_cnt != info->nr_jited_func_lens) {
+		free(info_linear);
 		return -1;
+	}
 
 	/* check BTF func info support */
 	if (info->btf_id && info->nr_func_info && info->func_info_rec_size) {
 		/* btf func info number should be same as sub_prog_cnt */
 		if (sub_prog_cnt != info->nr_func_info) {
 			pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__);
-			err = -1;
-			goto out;
+			free(info_linear);
+			return -1;
 		}
 		if (btf__get_from_id(info->btf_id, &btf)) {
 			pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info->btf_id);

From 8ca88d53351cc58d535b2bfc7386835378fb0db2 Mon Sep 17 00:00:00 2001
From: Sameer Pujar <spujar@nvidia.com>
Date: Mon, 15 Mar 2021 23:01:31 +0530
Subject: [PATCH 0890/1820] ASoC: simple-card-utils: Do not handle device clock

This reverts commit 1e30f642cf29 ("ASoC: simple-card-utils: Fix device
module clock"). The original patch ended up breaking following platform,
which depends on set_sysclk() to configure internal PLL on wm8904 codec
and expects simple-card-utils to not update the MCLK rate.
 - "arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var3-ads2.dts"

It would be best if codec takes care of setting MCLK clock via DAI
set_sysclk() callback.

Reported-by: Michael Walle <michael@walle.cc>
Suggested-by: Mark Brown <broonie@kernel.org>
Suggested-by: Michael Walle <michael@walle.cc>
Fixes: 1e30f642cf29 ("ASoC: simple-card-utils: Fix device module clock")
Signed-off-by: Sameer Pujar <spujar@nvidia.com>
Tested-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/1615829492-8972-2-git-send-email-spujar@nvidia.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/generic/simple-card-utils.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index ab31045cfc95..6cada4c1e283 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -172,15 +172,16 @@ int asoc_simple_parse_clk(struct device *dev,
 	 *  or device's module clock.
 	 */
 	clk = devm_get_clk_from_child(dev, node, NULL);
-	if (IS_ERR(clk))
-		clk = devm_get_clk_from_child(dev, dlc->of_node, NULL);
-
 	if (!IS_ERR(clk)) {
-		simple_dai->clk = clk;
 		simple_dai->sysclk = clk_get_rate(clk);
-	} else if (!of_property_read_u32(node, "system-clock-frequency",
-					 &val)) {
+
+		simple_dai->clk = clk;
+	} else if (!of_property_read_u32(node, "system-clock-frequency", &val)) {
 		simple_dai->sysclk = val;
+	} else {
+		clk = devm_get_clk_from_child(dev, dlc->of_node, NULL);
+		if (!IS_ERR(clk))
+			simple_dai->sysclk = clk_get_rate(clk);
 	}
 
 	if (of_property_read_bool(node, "system-clock-direction-out"))

From dbf54a9534350d6aebbb34f5c1c606b81a4f35dd Mon Sep 17 00:00:00 2001
From: Sameer Pujar <spujar@nvidia.com>
Date: Mon, 15 Mar 2021 23:01:32 +0530
Subject: [PATCH 0891/1820] ASoC: rt5659: Update MCLK rate in set_sysclk()

Simple-card/audio-graph-card drivers do not handle MCLK clock when it
is specified in the codec device node. The expectation here is that,
the codec should actually own up the MCLK clock and do necessary setup
in the driver.

Suggested-by: Mark Brown <broonie@kernel.org>
Suggested-by: Michael Walle <michael@walle.cc>
Signed-off-by: Sameer Pujar <spujar@nvidia.com>
Link: https://lore.kernel.org/r/1615829492-8972-3-git-send-email-spujar@nvidia.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5659.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/soc/codecs/rt5659.c b/sound/soc/codecs/rt5659.c
index 41e5917b16a5..91a4ef7f620c 100644
--- a/sound/soc/codecs/rt5659.c
+++ b/sound/soc/codecs/rt5659.c
@@ -3426,12 +3426,17 @@ static int rt5659_set_component_sysclk(struct snd_soc_component *component, int
 {
 	struct rt5659_priv *rt5659 = snd_soc_component_get_drvdata(component);
 	unsigned int reg_val = 0;
+	int ret;
 
 	if (freq == rt5659->sysclk && clk_id == rt5659->sysclk_src)
 		return 0;
 
 	switch (clk_id) {
 	case RT5659_SCLK_S_MCLK:
+		ret = clk_set_rate(rt5659->mclk, freq);
+		if (ret)
+			return ret;
+
 		reg_val |= RT5659_SCLK_SRC_MCLK;
 		break;
 	case RT5659_SCLK_S_PLL1:

From 899b12542b0897f92de9ba30944937c39ebb246d Mon Sep 17 00:00:00 2001
From: Bard Liao <yung-chuan.liao@linux.intel.com>
Date: Tue, 16 Mar 2021 08:52:54 +0800
Subject: [PATCH 0892/1820] ASoC: rt711: add snd_soc_component remove callback

We do some IO operations in the snd_soc_component_set_jack callback
function and snd_soc_component_set_jack() will be called when soc
component is removed. However, we should not access SoundWire registers
when the bus is suspended.
So set regcache_cache_only(regmap, true) to avoid accessing in the
soc component removal process.

Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@intel.com>
Link: https://lore.kernel.org/r/20210316005254.29699-1-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt711.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/soc/codecs/rt711.c b/sound/soc/codecs/rt711.c
index 85f744184a60..047f4e677d78 100644
--- a/sound/soc/codecs/rt711.c
+++ b/sound/soc/codecs/rt711.c
@@ -895,6 +895,13 @@ static int rt711_probe(struct snd_soc_component *component)
 	return 0;
 }
 
+static void rt711_remove(struct snd_soc_component *component)
+{
+	struct rt711_priv *rt711 = snd_soc_component_get_drvdata(component);
+
+	regcache_cache_only(rt711->regmap, true);
+}
+
 static const struct snd_soc_component_driver soc_codec_dev_rt711 = {
 	.probe = rt711_probe,
 	.set_bias_level = rt711_set_bias_level,
@@ -905,6 +912,7 @@ static const struct snd_soc_component_driver soc_codec_dev_rt711 = {
 	.dapm_routes = rt711_audio_map,
 	.num_dapm_routes = ARRAY_SIZE(rt711_audio_map),
 	.set_jack = rt711_set_jack_detect,
+	.remove = rt711_remove,
 };
 
 static int rt711_set_sdw_stream(struct snd_soc_dai *dai, void *sdw_stream,

From 9deef665f5811a7ad22b5e6eb80fe2a14ba4494c Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@nxp.com>
Date: Tue, 16 Mar 2021 16:40:53 +0800
Subject: [PATCH 0893/1820] ASoC: dt-bindings: fsl_spdif: Add compatible string
 for new platforms

Add compatible string for new added platforms which support spdif module.
They are i.MX8QXP, i.MX8MM, i.MX8MN, i.MX8MQ.

Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Link: https://lore.kernel.org/r/1615884053-4264-1-git-send-email-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/fsl,spdif.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/sound/fsl,spdif.yaml b/Documentation/devicetree/bindings/sound/fsl,spdif.yaml
index 50449b6d1048..4454aca34d56 100644
--- a/Documentation/devicetree/bindings/sound/fsl,spdif.yaml
+++ b/Documentation/devicetree/bindings/sound/fsl,spdif.yaml
@@ -21,6 +21,10 @@ properties:
       - fsl,vf610-spdif
       - fsl,imx6sx-spdif
       - fsl,imx8qm-spdif
+      - fsl,imx8qxp-spdif
+      - fsl,imx8mq-spdif
+      - fsl,imx8mm-spdif
+      - fsl,imx8mn-spdif
 
   reg:
     maxItems: 1

From 53b861bec737c189cc14ec3b5785d0f13445ac0f Mon Sep 17 00:00:00 2001
From: Jeremy Szu <jeremy.szu@canonical.com>
Date: Tue, 16 Mar 2021 17:42:35 +0800
Subject: [PATCH 0894/1820] ALSA: hda/realtek: fix mute/micmute LEDs for HP 850
 G8

The HP EliteBook 850 G8 Notebook PC is using ALC285 codec which is
using 0x04 to control mute LED and 0x01 to control micmute LED.
Therefore, add a quirk to make it works.

Signed-off-by: Jeremy Szu <jeremy.szu@canonical.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210316094236.89028-1-jeremy.szu@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 145d6cf4939e..316b9b4ccb32 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -8060,6 +8060,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),
+	SND_PCI_QUIRK(0x103c, 0x8846, "HP EliteBook 850 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x884c, "HP EliteBook 840 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),

From f8425c9396639cc462bcce44b1051f8b4e62fddb Mon Sep 17 00:00:00 2001
From: Alessio Balsini <balsini@android.com>
Date: Mon, 25 Jan 2021 15:30:51 +0000
Subject: [PATCH 0895/1820] fuse: 32-bit user space ioctl compat for fuse
 device

With a 64-bit kernel build the FUSE device cannot handle ioctl requests
coming from 32-bit user space.  This is due to the ioctl command
translation that generates different command identifiers that thus cannot
be used for direct comparisons without proper manipulation.

Explicitly extract type and number from the ioctl command to enable 32-bit
user space compatibility on 64-bit kernel builds.

Signed-off-by: Alessio Balsini <balsini@android.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dev.c             | 26 ++++++++++++++++----------
 include/uapi/linux/fuse.h |  3 ++-
 2 files changed, 18 insertions(+), 11 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index c6636b4c4ccf..c0fee830a34e 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -2229,19 +2229,21 @@ static int fuse_device_clone(struct fuse_conn *fc, struct file *new)
 static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
 			   unsigned long arg)
 {
-	int err = -ENOTTY;
+	int res;
+	int oldfd;
+	struct fuse_dev *fud = NULL;
 
-	if (cmd == FUSE_DEV_IOC_CLONE) {
-		int oldfd;
+	if (_IOC_TYPE(cmd) != FUSE_DEV_IOC_MAGIC)
+		return -ENOTTY;
 
-		err = -EFAULT;
-		if (!get_user(oldfd, (__u32 __user *) arg)) {
+	switch (_IOC_NR(cmd)) {
+	case _IOC_NR(FUSE_DEV_IOC_CLONE):
+		res = -EFAULT;
+		if (!get_user(oldfd, (__u32 __user *)arg)) {
 			struct file *old = fget(oldfd);
 
-			err = -EINVAL;
+			res = -EINVAL;
 			if (old) {
-				struct fuse_dev *fud = NULL;
-
 				/*
 				 * Check against file->f_op because CUSE
 				 * uses the same ioctl handler.
@@ -2252,14 +2254,18 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
 
 				if (fud) {
 					mutex_lock(&fuse_mutex);
-					err = fuse_device_clone(fud->fc, file);
+					res = fuse_device_clone(fud->fc, file);
 					mutex_unlock(&fuse_mutex);
 				}
 				fput(old);
 			}
 		}
+		break;
+	default:
+		res = -ENOTTY;
+		break;
 	}
-	return err;
+	return res;
 }
 
 const struct file_operations fuse_dev_operations = {
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 98ca64d1beb6..54442612c48b 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -903,7 +903,8 @@ struct fuse_notify_retrieve_in {
 };
 
 /* Device ioctls: */
-#define FUSE_DEV_IOC_CLONE	_IOR(229, 0, uint32_t)
+#define FUSE_DEV_IOC_MAGIC		229
+#define FUSE_DEV_IOC_CLONE		_IOR(FUSE_DEV_IOC_MAGIC, 0, uint32_t)
 
 struct fuse_lseek_in {
 	uint64_t	fh;

From 276559d8d02c2709281578976ca2f53bc62063d4 Mon Sep 17 00:00:00 2001
From: Ping Cheng <pinglinux@gmail.com>
Date: Thu, 11 Mar 2021 11:30:09 -0800
Subject: [PATCH 0896/1820] HID: wacom: set EV_KEY and EV_ABS only for
 non-HID_GENERIC type of devices

Valid HID_GENERIC type of devices set EV_KEY and EV_ABS by wacom_map_usage.
When *_input_capabilities are reached, those devices should already have
their proper EV_* set. EV_KEY and EV_ABS only need to be set for
non-HID_GENERIC type of devices in *_input_capabilities.

Devices that don't support HID descitoprs will pass back to hid-input for
registration without being accidentally rejected by the introduction of
patch: "Input: refuse to register absolute devices without absinfo"

Fixes: 6ecfe51b4082 ("Input: refuse to register absolute devices without absinfo")
Signed-off-by: Ping Cheng <ping.cheng@wacom.com>
Reviewed-by: Jason Gerecke <Jason.Gerecke@wacom.com>
Tested-by: Juan Garrido <Juan.Garrido@wacom.com>
CC: stable@vger.kernel.org
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/wacom_wac.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index bdd9ba577150..2d70dc4bea65 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -3574,8 +3574,6 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
 {
 	struct wacom_features *features = &wacom_wac->features;
 
-	input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
-
 	if (!(features->device_type & WACOM_DEVICETYPE_PEN))
 		return -ENODEV;
 
@@ -3590,6 +3588,7 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
 		return 0;
 	}
 
+	input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
 	__set_bit(BTN_TOUCH, input_dev->keybit);
 	__set_bit(ABS_MISC, input_dev->absbit);
 
@@ -3742,8 +3741,6 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
 {
 	struct wacom_features *features = &wacom_wac->features;
 
-	input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
-
 	if (!(features->device_type & WACOM_DEVICETYPE_TOUCH))
 		return -ENODEV;
 
@@ -3756,6 +3753,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
 		/* setup has already been done */
 		return 0;
 
+	input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
 	__set_bit(BTN_TOUCH, input_dev->keybit);
 
 	if (features->touch_max == 1) {

From ef4cb70a4c22bf301cd757dcc838dc8ca9526477 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 2 Mar 2021 18:14:53 +0200
Subject: [PATCH 0897/1820] genirq/irq_sim: Fix typos in kernel doc (fnode ->
 fwnode)

Fix typos in kernel doc, otherwise validation script complains:

.../irq_sim.c:170: warning: Function parameter or member 'fwnode' not described in 'irq_domain_create_sim'
.../irq_sim.c:170: warning: Excess function parameter 'fnode' description in 'irq_domain_create_sim'
.../irq_sim.c:240: warning: Function parameter or member 'fwnode' not described in 'devm_irq_domain_create_sim'
.../irq_sim.c:240: warning: Excess function parameter 'fnode' description in 'devm_irq_domain_create_sim'

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20210302161453.28540-1-andriy.shevchenko@linux.intel.com
---
 kernel/irq/irq_sim.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index 48006608baf0..40880c350b95 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -159,7 +159,7 @@ static const struct irq_domain_ops irq_sim_domain_ops = {
  * irq_domain_create_sim - Create a new interrupt simulator irq_domain and
  *                         allocate a range of dummy interrupts.
  *
- * @fnode:      struct fwnode_handle to be associated with this domain.
+ * @fwnode:     struct fwnode_handle to be associated with this domain.
  * @num_irqs:   Number of interrupts to allocate.
  *
  * On success: return a new irq_domain object.
@@ -228,7 +228,7 @@ static void devm_irq_domain_release_sim(struct device *dev, void *res)
  *                              a managed device.
  *
  * @dev:        Device to initialize the simulator object for.
- * @fnode:      struct fwnode_handle to be associated with this domain.
+ * @fwnode:     struct fwnode_handle to be associated with this domain.
  * @num_irqs:   Number of interrupts to allocate
  *
  * On success: return a new irq_domain object.

From 701454bce906241ba7f50e2773881560d6404d29 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 16 Feb 2021 19:27:14 +0100
Subject: [PATCH 0898/1820] auxdisplay: Remove in_interrupt() usage.

charlcd_write() is invoked as a VFS->write() callback and as such it is
always invoked from preemptible context and may sleep.

charlcd_puts() is invoked from register/unregister callback which is
preemptible. The reboot notifier callback is also invoked from
preemptible context.

Therefore there is no need to use in_interrupt() to figure out if it
is safe to sleep because it always is. in_interrupt() and related
context checks are being removed from non-core code.
Using schedule() to schedule (and be friendly to others) is
discouraged and cond_resched() should be used instead.

Remove in_interrupt() and use cond_resched() to schedule every 32
iterations if needed.

Link: https://lkml.kernel.org/r/20200914204209.256266093@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
[mo: fixed a couple typos in comment and commit message]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 drivers/auxdisplay/charlcd.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c
index f43430e9dcee..24fd6f369ebe 100644
--- a/drivers/auxdisplay/charlcd.c
+++ b/drivers/auxdisplay/charlcd.c
@@ -470,12 +470,14 @@ static ssize_t charlcd_write(struct file *file, const char __user *buf,
 	char c;
 
 	for (; count-- > 0; (*ppos)++, tmp++) {
-		if (!in_interrupt() && (((count + 1) & 0x1f) == 0))
+		if (((count + 1) & 0x1f) == 0) {
 			/*
-			 * let's be a little nice with other processes
-			 * that need some CPU
+			 * charlcd_write() is invoked as a VFS->write() callback
+			 * and as such it is always invoked from preemptible
+			 * context and may sleep.
 			 */
-			schedule();
+			cond_resched();
+		}
 
 		if (get_user(c, tmp))
 			return -EFAULT;
@@ -537,12 +539,8 @@ static void charlcd_puts(struct charlcd *lcd, const char *s)
 	int count = strlen(s);
 
 	for (; count-- > 0; tmp++) {
-		if (!in_interrupt() && (((count + 1) & 0x1f) == 0))
-			/*
-			 * let's be a little nice with other processes
-			 * that need some CPU
-			 */
-			schedule();
+		if (((count + 1) & 0x1f) == 0)
+			cond_resched();
 
 		charlcd_write_char(lcd, *tmp);
 	}

From 7dc4b2fdb27242faf40fc20ef83372b7033af050 Mon Sep 17 00:00:00 2001
From: Steve Sistare <steven.sistare@oracle.com>
Date: Thu, 25 Feb 2021 11:25:02 -0800
Subject: [PATCH 0899/1820] vfio/type1: fix unmap all on ILP32

Some ILP32 architectures support mapping a 32-bit vaddr within a 64-bit
iova space.  The unmap-all code uses 32-bit SIZE_MAX as an upper bound on
the extent of the mappings within iova space, so mappings above 4G cannot
be found and unmapped.  Use U64_MAX instead, and use u64 for size variables.
This also fixes a static analysis bug found by the kernel test robot running
smatch for ILP32.

Fixes: 0f53afa12bae ("vfio/type1: unmap cleanup")
Fixes: c19650995374 ("vfio/type1: implement unmap all")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Message-Id: <1614281102-230747-1-git-send-email-steven.sistare@oracle.com>
Link: https://lore.kernel.org/linux-mm/20210222141043.GW2222@kadam
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio_iommu_type1.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 4bb162c1d649..12d9905b429f 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -189,7 +189,7 @@ static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu,
 }
 
 static struct rb_node *vfio_find_dma_first_node(struct vfio_iommu *iommu,
-						dma_addr_t start, size_t size)
+						dma_addr_t start, u64 size)
 {
 	struct rb_node *res = NULL;
 	struct rb_node *node = iommu->dma_list.rb_node;
@@ -1288,7 +1288,7 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
 	int ret = -EINVAL, retries = 0;
 	unsigned long pgshift;
 	dma_addr_t iova = unmap->iova;
-	unsigned long size = unmap->size;
+	u64 size = unmap->size;
 	bool unmap_all = unmap->flags & VFIO_DMA_UNMAP_FLAG_ALL;
 	bool invalidate_vaddr = unmap->flags & VFIO_DMA_UNMAP_FLAG_VADDR;
 	struct rb_node *n, *first_n;
@@ -1304,14 +1304,12 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
 	if (unmap_all) {
 		if (iova || size)
 			goto unlock;
-		size = SIZE_MAX;
-	} else if (!size || size & (pgsize - 1)) {
+		size = U64_MAX;
+	} else if (!size || size & (pgsize - 1) ||
+		   iova + size - 1 < iova || size > SIZE_MAX) {
 		goto unlock;
 	}
 
-	if (iova + size - 1 < iova || size > SIZE_MAX)
-		goto unlock;
-
 	/* When dirty tracking is enabled, allow only min supported pgsize */
 	if ((unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) &&
 	    (!iommu->dirty_page_tracking || (bitmap->pgsize != pgsize))) {

From 179209fa12709a3df8888c323b37315da2683c24 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 23 Feb 2021 15:17:46 -0400
Subject: [PATCH 0900/1820] vfio: IOMMU_API should be selected

As IOMMU_API is a kconfig without a description (eg does not show in the
menu) the correct operator is select not 'depends on'. Using 'depends on'
for this kind of symbol means VFIO is not selectable unless some other
random kconfig has already enabled IOMMU_API for it.

Fixes: cba3345cc494 ("vfio: VFIO core")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Message-Id: <1-v1-df057e0f92c3+91-vfio_arm_compile_test_jgg@nvidia.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 5533df91b257..90c0525b1e0c 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -21,7 +21,7 @@ config VFIO_VIRQFD
 
 menuconfig VFIO
 	tristate "VFIO Non-Privileged userspace driver framework"
-	depends on IOMMU_API
+	select IOMMU_API
 	select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM || ARM64)
 	help
 	  VFIO provides a framework for secure userspace device drivers.

From d3d72a6dfffd3fcaac969786118162b596227f70 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 23 Feb 2021 15:17:47 -0400
Subject: [PATCH 0901/1820] vfio-platform: Add COMPILE_TEST to VFIO_PLATFORM

x86 can build platform bus code too, so vfio-platform and all the platform
reset implementations compile successfully on x86.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Message-Id: <2-v1-df057e0f92c3+91-vfio_arm_compile_test_jgg@nvidia.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/platform/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vfio/platform/Kconfig b/drivers/vfio/platform/Kconfig
index dc1a3c44f2c6..233efde219cc 100644
--- a/drivers/vfio/platform/Kconfig
+++ b/drivers/vfio/platform/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config VFIO_PLATFORM
 	tristate "VFIO support for platform devices"
-	depends on VFIO && EVENTFD && (ARM || ARM64)
+	depends on VFIO && EVENTFD && (ARM || ARM64 || COMPILE_TEST)
 	select VFIO_VIRQFD
 	help
 	  Support for platform devices with VFIO. This is required to make

From 3b49dfb08c750d4745ad42ec042288aba932b9d5 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 23 Feb 2021 15:17:48 -0400
Subject: [PATCH 0902/1820] ARM: amba: Allow some ARM_AMBA users to compile
 with COMPILE_TEST

CONFIG_VFIO_AMBA has a light use of AMBA, adding some inline fallbacks
when AMBA is disabled will allow it to be compiled under COMPILE_TEST and
make VFIO easier to maintain.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Message-Id: <3-v1-df057e0f92c3+91-vfio_arm_compile_test_jgg@nvidia.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/platform/Kconfig |  2 +-
 include/linux/amba/bus.h      | 11 +++++++++++
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/platform/Kconfig b/drivers/vfio/platform/Kconfig
index 233efde219cc..ab341108a0be 100644
--- a/drivers/vfio/platform/Kconfig
+++ b/drivers/vfio/platform/Kconfig
@@ -12,7 +12,7 @@ config VFIO_PLATFORM
 
 config VFIO_AMBA
 	tristate "VFIO support for AMBA devices"
-	depends on VFIO_PLATFORM && ARM_AMBA
+	depends on VFIO_PLATFORM && (ARM_AMBA || COMPILE_TEST)
 	help
 	  Support for ARM AMBA devices with VFIO. This is required to make
 	  use of ARM AMBA devices present on the system using the VFIO
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 6cc93ab5b809..c68d87b87283 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -105,8 +105,19 @@ extern struct bus_type amba_bustype;
 #define amba_get_drvdata(d)	dev_get_drvdata(&d->dev)
 #define amba_set_drvdata(d,p)	dev_set_drvdata(&d->dev, p)
 
+#ifdef CONFIG_ARM_AMBA
 int amba_driver_register(struct amba_driver *);
 void amba_driver_unregister(struct amba_driver *);
+#else
+static inline int amba_driver_register(struct amba_driver *drv)
+{
+	return -EINVAL;
+}
+static inline void amba_driver_unregister(struct amba_driver *drv)
+{
+}
+#endif
+
 struct amba_device *amba_device_alloc(const char *, resource_size_t, size_t);
 void amba_device_put(struct amba_device *);
 int amba_device_add(struct amba_device *, struct resource *);

From b2b12db53507bc97d96f6b7cb279e831e5eafb00 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 4 Mar 2021 21:30:03 -0400
Subject: [PATCH 0903/1820] vfio: Depend on MMU

VFIO_IOMMU_TYPE1 does not compile with !MMU:

../drivers/vfio/vfio_iommu_type1.c: In function 'follow_fault_pfn':
../drivers/vfio/vfio_iommu_type1.c:536:22: error: implicit declaration of function 'pte_write'; did you mean 'vfs_write'? [-Werror=implicit-function-declaration]

So require it.

Suggested-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Message-Id: <0-v1-02cb5500df6e+78-vfio_no_mmu_jgg@nvidia.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 90c0525b1e0c..67d0bf4efa16 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -22,7 +22,7 @@ config VFIO_VIRQFD
 menuconfig VFIO
 	tristate "VFIO Non-Privileged userspace driver framework"
 	select IOMMU_API
-	select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM || ARM64)
+	select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
 	help
 	  VFIO provides a framework for secure userspace device drivers.
 	  See Documentation/driver-api/vfio.rst for more details.

From 4ab4fcfce5b540227d80eb32f1db45ab615f7c92 Mon Sep 17 00:00:00 2001
From: Daniel Jordan <daniel.m.jordan@oracle.com>
Date: Mon, 8 Mar 2021 12:24:52 -0500
Subject: [PATCH 0904/1820] vfio/type1: fix vaddr_get_pfns() return in
 vfio_pin_page_external()

vaddr_get_pfns() now returns the positive number of pfns successfully
gotten instead of zero.  vfio_pin_page_external() might return 1 to
vfio_iommu_type1_pin_pages(), which will treat it as an error, if
vaddr_get_pfns() is successful but vfio_pin_page_external() doesn't
reach vfio_lock_acct().

Fix it up in vfio_pin_page_external().  Found by inspection.

Fixes: be16c1fd99f4 ("vfio/type1: Change success value of vaddr_get_pfn()")
Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Message-Id: <20210308172452.38864-1-daniel.m.jordan@oracle.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio_iommu_type1.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 12d9905b429f..be444407664a 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -785,7 +785,12 @@ static int vfio_pin_page_external(struct vfio_dma *dma, unsigned long vaddr,
 		return -ENODEV;
 
 	ret = vaddr_get_pfns(mm, vaddr, 1, dma->prot, pfn_base, pages);
-	if (ret == 1 && do_accounting && !is_invalid_reserved_pfn(*pfn_base)) {
+	if (ret != 1)
+		goto out;
+
+	ret = 0;
+
+	if (do_accounting && !is_invalid_reserved_pfn(*pfn_base)) {
 		ret = vfio_lock_acct(dma, 1, true);
 		if (ret) {
 			put_pfn(*pfn_base, dma->prot);
@@ -797,6 +802,7 @@ static int vfio_pin_page_external(struct vfio_dma *dma, unsigned long vaddr,
 		}
 	}
 
+out:
 	mmput(mm);
 	return ret;
 }

From 70fb3e41a97a5fecc0aedc9a429479d702c3ab66 Mon Sep 17 00:00:00 2001
From: Ben Gardon <bgardon@google.com>
Date: Mon, 15 Mar 2021 16:38:00 -0700
Subject: [PATCH 0905/1820] KVM: x86/mmu: Fix RCU usage in
 handle_removed_tdp_mmu_page

The pt passed into handle_removed_tdp_mmu_page does not need RCU
protection, as it is not at any risk of being freed by another thread at
that point. However, the implicit cast from tdp_sptep_t to u64 * dropped
the __rcu annotation without a proper rcu_derefrence. Fix this by
passing the pt as a tdp_ptep_t and then rcu_dereferencing it in
the function.

Suggested-by: Sean Christopherson <seanjc@google.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210315233803.2706477-2-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/tdp_mmu.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index d78915019b08..db2936cca4bf 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -301,11 +301,16 @@ static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp,
  *
  * Given a page table that has been removed from the TDP paging structure,
  * iterates through the page table to clear SPTEs and free child page tables.
+ *
+ * Note that pt is passed in as a tdp_ptep_t, but it does not need RCU
+ * protection. Since this thread removed it from the paging structure,
+ * this thread will be responsible for ensuring the page is freed. Hence the
+ * early rcu_dereferences in the function.
  */
-static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
+static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 					bool shared)
 {
-	struct kvm_mmu_page *sp = sptep_to_sp(pt);
+	struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
 	int level = sp->role.level;
 	gfn_t base_gfn = sp->gfn;
 	u64 old_child_spte;
@@ -318,7 +323,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
 	tdp_mmu_unlink_page(kvm, sp, shared);
 
 	for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
-		sptep = pt + i;
+		sptep = rcu_dereference(pt) + i;
 		gfn = base_gfn + (i * KVM_PAGES_PER_HPAGE(level - 1));
 
 		if (shared) {

From 14f6fec2e8e04b83c87c339b8d8ff4cc62b23d35 Mon Sep 17 00:00:00 2001
From: Ben Gardon <bgardon@google.com>
Date: Mon, 15 Mar 2021 16:38:01 -0700
Subject: [PATCH 0906/1820] KVM: x86/mmu: Fix RCU usage when atomically zapping
 SPTEs

Fix a missing rcu_dereference in tdp_mmu_zap_spte_atomic.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210315233803.2706477-3-bgardon@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/tdp_mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index db2936cca4bf..946da74e069c 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -543,7 +543,7 @@ static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm,
 	 * here since the SPTE is going from non-present
 	 * to non-present.
 	 */
-	WRITE_ONCE(*iter->sptep, 0);
+	WRITE_ONCE(*rcu_dereference(iter->sptep), 0);
 
 	return true;
 }

From b601c3bc9d5053065acdaa1481c21481d0dc3f10 Mon Sep 17 00:00:00 2001
From: Ben Gardon <bgardon@google.com>
Date: Mon, 15 Mar 2021 16:38:02 -0700
Subject: [PATCH 0907/1820] KVM: x86/mmu: Factor out tdp_iter_return_to_root

In tdp_mmu_iter_cond_resched there is a call to tdp_iter_start which
causes the iterator to continue its walk over the paging structure from
the root. This is needed after a yield as paging structure could have
been freed in the interim.

The tdp_iter_start call is not very clear and something of a hack. It
requires exposing tdp_iter fields not used elsewhere in tdp_mmu.c and
the effect is not obvious from the function name. Factor a more aptly
named function out of tdp_iter_start and call it from
tdp_mmu_iter_cond_resched and tdp_iter_start.

No functional change intended.

Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210315233803.2706477-4-bgardon@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/tdp_iter.c | 24 +++++++++++++++++-------
 arch/x86/kvm/mmu/tdp_iter.h |  1 +
 arch/x86/kvm/mmu/tdp_mmu.c  |  4 +---
 3 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index e5f148106e20..f7f94ea65243 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -20,6 +20,21 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level)
 	return gfn & -KVM_PAGES_PER_HPAGE(level);
 }
 
+/*
+ * Return the TDP iterator to the root PT and allow it to continue its
+ * traversal over the paging structure from there.
+ */
+void tdp_iter_restart(struct tdp_iter *iter)
+{
+	iter->yielded_gfn = iter->next_last_level_gfn;
+	iter->level = iter->root_level;
+
+	iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
+	tdp_iter_refresh_sptep(iter);
+
+	iter->valid = true;
+}
+
 /*
  * Sets a TDP iterator to walk a pre-order traversal of the paging structure
  * rooted at root_pt, starting with the walk to translate next_last_level_gfn.
@@ -31,16 +46,11 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
 	WARN_ON(root_level > PT64_ROOT_MAX_LEVEL);
 
 	iter->next_last_level_gfn = next_last_level_gfn;
-	iter->yielded_gfn = iter->next_last_level_gfn;
 	iter->root_level = root_level;
 	iter->min_level = min_level;
-	iter->level = root_level;
-	iter->pt_path[iter->level - 1] = (tdp_ptep_t)root_pt;
+	iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root_pt;
 
-	iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
-	tdp_iter_refresh_sptep(iter);
-
-	iter->valid = true;
+	tdp_iter_restart(iter);
 }
 
 /*
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index 4cc177d75c4a..8eb424d17c91 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -63,5 +63,6 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
 		    int min_level, gfn_t next_last_level_gfn);
 void tdp_iter_next(struct tdp_iter *iter);
 tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter);
+void tdp_iter_restart(struct tdp_iter *iter);
 
 #endif /* __KVM_X86_MMU_TDP_ITER_H */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 946da74e069c..38b6b6936171 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -664,9 +664,7 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
 
 		WARN_ON(iter->gfn > iter->next_last_level_gfn);
 
-		tdp_iter_start(iter, iter->pt_path[iter->root_level - 1],
-			       iter->root_level, iter->min_level,
-			       iter->next_last_level_gfn);
+		tdp_iter_restart(iter);
 
 		return true;
 	}

From 08889894cc82bc3b213bdb192f274358e5a6b78d Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 15 Mar 2021 16:38:03 -0700
Subject: [PATCH 0908/1820] KVM: x86/mmu: Store the address space ID in the TDP
 iterator

Store the address space ID in the TDP iterator so that it can be
retrieved without having to bounce through the root shadow page.  This
streamlines the code and fixes a Sparse warning about not properly using
rcu_dereference() when grabbing the ID from the root on the fly.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210315233803.2706477-5-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu_internal.h |  5 +++++
 arch/x86/kvm/mmu/tdp_iter.c     |  6 +-----
 arch/x86/kvm/mmu/tdp_iter.h     |  3 ++-
 arch/x86/kvm/mmu/tdp_mmu.c      | 23 +++++------------------
 4 files changed, 13 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index ec4fc28b325a..1f6f98c76bdf 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -78,6 +78,11 @@ static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
 	return to_shadow_page(__pa(sptep));
 }
 
+static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
+{
+	return sp->role.smm ? 1 : 0;
+}
+
 static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
 {
 	/*
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index f7f94ea65243..b3ed302c1a35 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -49,6 +49,7 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
 	iter->root_level = root_level;
 	iter->min_level = min_level;
 	iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root_pt;
+	iter->as_id = kvm_mmu_page_as_id(sptep_to_sp(root_pt));
 
 	tdp_iter_restart(iter);
 }
@@ -169,8 +170,3 @@ void tdp_iter_next(struct tdp_iter *iter)
 	iter->valid = false;
 }
 
-tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter)
-{
-	return iter->pt_path[iter->root_level - 1];
-}
-
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index 8eb424d17c91..b1748b988d3a 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -36,6 +36,8 @@ struct tdp_iter {
 	int min_level;
 	/* The iterator's current level within the paging structure */
 	int level;
+	/* The address space ID, i.e. SMM vs. regular. */
+	int as_id;
 	/* A snapshot of the value at sptep */
 	u64 old_spte;
 	/*
@@ -62,7 +64,6 @@ tdp_ptep_t spte_to_child_pt(u64 pte, int level);
 void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
 		    int min_level, gfn_t next_last_level_gfn);
 void tdp_iter_next(struct tdp_iter *iter);
-tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter);
 void tdp_iter_restart(struct tdp_iter *iter);
 
 #endif /* __KVM_X86_MMU_TDP_ITER_H */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 38b6b6936171..462b1f71c77f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -203,11 +203,6 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 				u64 old_spte, u64 new_spte, int level,
 				bool shared);
 
-static int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
-{
-	return sp->role.smm ? 1 : 0;
-}
-
 static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level)
 {
 	bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
@@ -497,10 +492,6 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
 					   struct tdp_iter *iter,
 					   u64 new_spte)
 {
-	u64 *root_pt = tdp_iter_root_pt(iter);
-	struct kvm_mmu_page *root = sptep_to_sp(root_pt);
-	int as_id = kvm_mmu_page_as_id(root);
-
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
 	/*
@@ -514,8 +505,8 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
 		      new_spte) != iter->old_spte)
 		return false;
 
-	handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
-			    iter->level, true);
+	handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+			    new_spte, iter->level, true);
 
 	return true;
 }
@@ -569,10 +560,6 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 				      u64 new_spte, bool record_acc_track,
 				      bool record_dirty_log)
 {
-	tdp_ptep_t root_pt = tdp_iter_root_pt(iter);
-	struct kvm_mmu_page *root = sptep_to_sp(root_pt);
-	int as_id = kvm_mmu_page_as_id(root);
-
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	/*
@@ -586,13 +573,13 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 
 	WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte);
 
-	__handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
-			      iter->level, false);
+	__handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+			      new_spte, iter->level, false);
 	if (record_acc_track)
 		handle_changed_spte_acc_track(iter->old_spte, new_spte,
 					      iter->level);
 	if (record_dirty_log)
-		handle_changed_spte_dirty_log(kvm, as_id, iter->gfn,
+		handle_changed_spte_dirty_log(kvm, iter->as_id, iter->gfn,
 					      iter->old_spte, new_spte,
 					      iter->level);
 }

From 34e49994d0dcdb2d31d4d2908d04f4e9ce57e4d7 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Mon, 15 Mar 2021 15:18:24 +0100
Subject: [PATCH 0909/1820] btrfs: fix slab cache flags for free space tree
 bitmap

The free space tree bitmap slab cache is created with SLAB_RED_ZONE but
that's a debugging flag and not always enabled. Also the other slabs are
created with at least SLAB_MEM_SPREAD that we want as well to average
the memory placement cost.

Reported-by: Vlastimil Babka <vbabka@suse.cz>
Fixes: 3acd48507dc4 ("btrfs: fix allocation of free space cache v1 bitmap pages")
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ea5ede619220..5092dea21448 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9005,7 +9005,7 @@ int __init btrfs_init_cachep(void)
 
 	btrfs_free_space_bitmap_cachep = kmem_cache_create("btrfs_free_space_bitmap",
 							PAGE_SIZE, PAGE_SIZE,
-							SLAB_RED_ZONE, NULL);
+							SLAB_MEM_SPREAD, NULL);
 	if (!btrfs_free_space_bitmap_cachep)
 		goto fail;
 

From dbcc7d57bffc0c8cac9dac11bec548597d59a6a5 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 11 Mar 2021 14:31:05 +0000
Subject: [PATCH 0910/1820] btrfs: fix race when cloning extent buffer during
 rewind of an old root

While resolving backreferences, as part of a logical ino ioctl call or
fiemap, we can end up hitting a BUG_ON() when replaying tree mod log
operations of a root, triggering a stack trace like the following:

  ------------[ cut here ]------------
  kernel BUG at fs/btrfs/ctree.c:1210!
  invalid opcode: 0000 [#1] SMP KASAN PTI
  CPU: 1 PID: 19054 Comm: crawl_335 Tainted: G        W         5.11.0-2d11c0084b02-misc-next+ #89
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
  RIP: 0010:__tree_mod_log_rewind+0x3b1/0x3c0
  Code: 05 48 8d 74 10 (...)
  RSP: 0018:ffffc90001eb70b8 EFLAGS: 00010297
  RAX: 0000000000000000 RBX: ffff88812344e400 RCX: ffffffffb28933b6
  RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff88812344e42c
  RBP: ffffc90001eb7108 R08: 1ffff11020b60a20 R09: ffffed1020b60a20
  R10: ffff888105b050f9 R11: ffffed1020b60a1f R12: 00000000000000ee
  R13: ffff8880195520c0 R14: ffff8881bc958500 R15: ffff88812344e42c
  FS:  00007fd1955e8700(0000) GS:ffff8881f5600000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007efdb7928718 CR3: 000000010103a006 CR4: 0000000000170ee0
  Call Trace:
   btrfs_search_old_slot+0x265/0x10d0
   ? lock_acquired+0xbb/0x600
   ? btrfs_search_slot+0x1090/0x1090
   ? free_extent_buffer.part.61+0xd7/0x140
   ? free_extent_buffer+0x13/0x20
   resolve_indirect_refs+0x3e9/0xfc0
   ? lock_downgrade+0x3d0/0x3d0
   ? __kasan_check_read+0x11/0x20
   ? add_prelim_ref.part.11+0x150/0x150
   ? lock_downgrade+0x3d0/0x3d0
   ? __kasan_check_read+0x11/0x20
   ? lock_acquired+0xbb/0x600
   ? __kasan_check_write+0x14/0x20
   ? do_raw_spin_unlock+0xa8/0x140
   ? rb_insert_color+0x30/0x360
   ? prelim_ref_insert+0x12d/0x430
   find_parent_nodes+0x5c3/0x1830
   ? resolve_indirect_refs+0xfc0/0xfc0
   ? lock_release+0xc8/0x620
   ? fs_reclaim_acquire+0x67/0xf0
   ? lock_acquire+0xc7/0x510
   ? lock_downgrade+0x3d0/0x3d0
   ? lockdep_hardirqs_on_prepare+0x160/0x210
   ? lock_release+0xc8/0x620
   ? fs_reclaim_acquire+0x67/0xf0
   ? lock_acquire+0xc7/0x510
   ? poison_range+0x38/0x40
   ? unpoison_range+0x14/0x40
   ? trace_hardirqs_on+0x55/0x120
   btrfs_find_all_roots_safe+0x142/0x1e0
   ? find_parent_nodes+0x1830/0x1830
   ? btrfs_inode_flags_to_xflags+0x50/0x50
   iterate_extent_inodes+0x20e/0x580
   ? tree_backref_for_extent+0x230/0x230
   ? lock_downgrade+0x3d0/0x3d0
   ? read_extent_buffer+0xdd/0x110
   ? lock_downgrade+0x3d0/0x3d0
   ? __kasan_check_read+0x11/0x20
   ? lock_acquired+0xbb/0x600
   ? __kasan_check_write+0x14/0x20
   ? _raw_spin_unlock+0x22/0x30
   ? __kasan_check_write+0x14/0x20
   iterate_inodes_from_logical+0x129/0x170
   ? iterate_inodes_from_logical+0x129/0x170
   ? btrfs_inode_flags_to_xflags+0x50/0x50
   ? iterate_extent_inodes+0x580/0x580
   ? __vmalloc_node+0x92/0xb0
   ? init_data_container+0x34/0xb0
   ? init_data_container+0x34/0xb0
   ? kvmalloc_node+0x60/0x80
   btrfs_ioctl_logical_to_ino+0x158/0x230
   btrfs_ioctl+0x205e/0x4040
   ? __might_sleep+0x71/0xe0
   ? btrfs_ioctl_get_supported_features+0x30/0x30
   ? getrusage+0x4b6/0x9c0
   ? __kasan_check_read+0x11/0x20
   ? lock_release+0xc8/0x620
   ? __might_fault+0x64/0xd0
   ? lock_acquire+0xc7/0x510
   ? lock_downgrade+0x3d0/0x3d0
   ? lockdep_hardirqs_on_prepare+0x210/0x210
   ? lockdep_hardirqs_on_prepare+0x210/0x210
   ? __kasan_check_read+0x11/0x20
   ? do_vfs_ioctl+0xfc/0x9d0
   ? ioctl_file_clone+0xe0/0xe0
   ? lock_downgrade+0x3d0/0x3d0
   ? lockdep_hardirqs_on_prepare+0x210/0x210
   ? __kasan_check_read+0x11/0x20
   ? lock_release+0xc8/0x620
   ? __task_pid_nr_ns+0xd3/0x250
   ? lock_acquire+0xc7/0x510
   ? __fget_files+0x160/0x230
   ? __fget_light+0xf2/0x110
   __x64_sys_ioctl+0xc3/0x100
   do_syscall_64+0x37/0x80
   entry_SYSCALL_64_after_hwframe+0x44/0xa9
  RIP: 0033:0x7fd1976e2427
  Code: 00 00 90 48 8b 05 (...)
  RSP: 002b:00007fd1955e5cf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
  RAX: ffffffffffffffda RBX: 00007fd1955e5f40 RCX: 00007fd1976e2427
  RDX: 00007fd1955e5f48 RSI: 00000000c038943b RDI: 0000000000000004
  RBP: 0000000001000000 R08: 0000000000000000 R09: 00007fd1955e6120
  R10: 0000557835366b00 R11: 0000000000000246 R12: 0000000000000004
  R13: 00007fd1955e5f48 R14: 00007fd1955e5f40 R15: 00007fd1955e5ef8
  Modules linked in:
  ---[ end trace ec8931a1c36e57be ]---

  (gdb) l *(__tree_mod_log_rewind+0x3b1)
  0xffffffff81893521 is in __tree_mod_log_rewind (fs/btrfs/ctree.c:1210).
  1205                     * the modification. as we're going backwards, we do the
  1206                     * opposite of each operation here.
  1207                     */
  1208                    switch (tm->op) {
  1209                    case MOD_LOG_KEY_REMOVE_WHILE_FREEING:
  1210                            BUG_ON(tm->slot < n);
  1211                            fallthrough;
  1212                    case MOD_LOG_KEY_REMOVE_WHILE_MOVING:
  1213                    case MOD_LOG_KEY_REMOVE:
  1214                            btrfs_set_node_key(eb, &tm->key, tm->slot);

Here's what happens to hit that BUG_ON():

1) We have one tree mod log user (through fiemap or the logical ino ioctl),
   with a sequence number of 1, so we have fs_info->tree_mod_seq == 1;

2) Another task is at ctree.c:balance_level() and we have eb X currently as
   the root of the tree, and we promote its single child, eb Y, as the new
   root.

   Then, at ctree.c:balance_level(), we call:

      tree_mod_log_insert_root(eb X, eb Y, 1);

3) At tree_mod_log_insert_root() we create tree mod log elements for each
   slot of eb X, of operation type MOD_LOG_KEY_REMOVE_WHILE_FREEING each
   with a ->logical pointing to ebX->start. These are placed in an array
   named tm_list.
   Lets assume there are N elements (N pointers in eb X);

4) Then, still at tree_mod_log_insert_root(), we create a tree mod log
   element of operation type MOD_LOG_ROOT_REPLACE, ->logical set to
   ebY->start, ->old_root.logical set to ebX->start, ->old_root.level set
   to the level of eb X and ->generation set to the generation of eb X;

5) Then tree_mod_log_insert_root() calls tree_mod_log_free_eb() with
   tm_list as argument. After that, tree_mod_log_free_eb() calls
   __tree_mod_log_insert() for each member of tm_list in reverse order,
   from highest slot in eb X, slot N - 1, to slot 0 of eb X;

6) __tree_mod_log_insert() sets the sequence number of each given tree mod
   log operation - it increments fs_info->tree_mod_seq and sets
   fs_info->tree_mod_seq as the sequence number of the given tree mod log
   operation.

   This means that for the tm_list created at tree_mod_log_insert_root(),
   the element corresponding to slot 0 of eb X has the highest sequence
   number (1 + N), and the element corresponding to the last slot has the
   lowest sequence number (2);

7) Then, after inserting tm_list's elements into the tree mod log rbtree,
   the MOD_LOG_ROOT_REPLACE element is inserted, which gets the highest
   sequence number, which is N + 2;

8) Back to ctree.c:balance_level(), we free eb X by calling
   btrfs_free_tree_block() on it. Because eb X was created in the current
   transaction, has no other references and writeback did not happen for
   it, we add it back to the free space cache/tree;

9) Later some other task T allocates the metadata extent from eb X, since
   it is marked as free space in the space cache/tree, and uses it as a
   node for some other btree;

10) The tree mod log user task calls btrfs_search_old_slot(), which calls
    get_old_root(), and finally that calls __tree_mod_log_oldest_root()
    with time_seq == 1 and eb_root == eb Y;

11) First iteration of the while loop finds the tree mod log element with
    sequence number N + 2, for the logical address of eb Y and of type
    MOD_LOG_ROOT_REPLACE;

12) Because the operation type is MOD_LOG_ROOT_REPLACE, we don't break out
    of the loop, and set root_logical to point to tm->old_root.logical
    which corresponds to the logical address of eb X;

13) On the next iteration of the while loop, the call to
    tree_mod_log_search_oldest() returns the smallest tree mod log element
    for the logical address of eb X, which has a sequence number of 2, an
    operation type of MOD_LOG_KEY_REMOVE_WHILE_FREEING and corresponds to
    the old slot N - 1 of eb X (eb X had N items in it before being freed);

14) We then break out of the while loop and return the tree mod log operation
    of type MOD_LOG_ROOT_REPLACE (eb Y), and not the one for slot N - 1 of
    eb X, to get_old_root();

15) At get_old_root(), we process the MOD_LOG_ROOT_REPLACE operation
    and set "logical" to the logical address of eb X, which was the old
    root. We then call tree_mod_log_search() passing it the logical
    address of eb X and time_seq == 1;

16) Then before calling tree_mod_log_search(), task T adds a key to eb X,
    which results in adding a tree mod log operation of type
    MOD_LOG_KEY_ADD to the tree mod log - this is done at
    ctree.c:insert_ptr() - but after adding the tree mod log operation
    and before updating the number of items in eb X from 0 to 1...

17) The task at get_old_root() calls tree_mod_log_search() and gets the
    tree mod log operation of type MOD_LOG_KEY_ADD just added by task T.
    Then it enters the following if branch:

    if (old_root && tm && tm->op != MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
       (...)
    } (...)

    Calls read_tree_block() for eb X, which gets a reference on eb X but
    does not lock it - task T has it locked.
    Then it clones eb X while it has nritems set to 0 in its header, before
    task T sets nritems to 1 in eb X's header. From hereupon we use the
    clone of eb X which no other task has access to;

18) Then we call __tree_mod_log_rewind(), passing it the MOD_LOG_KEY_ADD
    mod log operation we just got from tree_mod_log_search() in the
    previous step and the cloned version of eb X;

19) At __tree_mod_log_rewind(), we set the local variable "n" to the number
    of items set in eb X's clone, which is 0. Then we enter the while loop,
    and in its first iteration we process the MOD_LOG_KEY_ADD operation,
    which just decrements "n" from 0 to (u32)-1, since "n" is declared with
    a type of u32. At the end of this iteration we call rb_next() to find the
    next tree mod log operation for eb X, that gives us the mod log operation
    of type MOD_LOG_KEY_REMOVE_WHILE_FREEING, for slot 0, with a sequence
    number of N + 1 (steps 3 to 6);

20) Then we go back to the top of the while loop and trigger the following
    BUG_ON():

        (...)
        switch (tm->op) {
        case MOD_LOG_KEY_REMOVE_WHILE_FREEING:
                 BUG_ON(tm->slot < n);
                 fallthrough;
        (...)

    Because "n" has a value of (u32)-1 (4294967295) and tm->slot is 0.

Fix this by taking a read lock on the extent buffer before cloning it at
ctree.c:get_old_root(). This should be done regardless of the extent
buffer having been freed and reused, as a concurrent task might be
modifying it (while holding a write lock on it).

Reported-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Link: https://lore.kernel.org/linux-btrfs/20210227155037.GN28049@hungrycats.org/
Fixes: 834328a8493079 ("Btrfs: tree mod log's old roots could still be part of the tree")
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index d56730a67885..34b929bd5c1a 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1365,7 +1365,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 				   "failed to read tree block %llu from get_old_root",
 				   logical);
 		} else {
+			btrfs_tree_read_lock(old);
 			eb = btrfs_clone_extent_buffer(old);
+			btrfs_tree_read_unlock(old);
 			free_extent_buffer(old);
 		}
 	} else if (old_root) {

From 485df75554257e883d0ce39bb886e8212349748e Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 11 Mar 2021 14:31:06 +0000
Subject: [PATCH 0911/1820] btrfs: always pin deleted leaves when there are
 active tree mod log users

When freeing a tree block we may end up adding its extent back to the
free space cache/tree, as long as there are no more references for it,
it was created in the current transaction and writeback for it never
happened. This is generally fine, however when we have tree mod log
operations it can result in inconsistent versions of a btree after
unwinding extent buffers with the recorded tree mod log operations.

This is because:

* We only log operations for nodes (adding and removing key/pointers),
  for leaves we don't do anything;

* This means that we can log a MOD_LOG_KEY_REMOVE_WHILE_FREEING operation
  for a node that points to a leaf that was deleted;

* Before we apply the logged operation to unwind a node, we can have
  that leaf's extent allocated again, either as a node or as a leaf, and
  possibly for another btree. This is possible if the leaf was created in
  the current transaction and writeback for it never started, in which
  case btrfs_free_tree_block() returns its extent back to the free space
  cache/tree;

* Then, before applying the tree mod log operation, some task allocates
  the metadata extent just freed before, and uses it either as a leaf or
  as a node for some btree (can be the same or another one, it does not
  matter);

* After applying the MOD_LOG_KEY_REMOVE_WHILE_FREEING operation we now
  get the target node with an item pointing to the metadata extent that
  now has content different from what it had before the leaf was deleted.
  It might now belong to a different btree and be a node and not a leaf
  anymore.

  As a consequence, the results of searches after the unwinding can be
  unpredictable and produce unexpected results.

So make sure we pin extent buffers corresponding to leaves when there
are tree mod log users.

CC: stable@vger.kernel.org # 4.14+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 78ad31a59e59..36a3c973fda1 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3323,6 +3323,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 
 	if (last_ref && btrfs_header_generation(buf) == trans->transid) {
 		struct btrfs_block_group *cache;
+		bool must_pin = false;
 
 		if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
 			ret = check_ref_cleanup(trans, buf->start);
@@ -3340,7 +3341,27 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 
-		if (btrfs_is_zoned(fs_info)) {
+		/*
+		 * If this is a leaf and there are tree mod log users, we may
+		 * have recorded mod log operations that point to this leaf.
+		 * So we must make sure no one reuses this leaf's extent before
+		 * mod log operations are applied to a node, otherwise after
+		 * rewinding a node using the mod log operations we get an
+		 * inconsistent btree, as the leaf's extent may now be used as
+		 * a node or leaf for another different btree.
+		 * We are safe from races here because at this point no other
+		 * node or root points to this extent buffer, so if after this
+		 * check a new tree mod log user joins, it will not be able to
+		 * find a node pointing to this leaf and record operations that
+		 * point to this leaf.
+		 */
+		if (btrfs_header_level(buf) == 0) {
+			read_lock(&fs_info->tree_mod_log_lock);
+			must_pin = !list_empty(&fs_info->tree_mod_seq_list);
+			read_unlock(&fs_info->tree_mod_log_lock);
+		}
+
+		if (must_pin || btrfs_is_zoned(fs_info)) {
 			btrfs_redirty_list_add(trans->transaction, buf);
 			pin_down_extent(trans, cache, buf->start, buf->len, 1);
 			btrfs_put_block_group(cache);

From 1944015fe9c1d9fa5e9eb7ffbbb5ef8954d6753b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 12 Feb 2021 11:22:14 +0100
Subject: [PATCH 0912/1820] mac80211: fix rate mask reset

Coverity reported the strange "if (~...)" condition that's
always true. It suggested that ! was intended instead of ~,
but upon further analysis I'm convinced that what really was
intended was a comparison to 0xff/0xffff (in HT/VHT cases
respectively), since this indicates that all of the rates
are enabled.

Change the comparison accordingly.

I'm guessing this never really mattered because a reset to
not having a rate mask is basically equivalent to having a
mask that enables all rates.

Reported-by: Colin Ian King <colin.king@canonical.com>
Fixes: 2ffbe6d33366 ("mac80211: fix and optimize MCS mask handling")
Fixes: b119ad6e726c ("mac80211: add rate mask logic for vht rates")
Reviewed-by: Colin Ian King <colin.king@canonical.com>
Link: https://lore.kernel.org/r/20210212112213.36b38078f569.I8546a20c80bc1669058eb453e213630b846e107b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index c4c70e30ad7f..68a0de02b561 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2950,14 +2950,14 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy,
 			continue;
 
 		for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) {
-			if (~sdata->rc_rateidx_mcs_mask[i][j]) {
+			if (sdata->rc_rateidx_mcs_mask[i][j] != 0xff) {
 				sdata->rc_has_mcs_mask[i] = true;
 				break;
 			}
 		}
 
 		for (j = 0; j < NL80211_VHT_NSS_MAX; j++) {
-			if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) {
+			if (sdata->rc_rateidx_vht_mcs_mask[i][j] != 0xffff) {
 				sdata->rc_has_vht_mcs_mask[i] = true;
 				break;
 			}

From 3bd801b14e0c5d29eeddc7336558beb3344efaa3 Mon Sep 17 00:00:00 2001
From: Markus Theil <markus.theil@tu-ilmenau.de>
Date: Sat, 13 Feb 2021 14:36:53 +0100
Subject: [PATCH 0913/1820] mac80211: fix double free in ibss_leave

Clear beacon ie pointer and ie length after free
in order to prevent double free.

==================================================================
BUG: KASAN: double-free or invalid-free \
in ieee80211_ibss_leave+0x83/0xe0 net/mac80211/ibss.c:1876

CPU: 0 PID: 8472 Comm: syz-executor100 Not tainted 5.11.0-rc6-syzkaller #0
Call Trace:
 __dump_stack lib/dump_stack.c:79 [inline]
 dump_stack+0x107/0x163 lib/dump_stack.c:120
 print_address_description.constprop.0.cold+0x5b/0x2c6 mm/kasan/report.c:230
 kasan_report_invalid_free+0x51/0x80 mm/kasan/report.c:355
 ____kasan_slab_free+0xcc/0xe0 mm/kasan/common.c:341
 kasan_slab_free include/linux/kasan.h:192 [inline]
 __cache_free mm/slab.c:3424 [inline]
 kfree+0xed/0x270 mm/slab.c:3760
 ieee80211_ibss_leave+0x83/0xe0 net/mac80211/ibss.c:1876
 rdev_leave_ibss net/wireless/rdev-ops.h:545 [inline]
 __cfg80211_leave_ibss+0x19a/0x4c0 net/wireless/ibss.c:212
 __cfg80211_leave+0x327/0x430 net/wireless/core.c:1172
 cfg80211_leave net/wireless/core.c:1221 [inline]
 cfg80211_netdev_notifier_call+0x9e8/0x12c0 net/wireless/core.c:1335
 notifier_call_chain+0xb5/0x200 kernel/notifier.c:83
 call_netdevice_notifiers_info+0xb5/0x130 net/core/dev.c:2040
 call_netdevice_notifiers_extack net/core/dev.c:2052 [inline]
 call_netdevice_notifiers net/core/dev.c:2066 [inline]
 __dev_close_many+0xee/0x2e0 net/core/dev.c:1586
 __dev_close net/core/dev.c:1624 [inline]
 __dev_change_flags+0x2cb/0x730 net/core/dev.c:8476
 dev_change_flags+0x8a/0x160 net/core/dev.c:8549
 dev_ifsioc+0x210/0xa70 net/core/dev_ioctl.c:265
 dev_ioctl+0x1b1/0xc40 net/core/dev_ioctl.c:511
 sock_do_ioctl+0x148/0x2d0 net/socket.c:1060
 sock_ioctl+0x477/0x6a0 net/socket.c:1177
 vfs_ioctl fs/ioctl.c:48 [inline]
 __do_sys_ioctl fs/ioctl.c:753 [inline]
 __se_sys_ioctl fs/ioctl.c:739 [inline]
 __x64_sys_ioctl+0x193/0x200 fs/ioctl.c:739
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Reported-by: syzbot+93976391bf299d425f44@syzkaller.appspotmail.com
Signed-off-by: Markus Theil <markus.theil@tu-ilmenau.de>
Link: https://lore.kernel.org/r/20210213133653.367130-1-markus.theil@tu-ilmenau.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ibss.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 1f552f374e97..a7ac53a2f00d 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -1874,6 +1874,8 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata)
 
 	/* remove beacon */
 	kfree(sdata->u.ibss.ie);
+	sdata->u.ibss.ie = NULL;
+	sdata->u.ibss.ie_len = 0;
 
 	/* on the next join, re-program HT parameters */
 	memset(&ifibss->ht_capa, 0, sizeof(ifibss->ht_capa));

From 29175be06d2f7d0e694bbdd086644dc15db66d60 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 19 Feb 2021 10:57:45 +0100
Subject: [PATCH 0914/1820] mac80211: minstrel_ht: remove unused variable 'mg'

This probably came in through some refactoring and what is
now a call to minstrel_ht_group_min_rate_offset(), remove
the unused variable.

Reported-by: kernel test robot <lkp@intel.com>
Acked-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/20210219105744.f2538a80f6cf.I3d53554c158d5b896ac07ea546bceac67372ec28@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/rc80211_minstrel_ht.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 2f44f4919789..ecad9b10984f 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -805,7 +805,6 @@ minstrel_ht_group_min_rate_offset(struct minstrel_ht_sta *mi, int group,
 static u16
 minstrel_ht_next_inc_rate(struct minstrel_ht_sta *mi, u32 fast_rate_dur)
 {
-	struct minstrel_mcs_group_data *mg;
 	u8 type = MINSTREL_SAMPLE_TYPE_INC;
 	int i, index = 0;
 	u8 group;
@@ -813,7 +812,6 @@ minstrel_ht_next_inc_rate(struct minstrel_ht_sta *mi, u32 fast_rate_dur)
 	group = mi->sample[type].sample_group;
 	for (i = 0; i < ARRAY_SIZE(minstrel_mcs_groups); i++) {
 		group = (group + 1) % ARRAY_SIZE(minstrel_mcs_groups);
-		mg = &mi->groups[group];
 
 		index = minstrel_ht_group_min_rate_offset(mi, group,
 							  fast_rate_dur);

From 0f7e90faddeef53a3568f449a0c3992d77510b66 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Tue, 23 Feb 2021 13:19:26 +0800
Subject: [PATCH 0915/1820] mac80211: Allow HE operation to be longer than
 expected.

We observed some Cisco APs sending the following HE Operation IE in
associate response:

  ff 0a 24 f4 3f 00 01 fc ff 00 00 00

Its HE operation parameter is 0x003ff4, so the expected total length is
7 which does not match the actual length = 10. This causes association
failing with "HE AP is missing HE Capability/operation."

According to P802.11ax_D4 Table9-94, HE operation is extensible, and
according to 802.11-2016 10.27.8, STA should discard the part beyond
the maximum length and parse the truncated element.

Allow HE operation element to be longer than expected to handle this
case and future extensions.

Fixes: e4d005b80dee ("mac80211: refactor extended element parsing")
Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Yen-lin Lai <yenlinlai@chromium.org>
Link: https://lore.kernel.org/r/20210223051926.2653301-1-yenlinlai@chromium.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 2 +-
 net/mac80211/util.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 2e33a1263518..ce4e3855fec1 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -5071,7 +5071,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 		he_oper_ie = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION,
 						  ies->data, ies->len);
 		if (he_oper_ie &&
-		    he_oper_ie[1] == ieee80211_he_oper_size(&he_oper_ie[3]))
+		    he_oper_ie[1] >= ieee80211_he_oper_size(&he_oper_ie[3]))
 			he_oper = (void *)(he_oper_ie + 3);
 		else
 			he_oper = NULL;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index f080fcf60e45..c0fa526a45b4 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -968,7 +968,7 @@ static void ieee80211_parse_extension_element(u32 *crc,
 		break;
 	case WLAN_EID_EXT_HE_OPERATION:
 		if (len >= sizeof(*elems->he_operation) &&
-		    len == ieee80211_he_oper_size(data) - 1) {
+		    len >= ieee80211_he_oper_size(data) - 1) {
 			if (crc)
 				*crc = crc32_be(*crc, (void *)elem,
 						elem->datalen + 2);

From 58d25626f6f0ea5bcec3c13387b9f835d188723d Mon Sep 17 00:00:00 2001
From: Daniel Phan <daniel.phan36@gmail.com>
Date: Tue, 9 Mar 2021 12:41:36 -0800
Subject: [PATCH 0916/1820] mac80211: Check crypto_aead_encrypt for errors

crypto_aead_encrypt returns <0 on error, so if these calls are not checked,
execution may continue with failed encrypts.  It also seems that these two
crypto_aead_encrypt calls are the only instances in the codebase that are
not checked for errors.

Signed-off-by: Daniel Phan <daniel.phan36@gmail.com>
Link: https://lore.kernel.org/r/20210309204137.823268-1-daniel.phan36@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/aead_api.c | 5 +++--
 net/mac80211/aes_gmac.c | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/aead_api.c b/net/mac80211/aead_api.c
index d7b3d905d535..b00d6f5b33f4 100644
--- a/net/mac80211/aead_api.c
+++ b/net/mac80211/aead_api.c
@@ -23,6 +23,7 @@ int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len,
 	struct aead_request *aead_req;
 	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
 	u8 *__aad;
+	int ret;
 
 	aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC);
 	if (!aead_req)
@@ -40,10 +41,10 @@ int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len,
 	aead_request_set_crypt(aead_req, sg, sg, data_len, b_0);
 	aead_request_set_ad(aead_req, sg[0].length);
 
-	crypto_aead_encrypt(aead_req);
+	ret = crypto_aead_encrypt(aead_req);
 	kfree_sensitive(aead_req);
 
-	return 0;
+	return ret;
 }
 
 int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len,
diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c
index 6f3b3a0cc10a..512cab073f2e 100644
--- a/net/mac80211/aes_gmac.c
+++ b/net/mac80211/aes_gmac.c
@@ -22,6 +22,7 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
 	struct aead_request *aead_req;
 	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
 	const __le16 *fc;
+	int ret;
 
 	if (data_len < GMAC_MIC_LEN)
 		return -EINVAL;
@@ -59,10 +60,10 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
 	aead_request_set_crypt(aead_req, sg, sg, 0, iv);
 	aead_request_set_ad(aead_req, GMAC_AAD_LEN + data_len);
 
-	crypto_aead_encrypt(aead_req);
+	ret = crypto_aead_encrypt(aead_req);
 	kfree_sensitive(aead_req);
 
-	return 0;
+	return ret;
 }
 
 struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[],

From 77cbf790e5b482256662e14c8b6ef4fecb07d06d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 10 Mar 2021 21:58:40 +0100
Subject: [PATCH 0917/1820] nl80211: fix locking for wireless device netns
 change

We have all the network interfaces marked as netns-local
since the only reasonable thing to do right now is to set
a whole device, including all netdevs, into a different
network namespace. For this reason, we also have our own
way of changing the network namespace.

Unfortunately, the RTNL locking changes broke this, and
it now results in many RTNL assertions. The trivial fix
for those (just hold RTNL for the changes) however leads
to deadlocks in the cfg80211 netdev notifier.

Since we only need the wiphy, and that's still protected
by the RTNL, add a new NL80211_FLAG_NO_WIPHY_MTX flag to
the nl80211 ops and use it to _not_ take the wiphy mutex
but only the RTNL. This way, the notifier does all the
work necessary during unregistration/registration of the
netdevs from the old and in the new namespace.

Reported-by: Sid Hayn <sidhayn@gmail.com>
Fixes: a05829a7222e ("cfg80211: avoid holding the RTNL when calling the driver")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://lore.kernel.org/r/20210310215839.eadf7c43781b.I5fc6cf6676f800ab8008e03bbea9c3349b02d804@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 521d36bb0803..ae6097fff133 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -14789,6 +14789,7 @@ bad_tid_conf:
 #define NL80211_FLAG_NEED_WDEV_UP	(NL80211_FLAG_NEED_WDEV |\
 					 NL80211_FLAG_CHECK_NETDEV_UP)
 #define NL80211_FLAG_CLEAR_SKB		0x20
+#define NL80211_FLAG_NO_WIPHY_MTX	0x40
 
 static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
 			    struct genl_info *info)
@@ -14840,7 +14841,7 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
 		info->user_ptr[0] = rdev;
 	}
 
-	if (rdev) {
+	if (rdev && !(ops->internal_flags & NL80211_FLAG_NO_WIPHY_MTX)) {
 		wiphy_lock(&rdev->wiphy);
 		/* we keep the mutex locked until post_doit */
 		__release(&rdev->wiphy.mtx);
@@ -14865,7 +14866,8 @@ static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
 		}
 	}
 
-	if (info->user_ptr[0]) {
+	if (info->user_ptr[0] &&
+	    !(ops->internal_flags & NL80211_FLAG_NO_WIPHY_MTX)) {
 		struct cfg80211_registered_device *rdev = info->user_ptr[0];
 
 		/* we kept the mutex locked since pre_doit */
@@ -15329,7 +15331,9 @@ static const struct genl_small_ops nl80211_small_ops[] = {
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_wiphy_netns,
 		.flags = GENL_UNS_ADMIN_PERM,
-		.internal_flags = NL80211_FLAG_NEED_WIPHY,
+		.internal_flags = NL80211_FLAG_NEED_WIPHY |
+				  NL80211_FLAG_NEED_RTNL |
+				  NL80211_FLAG_NO_WIPHY_MTX,
 	},
 	{
 		.cmd = NL80211_CMD_GET_SURVEY,

From 041c881a0ba8a75f71118bd9766b78f04beed469 Mon Sep 17 00:00:00 2001
From: Karthikeyan Kathirvel <kathirve@codeaurora.org>
Date: Thu, 11 Mar 2021 10:59:07 +0530
Subject: [PATCH 0918/1820] mac80211: choose first enabled channel for monitor

Even if the first channel from sband channel list is invalid
or disabled mac80211 ends up choosing it as the default channel
for monitor interfaces, making them not usable.

Fix this by assigning the first available valid or enabled
channel instead.

Signed-off-by: Karthikeyan Kathirvel <kathirve@codeaurora.org>
Link: https://lore.kernel.org/r/1615440547-7661-1-git-send-email-kathirve@codeaurora.org
[reword commit message, comment, code cleanups]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/main.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 4f3f8bb58e76..1b9c82616606 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -973,8 +973,19 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 			continue;
 
 		if (!dflt_chandef.chan) {
+			/*
+			 * Assign the first enabled channel to dflt_chandef
+			 * from the list of channels
+			 */
+			for (i = 0; i < sband->n_channels; i++)
+				if (!(sband->channels[i].flags &
+						IEEE80211_CHAN_DISABLED))
+					break;
+			/* if none found then use the first anyway */
+			if (i == sband->n_channels)
+				i = 0;
 			cfg80211_chandef_create(&dflt_chandef,
-						&sband->channels[0],
+						&sband->channels[i],
 						NL80211_CHAN_NO_HT);
 			/* init channel we're on */
 			if (!local->use_chanctx && !local->_oper_chandef.chan) {

From 239729a21e528466d02f5558936306ffa9314ad1 Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Fri, 12 Mar 2021 11:36:51 -0500
Subject: [PATCH 0919/1820] wireless/nl80211: fix wdev_id may be used
 uninitialized

Build currently fails with -Werror=maybe-uninitialized set:

net/wireless/nl80211.c: In function '__cfg80211_wdev_from_attrs':
net/wireless/nl80211.c:124:44: error: 'wdev_id' may be used
uninitialized in this function [-Werror=maybe-uninitialized]

Easy fix is to just initialize wdev_id to 0, since it's value doesn't
otherwise matter unless have_wdev_id is true.

Fixes: a05829a7222e ("cfg80211: avoid holding the RTNL when calling the driver")
CC: Johannes Berg <johannes@sipsolutions.net>
CC: "David S. Miller" <davem@davemloft.net>
CC: Jakub Kicinski <kuba@kernel.org>
CC: linux-wireless@vger.kernel.org
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Link: https://lore.kernel.org/r/20210312163651.1398207-1-jarod@redhat.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ae6097fff133..034af85f79d8 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -70,7 +70,7 @@ __cfg80211_wdev_from_attrs(struct cfg80211_registered_device *rdev,
 	struct wireless_dev *result = NULL;
 	bool have_ifidx = attrs[NL80211_ATTR_IFINDEX];
 	bool have_wdev_id = attrs[NL80211_ATTR_WDEV];
-	u64 wdev_id;
+	u64 wdev_id = 0;
 	int wiphy_idx = -1;
 	int ifidx = -1;
 

From d88d05a9e0b6d9356e97129d4ff9942d765f46ea Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 12 Mar 2021 05:21:37 -0800
Subject: [PATCH 0920/1820] perf/x86/intel: Fix a crash caused by zero PEBS
 status

A repeatable crash can be triggered by the perf_fuzzer on some Haswell
system.
https://lore.kernel.org/lkml/7170d3b-c17f-1ded-52aa-cc6d9ae999f4@maine.edu/

For some old CPUs (HSW and earlier), the PEBS status in a PEBS record
may be mistakenly set to 0. To minimize the impact of the defect, the
commit was introduced to try to avoid dropping the PEBS record for some
cases. It adds a check in the intel_pmu_drain_pebs_nhm(), and updates
the local pebs_status accordingly. However, it doesn't correct the PEBS
status in the PEBS record, which may trigger the crash, especially for
the large PEBS.

It's possible that all the PEBS records in a large PEBS have the PEBS
status 0. If so, the first get_next_pebs_record_by_bit() in the
__intel_pmu_pebs_event() returns NULL. The at = NULL. Since it's a large
PEBS, the 'count' parameter must > 1. The second
get_next_pebs_record_by_bit() will crash.

Besides the local pebs_status, correct the PEBS status in the PEBS
record as well.

Fixes: 01330d7288e0 ("perf/x86: Allow zero PEBS status with only single active event")
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1615555298-140216-1-git-send-email-kan.liang@linux.intel.com
---
 arch/x86/events/intel/ds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7ebae1826403..d32b302719fe 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -2010,7 +2010,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 		 */
 		if (!pebs_status && cpuc->pebs_enabled &&
 			!(cpuc->pebs_enabled & (cpuc->pebs_enabled-1)))
-			pebs_status = cpuc->pebs_enabled;
+			pebs_status = p->status = cpuc->pebs_enabled;
 
 		bit = find_first_bit((unsigned long *)&pebs_status,
 					x86_pmu.max_pebs_events);

From 2dc0572f2cef87425147658698dce2600b799bd3 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 12 Mar 2021 05:21:38 -0800
Subject: [PATCH 0921/1820] perf/x86/intel: Fix unchecked MSR access error
 caused by VLBR_EVENT

On a Haswell machine, the perf_fuzzer managed to trigger this message:

[117248.075892] unchecked MSR access error: WRMSR to 0x3f1 (tried to
write 0x0400000000000000) at rIP: 0xffffffff8106e4f4
(native_write_msr+0x4/0x20)
[117248.089957] Call Trace:
[117248.092685]  intel_pmu_pebs_enable_all+0x31/0x40
[117248.097737]  intel_pmu_enable_all+0xa/0x10
[117248.102210]  __perf_event_task_sched_in+0x2df/0x2f0
[117248.107511]  finish_task_switch.isra.0+0x15f/0x280
[117248.112765]  schedule_tail+0xc/0x40
[117248.116562]  ret_from_fork+0x8/0x30

A fake event called VLBR_EVENT may use the bit 58 of the PEBS_ENABLE, if
the precise_ip is set. The bit 58 is reserved by the HW. Accessing the
bit causes the unchecked MSR access error.

The fake event doesn't support PEBS. The case should be rejected.

Fixes: 097e4311cda9 ("perf/x86: Add constraint to create guest LBR event without hw counter")
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1615555298-140216-2-git-send-email-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7bbb5bb98d8c..37ce38403cb8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3659,6 +3659,9 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		return ret;
 
 	if (event->attr.precise_ip) {
+		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
+			return -EINVAL;
+
 		if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &

From 5abbe51a526253b9f003e9a0a195638dc882d660 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 1 Feb 2021 18:46:41 +0100
Subject: [PATCH 0922/1820] kernel, fs: Introduce and use set_restart_fn() and
 arch_set_restart_data()

Preparation for fixing get_nr_restart_syscall() on X86 for COMPAT.

Add a new helper which sets restart_block->fn and calls a dummy
arch_set_restart_data() helper.

Fixes: 609c19a385c8 ("x86/ptrace: Stop setting TS_COMPAT in ptrace code")
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210201174641.GA17871@redhat.com
---
 fs/select.c                    | 10 ++++------
 include/linux/thread_info.h    | 13 +++++++++++++
 kernel/futex.c                 |  3 +--
 kernel/time/alarmtimer.c       |  2 +-
 kernel/time/hrtimer.c          |  2 +-
 kernel/time/posix-cpu-timers.c |  2 +-
 6 files changed, 21 insertions(+), 11 deletions(-)

diff --git a/fs/select.c b/fs/select.c
index 37aaa8317f3a..945896d0ac9e 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -1055,10 +1055,9 @@ static long do_restart_poll(struct restart_block *restart_block)
 
 	ret = do_sys_poll(ufds, nfds, to);
 
-	if (ret == -ERESTARTNOHAND) {
-		restart_block->fn = do_restart_poll;
-		ret = -ERESTART_RESTARTBLOCK;
-	}
+	if (ret == -ERESTARTNOHAND)
+		ret = set_restart_fn(restart_block, do_restart_poll);
+
 	return ret;
 }
 
@@ -1080,7 +1079,6 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
 		struct restart_block *restart_block;
 
 		restart_block = &current->restart_block;
-		restart_block->fn = do_restart_poll;
 		restart_block->poll.ufds = ufds;
 		restart_block->poll.nfds = nfds;
 
@@ -1091,7 +1089,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
 		} else
 			restart_block->poll.has_timeout = 0;
 
-		ret = -ERESTART_RESTARTBLOCK;
+		ret = set_restart_fn(restart_block, do_restart_poll);
 	}
 	return ret;
 }
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 9b2158c69275..157762db9d4b 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <linux/bug.h>
 #include <linux/restart_block.h>
+#include <linux/errno.h>
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 /*
@@ -59,6 +60,18 @@ enum syscall_work_bit {
 
 #ifdef __KERNEL__
 
+#ifndef arch_set_restart_data
+#define arch_set_restart_data(restart) do { } while (0)
+#endif
+
+static inline long set_restart_fn(struct restart_block *restart,
+					long (*fn)(struct restart_block *))
+{
+	restart->fn = fn;
+	arch_set_restart_data(restart);
+	return -ERESTART_RESTARTBLOCK;
+}
+
 #ifndef THREAD_ALIGN
 #define THREAD_ALIGN	THREAD_SIZE
 #endif
diff --git a/kernel/futex.c b/kernel/futex.c
index e68db7745039..00febd6dea9c 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2728,14 +2728,13 @@ retry:
 		goto out;
 
 	restart = &current->restart_block;
-	restart->fn = futex_wait_restart;
 	restart->futex.uaddr = uaddr;
 	restart->futex.val = val;
 	restart->futex.time = *abs_time;
 	restart->futex.bitset = bitset;
 	restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
 
-	ret = -ERESTART_RESTARTBLOCK;
+	ret = set_restart_fn(restart, futex_wait_restart);
 
 out:
 	if (to) {
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 98d7a15e8cf6..4d94e2b5499d 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -854,9 +854,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	if (flags == TIMER_ABSTIME)
 		return -ERESTARTNOHAND;
 
-	restart->fn = alarm_timer_nsleep_restart;
 	restart->nanosleep.clockid = type;
 	restart->nanosleep.expires = exp;
+	set_restart_fn(restart, alarm_timer_nsleep_restart);
 	return ret;
 }
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 788b9d137de4..5c9d968187ae 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1957,9 +1957,9 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
 	}
 
 	restart = &current->restart_block;
-	restart->fn = hrtimer_nanosleep_restart;
 	restart->nanosleep.clockid = t.timer.base->clockid;
 	restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
+	set_restart_fn(restart, hrtimer_nanosleep_restart);
 out:
 	destroy_hrtimer_on_stack(&t.timer);
 	return ret;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index a71758e34e45..9abe15255bc4 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1480,8 +1480,8 @@ static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 		if (flags & TIMER_ABSTIME)
 			return -ERESTARTNOHAND;
 
-		restart_block->fn = posix_cpu_nsleep_restart;
 		restart_block->nanosleep.clockid = which_clock;
+		set_restart_fn(restart_block, posix_cpu_nsleep_restart);
 	}
 	return error;
 }

From 66c1b6d74cd7035e85c426f0af4aede19e805c8a Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 1 Feb 2021 18:46:49 +0100
Subject: [PATCH 0923/1820] x86: Move TS_COMPAT back to asm/thread_info.h

Move TS_COMPAT back to asm/thread_info.h, close to TS_I386_REGS_POKED.

It was moved to asm/processor.h by b9d989c7218a ("x86/asm: Move the
thread_info::status field to thread_struct"), then later 37a8f7c38339
("x86/asm: Move 'status' from thread_struct to thread_info") moved the
'status' field back but TS_COMPAT was forgotten.

Preparatory patch to fix the COMPAT case for get_nr_restart_syscall()

Fixes: 609c19a385c8 ("x86/ptrace: Stop setting TS_COMPAT in ptrace code")
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210201174649.GA17880@redhat.com
---
 arch/x86/include/asm/processor.h   | 9 ---------
 arch/x86/include/asm/thread_info.h | 9 +++++++++
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index dc6d149bf851..f1b9ed5efaa9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -551,15 +551,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
 	*size = fpu_kernel_xstate_size;
 }
 
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
-
 static inline void
 native_load_sp0(unsigned long sp0)
 {
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 0d751d5da702..c2dc29e215ea 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -205,6 +205,15 @@ static inline int arch_within_stack_frames(const void * const stack,
 
 #endif
 
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
+
 #ifdef CONFIG_COMPAT
 #define TS_I386_REGS_POKED	0x0004	/* regs poked by 32-bit ptracer */
 #endif

From 8c150ba2fb5995c84a7a43848250d444a3329a7d Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 1 Feb 2021 18:47:09 +0100
Subject: [PATCH 0924/1820] x86: Introduce TS_COMPAT_RESTART to fix
 get_nr_restart_syscall()

The comment in get_nr_restart_syscall() says:

	 * The problem is that we can get here when ptrace pokes
	 * syscall-like values into regs even if we're not in a syscall
	 * at all.

Yes, but if not in a syscall then the

	status & (TS_COMPAT|TS_I386_REGS_POKED)

check below can't really help:

	- TS_COMPAT can't be set

	- TS_I386_REGS_POKED is only set if regs->orig_ax was changed by
	  32bit debugger; and even in this case get_nr_restart_syscall()
	  is only correct if the tracee is 32bit too.

Suppose that a 64bit debugger plays with a 32bit tracee and

	* Tracee calls sleep(2)	// TS_COMPAT is set
	* User interrupts the tracee by CTRL-C after 1 sec and does
	  "(gdb) call func()"
	* gdb saves the regs by PTRACE_GETREGS
	* does PTRACE_SETREGS to set %rip='func' and %orig_rax=-1
	* PTRACE_CONT		// TS_COMPAT is cleared
	* func() hits int3.
	* Debugger catches SIGTRAP.
	* Restore original regs by PTRACE_SETREGS.
	* PTRACE_CONT

get_nr_restart_syscall() wrongly returns __NR_restart_syscall==219, the
tracee calls ia32_sys_call_table[219] == sys_madvise.

Add the sticky TS_COMPAT_RESTART flag which survives after return to user
mode. It's going to be removed in the next step again by storing the
information in the restart block. As a further cleanup it might be possible
to remove also TS_I386_REGS_POKED with that.

Test-case:

  $ cvs -d :pserver:anoncvs:anoncvs@sourceware.org:/cvs/systemtap co ptrace-tests
  $ gcc -o erestartsys-trap-debuggee ptrace-tests/tests/erestartsys-trap-debuggee.c --m32
  $ gcc -o erestartsys-trap-debugger ptrace-tests/tests/erestartsys-trap-debugger.c -lutil
  $ ./erestartsys-trap-debugger
  Unexpected: retval 1, errno 22
  erestartsys-trap-debugger: ptrace-tests/tests/erestartsys-trap-debugger.c:421

Fixes: 609c19a385c8 ("x86/ptrace: Stop setting TS_COMPAT in ptrace code")
Reported-by: Jan Kratochvil <jan.kratochvil@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210201174709.GA17895@redhat.com
---
 arch/x86/include/asm/thread_info.h | 14 +++++++++++++-
 arch/x86/kernel/signal.c           | 24 +-----------------------
 2 files changed, 14 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index c2dc29e215ea..30d1d187019f 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -214,10 +214,22 @@ static inline int arch_within_stack_frames(const void * const stack,
  */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 
+#ifndef __ASSEMBLY__
 #ifdef CONFIG_COMPAT
 #define TS_I386_REGS_POKED	0x0004	/* regs poked by 32-bit ptracer */
+#define TS_COMPAT_RESTART	0x0008
+
+#define arch_set_restart_data	arch_set_restart_data
+
+static inline void arch_set_restart_data(struct restart_block *restart)
+{
+	struct thread_info *ti = current_thread_info();
+	if (ti->status & TS_COMPAT)
+		ti->status |= TS_COMPAT_RESTART;
+	else
+		ti->status &= ~TS_COMPAT_RESTART;
+}
 #endif
-#ifndef __ASSEMBLY__
 
 #ifdef CONFIG_X86_32
 #define in_ia32_syscall() true
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index ea794a083c44..6c26d2c3a2e4 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -766,30 +766,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 
 static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
 {
-	/*
-	 * This function is fundamentally broken as currently
-	 * implemented.
-	 *
-	 * The idea is that we want to trigger a call to the
-	 * restart_block() syscall and that we want in_ia32_syscall(),
-	 * in_x32_syscall(), etc. to match whatever they were in the
-	 * syscall being restarted.  We assume that the syscall
-	 * instruction at (regs->ip - 2) matches whatever syscall
-	 * instruction we used to enter in the first place.
-	 *
-	 * The problem is that we can get here when ptrace pokes
-	 * syscall-like values into regs even if we're not in a syscall
-	 * at all.
-	 *
-	 * For now, we maintain historical behavior and guess based on
-	 * stored state.  We could do better by saving the actual
-	 * syscall arch in restart_block or (with caveats on x32) by
-	 * checking if regs->ip points to 'int $0x80'.  The current
-	 * behavior is incorrect if a tracer has a different bitness
-	 * than the tracee.
-	 */
 #ifdef CONFIG_IA32_EMULATION
-	if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED))
+	if (current_thread_info()->status & TS_COMPAT_RESTART)
 		return __NR_ia32_restart_syscall;
 #endif
 #ifdef CONFIG_X86_X32_ABI

From b2e9df850c58c2b36e915e7d3bed3f6107cccba6 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 1 Feb 2021 18:47:16 +0100
Subject: [PATCH 0925/1820] x86: Introduce restart_block->arch_data to remove
 TS_COMPAT_RESTART

Save the current_thread_info()->status of X86 in the new
restart_block->arch_data field so TS_COMPAT_RESTART can be removed again.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20210201174716.GA17898@redhat.com
---
 arch/x86/include/asm/thread_info.h | 12 ++----------
 arch/x86/kernel/signal.c           |  2 +-
 include/linux/restart_block.h      |  1 +
 3 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 30d1d187019f..06b740bae431 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -217,18 +217,10 @@ static inline int arch_within_stack_frames(const void * const stack,
 #ifndef __ASSEMBLY__
 #ifdef CONFIG_COMPAT
 #define TS_I386_REGS_POKED	0x0004	/* regs poked by 32-bit ptracer */
-#define TS_COMPAT_RESTART	0x0008
 
-#define arch_set_restart_data	arch_set_restart_data
+#define arch_set_restart_data(restart)	\
+	do { restart->arch_data = current_thread_info()->status; } while (0)
 
-static inline void arch_set_restart_data(struct restart_block *restart)
-{
-	struct thread_info *ti = current_thread_info();
-	if (ti->status & TS_COMPAT)
-		ti->status |= TS_COMPAT_RESTART;
-	else
-		ti->status &= ~TS_COMPAT_RESTART;
-}
 #endif
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 6c26d2c3a2e4..f306e85a08a6 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -767,7 +767,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
 {
 #ifdef CONFIG_IA32_EMULATION
-	if (current_thread_info()->status & TS_COMPAT_RESTART)
+	if (current->restart_block.arch_data & TS_COMPAT)
 		return __NR_ia32_restart_syscall;
 #endif
 #ifdef CONFIG_X86_X32_ABI
diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h
index bba2920e9c05..980a65594412 100644
--- a/include/linux/restart_block.h
+++ b/include/linux/restart_block.h
@@ -23,6 +23,7 @@ enum timespec_type {
  * System call restart block.
  */
 struct restart_block {
+	unsigned long arch_data;
 	long (*fn)(struct restart_block *);
 	union {
 		/* For futex_wait and futex_wait_requeue_pi */

From 3f6c515d723480bc8afd456b0a52438fe79128a8 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Tue, 16 Mar 2021 15:45:15 +0000
Subject: [PATCH 0926/1820] MIPS: vmlinux.lds.S: Fix appended dtb not properly
 aligned
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 6654111c893f ("MIPS: vmlinux.lds.S: align raw appended dtb to 8
bytes") changed the alignment from STRUCT_ALIGNMENT bytes to 8 bytes.

The commit's message makes it sound like it was actually done on
purpose, but this is not the case. The commit was written when raw
appended dtb were not aligned at all. The STRUCT_ALIGN() was added a few
days before, in commit 7a05293af39f ("MIPS: boot/compressed: Copy DTB to
aligned address"). The true purpose of the commit was not to align
specifically to 8 bytes, but to make sure that the generated vmlinux'
size was properly padded to the alignment required for DTBs.

While the switch to 8-byte alignment worked for vmlinux-appended dtb
blobs, it broke vmlinuz-appended dtb blobs, as the decompress routine
moves the blob to a STRUCT_ALIGNMENT aligned address.

Fix this by changing the raw appended dtb blob alignment from 8 bytes
back to STRUCT_ALIGNMENT bytes in vmlinux.lds.S.

Fixes: 6654111c893f ("MIPS: vmlinux.lds.S: align raw appended dtb to 8 bytes")
Cc: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/kernel/vmlinux.lds.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 1234834cc4c4..1f98947fe715 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -176,7 +176,7 @@ SECTIONS
 	.fill : {
 		FILL(0);
 		BYTE(0);
-		. = ALIGN(8);
+		STRUCT_ALIGN();
 	}
 	__appended_dtb = .;
 	/* leave space for appended DTB */

From 81f711d67a973bf8a6db9556faf299b4074d536e Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Tue, 16 Mar 2021 01:04:29 +0000
Subject: [PATCH 0927/1820] selftests/net: fix warnings on
 reuseaddr_ports_exhausted

Fix multiple warnings seen with gcc 10.2.1:
reuseaddr_ports_exhausted.c:32:41: warning: missing braces around initializer [-Wmissing-braces]
   32 | struct reuse_opts unreusable_opts[12] = {
      |                                         ^
   33 |  {0, 0, 0, 0},
      |   {   } {   }

Fixes: 7f204a7de8b0 ("selftests: net: Add SO_REUSEADDR test to check if 4-tuples are fully utilized.")
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/reuseaddr_ports_exhausted.c | 32 +++++++++----------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
index 7b01b7c2ec10..066efd30e294 100644
--- a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
+++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
@@ -30,25 +30,25 @@ struct reuse_opts {
 };
 
 struct reuse_opts unreusable_opts[12] = {
-	{0, 0, 0, 0},
-	{0, 0, 0, 1},
-	{0, 0, 1, 0},
-	{0, 0, 1, 1},
-	{0, 1, 0, 0},
-	{0, 1, 0, 1},
-	{0, 1, 1, 0},
-	{0, 1, 1, 1},
-	{1, 0, 0, 0},
-	{1, 0, 0, 1},
-	{1, 0, 1, 0},
-	{1, 0, 1, 1},
+	{{0, 0}, {0, 0}},
+	{{0, 0}, {0, 1}},
+	{{0, 0}, {1, 0}},
+	{{0, 0}, {1, 1}},
+	{{0, 1}, {0, 0}},
+	{{0, 1}, {0, 1}},
+	{{0, 1}, {1, 0}},
+	{{0, 1}, {1, 1}},
+	{{1, 0}, {0, 0}},
+	{{1, 0}, {0, 1}},
+	{{1, 0}, {1, 0}},
+	{{1, 0}, {1, 1}},
 };
 
 struct reuse_opts reusable_opts[4] = {
-	{1, 1, 0, 0},
-	{1, 1, 0, 1},
-	{1, 1, 1, 0},
-	{1, 1, 1, 1},
+	{{1, 1}, {0, 0}},
+	{{1, 1}, {0, 1}},
+	{{1, 1}, {1, 0}},
+	{{1, 1}, {1, 1}},
 };
 
 int bind_port(struct __test_metadata *_metadata, int reuseaddr, int reuseport)

From 8a4452ca29f9dc6a65e45a38c96af83b8ecb27fc Mon Sep 17 00:00:00 2001
From: Zenghui Yu <yuzenghui@huawei.com>
Date: Tue, 16 Mar 2021 11:27:37 +0800
Subject: [PATCH 0928/1820] docs: net: ena: Fix ena_start_xmit() function name
 typo

The ena.rst documentation referred to end_start_xmit() when it should refer
to ena_start_xmit(). Fix the typo.

Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
Acked-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/device_drivers/ethernet/amazon/ena.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
index 3561a8a29fd2..f8c6469f2bd2 100644
--- a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
+++ b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
@@ -267,7 +267,7 @@ DATA PATH
 Tx
 --
 
-end_start_xmit() is called by the stack. This function does the following:
+ena_start_xmit() is called by the stack. This function does the following:
 
 - Maps data buffers (skb->data and frags).
 - Populates ena_buf for the push buffer (if the driver and device are

From d29334c15d33a6a92d2043ca88f84cd5ad026c57 Mon Sep 17 00:00:00 2001
From: wenxu <wenxu@ucloud.cn>
Date: Tue, 16 Mar 2021 16:33:54 +0800
Subject: [PATCH 0929/1820] net/sched: act_api: fix miss set post_ct for ovs
 after do conntrack in act_ct

When openvswitch conntrack offload with act_ct action. The first rule
do conntrack in the act_ct in tc subsystem. And miss the next rule in
the tc and fallback to the ovs datapath but miss set post_ct flag
which will lead the ct_state_key with -trk flag.

Fixes: 7baf2429a1a9 ("net/sched: cls_flower add CT_FLAGS_INVALID flag support")
Signed-off-by: wenxu <wenxu@ucloud.cn>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h      | 1 +
 net/openvswitch/conntrack.c | 8 +++++---
 net/openvswitch/conntrack.h | 6 ++++--
 net/openvswitch/flow.c      | 4 +++-
 net/sched/cls_api.c         | 1 +
 5 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6d0a33d1c0db..f2c9ee71cb2c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -285,6 +285,7 @@ struct nf_bridge_info {
 struct tc_skb_ext {
 	__u32 chain;
 	__u16 mru;
+	bool post_ct;
 };
 #endif
 
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 5eddfe7bd391..71cec03e8612 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -271,9 +271,11 @@ static void ovs_ct_update_key(const struct sk_buff *skb,
 /* This is called to initialize CT key fields possibly coming in from the local
  * stack.
  */
-void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
+void ovs_ct_fill_key(const struct sk_buff *skb,
+		     struct sw_flow_key *key,
+		     bool post_ct)
 {
-	ovs_ct_update_key(skb, NULL, key, false, false);
+	ovs_ct_update_key(skb, NULL, key, post_ct, false);
 }
 
 int ovs_ct_put_key(const struct sw_flow_key *swkey,
@@ -1332,7 +1334,7 @@ int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key)
 	if (skb_nfct(skb)) {
 		nf_conntrack_put(skb_nfct(skb));
 		nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
-		ovs_ct_fill_key(skb, key);
+		ovs_ct_fill_key(skb, key, false);
 	}
 
 	return 0;
diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h
index 59dc32761b91..317e525c8a11 100644
--- a/net/openvswitch/conntrack.h
+++ b/net/openvswitch/conntrack.h
@@ -25,7 +25,8 @@ int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *,
 		   const struct ovs_conntrack_info *);
 int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key);
 
-void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key);
+void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key,
+		     bool post_ct);
 int ovs_ct_put_key(const struct sw_flow_key *swkey,
 		   const struct sw_flow_key *output, struct sk_buff *skb);
 void ovs_ct_free_action(const struct nlattr *a);
@@ -74,7 +75,8 @@ static inline int ovs_ct_clear(struct sk_buff *skb,
 }
 
 static inline void ovs_ct_fill_key(const struct sk_buff *skb,
-				   struct sw_flow_key *key)
+				   struct sw_flow_key *key,
+				   bool post_ct)
 {
 	key->ct_state = 0;
 	key->ct_zone = 0;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index c7f34d6a9934..e586424d8b04 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -857,6 +857,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
 	struct tc_skb_ext *tc_ext;
 #endif
+	bool post_ct = false;
 	int res, err;
 
 	/* Extract metadata from packet. */
@@ -895,6 +896,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 		tc_ext = skb_ext_find(skb, TC_SKB_EXT);
 		key->recirc_id = tc_ext ? tc_ext->chain : 0;
 		OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0;
+		post_ct = tc_ext ? tc_ext->post_ct : false;
 	} else {
 		key->recirc_id = 0;
 	}
@@ -904,7 +906,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 
 	err = key_extract(skb, key);
 	if (!err)
-		ovs_ct_fill_key(skb, key);   /* Must be after key_extract(). */
+		ovs_ct_fill_key(skb, key, post_ct);   /* Must be after key_extract(). */
 	return err;
 }
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e37556cc37ab..13341e7fb077 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1629,6 +1629,7 @@ int tcf_classify_ingress(struct sk_buff *skb,
 			return TC_ACT_SHOT;
 		ext->chain = last_executed_chain;
 		ext->mru = qdisc_skb_cb(skb)->mru;
+		ext->post_ct = qdisc_skb_cb(skb)->post_ct;
 	}
 
 	return ret;

From a3bc483216650a7232559bf0a1debfbabff3e12c Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 16 Mar 2021 15:03:41 +0100
Subject: [PATCH 0930/1820] net: broadcom: BCM4908_ENET should not default to
 y, unconditionally
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Merely enabling compile-testing should not enable additional code.
To fix this, restrict the automatic enabling of BCM4908_ENET to
ARCH_BCM4908.

Fixes: 4feffeadbcb2e5b1 ("net: broadcom: bcm4908enet: add BCM4908 controller driver")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index f8a168b73307..cb88ffb8f12f 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -54,7 +54,7 @@ config B44_PCI
 config BCM4908_ENET
 	tristate "Broadcom BCM4908 internal mac support"
 	depends on ARCH_BCM4908 || COMPILE_TEST
-	default y
+	default y if ARCH_BCM4908
 	help
 	  This driver supports Ethernet controller integrated into Broadcom
 	  BCM4908 family SoCs.

From 982e5ee23d764fe6158f67a7813d416335e978b0 Mon Sep 17 00:00:00 2001
From: Louis Peens <louis.peens@corigine.com>
Date: Tue, 16 Mar 2021 19:13:08 +0100
Subject: [PATCH 0931/1820] nfp: flower: fix unsupported pre_tunnel flows

There are some pre_tunnel flows combinations which are incorrectly being
offloaded without proper support, fix these.

- Matching on MPLS is not supported for pre_tun.
- Match on IPv4/IPv6 layer must be present.
- Destination MAC address must match pre_tun.dev MAC

Fixes: 120ffd84a9ec ("nfp: flower: verify pre-tunnel rules")
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/netronome/nfp/flower/offload.c    | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 1c59aff2163c..d72225d64a75 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1142,6 +1142,12 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app,
 		return -EOPNOTSUPP;
 	}
 
+	if (!(key_layer & NFP_FLOWER_LAYER_IPV4) &&
+	    !(key_layer & NFP_FLOWER_LAYER_IPV6)) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: match on ipv4/ipv6 eth_type must be present");
+		return -EOPNOTSUPP;
+	}
+
 	/* Skip fields known to exist. */
 	mask += sizeof(struct nfp_flower_meta_tci);
 	ext += sizeof(struct nfp_flower_meta_tci);
@@ -1152,6 +1158,13 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app,
 	mask += sizeof(struct nfp_flower_in_port);
 	ext += sizeof(struct nfp_flower_in_port);
 
+	/* Ensure destination MAC address matches pre_tun_dev. */
+	mac = (struct nfp_flower_mac_mpls *)ext;
+	if (memcmp(&mac->mac_dst[0], flow->pre_tun_rule.dev->dev_addr, 6)) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: dest MAC must match output dev MAC");
+		return -EOPNOTSUPP;
+	}
+
 	/* Ensure destination MAC address is fully matched. */
 	mac = (struct nfp_flower_mac_mpls *)mask;
 	if (!is_broadcast_ether_addr(&mac->mac_dst[0])) {
@@ -1159,6 +1172,11 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app,
 		return -EOPNOTSUPP;
 	}
 
+	if (mac->mpls_lse) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: MPLS not supported");
+		return -EOPNOTSUPP;
+	}
+
 	mask += sizeof(struct nfp_flower_mac_mpls);
 	ext += sizeof(struct nfp_flower_mac_mpls);
 	if (key_layer & NFP_FLOWER_LAYER_IPV4 ||

From 5c4f5e19d6a8e159127b9d653bb67e0dc7a28047 Mon Sep 17 00:00:00 2001
From: Louis Peens <louis.peens@corigine.com>
Date: Tue, 16 Mar 2021 19:13:09 +0100
Subject: [PATCH 0932/1820] nfp: flower: add ipv6 bit to pre_tunnel control
 message

Differentiate between ipv4 and ipv6 flows when configuring the pre_tunnel
table to prevent them trampling each other in the table.

Fixes: 783461604f7e ("nfp: flower: update flow merge code to support IPv6 tunnels")
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/netronome/nfp/flower/tunnel_conf.c   | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 7248d248f604..d19c02e99114 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -16,8 +16,9 @@
 #define NFP_FL_MAX_ROUTES               32
 
 #define NFP_TUN_PRE_TUN_RULE_LIMIT	32
-#define NFP_TUN_PRE_TUN_RULE_DEL	0x1
-#define NFP_TUN_PRE_TUN_IDX_BIT		0x8
+#define NFP_TUN_PRE_TUN_RULE_DEL	BIT(0)
+#define NFP_TUN_PRE_TUN_IDX_BIT		BIT(3)
+#define NFP_TUN_PRE_TUN_IPV6_BIT	BIT(7)
 
 /**
  * struct nfp_tun_pre_run_rule - rule matched before decap
@@ -1268,6 +1269,7 @@ int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app,
 {
 	struct nfp_flower_priv *app_priv = app->priv;
 	struct nfp_tun_offloaded_mac *mac_entry;
+	struct nfp_flower_meta_tci *key_meta;
 	struct nfp_tun_pre_tun_rule payload;
 	struct net_device *internal_dev;
 	int err;
@@ -1290,6 +1292,15 @@ int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app,
 	if (!mac_entry)
 		return -ENOENT;
 
+	/* Set/clear IPV6 bit. cpu_to_be16() swap will lead to MSB being
+	 * set/clear for port_idx.
+	 */
+	key_meta = (struct nfp_flower_meta_tci *)flow->unmasked_data;
+	if (key_meta->nfp_flow_key_layer & NFP_FLOWER_LAYER_IPV6)
+		mac_entry->index |= NFP_TUN_PRE_TUN_IPV6_BIT;
+	else
+		mac_entry->index &= ~NFP_TUN_PRE_TUN_IPV6_BIT;
+
 	payload.port_idx = cpu_to_be16(mac_entry->index);
 
 	/* Copy mac id and vlan to flow - dev may not exist at delete time. */

From d8ce0275e45ec809a33f98fc080fe7921b720dfb Mon Sep 17 00:00:00 2001
From: Louis Peens <louis.peens@corigine.com>
Date: Tue, 16 Mar 2021 19:13:10 +0100
Subject: [PATCH 0933/1820] nfp: flower: fix pre_tun mask id allocation

pre_tun_rule flows does not follow the usual add-flow path, instead
they are used to update the pre_tun table on the firmware. This means
that if the mask-id gets allocated here the firmware will never see the
"NFP_FL_META_FLAG_MANAGE_MASK" flag for the specific mask id, which
triggers the allocation on the firmware side. This leads to the firmware
mask being corrupted and causing all sorts of strange behaviour.

Fixes: f12725d98cbe ("nfp: flower: offload pre-tunnel rules")
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/netronome/nfp/flower/metadata.c  | 24 +++++++++++++------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 5defd31d481c..aa06fcb38f8b 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -327,8 +327,14 @@ int nfp_compile_flow_metadata(struct nfp_app *app,
 		goto err_free_ctx_entry;
 	}
 
+	/* Do net allocate a mask-id for pre_tun_rules. These flows are used to
+	 * configure the pre_tun table and are never actually send to the
+	 * firmware as an add-flow message. This causes the mask-id allocation
+	 * on the firmware to get out of sync if allocated here.
+	 */
 	new_mask_id = 0;
-	if (!nfp_check_mask_add(app, nfp_flow->mask_data,
+	if (!nfp_flow->pre_tun_rule.dev &&
+	    !nfp_check_mask_add(app, nfp_flow->mask_data,
 				nfp_flow->meta.mask_len,
 				&nfp_flow->meta.flags, &new_mask_id)) {
 		NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot allocate a new mask id");
@@ -359,7 +365,8 @@ int nfp_compile_flow_metadata(struct nfp_app *app,
 			goto err_remove_mask;
 		}
 
-		if (!nfp_check_mask_remove(app, nfp_flow->mask_data,
+		if (!nfp_flow->pre_tun_rule.dev &&
+		    !nfp_check_mask_remove(app, nfp_flow->mask_data,
 					   nfp_flow->meta.mask_len,
 					   NULL, &new_mask_id)) {
 			NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot release mask id");
@@ -374,8 +381,10 @@ int nfp_compile_flow_metadata(struct nfp_app *app,
 	return 0;
 
 err_remove_mask:
-	nfp_check_mask_remove(app, nfp_flow->mask_data, nfp_flow->meta.mask_len,
-			      NULL, &new_mask_id);
+	if (!nfp_flow->pre_tun_rule.dev)
+		nfp_check_mask_remove(app, nfp_flow->mask_data,
+				      nfp_flow->meta.mask_len,
+				      NULL, &new_mask_id);
 err_remove_rhash:
 	WARN_ON_ONCE(rhashtable_remove_fast(&priv->stats_ctx_table,
 					    &ctx_entry->ht_node,
@@ -406,9 +415,10 @@ int nfp_modify_flow_metadata(struct nfp_app *app,
 
 	__nfp_modify_flow_metadata(priv, nfp_flow);
 
-	nfp_check_mask_remove(app, nfp_flow->mask_data,
-			      nfp_flow->meta.mask_len, &nfp_flow->meta.flags,
-			      &new_mask_id);
+	if (!nfp_flow->pre_tun_rule.dev)
+		nfp_check_mask_remove(app, nfp_flow->mask_data,
+				      nfp_flow->meta.mask_len, &nfp_flow->meta.flags,
+				      &new_mask_id);
 
 	/* Update flow payload with mask ids. */
 	nfp_flow->unmasked_data[NFP_FL_MASK_ID_LOCATION] = new_mask_id;

From fc649670ba50160dd29280c0d91c1635623e88e1 Mon Sep 17 00:00:00 2001
From: Geoff Levand <geoff@infradead.org>
Date: Tue, 16 Mar 2021 10:13:52 -0700
Subject: [PATCH 0934/1820] MAINTAINERS: Update Spidernet network driver

Change the Spidernet network driver from supported to
maintained, add the linuxppc-dev ML, and add myself as
a 'maintainer'.

Cc: Ishizaki Kou <kou.ishizaki@toshiba.co.jp>
Signed-off-by: Geoff Levand <geoff@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 6acc3b839187..0d80d3dda3d0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16888,8 +16888,10 @@ F:	tools/spi/
 
 SPIDERNET NETWORK DRIVER for CELL
 M:	Ishizaki Kou <kou.ishizaki@toshiba.co.jp>
+M:	Geoff Levand <geoff@infradead.org>
 L:	netdev@vger.kernel.org
-S:	Supported
+L:	linuxppc-dev@lists.ozlabs.org
+S:	Maintained
 F:	Documentation/networking/device_drivers/ethernet/toshiba/spider_net.rst
 F:	drivers/net/ethernet/toshiba/spider_net*
 

From 8a141dd7f7060d1e64c14a5257e0babae20ac99b Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 16 Mar 2021 12:58:15 -0700
Subject: [PATCH 0935/1820] ftrace: Fix modify_ftrace_direct.

The following sequence of commands:
  register_ftrace_direct(ip, addr1);
  modify_ftrace_direct(ip, addr1, addr2);
  unregister_ftrace_direct(ip, addr2);
will cause the kernel to warn:
[   30.179191] WARNING: CPU: 2 PID: 1961 at kernel/trace/ftrace.c:5223 unregister_ftrace_direct+0x130/0x150
[   30.180556] CPU: 2 PID: 1961 Comm: test_progs    W  O      5.12.0-rc2-00378-g86bc10a0a711-dirty #3246
[   30.182453] RIP: 0010:unregister_ftrace_direct+0x130/0x150

When modify_ftrace_direct() changes the addr from old to new it should update
the addr stored in ftrace_direct_funcs. Otherwise the final
unregister_ftrace_direct() won't find the address and will cause the splat.

Fixes: 0567d6809182 ("ftrace: Add modify_ftrace_direct()")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lore.kernel.org/bpf/20210316195815.34714-1-alexei.starovoitov@gmail.com
---
 kernel/trace/ftrace.c | 43 ++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 38 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4d8e35575549..b7e29db127fa 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5045,6 +5045,20 @@ struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr)
 	return NULL;
 }
 
+static struct ftrace_direct_func *ftrace_alloc_direct_func(unsigned long addr)
+{
+	struct ftrace_direct_func *direct;
+
+	direct = kmalloc(sizeof(*direct), GFP_KERNEL);
+	if (!direct)
+		return NULL;
+	direct->addr = addr;
+	direct->count = 0;
+	list_add_rcu(&direct->next, &ftrace_direct_funcs);
+	ftrace_direct_func_count++;
+	return direct;
+}
+
 /**
  * register_ftrace_direct - Call a custom trampoline directly
  * @ip: The address of the nop at the beginning of a function
@@ -5120,15 +5134,11 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 
 	direct = ftrace_find_direct_func(addr);
 	if (!direct) {
-		direct = kmalloc(sizeof(*direct), GFP_KERNEL);
+		direct = ftrace_alloc_direct_func(addr);
 		if (!direct) {
 			kfree(entry);
 			goto out_unlock;
 		}
-		direct->addr = addr;
-		direct->count = 0;
-		list_add_rcu(&direct->next, &ftrace_direct_funcs);
-		ftrace_direct_func_count++;
 	}
 
 	entry->ip = ip;
@@ -5329,6 +5339,7 @@ int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 int modify_ftrace_direct(unsigned long ip,
 			 unsigned long old_addr, unsigned long new_addr)
 {
+	struct ftrace_direct_func *direct, *new_direct = NULL;
 	struct ftrace_func_entry *entry;
 	struct dyn_ftrace *rec;
 	int ret = -ENODEV;
@@ -5344,6 +5355,20 @@ int modify_ftrace_direct(unsigned long ip,
 	if (entry->direct != old_addr)
 		goto out_unlock;
 
+	direct = ftrace_find_direct_func(old_addr);
+	if (WARN_ON(!direct))
+		goto out_unlock;
+	if (direct->count > 1) {
+		ret = -ENOMEM;
+		new_direct = ftrace_alloc_direct_func(new_addr);
+		if (!new_direct)
+			goto out_unlock;
+		direct->count--;
+		new_direct->count++;
+	} else {
+		direct->addr = new_addr;
+	}
+
 	/*
 	 * If there's no other ftrace callback on the rec->ip location,
 	 * then it can be changed directly by the architecture.
@@ -5357,6 +5382,14 @@ int modify_ftrace_direct(unsigned long ip,
 		ret = 0;
 	}
 
+	if (unlikely(ret && new_direct)) {
+		direct->count++;
+		list_del_rcu(&new_direct->next);
+		synchronize_rcu_tasks();
+		kfree(new_direct);
+		ftrace_direct_func_count--;
+	}
+
  out_unlock:
 	mutex_unlock(&ftrace_lock);
 	mutex_unlock(&direct_mutex);

From 6980d29ce4da223ad7f0751c7f1d61d3c6b54ab3 Mon Sep 17 00:00:00 2001
From: Chao Yu <yuchao0@huawei.com>
Date: Tue, 16 Mar 2021 20:30:26 +0800
Subject: [PATCH 0936/1820] zonefs: fix to update .i_wr_refcnt correctly in
 zonefs_open_zone()

In zonefs_open_zone(), if opened zone count is larger than
.s_max_open_zones threshold, we missed to recover .i_wr_refcnt,
fix this.

Fixes: b5c00e975779 ("zonefs: open/close zone on file open/close")
Cc: <stable@vger.kernel.org>
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
---
 fs/zonefs/super.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 3427c99abb4d..049e36c69ed7 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -1040,9 +1040,7 @@ static int zonefs_open_zone(struct inode *inode)
 
 	mutex_lock(&zi->i_truncate_mutex);
 
-	zi->i_wr_refcnt++;
-	if (zi->i_wr_refcnt == 1) {
-
+	if (!zi->i_wr_refcnt) {
 		if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) {
 			atomic_dec(&sbi->s_open_zones);
 			ret = -EBUSY;
@@ -1052,7 +1050,6 @@ static int zonefs_open_zone(struct inode *inode)
 		if (i_size_read(inode) < zi->i_max_size) {
 			ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
 			if (ret) {
-				zi->i_wr_refcnt--;
 				atomic_dec(&sbi->s_open_zones);
 				goto unlock;
 			}
@@ -1060,6 +1057,8 @@ static int zonefs_open_zone(struct inode *inode)
 		}
 	}
 
+	zi->i_wr_refcnt++;
+
 unlock:
 	mutex_unlock(&zi->i_truncate_mutex);
 

From 2db4215f47557703dade2baccfa8da7b7e42a7e4 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Date: Wed, 10 Mar 2021 18:48:06 +0900
Subject: [PATCH 0937/1820] scsi: sd_zbc: Update write pointer offset cache

Recent changes changed the completion of SCSI commands from Soft-IRQ
context to IRQ context. This triggers the following warning, when we're
completing writes to zoned block devices that go through the zone append
emulation:

 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.12.0-rc2+ #2
 Hardware name: Supermicro Super Server/X10SRL-F, BIOS 2.0 12/17/2015
 RIP: 0010:__local_bh_disable_ip+0x3f/0x50
 RSP: 0018:ffff8883e1409ba8 EFLAGS: 00010006
 RAX: 0000000080010001 RBX: 0000000000000001 RCX: 0000000000000013
 RDX: ffff888129e4d200 RSI: 0000000000000201 RDI: ffffffff915b9dbd
 RBP: ffff888113e9a540 R08: ffff888113e9a540 R09: 00000000000077f0
 R10: 0000000000080000 R11: 0000000000000001 R12: ffff888129e4d200
 R13: 0000000000001000 R14: 00000000000077f0 R15: ffff888129e4d218
 FS:  0000000000000000(0000) GS:ffff8883e1400000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f2f8418ebc0 CR3: 000000021202a006 CR4: 00000000001706f0
 Call Trace:
  <IRQ>
  _raw_spin_lock_bh+0x18/0x40
  sd_zbc_complete+0x43d/0x1150
  sd_done+0x631/0x1040
  ? mark_lock+0xe4/0x2fd0
  ? provisioning_mode_store+0x3f0/0x3f0
  scsi_finish_command+0x31b/0x5c0
  _scsih_io_done+0x960/0x29e0 [mpt3sas]
  ? mpt3sas_scsih_scsi_lookup_get+0x1c7/0x340 [mpt3sas]
  ? __lock_acquire+0x166b/0x58b0
  ? _get_st_from_smid+0x4a/0x80 [mpt3sas]
  _base_process_reply_queue+0x23f/0x26e0 [mpt3sas]
  ? lock_is_held_type+0x98/0x110
  ? find_held_lock+0x2c/0x110
  ? mpt3sas_base_sync_reply_irqs+0x360/0x360 [mpt3sas]
  _base_interrupt+0x8d/0xd0 [mpt3sas]
  ? rcu_read_lock_sched_held+0x3f/0x70
  __handle_irq_event_percpu+0x24d/0x600
  handle_irq_event+0xef/0x240
  ? handle_irq_event_percpu+0x110/0x110
  handle_edge_irq+0x1f6/0xb60
  __common_interrupt+0x75/0x160
  common_interrupt+0x7b/0xa0
  </IRQ>
  asm_common_interrupt+0x1e/0x40

Don't use spin_lock_bh() to protect the update of the write pointer offset
cache, but use spin_lock_irqsave() for it.

Link: https://lore.kernel.org/r/3cfebe48d09db73041b7849be71ffbcec7ee40b3.1615369586.git.johannes.thumshirn@wdc.com
Fixes: 664f0dce2058 ("scsi: mpt3sas: Add support for shared host tagset for CPU hotplug")
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sd_zbc.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index ee558675eab4..994f1b8e3504 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -280,27 +280,28 @@ static int sd_zbc_update_wp_offset_cb(struct blk_zone *zone, unsigned int idx,
 static void sd_zbc_update_wp_offset_workfn(struct work_struct *work)
 {
 	struct scsi_disk *sdkp;
+	unsigned long flags;
 	unsigned int zno;
 	int ret;
 
 	sdkp = container_of(work, struct scsi_disk, zone_wp_offset_work);
 
-	spin_lock_bh(&sdkp->zones_wp_offset_lock);
+	spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
 	for (zno = 0; zno < sdkp->nr_zones; zno++) {
 		if (sdkp->zones_wp_offset[zno] != SD_ZBC_UPDATING_WP_OFST)
 			continue;
 
-		spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+		spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
 		ret = sd_zbc_do_report_zones(sdkp, sdkp->zone_wp_update_buf,
 					     SD_BUF_SIZE,
 					     zno * sdkp->zone_blocks, true);
-		spin_lock_bh(&sdkp->zones_wp_offset_lock);
+		spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
 		if (!ret)
 			sd_zbc_parse_report(sdkp, sdkp->zone_wp_update_buf + 64,
 					    zno, sd_zbc_update_wp_offset_cb,
 					    sdkp);
 	}
-	spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+	spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
 
 	scsi_device_put(sdkp->device);
 }
@@ -324,6 +325,7 @@ blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
 	struct request *rq = cmd->request;
 	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
 	unsigned int wp_offset, zno = blk_rq_zone_no(rq);
+	unsigned long flags;
 	blk_status_t ret;
 
 	ret = sd_zbc_cmnd_checks(cmd);
@@ -337,7 +339,7 @@ blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
 	if (!blk_req_zone_write_trylock(rq))
 		return BLK_STS_ZONE_RESOURCE;
 
-	spin_lock_bh(&sdkp->zones_wp_offset_lock);
+	spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
 	wp_offset = sdkp->zones_wp_offset[zno];
 	switch (wp_offset) {
 	case SD_ZBC_INVALID_WP_OFST:
@@ -366,7 +368,7 @@ blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
 
 		*lba += wp_offset;
 	}
-	spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+	spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
 	if (ret)
 		blk_req_zone_write_unlock(rq);
 	return ret;
@@ -445,6 +447,7 @@ static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd,
 	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
 	unsigned int zno = blk_rq_zone_no(rq);
 	enum req_opf op = req_op(rq);
+	unsigned long flags;
 
 	/*
 	 * If we got an error for a command that needs updating the write
@@ -452,7 +455,7 @@ static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd,
 	 * invalid to force an update from disk the next time a zone append
 	 * command is issued.
 	 */
-	spin_lock_bh(&sdkp->zones_wp_offset_lock);
+	spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
 
 	if (result && op != REQ_OP_ZONE_RESET_ALL) {
 		if (op == REQ_OP_ZONE_APPEND) {
@@ -496,7 +499,7 @@ static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd,
 	}
 
 unlock_wp_offset:
-	spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+	spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
 
 	return good_bytes;
 }

From 0fdc7d5d8f3719950478cca452cf7f0f1355be10 Mon Sep 17 00:00:00 2001
From: dongjian <dongjian@yulong.com>
Date: Tue, 16 Mar 2021 20:15:15 +0800
Subject: [PATCH 0938/1820] scsi: ufs: ufs-mediatek: Correct operator & -> &&

The "lpm" and "->enabled" are all boolean. We should be using &&
rather than the bit operator.

Link: https://lore.kernel.org/r/1615896915-148864-1-git-send-email-dj0227@163.com
Fixes: 488edafb1120 ("scsi: ufs-mediatek: Introduce low-power mode for device power supply")
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: dongjian <dongjian@yulong.com>
Signed-off-by: Yue Hu <huyue2@yulong.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/ufs-mediatek.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c
index c55202b92a43..a981f261b304 100644
--- a/drivers/scsi/ufs/ufs-mediatek.c
+++ b/drivers/scsi/ufs/ufs-mediatek.c
@@ -911,7 +911,7 @@ static void ufs_mtk_vreg_set_lpm(struct ufs_hba *hba, bool lpm)
 	if (!hba->vreg_info.vccq2 || !hba->vreg_info.vcc)
 		return;
 
-	if (lpm & !hba->vreg_info.vcc->enabled)
+	if (lpm && !hba->vreg_info.vcc->enabled)
 		regulator_set_mode(hba->vreg_info.vccq2->reg,
 				   REGULATOR_MODE_IDLE);
 	else if (!lpm)

From cc7a0bb058b85ea03db87169c60c7cfdd5d34678 Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.ibm.com>
Date: Mon, 15 Mar 2021 15:48:21 -0600
Subject: [PATCH 0939/1820] PCI: rpadlpar: Fix potential drc_name corruption in
 store functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Both add_slot_store() and remove_slot_store() try to fix up the
drc_name copied from the store buffer by placing a NUL terminator at
nbyte + 1 or in place of a '\n' if present. However, the static buffer
that we copy the drc_name data into is not zeroed and can contain
anything past the n-th byte.

This is problematic if a '\n' byte appears in that buffer after nbytes
and the string copied into the store buffer was not NUL terminated to
start with as the strchr() search for a '\n' byte will mark this
incorrectly as the end of the drc_name string resulting in a drc_name
string that contains garbage data after the n-th byte.

Additionally it will cause us to overwrite that '\n' byte on the stack
with NUL, potentially corrupting data on the stack.

The following debugging shows an example of the drmgr utility writing
"PHB 4543" to the add_slot sysfs attribute, but add_slot_store()
logging a corrupted string value.

  drmgr: drmgr: -c phb -a -s PHB 4543 -d 1
  add_slot_store: drc_name = PHB 4543°|<82>!, rc = -19

Fix this by using strscpy() instead of memcpy() to ensure the string
is NUL terminated when copied into the static drc_name buffer.
Further, since the string is now NUL terminated the code only needs to
change '\n' to '\0' when present.

Cc: stable@vger.kernel.org
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
[mpe: Reformat change log and add mention of possible stack corruption]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210315214821.452959-1-tyreld@linux.ibm.com
---
 drivers/pci/hotplug/rpadlpar_sysfs.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/hotplug/rpadlpar_sysfs.c b/drivers/pci/hotplug/rpadlpar_sysfs.c
index cdbfa5df3a51..dbfa0b55d31a 100644
--- a/drivers/pci/hotplug/rpadlpar_sysfs.c
+++ b/drivers/pci/hotplug/rpadlpar_sysfs.c
@@ -34,12 +34,11 @@ static ssize_t add_slot_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (nbytes >= MAX_DRC_NAME_LEN)
 		return 0;
 
-	memcpy(drc_name, buf, nbytes);
+	strscpy(drc_name, buf, nbytes + 1);
 
 	end = strchr(drc_name, '\n');
-	if (!end)
-		end = &drc_name[nbytes];
-	*end = '\0';
+	if (end)
+		*end = '\0';
 
 	rc = dlpar_add_slot(drc_name);
 	if (rc)
@@ -65,12 +64,11 @@ static ssize_t remove_slot_store(struct kobject *kobj,
 	if (nbytes >= MAX_DRC_NAME_LEN)
 		return 0;
 
-	memcpy(drc_name, buf, nbytes);
+	strscpy(drc_name, buf, nbytes + 1);
 
 	end = strchr(drc_name, '\n');
-	if (!end)
-		end = &drc_name[nbytes];
-	*end = '\0';
+	if (end)
+		*end = '\0';
 
 	rc = dlpar_remove_slot(drc_name);
 	if (rc)

From a50bd64616907ed126ffbdbaa06c5ce708c4a404 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 20 Feb 2021 10:39:51 +0100
Subject: [PATCH 0940/1820] scsi: mpt3sas: Do not use GFP_KERNEL in atomic
 context

mpt3sas_get_port_by_id() can be called when a spinlock is held. Use
GFP_ATOMIC instead of GFP_KERNEL when allocating memory.

Issue spotted by call_kern.cocci:
./drivers/scsi/mpt3sas/mpt3sas_scsih.c:416:42-52: ERROR: function mpt3sas_get_port_by_id called on line 7125 inside lock on line 7123 but uses GFP_KERNEL
./drivers/scsi/mpt3sas/mpt3sas_scsih.c:416:42-52: ERROR: function mpt3sas_get_port_by_id called on line 6842 inside lock on line 6839 but uses GFP_KERNEL
./drivers/scsi/mpt3sas/mpt3sas_scsih.c:416:42-52: ERROR: function mpt3sas_get_port_by_id called on line 6854 inside lock on line 6851 but uses GFP_KERNEL
./drivers/scsi/mpt3sas/mpt3sas_scsih.c:416:42-52: ERROR: function mpt3sas_get_port_by_id called on line 7706 inside lock on line 7702 but uses GFP_KERNEL
./drivers/scsi/mpt3sas/mpt3sas_scsih.c:416:42-52: ERROR: function mpt3sas_get_port_by_id called on line 10260 inside lock on line 10256 but uses GFP_KERNEL

Link: https://lore.kernel.org/r/20210220093951.905362-1-christophe.jaillet@wanadoo.fr
Fixes: 324c122fc0a4 ("scsi: mpt3sas: Add module parameter multipath_on_hba")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index ffca03064797..6aa6de729187 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -413,7 +413,7 @@ mpt3sas_get_port_by_id(struct MPT3SAS_ADAPTER *ioc,
 	 * And add this object to port_table_list.
 	 */
 	if (!ioc->multipath_on_hba) {
-		port = kzalloc(sizeof(struct hba_port), GFP_KERNEL);
+		port = kzalloc(sizeof(struct hba_port), GFP_ATOMIC);
 		if (!port)
 			return NULL;
 

From 6e9070dc2e847ef77aa1c581252a1b97eb2225b9 Mon Sep 17 00:00:00 2001
From: kernel test robot <lkp@intel.com>
Date: Sun, 28 Feb 2021 12:10:22 +0100
Subject: [PATCH 0941/1820] riscv: fix bugon.cocci warnings

Use BUG_ON instead of a if condition followed by BUG.

Generated by: scripts/coccinelle/misc/bugon.cocci

Fixes: c22b0bcb1dd0 ("riscv: Add kprobes supported")
CC: Guo Ren <guoren@linux.alibaba.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: kernel test robot <lkp@intel.com>
Signed-off-by: Julia Lawall <julia.lawall@inria.fr>
Reviewed-by: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/kernel/probes/kprobes.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c
index a2ec18662fee..7e2c78e2ca6b 100644
--- a/arch/riscv/kernel/probes/kprobes.c
+++ b/arch/riscv/kernel/probes/kprobes.c
@@ -256,8 +256,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr)
 		 * normal page fault.
 		 */
 		regs->epc = (unsigned long) cur->addr;
-		if (!instruction_pointer(regs))
-			BUG();
+		BUG_ON(!instruction_pointer(regs));
 
 		if (kcb->kprobe_status == KPROBE_REENTER)
 			restore_previous_kprobe(kcb);

From bab1770a2ce00bf201c6ac5a013a7195db2e02b7 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 11 Mar 2021 09:40:22 +0000
Subject: [PATCH 0942/1820] ftrace: Fix spelling mistake "disabed" ->
 "disabled"

There is a spelling mistake in a comment, fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/csky/kernel/probes/ftrace.c  | 2 +-
 arch/riscv/kernel/probes/ftrace.c | 2 +-
 arch/x86/kernel/kprobes/ftrace.c  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c
index ae2b1c7b3b5c..ef2bb9bd9605 100644
--- a/arch/csky/kernel/probes/ftrace.c
+++ b/arch/csky/kernel/probes/ftrace.c
@@ -9,7 +9,7 @@ int arch_check_ftrace_location(struct kprobe *p)
 	return 0;
 }
 
-/* Ftrace callback handler for kprobes -- called under preepmt disabed */
+/* Ftrace callback handler for kprobes -- called under preepmt disabled */
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c
index 2dfb33fdac74..17ca5e923bb0 100644
--- a/arch/riscv/kernel/probes/ftrace.c
+++ b/arch/riscv/kernel/probes/ftrace.c
@@ -2,7 +2,7 @@
 
 #include <linux/kprobes.h>
 
-/* Ftrace callback handler for kprobes -- called under preepmt disabed */
+/* Ftrace callback handler for kprobes -- called under preepmt disabled */
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 373e5fa3ce1f..51c7f5271aee 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -12,7 +12,7 @@
 
 #include "common.h"
 
-/* Ftrace callback handler for kprobes -- called under preepmt disabed */
+/* Ftrace callback handler for kprobes -- called under preepmt disabled */
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {

From fa59030bf8555a4eb83342fd23c32e30d4f2fe7a Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@wdc.com>
Date: Thu, 11 Mar 2021 19:24:24 +0900
Subject: [PATCH 0943/1820] riscv: Fix compilation error with Canaan SoC

When CONFIG_SOC_CANAAN is selected, the K210 sysctl driver is always
compiled. Since this driver early init function calls the function
k210_clk_early_init() implemented by the K210 clk driver, this driver
must also always be selected for compilation ot avoid build failures.

Avoid such build failures by always selecting CONFIG_COMMON_CLK and
CONFIG_COMMON_CLK_K210 when CONFIG_SOC_CANAAN is enabled.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Fixes: c6ca7616f7d5 ("clk: Add RISC-V Canaan Kendryte K210 clock driver")
Cc: stable@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/Kconfig.socs | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
index 7efcece8896c..e1b2690b6e45 100644
--- a/arch/riscv/Kconfig.socs
+++ b/arch/riscv/Kconfig.socs
@@ -31,6 +31,8 @@ config SOC_CANAAN
 	select SIFIVE_PLIC
 	select ARCH_HAS_RESET_CONTROLLER
 	select PINCTRL
+	select COMMON_CLK
+	select COMMON_CLK_K210
 	help
 	  This enables support for Canaan Kendryte K210 SoC platform hardware.
 

From ce989f1472ae350e844b10c880b22543168fbc92 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 12 Mar 2021 16:46:34 +0100
Subject: [PATCH 0944/1820] RISC-V: Fix out-of-bounds accesses in
 init_resources()

init_resources() allocates an array of resources, based on the current
total number of memory regions and reserved memory regions.  However,
allocating this array using memblock_alloc() might increase the number
of reserved memory regions.  If that happens, populating the array later
based on the new number of regions will cause out-of-bounds writes
beyond the end of the allocated array.

Fix this by allocating one more entry, which may or may not be used.

Fixes: 797f0375dd2ef5cd ("RISC-V: Do not allocate memblock while iterating reserved memblocks")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Atish Patra <atish.patra@wdc.com>
Cc: stable@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/kernel/setup.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index e85bacff1b50..f8f15332caa2 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -147,7 +147,8 @@ static void __init init_resources(void)
 	bss_res.end = __pa_symbol(__bss_stop) - 1;
 	bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
-	mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res);
+	/* + 1 as memblock_alloc() might increase memblock.reserved.cnt */
+	mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt + 1) * sizeof(*mem_res);
 	mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES);
 	if (!mem_res)
 		panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz);

From f3773dd031de7b283227f6104049688f77074a2d Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alex@ghiti.fr>
Date: Sat, 13 Mar 2021 03:45:04 -0500
Subject: [PATCH 0945/1820] riscv: Ensure page table writes are flushed when
 initializing KASAN vmalloc

Make sure that writes to kernel page table during KASAN vmalloc
initialization are made visible by adding a sfence.vma.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
Reviewed-by: Palmer Dabbelt <palmerdabbelt@google.com>
Fixes: e178d670f251 ("riscv/kasan: add KASAN_VMALLOC support")
Cc: stable@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/mm/kasan_init.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 3fc18f469efb..5c35e0f71e88 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -187,6 +187,8 @@ void __init kasan_shallow_populate(void *start, void *end)
 		}
 		vaddr += PAGE_SIZE;
 	}
+
+	local_flush_tlb_all();
 }
 
 void __init kasan_init(void)

From 78947bdfd75211cc9482cad01f95fe103a863110 Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmerdabbelt@google.com>
Date: Tue, 16 Mar 2021 22:01:04 -0700
Subject: [PATCH 0946/1820] RISC-V: kasan: Declare kasan_shallow_populate()
 static

Without this I get a missing prototype warning.

Reported-by: kernel test robot <lkp@intel.com>
Fixes: e178d670f251 ("riscv/kasan: add KASAN_VMALLOC support")
Cc: stable@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/mm/kasan_init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 5c35e0f71e88..4f85c6d0ddf8 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -155,7 +155,7 @@ static void __init kasan_populate(void *start, void *end)
 	memset(start, KASAN_SHADOW_INIT, end - start);
 }
 
-void __init kasan_shallow_populate(void *start, void *end)
+static void __init kasan_shallow_populate(void *start, void *end)
 {
 	unsigned long vaddr = (unsigned long)start & PAGE_MASK;
 	unsigned long vend = PAGE_ALIGN((unsigned long)end);

From a5406a7ff56e63376c210b06072aa0ef23473366 Mon Sep 17 00:00:00 2001
From: Kefeng Wang <wangkefeng.wang@huawei.com>
Date: Mon, 15 Mar 2021 20:03:07 +0800
Subject: [PATCH 0947/1820] riscv: Correct SPARSEMEM configuration

There are two issues for RV32,
1) if use FLATMEM, it is useless to enable SPARSEMEM_STATIC.
2) if use SPARSMEM, both SPARSEMEM_VMEMMAP and SPARSEMEM_STATIC is enabled.

Fixes: d95f1a542c3d ("RISC-V: Implement sparsemem")
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: stable@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 85d626b8ce5e..87d7b52f278f 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -93,7 +93,6 @@ config RISCV
 	select PCI_MSI if PCI
 	select RISCV_INTC
 	select RISCV_TIMER if RISCV_SBI
-	select SPARSEMEM_STATIC if 32BIT
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
@@ -154,7 +153,8 @@ config ARCH_FLATMEM_ENABLE
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
 	depends on MMU
-	select SPARSEMEM_VMEMMAP_ENABLE
+	select SPARSEMEM_STATIC if 32BIT && SPARSMEM
+	select SPARSEMEM_VMEMMAP_ENABLE if 64BIT
 
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool ARCH_SPARSEMEM_ENABLE

From d2547cf59793168b564372d75620897416cbaf87 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Mar 2021 15:37:33 +0100
Subject: [PATCH 0948/1820] KVM: x86: hyper-v: Limit guest to writing zero to
 HV_X64_MSR_TSC_EMULATION_STATUS

HV_X64_MSR_TSC_EMULATION_STATUS indicates whether TSC accesses are emulated
after migration (to accommodate for a different host TSC frequency when TSC
scaling is not supported; we don't implement this in KVM). Guest can use
the same MSR to stop TSC access emulation by writing zero. Writing anything
else is forbidden.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210316143736.964151-2-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/hyperv.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 58fa8c029867..eefb85b86fe8 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1229,6 +1229,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 		hv->hv_tsc_emulation_control = data;
 		break;
 	case HV_X64_MSR_TSC_EMULATION_STATUS:
+		if (data && !host)
+			return 1;
+
 		hv->hv_tsc_emulation_status = data;
 		break;
 	case HV_X64_MSR_TIME_REF_COUNT:

From e880c6ea55b9805294ecc100ee95e0c9860ae90e Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Mar 2021 15:37:34 +0100
Subject: [PATCH 0949/1820] KVM: x86: hyper-v: Prevent using not-yet-updated
 TSC page by secondary CPUs

When KVM_REQ_MASTERCLOCK_UPDATE request is issued (e.g. after migration)
we need to make sure no vCPU sees stale values in PV clock structures and
thus all vCPUs are kicked with KVM_REQ_CLOCK_UPDATE. Hyper-V TSC page
clocksource is global and kvm_guest_time_update() only updates in on vCPU0
but this is not entirely correct: nothing blocks some other vCPU from
entering the guest before we finish the update on CPU0 and it can read
stale values from the page.

Invalidate TSC page in kvm_gen_update_masterclock() to switch all vCPUs
to using MSR based clocksource (HV_X64_MSR_TIME_REF_COUNT).

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210316143736.964151-3-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/hyperv.c | 23 +++++++++++++++++++++++
 arch/x86/kvm/hyperv.h |  1 +
 arch/x86/kvm/x86.c    |  2 ++
 3 files changed, 26 insertions(+)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index eefb85b86fe8..a0e3c49233d4 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1137,6 +1137,29 @@ out_unlock:
 	mutex_unlock(&hv->hv_lock);
 }
 
+void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
+{
+	struct kvm_hv *hv = to_kvm_hv(kvm);
+	u64 gfn;
+
+	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+		return;
+
+	mutex_lock(&hv->hv_lock);
+
+	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+		goto out_unlock;
+
+	gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
+
+	hv->tsc_ref.tsc_sequence = 0;
+	kvm_write_guest(kvm, gfn_to_gpa(gfn),
+			&hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence));
+
+out_unlock:
+	mutex_unlock(&hv->hv_lock);
+}
+
 static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 			     bool host)
 {
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index e951af1fcb2c..60547d5cb6d7 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -133,6 +133,7 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu);
 
 void kvm_hv_setup_tsc_page(struct kvm *kvm,
 			   struct pvclock_vcpu_time_info *hv_clock);
+void kvm_hv_invalidate_tsc_page(struct kvm *kvm);
 
 void kvm_hv_init_vm(struct kvm *kvm);
 void kvm_hv_destroy_vm(struct kvm *kvm);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 47e021bdcc94..a5c5b38735e1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2551,6 +2551,8 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	struct kvm_arch *ka = &kvm->arch;
 
+	kvm_hv_invalidate_tsc_page(kvm);
+
 	spin_lock(&ka->pvclock_gtod_sync_lock);
 	kvm_make_mclock_inprogress_request(kvm);
 	/* no guest entries from this point */

From 483028edacab374060d93955382b4865a9e07cba Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Wed, 17 Mar 2021 14:36:06 +0800
Subject: [PATCH 0950/1820] efivars: respect EFI_UNSUPPORTED return from
 firmware

As per UEFI spec 2.8B section 8.2, EFI_UNSUPPORTED may be returned by
EFI variable runtime services if no variable storage is supported by
firmware.  In this case, there is no point for kernel to continue
efivars initialization.  That said, efivar_init() should fail by
returning an error code, so that efivarfs will not be mounted on
/sys/firmware/efi/efivars at all.  Otherwise, user space like efibootmgr
will be confused by the EFIVARFS_MAGIC seen there, while EFI variable
calls cannot be made successfully.

Cc: <stable@vger.kernel.org> # v5.10+
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/vars.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 41c1d00bf933..abdc8a6a3963 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -484,6 +484,10 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *),
 				}
 			}
 
+			break;
+		case EFI_UNSUPPORTED:
+			err = -EOPNOTSUPP;
+			status = EFI_NOT_FOUND;
 			break;
 		case EFI_NOT_FOUND:
 			break;

From 2046a24ae121cd107929655a6aaf3b8c5beea01f Mon Sep 17 00:00:00 2001
From: Manaf Meethalavalappu Pallikunhi <manafm@codeaurora.org>
Date: Tue, 8 Dec 2020 00:23:01 +0530
Subject: [PATCH 0951/1820] thermal/core: Add NULL pointer check before using
 cooling device stats

There is a possible chance that some cooling device stats buffer
allocation fails due to very high cooling device max state value.
Later cooling device update sysfs can try to access stats data
for the same cooling device. It will lead to NULL pointer
dereference issue.

Add a NULL pointer check before accessing thermal cooling device
stats data. It fixes the following bug

[ 26.812833] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000004
[ 27.122960] Call trace:
[ 27.122963] do_raw_spin_lock+0x18/0xe8
[ 27.122966] _raw_spin_lock+0x24/0x30
[ 27.128157] thermal_cooling_device_stats_update+0x24/0x98
[ 27.128162] cur_state_store+0x88/0xb8
[ 27.128166] dev_attr_store+0x40/0x58
[ 27.128169] sysfs_kf_write+0x50/0x68
[ 27.133358] kernfs_fop_write+0x12c/0x1c8
[ 27.133362] __vfs_write+0x54/0x160
[ 27.152297] vfs_write+0xcc/0x188
[ 27.157132] ksys_write+0x78/0x108
[ 27.162050] ksys_write+0xf8/0x108
[ 27.166968] __arm_smccc_hvc+0x158/0x4b0
[ 27.166973] __arm_smccc_hvc+0x9c/0x4b0
[ 27.186005] el0_svc+0x8/0xc

Signed-off-by: Manaf Meethalavalappu Pallikunhi <manafm@codeaurora.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/1607367181-24589-1-git-send-email-manafm@codeaurora.org
---
 drivers/thermal/thermal_sysfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
index 345917a58f2f..1c4aac8464a7 100644
--- a/drivers/thermal/thermal_sysfs.c
+++ b/drivers/thermal/thermal_sysfs.c
@@ -674,6 +674,9 @@ void thermal_cooling_device_stats_update(struct thermal_cooling_device *cdev,
 {
 	struct cooling_dev_stats *stats = cdev->stats;
 
+	if (!stats)
+		return;
+
 	spin_lock(&stats->lock);
 
 	if (stats->state == new_state)

From 5de2055d31ea88fd9ae9709ac95c372a505a60fa Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 16 Mar 2021 11:31:16 -0400
Subject: [PATCH 0952/1820] locking/ww_mutex: Simplify use_ww_ctx & ww_ctx
 handling

The use_ww_ctx flag is passed to mutex_optimistic_spin(), but the
function doesn't use it. The frequent use of the (use_ww_ctx && ww_ctx)
combination is repetitive.

In fact, ww_ctx should not be used at all if !use_ww_ctx.  Simplify
ww_mutex code by dropping use_ww_ctx from mutex_optimistic_spin() an
clear ww_ctx if !use_ww_ctx. In this way, we can replace (use_ww_ctx &&
ww_ctx) by just (ww_ctx).

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Davidlohr Bueso <dbueso@suse.de>
Link: https://lore.kernel.org/r/20210316153119.13802-2-longman@redhat.com
---
 kernel/locking/mutex.c | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index adb935090768..622ebdfcd083 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -626,7 +626,7 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
  */
 static __always_inline bool
 mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
-		      const bool use_ww_ctx, struct mutex_waiter *waiter)
+		      struct mutex_waiter *waiter)
 {
 	if (!waiter) {
 		/*
@@ -702,7 +702,7 @@ fail:
 #else
 static __always_inline bool
 mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
-		      const bool use_ww_ctx, struct mutex_waiter *waiter)
+		      struct mutex_waiter *waiter)
 {
 	return false;
 }
@@ -922,6 +922,9 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	struct ww_mutex *ww;
 	int ret;
 
+	if (!use_ww_ctx)
+		ww_ctx = NULL;
+
 	might_sleep();
 
 #ifdef CONFIG_DEBUG_MUTEXES
@@ -929,7 +932,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 #endif
 
 	ww = container_of(lock, struct ww_mutex, base);
-	if (use_ww_ctx && ww_ctx) {
+	if (ww_ctx) {
 		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
 			return -EALREADY;
 
@@ -946,10 +949,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
 	if (__mutex_trylock(lock) ||
-	    mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, NULL)) {
+	    mutex_optimistic_spin(lock, ww_ctx, NULL)) {
 		/* got the lock, yay! */
 		lock_acquired(&lock->dep_map, ip);
-		if (use_ww_ctx && ww_ctx)
+		if (ww_ctx)
 			ww_mutex_set_context_fastpath(ww, ww_ctx);
 		preempt_enable();
 		return 0;
@@ -960,7 +963,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	 * After waiting to acquire the wait_lock, try again.
 	 */
 	if (__mutex_trylock(lock)) {
-		if (use_ww_ctx && ww_ctx)
+		if (ww_ctx)
 			__ww_mutex_check_waiters(lock, ww_ctx);
 
 		goto skip_wait;
@@ -1013,7 +1016,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 			goto err;
 		}
 
-		if (use_ww_ctx && ww_ctx) {
+		if (ww_ctx) {
 			ret = __ww_mutex_check_kill(lock, &waiter, ww_ctx);
 			if (ret)
 				goto err;
@@ -1026,7 +1029,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * ww_mutex needs to always recheck its position since its waiter
 		 * list is not FIFO ordered.
 		 */
-		if ((use_ww_ctx && ww_ctx) || !first) {
+		if (ww_ctx || !first) {
 			first = __mutex_waiter_is_first(lock, &waiter);
 			if (first)
 				__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
@@ -1039,7 +1042,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * or we must see its unlock and acquire.
 		 */
 		if (__mutex_trylock(lock) ||
-		    (first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, &waiter)))
+		    (first && mutex_optimistic_spin(lock, ww_ctx, &waiter)))
 			break;
 
 		spin_lock(&lock->wait_lock);
@@ -1048,7 +1051,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 acquired:
 	__set_current_state(TASK_RUNNING);
 
-	if (use_ww_ctx && ww_ctx) {
+	if (ww_ctx) {
 		/*
 		 * Wound-Wait; we stole the lock (!first_waiter), check the
 		 * waiters as anyone might want to wound us.
@@ -1068,7 +1071,7 @@ skip_wait:
 	/* got the lock - cleanup and rejoice! */
 	lock_acquired(&lock->dep_map, ip);
 
-	if (use_ww_ctx && ww_ctx)
+	if (ww_ctx)
 		ww_mutex_lock_acquired(ww, ww_ctx);
 
 	spin_unlock(&lock->wait_lock);

From bee645788e07eea63055d261d2884ea45c2ba857 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 16 Mar 2021 11:31:17 -0400
Subject: [PATCH 0953/1820] locking/ww_mutex: Fix acquire/release imbalance in
 ww_acquire_init()/ww_acquire_fini()

In ww_acquire_init(), mutex_acquire() is gated by CONFIG_DEBUG_LOCK_ALLOC.
The dep_map in the ww_acquire_ctx structure is also gated by the
same config. However mutex_release() in ww_acquire_fini() is gated by
CONFIG_DEBUG_MUTEXES. It is possible to set CONFIG_DEBUG_MUTEXES without
setting CONFIG_DEBUG_LOCK_ALLOC though it is an unlikely configuration.
That may cause a compilation error as dep_map isn't defined in this
case. Fix this potential problem by enclosing mutex_release() inside
CONFIG_DEBUG_LOCK_ALLOC.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210316153119.13802-3-longman@redhat.com
---
 include/linux/ww_mutex.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index 850424e5d030..6ecf2a0220db 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -173,9 +173,10 @@ static inline void ww_acquire_done(struct ww_acquire_ctx *ctx)
  */
 static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx)
 {
-#ifdef CONFIG_DEBUG_MUTEXES
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
 	mutex_release(&ctx->dep_map, _THIS_IP_);
-
+#endif
+#ifdef CONFIG_DEBUG_MUTEXES
 	DEBUG_LOCKS_WARN_ON(ctx->acquired);
 	if (!IS_ENABLED(CONFIG_PROVE_LOCKING))
 		/*

From 8e62438a1ee74ceeac77bb4c680ceaaf3f860488 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Sat, 20 Feb 2021 12:33:03 +0200
Subject: [PATCH 0954/1820] drm/i915: Workaround async flip + VT-d corruption
 on HSW/BDW
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On HSW/BDW with VT-d active the first tile row scanned out
after the first async flip of the frame often ends up corrupted.

Whether the corruption happens or not depends on the scanline
on which the async flip happens, but the behaviour seems very
consistent. Ie. the same set of scanlines (which are most scanlines)
always show the corruption. And another set of scanlines (far less
of them) never shows the corruption.

I discovered that disabling the fetch-stride stretching
feature cures the corruption. This is some kind of TLB related
prefetch thing AFAIK. We already disable it on SNB primary
planes due to a documented workaround. The hardware folks
indicated that disabling this should be fine, so let's go
with that.

And while we're here, let's document the relevant bits on all
pre-skl platforms.

Fixes: 2a636e240c77 ("drm/i915: Implement async flip for ivb/hsw")
Fixes: cda195f13abd ("drm/i915: Implement async flips for bdw")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210220103303.3448-1-ville.syrjala@linux.intel.com
Reviewed-by: Karthik B S <karthik.b.s@intel.com>
(cherry picked from commit b7a7053ab2ec558b8ae4e55f62ea8f1f58e14f5c)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/i915_reg.h | 23 ++++++++++++++++++++++-
 drivers/gpu/drm/i915/intel_pm.c | 16 +++++++++++++++-
 2 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 7146cd0f3256..aaf1f0045b16 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3316,7 +3316,18 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define ILK_DISPLAY_CHICKEN1	_MMIO(0x42000)
 #define   ILK_FBCQ_DIS		(1 << 22)
-#define	  ILK_PABSTRETCH_DIS	(1 << 21)
+#define   ILK_PABSTRETCH_DIS	REG_BIT(21)
+#define   ILK_SABSTRETCH_DIS	REG_BIT(20)
+#define   IVB_PRI_STRETCH_MAX_MASK	REG_GENMASK(21, 20)
+#define   IVB_PRI_STRETCH_MAX_X8	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 0)
+#define   IVB_PRI_STRETCH_MAX_X4	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 1)
+#define   IVB_PRI_STRETCH_MAX_X2	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 2)
+#define   IVB_PRI_STRETCH_MAX_X1	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 3)
+#define   IVB_SPR_STRETCH_MAX_MASK	REG_GENMASK(19, 18)
+#define   IVB_SPR_STRETCH_MAX_X8	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 0)
+#define   IVB_SPR_STRETCH_MAX_X4	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 1)
+#define   IVB_SPR_STRETCH_MAX_X2	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 2)
+#define   IVB_SPR_STRETCH_MAX_X1	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 3)
 
 
 /*
@@ -8039,6 +8050,16 @@ enum {
 
 #define _CHICKEN_PIPESL_1_A	0x420b0
 #define _CHICKEN_PIPESL_1_B	0x420b4
+#define  HSW_PRI_STRETCH_MAX_MASK	REG_GENMASK(28, 27)
+#define  HSW_PRI_STRETCH_MAX_X8		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 0)
+#define  HSW_PRI_STRETCH_MAX_X4		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 1)
+#define  HSW_PRI_STRETCH_MAX_X2		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 2)
+#define  HSW_PRI_STRETCH_MAX_X1		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 3)
+#define  HSW_SPR_STRETCH_MAX_MASK	REG_GENMASK(26, 25)
+#define  HSW_SPR_STRETCH_MAX_X8		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 0)
+#define  HSW_SPR_STRETCH_MAX_X4		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 1)
+#define  HSW_SPR_STRETCH_MAX_X2		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 2)
+#define  HSW_SPR_STRETCH_MAX_X1		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 3)
 #define  HSW_FBCQ_DIS			(1 << 22)
 #define  BDW_DPRS_MASK_VBLANK_SRD	(1 << 0)
 #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 0c3e63f27c29..97b57acc02e2 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -7245,11 +7245,16 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
 	intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1,
 		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD);
 
-	/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
 	for_each_pipe(dev_priv, pipe) {
+		/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
 		intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
 			   intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe)) |
 			   BDW_DPRS_MASK_VBLANK_SRD);
+
+		/* Undocumented but fixes async flip + VT-d corruption */
+		if (intel_vtd_active())
+			intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
+					 HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1);
 	}
 
 	/* WaVSRefCountFullforceMissDisable:bdw */
@@ -7285,11 +7290,20 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
 
 static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
 {
+	enum pipe pipe;
+
 	/* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
 	intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A),
 		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A)) |
 		   HSW_FBCQ_DIS);
 
+	for_each_pipe(dev_priv, pipe) {
+		/* Undocumented but fixes async flip + VT-d corruption */
+		if (intel_vtd_active())
+			intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
+					 HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1);
+	}
+
 	/* This is required by WaCatErrorRejectionIssue:hsw */
 	intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
 		   intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |

From 6a77c6bb7260bd5000f95df454d9f8cdb1af7132 Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Fri, 5 Mar 2021 13:09:47 -0800
Subject: [PATCH 0955/1820] i915/perf: Start hrtimer only if sampling the OA
 buffer

SAMPLE_OA parameter enables sampling of OA buffer and results in a call
to init the OA buffer which initializes the OA unit head/tail pointers.
The OA_EXPONENT parameter controls the periodicity of the OA reports in
the OA buffer and results in starting a hrtimer.

Before gen12, all use cases required the use of the OA buffer and i915
enforced this setting when vetting out the parameters passed. In these
platforms the hrtimer was enabled if OA_EXPONENT was passed. This worked
fine since it was implied that SAMPLE_OA is always passed.

With gen12, this changed. Users can use perf without enabling the OA
buffer as in OAR use cases. While an OAR use case should ideally not
start the hrtimer, we see that passing an OA_EXPONENT parameter will
start the hrtimer even though SAMPLE_OA is not specified. This results
in an uninitialized OA buffer, so the head/tail pointers used to track
the buffer are zero.

This itself does not fail, but if we ran a use-case that SAMPLED the OA
buffer previously, then the OA_TAIL register is still pointing to an old
value. When the timer callback runs, it ends up calculating a
wrong/large number of available reports. Since we do a spinlock_irq_save
and start processing a large number of reports, NMI watchdog fires and
causes a crash.

Start the timer only if SAMPLE_OA is specified.

v2:
- Drop SAMPLE OA check when appending samples (Ashutosh)
- Prevent read if OA buffer is not being sampled

Fixes: 00a7f0d7155c ("drm/i915/tgl: Add perf support on TGL")
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210305210947.58751-1-umesh.nerlige.ramappa@intel.com
(cherry picked from commit be0bdd67fda9468156c733976688f6487d0c42f7)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/i915_perf.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 112ba5f2ce90..e62ad69606f6 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -603,7 +603,6 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 {
 	int report_size = stream->oa_buffer.format_size;
 	struct drm_i915_perf_record_header header;
-	u32 sample_flags = stream->sample_flags;
 
 	header.type = DRM_I915_PERF_RECORD_SAMPLE;
 	header.pad = 0;
@@ -617,10 +616,8 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 		return -EFAULT;
 	buf += sizeof(header);
 
-	if (sample_flags & SAMPLE_OA_REPORT) {
-		if (copy_to_user(buf, report, report_size))
-			return -EFAULT;
-	}
+	if (copy_to_user(buf, report, report_size))
+		return -EFAULT;
 
 	(*offset) += header.size;
 
@@ -2682,7 +2679,7 @@ static void i915_oa_stream_enable(struct i915_perf_stream *stream)
 
 	stream->perf->ops.oa_enable(stream);
 
-	if (stream->periodic)
+	if (stream->sample_flags & SAMPLE_OA_REPORT)
 		hrtimer_start(&stream->poll_check_timer,
 			      ns_to_ktime(stream->poll_oa_period),
 			      HRTIMER_MODE_REL_PINNED);
@@ -2745,7 +2742,7 @@ static void i915_oa_stream_disable(struct i915_perf_stream *stream)
 {
 	stream->perf->ops.oa_disable(stream);
 
-	if (stream->periodic)
+	if (stream->sample_flags & SAMPLE_OA_REPORT)
 		hrtimer_cancel(&stream->poll_check_timer);
 }
 
@@ -3028,7 +3025,7 @@ static ssize_t i915_perf_read(struct file *file,
 	 * disabled stream as an error. In particular it might otherwise lead
 	 * to a deadlock for blocking file descriptors...
 	 */
-	if (!stream->enabled)
+	if (!stream->enabled || !(stream->sample_flags & SAMPLE_OA_REPORT))
 		return -EIO;
 
 	if (!(file->f_flags & O_NONBLOCK)) {

From 6909115442759efef3d4bc5d9c54d7943f1afc14 Mon Sep 17 00:00:00 2001
From: Junlin Yang <yangjunlin@yulong.com>
Date: Fri, 12 Mar 2021 15:14:45 +0800
Subject: [PATCH 0956/1820] drm/omap: dsi: fix unsigned expression compared
 with zero

r is "u32" always >= 0,mipi_dsi_create_packet may return little than zero.
so r < 0 condition is never accessible.

Fixes coccicheck warnings:
./drivers/gpu/drm/omapdrm/dss/dsi.c:2155:5-6:
WARNING: Unsigned expression compared with zero: r < 0

Signed-off-by: Junlin Yang <yangjunlin@yulong.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210312071445.1721-1-angkery@163.com
---
 drivers/gpu/drm/omapdrm/dss/dsi.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c
index 8e11612f5fe1..b31d750c425a 100644
--- a/drivers/gpu/drm/omapdrm/dss/dsi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dsi.c
@@ -2149,11 +2149,12 @@ static int dsi_vc_send_short(struct dsi_data *dsi, int vc,
 			     const struct mipi_dsi_msg *msg)
 {
 	struct mipi_dsi_packet pkt;
+	int ret;
 	u32 r;
 
-	r = mipi_dsi_create_packet(&pkt, msg);
-	if (r < 0)
-		return r;
+	ret = mipi_dsi_create_packet(&pkt, msg);
+	if (ret < 0)
+		return ret;
 
 	WARN_ON(!dsi_bus_is_locked(dsi));
 

From 30916faa1a6009122e10d0c42338b8db44a36fde Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Sun, 14 Mar 2021 18:41:01 +0200
Subject: [PATCH 0957/1820] ARM: OMAP4: Fix PMIC voltage domains for bionic

We are now registering the mpu domain three times instead of registering
mpu, core and iva domains like we should.

Fixes: d44fa156dcb2 ("ARM: OMAP2+: Configure voltage controller for cpcap")
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/pmic-cpcap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/mach-omap2/pmic-cpcap.c b/arch/arm/mach-omap2/pmic-cpcap.c
index 09076ad0576d..668dc84fd31e 100644
--- a/arch/arm/mach-omap2/pmic-cpcap.c
+++ b/arch/arm/mach-omap2/pmic-cpcap.c
@@ -246,10 +246,10 @@ int __init omap4_cpcap_init(void)
 	omap_voltage_register_pmic(voltdm, &omap443x_max8952_mpu);
 
 	if (of_machine_is_compatible("motorola,droid-bionic")) {
-		voltdm = voltdm_lookup("mpu");
+		voltdm = voltdm_lookup("core");
 		omap_voltage_register_pmic(voltdm, &omap_cpcap_core);
 
-		voltdm = voltdm_lookup("mpu");
+		voltdm = voltdm_lookup("iva");
 		omap_voltage_register_pmic(voltdm, &omap_cpcap_iva);
 	} else {
 		voltdm = voltdm_lookup("core");

From b3d09a06d89f474cb52664e016849315a97e09d9 Mon Sep 17 00:00:00 2001
From: Carlos Leija <cileija@ti.com>
Date: Sun, 14 Mar 2021 18:35:44 +0200
Subject: [PATCH 0958/1820] ARM: OMAP4: PM: update ROM return address for OSWR
 and OFF

We need to add a dummy smc call to the cpuidle wakeup path to force the
ROM code to save the return address after MMU is enabled again. This is
needed to prevent random hangs on secure devices like droid4.

Otherwise the system will eventually hang when entering deeper SoC idle
states with the core and mpu domains in open-switch retention (OSWR).
The hang happens as the ROM code tries to use the earlier physical return
address set by omap-headsmp.S with MMU off while waking up CPU1 again.

The hangs started happening in theory already with commit caf8c87d7ff2
("ARM: OMAP2+: Allow core oswr for omap4"), but in practise the issue went
unnoticed as various drivers were often blocking any deeper idle states
with hardware autoidle features.

This patch is based on an earlier TI Linux kernel tree commit 92f0b3028d9e
("OMAP4: PM: update ROM return address for OSWR and OFF") written by
Carlos Leija <cileija@ti.com>, Praneeth Bajjuri <praneeth@ti.com>, and
Bryan Buckley <bryan.buckley@ti.com>. A later version of the patch was
updated to use CPU_PM notifiers by Tero Kristo <t-kristo@ti.com>.

Signed-off-by: Carlos Leija <cileija@ti.com>
Signed-off-by: Praneeth Bajjuri <praneeth@ti.com>
Signed-off-by: Bryan Buckley <bryan.buckley@ti.com>
Signed-off-by: Tero Kristo <t-kristo@ti.com>
Fixes: caf8c87d7ff2 ("ARM: OMAP2+: Allow core oswr for omap4")
Reported-by: Carl Philipp Klemm <philipp@uvos.xyz>
Reported-by: Merlijn Wajer <merlijn@wizzup.org>
Cc: Ivan Jelincic <parazyd@dyne.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Sebastian Reichel <sre@kernel.org>
Cc: Tero Kristo <kristo@kernel.org>
[tony@atomide.com: updated to apply, updated description]
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/omap-secure.c | 39 +++++++++++++++++++++++++++++++
 arch/arm/mach-omap2/omap-secure.h |  1 +
 2 files changed, 40 insertions(+)

diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c
index f70d561f37f7..0659ab4cb0af 100644
--- a/arch/arm/mach-omap2/omap-secure.c
+++ b/arch/arm/mach-omap2/omap-secure.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/arm-smccc.h>
+#include <linux/cpu_pm.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/io.h>
@@ -20,6 +21,7 @@
 
 #include "common.h"
 #include "omap-secure.h"
+#include "soc.h"
 
 static phys_addr_t omap_secure_memblock_base;
 
@@ -213,3 +215,40 @@ void __init omap_secure_init(void)
 {
 	omap_optee_init_check();
 }
+
+/*
+ * Dummy dispatcher call after core OSWR and MPU off. Updates the ROM return
+ * address after MMU has been re-enabled after CPU1 has been woken up again.
+ * Otherwise the ROM code will attempt to use the earlier physical return
+ * address that got set with MMU off when waking up CPU1. Only used on secure
+ * devices.
+ */
+static int cpu_notifier(struct notifier_block *nb, unsigned long cmd, void *v)
+{
+	switch (cmd) {
+	case CPU_CLUSTER_PM_EXIT:
+		omap_secure_dispatcher(OMAP4_PPA_SERVICE_0,
+				       FLAG_START_CRITICAL,
+				       0, 0, 0, 0, 0);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block secure_notifier_block = {
+	.notifier_call = cpu_notifier,
+};
+
+static int __init secure_pm_init(void)
+{
+	if (omap_type() == OMAP2_DEVICE_TYPE_GP || !soc_is_omap44xx())
+		return 0;
+
+	cpu_pm_register_notifier(&secure_notifier_block);
+
+	return 0;
+}
+omap_arch_initcall(secure_pm_init);
diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h
index 4aaa95706d39..172069f31616 100644
--- a/arch/arm/mach-omap2/omap-secure.h
+++ b/arch/arm/mach-omap2/omap-secure.h
@@ -50,6 +50,7 @@
 #define OMAP5_DRA7_MON_SET_ACR_INDEX	0x107
 
 /* Secure PPA(Primary Protected Application) APIs */
+#define OMAP4_PPA_SERVICE_0		0x21
 #define OMAP4_PPA_L2_POR_INDEX		0x23
 #define OMAP4_PPA_CPU_ACTRL_SMP_INDEX	0x25
 

From 3b24cdfc721a5f1098da22f9f68ff5f4a5efccc9 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Thu, 25 Feb 2021 01:47:51 +0300
Subject: [PATCH 0959/1820] drm/msm/dsi: fix check-before-set in the 7nm
 dsi_pll code

Fix setting min/max DSI PLL rate for the V4.1 7nm DSI PLL (used on
sm8250). Current code checks for pll->type before it is set (as it is
set in the msm_dsi_pll_init() after calling device-specific functions.

Cc: Jonathan Marek <jonathan@marek.ca>
Fixes: 1ef7c99d145c ("drm/msm/dsi: add support for 7nm DSI PHY/PLL")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/dsi/pll/dsi_pll.c     | 2 +-
 drivers/gpu/drm/msm/dsi/pll/dsi_pll.h     | 6 ++++--
 drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c | 5 +++--
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
index a45fe95aff49..3dc65877fa10 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
@@ -163,7 +163,7 @@ struct msm_dsi_pll *msm_dsi_pll_init(struct platform_device *pdev,
 		break;
 	case MSM_DSI_PHY_7NM:
 	case MSM_DSI_PHY_7NM_V4_1:
-		pll = msm_dsi_pll_7nm_init(pdev, id);
+		pll = msm_dsi_pll_7nm_init(pdev, type, id);
 		break;
 	default:
 		pll = ERR_PTR(-ENXIO);
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h
index 3405982a092c..bbecb1de5678 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h
@@ -117,10 +117,12 @@ msm_dsi_pll_10nm_init(struct platform_device *pdev, int id)
 }
 #endif
 #ifdef CONFIG_DRM_MSM_DSI_7NM_PHY
-struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id);
+struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev,
+					enum msm_dsi_phy_type type, int id);
 #else
 static inline struct msm_dsi_pll *
-msm_dsi_pll_7nm_init(struct platform_device *pdev, int id)
+msm_dsi_pll_7nm_init(struct platform_device *pdev,
+					enum msm_dsi_phy_type type, int id)
 {
 	return ERR_PTR(-ENODEV);
 }
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
index 93bf142e4a4e..c1f6708367ae 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
@@ -852,7 +852,8 @@ err_base_clk_hw:
 	return ret;
 }
 
-struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id)
+struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev,
+					enum msm_dsi_phy_type type, int id)
 {
 	struct dsi_pll_7nm *pll_7nm;
 	struct msm_dsi_pll *pll;
@@ -885,7 +886,7 @@ struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id)
 	pll = &pll_7nm->base;
 	pll->min_rate = 1000000000UL;
 	pll->max_rate = 3500000000UL;
-	if (pll->type == MSM_DSI_PHY_7NM_V4_1) {
+	if (type == MSM_DSI_PHY_7NM_V4_1) {
 		pll->min_rate = 600000000UL;
 		pll->max_rate = (unsigned long)5000000000ULL;
 		/* workaround for max rate overflowing on 32-bit builds: */

From 19f4a055abf2a69a1c0109456c3758b5697730c9 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Thu, 25 Feb 2021 02:01:43 +0300
Subject: [PATCH 0960/1820] drm/msm/dsi_pll_7nm: Solve TODO for multiplier
 frac_bits assignment

The number of fractional registers bits is known and already set in
the frac_bits variable of the dsi_pll_config struct here in 7nm:
remove the TODO by simply using that variable. This is a copy of
196145eb1af1 ("drm/msm/dsi_pll_10nm: Solve TODO for multiplier frac_bits
assignment").

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <abhinavk@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
index c1f6708367ae..0458eda15114 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
@@ -509,6 +509,7 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw,
 {
 	struct msm_dsi_pll *pll = hw_clk_to_pll(hw);
 	struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll);
+	struct dsi_pll_config *config = &pll_7nm->pll_configuration;
 	void __iomem *base = pll_7nm->mmio;
 	u64 ref_clk = pll_7nm->vco_ref_clk_rate;
 	u64 vco_rate = 0x0;
@@ -529,9 +530,8 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw,
 	/*
 	 * TODO:
 	 *	1. Assumes prescaler is disabled
-	 *	2. Multiplier is 2^18. it should be 2^(num_of_frac_bits)
 	 */
-	multiplier = 1 << 18;
+	multiplier = 1 << config->frac_bits;
 	pll_freq = dec * (ref_clk * 2);
 	tmp64 = (ref_clk * 2 * frac);
 	pll_freq += div_u64(tmp64, multiplier);

From 9daaf31307856defb1070685418ce5a484ecda3a Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Thu, 25 Feb 2021 02:05:28 +0300
Subject: [PATCH 0961/1820] drm/msm/dsi_pll_7nm: Fix variable usage for
 pll_lockdet_rate

The PLL_LOCKDET_RATE_1 was being programmed with a hardcoded value
directly, but the same value was also being specified in the
dsi_pll_regs struct pll_lockdet_rate variable: let's use it!

Based on 362cadf34b9f ("drm/msm/dsi_pll_10nm: Fix variable usage for
pll_lockdet_rate")

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <abhinavk@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
index 0458eda15114..e29b3bfd63d1 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
@@ -325,7 +325,7 @@ static void dsi_pll_commit(struct dsi_pll_7nm *pll)
 	pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1, reg->frac_div_start_low);
 	pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1, reg->frac_div_start_mid);
 	pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1, reg->frac_div_start_high);
-	pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40);
+	pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, reg->pll_lockdet_rate);
 	pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_DELAY, 0x06);
 	pll_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, 0x10); /* TODO: 0x00 for CPHY */
 	pll_write(base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS, reg->pll_clock_inverters);

From 413b7a320e238d1a79dfca24c35ce4e1a0e7a8d6 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Fri, 26 Feb 2021 13:08:21 -0800
Subject: [PATCH 0962/1820] drm/msm/dp: Restore aux retry tuning logic

In commit 9fc418430c65 ("drm/msm/dp: unplug interrupt missed after
irq_hpd handler") we dropped a reset of the aux phy during aux transfers
because resetting the phy during active communication caused us to miss
an hpd irq in some cases. Unfortunately, we also dropped the part of the
code that changes the aux phy tuning when an aux transfer fails due to a
timeout. That part of the code was calling into the phy driver to
reconfigure the aux TX swing controls, working around poor channel
quality. Let's restore this phy setting code so that aux channel
communication is more reliable.

Cc: Kuogee Hsieh <khsieh@codeaurora.org>
Fixes: 9fc418430c65 ("drm/msm/dp: unplug interrupt missed after irq_hpd handler")
Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/dp/dp_aux.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c
index 1c6e1d2b947c..7c22bfe0fc7d 100644
--- a/drivers/gpu/drm/msm/dp/dp_aux.c
+++ b/drivers/gpu/drm/msm/dp/dp_aux.c
@@ -32,6 +32,8 @@ struct dp_aux_private {
 	struct drm_dp_aux dp_aux;
 };
 
+#define MAX_AUX_RETRIES			5
+
 static const char *dp_aux_get_error(u32 aux_error)
 {
 	switch (aux_error) {
@@ -377,6 +379,11 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux,
 	ret = dp_aux_cmd_fifo_tx(aux, msg);
 
 	if (ret < 0) {
+		if (aux->native) {
+			aux->retry_cnt++;
+			if (!(aux->retry_cnt % MAX_AUX_RETRIES))
+				dp_catalog_aux_update_cfg(aux->catalog);
+		}
 		usleep_range(400, 500); /* at least 400us to next try */
 		goto unlock_exit;
 	}

From 4a9d36b0610aa7034340e976652e5b43320dd7c5 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@somainline.org>
Date: Sun, 28 Feb 2021 13:36:51 +0100
Subject: [PATCH 0963/1820] drm/msm/adreno: a5xx_power: Don't apply A540
 lm_setup to other GPUs

While passing the A530-specific lm_setup func to A530 and A540
to !A530 was fine back when only these two were supported, it
certainly is not a good idea to send A540 specifics to smaller
GPUs like A508 and friends.

Signed-off-by: Konrad Dybcio <konrad.dybcio@somainline.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/adreno/a5xx_power.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index 5ccc9da455a1..c35b06b46fcc 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -304,7 +304,7 @@ int a5xx_power_init(struct msm_gpu *gpu)
 	/* Set up the limits management */
 	if (adreno_is_a530(adreno_gpu))
 		a530_lm_setup(gpu);
-	else
+	else if (adreno_is_a540(adreno_gpu))
 		a540_lm_setup(gpu);
 
 	/* Set up SP/TP power collpase */

From f232326f6966cf2a1d1db7bc917a4ce5f9f55f76 Mon Sep 17 00:00:00 2001
From: Piotr Krysiuk <piotras@gmail.com>
Date: Tue, 16 Mar 2021 09:47:02 +0100
Subject: [PATCH 0964/1820] bpf: Prohibit alu ops for pointer types not
 defining ptr_limit

The purpose of this patch is to streamline error propagation and in particular
to propagate retrieve_ptr_limit() errors for pointer types that are not defining
a ptr_limit such that register-based alu ops against these types can be rejected.

The main rationale is that a gap has been identified by Piotr in the existing
protection against speculatively out-of-bounds loads, for example, in case of
ctx pointers, unprivileged programs can still perform pointer arithmetic. This
can be abused to execute speculatively out-of-bounds loads without restrictions
and thus extract contents of kernel memory.

Fix this by rejecting unprivileged programs that attempt any pointer arithmetic
on unprotected pointer types. The two affected ones are pointer to ctx as well
as pointer to map. Field access to a modified ctx' pointer is rejected at a
later point in time in the verifier, and 7c6967326267 ("bpf: Permit map_ptr
arithmetic with opcode add and offset 0") only relevant for root-only use cases.
Risk of unprivileged program breakage is considered very low.

Fixes: 7c6967326267 ("bpf: Permit map_ptr arithmetic with opcode add and offset 0")
Fixes: b2157399cc98 ("bpf: prevent out-of-bounds speculation")
Signed-off-by: Piotr Krysiuk <piotras@gmail.com>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4192a9e56654..1c8cbef7cc14 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5934,6 +5934,7 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 	u32 alu_state, alu_limit;
 	struct bpf_reg_state tmp;
 	bool ret;
+	int err;
 
 	if (can_skip_alu_sanitation(env, insn))
 		return 0;
@@ -5949,10 +5950,13 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 	alu_state |= ptr_is_dst_reg ?
 		     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
 
-	if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg))
-		return 0;
-	if (update_alu_sanitation_state(aux, alu_state, alu_limit))
-		return -EACCES;
+	err = retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg);
+	if (err < 0)
+		return err;
+
+	err = update_alu_sanitation_state(aux, alu_state, alu_limit);
+	if (err < 0)
+		return err;
 do_sim:
 	/* Simulate and find potential out-of-bounds access under
 	 * speculative execution from truncation as a result of
@@ -6103,7 +6107,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	case BPF_ADD:
 		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
 		if (ret < 0) {
-			verbose(env, "R%d tried to add from different maps or paths\n", dst);
+			verbose(env, "R%d tried to add from different maps, paths, or prohibited types\n", dst);
 			return ret;
 		}
 		/* We can take a fixed offset as long as it doesn't overflow
@@ -6158,7 +6162,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	case BPF_SUB:
 		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
 		if (ret < 0) {
-			verbose(env, "R%d tried to sub from different maps or paths\n", dst);
+			verbose(env, "R%d tried to sub from different maps, paths, or prohibited types\n", dst);
 			return ret;
 		}
 		if (dst_reg == off_reg) {

From 10d2bb2e6b1d8c4576c56a748f697dbeb8388899 Mon Sep 17 00:00:00 2001
From: Piotr Krysiuk <piotras@gmail.com>
Date: Tue, 16 Mar 2021 08:20:16 +0100
Subject: [PATCH 0965/1820] bpf: Fix off-by-one for area size in creating mask
 to left

retrieve_ptr_limit() computes the ptr_limit for registers with stack and
map_value type. ptr_limit is the size of the memory area that is still
valid / in-bounds from the point of the current position and direction
of the operation (add / sub). This size will later be used for masking
the operation such that attempting out-of-bounds access in the speculative
domain is redirected to remain within the bounds of the current map value.

When masking to the right the size is correct, however, when masking to
the left, the size is off-by-one which would lead to an incorrect mask
and thus incorrect arithmetic operation in the non-speculative domain.
Piotr found that if the resulting alu_limit value is zero, then the
BPF_MOV32_IMM() from the fixup_bpf_calls() rewrite will end up loading
0xffffffff into AX instead of sign-extending to the full 64 bit range,
and as a result, this allows abuse for executing speculatively out-of-
bounds loads against 4GB window of address space and thus extracting the
contents of kernel memory via side-channel.

Fixes: 979d63d50c0c ("bpf: prevent out of bounds speculation on pointer arithmetic")
Signed-off-by: Piotr Krysiuk <piotras@gmail.com>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1c8cbef7cc14..56c63658b702 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5870,13 +5870,13 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 		 */
 		off = ptr_reg->off + ptr_reg->var_off.value;
 		if (mask_to_left)
-			*ptr_limit = MAX_BPF_STACK + off;
+			*ptr_limit = MAX_BPF_STACK + off + 1;
 		else
 			*ptr_limit = -off;
 		return 0;
 	case PTR_TO_MAP_VALUE:
 		if (mask_to_left) {
-			*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
+			*ptr_limit = ptr_reg->umax_value + ptr_reg->off + 1;
 		} else {
 			off = ptr_reg->smin_value + ptr_reg->off;
 			*ptr_limit = ptr_reg->map_ptr->value_size - off;

From b5871dca250cd391885218b99cc015aca1a51aea Mon Sep 17 00:00:00 2001
From: Piotr Krysiuk <piotras@gmail.com>
Date: Tue, 16 Mar 2021 08:26:25 +0100
Subject: [PATCH 0966/1820] bpf: Simplify alu_limit masking for pointer
 arithmetic

Instead of having the mov32 with aux->alu_limit - 1 immediate, move this
operation to retrieve_ptr_limit() instead to simplify the logic and to
allow for subsequent sanity boundary checks inside retrieve_ptr_limit().
This avoids in future that at the time of the verifier masking rewrite
we'd run into an underflow which would not sign extend due to the nature
of mov32 instruction.

Signed-off-by: Piotr Krysiuk <piotras@gmail.com>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 56c63658b702..d16722a99b61 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5870,16 +5870,16 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 		 */
 		off = ptr_reg->off + ptr_reg->var_off.value;
 		if (mask_to_left)
-			*ptr_limit = MAX_BPF_STACK + off + 1;
+			*ptr_limit = MAX_BPF_STACK + off;
 		else
-			*ptr_limit = -off;
+			*ptr_limit = -off - 1;
 		return 0;
 	case PTR_TO_MAP_VALUE:
 		if (mask_to_left) {
-			*ptr_limit = ptr_reg->umax_value + ptr_reg->off + 1;
+			*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
 		} else {
 			off = ptr_reg->smin_value + ptr_reg->off;
-			*ptr_limit = ptr_reg->map_ptr->value_size - off;
+			*ptr_limit = ptr_reg->map_ptr->value_size - off - 1;
 		}
 		return 0;
 	default:
@@ -11668,7 +11668,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			off_reg = issrc ? insn->src_reg : insn->dst_reg;
 			if (isneg)
 				*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
-			*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1);
+			*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit);
 			*patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
 			*patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
 			*patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);

From d2c21422323b06938b3c070361dc544f047489d7 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Tue, 16 Mar 2021 17:07:47 -0700
Subject: [PATCH 0967/1820] ionic: linearize tso skb with too many frags

We were linearizing non-TSO skbs that had too many frags, but
we weren't checking number of frags on TSO skbs.  This could
lead to a bad page reference when we received a TSO skb with
more frags than the Tx descriptor could support.

v2: use gso_segs rather than yet another division
    don't rework the check on the nr_frags

Fixes: 0f3154e6bcb3 ("ionic: Add Tx and Rx handling")
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 162a1ff1e9d2..4087311f7082 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -1079,15 +1079,17 @@ static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb)
 {
 	int sg_elems = q->lif->qtype_info[IONIC_QTYPE_TXQ].max_sg_elems;
 	struct ionic_tx_stats *stats = q_to_tx_stats(q);
+	int ndescs;
 	int err;
 
-	/* If TSO, need roundup(skb->len/mss) descs */
+	/* Each desc is mss long max, so a descriptor for each gso_seg */
 	if (skb_is_gso(skb))
-		return (skb->len / skb_shinfo(skb)->gso_size) + 1;
+		ndescs = skb_shinfo(skb)->gso_segs;
+	else
+		ndescs = 1;
 
-	/* If non-TSO, just need 1 desc and nr_frags sg elems */
 	if (skb_shinfo(skb)->nr_frags <= sg_elems)
-		return 1;
+		return ndescs;
 
 	/* Too many frags, so linearize */
 	err = skb_linearize(skb);
@@ -1096,8 +1098,7 @@ static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb)
 
 	stats->linearize++;
 
-	/* Need 1 desc and zero sg elems */
-	return 1;
+	return ndescs;
 }
 
 static int ionic_maybe_stop_tx(struct ionic_queue *q, int ndescs)

From f3da882eae2d6ba6c72062a46344ba096a7c2b3d Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Date: Wed, 17 Mar 2021 17:57:31 +0900
Subject: [PATCH 0968/1820] btrfs: zoned: remove outdated WARN_ON in direct IO

In btrfs_submit_direct() there's a WAN_ON_ONCE() that will trigger if
we're submitting a DIO write on a zoned filesystem but are not using
REQ_OP_ZONE_APPEND to submit the IO to the block device.

This is a left over from a previous version where btrfs_dio_iomap_begin()
didn't use btrfs_use_zone_append() to check for sequential write only
zones.

It is an oversight from the development phase. In v11 (I think) I've
added 08f455593fff ("btrfs: zoned: cache if block group is on a
sequential zone") and forgot to remove the WARN_ON_ONCE() for
544d24f9de73 ("btrfs: zoned: enable zone append writing for direct IO").

When developing auto relocation I got hit by the WARN as a block groups
where relocated to conventional zone and the dio code calls
btrfs_use_zone_append() introduced by 08f455593fff to check if it can
use zone append (a.k.a. if it's a sequential zone) or not and sets the
appropriate flags for iomap.

I've never hit it in testing before, as I was relying on emulation to
test the conventional zones code but this one case wasn't hit, because
on emulation fs_info->max_zone_append_size is 0 and the WARN doesn't
trigger either.

Fixes: 544d24f9de73 ("btrfs: zoned: enable zone append writing for direct IO")
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5092dea21448..4120fd96a134 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8166,10 +8166,6 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
 		bio->bi_end_io = btrfs_end_dio_bio;
 		btrfs_io_bio(bio)->logical = file_offset;
 
-		WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) &&
-			     fs_info->max_zone_append_size &&
-			     bio_op(bio) != REQ_OP_ZONE_APPEND);
-
 		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
 			status = extract_ordered_extent(BTRFS_I(inode), bio,
 							file_offset);

From 82d62d06db404d03836cdabbca41d38646d97cbb Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Thu, 11 Mar 2021 11:23:15 -0500
Subject: [PATCH 0969/1820] btrfs: do not initialize dev stats if we have no
 dev_root

Neal reported a panic trying to use -o rescue=all

  BUG: kernel NULL pointer dereference, address: 0000000000000030
  PGD 0 P4D 0
  Oops: 0000 [#1] SMP PTI
  CPU: 0 PID: 4095 Comm: mount Not tainted 5.11.0-0.rc7.149.fc34.x86_64 #1
  RIP: 0010:btrfs_device_init_dev_stats+0x4c/0x1f0
  RSP: 0018:ffffa60285fbfb68 EFLAGS: 00010246
  RAX: 0000000000000000 RBX: ffff88b88f806498 RCX: ffff88b82e7a2a10
  RDX: ffffa60285fbfb97 RSI: ffff88b82e7a2a10 RDI: 0000000000000000
  RBP: ffff88b88f806b3c R08: 0000000000000000 R09: 0000000000000000
  R10: ffff88b82e7a2a10 R11: 0000000000000000 R12: ffff88b88f806a00
  R13: ffff88b88f806478 R14: ffff88b88f806a00 R15: ffff88b82e7a2a10
  FS:  00007f698be1ec40(0000) GS:ffff88b937e00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000030 CR3: 0000000092c9c006 CR4: 00000000003706f0
  Call Trace:
  ? btrfs_init_dev_stats+0x1f/0xf0
  btrfs_init_dev_stats+0x62/0xf0
  open_ctree+0x1019/0x15ff
  btrfs_mount_root.cold+0x13/0xfa
  legacy_get_tree+0x27/0x40
  vfs_get_tree+0x25/0xb0
  vfs_kern_mount.part.0+0x71/0xb0
  btrfs_mount+0x131/0x3d0
  ? legacy_get_tree+0x27/0x40
  ? btrfs_show_options+0x640/0x640
  legacy_get_tree+0x27/0x40
  vfs_get_tree+0x25/0xb0
  path_mount+0x441/0xa80
  __x64_sys_mount+0xf4/0x130
  do_syscall_64+0x33/0x40
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
  RIP: 0033:0x7f698c04e52e

This happens because we unconditionally attempt to initialize device
stats on mount, but we may not have been able to read the device root.
Fix this by skipping initializing the device stats if we do not have a
device root.

Reported-by: Neal Gompa <ngompa13@gmail.com>
CC: stable@vger.kernel.org # 5.11+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b8fab44394f5..e2df6e6e2c18 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7448,6 +7448,9 @@ static int btrfs_device_init_dev_stats(struct btrfs_device *device,
 	int item_size;
 	int i, ret, slot;
 
+	if (!device->fs_info->dev_root)
+		return 0;
+
 	key.objectid = BTRFS_DEV_STATS_OBJECTID;
 	key.type = BTRFS_PERSISTENT_ITEM_KEY;
 	key.offset = device->devid;

From 820a49dafc3304de06f296c35c9ff1ebc1666343 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Thu, 11 Mar 2021 11:23:14 -0500
Subject: [PATCH 0970/1820] btrfs: initialize device::fs_info always

Neal reported a panic trying to use -o rescue=all

  BUG: kernel NULL pointer dereference, address: 0000000000000030
  PGD 0 P4D 0
  Oops: 0000 [#1] SMP NOPTI
  CPU: 0 PID: 696 Comm: mount Tainted: G        W         5.12.0-rc2+ #296
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
  RIP: 0010:btrfs_device_init_dev_stats+0x1d/0x200
  RSP: 0018:ffffafaec1483bb8 EFLAGS: 00010286
  RAX: 0000000000000000 RBX: ffff9a5715bcb298 RCX: 0000000000000070
  RDX: ffff9a5703248000 RSI: ffff9a57052ea150 RDI: ffff9a5715bca400
  RBP: ffff9a57052ea150 R08: 0000000000000070 R09: ffff9a57052ea150
  R10: 000130faf0741c10 R11: 0000000000000000 R12: ffff9a5703700000
  R13: 0000000000000000 R14: ffff9a5715bcb278 R15: ffff9a57052ea150
  FS:  00007f600d122c40(0000) GS:ffff9a577bc00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000030 CR3: 0000000112a46005 CR4: 0000000000370ef0
  Call Trace:
   ? btrfs_init_dev_stats+0x1f/0xf0
   ? kmem_cache_alloc+0xef/0x1f0
   btrfs_init_dev_stats+0x5f/0xf0
   open_ctree+0x10cb/0x1720
   btrfs_mount_root.cold+0x12/0xea
   legacy_get_tree+0x27/0x40
   vfs_get_tree+0x25/0xb0
   vfs_kern_mount.part.0+0x71/0xb0
   btrfs_mount+0x10d/0x380
   legacy_get_tree+0x27/0x40
   vfs_get_tree+0x25/0xb0
   path_mount+0x433/0xa00
   __x64_sys_mount+0xe3/0x120
   do_syscall_64+0x33/0x40
   entry_SYSCALL_64_after_hwframe+0x44/0xae

This happens because when we call btrfs_init_dev_stats we do
device->fs_info->dev_root.  However device->fs_info isn't initialized
because we were only calling btrfs_init_devices_late() if we properly
read the device root.  However we don't actually need the device root to
init the devices, this function simply assigns the devices their
->fs_info pointer properly, so this needs to be done unconditionally
always so that we can properly dereference device->fs_info in rescue
cases.

Reported-by: Neal Gompa <ngompa13@gmail.com>
CC: stable@vger.kernel.org # 5.11+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c2576c5fe62e..98c46cde7d79 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2387,8 +2387,9 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	} else {
 		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
 		fs_info->dev_root = root;
-		btrfs_init_devices_late(fs_info);
 	}
+	/* Initialize fs_info for all devices in any case */
+	btrfs_init_devices_late(fs_info);
 
 	/* If IGNOREDATACSUMS is set don't bother reading the csum root. */
 	if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {

From 3cb894972f1809aa8d087c42e5e8b26c64b7d508 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Thu, 11 Mar 2021 11:23:16 -0500
Subject: [PATCH 0971/1820] btrfs: do not initialize dev replace for bad dev
 root

While helping Neal fix his broken file system I added a debug patch to
catch if we were calling btrfs_search_slot with a NULL root, and this
stack trace popped:

  we tried to search with a NULL root
  CPU: 0 PID: 1760 Comm: mount Not tainted 5.11.0-155.nealbtrfstest.1.fc34.x86_64 #1
  Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/22/2020
  Call Trace:
   dump_stack+0x6b/0x83
   btrfs_search_slot.cold+0x11/0x1b
   ? btrfs_init_dev_replace+0x36/0x450
   btrfs_init_dev_replace+0x71/0x450
   open_ctree+0x1054/0x1610
   btrfs_mount_root.cold+0x13/0xfa
   legacy_get_tree+0x27/0x40
   vfs_get_tree+0x25/0xb0
   vfs_kern_mount.part.0+0x71/0xb0
   btrfs_mount+0x131/0x3d0
   ? legacy_get_tree+0x27/0x40
   ? btrfs_show_options+0x640/0x640
   legacy_get_tree+0x27/0x40
   vfs_get_tree+0x25/0xb0
   path_mount+0x441/0xa80
   __x64_sys_mount+0xf4/0x130
   do_syscall_64+0x33/0x40
   entry_SYSCALL_64_after_hwframe+0x44/0xa9
  RIP: 0033:0x7f644730352e

Fix this by not starting the device replace stuff if we do not have a
NULL dev root.

Reported-by: Neal Gompa <ngompa13@gmail.com>
CC: stable@vger.kernel.org # 5.11+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/dev-replace.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 3a9c1e046ebe..d05f73530af7 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -81,6 +81,9 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
 	struct btrfs_dev_replace_item *ptr;
 	u64 src_devid;
 
+	if (!dev_root)
+		return 0;
+
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;

From ebd99a6b34fbcccf21067b66d1718000feb80ce8 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Wed, 17 Mar 2021 11:43:13 +0100
Subject: [PATCH 0972/1820] btrfs: fix build when using M=fs/btrfs

There are people building the module with M= that's supposed to be used
for external modules. This got broken in e9aa7c285d20 ("btrfs: enable
W=1 checks for btrfs").

  $ make M=fs/btrfs
  scripts/Makefile.lib:10: *** Recursive variable 'KBUILD_CFLAGS' references itself (eventually).  Stop.
  make: *** [Makefile:1755: modules] Error 2

There's a difference compared to 'make fs/btrfs/btrfs.ko' which needs
to rebuild a few more things and also the dependency modules need to be
available. It could fail with eg.

  WARNING: Symbol version dump "Module.symvers" is missing.
	   Modules may not have dependencies or modversions.

In some environments it's more convenient to rebuild just the btrfs
module by M= so let's make it work.

The problem is with recursive variable evaluation in += so the
conditional C options are stored in a temporary variable to avoid the
recursion.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/Makefile | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index b634c42115ea..b4fb997eda16 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -7,10 +7,12 @@ subdir-ccflags-y += -Wmissing-format-attribute
 subdir-ccflags-y += -Wmissing-prototypes
 subdir-ccflags-y += -Wold-style-definition
 subdir-ccflags-y += -Wmissing-include-dirs
-subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable)
-subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
-subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
-subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
+condflags := \
+	$(call cc-option, -Wunused-but-set-variable)		\
+	$(call cc-option, -Wunused-const-variable)		\
+	$(call cc-option, -Wpacked-not-aligned)			\
+	$(call cc-option, -Wstringop-truncation)
+subdir-ccflags-y += $(condflags)
 # The following turn off the warnings enabled by -Wextra
 subdir-ccflags-y += -Wno-missing-field-initializers
 subdir-ccflags-y += -Wno-sign-compare

From 8d488a8c7ba22d7112fbf6b0a82beb1cdea1c0d5 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 16 Mar 2021 16:53:46 +0000
Subject: [PATCH 0973/1820] btrfs: fix subvolume/snapshot deletion not
 triggered on mount

During the mount procedure we are calling btrfs_orphan_cleanup() against
the root tree, which will find all orphans items in this tree. When an
orphan item corresponds to a deleted subvolume/snapshot (instead of an
inode space cache), it must not delete the orphan item, because that will
cause btrfs_find_orphan_roots() to not find the orphan item and therefore
not add the corresponding subvolume root to the list of dead roots, which
results in the subvolume's tree never being deleted by the cleanup thread.

The same applies to the remount from RO to RW path.

Fix this by making btrfs_find_orphan_roots() run before calling
btrfs_orphan_cleanup() against the root tree.

A test case for fstests will follow soon.

Reported-by: Robbie Ko <robbieko@synology.com>
Link: https://lore.kernel.org/linux-btrfs/b19f4310-35e0-606e-1eea-2dd84d28c5da@synology.com/
Fixes: 638331fa56caea ("btrfs: fix transaction leak and crash after cleaning up orphans on RO mount")
CC: stable@vger.kernel.org # 5.11+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 98c46cde7d79..48e9cf01abc5 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3010,6 +3010,21 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 		}
 	}
 
+	/*
+	 * btrfs_find_orphan_roots() is responsible for finding all the dead
+	 * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load
+	 * them into the fs_info->fs_roots_radix tree. This must be done before
+	 * calling btrfs_orphan_cleanup() on the tree root. If we don't do it
+	 * first, then btrfs_orphan_cleanup() will delete a dead root's orphan
+	 * item before the root's tree is deleted - this means that if we unmount
+	 * or crash before the deletion completes, on the next mount we will not
+	 * delete what remains of the tree because the orphan item does not
+	 * exists anymore, which is what tells us we have a pending deletion.
+	 */
+	ret = btrfs_find_orphan_roots(fs_info);
+	if (ret)
+		goto out;
+
 	ret = btrfs_cleanup_fs_roots(fs_info);
 	if (ret)
 		goto out;
@@ -3069,7 +3084,6 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 		}
 	}
 
-	ret = btrfs_find_orphan_roots(fs_info);
 out:
 	return ret;
 }

From afa536d8405a9ca36e45ba035554afbb8da27b82 Mon Sep 17 00:00:00 2001
From: wenxu <wenxu@ucloud.cn>
Date: Wed, 17 Mar 2021 12:02:43 +0800
Subject: [PATCH 0974/1820] net/sched: cls_flower: fix only mask bit check in
 the validate_ct_state

The ct_state validate should not only check the mask bit and also
check mask_bit & key_bit..
For the +new+est case example, The 'new' and 'est' bits should be
set in both state_mask and state flags. Or the -new-est case also
will be reject by kernel.
When Openvswitch with two flows
ct_state=+trk+new,action=commit,forward
ct_state=+trk+est,action=forward

A packet go through the kernel  and the contrack state is invalid,
The ct_state will be +trk-inv. Upcall to the ovs-vswitchd, the
finally dp action will be drop with -new-est+trk.

Fixes: 1bcc51ac0731 ("net/sched: cls_flower: Reject invalid ct_state flags rules")
Fixes: 3aed8b63336c ("net/sched: cls_flower: validate ct_state for invalid and reply flags")
Signed-off-by: wenxu <wenxu@ucloud.cn>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index d097b5c15faa..c69a4ba9c33f 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1451,7 +1451,7 @@ static int fl_set_key_ct(struct nlattr **tb,
 			       &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK,
 			       sizeof(key->ct_state));
 
-		err = fl_validate_ct_state(mask->ct_state,
+		err = fl_validate_ct_state(key->ct_state & mask->ct_state,
 					   tb[TCA_FLOWER_KEY_CT_STATE_MASK],
 					   extack);
 		if (err)

From 9afeefcf06fc7b4bdab06a6e2cb06745bded34dd Mon Sep 17 00:00:00 2001
From: Suman Anna <s-anna@ti.com>
Date: Mon, 15 Mar 2021 15:58:59 -0500
Subject: [PATCH 0975/1820] remoteproc: pru: Fix firmware loading crashes on K3
 SoCs

The K3 PRUs are 32-bit processors and in general have some limitations
in using the standard ARMv8 memcpy function for loading firmware segments,
so the driver already uses a custom memcpy implementation. This added
logic however is limited to only IRAMs at the moment, but the loading
into Data RAMs is not completely ok either and does generate a kernel
crash for unaligned accesses.

Fix these crashes by removing the existing IRAM logic limitation and
extending the custom memcpy usage to Data RAMs as well for all K3 SoCs.

Fixes: 1d39f4d19921 ("remoteproc: pru: Add support for various PRU cores on K3 AM65x SoCs")
Signed-off-by: Suman Anna <s-anna@ti.com>
Link: https://lore.kernel.org/r/20210315205859.19590-1-s-anna@ti.com
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/pru_rproc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/pru_rproc.c b/drivers/remoteproc/pru_rproc.c
index 5fad787ba012..dcb380e868df 100644
--- a/drivers/remoteproc/pru_rproc.c
+++ b/drivers/remoteproc/pru_rproc.c
@@ -603,7 +603,7 @@ pru_rproc_load_elf_segments(struct rproc *rproc, const struct firmware *fw)
 			break;
 		}
 
-		if (pru->data->is_k3 && is_iram) {
+		if (pru->data->is_k3) {
 			ret = pru_rproc_memcpy(ptr, elf_data + phdr->p_offset,
 					       filesz);
 			if (ret) {

From 6417f03132a6952cd17ddd8eaddbac92b61b17e0 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 17 Mar 2021 12:45:47 +0200
Subject: [PATCH 0976/1820] module: remove never implemented
 MODULE_SUPPORTED_DEVICE

MODULE_SUPPORTED_DEVICE was added in pre-git era and never was
implemented. We can safely remove it, because the kernel has grown
to have many more reliable mechanisms to determine if device is
supported or not.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/platform/iris/iris.c                 |  1 -
 drivers/atm/fore200e.c                        |  2 --
 drivers/block/floppy.c                        |  1 -
 drivers/bluetooth/btrsi.c                     |  1 -
 drivers/char/applicom.c                       |  3 --
 drivers/char/toshiba.c                        |  1 -
 drivers/input/joydev.c                        |  1 -
 drivers/media/firewire/firedtv-fw.c           |  1 -
 drivers/media/pci/cx18/cx18-alsa-main.c       |  1 -
 drivers/media/pci/cx18/cx18-driver.c          |  1 -
 drivers/media/pci/cx25821/cx25821-alsa.c      |  1 -
 drivers/media/pci/cx88/cx88-alsa.c            |  1 -
 drivers/media/pci/ivtv/ivtv-alsa-main.c       |  1 -
 drivers/media/pci/ivtv/ivtv-driver.c          |  3 --
 drivers/media/pci/sta2x11/sta2x11_vip.c       |  1 -
 drivers/media/platform/atmel/atmel-isi.c      |  1 -
 .../media/platform/atmel/atmel-sama5d2-isc.c  |  1 -
 .../media/platform/marvell-ccic/cafe-driver.c |  4 ---
 drivers/media/platform/stm32/stm32-dcmi.c     |  1 -
 drivers/media/usb/cpia2/cpia2_v4l.c           |  1 -
 drivers/media/usb/tm6000/tm6000-alsa.c        |  1 -
 drivers/media/usb/tm6000/tm6000-dvb.c         |  2 --
 drivers/mtd/maps/sun_uflash.c                 |  1 -
 drivers/net/can/peak_canfd/peak_pciefd_main.c |  1 -
 drivers/net/can/sja1000/ems_pci.c             |  1 -
 drivers/net/can/sja1000/ems_pcmcia.c          |  1 -
 drivers/net/can/sja1000/kvaser_pci.c          |  1 -
 drivers/net/can/sja1000/peak_pci.c            |  2 --
 drivers/net/can/sja1000/peak_pcmcia.c         |  1 -
 drivers/net/can/sja1000/plx_pci.c             | 12 -------
 drivers/net/can/usb/peak_usb/pcan_usb.c       |  2 --
 drivers/net/can/usb/peak_usb/pcan_usb_fd.c    |  3 --
 drivers/net/can/usb/peak_usb/pcan_usb_pro.c   |  2 --
 drivers/net/hamradio/scc.c                    |  1 -
 drivers/net/wireless/admtek/adm8211.c         |  1 -
 drivers/net/wireless/ath/ath5k/base.c         |  1 -
 drivers/net/wireless/ath/ath9k/hw.c           |  1 -
 drivers/net/wireless/ath/ath9k/init.c         |  1 -
 drivers/net/wireless/atmel/atmel.c            |  1 -
 drivers/net/wireless/atmel/atmel_cs.c         |  1 -
 drivers/net/wireless/atmel/atmel_pci.c        |  1 -
 .../broadcom/brcm80211/brcmsmac/mac80211_if.c |  1 -
 .../broadcom/brcm80211/brcmutil/utils.c       |  1 -
 drivers/net/wireless/cisco/airo.c             |  1 -
 drivers/net/wireless/cisco/airo_cs.c          |  1 -
 .../net/wireless/intersil/hostap/hostap_cs.c  |  1 -
 .../net/wireless/intersil/hostap/hostap_pci.c |  1 -
 .../net/wireless/intersil/hostap/hostap_plx.c |  1 -
 .../net/wireless/ralink/rt2x00/rt2400pci.c    |  1 -
 .../net/wireless/ralink/rt2x00/rt2500pci.c    |  1 -
 .../net/wireless/ralink/rt2x00/rt2500usb.c    |  1 -
 .../net/wireless/ralink/rt2x00/rt2800pci.c    |  1 -
 .../net/wireless/ralink/rt2x00/rt2800usb.c    |  1 -
 drivers/net/wireless/ralink/rt2x00/rt61pci.c  |  2 --
 drivers/net/wireless/ralink/rt2x00/rt73usb.c  |  1 -
 drivers/net/wireless/rsi/rsi_91x_main.c       |  1 -
 drivers/net/wireless/rsi/rsi_91x_sdio.c       |  1 -
 drivers/net/wireless/rsi/rsi_91x_usb.c        |  1 -
 drivers/parport/parport_amiga.c               |  1 -
 drivers/parport/parport_atari.c               |  1 -
 drivers/parport/parport_gsc.c                 |  1 -
 drivers/parport/parport_mfc3.c                |  1 -
 drivers/parport/parport_sunbpp.c              |  1 -
 drivers/s390/block/dasd.c                     |  1 -
 drivers/sbus/char/display7seg.c               |  1 -
 drivers/scsi/hpsa.c                           |  1 -
 drivers/scsi/pcmcia/nsp_cs.c                  |  1 -
 drivers/scsi/smartpqi/smartpqi_init.c         |  1 -
 drivers/sh/maple/maple.c                      |  1 -
 drivers/staging/comedi/drivers/vmk80xx.c      |  1 -
 drivers/tee/optee/core.c                      |  1 -
 drivers/tty/serial/icom.c                     |  2 --
 drivers/tty/serial/jsm/jsm_driver.c           |  1 -
 drivers/usb/misc/ldusb.c                      |  1 -
 drivers/watchdog/cpu5wdt.c                    |  1 -
 drivers/watchdog/cpwd.c                       |  1 -
 drivers/watchdog/riowd.c                      |  1 -
 include/linux/module.h                        |  3 --
 net/batman-adv/main.c                         |  1 -
 sound/drivers/aloop.c                         |  1 -
 sound/drivers/dummy.c                         |  1 -
 sound/drivers/mtpav.c                         |  1 -
 sound/drivers/mts64.c                         |  1 -
 sound/drivers/pcsp/pcsp.c                     |  1 -
 sound/drivers/portman2x4.c                    |  1 -
 sound/drivers/serial-u16550.c                 |  1 -
 sound/drivers/virmidi.c                       |  1 -
 sound/isa/ad1816a/ad1816a.c                   |  7 ----
 sound/isa/ad1848/ad1848.c                     |  3 --
 sound/isa/als100.c                            | 11 ------
 sound/isa/azt2320.c                           |  5 ---
 sound/isa/cmi8330.c                           |  1 -
 sound/isa/cs423x/cs4231.c                     |  1 -
 sound/isa/cs423x/cs4236.c                     | 34 -------------------
 sound/isa/es1688/es1688.c                     |  5 ---
 sound/isa/es18xx.c                            | 10 +-----
 sound/isa/gus/gusclassic.c                    |  1 -
 sound/isa/gus/gusextreme.c                    |  1 -
 sound/isa/gus/gusmax.c                        |  1 -
 sound/isa/gus/interwave.c                     |  6 ----
 sound/isa/opl3sa2.c                           |  5 ---
 sound/isa/opti9xx/miro.c                      |  3 --
 sound/isa/opti9xx/opti92x-ad1848.c            |  6 ----
 sound/isa/sb/jazz16.c                         |  3 --
 sound/isa/sb/sb16.c                           |  8 -----
 sound/isa/sb/sb8.c                            |  1 -
 sound/isa/sc6000.c                            |  3 --
 sound/isa/wavefront/wavefront.c               |  1 -
 sound/mips/sgio2audio.c                       |  1 -
 sound/pci/ad1889.c                            |  1 -
 sound/pci/ali5451/ali5451.c                   |  1 -
 sound/pci/als300.c                            |  1 -
 sound/pci/als4000.c                           |  1 -
 sound/pci/atiixp.c                            |  1 -
 sound/pci/atiixp_modem.c                      |  1 -
 sound/pci/au88x0/au88x0.c                     |  2 --
 sound/pci/azt3328.c                           |  1 -
 sound/pci/bt87x.c                             |  2 --
 sound/pci/ca0106/ca0106_main.c                |  1 -
 sound/pci/cmipci.c                            |  4 ---
 sound/pci/cs4281.c                            |  1 -
 sound/pci/cs46xx/cs46xx.c                     |  7 ----
 sound/pci/cs5535audio/cs5535audio.c           |  1 -
 sound/pci/ctxfi/xfi.c                         |  1 -
 sound/pci/echoaudio/echoaudio.c               |  1 -
 sound/pci/emu10k1/emu10k1.c                   |  2 --
 sound/pci/emu10k1/emu10k1x.c                  |  1 -
 sound/pci/ens1370.c                           |  8 -----
 sound/pci/es1938.c                            |  4 ---
 sound/pci/es1968.c                            |  4 ---
 sound/pci/fm801.c                             |  2 --
 sound/pci/hda/hda_intel.c                     | 34 -------------------
 sound/pci/ice1712/ice1712.c                   |  6 ----
 sound/pci/ice1712/ice1724.c                   | 19 -----------
 sound/pci/intel8x0.c                          | 23 -------------
 sound/pci/intel8x0m.c                         | 15 --------
 sound/pci/korg1212/korg1212.c                 |  1 -
 sound/pci/lola/lola.c                         |  1 -
 sound/pci/lx6464es/lx6464es.c                 |  2 --
 sound/pci/maestro3.c                          |  5 ---
 sound/pci/mixart/mixart.c                     |  1 -
 sound/pci/nm256/nm256.c                       |  2 --
 sound/pci/oxygen/oxygen.c                     |  3 --
 sound/pci/oxygen/se6x.c                       |  1 -
 sound/pci/oxygen/virtuoso.c                   |  1 -
 sound/pci/pcxhr/pcxhr.c                       |  1 -
 sound/pci/riptide/riptide.c                   |  1 -
 sound/pci/rme32.c                             |  1 -
 sound/pci/rme96.c                             |  5 ---
 sound/pci/rme9652/hdsp.c                      |  3 --
 sound/pci/rme9652/hdspm.c                     |  1 -
 sound/pci/rme9652/rme9652.c                   |  2 --
 sound/pci/sis7019.c                           |  1 -
 sound/pci/sonicvibes.c                        |  1 -
 sound/pci/trident/trident.c                   | 12 -------
 sound/pci/via82xx.c                           |  1 -
 sound/pci/via82xx_modem.c                     |  1 -
 sound/pci/vx222/vx222.c                       |  1 -
 sound/pci/ymfpci/ymfpci.c                     |  6 ----
 sound/pcmcia/pdaudiocf/pdaudiocf.c            |  1 -
 sound/pcmcia/vx/vxpocket.c                    |  4 ---
 sound/ppc/powermac.c                          |  1 -
 sound/sh/aica.c                               |  1 -
 sound/sh/sh_dac_audio.c                       |  1 -
 sound/sparc/amd7930.c                         |  1 -
 sound/sparc/cs4231.c                          |  1 -
 sound/sparc/dbri.c                            |  1 -
 sound/usb/6fire/chip.c                        |  1 -
 sound/usb/caiaq/device.c                      | 14 --------
 sound/usb/card.c                              |  2 --
 sound/usb/hiface/chip.c                       | 17 ----------
 sound/usb/misc/ua101.c                        |  1 -
 sound/usb/usx2y/usbusx2y.c                    |  1 -
 sound/x86/intel_hdmi_audio.c                  |  1 -
 sound/xen/xen_snd_front.c                     |  1 -
 175 files changed, 1 insertion(+), 480 deletions(-)

diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c
index 1ac8578258af..b42bfdab01a9 100644
--- a/arch/x86/platform/iris/iris.c
+++ b/arch/x86/platform/iris/iris.c
@@ -27,7 +27,6 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Sébastien Hinderer <Sebastien.Hinderer@ens-lyon.org>");
 MODULE_DESCRIPTION("A power_off handler for Iris devices from EuroBraille");
-MODULE_SUPPORTED_DEVICE("Eurobraille/Iris");
 
 static bool force;
 
diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c
index 9a70bee84125..495fd0a1f040 100644
--- a/drivers/atm/fore200e.c
+++ b/drivers/atm/fore200e.c
@@ -100,8 +100,6 @@ static LIST_HEAD(fore200e_boards);
 
 MODULE_AUTHOR("Christophe Lizzi - credits to Uwe Dannowski and Heikki Vatiainen");
 MODULE_DESCRIPTION("FORE Systems 200E-series ATM driver - version " FORE200E_VERSION);
-MODULE_SUPPORTED_DEVICE("PCA-200E, SBA-200E");
-
 
 static const int fore200e_rx_buf_nbr[ BUFFER_SCHEME_NBR ][ BUFFER_MAGN_NBR ] = {
     { BUFFER_S1_NBR, BUFFER_L1_NBR },
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 0b71292d9d5a..4aa9683ee0c1 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -5091,7 +5091,6 @@ module_param(floppy, charp, 0);
 module_param(FLOPPY_IRQ, int, 0);
 module_param(FLOPPY_DMA, int, 0);
 MODULE_AUTHOR("Alain L. Knaff");
-MODULE_SUPPORTED_DEVICE("fd");
 MODULE_LICENSE("GPL");
 
 /* This doesn't actually get used other than for module information */
diff --git a/drivers/bluetooth/btrsi.c b/drivers/bluetooth/btrsi.c
index 3951f7b23840..bea1595f6432 100644
--- a/drivers/bluetooth/btrsi.c
+++ b/drivers/bluetooth/btrsi.c
@@ -194,5 +194,4 @@ module_init(rsi_91x_bt_module_init);
 module_exit(rsi_91x_bt_module_exit);
 MODULE_AUTHOR("Redpine Signals Inc");
 MODULE_DESCRIPTION("RSI BT driver");
-MODULE_SUPPORTED_DEVICE("RSI-BT");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c
index 14b2d8034c51..45ac7ab003ce 100644
--- a/drivers/char/applicom.c
+++ b/drivers/char/applicom.c
@@ -81,9 +81,6 @@ MODULE_DESCRIPTION("Driver for Applicom Profibus card");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_MISCDEV(AC_MINOR);
 
-MODULE_SUPPORTED_DEVICE("ac");
-
-
 static struct applicom_board {
 	unsigned long PhysIO;
 	void __iomem *RamIO;
diff --git a/drivers/char/toshiba.c b/drivers/char/toshiba.c
index aff0a8e44fff..776abbfd85d6 100644
--- a/drivers/char/toshiba.c
+++ b/drivers/char/toshiba.c
@@ -64,7 +64,6 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jonathan Buzzard <jonathan@buzzard.org.uk>");
 MODULE_DESCRIPTION("Toshiba laptop SMM driver");
-MODULE_SUPPORTED_DEVICE("toshiba");
 
 static DEFINE_MUTEX(tosh_mutex);
 static int tosh_fn;
diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c
index 430dc6975004..da8963a9f044 100644
--- a/drivers/input/joydev.c
+++ b/drivers/input/joydev.c
@@ -26,7 +26,6 @@
 
 MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>");
 MODULE_DESCRIPTION("Joystick device interfaces");
-MODULE_SUPPORTED_DEVICE("input/js");
 MODULE_LICENSE("GPL");
 
 #define JOYDEV_MINOR_BASE	0
diff --git a/drivers/media/firewire/firedtv-fw.c b/drivers/media/firewire/firedtv-fw.c
index 8a8585261bb8..5f6e97a8d1c0 100644
--- a/drivers/media/firewire/firedtv-fw.c
+++ b/drivers/media/firewire/firedtv-fw.c
@@ -430,4 +430,3 @@ MODULE_AUTHOR("Andreas Monitzer <andy@monitzer.com>");
 MODULE_AUTHOR("Ben Backx <ben@bbackx.com>");
 MODULE_DESCRIPTION("FireDTV DVB Driver");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("FireDTV DVB");
diff --git a/drivers/media/pci/cx18/cx18-alsa-main.c b/drivers/media/pci/cx18/cx18-alsa-main.c
index 692b95a685d1..9a82e68303b6 100644
--- a/drivers/media/pci/cx18/cx18-alsa-main.c
+++ b/drivers/media/pci/cx18/cx18-alsa-main.c
@@ -41,7 +41,6 @@ MODULE_PARM_DESC(debug,
 
 MODULE_AUTHOR("Andy Walls");
 MODULE_DESCRIPTION("CX23418 ALSA Interface");
-MODULE_SUPPORTED_DEVICE("CX23418 MPEG2 encoder");
 MODULE_LICENSE("GPL");
 
 MODULE_VERSION(CX18_VERSION);
diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c
index 95aed00f353b..f2440eb38820 100644
--- a/drivers/media/pci/cx18/cx18-driver.c
+++ b/drivers/media/pci/cx18/cx18-driver.c
@@ -232,7 +232,6 @@ MODULE_PARM_DESC(cx18_first_minor,
 
 MODULE_AUTHOR("Hans Verkuil");
 MODULE_DESCRIPTION("CX23418 driver");
-MODULE_SUPPORTED_DEVICE("CX23418 MPEG2 encoder");
 MODULE_LICENSE("GPL");
 
 MODULE_VERSION(CX18_VERSION);
diff --git a/drivers/media/pci/cx25821/cx25821-alsa.c b/drivers/media/pci/cx25821/cx25821-alsa.c
index 608fbaf0f659..8797d85a6b0a 100644
--- a/drivers/media/pci/cx25821/cx25821-alsa.c
+++ b/drivers/media/pci/cx25821/cx25821-alsa.c
@@ -104,7 +104,6 @@ MODULE_PARM_DESC(index, "Index value for cx25821 capture interface(s).");
 MODULE_DESCRIPTION("ALSA driver module for cx25821 based capture cards");
 MODULE_AUTHOR("Hiep Huynh");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Conexant,25821}");	/* "{{Conexant,23881}," */
 
 static unsigned int debug;
 module_param(debug, int, 0644);
diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c
index 95e0cbb1277d..c83814c052d3 100644
--- a/drivers/media/pci/cx88/cx88-alsa.c
+++ b/drivers/media/pci/cx88/cx88-alsa.c
@@ -98,7 +98,6 @@ MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
 MODULE_LICENSE("GPL v2");
 MODULE_VERSION(CX88_VERSION);
 
-MODULE_SUPPORTED_DEVICE("{{Conexant,23881},{{Conexant,23882},{{Conexant,23883}");
 static unsigned int debug;
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "enable debug messages");
diff --git a/drivers/media/pci/ivtv/ivtv-alsa-main.c b/drivers/media/pci/ivtv/ivtv-alsa-main.c
index 39029b8e12c9..4cefdb2e4d40 100644
--- a/drivers/media/pci/ivtv/ivtv-alsa-main.c
+++ b/drivers/media/pci/ivtv/ivtv-alsa-main.c
@@ -38,7 +38,6 @@ MODULE_PARM_DESC(index,
 
 MODULE_AUTHOR("Andy Walls");
 MODULE_DESCRIPTION("CX23415/CX23416 ALSA Interface");
-MODULE_SUPPORTED_DEVICE("CX23415/CX23416 MPEG2 encoder");
 MODULE_LICENSE("GPL");
 
 MODULE_VERSION(IVTV_VERSION);
diff --git a/drivers/media/pci/ivtv/ivtv-driver.c b/drivers/media/pci/ivtv/ivtv-driver.c
index 6e448cb3b51c..942b8c266f50 100644
--- a/drivers/media/pci/ivtv/ivtv-driver.c
+++ b/drivers/media/pci/ivtv/ivtv-driver.c
@@ -275,9 +275,6 @@ MODULE_PARM_DESC(ivtv_first_minor, "Set device node number assigned to first car
 
 MODULE_AUTHOR("Kevin Thayer, Chris Kennedy, Hans Verkuil");
 MODULE_DESCRIPTION("CX23415/CX23416 driver");
-MODULE_SUPPORTED_DEVICE
-    ("CX23415/CX23416 MPEG2 encoder (WinTV PVR-150/250/350/500,\n"
-		"\t\t\tYuan MPG series and similar)");
 MODULE_LICENSE("GPL");
 
 MODULE_VERSION(IVTV_VERSION);
diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c
index 336df65c8af1..524912f20d9f 100644
--- a/drivers/media/pci/sta2x11/sta2x11_vip.c
+++ b/drivers/media/pci/sta2x11/sta2x11_vip.c
@@ -1269,6 +1269,5 @@ late_initcall_sync(sta2x11_vip_init_module);
 MODULE_DESCRIPTION("STA2X11 Video Input Port driver");
 MODULE_AUTHOR("Wind River");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("sta2x11 video input");
 MODULE_VERSION(DRV_VERSION);
 MODULE_DEVICE_TABLE(pci, sta2x11_vip_pci_tbl);
diff --git a/drivers/media/platform/atmel/atmel-isi.c b/drivers/media/platform/atmel/atmel-isi.c
index 0514be6153df..e392b3efe363 100644
--- a/drivers/media/platform/atmel/atmel-isi.c
+++ b/drivers/media/platform/atmel/atmel-isi.c
@@ -1363,4 +1363,3 @@ module_platform_driver(atmel_isi_driver);
 MODULE_AUTHOR("Josh Wu <josh.wu@atmel.com>");
 MODULE_DESCRIPTION("The V4L2 driver for Atmel Linux");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("video");
diff --git a/drivers/media/platform/atmel/atmel-sama5d2-isc.c b/drivers/media/platform/atmel/atmel-sama5d2-isc.c
index 0b78fecfd2a8..61d9885765f4 100644
--- a/drivers/media/platform/atmel/atmel-sama5d2-isc.c
+++ b/drivers/media/platform/atmel/atmel-sama5d2-isc.c
@@ -330,4 +330,3 @@ module_platform_driver(atmel_isc_driver);
 MODULE_AUTHOR("Songjun Wu");
 MODULE_DESCRIPTION("The V4L2 driver for Atmel-ISC");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("video");
diff --git a/drivers/media/platform/marvell-ccic/cafe-driver.c b/drivers/media/platform/marvell-ccic/cafe-driver.c
index 9c94a8b58b7c..baac86f3d153 100644
--- a/drivers/media/platform/marvell-ccic/cafe-driver.c
+++ b/drivers/media/platform/marvell-ccic/cafe-driver.c
@@ -44,10 +44,6 @@
 MODULE_AUTHOR("Jonathan Corbet <corbet@lwn.net>");
 MODULE_DESCRIPTION("Marvell 88ALP01 CMOS Camera Controller driver");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("Video");
-
-
-
 
 struct cafe_camera {
 	int registered;			/* Fully initialized? */
diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index bbcc2254fa2e..d9b4ad0abf0c 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -2149,4 +2149,3 @@ MODULE_AUTHOR("Yannick Fertre <yannick.fertre@st.com>");
 MODULE_AUTHOR("Hugues Fruchet <hugues.fruchet@st.com>");
 MODULE_DESCRIPTION("STMicroelectronics STM32 Digital Camera Memory Interface driver");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("video");
diff --git a/drivers/media/usb/cpia2/cpia2_v4l.c b/drivers/media/usb/cpia2/cpia2_v4l.c
index e488e7870f42..69d5c628a797 100644
--- a/drivers/media/usb/cpia2/cpia2_v4l.c
+++ b/drivers/media/usb/cpia2/cpia2_v4l.c
@@ -56,7 +56,6 @@ MODULE_PARM_DESC(flicker_mode, "Flicker frequency (0 (disabled), " __stringify(5
 
 MODULE_AUTHOR("Steve Miller (STMicroelectronics) <steve.miller@st.com>");
 MODULE_DESCRIPTION("V4L-driver for STMicroelectronics CPiA2 based cameras");
-MODULE_SUPPORTED_DEVICE("video");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(CPIA_VERSION);
 
diff --git a/drivers/media/usb/tm6000/tm6000-alsa.c b/drivers/media/usb/tm6000/tm6000-alsa.c
index 3a2df36ef1db..a19a46770c2b 100644
--- a/drivers/media/usb/tm6000/tm6000-alsa.c
+++ b/drivers/media/usb/tm6000/tm6000-alsa.c
@@ -51,7 +51,6 @@ MODULE_PARM_DESC(index, "Index value for tm6000x capture interface(s).");
 MODULE_DESCRIPTION("ALSA driver module for tm5600/tm6000/tm6010 based TV cards");
 MODULE_AUTHOR("Mauro Carvalho Chehab");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{Trident,tm5600},{{Trident,tm6000},{{Trident,tm6010}");
 static unsigned int debug;
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "enable debug messages");
diff --git a/drivers/media/usb/tm6000/tm6000-dvb.c b/drivers/media/usb/tm6000/tm6000-dvb.c
index 293a460f4616..4990fa886d7a 100644
--- a/drivers/media/usb/tm6000/tm6000-dvb.c
+++ b/drivers/media/usb/tm6000/tm6000-dvb.c
@@ -23,8 +23,6 @@ MODULE_DESCRIPTION("DVB driver extension module for tm5600/6000/6010 based TV ca
 MODULE_AUTHOR("Mauro Carvalho Chehab");
 MODULE_LICENSE("GPL");
 
-MODULE_SUPPORTED_DEVICE("{{Trident, tm5600},{{Trident, tm6000},{{Trident, tm6010}");
-
 static int debug;
 
 module_param(debug, int, 0644);
diff --git a/drivers/mtd/maps/sun_uflash.c b/drivers/mtd/maps/sun_uflash.c
index eb7258293256..f9cfb084c029 100644
--- a/drivers/mtd/maps/sun_uflash.c
+++ b/drivers/mtd/maps/sun_uflash.c
@@ -32,7 +32,6 @@
 
 MODULE_AUTHOR("Eric Brower <ebrower@usa.net>");
 MODULE_DESCRIPTION("User-programmable flash device on Sun Microsystems boardsets");
-MODULE_SUPPORTED_DEVICE(DRIVER_NAME);
 MODULE_LICENSE("GPL");
 MODULE_VERSION("2.1");
 
diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index 0df1cdfa6835..1df3c4b54f03 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -21,7 +21,6 @@
 
 MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>");
 MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCIe/M.2 FD family cards");
-MODULE_SUPPORTED_DEVICE("PEAK PCAN PCIe/M.2 FD CAN cards");
 MODULE_LICENSE("GPL v2");
 
 #define PCIEFD_DRV_NAME		"peak_pciefd"
diff --git a/drivers/net/can/sja1000/ems_pci.c b/drivers/net/can/sja1000/ems_pci.c
index 6f88c9932920..4ab91759a5c6 100644
--- a/drivers/net/can/sja1000/ems_pci.c
+++ b/drivers/net/can/sja1000/ems_pci.c
@@ -21,7 +21,6 @@
 
 MODULE_AUTHOR("Sebastian Haas <haas@ems-wuenche.com>");
 MODULE_DESCRIPTION("Socket-CAN driver for EMS CPC-PCI/PCIe/104P CAN cards");
-MODULE_SUPPORTED_DEVICE("EMS CPC-PCI/PCIe/104P CAN card");
 MODULE_LICENSE("GPL v2");
 
 #define EMS_PCI_V1_MAX_CHAN 2
diff --git a/drivers/net/can/sja1000/ems_pcmcia.c b/drivers/net/can/sja1000/ems_pcmcia.c
index 770304eaef95..e21b169c14c0 100644
--- a/drivers/net/can/sja1000/ems_pcmcia.c
+++ b/drivers/net/can/sja1000/ems_pcmcia.c
@@ -21,7 +21,6 @@
 
 MODULE_AUTHOR("Markus Plessing <plessing@ems-wuensche.com>");
 MODULE_DESCRIPTION("Socket-CAN driver for EMS CPC-CARD cards");
-MODULE_SUPPORTED_DEVICE("EMS CPC-CARD CAN card");
 MODULE_LICENSE("GPL v2");
 
 #define EMS_PCMCIA_MAX_CHAN 2
diff --git a/drivers/net/can/sja1000/kvaser_pci.c b/drivers/net/can/sja1000/kvaser_pci.c
index 0ea6b711c07b..95fe9ee1ce32 100644
--- a/drivers/net/can/sja1000/kvaser_pci.c
+++ b/drivers/net/can/sja1000/kvaser_pci.c
@@ -33,7 +33,6 @@
 
 MODULE_AUTHOR("Per Dalen <per.dalen@cnw.se>");
 MODULE_DESCRIPTION("Socket-CAN driver for KVASER PCAN PCI cards");
-MODULE_SUPPORTED_DEVICE("KVASER PCAN PCI CAN card");
 MODULE_LICENSE("GPL v2");
 
 #define MAX_NO_OF_CHANNELS        4 /* max no of channels on a single card */
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 4713921bd511..84eac8cb8686 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -24,8 +24,6 @@
 
 MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>");
 MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCI family cards");
-MODULE_SUPPORTED_DEVICE("PEAK PCAN PCI/PCIe/PCIeC miniPCI CAN cards");
-MODULE_SUPPORTED_DEVICE("PEAK PCAN miniPCIe/cPCI PC/104+ PCI/104e CAN Cards");
 MODULE_LICENSE("GPL v2");
 
 #define DRV_NAME  "peak_pci"
diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c
index cf951a783078..131a084c3535 100644
--- a/drivers/net/can/sja1000/peak_pcmcia.c
+++ b/drivers/net/can/sja1000/peak_pcmcia.c
@@ -22,7 +22,6 @@
 MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>");
 MODULE_DESCRIPTION("CAN driver for PEAK-System PCAN-PC Cards");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("PEAK PCAN-PC Card");
 
 /* PEAK-System PCMCIA driver name */
 #define PCC_NAME		"peak_pcmcia"
diff --git a/drivers/net/can/sja1000/plx_pci.c b/drivers/net/can/sja1000/plx_pci.c
index 85679588ef73..5de1ebb0c6f0 100644
--- a/drivers/net/can/sja1000/plx_pci.c
+++ b/drivers/net/can/sja1000/plx_pci.c
@@ -25,18 +25,6 @@
 MODULE_AUTHOR("Pavel Cheblakov <P.B.Cheblakov@inp.nsk.su>");
 MODULE_DESCRIPTION("Socket-CAN driver for PLX90xx PCI-bridge cards with "
 		   "the SJA1000 chips");
-MODULE_SUPPORTED_DEVICE("Adlink PCI-7841/cPCI-7841, "
-			"Adlink PCI-7841/cPCI-7841 SE, "
-			"Marathon CAN-bus-PCI, "
-			"Marathon CAN-bus-PCIe, "
-			"TEWS TECHNOLOGIES TPMC810, "
-			"esd CAN-PCI/CPCI/PCI104/200, "
-			"esd CAN-PCI/PMC/266, "
-			"esd CAN-PCIe/2000, "
-			"Connect Tech Inc. CANpro/104-Plus Opto (CRG001), "
-			"IXXAT PC-I 04/PCI, "
-			"ELCUS CAN-200-PCI, "
-			"ASEM DUAL CAN-RAW")
 MODULE_LICENSE("GPL v2");
 
 #define PLX_PCI_MAX_CHAN 2
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index e6c1e5d33924..e393e8457d77 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -18,8 +18,6 @@
 
 #include "pcan_usb_core.h"
 
-MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB adapter");
-
 /* PCAN-USB Endpoints */
 #define PCAN_USB_EP_CMDOUT		1
 #define PCAN_USB_EP_CMDIN		(PCAN_USB_EP_CMDOUT | USB_DIR_IN)
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index f347ecc79aef..bae078579c0d 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -16,9 +16,6 @@
 #include "pcan_usb_core.h"
 #include "pcan_usb_pro.h"
 
-MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB FD adapter");
-MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro FD adapter");
-
 #define PCAN_USBPROFD_CHANNEL_COUNT	2
 #define PCAN_USBFD_CHANNEL_COUNT	1
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index 275087c39602..18fa180ecc81 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -17,8 +17,6 @@
 #include "pcan_usb_core.h"
 #include "pcan_usb_pro.h"
 
-MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro adapter");
-
 #define PCAN_USBPRO_CHANNEL_COUNT	2
 
 /* PCAN-USB Pro adapter internal clock (MHz) */
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index 36eeb80406f2..4690c6a59054 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -2167,7 +2167,6 @@ static void __exit scc_cleanup_driver(void)
 
 MODULE_AUTHOR("Joerg Reuter <jreuter@yaina.de>");
 MODULE_DESCRIPTION("AX.25 Device Driver for Z8530 based HDLC cards");
-MODULE_SUPPORTED_DEVICE("Z8530 based SCC cards for Amateur Radio");
 MODULE_LICENSE("GPL");
 module_init(scc_init_driver);
 module_exit(scc_cleanup_driver);
diff --git a/drivers/net/wireless/admtek/adm8211.c b/drivers/net/wireless/admtek/adm8211.c
index c41e72508d3d..2db9c948c0fc 100644
--- a/drivers/net/wireless/admtek/adm8211.c
+++ b/drivers/net/wireless/admtek/adm8211.c
@@ -28,7 +28,6 @@
 MODULE_AUTHOR("Michael Wu <flamingice@sourmilk.net>");
 MODULE_AUTHOR("Jouni Malinen <j@w1.fi>");
 MODULE_DESCRIPTION("Driver for IEEE 802.11b wireless cards based on ADMtek ADM8211");
-MODULE_SUPPORTED_DEVICE("ADM8211");
 MODULE_LICENSE("GPL");
 
 static unsigned int tx_ring_size __read_mostly = 16;
diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index 4c6e57f9976d..cef17f33c69e 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -90,7 +90,6 @@ MODULE_PARM_DESC(no_hw_rfkill_switch, "Ignore the GPIO RFKill switch state");
 MODULE_AUTHOR("Jiri Slaby");
 MODULE_AUTHOR("Nick Kossifidis");
 MODULE_DESCRIPTION("Support for 5xxx series of Atheros 802.11 wireless LAN cards.");
-MODULE_SUPPORTED_DEVICE("Atheros 5xxx WLAN cards");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static int ath5k_init(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index b66eeb577272..5abc2a5526ec 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -34,7 +34,6 @@ static bool ath9k_hw_set_reset_reg(struct ath_hw *ah, u32 type);
 
 MODULE_AUTHOR("Atheros Communications");
 MODULE_DESCRIPTION("Support for Atheros 802.11n wireless LAN cards.");
-MODULE_SUPPORTED_DEVICE("Atheros 802.11n WLAN cards");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static void ath9k_hw_set_clockrate(struct ath_hw *ah)
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index 42a208787f5a..01f9c26f9bf3 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -37,7 +37,6 @@ static char *dev_info = "ath9k";
 
 MODULE_AUTHOR("Atheros Communications");
 MODULE_DESCRIPTION("Support for Atheros 802.11n wireless LAN cards.");
-MODULE_SUPPORTED_DEVICE("Atheros 802.11n WLAN cards");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static unsigned int ath9k_debug = ATH_DBG_DEFAULT;
diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index 707fe66727f8..febce4e8b3dd 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -75,7 +75,6 @@
 MODULE_AUTHOR("Simon Kelley");
 MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards.");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("Atmel at76c50x wireless cards");
 
 /* The name of the firmware file to be loaded
    over-rides any automatic selection */
diff --git a/drivers/net/wireless/atmel/atmel_cs.c b/drivers/net/wireless/atmel/atmel_cs.c
index 368eebefa741..453bb84cb338 100644
--- a/drivers/net/wireless/atmel/atmel_cs.c
+++ b/drivers/net/wireless/atmel/atmel_cs.c
@@ -57,7 +57,6 @@
 MODULE_AUTHOR("Simon Kelley");
 MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards.");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("Atmel at76c50x PCMCIA cards");
 
 /*====================================================================*/
 
diff --git a/drivers/net/wireless/atmel/atmel_pci.c b/drivers/net/wireless/atmel/atmel_pci.c
index 47f7ccb32414..f428dc79d916 100644
--- a/drivers/net/wireless/atmel/atmel_pci.c
+++ b/drivers/net/wireless/atmel/atmel_pci.c
@@ -16,7 +16,6 @@
 MODULE_AUTHOR("Simon Kelley");
 MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards.");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("Atmel at76c506 PCI wireless cards");
 
 static const struct pci_device_id card_ids[] = {
 	{ 0x1114, 0x0506, PCI_ANY_ID, PCI_ANY_ID },
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
index 818e523f6025..39f3af2d0439 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
@@ -87,7 +87,6 @@ static int n_adapters_found;
 
 MODULE_AUTHOR("Broadcom Corporation");
 MODULE_DESCRIPTION("Broadcom 802.11n wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Broadcom 802.11n WLAN cards");
 MODULE_LICENSE("Dual BSD/GPL");
 /* This needs to be adjusted when brcms_firmwares changes */
 MODULE_FIRMWARE("brcm/bcm43xx-0.fw");
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmutil/utils.c b/drivers/net/wireless/broadcom/brcm80211/brcmutil/utils.c
index 4c84c3001c3f..e87e68cc46e2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmutil/utils.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmutil/utils.c
@@ -12,7 +12,6 @@
 
 MODULE_AUTHOR("Broadcom Corporation");
 MODULE_DESCRIPTION("Broadcom 802.11n wireless LAN driver utilities.");
-MODULE_SUPPORTED_DEVICE("Broadcom 802.11n WLAN cards");
 MODULE_LICENSE("Dual BSD/GPL");
 
 struct sk_buff *brcmu_pkt_buf_get_skb(uint len)
diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index e35e1380ae43..60db38c38960 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -251,7 +251,6 @@ MODULE_AUTHOR("Benjamin Reed");
 MODULE_DESCRIPTION("Support for Cisco/Aironet 802.11 wireless ethernet cards.  "
 		   "Direct support for ISA/PCI/MPI cards and support for PCMCIA when used with airo_cs.");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_SUPPORTED_DEVICE("Aironet 4500, 4800 and Cisco 340/350");
 module_param_hw_array(io, int, ioport, NULL, 0);
 module_param_hw_array(irq, int, irq, NULL, 0);
 module_param_array(rates, int, NULL, 0);
diff --git a/drivers/net/wireless/cisco/airo_cs.c b/drivers/net/wireless/cisco/airo_cs.c
index 3718f958c0fc..fcfe4c6d62f0 100644
--- a/drivers/net/wireless/cisco/airo_cs.c
+++ b/drivers/net/wireless/cisco/airo_cs.c
@@ -47,7 +47,6 @@ MODULE_DESCRIPTION("Support for Cisco/Aironet 802.11 wireless ethernet "
 		   "cards.  This is the module that links the PCMCIA card "
 		   "with the airo module.");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_SUPPORTED_DEVICE("Aironet 4500, 4800 and Cisco 340 PCMCIA cards");
 
 /*====================================================================*/
 
diff --git a/drivers/net/wireless/intersil/hostap/hostap_cs.c b/drivers/net/wireless/intersil/hostap/hostap_cs.c
index 1a748670835a..ec7db2badc40 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_cs.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_cs.c
@@ -26,7 +26,6 @@ static char *dev_info = "hostap_cs";
 MODULE_AUTHOR("Jouni Malinen");
 MODULE_DESCRIPTION("Support for Intersil Prism2-based 802.11 wireless LAN "
 		   "cards (PC Card).");
-MODULE_SUPPORTED_DEVICE("Intersil Prism2-based WLAN cards (PC Card)");
 MODULE_LICENSE("GPL");
 
 
diff --git a/drivers/net/wireless/intersil/hostap/hostap_pci.c b/drivers/net/wireless/intersil/hostap/hostap_pci.c
index 101887e6bd0f..52d77506effd 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_pci.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_pci.c
@@ -27,7 +27,6 @@ static char *dev_info = "hostap_pci";
 MODULE_AUTHOR("Jouni Malinen");
 MODULE_DESCRIPTION("Support for Intersil Prism2.5-based 802.11 wireless LAN "
 		   "PCI cards.");
-MODULE_SUPPORTED_DEVICE("Intersil Prism2.5-based WLAN PCI cards");
 MODULE_LICENSE("GPL");
 
 
diff --git a/drivers/net/wireless/intersil/hostap/hostap_plx.c b/drivers/net/wireless/intersil/hostap/hostap_plx.c
index 841cfc68ce84..58247290fcbc 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_plx.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_plx.c
@@ -30,7 +30,6 @@ static char *dev_info = "hostap_plx";
 MODULE_AUTHOR("Jouni Malinen");
 MODULE_DESCRIPTION("Support for Intersil Prism2-based 802.11 wireless LAN "
 		   "cards (PLX).");
-MODULE_SUPPORTED_DEVICE("Intersil Prism2-based WLAN cards (PLX)");
 MODULE_LICENSE("GPL");
 
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c
index 8f860c14da58..dec6ffdf07c4 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c
@@ -1821,7 +1821,6 @@ static const struct pci_device_id rt2400pci_device_table[] = {
 MODULE_AUTHOR(DRV_PROJECT);
 MODULE_VERSION(DRV_VERSION);
 MODULE_DESCRIPTION("Ralink RT2400 PCI & PCMCIA Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2460 PCI & PCMCIA chipset based cards");
 MODULE_DEVICE_TABLE(pci, rt2400pci_device_table);
 MODULE_LICENSE("GPL");
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c
index e940443c52ad..8faa0a80e73a 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c
@@ -2119,7 +2119,6 @@ static const struct pci_device_id rt2500pci_device_table[] = {
 MODULE_AUTHOR(DRV_PROJECT);
 MODULE_VERSION(DRV_VERSION);
 MODULE_DESCRIPTION("Ralink RT2500 PCI & PCMCIA Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2560 PCI & PCMCIA chipset based cards");
 MODULE_DEVICE_TABLE(pci, rt2500pci_device_table);
 MODULE_LICENSE("GPL");
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c
index fce05fc88aaf..bb5ed6630645 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c
@@ -1956,7 +1956,6 @@ static const struct usb_device_id rt2500usb_device_table[] = {
 MODULE_AUTHOR(DRV_PROJECT);
 MODULE_VERSION(DRV_VERSION);
 MODULE_DESCRIPTION("Ralink RT2500 USB Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2570 USB chipset based cards");
 MODULE_DEVICE_TABLE(usb, rt2500usb_device_table);
 MODULE_LICENSE("GPL");
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800pci.c b/drivers/net/wireless/ralink/rt2x00/rt2800pci.c
index 9a33baaa6184..1fde0e767ce3 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800pci.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800pci.c
@@ -439,7 +439,6 @@ static const struct pci_device_id rt2800pci_device_table[] = {
 MODULE_AUTHOR(DRV_PROJECT);
 MODULE_VERSION(DRV_VERSION);
 MODULE_DESCRIPTION("Ralink RT2800 PCI & PCMCIA Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2860 PCI & PCMCIA chipset based cards");
 MODULE_FIRMWARE(FIRMWARE_RT2860);
 MODULE_DEVICE_TABLE(pci, rt2800pci_device_table);
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800usb.c b/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
index 36ac18ca8082..b5c67f656cfd 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
@@ -1248,7 +1248,6 @@ static const struct usb_device_id rt2800usb_device_table[] = {
 MODULE_AUTHOR(DRV_PROJECT);
 MODULE_VERSION(DRV_VERSION);
 MODULE_DESCRIPTION("Ralink RT2800 USB Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2870 USB chipset based cards");
 MODULE_DEVICE_TABLE(usb, rt2800usb_device_table);
 MODULE_FIRMWARE(FIRMWARE_RT2870);
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/ralink/rt2x00/rt61pci.c b/drivers/net/wireless/ralink/rt2x00/rt61pci.c
index 02da5dd37ddd..82cfc2aadc2b 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt61pci.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt61pci.c
@@ -2993,8 +2993,6 @@ static const struct pci_device_id rt61pci_device_table[] = {
 MODULE_AUTHOR(DRV_PROJECT);
 MODULE_VERSION(DRV_VERSION);
 MODULE_DESCRIPTION("Ralink RT61 PCI & PCMCIA Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2561, RT2561s & RT2661 "
-			"PCI & PCMCIA chipset based cards");
 MODULE_DEVICE_TABLE(pci, rt61pci_device_table);
 MODULE_FIRMWARE(FIRMWARE_RT2561);
 MODULE_FIRMWARE(FIRMWARE_RT2561s);
diff --git a/drivers/net/wireless/ralink/rt2x00/rt73usb.c b/drivers/net/wireless/ralink/rt2x00/rt73usb.c
index e69793773d87..5ff2c740c3ea 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt73usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt73usb.c
@@ -2513,7 +2513,6 @@ static const struct usb_device_id rt73usb_device_table[] = {
 MODULE_AUTHOR(DRV_PROJECT);
 MODULE_VERSION(DRV_VERSION);
 MODULE_DESCRIPTION("Ralink RT73 USB Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2571W & RT2671 USB chipset based cards");
 MODULE_DEVICE_TABLE(usb, rt73usb_device_table);
 MODULE_FIRMWARE(FIRMWARE_RT2571);
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c
index 9a3d2439a8e7..d98483298555 100644
--- a/drivers/net/wireless/rsi/rsi_91x_main.c
+++ b/drivers/net/wireless/rsi/rsi_91x_main.c
@@ -441,6 +441,5 @@ module_init(rsi_91x_hal_module_init);
 module_exit(rsi_91x_hal_module_exit);
 MODULE_AUTHOR("Redpine Signals Inc");
 MODULE_DESCRIPTION("Station driver for RSI 91x devices");
-MODULE_SUPPORTED_DEVICE("RSI-91x");
 MODULE_VERSION("0.1");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c
index 592e9dadcb55..fe0287b22a25 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c
@@ -1571,7 +1571,6 @@ module_exit(rsi_module_exit);
 
 MODULE_AUTHOR("Redpine Signals Inc");
 MODULE_DESCRIPTION("Common SDIO layer for RSI drivers");
-MODULE_SUPPORTED_DEVICE("RSI-91x");
 MODULE_DEVICE_TABLE(sdio, rsi_dev_table);
 MODULE_FIRMWARE(FIRMWARE_RSI9113);
 MODULE_VERSION("0.1");
diff --git a/drivers/net/wireless/rsi/rsi_91x_usb.c b/drivers/net/wireless/rsi/rsi_91x_usb.c
index a4a533c2a783..3fbe2a3c1455 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb.c
@@ -928,7 +928,6 @@ module_usb_driver(rsi_driver);
 
 MODULE_AUTHOR("Redpine Signals Inc");
 MODULE_DESCRIPTION("Common USB layer for RSI drivers");
-MODULE_SUPPORTED_DEVICE("RSI-91x");
 MODULE_DEVICE_TABLE(usb, rsi_dev_table);
 MODULE_FIRMWARE(FIRMWARE_RSI9113);
 MODULE_VERSION("0.1");
diff --git a/drivers/parport/parport_amiga.c b/drivers/parport/parport_amiga.c
index 1e88bcfe0d7b..84d5701d606c 100644
--- a/drivers/parport/parport_amiga.c
+++ b/drivers/parport/parport_amiga.c
@@ -241,6 +241,5 @@ module_platform_driver_probe(amiga_parallel_driver, amiga_parallel_probe);
 
 MODULE_AUTHOR("Joerg Dorchain <joerg@dorchain.net>");
 MODULE_DESCRIPTION("Parport Driver for Amiga builtin Port");
-MODULE_SUPPORTED_DEVICE("Amiga builtin Parallel Port");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:amiga-parallel");
diff --git a/drivers/parport/parport_atari.c b/drivers/parport/parport_atari.c
index 2ff0fe053e6e..1623f010cdcc 100644
--- a/drivers/parport/parport_atari.c
+++ b/drivers/parport/parport_atari.c
@@ -218,7 +218,6 @@ static void __exit parport_atari_exit(void)
 
 MODULE_AUTHOR("Andreas Schwab");
 MODULE_DESCRIPTION("Parport Driver for Atari builtin Port");
-MODULE_SUPPORTED_DEVICE("Atari builtin Parallel Port");
 MODULE_LICENSE("GPL");
 
 module_init(parport_atari_init)
diff --git a/drivers/parport/parport_gsc.c b/drivers/parport/parport_gsc.c
index 9228e8f90309..1e43b3f399a8 100644
--- a/drivers/parport/parport_gsc.c
+++ b/drivers/parport/parport_gsc.c
@@ -41,7 +41,6 @@
 
 MODULE_AUTHOR("Helge Deller <deller@gmx.de>");
 MODULE_DESCRIPTION("HP-PARISC PC-style parallel port driver");
-MODULE_SUPPORTED_DEVICE("integrated PC-style parallel port");
 MODULE_LICENSE("GPL");
 
 
diff --git a/drivers/parport/parport_mfc3.c b/drivers/parport/parport_mfc3.c
index d6bbe8446301..f4d0da741e85 100644
--- a/drivers/parport/parport_mfc3.c
+++ b/drivers/parport/parport_mfc3.c
@@ -359,7 +359,6 @@ static void __exit parport_mfc3_exit(void)
 
 MODULE_AUTHOR("Joerg Dorchain <joerg@dorchain.net>");
 MODULE_DESCRIPTION("Parport Driver for Multiface 3 expansion cards Parallel Port");
-MODULE_SUPPORTED_DEVICE("Multiface 3 Parallel Port");
 MODULE_LICENSE("GPL");
 
 module_init(parport_mfc3_init)
diff --git a/drivers/parport/parport_sunbpp.c b/drivers/parport/parport_sunbpp.c
index e840c1b5ab90..865fc41dbb6c 100644
--- a/drivers/parport/parport_sunbpp.c
+++ b/drivers/parport/parport_sunbpp.c
@@ -377,6 +377,5 @@ module_platform_driver(bpp_sbus_driver);
 
 MODULE_AUTHOR("Derrick J Brashear");
 MODULE_DESCRIPTION("Parport Driver for Sparc bidirectional Port");
-MODULE_SUPPORTED_DEVICE("Sparc Bidirectional Parallel Port");
 MODULE_VERSION("2.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index ba9ce4e0d30a..3a945abf268c 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -63,7 +63,6 @@ void dasd_int_handler(struct ccw_device *, unsigned long, struct irb *);
 MODULE_AUTHOR("Holger Smolinski <Holger.Smolinski@de.ibm.com>");
 MODULE_DESCRIPTION("Linux on S/390 DASD device driver,"
 		   " Copyright IBM Corp. 2000");
-MODULE_SUPPORTED_DEVICE("dasd");
 MODULE_LICENSE("GPL");
 
 /*
diff --git a/drivers/sbus/char/display7seg.c b/drivers/sbus/char/display7seg.c
index 00e72b97d0b6..d93595b39afa 100644
--- a/drivers/sbus/char/display7seg.c
+++ b/drivers/sbus/char/display7seg.c
@@ -50,7 +50,6 @@ MODULE_PARM_DESC(sol_compat,
 MODULE_AUTHOR("Eric Brower <ebrower@usa.net>");
 MODULE_DESCRIPTION("7-Segment Display driver for Sun Microsystems CP1400/1500");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("d7s");
 
 struct d7s {
 	void __iomem	*regs;
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 38369766511c..f135a10f582b 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -80,7 +80,6 @@
 MODULE_AUTHOR("Hewlett-Packard Company");
 MODULE_DESCRIPTION("Driver for HP Smart Array Controller version " \
 	HPSA_DRIVER_VERSION);
-MODULE_SUPPORTED_DEVICE("HP Smart Array Controllers");
 MODULE_VERSION(HPSA_DRIVER_VERSION);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("cciss");
diff --git a/drivers/scsi/pcmcia/nsp_cs.c b/drivers/scsi/pcmcia/nsp_cs.c
index 5d5f50d6a02d..ac89002646a3 100644
--- a/drivers/scsi/pcmcia/nsp_cs.c
+++ b/drivers/scsi/pcmcia/nsp_cs.c
@@ -55,7 +55,6 @@
 
 MODULE_AUTHOR("YOKOTA Hiroshi <yokota@netlab.is.tsukuba.ac.jp>");
 MODULE_DESCRIPTION("WorkBit NinjaSCSI-3 / NinjaSCSI-32Bi(16bit) PCMCIA SCSI host adapter module");
-MODULE_SUPPORTED_DEVICE("sd,sr,sg,st");
 MODULE_LICENSE("GPL");
 
 #include "nsp_io.h"
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index c53f456fbd09..a1dacb6e993e 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -48,7 +48,6 @@
 MODULE_AUTHOR("Microsemi");
 MODULE_DESCRIPTION("Driver for Microsemi Smart Family Controller version "
 	DRIVER_VERSION);
-MODULE_SUPPORTED_DEVICE("Microsemi Smart Family Controllers");
 MODULE_VERSION(DRIVER_VERSION);
 MODULE_LICENSE("GPL");
 
diff --git a/drivers/sh/maple/maple.c b/drivers/sh/maple/maple.c
index e5d7fb81ad66..bd0fbcdbdefe 100644
--- a/drivers/sh/maple/maple.c
+++ b/drivers/sh/maple/maple.c
@@ -30,7 +30,6 @@
 MODULE_AUTHOR("Adrian McMenamin <adrian@mcmen.demon.co.uk>");
 MODULE_DESCRIPTION("Maple bus driver for Dreamcast");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{SEGA, Dreamcast/Maple}}");
 
 static void maple_dma_handler(struct work_struct *work);
 static void maple_vblank_handler(struct work_struct *work);
diff --git a/drivers/staging/comedi/drivers/vmk80xx.c b/drivers/staging/comedi/drivers/vmk80xx.c
index 7956abcbae22..9f920819cd74 100644
--- a/drivers/staging/comedi/drivers/vmk80xx.c
+++ b/drivers/staging/comedi/drivers/vmk80xx.c
@@ -877,5 +877,4 @@ module_comedi_usb_driver(vmk80xx_driver, vmk80xx_usb_driver);
 
 MODULE_AUTHOR("Manuel Gebele <forensixs@gmx.de>");
 MODULE_DESCRIPTION("Velleman USB Board Low-Level Driver");
-MODULE_SUPPORTED_DEVICE("K8055/K8061 aka VM110/VM140");
 MODULE_LICENSE("GPL");
diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c
index cf4718c6d35d..319a1e701163 100644
--- a/drivers/tee/optee/core.c
+++ b/drivers/tee/optee/core.c
@@ -747,7 +747,6 @@ module_platform_driver(optee_driver);
 
 MODULE_AUTHOR("Linaro");
 MODULE_DESCRIPTION("OP-TEE driver");
-MODULE_SUPPORTED_DEVICE("");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("platform:optee");
diff --git a/drivers/tty/serial/icom.c b/drivers/tty/serial/icom.c
index 9a872750581c..94af7a5ea497 100644
--- a/drivers/tty/serial/icom.c
+++ b/drivers/tty/serial/icom.c
@@ -1639,8 +1639,6 @@ module_exit(icom_exit);
 
 MODULE_AUTHOR("Michael Anderson <mjanders@us.ibm.com>");
 MODULE_DESCRIPTION("IBM iSeries Serial IOA driver");
-MODULE_SUPPORTED_DEVICE
-    ("IBM iSeries 2745, 2771, 2772, 2742, 2793 and 2805 Communications adapters");
 MODULE_LICENSE("GPL");
 MODULE_FIRMWARE("icom_call_setup.bin");
 MODULE_FIRMWARE("icom_res_dce.bin");
diff --git a/drivers/tty/serial/jsm/jsm_driver.c b/drivers/tty/serial/jsm/jsm_driver.c
index cd30da0ef083..0ea799bf8dbb 100644
--- a/drivers/tty/serial/jsm/jsm_driver.c
+++ b/drivers/tty/serial/jsm/jsm_driver.c
@@ -19,7 +19,6 @@
 MODULE_AUTHOR("Digi International, https://www.digi.com");
 MODULE_DESCRIPTION("Driver for the Digi International Neo and Classic PCI based product line");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("jsm");
 
 #define JSM_DRIVER_NAME "jsm"
 #define NR_PORTS	32
diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c
index 670e4d91e9ca..dcc88df72df4 100644
--- a/drivers/usb/misc/ldusb.c
+++ b/drivers/usb/misc/ldusb.c
@@ -117,7 +117,6 @@ MODULE_DEVICE_TABLE(usb, ld_usb_table);
 MODULE_AUTHOR("Michael Hund <mhund@ld-didactic.de>");
 MODULE_DESCRIPTION("LD USB Driver");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("LD USB Devices");
 
 /* All interrupt in transfers are collected in a ring buffer to
  * avoid racing conditions and get better performance of the driver.
diff --git a/drivers/watchdog/cpu5wdt.c b/drivers/watchdog/cpu5wdt.c
index 9867a3a936df..688b112e712b 100644
--- a/drivers/watchdog/cpu5wdt.c
+++ b/drivers/watchdog/cpu5wdt.c
@@ -273,7 +273,6 @@ module_exit(cpu5wdt_exit_module);
 
 MODULE_AUTHOR("Heiko Ronsdorf <hero@ihg.uni-duisburg.de>");
 MODULE_DESCRIPTION("sma cpu5 watchdog driver");
-MODULE_SUPPORTED_DEVICE("sma cpu5 watchdog");
 MODULE_LICENSE("GPL");
 
 module_param_hw(port, int, ioport, 0);
diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c
index 808eeb4779e4..1eafe0b4d71c 100644
--- a/drivers/watchdog/cpwd.c
+++ b/drivers/watchdog/cpwd.c
@@ -172,7 +172,6 @@ MODULE_PARM_DESC(wd2_timeout, "Default watchdog2 timeout in 1/10secs");
 MODULE_AUTHOR("Eric Brower <ebrower@usa.net>");
 MODULE_DESCRIPTION("Hardware watchdog driver for Sun Microsystems CP1400/1500");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("watchdog");
 
 static void cpwd_writew(u16 val, void __iomem *addr)
 {
diff --git a/drivers/watchdog/riowd.c b/drivers/watchdog/riowd.c
index 7008596a575f..747e346ed06c 100644
--- a/drivers/watchdog/riowd.c
+++ b/drivers/watchdog/riowd.c
@@ -46,7 +46,6 @@
 
 MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
 MODULE_DESCRIPTION("Hardware watchdog driver for Sun RIO");
-MODULE_SUPPORTED_DEVICE("watchdog");
 MODULE_LICENSE("GPL");
 
 #define DRIVER_NAME	"riowd"
diff --git a/include/linux/module.h b/include/linux/module.h
index 59f094fa6f74..da4b6fbe8ebe 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -30,9 +30,6 @@
 #include <linux/percpu.h>
 #include <asm/module.h>
 
-/* Not Yet Implemented */
-#define MODULE_SUPPORTED_DEVICE(name)
-
 #define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN
 
 struct modversion_info {
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index e48f7ac8a854..3ddd66e4c29e 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -702,7 +702,6 @@ MODULE_LICENSE("GPL");
 
 MODULE_AUTHOR(BATADV_DRIVER_AUTHOR);
 MODULE_DESCRIPTION(BATADV_DRIVER_DESC);
-MODULE_SUPPORTED_DEVICE(BATADV_DRIVER_DEVICE);
 MODULE_VERSION(BATADV_SOURCE_VERSION);
 MODULE_ALIAS_RTNL_LINK("batadv");
 MODULE_ALIAS_GENL_FAMILY(BATADV_NL_NAME);
diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c
index 8a24e5ae7cef..52637180af33 100644
--- a/sound/drivers/aloop.c
+++ b/sound/drivers/aloop.c
@@ -33,7 +33,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("A loopback soundcard");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ALSA,Loopback soundcard}}");
 
 #define MAX_PCM_SUBSTREAMS	8
 
diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index 316c9afadefe..01a3eab50d7b 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -25,7 +25,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Dummy soundcard (/dev/null)");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ALSA,Dummy soundcard}}");
 
 #define MAX_PCM_DEVICES		4
 #define MAX_PCM_SUBSTREAMS	128
diff --git a/sound/drivers/mtpav.c b/sound/drivers/mtpav.c
index ce5fd17bd720..df4b7f9cd50f 100644
--- a/sound/drivers/mtpav.c
+++ b/sound/drivers/mtpav.c
@@ -53,7 +53,6 @@
 MODULE_AUTHOR("Michael T. Mayers");
 MODULE_DESCRIPTION("MOTU MidiTimePiece AV multiport MIDI");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{MOTU,MidiTimePiece AV multiport MIDI}}");
 
 // io resources
 #define MTPAV_IOBASE		0x378
diff --git a/sound/drivers/mts64.c b/sound/drivers/mts64.c
index 9c708b693cb3..322d530ab07b 100644
--- a/sound/drivers/mts64.c
+++ b/sound/drivers/mts64.c
@@ -37,7 +37,6 @@ MODULE_PARM_DESC(enable, "Enable " CARD_NAME " soundcard.");
 MODULE_AUTHOR("Matthias Koenig <mk@phasorlab.de>");
 MODULE_DESCRIPTION("ESI Miditerminal 4140");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESI,Miditerminal 4140}}");
 
 /*********************************************************************
  * Chip specific
diff --git a/sound/drivers/pcsp/pcsp.c b/sound/drivers/pcsp/pcsp.c
index fd79e57c85ca..7689fa2f9531 100644
--- a/sound/drivers/pcsp/pcsp.c
+++ b/sound/drivers/pcsp/pcsp.c
@@ -22,7 +22,6 @@
 MODULE_AUTHOR("Stas Sergeev <stsp@users.sourceforge.net>");
 MODULE_DESCRIPTION("PC-Speaker driver");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{PC-Speaker, pcsp}}");
 MODULE_ALIAS("platform:pcspkr");
 
 static int index = SNDRV_DEFAULT_IDX1;	/* Index 0-MAX */
diff --git a/sound/drivers/portman2x4.c b/sound/drivers/portman2x4.c
index c876cf9b5005..2f4514ed47c5 100644
--- a/sound/drivers/portman2x4.c
+++ b/sound/drivers/portman2x4.c
@@ -57,7 +57,6 @@ MODULE_PARM_DESC(enable, "Enable " CARD_NAME " soundcard.");
 MODULE_AUTHOR("Levent Guendogdu, Tobias Gehrig, Matthias Koenig");
 MODULE_DESCRIPTION("Midiman Portman2x4");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Midiman,Portman2x4}}");
 
 /*********************************************************************
  * Chip specific
diff --git a/sound/drivers/serial-u16550.c b/sound/drivers/serial-u16550.c
index 3947f084dd6b..6d5d1ca59ecf 100644
--- a/sound/drivers/serial-u16550.c
+++ b/sound/drivers/serial-u16550.c
@@ -34,7 +34,6 @@
 
 MODULE_DESCRIPTION("MIDI serial u16550");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ALSA, MIDI serial u16550}}");
 
 #define SNDRV_SERIAL_SOUNDCANVAS 0 /* Roland Soundcanvas; F5 NN selects part */
 #define SNDRV_SERIAL_MS124T 1      /* Midiator MS-124T */
diff --git a/sound/drivers/virmidi.c b/sound/drivers/virmidi.c
index f1fb68b15498..4206d93ab47e 100644
--- a/sound/drivers/virmidi.c
+++ b/sound/drivers/virmidi.c
@@ -43,7 +43,6 @@
 MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
 MODULE_DESCRIPTION("Dummy soundcard for virtual rawmidi devices");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ALSA,Virtual rawmidi device}}");
 
 #define MAX_MIDI_DEVICES	4
 
diff --git a/sound/isa/ad1816a/ad1816a.c b/sound/isa/ad1816a/ad1816a.c
index ca18fe3ff8a5..f11af983b3b6 100644
--- a/sound/isa/ad1816a/ad1816a.c
+++ b/sound/isa/ad1816a/ad1816a.c
@@ -22,13 +22,6 @@
 MODULE_AUTHOR("Massimo Piccioni <dafastidio@libero.it>");
 MODULE_DESCRIPTION("AD1816A, AD1815");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Highscreen,Sound-Boostar 16 3D},"
-		"{Analog Devices,AD1815},"
-		"{Analog Devices,AD1816A},"
-		"{TerraTec,Base 64},"
-		"{TerraTec,AudioSystem EWS64S},"
-		"{Aztech/Newcom SC-16 3D},"
-		"{Shark Predator ISA}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 1-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/isa/ad1848/ad1848.c b/sound/isa/ad1848/ad1848.c
index 6f221eed44e2..edafb49797e7 100644
--- a/sound/isa/ad1848/ad1848.c
+++ b/sound/isa/ad1848/ad1848.c
@@ -22,9 +22,6 @@
 MODULE_DESCRIPTION(CRD_NAME);
 MODULE_AUTHOR("Tugrul Galatali <galatalt@stuy.edu>, Jaroslav Kysela <perex@perex.cz>");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Analog Devices,AD1848},"
-	        "{Analog Devices,AD1847},"
-		"{Crystal Semiconductors,CS4248}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/isa/als100.c b/sound/isa/als100.c
index 1085f5b01318..bacb7a1b930c 100644
--- a/sound/isa/als100.c
+++ b/sound/isa/als100.c
@@ -26,17 +26,6 @@
 #define PFX "als100: "
 
 MODULE_DESCRIPTION("Avance Logic ALS007/ALS1X0");
-MODULE_SUPPORTED_DEVICE("{{Diamond Technologies DT-019X},"
-		"{Avance Logic ALS-007}}"
-		"{{Avance Logic,ALS100 - PRO16PNP},"
-	        "{Avance Logic,ALS110},"
-	        "{Avance Logic,ALS120},"
-	        "{Avance Logic,ALS200},"
-	        "{3D Melody,MF1000},"
-	        "{Digimate,3D Sound},"
-	        "{Avance Logic,ALS120},"
-	        "{RTL,RTL3000}}");
-
 MODULE_AUTHOR("Massimo Piccioni <dafastidio@libero.it>");
 MODULE_LICENSE("GPL");
 
diff --git a/sound/isa/azt2320.c b/sound/isa/azt2320.c
index 4ed52094fc8d..867e9ae8f65a 100644
--- a/sound/isa/azt2320.c
+++ b/sound/isa/azt2320.c
@@ -35,11 +35,6 @@
 MODULE_AUTHOR("Massimo Piccioni <dafastidio@libero.it>");
 MODULE_DESCRIPTION("Aztech Systems AZT2320");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Aztech Systems,PRO16V},"
-		"{Aztech Systems,AZT2320},"
-		"{Aztech Systems,AZT3300},"
-		"{Aztech Systems,AZT2320},"
-		"{Aztech Systems,AZT3000}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/isa/cmi8330.c b/sound/isa/cmi8330.c
index 19e258527d69..bc112df10fc5 100644
--- a/sound/isa/cmi8330.c
+++ b/sound/isa/cmi8330.c
@@ -51,7 +51,6 @@
 MODULE_AUTHOR("George Talusan <gstalusan@uwaterloo.ca>");
 MODULE_DESCRIPTION("C-Media CMI8330/CMI8329");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{C-Media,CMI8330,isapnp:{CMI0001,@@@0001,@X@0001}}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
diff --git a/sound/isa/cs423x/cs4231.c b/sound/isa/cs423x/cs4231.c
index c56cbc072918..ec054b929214 100644
--- a/sound/isa/cs423x/cs4231.c
+++ b/sound/isa/cs423x/cs4231.c
@@ -23,7 +23,6 @@
 MODULE_DESCRIPTION(CRD_NAME);
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Crystal Semiconductors,CS4231}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/isa/cs423x/cs4236.c b/sound/isa/cs423x/cs4236.c
index 63fb0cb754d0..186d7d4db45e 100644
--- a/sound/isa/cs423x/cs4236.c
+++ b/sound/isa/cs423x/cs4236.c
@@ -18,40 +18,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Cirrus Logic CS4232-9");
-MODULE_SUPPORTED_DEVICE("{{Turtle Beach,TBS-2000},"
-		"{Turtle Beach,Tropez Plus},"
-		"{SIC CrystalWave 32},"
-		"{Hewlett Packard,Omnibook 5500},"
-		"{TerraTec,Maestro 32/96},"
-		"{Philips,PCA70PS}},"
-		"{{Crystal Semiconductors,CS4235},"
-		"{Crystal Semiconductors,CS4236},"
-		"{Crystal Semiconductors,CS4237},"
-		"{Crystal Semiconductors,CS4238},"
-		"{Crystal Semiconductors,CS4239},"
-		"{Acer,AW37},"
-		"{Acer,AW35/Pro},"
-		"{Crystal,3D},"
-		"{Crystal Computer,TidalWave128},"
-		"{Dell,Optiplex GX1},"
-		"{Dell,Workstation 400 sound},"
-		"{EliteGroup,P5TX-LA sound},"
-		"{Gallant,SC-70P},"
-		"{Gateway,E1000 Onboard CS4236B},"
-		"{Genius,Sound Maker 3DJ},"
-		"{Hewlett Packard,HP6330 sound},"
-		"{IBM,PC 300PL sound},"
-		"{IBM,Aptiva 2137 E24},"
-		"{IBM,IntelliStation M Pro},"
-		"{Intel,Marlin Spike Mobo CS4235},"
-		"{Intel PR440FX Onboard},"
-		"{Guillemot,MaxiSound 16 PnP},"
-		"{NewClear,3D},"
-		"{TerraTec,AudioSystem EWS64L/XL},"
-		"{Typhoon Soundsystem,CS4236B},"
-		"{Turtle Beach,Malibu},"
-		"{Unknown,Digital PC 5000 Onboard}}");
-
 MODULE_ALIAS("snd_cs4232");
 
 #define IDENT "CS4232+"
diff --git a/sound/isa/es1688/es1688.c b/sound/isa/es1688/es1688.c
index 4a1f61f1a331..750d4995634f 100644
--- a/sound/isa/es1688/es1688.c
+++ b/sound/isa/es1688/es1688.c
@@ -26,11 +26,6 @@
 MODULE_DESCRIPTION(CRD_NAME);
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESS,ES688 PnP AudioDrive,pnp:ESS0100},"
-	        "{ESS,ES1688 PnP AudioDrive,pnp:ESS0102},"
-	        "{ESS,ES688 AudioDrive,pnp:ESS6881},"
-	        "{ESS,ES1688 AudioDrive,pnp:ESS1681}}");
-
 MODULE_ALIAS("snd_es968");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
diff --git a/sound/isa/es18xx.c b/sound/isa/es18xx.c
index 9beef8079177..375a4a6a4717 100644
--- a/sound/isa/es18xx.c
+++ b/sound/isa/es18xx.c
@@ -1929,17 +1929,9 @@ static int snd_es18xx_mixer(struct snd_card *card)
 
 /* Card level */
 
-MODULE_AUTHOR("Christian Fischbach <fishbach@pool.informatik.rwth-aachen.de>, Abramo Bagnara <abramo@alsa-project.org>");  
+MODULE_AUTHOR("Christian Fischbach <fishbach@pool.informatik.rwth-aachen.de>, Abramo Bagnara <abramo@alsa-project.org>");
 MODULE_DESCRIPTION("ESS ES18xx AudioDrive");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESS,ES1868 PnP AudioDrive},"
-		"{ESS,ES1869 PnP AudioDrive},"
-		"{ESS,ES1878 PnP AudioDrive},"
-		"{ESS,ES1879 PnP AudioDrive},"
-		"{ESS,ES1887 PnP AudioDrive},"
-		"{ESS,ES1888 PnP AudioDrive},"
-		"{ESS,ES1887 AudioDrive},"
-		"{ESS,ES1888 AudioDrive}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/isa/gus/gusclassic.c b/sound/isa/gus/gusclassic.c
index 015f88a11352..0fba5d8fe84f 100644
--- a/sound/isa/gus/gusclassic.c
+++ b/sound/isa/gus/gusclassic.c
@@ -23,7 +23,6 @@
 MODULE_DESCRIPTION(CRD_NAME);
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Gravis,UltraSound Classic}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/isa/gus/gusextreme.c b/sound/isa/gus/gusextreme.c
index c9f31b4fb887..da2b2ca6b721 100644
--- a/sound/isa/gus/gusextreme.c
+++ b/sound/isa/gus/gusextreme.c
@@ -27,7 +27,6 @@
 MODULE_DESCRIPTION(CRD_NAME);
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Gravis,UltraSound Extreme}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/isa/gus/gusmax.c b/sound/isa/gus/gusmax.c
index dc09fbd6f88d..24b945f1768d 100644
--- a/sound/isa/gus/gusmax.c
+++ b/sound/isa/gus/gusmax.c
@@ -21,7 +21,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Gravis UltraSound MAX");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Gravis,UltraSound MAX}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/isa/gus/interwave.c b/sound/isa/gus/interwave.c
index e4d412e72b75..99581fba4ca8 100644
--- a/sound/isa/gus/interwave.c
+++ b/sound/isa/gus/interwave.c
@@ -28,14 +28,8 @@ MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_LICENSE("GPL");
 #ifndef SNDRV_STB
 MODULE_DESCRIPTION("AMD InterWave");
-MODULE_SUPPORTED_DEVICE("{{Gravis,UltraSound Plug & Play},"
-		"{STB,SoundRage32},"
-		"{MED,MED3210},"
-		"{Dynasonix,Dynasonix Pro},"
-		"{Panasonic,PCA761AW}}");
 #else
 MODULE_DESCRIPTION("AMD InterWave STB with TEA6330T");
-MODULE_SUPPORTED_DEVICE("{{AMD,InterWave STB with TEA6330T}}");
 #endif
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
diff --git a/sound/isa/opl3sa2.c b/sound/isa/opl3sa2.c
index 7649a8a4128d..9bde11d1cfe8 100644
--- a/sound/isa/opl3sa2.c
+++ b/sound/isa/opl3sa2.c
@@ -22,11 +22,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Yamaha OPL3SA2+");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Yamaha,YMF719E-S},"
-		"{Genius,Sound Maker 3DX},"
-		"{Yamaha,OPL3SA3},"
-		"{Intel,AL440LX sound},"
-	        "{NeoMagic,MagicWave 3DX}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/isa/opti9xx/miro.c b/sound/isa/opti9xx/miro.c
index 20933342f5eb..a510b201143c 100644
--- a/sound/isa/opti9xx/miro.c
+++ b/sound/isa/opti9xx/miro.c
@@ -33,9 +33,6 @@
 MODULE_AUTHOR("Martin Langer <martin-langer@gmx.de>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Miro miroSOUND PCM1 pro, PCM12, PCM20 Radio");
-MODULE_SUPPORTED_DEVICE("{{Miro,miroSOUND PCM1 pro}, "
-			"{Miro,miroSOUND PCM12}, "
-			"{Miro,miroSOUND PCM20 Radio}}");
 
 static int index = SNDRV_DEFAULT_IDX1;		/* Index 0-MAX */
 static char *id = SNDRV_DEFAULT_STR1;		/* ID for this card */
diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c
index 758f5b579138..08e61d90057b 100644
--- a/sound/isa/opti9xx/opti92x-ad1848.c
+++ b/sound/isa/opti9xx/opti92x-ad1848.c
@@ -36,17 +36,11 @@ MODULE_AUTHOR("Massimo Piccioni <dafastidio@libero.it>");
 MODULE_LICENSE("GPL");
 #ifdef OPTi93X
 MODULE_DESCRIPTION("OPTi93X");
-MODULE_SUPPORTED_DEVICE("{{OPTi,82C931/3}}");
 #else	/* OPTi93X */
 #ifdef CS4231
 MODULE_DESCRIPTION("OPTi92X - CS4231");
-MODULE_SUPPORTED_DEVICE("{{OPTi,82C924 (CS4231)},"
-		"{OPTi,82C925 (CS4231)}}");
 #else	/* CS4231 */
 MODULE_DESCRIPTION("OPTi92X - AD1848");
-MODULE_SUPPORTED_DEVICE("{{OPTi,82C924 (AD1848)},"
-		"{OPTi,82C925 (AD1848)},"
-	        "{OAK,Mozart}}");
 #endif	/* CS4231 */
 #endif	/* OPTi93X */
 
diff --git a/sound/isa/sb/jazz16.c b/sound/isa/sb/jazz16.c
index 0e2e0ab3b9e4..7ba5dd1ec810 100644
--- a/sound/isa/sb/jazz16.c
+++ b/sound/isa/sb/jazz16.c
@@ -28,9 +28,6 @@
 #define PFX "jazz16: "
 
 MODULE_DESCRIPTION("Media Vision Jazz16");
-MODULE_SUPPORTED_DEVICE("{{Media Vision ??? },"
-		"{RTL,RTL3000}}");
-
 MODULE_AUTHOR("Krzysztof Helt <krzysztof.h1@wp.pl>");
 MODULE_LICENSE("GPL");
 
diff --git a/sound/isa/sb/sb16.c b/sound/isa/sb/sb16.c
index db284b7b88a7..63ef960abd25 100644
--- a/sound/isa/sb/sb16.c
+++ b/sound/isa/sb/sb16.c
@@ -31,16 +31,8 @@ MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_LICENSE("GPL");
 #ifndef SNDRV_SBAWE
 MODULE_DESCRIPTION("Sound Blaster 16");
-MODULE_SUPPORTED_DEVICE("{{Creative Labs,SB 16},"
-		"{Creative Labs,SB Vibra16S},"
-		"{Creative Labs,SB Vibra16C},"
-		"{Creative Labs,SB Vibra16CL},"
-		"{Creative Labs,SB Vibra16X}}");
 #else
 MODULE_DESCRIPTION("Sound Blaster AWE");
-MODULE_SUPPORTED_DEVICE("{{Creative Labs,SB AWE 32},"
-		"{Creative Labs,SB AWE 64},"
-		"{Creative Labs,SB AWE 64 Gold}}");
 #endif
 
 #if 0
diff --git a/sound/isa/sb/sb8.c b/sound/isa/sb/sb8.c
index 8e3e67b9a341..6c9d534ce8b6 100644
--- a/sound/isa/sb/sb8.c
+++ b/sound/isa/sb/sb8.c
@@ -17,7 +17,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Sound Blaster 1.0/2.0/Pro");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Creative Labs,SB 1.0/SB 2.0/SB Pro}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/isa/sc6000.c b/sound/isa/sc6000.c
index def137579717..3462663050bb 100644
--- a/sound/isa/sc6000.c
+++ b/sound/isa/sc6000.c
@@ -29,9 +29,6 @@
 MODULE_AUTHOR("Krzysztof Helt");
 MODULE_DESCRIPTION("Gallant SC-6000");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Gallant, SC-6000},"
-			"{AudioExcel, Audio Excel DSP 16},"
-			"{Zoltrix, AV302}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/isa/wavefront/wavefront.c b/sound/isa/wavefront/wavefront.c
index b750a4fd40de..a4437971df2f 100644
--- a/sound/isa/wavefront/wavefront.c
+++ b/sound/isa/wavefront/wavefront.c
@@ -21,7 +21,6 @@
 MODULE_AUTHOR("Paul Barton-Davis <pbd@op.net>");
 MODULE_DESCRIPTION("Turtle Beach Wavefront");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Turtle Beach,Maui/Tropez/Tropez+}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	    /* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	    /* ID for this card */
diff --git a/sound/mips/sgio2audio.c b/sound/mips/sgio2audio.c
index 5bf1ea150f26..989f656e2de7 100644
--- a/sound/mips/sgio2audio.c
+++ b/sound/mips/sgio2audio.c
@@ -32,7 +32,6 @@
 MODULE_AUTHOR("Vivien Chappelier <vivien.chappelier@linux-mips.org>");
 MODULE_DESCRIPTION("SGI O2 Audio");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Silicon Graphics, O2 Audio}}");
 
 static int index = SNDRV_DEFAULT_IDX1;  /* Index 0-MAX */
 static char *id = SNDRV_DEFAULT_STR1;   /* ID for this card */
diff --git a/sound/pci/ad1889.c b/sound/pci/ad1889.c
index 5d835d2af054..4520022801d9 100644
--- a/sound/pci/ad1889.c
+++ b/sound/pci/ad1889.c
@@ -43,7 +43,6 @@
 MODULE_AUTHOR("Kyle McMartin <kyle@parisc-linux.org>, Thibaut Varene <t-bone@parisc-linux.org>");
 MODULE_DESCRIPTION("Analog Devices AD1889 ALSA sound driver");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Analog Devices,AD1889}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
 module_param_array(index, int, NULL, 0444);
diff --git a/sound/pci/ali5451/ali5451.c b/sound/pci/ali5451/ali5451.c
index 51f24796f03f..0d66b92466d5 100644
--- a/sound/pci/ali5451/ali5451.c
+++ b/sound/pci/ali5451/ali5451.c
@@ -29,7 +29,6 @@
 MODULE_AUTHOR("Matt Wu <Matt_Wu@acersoftech.com.cn>");
 MODULE_DESCRIPTION("ALI M5451");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ALI,M5451,pci},{ALI,M5451}}");
 
 static int index = SNDRV_DEFAULT_IDX1;	/* Index */
 static char *id = SNDRV_DEFAULT_STR1;	/* ID for this card */
diff --git a/sound/pci/als300.c b/sound/pci/als300.c
index 1dc8c4ed0592..bd4fd09e982b 100644
--- a/sound/pci/als300.c
+++ b/sound/pci/als300.c
@@ -86,7 +86,6 @@ enum {DEVICE_ALS300, DEVICE_ALS300_PLUS};
 MODULE_AUTHOR("Ash Willis <ashwillis@programmer.net>");
 MODULE_DESCRIPTION("Avance Logic ALS300");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Avance Logic,ALS300},{Avance Logic,ALS300+}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
diff --git a/sound/pci/als4000.c b/sound/pci/als4000.c
index 2edc7455285a..139ac2a3a0ef 100644
--- a/sound/pci/als4000.c
+++ b/sound/pci/als4000.c
@@ -68,7 +68,6 @@
 MODULE_AUTHOR("Bart Hartgers <bart@etpmod.phys.tue.nl>, Andreas Mohr");
 MODULE_DESCRIPTION("Avance Logic ALS4000");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Avance Logic,ALS4000}}");
 
 #if IS_REACHABLE(CONFIG_GAMEPORT)
 #define SUPPORT_JOYSTICK 1
diff --git a/sound/pci/atiixp.c b/sound/pci/atiixp.c
index a25d75455802..579425ccbb6a 100644
--- a/sound/pci/atiixp.c
+++ b/sound/pci/atiixp.c
@@ -23,7 +23,6 @@
 MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
 MODULE_DESCRIPTION("ATI IXP AC97 controller");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ATI,IXP150/200/250/300/400/600}}");
 
 static int index = SNDRV_DEFAULT_IDX1;	/* Index 0-MAX */
 static char *id = SNDRV_DEFAULT_STR1;	/* ID for this card */
diff --git a/sound/pci/atiixp_modem.c b/sound/pci/atiixp_modem.c
index ae88217d685a..45e75afec7a0 100644
--- a/sound/pci/atiixp_modem.c
+++ b/sound/pci/atiixp_modem.c
@@ -23,7 +23,6 @@
 MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
 MODULE_DESCRIPTION("ATI IXP MC97 controller");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ATI,IXP150/200/250}}");
 
 static int index = -2; /* Exclude the first card */
 static char *id = SNDRV_DEFAULT_STR1;	/* ID for this card */
diff --git a/sound/pci/au88x0/au88x0.c b/sound/pci/au88x0/au88x0.c
index 5dd98e6ff34b..1b37b7225b1d 100644
--- a/sound/pci/au88x0/au88x0.c
+++ b/sound/pci/au88x0/au88x0.c
@@ -41,8 +41,6 @@ MODULE_PARM_DESC(pcifix, "Enable VIA-workaround for " CARD_NAME " soundcard.");
 
 MODULE_DESCRIPTION("Aureal vortex");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Aureal Semiconductor Inc., Aureal Vortex Sound Processor}}");
-
 MODULE_DEVICE_TABLE(pci, snd_vortex_ids);
 
 static void vortex_fix_latency(struct pci_dev *vortex)
diff --git a/sound/pci/azt3328.c b/sound/pci/azt3328.c
index 2ac594dcf21c..51dcf1bc4c0c 100644
--- a/sound/pci/azt3328.c
+++ b/sound/pci/azt3328.c
@@ -196,7 +196,6 @@
 MODULE_AUTHOR("Andreas Mohr <andi AT lisas.de>");
 MODULE_DESCRIPTION("Aztech AZF3328 (PCI168)");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Aztech,AZF3328}}");
 
 #if IS_REACHABLE(CONFIG_GAMEPORT)
 #define SUPPORT_GAMEPORT 1
diff --git a/sound/pci/bt87x.c b/sound/pci/bt87x.c
index cf9f8d80a0b6..91512b345d19 100644
--- a/sound/pci/bt87x.c
+++ b/sound/pci/bt87x.c
@@ -23,8 +23,6 @@
 MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
 MODULE_DESCRIPTION("Brooktree Bt87x audio driver");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Brooktree,Bt878},"
-		"{Brooktree,Bt879}}");
 
 static int index[SNDRV_CARDS] = {[0 ... (SNDRV_CARDS - 1)] = -2}; /* Exclude the first card */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/ca0106/ca0106_main.c b/sound/pci/ca0106/ca0106_main.c
index ee20f9a1aae9..bee4710916c4 100644
--- a/sound/pci/ca0106/ca0106_main.c
+++ b/sound/pci/ca0106/ca0106_main.c
@@ -137,7 +137,6 @@
 MODULE_AUTHOR("James Courtier-Dutton <James@superbug.demon.co.uk>");
 MODULE_DESCRIPTION("CA0106");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Creative,SB CA0106 chip}}");
 
 // module parameters (see "Module Parameters")
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c
index 7363d61eaec2..598446348da6 100644
--- a/sound/pci/cmipci.c
+++ b/sound/pci/cmipci.c
@@ -30,10 +30,6 @@
 MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
 MODULE_DESCRIPTION("C-Media CMI8x38 PCI");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{C-Media,CMI8738},"
-		"{C-Media,CMI8738B},"
-		"{C-Media,CMI8338A},"
-		"{C-Media,CMI8338B}}");
 
 #if IS_REACHABLE(CONFIG_GAMEPORT)
 #define SUPPORT_JOYSTICK 1
diff --git a/sound/pci/cs4281.c b/sound/pci/cs4281.c
index 94d2a6a466a8..bf3bb70ffaf9 100644
--- a/sound/pci/cs4281.c
+++ b/sound/pci/cs4281.c
@@ -25,7 +25,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Cirrus Logic CS4281");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Cirrus Logic,CS4281}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/cs46xx/cs46xx.c b/sound/pci/cs46xx/cs46xx.c
index a6e0a4439332..1db7b4112840 100644
--- a/sound/pci/cs46xx/cs46xx.c
+++ b/sound/pci/cs46xx/cs46xx.c
@@ -21,13 +21,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Cirrus Logic Sound Fusion CS46XX");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Cirrus Logic,Sound Fusion (CS4280)},"
-		"{Cirrus Logic,Sound Fusion (CS4610)},"
-		"{Cirrus Logic,Sound Fusion (CS4612)},"
-		"{Cirrus Logic,Sound Fusion (CS4615)},"
-		"{Cirrus Logic,Sound Fusion (CS4622)},"
-		"{Cirrus Logic,Sound Fusion (CS4624)},"
-		"{Cirrus Logic,Sound Fusion (CS4630)}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/cs5535audio/cs5535audio.c b/sound/pci/cs5535audio/cs5535audio.c
index 359bc6af8670..9b716b56d739 100644
--- a/sound/pci/cs5535audio/cs5535audio.c
+++ b/sound/pci/cs5535audio/cs5535audio.c
@@ -393,4 +393,3 @@ module_pci_driver(cs5535audio_driver);
 MODULE_AUTHOR("Jaya Kumar");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CS5535 Audio");
-MODULE_SUPPORTED_DEVICE("CS5535 Audio");
diff --git a/sound/pci/ctxfi/xfi.c b/sound/pci/ctxfi/xfi.c
index 8c07c6463c24..713d36ea40cb 100644
--- a/sound/pci/ctxfi/xfi.c
+++ b/sound/pci/ctxfi/xfi.c
@@ -18,7 +18,6 @@
 MODULE_AUTHOR("Creative Technology Ltd");
 MODULE_DESCRIPTION("X-Fi driver version 1.03");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{Creative Labs, Sound Blaster X-Fi}");
 
 static unsigned int reference_rate = 48000;
 static unsigned int multiple = 2;
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index a20b2bb5c898..9bd67ac33657 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -10,7 +10,6 @@
 MODULE_AUTHOR("Giuliano Pochini <pochini@shiny.it>");
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Echoaudio " ECHOCARD_NAME " soundcards driver");
-MODULE_SUPPORTED_DEVICE("{{Echoaudio," ECHOCARD_NAME "}}");
 MODULE_DEVICE_TABLE(pci, snd_echo_ids);
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c
index 353934c88cbd..45833bc2a7e7 100644
--- a/sound/pci/emu10k1/emu10k1.c
+++ b/sound/pci/emu10k1/emu10k1.c
@@ -18,8 +18,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("EMU10K1");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Creative Labs,SB Live!/PCI512/E-mu APS},"
-	       "{Creative Labs,SB Audigy}}");
 
 #if IS_ENABLED(CONFIG_SND_SEQUENCER)
 #define ENABLE_SYNTH
diff --git a/sound/pci/emu10k1/emu10k1x.c b/sound/pci/emu10k1/emu10k1x.c
index 785ec0cf3933..d9a12cd01647 100644
--- a/sound/pci/emu10k1/emu10k1x.c
+++ b/sound/pci/emu10k1/emu10k1x.c
@@ -31,7 +31,6 @@
 MODULE_AUTHOR("Francisco Moraes <fmoraes@nc.rr.com>");
 MODULE_DESCRIPTION("EMU10K1X");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Dell Creative Labs,SB Live!}");
 
 // module parameters (see "Module Parameters")
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
diff --git a/sound/pci/ens1370.c b/sound/pci/ens1370.c
index 93c4fd313311..3ccccdbc0029 100644
--- a/sound/pci/ens1370.c
+++ b/sound/pci/ens1370.c
@@ -52,17 +52,9 @@ MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>, Thomas Sailer <sailer@ife.ee.et
 MODULE_LICENSE("GPL");
 #ifdef CHIP1370
 MODULE_DESCRIPTION("Ensoniq AudioPCI ES1370");
-MODULE_SUPPORTED_DEVICE("{{Ensoniq,AudioPCI-97 ES1370},"
-	        "{Creative Labs,SB PCI64/128 (ES1370)}}");
 #endif
 #ifdef CHIP1371
 MODULE_DESCRIPTION("Ensoniq/Creative AudioPCI ES1371+");
-MODULE_SUPPORTED_DEVICE("{{Ensoniq,AudioPCI ES1371/73},"
-		"{Ensoniq,AudioPCI ES1373},"
-		"{Creative Labs,Ectiva EV1938},"
-		"{Creative Labs,SB PCI64/128 (ES1371/73)},"
-		"{Creative Labs,Vibra PCI128},"
-		"{Ectiva,EV1938}}");
 #endif
 
 #if IS_REACHABLE(CONFIG_GAMEPORT)
diff --git a/sound/pci/es1938.c b/sound/pci/es1938.c
index 3b5d68ce9dd5..afc66347d162 100644
--- a/sound/pci/es1938.c
+++ b/sound/pci/es1938.c
@@ -52,10 +52,6 @@
 MODULE_AUTHOR("Jaromir Koutek <miri@punknet.cz>");
 MODULE_DESCRIPTION("ESS Solo-1");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESS,ES1938},"
-                "{ESS,ES1946},"
-                "{ESS,ES1969},"
-		"{TerraTec,128i PCI}}");
 
 #if IS_REACHABLE(CONFIG_GAMEPORT)
 #define SUPPORT_JOYSTICK 1
diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c
index 747fa69bb1c9..5fa1861236f5 100644
--- a/sound/pci/es1968.c
+++ b/sound/pci/es1968.c
@@ -107,10 +107,6 @@
 
 MODULE_DESCRIPTION("ESS Maestro");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESS,Maestro 2e},"
-		"{ESS,Maestro 2},"
-		"{ESS,Maestro 1},"
-		"{TerraTec,DMX}}");
 
 #if IS_REACHABLE(CONFIG_GAMEPORT)
 #define SUPPORT_JOYSTICK 1
diff --git a/sound/pci/fm801.c b/sound/pci/fm801.c
index c6ad6235a669..6279eb156e36 100644
--- a/sound/pci/fm801.c
+++ b/sound/pci/fm801.c
@@ -26,8 +26,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("ForteMedia FM801");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ForteMedia,FM801},"
-		"{Genius,SoundMaker Live 5.1}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 5eea130dcf0a..b59b0f323d4e 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -208,40 +208,6 @@ MODULE_PARM_DESC(snoop, "Enable/disable snooping");
 
 
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Intel, ICH6},"
-			 "{Intel, ICH6M},"
-			 "{Intel, ICH7},"
-			 "{Intel, ESB2},"
-			 "{Intel, ICH8},"
-			 "{Intel, ICH9},"
-			 "{Intel, ICH10},"
-			 "{Intel, PCH},"
-			 "{Intel, CPT},"
-			 "{Intel, PPT},"
-			 "{Intel, LPT},"
-			 "{Intel, LPT_LP},"
-			 "{Intel, WPT_LP},"
-			 "{Intel, SPT},"
-			 "{Intel, SPT_LP},"
-			 "{Intel, HPT},"
-			 "{Intel, PBG},"
-			 "{Intel, SCH},"
-			 "{ATI, SB450},"
-			 "{ATI, SB600},"
-			 "{ATI, RS600},"
-			 "{ATI, RS690},"
-			 "{ATI, RS780},"
-			 "{ATI, R600},"
-			 "{ATI, RV630},"
-			 "{ATI, RV610},"
-			 "{ATI, RV670},"
-			 "{ATI, RV635},"
-			 "{ATI, RV620},"
-			 "{ATI, RV770},"
-			 "{VIA, VT8251},"
-			 "{VIA, VT8237A},"
-			 "{SiS, SIS966},"
-			 "{ULI, M5461}}");
 MODULE_DESCRIPTION("Intel HDA driver");
 
 #if defined(CONFIG_PM) && defined(CONFIG_VGA_SWITCHEROO)
diff --git a/sound/pci/ice1712/ice1712.c b/sound/pci/ice1712/ice1712.c
index f814dbbec2a4..d54cd5143e9f 100644
--- a/sound/pci/ice1712/ice1712.c
+++ b/sound/pci/ice1712/ice1712.c
@@ -60,12 +60,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("ICEnsemble ICE1712 (Envy24)");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{"
-	       HOONTECH_DEVICE_DESC
-	       DELTA_DEVICE_DESC
-	       EWS_DEVICE_DESC
-	       "{ICEnsemble,Generic ICE1712},"
-	       "{ICEnsemble,Generic Envy24}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/ice1712/ice1724.c b/sound/pci/ice1712/ice1724.c
index c0fca94c1dd2..ef2367d86148 100644
--- a/sound/pci/ice1712/ice1724.c
+++ b/sound/pci/ice1712/ice1724.c
@@ -44,25 +44,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("VIA ICEnsemble ICE1724/1720 (Envy24HT/PT)");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{"
-	       REVO_DEVICE_DESC
-	       AMP_AUDIO2000_DEVICE_DESC
-	       AUREON_DEVICE_DESC
-	       VT1720_MOBO_DEVICE_DESC
-	       PONTIS_DEVICE_DESC
-	       PRODIGY192_DEVICE_DESC
-	       PRODIGY_HIFI_DEVICE_DESC
-	       JULI_DEVICE_DESC
-	       MAYA44_DEVICE_DESC
-	       PHASE_DEVICE_DESC
-	       WTM_DEVICE_DESC
-	       SE_DEVICE_DESC
-	       QTET_DEVICE_DESC
-		"{VIA,VT1720},"
-		"{VIA,VT1724},"
-		"{ICEnsemble,Generic ICE1724},"
-		"{ICEnsemble,Generic Envy24HT}"
-		"{ICEnsemble,Generic Envy24PT}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 3349e455a871..35903d1a1cbd 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -27,29 +27,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Intel 82801AA,82901AB,i810,i820,i830,i840,i845,MX440; SiS 7012; Ali 5455");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Intel,82801AA-ICH},"
-		"{Intel,82901AB-ICH0},"
-		"{Intel,82801BA-ICH2},"
-		"{Intel,82801CA-ICH3},"
-		"{Intel,82801DB-ICH4},"
-		"{Intel,ICH5},"
-		"{Intel,ICH6},"
-		"{Intel,ICH7},"
-		"{Intel,6300ESB},"
-		"{Intel,ESB2},"
-		"{Intel,MX440},"
-		"{SiS,SI7012},"
-		"{NVidia,nForce Audio},"
-		"{NVidia,nForce2 Audio},"
-		"{NVidia,nForce3 Audio},"
-		"{NVidia,MCP04},"
-		"{NVidia,MCP501},"
-		"{NVidia,CK804},"
-		"{NVidia,CK8},"
-		"{NVidia,CK8S},"
-		"{AMD,AMD768},"
-		"{AMD,AMD8111},"
-	        "{ALI,M5455}}");
 
 static int index = SNDRV_DEFAULT_IDX1;	/* Index 0-MAX */
 static char *id = SNDRV_DEFAULT_STR1;	/* ID for this card */
diff --git a/sound/pci/intel8x0m.c b/sound/pci/intel8x0m.c
index 19872cecc9d2..13ef838b26c1 100644
--- a/sound/pci/intel8x0m.c
+++ b/sound/pci/intel8x0m.c
@@ -25,21 +25,6 @@ MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Intel 82801AA,82901AB,i810,i820,i830,i840,i845,MX440; "
 		   "SiS 7013; NVidia MCP/2/2S/3 modems");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Intel,82801AA-ICH},"
-		"{Intel,82901AB-ICH0},"
-		"{Intel,82801BA-ICH2},"
-		"{Intel,82801CA-ICH3},"
-		"{Intel,82801DB-ICH4},"
-		"{Intel,ICH5},"
-		"{Intel,ICH6},"
-		"{Intel,ICH7},"
-	        "{Intel,MX440},"
-		"{SiS,7013},"
-		"{NVidia,NForce Modem},"
-		"{NVidia,NForce2 Modem},"
-		"{NVidia,NForce2s Modem},"
-		"{NVidia,NForce3 Modem},"
-		"{AMD,AMD768}}");
 
 static int index = -2; /* Exclude the first card */
 static char *id = SNDRV_DEFAULT_STR1;	/* ID for this card */
diff --git a/sound/pci/korg1212/korg1212.c b/sound/pci/korg1212/korg1212.c
index 2eddd9de9e6d..80ac3c6152ad 100644
--- a/sound/pci/korg1212/korg1212.c
+++ b/sound/pci/korg1212/korg1212.c
@@ -388,7 +388,6 @@ struct snd_korg1212 {
 
 MODULE_DESCRIPTION("korg1212");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{KORG,korg1212}}");
 MODULE_FIRMWARE("korg/k1212.dsp");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;     /* Index 0-MAX */
diff --git a/sound/pci/lola/lola.c b/sound/pci/lola/lola.c
index 491c90f83fbc..03b4be44bb26 100644
--- a/sound/pci/lola/lola.c
+++ b/sound/pci/lola/lola.c
@@ -54,7 +54,6 @@ MODULE_PARM_DESC(sample_rate_min, "Minimal sample rate");
  */
 
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Digigram, Lola}}");
 MODULE_DESCRIPTION("Digigram Lola driver");
 MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
 
diff --git a/sound/pci/lx6464es/lx6464es.c b/sound/pci/lx6464es/lx6464es.c
index b92ea074ff2a..1be97c38bc71 100644
--- a/sound/pci/lx6464es/lx6464es.c
+++ b/sound/pci/lx6464es/lx6464es.c
@@ -21,8 +21,6 @@
 MODULE_AUTHOR("Tim Blechmann");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("digigram lx6464es");
-MODULE_SUPPORTED_DEVICE("{digigram lx6464es{}}");
-
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
diff --git a/sound/pci/maestro3.c b/sound/pci/maestro3.c
index d2c2cd6006f0..cdc4b6106252 100644
--- a/sound/pci/maestro3.c
+++ b/sound/pci/maestro3.c
@@ -39,11 +39,6 @@
 MODULE_AUTHOR("Zach Brown <zab@zabbo.net>, Takashi Iwai <tiwai@suse.de>");
 MODULE_DESCRIPTION("ESS Maestro3 PCI");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESS,Maestro3 PCI},"
-		"{ESS,ES1988},"
-		"{ESS,Allegro PCI},"
-		"{ESS,Allegro-1 PCI},"
-	        "{ESS,Canyon3D-2/LE PCI}}");
 MODULE_FIRMWARE("ess/maestro3_assp_kernel.fw");
 MODULE_FIRMWARE("ess/maestro3_assp_minisrc.fw");
 
diff --git a/sound/pci/mixart/mixart.c b/sound/pci/mixart/mixart.c
index efff220b26ea..a0bbb386dc25 100644
--- a/sound/pci/mixart/mixart.c
+++ b/sound/pci/mixart/mixart.c
@@ -32,7 +32,6 @@
 MODULE_AUTHOR("Digigram <alsa@digigram.com>");
 MODULE_DESCRIPTION("Digigram " CARD_NAME);
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Digigram," CARD_NAME "}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;             /* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;              /* ID for this card */
diff --git a/sound/pci/nm256/nm256.c b/sound/pci/nm256/nm256.c
index 975994623c2c..6cb689aa28c2 100644
--- a/sound/pci/nm256/nm256.c
+++ b/sound/pci/nm256/nm256.c
@@ -32,8 +32,6 @@
 MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
 MODULE_DESCRIPTION("NeoMagic NM256AV/ZX");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{NeoMagic,NM256AV},"
-		"{NeoMagic,NM256ZX}}");
 
 /*
  * some compile conditions.
diff --git a/sound/pci/oxygen/oxygen.c b/sound/pci/oxygen/oxygen.c
index a751fcce7c8e..e335c4b5b381 100644
--- a/sound/pci/oxygen/oxygen.c
+++ b/sound/pci/oxygen/oxygen.c
@@ -56,9 +56,6 @@
 MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
 MODULE_DESCRIPTION("C-Media CMI8788 driver");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{C-Media,CMI8786}"
-			",{C-Media,CMI8787}"
-			",{C-Media,CMI8788}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
diff --git a/sound/pci/oxygen/se6x.c b/sound/pci/oxygen/se6x.c
index 78c35a0a5477..434f885f6f91 100644
--- a/sound/pci/oxygen/se6x.c
+++ b/sound/pci/oxygen/se6x.c
@@ -29,7 +29,6 @@
 MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
 MODULE_DESCRIPTION("Studio Evolution SE6X driver");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{Studio Evolution,SE6X}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
diff --git a/sound/pci/oxygen/virtuoso.c b/sound/pci/oxygen/virtuoso.c
index 98ab16329827..baa3244d4dab 100644
--- a/sound/pci/oxygen/virtuoso.c
+++ b/sound/pci/oxygen/virtuoso.c
@@ -16,7 +16,6 @@
 MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
 MODULE_DESCRIPTION("Asus Virtuoso driver");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{Asus,AV66},{Asus,AV100},{Asus,AV200}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
diff --git a/sound/pci/pcxhr/pcxhr.c b/sound/pci/pcxhr/pcxhr.c
index c2e4831c3a13..751f9744b089 100644
--- a/sound/pci/pcxhr/pcxhr.c
+++ b/sound/pci/pcxhr/pcxhr.c
@@ -35,7 +35,6 @@ MODULE_AUTHOR("Markus Bollinger <bollinger@digigram.com>, "
 	      "Marc Titinger <titinger@digigram.com>");
 MODULE_DESCRIPTION("Digigram " DRIVER_NAME " " PCXHR_DRIVER_VERSION_STRING);
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Digigram," DRIVER_NAME "}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c
index fcc2073c5025..56827db97239 100644
--- a/sound/pci/riptide/riptide.c
+++ b/sound/pci/riptide/riptide.c
@@ -103,7 +103,6 @@
 MODULE_AUTHOR("Peter Gruber <nokos@gmx.net>");
 MODULE_DESCRIPTION("riptide");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Conexant,Riptide}}");
 MODULE_FIRMWARE("riptide.hex");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
diff --git a/sound/pci/rme32.c b/sound/pci/rme32.c
index 4eabece4dcba..54f3e39f97f5 100644
--- a/sound/pci/rme32.c
+++ b/sound/pci/rme32.c
@@ -88,7 +88,6 @@ MODULE_PARM_DESC(fullduplex, "Support full-duplex mode.");
 MODULE_AUTHOR("Martin Langer <martin-langer@gmx.de>, Pilo Chambert <pilo.c@wanadoo.fr>");
 MODULE_DESCRIPTION("RME Digi32, Digi32/8, Digi32 PRO");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{RME,Digi32}," "{RME,Digi32/8}," "{RME,Digi32 PRO}}");
 
 /* Defines for RME Digi32 series */
 #define RME32_SPDIF_NCHANNELS 2
diff --git a/sound/pci/rme96.c b/sound/pci/rme96.c
index 84eef6a3739f..66082e9f526d 100644
--- a/sound/pci/rme96.c
+++ b/sound/pci/rme96.c
@@ -31,11 +31,6 @@ MODULE_AUTHOR("Anders Torger <torger@ludd.luth.se>");
 MODULE_DESCRIPTION("RME Digi96, Digi96/8, Digi96/8 PRO, Digi96/8 PST, "
 		   "Digi96/8 PAD");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{RME,Digi96},"
-		"{RME,Digi96/8},"
-		"{RME,Digi96/8 PRO},"
-		"{RME,Digi96/8 PST},"
-		"{RME,Digi96/8 PAD}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c
index 6d9029333a12..4cf879c42dc4 100644
--- a/sound/pci/rme9652/hdsp.c
+++ b/sound/pci/rme9652/hdsp.c
@@ -44,9 +44,6 @@ MODULE_PARM_DESC(enable, "Enable/disable specific Hammerfall DSP soundcards.");
 MODULE_AUTHOR("Paul Davis <paul@linuxaudiosystems.com>, Marcus Andersson, Thomas Charbonnel <thomas@undata.org>");
 MODULE_DESCRIPTION("RME Hammerfall DSP");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{RME Hammerfall-DSP},"
-	        "{RME HDSP-9652},"
-		"{RME HDSP-9632}}");
 MODULE_FIRMWARE("rpm_firmware.bin");
 MODULE_FIRMWARE("multiface_firmware.bin");
 MODULE_FIRMWARE("multiface_firmware_rev11.bin");
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index b66711574b1a..8d900c132f0f 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -165,7 +165,6 @@ MODULE_AUTHOR
 );
 MODULE_DESCRIPTION("RME HDSPM");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{RME HDSPM-MADI}}");
 
 /* --- Write registers. ---
   These are defined as byte-offsets from the iobase value.  */
diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c
index 012fbec5e6a7..4df992e846f2 100644
--- a/sound/pci/rme9652/rme9652.c
+++ b/sound/pci/rme9652/rme9652.c
@@ -39,8 +39,6 @@ MODULE_PARM_DESC(precise_ptr, "Enable precise pointer (doesn't work reliably).")
 MODULE_AUTHOR("Paul Davis <pbd@op.net>, Winfried Ritsch");
 MODULE_DESCRIPTION("RME Digi9652/Digi9636");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{RME,Hammerfall},"
-		"{RME,Hammerfall-Light}}");
 
 /* The Hammerfall has two sets of 24 ADAT + 2 S/PDIF channels, one for
    capture, one for playback. Both the ADAT and S/PDIF channels appear
diff --git a/sound/pci/sis7019.c b/sound/pci/sis7019.c
index 8ffa2f53c0b5..00ab51c889da 100644
--- a/sound/pci/sis7019.c
+++ b/sound/pci/sis7019.c
@@ -24,7 +24,6 @@
 MODULE_AUTHOR("David Dillow <dave@thedillows.org>");
 MODULE_DESCRIPTION("SiS7019");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{SiS,SiS7019 Audio Accelerator}}");
 
 static int index = SNDRV_DEFAULT_IDX1;	/* Index 0-MAX */
 static char *id = SNDRV_DEFAULT_STR1;	/* ID for this card */
diff --git a/sound/pci/sonicvibes.c b/sound/pci/sonicvibes.c
index 26fd1d08c179..7de10997775f 100644
--- a/sound/pci/sonicvibes.c
+++ b/sound/pci/sonicvibes.c
@@ -29,7 +29,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("S3 SonicVibes PCI");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{S3,SonicVibes PCI}}");
 
 #if IS_REACHABLE(CONFIG_GAMEPORT)
 #define SUPPORT_JOYSTICK 1
diff --git a/sound/pci/trident/trident.c b/sound/pci/trident/trident.c
index 5bc79da6e35e..a51041205f7c 100644
--- a/sound/pci/trident/trident.c
+++ b/sound/pci/trident/trident.c
@@ -17,18 +17,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>, <audio@tridentmicro.com>");
 MODULE_DESCRIPTION("Trident 4D-WaveDX/NX & SiS SI7018");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Trident,4DWave DX},"
-		"{Trident,4DWave NX},"
-		"{SiS,SI7018 PCI Audio},"
-		"{Best Union,Miss Melody 4DWave PCI},"
-		"{HIS,4DWave PCI},"
-		"{Warpspeed,ONSpeed 4DWave PCI},"
-		"{Aztech Systems,PCI 64-Q3D},"
-		"{Addonics,SV 750},"
-		"{CHIC,True Sound 4Dwave},"
-		"{Shark,Predator4D-PCI},"
-		"{Jaton,SonicWave 4D},"
-		"{Hoontech,SoundTrack Digital 4DWave NX}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/via82xx.c b/sound/pci/via82xx.c
index 154d88ce8813..fd1f2f9cfbc3 100644
--- a/sound/pci/via82xx.c
+++ b/sound/pci/via82xx.c
@@ -56,7 +56,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("VIA VT82xx audio");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{VIA,VT82C686A/B/C,pci},{VIA,VT8233A/C,8235}}");
 
 #if IS_REACHABLE(CONFIG_GAMEPORT)
 #define SUPPORT_JOYSTICK 1
diff --git a/sound/pci/via82xx_modem.c b/sound/pci/via82xx_modem.c
index addfa196df21..30253306f67c 100644
--- a/sound/pci/via82xx_modem.c
+++ b/sound/pci/via82xx_modem.c
@@ -38,7 +38,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("VIA VT82xx modem");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{VIA,VT82C686A/B/C modem,pci}}");
 
 static int index = -2; /* Exclude the first card */
 static char *id = SNDRV_DEFAULT_STR1;	/* ID for this card */
diff --git a/sound/pci/vx222/vx222.c b/sound/pci/vx222/vx222.c
index f7800ed1b67e..2a9e1a77a81a 100644
--- a/sound/pci/vx222/vx222.c
+++ b/sound/pci/vx222/vx222.c
@@ -20,7 +20,6 @@
 MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
 MODULE_DESCRIPTION("Digigram VX222 V2/Mic");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Digigram," CARD_NAME "}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/ymfpci/ymfpci.c b/sound/pci/ymfpci/ymfpci.c
index 9b0d18a7bf35..99be1490ef0e 100644
--- a/sound/pci/ymfpci/ymfpci.c
+++ b/sound/pci/ymfpci/ymfpci.c
@@ -17,12 +17,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Yamaha DS-1 PCI");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Yamaha,YMF724},"
-		"{Yamaha,YMF724F},"
-		"{Yamaha,YMF740},"
-		"{Yamaha,YMF740C},"
-		"{Yamaha,YMF744},"
-		"{Yamaha,YMF754}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf.c b/sound/pcmcia/pdaudiocf/pdaudiocf.c
index 27d9da6d61e8..144582350a05 100644
--- a/sound/pcmcia/pdaudiocf/pdaudiocf.c
+++ b/sound/pcmcia/pdaudiocf/pdaudiocf.c
@@ -22,7 +22,6 @@
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Sound Core " CARD_NAME);
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Sound Core," CARD_NAME "}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pcmcia/vx/vxpocket.c b/sound/pcmcia/vx/vxpocket.c
index afd30a90c807..636320489805 100644
--- a/sound/pcmcia/vx/vxpocket.c
+++ b/sound/pcmcia/vx/vxpocket.c
@@ -17,13 +17,9 @@
 #include <sound/initval.h>
 #include <sound/tlv.h>
 
-/*
- */
-
 MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
 MODULE_DESCRIPTION("Digigram VXPocket");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Digigram,VXPocket},{Digigram,VXPocket440}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/ppc/powermac.c b/sound/ppc/powermac.c
index 96ef55082bf9..9fb51ebafde1 100644
--- a/sound/ppc/powermac.c
+++ b/sound/ppc/powermac.c
@@ -18,7 +18,6 @@
 #define CHIP_NAME "PMac"
 
 MODULE_DESCRIPTION("PowerMac");
-MODULE_SUPPORTED_DEVICE("{{Apple,PowerMac}}");
 MODULE_LICENSE("GPL");
 
 static int index = SNDRV_DEFAULT_IDX1;		/* Index 0-MAX */
diff --git a/sound/sh/aica.c b/sound/sh/aica.c
index 8fa68432d3c1..6e9d6bd67369 100644
--- a/sound/sh/aica.c
+++ b/sound/sh/aica.c
@@ -32,7 +32,6 @@
 MODULE_AUTHOR("Adrian McMenamin <adrian@mcmen.demon.co.uk>");
 MODULE_DESCRIPTION("Dreamcast AICA sound (pcm) driver");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Yamaha/SEGA, AICA}}");
 MODULE_FIRMWARE("aica_firmware.bin");
 
 /* module parameters */
diff --git a/sound/sh/sh_dac_audio.c b/sound/sh/sh_dac_audio.c
index feb28502940f..8ebd972846ac 100644
--- a/sound/sh/sh_dac_audio.c
+++ b/sound/sh/sh_dac_audio.c
@@ -25,7 +25,6 @@
 MODULE_AUTHOR("Rafael Ignacio Zurita <rizurita@yahoo.com>");
 MODULE_DESCRIPTION("SuperH DAC audio driver");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{SuperH DAC audio support}}");
 
 /* Module Parameters */
 static int index = SNDRV_DEFAULT_IDX1;
diff --git a/sound/sparc/amd7930.c b/sound/sparc/amd7930.c
index 9d0da5fa1c70..d24ae00878f5 100644
--- a/sound/sparc/amd7930.c
+++ b/sound/sparc/amd7930.c
@@ -62,7 +62,6 @@ MODULE_PARM_DESC(enable, "Enable Sun AMD7930 soundcard.");
 MODULE_AUTHOR("Thomas K. Dyas and David S. Miller");
 MODULE_DESCRIPTION("Sun AMD7930");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Sun,AMD7930}}");
 
 /* Device register layout.  */
 
diff --git a/sound/sparc/cs4231.c b/sound/sparc/cs4231.c
index 0eed5f79a2bf..35c17803a430 100644
--- a/sound/sparc/cs4231.c
+++ b/sound/sparc/cs4231.c
@@ -52,7 +52,6 @@ MODULE_PARM_DESC(enable, "Enable Sun CS4231 soundcard.");
 MODULE_AUTHOR("Jaroslav Kysela, Derrick J. Brashear and David S. Miller");
 MODULE_DESCRIPTION("Sun CS4231");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Sun,CS4231}}");
 
 #ifdef SBUS_SUPPORT
 struct sbus_dma_info {
diff --git a/sound/sparc/dbri.c b/sound/sparc/dbri.c
index 5a6fb66dd118..b055f5839578 100644
--- a/sound/sparc/dbri.c
+++ b/sound/sparc/dbri.c
@@ -76,7 +76,6 @@
 MODULE_AUTHOR("Rudolf Koenig, Brent Baccala and Martin Habets");
 MODULE_DESCRIPTION("Sun DBRI");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Sun,DBRI}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/usb/6fire/chip.c b/sound/usb/6fire/chip.c
index 08c6e6a52eb9..33e962178c93 100644
--- a/sound/usb/6fire/chip.c
+++ b/sound/usb/6fire/chip.c
@@ -26,7 +26,6 @@
 MODULE_AUTHOR("Torsten Schenk <torsten.schenk@zoho.com>");
 MODULE_DESCRIPTION("TerraTec DMX 6Fire USB audio driver");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{TerraTec,DMX 6Fire USB}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-max */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* Id for card */
diff --git a/sound/usb/caiaq/device.c b/sound/usb/caiaq/device.c
index e03481caf7f6..49f63f878e6f 100644
--- a/sound/usb/caiaq/device.c
+++ b/sound/usb/caiaq/device.c
@@ -26,20 +26,6 @@
 MODULE_AUTHOR("Daniel Mack <daniel@caiaq.de>");
 MODULE_DESCRIPTION("caiaq USB audio");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Native Instruments,RigKontrol2},"
-			 "{Native Instruments,RigKontrol3},"
-			 "{Native Instruments,Kore Controller},"
-			 "{Native Instruments,Kore Controller 2},"
-			 "{Native Instruments,Audio Kontrol 1},"
-			 "{Native Instruments,Audio 2 DJ},"
-			 "{Native Instruments,Audio 4 DJ},"
-			 "{Native Instruments,Audio 8 DJ},"
-			 "{Native Instruments,Traktor Audio 2},"
-			 "{Native Instruments,Session I/O},"
-			 "{Native Instruments,GuitarRig mobile},"
-			 "{Native Instruments,Traktor Kontrol X1},"
-			 "{Native Instruments,Traktor Kontrol S4},"
-			 "{Native Instruments,Maschine Controller}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-max */
 static char* id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* Id for this card */
diff --git a/sound/usb/card.c b/sound/usb/card.c
index b6f4c0848e66..0826a437f8fc 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -58,8 +58,6 @@
 MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
 MODULE_DESCRIPTION("USB Audio");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Generic,USB Audio}}");
-
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/usb/hiface/chip.c b/sound/usb/hiface/chip.c
index c2824188d142..95385e90882c 100644
--- a/sound/usb/hiface/chip.c
+++ b/sound/usb/hiface/chip.c
@@ -21,23 +21,6 @@ MODULE_AUTHOR("Michael Trimarchi <michael@amarulasolutions.com>");
 MODULE_AUTHOR("Antonio Ospite <ao2@amarulasolutions.com>");
 MODULE_DESCRIPTION("M2Tech hiFace USB-SPDIF audio driver");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{M2Tech,Young},"
-			 "{M2Tech,hiFace},"
-			 "{M2Tech,North Star},"
-			 "{M2Tech,W4S Young},"
-			 "{M2Tech,Corrson},"
-			 "{M2Tech,AUDIA},"
-			 "{M2Tech,SL Audio},"
-			 "{M2Tech,Empirical},"
-			 "{M2Tech,Rockna},"
-			 "{M2Tech,Pathos},"
-			 "{M2Tech,Metronome},"
-			 "{M2Tech,CAD},"
-			 "{M2Tech,Audio Esclusive},"
-			 "{M2Tech,Rotel},"
-			 "{M2Tech,Eeaudio},"
-			 "{The Chord Company,CHORD},"
-			 "{AVA Group A/S,Vitus}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-max */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* Id for card */
diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c
index 6b30155964ec..5834d1dc317e 100644
--- a/sound/usb/misc/ua101.c
+++ b/sound/usb/misc/ua101.c
@@ -19,7 +19,6 @@
 MODULE_DESCRIPTION("Edirol UA-101/1000 driver");
 MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{Edirol,UA-101},{Edirol,UA-1000}}");
 
 /*
  * Should not be lower than the minimum scheduling delay of the host
diff --git a/sound/usb/usx2y/usbusx2y.c b/sound/usb/usx2y/usbusx2y.c
index c54158146917..3cd28d24f0a7 100644
--- a/sound/usb/usx2y/usbusx2y.c
+++ b/sound/usb/usx2y/usbusx2y.c
@@ -137,7 +137,6 @@
 MODULE_AUTHOR("Karsten Wiese <annabellesgarden@yahoo.de>");
 MODULE_DESCRIPTION("TASCAM "NAME_ALLCAPS" Version 0.8.7.2");
 MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{TASCAM(0x1604),"NAME_ALLCAPS"(0x8001)(0x8005)(0x8007)}}");
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-max */
 static char* id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* Id for this card */
diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c
index 1d66c3a4fb10..33b12aa67cf5 100644
--- a/sound/x86/intel_hdmi_audio.c
+++ b/sound/x86/intel_hdmi_audio.c
@@ -1887,4 +1887,3 @@ MODULE_AUTHOR("Vaibhav Agarwal <vaibhav.agarwal@intel.com>");
 MODULE_AUTHOR("Jerome Anand <jerome.anand@intel.com>");
 MODULE_DESCRIPTION("Intel HDMI Audio driver");
 MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{Intel,Intel_HAD}");
diff --git a/sound/xen/xen_snd_front.c b/sound/xen/xen_snd_front.c
index 228d82031297..2cb0a19be2b8 100644
--- a/sound/xen/xen_snd_front.c
+++ b/sound/xen/xen_snd_front.c
@@ -391,4 +391,3 @@ module_exit(xen_drv_fini);
 MODULE_DESCRIPTION("Xen virtual sound device frontend");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("xen:" XENSND_DRIVER_NAME);
-MODULE_SUPPORTED_DEVICE("{{ALSA,Virtual soundcard}}");

From 9858af27e69247c5d04c3b093190a93ca365f33d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 11 Mar 2021 10:44:45 +0000
Subject: [PATCH 0977/1820] usbip: Fix incorrect double assignment to
 udc->ud.tcp_rx

Currently udc->ud.tcp_rx is being assigned twice, the second assignment
is incorrect, it should be to udc->ud.tcp_tx instead of rx. Fix this.

Fixes: 46613c9dfa96 ("usbip: fix vudc usbip_sockfd_store races leading to gpf")
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Cc: stable <stable@vger.kernel.org>
Addresses-Coverity: ("Unused value")
Link: https://lore.kernel.org/r/20210311104445.7811-1-colin.king@canonical.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/vudc_sysfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/usbip/vudc_sysfs.c b/drivers/usb/usbip/vudc_sysfs.c
index a3ec39fc6177..7383a543c6d1 100644
--- a/drivers/usb/usbip/vudc_sysfs.c
+++ b/drivers/usb/usbip/vudc_sysfs.c
@@ -174,7 +174,7 @@ static ssize_t usbip_sockfd_store(struct device *dev,
 
 		udc->ud.tcp_socket = socket;
 		udc->ud.tcp_rx = tcp_rx;
-		udc->ud.tcp_rx = tcp_tx;
+		udc->ud.tcp_tx = tcp_tx;
 		udc->ud.status = SDEV_ST_USED;
 
 		spin_unlock_irq(&udc->ud.lock);

From 98f153a10da403ddd5e9d98a3c8c2bb54bb5a0b6 Mon Sep 17 00:00:00 2001
From: Jim Lin <jilin@nvidia.com>
Date: Thu, 11 Mar 2021 14:42:41 +0800
Subject: [PATCH 0978/1820] usb: gadget: configfs: Fix KASAN use-after-free

When gadget is disconnected, running sequence is like this.
. composite_disconnect
. Call trace:
  usb_string_copy+0xd0/0x128
  gadget_config_name_configuration_store+0x4
  gadget_config_name_attr_store+0x40/0x50
  configfs_write_file+0x198/0x1f4
  vfs_write+0x100/0x220
  SyS_write+0x58/0xa8
. configfs_composite_unbind
. configfs_composite_bind

In configfs_composite_bind, it has
"cn->strings.s = cn->configuration;"

When usb_string_copy is invoked. it would
allocate memory, copy input string, release previous pointed memory space,
and use new allocated memory.

When gadget is connected, host sends down request to get information.
Call trace:
  usb_gadget_get_string+0xec/0x168
  lookup_string+0x64/0x98
  composite_setup+0xa34/0x1ee8

If gadget is disconnected and connected quickly, in the failed case,
cn->configuration memory has been released by usb_string_copy kfree but
configfs_composite_bind hasn't been run in time to assign new allocated
"cn->configuration" pointer to "cn->strings.s".

When "strlen(s->s) of usb_gadget_get_string is being executed, the dangling
memory is accessed, "BUG: KASAN: use-after-free" error occurs.

Cc: stable@vger.kernel.org
Signed-off-by: Jim Lin <jilin@nvidia.com>
Signed-off-by: Macpaul Lin <macpaul.lin@mediatek.com>
Link: https://lore.kernel.org/r/1615444961-13376-1-git-send-email-macpaul.lin@mediatek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/configfs.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 0d56f33d63c2..15a607ccef8a 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -97,6 +97,8 @@ struct gadget_config_name {
 	struct list_head list;
 };
 
+#define USB_MAX_STRING_WITH_NULL_LEN	(USB_MAX_STRING_LEN+1)
+
 static int usb_string_copy(const char *s, char **s_copy)
 {
 	int ret;
@@ -106,12 +108,16 @@ static int usb_string_copy(const char *s, char **s_copy)
 	if (ret > USB_MAX_STRING_LEN)
 		return -EOVERFLOW;
 
-	str = kstrdup(s, GFP_KERNEL);
-	if (!str)
-		return -ENOMEM;
+	if (copy) {
+		str = copy;
+	} else {
+		str = kmalloc(USB_MAX_STRING_WITH_NULL_LEN, GFP_KERNEL);
+		if (!str)
+			return -ENOMEM;
+	}
+	strcpy(str, s);
 	if (str[ret - 1] == '\n')
 		str[ret - 1] = '\0';
-	kfree(copy);
 	*s_copy = str;
 	return 0;
 }

From 546aa0e4ea6ed81b6c51baeebc4364542fa3f3a7 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Wed, 17 Mar 2021 15:06:54 -0400
Subject: [PATCH 0979/1820] usb-storage: Add quirk to defeat Kindle's automatic
 unload

Matthias reports that the Amazon Kindle automatically removes its
emulated media if it doesn't receive another SCSI command within about
one second after a SYNCHRONIZE CACHE.  It does so even when the host
has sent a PREVENT MEDIUM REMOVAL command.  The reason for this
behavior isn't clear, although it's not hard to make some guesses.

At any rate, the results can be unexpected for anyone who tries to
access the Kindle in an unusual fashion, and in theory they can lead
to data loss (for example, if one file is closed and synchronized
while other files are still in the middle of being written).

To avoid such problems, this patch creates a new usb-storage quirks
flag telling the driver always to issue a REQUEST SENSE following a
SYNCHRONIZE CACHE command, and adds an unusual_devs entry for the
Kindle with the flag set.  This is sufficient to prevent the Kindle
from doing its automatic unload, without interfering with proper
operation.

Another possible way to deal with this would be to increase the
frequency of TEST UNIT READY polling that the kernel normally carries
out for removable-media storage devices.  However that would increase
the overall load on the system and it is not as reliable, because the
user can override the polling interval.  Changing the driver's
behavior is safer and has minimal overhead.

CC: <stable@vger.kernel.org>
Reported-and-tested-by: Matthias Schwarzott <zzam@gentoo.org>
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20210317190654.GA497856@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/storage/transport.c    |  7 +++++++
 drivers/usb/storage/unusual_devs.h | 12 ++++++++++++
 include/linux/usb_usual.h          |  2 ++
 3 files changed, 21 insertions(+)

diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index 5eb895b19c55..f4304ce69350 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -656,6 +656,13 @@ void usb_stor_invoke_transport(struct scsi_cmnd *srb, struct us_data *us)
 		need_auto_sense = 1;
 	}
 
+	/* Some devices (Kindle) require another command after SYNC CACHE */
+	if ((us->fflags & US_FL_SENSE_AFTER_SYNC) &&
+			srb->cmnd[0] == SYNCHRONIZE_CACHE) {
+		usb_stor_dbg(us, "-- sense after SYNC CACHE\n");
+		need_auto_sense = 1;
+	}
+
 	/*
 	 * If we have a failure, we're going to do a REQUEST_SENSE 
 	 * automatically.  Note that we differentiate between a command
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 5732e9691f08..efa972be2ee3 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2211,6 +2211,18 @@ UNUSUAL_DEV( 0x1908, 0x3335, 0x0200, 0x0200,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_READ_DISC_INFO ),
 
+/*
+ * Reported by Matthias Schwarzott <zzam@gentoo.org>
+ * The Amazon Kindle treats SYNCHRONIZE CACHE as an indication that
+ * the host may be finished with it, and automatically ejects its
+ * emulated media unless it receives another command within one second.
+ */
+UNUSUAL_DEV( 0x1949, 0x0004, 0x0000, 0x9999,
+		"Amazon",
+		"Kindle",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_SENSE_AFTER_SYNC ),
+
 /*
  * Reported by Oliver Neukum <oneukum@suse.com>
  * This device morphes spontaneously into another device if the access
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index 6b03fdd69d27..712363c7a2e8 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -86,6 +86,8 @@
 		/* lies about caching, so always sync */	\
 	US_FLAG(NO_SAME, 0x40000000)				\
 		/* Cannot handle WRITE_SAME */			\
+	US_FLAG(SENSE_AFTER_SYNC, 0x80000000)			\
+		/* Do REQUEST_SENSE after SYNCHRONIZE_CACHE */	\
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };

From 3cac9104bea41099cf622091f0c0538bcb19050d Mon Sep 17 00:00:00 2001
From: Elias Rudberg <mail@eliasrudberg.se>
Date: Thu, 11 Mar 2021 13:47:10 +0100
Subject: [PATCH 0980/1820] usb: typec: Remove vdo[3] part of
 tps6598x_rx_identity_reg struct
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the unused "u32 vdo[3]" part in the tps6598x_rx_identity_reg
struct. This helps avoid "failed to register partner" errors which
happen when tps6598x_read_partner_identity() fails because the
amount of data read is 12 bytes smaller than the struct size.
Note that vdo[3] is already in usb_pd_identity and hence
shouldn't be added to tps6598x_rx_identity_reg as well.

Fixes: f6c56ca91b92 ("usb: typec: Add the Product Type VDOs to struct usb_pd_identity")
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Guido Günther <agx@sigxcpu.org>
Signed-off-by: Elias Rudberg <mail@eliasrudberg.se>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210311124710.6563-1-mail@eliasrudberg.se
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tps6598x.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/usb/typec/tps6598x.c b/drivers/usb/typec/tps6598x.c
index 6e6ef6317523..29bd1c5a283c 100644
--- a/drivers/usb/typec/tps6598x.c
+++ b/drivers/usb/typec/tps6598x.c
@@ -64,7 +64,6 @@ enum {
 struct tps6598x_rx_identity_reg {
 	u8 status;
 	struct usb_pd_identity identity;
-	u32 vdo[3];
 } __packed;
 
 /* Standard Task return codes */

From 86629e098a077922438efa98dc80917604dfd317 Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Wed, 17 Mar 2021 11:12:48 -0700
Subject: [PATCH 0981/1820] usb: typec: tcpm: Invoke power_supply_changed for
 tcpm-source-psy-

tcpm-source-psy- does not invoke power_supply_changed API when
one of the published power supply properties is changed.
power_supply_changed needs to be called to notify
userspace clients(uevents) and kernel clients.

Fixes: f2a8aa053c176 ("typec: tcpm: Represent source supply through power_supply")
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210317181249.1062995-1-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index be0b6469dd3d..92093ea12cff 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -942,6 +942,7 @@ static int tcpm_set_current_limit(struct tcpm_port *port, u32 max_ma, u32 mv)
 
 	port->supply_voltage = mv;
 	port->current_limit = max_ma;
+	power_supply_changed(port->psy);
 
 	if (port->tcpc->set_current_limit)
 		ret = port->tcpc->set_current_limit(port->tcpc, max_ma, mv);
@@ -2928,6 +2929,7 @@ static int tcpm_pd_select_pdo(struct tcpm_port *port, int *sink_pdo,
 
 	port->pps_data.supported = false;
 	port->usb_type = POWER_SUPPLY_USB_TYPE_PD;
+	power_supply_changed(port->psy);
 
 	/*
 	 * Select the source PDO providing the most power which has a
@@ -2952,6 +2954,7 @@ static int tcpm_pd_select_pdo(struct tcpm_port *port, int *sink_pdo,
 				port->pps_data.supported = true;
 				port->usb_type =
 					POWER_SUPPLY_USB_TYPE_PD_PPS;
+				power_supply_changed(port->psy);
 			}
 			continue;
 		default:
@@ -3109,6 +3112,7 @@ static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port)
 						  port->pps_data.out_volt));
 		port->pps_data.op_curr = min(port->pps_data.max_curr,
 					     port->pps_data.op_curr);
+		power_supply_changed(port->psy);
 	}
 
 	return src_pdo;
@@ -3344,6 +3348,7 @@ static int tcpm_set_charge(struct tcpm_port *port, bool charge)
 			return ret;
 	}
 	port->vbus_charge = charge;
+	power_supply_changed(port->psy);
 	return 0;
 }
 
@@ -3523,6 +3528,7 @@ static void tcpm_reset_port(struct tcpm_port *port)
 	port->try_src_count = 0;
 	port->try_snk_count = 0;
 	port->usb_type = POWER_SUPPLY_USB_TYPE_C;
+	power_supply_changed(port->psy);
 	port->nr_sink_caps = 0;
 	port->sink_cap_done = false;
 	if (port->tcpc->enable_frs)
@@ -5905,7 +5911,7 @@ static int tcpm_psy_set_prop(struct power_supply *psy,
 		ret = -EINVAL;
 		break;
 	}
-
+	power_supply_changed(port->psy);
 	return ret;
 }
 
@@ -6058,6 +6064,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	err = devm_tcpm_psy_register(port);
 	if (err)
 		goto out_role_sw_put;
+	power_supply_changed(port->psy);
 
 	port->typec_port = typec_register_port(port->dev, &port->typec_caps);
 	if (IS_ERR(port->typec_port)) {

From f09ddcfcb8c569675066337adac2ac205113471f Mon Sep 17 00:00:00 2001
From: Wesley Cheng <wcheng@codeaurora.org>
Date: Thu, 11 Mar 2021 15:59:02 -0800
Subject: [PATCH 0982/1820] usb: dwc3: gadget: Prevent EP queuing while
 stopping transfers

In the situations where the DWC3 gadget stops active transfers, once
calling the dwc3_gadget_giveback(), there is a chance where a function
driver can queue a new USB request in between the time where the dwc3
lock has been released and re-aquired.  This occurs after we've already
issued an ENDXFER command.  When the stop active transfers continues
to remove USB requests from all dep lists, the newly added request will
also be removed, while controller still has an active TRB for it.
This can lead to the controller accessing an unmapped memory address.

Fix this by ensuring parameters to prevent EP queuing are set before
calling the stop active transfers API.

Fixes: ae7e86108b12 ("usb: dwc3: Stop active transfers before halting the controller")
Signed-off-by: Wesley Cheng <wcheng@codeaurora.org>
Link: https://lore.kernel.org/r/1615507142-23097-1-git-send-email-wcheng@codeaurora.org
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/gadget.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index aebcf8ec0716..4a337f348651 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -783,8 +783,6 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep)
 
 	trace_dwc3_gadget_ep_disable(dep);
 
-	dwc3_remove_requests(dwc, dep);
-
 	/* make sure HW endpoint isn't stalled */
 	if (dep->flags & DWC3_EP_STALL)
 		__dwc3_gadget_ep_set_halt(dep, 0, false);
@@ -803,6 +801,8 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep)
 		dep->endpoint.desc = NULL;
 	}
 
+	dwc3_remove_requests(dwc, dep);
+
 	return 0;
 }
 
@@ -1617,7 +1617,7 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req)
 {
 	struct dwc3		*dwc = dep->dwc;
 
-	if (!dep->endpoint.desc || !dwc->pullups_connected) {
+	if (!dep->endpoint.desc || !dwc->pullups_connected || !dwc->connected) {
 		dev_err(dwc->dev, "%s: can't queue to disabled endpoint\n",
 				dep->name);
 		return -ESHUTDOWN;
@@ -2247,6 +2247,7 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on)
 	if (!is_on) {
 		u32 count;
 
+		dwc->connected = false;
 		/*
 		 * In the Synopsis DesignWare Cores USB3 Databook Rev. 3.30a
 		 * Section 4.1.8 Table 4-7, it states that for a device-initiated
@@ -2271,7 +2272,6 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on)
 			dwc->ev_buf->lpos = (dwc->ev_buf->lpos + count) %
 						dwc->ev_buf->length;
 		}
-		dwc->connected = false;
 	} else {
 		__dwc3_gadget_start(dwc);
 	}
@@ -3321,8 +3321,6 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc)
 {
 	u32			reg;
 
-	dwc->connected = true;
-
 	/*
 	 * WORKAROUND: DWC3 revisions <1.88a have an issue which
 	 * would cause a missing Disconnect Event if there's a
@@ -3362,6 +3360,7 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc)
 	 * transfers."
 	 */
 	dwc3_stop_active_transfers(dwc);
+	dwc->connected = true;
 
 	reg = dwc3_readl(dwc->regs, DWC3_DCTL);
 	reg &= ~DWC3_DCTL_TSTCTRL_MASK;

From 1b1597e64e1a610c7a96710fc4717158e98a08b3 Mon Sep 17 00:00:00 2001
From: Piotr Krysiuk <piotras@gmail.com>
Date: Tue, 16 Mar 2021 09:47:02 +0100
Subject: [PATCH 0983/1820] bpf: Add sanity check for upper ptr_limit

Given we know the max possible value of ptr_limit at the time of retrieving
the latter, add basic assertions, so that the verifier can bail out if
anything looks odd and reject the program. Nothing triggered this so far,
but it also does not hurt to have these.

Signed-off-by: Piotr Krysiuk <piotras@gmail.com>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d16722a99b61..44e4ec1640f1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5861,10 +5861,14 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 {
 	bool mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
 			    (opcode == BPF_SUB && !off_is_neg);
-	u32 off;
+	u32 off, max;
 
 	switch (ptr_reg->type) {
 	case PTR_TO_STACK:
+		/* Offset 0 is out-of-bounds, but acceptable start for the
+		 * left direction, see BPF_REG_FP.
+		 */
+		max = MAX_BPF_STACK + mask_to_left;
 		/* Indirect variable offset stack access is prohibited in
 		 * unprivileged mode so it's not handled here.
 		 */
@@ -5873,15 +5877,16 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 			*ptr_limit = MAX_BPF_STACK + off;
 		else
 			*ptr_limit = -off - 1;
-		return 0;
+		return *ptr_limit >= max ? -ERANGE : 0;
 	case PTR_TO_MAP_VALUE:
+		max = ptr_reg->map_ptr->value_size;
 		if (mask_to_left) {
 			*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
 		} else {
 			off = ptr_reg->smin_value + ptr_reg->off;
 			*ptr_limit = ptr_reg->map_ptr->value_size - off - 1;
 		}
-		return 0;
+		return *ptr_limit >= max ? -ERANGE : 0;
 	default:
 		return -EINVAL;
 	}

From 0a13e3537ea67452d549a6a80da3776d6b7dedb3 Mon Sep 17 00:00:00 2001
From: Piotr Krysiuk <piotras@gmail.com>
Date: Tue, 16 Mar 2021 11:44:42 +0100
Subject: [PATCH 0984/1820] bpf, selftests: Fix up some test_verifier cases for
 unprivileged

Fix up test_verifier error messages for the case where the original error
message changed, or for the case where pointer alu errors differ between
privileged and unprivileged tests. Also, add alternative tests for keeping
coverage of the original verifier rejection error message (fp alu), and
newly reject map_ptr += rX where rX == 0 given we now forbid alu on these
types for unprivileged. All test_verifier cases pass after the change. The
test case fixups were kept separate to ease backporting of core changes.

Signed-off-by: Piotr Krysiuk <piotras@gmail.com>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/verifier/bounds_deduction.c | 27 +++++++++++++------
 .../testing/selftests/bpf/verifier/map_ptr.c  |  4 +++
 tools/testing/selftests/bpf/verifier/unpriv.c | 15 ++++++++++-
 .../selftests/bpf/verifier/value_ptr_arith.c  | 23 +++++++++++++++-
 4 files changed, 59 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/bpf/verifier/bounds_deduction.c b/tools/testing/selftests/bpf/verifier/bounds_deduction.c
index 1fd07a4f27ac..c162498a64fc 100644
--- a/tools/testing/selftests/bpf/verifier/bounds_deduction.c
+++ b/tools/testing/selftests/bpf/verifier/bounds_deduction.c
@@ -6,8 +6,9 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
 	.errstr = "R0 tried to subtract pointer from scalar",
+	.result = REJECT,
 },
 {
 	"check deducing bounds from const, 2",
@@ -20,6 +21,8 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
 		BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R1 tried to sub from different maps, paths, or prohibited types",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 1,
 },
@@ -31,8 +34,9 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
 	.errstr = "R0 tried to subtract pointer from scalar",
+	.result = REJECT,
 },
 {
 	"check deducing bounds from const, 4",
@@ -45,6 +49,8 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
 		BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R1 tried to sub from different maps, paths, or prohibited types",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -55,8 +61,9 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
 	.errstr = "R0 tried to subtract pointer from scalar",
+	.result = REJECT,
 },
 {
 	"check deducing bounds from const, 6",
@@ -67,8 +74,9 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
 	.errstr = "R0 tried to subtract pointer from scalar",
+	.result = REJECT,
 },
 {
 	"check deducing bounds from const, 7",
@@ -80,8 +88,9 @@
 			    offsetof(struct __sk_buff, mark)),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R1 tried to sub from different maps, paths, or prohibited types",
 	.errstr = "dereference of modified ctx ptr",
+	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
@@ -94,8 +103,9 @@
 			    offsetof(struct __sk_buff, mark)),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
 	.errstr = "dereference of modified ctx ptr",
+	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
@@ -106,8 +116,9 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
 	.errstr = "R0 tried to subtract pointer from scalar",
+	.result = REJECT,
 },
 {
 	"check deducing bounds from const, 10",
@@ -119,6 +130,6 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
 	.errstr = "math between ctx pointer and register with unbounded min value is not allowed",
+	.result = REJECT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c
index b117bdd3806d..6f610cfddae5 100644
--- a/tools/testing/selftests/bpf/verifier/map_ptr.c
+++ b/tools/testing/selftests/bpf/verifier/map_ptr.c
@@ -75,6 +75,8 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_16b = { 4 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
 	.result = ACCEPT,
 },
 {
@@ -91,5 +93,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_16b = { 4 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
 	.result = ACCEPT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c
index b018ad71e0a8..3e32400c4b44 100644
--- a/tools/testing/selftests/bpf/verifier/unpriv.c
+++ b/tools/testing/selftests/bpf/verifier/unpriv.c
@@ -497,7 +497,7 @@
 	.result = ACCEPT,
 },
 {
-	"unpriv: adding of fp",
+	"unpriv: adding of fp, reg",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_MOV64_IMM(BPF_REG_1, 0),
@@ -505,6 +505,19 @@
 	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
+	.result_unpriv = REJECT,
+	.result = ACCEPT,
+},
+{
+	"unpriv: adding of fp, imm",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0),
+	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
+	BPF_EXIT_INSN(),
+	},
 	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index ed4e76b24649..feb91266db39 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -169,7 +169,7 @@
 	.fixup_map_array_48b = { 1 },
 	.result = ACCEPT,
 	.result_unpriv = REJECT,
-	.errstr_unpriv = "R2 tried to add from different maps or paths",
+	.errstr_unpriv = "R2 tried to add from different maps, paths, or prohibited types",
 	.retval = 0,
 },
 {
@@ -516,6 +516,27 @@
 	.result = ACCEPT,
 	.retval = 0xabcdef12,
 },
+{
+	"map access: value_ptr += N, value_ptr -= N known scalar",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+	BPF_MOV32_IMM(BPF_REG_1, 0x12345678),
+	BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2),
+	BPF_MOV64_IMM(BPF_REG_1, 2),
+	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 3 },
+	.result = ACCEPT,
+	.retval = 0x12345678,
+},
 {
 	"map access: unknown scalar += value_ptr, 1",
 	.insns = {

From 7ad48d27a2846bfda29214fb454d001c3e02b9e7 Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Wed, 17 Mar 2021 09:40:38 -0700
Subject: [PATCH 0985/1820] drm/msm: Ratelimit invalid-fence message

We have seen a couple cases where low memory situations cause something
bad to happen, followed by a flood of these messages obscuring the root
cause.  Lets ratelimit the dmesg spam so that next time it happens we
don't lose the kernel traces leading up to this.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
---
 drivers/gpu/drm/msm/msm_fence.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
index ad2703698b05..cd59a5918038 100644
--- a/drivers/gpu/drm/msm/msm_fence.c
+++ b/drivers/gpu/drm/msm/msm_fence.c
@@ -45,7 +45,7 @@ int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence,
 	int ret;
 
 	if (fence > fctx->last_fence) {
-		DRM_ERROR("%s: waiting on invalid fence: %u (of %u)\n",
+		DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n",
 				fctx->name, fence, fctx->last_fence);
 		return -EINVAL;
 	}

From cb038357937ee4f589aab2469ec3896dce90f317 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 16 Mar 2021 15:36:47 -0700
Subject: [PATCH 0986/1820] net: fix race between napi kthread mode and busy
 poll

Currently, napi_thread_wait() checks for NAPI_STATE_SCHED bit to
determine if the kthread owns this napi and could call napi->poll() on
it. However, if socket busy poll is enabled, it is possible that the
busy poll thread grabs this SCHED bit (after the previous napi->poll()
invokes napi_complete_done() and clears SCHED bit) and tries to poll
on the same napi. napi_disable() could grab the SCHED bit as well.
This patch tries to fix this race by adding a new bit
NAPI_STATE_SCHED_THREADED in napi->state. This bit gets set in
____napi_schedule() if the threaded mode is enabled, and gets cleared
in napi_complete_done(), and we only poll the napi in kthread if this
bit is set. This helps distinguish the ownership of the napi between
kthread and other scenarios and fixes the race issue.

Fixes: 29863d41bb6e ("net: implement threaded-able napi poll loop support")
Reported-by: Martin Zaharinov <micron10@gmail.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Wei Wang <weiwan@google.com>
Cc: Alexander Duyck <alexanderduyck@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  2 ++
 net/core/dev.c            | 19 ++++++++++++++++++-
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5b67ea89d5f2..87a5d186faff 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -360,6 +360,7 @@ enum {
 	NAPI_STATE_IN_BUSY_POLL,	/* sk_busy_loop() owns this NAPI */
 	NAPI_STATE_PREFER_BUSY_POLL,	/* prefer busy-polling over softirq processing*/
 	NAPI_STATE_THREADED,		/* The poll is performed inside its own thread*/
+	NAPI_STATE_SCHED_THREADED,	/* Napi is currently scheduled in threaded mode */
 };
 
 enum {
@@ -372,6 +373,7 @@ enum {
 	NAPIF_STATE_IN_BUSY_POLL	= BIT(NAPI_STATE_IN_BUSY_POLL),
 	NAPIF_STATE_PREFER_BUSY_POLL	= BIT(NAPI_STATE_PREFER_BUSY_POLL),
 	NAPIF_STATE_THREADED		= BIT(NAPI_STATE_THREADED),
+	NAPIF_STATE_SCHED_THREADED	= BIT(NAPI_STATE_SCHED_THREADED),
 };
 
 enum gro_result {
diff --git a/net/core/dev.c b/net/core/dev.c
index a142a207fc1d..bb568f7cb81b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4294,6 +4294,13 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 		 */
 		thread = READ_ONCE(napi->thread);
 		if (thread) {
+			/* Avoid doing set_bit() if the thread is in
+			 * INTERRUPTIBLE state, cause napi_thread_wait()
+			 * makes sure to proceed with napi polling
+			 * if the thread is explicitly woken from here.
+			 */
+			if (READ_ONCE(thread->state) != TASK_INTERRUPTIBLE)
+				set_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
 			wake_up_process(thread);
 			return;
 		}
@@ -6486,6 +6493,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
 
 		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
+			      NAPIF_STATE_SCHED_THREADED |
 			      NAPIF_STATE_PREFER_BUSY_POLL);
 
 		/* If STATE_MISSED was set, leave STATE_SCHED set,
@@ -6968,16 +6976,25 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 
 static int napi_thread_wait(struct napi_struct *napi)
 {
+	bool woken = false;
+
 	set_current_state(TASK_INTERRUPTIBLE);
 
 	while (!kthread_should_stop() && !napi_disable_pending(napi)) {
-		if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
+		/* Testing SCHED_THREADED bit here to make sure the current
+		 * kthread owns this napi and could poll on this napi.
+		 * Testing SCHED bit is not enough because SCHED bit might be
+		 * set by some other busy poll thread or by napi_disable().
+		 */
+		if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) {
 			WARN_ON(!list_empty(&napi->poll_list));
 			__set_current_state(TASK_RUNNING);
 			return 0;
 		}
 
 		schedule();
+		/* woken being true indicates this thread owns this napi. */
+		woken = true;
 		set_current_state(TASK_INTERRUPTIBLE);
 	}
 	__set_current_state(TASK_RUNNING);

From e21aa341785c679dd409c8cb71f864c00fe6c463 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 16 Mar 2021 14:00:07 -0700
Subject: [PATCH 0987/1820] bpf: Fix fexit trampoline.

The fexit/fmod_ret programs can be attached to kernel functions that can sleep.
The synchronize_rcu_tasks() will not wait for such tasks to complete.
In such case the trampoline image will be freed and when the task
wakes up the return IP will point to freed memory causing the crash.
Solve this by adding percpu_ref_get/put for the duration of trampoline
and separate trampoline vs its image life times.
The "half page" optimization has to be removed, since
first_half->second_half->first_half transition cannot be guaranteed to
complete in deterministic time. Every trampoline update becomes a new image.
The image with fmod_ret or fexit progs will be freed via percpu_ref_kill and
call_rcu_tasks. Together they will wait for the original function and
trampoline asm to complete. The trampoline is patched from nop to jmp to skip
fexit progs. They are freed independently from the trampoline. The image with
fentry progs only will be freed via call_rcu_tasks_trace+call_rcu_tasks which
will wait for both sleepable and non-sleepable progs to complete.

Fixes: fec56f5890d9 ("bpf: Introduce BPF trampoline")
Reported-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Paul E. McKenney <paulmck@kernel.org>  # for RCU
Link: https://lore.kernel.org/bpf/20210316210007.38949-1-alexei.starovoitov@gmail.com
---
 arch/x86/net/bpf_jit_comp.c |  26 ++++-
 include/linux/bpf.h         |  24 +++-
 kernel/bpf/bpf_struct_ops.c |   2 +-
 kernel/bpf/core.c           |   4 +-
 kernel/bpf/trampoline.c     | 218 +++++++++++++++++++++++++++---------
 5 files changed, 213 insertions(+), 61 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 747bba0a584a..72b5a57e9e31 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1936,7 +1936,7 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
  * add rsp, 8                      // skip eth_type_trans's frame
  * ret                             // return to its caller
  */
-int arch_prepare_bpf_trampoline(void *image, void *image_end,
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
 				const struct btf_func_model *m, u32 flags,
 				struct bpf_tramp_progs *tprogs,
 				void *orig_call)
@@ -1975,6 +1975,15 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 
 	save_regs(m, &prog, nr_args, stack_size);
 
+	if (flags & BPF_TRAMP_F_CALL_ORIG) {
+		/* arg1: mov rdi, im */
+		emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
+		if (emit_call(&prog, __bpf_tramp_enter, prog)) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
+	}
+
 	if (fentry->nr_progs)
 		if (invoke_bpf(m, &prog, fentry, stack_size))
 			return -EINVAL;
@@ -1993,8 +2002,7 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 	}
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		if (fentry->nr_progs || fmod_ret->nr_progs)
-			restore_regs(m, &prog, nr_args, stack_size);
+		restore_regs(m, &prog, nr_args, stack_size);
 
 		/* call original function */
 		if (emit_call(&prog, orig_call, prog)) {
@@ -2003,6 +2011,8 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 		}
 		/* remember return value in a stack for bpf prog to access */
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
+		im->ip_after_call = prog;
+		emit_nops(&prog, 5);
 	}
 
 	if (fmod_ret->nr_progs) {
@@ -2033,9 +2043,17 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 	 * the return value is only updated on the stack and still needs to be
 	 * restored to R0.
 	 */
-	if (flags & BPF_TRAMP_F_CALL_ORIG)
+	if (flags & BPF_TRAMP_F_CALL_ORIG) {
+		im->ip_epilogue = prog;
+		/* arg1: mov rdi, im */
+		emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
+		if (emit_call(&prog, __bpf_tramp_exit, prog)) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
 		/* restore original return value back into RAX */
 		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
+	}
 
 	EMIT1(0x5B); /* pop rbx */
 	EMIT1(0xC9); /* leave */
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d7e0f479a5b0..3625f019767d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -21,6 +21,7 @@
 #include <linux/capability.h>
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
+#include <linux/percpu-refcount.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -556,7 +557,8 @@ struct bpf_tramp_progs {
  *      fentry = a set of program to run before calling original function
  *      fexit = a set of program to run after original function
  */
-int arch_prepare_bpf_trampoline(void *image, void *image_end,
+struct bpf_tramp_image;
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
 				const struct btf_func_model *m, u32 flags,
 				struct bpf_tramp_progs *tprogs,
 				void *orig_call);
@@ -565,6 +567,8 @@ u64 notrace __bpf_prog_enter(struct bpf_prog *prog);
 void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
 u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog);
 void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start);
+void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr);
+void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);
 
 struct bpf_ksym {
 	unsigned long		 start;
@@ -583,6 +587,18 @@ enum bpf_tramp_prog_type {
 	BPF_TRAMP_REPLACE, /* more than MAX */
 };
 
+struct bpf_tramp_image {
+	void *image;
+	struct bpf_ksym ksym;
+	struct percpu_ref pcref;
+	void *ip_after_call;
+	void *ip_epilogue;
+	union {
+		struct rcu_head rcu;
+		struct work_struct work;
+	};
+};
+
 struct bpf_trampoline {
 	/* hlist for trampoline_table */
 	struct hlist_node hlist;
@@ -605,9 +621,8 @@ struct bpf_trampoline {
 	/* Number of attached programs. A counter per kind. */
 	int progs_cnt[BPF_TRAMP_MAX];
 	/* Executable image of trampoline */
-	void *image;
+	struct bpf_tramp_image *cur_image;
 	u64 selector;
-	struct bpf_ksym ksym;
 };
 
 struct bpf_attach_target_info {
@@ -691,6 +706,8 @@ void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym);
 void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
+int bpf_jit_charge_modmem(u32 pages);
+void bpf_jit_uncharge_modmem(u32 pages);
 #else
 static inline int bpf_trampoline_link_prog(struct bpf_prog *prog,
 					   struct bpf_trampoline *tr)
@@ -787,7 +804,6 @@ struct bpf_prog_aux {
 	bool func_proto_unreliable;
 	bool sleepable;
 	bool tail_call_reachable;
-	enum bpf_tramp_prog_type trampoline_prog_type;
 	struct hlist_node tramp_hlist;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 1a666a975416..70f6fd4fa305 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -430,7 +430,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 
 		tprogs[BPF_TRAMP_FENTRY].progs[0] = prog;
 		tprogs[BPF_TRAMP_FENTRY].nr_progs = 1;
-		err = arch_prepare_bpf_trampoline(image,
+		err = arch_prepare_bpf_trampoline(NULL, image,
 						  st_map->image + PAGE_SIZE,
 						  &st_ops->func_models[i], 0,
 						  tprogs, NULL);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 3a283bf97f2f..75244ecb2389 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -827,7 +827,7 @@ static int __init bpf_jit_charge_init(void)
 }
 pure_initcall(bpf_jit_charge_init);
 
-static int bpf_jit_charge_modmem(u32 pages)
+int bpf_jit_charge_modmem(u32 pages)
 {
 	if (atomic_long_add_return(pages, &bpf_jit_current) >
 	    (bpf_jit_limit >> PAGE_SHIFT)) {
@@ -840,7 +840,7 @@ static int bpf_jit_charge_modmem(u32 pages)
 	return 0;
 }
 
-static void bpf_jit_uncharge_modmem(u32 pages)
+void bpf_jit_uncharge_modmem(u32 pages)
 {
 	atomic_long_sub(pages, &bpf_jit_current);
 }
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 7bc3b3209224..1f3a4be4b175 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -57,19 +57,10 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym)
 			   PAGE_SIZE, true, ksym->name);
 }
 
-static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr)
-{
-	struct bpf_ksym *ksym = &tr->ksym;
-
-	snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", tr->key);
-	bpf_image_ksym_add(tr->image, ksym);
-}
-
 static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 {
 	struct bpf_trampoline *tr;
 	struct hlist_head *head;
-	void *image;
 	int i;
 
 	mutex_lock(&trampoline_mutex);
@@ -84,14 +75,6 @@ static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 	if (!tr)
 		goto out;
 
-	/* is_root was checked earlier. No need for bpf_jit_charge_modmem() */
-	image = bpf_jit_alloc_exec_page();
-	if (!image) {
-		kfree(tr);
-		tr = NULL;
-		goto out;
-	}
-
 	tr->key = key;
 	INIT_HLIST_NODE(&tr->hlist);
 	hlist_add_head(&tr->hlist, head);
@@ -99,9 +82,6 @@ static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 	mutex_init(&tr->mutex);
 	for (i = 0; i < BPF_TRAMP_MAX; i++)
 		INIT_HLIST_HEAD(&tr->progs_hlist[i]);
-	tr->image = image;
-	INIT_LIST_HEAD_RCU(&tr->ksym.lnode);
-	bpf_trampoline_ksym_add(tr);
 out:
 	mutex_unlock(&trampoline_mutex);
 	return tr;
@@ -185,10 +165,142 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total)
 	return tprogs;
 }
 
+static void __bpf_tramp_image_put_deferred(struct work_struct *work)
+{
+	struct bpf_tramp_image *im;
+
+	im = container_of(work, struct bpf_tramp_image, work);
+	bpf_image_ksym_del(&im->ksym);
+	bpf_jit_free_exec(im->image);
+	bpf_jit_uncharge_modmem(1);
+	percpu_ref_exit(&im->pcref);
+	kfree_rcu(im, rcu);
+}
+
+/* callback, fexit step 3 or fentry step 2 */
+static void __bpf_tramp_image_put_rcu(struct rcu_head *rcu)
+{
+	struct bpf_tramp_image *im;
+
+	im = container_of(rcu, struct bpf_tramp_image, rcu);
+	INIT_WORK(&im->work, __bpf_tramp_image_put_deferred);
+	schedule_work(&im->work);
+}
+
+/* callback, fexit step 2. Called after percpu_ref_kill confirms. */
+static void __bpf_tramp_image_release(struct percpu_ref *pcref)
+{
+	struct bpf_tramp_image *im;
+
+	im = container_of(pcref, struct bpf_tramp_image, pcref);
+	call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu);
+}
+
+/* callback, fexit or fentry step 1 */
+static void __bpf_tramp_image_put_rcu_tasks(struct rcu_head *rcu)
+{
+	struct bpf_tramp_image *im;
+
+	im = container_of(rcu, struct bpf_tramp_image, rcu);
+	if (im->ip_after_call)
+		/* the case of fmod_ret/fexit trampoline and CONFIG_PREEMPTION=y */
+		percpu_ref_kill(&im->pcref);
+	else
+		/* the case of fentry trampoline */
+		call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu);
+}
+
+static void bpf_tramp_image_put(struct bpf_tramp_image *im)
+{
+	/* The trampoline image that calls original function is using:
+	 * rcu_read_lock_trace to protect sleepable bpf progs
+	 * rcu_read_lock to protect normal bpf progs
+	 * percpu_ref to protect trampoline itself
+	 * rcu tasks to protect trampoline asm not covered by percpu_ref
+	 * (which are few asm insns before __bpf_tramp_enter and
+	 *  after __bpf_tramp_exit)
+	 *
+	 * The trampoline is unreachable before bpf_tramp_image_put().
+	 *
+	 * First, patch the trampoline to avoid calling into fexit progs.
+	 * The progs will be freed even if the original function is still
+	 * executing or sleeping.
+	 * In case of CONFIG_PREEMPT=y use call_rcu_tasks() to wait on
+	 * first few asm instructions to execute and call into
+	 * __bpf_tramp_enter->percpu_ref_get.
+	 * Then use percpu_ref_kill to wait for the trampoline and the original
+	 * function to finish.
+	 * Then use call_rcu_tasks() to make sure few asm insns in
+	 * the trampoline epilogue are done as well.
+	 *
+	 * In !PREEMPT case the task that got interrupted in the first asm
+	 * insns won't go through an RCU quiescent state which the
+	 * percpu_ref_kill will be waiting for. Hence the first
+	 * call_rcu_tasks() is not necessary.
+	 */
+	if (im->ip_after_call) {
+		int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_JUMP,
+					     NULL, im->ip_epilogue);
+		WARN_ON(err);
+		if (IS_ENABLED(CONFIG_PREEMPTION))
+			call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
+		else
+			percpu_ref_kill(&im->pcref);
+		return;
+	}
+
+	/* The trampoline without fexit and fmod_ret progs doesn't call original
+	 * function and doesn't use percpu_ref.
+	 * Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
+	 * Then use call_rcu_tasks() to wait for the rest of trampoline asm
+	 * and normal progs.
+	 */
+	call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
+}
+
+static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx)
+{
+	struct bpf_tramp_image *im;
+	struct bpf_ksym *ksym;
+	void *image;
+	int err = -ENOMEM;
+
+	im = kzalloc(sizeof(*im), GFP_KERNEL);
+	if (!im)
+		goto out;
+
+	err = bpf_jit_charge_modmem(1);
+	if (err)
+		goto out_free_im;
+
+	err = -ENOMEM;
+	im->image = image = bpf_jit_alloc_exec_page();
+	if (!image)
+		goto out_uncharge;
+
+	err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL);
+	if (err)
+		goto out_free_image;
+
+	ksym = &im->ksym;
+	INIT_LIST_HEAD_RCU(&ksym->lnode);
+	snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu_%u", key, idx);
+	bpf_image_ksym_add(image, ksym);
+	return im;
+
+out_free_image:
+	bpf_jit_free_exec(im->image);
+out_uncharge:
+	bpf_jit_uncharge_modmem(1);
+out_free_im:
+	kfree(im);
+out:
+	return ERR_PTR(err);
+}
+
 static int bpf_trampoline_update(struct bpf_trampoline *tr)
 {
-	void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2;
-	void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2;
+	struct bpf_tramp_image *im;
 	struct bpf_tramp_progs *tprogs;
 	u32 flags = BPF_TRAMP_F_RESTORE_REGS;
 	int err, total;
@@ -198,41 +310,42 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 		return PTR_ERR(tprogs);
 
 	if (total == 0) {
-		err = unregister_fentry(tr, old_image);
+		err = unregister_fentry(tr, tr->cur_image->image);
+		bpf_tramp_image_put(tr->cur_image);
+		tr->cur_image = NULL;
 		tr->selector = 0;
 		goto out;
 	}
 
+	im = bpf_tramp_image_alloc(tr->key, tr->selector);
+	if (IS_ERR(im)) {
+		err = PTR_ERR(im);
+		goto out;
+	}
+
 	if (tprogs[BPF_TRAMP_FEXIT].nr_progs ||
 	    tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs)
 		flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
 
-	/* Though the second half of trampoline page is unused a task could be
-	 * preempted in the middle of the first half of trampoline and two
-	 * updates to trampoline would change the code from underneath the
-	 * preempted task. Hence wait for tasks to voluntarily schedule or go
-	 * to userspace.
-	 * The same trampoline can hold both sleepable and non-sleepable progs.
-	 * synchronize_rcu_tasks_trace() is needed to make sure all sleepable
-	 * programs finish executing.
-	 * Wait for these two grace periods together.
-	 */
-	synchronize_rcu_mult(call_rcu_tasks, call_rcu_tasks_trace);
-
-	err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2,
+	err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE,
 					  &tr->func.model, flags, tprogs,
 					  tr->func.addr);
 	if (err < 0)
 		goto out;
 
-	if (tr->selector)
+	WARN_ON(tr->cur_image && tr->selector == 0);
+	WARN_ON(!tr->cur_image && tr->selector);
+	if (tr->cur_image)
 		/* progs already running at this address */
-		err = modify_fentry(tr, old_image, new_image);
+		err = modify_fentry(tr, tr->cur_image->image, im->image);
 	else
 		/* first time registering */
-		err = register_fentry(tr, new_image);
+		err = register_fentry(tr, im->image);
 	if (err)
 		goto out;
+	if (tr->cur_image)
+		bpf_tramp_image_put(tr->cur_image);
+	tr->cur_image = im;
 	tr->selector++;
 out:
 	kfree(tprogs);
@@ -364,17 +477,12 @@ void bpf_trampoline_put(struct bpf_trampoline *tr)
 		goto out;
 	if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT])))
 		goto out;
-	bpf_image_ksym_del(&tr->ksym);
-	/* This code will be executed when all bpf progs (both sleepable and
-	 * non-sleepable) went through
-	 * bpf_prog_put()->call_rcu[_tasks_trace]()->bpf_prog_free_deferred().
-	 * Hence no need for another synchronize_rcu_tasks_trace() here,
-	 * but synchronize_rcu_tasks() is still needed, since trampoline
-	 * may not have had any sleepable programs and we need to wait
-	 * for tasks to get out of trampoline code before freeing it.
+	/* This code will be executed even when the last bpf_tramp_image
+	 * is alive. All progs are detached from the trampoline and the
+	 * trampoline image is patched with jmp into epilogue to skip
+	 * fexit progs. The fentry-only trampoline will be freed via
+	 * multiple rcu callbacks.
 	 */
-	synchronize_rcu_tasks();
-	bpf_jit_free_exec(tr->image);
 	hlist_del(&tr->hlist);
 	kfree(tr);
 out:
@@ -478,8 +586,18 @@ void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start)
 	rcu_read_unlock_trace();
 }
 
+void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr)
+{
+	percpu_ref_get(&tr->pcref);
+}
+
+void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr)
+{
+	percpu_ref_put(&tr->pcref);
+}
+
 int __weak
-arch_prepare_bpf_trampoline(void *image, void *image_end,
+arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
 			    const struct btf_func_model *m, u32 flags,
 			    struct bpf_tramp_progs *tprogs,
 			    void *orig_call)

From 8b2030b4305951f44afef80225f1475618e25a73 Mon Sep 17 00:00:00 2001
From: Ludovic Senecaux <linuxludo@free.fr>
Date: Thu, 4 Mar 2021 04:10:50 -0500
Subject: [PATCH 0988/1820] netfilter: conntrack: Fix gre tunneling over ipv6

This fix permits gre connections to be tracked within ip6tables rules

Signed-off-by: Ludovic Senecaux <linuxludo@free.fr>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_proto_gre.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 5b05487a60d2..db11e403d818 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -218,9 +218,6 @@ int nf_conntrack_gre_packet(struct nf_conn *ct,
 			    enum ip_conntrack_info ctinfo,
 			    const struct nf_hook_state *state)
 {
-	if (state->pf != NFPROTO_IPV4)
-		return -NF_ACCEPT;
-
 	if (!nf_ct_is_confirmed(ct)) {
 		unsigned int *timeouts = nf_ct_timeout_lookup(ct);
 

From 7e6136f1b7272b2202817cff37ada355eb5e6784 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 17 Mar 2021 11:31:55 +0100
Subject: [PATCH 0989/1820] netfilter: nftables: report EOPNOTSUPP on
 unsupported flowtable flags

Error was not set accordingly.

Fixes: 8bb69f3b2918 ("netfilter: nf_tables: add flowtable offload control plane")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 224c8e537cb3..0d034f895b7b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6963,8 +6963,10 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 	if (nla[NFTA_FLOWTABLE_FLAGS]) {
 		flowtable->data.flags =
 			ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS]));
-		if (flowtable->data.flags & ~NFT_FLOWTABLE_MASK)
+		if (flowtable->data.flags & ~NFT_FLOWTABLE_MASK) {
+			err = -EOPNOTSUPP;
 			goto err3;
+		}
 	}
 
 	write_pnet(&flowtable->data.net, net);

From 7b35582cd04ace2fd1807c1b624934e465cc939d Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 17 Mar 2021 12:54:57 +0100
Subject: [PATCH 0990/1820] netfilter: nftables: allow to update flowtable
 flags

Honor flowtable flags from the control update path. Disallow disabling
to toggle hardware offload support though.

Fixes: 8bb69f3b2918 ("netfilter: nf_tables: add flowtable offload control plane")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  3 +++
 net/netfilter/nf_tables_api.c     | 15 +++++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index fdec57d862b7..5aaced6bf13e 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1536,6 +1536,7 @@ struct nft_trans_flowtable {
 	struct nft_flowtable		*flowtable;
 	bool				update;
 	struct list_head		hook_list;
+	u32				flags;
 };
 
 #define nft_trans_flowtable(trans)	\
@@ -1544,6 +1545,8 @@ struct nft_trans_flowtable {
 	(((struct nft_trans_flowtable *)trans->data)->update)
 #define nft_trans_flowtable_hooks(trans)	\
 	(((struct nft_trans_flowtable *)trans->data)->hook_list)
+#define nft_trans_flowtable_flags(trans)	\
+	(((struct nft_trans_flowtable *)trans->data)->flags)
 
 int __init nft_chain_filter_init(void);
 void nft_chain_filter_fini(void);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0d034f895b7b..4fcd07f1e925 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6842,6 +6842,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh,
 	struct nft_hook *hook, *next;
 	struct nft_trans *trans;
 	bool unregister = false;
+	u32 flags;
 	int err;
 
 	err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK],
@@ -6856,6 +6857,17 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh,
 		}
 	}
 
+	if (nla[NFTA_FLOWTABLE_FLAGS]) {
+		flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS]));
+		if (flags & ~NFT_FLOWTABLE_MASK)
+			return -EOPNOTSUPP;
+		if ((flowtable->data.flags & NFT_FLOWTABLE_HW_OFFLOAD) ^
+		    (flags & NFT_FLOWTABLE_HW_OFFLOAD))
+			return -EOPNOTSUPP;
+	} else {
+		flags = flowtable->data.flags;
+	}
+
 	err = nft_register_flowtable_net_hooks(ctx->net, ctx->table,
 					       &flowtable_hook.list, flowtable);
 	if (err < 0)
@@ -6869,6 +6881,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh,
 		goto err_flowtable_update_hook;
 	}
 
+	nft_trans_flowtable_flags(trans) = flags;
 	nft_trans_flowtable(trans) = flowtable;
 	nft_trans_flowtable_update(trans) = true;
 	INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans));
@@ -8178,6 +8191,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 			break;
 		case NFT_MSG_NEWFLOWTABLE:
 			if (nft_trans_flowtable_update(trans)) {
+				nft_trans_flowtable(trans)->data.flags =
+					nft_trans_flowtable_flags(trans);
 				nf_tables_flowtable_notify(&trans->ctx,
 							   nft_trans_flowtable(trans),
 							   &nft_trans_flowtable_hooks(trans),

From 740b486a8d1f966e68ac0666f1fd57441a7cda94 Mon Sep 17 00:00:00 2001
From: Yinjun Zhang <yinjun.zhang@corigine.com>
Date: Wed, 17 Mar 2021 13:42:24 +0100
Subject: [PATCH 0991/1820] netfilter: flowtable: Make sure GC works
 periodically in idle system

Currently flowtable's GC work is initialized as deferrable, which
means GC cannot work on time when system is idle. So the hardware
offloaded flow may be deleted for timeout, since its used time is
not timely updated.

Resolve it by initializing the GC work as delayed work instead of
deferrable.

Fixes: c29f74e0df7a ("netfilter: nf_flow_table: hardware offload support")
Signed-off-by: Yinjun Zhang <yinjun.zhang@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_flow_table_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 5fa657b8e03d..c77ba8690ed8 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -506,7 +506,7 @@ int nf_flow_table_init(struct nf_flowtable *flowtable)
 {
 	int err;
 
-	INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc);
+	INIT_DELAYED_WORK(&flowtable->gc_work, nf_flow_offload_work_gc);
 	flow_block_init(&flowtable->flow_block);
 	init_rwsem(&flowtable->flow_block_lock);
 

From 8f3f5792f2940c16ab63c614b26494c8689c9c1e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 17 Mar 2021 23:54:14 +0900
Subject: [PATCH 0992/1820] libbpf: Fix error path in bpf_object__elf_init()

When it failed to get section names, it should call into
bpf_object__elf_finish() like others.

Fixes: 88a82120282b ("libbpf: Factor out common ELF operations and improve logging")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210317145414.884817-1-namhyung@kernel.org
---
 tools/lib/bpf/libbpf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d43cc3f29dae..4181d178ee7b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1181,7 +1181,8 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	if (!elf_rawdata(elf_getscn(obj->efile.elf, obj->efile.shstrndx), NULL)) {
 		pr_warn("elf: failed to get section names strings from %s: %s\n",
 			obj->path, elf_errmsg(-1));
-		return -LIBBPF_ERRNO__FORMAT;
+		err = -LIBBPF_ERRNO__FORMAT;
+		goto errout;
 	}
 
 	/* Old LLVM set e_machine to EM_NONE */

From 58bfd95b554f1a23d01228672f86bb489bdbf4ba Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Wed, 17 Mar 2021 17:28:58 +0530
Subject: [PATCH 0993/1820] libbpf: Use SOCK_CLOEXEC when opening the netlink
 socket
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Otherwise, there exists a small window between the opening and closing
of the socket fd where it may leak into processes launched by some other
thread.

Fixes: 949abbe88436 ("libbpf: add function to setup XDP")
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20210317115857.6536-1-memxor@gmail.com
---
 tools/lib/bpf/netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 4dd73de00b6f..d2cb28e9ef52 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -40,7 +40,7 @@ static int libbpf_netlink_open(__u32 *nl_pid)
 	memset(&sa, 0, sizeof(sa));
 	sa.nl_family = AF_NETLINK;
 
-	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE);
 	if (sock < 0)
 		return -errno;
 

From 86fe2c19eec4728fd9a42ba18f3b47f0d5f9fd7c Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 17 Mar 2021 21:19:57 +0100
Subject: [PATCH 0994/1820] netfilter: nftables: skip hook overlap logic if
 flowtable is stale

If the flowtable has been previously removed in this batch, skip the
hook overlap checks. This fixes spurious EEXIST errors when removing and
adding the flowtable in the same batch.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 4fcd07f1e925..f57f1a6ba96f 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6783,6 +6783,9 @@ static int nft_register_flowtable_net_hooks(struct net *net,
 
 	list_for_each_entry(hook, hook_list, list) {
 		list_for_each_entry(ft, &table->flowtables, list) {
+			if (!nft_is_active_next(net, ft))
+				continue;
+
 			list_for_each_entry(hook2, &ft->hook_list, list) {
 				if (hook->ops.dev == hook2->ops.dev &&
 				    hook->ops.pf == hook2->ops.pf) {

From 34fa493a565cc6fcee6919787c11e264f55603c6 Mon Sep 17 00:00:00 2001
From: Calvin Hou <Calvin.Hou@amd.com>
Date: Tue, 2 Mar 2021 10:48:26 -0500
Subject: [PATCH 0995/1820] drm/amd/display: Correct algorithm for reversed
 gamma

[Why]
DCN30 needs to correctly program reversed gamma curve, which DCN20
already has.
Also needs to fix a bug that 252-255 values are clipped.

[How]
Apply two fixes into DCN30.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1513
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Calvin Hou <Calvin.Hou@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Acked-by: Solomon Chiu <solomon.chiu@amd.com>
Acked-by: Vladimir Stempen <Vladimir.Stempen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 .../amd/display/dc/dcn30/dcn30_cm_common.c    | 26 +++++++++++++------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c
index 41a1d0e9b7e2..e0df9b0065f9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c
@@ -113,6 +113,7 @@ bool cm3_helper_translate_curve_to_hw_format(
 	struct pwl_result_data *rgb_resulted;
 	struct pwl_result_data *rgb;
 	struct pwl_result_data *rgb_plus_1;
+	struct pwl_result_data *rgb_minus_1;
 	struct fixed31_32 end_value;
 
 	int32_t region_start, region_end;
@@ -140,7 +141,7 @@ bool cm3_helper_translate_curve_to_hw_format(
 		region_start = -MAX_LOW_POINT;
 		region_end   = NUMBER_REGIONS - MAX_LOW_POINT;
 	} else {
-		/* 10 segments
+		/* 11 segments
 		 * segment is from 2^-10 to 2^0
 		 * There are less than 256 points, for optimization
 		 */
@@ -154,9 +155,10 @@ bool cm3_helper_translate_curve_to_hw_format(
 		seg_distr[7] = 4;
 		seg_distr[8] = 4;
 		seg_distr[9] = 4;
+		seg_distr[10] = 1;
 
 		region_start = -10;
-		region_end = 0;
+		region_end = 1;
 	}
 
 	for (i = region_end - region_start; i < MAX_REGIONS_NUMBER ; i++)
@@ -189,6 +191,10 @@ bool cm3_helper_translate_curve_to_hw_format(
 	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
 	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
+	rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+	rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+	rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
 	// All 3 color channels have same x
 	corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
 					     dc_fixpt_from_int(region_start));
@@ -259,15 +265,18 @@ bool cm3_helper_translate_curve_to_hw_format(
 
 	rgb = rgb_resulted;
 	rgb_plus_1 = rgb_resulted + 1;
+	rgb_minus_1 = rgb;
 
 	i = 1;
 	while (i != hw_points + 1) {
-		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
-			rgb_plus_1->red = rgb->red;
-		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
-			rgb_plus_1->green = rgb->green;
-		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
-			rgb_plus_1->blue = rgb->blue;
+		if (i >= hw_points - 1) {
+			if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
+				rgb_plus_1->red = dc_fixpt_add(rgb->red, rgb_minus_1->delta_red);
+			if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
+				rgb_plus_1->green = dc_fixpt_add(rgb->green, rgb_minus_1->delta_green);
+			if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
+				rgb_plus_1->blue = dc_fixpt_add(rgb->blue, rgb_minus_1->delta_blue);
+		}
 
 		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
 		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
@@ -283,6 +292,7 @@ bool cm3_helper_translate_curve_to_hw_format(
 		}
 
 		++rgb_plus_1;
+		rgb_minus_1 = rgb;
 		++rgb;
 		++i;
 	}

From beb6b2f97e0a02164c7f0df6e08c49219cfc2b80 Mon Sep 17 00:00:00 2001
From: Dillon Varone <dillon.varone@amd.com>
Date: Thu, 4 Mar 2021 17:39:10 -0500
Subject: [PATCH 0996/1820] drm/amd/display: Remove MPC gamut remap logic for
 DCN30

[Why?]
Should only reroute gamut remap to mpc unless 3D LUT is not used and all
planes are using the same src->dest.

[How?]
Remove DCN30 specific logic for rerouting gamut remap to mpc.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1513
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Dillon Varone <dillon.varone@amd.com>
Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Acked-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Solomon Chiu <solomon.chiu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 .../drm/amd/display/dc/dcn20/dcn20_hwseq.c    | 34 ++-----------------
 1 file changed, 2 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 5342c309b78c..aece1103331d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1507,38 +1507,8 @@ static void dcn20_update_dchubp_dpp(
 	if (pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed
 			|| pipe_ctx->stream->update_flags.bits.gamut_remap
 			|| pipe_ctx->stream->update_flags.bits.out_csc) {
-		struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc;
-
-		if (mpc->funcs->set_gamut_remap) {
-			int i;
-			int mpcc_id = hubp->inst;
-			struct mpc_grph_gamut_adjustment adjust;
-			bool enable_remap_dpp = false;
-
-			memset(&adjust, 0, sizeof(adjust));
-			adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_BYPASS;
-
-			/* save the enablement of gamut remap for dpp */
-			enable_remap_dpp = pipe_ctx->stream->gamut_remap_matrix.enable_remap;
-
-			/* force bypass gamut remap for dpp/cm */
-			pipe_ctx->stream->gamut_remap_matrix.enable_remap = false;
-			dc->hwss.program_gamut_remap(pipe_ctx);
-
-			/* restore gamut remap flag and use this remap into mpc */
-			pipe_ctx->stream->gamut_remap_matrix.enable_remap = enable_remap_dpp;
-
-			/* build remap matrix for top plane if enabled */
-			if (enable_remap_dpp && pipe_ctx->top_pipe == NULL) {
-					adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_SW;
-					for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++)
-						adjust.temperature_matrix[i] =
-								pipe_ctx->stream->gamut_remap_matrix.matrix[i];
-			}
-			mpc->funcs->set_gamut_remap(mpc, mpcc_id, &adjust);
-		} else
-			/* dpp/cm gamut remap*/
-			dc->hwss.program_gamut_remap(pipe_ctx);
+		/* dpp/cm gamut remap*/
+		dc->hwss.program_gamut_remap(pipe_ctx);
 
 		/*call the dcn2 method which uses mpc csc*/
 		dc->hwss.program_output_csc(dc,

From e4817a1b6b77db538bc0141c3b138f2df803ce87 Mon Sep 17 00:00:00 2001
From: dillon min <dillon.minfei@gmail.com>
Date: Wed, 17 Mar 2021 23:45:09 +0800
Subject: [PATCH 0997/1820] ARM: dts: imx6ull: fix ubi filesystem mount failed

For NAND Ecc layout, there is a dependency from old kernel's nand driver
setting and current. if old kernel use 4 bit ecc , we should use 4 bit
in new kernel either. else will run into following error at filesystem
mounting.

So, enable fsl,use-minimum-ecc from device tree, to fix this mismatch

[    9.449265] ubi0: scanning is finished
[    9.463968] ubi0 warning: ubi_io_read: error -74 (ECC error) while reading
22528 bytes from PEB 513:4096, read only 22528 bytes, retry
[    9.486940] ubi0 warning: ubi_io_read: error -74 (ECC error) while reading
22528 bytes from PEB 513:4096, read only 22528 bytes, retry
[    9.509906] ubi0 warning: ubi_io_read: error -74 (ECC error) while reading
22528 bytes from PEB 513:4096, read only 22528 bytes, retry
[    9.532845] ubi0 error: ubi_io_read: error -74 (ECC error) while reading
22528 bytes from PEB 513:4096, read 22528 bytes

Fixes: f9ecf10cb88c ("ARM: dts: imx6ull: add MYiR MYS-6ULX SBC")
Signed-off-by: dillon min <dillon.minfei@gmail.com>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts b/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts
index ecbb2cc5b9ab..79cc45728cd2 100644
--- a/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts
+++ b/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts
@@ -14,5 +14,6 @@
 };
 
 &gpmi {
+	fsl,use-minimum-ecc;
 	status = "okay";
 };

From ed01fee283a067c72b2d6500046080dbc1bb9dae Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 3 Mar 2021 13:28:22 +0100
Subject: [PATCH 0998/1820] nvme-fabrics: only reserve a single tag

Fabrics drivers currently reserve two tags on the admin queue.  But
given that the connect command is only run on a freshly created queue
or after all commands have been force aborted we only need to reserve
a single tag.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
---
 drivers/nvme/host/fabrics.h | 7 +++++++
 drivers/nvme/host/fc.c      | 4 ++--
 drivers/nvme/host/rdma.c    | 4 ++--
 drivers/nvme/host/tcp.c     | 4 ++--
 drivers/nvme/target/loop.c  | 4 ++--
 5 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 733010d2eafd..888b108d87a4 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -18,6 +18,13 @@
 /* default is -1: the fail fast mechanism is disabled  */
 #define NVMF_DEF_FAIL_FAST_TMO		-1
 
+/*
+ * Reserved one command for internal usage.  This command is used for sending
+ * the connect command, as well as for the keep alive command on the admin
+ * queue once live.
+ */
+#define NVMF_RESERVED_TAGS	1
+
 /*
  * Define a host as seen by the target.  We allocate one at boot, but also
  * allow the override it when creating controllers.  This is both to provide
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 73d073748389..6ffa8de2a0d7 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2863,7 +2863,7 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
 	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
 	ctrl->tag_set.ops = &nvme_fc_mq_ops;
 	ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
-	ctrl->tag_set.reserved_tags = 1; /* fabric connect */
+	ctrl->tag_set.reserved_tags = NVMF_RESERVED_TAGS;
 	ctrl->tag_set.numa_node = ctrl->ctrl.numa_node;
 	ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 	ctrl->tag_set.cmd_size =
@@ -3485,7 +3485,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
 	ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops;
 	ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH;
-	ctrl->admin_tag_set.reserved_tags = 2; /* fabric connect + Keep-Alive */
+	ctrl->admin_tag_set.reserved_tags = NVMF_RESERVED_TAGS;
 	ctrl->admin_tag_set.numa_node = ctrl->ctrl.numa_node;
 	ctrl->admin_tag_set.cmd_size =
 		struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv,
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 53ac4d7442ba..7855103e05d2 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -798,7 +798,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl,
 		memset(set, 0, sizeof(*set));
 		set->ops = &nvme_rdma_admin_mq_ops;
 		set->queue_depth = NVME_AQ_MQ_TAG_DEPTH;
-		set->reserved_tags = 2; /* connect + keep-alive */
+		set->reserved_tags = NVMF_RESERVED_TAGS;
 		set->numa_node = nctrl->numa_node;
 		set->cmd_size = sizeof(struct nvme_rdma_request) +
 				NVME_RDMA_DATA_SGL_SIZE;
@@ -811,7 +811,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl,
 		memset(set, 0, sizeof(*set));
 		set->ops = &nvme_rdma_mq_ops;
 		set->queue_depth = nctrl->sqsize + 1;
-		set->reserved_tags = 1; /* fabric connect */
+		set->reserved_tags = NVMF_RESERVED_TAGS;
 		set->numa_node = nctrl->numa_node;
 		set->flags = BLK_MQ_F_SHOULD_MERGE;
 		set->cmd_size = sizeof(struct nvme_rdma_request) +
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 69f59d2c5799..c535836e7065 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1575,7 +1575,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl,
 		memset(set, 0, sizeof(*set));
 		set->ops = &nvme_tcp_admin_mq_ops;
 		set->queue_depth = NVME_AQ_MQ_TAG_DEPTH;
-		set->reserved_tags = 2; /* connect + keep-alive */
+		set->reserved_tags = NVMF_RESERVED_TAGS;
 		set->numa_node = nctrl->numa_node;
 		set->flags = BLK_MQ_F_BLOCKING;
 		set->cmd_size = sizeof(struct nvme_tcp_request);
@@ -1587,7 +1587,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl,
 		memset(set, 0, sizeof(*set));
 		set->ops = &nvme_tcp_mq_ops;
 		set->queue_depth = nctrl->sqsize + 1;
-		set->reserved_tags = 1; /* fabric connect */
+		set->reserved_tags = NVMF_RESERVED_TAGS;
 		set->numa_node = nctrl->numa_node;
 		set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING;
 		set->cmd_size = sizeof(struct nvme_tcp_request);
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index cb6f86572b24..3e189e753bcf 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -349,7 +349,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 	memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
 	ctrl->admin_tag_set.ops = &nvme_loop_admin_mq_ops;
 	ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH;
-	ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */
+	ctrl->admin_tag_set.reserved_tags = NVMF_RESERVED_TAGS;
 	ctrl->admin_tag_set.numa_node = ctrl->ctrl.numa_node;
 	ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
 		NVME_INLINE_SG_CNT * sizeof(struct scatterlist);
@@ -520,7 +520,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
 	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
 	ctrl->tag_set.ops = &nvme_loop_mq_ops;
 	ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
-	ctrl->tag_set.reserved_tags = 1; /* fabric connect */
+	ctrl->tag_set.reserved_tags = NVMF_RESERVED_TAGS;
 	ctrl->tag_set.numa_node = ctrl->ctrl.numa_node;
 	ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 	ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) +

From 06c3c3365b4bae5ef0f0525d3683b73cbae1e69c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 3 Mar 2021 13:46:06 +0100
Subject: [PATCH 0999/1820] nvme: merge nvme_keep_alive into
 nvme_keep_alive_work

Merge nvme_keep_alive into its only caller to prepare for additional
changes to this code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
---
 drivers/nvme/host/core.c | 26 ++++++++------------------
 1 file changed, 8 insertions(+), 18 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index a5653892d773..45d510a12c6b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1226,28 +1226,12 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
 		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
-static int nvme_keep_alive(struct nvme_ctrl *ctrl)
-{
-	struct request *rq;
-
-	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
-			BLK_MQ_REQ_RESERVED);
-	if (IS_ERR(rq))
-		return PTR_ERR(rq);
-
-	rq->timeout = ctrl->kato * HZ;
-	rq->end_io_data = ctrl;
-
-	blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io);
-
-	return 0;
-}
-
 static void nvme_keep_alive_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
 			struct nvme_ctrl, ka_work);
 	bool comp_seen = ctrl->comp_seen;
+	struct request *rq;
 
 	if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) {
 		dev_dbg(ctrl->device,
@@ -1257,12 +1241,18 @@ static void nvme_keep_alive_work(struct work_struct *work)
 		return;
 	}
 
-	if (nvme_keep_alive(ctrl)) {
+	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
+				BLK_MQ_REQ_RESERVED);
+	if (IS_ERR(rq)) {
 		/* allocation failure, reset the controller */
 		dev_err(ctrl->device, "keep-alive failed\n");
 		nvme_reset_ctrl(ctrl);
 		return;
 	}
+
+	rq->timeout = ctrl->kato * HZ;
+	rq->end_io_data = ctrl;
+	blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io);
 }
 
 static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)

From 985c5a329dfe5ecb782551cddef48912961b83f1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 3 Mar 2021 13:51:47 +0100
Subject: [PATCH 1000/1820] nvme: allocate the keep alive request using
 BLK_MQ_REQ_NOWAIT

To avoid an error recovery deadlock where the keep alive work is waiting
for a request and thus can't be flushed to make progress for tearing down
the controller.  Also print the error code returned from
blk_mq_alloc_request to help debugging any future issues in this code.

Based on an earlier patch from Hannes Reinecke <hare@suse.de>.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
---
 drivers/nvme/host/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 45d510a12c6b..83d6740f8d4e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1242,10 +1242,10 @@ static void nvme_keep_alive_work(struct work_struct *work)
 	}
 
 	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
-				BLK_MQ_REQ_RESERVED);
+				BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
 	if (IS_ERR(rq)) {
 		/* allocation failure, reset the controller */
-		dev_err(ctrl->device, "keep-alive failed\n");
+		dev_err(ctrl->device, "keep-alive failed: %ld\n", PTR_ERR(rq));
 		nvme_reset_ctrl(ctrl);
 		return;
 	}

From b94e8cd2e6a94fc7563529ddc82726a7e77e04de Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 15 Mar 2021 10:32:07 +0100
Subject: [PATCH 1001/1820] nvme: fix Write Zeroes limitations

We voluntarily limit the Write Zeroes sizes to the MDTS value provided by
the hardware, but currently get the units wrong, so fix that.

Fixes: 6e02318eaea5 ("nvme: add support for the Write Zeroes command")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Tested-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
---
 drivers/nvme/host/core.c | 36 ++++++++++++------------------------
 1 file changed, 12 insertions(+), 24 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 83d6740f8d4e..0896e21642be 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1954,30 +1954,18 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
 }
 
-static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns)
+/*
+ * Even though NVMe spec explicitly states that MDTS is not applicable to the
+ * write-zeroes, we are cautious and limit the size to the controllers
+ * max_hw_sectors value, which is based on the MDTS field and possibly other
+ * limiting factors.
+ */
+static void nvme_config_write_zeroes(struct request_queue *q,
+		struct nvme_ctrl *ctrl)
 {
-	u64 max_blocks;
-
-	if (!(ns->ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) ||
-	    (ns->ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES))
-		return;
-	/*
-	 * Even though NVMe spec explicitly states that MDTS is not
-	 * applicable to the write-zeroes:- "The restriction does not apply to
-	 * commands that do not transfer data between the host and the
-	 * controller (e.g., Write Uncorrectable ro Write Zeroes command).".
-	 * In order to be more cautious use controller's max_hw_sectors value
-	 * to configure the maximum sectors for the write-zeroes which is
-	 * configured based on the controller's MDTS field in the
-	 * nvme_init_identify() if available.
-	 */
-	if (ns->ctrl->max_hw_sectors == UINT_MAX)
-		max_blocks = (u64)USHRT_MAX + 1;
-	else
-		max_blocks = ns->ctrl->max_hw_sectors + 1;
-
-	blk_queue_max_write_zeroes_sectors(disk->queue,
-					   nvme_lba_to_sect(ns, max_blocks));
+	if ((ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) &&
+	    !(ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES))
+		blk_queue_max_write_zeroes_sectors(q, ctrl->max_hw_sectors);
 }
 
 static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
@@ -2149,7 +2137,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	set_capacity_and_notify(disk, capacity);
 
 	nvme_config_discard(disk, ns);
-	nvme_config_write_zeroes(disk, ns);
+	nvme_config_write_zeroes(disk->queue, ns->ctrl);
 
 	set_disk_ro(disk, (id->nsattr & NVME_NS_ATTR_RO) ||
 		test_bit(NVME_NS_FORCE_RO, &ns->flags));

From fd0823f405090f9f410fc3e3ff7efb52e7b486fa Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Mon, 15 Mar 2021 14:08:11 -0700
Subject: [PATCH 1002/1820] nvme-tcp: fix a NULL deref when receiving a
 0-length r2t PDU

When the controller sends us a 0-length r2t PDU we should not attempt to
try to set up a h2cdata PDU but rather conclude that this is a buggy
controller (forward progress is not possible) and simply fail it
immediately.

Fixes: 3f2304f8c6d6 ("nvme-tcp: add NVMe over TCP host driver")
Reported-by: Belanger, Martin <Martin.Belanger@dell.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/tcp.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index c535836e7065..5b23e1d52cb3 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -568,6 +568,13 @@ static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req,
 	req->pdu_len = le32_to_cpu(pdu->r2t_length);
 	req->pdu_sent = 0;
 
+	if (unlikely(!req->pdu_len)) {
+		dev_err(queue->ctrl->ctrl.device,
+			"req %d r2t len is %u, probably a bug...\n",
+			rq->tag, req->pdu_len);
+		return -EPROTO;
+	}
+
 	if (unlikely(req->data_sent + req->pdu_len > req->data_len)) {
 		dev_err(queue->ctrl->ctrl.device,
 			"req %d r2t len %u exceeded data len %u (%zu sent)\n",

From bb83337058a7000644cdeffc67361d2473534756 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Mon, 15 Mar 2021 13:53:47 -0700
Subject: [PATCH 1003/1820] nvme-tcp: fix misuse of __smp_processor_id with
 preemption enabled

For our pure advisory use-case, we only rely on this call as a hint, so
fix the warning complaints of using the smp_processor_id variants with
preemption enabled.

Fixes: db5ad6b7f8cd ("nvme-tcp: try to send request in queue_rq context")
Fixes: ada831772188 ("nvme-tcp: Fix warning with CONFIG_DEBUG_PREEMPT")
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 5b23e1d52cb3..35a78682f8de 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -287,7 +287,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 	 * directly, otherwise queue io_work. Also, only do that if we
 	 * are on the same cpu, so we don't introduce contention.
 	 */
-	if (queue->io_cpu == __smp_processor_id() &&
+	if (queue->io_cpu == raw_smp_processor_id() &&
 	    sync && empty && mutex_trylock(&queue->send_mutex)) {
 		queue->more_requests = !last;
 		nvme_tcp_send_all(queue);

From 72f572428b83d0bc7028e7c4326d1a5f45205e44 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Mon, 15 Mar 2021 14:04:26 -0700
Subject: [PATCH 1004/1820] nvme-tcp: fix possible hang when failing to set io
 queues

We only setup io queues for nvme controllers, and it makes absolutely no
sense to allow a controller (re)connect without any I/O queues.  If we
happen to fail setting the queue count for any reason, we should not
allow this to be a successful reconnect as I/O has no chance in going
through. Instead just fail and schedule another reconnect.

Fixes: 3f2304f8c6d6 ("nvme-tcp: add NVMe over TCP host driver")
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/tcp.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 35a78682f8de..a0f00cb8f9f3 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1752,8 +1752,11 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 		return ret;
 
 	ctrl->queue_count = nr_io_queues + 1;
-	if (ctrl->queue_count < 2)
-		return 0;
+	if (ctrl->queue_count < 2) {
+		dev_err(ctrl->device,
+			"unable to set any I/O queues\n");
+		return -ENOMEM;
+	}
 
 	dev_info(ctrl->device,
 		"creating %d I/O queues.\n", nr_io_queues);

From c4c6df5fc84659690d4391d1fba155cd94185295 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Mon, 15 Mar 2021 14:04:27 -0700
Subject: [PATCH 1005/1820] nvme-rdma: fix possible hang when failing to set io
 queues

We only setup io queues for nvme controllers, and it makes absolutely no
sense to allow a controller (re)connect without any I/O queues.  If we
happen to fail setting the queue count for any reason, we should not allow
this to be a successful reconnect as I/O has no chance in going through.
Instead just fail and schedule another reconnect.

Reported-by: Chao Leng <lengchao@huawei.com>
Fixes: 711023071960 ("nvme-rdma: add a NVMe over Fabrics RDMA host driver")
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chao Leng <lengchao@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/rdma.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 7855103e05d2..be905d4fdb47 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -736,8 +736,11 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl)
 		return ret;
 
 	ctrl->ctrl.queue_count = nr_io_queues + 1;
-	if (ctrl->ctrl.queue_count < 2)
-		return 0;
+	if (ctrl->ctrl.queue_count < 2) {
+		dev_err(ctrl->ctrl.device,
+			"unable to set any I/O queues\n");
+		return -ENOMEM;
+	}
 
 	dev_info(ctrl->ctrl.device,
 		"creating %d I/O queues.\n", nr_io_queues);

From d218a8a3003e84ab136e69a4e30dd4ec7dab2d22 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Mon, 15 Mar 2021 15:34:51 -0700
Subject: [PATCH 1006/1820] nvmet: don't check iosqes,iocqes for discovery
 controllers

From the base spec, Figure 78:

  "Controller Configuration, these fields are defined as parameters to
   configure an "I/O Controller (IOC)" and not to configure a "Discovery
   Controller (DC).

   ...
   If the controller does not support I/O queues, then this field shall
   be read-only with a value of 0h

Just perform this check for I/O controllers.

Fixes: a07b4970f464 ("nvmet: add a generic NVMe target")
Reported-by: Belanger, Martin <Martin.Belanger@dell.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/core.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index be6fcdaf51a7..a027433b8be8 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -1118,9 +1118,20 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
 {
 	lockdep_assert_held(&ctrl->lock);
 
-	if (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
-	    nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES ||
-	    nvmet_cc_mps(ctrl->cc) != 0 ||
+	/*
+	 * Only I/O controllers should verify iosqes,iocqes.
+	 * Strictly speaking, the spec says a discovery controller
+	 * should verify iosqes,iocqes are zeroed, however that
+	 * would break backwards compatibility, so don't enforce it.
+	 */
+	if (ctrl->subsys->type != NVME_NQN_DISC &&
+	    (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
+	     nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES)) {
+		ctrl->csts = NVME_CSTS_CFS;
+		return;
+	}
+
+	if (nvmet_cc_mps(ctrl->cc) != 0 ||
 	    nvmet_cc_ams(ctrl->cc) != 0 ||
 	    nvmet_cc_css(ctrl->cc) != 0) {
 		ctrl->csts = NVME_CSTS_CFS;

From bac04454ef9fada009f0572576837548b190bf94 Mon Sep 17 00:00:00 2001
From: Elad Grupi <elad.grupi@dell.com>
Date: Tue, 16 Mar 2021 17:44:25 +0200
Subject: [PATCH 1007/1820] nvmet-tcp: fix kmap leak when data digest in use

When data digest is enabled we should unmap pdu iovec before handling
the data digest pdu.

Signed-off-by: Elad Grupi <elad.grupi@dell.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 8b0485ada315..d658c6e8263a 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1098,11 +1098,11 @@ static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue)
 		cmd->rbytes_done += ret;
 	}
 
+	nvmet_tcp_unmap_pdu_iovec(cmd);
 	if (queue->data_digest) {
 		nvmet_tcp_prep_recv_ddgst(cmd);
 		return 0;
 	}
-	nvmet_tcp_unmap_pdu_iovec(cmd);
 
 	if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) &&
 	    cmd->rbytes_done == cmd->req.transfer_len) {

From 2b8c956ea6ba896ec18ae36c2684ecfa04c1f479 Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Wed, 17 Mar 2021 23:48:05 -0700
Subject: [PATCH 1008/1820] usb: typec: tcpm: Skip sink_cap query only when VDM
 sm is busy

When port partner responds "Not supported" to the DiscIdentity command,
VDM state machine can remain in NVDM_STATE_ERR_TMOUT and this causes
querying sink cap to be skipped indefinitely. Hence check for
vdm_sm_running instead of checking for VDM_STATE_DONE.

Fixes: 8dc4bd073663f ("usb: typec: tcpm: Add support for Sink Fast Role SWAP(FRS)")
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210318064805.3747831-1-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 92093ea12cff..ce7af398c7c1 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -5173,7 +5173,7 @@ static void tcpm_enable_frs_work(struct kthread_work *work)
 		goto unlock;
 
 	/* Send when the state machine is idle */
-	if (port->state != SNK_READY || port->vdm_state != VDM_STATE_DONE || port->send_discover)
+	if (port->state != SNK_READY || port->vdm_sm_running || port->send_discover)
 		goto resched;
 
 	port->upcoming_state = GET_SINK_CAP;

From 2cafd46a714af1e55354bc6dcea9dcc13f9475b5 Mon Sep 17 00:00:00 2001
From: Edmundo Carmona Antoranz <eantoranz@gmail.com>
Date: Tue, 16 Mar 2021 12:17:35 -0600
Subject: [PATCH 1009/1820] staging: vt665x: fix alignment constraints
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Removing 2 instances of alignment warnings

drivers/staging/vt6655/rxtx.h:153:1: warning: alignment 1 of ‘struct vnt_cts’ is less than 2 [-Wpacked-not-aligned]
drivers/staging/vt6655/rxtx.h:163:1: warning: alignment 1 of ‘struct vnt_cts_fb’ is less than 2 [-Wpacked-not-aligned]

The root cause seems to be that _because_ struct ieee80211_cts is marked as __aligned(2),
this requires any encapsulating struct to also have an alignment of 2.

Fixes: 2faf12c57efe ("staging: vt665x: fix alignment constraints")
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Edmundo Carmona Antoranz <eantoranz@gmail.com>
Link: https://lore.kernel.org/r/20210316181736.2553318-1-eantoranz@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/rxtx.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/vt6655/rxtx.h b/drivers/staging/vt6655/rxtx.h
index e7061d383306..c3c2c1566882 100644
--- a/drivers/staging/vt6655/rxtx.h
+++ b/drivers/staging/vt6655/rxtx.h
@@ -150,7 +150,7 @@ struct vnt_cts {
 	u16 reserved;
 	struct ieee80211_cts data;
 	u16 reserved2;
-} __packed;
+} __packed __aligned(2);
 
 struct vnt_cts_fb {
 	struct vnt_phy_field b;
@@ -160,7 +160,7 @@ struct vnt_cts_fb {
 	__le16 cts_duration_ba_f1;
 	struct ieee80211_cts data;
 	u16 reserved2;
-} __packed;
+} __packed __aligned(2);
 
 struct vnt_tx_fifo_head {
 	u8 tx_key[WLAN_KEY_LEN_CCMP];

From 072a03e0a0b1bc22eb5970727877264657c61fd3 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 17 Mar 2021 10:10:35 +0100
Subject: [PATCH 1010/1820] iommu/amd: Move Stoney Ridge check to detect_ivrs()

The AMD IOMMU will not be enabled on AMD Stoney Ridge systems. Bail
out even earlier and refuse to even detect the IOMMU there.

References: https://bugzilla.kernel.org/show_bug.cgi?id=212133
References: https://bugzilla.suse.com/show_bug.cgi?id=1183132
Cc: stable@vger.kernel.org # v5.11
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20210317091037.31374-2-joro@8bytes.org
Acked-by: Huang Rui <ray.huang@amd.com>
---
 drivers/iommu/amd/init.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 9126efcbaf2c..3280e6f5b720 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -2714,7 +2714,6 @@ static int __init early_amd_iommu_init(void)
 	struct acpi_table_header *ivrs_base;
 	int i, remap_cache_sz, ret;
 	acpi_status status;
-	u32 pci_id;
 
 	if (!amd_iommu_detected)
 		return -ENODEV;
@@ -2804,16 +2803,6 @@ static int __init early_amd_iommu_init(void)
 	if (ret)
 		goto out;
 
-	/* Disable IOMMU if there's Stoney Ridge graphics */
-	for (i = 0; i < 32; i++) {
-		pci_id = read_pci_config(0, i, 0, 0);
-		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
-			pr_info("Disable IOMMU on Stoney Ridge\n");
-			amd_iommu_disabled = true;
-			break;
-		}
-	}
-
 	/* Disable any previously enabled IOMMUs */
 	if (!is_kdump_kernel() || amd_iommu_disabled)
 		disable_iommus();
@@ -2880,6 +2869,7 @@ static bool detect_ivrs(void)
 {
 	struct acpi_table_header *ivrs_base;
 	acpi_status status;
+	int i;
 
 	status = acpi_get_table("IVRS", 0, &ivrs_base);
 	if (status == AE_NOT_FOUND)
@@ -2892,6 +2882,17 @@ static bool detect_ivrs(void)
 
 	acpi_put_table(ivrs_base);
 
+	/* Don't use IOMMU if there is Stoney Ridge graphics */
+	for (i = 0; i < 32; i++) {
+		u32 pci_id;
+
+		pci_id = read_pci_config(0, i, 0, 0);
+		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
+			pr_info("Disable IOMMU on Stoney Ridge\n");
+			return false;
+		}
+	}
+
 	/* Make sure ACS will be enabled during PCI probe */
 	pci_request_acs();
 

From 9f81ca8d1fd68f5697c201f26632ed622e9e462f Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 17 Mar 2021 10:10:36 +0100
Subject: [PATCH 1011/1820] iommu/amd: Don't call early_amd_iommu_init() when
 AMD IOMMU is disabled

Don't even try to initialize the AMD IOMMU hardware when amd_iommu=off has been
passed on the kernel command line.

References: https://bugzilla.kernel.org/show_bug.cgi?id=212133
References: https://bugzilla.suse.com/show_bug.cgi?id=1183132
Cc: stable@vger.kernel.org # v5.11
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20210317091037.31374-3-joro@8bytes.org
Acked-by: Huang Rui <ray.huang@amd.com>
---
 drivers/iommu/amd/init.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 3280e6f5b720..61dae1800b7f 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -2919,12 +2919,12 @@ static int __init state_next(void)
 		}
 		break;
 	case IOMMU_IVRS_DETECTED:
-		ret = early_amd_iommu_init();
-		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
-		if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) {
-			pr_info("AMD IOMMU disabled\n");
+		if (amd_iommu_disabled) {
 			init_state = IOMMU_CMDLINE_DISABLED;
 			ret = -EINVAL;
+		} else {
+			ret = early_amd_iommu_init();
+			init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
 		}
 		break;
 	case IOMMU_ACPI_FINISHED:

From 4b8ef157ca832f812b3302b1800548bd92c207de Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 17 Mar 2021 10:10:37 +0100
Subject: [PATCH 1012/1820] iommu/amd: Keep track of amd_iommu_irq_remap state

The amd_iommu_irq_remap variable is set to true in amd_iommu_prepare().
But if initialization fails it is not set to false. Fix that and
correctly keep track of whether irq remapping is enabled or not.

References: https://bugzilla.kernel.org/show_bug.cgi?id=212133
References: https://bugzilla.suse.com/show_bug.cgi?id=1183132
Fixes: b34f10c2dc59 ("iommu/amd: Stop irq_remapping_select() matching when remapping is disabled")
Cc: stable@vger.kernel.org # v5.11
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20210317091037.31374-4-joro@8bytes.org
Acked-by: Huang Rui <ray.huang@amd.com>
---
 drivers/iommu/amd/init.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 61dae1800b7f..321f5906e6ed 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -3002,8 +3002,11 @@ int __init amd_iommu_prepare(void)
 	amd_iommu_irq_remap = true;
 
 	ret = iommu_go_to_state(IOMMU_ACPI_FINISHED);
-	if (ret)
+	if (ret) {
+		amd_iommu_irq_remap = false;
 		return ret;
+	}
+
 	return amd_iommu_irq_remap ? 0 : -ENODEV;
 }
 

From 8dfd0fa6ecdc5e2099a57d485b7ce237abc6c7a0 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Fri, 12 Mar 2021 18:54:39 +0300
Subject: [PATCH 1013/1820] iommu/tegra-smmu: Make tegra_smmu_probe_device() to
 handle all IOMMU phandles

The tegra_smmu_probe_device() handles only the first IOMMU device-tree
phandle, skipping the rest. Devices like 3D module on Tegra30 have
multiple IOMMU phandles, one for each h/w block, and thus, only one
IOMMU phandle is added to fwspec for the 3D module, breaking GPU.
Previously this problem was masked by tegra_smmu_attach_dev() which
didn't use the fwspec, but parsed the DT by itself. The previous commit
to tegra-smmu driver partially reverted changes that caused problems for
T124 and now we have tegra_smmu_attach_dev() that uses the fwspec and
the old-buggy variant of tegra_smmu_probe_device() which skips secondary
IOMMUs.

Make tegra_smmu_probe_device() not to skip the secondary IOMMUs. This
fixes a partially attached IOMMU of the 3D module on Tegra30 and now GPU
works properly once again.

Fixes: 765a9d1d02b2 ("iommu/tegra-smmu: Fix mc errors on tegra124-nyan")
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Tested-by: Nicolin Chen <nicoleotsuka@gmail.com>
Link: https://lore.kernel.org/r/20210312155439.18477-1-digetx@gmail.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/tegra-smmu.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 97eb62f667d2..602aab98c079 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -849,12 +849,11 @@ static struct iommu_device *tegra_smmu_probe_device(struct device *dev)
 		smmu = tegra_smmu_find(args.np);
 		if (smmu) {
 			err = tegra_smmu_configure(smmu, dev, &args);
-			of_node_put(args.np);
 
-			if (err < 0)
+			if (err < 0) {
+				of_node_put(args.np);
 				return ERR_PTR(err);
-
-			break;
+			}
 		}
 
 		of_node_put(args.np);

From e409a6a3e0690efdef9b8a96197bc61ff117cfaf Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 15 Mar 2021 12:50:08 +0100
Subject: [PATCH 1014/1820] i2c: turn recovery error on init to debug

In some configurations, recovery is optional. So, don't throw an error
when it is not used because e.g. pinctrl settings for recovery are not
provided. Reword the message and make it debug output.

Reported-by: Klaus Kudielka <klaus.kudielka@gmail.com>
Tested-by: Klaus Kudielka <klaus.kudielka@gmail.com>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
Cc: stable@kernel.org
---
 drivers/i2c/i2c-core-base.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 63ebf722a424..f21362355973 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -378,7 +378,7 @@ static int i2c_gpio_init_recovery(struct i2c_adapter *adap)
 static int i2c_init_recovery(struct i2c_adapter *adap)
 {
 	struct i2c_bus_recovery_info *bri = adap->bus_recovery_info;
-	char *err_str;
+	char *err_str, *err_level = KERN_ERR;
 
 	if (!bri)
 		return 0;
@@ -387,7 +387,8 @@ static int i2c_init_recovery(struct i2c_adapter *adap)
 		return -EPROBE_DEFER;
 
 	if (!bri->recover_bus) {
-		err_str = "no recover_bus() found";
+		err_str = "no suitable method provided";
+		err_level = KERN_DEBUG;
 		goto err;
 	}
 
@@ -414,7 +415,7 @@ static int i2c_init_recovery(struct i2c_adapter *adap)
 
 	return 0;
  err:
-	dev_err(&adap->dev, "Not using recovery: %s\n", err_str);
+	dev_printk(err_level, &adap->dev, "Not using recovery: %s\n", err_str);
 	adap->bus_recovery_info = NULL;
 
 	return -EINVAL;

From cc9cfddb0433961107bb156fa769fdd7eb6718de Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Mar 2021 15:37:35 +0100
Subject: [PATCH 1015/1820] KVM: x86: hyper-v: Track Hyper-V TSC page status

Create an infrastructure for tracking Hyper-V TSC page status, i.e. if it
was updated from guest/host side or if we've failed to set it up (because
e.g. guest wrote some garbage to HV_X64_MSR_REFERENCE_TSC) and there's no
need to retry.

Also, in a hypothetical situation when we are in 'always catchup' mode for
TSC we can now avoid contending 'hv->hv_lock' on every guest enter by
setting the state to HV_TSC_PAGE_BROKEN after compute_tsc_page_parameters()
returns false.

Check for HV_TSC_PAGE_SET state instead of '!hv->tsc_ref.tsc_sequence' in
get_time_ref_counter() to properly handle the situation when we failed to
write the updated TSC page values to the guest.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210316143736.964151-4-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h | 17 ++++++++++++
 arch/x86/kvm/hyperv.c           | 49 +++++++++++++++++++++++----------
 2 files changed, 52 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9bc091ecaaeb..e1b6e2edc828 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -884,12 +884,29 @@ struct kvm_hv_syndbg {
 	u64 options;
 };
 
+/* Current state of Hyper-V TSC page clocksource */
+enum hv_tsc_page_status {
+	/* TSC page was not set up or disabled */
+	HV_TSC_PAGE_UNSET = 0,
+	/* TSC page MSR was written by the guest, update pending */
+	HV_TSC_PAGE_GUEST_CHANGED,
+	/* TSC page MSR was written by KVM userspace, update pending */
+	HV_TSC_PAGE_HOST_CHANGED,
+	/* TSC page was properly set up and is currently active  */
+	HV_TSC_PAGE_SET,
+	/* TSC page is currently being updated and therefore is inactive */
+	HV_TSC_PAGE_UPDATING,
+	/* TSC page was set up with an inaccessible GPA */
+	HV_TSC_PAGE_BROKEN,
+};
+
 /* Hyper-V emulation context */
 struct kvm_hv {
 	struct mutex hv_lock;
 	u64 hv_guest_os_id;
 	u64 hv_hypercall;
 	u64 hv_tsc_page;
+	enum hv_tsc_page_status hv_tsc_page_status;
 
 	/* Hyper-v based guest crash (NT kernel bugcheck) parameters */
 	u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index a0e3c49233d4..5c0f10a2b3ab 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -520,10 +520,10 @@ static u64 get_time_ref_counter(struct kvm *kvm)
 	u64 tsc;
 
 	/*
-	 * The guest has not set up the TSC page or the clock isn't
-	 * stable, fall back to get_kvmclock_ns.
+	 * Fall back to get_kvmclock_ns() when TSC page hasn't been set up,
+	 * is broken, disabled or being updated.
 	 */
-	if (!hv->tsc_ref.tsc_sequence)
+	if (hv->hv_tsc_page_status != HV_TSC_PAGE_SET)
 		return div_u64(get_kvmclock_ns(kvm), 100);
 
 	vcpu = kvm_get_vcpu(kvm, 0);
@@ -1087,7 +1087,8 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence));
 	BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0);
 
-	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+	if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
+	    hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET)
 		return;
 
 	mutex_lock(&hv->hv_lock);
@@ -1101,7 +1102,7 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	 */
 	if (unlikely(kvm_read_guest(kvm, gfn_to_gpa(gfn),
 				    &tsc_seq, sizeof(tsc_seq))))
-		goto out_unlock;
+		goto out_err;
 
 	/*
 	 * While we're computing and writing the parameters, force the
@@ -1110,15 +1111,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	hv->tsc_ref.tsc_sequence = 0;
 	if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
 			    &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
-		goto out_unlock;
+		goto out_err;
 
 	if (!compute_tsc_page_parameters(hv_clock, &hv->tsc_ref))
-		goto out_unlock;
+		goto out_err;
 
 	/* Ensure sequence is zero before writing the rest of the struct.  */
 	smp_wmb();
 	if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref)))
-		goto out_unlock;
+		goto out_err;
 
 	/*
 	 * Now switch to the TSC page mechanism by writing the sequence.
@@ -1131,8 +1132,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	smp_wmb();
 
 	hv->tsc_ref.tsc_sequence = tsc_seq;
-	kvm_write_guest(kvm, gfn_to_gpa(gfn),
-			&hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence));
+	if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
+			    &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
+		goto out_err;
+
+	hv->hv_tsc_page_status = HV_TSC_PAGE_SET;
+	goto out_unlock;
+
+out_err:
+	hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
 out_unlock:
 	mutex_unlock(&hv->hv_lock);
 }
@@ -1142,7 +1150,8 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
 	struct kvm_hv *hv = to_kvm_hv(kvm);
 	u64 gfn;
 
-	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+	if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
+	    hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET)
 		return;
 
 	mutex_lock(&hv->hv_lock);
@@ -1150,11 +1159,16 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
 	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
 		goto out_unlock;
 
+	/* Preserve HV_TSC_PAGE_GUEST_CHANGED/HV_TSC_PAGE_HOST_CHANGED states */
+	if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET)
+		hv->hv_tsc_page_status = HV_TSC_PAGE_UPDATING;
+
 	gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
 
 	hv->tsc_ref.tsc_sequence = 0;
-	kvm_write_guest(kvm, gfn_to_gpa(gfn),
-			&hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence));
+	if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
+			    &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
+		hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
 
 out_unlock:
 	mutex_unlock(&hv->hv_lock);
@@ -1216,8 +1230,15 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 	}
 	case HV_X64_MSR_REFERENCE_TSC:
 		hv->hv_tsc_page = data;
-		if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)
+		if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) {
+			if (!host)
+				hv->hv_tsc_page_status = HV_TSC_PAGE_GUEST_CHANGED;
+			else
+				hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED;
 			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
+		} else {
+			hv->hv_tsc_page_status = HV_TSC_PAGE_UNSET;
+		}
 		break;
 	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
 		return kvm_hv_msr_set_crash_data(kvm,

From 0469f2f7ab4c6a6cae4b74c4f981c4da6d909411 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Mar 2021 15:37:36 +0100
Subject: [PATCH 1016/1820] KVM: x86: hyper-v: Don't touch TSC page values when
 guest opted for re-enlightenment

When guest opts for re-enlightenment notifications upon migration, it is
in its right to assume that TSC page values never change (as they're only
supposed to change upon migration and the host has to keep things as they
are before it receives confirmation from the guest). This is mostly true
until the guest is migrated somewhere. KVM userspace (e.g. QEMU) will
trigger masterclock update by writing to HV_X64_MSR_REFERENCE_TSC, by
calling KVM_SET_CLOCK,... and as TSC value and kvmclock reading drift
apart (even slightly), the update causes TSC page values to change.

The issue at hand is that when Hyper-V is migrated, it uses stale (cached)
TSC page values to compute the difference between its own clocksource
(provided by KVM) and its guests' TSC pages to program synthetic timers
and in some cases, when TSC page is updated, this puts all stimer
expirations in the past. This, in its turn, causes an interrupt storm
and L2 guests not making much forward progress.

Note, KVM doesn't fully implement re-enlightenment notification. Basically,
the support for reenlightenment MSRs is just a stub and userspace is only
expected to expose the feature when TSC scaling on the expected destination
hosts is available. With TSC scaling, no real re-enlightenment is needed
as TSC frequency doesn't change. With TSC scaling becoming ubiquitous, it
likely makes little sense to fully implement re-enlightenment in KVM.

Prevent TSC page from being updated after migration. In case it's not the
guest who's initiating the change and when TSC page is already enabled,
just keep it as it is: TSC value is supposed to be preserved across
migration and TSC frequency can't change with re-enlightenment enabled.
The guest is doomed anyway if any of this is not true.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210316143736.964151-5-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/hyperv.c | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 5c0f10a2b3ab..f98370a39936 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1077,6 +1077,21 @@ static bool compute_tsc_page_parameters(struct pvclock_vcpu_time_info *hv_clock,
 	return true;
 }
 
+/*
+ * Don't touch TSC page values if the guest has opted for TSC emulation after
+ * migration. KVM doesn't fully support reenlightenment notifications and TSC
+ * access emulation and Hyper-V is known to expect the values in TSC page to
+ * stay constant before TSC access emulation is disabled from guest side
+ * (HV_X64_MSR_TSC_EMULATION_STATUS). KVM userspace is expected to preserve TSC
+ * frequency and guest visible TSC value across migration (and prevent it when
+ * TSC scaling is unsupported).
+ */
+static inline bool tsc_page_update_unsafe(struct kvm_hv *hv)
+{
+	return (hv->hv_tsc_page_status != HV_TSC_PAGE_GUEST_CHANGED) &&
+		hv->hv_tsc_emulation_control;
+}
+
 void kvm_hv_setup_tsc_page(struct kvm *kvm,
 			   struct pvclock_vcpu_time_info *hv_clock)
 {
@@ -1104,6 +1119,14 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 				    &tsc_seq, sizeof(tsc_seq))))
 		goto out_err;
 
+	if (tsc_seq && tsc_page_update_unsafe(hv)) {
+		if (kvm_read_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref)))
+			goto out_err;
+
+		hv->hv_tsc_page_status = HV_TSC_PAGE_SET;
+		goto out_unlock;
+	}
+
 	/*
 	 * While we're computing and writing the parameters, force the
 	 * guest to use the time reference count MSR.
@@ -1151,7 +1174,8 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
 	u64 gfn;
 
 	if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
-	    hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET)
+	    hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET ||
+	    tsc_page_update_unsafe(hv))
 		return;
 
 	mutex_lock(&hv->hv_lock);

From 053191b6a4bc2d429e94e866e3b2bc611d5add31 Mon Sep 17 00:00:00 2001
From: Mark Pearson <markpearson@lenovo.com>
Date: Thu, 11 Mar 2021 12:48:43 -0500
Subject: [PATCH 1017/1820] platform/x86: thinkpad_acpi: check dytc version for
 lapmode sysfs

Lenovo platforms with DYTC versions earlier than version 5 don't set
the lapmode interface correctly, causing issues with thermald on
older platforms.

Add checking to only create the dytc_lapmode interface for version
5 and later.

Fixes: 1ac09656bded ("platform/x86: thinkpad_acpi: Add palm sensor support")
Signed-off-by: Mark Pearson <markpearson@lenovo.com>
Link: https://lore.kernel.org/r/20210311174843.3161-1-markpearson@lenovo.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/thinkpad_acpi.c | 91 ++++++++++++++++++++--------
 1 file changed, 65 insertions(+), 26 deletions(-)

diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index b881044b31b0..f7de90a47e28 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -9845,6 +9845,11 @@ static struct ibm_struct lcdshadow_driver_data = {
  * Thinkpad sensor interfaces
  */
 
+#define DYTC_CMD_QUERY        0 /* To get DYTC status - enable/revision */
+#define DYTC_QUERY_ENABLE_BIT 8  /* Bit        8 - 0 = disabled, 1 = enabled */
+#define DYTC_QUERY_SUBREV_BIT 16 /* Bits 16 - 27 - sub revision */
+#define DYTC_QUERY_REV_BIT    28 /* Bits 28 - 31 - revision */
+
 #define DYTC_CMD_GET          2 /* To get current IC function and mode */
 #define DYTC_GET_LAPMODE_BIT 17 /* Set when in lapmode */
 
@@ -9855,6 +9860,7 @@ static bool has_palmsensor;
 static bool has_lapsensor;
 static bool palm_state;
 static bool lap_state;
+static int dytc_version;
 
 static int dytc_command(int command, int *output)
 {
@@ -9869,6 +9875,33 @@ static int dytc_command(int command, int *output)
 	return 0;
 }
 
+static int dytc_get_version(void)
+{
+	int err, output;
+
+	/* Check if we've been called before - and just return cached value */
+	if (dytc_version)
+		return dytc_version;
+
+	/* Otherwise query DYTC and extract version information */
+	err = dytc_command(DYTC_CMD_QUERY, &output);
+	/*
+	 * If support isn't available (ENODEV) then don't return an error
+	 * and don't create the sysfs group
+	 */
+	if (err == -ENODEV)
+		return 0;
+	/* For all other errors we can flag the failure */
+	if (err)
+		return err;
+
+	/* Check DYTC is enabled and supports mode setting */
+	if (output & BIT(DYTC_QUERY_ENABLE_BIT))
+		dytc_version = (output >> DYTC_QUERY_REV_BIT) & 0xF;
+
+	return 0;
+}
+
 static int lapsensor_get(bool *present, bool *state)
 {
 	int output, err;
@@ -9974,7 +10007,18 @@ static int tpacpi_proxsensor_init(struct ibm_init_struct *iibm)
 		if (err)
 			return err;
 	}
-	if (has_lapsensor) {
+
+	/* Check if we know the DYTC version, if we don't then get it */
+	if (!dytc_version) {
+		err = dytc_get_version();
+		if (err)
+			return err;
+	}
+	/*
+	 * Platforms before DYTC version 5 claim to have a lap sensor, but it doesn't work, so we
+	 * ignore them
+	 */
+	if (has_lapsensor && (dytc_version >= 5)) {
 		err = sysfs_create_file(&tpacpi_pdev->dev.kobj, &dev_attr_dytc_lapmode.attr);
 		if (err)
 			return err;
@@ -9999,14 +10043,9 @@ static struct ibm_struct proxsensor_driver_data = {
  * DYTC Platform Profile interface
  */
 
-#define DYTC_CMD_QUERY        0 /* To get DYTC status - enable/revision */
 #define DYTC_CMD_SET          1 /* To enable/disable IC function mode */
 #define DYTC_CMD_RESET    0x1ff /* To reset back to default */
 
-#define DYTC_QUERY_ENABLE_BIT 8  /* Bit        8 - 0 = disabled, 1 = enabled */
-#define DYTC_QUERY_SUBREV_BIT 16 /* Bits 16 - 27 - sub revision */
-#define DYTC_QUERY_REV_BIT    28 /* Bits 28 - 31 - revision */
-
 #define DYTC_GET_FUNCTION_BIT 8  /* Bits  8-11 - function setting */
 #define DYTC_GET_MODE_BIT     12 /* Bits 12-15 - mode setting */
 
@@ -10211,28 +10250,28 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm)
 	if (err)
 		return err;
 
+	/* Check if we know the DYTC version, if we don't then get it */
+	if (!dytc_version) {
+		err = dytc_get_version();
+		if (err)
+			return err;
+	}
 	/* Check DYTC is enabled and supports mode setting */
-	if (output & BIT(DYTC_QUERY_ENABLE_BIT)) {
-		/* Only DYTC v5.0 and later has this feature. */
-		int dytc_version;
+	if (dytc_version >= 5) {
+		dbg_printk(TPACPI_DBG_INIT,
+				"DYTC version %d: thermal mode available\n", dytc_version);
+		/* Create platform_profile structure and register */
+		err = platform_profile_register(&dytc_profile);
+		/*
+		 * If for some reason platform_profiles aren't enabled
+		 * don't quit terminally.
+		 */
+		if (err)
+			return 0;
 
-		dytc_version = (output >> DYTC_QUERY_REV_BIT) & 0xF;
-		if (dytc_version >= 5) {
-			dbg_printk(TPACPI_DBG_INIT,
-				   "DYTC version %d: thermal mode available\n", dytc_version);
-			/* Create platform_profile structure and register */
-			err = platform_profile_register(&dytc_profile);
-			/*
-			 * If for some reason platform_profiles aren't enabled
-			 * don't quit terminally.
-			 */
-			if (err)
-				return 0;
-
-			dytc_profile_available = true;
-			/* Ensure initial values are correct */
-			dytc_profile_refresh();
-		}
+		dytc_profile_available = true;
+		/* Ensure initial values are correct */
+		dytc_profile_refresh();
 	}
 	return 0;
 }

From 50b1affc891cbc103a2334ce909a026e25f4c84d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 18 Mar 2021 13:20:08 +0000
Subject: [PATCH 1018/1820] ALSA: usb-audio: Fix unintentional sign extension
 issue

The shifting of the u8 integer device by 24 bits to the left will
be promoted to a 32 bit signed int and then sign-extended to a
64 bit unsigned long. In the event that the top bit of device is
set then all then all the upper 32 bits of the unsigned long will
end up as also being set because of the sign-extension. Fix this
by casting device to an unsigned long before the shift.

Addresses-Coverity: ("Unintended sign extension")
Fixes: a07df82c7990 ("ALSA: usb-audio: Add DJM750 to Pioneer mixer quirk")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Link: https://lore.kernel.org/r/20210318132008.15266-1-colin.king@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer_quirks.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 08873d2afe4d..ffd922327ae4 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -2883,7 +2883,7 @@ static int snd_djm_controls_put(struct snd_kcontrol *kctl, struct snd_ctl_elem_v
 	u8 group = (private_value & SND_DJM_GROUP_MASK) >> SND_DJM_GROUP_SHIFT;
 	u16 value = elem->value.enumerated.item[0];
 
-	kctl->private_value = ((device << SND_DJM_DEVICE_SHIFT) |
+	kctl->private_value = (((unsigned long)device << SND_DJM_DEVICE_SHIFT) |
 			      (group << SND_DJM_GROUP_SHIFT) |
 			      value);
 
@@ -2921,7 +2921,7 @@ static int snd_djm_controls_create(struct usb_mixer_interface *mixer,
 		value = device->controls[i].default_value;
 		knew.name = device->controls[i].name;
 		knew.private_value = (
-			(device_idx << SND_DJM_DEVICE_SHIFT) |
+			((unsigned long)device_idx << SND_DJM_DEVICE_SHIFT) |
 			(i << SND_DJM_GROUP_SHIFT) |
 			value);
 		err = snd_djm_controls_update(mixer, device_idx, i, value);

From 2c7f76b4c42bd5d953bc821e151644434865f999 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Thu, 18 Mar 2021 15:09:49 +0100
Subject: [PATCH 1019/1820] selftests: kvm: Add basic Hyper-V clocksources
 tests

Introduce a new selftest for Hyper-V clocksources (MSR-based reference TSC
and TSC page). As a starting point, test the following:
1) Reference TSC is 1Ghz clock.
2) Reference TSC and TSC page give the same reading.
3) TSC page gets updated upon KVM_SET_CLOCK call.
4) TSC page does not get updated when guest opted for reenlightenment.
5) Disabled TSC page doesn't get updated.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210318140949.1065740-1-vkuznets@redhat.com>
[Add a host-side test using TSC + KVM_GET_MSR too. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore        |   1 +
 tools/testing/selftests/kvm/Makefile          |   1 +
 .../selftests/kvm/x86_64/hyperv_clock.c       | 260 ++++++++++++++++++
 3 files changed, 262 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/x86_64/hyperv_clock.c

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 32b87cc77c8e..22be05c55f13 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -9,6 +9,7 @@
 /x86_64/evmcs_test
 /x86_64/get_cpuid_test
 /x86_64/kvm_pv_test
+/x86_64/hyperv_clock
 /x86_64/hyperv_cpuid
 /x86_64/mmio_warning_test
 /x86_64/platform_info_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index a6d61f451f88..c3672e9087d3 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -41,6 +41,7 @@ LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_ha
 TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test
+TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
 TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
 TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
new file mode 100644
index 000000000000..ffbc4555c6e2
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -0,0 +1,260 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021, Red Hat, Inc.
+ *
+ * Tests for Hyper-V clocksources
+ */
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+struct ms_hyperv_tsc_page {
+	volatile u32 tsc_sequence;
+	u32 reserved1;
+	volatile u64 tsc_scale;
+	volatile s64 tsc_offset;
+} __packed;
+
+#define HV_X64_MSR_GUEST_OS_ID			0x40000000
+#define HV_X64_MSR_TIME_REF_COUNT		0x40000020
+#define HV_X64_MSR_REFERENCE_TSC		0x40000021
+#define HV_X64_MSR_TSC_FREQUENCY		0x40000022
+#define HV_X64_MSR_REENLIGHTENMENT_CONTROL	0x40000106
+#define HV_X64_MSR_TSC_EMULATION_CONTROL	0x40000107
+
+/* Simplified mul_u64_u64_shr() */
+static inline u64 mul_u64_u64_shr64(u64 a, u64 b)
+{
+	union {
+		u64 ll;
+		struct {
+			u32 low, high;
+		} l;
+	} rm, rn, rh, a0, b0;
+	u64 c;
+
+	a0.ll = a;
+	b0.ll = b;
+
+	rm.ll = (u64)a0.l.low * b0.l.high;
+	rn.ll = (u64)a0.l.high * b0.l.low;
+	rh.ll = (u64)a0.l.high * b0.l.high;
+
+	rh.l.low = c = rm.l.high + rn.l.high + rh.l.low;
+	rh.l.high = (c >> 32) + rh.l.high;
+
+	return rh.ll;
+}
+
+static inline void nop_loop(void)
+{
+	int i;
+
+	for (i = 0; i < 1000000; i++)
+		asm volatile("nop");
+}
+
+static inline void check_tsc_msr_rdtsc(void)
+{
+	u64 tsc_freq, r1, r2, t1, t2;
+	s64 delta_ns;
+
+	tsc_freq = rdmsr(HV_X64_MSR_TSC_FREQUENCY);
+	GUEST_ASSERT(tsc_freq > 0);
+
+	/* First, check MSR-based clocksource */
+	r1 = rdtsc();
+	t1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+	nop_loop();
+	r2 = rdtsc();
+	t2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+
+	GUEST_ASSERT(r2 > r1 && t2 > t1);
+
+	/* HV_X64_MSR_TIME_REF_COUNT is in 100ns */
+	delta_ns = ((t2 - t1) * 100) - ((r2 - r1) * 1000000000 / tsc_freq);
+	if (delta_ns < 0)
+		delta_ns = -delta_ns;
+
+	/* 1% tolerance */
+	GUEST_ASSERT(delta_ns * 100 < (t2 - t1) * 100);
+}
+
+static inline void check_tsc_msr_tsc_page(struct ms_hyperv_tsc_page *tsc_page)
+{
+	u64 r1, r2, t1, t2;
+
+	/* Compare TSC page clocksource with HV_X64_MSR_TIME_REF_COUNT */
+	t1 = mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset;
+	r1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+
+	/* 10 ms tolerance */
+	GUEST_ASSERT(r1 >= t1 && r1 - t1 < 100000);
+	nop_loop();
+
+	t2 = mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset;
+	r2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+	GUEST_ASSERT(r2 >= t1 && r2 - t2 < 100000);
+}
+
+static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_gpa)
+{
+	u64 tsc_scale, tsc_offset;
+
+	/* Set Guest OS id to enable Hyper-V emulation */
+	GUEST_SYNC(1);
+	wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48);
+	GUEST_SYNC(2);
+
+	check_tsc_msr_rdtsc();
+
+	GUEST_SYNC(3);
+
+	/* Set up TSC page is disabled state, check that it's clean */
+	wrmsr(HV_X64_MSR_REFERENCE_TSC, tsc_page_gpa);
+	GUEST_ASSERT(tsc_page->tsc_sequence == 0);
+	GUEST_ASSERT(tsc_page->tsc_scale == 0);
+	GUEST_ASSERT(tsc_page->tsc_offset == 0);
+
+	GUEST_SYNC(4);
+
+	/* Set up TSC page is enabled state */
+	wrmsr(HV_X64_MSR_REFERENCE_TSC, tsc_page_gpa | 0x1);
+	GUEST_ASSERT(tsc_page->tsc_sequence != 0);
+
+	GUEST_SYNC(5);
+
+	check_tsc_msr_tsc_page(tsc_page);
+
+	GUEST_SYNC(6);
+
+	tsc_offset = tsc_page->tsc_offset;
+	/* Call KVM_SET_CLOCK from userspace, check that TSC page was updated */
+	GUEST_SYNC(7);
+	GUEST_ASSERT(tsc_page->tsc_offset != tsc_offset);
+
+	nop_loop();
+
+	/*
+	 * Enable Re-enlightenment and check that TSC page stays constant across
+	 * KVM_SET_CLOCK.
+	 */
+	wrmsr(HV_X64_MSR_REENLIGHTENMENT_CONTROL, 0x1 << 16 | 0xff);
+	wrmsr(HV_X64_MSR_TSC_EMULATION_CONTROL, 0x1);
+	tsc_offset = tsc_page->tsc_offset;
+	tsc_scale = tsc_page->tsc_scale;
+	GUEST_SYNC(8);
+	GUEST_ASSERT(tsc_page->tsc_offset == tsc_offset);
+	GUEST_ASSERT(tsc_page->tsc_scale == tsc_scale);
+
+	GUEST_SYNC(9);
+
+	check_tsc_msr_tsc_page(tsc_page);
+
+	/*
+	 * Disable re-enlightenment and TSC page, check that KVM doesn't update
+	 * it anymore.
+	 */
+	wrmsr(HV_X64_MSR_REENLIGHTENMENT_CONTROL, 0);
+	wrmsr(HV_X64_MSR_TSC_EMULATION_CONTROL, 0);
+	wrmsr(HV_X64_MSR_REFERENCE_TSC, 0);
+	memset(tsc_page, 0, sizeof(*tsc_page));
+
+	GUEST_SYNC(10);
+	GUEST_ASSERT(tsc_page->tsc_sequence == 0);
+	GUEST_ASSERT(tsc_page->tsc_offset == 0);
+	GUEST_ASSERT(tsc_page->tsc_scale == 0);
+
+	GUEST_DONE();
+}
+
+#define VCPU_ID 0
+
+static void host_check_tsc_msr_rdtsc(struct kvm_vm *vm)
+{
+	u64 tsc_freq, r1, r2, t1, t2;
+	s64 delta_ns;
+
+	tsc_freq = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TSC_FREQUENCY);
+	TEST_ASSERT(tsc_freq > 0, "TSC frequency must be nonzero");
+
+	/* First, check MSR-based clocksource */
+	r1 = rdtsc();
+	t1 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+	nop_loop();
+	r2 = rdtsc();
+	t2 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+
+	TEST_ASSERT(t2 > t1, "Time reference MSR is not monotonic (%ld <= %ld)", t1, t2);
+
+	/* HV_X64_MSR_TIME_REF_COUNT is in 100ns */
+	delta_ns = ((t2 - t1) * 100) - ((r2 - r1) * 1000000000 / tsc_freq);
+	if (delta_ns < 0)
+		delta_ns = -delta_ns;
+
+	/* 1% tolerance */
+	TEST_ASSERT(delta_ns * 100 < (t2 - t1) * 100,
+		    "Elapsed time does not match (MSR=%ld, TSC=%ld)",
+		    (t2 - t1) * 100, (r2 - r1) * 1000000000 / tsc_freq);
+}
+
+int main(void)
+{
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct ucall uc;
+	vm_vaddr_t tsc_page_gva;
+	int stage;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_main);
+	run = vcpu_state(vm, VCPU_ID);
+
+	vcpu_set_hv_cpuid(vm, VCPU_ID);
+
+	tsc_page_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	memset(addr_gpa2hva(vm, tsc_page_gva), 0x0, getpagesize());
+	TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0,
+		"TSC page has to be page aligned\n");
+	vcpu_args_set(vm, VCPU_ID, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva));
+
+	host_check_tsc_msr_rdtsc(vm);
+
+	for (stage = 1;; stage++) {
+		_vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Stage %d: unexpected exit reason: %u (%s),\n",
+			    stage, run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+				  __FILE__, uc.args[1]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			/* Keep in sync with guest_main() */
+			TEST_ASSERT(stage == 11, "Testing ended prematurely, stage %d\n",
+				    stage);
+			goto out;
+		default:
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+
+		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+			    uc.args[1] == stage,
+			    "Stage %d: Unexpected register values vmexit, got %lx",
+			    stage, (ulong)uc.args[1]);
+
+		/* Reset kvmclock triggering TSC page update */
+		if (stage == 7 || stage == 8 || stage == 10) {
+			struct kvm_clock_data clock = {0};
+
+			vm_ioctl(vm, KVM_SET_CLOCK, &clock);
+		}
+	}
+
+out:
+	kvm_vm_free(vm);
+}

From 76cd979f4f38a27df22efb5773a0d567181a9392 Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Tue, 16 Mar 2021 16:33:27 +0100
Subject: [PATCH 1020/1820] io_uring: imply MSG_NOSIGNAL for
 send[msg]()/recv[msg]() calls

We never want to generate any SIGPIPE, -EPIPE only is much better.

Signed-off-by: Stefan Metzmacher <metze@samba.org>
Link: https://lore.kernel.org/r/38961085c3ec49fd21550c7788f214d1ff02d2d4.1615908477.git.metze@samba.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5f4e312111ea..a81f7a30ea70 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4384,7 +4384,7 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 		kmsg = &iomsg;
 	}
 
-	flags = req->sr_msg.msg_flags;
+	flags = req->sr_msg.msg_flags | MSG_NOSIGNAL;
 	if (flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
 	else if (issue_flags & IO_URING_F_NONBLOCK)
@@ -4428,7 +4428,7 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags)
 	msg.msg_controllen = 0;
 	msg.msg_namelen = 0;
 
-	flags = req->sr_msg.msg_flags;
+	flags = req->sr_msg.msg_flags | MSG_NOSIGNAL;
 	if (flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
 	else if (issue_flags & IO_URING_F_NONBLOCK)
@@ -4618,7 +4618,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 				1, req->sr_msg.len);
 	}
 
-	flags = req->sr_msg.msg_flags;
+	flags = req->sr_msg.msg_flags | MSG_NOSIGNAL;
 	if (flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
 	else if (force_nonblock)
@@ -4677,7 +4677,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	msg.msg_iocb = NULL;
 	msg.msg_flags = 0;
 
-	flags = req->sr_msg.msg_flags;
+	flags = req->sr_msg.msg_flags | MSG_NOSIGNAL;
 	if (flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
 	else if (force_nonblock)

From 53e043b2b432ef2294efec04dd8a88d96c024624 Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Mon, 15 Mar 2021 12:56:56 +0100
Subject: [PATCH 1021/1820] io_uring: remove structures from
 include/linux/io_uring.h

Link: https://lore.kernel.org/r/8c1d14f3748105f4caeda01716d47af2fa41d11c.1615809009.git.metze@samba.org
Signed-off-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.h               | 10 +++++++++-
 fs/io_uring.c            | 16 ++++++++++++++++
 include/linux/io_uring.h | 25 -------------------------
 3 files changed, 25 insertions(+), 26 deletions(-)

diff --git a/fs/io-wq.h b/fs/io-wq.h
index 1ac2f3248088..80d590564ff9 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -2,7 +2,6 @@
 #define INTERNAL_IO_WQ_H
 
 #include <linux/refcount.h>
-#include <linux/io_uring.h>
 
 struct io_wq;
 
@@ -21,6 +20,15 @@ enum io_wq_cancel {
 	IO_WQ_CANCEL_NOTFOUND,	/* work not found */
 };
 
+struct io_wq_work_node {
+	struct io_wq_work_node *next;
+};
+
+struct io_wq_work_list {
+	struct io_wq_work_node *first;
+	struct io_wq_work_node *last;
+};
+
 static inline void wq_list_add_after(struct io_wq_work_node *node,
 				     struct io_wq_work_node *pos,
 				     struct io_wq_work_list *list)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index a81f7a30ea70..52ba8d7f3eb8 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -456,6 +456,22 @@ struct io_ring_ctx {
 	struct list_head		tctx_list;
 };
 
+struct io_uring_task {
+	/* submission side */
+	struct xarray		xa;
+	struct wait_queue_head	wait;
+	void			*last;
+	void			*io_wq;
+	struct percpu_counter	inflight;
+	atomic_t		in_idle;
+	bool			sqpoll;
+
+	spinlock_t		task_lock;
+	struct io_wq_work_list	task_list;
+	unsigned long		task_state;
+	struct callback_head	task_work;
+};
+
 /*
  * First field must be the file pointer in all the
  * iocb unions! See also 'struct kiocb' in <linux/fs.h>
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 9761a0ec9f95..79cde9906be0 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -5,31 +5,6 @@
 #include <linux/sched.h>
 #include <linux/xarray.h>
 
-struct io_wq_work_node {
-	struct io_wq_work_node *next;
-};
-
-struct io_wq_work_list {
-	struct io_wq_work_node *first;
-	struct io_wq_work_node *last;
-};
-
-struct io_uring_task {
-	/* submission side */
-	struct xarray		xa;
-	struct wait_queue_head	wait;
-	void			*last;
-	void			*io_wq;
-	struct percpu_counter	inflight;
-	atomic_t		in_idle;
-	bool			sqpoll;
-
-	spinlock_t		task_lock;
-	struct io_wq_work_list	task_list;
-	unsigned long		task_state;
-	struct callback_head	task_work;
-};
-
 #if defined(CONFIG_IO_URING)
 struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_task_cancel(void);

From ee53fb2b197b72b126ca0387ae636da75d969428 Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Mon, 15 Mar 2021 12:56:57 +0100
Subject: [PATCH 1022/1820] io_uring: use typesafe pointers in io_uring_task

Signed-off-by: Stefan Metzmacher <metze@samba.org>
Link: https://lore.kernel.org/r/ce2a598e66e48347bb04afbaf2acc67c0cc7971a.1615809009.git.metze@samba.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 52ba8d7f3eb8..675073966760 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -460,8 +460,8 @@ struct io_uring_task {
 	/* submission side */
 	struct xarray		xa;
 	struct wait_queue_head	wait;
-	void			*last;
-	void			*io_wq;
+	const struct io_ring_ctx *last;
+	struct io_wq		*io_wq;
 	struct percpu_counter	inflight;
 	atomic_t		in_idle;
 	bool			sqpoll;

From de75a3d3f5a14c9ab3c4883de3471d3c92a8ee78 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 18 Mar 2021 11:54:35 +0000
Subject: [PATCH 1023/1820] io_uring: don't leak creds on SQO attach error

Attaching to already dead/dying SQPOLL task is disallowed in
io_sq_offload_create(), but cleanup is hand coded by calling
io_put_sq_data()/etc., that miss to put ctx->sq_creds.

Defer everything to error-path io_sq_thread_finish(), adding
ctx->sqd_list in the error case as well as finish will handle it.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 675073966760..ea2d3e120555 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7910,22 +7910,17 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 
 		ret = 0;
 		io_sq_thread_park(sqd);
+		list_add(&ctx->sqd_list, &sqd->ctx_list);
+		io_sqd_update_thread_idle(sqd);
 		/* don't attach to a dying SQPOLL thread, would be racy */
-		if (attached && !sqd->thread) {
+		if (attached && !sqd->thread)
 			ret = -ENXIO;
-		} else {
-			list_add(&ctx->sqd_list, &sqd->ctx_list);
-			io_sqd_update_thread_idle(sqd);
-		}
 		io_sq_thread_unpark(sqd);
 
-		if (ret < 0) {
-			io_put_sq_data(sqd);
-			ctx->sq_data = NULL;
-			return ret;
-		} else if (attached) {
+		if (ret < 0)
+			goto err;
+		if (attached)
 			return 0;
-		}
 
 		if (p->flags & IORING_SETUP_SQ_AFF) {
 			int cpu = p->sq_thread_cpu;

From 0bb788300990d3eb5582d3301a720f846c78925c Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 18 Mar 2021 11:22:05 +0000
Subject: [PATCH 1024/1820] btrfs: fix sleep while in non-sleep context during
 qgroup removal

While removing a qgroup's sysfs entry we end up taking the kernfs_mutex,
through kobject_del(), while holding the fs_info->qgroup_lock spinlock,
producing the following trace:

  [821.843637] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:281
  [821.843641] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 28214, name: podman
  [821.843644] CPU: 3 PID: 28214 Comm: podman Tainted: G        W         5.11.6 #15
  [821.843646] Hardware name: Dell Inc. PowerEdge R330/084XW4, BIOS 2.11.0 12/08/2020
  [821.843647] Call Trace:
  [821.843650]  dump_stack+0xa1/0xfb
  [821.843656]  ___might_sleep+0x144/0x160
  [821.843659]  mutex_lock+0x17/0x40
  [821.843662]  kernfs_remove_by_name_ns+0x1f/0x80
  [821.843666]  sysfs_remove_group+0x7d/0xe0
  [821.843668]  sysfs_remove_groups+0x28/0x40
  [821.843670]  kobject_del+0x2a/0x80
  [821.843672]  btrfs_sysfs_del_one_qgroup+0x2b/0x40 [btrfs]
  [821.843685]  __del_qgroup_rb+0x12/0x150 [btrfs]
  [821.843696]  btrfs_remove_qgroup+0x288/0x2a0 [btrfs]
  [821.843707]  btrfs_ioctl+0x3129/0x36a0 [btrfs]
  [821.843717]  ? __mod_lruvec_page_state+0x5e/0xb0
  [821.843719]  ? page_add_new_anon_rmap+0xbc/0x150
  [821.843723]  ? kfree+0x1b4/0x300
  [821.843725]  ? mntput_no_expire+0x55/0x330
  [821.843728]  __x64_sys_ioctl+0x5a/0xa0
  [821.843731]  do_syscall_64+0x33/0x70
  [821.843733]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
  [821.843736] RIP: 0033:0x4cd3fb
  [821.843741] RSP: 002b:000000c000906b20 EFLAGS: 00000206 ORIG_RAX: 0000000000000010
  [821.843744] RAX: ffffffffffffffda RBX: 000000c000050000 RCX: 00000000004cd3fb
  [821.843745] RDX: 000000c000906b98 RSI: 000000004010942a RDI: 000000000000000f
  [821.843747] RBP: 000000c000907cd0 R08: 000000c000622901 R09: 0000000000000000
  [821.843748] R10: 000000c000d992c0 R11: 0000000000000206 R12: 000000000000012d
  [821.843749] R13: 000000000000012c R14: 0000000000000200 R15: 0000000000000049

Fix this by removing the qgroup sysfs entry while not holding the spinlock,
since the spinlock is only meant for protection of the qgroup rbtree.

Reported-by: Stuart Shelton <srcshelton@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/7A5485BB-0628-419D-A4D3-27B1AF47E25A@gmail.com/
Fixes: 49e5fb46211de0 ("btrfs: qgroup: export qgroups in sysfs")
CC: stable@vger.kernel.org # 5.10+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 14ff388fd3bd..f0b9ef13153a 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -226,7 +226,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_qgroup_list *list;
 
-	btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
 	list_del(&qgroup->dirty);
 	while (!list_empty(&qgroup->groups)) {
 		list = list_first_entry(&qgroup->groups,
@@ -243,7 +242,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
 		list_del(&list->next_member);
 		kfree(list);
 	}
-	kfree(qgroup);
 }
 
 /* must be called with qgroup_lock held */
@@ -569,6 +567,8 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
 		qgroup = rb_entry(n, struct btrfs_qgroup, node);
 		rb_erase(n, &fs_info->qgroup_tree);
 		__del_qgroup_rb(fs_info, qgroup);
+		btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+		kfree(qgroup);
 	}
 	/*
 	 * We call btrfs_free_qgroup_config() when unmounting
@@ -1578,6 +1578,14 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 	spin_lock(&fs_info->qgroup_lock);
 	del_qgroup_rb(fs_info, qgroupid);
 	spin_unlock(&fs_info->qgroup_lock);
+
+	/*
+	 * Remove the qgroup from sysfs now without holding the qgroup_lock
+	 * spinlock, since the sysfs_remove_group() function needs to take
+	 * the mutex kernfs_mutex through kernfs_remove_by_name_ns().
+	 */
+	btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+	kfree(qgroup);
 out:
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	return ret;

From 9d3fcb28f9b9750b474811a2964ce022df56336e Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Tue, 16 Mar 2021 22:17:48 -0400
Subject: [PATCH 1025/1820] Revert "PM: ACPI: reboot: Use S5 for reboot"

This reverts commit d60cd06331a3566d3305b3c7b566e79edf4e2095.

This patch causes a panic when rebooting my Dell Poweredge r440.  I do
not have the full panic log as it's lost at that stage of the reboot and
I do not have a serial console.  Reverting this patch makes my system
able to reboot again.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/reboot.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/reboot.c b/kernel/reboot.c
index eb1b15850761..a6ad5eb2fa73 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -244,8 +244,6 @@ void migrate_to_reboot_cpu(void)
 void kernel_restart(char *cmd)
 {
 	kernel_restart_prepare(cmd);
-	if (pm_power_off_prepare)
-		pm_power_off_prepare();
 	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	if (!cmd)

From eddbe8e6521401003e37e7848ef72e75c10ee2aa Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 17 Mar 2021 17:45:23 -0700
Subject: [PATCH 1026/1820] selftest/bpf: Add a test to check trampoline
 freeing logic.

Add a selftest for commit e21aa341785c ("bpf: Fix fexit trampoline.")
to make sure that attaching fexit prog to a sleeping kernel function
will trigger appropriate trampoline and program destruction.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210318004523.55908-1-alexei.starovoitov@gmail.com
---
 .../selftests/bpf/prog_tests/fexit_sleep.c    | 82 +++++++++++++++++++
 .../testing/selftests/bpf/progs/fexit_sleep.c | 31 +++++++
 2 files changed, 113 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
 create mode 100644 tools/testing/selftests/bpf/progs/fexit_sleep.c

diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
new file mode 100644
index 000000000000..6c4d42a2386f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <test_progs.h>
+#include <time.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include "fexit_sleep.skel.h"
+
+static int do_sleep(void *skel)
+{
+	struct fexit_sleep *fexit_skel = skel;
+	struct timespec ts1 = { .tv_nsec = 1 };
+	struct timespec ts2 = { .tv_sec = 10 };
+
+	fexit_skel->bss->pid = getpid();
+	(void)syscall(__NR_nanosleep, &ts1, NULL);
+	(void)syscall(__NR_nanosleep, &ts2, NULL);
+	return 0;
+}
+
+#define STACK_SIZE (1024 * 1024)
+static char child_stack[STACK_SIZE];
+
+void test_fexit_sleep(void)
+{
+	struct fexit_sleep *fexit_skel = NULL;
+	int wstatus, duration = 0;
+	pid_t cpid;
+	int err, fexit_cnt;
+
+	fexit_skel = fexit_sleep__open_and_load();
+	if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
+		goto cleanup;
+
+	err = fexit_sleep__attach(fexit_skel);
+	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
+		goto cleanup;
+
+	cpid = clone(do_sleep, child_stack + STACK_SIZE, CLONE_FILES | SIGCHLD, fexit_skel);
+	if (CHECK(cpid == -1, "clone", strerror(errno)))
+		goto cleanup;
+
+	/* wait until first sys_nanosleep ends and second sys_nanosleep starts */
+	while (READ_ONCE(fexit_skel->bss->fentry_cnt) != 2);
+	fexit_cnt = READ_ONCE(fexit_skel->bss->fexit_cnt);
+	if (CHECK(fexit_cnt != 1, "fexit_cnt", "%d", fexit_cnt))
+		goto cleanup;
+
+	/* close progs and detach them. That will trigger two nop5->jmp5 rewrites
+	 * in the trampolines to skip nanosleep_fexit prog.
+	 * The nanosleep_fentry prog will get detached first.
+	 * The nanosleep_fexit prog will get detached second.
+	 * Detaching will trigger freeing of both progs JITed images.
+	 * There will be two dying bpf_tramp_image-s, but only the initial
+	 * bpf_tramp_image (with both _fentry and _fexit progs will be stuck
+	 * waiting for percpu_ref_kill to confirm). The other one
+	 * will be freed quickly.
+	 */
+	close(bpf_program__fd(fexit_skel->progs.nanosleep_fentry));
+	close(bpf_program__fd(fexit_skel->progs.nanosleep_fexit));
+	fexit_sleep__detach(fexit_skel);
+
+	/* kill the thread to unwind sys_nanosleep stack through the trampoline */
+	kill(cpid, 9);
+
+	if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", strerror(errno)))
+		goto cleanup;
+	if (CHECK(WEXITSTATUS(wstatus) != 0, "exitstatus", "failed"))
+		goto cleanup;
+
+	/* The bypassed nanosleep_fexit prog shouldn't have executed.
+	 * Unlike progs the maps were not freed and directly accessible.
+	 */
+	fexit_cnt = READ_ONCE(fexit_skel->bss->fexit_cnt);
+	if (CHECK(fexit_cnt != 1, "fexit_cnt", "%d", fexit_cnt))
+		goto cleanup;
+
+cleanup:
+	fexit_sleep__destroy(fexit_skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/fexit_sleep.c b/tools/testing/selftests/bpf/progs/fexit_sleep.c
new file mode 100644
index 000000000000..03a672d76353
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fexit_sleep.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+int pid = 0;
+int fentry_cnt = 0;
+int fexit_cnt = 0;
+
+SEC("fentry/__x64_sys_nanosleep")
+int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs)
+{
+	if ((int)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	fentry_cnt++;
+	return 0;
+}
+
+SEC("fexit/__x64_sys_nanosleep")
+int BPF_PROG(nanosleep_fexit, const struct pt_regs *regs, int ret)
+{
+	if ((int)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	fexit_cnt++;
+	return 0;
+}

From 2e8496f31d0be8f43849b2980b069f3a9805d047 Mon Sep 17 00:00:00 2001
From: Richard Gong <richard.gong@intel.com>
Date: Tue, 9 Feb 2021 16:20:27 -0600
Subject: [PATCH 1027/1820] firmware: stratix10-svc: reset
 COMMAND_RECONFIG_FLAG_PARTIAL to 0

Clean up COMMAND_RECONFIG_FLAG_PARTIAL flag by resetting it to 0, which
aligns with the firmware settings.

Fixes: 36847f9e3e56 ("firmware: stratix10-svc: correct reconfig flag and timeout values")
Signed-off-by: Richard Gong <richard.gong@intel.com>
Reviewed-by: Tom Rix <trix@redhat.com>
Signed-off-by: Moritz Fischer <mdf@kernel.org>
---
 include/linux/firmware/intel/stratix10-svc-client.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h
index ebc295647581..19781b0f6429 100644
--- a/include/linux/firmware/intel/stratix10-svc-client.h
+++ b/include/linux/firmware/intel/stratix10-svc-client.h
@@ -56,7 +56,7 @@
  * COMMAND_RECONFIG_FLAG_PARTIAL:
  * Set to FPGA configuration type (full or partial).
  */
-#define COMMAND_RECONFIG_FLAG_PARTIAL	1
+#define COMMAND_RECONFIG_FLAG_PARTIAL	0
 
 /*
  * Timeout settings for service clients:

From 83b62687a05205847d627f29126a8fee3c644335 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 18 Mar 2021 11:44:08 -0400
Subject: [PATCH 1028/1820] workqueue/tracing: Copy workqueue name to buffer in
 trace event

The trace event "workqueue_queue_work" references an unsafe string in
dereferencing the name of the workqueue. As the name is allocated, it
could later be freed, and the pointer to that string could stay on the
tracing buffer. If the trace buffer is read after the string is freed, it
will reference an unsafe pointer.

I added a new verifier to make sure that all strings referenced in the
output of the trace buffer is safe to read and this triggered on the
workqueue_queue_work trace event:

workqueue_queue_work: work struct=00000000b2b235c7 function=gc_worker workqueue=(0xffff888100051160:events_power_efficient)[UNSAFE-MEMORY] req_cpu=256 cpu=1
workqueue_queue_work: work struct=00000000c344caec function=flush_to_ldisc workqueue=(0xffff888100054d60:events_unbound)[UNSAFE-MEMORY] req_cpu=256 cpu=4294967295
workqueue_queue_work: work struct=00000000b2b235c7 function=gc_worker workqueue=(0xffff888100051160:events_power_efficient)[UNSAFE-MEMORY] req_cpu=256 cpu=1
workqueue_queue_work: work struct=000000000b238b3f function=vmstat_update workqueue=(0xffff8881000c3760:mm_percpu_wq)[UNSAFE-MEMORY] req_cpu=1 cpu=1

Also, if this event is read via a user space application like perf or
trace-cmd, the name would only be an address and useless information:

workqueue_queue_work: work struct=0xffff953f80b4b918 function=disk_events_workfn workqueue=ffff953f8005d378 req_cpu=8192 cpu=5

Cc: Zqiang <qiang.zhang@windriver.com>
Cc: Tejun Heo <tj@kernel.org>
Fixes: 7bf9c4a88e3e3 ("workqueue: tracing the name of the workqueue instead of it's address")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/trace/events/workqueue.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
index 970cc2ea2850..6154a2e72bce 100644
--- a/include/trace/events/workqueue.h
+++ b/include/trace/events/workqueue.h
@@ -30,7 +30,7 @@ TRACE_EVENT(workqueue_queue_work,
 	TP_STRUCT__entry(
 		__field( void *,	work	)
 		__field( void *,	function)
-		__field( const char *,	workqueue)
+		__string( workqueue,	pwq->wq->name)
 		__field( unsigned int,	req_cpu	)
 		__field( unsigned int,	cpu	)
 	),
@@ -38,13 +38,13 @@ TRACE_EVENT(workqueue_queue_work,
 	TP_fast_assign(
 		__entry->work		= work;
 		__entry->function	= work->func;
-		__entry->workqueue	= pwq->wq->name;
+		__assign_str(workqueue, pwq->wq->name);
 		__entry->req_cpu	= req_cpu;
 		__entry->cpu		= pwq->pool->cpu;
 	),
 
 	TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%u cpu=%u",
-		  __entry->work, __entry->function, __entry->workqueue,
+		  __entry->work, __entry->function, __get_str(workqueue),
 		  __entry->req_cpu, __entry->cpu)
 );
 

From 77a3aa26a00fe55325ae2a51d80a56836d1edce8 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Thu, 18 Mar 2021 15:56:29 +0100
Subject: [PATCH 1029/1820] selftests: kvm: add get_msr_index_features

Test the KVM_GET_MSR_FEATURE_INDEX_LIST
and KVM_GET_MSR_INDEX_LIST ioctls.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-Id: <20210318145629.486450-1-eesposit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore        |   1 +
 tools/testing/selftests/kvm/Makefile          |   1 +
 .../testing/selftests/kvm/include/kvm_util.h  |   1 +
 .../selftests/kvm/lib/kvm_util_internal.h     |   2 -
 .../kvm/x86_64/get_msr_index_features.c       | 134 ++++++++++++++++++
 5 files changed, 137 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/x86_64/get_msr_index_features.c

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 22be05c55f13..5873d54b19a0 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -8,6 +8,7 @@
 /x86_64/debug_regs
 /x86_64/evmcs_test
 /x86_64/get_cpuid_test
+/x86_64/get_msr_index_features
 /x86_64/kvm_pv_test
 /x86_64/hyperv_clock
 /x86_64/hyperv_cpuid
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index c3672e9087d3..ce34c8160fa3 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -39,6 +39,7 @@ LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
 LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 2d7eb6989e83..81af4bcc9ab9 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -16,6 +16,7 @@
 
 #include "sparsebit.h"
 
+#define KVM_DEV_PATH "/dev/kvm"
 #define KVM_MAX_VCPUS 512
 
 /*
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 34465dc562d8..91ce1b5d480b 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -10,8 +10,6 @@
 
 #include "sparsebit.h"
 
-#define KVM_DEV_PATH		"/dev/kvm"
-
 struct userspace_mem_region {
 	struct kvm_userspace_memory_region region;
 	struct sparsebit *unused_phy_pages;
diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c
new file mode 100644
index 000000000000..cb953df4d7d0
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that KVM_GET_MSR_INDEX_LIST and
+ * KVM_GET_MSR_FEATURE_INDEX_LIST work as intended
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+static int kvm_num_index_msrs(int kvm_fd, int nmsrs)
+{
+	struct kvm_msr_list *list;
+	int r;
+
+	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+	list->nmsrs = nmsrs;
+	r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+	TEST_ASSERT(r == -1 && errno == E2BIG,
+				"Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i",
+				r);
+
+	r = list->nmsrs;
+	free(list);
+	return r;
+}
+
+static void test_get_msr_index(void)
+{
+	int old_res, res, kvm_fd, r;
+	struct kvm_msr_list *list;
+
+	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+	if (kvm_fd < 0)
+		exit(KSFT_SKIP);
+
+	old_res = kvm_num_index_msrs(kvm_fd, 0);
+	TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0");
+
+	if (old_res != 1) {
+		res = kvm_num_index_msrs(kvm_fd, 1);
+		TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1");
+		TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical");
+	}
+
+	list = malloc(sizeof(*list) + old_res * sizeof(list->indices[0]));
+	list->nmsrs = old_res;
+	r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+
+	TEST_ASSERT(r == 0,
+		    "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i",
+		    r);
+	TEST_ASSERT(list->nmsrs == old_res, "Expecting nmsrs to be identical");
+	free(list);
+
+	close(kvm_fd);
+}
+
+static int kvm_num_feature_msrs(int kvm_fd, int nmsrs)
+{
+	struct kvm_msr_list *list;
+	int r;
+
+	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+	list->nmsrs = nmsrs;
+	r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list);
+	TEST_ASSERT(r == -1 && errno == E2BIG,
+		"Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST probe, r: %i",
+				r);
+
+	r = list->nmsrs;
+	free(list);
+	return r;
+}
+
+struct kvm_msr_list *kvm_get_msr_feature_list(int kvm_fd, int nmsrs)
+{
+	struct kvm_msr_list *list;
+	int r;
+
+	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+	list->nmsrs = nmsrs;
+	r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list);
+
+	TEST_ASSERT(r == 0,
+		"Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i",
+		r);
+
+	return list;
+}
+
+static void test_get_msr_feature(void)
+{
+	int res, old_res, i, kvm_fd;
+	struct kvm_msr_list *feature_list;
+
+	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+	if (kvm_fd < 0)
+		exit(KSFT_SKIP);
+
+	old_res = kvm_num_feature_msrs(kvm_fd, 0);
+	TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0");
+
+	if (old_res != 1) {
+		res = kvm_num_feature_msrs(kvm_fd, 1);
+		TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1");
+		TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical");
+	}
+
+	feature_list = kvm_get_msr_feature_list(kvm_fd, old_res);
+	TEST_ASSERT(old_res == feature_list->nmsrs,
+				"Unmatching number of msr indexes");
+
+	for (i = 0; i < feature_list->nmsrs; i++)
+		kvm_get_feature_msr(feature_list->indices[i]);
+
+	free(feature_list);
+	close(kvm_fd);
+}
+
+int main(int argc, char *argv[])
+{
+	if (kvm_check_cap(KVM_CAP_GET_MSR_FEATURES))
+		test_get_msr_feature();
+
+	test_get_msr_index();
+}

From e2c12909ae5f5181d9e0b0c536e26c6877daec48 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Thu, 18 Mar 2021 16:16:23 +0100
Subject: [PATCH 1030/1820] selftests: kvm: add _vm_ioctl

As in kvm_ioctl and _kvm_ioctl, add
the respective _vm_ioctl for vm_ioctl.

_vm_ioctl invokes an ioctl using the vm fd,
leaving the caller to test the result.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-Id: <20210318151624.490861-1-eesposit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h | 1 +
 tools/testing/selftests/kvm/lib/kvm_util.c     | 7 ++++++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 81af4bcc9ab9..0f4258eaa629 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -134,6 +134,7 @@ void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
 int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
 		void *arg);
 void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg);
 void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
 int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
 void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index e5fbf16f725b..b8849a1aca79 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1697,11 +1697,16 @@ void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
 {
 	int ret;
 
-	ret = ioctl(vm->fd, cmd, arg);
+	ret = _vm_ioctl(vm, cmd, arg);
 	TEST_ASSERT(ret == 0, "vm ioctl %lu failed, rc: %i errno: %i (%s)",
 		cmd, ret, errno, strerror(errno));
 }
 
+int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
+{
+	return ioctl(vm->fd, cmd, arg);
+}
+
 /*
  * KVM system ioctl
  *

From 3df2252436c08028a549e27ed7f097974e21d17b Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Thu, 18 Mar 2021 16:16:24 +0100
Subject: [PATCH 1031/1820] selftests: kvm: add set_boot_cpu_id test

Test for the KVM_SET_BOOT_CPU_ID ioctl.
Check that it correctly allows to change the BSP vcpu.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-Id: <20210318151624.490861-2-eesposit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore        |   1 +
 tools/testing/selftests/kvm/Makefile          |   1 +
 .../selftests/kvm/x86_64/set_boot_cpu_id.c    | 166 ++++++++++++++++++
 3 files changed, 168 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 5873d54b19a0..7bd7e776c266 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -14,6 +14,7 @@
 /x86_64/hyperv_cpuid
 /x86_64/mmio_warning_test
 /x86_64/platform_info_test
+/x86_64/set_boot_cpu_id
 /x86_64/set_sregs_test
 /x86_64/smm_test
 /x86_64/state_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index ce34c8160fa3..67eebb53235f 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -47,6 +47,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
 TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
 TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
 TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
 TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
 TEST_GEN_PROGS_x86_64 += x86_64/smm_test
 TEST_GEN_PROGS_x86_64 += x86_64/state_test
diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
new file mode 100644
index 000000000000..12c558fc8074
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that KVM_SET_BOOT_CPU_ID works as intended
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#define _GNU_SOURCE /* for program_invocation_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define N_VCPU 2
+#define VCPU_ID0 0
+#define VCPU_ID1 1
+
+static uint32_t get_bsp_flag(void)
+{
+	return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP;
+}
+
+static void guest_bsp_vcpu(void *arg)
+{
+	GUEST_SYNC(1);
+
+	GUEST_ASSERT(get_bsp_flag() != 0);
+
+	GUEST_DONE();
+}
+
+static void guest_not_bsp_vcpu(void *arg)
+{
+	GUEST_SYNC(1);
+
+	GUEST_ASSERT(get_bsp_flag() == 0);
+
+	GUEST_DONE();
+}
+
+static void test_set_boot_busy(struct kvm_vm *vm)
+{
+	int res;
+
+	res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID0);
+	TEST_ASSERT(res == -1 && errno == EBUSY,
+			"KVM_SET_BOOT_CPU_ID set while running vm");
+}
+
+static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct ucall uc;
+	int stage;
+
+	for (stage = 0; stage < 2; stage++) {
+
+		vcpu_run(vm, vcpuid);
+
+		switch (get_ucall(vm, vcpuid, &uc)) {
+		case UCALL_SYNC:
+			TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+					uc.args[1] == stage + 1,
+					"Stage %d: Unexpected register values vmexit, got %lx",
+					stage + 1, (ulong)uc.args[1]);
+			test_set_boot_busy(vm);
+			break;
+		case UCALL_DONE:
+			TEST_ASSERT(stage == 1,
+					"Expected GUEST_DONE in stage 2, got stage %d",
+					stage);
+			break;
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s at %s:%ld\n\tvalues: %#lx, %#lx",
+						(const char *)uc.args[0], __FILE__,
+						uc.args[1], uc.args[2], uc.args[3]);
+		default:
+			TEST_ASSERT(false, "Unexpected exit: %s",
+					exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason));
+		}
+	}
+}
+
+static struct kvm_vm *create_vm(void)
+{
+	struct kvm_vm *vm;
+	uint64_t vcpu_pages = (DEFAULT_STACK_PGS) * 2;
+	uint64_t extra_pg_pages = vcpu_pages / PTES_PER_MIN_PAGE * N_VCPU;
+	uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages;
+
+	pages = vm_adjust_num_guest_pages(VM_MODE_DEFAULT, pages);
+	vm = vm_create(VM_MODE_DEFAULT, pages, O_RDWR);
+
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+	vm_create_irqchip(vm);
+
+	return vm;
+}
+
+static void add_x86_vcpu(struct kvm_vm *vm, uint32_t vcpuid, bool bsp_code)
+{
+	if (bsp_code)
+		vm_vcpu_add_default(vm, vcpuid, guest_bsp_vcpu);
+	else
+		vm_vcpu_add_default(vm, vcpuid, guest_not_bsp_vcpu);
+
+	vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
+}
+
+static void run_vm_bsp(uint32_t bsp_vcpu)
+{
+	struct kvm_vm *vm;
+	bool is_bsp_vcpu1 = bsp_vcpu == VCPU_ID1;
+
+	vm = create_vm();
+
+	if (is_bsp_vcpu1)
+		vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+
+	add_x86_vcpu(vm, VCPU_ID0, !is_bsp_vcpu1);
+	add_x86_vcpu(vm, VCPU_ID1, is_bsp_vcpu1);
+
+	run_vcpu(vm, VCPU_ID0);
+	run_vcpu(vm, VCPU_ID1);
+
+	kvm_vm_free(vm);
+}
+
+static void check_set_bsp_busy(void)
+{
+	struct kvm_vm *vm;
+	int res;
+
+	vm = create_vm();
+
+	add_x86_vcpu(vm, VCPU_ID0, true);
+	add_x86_vcpu(vm, VCPU_ID1, false);
+
+	res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+	TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set after adding vcpu");
+
+	run_vcpu(vm, VCPU_ID0);
+	run_vcpu(vm, VCPU_ID1);
+
+	res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+	TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set to a terminated vcpu");
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	if (!kvm_check_cap(KVM_CAP_SET_BOOT_CPU_ID)) {
+		print_skip("set_boot_cpu_id not available");
+		return 0;
+	}
+
+	run_vm_bsp(VCPU_ID0);
+	run_vm_bsp(VCPU_ID1);
+	run_vm_bsp(VCPU_ID0);
+
+	check_set_bsp_busy();
+}

From b318e8decf6b9ef1bcf4ca06fae6d6a2cb5d5c5c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 16 Mar 2021 11:44:33 -0700
Subject: [PATCH 1032/1820] KVM: x86: Protect userspace MSR filter with SRCU,
 and set atomically-ish

Fix a plethora of issues with MSR filtering by installing the resulting
filter as an atomic bundle instead of updating the live filter one range
at a time.  The KVM_X86_SET_MSR_FILTER ioctl() isn't truly atomic, as
the hardware MSR bitmaps won't be updated until the next VM-Enter, but
the relevant software struct is atomically updated, which is what KVM
really needs.

Similar to the approach used for modifying memslots, make arch.msr_filter
a SRCU-protected pointer, do all the work configuring the new filter
outside of kvm->lock, and then acquire kvm->lock only when the new filter
has been vetted and created.  That way vCPU readers either see the old
filter or the new filter in their entirety, not some half-baked state.

Yuan Yao pointed out a use-after-free in ksm_msr_allowed() due to a
TOCTOU bug, but that's just the tip of the iceberg...

  - Nothing is __rcu annotated, making it nigh impossible to audit the
    code for correctness.
  - kvm_add_msr_filter() has an unpaired smp_wmb().  Violation of kernel
    coding style aside, the lack of a smb_rmb() anywhere casts all code
    into doubt.
  - kvm_clear_msr_filter() has a double free TOCTOU bug, as it grabs
    count before taking the lock.
  - kvm_clear_msr_filter() also has memory leak due to the same TOCTOU bug.

The entire approach of updating the live filter is also flawed.  While
installing a new filter is inherently racy if vCPUs are running, fixing
the above issues also makes it trivial to ensure certain behavior is
deterministic, e.g. KVM can provide deterministic behavior for MSRs with
identical settings in the old and new filters.  An atomic update of the
filter also prevents KVM from getting into a half-baked state, e.g. if
installing a filter fails, the existing approach would leave the filter
in a half-baked state, having already committed whatever bits of the
filter were already processed.

[*] https://lkml.kernel.org/r/20210312083157.25403-1-yaoyuan0329os@gmail.com

Fixes: 1a155254ff93 ("KVM: x86: Introduce MSR filtering")
Cc: stable@vger.kernel.org
Cc: Alexander Graf <graf@amazon.com>
Reported-by: Yuan Yao <yaoyuan0329os@gmail.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210316184436.2544875-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst  |   6 +-
 arch/x86/include/asm/kvm_host.h |  17 ++---
 arch/x86/kvm/x86.c              | 111 +++++++++++++++++++-------------
 3 files changed, 79 insertions(+), 55 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 38e327d4b479..2898d3e86b08 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -4806,8 +4806,10 @@ If an MSR access is not permitted through the filtering, it generates a
 allows user space to deflect and potentially handle various MSR accesses
 into user space.
 
-If a vCPU is in running state while this ioctl is invoked, the vCPU may
-experience inconsistent filtering behavior on MSR accesses.
+Note, invoking this ioctl with a vCPU is running is inherently racy.  However,
+KVM does guarantee that vCPUs will see either the previous filter or the new
+filter, e.g. MSRs with identical settings in both the old and new filter will
+have deterministic behavior.
 
 4.127 KVM_XEN_HVM_SET_ATTR
 --------------------------
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e1b6e2edc828..3768819693e5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -948,6 +948,12 @@ enum kvm_irqchip_mode {
 	KVM_IRQCHIP_SPLIT,        /* created with KVM_CAP_SPLIT_IRQCHIP */
 };
 
+struct kvm_x86_msr_filter {
+	u8 count;
+	bool default_allow:1;
+	struct msr_bitmap_range ranges[16];
+};
+
 #define APICV_INHIBIT_REASON_DISABLE    0
 #define APICV_INHIBIT_REASON_HYPERV     1
 #define APICV_INHIBIT_REASON_NESTED     2
@@ -1042,16 +1048,11 @@ struct kvm_arch {
 	bool guest_can_read_msr_platform_info;
 	bool exception_payload_enabled;
 
+	bool bus_lock_detection_enabled;
+
 	/* Deflect RDMSR and WRMSR to user space when they trigger a #GP */
 	u32 user_space_msr_mask;
-
-	struct {
-		u8 count;
-		bool default_allow:1;
-		struct msr_bitmap_range ranges[16];
-	} msr_filter;
-
-	bool bus_lock_detection_enabled;
+	struct kvm_x86_msr_filter __rcu *msr_filter;
 
 	struct kvm_pmu_event_filter __rcu *pmu_event_filter;
 	struct task_struct *nx_lpage_recovery_thread;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a5c5b38735e1..a04e78b89637 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1526,35 +1526,44 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
 
 bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type)
 {
+	struct kvm_x86_msr_filter *msr_filter;
+	struct msr_bitmap_range *ranges;
 	struct kvm *kvm = vcpu->kvm;
-	struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
-	u32 count = kvm->arch.msr_filter.count;
-	u32 i;
-	bool r = kvm->arch.msr_filter.default_allow;
+	bool allowed;
 	int idx;
+	u32 i;
 
-	/* MSR filtering not set up or x2APIC enabled, allow everything */
-	if (!count || (index >= 0x800 && index <= 0x8ff))
+	/* x2APIC MSRs do not support filtering. */
+	if (index >= 0x800 && index <= 0x8ff)
 		return true;
 
-	/* Prevent collision with set_msr_filter */
 	idx = srcu_read_lock(&kvm->srcu);
 
-	for (i = 0; i < count; i++) {
+	msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu);
+	if (!msr_filter) {
+		allowed = true;
+		goto out;
+	}
+
+	allowed = msr_filter->default_allow;
+	ranges = msr_filter->ranges;
+
+	for (i = 0; i < msr_filter->count; i++) {
 		u32 start = ranges[i].base;
 		u32 end = start + ranges[i].nmsrs;
 		u32 flags = ranges[i].flags;
 		unsigned long *bitmap = ranges[i].bitmap;
 
 		if ((index >= start) && (index < end) && (flags & type)) {
-			r = !!test_bit(index - start, bitmap);
+			allowed = !!test_bit(index - start, bitmap);
 			break;
 		}
 	}
 
+out:
 	srcu_read_unlock(&kvm->srcu, idx);
 
-	return r;
+	return allowed;
 }
 EXPORT_SYMBOL_GPL(kvm_msr_allowed);
 
@@ -5354,25 +5363,34 @@ split_irqchip_unlock:
 	return r;
 }
 
-static void kvm_clear_msr_filter(struct kvm *kvm)
+static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow)
 {
-	u32 i;
-	u32 count = kvm->arch.msr_filter.count;
-	struct msr_bitmap_range ranges[16];
+	struct kvm_x86_msr_filter *msr_filter;
 
-	mutex_lock(&kvm->lock);
-	kvm->arch.msr_filter.count = 0;
-	memcpy(ranges, kvm->arch.msr_filter.ranges, count * sizeof(ranges[0]));
-	mutex_unlock(&kvm->lock);
-	synchronize_srcu(&kvm->srcu);
+	msr_filter = kzalloc(sizeof(*msr_filter), GFP_KERNEL_ACCOUNT);
+	if (!msr_filter)
+		return NULL;
 
-	for (i = 0; i < count; i++)
-		kfree(ranges[i].bitmap);
+	msr_filter->default_allow = default_allow;
+	return msr_filter;
 }
 
-static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user_range)
+static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter)
+{
+	u32 i;
+
+	if (!msr_filter)
+		return;
+
+	for (i = 0; i < msr_filter->count; i++)
+		kfree(msr_filter->ranges[i].bitmap);
+
+	kfree(msr_filter);
+}
+
+static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter,
+			      struct kvm_msr_filter_range *user_range)
 {
-	struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
 	struct msr_bitmap_range range;
 	unsigned long *bitmap = NULL;
 	size_t bitmap_size;
@@ -5406,11 +5424,9 @@ static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user
 		goto err;
 	}
 
-	/* Everything ok, add this range identifier to our global pool */
-	ranges[kvm->arch.msr_filter.count] = range;
-	/* Make sure we filled the array before we tell anyone to walk it */
-	smp_wmb();
-	kvm->arch.msr_filter.count++;
+	/* Everything ok, add this range identifier. */
+	msr_filter->ranges[msr_filter->count] = range;
+	msr_filter->count++;
 
 	return 0;
 err:
@@ -5421,10 +5437,11 @@ err:
 static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_msr_filter __user *user_msr_filter = argp;
+	struct kvm_x86_msr_filter *new_filter, *old_filter;
 	struct kvm_msr_filter filter;
 	bool default_allow;
-	int r = 0;
 	bool empty = true;
+	int r = 0;
 	u32 i;
 
 	if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
@@ -5437,25 +5454,32 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
 	if (empty && !default_allow)
 		return -EINVAL;
 
-	kvm_clear_msr_filter(kvm);
+	new_filter = kvm_alloc_msr_filter(default_allow);
+	if (!new_filter)
+		return -ENOMEM;
 
-	kvm->arch.msr_filter.default_allow = default_allow;
-
-	/*
-	 * Protect from concurrent calls to this function that could trigger
-	 * a TOCTOU violation on kvm->arch.msr_filter.count.
-	 */
-	mutex_lock(&kvm->lock);
 	for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
-		r = kvm_add_msr_filter(kvm, &filter.ranges[i]);
-		if (r)
-			break;
+		r = kvm_add_msr_filter(new_filter, &filter.ranges[i]);
+		if (r) {
+			kvm_free_msr_filter(new_filter);
+			return r;
+		}
 	}
 
+	mutex_lock(&kvm->lock);
+
+	/* The per-VM filter is protected by kvm->lock... */
+	old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1);
+
+	rcu_assign_pointer(kvm->arch.msr_filter, new_filter);
+	synchronize_srcu(&kvm->srcu);
+
+	kvm_free_msr_filter(old_filter);
+
 	kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED);
 	mutex_unlock(&kvm->lock);
 
-	return r;
+	return 0;
 }
 
 long kvm_arch_vm_ioctl(struct file *filp,
@@ -10636,8 +10660,6 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm)
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
-	u32 i;
-
 	if (current->mm == kvm->mm) {
 		/*
 		 * Free memory regions allocated on behalf of userspace,
@@ -10653,8 +10675,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		mutex_unlock(&kvm->slots_lock);
 	}
 	static_call_cond(kvm_x86_vm_destroy)(kvm);
-	for (i = 0; i < kvm->arch.msr_filter.count; i++)
-		kfree(kvm->arch.msr_filter.ranges[i].bitmap);
+	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);

From c2162e13d6e2f43e5001a356196871642de070ba Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpengli@tencent.com>
Date: Fri, 12 Mar 2021 10:45:51 +0800
Subject: [PATCH 1033/1820] KVM: X86: Fix missing local pCPU when executing
 wbinvd on all dirty pCPUs

In order to deal with noncoherent DMA, we should execute wbinvd on
all dirty pCPUs when guest wbinvd exits to maintain data consistency.
smp_call_function_many() does not execute the provided function on the
local core, therefore replace it by on_each_cpu_mask().

Reported-by: Nadav Amit <namit@vmware.com>
Cc: Nadav Amit <namit@vmware.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Message-Id: <1615517151-7465-1-git-send-email-wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a04e78b89637..fe806e894212 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6629,7 +6629,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
 		int cpu = get_cpu();
 
 		cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
-		smp_call_function_many(vcpu->arch.wbinvd_dirty_mask,
+		on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask,
 				wbinvd_ipi, NULL, 1);
 		put_cpu();
 		cpumask_clear(vcpu->arch.wbinvd_dirty_mask);

From f4e61f0c9add3b00bd5f2df3c814d688849b8707 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpengli@tencent.com>
Date: Mon, 15 Mar 2021 14:55:28 +0800
Subject: [PATCH 1034/1820] x86/kvm: Fix broken irq restoration in kvm_wait

After commit 997acaf6b4b59c (lockdep: report broken irq restoration), the guest
splatting below during boot:

 raw_local_irq_restore() called with IRQs enabled
 WARNING: CPU: 1 PID: 169 at kernel/locking/irqflag-debug.c:10 warn_bogus_irq_restore+0x26/0x30
 Modules linked in: hid_generic usbhid hid
 CPU: 1 PID: 169 Comm: systemd-udevd Not tainted 5.11.0+ #25
 RIP: 0010:warn_bogus_irq_restore+0x26/0x30
 Call Trace:
  kvm_wait+0x76/0x90
  __pv_queued_spin_lock_slowpath+0x285/0x2e0
  do_raw_spin_lock+0xc9/0xd0
  _raw_spin_lock+0x59/0x70
  lockref_get_not_dead+0xf/0x50
  __legitimize_path+0x31/0x60
  legitimize_root+0x37/0x50
  try_to_unlazy_next+0x7f/0x1d0
  lookup_fast+0xb0/0x170
  path_openat+0x165/0x9b0
  do_filp_open+0x99/0x110
  do_sys_openat2+0x1f1/0x2e0
  do_sys_open+0x5c/0x80
  __x64_sys_open+0x21/0x30
  do_syscall_64+0x32/0x50
  entry_SYSCALL_64_after_hwframe+0x44/0xae

The new consistency checking,  expects local_irq_save() and
local_irq_restore() to be paired and sanely nested, and therefore expects
local_irq_restore() to be called with irqs disabled.
The irqflags handling in kvm_wait() which ends up doing:

	local_irq_save(flags);
	safe_halt();
	local_irq_restore(flags);

instead triggers it.  This patch fixes it by using
local_irq_disable()/enable() directly.

Cc: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Message-Id: <1615791328-2735-1-git-send-email-wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kernel/kvm.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5e78e01ca3b4..78bb0fae3982 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -836,28 +836,25 @@ static void kvm_kick_cpu(int cpu)
 
 static void kvm_wait(u8 *ptr, u8 val)
 {
-	unsigned long flags;
-
 	if (in_nmi())
 		return;
 
-	local_irq_save(flags);
-
-	if (READ_ONCE(*ptr) != val)
-		goto out;
-
 	/*
 	 * halt until it's our turn and kicked. Note that we do safe halt
 	 * for irq enabled case to avoid hang when lock info is overwritten
 	 * in irq spinlock slowpath and no spurious interrupt occur to save us.
 	 */
-	if (arch_irqs_disabled_flags(flags))
-		halt();
-	else
-		safe_halt();
+	if (irqs_disabled()) {
+		if (READ_ONCE(*ptr) == val)
+			halt();
+	} else {
+		local_irq_disable();
 
-out:
-	local_irq_restore(flags);
+		if (READ_ONCE(*ptr) == val)
+			safe_halt();
+
+		local_irq_enable();
+	}
 }
 
 #ifdef CONFIG_X86_32

From dcc32f4f183ab8479041b23a1525d48233df1d43 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 17 Mar 2021 09:55:15 -0700
Subject: [PATCH 1035/1820] ipv6: weaken the v4mapped source check

This reverts commit 6af1799aaf3f1bc8defedddfa00df3192445bbf3.

Commit 6af1799aaf3f ("ipv6: drop incoming packets having a v4mapped
source address") introduced an input check against v4mapped addresses.
Use of such addresses on the wire is indeed questionable and not
allowed on public Internet. As the commit pointed out

  https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02

lists potential issues.

Unfortunately there are applications which use v4mapped addresses,
and breaking them is a clear regression. For example v4mapped
addresses (or any semi-valid addresses, really) may be used
for uni-direction event streams or packet export.

Since the issue which sparked the addition of the check was with
TCP and request_socks in particular push the check down to TCPv6
and DCCP. This restores the ability to receive UDPv6 packets with
v4mapped address as the source.

Keep using the IPSTATS_MIB_INHDRERRORS statistic to minimize the
user-visible changes.

Fixes: 6af1799aaf3f ("ipv6: drop incoming packets having a v4mapped source address")
Reported-by: Sunyi Shao <sunyishao@fb.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv6.c      |  5 +++++
 net/ipv6/ip6_input.c | 10 ----------
 net/ipv6/tcp_ipv6.c  |  5 +++++
 net/mptcp/subflow.c  |  5 +++++
 4 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 1f73603913f5..2be5c69824f9 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -319,6 +319,11 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (!ipv6_unicast_destination(skb))
 		return 0;	/* discard, don't send a reset here */
 
+	if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
+		__IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
+		return 0;
+	}
+
 	if (dccp_bad_service_code(sk, service)) {
 		dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE;
 		goto drop;
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index e9d2a4a409aa..80256717868e 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -245,16 +245,6 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 	if (ipv6_addr_is_multicast(&hdr->saddr))
 		goto err;
 
-	/* While RFC4291 is not explicit about v4mapped addresses
-	 * in IPv6 headers, it seems clear linux dual-stack
-	 * model can not deal properly with these.
-	 * Security models could be fooled by ::ffff:127.0.0.1 for example.
-	 *
-	 * https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02
-	 */
-	if (ipv6_addr_v4mapped(&hdr->saddr))
-		goto err;
-
 	skb->transport_header = skb->network_header + sizeof(*hdr);
 	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index bd44ded7e50c..d0f007741e8e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1175,6 +1175,11 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (!ipv6_unicast_destination(skb))
 		goto drop;
 
+	if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
+		__IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
+		return 0;
+	}
+
 	return tcp_conn_request(&tcp6_request_sock_ops,
 				&tcp_request_sock_ipv6_ops, sk, skb);
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 3d47d670e665..d17d39ccdf34 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -477,6 +477,11 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (!ipv6_unicast_destination(skb))
 		goto drop;
 
+	if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
+		__IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
+		return 0;
+	}
+
 	return tcp_conn_request(&mptcp_subflow_request_sock_ops,
 				&subflow_request_sock_ipv6_ops, sk, skb);
 

From 804741ac7b9f2fdebe3740cb0579cb8d94d49e60 Mon Sep 17 00:00:00 2001
From: Mian Yousaf Kaukab <ykaukab@suse.de>
Date: Thu, 18 Mar 2021 09:50:26 +0100
Subject: [PATCH 1036/1820] netsec: restore phy power state after controller
 reset

Since commit 8e850f25b581 ("net: socionext: Stop PHY before resetting
netsec") netsec_netdev_init() power downs phy before resetting the
controller. However, the state is not restored once the reset is
complete. As a result it is not possible to bring up network on a
platform with Broadcom BCM5482 phy.

Fix the issue by restoring phy power state after controller reset is
complete.

Fixes: 8e850f25b581 ("net: socionext: Stop PHY before resetting netsec")
Cc: stable@vger.kernel.org
Signed-off-by: Mian Yousaf Kaukab <ykaukab@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 3c53051bdacf..200785e703c8 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -1715,14 +1715,17 @@ static int netsec_netdev_init(struct net_device *ndev)
 		goto err1;
 
 	/* set phy power down */
-	data = netsec_phy_read(priv->mii_bus, priv->phy_addr, MII_BMCR) |
-		BMCR_PDOWN;
-	netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, data);
+	data = netsec_phy_read(priv->mii_bus, priv->phy_addr, MII_BMCR);
+	netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR,
+			 data | BMCR_PDOWN);
 
 	ret = netsec_reset_hardware(priv, true);
 	if (ret)
 		goto err2;
 
+	/* Restore phy power state */
+	netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, data);
+
 	spin_lock_init(&priv->desc_ring[NETSEC_RING_TX].lock);
 	spin_lock_init(&priv->desc_ring[NETSEC_RING_RX].lock);
 

From c1d6abdac46ca8127274bea195d804e3f2cec7ee Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@fb.com>
Date: Tue, 16 Mar 2021 12:43:00 -0700
Subject: [PATCH 1037/1820] btrfs: fix check_data_csum() error message for
 direct I/O

Commit 1dae796aabf6 ("btrfs: inode: sink parameter start and len to
check_data_csum()") replaced the start parameter to check_data_csum()
with page_offset(), but page_offset() is not meaningful for direct I/O
pages. Bring back the start parameter.

Fixes: 265d4ac03fdf ("btrfs: sink parameter start and len to check_data_csum")
CC: stable@vger.kernel.org # 5.11+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4120fd96a134..a7be4c9ec835 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3099,11 +3099,13 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
  * @bio_offset:	offset to the beginning of the bio (in bytes)
  * @page:	page where is the data to be verified
  * @pgoff:	offset inside the page
+ * @start:	logical offset in the file
  *
  * The length of such check is always one sector size.
  */
 static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
-			   u32 bio_offset, struct page *page, u32 pgoff)
+			   u32 bio_offset, struct page *page, u32 pgoff,
+			   u64 start)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
@@ -3130,8 +3132,8 @@ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
 	kunmap_atomic(kaddr);
 	return 0;
 zeroit:
-	btrfs_print_data_csum_error(BTRFS_I(inode), page_offset(page) + pgoff,
-				    csum, csum_expected, io_bio->mirror_num);
+	btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
+				    io_bio->mirror_num);
 	if (io_bio->device)
 		btrfs_dev_stat_inc_and_print(io_bio->device,
 					     BTRFS_DEV_STAT_CORRUPTION_ERRS);
@@ -3184,7 +3186,8 @@ int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset,
 	     pg_off += sectorsize, bio_offset += sectorsize) {
 		int ret;
 
-		ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off);
+		ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off,
+				      page_offset(page) + pg_off);
 		if (ret < 0)
 			return -EIO;
 	}
@@ -7907,7 +7910,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode,
 			ASSERT(pgoff < PAGE_SIZE);
 			if (uptodate &&
 			    (!csum || !check_data_csum(inode, io_bio,
-					bio_offset, bvec.bv_page, pgoff))) {
+						       bio_offset, bvec.bv_page,
+						       pgoff, start))) {
 				clean_io_failure(fs_info, failure_tree, io_tree,
 						 start, bvec.bv_page,
 						 btrfs_ino(BTRFS_I(inode)),

From f41b2d67d767f34bcd29fab83efaddb7f1e54579 Mon Sep 17 00:00:00 2001
From: Subbaraya Sundeep <sbhatta@marvell.com>
Date: Thu, 18 Mar 2021 19:45:42 +0530
Subject: [PATCH 1038/1820] octeontx2-pf: Do not modify number of rules

In the ETHTOOL_GRXCLSRLALL ioctl ethtool uses
below structure to read number of rules from the driver.

    struct ethtool_rxnfc {
            __u32                           cmd;
            __u32                           flow_type;
            __u64                           data;
            struct ethtool_rx_flow_spec     fs;
            union {
                    __u32                   rule_cnt;
                    __u32                   rss_context;
            };
            __u32                           rule_locs[0];
    };

Driver must not modify rule_cnt member. But currently driver
modifies it by modifying rss_context. Hence fix it by using a
local variable.

Fixes: 81a4362016e7 ("octeontx2-pf: Add RSS multi group support")
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 0dbbf38e0597..dc1778420978 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -257,17 +257,19 @@ int otx2_get_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc,
 int otx2_get_all_flows(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc,
 		       u32 *rule_locs)
 {
+	u32 rule_cnt = nfc->rule_cnt;
 	u32 location = 0;
 	int idx = 0;
 	int err = 0;
 
 	nfc->data = pfvf->flow_cfg->ntuple_max_flows;
-	while ((!err || err == -ENOENT) && idx < nfc->rule_cnt) {
+	while ((!err || err == -ENOENT) && idx < rule_cnt) {
 		err = otx2_get_flow(pfvf, nfc, location);
 		if (!err)
 			rule_locs[idx++] = location;
 		location++;
 	}
+	nfc->rule_cnt = rule_cnt;
 
 	return err;
 }

From f7884097141b615b6ce89c16f456a53902b4eec3 Mon Sep 17 00:00:00 2001
From: Rakesh Babu <rsaladi2@marvell.com>
Date: Thu, 18 Mar 2021 19:45:43 +0530
Subject: [PATCH 1039/1820] octeontx2-af: Formatting debugfs entry rsrc_alloc.

With the existing rsrc_alloc's format, there is misalignment for the
pcifunc entries whose VF's index is a double digit. This patch fixes
this.

    pcifunc     NPA         NIX0        NIX1        SSO GROUP   SSOWS
    TIM         CPT0        CPT1        REE0        REE1
    PF0:VF0     8           5
    PF0:VF1     9                       3
    PF0:VF10    18          10
    PF0:VF11    19                      8
    PF0:VF12    20          11
    PF0:VF13    21                      9
    PF0:VF14    22          12
    PF0:VF15    23                      10
    PF1         0           0

Fixes: 23205e6d06d4 ("octeontx2-af: Dump current resource provisioning status")
Signed-off-by: Rakesh Babu <rsaladi2@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../marvell/octeontx2/af/rvu_debugfs.c        | 46 ++++++++++++-------
 1 file changed, 29 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index aa2ca8780b9c..dc946953af06 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -234,12 +234,14 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
 					  char __user *buffer,
 					  size_t count, loff_t *ppos)
 {
-	int index, off = 0, flag = 0, go_back = 0, off_prev;
+	int index, off = 0, flag = 0, go_back = 0, len = 0;
 	struct rvu *rvu = filp->private_data;
 	int lf, pf, vf, pcifunc;
 	struct rvu_block block;
 	int bytes_not_copied;
+	int lf_str_size = 12;
 	int buf_size = 2048;
+	char *lfs;
 	char *buf;
 
 	/* don't allow partial reads */
@@ -249,12 +251,18 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
 	buf = kzalloc(buf_size, GFP_KERNEL);
 	if (!buf)
 		return -ENOSPC;
-	off +=	scnprintf(&buf[off], buf_size - 1 - off, "\npcifunc\t\t");
+
+	lfs = kzalloc(lf_str_size, GFP_KERNEL);
+	if (!lfs)
+		return -ENOMEM;
+	off +=	scnprintf(&buf[off], buf_size - 1 - off, "%-*s", lf_str_size,
+			  "pcifunc");
 	for (index = 0; index < BLK_COUNT; index++)
-		if (strlen(rvu->hw->block[index].name))
-			off +=	scnprintf(&buf[off], buf_size - 1 - off,
-					  "%*s\t", (index - 1) * 2,
-					  rvu->hw->block[index].name);
+		if (strlen(rvu->hw->block[index].name)) {
+			off += scnprintf(&buf[off], buf_size - 1 - off,
+					 "%-*s", lf_str_size,
+					 rvu->hw->block[index].name);
+		}
 	off += scnprintf(&buf[off], buf_size - 1 - off, "\n");
 	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
 		for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
@@ -263,14 +271,15 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
 				continue;
 
 			if (vf) {
+				sprintf(lfs, "PF%d:VF%d", pf, vf - 1);
 				go_back = scnprintf(&buf[off],
 						    buf_size - 1 - off,
-						    "PF%d:VF%d\t\t", pf,
-						    vf - 1);
+						    "%-*s", lf_str_size, lfs);
 			} else {
+				sprintf(lfs, "PF%d", pf);
 				go_back = scnprintf(&buf[off],
 						    buf_size - 1 - off,
-						    "PF%d\t\t", pf);
+						    "%-*s", lf_str_size, lfs);
 			}
 
 			off += go_back;
@@ -278,20 +287,22 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
 				block = rvu->hw->block[index];
 				if (!strlen(block.name))
 					continue;
-				off_prev = off;
+				len = 0;
+				lfs[len] = '\0';
 				for (lf = 0; lf < block.lf.max; lf++) {
 					if (block.fn_map[lf] != pcifunc)
 						continue;
 					flag = 1;
-					off += scnprintf(&buf[off], buf_size - 1
-							- off, "%3d,", lf);
+					len += sprintf(&lfs[len], "%d,", lf);
 				}
-				if (flag && off_prev != off)
-					off--;
-				else
-					go_back++;
+
+				if (flag)
+					len--;
+				lfs[len] = '\0';
 				off += scnprintf(&buf[off], buf_size - 1 - off,
-						"\t");
+						 "%-*s", lf_str_size, lfs);
+				if (!strlen(lfs))
+					go_back += lf_str_size;
 			}
 			if (!flag)
 				off -= go_back;
@@ -303,6 +314,7 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
 	}
 
 	bytes_not_copied = copy_to_user(buffer, buf, off);
+	kfree(lfs);
 	kfree(buf);
 
 	if (bytes_not_copied)

From ce86c2a531e2f2995ee55ea527c1f39ba1d95f73 Mon Sep 17 00:00:00 2001
From: Subbaraya Sundeep <sbhatta@marvell.com>
Date: Thu, 18 Mar 2021 19:45:44 +0530
Subject: [PATCH 1040/1820] octeontx2-af: Remove TOS field from MKEX TX

The MKEX profile describes what packet fields need to be extracted from
the input packet and how to place those packet fields in the output key
for MCAM matching.  The MKEX profile can be in a way where higher layer
packet fields can overwrite lower layer packet fields in output MCAM
Key.
Hence MKEX profile is always ensured that there are no overlaps between
any of the layers. But the commit 42006910b5ea
("octeontx2-af: cleanup KPU config data") introduced TX TOS field which
overlaps with DMAC in MCAM key.
This led to AF driver returning error when TX rule is installed with
DMAC as match criteria since DMAC gets overwritten and cannot be
supported. This patch fixes the issue by removing TOS field from MKEX TX
profile.

Fixes: 42006910b5ea ("octeontx2-af: cleanup KPU config data")
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
index b192692b4fc4..5c372d2c24a1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
@@ -13499,8 +13499,6 @@ static struct npc_mcam_kex npc_mkex_default = {
 			[NPC_LT_LC_IP] = {
 				/* SIP+DIP: 8 bytes, KW2[63:0] */
 				KEX_LD_CFG(0x07, 0xc, 0x1, 0x0, 0x10),
-				/* TOS: 1 byte, KW1[63:56] */
-				KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0xf),
 			},
 			/* Layer C: IPv6 */
 			[NPC_LT_LC_IP6] = {

From 297887872973555cb9fb83fdd5a2748d6cd8fc1d Mon Sep 17 00:00:00 2001
From: Subbaraya Sundeep <sbhatta@marvell.com>
Date: Thu, 18 Mar 2021 19:45:45 +0530
Subject: [PATCH 1041/1820] octeontx2-af: Return correct CGX RX fifo size

CGX receive buffer size is a constant value and
cannot be read from CGX0 block always since
CGX0 may not enabled everytime. Hence return CGX
receive buffer size from first enabled CGX block
instead of CGX0.

Fixes: 6e54e1c5399a ("octeontx2-af: cn10K: MTU configuration")
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/octeontx2/af/rvu.h    |  1 +
 .../ethernet/marvell/octeontx2/af/rvu_cgx.c    | 18 ++++++++++++++++--
 .../marvell/octeontx2/af/rvu_debugfs.c         |  9 +++++----
 3 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index fa6e46e36ae4..76f399229ddb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -678,6 +678,7 @@ void npc_read_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 			 u8 *intf, u8 *ena);
 bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature);
 u32  rvu_cgx_get_fifolen(struct rvu *rvu);
+void *rvu_first_cgx_pdata(struct rvu *rvu);
 
 /* CPT APIs */
 int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index e668e482383a..6e2bf4fcd29c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -89,6 +89,21 @@ void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu)
 	return rvu->cgx_idmap[cgx_id];
 }
 
+/* Return first enabled CGX instance if none are enabled then return NULL */
+void *rvu_first_cgx_pdata(struct rvu *rvu)
+{
+	int first_enabled_cgx = 0;
+	void *cgxd = NULL;
+
+	for (; first_enabled_cgx < rvu->cgx_cnt_max; first_enabled_cgx++) {
+		cgxd = rvu_cgx_pdata(first_enabled_cgx, rvu);
+		if (cgxd)
+			break;
+	}
+
+	return cgxd;
+}
+
 /* Based on P2X connectivity find mapped NIX block for a PF */
 static void rvu_map_cgx_nix_block(struct rvu *rvu, int pf,
 				  int cgx_id, int lmac_id)
@@ -711,10 +726,9 @@ int rvu_mbox_handler_cgx_features_get(struct rvu *rvu,
 u32 rvu_cgx_get_fifolen(struct rvu *rvu)
 {
 	struct mac_ops *mac_ops;
-	int rvu_def_cgx_id = 0;
 	u32 fifo_len;
 
-	mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu));
+	mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu));
 	fifo_len = mac_ops ? mac_ops->fifo_len : 0;
 
 	return fifo_len;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index dc946953af06..b4c53b19f535 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -331,7 +331,6 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused)
 	struct rvu *rvu = filp->private;
 	struct pci_dev *pdev = NULL;
 	struct mac_ops *mac_ops;
-	int rvu_def_cgx_id = 0;
 	char cgx[10], lmac[10];
 	struct rvu_pfvf *pfvf;
 	int pf, domain, blkid;
@@ -339,7 +338,10 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused)
 	u16 pcifunc;
 
 	domain = 2;
-	mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu));
+	mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu));
+	/* There can be no CGX devices at all */
+	if (!mac_ops)
+		return 0;
 	seq_printf(filp, "PCI dev\t\tRVU PF Func\tNIX block\t%s\tLMAC\n",
 		   mac_ops->name);
 	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
@@ -1830,7 +1832,6 @@ static void rvu_dbg_cgx_init(struct rvu *rvu)
 {
 	struct mac_ops *mac_ops;
 	unsigned long lmac_bmap;
-	int rvu_def_cgx_id = 0;
 	int i, lmac_id;
 	char dname[20];
 	void *cgx;
@@ -1838,7 +1839,7 @@ static void rvu_dbg_cgx_init(struct rvu *rvu)
 	if (!cgx_get_cgxcnt_max())
 		return;
 
-	mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu));
+	mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu));
 	if (!mac_ops)
 		return;
 

From ae2619dd4fccdad9876aa5f900bd85484179c50f Mon Sep 17 00:00:00 2001
From: Geetha sowjanya <gakula@marvell.com>
Date: Thu, 18 Mar 2021 19:45:46 +0530
Subject: [PATCH 1042/1820] octeontx2-af: Fix irq free in rvu teardown

Current devlink code try to free already freed irqs as the
irq_allocate flag is not cleared after free leading to kernel
crash while removing rvu driver. The patch fixes the irq free
sequence and clears the irq_allocate flag on free.

Fixes: 7304ac4567bc ("octeontx2-af: Add mailbox IRQ and msg handlers")
Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index d9a1a71c7ccc..ab24a5e8ee8a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -2462,8 +2462,10 @@ static void rvu_unregister_interrupts(struct rvu *rvu)
 		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
 
 	for (irq = 0; irq < rvu->num_vec; irq++) {
-		if (rvu->irq_allocated[irq])
+		if (rvu->irq_allocated[irq]) {
 			free_irq(pci_irq_vector(rvu->pdev, irq), rvu);
+			rvu->irq_allocated[irq] = false;
+		}
 	}
 
 	pci_free_irq_vectors(rvu->pdev);
@@ -2975,8 +2977,8 @@ static void rvu_remove(struct pci_dev *pdev)
 	struct rvu *rvu = pci_get_drvdata(pdev);
 
 	rvu_dbg_exit(rvu);
-	rvu_unregister_interrupts(rvu);
 	rvu_unregister_dl(rvu);
+	rvu_unregister_interrupts(rvu);
 	rvu_flr_wq_destroy(rvu);
 	rvu_cgx_exit(rvu);
 	rvu_fwdata_exit(rvu);

From f12098ce9b43e1a6fcaa524acbd90f9118a74c0a Mon Sep 17 00:00:00 2001
From: Geetha sowjanya <gakula@marvell.com>
Date: Thu, 18 Mar 2021 19:45:47 +0530
Subject: [PATCH 1043/1820] octeontx2-pf: Clear RSS enable flag on interace
 down

RSS configuration can not be get/set when interface is in down state
as they required mbox communication. RSS enable flag status
is used for set/get configuration. Current code do not clear the
RSS enable flag on interface down which lead to mbox error while
trying to set/get RSS configuration.

Fixes: 85069e95e531 ("octeontx2-pf: Receive side scaling support")
Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 53ab1814d74b..2fd3d235d292 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1672,6 +1672,7 @@ int otx2_stop(struct net_device *netdev)
 	struct otx2_nic *pf = netdev_priv(netdev);
 	struct otx2_cq_poll *cq_poll = NULL;
 	struct otx2_qset *qset = &pf->qset;
+	struct otx2_rss_info *rss;
 	int qidx, vec, wrk;
 
 	netif_carrier_off(netdev);
@@ -1684,6 +1685,10 @@ int otx2_stop(struct net_device *netdev)
 	/* First stop packet Rx/Tx */
 	otx2_rxtx_enable(pf, false);
 
+	/* Clear RSS enable flag */
+	rss = &pf->hw.rss_info;
+	rss->enable = false;
+
 	/* Cleanup Queue IRQ */
 	vec = pci_irq_vector(pf->pdev,
 			     pf->hw.nix_msixoff + NIX_LF_QINT_VEC_START);

From 64451b98306bf1334a62bcd020ec92bdb4cb68db Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Thu, 18 Mar 2021 19:45:48 +0530
Subject: [PATCH 1044/1820] octeontx2-af: fix infinite loop in unmapping NPC
 counter

unmapping npc counter works in a way by traversing all mcam
entries to find which mcam rule is associated with counter.
But loop cursor variable 'entry' is not incremented before
checking next mcam entry which resulting in infinite loop.

This in turn hogs the kworker thread forever and no other
mbox message is processed by AF driver after that.
Fix this by updating entry value before checking next
mcam entry.

Fixes: a958dd59f9ce ("octeontx2-af: Map or unmap NPC MCAM entry and counter")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 04bb0803a5c5..0bd49c7080a6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -2490,10 +2490,10 @@ int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu,
 		index = find_next_bit(mcam->bmap, mcam->bmap_entries, entry);
 		if (index >= mcam->bmap_entries)
 			break;
+		entry = index + 1;
 		if (mcam->entry2cntr_map[index] != req->cntr)
 			continue;
 
-		entry = index + 1;
 		npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
 					      index, req->cntr);
 	}

From 8c16cb0304cd582e83584b81813a3404e9c7db47 Mon Sep 17 00:00:00 2001
From: Subbaraya Sundeep <sbhatta@marvell.com>
Date: Thu, 18 Mar 2021 19:45:49 +0530
Subject: [PATCH 1045/1820] octeontx2-af: Fix uninitialized variable warning

Initialize l4_key_offset variable to fix uninitialized
variable compiler warning.

Fixes: b9b7421a01d8 ("octeontx2-af: Support ESP/AH RSS hashing")
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index d3000194e2d3..3d068b7d46bd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -2629,7 +2629,7 @@ static int set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
 	struct nix_rx_flowkey_alg *field;
 	struct nix_rx_flowkey_alg tmp;
 	u32 key_type, valid_key;
-	int l4_key_offset;
+	int l4_key_offset = 0;
 
 	if (!alg)
 		return -EINVAL;

From 600cc3c9c62defd920da07bc585eb739247bb732 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Thu, 18 Mar 2021 17:25:08 +0000
Subject: [PATCH 1046/1820] net: marvell: Remove reference to CONFIG_MV64X60

Commit 92c8c16f3457 ("powerpc/embedded6xx: Remove C2K board support")
removed last selector of CONFIG_MV64X60.

As it is not a user selectable config item, all references to it
are stale. Remove them.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/Kconfig       | 4 ++--
 drivers/net/ethernet/marvell/mv643xx_eth.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index 7fe15a3286f4..fe0989c0fc25 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -6,7 +6,7 @@
 config NET_VENDOR_MARVELL
 	bool "Marvell devices"
 	default y
-	depends on PCI || CPU_PXA168 || MV64X60 || PPC32 || PLAT_ORION || INET || COMPILE_TEST
+	depends on PCI || CPU_PXA168 || PPC32 || PLAT_ORION || INET || COMPILE_TEST
 	help
 	  If you have a network (Ethernet) card belonging to this class, say Y.
 
@@ -19,7 +19,7 @@ if NET_VENDOR_MARVELL
 
 config MV643XX_ETH
 	tristate "Marvell Discovery (643XX) and Orion ethernet support"
-	depends on MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST
+	depends on PPC32 || PLAT_ORION || COMPILE_TEST
 	depends on INET
 	select PHYLIB
 	select MVMDIO
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 90e6111ce534..3bfb659b5c99 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -2684,7 +2684,7 @@ static const struct of_device_id mv643xx_eth_shared_ids[] = {
 MODULE_DEVICE_TABLE(of, mv643xx_eth_shared_ids);
 #endif
 
-#if defined(CONFIG_OF_IRQ) && !defined(CONFIG_MV64X60)
+#ifdef CONFIG_OF_IRQ
 #define mv643xx_eth_property(_np, _name, _v)				\
 	do {								\
 		u32 tmp;						\

From 6c015a2256801597fadcbc11d287774c9c512fa5 Mon Sep 17 00:00:00 2001
From: Jiri Bohac <jbohac@suse.cz>
Date: Thu, 18 Mar 2021 04:42:53 +0100
Subject: [PATCH 1047/1820] net: check all name nodes in __dev_alloc_name

__dev_alloc_name(), when supplied with a name containing '%d',
will search for the first available device number to generate a
unique device name.

Since commit ff92741270bf8b6e78aa885f166b68c7a67ab13a ("net:
introduce name_node struct to be used in hashlist") network
devices may have alternate names.  __dev_alloc_name() does take
these alternate names into account, possibly generating a name
that is already taken and failing with -ENFILE as a result.

This demonstrates the bug:

    # rmmod dummy 2>/dev/null
    # ip link property add dev lo altname dummy0
    # modprobe dummy numdummies=1
    modprobe: ERROR: could not insert 'dummy': Too many open files in system

Instead of creating a device named dummy1, modprobe fails.

Fix this by checking all the names in the d->name_node list, not just d->name.

Signed-off-by: Jiri Bohac <jbohac@suse.cz>
Fixes: ff92741270bf ("net: introduce name_node struct to be used in hashlist")
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index bb568f7cb81b..0f72ff5d34ba 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1184,6 +1184,18 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
 			return -ENOMEM;
 
 		for_each_netdev(net, d) {
+			struct netdev_name_node *name_node;
+			list_for_each_entry(name_node, &d->name_node->list, list) {
+				if (!sscanf(name_node->name, name, &i))
+					continue;
+				if (i < 0 || i >= max_netdevices)
+					continue;
+
+				/*  avoid cases where sscanf is not exact inverse of printf */
+				snprintf(buf, IFNAMSIZ, name, i);
+				if (!strncmp(buf, name_node->name, IFNAMSIZ))
+					set_bit(i, inuse);
+			}
 			if (!sscanf(d->name, name, &i))
 				continue;
 			if (i < 0 || i >= max_netdevices)

From 491aef7caeb345ccfd658a7fc8a42944a7f82494 Mon Sep 17 00:00:00 2001
From: Georgi Djakov <georgi.djakov@linaro.org>
Date: Thu, 18 Mar 2021 18:34:15 +0200
Subject: [PATCH 1048/1820] interconnect: Fix kerneldoc warning

Fix the following warning:
drivers/interconnect/bulk.c:63: warning: expecting prototype for
icc_bulk_set(). Prototype was for icc_bulk_set_bw() instead

Link: https://lore.kernel.org/r/20210318163415.30941-1-georgi.djakov@linaro.org
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/bulk.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/interconnect/bulk.c b/drivers/interconnect/bulk.c
index 73e2c8d0a412..448cc536aa79 100644
--- a/drivers/interconnect/bulk.c
+++ b/drivers/interconnect/bulk.c
@@ -53,7 +53,7 @@ void icc_bulk_put(int num_paths, struct icc_bulk_data *paths)
 EXPORT_SYMBOL_GPL(icc_bulk_put);
 
 /**
- * icc_bulk_set() - set bandwidth to a set of paths
+ * icc_bulk_set_bw() - set bandwidth to a set of paths
  * @num_paths: the number of icc_bulk_data
  * @paths: the icc_bulk_data table containing the paths and bandwidth
  *

From a21ddeb227b115bc7945d5af66c0d167359c8c31 Mon Sep 17 00:00:00 2001
From: Patrice Chotard <patrice.chotard@foss.st.com>
Date: Tue, 16 Feb 2021 08:49:27 +0100
Subject: [PATCH 1049/1820] MAINTAINERS: Update some st.com email addresses to
 foss.st.com

Update some st.com to foss.st.com addresses related to STMicroelectronics
drivers. All these people will now use this new email address for upstream
activities.

Signed-off-by: Patrice Chotard <patrice.chotard@foss.st.com>
Link: https://lore.kernel.org/r/20210216074929.29033-2-patrice.chotard@foss.st.com'
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 MAINTAINERS | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d92f85ca831d..0dc4550a5376 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2489,7 +2489,7 @@ N:	sc27xx
 N:	sc2731
 
 ARM/STI ARCHITECTURE
-M:	Patrice Chotard <patrice.chotard@st.com>
+M:	Patrice Chotard <patrice.chotard@foss.st.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 W:	http://www.stlinux.com
@@ -2522,7 +2522,7 @@ F:	include/linux/remoteproc/st_slim_rproc.h
 
 ARM/STM32 ARCHITECTURE
 M:	Maxime Coquelin <mcoquelin.stm32@gmail.com>
-M:	Alexandre Torgue <alexandre.torgue@st.com>
+M:	Alexandre Torgue <alexandre.torgue@foss.st.com>
 L:	linux-stm32@st-md-mailman.stormreply.com (moderated for non-subscribers)
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -3115,7 +3115,7 @@ C:	irc://irc.oftc.net/bcache
 F:	drivers/md/bcache/
 
 BDISP ST MEDIA DRIVER
-M:	Fabien Dessenne <fabien.dessenne@st.com>
+M:	Fabien Dessenne <fabien.dessenne@foss.st.com>
 L:	linux-media@vger.kernel.org
 S:	Supported
 W:	https://linuxtv.org
@@ -5080,7 +5080,7 @@ S:	Maintained
 F:	drivers/platform/x86/dell/dell-wmi.c
 
 DELTA ST MEDIA DRIVER
-M:	Hugues Fruchet <hugues.fruchet@st.com>
+M:	Hugues Fruchet <hugues.fruchet@foss.st.com>
 L:	linux-media@vger.kernel.org
 S:	Supported
 W:	https://linuxtv.org
@@ -6014,8 +6014,8 @@ F:	Documentation/devicetree/bindings/display/st,stih4xx.txt
 F:	drivers/gpu/drm/sti
 
 DRM DRIVERS FOR STM
-M:	Yannick Fertre <yannick.fertre@st.com>
-M:	Philippe Cornu <philippe.cornu@st.com>
+M:	Yannick Fertre <yannick.fertre@foss.st.com>
+M:	Philippe Cornu <philippe.cornu@foss.st.com>
 M:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
 M:	Vincent Abriou <vincent.abriou@st.com>
 L:	dri-devel@lists.freedesktop.org
@@ -8231,7 +8231,7 @@ F:	include/linux/hugetlb.h
 F:	mm/hugetlb.c
 
 HVA ST MEDIA DRIVER
-M:	Jean-Christophe Trotin <jean-christophe.trotin@st.com>
+M:	Jean-Christophe Trotin <jean-christophe.trotin@foss.st.com>
 L:	linux-media@vger.kernel.org
 S:	Supported
 W:	https://linuxtv.org
@@ -11166,7 +11166,7 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/dvb-frontends/stv6111*
 
 MEDIA DRIVERS FOR STM32 - DCMI
-M:	Hugues Fruchet <hugues.fruchet@st.com>
+M:	Hugues Fruchet <hugues.fruchet@foss.st.com>
 L:	linux-media@vger.kernel.org
 S:	Supported
 T:	git git://linuxtv.org/media_tree.git
@@ -16941,7 +16941,7 @@ F:	Documentation/devicetree/bindings/media/i2c/st,st-mipid02.txt
 F:	drivers/media/i2c/st-mipid02.c
 
 ST STM32 I2C/SMBUS DRIVER
-M:	Pierre-Yves MORDRET <pierre-yves.mordret@st.com>
+M:	Pierre-Yves MORDRET <pierre-yves.mordret@foss.st.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-stm32*
@@ -17066,7 +17066,7 @@ F:	kernel/jump_label.c
 F:	kernel/static_call.c
 
 STI AUDIO (ASoC) DRIVERS
-M:	Arnaud Pouliquen <arnaud.pouliquen@st.com>
+M:	Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Maintained
 F:	Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
@@ -17086,15 +17086,15 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/usb/stk1160/
 
 STM32 AUDIO (ASoC) DRIVERS
-M:	Olivier Moysan <olivier.moysan@st.com>
-M:	Arnaud Pouliquen <arnaud.pouliquen@st.com>
+M:	Olivier Moysan <olivier.moysan@foss.st.com>
+M:	Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Maintained
 F:	Documentation/devicetree/bindings/iio/adc/st,stm32-*.yaml
 F:	sound/soc/stm/
 
 STM32 TIMER/LPTIMER DRIVERS
-M:	Fabrice Gasnier <fabrice.gasnier@st.com>
+M:	Fabrice Gasnier <fabrice.gasnier@foss.st.com>
 S:	Maintained
 F:	Documentation/ABI/testing/*timer-stm32
 F:	Documentation/devicetree/bindings/*/*stm32-*timer*
@@ -17104,7 +17104,7 @@ F:	include/linux/*/stm32-*tim*
 
 STMMAC ETHERNET DRIVER
 M:	Giuseppe Cavallaro <peppe.cavallaro@st.com>
-M:	Alexandre Torgue <alexandre.torgue@st.com>
+M:	Alexandre Torgue <alexandre.torgue@foss.st.com>
 M:	Jose Abreu <joabreu@synopsys.com>
 L:	netdev@vger.kernel.org
 S:	Supported

From 7a2e796173fbb17635c5ce822ede0ace8843209d Mon Sep 17 00:00:00 2001
From: Patrice Chotard <patrice.chotard@foss.st.com>
Date: Tue, 16 Feb 2021 08:49:28 +0100
Subject: [PATCH 1050/1820] MAINTAINERS: Remove Vincent Abriou for STM/STI DRM
 drivers.

Remove Vincent Abriou's email as he has no more review activities on
STM/STI DRM drivers.

Signed-off-by: Patrice Chotard <patrice.chotard@foss.st.com>
Cc: Vincent Abriou <vincent.abriou@st.com>
Link: https://lore.kernel.org/r/20210216074929.29033-3-patrice.chotard@foss.st.com'
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 MAINTAINERS | 2 --
 1 file changed, 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0dc4550a5376..1bfee5286b46 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6006,7 +6006,6 @@ F:	drivers/gpu/drm/rockchip/
 
 DRM DRIVERS FOR STI
 M:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
-M:	Vincent Abriou <vincent.abriou@st.com>
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
 T:	git git://anongit.freedesktop.org/drm/drm-misc
@@ -6017,7 +6016,6 @@ DRM DRIVERS FOR STM
 M:	Yannick Fertre <yannick.fertre@foss.st.com>
 M:	Philippe Cornu <philippe.cornu@foss.st.com>
 M:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
-M:	Vincent Abriou <vincent.abriou@st.com>
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
 T:	git git://anongit.freedesktop.org/drm/drm-misc

From 303a91f15f3499e47b256dc8647e3e0cfa0ff7b5 Mon Sep 17 00:00:00 2001
From: Patrice Chotard <patrice.chotard@foss.st.com>
Date: Tue, 16 Feb 2021 08:49:29 +0100
Subject: [PATCH 1051/1820] MAINTAINERS: Add Alain Volmat as STM32 I2C/SMBUS
 maintainer

Add Alain Volmat as STM32 I2C/SMBUS driver co-maintainer.

Signed-off-by: Patrice Chotard <patrice.chotard@foss.st.com>
Cc: alain.volmat@foss.st.com
Link: https://lore.kernel.org/r/20210216074929.29033-4-patrice.chotard@foss.st.com'
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 1bfee5286b46..75a329ef7154 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16940,6 +16940,7 @@ F:	drivers/media/i2c/st-mipid02.c
 
 ST STM32 I2C/SMBUS DRIVER
 M:	Pierre-Yves MORDRET <pierre-yves.mordret@foss.st.com>
+M:	Alain Volmat <alain.volmat@foss.st.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-stm32*

From e94c55b8e0a0bbe9a026250cf31e2fa45957d776 Mon Sep 17 00:00:00 2001
From: Tobias Klausmann <tobias.klausmann@freenet.de>
Date: Sat, 13 Mar 2021 23:21:59 +0100
Subject: [PATCH 1052/1820] nouveau: Skip unvailable ttm page entries

Starting with commit f295c8cfec833c2707ff1512da10d65386dde7af
("drm/nouveau: fix dma syncing warning with debugging on.")
the following oops occures:

   BUG: kernel NULL pointer dereference, address: 0000000000000000
   #PF: supervisor read access in kernel mode
   #PF: error_code(0x0000) - not-present page
   PGD 0 P4D 0
   Oops: 0000 [#1] PREEMPT SMP PTI
   CPU: 6 PID: 1013 Comm: Xorg.bin Tainted: G E     5.11.0-desktop-rc0+ #2
   Hardware name: Acer Aspire VN7-593G/Pluto_KLS, BIOS V1.11 08/01/2018
   RIP: 0010:nouveau_bo_sync_for_device+0x40/0xb0 [nouveau]
   Call Trace:
    nouveau_bo_validate+0x5d/0x80 [nouveau]
    nouveau_gem_ioctl_pushbuf+0x662/0x1120 [nouveau]
    ? nouveau_gem_ioctl_new+0xf0/0xf0 [nouveau]
    drm_ioctl_kernel+0xa6/0xf0 [drm]
    drm_ioctl+0x1f4/0x3a0 [drm]
    ? nouveau_gem_ioctl_new+0xf0/0xf0 [nouveau]
    nouveau_drm_ioctl+0x50/0xa0 [nouveau]
    __x64_sys_ioctl+0x7e/0xb0
    do_syscall_64+0x33/0x80
    entry_SYSCALL_64_after_hwframe+0x44/0xae
   ---[ end trace ccfb1e7f4064374f ]---
   RIP: 0010:nouveau_bo_sync_for_device+0x40/0xb0 [nouveau]

The underlying problem is not introduced by the commit, yet it uncovered the
underlying issue. The cited commit relies on valid pages. This is not given for
due to some bugs. For now, just warn and work around the issue by just ignoring
the bad ttm objects.
Below is some debug info gathered while debugging this issue:

nouveau 0000:01:00.0: DRM: ttm_dma->num_pages: 2048
nouveau 0000:01:00.0: DRM: ttm_dma->pages is NULL
nouveau 0000:01:00.0: DRM: ttm_dma: 00000000e96058e7
nouveau 0000:01:00.0: DRM: ttm_dma->page_flags:
nouveau 0000:01:00.0: DRM: ttm_dma:   Populated: 1
nouveau 0000:01:00.0: DRM: ttm_dma:   No Retry: 0
nouveau 0000:01:00.0: DRM: ttm_dma:   SG: 256
nouveau 0000:01:00.0: DRM: ttm_dma:   Zero Alloc: 0
nouveau 0000:01:00.0: DRM: ttm_dma:   Swapped: 0

Signed-off-by: Tobias Klausmann <tobias.klausmann@freenet.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210313222159.3346-1-tobias.klausmann@freenet.de
---
 drivers/gpu/drm/nouveau/nouveau_bo.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index fabb314a0b2f..f2720a006199 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -551,6 +551,10 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo)
 
 	if (!ttm_dma)
 		return;
+	if (!ttm_dma->pages) {
+		NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma);
+		return;
+	}
 
 	/* Don't waste time looping if the object is coherent */
 	if (nvbo->force_coherent)
@@ -583,6 +587,10 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo)
 
 	if (!ttm_dma)
 		return;
+	if (!ttm_dma->pages) {
+		NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma);
+		return;
+	}
 
 	/* Don't waste time looping if the object is coherent */
 	if (nvbo->force_coherent)

From c79a707072fe3fea0e3c92edee6ca85c1e53c29f Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 18 Mar 2021 16:57:49 +0100
Subject: [PATCH 1053/1820] net: cdc-phonet: fix data-interface release on
 probe failure

Set the disconnected flag before releasing the data interface in case
netdev registration fails to avoid having the disconnect callback try to
deregister the never registered netdev (and trigger a WARN_ON()).

Fixes: 87cf65601e17 ("USB host CDC Phonet network interface driver")
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc-phonet.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c
index 02e6bbb17b15..8d1f69dad603 100644
--- a/drivers/net/usb/cdc-phonet.c
+++ b/drivers/net/usb/cdc-phonet.c
@@ -387,6 +387,8 @@ static int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *i
 
 	err = register_netdev(dev);
 	if (err) {
+		/* Set disconnected flag so that disconnect() returns early. */
+		pnd->disconnected = 1;
 		usb_driver_release_interface(&usbpn_driver, data_intf);
 		goto out;
 	}

From 519dad3bcd809dc1523bf80ab0310ddb3bf00ade Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Thu, 18 Mar 2021 22:53:01 +0100
Subject: [PATCH 1054/1820] selinux: don't log MAC_POLICY_LOAD record on failed
 policy load

If sel_make_policy_nodes() fails, we should jump to 'out', not 'out1',
as the latter would incorrectly log an MAC_POLICY_LOAD audit record,
even though the policy hasn't actually been reloaded. The 'out1' jump
label now becomes unused and can be removed.

Fixes: 02a52c5c8c3b ("selinux: move policy commit after updating selinuxfs")
Cc: stable@vger.kernel.org
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/selinuxfs.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 01a7d50ed39b..340711e3dc9a 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -651,14 +651,13 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf,
 	length = sel_make_policy_nodes(fsi, newpolicy);
 	if (length) {
 		selinux_policy_cancel(fsi->state, newpolicy);
-		goto out1;
+		goto out;
 	}
 
 	selinux_policy_commit(fsi->state, newpolicy);
 
 	length = count;
 
-out1:
 	audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_POLICY_LOAD,
 		"auid=%u ses=%u lsm=selinux res=1",
 		from_kuid(&init_user_ns, audit_get_loginuid(current)),

From 6406887a12ee5dcdaffff1a8508d91113d545559 Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Thu, 18 Mar 2021 22:53:02 +0100
Subject: [PATCH 1055/1820] selinux: fix variable scope issue in live sidtab
 conversion

Commit 02a52c5c8c3b ("selinux: move policy commit after updating
selinuxfs") moved the selinux_policy_commit() call out of
security_load_policy() into sel_write_load(), which caused a subtle yet
rather serious bug.

The problem is that security_load_policy() passes a reference to the
convert_params local variable to sidtab_convert(), which stores it in
the sidtab, where it may be accessed until the policy is swapped over
and RCU synchronized. Before 02a52c5c8c3b, selinux_policy_commit() was
called directly from security_load_policy(), so the convert_params
pointer remained valid all the way until the old sidtab was destroyed,
but now that's no longer the case and calls to sidtab_context_to_sid()
on the old sidtab after security_load_policy() returns may cause invalid
memory accesses.

This can be easily triggered using the stress test from commit
ee1a84fdfeed ("selinux: overhaul sidtab to fix bug and improve
performance"):
```
function rand_cat() {
	echo $(( $RANDOM % 1024 ))
}

function do_work() {
	while true; do
		echo -n "system_u:system_r:kernel_t:s0:c$(rand_cat),c$(rand_cat)" \
			>/sys/fs/selinux/context 2>/dev/null || true
	done
}

do_work >/dev/null &
do_work >/dev/null &
do_work >/dev/null &

while load_policy; do echo -n .; sleep 0.1; done

kill %1
kill %2
kill %3
```

Fix this by allocating the temporary sidtab convert structures
dynamically and passing them among the
selinux_policy_{load,cancel,commit} functions.

Fixes: 02a52c5c8c3b ("selinux: move policy commit after updating selinuxfs")
Cc: stable@vger.kernel.org
Tested-by: Tyler Hicks <tyhicks@linux.microsoft.com>
Reviewed-by: Tyler Hicks <tyhicks@linux.microsoft.com>
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
[PM: merge fuzz in security.h and services.c]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/include/security.h | 15 +++++--
 security/selinux/selinuxfs.c        | 10 ++---
 security/selinux/ss/services.c      | 63 ++++++++++++++++++-----------
 3 files changed, 55 insertions(+), 33 deletions(-)

diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 765a258a899e..25db66e0ac51 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -219,14 +219,21 @@ static inline bool selinux_policycap_genfs_seclabel_symlinks(void)
 	return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_GENFS_SECLABEL_SYMLINKS]);
 }
 
+struct selinux_policy_convert_data;
+
+struct selinux_load_state {
+	struct selinux_policy *policy;
+	struct selinux_policy_convert_data *convert_data;
+};
+
 int security_mls_enabled(struct selinux_state *state);
 int security_load_policy(struct selinux_state *state,
-			void *data, size_t len,
-			struct selinux_policy **newpolicyp);
+			 void *data, size_t len,
+			 struct selinux_load_state *load_state);
 void selinux_policy_commit(struct selinux_state *state,
-			struct selinux_policy *newpolicy);
+			   struct selinux_load_state *load_state);
 void selinux_policy_cancel(struct selinux_state *state,
-			struct selinux_policy *policy);
+			   struct selinux_load_state *load_state);
 int security_read_policy(struct selinux_state *state,
 			 void **data, size_t *len);
 
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 340711e3dc9a..158d44ea93f4 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -616,7 +616,7 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf,
 
 {
 	struct selinux_fs_info *fsi = file_inode(file)->i_sb->s_fs_info;
-	struct selinux_policy *newpolicy;
+	struct selinux_load_state load_state;
 	ssize_t length;
 	void *data = NULL;
 
@@ -642,19 +642,19 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf,
 	if (copy_from_user(data, buf, count) != 0)
 		goto out;
 
-	length = security_load_policy(fsi->state, data, count, &newpolicy);
+	length = security_load_policy(fsi->state, data, count, &load_state);
 	if (length) {
 		pr_warn_ratelimited("SELinux: failed to load policy\n");
 		goto out;
 	}
 
-	length = sel_make_policy_nodes(fsi, newpolicy);
+	length = sel_make_policy_nodes(fsi, load_state.policy);
 	if (length) {
-		selinux_policy_cancel(fsi->state, newpolicy);
+		selinux_policy_cancel(fsi->state, &load_state);
 		goto out;
 	}
 
-	selinux_policy_commit(fsi->state, newpolicy);
+	selinux_policy_commit(fsi->state, &load_state);
 
 	length = count;
 
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 5e08ce2c5994..4a907e008a98 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -66,6 +66,17 @@
 #include "audit.h"
 #include "policycap_names.h"
 
+struct convert_context_args {
+	struct selinux_state *state;
+	struct policydb *oldp;
+	struct policydb *newp;
+};
+
+struct selinux_policy_convert_data {
+	struct convert_context_args args;
+	struct sidtab_convert_params sidtab_params;
+};
+
 /* Forward declaration. */
 static int context_struct_to_string(struct policydb *policydb,
 				    struct context *context,
@@ -1973,12 +1984,6 @@ static inline int convert_context_handle_invalid_context(
 	return 0;
 }
 
-struct convert_context_args {
-	struct selinux_state *state;
-	struct policydb *oldp;
-	struct policydb *newp;
-};
-
 /*
  * Convert the values in the security context
  * structure `oldc' from the values specified
@@ -2158,7 +2163,7 @@ static void selinux_policy_cond_free(struct selinux_policy *policy)
 }
 
 void selinux_policy_cancel(struct selinux_state *state,
-			struct selinux_policy *policy)
+			   struct selinux_load_state *load_state)
 {
 	struct selinux_policy *oldpolicy;
 
@@ -2166,7 +2171,8 @@ void selinux_policy_cancel(struct selinux_state *state,
 					lockdep_is_held(&state->policy_mutex));
 
 	sidtab_cancel_convert(oldpolicy->sidtab);
-	selinux_policy_free(policy);
+	selinux_policy_free(load_state->policy);
+	kfree(load_state->convert_data);
 }
 
 static void selinux_notify_policy_change(struct selinux_state *state,
@@ -2181,9 +2187,9 @@ static void selinux_notify_policy_change(struct selinux_state *state,
 }
 
 void selinux_policy_commit(struct selinux_state *state,
-			struct selinux_policy *newpolicy)
+			   struct selinux_load_state *load_state)
 {
-	struct selinux_policy *oldpolicy;
+	struct selinux_policy *oldpolicy, *newpolicy = load_state->policy;
 	u32 seqno;
 
 	oldpolicy = rcu_dereference_protected(state->policy,
@@ -2223,6 +2229,7 @@ void selinux_policy_commit(struct selinux_state *state,
 	/* Free the old policy */
 	synchronize_rcu();
 	selinux_policy_free(oldpolicy);
+	kfree(load_state->convert_data);
 
 	/* Notify others of the policy change */
 	selinux_notify_policy_change(state, seqno);
@@ -2239,11 +2246,10 @@ void selinux_policy_commit(struct selinux_state *state,
  * loading the new policy.
  */
 int security_load_policy(struct selinux_state *state, void *data, size_t len,
-			struct selinux_policy **newpolicyp)
+			 struct selinux_load_state *load_state)
 {
 	struct selinux_policy *newpolicy, *oldpolicy;
-	struct sidtab_convert_params convert_params;
-	struct convert_context_args args;
+	struct selinux_policy_convert_data *convert_data;
 	int rc = 0;
 	struct policy_file file = { data, len }, *fp = &file;
 
@@ -2273,10 +2279,10 @@ int security_load_policy(struct selinux_state *state, void *data, size_t len,
 		goto err_mapping;
 	}
 
-
 	if (!selinux_initialized(state)) {
 		/* First policy load, so no need to preserve state from old policy */
-		*newpolicyp = newpolicy;
+		load_state->policy = newpolicy;
+		load_state->convert_data = NULL;
 		return 0;
 	}
 
@@ -2290,29 +2296,38 @@ int security_load_policy(struct selinux_state *state, void *data, size_t len,
 		goto err_free_isids;
 	}
 
+	convert_data = kmalloc(sizeof(*convert_data), GFP_KERNEL);
+	if (!convert_data) {
+		rc = -ENOMEM;
+		goto err_free_isids;
+	}
+
 	/*
 	 * Convert the internal representations of contexts
 	 * in the new SID table.
 	 */
-	args.state = state;
-	args.oldp = &oldpolicy->policydb;
-	args.newp = &newpolicy->policydb;
+	convert_data->args.state = state;
+	convert_data->args.oldp = &oldpolicy->policydb;
+	convert_data->args.newp = &newpolicy->policydb;
 
-	convert_params.func = convert_context;
-	convert_params.args = &args;
-	convert_params.target = newpolicy->sidtab;
+	convert_data->sidtab_params.func = convert_context;
+	convert_data->sidtab_params.args = &convert_data->args;
+	convert_data->sidtab_params.target = newpolicy->sidtab;
 
-	rc = sidtab_convert(oldpolicy->sidtab, &convert_params);
+	rc = sidtab_convert(oldpolicy->sidtab, &convert_data->sidtab_params);
 	if (rc) {
 		pr_err("SELinux:  unable to convert the internal"
 			" representation of contexts in the new SID"
 			" table\n");
-		goto err_free_isids;
+		goto err_free_convert_data;
 	}
 
-	*newpolicyp = newpolicy;
+	load_state->policy = newpolicy;
+	load_state->convert_data = convert_data;
 	return 0;
 
+err_free_convert_data:
+	kfree(convert_data);
 err_free_isids:
 	sidtab_destroy(newpolicy->sidtab);
 err_mapping:

From ee5de60a08b7d8d255722662da461ea159c15538 Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Thu, 18 Mar 2021 22:53:03 +0100
Subject: [PATCH 1056/1820] selinuxfs: unify policy load error reporting

Let's drop the pr_err()s from sel_make_policy_nodes() and just add one
pr_warn_ratelimited() call to the sel_make_policy_nodes() error path in
sel_write_load().

Changing from error to warning makes sense, since after 02a52c5c8c3b
("selinux: move policy commit after updating selinuxfs"), this error
path no longer leads to a broken selinuxfs tree (it's just kept in the
original state and policy load is aborted).

I also added _ratelimited to be consistent with the other prtin in the
same function (it's probably not necessary, but can't really hurt...
there are likely more important error messages to be printed when
filesystem entry creation starts erroring out).

Suggested-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/selinuxfs.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 158d44ea93f4..fff6babeeae6 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -563,17 +563,13 @@ static int sel_make_policy_nodes(struct selinux_fs_info *fsi,
 
 	ret = sel_make_bools(newpolicy, tmp_bool_dir, &tmp_bool_num,
 			     &tmp_bool_names, &tmp_bool_values);
-	if (ret) {
-		pr_err("SELinux: failed to load policy booleans\n");
+	if (ret)
 		goto out;
-	}
 
 	ret = sel_make_classes(newpolicy, tmp_class_dir,
 			       &fsi->last_class_ino);
-	if (ret) {
-		pr_err("SELinux: failed to load policy classes\n");
+	if (ret)
 		goto out;
-	}
 
 	/* booleans */
 	old_dentry = fsi->bool_dir;
@@ -650,6 +646,7 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf,
 
 	length = sel_make_policy_nodes(fsi, load_state.policy);
 	if (length) {
+		pr_warn_ratelimited("SELinux: failed to initialize selinuxfs\n");
 		selinux_policy_cancel(fsi->state, &load_state);
 		goto out;
 	}

From 403dba003d17b3f0c1627b355cec2d74041cf648 Mon Sep 17 00:00:00 2001
From: Liu xuzhi <liu.xuzhi@zte.com.cn>
Date: Thu, 18 Mar 2021 17:46:57 -0700
Subject: [PATCH 1057/1820] fs/cifs/: fix misspellings using codespell tool

A typo is found out by codespell tool in 251th lines of cifs_swn.c:

$ codespell ./fs/cifs/
./cifs_swn.c:251: funciton  ==> function

Fix a typo found by codespell.

Signed-off-by: Liu xuzhi <liu.xuzhi@zte.com.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cifs_swn.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c
index f2d730fffccb..d829b8bf833e 100644
--- a/fs/cifs/cifs_swn.c
+++ b/fs/cifs/cifs_swn.c
@@ -248,7 +248,7 @@ nlmsg_fail:
 
 /*
  * Try to find a matching registration for the tcon's server name and share name.
- * Calls to this funciton must be protected by cifs_swnreg_idr_mutex.
+ * Calls to this function must be protected by cifs_swnreg_idr_mutex.
  * TODO Try to avoid memory allocations
  */
 static struct cifs_swn_reg *cifs_find_swn_reg(struct cifs_tcon *tcon)

From af3ef3b1031634724a3763606695ebcd113d782b Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Thu, 18 Mar 2021 19:17:10 +0100
Subject: [PATCH 1058/1820] cifs: warn and fail if trying to use rootfs without
 the config option

If CONFIG_CIFS_ROOT is not set, rootfs mount option is invalid

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
CC: <stable@vger.kernel.org> # v5.11
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/fs_context.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c
index 892f51a21278..78889024a7ed 100644
--- a/fs/cifs/fs_context.c
+++ b/fs/cifs/fs_context.c
@@ -1196,9 +1196,11 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		pr_warn_once("Witness protocol support is experimental\n");
 		break;
 	case Opt_rootfs:
-#ifdef CONFIG_CIFS_ROOT
-		ctx->rootfs = true;
+#ifndef CONFIG_CIFS_ROOT
+		cifs_dbg(VFS, "rootfs support requires CONFIG_CIFS_ROOT config option\n");
+		goto cifs_parse_mount_err;
 #endif
+		ctx->rootfs = true;
 		break;
 	case Opt_posixpaths:
 		if (result.negated)

From 9ceee7d0841a8f7d7644021ba7d4cc1fbc7966e3 Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Wed, 10 Mar 2021 00:31:27 -0800
Subject: [PATCH 1059/1820] firmware/efi: Fix a use after bug in
 efi_mem_reserve_persistent

In the for loop in efi_mem_reserve_persistent(), prsv = rsv->next
use the unmapped rsv. Use the unmapped pages will cause segment
fault.

Fixes: 18df7577adae6 ("efi/memreserve: deal with memreserve entries in unmapped memory")
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index df3f9bcab581..4b7ee3fa9224 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -927,7 +927,7 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size)
 	}
 
 	/* first try to find a slot in an existing linked list entry */
-	for (prsv = efi_memreserve_root->next; prsv; prsv = rsv->next) {
+	for (prsv = efi_memreserve_root->next; prsv; ) {
 		rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB);
 		index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size);
 		if (index < rsv->size) {
@@ -937,6 +937,7 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size)
 			memunmap(rsv);
 			return efi_mem_reserve_iomem(addr, size);
 		}
+		prsv = rsv->next;
 		memunmap(rsv);
 	}
 

From fb98cc0b3af2ba4d87301dff2b381b12eee35d7d Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 10 Mar 2021 08:33:19 +0100
Subject: [PATCH 1060/1820] efi: use 32-bit alignment for efi_guid_t literals

Commit 494c704f9af0 ("efi: Use 32-bit alignment for efi_guid_t") updated
the type definition of efi_guid_t to ensure that it always appears
sufficiently aligned (the UEFI spec is ambiguous about this, but given
the fact that its EFI_GUID type is defined in terms of a struct carrying
a uint32_t, the natural alignment is definitely >= 32 bits).

However, we missed the EFI_GUID() macro which is used to instantiate
efi_guid_t literals: that macro is still based on the guid_t type,
which does not have a minimum alignment at all. This results in warnings
such as

  In file included from drivers/firmware/efi/mokvar-table.c:35:
  include/linux/efi.h:1093:34: warning: passing 1-byte aligned argument to
      4-byte aligned parameter 2 of 'get_var' may result in an unaligned pointer
      access [-Walign-mismatch]
          status = get_var(L"SecureBoot", &EFI_GLOBAL_VARIABLE_GUID, NULL, &size,
                                          ^
  include/linux/efi.h:1101:24: warning: passing 1-byte aligned argument to
      4-byte aligned parameter 2 of 'get_var' may result in an unaligned pointer
      access [-Walign-mismatch]
          get_var(L"SetupMode", &EFI_GLOBAL_VARIABLE_GUID, NULL, &size, &setupmode);

The distinction only matters on CPUs that do not support misaligned loads
fully, but 32-bit ARM's load-multiple instructions fall into that category,
and these are likely to be emitted by the compiler that built the firmware
for loading word-aligned 128-bit GUIDs from memory

So re-implement the initializer in terms of our own efi_guid_t type, so that
the alignment becomes a property of the literal's type.

Fixes: 494c704f9af0 ("efi: Use 32-bit alignment for efi_guid_t")
Reported-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Link: https://github.com/ClangBuiltLinux/linux/issues/1327
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 include/linux/efi.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/linux/efi.h b/include/linux/efi.h
index 8710f5710c1d..6b5d36babfcc 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -72,8 +72,10 @@ typedef void *efi_handle_t;
  */
 typedef guid_t efi_guid_t __aligned(__alignof__(u32));
 
-#define EFI_GUID(a,b,c,d0,d1,d2,d3,d4,d5,d6,d7) \
-	GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7)
+#define EFI_GUID(a, b, c, d...) (efi_guid_t){ {					\
+	(a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff,	\
+	(b) & 0xff, ((b) >> 8) & 0xff,						\
+	(c) & 0xff, ((c) >> 8) & 0xff, d } }
 
 /*
  * Generic EFI table header

From 9ce3746d64132a561bceab6421715e7c04e85074 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Fri, 19 Mar 2021 10:16:50 +0100
Subject: [PATCH 1061/1820] documentation/kvm: additional explanations on
 KVM_SET_BOOT_CPU_ID

The ioctl KVM_SET_BOOT_CPU_ID fails when called after vcpu creation.
Add this explanation in the documentation.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-Id: <20210319091650.11967-1-eesposit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 2898d3e86b08..307f2fcf1b02 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -1495,7 +1495,8 @@ Fails if any VCPU has already been created.
 
 Define which vcpu is the Bootstrap Processor (BSP).  Values are the same
 as the vcpu id in KVM_CREATE_VCPU.  If this ioctl is not called, the default
-is vcpu 0.
+is vcpu 0. This ioctl has to be called before vcpu creation,
+otherwise it will return EBUSY error.
 
 
 4.42 KVM_GET_XSAVE

From a501b048a95b79e1e34f03cac3c87ff1e9f229ad Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 18 Mar 2021 20:26:47 +0100
Subject: [PATCH 1062/1820] x86/ioapic: Ignore IRQ2 again

Vitaly ran into an issue with hotplugging CPU0 on an Amazon instance where
the matrix allocator claimed to be out of vectors. He analyzed it down to
the point that IRQ2, the PIC cascade interrupt, which is supposed to be not
ever routed to the IO/APIC ended up having an interrupt vector assigned
which got moved during unplug of CPU0.

The underlying issue is that IRQ2 for various reasons (see commit
af174783b925 ("x86: I/O APIC: Never configure IRQ2" for details) is treated
as a reserved system vector by the vector core code and is not accounted as
a regular vector. The Amazon BIOS has an routing entry of pin2 to IRQ2
which causes the IO/APIC setup to claim that interrupt which is granted by
the vector domain because there is no sanity check. As a consequence the
allocation counter of CPU0 underflows which causes a subsequent unplug to
fail with:

  [ ... ] CPU 0 has 4294967295 vectors, 589 available. Cannot disable CPU

There is another sanity check missing in the matrix allocator, but the
underlying root cause is that the IO/APIC code lost the IRQ2 ignore logic
during the conversion to irqdomains.

For almost 6 years nobody complained about this wreckage, which might
indicate that this requirement could be lifted, but for any system which
actually has a PIC IRQ2 is unusable by design so any routing entry has no
effect and the interrupt cannot be connected to a device anyway.

Due to that and due to history biased paranoia reasons restore the IRQ2
ignore logic and treat it as non existent despite a routing entry claiming
otherwise.

Fixes: d32932d02e18 ("x86/irq: Convert IOAPIC to use hierarchical irqdomain interfaces")
Reported-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210318192819.636943062@linutronix.de
---
 arch/x86/kernel/apic/io_apic.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c3b60c37c728..73ff4dd426a8 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1032,6 +1032,16 @@ static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin,
 	if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
 		irq = mp_irqs[idx].srcbusirq;
 		legacy = mp_is_legacy_irq(irq);
+		/*
+		 * IRQ2 is unusable for historical reasons on systems which
+		 * have a legacy PIC. See the comment vs. IRQ2 further down.
+		 *
+		 * If this gets removed at some point then the related code
+		 * in lapic_assign_system_vectors() needs to be adjusted as
+		 * well.
+		 */
+		if (legacy && irq == PIC_CASCADE_IR)
+			return -EINVAL;
 	}
 
 	mutex_lock(&ioapic_mutex);

From 68b1eddd421d2b16c6655eceb48918a1e896bbbc Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 18 Mar 2021 11:27:19 +0100
Subject: [PATCH 1063/1820] static_call: Fix static_call_set_init()

It turns out that static_call_set_init() does not preserve the other
flags; IOW. it clears TAIL if it was set.

Fixes: 9183c3f9ed710 ("static_call: Add inline static call infrastructure")
Reported-by: Sumit Garg <sumit.garg@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Sumit Garg <sumit.garg@linaro.org>
Link: https://lkml.kernel.org/r/20210318113610.519406371@infradead.org
---
 kernel/static_call.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/kernel/static_call.c b/kernel/static_call.c
index ae825295cf68..080c8a9ddfaf 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -35,27 +35,30 @@ static inline void *static_call_addr(struct static_call_site *site)
 	return (void *)((long)site->addr + (long)&site->addr);
 }
 
+static inline unsigned long __static_call_key(const struct static_call_site *site)
+{
+	return (long)site->key + (long)&site->key;
+}
 
 static inline struct static_call_key *static_call_key(const struct static_call_site *site)
 {
-	return (struct static_call_key *)
-		(((long)site->key + (long)&site->key) & ~STATIC_CALL_SITE_FLAGS);
+	return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS);
 }
 
 /* These assume the key is word-aligned. */
 static inline bool static_call_is_init(struct static_call_site *site)
 {
-	return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_INIT;
+	return __static_call_key(site) & STATIC_CALL_SITE_INIT;
 }
 
 static inline bool static_call_is_tail(struct static_call_site *site)
 {
-	return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_TAIL;
+	return __static_call_key(site) & STATIC_CALL_SITE_TAIL;
 }
 
 static inline void static_call_set_init(struct static_call_site *site)
 {
-	site->key = ((long)static_call_key(site) | STATIC_CALL_SITE_INIT) -
+	site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) -
 		    (long)&site->key;
 }
 
@@ -190,7 +193,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 			}
 
 			arch_static_call_transform(site_addr, NULL, func,
-				static_call_is_tail(site));
+						   static_call_is_tail(site));
 		}
 	}
 
@@ -349,7 +352,7 @@ static int static_call_add_module(struct module *mod)
 	struct static_call_site *site;
 
 	for (site = start; site != stop; site++) {
-		unsigned long s_key = (long)site->key + (long)&site->key;
+		unsigned long s_key = __static_call_key(site);
 		unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS;
 		unsigned long key;
 

From 698bacefe993ad2922c9d3b1380591ad489355e9 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 18 Mar 2021 11:29:56 +0100
Subject: [PATCH 1064/1820] static_call: Align static_call_is_init() patching
 condition

The intent is to avoid writing init code after init (because the text
might have been freed). The code is needlessly different between
jump_label and static_call and not obviously correct.

The existing code relies on the fact that the module loader clears the
init layout, such that within_module_init() always fails, while
jump_label relies on the module state which is more obvious and
matches the kernel logic.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Sumit Garg <sumit.garg@linaro.org>
Link: https://lkml.kernel.org/r/20210318113610.636651340@infradead.org
---
 kernel/static_call.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/kernel/static_call.c b/kernel/static_call.c
index 080c8a9ddfaf..fc2259047be2 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -149,6 +149,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 	};
 
 	for (site_mod = &first; site_mod; site_mod = site_mod->next) {
+		bool init = system_state < SYSTEM_RUNNING;
 		struct module *mod = site_mod->mod;
 
 		if (!site_mod->sites) {
@@ -168,6 +169,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 		if (mod) {
 			stop = mod->static_call_sites +
 			       mod->num_static_call_sites;
+			init = mod->state == MODULE_STATE_COMING;
 		}
 #endif
 
@@ -175,16 +177,8 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 		     site < stop && static_call_key(site) == key; site++) {
 			void *site_addr = static_call_addr(site);
 
-			if (static_call_is_init(site)) {
-				/*
-				 * Don't write to call sites which were in
-				 * initmem and have since been freed.
-				 */
-				if (!mod && system_state >= SYSTEM_RUNNING)
-					continue;
-				if (mod && !within_module_init((unsigned long)site_addr, mod))
-					continue;
-			}
+			if (!init && static_call_is_init(site))
+				continue;
 
 			if (!kernel_text_address((unsigned long)site_addr)) {
 				WARN_ONCE(1, "can't patch static call site at %pS",

From 38c93587375053c5b9ef093f4a5ea754538cba32 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 18 Mar 2021 11:31:51 +0100
Subject: [PATCH 1065/1820] static_call: Fix static_call_update() sanity check

Sites that match init_section_contains() get marked as INIT. For
built-in code init_sections contains both __init and __exit text. OTOH
kernel_text_address() only explicitly includes __init text (and there
are no __exit text markers).

Match what jump_label already does and ignore the warning for INIT
sites. Also see the excellent changelog for commit: 8f35eaa5f2de
("jump_label: Don't warn on __exit jump entries")

Fixes: 9183c3f9ed710 ("static_call: Add inline static call infrastructure")
Reported-by: Sumit Garg <sumit.garg@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Sumit Garg <sumit.garg@linaro.org>
Link: https://lkml.kernel.org/r/20210318113610.739542434@infradead.org
---
 kernel/jump_label.c  |  8 ++++++++
 kernel/static_call.c | 11 ++++++++++-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index c6a39d662935..ba39fbb1f8e7 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -407,6 +407,14 @@ static bool jump_label_can_update(struct jump_entry *entry, bool init)
 		return false;
 
 	if (!kernel_text_address(jump_entry_code(entry))) {
+		/*
+		 * This skips patching built-in __exit, which
+		 * is part of init_section_contains() but is
+		 * not part of kernel_text_address().
+		 *
+		 * Skipping built-in __exit is fine since it
+		 * will never be executed.
+		 */
 		WARN_ONCE(!jump_entry_is_init(entry),
 			  "can't patch jump_label at %pS",
 			  (void *)jump_entry_code(entry));
diff --git a/kernel/static_call.c b/kernel/static_call.c
index fc2259047be2..2c5950b0b90e 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -181,7 +181,16 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 				continue;
 
 			if (!kernel_text_address((unsigned long)site_addr)) {
-				WARN_ONCE(1, "can't patch static call site at %pS",
+				/*
+				 * This skips patching built-in __exit, which
+				 * is part of init_section_contains() but is
+				 * not part of kernel_text_address().
+				 *
+				 * Skipping built-in __exit is fine since it
+				 * will never be executed.
+				 */
+				WARN_ONCE(!static_call_is_init(site),
+					  "can't patch static call site at %pS",
 					  site_addr);
 				continue;
 			}

From 0cab893f409c53634d0d818fa414641cbcdb0dab Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 19 Mar 2021 15:47:25 +0100
Subject: [PATCH 1066/1820] Revert "PM: runtime: Update device status before
 letting suppliers suspend"

Revert commit 44cc89f76464 ("PM: runtime: Update device status
before letting suppliers suspend") that introduced a race condition
into __rpm_callback() which allowed a concurrent rpm_resume() to
run and resume the device prematurely after its status had been
changed to RPM_SUSPENDED by __rpm_callback().

Fixes: 44cc89f76464 ("PM: runtime: Update device status before letting suppliers suspend")
Link: https://lore.kernel.org/linux-pm/24dfb6fc-5d54-6ee2-9195-26428b7ecf8a@intel.com/
Reported-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: 4.10+ <stable@vger.kernel.org> # 4.10+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/base/power/runtime.c | 62 +++++++++++++++---------------------
 1 file changed, 25 insertions(+), 37 deletions(-)

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 18b82427d0cb..a46a7e30881b 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -325,22 +325,22 @@ static void rpm_put_suppliers(struct device *dev)
 static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
 	__releases(&dev->power.lock) __acquires(&dev->power.lock)
 {
-	bool use_links = dev->power.links_count > 0;
-	bool get = false;
 	int retval, idx;
-	bool put;
+	bool use_links = dev->power.links_count > 0;
 
 	if (dev->power.irq_safe) {
 		spin_unlock(&dev->power.lock);
-	} else if (!use_links) {
-		spin_unlock_irq(&dev->power.lock);
 	} else {
-		get = dev->power.runtime_status == RPM_RESUMING;
-
 		spin_unlock_irq(&dev->power.lock);
 
-		/* Resume suppliers if necessary. */
-		if (get) {
+		/*
+		 * Resume suppliers if necessary.
+		 *
+		 * The device's runtime PM status cannot change until this
+		 * routine returns, so it is safe to read the status outside of
+		 * the lock.
+		 */
+		if (use_links && dev->power.runtime_status == RPM_RESUMING) {
 			idx = device_links_read_lock();
 
 			retval = rpm_get_suppliers(dev);
@@ -355,36 +355,24 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
 
 	if (dev->power.irq_safe) {
 		spin_lock(&dev->power.lock);
-		return retval;
-	}
+	} else {
+		/*
+		 * If the device is suspending and the callback has returned
+		 * success, drop the usage counters of the suppliers that have
+		 * been reference counted on its resume.
+		 *
+		 * Do that if resume fails too.
+		 */
+		if (use_links
+		    && ((dev->power.runtime_status == RPM_SUSPENDING && !retval)
+		    || (dev->power.runtime_status == RPM_RESUMING && retval))) {
+			idx = device_links_read_lock();
 
-	spin_lock_irq(&dev->power.lock);
+ fail:
+			rpm_put_suppliers(dev);
 
-	if (!use_links)
-		return retval;
-
-	/*
-	 * If the device is suspending and the callback has returned success,
-	 * drop the usage counters of the suppliers that have been reference
-	 * counted on its resume.
-	 *
-	 * Do that if the resume fails too.
-	 */
-	put = dev->power.runtime_status == RPM_SUSPENDING && !retval;
-	if (put)
-		__update_runtime_status(dev, RPM_SUSPENDED);
-	else
-		put = get && retval;
-
-	if (put) {
-		spin_unlock_irq(&dev->power.lock);
-
-		idx = device_links_read_lock();
-
-fail:
-		rpm_put_suppliers(dev);
-
-		device_links_read_unlock(idx);
+			device_links_read_unlock(idx);
+		}
 
 		spin_lock_irq(&dev->power.lock);
 	}

From 896ea5dab25ef12f7d0988b8f0b053a287faf889 Mon Sep 17 00:00:00 2001
From: Tom Seewald <tseewald@gmail.com>
Date: Sun, 21 Feb 2021 22:00:04 -0600
Subject: [PATCH 1067/1820] e1000e: Fix duplicate include guard

The include guard "_E1000_HW_H_" is used by header files in three
different drivers (e1000/e1000_hw.h, e1000e/hw.h, and igb/e1000_hw.h).
Using the same include guard macro in more than one header file may
cause unexpected behavior from the compiler. Fix the duplicate include
guard in the e1000e driver by renaming it.

Fixes: bc7f75fa9788 ("[E1000E]: New pci-express e1000 driver (currently for ICH9 devices only)")
Signed-off-by: Tom Seewald <tseewald@gmail.com>
Tested-by: Dvora Fuxbrumer <dvorax.fuxbrumer@linux.intel.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/hw.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index 69a2329ea463..db79c4e6413e 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -1,8 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright(c) 1999 - 2018 Intel Corporation. */
 
-#ifndef _E1000_HW_H_
-#define _E1000_HW_H_
+#ifndef _E1000E_HW_H_
+#define _E1000E_HW_H_
 
 #include "regs.h"
 #include "defines.h"
@@ -714,4 +714,4 @@ struct e1000_hw {
 #include "80003es2lan.h"
 #include "ich8lan.h"
 
-#endif
+#endif /* _E1000E_HW_H_ */

From a75519a84855bca029ce7d8a27de9409d9b84956 Mon Sep 17 00:00:00 2001
From: Tom Seewald <tseewald@gmail.com>
Date: Sun, 21 Feb 2021 22:00:05 -0600
Subject: [PATCH 1068/1820] igb: Fix duplicate include guard

The include guard "_E1000_HW_H_" is used by two separate header files in
two different drivers (e1000/e1000_hw.h and igb/e1000_hw.h). Using the
same include guard macro in more than one header file may cause
unexpected behavior from the compiler. Fix this by renaming the
duplicate guard in the igb driver.

Fixes: 9d5c824399de ("igb: PCI-Express 82575 Gigabit Ethernet driver")
Signed-off-by: Tom Seewald <tseewald@gmail.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igb/e1000_hw.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h
index 5d87957b2627..44111f65afc7 100644
--- a/drivers/net/ethernet/intel/igb/e1000_hw.h
+++ b/drivers/net/ethernet/intel/igb/e1000_hw.h
@@ -1,8 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright(c) 2007 - 2018 Intel Corporation. */
 
-#ifndef _E1000_HW_H_
-#define _E1000_HW_H_
+#ifndef _E1000_IGB_HW_H_
+#define _E1000_IGB_HW_H_
 
 #include <linux/types.h>
 #include <linux/delay.h>
@@ -551,4 +551,4 @@ s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value);
 
 void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value);
 void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value);
-#endif /* _E1000_HW_H_ */
+#endif /* _E1000_IGB_HW_H_ */

From f0a03a026857d6c7766eb7d5835edbf5523ca15c Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Wed, 3 Mar 2021 12:51:03 -0800
Subject: [PATCH 1069/1820] igb: check timestamp validity

Add a couple of checks to make sure timestamping is on and that the
timestamp value from DMA is valid. This avoids any functional issues
that could come from a misinterpreted time stamp.

One of the functions changed doesn't need a return value added because
there was no value in checking from the calling locations.

While here, fix a couple of reverse christmas tree issues next to
the code being changed.

Fixes: f56e7bba22fa ("igb: Pull timestamp from fragment before adding it to skb")
Fixes: 9cbc948b5a20 ("igb: add XDP support")
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Dave Switzer <david.switzer@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igb/igb.h      |  4 +--
 drivers/net/ethernet/intel/igb/igb_main.c | 11 ++++----
 drivers/net/ethernet/intel/igb/igb_ptp.c  | 31 ++++++++++++++++++-----
 3 files changed, 32 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index aaa954aae574..7bda8c5edea5 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -748,8 +748,8 @@ void igb_ptp_suspend(struct igb_adapter *adapter);
 void igb_ptp_rx_hang(struct igb_adapter *adapter);
 void igb_ptp_tx_hang(struct igb_adapter *adapter);
 void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
-void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
-			 struct sk_buff *skb);
+int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
+			struct sk_buff *skb);
 int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
 int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
 void igb_set_flag_queue_pairs(struct igb_adapter *, const u32);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index d3b37761f637..a45cd2b416c8 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -8302,9 +8302,10 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 		return NULL;
 
 	if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) {
-		igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb);
-		xdp->data += IGB_TS_HDR_LEN;
-		size -= IGB_TS_HDR_LEN;
+		if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb)) {
+			xdp->data += IGB_TS_HDR_LEN;
+			size -= IGB_TS_HDR_LEN;
+		}
 	}
 
 	/* Determine available headroom for copy */
@@ -8365,8 +8366,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
 
 	/* pull timestamp out of packet data */
 	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
-		igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb);
-		__skb_pull(skb, IGB_TS_HDR_LEN);
+		if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb))
+			__skb_pull(skb, IGB_TS_HDR_LEN);
 	}
 
 	/* update buffer offset */
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index 7cc5428c3b3d..86a576201f5f 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -856,6 +856,9 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
 	dev_kfree_skb_any(skb);
 }
 
+#define IGB_RET_PTP_DISABLED 1
+#define IGB_RET_PTP_INVALID 2
+
 /**
  * igb_ptp_rx_pktstamp - retrieve Rx per packet timestamp
  * @q_vector: Pointer to interrupt specific structure
@@ -864,19 +867,29 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
  *
  * This function is meant to retrieve a timestamp from the first buffer of an
  * incoming frame.  The value is stored in little endian format starting on
- * byte 8.
+ * byte 8
+ *
+ * Returns: 0 if success, nonzero if failure
  **/
-void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
-			 struct sk_buff *skb)
+int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
+			struct sk_buff *skb)
 {
-	__le64 *regval = (__le64 *)va;
 	struct igb_adapter *adapter = q_vector->adapter;
+	__le64 *regval = (__le64 *)va;
 	int adjust = 0;
 
+	if (!(adapter->ptp_flags & IGB_PTP_ENABLED))
+		return IGB_RET_PTP_DISABLED;
+
 	/* The timestamp is recorded in little endian format.
 	 * DWORD: 0        1        2        3
 	 * Field: Reserved Reserved SYSTIML  SYSTIMH
 	 */
+
+	/* check reserved dwords are zero, be/le doesn't matter for zero */
+	if (regval[0])
+		return IGB_RET_PTP_INVALID;
+
 	igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb),
 				   le64_to_cpu(regval[1]));
 
@@ -896,6 +909,8 @@ void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 	}
 	skb_hwtstamps(skb)->hwtstamp =
 		ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust);
+
+	return 0;
 }
 
 /**
@@ -906,13 +921,15 @@ void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
  * This function is meant to retrieve a timestamp from the internal registers
  * of the adapter and store it in the skb.
  **/
-void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector,
-			 struct sk_buff *skb)
+void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb)
 {
 	struct igb_adapter *adapter = q_vector->adapter;
 	struct e1000_hw *hw = &adapter->hw;
-	u64 regval;
 	int adjust = 0;
+	u64 regval;
+
+	if (!(adapter->ptp_flags & IGB_PTP_ENABLED))
+		return;
 
 	/* If this bit is set, then the RX registers contain the time stamp. No
 	 * other packet will be time stamped until we read these registers, so

From c1d1e25a8c542816ae8dee41b81a18d30c7519a0 Mon Sep 17 00:00:00 2001
From: Chris Chiu <chris.chiu@canonical.com>
Date: Fri, 12 Mar 2021 11:24:30 +0800
Subject: [PATCH 1070/1820] ACPI: video: Add missing callback back for Sony
 VPCEH3U1E

The .callback of the quirk for Sony VPCEH3U1E was unintetionally
removed by the commit 25417185e9b5 ("ACPI: video: Add DMI quirk
for GIGABYTE GB-BXBT-2807"). Add it back to make sure the quirk
for Sony VPCEH3U1E works as expected.

Fixes: 25417185e9b5 ("ACPI: video: Add DMI quirk for GIGABYTE GB-BXBT-2807")
Signed-off-by: Chris Chiu <chris.chiu@canonical.com>
Reported-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Pavel Machek (CIP) <pavel@denx.de>
Cc: 5.11+ <stable@vger.kernel.org> # 5.11+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/video_detect.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 811d298637cb..83cd4c95faf0 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -147,6 +147,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		},
 	},
 	{
+	.callback = video_detect_force_vendor,
 	.ident = "Sony VPCEH3U1E",
 	.matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),

From 65af8f0166f4d15e61c63db498ec7981acdd897f Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Fri, 19 Mar 2021 00:05:48 -0500
Subject: [PATCH 1071/1820] cifs: fix allocation size on newly created files

Applications that create and extend and write to a file do not
expect to see 0 allocation size.  When file is extended,
set its allocation size to a plausible value until we have a
chance to query the server for it.  When the file is cached
this will prevent showing an impossible number of allocated
blocks (like 0).  This fixes e.g. xfstests 614 which does

    1) create a file and set its size to 64K
    2) mmap write 64K to the file
    3) stat -c %b for the file (to query the number of allocated blocks)

It was failing because we returned 0 blocks.  Even though we would
return the correct cached file size, we returned an impossible
allocation size.

Signed-off-by: Steve French <stfrench@microsoft.com>
CC: <stable@vger.kernel.org>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
---
 fs/cifs/inode.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 7c61bc9573c0..f2df4422e54a 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -2395,7 +2395,7 @@ int cifs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 	 * We need to be sure that all dirty pages are written and the server
 	 * has actual ctime, mtime and file length.
 	 */
-	if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_SIZE)) &&
+	if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_SIZE | STATX_BLOCKS)) &&
 	    !CIFS_CACHE_READ(CIFS_I(inode)) &&
 	    inode->i_mapping && inode->i_mapping->nrpages != 0) {
 		rc = filemap_fdatawait(inode->i_mapping);
@@ -2585,6 +2585,14 @@ set_size_out:
 	if (rc == 0) {
 		cifsInode->server_eof = attrs->ia_size;
 		cifs_setsize(inode, attrs->ia_size);
+		/*
+		 * i_blocks is not related to (i_size / i_blksize), but instead
+		 * 512 byte (2**9) size is required for calculating num blocks.
+		 * Until we can query the server for actual allocation size,
+		 * this is best estimate we have for blocks allocated for a file
+		 * Number of blocks must be rounded up so size 1 is not 0 blocks
+		 */
+		inode->i_blocks = (512 - 1 + attrs->ia_size) >> 9;
 
 		/*
 		 * The man page of truncate says if the size changed,

From 8ff0b1f08ea73e5c08f5addd23481e76a60e741c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 19 Mar 2021 11:52:41 +0800
Subject: [PATCH 1072/1820] sctp: move sk_route_caps check and set into
 sctp_outq_flush_transports

The sk's sk_route_caps is set in sctp_packet_config, and later it
only needs to change when traversing the transport_list in a loop,
as the dst might be changed in the tx path.

So move sk_route_caps check and set into sctp_outq_flush_transports
from sctp_packet_transmit. This also fixes a dst leak reported by
Chen Yi:

  https://bugzilla.kernel.org/show_bug.cgi?id=212227

As calling sk_setup_caps() in sctp_packet_transmit may also set the
sk_route_caps for the ctrl sock in a netns. When the netns is being
deleted, the ctrl sock's releasing is later than dst dev's deleting,
which will cause this dev's deleting to hang and dmesg error occurs:

  unregister_netdevice: waiting for xxx to become free. Usage count = 1

Reported-by: Chen Yi <yiche@redhat.com>
Fixes: bcd623d8e9fa ("sctp: call sk_setup_caps in sctp_packet_transmit instead")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/output.c   | 7 -------
 net/sctp/outqueue.c | 7 +++++++
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/sctp/output.c b/net/sctp/output.c
index 6614c9fdc51e..a6aa17df09ef 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -584,13 +584,6 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 		goto out;
 	}
 
-	rcu_read_lock();
-	if (__sk_dst_get(sk) != tp->dst) {
-		dst_hold(tp->dst);
-		sk_setup_caps(sk, tp->dst);
-	}
-	rcu_read_unlock();
-
 	/* pack up chunks */
 	pkt_count = sctp_packet_pack(packet, head, gso, gfp);
 	if (!pkt_count) {
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 3fd06a27105d..5cb1aa5f067b 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -1135,6 +1135,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
 
 static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx)
 {
+	struct sock *sk = ctx->asoc->base.sk;
 	struct list_head *ltransport;
 	struct sctp_packet *packet;
 	struct sctp_transport *t;
@@ -1144,6 +1145,12 @@ static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx)
 		t = list_entry(ltransport, struct sctp_transport, send_ready);
 		packet = &t->packet;
 		if (!sctp_packet_empty(packet)) {
+			rcu_read_lock();
+			if (t->dst && __sk_dst_get(sk) != t->dst) {
+				dst_hold(t->dst);
+				sk_setup_caps(sk, t->dst);
+			}
+			rcu_read_unlock();
 			error = sctp_packet_transmit(packet, ctx->gfp);
 			if (error < 0)
 				ctx->q->asoc->base.sk->sk_err = -error;

From 8a2dc6af67a0c9f65a22ea40fc79974ee8f368c7 Mon Sep 17 00:00:00 2001
From: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Date: Fri, 19 Mar 2021 10:16:23 +0530
Subject: [PATCH 1073/1820] sch_red: Fix a typo

s/recalcultion/recalculation/

Signed-off-by: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/red.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/red.h b/include/net/red.h
index 9e6647c4ccd1..0b39eff1d50a 100644
--- a/include/net/red.h
+++ b/include/net/red.h
@@ -295,7 +295,7 @@ static inline unsigned long red_calc_qavg_from_idle_time(const struct red_parms
 	int  shift;
 
 	/*
-	 * The problem: ideally, average length queue recalcultion should
+	 * The problem: ideally, average length queue recalculation should
 	 * be done over constant clock intervals. This is too expensive, so
 	 * that the calculation is driven by outgoing packets.
 	 * When the queue is idle we have to model this clock by hand.

From f91a50d8b51b5c8ef1cfb08115a005bba4250507 Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Fri, 19 Mar 2021 15:37:21 +0800
Subject: [PATCH 1074/1820] r8152: limit the RX buffer size of RTL8153A for USB
 2.0

If the USB host controller is EHCI, the throughput is reduced from
300Mb/s to 60Mb/s, when the rx buffer size is modified from 16K to
32K.

According to the EHCI spec, the maximum size of the qTD is 20K.
Therefore, when the driver uses more than 20K buffer, the latency
time of EHCI would be increased. And, it let the RTL8153A get worse
throughput.

However, the driver uses alloc_pages() for rx buffer, so I limit
the rx buffer to 16K rather than 20K.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=205923
Fixes: ec5791c202ac ("r8152: separate the rx buffer size")
Reported-by: Robert Davies <robdavies1977@gmail.com>
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 90f1c0200042..20fb5638ac65 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -6553,7 +6553,10 @@ static int rtl_ops_init(struct r8152 *tp)
 		ops->in_nway		= rtl8153_in_nway;
 		ops->hw_phy_cfg		= r8153_hw_phy_cfg;
 		ops->autosuspend_en	= rtl8153_runtime_enable;
-		tp->rx_buf_sz		= 32 * 1024;
+		if (tp->udev->speed < USB_SPEED_SUPER)
+			tp->rx_buf_sz	= 16 * 1024;
+		else
+			tp->rx_buf_sz	= 32 * 1024;
 		tp->eee_en		= true;
 		tp->eee_adv		= MDIO_EEE_1000T | MDIO_EEE_100TX;
 		break;

From cd5297b0855f17c8b4e3ef1d20c6a3656209c7b3 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 1 Mar 2021 10:52:53 +0100
Subject: [PATCH 1075/1820] drm/etnaviv: Use FOLL_FORCE for userptr

Nothing checks userptr.ro except this call to pup_fast, which means
there's nothing actually preventing userspace from writing to this.
Which means you can just read-only mmap any file you want, userptr it
and then write to it with the gpu. Not good.

The right way to handle this is FOLL_WRITE | FOLL_FORCE, which will
break any COW mappings and update tracking for MAY_WRITE mappings so
there's no exploit and the vm isn't confused about what's going on.
For any legit use case there's no difference from what userspace can
observe and do.

Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Cc: stable@vger.kernel.org
Cc: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Lucas Stach <l.stach@pengutronix.de>
Cc: Russell King <linux+etnaviv@armlinux.org.uk>
Cc: Christian Gmeiner <christian.gmeiner@gmail.com>
Cc: etnaviv@lists.freedesktop.org
Link: https://patchwork.freedesktop.org/patch/msgid/20210301095254.1946084-1-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/etnaviv/etnaviv_gem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 6d38c5c17f23..a9e696d05b33 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -689,7 +689,7 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj)
 		struct page **pages = pvec + pinned;
 
 		ret = pin_user_pages_fast(ptr, num_pages,
-					  !userptr->ro ? FOLL_WRITE : 0, pages);
+					  FOLL_WRITE | FOLL_FORCE, pages);
 		if (ret < 0) {
 			unpin_user_pages(pvec, pinned);
 			kvfree(pvec);

From 50891bead80bc79871528c2962d65c781c02330b Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 1 Mar 2021 10:52:54 +0100
Subject: [PATCH 1076/1820] drm/etnaviv: User FOLL_LONGTERM in userptr

There's no mmu notifier or anything like that, releasing this pin is
entirely up to userspace. Hence FOLL_LONGTERM.

No cc: stable for this patch since a lot of the infrastructure around
FOLL_LONGETRM (like not allowing it for pages currently sitting in
ZONE_MOVEABLE before they're migrated) is still being worked on. So
not big benefits yet.

Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Lucas Stach <l.stach@pengutronix.de>
Cc: Russell King <linux+etnaviv@armlinux.org.uk>
Cc: Christian Gmeiner <christian.gmeiner@gmail.com>
Cc: etnaviv@lists.freedesktop.org
Link: https://patchwork.freedesktop.org/patch/msgid/20210301095254.1946084-2-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/etnaviv/etnaviv_gem.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index a9e696d05b33..db69f19ab5bc 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -689,7 +689,8 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj)
 		struct page **pages = pvec + pinned;
 
 		ret = pin_user_pages_fast(ptr, num_pages,
-					  FOLL_WRITE | FOLL_FORCE, pages);
+					  FOLL_WRITE | FOLL_FORCE | FOLL_LONGTERM,
+					  pages);
 		if (ret < 0) {
 			unpin_user_pages(pvec, pinned);
 			kvfree(pvec);

From 014dfa26ce1c647af09bf506285ef67e0e3f0a6b Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Fri, 19 Mar 2021 13:44:22 +0000
Subject: [PATCH 1077/1820] net: stmmac: dwmac-sun8i: Provide TX and RX fifo
 sizes

MTU cannot be changed on dwmac-sun8i. (ip link set eth0 mtu xxx returning EINVAL)
This is due to tx_fifo_size being 0, since this value is used to compute valid
MTU range.
Like dwmac-sunxi (with commit 806fd188ce2a ("net: stmmac: dwmac-sunxi: Provide TX and RX fifo sizes"))
dwmac-sun8i need to have tx and rx fifo sizes set.
I have used values from datasheets.
After this patch, setting a non-default MTU (like 1000) value works and network is still useable.

Tested-on: sun8i-h3-orangepi-pc
Tested-on: sun8i-r40-bananapi-m2-ultra
Tested-on: sun50i-a64-bananapi-m64
Tested-on: sun50i-h5-nanopi-neo-plus2
Tested-on: sun50i-h6-pine-h64
Fixes: 9f93ac8d408 ("net-next: stmmac: Add dwmac-sun8i")
Reported-by: Belisko Marek <marek.belisko@gmail.com>
Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 6b75cf2603ff..e62efd166ec8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -1214,6 +1214,8 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	plat_dat->init = sun8i_dwmac_init;
 	plat_dat->exit = sun8i_dwmac_exit;
 	plat_dat->setup = sun8i_dwmac_setup;
+	plat_dat->tx_fifo_size = 4096;
+	plat_dat->rx_fifo_size = 16384;
 
 	ret = sun8i_dwmac_set_syscon(&pdev->dev, plat_dat);
 	if (ret)

From 1f935e8e72ec28dddb2dc0650b3b6626a293d94b Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Fri, 19 Mar 2021 13:05:41 +0000
Subject: [PATCH 1078/1820] selinux: vsock: Set SID for socket returned by
 accept()

For AF_VSOCK, accept() currently returns sockets that are unlabelled.
Other socket families derive the child's SID from the SID of the parent
and the SID of the incoming packet. This is typically done as the
connected socket is placed in the queue that accept() removes from.

Reuse the existing 'security_sk_clone' hook to copy the SID from the
parent (server) socket to the child. There is no packet SID in this
case.

Fixes: d021c344051a ("VSOCK: Introduce VM Sockets")
Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 5546710d8ac1..bc7fb9bf3351 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -755,6 +755,7 @@ static struct sock *__vsock_create(struct net *net,
 		vsk->buffer_size = psk->buffer_size;
 		vsk->buffer_min_size = psk->buffer_min_size;
 		vsk->buffer_max_size = psk->buffer_max_size;
+		security_sk_clone(parent, sk);
 	} else {
 		vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN);
 		vsk->owner = get_current_cred();

From ef2ef02cd9c2484f7ba29227d5fd5c78d7ea0393 Mon Sep 17 00:00:00 2001
From: Mat Martineau <mathew.j.martineau@linux.intel.com>
Date: Fri, 19 Mar 2021 11:33:02 -0700
Subject: [PATCH 1079/1820] mptcp: Change mailing list address

The mailing list for MPTCP maintenance has moved to the
kernel.org-supported mptcp@lists.linux.dev address.

Complete, combined archives for both lists are now hosted at
https://lore.kernel.org/mptcp

Cc: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0d80d3dda3d0..8e43e0417335 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12539,7 +12539,7 @@ NETWORKING [MPTCP]
 M:	Mat Martineau <mathew.j.martineau@linux.intel.com>
 M:	Matthieu Baerts <matthieu.baerts@tessares.net>
 L:	netdev@vger.kernel.org
-L:	mptcp@lists.01.org
+L:	mptcp@lists.linux.dev
 S:	Maintained
 W:	https://github.com/multipath-tcp/mptcp_net-next/wiki
 B:	https://github.com/multipath-tcp/mptcp_net-next/issues

From 5aa3c334a449bab24519c4967f5ac2b3304c8dcf Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 19 Mar 2021 22:33:14 +0800
Subject: [PATCH 1080/1820] selftests: forwarding: vxlan_bridge_1d: Fix vxlan
 ecn decapsulate value

The ECN bit defines ECT(1) = 1, ECT(0) = 2. So inner 0x02 + outer 0x01
should be inner ECT(0) + outer ECT(1). Based on the description of
__INET_ECN_decapsulate, the final decapsulate value should be
ECT(1). So fix the test expect value to 0x01.

Before the fix:
TEST: VXLAN: ECN decap: 01/02->0x02                                 [FAIL]
        Expected to capture 10 packets, got 0.

After the fix:
TEST: VXLAN: ECN decap: 01/02->0x01                                 [ OK ]

Fixes: a0b61f3d8ebf ("selftests: forwarding: vxlan_bridge_1d: Add an ECN decap test")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index ce6bea9675c0..0ccb1dda099a 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -658,7 +658,7 @@ test_ecn_decap()
 	# In accordance with INET_ECN_decapsulate()
 	__test_ecn_decap 00 00 0x00
 	__test_ecn_decap 01 01 0x01
-	__test_ecn_decap 02 01 0x02
+	__test_ecn_decap 02 01 0x01
 	__test_ecn_decap 01 03 0x03
 	__test_ecn_decap 02 03 0x03
 	test_ecn_decap_error

From 901ee1d750f29a335423eeb9463c3ca461ca18c2 Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Fri, 19 Mar 2021 12:25:54 +0100
Subject: [PATCH 1081/1820] libbpf: Fix BTF dump of pointer-to-array-of-struct
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The vmlinux.h generated from BTF is invalid when building
drivers/phy/ti/phy-gmii-sel.c with clang:

vmlinux.h:61702:27: error: array type has incomplete element type ‘struct reg_field’
61702 |  const struct reg_field (*regfields)[3];
      |                           ^~~~~~~~~

bpftool generates a forward declaration for this struct regfield, which
compilers aren't happy about. Here's a simplified reproducer:

	struct inner {
		int val;
	};
	struct outer {
		struct inner (*ptr_to_array)[2];
	} A;

After build with clang -> bpftool btf dump c -> clang/gcc:
./def-clang.h:11:23: error: array has incomplete element type 'struct inner'
        struct inner (*ptr_to_array)[2];

Member ptr_to_array of struct outer is a pointer to an array of struct
inner. In the DWARF generated by clang, struct outer appears before
struct inner, so when converting BTF of struct outer into C, bpftool
issues a forward declaration to struct inner. With GCC the DWARF info is
reversed so struct inner gets fully defined.

That forward declaration is not sufficient when compilers handle an
array of the struct, even when it's only used through a pointer. Note
that we can trigger the same issue with an intermediate typedef:

	struct inner {
	        int val;
	};
	typedef struct inner inner2_t[2];
	struct outer {
	        inner2_t *ptr_to_array;
	} A;

Becomes:

	struct inner;
	typedef struct inner inner2_t[2];

And causes:

./def-clang.h:10:30: error: array has incomplete element type 'struct inner'
	typedef struct inner inner2_t[2];

To fix this, clear through_ptr whenever we encounter an intermediate
array, to make the inner struct part of a strong link and force full
declaration.

Fixes: 351131b51c7a ("libbpf: add btf_dump API for BTF-to-C conversion")
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210319112554.794552-2-jean-philippe@linaro.org
---
 tools/lib/bpf/btf_dump.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 2f9d685bd522..0911aea4cdbe 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -462,7 +462,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 		return err;
 
 	case BTF_KIND_ARRAY:
-		return btf_dump_order_type(d, btf_array(t)->type, through_ptr);
+		return btf_dump_order_type(d, btf_array(t)->type, false);
 
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION: {

From f118aac651d87c1811d2abd940f73c45c16b29d7 Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Fri, 19 Mar 2021 12:25:55 +0100
Subject: [PATCH 1082/1820] selftests/bpf: Add selftest for
 pointer-to-array-of-struct BTF dump

Bpftool used to issue forward declarations for a struct used as part of
a pointer to array, which is invalid. Add a test to check that the
struct is fully defined in this case:

	@@ -134,9 +134,9 @@
	 	};
	 };

	-struct struct_in_array {};
	+struct struct_in_array;

	-struct struct_in_array_typed {};
	+struct struct_in_array_typed;

	 typedef struct struct_in_array_typed struct_in_array_t[2];

	@@ -189,3 +189,7 @@
	 	struct struct_with_embedded_stuff _14;
	 };

	+struct struct_in_array {};
	+
	+struct struct_in_array_typed {};
	+
	...
	#13/1 btf_dump: syntax:FAIL

Suggested-by: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210319112554.794552-3-jean-philippe@linaro.org
---
 .../selftests/bpf/progs/btf_dump_test_case_syntax.c       | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
index 31975c96e2c9..3ac0c9afc35a 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
@@ -174,6 +174,12 @@ struct struct_in_struct {
 	};
 };
 
+struct struct_in_array {};
+
+struct struct_in_array_typed {};
+
+typedef struct struct_in_array_typed struct_in_array_t[2];
+
 struct struct_with_embedded_stuff {
 	int a;
 	struct {
@@ -203,6 +209,8 @@ struct struct_with_embedded_stuff {
 	} r[5];
 	struct struct_in_struct s[10];
 	int t[11];
+	struct struct_in_array (*u)[2];
+	struct_in_array_t *v;
 };
 
 struct root_struct {

From f60a85cad677c4f9bb4cadd764f1d106c38c7cf8 Mon Sep 17 00:00:00 2001
From: Zqiang <qiang.zhang@windriver.com>
Date: Wed, 17 Mar 2021 11:09:15 +0800
Subject: [PATCH 1083/1820] bpf: Fix umd memory leak in copy_process()

The syzbot reported a memleak as follows:

BUG: memory leak
unreferenced object 0xffff888101b41d00 (size 120):
  comm "kworker/u4:0", pid 8, jiffies 4294944270 (age 12.780s)
  backtrace:
    [<ffffffff8125dc56>] alloc_pid+0x66/0x560
    [<ffffffff81226405>] copy_process+0x1465/0x25e0
    [<ffffffff81227943>] kernel_clone+0xf3/0x670
    [<ffffffff812281a1>] kernel_thread+0x61/0x80
    [<ffffffff81253464>] call_usermodehelper_exec_work
    [<ffffffff81253464>] call_usermodehelper_exec_work+0xc4/0x120
    [<ffffffff812591c9>] process_one_work+0x2c9/0x600
    [<ffffffff81259ab9>] worker_thread+0x59/0x5d0
    [<ffffffff812611c8>] kthread+0x178/0x1b0
    [<ffffffff8100227f>] ret_from_fork+0x1f/0x30

unreferenced object 0xffff888110ef5c00 (size 232):
  comm "kworker/u4:0", pid 8414, jiffies 4294944270 (age 12.780s)
  backtrace:
    [<ffffffff8154a0cf>] kmem_cache_zalloc
    [<ffffffff8154a0cf>] __alloc_file+0x1f/0xf0
    [<ffffffff8154a809>] alloc_empty_file+0x69/0x120
    [<ffffffff8154a8f3>] alloc_file+0x33/0x1b0
    [<ffffffff8154ab22>] alloc_file_pseudo+0xb2/0x140
    [<ffffffff81559218>] create_pipe_files+0x138/0x2e0
    [<ffffffff8126c793>] umd_setup+0x33/0x220
    [<ffffffff81253574>] call_usermodehelper_exec_async+0xb4/0x1b0
    [<ffffffff8100227f>] ret_from_fork+0x1f/0x30

After the UMD process exits, the pipe_to_umh/pipe_from_umh and
tgid need to be released.

Fixes: d71fa5c9763c ("bpf: Add kernel module with user mode driver that populates bpffs.")
Reported-by: syzbot+44908bb56d2bfe56b28e@syzkaller.appspotmail.com
Signed-off-by: Zqiang <qiang.zhang@windriver.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210317030915.2865-1-qiang.zhang@windriver.com
---
 include/linux/usermode_driver.h       |  1 +
 kernel/bpf/preload/bpf_preload_kern.c | 19 +++++++++++++++----
 kernel/usermode_driver.c              | 21 +++++++++++++++------
 3 files changed, 31 insertions(+), 10 deletions(-)

diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h
index 073a9e0ec07d..ad970416260d 100644
--- a/include/linux/usermode_driver.h
+++ b/include/linux/usermode_driver.h
@@ -14,5 +14,6 @@ struct umd_info {
 int umd_load_blob(struct umd_info *info, const void *data, size_t len);
 int umd_unload_blob(struct umd_info *info);
 int fork_usermode_driver(struct umd_info *info);
+void umd_cleanup_helper(struct umd_info *info);
 
 #endif /* __LINUX_USERMODE_DRIVER_H__ */
diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c
index 79c5772465f1..53736e52c1df 100644
--- a/kernel/bpf/preload/bpf_preload_kern.c
+++ b/kernel/bpf/preload/bpf_preload_kern.c
@@ -60,9 +60,12 @@ static int finish(void)
 			 &magic, sizeof(magic), &pos);
 	if (n != sizeof(magic))
 		return -EPIPE;
+
 	tgid = umd_ops.info.tgid;
-	wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
-	umd_ops.info.tgid = NULL;
+	if (tgid) {
+		wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
+		umd_cleanup_helper(&umd_ops.info);
+	}
 	return 0;
 }
 
@@ -80,10 +83,18 @@ static int __init load_umd(void)
 
 static void __exit fini_umd(void)
 {
+	struct pid *tgid;
+
 	bpf_preload_ops = NULL;
+
 	/* kill UMD in case it's still there due to earlier error */
-	kill_pid(umd_ops.info.tgid, SIGKILL, 1);
-	umd_ops.info.tgid = NULL;
+	tgid = umd_ops.info.tgid;
+	if (tgid) {
+		kill_pid(tgid, SIGKILL, 1);
+
+		wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
+		umd_cleanup_helper(&umd_ops.info);
+	}
 	umd_unload_blob(&umd_ops.info);
 }
 late_initcall(load_umd);
diff --git a/kernel/usermode_driver.c b/kernel/usermode_driver.c
index 0b35212ffc3d..bb7bb3b478ab 100644
--- a/kernel/usermode_driver.c
+++ b/kernel/usermode_driver.c
@@ -139,14 +139,23 @@ static void umd_cleanup(struct subprocess_info *info)
 	struct umd_info *umd_info = info->data;
 
 	/* cleanup if umh_setup() was successful but exec failed */
-	if (info->retval) {
-		fput(umd_info->pipe_to_umh);
-		fput(umd_info->pipe_from_umh);
-		put_pid(umd_info->tgid);
-		umd_info->tgid = NULL;
-	}
+	if (info->retval)
+		umd_cleanup_helper(umd_info);
 }
 
+/**
+ * umd_cleanup_helper - release the resources which were allocated in umd_setup
+ * @info: information about usermode driver
+ */
+void umd_cleanup_helper(struct umd_info *info)
+{
+	fput(info->pipe_to_umh);
+	fput(info->pipe_from_umh);
+	put_pid(info->tgid);
+	info->tgid = NULL;
+}
+EXPORT_SYMBOL_GPL(umd_cleanup_helper);
+
 /**
  * fork_usermode_driver - fork a usermode driver
  * @info: information about usermode driver (shouldn't be NULL)

From dd926880da8dbbe409e709c1d3c1620729a94732 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Fri, 12 Mar 2021 10:20:33 +0100
Subject: [PATCH 1084/1820] x86/apic/of: Fix CPU devicetree-node lookups

Architectures that describe the CPU topology in devicetree and do not have
an identity mapping between physical and logical CPU ids must override the
default implementation of arch_match_cpu_phys_id().

Failing to do so breaks CPU devicetree-node lookups using of_get_cpu_node()
and of_cpu_device_node_get() which several drivers rely on. It also causes
the CPU struct devices exported through sysfs to point to the wrong
devicetree nodes.

On x86, CPUs are described in devicetree using their APIC ids and those
do not generally coincide with the logical ids, even if CPU0 typically
uses APIC id 0.

Add the missing implementation of arch_match_cpu_phys_id() so that CPU-node
lookups work also with SMP.

Apart from fixing the broken sysfs devicetree-node links this likely does
not affect current users of mainline kernels on x86.

Fixes: 4e07db9c8db8 ("x86/devicetree: Use CPU description from Device Tree")
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20210312092033.26317-1-johan@kernel.org
---
 arch/x86/kernel/apic/apic.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index bda4f2a36868..4f26700f314d 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2342,6 +2342,11 @@ static int cpuid_to_apicid[] = {
 	[0 ... NR_CPUS - 1] = -1,
 };
 
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return phys_id == cpuid_to_apicid[cpu];
+}
+
 #ifdef CONFIG_SMP
 /**
  * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread

From b9082970478009b778aa9b22d5561eef35b53b63 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Fri, 19 Mar 2021 17:00:01 -0700
Subject: [PATCH 1085/1820] bpf: Use NOP_ATOMIC5 instead of emit_nops(&prog, 5)
 for BPF_TRAMP_F_CALL_ORIG

__bpf_arch_text_poke does rewrite only for atomic nop5, emit_nops(xxx, 5)
emits non-atomic one which breaks fentry/fexit with k8 atomics:

P6_NOP5 == P6_NOP5_ATOMIC (0f1f440000 == 0f1f440000)
K8_NOP5 != K8_NOP5_ATOMIC (6666906690 != 6666666690)

Can be reproduced by doing "ideal_nops = k8_nops" in "arch_init_ideal_nops()
and running fexit_bpf2bpf selftest.

Fixes: e21aa341785c ("bpf: Fix fexit trampoline.")
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210320000001.915366-1-sdf@google.com
---
 arch/x86/net/bpf_jit_comp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 72b5a57e9e31..b35fc8023884 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2012,7 +2012,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		/* remember return value in a stack for bpf prog to access */
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 		im->ip_after_call = prog;
-		emit_nops(&prog, 5);
+		memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
+		prog += X86_PATCH_SIZE;
 	}
 
 	if (fmod_ret->nr_progs) {

From b5f020f82a8e41201c6ede20fa00389d6980b223 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Fri, 19 Mar 2021 11:06:19 +0100
Subject: [PATCH 1086/1820] can: isotp: tx-path: zero initialize outgoing CAN
 frames

Commit d4eb538e1f48 ("can: isotp: TX-path: ensure that CAN frame flags are
initialized") ensured the TX flags to be properly set for outgoing CAN
frames.

In fact the root cause of the issue results from a missing initialization
of outgoing CAN frames created by isotp. This is no problem on the CAN bus
as the CAN driver only picks the correctly defined content from the struct
can(fd)_frame. But when the outgoing frames are monitored (e.g. with
candump) we potentially leak some bytes in the unused content of
struct can(fd)_frame.

Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol")
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://lore.kernel.org/r/20210319100619.10858-1-socketcan@hartkopp.net
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/isotp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/can/isotp.c b/net/can/isotp.c
index 430976485d95..15ea1234d457 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -196,7 +196,7 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus)
 	nskb->dev = dev;
 	can_skb_set_owner(nskb, sk);
 	ncf = (struct canfd_frame *)nskb->data;
-	skb_put(nskb, so->ll.mtu);
+	skb_put_zero(nskb, so->ll.mtu);
 
 	/* create & send flow control reply */
 	ncf->can_id = so->txid;
@@ -779,7 +779,7 @@ isotp_tx_burst:
 		can_skb_prv(skb)->skbcnt = 0;
 
 		cf = (struct canfd_frame *)skb->data;
-		skb_put(skb, so->ll.mtu);
+		skb_put_zero(skb, so->ll.mtu);
 
 		/* create consecutive frame */
 		isotp_fill_dataframe(cf, so, ae, 0);
@@ -895,7 +895,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	so->tx.idx = 0;
 
 	cf = (struct canfd_frame *)skb->data;
-	skb_put(skb, so->ll.mtu);
+	skb_put_zero(skb, so->ll.mtu);
 
 	/* check for single frame transmission depending on TX_DL */
 	if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) {

From 5d7047ed6b7214fbabc16d8712a822e256b1aa44 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Sat, 20 Mar 2021 20:21:54 +0100
Subject: [PATCH 1087/1820] can: peak_usb: Revert "can: peak_usb: add forgotten
 supported devices"

In commit 6417f03132a6 ("module: remove never implemented
MODULE_SUPPORTED_DEVICE") the MODULE_SUPPORTED_DEVICE macro was
removed from the kerne entirely. Shortly before this patch was applied
mainline the commit 59ec7b89ed3e ("can: peak_usb: add forgotten
supported devices") was added to net/master. As this would result in a
merge conflict, let's revert this patch.

Fixes: 59ec7b89ed3e ("can: peak_usb: add forgotten supported devices")
Link: https://lore.kernel.org/r/20210320192649.341832-1-mkl@pengutronix.de
Suggested-by: Leon Romanovsky <leon@kernel.org>
Cc: Stephane Grosjean <s.grosjean@peak-system.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/peak_usb/pcan_usb_fd.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index f1d018218c93..f347ecc79aef 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -18,8 +18,6 @@
 
 MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB FD adapter");
 MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro FD adapter");
-MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-Chip USB");
-MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB X6 adapter");
 
 #define PCAN_USBPROFD_CHANNEL_COUNT	2
 #define PCAN_USBFD_CHANNEL_COUNT	1

From 81e2073c175b887398e5bca6c004efa89983f58d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 17 Mar 2021 15:38:52 +0100
Subject: [PATCH 1088/1820] genirq: Disable interrupts for force threaded
 handlers

With interrupt force threading all device interrupt handlers are invoked
from kernel threads. Contrary to hard interrupt context the invocation only
disables bottom halfs, but not interrupts. This was an oversight back then
because any code like this will have an issue:

thread(irq_A)
  irq_handler(A)
    spin_lock(&foo->lock);

interrupt(irq_B)
  irq_handler(B)
    spin_lock(&foo->lock);

This has been triggered with networking (NAPI vs. hrtimers) and console
drivers where printk() happens from an interrupt which interrupted the
force threaded handler.

Now people noticed and started to change the spin_lock() in the handler to
spin_lock_irqsave() which affects performance or add IRQF_NOTHREAD to the
interrupt request which in turn breaks RT.

Fix the root cause and not the symptom and disable interrupts before
invoking the force threaded handler which preserves the regular semantics
and the usefulness of the interrupt force threading as a general debugging
tool.

For not RT this is not changing much, except that during the execution of
the threaded handler interrupts are delayed until the handler
returns. Vs. scheduling and softirq processing there is no difference.

For RT kernels there is no issue.

Fixes: 8d32a307e4fa ("genirq: Provide forced interrupt threading")
Reported-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Johan Hovold <johan@kernel.org>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20210317143859.513307808@linutronix.de
---
 kernel/irq/manage.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index dec3f73e8db9..21ea370fccda 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1142,11 +1142,15 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
 	irqreturn_t ret;
 
 	local_bh_disable();
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_disable();
 	ret = action->thread_fn(action->irq, action->dev_id);
 	if (ret == IRQ_HANDLED)
 		atomic_inc(&desc->threads_handled);
 
 	irq_finalize_oneshot(desc, action);
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_enable();
 	local_bh_enable();
 	return ret;
 }

From b4afd4b90a7cfe54c7cd9db49e3c36d552325eac Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@linaro.org>
Date: Sat, 20 Mar 2021 09:17:28 -0500
Subject: [PATCH 1089/1820] net: ipa: fix init header command validation

We use ipa_cmd_header_valid() to ensure certain values we will
program into hardware are within range, well in advance of when we
actually program them.  This way we avoid having to check for errors
when we actually program the hardware.

Unfortunately the dev_err() call for a bad offset value does not
supply the arguments to match the format specifiers properly.
Fix this.

There was also supposed to be a check to ensure the size to be
programmed fits in the field that holds it.  Add this missing check.

Rearrange the way we ensure the header table fits in overall IPA
memory range.

Finally, update ipa_cmd_table_valid() so the format of messages
printed for errors matches what's done in ipa_cmd_header_valid().

Signed-off-by: Alex Elder <elder@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipa/ipa_cmd.c | 50 ++++++++++++++++++++++++++-------------
 1 file changed, 33 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c
index 35e35852c25c..d73b03a80ef8 100644
--- a/drivers/net/ipa/ipa_cmd.c
+++ b/drivers/net/ipa/ipa_cmd.c
@@ -175,21 +175,23 @@ bool ipa_cmd_table_valid(struct ipa *ipa, const struct ipa_mem *mem,
 			    : field_max(IP_FLTRT_FLAGS_NHASH_ADDR_FMASK);
 	if (mem->offset > offset_max ||
 	    ipa->mem_offset > offset_max - mem->offset) {
-		dev_err(dev, "IPv%c %s%s table region offset too large "
-			      "(0x%04x + 0x%04x > 0x%04x)\n",
-			      ipv6 ? '6' : '4', hashed ? "hashed " : "",
-			      route ? "route" : "filter",
-			      ipa->mem_offset, mem->offset, offset_max);
+		dev_err(dev, "IPv%c %s%s table region offset too large\n",
+			ipv6 ? '6' : '4', hashed ? "hashed " : "",
+			route ? "route" : "filter");
+		dev_err(dev, "    (0x%04x + 0x%04x > 0x%04x)\n",
+			ipa->mem_offset, mem->offset, offset_max);
+
 		return false;
 	}
 
 	if (mem->offset > ipa->mem_size ||
 	    mem->size > ipa->mem_size - mem->offset) {
-		dev_err(dev, "IPv%c %s%s table region out of range "
-			      "(0x%04x + 0x%04x > 0x%04x)\n",
-			      ipv6 ? '6' : '4', hashed ? "hashed " : "",
-			      route ? "route" : "filter",
-			      mem->offset, mem->size, ipa->mem_size);
+		dev_err(dev, "IPv%c %s%s table region out of range\n",
+			ipv6 ? '6' : '4', hashed ? "hashed " : "",
+			route ? "route" : "filter");
+		dev_err(dev, "    (0x%04x + 0x%04x > 0x%04x)\n",
+			mem->offset, mem->size, ipa->mem_size);
+
 		return false;
 	}
 
@@ -205,22 +207,36 @@ static bool ipa_cmd_header_valid(struct ipa *ipa)
 	u32 size_max;
 	u32 size;
 
+	/* In ipa_cmd_hdr_init_local_add() we record the offset and size
+	 * of the header table memory area.  Make sure the offset and size
+	 * fit in the fields that need to hold them, and that the entire
+	 * range is within the overall IPA memory range.
+	 */
 	offset_max = field_max(HDR_INIT_LOCAL_FLAGS_HDR_ADDR_FMASK);
 	if (mem->offset > offset_max ||
 	    ipa->mem_offset > offset_max - mem->offset) {
-		dev_err(dev, "header table region offset too large "
-			      "(0x%04x + 0x%04x > 0x%04x)\n",
-			      ipa->mem_offset + mem->offset, offset_max);
+		dev_err(dev, "header table region offset too large\n");
+		dev_err(dev, "    (0x%04x + 0x%04x > 0x%04x)\n",
+			ipa->mem_offset, mem->offset, offset_max);
+
 		return false;
 	}
 
 	size_max = field_max(HDR_INIT_LOCAL_FLAGS_TABLE_SIZE_FMASK);
 	size = ipa->mem[IPA_MEM_MODEM_HEADER].size;
 	size += ipa->mem[IPA_MEM_AP_HEADER].size;
-	if (mem->offset > ipa->mem_size || size > ipa->mem_size - mem->offset) {
-		dev_err(dev, "header table region out of range "
-			      "(0x%04x + 0x%04x > 0x%04x)\n",
-			      mem->offset, size, ipa->mem_size);
+
+	if (size > size_max) {
+		dev_err(dev, "header table region size too large\n");
+		dev_err(dev, "    (0x%04x > 0x%08x)\n", size, size_max);
+
+		return false;
+	}
+	if (size > ipa->mem_size || mem->offset > ipa->mem_size - size) {
+		dev_err(dev, "header table region out of range\n");
+		dev_err(dev, "    (0x%04x + 0x%04x > 0x%04x)\n",
+			mem->offset, size, ipa->mem_size);
+
 		return false;
 	}
 

From f658b90977d2e79822a558e48116e059a7e75dec Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 20 Mar 2021 21:40:08 +0100
Subject: [PATCH 1090/1820] r8169: fix DMA being used after buffer free if WoL
 is enabled

IOMMU errors have been reported if WoL is enabled and interface is
brought down. It turned out that the network chip triggers DMA
transfers after the DMA buffers have been freed. For WoL to work we
need to leave rx enabled, therefore simply stop the chip from being
a DMA busmaster.

Fixes: 567ca57faa62 ("r8169: add rtl8169_up")
Tested-by: Paul Blazejowski <paulb@blazebox.homeip.net>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 7aad0ba53372..581a92fc3292 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4646,6 +4646,9 @@ static void rtl8169_down(struct rtl8169_private *tp)
 
 	rtl8169_update_counters(tp);
 
+	pci_clear_master(tp->pci_dev);
+	rtl_pci_commit(tp);
+
 	rtl8169_cleanup(tp, true);
 
 	rtl_prepare_power_down(tp);
@@ -4653,6 +4656,7 @@ static void rtl8169_down(struct rtl8169_private *tp)
 
 static void rtl8169_up(struct rtl8169_private *tp)
 {
+	pci_set_master(tp->pci_dev);
 	phy_resume(tp->phydev);
 	rtl8169_init_phy(tp);
 	napi_enable(&tp->napi);
@@ -5307,8 +5311,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	rtl_hw_reset(tp);
 
-	pci_set_master(pdev);
-
 	rc = rtl_alloc_irq(tp);
 	if (rc < 0) {
 		dev_err(&pdev->dev, "Can't allocate interrupt\n");

From 87d77e59d1ebc31850697341ab15ca013004b81b Mon Sep 17 00:00:00 2001
From: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Date: Sun, 21 Mar 2021 02:37:03 +0530
Subject: [PATCH 1091/1820] docs: networking: Fix a typo

s/subsytem/subsystem/

Signed-off-by: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/xfrm_device.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/networking/xfrm_device.rst b/Documentation/networking/xfrm_device.rst
index da1073acda96..01391dfd37d9 100644
--- a/Documentation/networking/xfrm_device.rst
+++ b/Documentation/networking/xfrm_device.rst
@@ -50,7 +50,7 @@ Callbacks to implement
 
 The NIC driver offering ipsec offload will need to implement these
 callbacks to make the offload available to the network stack's
-XFRM subsytem.  Additionally, the feature bits NETIF_F_HW_ESP and
+XFRM subsystem.  Additionally, the feature bits NETIF_F_HW_ESP and
 NETIF_F_HW_ESP_TX_CSUM will signal the availability of the offload.
 
 

From b7ff91fd030dc9d72ed91b1aab36e445a003af4f Mon Sep 17 00:00:00 2001
From: "zhangyi (F)" <yi.zhang@huawei.com>
Date: Wed, 3 Mar 2021 21:17:02 +0800
Subject: [PATCH 1092/1820] ext4: find old entry again if failed to rename
 whiteout

If we failed to add new entry on rename whiteout, we cannot reset the
old->de entry directly, because the old->de could have moved from under
us during make indexed dir. So find the old entry again before reset is
needed, otherwise it may corrupt the filesystem as below.

  /dev/sda: Entry '00000001' in ??? (12) has deleted/unused inode 15. CLEARED.
  /dev/sda: Unattached inode 75
  /dev/sda: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY.

Fixes: 6b4b8e6b4ad ("ext4: fix bug for rename with RENAME_WHITEOUT")
Cc: stable@vger.kernel.org
Signed-off-by: zhangyi (F) <yi.zhang@huawei.com>
Link: https://lore.kernel.org/r/20210303131703.330415-1-yi.zhang@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/namei.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 686bf982c84e..4aae59d55288 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3613,6 +3613,31 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
 	return retval;
 }
 
+static void ext4_resetent(handle_t *handle, struct ext4_renament *ent,
+			  unsigned ino, unsigned file_type)
+{
+	struct ext4_renament old = *ent;
+	int retval = 0;
+
+	/*
+	 * old->de could have moved from under us during make indexed dir,
+	 * so the old->de may no longer valid and need to find it again
+	 * before reset old inode info.
+	 */
+	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+	if (IS_ERR(old.bh))
+		retval = PTR_ERR(old.bh);
+	if (!old.bh)
+		retval = -ENOENT;
+	if (retval) {
+		ext4_std_error(old.dir->i_sb, retval);
+		return;
+	}
+
+	ext4_setent(handle, &old, ino, file_type);
+	brelse(old.bh);
+}
+
 static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
 				  const struct qstr *d_name)
 {
@@ -3937,8 +3962,8 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 end_rename:
 	if (whiteout) {
 		if (retval) {
-			ext4_setent(handle, &old,
-				old.inode->i_ino, old_file_type);
+			ext4_resetent(handle, &old,
+				      old.inode->i_ino, old_file_type);
 			drop_nlink(whiteout);
 		}
 		unlock_new_inode(whiteout);

From 5dccdc5a1916d4266edd251f20bbbb113a5c495f Mon Sep 17 00:00:00 2001
From: "zhangyi (F)" <yi.zhang@huawei.com>
Date: Wed, 3 Mar 2021 21:17:03 +0800
Subject: [PATCH 1093/1820] ext4: do not iput inode under running transaction
 in ext4_rename()

In ext4_rename(), when RENAME_WHITEOUT failed to add new entry into
directory, it ends up dropping new created whiteout inode under the
running transaction. After commit <9b88f9fb0d2> ("ext4: Do not iput inode
under running transaction"), we follow the assumptions that evict() does
not get called from a transaction context but in ext4_rename() it breaks
this suggestion. Although it's not a real problem, better to obey it, so
this patch add inode to orphan list and stop transaction before final
iput().

Signed-off-by: zhangyi (F) <yi.zhang@huawei.com>
Link: https://lore.kernel.org/r/20210303131703.330415-2-yi.zhang@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/namei.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 4aae59d55288..1fe8370dbf0b 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3799,14 +3799,14 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 	 */
 	retval = -ENOENT;
 	if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino)
-		goto end_rename;
+		goto release_bh;
 
 	new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
 				 &new.de, &new.inlined);
 	if (IS_ERR(new.bh)) {
 		retval = PTR_ERR(new.bh);
 		new.bh = NULL;
-		goto end_rename;
+		goto release_bh;
 	}
 	if (new.bh) {
 		if (!new.inode) {
@@ -3823,15 +3823,13 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 		handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits);
 		if (IS_ERR(handle)) {
 			retval = PTR_ERR(handle);
-			handle = NULL;
-			goto end_rename;
+			goto release_bh;
 		}
 	} else {
 		whiteout = ext4_whiteout_for_rename(mnt_userns, &old, credits, &handle);
 		if (IS_ERR(whiteout)) {
 			retval = PTR_ERR(whiteout);
-			whiteout = NULL;
-			goto end_rename;
+			goto release_bh;
 		}
 	}
 
@@ -3965,16 +3963,18 @@ end_rename:
 			ext4_resetent(handle, &old,
 				      old.inode->i_ino, old_file_type);
 			drop_nlink(whiteout);
+			ext4_orphan_add(handle, whiteout);
 		}
 		unlock_new_inode(whiteout);
+		ext4_journal_stop(handle);
 		iput(whiteout);
-
+	} else {
+		ext4_journal_stop(handle);
 	}
+release_bh:
 	brelse(old.dir_bh);
 	brelse(old.bh);
 	brelse(new.bh);
-	if (handle)
-		ext4_journal_stop(handle);
 	return retval;
 }
 

From 6b22489911b726eebbf169caee52fea52013fbdd Mon Sep 17 00:00:00 2001
From: "zhangyi (F)" <yi.zhang@huawei.com>
Date: Fri, 5 Mar 2021 20:05:08 +0800
Subject: [PATCH 1094/1820] ext4: do not try to set xattr into ea_inode if
 value is empty

Syzbot report a warning that ext4 may create an empty ea_inode if set
an empty extent attribute to a file on the file system which is no free
blocks left.

  WARNING: CPU: 6 PID: 10667 at fs/ext4/xattr.c:1640 ext4_xattr_set_entry+0x10f8/0x1114 fs/ext4/xattr.c:1640
  ...
  Call trace:
   ext4_xattr_set_entry+0x10f8/0x1114 fs/ext4/xattr.c:1640
   ext4_xattr_block_set+0x1d0/0x1b1c fs/ext4/xattr.c:1942
   ext4_xattr_set_handle+0x8a0/0xf1c fs/ext4/xattr.c:2390
   ext4_xattr_set+0x120/0x1f0 fs/ext4/xattr.c:2491
   ext4_xattr_trusted_set+0x48/0x5c fs/ext4/xattr_trusted.c:37
   __vfs_setxattr+0x208/0x23c fs/xattr.c:177
  ...

Now, ext4 try to store extent attribute into an external inode if
ext4_xattr_block_set() return -ENOSPC, but for the case of store an
empty extent attribute, store the extent entry into the extent
attribute block is enough. A simple reproduce below.

  fallocate test.img -l 1M
  mkfs.ext4 -F -b 2048 -O ea_inode test.img
  mount test.img /mnt
  dd if=/dev/zero of=/mnt/foo bs=2048 count=500
  setfattr -n "user.test" /mnt/foo

Reported-by: syzbot+98b881fdd8ebf45ab4ae@syzkaller.appspotmail.com
Fixes: 9c6e7853c531 ("ext4: reserve space for xattr entries/names")
Cc: stable@kernel.org
Signed-off-by: zhangyi (F) <yi.zhang@huawei.com>
Link: https://lore.kernel.org/r/20210305120508.298465-1-yi.zhang@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/xattr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 083c95126781..6c1018223c54 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -2404,7 +2404,7 @@ retry_inode:
 				 * external inode if possible.
 				 */
 				if (ext4_has_feature_ea_inode(inode->i_sb) &&
-				    !i.in_inode) {
+				    i.value_len && !i.in_inode) {
 					i.in_inode = 1;
 					goto retry_inode;
 				}

From 7d8bd3c76da1d94b85e6c9b7007e20e980bfcfe6 Mon Sep 17 00:00:00 2001
From: Shijie Luo <luoshijie1@huawei.com>
Date: Fri, 12 Mar 2021 01:50:51 -0500
Subject: [PATCH 1095/1820] ext4: fix potential error in ext4_do_update_inode

If set_large_file = 1 and errors occur in ext4_handle_dirty_metadata(),
the error code will be overridden, go to out_brelse to avoid this
situation.

Signed-off-by: Shijie Luo <luoshijie1@huawei.com>
Link: https://lore.kernel.org/r/20210312065051.36314-1-luoshijie1@huawei.com
Cc: stable@kernel.org
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index a79a9ea58c56..927e47db7f00 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5026,7 +5026,7 @@ static int ext4_do_update_inode(handle_t *handle,
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct buffer_head *bh = iloc->bh;
 	struct super_block *sb = inode->i_sb;
-	int err = 0, rc, block;
+	int err = 0, block;
 	int need_datasync = 0, set_large_file = 0;
 	uid_t i_uid;
 	gid_t i_gid;
@@ -5138,9 +5138,9 @@ static int ext4_do_update_inode(handle_t *handle,
 					      bh->b_data);
 
 	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-	rc = ext4_handle_dirty_metadata(handle, NULL, bh);
-	if (!err)
-		err = rc;
+	err = ext4_handle_dirty_metadata(handle, NULL, bh);
+	if (err)
+		goto out_brelse;
 	ext4_clear_inode_state(inode, EXT4_STATE_NEW);
 	if (set_large_file) {
 		BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");

From 2a4ae3bcdf05b8639406eaa09a2939f3c6dd8e75 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 15 Mar 2021 17:59:06 +0100
Subject: [PATCH 1096/1820] ext4: fix timer use-after-free on failed mount

When filesystem mount fails because of corrupted filesystem we first
cancel the s_err_report timer reminding fs errors every day and only
then we flush s_error_work. However s_error_work may report another fs
error and re-arm timer thus resulting in timer use-after-free. Fix the
problem by first flushing the work and only after that canceling the
s_err_report timer.

Reported-by: syzbot+628472a2aac693ab0fcd@syzkaller.appspotmail.com
Fixes: 2d01ddc86606 ("ext4: save error info to sb through journal if available")
CC: stable@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20210315165906.2175-1-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/super.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index a0a256859662..b9693680463a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5154,8 +5154,8 @@ failed_mount_wq:
 failed_mount3a:
 	ext4_es_unregister_shrinker(sbi);
 failed_mount3:
-	del_timer_sync(&sbi->s_err_report);
 	flush_work(&sbi->s_error_work);
+	del_timer_sync(&sbi->s_err_report);
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2:

From 8210bb29c1b66200cff7b25febcf6e39baf49fbf Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Tue, 16 Mar 2021 15:19:21 -0700
Subject: [PATCH 1097/1820] ext4: fix rename whiteout with fast commit

This patch adds rename whiteout support in fast commits. Note that the
whiteout object that gets created is actually char device. Which
imples, the function ext4_inode_journal_mode(struct inode *inode)
would return "JOURNAL_DATA" for this inode. This has a consequence in
fast commit code that it will make creation of the whiteout object a
fast-commit ineligible behavior and thus will fall back to full
commits. With this patch, this can be observed by running fast commits
with rename whiteout and seeing the stats generated by ext4_fc_stats
tracepoint as follows:

ext4_fc_stats: dev 254:32 fc ineligible reasons:
XATTR:0, CROSS_RENAME:0, JOURNAL_FLAG_CHANGE:0, NO_MEM:0, SWAP_BOOT:0,
RESIZE:0, RENAME_DIR:0, FALLOC_RANGE:0, INODE_JOURNAL_DATA:16;
num_commits:6, ineligible: 6, numblks: 3

So in short, this patch guarantees that in case of rename whiteout, we
fall back to full commits.

Amir mentioned that instead of creating a new whiteout object for
every rename, we can create a static whiteout object with irrelevant
nlink. That will make fast commits to not fall back to full
commit. But until this happens, this patch will ensure correctness by
falling back to full commits.

Fixes: 8016e29f4362 ("ext4: fast commit recovery path")
Cc: stable@kernel.org
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20210316221921.1124955-1-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h        | 2 ++
 fs/ext4/fast_commit.c | 9 +++++++--
 fs/ext4/namei.c       | 3 +++
 3 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index ea3b41579f38..826a56e3bbd2 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2794,6 +2794,8 @@ void __ext4_fc_track_link(handle_t *handle, struct inode *inode,
 	struct dentry *dentry);
 void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry);
 void ext4_fc_track_link(handle_t *handle, struct dentry *dentry);
+void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
+			    struct dentry *dentry);
 void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
 void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
 void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 6c4f19b0a556..7541d0b5d706 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -513,10 +513,10 @@ void ext4_fc_track_link(handle_t *handle, struct dentry *dentry)
 	__ext4_fc_track_link(handle, d_inode(dentry), dentry);
 }
 
-void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
+void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
+			  struct dentry *dentry)
 {
 	struct __track_dentry_update_args args;
-	struct inode *inode = d_inode(dentry);
 	int ret;
 
 	args.dentry = dentry;
@@ -527,6 +527,11 @@ void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
 	trace_ext4_fc_track_create(inode, dentry, ret);
 }
 
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
+{
+	__ext4_fc_track_create(handle, d_inode(dentry), dentry);
+}
+
 /* __track_fn for inode tracking */
 static int __track_inode(struct inode *inode, void *arg, bool update)
 {
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 1fe8370dbf0b..883e2a7cd4ab 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3873,6 +3873,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 		retval = ext4_mark_inode_dirty(handle, whiteout);
 		if (unlikely(retval))
 			goto end_rename;
+
 	}
 	if (!new.bh) {
 		retval = ext4_add_entry(handle, new.dentry, old.inode);
@@ -3946,6 +3947,8 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 			ext4_fc_track_unlink(handle, new.dentry);
 		__ext4_fc_track_link(handle, old.inode, new.dentry);
 		__ext4_fc_track_unlink(handle, old.inode, old.dentry);
+		if (whiteout)
+			__ext4_fc_track_create(handle, whiteout, old.dentry);
 	}
 
 	if (new.inode) {

From 512c15ef05d73a04f1aef18a3bc61a8bb516f323 Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Sun, 17 Jan 2021 00:57:32 -0800
Subject: [PATCH 1098/1820] ext4: stop inode update before return

The inode update should be stopped before returing the error code.

Signed-off-by: Pan Bian <bianpan2016@163.com>
Link: https://lore.kernel.org/r/20210117085732.93788-1-bianpan2016@163.com
Fixes: 8016e29f4362 ("ext4: fast commit recovery path")
Cc: stable@kernel.org
Reviewed-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 927e47db7f00..0948a43f1b3d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5387,8 +5387,10 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 			inode->i_gid = attr->ia_gid;
 		error = ext4_mark_inode_dirty(handle, inode);
 		ext4_journal_stop(handle);
-		if (unlikely(error))
+		if (unlikely(error)) {
+			ext4_fc_stop_update(inode);
 			return error;
+		}
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {

From 64395d950bc476106b39341e42ebfd4d2eb71d2c Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Sun, 21 Mar 2021 00:45:37 -0400
Subject: [PATCH 1099/1820] ext4: initialize ret to suppress smatch warning

Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/extents.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 77c7c8a54da7..77c84d6f1af6 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4382,7 +4382,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 {
 	struct inode *inode = file_inode(file);
 	handle_t *handle;
-	int ret, ret2 = 0, ret3 = 0;
+	int ret = 0, ret2 = 0, ret3 = 0;
 	int retries = 0;
 	int depth = 0;
 	struct ext4_map_blocks map;

From 3a85969e9d912d5dd85362ee37b5f81266e00e77 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Sun, 21 Mar 2021 15:49:13 +0900
Subject: [PATCH 1100/1820] lockdep: Add a missing initialization hint to the
 "INFO: Trying to register non-static key" message

Since this message is printed when dynamically allocated spinlocks (e.g.
kzalloc()) are used without initialization (e.g. spin_lock_init()),
suggest to developers to check whether initialization functions for objects
were called, before making developers wonder what annotation is missing.

[ mingo: Minor tweaks to the message. ]

Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210321064913.4619-1-penguin-kernel@I-love.SAKURA.ne.jp
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/locking/lockdep.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c6d0c1dc6253..c30eb887ca7d 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -930,7 +930,8 @@ static bool assign_lock_key(struct lockdep_map *lock)
 		/* Debug-check: all keys must be persistent! */
 		debug_locks_off();
 		pr_err("INFO: trying to register non-static key.\n");
-		pr_err("the code is fine but needs lockdep annotation.\n");
+		pr_err("The code is fine but needs lockdep annotation, or maybe\n");
+		pr_err("you didn't initialize this object before use?\n");
 		pr_err("turning off the locking correctness validator.\n");
 		dump_stack();
 		return false;

From 5be28c8f85ce99ed2d329d2ad8bdd18ea19473a5 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 19 Mar 2021 19:25:13 -0600
Subject: [PATCH 1101/1820] signal: don't allow sending any signals to
 PF_IO_WORKER threads

They don't take signals individually, and even if they share signals with
the parent task, don't allow them to be delivered through the worker
thread. Linux does allow this kind of behavior for regular threads, but
it's really a compatability thing that we need not care about for the IO
threads.

Reported-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/signal.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/signal.c b/kernel/signal.c
index ba4d1ef39a9e..11cabcf20e7a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -833,6 +833,9 @@ static int check_kill_permission(int sig, struct kernel_siginfo *info,
 
 	if (!valid_signal(sig))
 		return -EINVAL;
+	/* PF_IO_WORKER threads don't take any signals */
+	if (t->flags & PF_IO_WORKER)
+		return -ESRCH;
 
 	if (!si_fromuser(info))
 		return 0;

From 4db4b1a0d1779dc159f7b87feb97030ec0b12597 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sun, 21 Mar 2021 09:37:48 -0600
Subject: [PATCH 1102/1820] signal: don't allow STOP on PF_IO_WORKER threads

Just like we don't allow normal signals to IO threads, don't deliver a
STOP to a task that has PF_IO_WORKER set. The IO threads don't take
signals in general, and have no means of flushing out a stop either.

Longer term, we may want to look into allowing stop of these threads,
as it relates to eg process freezing. For now, this prevents a spin
issue if a SIGSTOP is delivered to the parent task.

Reported-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 kernel/signal.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/signal.c b/kernel/signal.c
index 11cabcf20e7a..f2a1b898da29 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -288,7 +288,8 @@ bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask)
 			JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING));
 	BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK));
 
-	if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING)))
+	if (unlikely(fatal_signal_pending(task) ||
+		     (task->flags & (PF_EXITING | PF_IO_WORKER))))
 		return false;
 
 	if (mask & JOBCTL_STOP_SIGMASK)

From 00ddff431a458bbf143ea7c4c42d022676da1b17 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sun, 21 Mar 2021 07:06:56 -0600
Subject: [PATCH 1103/1820] io-wq: ensure task is running before processing
 task_work

Mark the current task as running if we need to run task_work from the
io-wq threads as part of work handling. If that is the case, then return
as such so that the caller can appropriately loop back and reset if it
was part of a going-to-sleep flush.

Fixes: 3bfe6106693b ("io-wq: fork worker threads from original task")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index e05f996d088f..3dc10bfd8c3b 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -386,13 +386,16 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe)
 	return NULL;
 }
 
-static void io_flush_signals(void)
+static bool io_flush_signals(void)
 {
 	if (unlikely(test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))) {
+		__set_current_state(TASK_RUNNING);
 		if (current->task_works)
 			task_work_run();
 		clear_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL);
+		return true;
 	}
+	return false;
 }
 
 static void io_assign_current_work(struct io_worker *worker,
@@ -499,7 +502,8 @@ loop:
 		}
 		__io_worker_idle(wqe, worker);
 		raw_spin_unlock_irq(&wqe->lock);
-		io_flush_signals();
+		if (io_flush_signals())
+			continue;
 		ret = schedule_timeout(WORKER_IDLE_TIMEOUT);
 		if (try_to_freeze() || ret)
 			continue;

From 0031275d119efe16711cd93519b595e6f9b4b330 Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Sat, 20 Mar 2021 20:33:36 +0100
Subject: [PATCH 1104/1820] io_uring: call req_set_fail_links() on short
 send[msg]()/recv[msg]() with MSG_WAITALL

Without that it's not safe to use them in a linked combination with
others.

Now combinations like IORING_OP_SENDMSG followed by IORING_OP_SPLICE
should be possible.

We already handle short reads and writes for the following opcodes:

- IORING_OP_READV
- IORING_OP_READ_FIXED
- IORING_OP_READ
- IORING_OP_WRITEV
- IORING_OP_WRITE_FIXED
- IORING_OP_WRITE
- IORING_OP_SPLICE
- IORING_OP_TEE

Now we have it for these as well:

- IORING_OP_SENDMSG
- IORING_OP_SEND
- IORING_OP_RECVMSG
- IORING_OP_RECV

For IORING_OP_RECVMSG we also check for the MSG_TRUNC and MSG_CTRUNC
flags in order to call req_set_fail_links().

There might be applications arround depending on the behavior
that even short send[msg]()/recv[msg]() retuns continue an
IOSQE_IO_LINK chain.

It's very unlikely that such applications pass in MSG_WAITALL,
which is only defined in 'man 2 recvmsg', but not in 'man 2 sendmsg'.

It's expected that the low level sock_sendmsg() call just ignores
MSG_WAITALL, as MSG_ZEROCOPY is also ignored without explicitly set
SO_ZEROCOPY.

We also expect the caller to know about the implicit truncation to
MAX_RW_COUNT, which we don't detect.

cc: netdev@vger.kernel.org
Link: https://lore.kernel.org/r/c4e1a4cc0d905314f4d5dc567e65a7b09621aab3.1615908477.git.metze@samba.org
Signed-off-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index ea2d3e120555..543551d70327 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4386,6 +4386,7 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 	struct io_async_msghdr iomsg, *kmsg;
 	struct socket *sock;
 	unsigned flags;
+	int min_ret = 0;
 	int ret;
 
 	sock = sock_from_file(req->file);
@@ -4406,6 +4407,9 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 	else if (issue_flags & IO_URING_F_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 
+	if (flags & MSG_WAITALL)
+		min_ret = iov_iter_count(&kmsg->msg.msg_iter);
+
 	ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
 	if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN)
 		return io_setup_async_msg(req, kmsg);
@@ -4416,7 +4420,7 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 	if (kmsg->free_iov)
 		kfree(kmsg->free_iov);
 	req->flags &= ~REQ_F_NEED_CLEANUP;
-	if (ret < 0)
+	if (ret < min_ret)
 		req_set_fail_links(req);
 	__io_req_complete(req, issue_flags, ret, 0);
 	return 0;
@@ -4429,6 +4433,7 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags)
 	struct iovec iov;
 	struct socket *sock;
 	unsigned flags;
+	int min_ret = 0;
 	int ret;
 
 	sock = sock_from_file(req->file);
@@ -4450,6 +4455,9 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags)
 	else if (issue_flags & IO_URING_F_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 
+	if (flags & MSG_WAITALL)
+		min_ret = iov_iter_count(&msg.msg_iter);
+
 	msg.msg_flags = flags;
 	ret = sock_sendmsg(sock, &msg);
 	if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN)
@@ -4457,7 +4465,7 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags)
 	if (ret == -ERESTARTSYS)
 		ret = -EINTR;
 
-	if (ret < 0)
+	if (ret < min_ret)
 		req_set_fail_links(req);
 	__io_req_complete(req, issue_flags, ret, 0);
 	return 0;
@@ -4609,6 +4617,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	struct socket *sock;
 	struct io_buffer *kbuf;
 	unsigned flags;
+	int min_ret = 0;
 	int ret, cflags = 0;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
 
@@ -4640,6 +4649,9 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	else if (force_nonblock)
 		flags |= MSG_DONTWAIT;
 
+	if (flags & MSG_WAITALL)
+		min_ret = iov_iter_count(&kmsg->msg.msg_iter);
+
 	ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg,
 					kmsg->uaddr, flags);
 	if (force_nonblock && ret == -EAGAIN)
@@ -4653,7 +4665,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	if (kmsg->free_iov)
 		kfree(kmsg->free_iov);
 	req->flags &= ~REQ_F_NEED_CLEANUP;
-	if (ret < 0)
+	if (ret < min_ret || ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))))
 		req_set_fail_links(req);
 	__io_req_complete(req, issue_flags, ret, cflags);
 	return 0;
@@ -4668,6 +4680,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	struct socket *sock;
 	struct iovec iov;
 	unsigned flags;
+	int min_ret = 0;
 	int ret, cflags = 0;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
 
@@ -4699,6 +4712,9 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	else if (force_nonblock)
 		flags |= MSG_DONTWAIT;
 
+	if (flags & MSG_WAITALL)
+		min_ret = iov_iter_count(&msg.msg_iter);
+
 	ret = sock_recvmsg(sock, &msg, flags);
 	if (force_nonblock && ret == -EAGAIN)
 		return -EAGAIN;
@@ -4707,7 +4723,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 out_free:
 	if (req->flags & REQ_F_BUFFER_SELECTED)
 		cflags = io_put_recv_kbuf(req);
-	if (ret < 0)
+	if (ret < min_ret || ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))))
 		req_set_fail_links(req);
 	__io_req_complete(req, issue_flags, ret, cflags);
 	return 0;

From 3d677f12ea3a2097a16ded570623567403dea959 Mon Sep 17 00:00:00 2001
From: Esteve Varela Colominas <esteve.varela@gmail.com>
Date: Mon, 15 Mar 2021 20:58:24 +0100
Subject: [PATCH 1105/1820] platform/x86: thinkpad_acpi: Allow the FnLock LED
 to change state

On many recent ThinkPad laptops, there's a new LED next to the ESC key,
that indicates the FnLock status.
When the Fn+ESC combo is pressed, FnLock is toggled, which causes the
Media Key functionality to change, making it so that the media keys
either perform their media key function, or function as an F-key by
default. The Fn key can be used the access the alternate function at any
time.

With the current linux kernel, the LED doens't change state if you press
the Fn+ESC key combo. However, the media key functionality *does*
change. This is annoying, since the LED will stay on if it was on during
bootup, and it makes it hard to keep track what the current state of the
FnLock is.

This patch calls an ACPI function, that gets the current media key
state, when the Fn+ESC key combo is pressed. Through testing it was
discovered that this function causes the LED to update correctly to
reflect the current state when this function is called.

The relevant ACPI calls are the following:
\_SB_.PCI0.LPC0.EC0_.HKEY.GMKS: Get media key state, returns 0x603 if the FnLock mode is enabled, and 0x602 if it's disabled.
\_SB_.PCI0.LPC0.EC0_.HKEY.SMKS: Set media key state, sending a 1 will enable FnLock mode, and a 0 will disable it.

Relevant discussion:
https://bugzilla.kernel.org/show_bug.cgi?id=207841
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1881015

Signed-off-by: Esteve Varela Colominas <esteve.varela@gmail.com>
Link: https://lore.kernel.org/r/20210315195823.23212-1-esteve.varela@gmail.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/thinkpad_acpi.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index f7de90a47e28..8569c1d2a52c 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -4081,13 +4081,19 @@ static bool hotkey_notify_6xxx(const u32 hkey,
 
 	case TP_HKEY_EV_KEY_NUMLOCK:
 	case TP_HKEY_EV_KEY_FN:
-	case TP_HKEY_EV_KEY_FN_ESC:
 		/* key press events, we just ignore them as long as the EC
 		 * is still reporting them in the normal keyboard stream */
 		*send_acpi_ev = false;
 		*ignore_acpi_ev = true;
 		return true;
 
+	case TP_HKEY_EV_KEY_FN_ESC:
+		/* Get the media key status to foce the status LED to update */
+		acpi_evalf(hkey_handle, NULL, "GMKS", "v");
+		*send_acpi_ev = false;
+		*ignore_acpi_ev = true;
+		return true;
+
 	case TP_HKEY_EV_TABLET_CHANGED:
 		tpacpi_input_send_tabletsw();
 		hotkey_tablet_mode_notify_change();

From ec0e8fc416f70645608c146dcf90d264b2ad6e3c Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 21 Mar 2021 12:31:08 +0100
Subject: [PATCH 1106/1820] platform/x86: thinkpad_acpi: Disable DYTC CQL mode
 around switching to balanced mode

Testing has shown that setting /sys/firmware/acpi/platform_profile to
"balanced" when /sys/bus/platform/devices/thinkpad_acpi/dytc_lapmode
reports 1, causes dytc_lapmode to get reset to 0 and then it becomes
stuck at 0 for aprox. 30 minutes even if the laptop is used on a lap.

Disabling CQL (when enabled) before issuing the DYTC_CMD_RESET to get
back to balanced mode and re-enabling it afterwards again, like the
code already does when switching to low-power / performance mode fixes
this.

Fixes: c3bfcd4c6762 ("platform/x86: thinkpad_acpi: Add platform profile support")
Tested-by: Mark Pearson <markpearson@lenovo.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210321113108.7069-1-hdegoede@redhat.com
---
 drivers/platform/x86/thinkpad_acpi.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 8569c1d2a52c..0d9e2ddbf904 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -10187,8 +10187,13 @@ static int dytc_profile_set(struct platform_profile_handler *pprof,
 		return err;
 
 	if (profile == PLATFORM_PROFILE_BALANCED) {
-		/* To get back to balanced mode we just issue a reset command */
-		err = dytc_command(DYTC_CMD_RESET, &output);
+		/*
+		 * To get back to balanced mode we need to issue a reset command.
+		 * Note we still need to disable CQL mode before hand and re-enable
+		 * it afterwards, otherwise dytc_lapmode gets reset to 0 and stays
+		 * stuck at 0 for aprox. 30 minutes.
+		 */
+		err = dytc_cql_command(DYTC_CMD_RESET, &output);
 		if (err)
 			goto unlock;
 	} else {

From d939cd96b9df6dcde1605fab23bbd6307e11f930 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 21 Mar 2021 12:58:55 +0100
Subject: [PATCH 1107/1820] platform/x86: dell-wmi-sysman: Fix crash caused by
 calling kset_unregister twice

On some system the WMI GUIDs used by dell-wmi-sysman are present but there
are no enum type attributes, this causes init_bios_attributes() to return
-ENODEV, after which sysman_init() does a "goto fail_create_group" and then
calls release_attributes_data().

release_attributes_data() calls kset_unregister(wmi_priv.main_dir_kset);
but before this commit it was missing a "wmi_priv.main_dir_kset = NULL;"
statement; and after calling release_attributes_data() the sysman_init()
error handling does this:

        if (wmi_priv.main_dir_kset) {
                kset_unregister(wmi_priv.main_dir_kset);
                wmi_priv.main_dir_kset = NULL;
        }

Which causes a second kset_unregister(wmi_priv.main_dir_kset), leading to
a double-free, which causes a crash.

Add the missing "wmi_priv.main_dir_kset = NULL;" statement to
release_attributes_data() to fix this double-free crash.

Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
Cc: Divya Bharathi <Divya_Bharathi@dell.com>
Cc: Mario Limonciello <mario.limonciello@dell.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210321115901.35072-2-hdegoede@redhat.com
---
 drivers/platform/x86/dell/dell-wmi-sysman/sysman.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
index cb81010ba1a2..c1997db74cca 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
@@ -388,6 +388,7 @@ static void release_attributes_data(void)
 	if (wmi_priv.main_dir_kset) {
 		destroy_attribute_objs(wmi_priv.main_dir_kset);
 		kset_unregister(wmi_priv.main_dir_kset);
+		wmi_priv.main_dir_kset = NULL;
 	}
 	mutex_unlock(&wmi_priv.mutex);
 

From c59ab4cedab70a1a117a2dba3c48bb78e66c55ca Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 21 Mar 2021 12:58:56 +0100
Subject: [PATCH 1108/1820] platform/x86: dell-wmi-sysman: Fix possible NULL
 pointer deref on exit

It is possible for release_attributes_data() to get called when the
main_dir_kset has not been created yet, move the removal of the bios-reset
sysfs attr to under a if (main_dir_kset) check to avoid a NULL pointer
deref.

Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
Cc: Divya Bharathi <Divya_Bharathi@dell.com>
Cc: Mario Limonciello <mario.limonciello@dell.com>
Reported-by: Alexander Naumann <alexandernaumann@gmx.de>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210321115901.35072-3-hdegoede@redhat.com
---
 drivers/platform/x86/dell/dell-wmi-sysman/sysman.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
index c1997db74cca..8b251b2c37a2 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
@@ -225,12 +225,6 @@ static int create_attributes_level_sysfs_files(void)
 	return ret;
 }
 
-static void release_reset_bios_data(void)
-{
-	sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr);
-	sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr);
-}
-
 static ssize_t wmi_sysman_attr_show(struct kobject *kobj, struct attribute *attr,
 				    char *buf)
 {
@@ -373,8 +367,6 @@ static void destroy_attribute_objs(struct kset *kset)
  */
 static void release_attributes_data(void)
 {
-	release_reset_bios_data();
-
 	mutex_lock(&wmi_priv.mutex);
 	exit_enum_attributes();
 	exit_int_attributes();
@@ -386,12 +378,13 @@ static void release_attributes_data(void)
 		wmi_priv.authentication_dir_kset = NULL;
 	}
 	if (wmi_priv.main_dir_kset) {
+		sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr);
+		sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr);
 		destroy_attribute_objs(wmi_priv.main_dir_kset);
 		kset_unregister(wmi_priv.main_dir_kset);
 		wmi_priv.main_dir_kset = NULL;
 	}
 	mutex_unlock(&wmi_priv.mutex);
-
 }
 
 /**

From 2d0c418c91d8c86a1b9fb254dda842ada9919513 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 21 Mar 2021 12:58:57 +0100
Subject: [PATCH 1109/1820] platform/x86: dell-wmi-sysman: Make it safe to call
 exit_foo_attributes() multiple times

During some of the error-exit paths it is possible that
release_attributes_data() will get called multiple times,
which results in exit_foo_attributes() getting called multiple
times.

Make it safe to call exit_foo_attributes() multiple times,
avoiding double-free()s in this case.

Note that release_attributes_data() really should only be called
once during error-exit paths. This will be fixed in a separate patch
and it is good to have the exit_foo_attributes() functions modified
this way regardless.

Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
Cc: Divya Bharathi <Divya_Bharathi@dell.com>
Cc: Mario Limonciello <mario.limonciello@dell.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210321115901.35072-4-hdegoede@redhat.com
---
 drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c    | 3 +++
 drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c     | 3 +++
 drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c | 3 +++
 drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c  | 3 +++
 4 files changed, 12 insertions(+)

diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c
index 80f4b7785c6c..091e48c217ed 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c
@@ -185,5 +185,8 @@ void exit_enum_attributes(void)
 			sysfs_remove_group(wmi_priv.enumeration_data[instance_id].attr_name_kobj,
 								&enumeration_attr_group);
 	}
+	wmi_priv.enumeration_instances_count = 0;
+
 	kfree(wmi_priv.enumeration_data);
+	wmi_priv.enumeration_data = NULL;
 }
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c
index 75aedbb733be..8a49ba6e44f9 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c
@@ -175,5 +175,8 @@ void exit_int_attributes(void)
 			sysfs_remove_group(wmi_priv.integer_data[instance_id].attr_name_kobj,
 								&integer_attr_group);
 	}
+	wmi_priv.integer_instances_count = 0;
+
 	kfree(wmi_priv.integer_data);
+	wmi_priv.integer_data = NULL;
 }
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c
index 3abcd95477c0..834b3e82ad9f 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c
@@ -183,5 +183,8 @@ void exit_po_attributes(void)
 			sysfs_remove_group(wmi_priv.po_data[instance_id].attr_name_kobj,
 								&po_attr_group);
 	}
+	wmi_priv.po_instances_count = 0;
+
 	kfree(wmi_priv.po_data);
+	wmi_priv.po_data = NULL;
 }
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c
index ac75dce88a4c..552537852459 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c
@@ -155,5 +155,8 @@ void exit_str_attributes(void)
 			sysfs_remove_group(wmi_priv.str_data[instance_id].attr_name_kobj,
 								&str_attr_group);
 	}
+	wmi_priv.str_instances_count = 0;
+
 	kfree(wmi_priv.str_data);
+	wmi_priv.str_data = NULL;
 }

From 59bbbeb9c22cc7c55965cd5ea8c16af7f16e61eb Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 21 Mar 2021 12:58:58 +0100
Subject: [PATCH 1110/1820] platform/x86: dell-wmi-sysman: Fix
 release_attributes_data() getting called twice on init_bios_attributes()
 failure

All calls of init_bios_attributes() will result in a
goto fail_create_group if they fail, which calls
release_attributes_data().

So there is no need to call release_attributes_data() from
init_bios_attributes() on failure itself.

Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
Cc: Divya Bharathi <Divya_Bharathi@dell.com>
Cc: Mario Limonciello <mario.limonciello@dell.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210321115901.35072-5-hdegoede@redhat.com
---
 drivers/platform/x86/dell/dell-wmi-sysman/sysman.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
index 8b251b2c37a2..58dc4571f987 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
@@ -491,7 +491,6 @@ nextobj:
 
 err_attr_init:
 	mutex_unlock(&wmi_priv.mutex);
-	release_attributes_data();
 	kfree(obj);
 	return retval;
 }

From 9c90cd869747e3492a9306dcd8123c17502ff1fc Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 21 Mar 2021 12:58:59 +0100
Subject: [PATCH 1111/1820] platform/x86: dell-wmi-sysman: Cleanup
 sysman_init() error-exit handling

Cleanup sysman_init() error-exit handling:

1. There is no need for the fail_reset_bios and fail_authentication_kset
   eror-exit cases, these can be handled by release_attributes_data()

2. Rename all the labels from fail_what_failed, to err_what_to_cleanup
   this is the usual way to name these and avoids the need to rename
   them when extra steps are added.

Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
Cc: Divya Bharathi <Divya_Bharathi@dell.com>
Cc: Mario Limonciello <mario.limonciello@dell.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210321115901.35072-6-hdegoede@redhat.com
---
 .../x86/dell/dell-wmi-sysman/sysman.c         | 45 +++++++------------
 1 file changed, 16 insertions(+), 29 deletions(-)

diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
index 58dc4571f987..99dc2f3bdf49 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
@@ -508,100 +508,87 @@ static int __init sysman_init(void)
 	ret = init_bios_attr_set_interface();
 	if (ret || !wmi_priv.bios_attr_wdev) {
 		pr_debug("failed to initialize set interface\n");
-		goto fail_set_interface;
+		return ret;
 	}
 
 	ret = init_bios_attr_pass_interface();
 	if (ret || !wmi_priv.password_attr_wdev) {
 		pr_debug("failed to initialize pass interface\n");
-		goto fail_pass_interface;
+		goto err_exit_bios_attr_set_interface;
 	}
 
 	ret = class_register(&firmware_attributes_class);
 	if (ret)
-		goto fail_class;
+		goto err_exit_bios_attr_pass_interface;
 
 	wmi_priv.class_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0),
 				  NULL, "%s", DRIVER_NAME);
 	if (IS_ERR(wmi_priv.class_dev)) {
 		ret = PTR_ERR(wmi_priv.class_dev);
-		goto fail_classdev;
+		goto err_unregister_class;
 	}
 
 	wmi_priv.main_dir_kset = kset_create_and_add("attributes", NULL,
 						     &wmi_priv.class_dev->kobj);
 	if (!wmi_priv.main_dir_kset) {
 		ret = -ENOMEM;
-		goto fail_main_kset;
+		goto err_destroy_classdev;
 	}
 
 	wmi_priv.authentication_dir_kset = kset_create_and_add("authentication", NULL,
 								&wmi_priv.class_dev->kobj);
 	if (!wmi_priv.authentication_dir_kset) {
 		ret = -ENOMEM;
-		goto fail_authentication_kset;
+		goto err_release_attributes_data;
 	}
 
 	ret = create_attributes_level_sysfs_files();
 	if (ret) {
 		pr_debug("could not create reset BIOS attribute\n");
-		goto fail_reset_bios;
+		goto err_release_attributes_data;
 	}
 
 	ret = init_bios_attributes(ENUM, DELL_WMI_BIOS_ENUMERATION_ATTRIBUTE_GUID);
 	if (ret) {
 		pr_debug("failed to populate enumeration type attributes\n");
-		goto fail_create_group;
+		goto err_release_attributes_data;
 	}
 
 	ret = init_bios_attributes(INT, DELL_WMI_BIOS_INTEGER_ATTRIBUTE_GUID);
 	if (ret) {
 		pr_debug("failed to populate integer type attributes\n");
-		goto fail_create_group;
+		goto err_release_attributes_data;
 	}
 
 	ret = init_bios_attributes(STR, DELL_WMI_BIOS_STRING_ATTRIBUTE_GUID);
 	if (ret) {
 		pr_debug("failed to populate string type attributes\n");
-		goto fail_create_group;
+		goto err_release_attributes_data;
 	}
 
 	ret = init_bios_attributes(PO, DELL_WMI_BIOS_PASSOBJ_ATTRIBUTE_GUID);
 	if (ret) {
 		pr_debug("failed to populate pass object type attributes\n");
-		goto fail_create_group;
+		goto err_release_attributes_data;
 	}
 
 	return 0;
 
-fail_create_group:
+err_release_attributes_data:
 	release_attributes_data();
 
-fail_reset_bios:
-	if (wmi_priv.authentication_dir_kset) {
-		kset_unregister(wmi_priv.authentication_dir_kset);
-		wmi_priv.authentication_dir_kset = NULL;
-	}
-
-fail_authentication_kset:
-	if (wmi_priv.main_dir_kset) {
-		kset_unregister(wmi_priv.main_dir_kset);
-		wmi_priv.main_dir_kset = NULL;
-	}
-
-fail_main_kset:
+err_destroy_classdev:
 	device_destroy(&firmware_attributes_class, MKDEV(0, 0));
 
-fail_classdev:
+err_unregister_class:
 	class_unregister(&firmware_attributes_class);
 
-fail_class:
+err_exit_bios_attr_pass_interface:
 	exit_bios_attr_pass_interface();
 
-fail_pass_interface:
+err_exit_bios_attr_set_interface:
 	exit_bios_attr_set_interface();
 
-fail_set_interface:
 	return ret;
 }
 

From 32418dd58c957f8fef25b97450d00275967604f1 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 21 Mar 2021 12:59:00 +0100
Subject: [PATCH 1112/1820] platform/x86: dell-wmi-sysman: Make sysman_init()
 return -ENODEV of the interfaces are not found

When either the attributes or the password interface is not found, then
unregister the 2 wmi drivers again and return -ENODEV from sysman_init().

Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
Cc: Divya Bharathi <Divya_Bharathi@dell.com>
Cc: Mario Limonciello <mario.limonciello@dell.com>
Reported-by: Alexander Naumann <alexandernaumann@gmx.de>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210321115901.35072-7-hdegoede@redhat.com
---
 drivers/platform/x86/dell/dell-wmi-sysman/sysman.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
index 99dc2f3bdf49..5dd9b29d939c 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
@@ -506,15 +506,17 @@ static int __init sysman_init(void)
 	}
 
 	ret = init_bios_attr_set_interface();
-	if (ret || !wmi_priv.bios_attr_wdev) {
-		pr_debug("failed to initialize set interface\n");
+	if (ret)
 		return ret;
-	}
 
 	ret = init_bios_attr_pass_interface();
-	if (ret || !wmi_priv.password_attr_wdev) {
-		pr_debug("failed to initialize pass interface\n");
+	if (ret)
 		goto err_exit_bios_attr_set_interface;
+
+	if (!wmi_priv.bios_attr_wdev || !wmi_priv.password_attr_wdev) {
+		pr_debug("failed to find set or pass interface\n");
+		ret = -ENODEV;
+		goto err_exit_bios_attr_pass_interface;
 	}
 
 	ret = class_register(&firmware_attributes_class);

From 35471138a9f7193482a2019e39643f575f8098dc Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 21 Mar 2021 12:59:01 +0100
Subject: [PATCH 1113/1820] platform/x86: dell-wmi-sysman: Cleanup
 create_attributes_level_sysfs_files()

Cleanup create_attributes_level_sysfs_files():

1. There is no need to call sysfs_remove_file() on error, sysman_init()
will already call release_attributes_data() on failure which already does
this.

2. There is no need for the pr_debug() calls sysfs_create_file() should
never fail and if it does it will already complain about the problem
itself.

Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
Cc: Divya Bharathi <Divya_Bharathi@dell.com>
Cc: Mario Limonciello <mario.limonciello@dell.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210321115901.35072-8-hdegoede@redhat.com
---
 .../platform/x86/dell/dell-wmi-sysman/sysman.c   | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
index 5dd9b29d939c..7410ccae650c 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
@@ -210,19 +210,17 @@ static struct kobj_attribute pending_reboot = __ATTR_RO(pending_reboot);
  */
 static int create_attributes_level_sysfs_files(void)
 {
-	int ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr);
+	int ret;
 
-	if (ret) {
-		pr_debug("could not create reset_bios file\n");
+	ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr);
+	if (ret)
 		return ret;
-	}
 
 	ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr);
-	if (ret) {
-		pr_debug("could not create changing_pending_reboot file\n");
-		sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr);
-	}
-	return ret;
+	if (ret)
+		return ret;
+
+	return 0;
 }
 
 static ssize_t wmi_sysman_attr_show(struct kobject *kobj, struct attribute *attr,

From 538d2dd0b9920334e6596977a664e9e7bac73703 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 21 Mar 2021 17:35:13 +0100
Subject: [PATCH 1114/1820] platform/x86: intel-vbtn: Stop reporting SW_DOCK
 events

Stop reporting SW_DOCK events because this breaks suspend-on-lid-close.

SW_DOCK should only be reported for docking stations, but all the DSDTs in
my DSDT collection which use the intel-vbtn code, always seem to use this
for 2-in-1s / convertibles and set SW_DOCK=1 when in laptop-mode (in tandem
with setting SW_TABLET_MODE=0).

This causes userspace to think the laptop is docked to a port-replicator
and to disable suspend-on-lid-close, which is undesirable.

Map the dock events to KEY_IGNORE to avoid this broken SW_DOCK reporting.

Note this may theoretically cause us to stop reporting SW_DOCK on some
device where the 0xCA and 0xCB intel-vbtn events are actually used for
reporting docking to a classic docking-station / port-replicator but
I'm not aware of any such devices.

Also the most important thing is that we only report SW_DOCK when it
reliably reports being docked to a classic docking-station without any
false positives, which clearly is not the case here. If there is a
chance of reporting false positives then it is better to not report
SW_DOCK at all.

Cc: stable@vger.kernel.org
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210321163513.72328-1-hdegoede@redhat.com
---
 drivers/platform/x86/intel-vbtn.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c
index 8a8017f9ca91..3fdf4cbec9ad 100644
--- a/drivers/platform/x86/intel-vbtn.c
+++ b/drivers/platform/x86/intel-vbtn.c
@@ -48,8 +48,16 @@ static const struct key_entry intel_vbtn_keymap[] = {
 };
 
 static const struct key_entry intel_vbtn_switchmap[] = {
-	{ KE_SW,     0xCA, { .sw = { SW_DOCK, 1 } } },		/* Docked */
-	{ KE_SW,     0xCB, { .sw = { SW_DOCK, 0 } } },		/* Undocked */
+	/*
+	 * SW_DOCK should only be reported for docking stations, but DSDTs using the
+	 * intel-vbtn code, always seem to use this for 2-in-1s / convertibles and set
+	 * SW_DOCK=1 when in laptop-mode (in tandem with setting SW_TABLET_MODE=0).
+	 * This causes userspace to think the laptop is docked to a port-replicator
+	 * and to disable suspend-on-lid-close, which is undesirable.
+	 * Map the dock events to KEY_IGNORE to avoid this broken SW_DOCK reporting.
+	 */
+	{ KE_IGNORE, 0xCA, { .sw = { SW_DOCK, 1 } } },		/* Docked */
+	{ KE_IGNORE, 0xCB, { .sw = { SW_DOCK, 0 } } },		/* Undocked */
 	{ KE_SW,     0xCC, { .sw = { SW_TABLET_MODE, 1 } } },	/* Tablet */
 	{ KE_SW,     0xCD, { .sw = { SW_TABLET_MODE, 0 } } },	/* Laptop */
 	{ KE_END }

From 0b8cfa974dfc964e6382c9e25fa6c1bdac6ef499 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sun, 21 Mar 2021 14:16:08 -0600
Subject: [PATCH 1115/1820] io_uring: don't use {test,clear}_tsk_thread_flag()
 for current

Linus correctly points out that this is both unnecessary and generates
much worse code on some archs as going from current to thread_info is
actually backwards - and obviously just wasteful, since the thread_info
is what we care about.

Since io_uring only operates on current for these operations, just use
test_thread_flag() instead. For io-wq, we can further simplify and use
tracehook_notify_signal() to handle the TIF_NOTIFY_SIGNAL work and clear
the flag. The latter isn't an actual bug right now, but it may very well
be in the future if we place other work items under TIF_NOTIFY_SIGNAL.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/io-uring/CAHk-=wgYhNck33YHKZ14mFB5MzTTk8gqXHcfj=RWTAXKwgQJgg@mail.gmail.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c    | 6 ++----
 fs/io_uring.c | 2 +-
 2 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 3dc10bfd8c3b..2dd43bdb9c7b 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -388,11 +388,9 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe)
 
 static bool io_flush_signals(void)
 {
-	if (unlikely(test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))) {
+	if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) {
 		__set_current_state(TASK_RUNNING);
-		if (current->task_works)
-			task_work_run();
-		clear_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL);
+		tracehook_notify_signal();
 		return true;
 	}
 	return false;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 543551d70327..be04bc6b5b99 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6873,7 +6873,7 @@ static int io_run_task_work_sig(void)
 		return 1;
 	if (!signal_pending(current))
 		return 0;
-	if (test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))
+	if (test_thread_flag(TIF_NOTIFY_SIGNAL))
 		return -ERESTARTSYS;
 	return -EINTR;
 }

From 623f279c77811475ac8fd5635cc4e4451aa71291 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Sat, 20 Mar 2021 08:56:02 -0300
Subject: [PATCH 1116/1820] drm/msm: fix shutdown hook in case GPU components
 failed to bind

If GPU components have failed to bind, shutdown callback would fail with
the following backtrace. Add safeguard check to stop that oops from
happening and allow the board to reboot.

[   66.617046] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
[   66.626066] Mem abort info:
[   66.628939]   ESR = 0x96000006
[   66.632088]   EC = 0x25: DABT (current EL), IL = 32 bits
[   66.637542]   SET = 0, FnV = 0
[   66.640688]   EA = 0, S1PTW = 0
[   66.643924] Data abort info:
[   66.646889]   ISV = 0, ISS = 0x00000006
[   66.650832]   CM = 0, WnR = 0
[   66.653890] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000107f81000
[   66.660505] [0000000000000000] pgd=0000000100bb2003, p4d=0000000100bb2003, pud=0000000100897003, pmd=0000000000000000
[   66.671398] Internal error: Oops: 96000006 [#1] PREEMPT SMP
[   66.677115] Modules linked in:
[   66.680261] CPU: 6 PID: 352 Comm: reboot Not tainted 5.11.0-rc2-00309-g79e3faa756b2 #38
[   66.688473] Hardware name: Qualcomm Technologies, Inc. Robotics RB5 (DT)
[   66.695347] pstate: 60400005 (nZCv daif +PAN -UAO -TCO BTYPE=--)
[   66.701507] pc : msm_atomic_commit_tail+0x78/0x4e0
[   66.706437] lr : commit_tail+0xa4/0x184
[   66.710381] sp : ffff8000108f3af0
[   66.713791] x29: ffff8000108f3af0 x28: ffff418c44337000
[   66.719242] x27: 0000000000000000 x26: ffff418c40a24490
[   66.724693] x25: ffffd3a842a4f1a0 x24: 0000000000000008
[   66.730146] x23: ffffd3a84313f030 x22: ffff418c444ce000
[   66.735598] x21: ffff418c408a4980 x20: 0000000000000000
[   66.741049] x19: 0000000000000000 x18: ffff800010710fbc
[   66.746500] x17: 000000000000000c x16: 0000000000000001
[   66.751954] x15: 0000000000010008 x14: 0000000000000068
[   66.757405] x13: 0000000000000001 x12: 0000000000000000
[   66.762855] x11: 0000000000000001 x10: 00000000000009b0
[   66.768306] x9 : ffffd3a843192000 x8 : ffff418c44337000
[   66.773757] x7 : 0000000000000000 x6 : 00000000a401b34e
[   66.779210] x5 : 00ffffffffffffff x4 : 0000000000000000
[   66.784660] x3 : 0000000000000000 x2 : ffff418c444ce000
[   66.790111] x1 : ffffd3a841dce530 x0 : ffff418c444cf000
[   66.795563] Call trace:
[   66.798075]  msm_atomic_commit_tail+0x78/0x4e0
[   66.802633]  commit_tail+0xa4/0x184
[   66.806217]  drm_atomic_helper_commit+0x160/0x390
[   66.811051]  drm_atomic_commit+0x4c/0x60
[   66.815082]  drm_atomic_helper_disable_all+0x1f4/0x210
[   66.820355]  drm_atomic_helper_shutdown+0x80/0x130
[   66.825276]  msm_pdev_shutdown+0x14/0x20
[   66.829303]  platform_shutdown+0x28/0x40
[   66.833330]  device_shutdown+0x158/0x330
[   66.837357]  kernel_restart+0x40/0xa0
[   66.841122]  __do_sys_reboot+0x228/0x250
[   66.845148]  __arm64_sys_reboot+0x28/0x34
[   66.849264]  el0_svc_common.constprop.0+0x74/0x190
[   66.854187]  do_el0_svc+0x24/0x90
[   66.857595]  el0_svc+0x14/0x20
[   66.860739]  el0_sync_handler+0x1a4/0x1b0
[   66.864858]  el0_sync+0x174/0x180
[   66.868269] Code: 1ac020a0 2a000273 eb02007f 54ffff01 (f9400285)
[   66.874525] ---[ end trace 20dedb2a3229fec8 ]---

Fixes: 9d5cbf5fe46e ("drm/msm: add shutdown support for display platform_driver")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/msm_drv.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 94525ac76d4e..fd2ac54caf9f 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1311,6 +1311,10 @@ static int msm_pdev_remove(struct platform_device *pdev)
 static void msm_pdev_shutdown(struct platform_device *pdev)
 {
 	struct drm_device *drm = platform_get_drvdata(pdev);
+	struct msm_drm_private *priv = drm ? drm->dev_private : NULL;
+
+	if (!priv || !priv->kms)
+		return;
 
 	drm_atomic_helper_shutdown(drm);
 }

From a9748134ea4aad989e52a6a91479e0acfd306e5b Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@gmail.com>
Date: Sat, 20 Mar 2021 08:56:03 -0300
Subject: [PATCH 1117/1820] drm/msm: Fix suspend/resume on i.MX5

When putting iMX5 into suspend, the following flow is
observed:

[   70.023427] [<c07755f0>] (msm_atomic_commit_tail) from [<c06e7218>]
(commit_tail+0x9c/0x18c)
[   70.031890] [<c06e7218>] (commit_tail) from [<c0e2920c>]
(drm_atomic_helper_commit+0x1a0/0x1d4)
[   70.040627] [<c0e2920c>] (drm_atomic_helper_commit) from
[<c06e74d4>] (drm_atomic_helper_disable_all+0x1c4/0x1d4)
[   70.050913] [<c06e74d4>] (drm_atomic_helper_disable_all) from
[<c0e2943c>] (drm_atomic_helper_suspend+0xb8/0x170)
[   70.061198] [<c0e2943c>] (drm_atomic_helper_suspend) from
[<c06e84bc>] (drm_mode_config_helper_suspend+0x24/0x58)

In the i.MX5 case, priv->kms is not populated (as i.MX5 does not use any
of the Qualcomm display controllers), causing a NULL pointer
dereference in msm_atomic_commit_tail():

[   24.268964] 8<--- cut here ---
[   24.274602] Unable to handle kernel NULL pointer dereference at
virtual address 00000000
[   24.283434] pgd = (ptrval)
[   24.286387] [00000000] *pgd=ca212831
[   24.290788] Internal error: Oops: 17 [#1] SMP ARM
[   24.295609] Modules linked in:
[   24.298777] CPU: 0 PID: 197 Comm: init Not tainted 5.11.0-rc2-next-20210111 #333
[   24.306276] Hardware name: Freescale i.MX53 (Device Tree Support)
[   24.312442] PC is at msm_atomic_commit_tail+0x54/0xb9c
[   24.317743] LR is at commit_tail+0xa4/0x1b0

Fix the problem by calling drm_mode_config_helper_suspend/resume()
only when priv->kms is available.

Fixes: ca8199f13498 ("drm/msm/dpu: ensure device suspend happens during PM sleep")
Signed-off-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/msm_drv.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index fd2ac54caf9f..a5c6b8c23336 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1072,6 +1072,10 @@ static int __maybe_unused msm_pm_resume(struct device *dev)
 static int __maybe_unused msm_pm_prepare(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL;
+
+	if (!priv || !priv->kms)
+		return 0;
 
 	return drm_mode_config_helper_suspend(ddev);
 }
@@ -1079,6 +1083,10 @@ static int __maybe_unused msm_pm_prepare(struct device *dev)
 static void __maybe_unused msm_pm_complete(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL;
+
+	if (!priv || !priv->kms)
+		return;
 
 	drm_mode_config_helper_resume(ddev);
 }

From 0d02ec6b3136c73c09e7859f0d0e4e2c4c07b49b Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 21 Mar 2021 14:56:43 -0700
Subject: [PATCH 1118/1820] Linux 5.12-rc4

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index a28bb374663d..d4784d181123 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Frozen Wasteland
 
 # *DOCUMENTATION*

From e88add19f68191448427a6e4eb059664650a837f Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Tue, 16 Mar 2021 11:56:29 +0100
Subject: [PATCH 1119/1820] net: xfrm: Localize sequence counter per network
 namespace

A sequence counter write section must be serialized or its internal
state can get corrupted. The "xfrm_state_hash_generation" seqcount is
global, but its write serialization lock (net->xfrm.xfrm_state_lock) is
instantiated per network namespace. The write protection is thus
insufficient.

To provide full protection, localize the sequence counter per network
namespace instead. This should be safe as both the seqcount read and
write sections access data exclusively within the network namespace. It
also lays the foundation for transforming "xfrm_state_hash_generation"
data type from seqcount_t to seqcount_LOCKNAME_t in further commits.

Fixes: b65e3d7be06f ("xfrm: state: add sequence count to detect hash resizes")
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/netns/xfrm.h |  4 +++-
 net/xfrm/xfrm_state.c    | 10 +++++-----
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 59f45b1e9dac..b59d73d529ba 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -72,7 +72,9 @@ struct netns_xfrm {
 #if IS_ENABLED(CONFIG_IPV6)
 	struct dst_ops		xfrm6_dst_ops;
 #endif
-	spinlock_t xfrm_state_lock;
+	spinlock_t		xfrm_state_lock;
+	seqcount_t		xfrm_state_hash_generation;
+
 	spinlock_t xfrm_policy_lock;
 	struct mutex xfrm_cfg_mutex;
 };
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index d01ca1a18418..ffd315cff984 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -44,7 +44,6 @@ static void xfrm_state_gc_task(struct work_struct *work);
  */
 
 static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
-static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation);
 static struct kmem_cache *xfrm_state_cache __ro_after_init;
 
 static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task);
@@ -140,7 +139,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 	}
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
-	write_seqcount_begin(&xfrm_state_hash_generation);
+	write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
 
 	nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
 	odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net);
@@ -156,7 +155,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 	rcu_assign_pointer(net->xfrm.state_byspi, nspi);
 	net->xfrm.state_hmask = nhashmask;
 
-	write_seqcount_end(&xfrm_state_hash_generation);
+	write_seqcount_end(&net->xfrm.xfrm_state_hash_generation);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	osize = (ohashmask + 1) * sizeof(struct hlist_head);
@@ -1063,7 +1062,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 
 	to_put = NULL;
 
-	sequence = read_seqcount_begin(&xfrm_state_hash_generation);
+	sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
 
 	rcu_read_lock();
 	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
@@ -1176,7 +1175,7 @@ out:
 	if (to_put)
 		xfrm_state_put(to_put);
 
-	if (read_seqcount_retry(&xfrm_state_hash_generation, sequence)) {
+	if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) {
 		*err = -EAGAIN;
 		if (x) {
 			xfrm_state_put(x);
@@ -2666,6 +2665,7 @@ int __net_init xfrm_state_init(struct net *net)
 	net->xfrm.state_num = 0;
 	INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize);
 	spin_lock_init(&net->xfrm.xfrm_state_lock);
+	seqcount_init(&net->xfrm.xfrm_state_hash_generation);
 	return 0;
 
 out_byspi:

From bc8e0adff343d992ca76d871e8b5e6cb86e1fad9 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Tue, 16 Mar 2021 11:56:30 +0100
Subject: [PATCH 1120/1820] net: xfrm: Use sequence counter with associated
 spinlock

A sequence counter write section must be serialized or its internal
state can get corrupted. A plain seqcount_t does not contain the
information of which lock must be held to guaranteee write side
serialization.

For xfrm_state_hash_generation, use seqcount_spinlock_t instead of plain
seqcount_t.  This allows to associate the spinlock used for write
serialization with the sequence counter. It thus enables lockdep to
verify that the write serialization lock is indeed held before entering
the sequence counter write section.

If lockdep is disabled, this lock association is compiled out and has
neither storage size nor runtime overhead.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/netns/xfrm.h | 2 +-
 net/xfrm/xfrm_state.c    | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index b59d73d529ba..e816b6a3ef2b 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -73,7 +73,7 @@ struct netns_xfrm {
 	struct dst_ops		xfrm6_dst_ops;
 #endif
 	spinlock_t		xfrm_state_lock;
-	seqcount_t		xfrm_state_hash_generation;
+	seqcount_spinlock_t	xfrm_state_hash_generation;
 
 	spinlock_t xfrm_policy_lock;
 	struct mutex xfrm_cfg_mutex;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index ffd315cff984..4496f7efa220 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2665,7 +2665,8 @@ int __net_init xfrm_state_init(struct net *net)
 	net->xfrm.state_num = 0;
 	INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize);
 	spin_lock_init(&net->xfrm.xfrm_state_lock);
-	seqcount_init(&net->xfrm.xfrm_state_hash_generation);
+	seqcount_spinlock_init(&net->xfrm.xfrm_state_hash_generation,
+			       &net->xfrm.xfrm_state_lock);
 	return 0;
 
 out_byspi:

From 154deab6a3ba47792936edf77f2f13a1cbc4351d Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 19 Mar 2021 15:35:07 +0800
Subject: [PATCH 1121/1820] esp: delete NETIF_F_SCTP_CRC bit from features for
 esp offload

Now in esp4/6_gso_segment(), before calling inner proto .gso_segment,
NETIF_F_CSUM_MASK bits are deleted, as HW won't be able to do the
csum for inner proto due to the packet encrypted already.

So the UDP/TCP packet has to do the checksum on its own .gso_segment.
But SCTP is using CRC checksum, and for that NETIF_F_SCTP_CRC should
be deleted to make SCTP do the csum in own .gso_segment as well.

In Xiumei's testing with SCTP over IPsec/veth, the packets are kept
dropping due to the wrong CRC checksum.

Reported-by: Xiumei Mu <xmu@redhat.com>
Fixes: 7862b4058b9f ("esp: Add gso handlers for esp4 and esp6")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv4/esp4_offload.c | 6 ++++--
 net/ipv6/esp6_offload.c | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 601f5fbfc63f..ed3de486ea34 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -217,10 +217,12 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
 
 	if ((!(skb->dev->gso_partial_features & NETIF_F_HW_ESP) &&
 	     !(features & NETIF_F_HW_ESP)) || x->xso.dev != skb->dev)
-		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
+		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK |
+					    NETIF_F_SCTP_CRC);
 	else if (!(features & NETIF_F_HW_ESP_TX_CSUM) &&
 		 !(skb->dev->gso_partial_features & NETIF_F_HW_ESP_TX_CSUM))
-		esp_features = features & ~NETIF_F_CSUM_MASK;
+		esp_features = features & ~(NETIF_F_CSUM_MASK |
+					    NETIF_F_SCTP_CRC);
 
 	xo->flags |= XFRM_GSO_SEGMENT;
 
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 1ca516fb30e1..f35203ab39f5 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -254,9 +254,11 @@ static struct sk_buff *esp6_gso_segment(struct sk_buff *skb,
 	skb->encap_hdr_csum = 1;
 
 	if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev)
-		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
+		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK |
+					    NETIF_F_SCTP_CRC);
 	else if (!(features & NETIF_F_HW_ESP_TX_CSUM))
-		esp_features = features & ~NETIF_F_CSUM_MASK;
+		esp_features = features & ~(NETIF_F_CSUM_MASK |
+					    NETIF_F_SCTP_CRC);
 
 	xo->flags |= XFRM_GSO_SEGMENT;
 

From febf22565549ea7111e7d45e8f2d64373cc66b11 Mon Sep 17 00:00:00 2001
From: Hui Wang <hui.wang@canonical.com>
Date: Sat, 20 Mar 2021 17:15:41 +0800
Subject: [PATCH 1122/1820] ALSA: hda/realtek: fix a determine_headset_type
 issue for a Dell AIO

We found a recording issue on a Dell AIO, users plug a headset-mic and
select headset-mic from UI, but can't record any sound from
headset-mic. The root cause is the determine_headset_type() returns a
wrong type, e.g. users plug a ctia type headset, but that function
returns omtp type.

On this machine, the internal mic is not connected to the codec, the
"Input Source" is headset mic by default. And when users plug a
headset, the determine_headset_type() will be called immediately, the
codec on this AIO is alc274, the delay time for this codec in the
determine_headset_type() is only 80ms, the delay is too short to
correctly determine the headset type, the fail rate is nearly 99% when
users plug the headset with the normal speed.

Other codecs set several hundred ms delay time, so here I change the
delay time to 850ms for alc2x4 series, after this change, the fail
rate is zero unless users plug the headset slowly on purpose.

Cc: <stable@vger.kernel.org>
Signed-off-by: Hui Wang <hui.wang@canonical.com>
Link: https://lore.kernel.org/r/20210320091542.6748-1-hui.wang@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 316b9b4ccb32..8935bbe411a2 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5256,7 +5256,7 @@ static void alc_determine_headset_type(struct hda_codec *codec)
 	case 0x10ec0274:
 	case 0x10ec0294:
 		alc_process_coef_fw(codec, coef0274);
-		msleep(80);
+		msleep(850);
 		val = alc_read_coef_idx(codec, 0x46);
 		is_ctia = (val & 0x00f0) == 0x00f0;
 		break;

From e54f30befa7990b897189b44a56c1138c6bfdbb5 Mon Sep 17 00:00:00 2001
From: Hui Wang <hui.wang@canonical.com>
Date: Sat, 20 Mar 2021 17:15:42 +0800
Subject: [PATCH 1123/1820] ALSA: hda/realtek: call alc_update_headset_mode()
 in hp_automute_hook

We found the alc_update_headset_mode() is not called on some machines
when unplugging the headset, as a result, the mode of the
ALC_HEADSET_MODE_UNPLUGGED can't be set, then the current_headset_type
is not cleared, if users plug a differnt type of headset next time,
the determine_headset_type() will not be called and the audio jack is
set to the headset type of previous time.

On the Dell machines which connect the dmic to the PCH, if we open
the gnome-sound-setting and unplug the headset, this issue will
happen. Those machines disable the auto-mute by ucm and has no
internal mic in the input source, so the update_headset_mode() will
not be called by cap_sync_hook or automute_hook when unplugging, and
because the gnome-sound-setting is opened, the codec will not enter
the runtime_suspend state, so the update_headset_mode() will not be
called by alc_resume when unplugging. In this case the
hp_automute_hook is called when unplugging, so add
update_headset_mode() calling to this function.

Cc: <stable@vger.kernel.org>
Signed-off-by: Hui Wang <hui.wang@canonical.com>
Link: https://lore.kernel.org/r/20210320091542.6748-2-hui.wang@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 8935bbe411a2..fc2f60c58ad8 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5440,6 +5440,7 @@ static void alc_update_headset_jack_cb(struct hda_codec *codec,
 				       struct hda_jack_callback *jack)
 {
 	snd_hda_gen_hp_automute(codec, jack);
+	alc_update_headset_mode(codec);
 }
 
 static void alc_probe_headset_mode(struct hda_codec *codec)

From af06b628a6bde8506bbad32dbf7cc641c0176ad7 Mon Sep 17 00:00:00 2001
From: Lang Cheng <chenglang@huawei.com>
Date: Sat, 13 Mar 2021 10:30:11 +0800
Subject: [PATCH 1124/1820] RDMA/hns: Fix bug during CMDQ initialization

When reloading driver, the head/tail pointer of CMDQ may be not at
position 0. Then during initialization of CMDQ, if head is reset first,
the firmware will start to handle CMDQ because the head is not equal to
the tail. The driver can reset tail first since the firmware will be
triggerred only by head. This bug is introduced by changing macros of
head/tail register without changing the order of initialization.

Fixes: 292b3352bd5b ("RDMA/hns: Adjust fields and variables about CMDQ tail/head")
Link: https://lore.kernel.org/r/1615602611-7963-1-git-send-email-liweihang@huawei.com
Signed-off-by: Lang Cheng <chenglang@huawei.com>
Signed-off-by: Weihang Li <liweihang@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index c3934abeb260..ce26f97b2ca2 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -1194,8 +1194,10 @@ static void hns_roce_cmq_init_regs(struct hns_roce_dev *hr_dev, bool ring_type)
 			   upper_32_bits(dma));
 		roce_write(hr_dev, ROCEE_TX_CMQ_DEPTH_REG,
 			   (u32)ring->desc_num >> HNS_ROCE_CMQ_DESC_NUM_S);
-		roce_write(hr_dev, ROCEE_TX_CMQ_HEAD_REG, 0);
+
+		/* Make sure to write tail first and then head */
 		roce_write(hr_dev, ROCEE_TX_CMQ_TAIL_REG, 0);
+		roce_write(hr_dev, ROCEE_TX_CMQ_HEAD_REG, 0);
 	} else {
 		roce_write(hr_dev, ROCEE_RX_CMQ_BASEADDR_L_REG, (u32)dma);
 		roce_write(hr_dev, ROCEE_RX_CMQ_BASEADDR_H_REG,

From c607ab4f916d4d5259072eca34055d3f5a795c21 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Fri, 19 Mar 2021 18:41:06 +0000
Subject: [PATCH 1125/1820] arm64: stacktrace: don't trace arch_stack_walk()

We recently converted arm64 to use arch_stack_walk() in commit:

  5fc57df2f6fd ("arm64: stacktrace: Convert to ARCH_STACKWALK")

The core stacktrace code expects that (when tracing the current task)
arch_stack_walk() starts a trace at its caller, and does not include
itself in the trace. However, arm64's arch_stack_walk() includes itself,
and so traces include one more entry than callers expect. The core
stacktrace code which calls arch_stack_walk() tries to skip a number of
entries to prevent itself appearing in a trace, and the additional entry
prevents skipping one of the core stacktrace functions, leaving this in
the trace unexpectedly.

We can fix this by having arm64's arch_stack_walk() begin the trace with
its caller. The first value returned by the trace will be
__builtin_return_address(0), i.e. the caller of arch_stack_walk(). The
first frame record to be unwound will be __builtin_frame_address(1),
i.e. the caller's frame record. To prevent surprises, arch_stack_walk()
is also marked noinline.

While __builtin_frame_address(1) is not safe in portable code, local GCC
developers have confirmed that it is safe on arm64. To find the caller's
frame record, the builtin can safely dereference the current function's
frame record or (in theory) could stash the original FP into another GPR
at function entry time, neither of which are problematic.

Prior to this patch, the tracing code would unexpectedly show up in
traces of the current task, e.g.

| # cat /proc/self/stack
| [<0>] stack_trace_save_tsk+0x98/0x100
| [<0>] proc_pid_stack+0xb4/0x130
| [<0>] proc_single_show+0x60/0x110
| [<0>] seq_read_iter+0x230/0x4d0
| [<0>] seq_read+0xdc/0x130
| [<0>] vfs_read+0xac/0x1e0
| [<0>] ksys_read+0x6c/0xfc
| [<0>] __arm64_sys_read+0x20/0x30
| [<0>] el0_svc_common.constprop.0+0x60/0x120
| [<0>] do_el0_svc+0x24/0x90
| [<0>] el0_svc+0x2c/0x54
| [<0>] el0_sync_handler+0x1a4/0x1b0
| [<0>] el0_sync+0x170/0x180

After this patch, the tracing code will not show up in such traces:

| # cat /proc/self/stack
| [<0>] proc_pid_stack+0xb4/0x130
| [<0>] proc_single_show+0x60/0x110
| [<0>] seq_read_iter+0x230/0x4d0
| [<0>] seq_read+0xdc/0x130
| [<0>] vfs_read+0xac/0x1e0
| [<0>] ksys_read+0x6c/0xfc
| [<0>] __arm64_sys_read+0x20/0x30
| [<0>] el0_svc_common.constprop.0+0x60/0x120
| [<0>] do_el0_svc+0x24/0x90
| [<0>] el0_svc+0x2c/0x54
| [<0>] el0_sync_handler+0x1a4/0x1b0
| [<0>] el0_sync+0x170/0x180

Erring on the side of caution, I've given this a spin with a bunch of
toolchains, verifying the output of /proc/self/stack and checking that
the assembly looked sound. For GCC (where we require version 5.1.0 or
later) I tested with the kernel.org crosstool binares for versions
5.5.0, 6.4.0, 6.5.0, 7.3.0, 7.5.0, 8.1.0, 8.3.0, 8.4.0, 9.2.0, and
10.1.0. For clang (where we require version 10.0.1 or later) I tested
with the llvm.org binary releases of 11.0.0, and 11.0.1.

Fixes: 5fc57df2f6fd ("arm64: stacktrace: Convert to ARCH_STACKWALK")
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chen Jun <chenjun102@huawei.com>
Cc: Marco Elver <elver@google.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: <stable@vger.kernel.org> # 5.10.x
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20210319184106.5688-1-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/stacktrace.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index ad20981dfda4..d55bdfb7789c 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -194,8 +194,9 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 
 #ifdef CONFIG_STACKTRACE
 
-void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
-		     struct task_struct *task, struct pt_regs *regs)
+noinline void arch_stack_walk(stack_trace_consume_fn consume_entry,
+			      void *cookie, struct task_struct *task,
+			      struct pt_regs *regs)
 {
 	struct stackframe frame;
 
@@ -203,8 +204,8 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 		start_backtrace(&frame, regs->regs[29], regs->pc);
 	else if (task == current)
 		start_backtrace(&frame,
-				(unsigned long)__builtin_frame_address(0),
-				(unsigned long)arch_stack_walk);
+				(unsigned long)__builtin_frame_address(1),
+				(unsigned long)__builtin_return_address(0));
 	else
 		start_backtrace(&frame, thread_saved_fp(task),
 				thread_saved_pc(task));

From e14a371f732b969d4dc881bdd874c93f1b4fdd30 Mon Sep 17 00:00:00 2001
From: Tom Saeger <tom.saeger@oracle.com>
Date: Tue, 16 Mar 2021 12:50:41 -0600
Subject: [PATCH 1126/1820] Documentation: arm64/acpi : clarify arm64 support
 of IBFT

In commit 94bccc340710 ("iscsi_ibft: make ISCSI_IBFT dependson ACPI instead
of ISCSI_IBFT_FIND") Kconfig was disentangled to make ISCSI_IBFT selection
not depend on x86.

Update arm64 acpi documentation, changing IBFT support status from
"Not Supported" to "Optional".
Opportunistically re-flow paragraph for changed lines.

Link: https://lore.kernel.org/lkml/1563475054-10680-1-git-send-email-thomas.tai@oracle.com/

Signed-off-by: Tom Saeger <tom.saeger@oracle.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Link: https://lore.kernel.org/r/9efc652df2b8d6b53d9acb170eb7c9ca3938dfef.1615920441.git.tom.saeger@oracle.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 Documentation/arm64/acpi_object_usage.rst | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/Documentation/arm64/acpi_object_usage.rst b/Documentation/arm64/acpi_object_usage.rst
index 377e9d224db0..0609da73970b 100644
--- a/Documentation/arm64/acpi_object_usage.rst
+++ b/Documentation/arm64/acpi_object_usage.rst
@@ -17,12 +17,12 @@ For ACPI on arm64, tables also fall into the following categories:
 
        -  Recommended: BERT, EINJ, ERST, HEST, PCCT, SSDT
 
-       -  Optional: BGRT, CPEP, CSRT, DBG2, DRTM, ECDT, FACS, FPDT, IORT,
-          MCHI, MPST, MSCT, NFIT, PMTT, RASF, SBST, SLIT, SPMI, SRAT, STAO,
-	  TCPA, TPM2, UEFI, XENV
+       -  Optional: BGRT, CPEP, CSRT, DBG2, DRTM, ECDT, FACS, FPDT, IBFT,
+          IORT, MCHI, MPST, MSCT, NFIT, PMTT, RASF, SBST, SLIT, SPMI, SRAT,
+          STAO, TCPA, TPM2, UEFI, XENV
 
-       -  Not supported: BOOT, DBGP, DMAR, ETDT, HPET, IBFT, IVRS, LPIT,
-          MSDM, OEMx, PSDT, RSDT, SLIC, WAET, WDAT, WDRT, WPBT
+       -  Not supported: BOOT, DBGP, DMAR, ETDT, HPET, IVRS, LPIT, MSDM, OEMx,
+          PSDT, RSDT, SLIC, WAET, WDAT, WDRT, WPBT
 
 ====== ========================================================================
 Table  Usage for ARMv8 Linux

From d1296f1265f7ebb66c2bfab387bc1a0f969a5968 Mon Sep 17 00:00:00 2001
From: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Date: Sat, 20 Mar 2021 03:58:48 +0530
Subject: [PATCH 1127/1820] arm64: cpuinfo: Fix a typo

s/acurate/accurate/

Signed-off-by: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20210319222848.29928-1-unixbhaskar@gmail.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/cpuinfo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 77605aec25fe..51fcf99d5351 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -353,7 +353,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	 * with the CLIDR_EL1 fields to avoid triggering false warnings
 	 * when there is a mismatch across the CPUs. Keep track of the
 	 * effective value of the CTR_EL0 in our internal records for
-	 * acurate sanity check and feature enablement.
+	 * accurate sanity check and feature enablement.
 	 */
 	info->reg_ctr = read_cpuid_effective_cachetype();
 	info->reg_dczid = read_cpuid(DCZID_EL0);

From 141f8202cfa4192c3af79b6cbd68e7760bb01b5a Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@soleen.com>
Date: Fri, 19 Mar 2021 16:50:54 -0400
Subject: [PATCH 1128/1820] arm64: kdump: update ppos when reading elfcorehdr

The ppos points to a position in the old kernel memory (and in case of
arm64 in the crash kernel since elfcorehdr is passed as a segment). The
function should update the ppos by the amount that was read. This bug is
not exposed by accident, but other platforms update this value properly.
So, fix it in ARM64 version of elfcorehdr_read() as well.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Fixes: e62aaeac426a ("arm64: kdump: provide /proc/vmcore file")
Reviewed-by: Tyler Hicks <tyhicks@linux.microsoft.com>
Link: https://lore.kernel.org/r/20210319205054.743368-1-pasha.tatashin@soleen.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/crash_dump.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c
index e6e284265f19..58303a9ec32c 100644
--- a/arch/arm64/kernel/crash_dump.c
+++ b/arch/arm64/kernel/crash_dump.c
@@ -64,5 +64,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
 {
 	memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count);
+	*ppos += count;
+
 	return count;
 }

From ee7febce051945be28ad86d16a15886f878204de Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@soleen.com>
Date: Tue, 16 Feb 2021 10:03:51 -0500
Subject: [PATCH 1129/1820] arm64: mm: correct the inside linear map range
 during hotplug check

Memory hotplug may fail on systems with CONFIG_RANDOMIZE_BASE because the
linear map range is not checked correctly.

The start physical address that linear map covers can be actually at the
end of the range because of randomization. Check that and if so reduce it
to 0.

This can be verified on QEMU with setting kaslr-seed to ~0ul:

memstart_offset_seed = 0xffff
START: __pa(_PAGE_OFFSET(vabits_actual)) = ffff9000c0000000
END:   __pa(PAGE_END - 1) =  1000bfffffff

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Fixes: 58284a901b42 ("arm64/mm: Validate hotplug range before creating linear mapping")
Tested-by: Tyler Hicks <tyhicks@linux.microsoft.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Link: https://lore.kernel.org/r/20210216150351.129018-2-pasha.tatashin@soleen.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/mmu.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 7484ea4f6ba0..5d9550fdb9cf 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1448,6 +1448,22 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
 struct range arch_get_mappable_range(void)
 {
 	struct range mhp_range;
+	u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual));
+	u64 end_linear_pa = __pa(PAGE_END - 1);
+
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+		/*
+		 * Check for a wrap, it is possible because of randomized linear
+		 * mapping the start physical address is actually bigger than
+		 * the end physical address. In this case set start to zero
+		 * because [0, end_linear_pa] range must still be able to cover
+		 * all addressable physical addresses.
+		 */
+		if (start_linear_pa > end_linear_pa)
+			start_linear_pa = 0;
+	}
+
+	WARN_ON(start_linear_pa > end_linear_pa);
 
 	/*
 	 * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)]
@@ -1455,8 +1471,9 @@ struct range arch_get_mappable_range(void)
 	 * range which can be mapped inside this linear mapping range, must
 	 * also be derived from its end points.
 	 */
-	mhp_range.start = __pa(_PAGE_OFFSET(vabits_actual));
-	mhp_range.end =  __pa(PAGE_END - 1);
+	mhp_range.start = start_linear_pa;
+	mhp_range.end =  end_linear_pa;
+
 	return mhp_range;
 }
 

From 7011d72588d16a9e5f5d85acbc8b10019809599c Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@arm.com>
Date: Fri, 19 Mar 2021 12:01:28 +0000
Subject: [PATCH 1130/1820] kselftest/arm64: sve: Do not use non-canonical FFR
 register value

The "First Fault Register" (FFR) is an SVE register that mimics a
predicate register, but clears bits when a load or store fails to handle
an element of a vector. The supposed usage scenario is to initialise
this register (using SETFFR), then *read* it later on to learn about
elements that failed to load or store. Explicit writes to this register
using the WRFFR instruction are only supposed to *restore* values
previously read from the register (for context-switching only).
As the manual describes, this register holds only certain values, it:
"... contains a monotonic predicate value, in which starting from bit 0
there are zero or more 1 bits, followed only by 0 bits in any remaining
bit positions."
Any other value is UNPREDICTABLE and is not supposed to be "restored"
into the register.

The SVE test currently tries to write a signature pattern into the
register, which is *not* a canonical FFR value. Apparently the existing
setups treat UNPREDICTABLE as "read-as-written", but a new
implementation actually only stores canonical values. As a consequence,
the sve-test fails immediately when comparing the FFR value:
-----------
 # ./sve-test
Vector length:  128 bits
PID:    207
Mismatch: PID=207, iteration=0, reg=48
        Expected [cf00]
        Got      [0f00]
Aborted
-----------

Fix this by only populating the FFR with proper canonical values.
Effectively the requirement described above limits us to 17 unique
values over 16 bits worth of FFR, so we condense our signature down to 4
bits (2 bits from the PID, 2 bits from the generation) and generate the
canonical pattern from it. Any bits describing elements above the
minimum 128 bit are set to 0.

This aligns the FFR usage to the architecture and fixes the test on
microarchitectures implementing FFR in a more restricted way.

Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Reviwed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20210319120128.29452-1-andre.przywara@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 tools/testing/selftests/arm64/fp/sve-test.S | 22 ++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index 9210691aa998..e3e08d9c7020 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -284,16 +284,28 @@ endfunction
 // Set up test pattern in the FFR
 // x0: pid
 // x2: generation
+//
+// We need to generate a canonical FFR value, which consists of a number of
+// low "1" bits, followed by a number of zeros. This gives us 17 unique values
+// per 16 bits of FFR, so we create a 4 bit signature out of the PID and
+// generation, and use that as the initial number of ones in the pattern.
+// We fill the upper lanes of FFR with zeros.
 // Beware: corrupts P0.
 function setup_ffr
 	mov	x4, x30
 
-	bl	pattern
+	and	w0, w0, #0x3
+	bfi	w0, w2, #2, #2
+	mov	w1, #1
+	lsl	w1, w1, w0
+	sub	w1, w1, #1
+
 	ldr	x0, =ffrref
-	ldr	x1, =scratch
-	rdvl	x2, #1
-	lsr	x2, x2, #3
-	bl	memcpy
+	strh	w1, [x0], 2
+	rdvl	x1, #1
+	lsr	x1, x1, #3
+	sub	x1, x1, #2
+	bl	memclr
 
 	mov	x0, #0
 	ldr	x1, =ffrref

From d07f1e8a42614cc938c9c88866d4474a5a7fee31 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Mon, 22 Mar 2021 01:45:58 +0000
Subject: [PATCH 1131/1820] io_uring: correct io_queue_async_work() traces

Request's io-wq work is hashed in io_prep_async_link(), so
as trace_io_uring_queue_async_work() looks at it should follow after
prep has been done.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/709c9f872f4d2e198c7aed9c49019ca7095dd24d.1616366969.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index be04bc6b5b99..50acd6dfd966 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1239,10 +1239,10 @@ static void io_queue_async_work(struct io_kiocb *req)
 	BUG_ON(!tctx);
 	BUG_ON(!tctx->io_wq);
 
-	trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
-					&req->work, req->flags);
 	/* init ->work of the whole link before punting */
 	io_prep_async_link(req);
+	trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
+					&req->work, req->flags);
 	io_wq_enqueue(tctx->io_wq, &req->work);
 	if (link)
 		io_queue_linked_timeout(link);

From b65c128f963df367a8adcfb08f5ecf8721052723 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Mon, 22 Mar 2021 01:45:59 +0000
Subject: [PATCH 1132/1820] io_uring: don't skip file_end_write() on reissue

Don't miss to call kiocb_end_write() from __io_complete_rw() on reissue.
Shouldn't be much of a problem as the function actually does some work
only for ISREG, and NONBLOCK won't be reissued.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/32af9b77c5b874e1bee1a3c46396094bd969e577.1616366969.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 50acd6dfd966..a664b44a5a94 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2524,13 +2524,12 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
 {
 	int cflags = 0;
 
+	if (req->rw.kiocb.ki_flags & IOCB_WRITE)
+		kiocb_end_write(req);
 	if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_reissue(req))
 		return;
 	if (res != req->result)
 		req_set_fail_links(req);
-
-	if (req->rw.kiocb.ki_flags & IOCB_WRITE)
-		kiocb_end_write(req);
 	if (req->flags & REQ_F_BUFFER_SELECTED)
 		cflags = io_put_rw_kbuf(req);
 	__io_req_complete(req, issue_flags, res, cflags);

From d81269fecb8ce16eb07efafc9ff5520b2a31c486 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Fri, 19 Mar 2021 10:21:19 +0000
Subject: [PATCH 1133/1820] io_uring: fix provide_buffers sign extension

io_provide_buffers_prep()'s "p->len * p->nbufs" to sign extension
problems. Not a huge problem as it's only used for access_ok() and
increases the checked length, but better to keep typing right.

Reported-by: Colin Ian King <colin.king@canonical.com>
Fixes: efe68c1ca8f49 ("io_uring: validate the full range of provided buffers for access")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Colin Ian King <colin.king@canonical.com>
Link: https://lore.kernel.org/r/562376a39509e260d8532186a06226e56eb1f594.1616149233.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index a664b44a5a94..f3ae83a2d7bc 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3977,6 +3977,7 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
 static int io_provide_buffers_prep(struct io_kiocb *req,
 				   const struct io_uring_sqe *sqe)
 {
+	unsigned long size;
 	struct io_provide_buf *p = &req->pbuf;
 	u64 tmp;
 
@@ -3990,7 +3991,8 @@ static int io_provide_buffers_prep(struct io_kiocb *req,
 	p->addr = READ_ONCE(sqe->addr);
 	p->len = READ_ONCE(sqe->len);
 
-	if (!access_ok(u64_to_user_ptr(p->addr), (p->len * p->nbufs)))
+	size = (unsigned long)p->len * p->nbufs;
+	if (!access_ok(u64_to_user_ptr(p->addr), size))
 		return -EFAULT;
 
 	p->bgid = READ_ONCE(sqe->buf_group);

From 5244f5e2d801259af877ee759e8c22364c607072 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 19 Mar 2021 15:47:31 +0100
Subject: [PATCH 1134/1820] PM: runtime: Defer suspending suppliers

Because the PM-runtime status of the device is not updated in
__rpm_callback(), attempts to suspend the suppliers of the given
device triggered by the rpm_put_suppliers() call in there may
cause a supplier to be suspended completely before the status of
the consumer is updated to RPM_SUSPENDED, which is confusing.

To avoid that (1) modify __rpm_callback() to only decrease the
PM-runtime usage counter of each supplier and (2) make rpm_suspend()
try to suspend the suppliers after changing the consumer's status to
RPM_SUSPENDED, in analogy with the device's parent.

Link: https://lore.kernel.org/linux-pm/CAPDyKFqm06KDw_p8WXsM4dijDbho4bb6T4k50UqqvR1_COsp8g@mail.gmail.com/
Fixes: 21d5c57b3726 ("PM / runtime: Use device links")
Reported-by: elaine.zhang <zhangqing@rock-chips.com>
Diagnosed-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/runtime.c | 45 +++++++++++++++++++++++++++++++-----
 1 file changed, 39 insertions(+), 6 deletions(-)

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index a46a7e30881b..d54e540067bf 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -305,7 +305,7 @@ static int rpm_get_suppliers(struct device *dev)
 	return 0;
 }
 
-static void rpm_put_suppliers(struct device *dev)
+static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend)
 {
 	struct device_link *link;
 
@@ -313,10 +313,30 @@ static void rpm_put_suppliers(struct device *dev)
 				device_links_read_lock_held()) {
 
 		while (refcount_dec_not_one(&link->rpm_active))
-			pm_runtime_put(link->supplier);
+			pm_runtime_put_noidle(link->supplier);
+
+		if (try_to_suspend)
+			pm_request_idle(link->supplier);
 	}
 }
 
+static void rpm_put_suppliers(struct device *dev)
+{
+	__rpm_put_suppliers(dev, true);
+}
+
+static void rpm_suspend_suppliers(struct device *dev)
+{
+	struct device_link *link;
+	int idx = device_links_read_lock();
+
+	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
+				device_links_read_lock_held())
+		pm_request_idle(link->supplier);
+
+	device_links_read_unlock(idx);
+}
+
 /**
  * __rpm_callback - Run a given runtime PM callback for a given device.
  * @cb: Runtime PM callback to run.
@@ -344,8 +364,10 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
 			idx = device_links_read_lock();
 
 			retval = rpm_get_suppliers(dev);
-			if (retval)
+			if (retval) {
+				rpm_put_suppliers(dev);
 				goto fail;
+			}
 
 			device_links_read_unlock(idx);
 		}
@@ -368,9 +390,9 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
 		    || (dev->power.runtime_status == RPM_RESUMING && retval))) {
 			idx = device_links_read_lock();
 
- fail:
-			rpm_put_suppliers(dev);
+			__rpm_put_suppliers(dev, false);
 
+fail:
 			device_links_read_unlock(idx);
 		}
 
@@ -642,8 +664,11 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 		goto out;
 	}
 
+	if (dev->power.irq_safe)
+		goto out;
+
 	/* Maybe the parent is now able to suspend. */
-	if (parent && !parent->power.ignore_children && !dev->power.irq_safe) {
+	if (parent && !parent->power.ignore_children) {
 		spin_unlock(&dev->power.lock);
 
 		spin_lock(&parent->power.lock);
@@ -652,6 +677,14 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 
 		spin_lock(&dev->power.lock);
 	}
+	/* Maybe the suppliers are now able to suspend. */
+	if (dev->power.links_count > 0) {
+		spin_unlock_irq(&dev->power.lock);
+
+		rpm_suspend_suppliers(dev);
+
+		spin_lock_irq(&dev->power.lock);
+	}
 
  out:
 	trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval);

From 9de82caad0282205d4c38a39456bce58e3219540 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 22 Mar 2021 12:44:58 +0100
Subject: [PATCH 1135/1820] dax: avoid -Wempty-body warnings

gcc warns about an empty body in an else statement:

drivers/dax/bus.c: In function 'do_id_store':
drivers/dax/bus.c:94:48: error: suggest braces around empty body in an 'else' statement [-Werror=empty-body]
   94 |                         /* nothing to remove */;
      |                                                ^
drivers/dax/bus.c:99:43: error: suggest braces around empty body in an 'else' statement [-Werror=empty-body]
   99 |                 /* dax_id already added */;
      |                                           ^

In both of these cases, the 'else' exists only to have a place to
add a comment, but that comment doesn't really explain that much
either, so the easiest way to shut up that warning is to just
remove the else.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20210322114514.3490752-1-arnd@kernel.org
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/bus.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 452e85ae87a8..5aee26e1bbd6 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -90,13 +90,11 @@ static ssize_t do_id_store(struct device_driver *drv, const char *buf,
 				list_add(&dax_id->list, &dax_drv->ids);
 			} else
 				rc = -ENOMEM;
-		} else
-			/* nothing to remove */;
+		}
 	} else if (action == ID_REMOVE) {
 		list_del(&dax_id->list);
 		kfree(dax_id);
-	} else
-		/* dax_id already added */;
+	}
 	mutex_unlock(&dax_bus_lock);
 
 	if (rc < 0)

From 160f99db943224e55906dd83880da1a704c6e6b9 Mon Sep 17 00:00:00 2001
From: JeongHyeon Lee <jhs2.lee@samsung.com>
Date: Thu, 11 Mar 2021 21:10:50 +0900
Subject: [PATCH 1136/1820] dm verity: fix DM_VERITY_OPTS_MAX value

Three optional parameters must be accepted at once in a DM verity table, e.g.:
  (verity_error_handling_mode) (ignore_zero_block) (check_at_most_once)
Fix this to be possible by incrementing DM_VERITY_OPTS_MAX.

Signed-off-by: JeongHyeon Lee <jhs2.lee@samsung.com>
Fixes: 843f38d382b1 ("dm verity: add 'check_at_most_once' option to only validate hashes once")
Cc: stable@vger.kernel.org
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-verity-target.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 6b8e5bdd8526..808a98ef624c 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -34,7 +34,7 @@
 #define DM_VERITY_OPT_IGN_ZEROES	"ignore_zero_blocks"
 #define DM_VERITY_OPT_AT_MOST_ONCE	"check_at_most_once"
 
-#define DM_VERITY_OPTS_MAX		(2 + DM_VERITY_OPTS_FEC + \
+#define DM_VERITY_OPTS_MAX		(3 + DM_VERITY_OPTS_FEC + \
 					 DM_VERITY_ROOT_HASH_VERIFICATION_OPTS)
 
 static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE;

From 2d669ceb69c276f7637cf760287ca4187add082e Mon Sep 17 00:00:00 2001
From: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Date: Tue, 16 Mar 2021 13:36:02 +0900
Subject: [PATCH 1137/1820] dm table: Fix zoned model check and zone sectors
 check

Commit 24f6b6036c9e ("dm table: fix zoned iterate_devices based device
capability checks") triggered dm table load failure when dm-zoned device
is set up for zoned block devices and a regular device for cache.

The commit inverted logic of two callback functions for iterate_devices:
device_is_zoned_model() and device_matches_zone_sectors(). The logic of
device_is_zoned_model() was inverted then all destination devices of all
targets in dm table are required to have the expected zoned model. This
is fine for dm-linear, dm-flakey and dm-crypt on zoned block devices
since each target has only one destination device. However, this results
in failure for dm-zoned with regular cache device since that target has
both regular block device and zoned block devices.

As for device_matches_zone_sectors(), the commit inverted the logic to
require all zoned block devices in each target have the specified
zone_sectors. This check also fails for regular block device which does
not have zones.

To avoid the check failures, fix the zone model check and the zone
sectors check. For zone model check, introduce the new feature flag
DM_TARGET_MIXED_ZONED_MODEL, and set it to dm-zoned target. When the
target has this flag, allow it to have destination devices with any
zoned model. For zone sectors check, skip the check if the destination
device is not a zoned block device. Also add comments and improve an
error message to clarify expectations to the two checks.

Fixes: 24f6b6036c9e ("dm table: fix zoned iterate_devices based device capability checks")
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-table.c         | 33 +++++++++++++++++++++++++--------
 drivers/md/dm-zoned-target.c  |  2 +-
 include/linux/device-mapper.h | 15 ++++++++++++++-
 3 files changed, 40 insertions(+), 10 deletions(-)

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 95391f78b8d5..e5f0f1703c5d 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1594,6 +1594,13 @@ static int device_not_zoned_model(struct dm_target *ti, struct dm_dev *dev,
 	return blk_queue_zoned_model(q) != *zoned_model;
 }
 
+/*
+ * Check the device zoned model based on the target feature flag. If the target
+ * has the DM_TARGET_ZONED_HM feature flag set, host-managed zoned devices are
+ * also accepted but all devices must have the same zoned model. If the target
+ * has the DM_TARGET_MIXED_ZONED_MODEL feature set, the devices can have any
+ * zoned model with all zoned devices having the same zone size.
+ */
 static bool dm_table_supports_zoned_model(struct dm_table *t,
 					  enum blk_zoned_model zoned_model)
 {
@@ -1603,13 +1610,15 @@ static bool dm_table_supports_zoned_model(struct dm_table *t,
 	for (i = 0; i < dm_table_get_num_targets(t); i++) {
 		ti = dm_table_get_target(t, i);
 
-		if (zoned_model == BLK_ZONED_HM &&
-		    !dm_target_supports_zoned_hm(ti->type))
-			return false;
-
-		if (!ti->type->iterate_devices ||
-		    ti->type->iterate_devices(ti, device_not_zoned_model, &zoned_model))
-			return false;
+		if (dm_target_supports_zoned_hm(ti->type)) {
+			if (!ti->type->iterate_devices ||
+			    ti->type->iterate_devices(ti, device_not_zoned_model,
+						      &zoned_model))
+				return false;
+		} else if (!dm_target_supports_mixed_zoned_model(ti->type)) {
+			if (zoned_model == BLK_ZONED_HM)
+				return false;
+		}
 	}
 
 	return true;
@@ -1621,9 +1630,17 @@ static int device_not_matches_zone_sectors(struct dm_target *ti, struct dm_dev *
 	struct request_queue *q = bdev_get_queue(dev->bdev);
 	unsigned int *zone_sectors = data;
 
+	if (!blk_queue_is_zoned(q))
+		return 0;
+
 	return blk_queue_zone_sectors(q) != *zone_sectors;
 }
 
+/*
+ * Check consistency of zoned model and zone sectors across all targets. For
+ * zone sectors, if the destination device is a zoned block device, it shall
+ * have the specified zone_sectors.
+ */
 static int validate_hardware_zoned_model(struct dm_table *table,
 					 enum blk_zoned_model zoned_model,
 					 unsigned int zone_sectors)
@@ -1642,7 +1659,7 @@ static int validate_hardware_zoned_model(struct dm_table *table,
 		return -EINVAL;
 
 	if (dm_table_any_dev_attr(table, device_not_matches_zone_sectors, &zone_sectors)) {
-		DMERR("%s: zone sectors is not consistent across all devices",
+		DMERR("%s: zone sectors is not consistent across all zoned devices",
 		      dm_device_name(table->md));
 		return -EINVAL;
 	}
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 697f9de37355..7e88df64d197 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -1143,7 +1143,7 @@ static int dmz_message(struct dm_target *ti, unsigned int argc, char **argv,
 static struct target_type dmz_type = {
 	.name		 = "zoned",
 	.version	 = {2, 0, 0},
-	.features	 = DM_TARGET_SINGLETON | DM_TARGET_ZONED_HM,
+	.features	 = DM_TARGET_SINGLETON | DM_TARGET_MIXED_ZONED_MODEL,
 	.module		 = THIS_MODULE,
 	.ctr		 = dmz_ctr,
 	.dtr		 = dmz_dtr,
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 7f4ac87c0b32..5c641f930caf 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -253,7 +253,11 @@ struct target_type {
 #define dm_target_passes_integrity(type) ((type)->features & DM_TARGET_PASSES_INTEGRITY)
 
 /*
- * Indicates that a target supports host-managed zoned block devices.
+ * Indicates support for zoned block devices:
+ * - DM_TARGET_ZONED_HM: the target also supports host-managed zoned
+ *   block devices but does not support combining different zoned models.
+ * - DM_TARGET_MIXED_ZONED_MODEL: the target supports combining multiple
+ *   devices with different zoned models.
  */
 #ifdef CONFIG_BLK_DEV_ZONED
 #define DM_TARGET_ZONED_HM		0x00000040
@@ -275,6 +279,15 @@ struct target_type {
 #define DM_TARGET_PASSES_CRYPTO		0x00000100
 #define dm_target_passes_crypto(type) ((type)->features & DM_TARGET_PASSES_CRYPTO)
 
+#ifdef CONFIG_BLK_DEV_ZONED
+#define DM_TARGET_MIXED_ZONED_MODEL	0x00000200
+#define dm_target_supports_mixed_zoned_model(type) \
+	((type)->features & DM_TARGET_MIXED_ZONED_MODEL)
+#else
+#define DM_TARGET_MIXED_ZONED_MODEL	0x00000000
+#define dm_target_supports_mixed_zoned_model(type) (false)
+#endif
+
 struct dm_target {
 	struct dm_table *table;
 	struct target_type *type;

From 5424a0b867e65f1ecf34ffe88d091a4fcbb35bc1 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Mon, 22 Mar 2021 10:13:54 -0400
Subject: [PATCH 1138/1820] dm: don't report "detected capacity change" on
 device creation

When a DM device is first created it doesn't yet have an established
capacity, therefore the use of set_capacity_and_notify() should be
conditional given the potential for needless pr_info "detected
capacity change" noise even if capacity is 0.

One could argue that the pr_info() in set_capacity_and_notify() is
misplaced, but that position is not held uniformly.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Fixes: f64d9b2eacb9 ("dm: use set_capacity_and_notify")
Cc: stable@vger.kernel.org
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 50b693d776d6..3f3be9408afa 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2036,7 +2036,10 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	if (size != dm_get_size(md))
 		memset(&md->geometry, 0, sizeof(md->geometry));
 
-	set_capacity_and_notify(md->disk, size);
+	if (!get_capacity(md->disk))
+		set_capacity(md->disk, size);
+	else
+		set_capacity_and_notify(md->disk, size);
 
 	dm_table_event_callback(t, event_callback, md);
 

From eb50aaf960e3bedfef79063411ffd670da94b84b Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 22 Mar 2021 18:31:00 +0200
Subject: [PATCH 1139/1820] ACPI: scan: Use unique number for instance_no

The decrementation of acpi_device_bus_id->instance_no
in acpi_device_del() is incorrect, because it may cause
a duplicate instance number to be allocated next time
a device with the same acpi_device_bus_id is added.

Replace above mentioned approach by using IDA framework.

While at it, define the instance range to be [0, 4096).

Fixes: e49bd2dd5a50 ("ACPI: use PNPID:instance_no as bus_id of ACPI device")
Fixes: ca9dc8d42b30 ("ACPI / scan: Fix acpi_bus_id_list bookkeeping")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: 4.10+ <stable@vger.kernel.org> # 4.10+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/internal.h |  6 +++++-
 drivers/acpi/scan.c     | 33 ++++++++++++++++++++++++++++-----
 include/acpi/acpi_bus.h |  1 +
 3 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index e6a5d997241c..cb8f70842249 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -9,6 +9,8 @@
 #ifndef _ACPI_INTERNAL_H_
 #define _ACPI_INTERNAL_H_
 
+#include <linux/idr.h>
+
 #define PREFIX "ACPI: "
 
 int early_acpi_osi_init(void);
@@ -96,9 +98,11 @@ void acpi_scan_table_handler(u32 event, void *table, void *context);
 
 extern struct list_head acpi_bus_id_list;
 
+#define ACPI_MAX_DEVICE_INSTANCES	4096
+
 struct acpi_device_bus_id {
 	const char *bus_id;
-	unsigned int instance_no;
+	struct ida instance_ida;
 	struct list_head node;
 };
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index a184529d8fa4..84bb7c1929f1 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -479,9 +479,8 @@ static void acpi_device_del(struct acpi_device *device)
 	list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node)
 		if (!strcmp(acpi_device_bus_id->bus_id,
 			    acpi_device_hid(device))) {
-			if (acpi_device_bus_id->instance_no > 0)
-				acpi_device_bus_id->instance_no--;
-			else {
+			ida_simple_remove(&acpi_device_bus_id->instance_ida, device->pnp.instance_no);
+			if (ida_is_empty(&acpi_device_bus_id->instance_ida)) {
 				list_del(&acpi_device_bus_id->node);
 				kfree_const(acpi_device_bus_id->bus_id);
 				kfree(acpi_device_bus_id);
@@ -631,6 +630,21 @@ static struct acpi_device_bus_id *acpi_device_bus_id_match(const char *dev_id)
 	return NULL;
 }
 
+static int acpi_device_set_name(struct acpi_device *device,
+				struct acpi_device_bus_id *acpi_device_bus_id)
+{
+	struct ida *instance_ida = &acpi_device_bus_id->instance_ida;
+	int result;
+
+	result = ida_simple_get(instance_ida, 0, ACPI_MAX_DEVICE_INSTANCES, GFP_KERNEL);
+	if (result < 0)
+		return result;
+
+	device->pnp.instance_no = result;
+	dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, result);
+	return 0;
+}
+
 int acpi_device_add(struct acpi_device *device,
 		    void (*release)(struct device *))
 {
@@ -665,7 +679,9 @@ int acpi_device_add(struct acpi_device *device,
 
 	acpi_device_bus_id = acpi_device_bus_id_match(acpi_device_hid(device));
 	if (acpi_device_bus_id) {
-		acpi_device_bus_id->instance_no++;
+		result = acpi_device_set_name(device, acpi_device_bus_id);
+		if (result)
+			goto err_unlock;
 	} else {
 		acpi_device_bus_id = kzalloc(sizeof(*acpi_device_bus_id),
 					     GFP_KERNEL);
@@ -681,9 +697,16 @@ int acpi_device_add(struct acpi_device *device,
 			goto err_unlock;
 		}
 
+		ida_init(&acpi_device_bus_id->instance_ida);
+
+		result = acpi_device_set_name(device, acpi_device_bus_id);
+		if (result) {
+			kfree(acpi_device_bus_id);
+			goto err_unlock;
+		}
+
 		list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list);
 	}
-	dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, acpi_device_bus_id->instance_no);
 
 	if (device->parent)
 		list_add_tail(&device->node, &device->parent->children);
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 02a716a0af5d..f28b097c658f 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -233,6 +233,7 @@ struct acpi_pnp_type {
 
 struct acpi_device_pnp {
 	acpi_bus_id bus_id;		/* Object name */
+	int instance_no;		/* Instance number of this object */
 	struct acpi_pnp_type type;	/* ID type */
 	acpi_bus_address bus_address;	/* _ADR */
 	char *unique_id;		/* _UID */

From 46e152186cd89d940b26726fff11eb3f4935b45a Mon Sep 17 00:00:00 2001
From: Wang Qing <wangqing@vivo.com>
Date: Mon, 1 Mar 2021 20:05:48 +0800
Subject: [PATCH 1140/1820] arc: kernel: Return -EFAULT if copy_to_user() fails

The copy_to_user() function returns the number of bytes remaining to be
copied, but we want to return -EFAULT if the copy doesn't complete.

Signed-off-by: Wang Qing <wangqing@vivo.com>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
---
 arch/arc/kernel/signal.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index a78d8f745a67..fdbe06c98895 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -96,7 +96,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs,
 			     sizeof(sf->uc.uc_mcontext.regs.scratch));
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
 
-	return err;
+	return err ? -EFAULT : 0;
 }
 
 static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
@@ -110,7 +110,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
 				&(sf->uc.uc_mcontext.regs.scratch),
 				sizeof(sf->uc.uc_mcontext.regs.scratch));
 	if (err)
-		return err;
+		return -EFAULT;
 
 	set_current_blocked(&set);
 	regs->bta	= uregs.scratch.bta;

From 83520d62cc5a94d2ff0e2d37c8204fca13dd2637 Mon Sep 17 00:00:00 2001
From: "dean.yang_cp" <yangdianqing@yulong.com>
Date: Tue, 23 Feb 2021 10:00:31 +0800
Subject: [PATCH 1141/1820] ARC: treewide: avoid the pointer addition with NULL
 pointer

Signed-off-by: dean.yang_cp <yangdianqing@yulong.com>
Acked-by: Vineet Gupta <vgupta@synopsys.com>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
---
 arch/arc/kernel/unwind.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 74ad4256022e..47bab67f8649 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -187,25 +187,26 @@ static void init_unwind_table(struct unwind_table *table, const char *name,
 			      const void *table_start, unsigned long table_size,
 			      const u8 *header_start, unsigned long header_size)
 {
-	const u8 *ptr = header_start + 4;
-	const u8 *end = header_start + header_size;
-
 	table->core.pc = (unsigned long)core_start;
 	table->core.range = core_size;
 	table->init.pc = (unsigned long)init_start;
 	table->init.range = init_size;
 	table->address = table_start;
 	table->size = table_size;
-
-	/* See if the linker provided table looks valid. */
-	if (header_size <= 4
-	    || header_start[0] != 1
-	    || (void *)read_pointer(&ptr, end, header_start[1]) != table_start
-	    || header_start[2] == DW_EH_PE_omit
-	    || read_pointer(&ptr, end, header_start[2]) <= 0
-	    || header_start[3] == DW_EH_PE_omit)
-		header_start = NULL;
-
+	/* To avoid the pointer addition with NULL pointer.*/
+	if (header_start != NULL) {
+		const u8 *ptr = header_start + 4;
+		const u8 *end = header_start + header_size;
+		/* See if the linker provided table looks valid. */
+		if (header_size <= 4
+		|| header_start[0] != 1
+		|| (void *)read_pointer(&ptr, end, header_start[1])
+				!= table_start
+		|| header_start[2] == DW_EH_PE_omit
+		|| read_pointer(&ptr, end, header_start[2]) <= 0
+		|| header_start[3] == DW_EH_PE_omit)
+			header_start = NULL;
+	}
 	table->hdrsz = header_size;
 	smp_wmb();
 	table->header = header_start;

From 92063f3ca73aab794bd5408d3361fd5b5ea33079 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.ibm.com>
Date: Fri, 19 Mar 2021 11:17:23 -0400
Subject: [PATCH 1142/1820] integrity: double check iint_cache was initialized

The kernel may be built with multiple LSMs, but only a subset may be
enabled on the boot command line by specifying "lsm=".  Not including
"integrity" on the ordered LSM list may result in a NULL deref.

As reported by Dmitry Vyukov:
in qemu:
qemu-system-x86_64       -enable-kvm     -machine q35,nvdimm -cpu
max,migratable=off -smp 4       -m 4G,slots=4,maxmem=16G        -hda
wheezy.img      -kernel arch/x86/boot/bzImage   -nographic -vga std
 -soundhw all     -usb -usbdevice tablet  -bt hci -bt device:keyboard
   -net user,host=10.0.2.10,hostfwd=tcp::10022-:22 -net
nic,model=virtio-net-pci   -object
memory-backend-file,id=pmem1,share=off,mem-path=/dev/zero,size=64M
  -device nvdimm,id=nvdimm1,memdev=pmem1  -append "console=ttyS0
root=/dev/sda earlyprintk=serial rodata=n oops=panic panic_on_warn=1
panic=86400 lsm=smack numa=fake=2 nopcid dummy_hcd.num=8"   -pidfile
vm_pid -m 2G -cpu host

But it crashes on NULL deref in integrity_inode_get during boot:

Run /sbin/init as init process
BUG: kernel NULL pointer dereference, address: 000000000000001c
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP KASAN
CPU: 3 PID: 1 Comm: swapper/0 Not tainted 5.12.0-rc2+ #97
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
rel-1.13.0-44-g88ab0c15525c-prebuilt.qemu.org 04/01/2014
RIP: 0010:kmem_cache_alloc+0x2b/0x370 mm/slub.c:2920
Code: 57 41 56 41 55 41 54 41 89 f4 55 48 89 fd 53 48 83 ec 10 44 8b
3d d9 1f 90 0b 65 48 8b 04 25 28 00 00 00 48 89 44 24 08 31 c0 <8b> 5f
1c 4cf
RSP: 0000:ffffc9000032f9d8 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff888017fc4f00 RCX: 0000000000000000
RDX: ffff888040220000 RSI: 0000000000000c40 RDI: 0000000000000000
RBP: 0000000000000000 R08: 0000000000000000 R09: ffff888019263627
R10: ffffffff83937cd1 R11: 0000000000000000 R12: 0000000000000c40
R13: ffff888019263538 R14: 0000000000000000 R15: 0000000000ffffff
FS:  0000000000000000(0000) GS:ffff88802d180000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000000001c CR3: 000000000b48e000 CR4: 0000000000750ee0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 integrity_inode_get+0x47/0x260 security/integrity/iint.c:105
 process_measurement+0x33d/0x17e0 security/integrity/ima/ima_main.c:237
 ima_bprm_check+0xde/0x210 security/integrity/ima/ima_main.c:474
 security_bprm_check+0x7d/0xa0 security/security.c:845
 search_binary_handler fs/exec.c:1708 [inline]
 exec_binprm fs/exec.c:1761 [inline]
 bprm_execve fs/exec.c:1830 [inline]
 bprm_execve+0x764/0x19a0 fs/exec.c:1792
 kernel_execve+0x370/0x460 fs/exec.c:1973
 try_to_run_init_process+0x14/0x4e init/main.c:1366
 kernel_init+0x11d/0x1b8 init/main.c:1477
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294
Modules linked in:
CR2: 000000000000001c
---[ end trace 22d601a500de7d79 ]---

Since LSMs and IMA may be configured at build time, but not enabled at
run time, panic the system if "integrity" was not initialized before use.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: 79f7865d844c ("LSM: Introduce "lsm=" for boottime LSM selection")
Cc: stable@vger.kernel.org
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
---
 security/integrity/iint.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/security/integrity/iint.c b/security/integrity/iint.c
index 1d20003243c3..0ba01847e836 100644
--- a/security/integrity/iint.c
+++ b/security/integrity/iint.c
@@ -98,6 +98,14 @@ struct integrity_iint_cache *integrity_inode_get(struct inode *inode)
 	struct rb_node *node, *parent = NULL;
 	struct integrity_iint_cache *iint, *test_iint;
 
+	/*
+	 * The integrity's "iint_cache" is initialized at security_init(),
+	 * unless it is not included in the ordered list of LSMs enabled
+	 * on the boot command line.
+	 */
+	if (!iint_cache)
+		panic("%s: lsm=integrity required.\n", __func__);
+
 	iint = integrity_iint_find(inode);
 	if (iint)
 		return iint;

From 9aa26019c1a60013ea866d460de6392acb1712ee Mon Sep 17 00:00:00 2001
From: Prike Liang <Prike.Liang@amd.com>
Date: Tue, 9 Mar 2021 09:34:00 +0800
Subject: [PATCH 1143/1820] drm/amdgpu: fix the hibernation suspend with s0ix

During system hibernation suspend still need un-gate gfx CG/PG firstly to handle HW
status check before HW resource destory.

Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6447cd6ca5a8..7ecc6e4b8456 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2678,7 +2678,7 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 {
 	int i, r;
 
-	if (adev->in_poweroff_reboot_com ||
+	if (adev->in_poweroff_reboot_com || adev->in_hibernate ||
 	    !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) {
 		amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
 		amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
@@ -3742,7 +3742,11 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	amdgpu_fence_driver_suspend(adev);
 
-	if (adev->in_poweroff_reboot_com ||
+	/*
+	 * TODO: Need figure out the each GNB IP idle off dependency and then
+	 * improve the AMDGPU suspend/resume sequence for system-wide Sx entry/exit.
+	 */
+	if (adev->in_poweroff_reboot_com || adev->in_hibernate ||
 	    !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev))
 		r = amdgpu_device_ip_suspend_phase2(adev);
 	else

From 8914089a205be1042f99d49d2087663efc6fafa3 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 12 Mar 2021 15:22:36 -0500
Subject: [PATCH 1144/1820] drm/amdgpu: rework S3/S4/S0ix state handling

Set flags at the top level pmops callbacks to track
state.  This cleans up the current set of flags and
properly handles S4 on S0ix capable systems.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        | 10 +++-----
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 12 +++------
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c    | 30 +++++++++++++---------
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c  |  2 +-
 4 files changed, 25 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 49267eb64302..29885febc0b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1007,13 +1007,9 @@ struct amdgpu_device {
 
 	/* s3/s4 mask */
 	bool                            in_suspend;
-	bool				in_hibernate;
-
-	/*
-	 * The combination flag in_poweroff_reboot_com used to identify the poweroff
-	 * and reboot opt in the s0i3 system-wide suspend.
-	 */
-	bool 				in_poweroff_reboot_com;
+	bool				in_s3;
+	bool				in_s4;
+	bool				in_s0ix;
 
 	atomic_t 			in_gpu_reset;
 	enum pp_mp1_state               mp1_state;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7ecc6e4b8456..53e60c4ef0d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2678,8 +2678,7 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 {
 	int i, r;
 
-	if (adev->in_poweroff_reboot_com || adev->in_hibernate ||
-	    !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) {
+	if (!adev->in_s0ix || amdgpu_in_reset(adev)) {
 		amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
 		amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
 	}
@@ -3742,12 +3741,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	amdgpu_fence_driver_suspend(adev);
 
-	/*
-	 * TODO: Need figure out the each GNB IP idle off dependency and then
-	 * improve the AMDGPU suspend/resume sequence for system-wide Sx entry/exit.
-	 */
-	if (adev->in_poweroff_reboot_com || adev->in_hibernate ||
-	    !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev))
+	if (!adev->in_s0ix || amdgpu_in_reset(adev))
 		r = amdgpu_device_ip_suspend_phase2(adev);
 	else
 		amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry);
@@ -3781,7 +3775,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	if (amdgpu_acpi_is_s0ix_supported(adev))
+	if (adev->in_s0ix)
 		amdgpu_gfx_state_change_set(adev, sGpuChangeState_D0Entry);
 
 	/* post card */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index b26e2fd1c538..1b145a29803c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1274,24 +1274,35 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)
 	 */
 	if (!amdgpu_passthrough(adev))
 		adev->mp1_state = PP_MP1_STATE_UNLOAD;
-	adev->in_poweroff_reboot_com = true;
 	amdgpu_device_ip_suspend(adev);
-	adev->in_poweroff_reboot_com = false;
 	adev->mp1_state = PP_MP1_STATE_NONE;
 }
 
 static int amdgpu_pmops_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+	int r;
 
-	return amdgpu_device_suspend(drm_dev, true);
+	if (amdgpu_acpi_is_s0ix_supported(adev))
+		adev->in_s0ix = true;
+	adev->in_s3 = true;
+	r = amdgpu_device_suspend(drm_dev, true);
+	adev->in_s3 = false;
+
+	return r;
 }
 
 static int amdgpu_pmops_resume(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+	int r;
 
-	return amdgpu_device_resume(drm_dev, true);
+	r = amdgpu_device_resume(drm_dev, true);
+	if (amdgpu_acpi_is_s0ix_supported(adev))
+		adev->in_s0ix = false;
+	return r;
 }
 
 static int amdgpu_pmops_freeze(struct device *dev)
@@ -1300,9 +1311,9 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int r;
 
-	adev->in_hibernate = true;
+	adev->in_s4 = true;
 	r = amdgpu_device_suspend(drm_dev, true);
-	adev->in_hibernate = false;
+	adev->in_s4 = false;
 	if (r)
 		return r;
 	return amdgpu_asic_reset(adev);
@@ -1318,13 +1329,8 @@ static int amdgpu_pmops_thaw(struct device *dev)
 static int amdgpu_pmops_poweroff(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = drm_to_adev(drm_dev);
-	int r;
 
-	adev->in_poweroff_reboot_com = true;
-	r =  amdgpu_device_suspend(drm_dev, true);
-	adev->in_poweroff_reboot_com = false;
-	return r;
+	return amdgpu_device_suspend(drm_dev, true);
 }
 
 static int amdgpu_pmops_restore(struct device *dev)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index d143ef1b460b..24b19ba7f784 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1294,7 +1294,7 @@ static int smu_disable_dpms(struct smu_context *smu)
 	bool use_baco = !smu->is_apu &&
 		((amdgpu_in_reset(adev) &&
 		  (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) ||
-		 ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev)));
+		 ((adev->in_runpm || adev->in_s4) && amdgpu_asic_supports_baco(adev)));
 
 	/*
 	 * For custom pptable uploading, skip the DPM features

From e13d002bbf1d211cfe831ad2b2ae229a351eb196 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 9 Mar 2021 23:20:46 -0500
Subject: [PATCH 1145/1820] drm/amdgpu: don't evict vram on APUs for suspend to
 ram (v4)

Vram is system memory, so no need to evict.

v2: use PM_EVENT messages
v3: use correct dev
v4: use driver flags

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 4b29b8205442..072050429a2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1028,13 +1028,10 @@ int amdgpu_bo_evict_vram(struct amdgpu_device *adev)
 {
 	struct ttm_resource_manager *man;
 
-	/* late 2.6.33 fix IGP hibernate - we need pm ops to do this correct */
-#ifndef CONFIG_HIBERNATION
-	if (adev->flags & AMD_IS_APU) {
-		/* Useless to evict on IGP chips */
+	if (adev->in_s3 && (adev->flags & AMD_IS_APU)) {
+		/* No need to evict vram on APUs for suspend to ram */
 		return 0;
 	}
-#endif
 
 	man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
 	return ttm_resource_manager_evict_all(&adev->mman.bdev, man);

From ca8ee26d616b5e1818a0c69285d8f01feec35af9 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 19 Mar 2021 16:34:45 -0400
Subject: [PATCH 1146/1820] drm/amdgpu: clean up non-DC suspend/resume handling

Move the non-DC specific code into the DCE IP blocks similar
to how we handle DC.  This cleans up the common suspend
and resume pathes.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c  | 86 +-------------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 89 +++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_display.h |  3 +
 drivers/gpu/drm/amd/amdgpu/dce_v10_0.c      |  9 ++-
 drivers/gpu/drm/amd/amdgpu/dce_v11_0.c      |  9 ++-
 drivers/gpu/drm/amd/amdgpu/dce_v6_0.c       |  8 +-
 drivers/gpu/drm/amd/amdgpu/dce_v8_0.c       |  9 ++-
 drivers/gpu/drm/amd/amdgpu/dce_virtual.c    | 15 +++-
 8 files changed, 139 insertions(+), 89 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 53e60c4ef0d3..d1028933f41b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3672,14 +3672,9 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
  */
 int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 {
-	struct amdgpu_device *adev;
-	struct drm_crtc *crtc;
-	struct drm_connector *connector;
-	struct drm_connector_list_iter iter;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int r;
 
-	adev = drm_to_adev(dev);
-
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
@@ -3691,45 +3686,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	cancel_delayed_work_sync(&adev->delayed_init_work);
 
-	if (!amdgpu_device_has_dc_support(adev)) {
-		/* turn off display hw */
-		drm_modeset_lock_all(dev);
-		drm_connector_list_iter_begin(dev, &iter);
-		drm_for_each_connector_iter(connector, &iter)
-			drm_helper_connector_dpms(connector,
-						  DRM_MODE_DPMS_OFF);
-		drm_connector_list_iter_end(&iter);
-		drm_modeset_unlock_all(dev);
-			/* unpin the front buffers and cursors */
-		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-			struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-			struct drm_framebuffer *fb = crtc->primary->fb;
-			struct amdgpu_bo *robj;
-
-			if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) {
-				struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
-				r = amdgpu_bo_reserve(aobj, true);
-				if (r == 0) {
-					amdgpu_bo_unpin(aobj);
-					amdgpu_bo_unreserve(aobj);
-				}
-			}
-
-			if (fb == NULL || fb->obj[0] == NULL) {
-				continue;
-			}
-			robj = gem_to_amdgpu_bo(fb->obj[0]);
-			/* don't unpin kernel fb objects */
-			if (!amdgpu_fbdev_robj_is_fb(adev, robj)) {
-				r = amdgpu_bo_reserve(robj, true);
-				if (r == 0) {
-					amdgpu_bo_unpin(robj);
-					amdgpu_bo_unreserve(robj);
-				}
-			}
-		}
-	}
-
 	amdgpu_ras_suspend(adev);
 
 	r = amdgpu_device_ip_suspend_phase1(adev);
@@ -3766,10 +3722,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
  */
 int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 {
-	struct drm_connector *connector;
-	struct drm_connector_list_iter iter;
 	struct amdgpu_device *adev = drm_to_adev(dev);
-	struct drm_crtc *crtc;
 	int r = 0;
 
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
@@ -3800,24 +3753,6 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	queue_delayed_work(system_wq, &adev->delayed_init_work,
 			   msecs_to_jiffies(AMDGPU_RESUME_MS));
 
-	if (!amdgpu_device_has_dc_support(adev)) {
-		/* pin cursors */
-		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-			struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-
-			if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) {
-				struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
-				r = amdgpu_bo_reserve(aobj, true);
-				if (r == 0) {
-					r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
-					if (r != 0)
-						dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r);
-					amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
-					amdgpu_bo_unreserve(aobj);
-				}
-			}
-		}
-	}
 	r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
 	if (r)
 		return r;
@@ -3825,25 +3760,8 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	/* Make sure IB tests flushed */
 	flush_delayed_work(&adev->delayed_init_work);
 
-	/* blat the mode back in */
-	if (fbcon) {
-		if (!amdgpu_device_has_dc_support(adev)) {
-			/* pre DCE11 */
-			drm_helper_resume_force_mode(dev);
-
-			/* turn on display hw */
-			drm_modeset_lock_all(dev);
-
-			drm_connector_list_iter_begin(dev, &iter);
-			drm_for_each_connector_iter(connector, &iter)
-				drm_helper_connector_dpms(connector,
-							  DRM_MODE_DPMS_ON);
-			drm_connector_list_iter_end(&iter);
-
-			drm_modeset_unlock_all(dev);
-		}
+	if (fbcon)
 		amdgpu_fbdev_set_suspend(adev, 0);
-	}
 
 	drm_kms_helper_poll_enable(dev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 48cb33e5b382..f753e04fee99 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -1310,3 +1310,92 @@ bool amdgpu_crtc_get_scanout_position(struct drm_crtc *crtc,
 	return amdgpu_display_get_crtc_scanoutpos(dev, pipe, 0, vpos, hpos,
 						  stime, etime, mode);
 }
+
+int amdgpu_display_suspend_helper(struct amdgpu_device *adev)
+{
+	struct drm_device *dev = adev_to_drm(adev);
+	struct drm_crtc *crtc;
+	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
+	int r;
+
+	/* turn off display hw */
+	drm_modeset_lock_all(dev);
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter)
+		drm_helper_connector_dpms(connector,
+					  DRM_MODE_DPMS_OFF);
+	drm_connector_list_iter_end(&iter);
+	drm_modeset_unlock_all(dev);
+	/* unpin the front buffers and cursors */
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+		struct drm_framebuffer *fb = crtc->primary->fb;
+		struct amdgpu_bo *robj;
+
+		if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) {
+			struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+			r = amdgpu_bo_reserve(aobj, true);
+			if (r == 0) {
+				amdgpu_bo_unpin(aobj);
+				amdgpu_bo_unreserve(aobj);
+			}
+		}
+
+		if (fb == NULL || fb->obj[0] == NULL) {
+			continue;
+		}
+		robj = gem_to_amdgpu_bo(fb->obj[0]);
+		/* don't unpin kernel fb objects */
+		if (!amdgpu_fbdev_robj_is_fb(adev, robj)) {
+			r = amdgpu_bo_reserve(robj, true);
+			if (r == 0) {
+				amdgpu_bo_unpin(robj);
+				amdgpu_bo_unreserve(robj);
+			}
+		}
+	}
+	return r;
+}
+
+int amdgpu_display_resume_helper(struct amdgpu_device *adev)
+{
+	struct drm_device *dev = adev_to_drm(adev);
+	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
+	struct drm_crtc *crtc;
+	int r;
+
+	/* pin cursors */
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+
+		if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) {
+			struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+			r = amdgpu_bo_reserve(aobj, true);
+			if (r == 0) {
+				r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
+				if (r != 0)
+					dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r);
+				amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
+				amdgpu_bo_unreserve(aobj);
+			}
+		}
+	}
+
+	drm_helper_resume_force_mode(dev);
+
+	/* turn on display hw */
+	drm_modeset_lock_all(dev);
+
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter)
+		drm_helper_connector_dpms(connector,
+					  DRM_MODE_DPMS_ON);
+	drm_connector_list_iter_end(&iter);
+
+	drm_modeset_unlock_all(dev);
+
+	return 0;
+}
+
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h
index dc7b7d116549..7b6d83e2b13c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h
@@ -47,4 +47,7 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev,
 const struct drm_format_info *
 amdgpu_lookup_format_info(u32 format, uint64_t modifier);
 
+int amdgpu_display_suspend_helper(struct amdgpu_device *adev);
+int amdgpu_display_resume_helper(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 7944781e1086..19abb740a169 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -2897,6 +2897,11 @@ static int dce_v10_0_hw_fini(void *handle)
 static int dce_v10_0_suspend(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = amdgpu_display_suspend_helper(adev);
+	if (r)
+		return r;
 
 	adev->mode_info.bl_level =
 		amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
@@ -2921,8 +2926,10 @@ static int dce_v10_0_resume(void *handle)
 		amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder,
 						    bl_level);
 	}
+	if (ret)
+		return ret;
 
-	return ret;
+	return amdgpu_display_resume_helper(adev);
 }
 
 static bool dce_v10_0_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 1b6ff0470011..320ec35bfd37 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -3027,6 +3027,11 @@ static int dce_v11_0_hw_fini(void *handle)
 static int dce_v11_0_suspend(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = amdgpu_display_suspend_helper(adev);
+	if (r)
+		return r;
 
 	adev->mode_info.bl_level =
 		amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
@@ -3051,8 +3056,10 @@ static int dce_v11_0_resume(void *handle)
 		amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder,
 						    bl_level);
 	}
+	if (ret)
+		return ret;
 
-	return ret;
+	return amdgpu_display_resume_helper(adev);
 }
 
 static bool dce_v11_0_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 83a88385b762..13322000ebd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -2770,7 +2770,11 @@ static int dce_v6_0_hw_fini(void *handle)
 static int dce_v6_0_suspend(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
 
+	r = amdgpu_display_suspend_helper(adev);
+	if (r)
+		return r;
 	adev->mode_info.bl_level =
 		amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
 
@@ -2794,8 +2798,10 @@ static int dce_v6_0_resume(void *handle)
 		amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder,
 						    bl_level);
 	}
+	if (ret)
+		return ret;
 
-	return ret;
+	return amdgpu_display_resume_helper(adev);
 }
 
 static bool dce_v6_0_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 224b30214427..04ebf02e5b8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -2796,6 +2796,11 @@ static int dce_v8_0_hw_fini(void *handle)
 static int dce_v8_0_suspend(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = amdgpu_display_suspend_helper(adev);
+	if (r)
+		return r;
 
 	adev->mode_info.bl_level =
 		amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
@@ -2820,8 +2825,10 @@ static int dce_v8_0_resume(void *handle)
 		amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder,
 						    bl_level);
 	}
+	if (ret)
+		return ret;
 
-	return ret;
+	return amdgpu_display_resume_helper(adev);
 }
 
 static bool dce_v8_0_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index 9810af712cc0..5c11144da051 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -39,6 +39,7 @@
 #include "dce_v11_0.h"
 #include "dce_virtual.h"
 #include "ivsrcid/ivsrcid_vislands30.h"
+#include "amdgpu_display.h"
 
 #define DCE_VIRTUAL_VBLANK_PERIOD 16666666
 
@@ -491,12 +492,24 @@ static int dce_virtual_hw_fini(void *handle)
 
 static int dce_virtual_suspend(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = amdgpu_display_suspend_helper(adev);
+	if (r)
+		return r;
 	return dce_virtual_hw_fini(handle);
 }
 
 static int dce_virtual_resume(void *handle)
 {
-	return dce_virtual_hw_init(handle);
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = dce_virtual_hw_init(handle);
+	if (r)
+		return r;
+	return amdgpu_display_resume_helper(adev);
 }
 
 static bool dce_virtual_is_idle(void *handle)

From 3aa2cacf79b37f703d6b8f7bd0252c8fe8c3f420 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 12 Mar 2021 15:33:46 -0500
Subject: [PATCH 1147/1820] drm/amdgpu: move s0ix check into
 amdgpu_device_ip_suspend_phase2 (v3)

No functional change.

v2: use correct dev
v3: rework

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d1028933f41b..a2e15c65fc8f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2721,6 +2721,11 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 {
 	int i, r;
 
+	if (adev->in_s0ix) {
+		amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry);
+		return 0;
+	}
+
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
@@ -3697,10 +3702,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	amdgpu_fence_driver_suspend(adev);
 
-	if (!adev->in_s0ix || amdgpu_in_reset(adev))
-		r = amdgpu_device_ip_suspend_phase2(adev);
-	else
-		amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry);
+	r = amdgpu_device_ip_suspend_phase2(adev);
 	/* evict remaining vram memory
 	 * This second call to evict vram is to evict the gart page table
 	 * using the CPU.

From 9adb125dde699ffcf5d3e64d2c1476efce00a6f3 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 12 Mar 2021 15:36:04 -0500
Subject: [PATCH 1148/1820] drm/amdgpu: re-enable suspend phase 2 for S0ix

This really needs to be done to properly tear down
the device.  SMC, PSP, and GFX are still problematic,
need to dig deeper into what aspect of them that is
problematic.

Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a2e15c65fc8f..7809bd6c50e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2721,10 +2721,8 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 {
 	int i, r;
 
-	if (adev->in_s0ix) {
+	if (adev->in_s0ix)
 		amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry);
-		return 0;
-	}
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.valid)
@@ -2738,6 +2736,14 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 			adev->ip_blocks[i].status.hw = false;
 			continue;
 		}
+
+		/* XXX fix these remaining cases */
+		if (adev->in_s0ix &&
+		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC || /* breaks suspend */
+		     adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP || /* breaks resume */
+		     adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX))  /* breaks suspend */
+			continue;
+
 		/* XXX handle errors */
 		r = adev->ip_blocks[i].version->funcs->suspend(adev);
 		/* XXX handle errors */

From 4021229e32bd9e35f2813715e056f59bb3739e7d Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 12 Mar 2021 16:00:21 -0500
Subject: [PATCH 1149/1820] drm/amdgpu/swsmu: skip gfx cgpg on s0ix suspend

The SMU expects CGPG to be enabled when entering S0ix.
with this we can re-enable SMU suspend.

Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +--
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c  | 3 ++-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7809bd6c50e0..fa69ce49eac0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2739,8 +2739,7 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 
 		/* XXX fix these remaining cases */
 		if (adev->in_s0ix &&
-		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC || /* breaks suspend */
-		     adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP || /* breaks resume */
+		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP || /* breaks resume */
 		     adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX))  /* breaks suspend */
 			continue;
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 24b19ba7f784..cd905e41080e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1431,7 +1431,8 @@ static int smu_suspend(void *handle)
 
 	smu->watermarks_bitmap &= ~(WATERMARKS_LOADED);
 
-	if (smu->is_apu)
+	/* skip CGPG when in S0ix */
+	if (smu->is_apu && !adev->in_s0ix)
 		smu_set_gfx_cgpg(&adev->smu, false);
 
 	return 0;

From 9bb735abcbd83ec0b75cb2edf8885cff841fc096 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 16 Mar 2021 14:00:36 -0400
Subject: [PATCH 1150/1820] drm/amdgpu: update comments about s0ix
 suspend/resume

Provide and explanation as to why we skip GFX and PSP for
S0ix.  GFX goes into gfxoff, same as runtime, so no need
to tear down and re-init.  PSP is part of the always on
state, so no need to touch it.

Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index fa69ce49eac0..a7ad4e3da218 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2737,10 +2737,14 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 			continue;
 		}
 
-		/* XXX fix these remaining cases */
+		/* skip suspend of gfx and psp for S0ix
+		 * gfx is in gfxoff state, so on resume it will exit gfxoff just
+		 * like at runtime. PSP is also part of the always on hardware
+		 * so no need to suspend it.
+		 */
 		if (adev->in_s0ix &&
-		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP || /* breaks resume */
-		     adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX))  /* breaks suspend */
+		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP ||
+		     adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX))
 			continue;
 
 		/* XXX handle errors */

From 10cb67eb8a1b21419a7cd8e12f002a36bfef12fd Mon Sep 17 00:00:00 2001
From: Pratik Vishwakarma <Pratik.Vishwakarma@amd.com>
Date: Tue, 16 Mar 2021 14:15:44 -0400
Subject: [PATCH 1151/1820] drm/amdgpu: skip CG/PG for gfx during S0ix

Not needed as the device is in gfxoff state so the CG/PG state
is handled just like it would be for gfxoff during runtime gfxoff.

This should also prevent delays on resume.

Reworked from Pratik's original patch (Alex)

Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Pratik Vishwakarma <Pratik.Vishwakarma@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a7ad4e3da218..eb61d5e5535b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2371,6 +2371,10 @@ static int amdgpu_device_set_cg_state(struct amdgpu_device *adev,
 		i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		/* skip CG for GFX on S0ix */
+		if (adev->in_s0ix &&
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX)
+			continue;
 		/* skip CG for VCE/UVD, it's handled specially */
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
 		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&
@@ -2402,6 +2406,10 @@ static int amdgpu_device_set_pg_state(struct amdgpu_device *adev, enum amd_power
 		i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		/* skip PG for GFX on S0ix */
+		if (adev->in_s0ix &&
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX)
+			continue;
 		/* skip CG for VCE/UVD, it's handled specially */
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
 		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&

From 264705005e6bc7f484652c1d7aee798034c82e12 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 16 Mar 2021 14:18:30 -0400
Subject: [PATCH 1152/1820] drm/amdgpu: drop S0ix checks around CG/PG in
 suspend

We handle it properly within the CG/PG functions directly
now.

Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index eb61d5e5535b..de2cb3b1757c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2686,10 +2686,8 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 {
 	int i, r;
 
-	if (!adev->in_s0ix || amdgpu_in_reset(adev)) {
-		amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
-		amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
-	}
+	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
+	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.valid)

From ac5789ef927006a8449ea235a866922b2d8f8290 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 16 Mar 2021 22:02:14 -0400
Subject: [PATCH 1153/1820] drm/amdgpu: skip kfd suspend/resume for S0ix

GFX is in gfxoff mode during s0ix so we shouldn't need to
actually tear anything down and restore it.

Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index de2cb3b1757c..8a5a8ff5d362 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3710,7 +3710,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	r = amdgpu_device_ip_suspend_phase1(adev);
 
-	amdgpu_amdkfd_suspend(adev, adev->in_runpm);
+	if (!adev->in_s0ix)
+		amdgpu_amdkfd_suspend(adev, adev->in_runpm);
 
 	/* evict vram memory */
 	amdgpu_bo_evict_vram(adev);
@@ -3770,9 +3771,11 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	queue_delayed_work(system_wq, &adev->delayed_init_work,
 			   msecs_to_jiffies(AMDGPU_RESUME_MS));
 
-	r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
-	if (r)
-		return r;
+	if (!adev->in_s0ix) {
+		r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
+		if (r)
+			return r;
+	}
 
 	/* Make sure IB tests flushed */
 	flush_delayed_work(&adev->delayed_init_work);

From 6debc0fd71b947b03c1a39cc100f52b8238259d4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= <j.neuschaefer@gmx.net>
Date: Sun, 21 Mar 2021 14:00:01 +0100
Subject: [PATCH 1154/1820] MAINTAINERS: Combine "QLOGIC QLGE 10Gb ETHERNET
 DRIVER" sections into one
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There ended up being two sections with the same title. Combine the two
into one section.

Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Cc: Manish Chopra <manishc@marvell.com>
Cc: Coiby Xu <coiby.xu@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8e43e0417335..897b7c249073 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14710,15 +14710,11 @@ F:	drivers/net/ethernet/qlogic/qlcnic/
 QLOGIC QLGE 10Gb ETHERNET DRIVER
 M:	Manish Chopra <manishc@marvell.com>
 M:	GR-Linux-NIC-Dev@marvell.com
-L:	netdev@vger.kernel.org
-S:	Supported
-F:	drivers/staging/qlge/
-
-QLOGIC QLGE 10Gb ETHERNET DRIVER
 M:	Coiby Xu <coiby.xu@gmail.com>
 L:	netdev@vger.kernel.org
-S:	Maintained
+S:	Supported
 F:	Documentation/networking/device_drivers/qlogic/qlge.rst
+F:	drivers/staging/qlge/
 
 QM1D1B0004 MEDIA DRIVER
 M:	Akihiro Tsukada <tskd08@gmail.com>

From a50a151e311bd3a793ebe4e5f233db8bfad0b78f Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 22 Mar 2021 02:26:37 +0200
Subject: [PATCH 1155/1820] net: ipconfig: ic_dev can be NULL in ic_close_devs

ic_close_dev contains a generalization of the logic to not close a
network interface if it's the host port for a DSA switch. This logic is
disguised behind an iteration through the lowers of ic_dev in
ic_close_dev.

When no interface for ipconfig can be found, ic_dev is NULL, and
ic_close_dev:
- dereferences a NULL pointer when assigning selected_dev
- would attempt to search through the lower interfaces of a NULL
  net_device pointer

So we should protect against that case.

The "lower_dev" iterator variable was shortened to "lower" in order to
keep the 80 character limit.

Fixes: f68cbaed67cb ("net: ipconfig: avoid use-after-free in ic_close_devs")
Fixes: 46acf7bdbc72 ("Revert "net: ipv4: handle DSA enabled master network devices"")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Heiko Thiery <heiko.thiery@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipconfig.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 47db1bfdaaa0..bc2f6ca97152 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -309,7 +309,7 @@ have_carrier:
  */
 static void __init ic_close_devs(void)
 {
-	struct net_device *selected_dev = ic_dev->dev;
+	struct net_device *selected_dev = ic_dev ? ic_dev->dev : NULL;
 	struct ic_device *d, *next;
 	struct net_device *dev;
 
@@ -317,16 +317,18 @@ static void __init ic_close_devs(void)
 	next = ic_first_dev;
 	while ((d = next)) {
 		bool bring_down = (d != ic_dev);
-		struct net_device *lower_dev;
+		struct net_device *lower;
 		struct list_head *iter;
 
 		next = d->next;
 		dev = d->dev;
 
-		netdev_for_each_lower_dev(selected_dev, lower_dev, iter) {
-			if (dev == lower_dev) {
-				bring_down = false;
-				break;
+		if (selected_dev) {
+			netdev_for_each_lower_dev(selected_dev, lower, iter) {
+				if (dev == lower) {
+					bring_down = false;
+					break;
+				}
 			}
 		}
 		if (bring_down) {

From a07231084da2207629b42244380ae2f1e10bd9b4 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@nvidia.com>
Date: Thu, 18 Mar 2021 20:33:19 -0500
Subject: [PATCH 1156/1820] net/mlx5: Add back multicast stats for uplink
 representor

The multicast counter got removed from uplink representor due to the
cited patch.

Fixes: 47c97e6b10a1 ("net/mlx5e: Fix multicast counter not up-to-date in "ip -s"")
Signed-off-by: Huy Nguyen <huyn@nvidia.com>
Reviewed-by: Daniel Jurgens <danielj@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 33b418796e43..c8b8249846a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3846,10 +3846,17 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	}
 
 	if (mlx5e_is_uplink_rep(priv)) {
+		struct mlx5e_vport_stats *vstats = &priv->stats.vport;
+
 		stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
 		stats->rx_bytes   = PPORT_802_3_GET(pstats, a_octets_received_ok);
 		stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok);
 		stats->tx_bytes   = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
+
+		/* vport multicast also counts packets that are dropped due to steering
+		 * or rx out of buffer
+		 */
+		stats->multicast = VPORT_COUNTER_GET(vstats, received_eth_multicast.packets);
 	} else {
 		mlx5e_fold_sw_stats64(priv, stats);
 	}

From 7d6c86e3ccb5ceea767df5c7a9a17cdfccd3df9a Mon Sep 17 00:00:00 2001
From: Alaa Hleihel <alaa@nvidia.com>
Date: Wed, 10 Mar 2021 17:01:46 +0200
Subject: [PATCH 1157/1820] net/mlx5e: Allow to match on MPLS parameters only
 for MPLS over UDP

Currently, we support hardware offload only for MPLS over UDP.
However, rules matching on MPLS parameters are now wrongly offloaded
for regular MPLS, without actually taking the parameters into
consideration when doing the offload.
Fix it by rejecting such unsupported rules.

Fixes: 72046a91d134 ("net/mlx5e: Allow to match on mpls parameters")
Signed-off-by: Alaa Hleihel <alaa@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 0cacf46dc950..3359098c51d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2296,6 +2296,16 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			*match_level = MLX5_MATCH_L4;
 	}
 
+	/* Currenlty supported only for MPLS over UDP */
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS) &&
+	    !netif_is_bareudp(filter_dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matching on MPLS is supported only for MPLS over UDP");
+		netdev_err(priv->netdev,
+			   "Matching on MPLS is supported only for MPLS over UDP\n");
+		return -EOPNOTSUPP;
+	}
+
 	return 0;
 }
 

From 96b5b4585843e3c83fb1930e5dfbefd0fb889c55 Mon Sep 17 00:00:00 2001
From: Dima Chumak <dchumak@nvidia.com>
Date: Thu, 4 Mar 2021 21:28:11 +0200
Subject: [PATCH 1158/1820] net/mlx5e: Offload tuple rewrite for non-CT flows

Setting connection tracking OVS flows and then setting non-CT flows that
use tuple rewrite action (e.g. mod_tp_dst), causes the latter flows not
being offloaded.

Fix by using a stricter condition in modify_header_match_supported() to
check tuple rewrite support only for flows with CT action. The check is
factored out into standalone modify_tuple_supported() function to aid
readability.

Fixes: 7e36feeb0467 ("net/mlx5e: CT: Don't offload tuple rewrites for established tuples")
Signed-off-by: Dima Chumak <dchumak@nvidia.com>
Reviewed-by: Paul Blakey <paulb@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en/tc_ct.c    |  3 +-
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 44 ++++++++++++++-----
 2 files changed, 35 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index f3f6eb081948..b2cd29847a37 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -1181,7 +1181,8 @@ int mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec)
 
 	mlx5e_tc_match_to_reg_get_match(spec, CTSTATE_TO_REG,
 					&ctstate, &ctstate_mask);
-	if (ctstate_mask)
+
+	if ((ctstate & ctstate_mask) == MLX5_CT_STATE_TRK_BIT)
 		return -EOPNOTSUPP;
 
 	ctstate_mask |= MLX5_CT_STATE_TRK_BIT;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3359098c51d4..df2a0af854bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2909,6 +2909,37 @@ static int is_action_keys_supported(const struct flow_action_entry *act,
 	return 0;
 }
 
+static bool modify_tuple_supported(bool modify_tuple, bool ct_clear,
+				   bool ct_flow, struct netlink_ext_ack *extack,
+				   struct mlx5e_priv *priv,
+				   struct mlx5_flow_spec *spec)
+{
+	if (!modify_tuple || ct_clear)
+		return true;
+
+	if (ct_flow) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "can't offload tuple modification with non-clear ct()");
+		netdev_info(priv->netdev,
+			    "can't offload tuple modification with non-clear ct()");
+		return false;
+	}
+
+	/* Add ct_state=-trk match so it will be offloaded for non ct flows
+	 * (or after clear action), as otherwise, since the tuple is changed,
+	 * we can't restore ct state
+	 */
+	if (mlx5_tc_ct_add_no_trk_match(spec)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "can't offload tuple modification with ct matches and no ct(clear) action");
+		netdev_info(priv->netdev,
+			    "can't offload tuple modification with ct matches and no ct(clear) action");
+		return false;
+	}
+
+	return true;
+}
+
 static bool modify_header_match_supported(struct mlx5e_priv *priv,
 					  struct mlx5_flow_spec *spec,
 					  struct flow_action *flow_action,
@@ -2947,18 +2978,9 @@ static bool modify_header_match_supported(struct mlx5e_priv *priv,
 			return err;
 	}
 
-	/* Add ct_state=-trk match so it will be offloaded for non ct flows
-	 * (or after clear action), as otherwise, since the tuple is changed,
-	 *  we can't restore ct state
-	 */
-	if (!ct_clear && modify_tuple &&
-	    mlx5_tc_ct_add_no_trk_match(spec)) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "can't offload tuple modify header with ct matches");
-		netdev_info(priv->netdev,
-			    "can't offload tuple modify header with ct matches");
+	if (!modify_tuple_supported(modify_tuple, ct_clear, ct_flow, extack,
+				    priv, spec))
 		return false;
-	}
 
 	ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol);
 	if (modify_ip_header && ip_proto != IPPROTO_TCP &&

From 4eacfe72e3e037e3fc019113df32c39a705148c2 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Thu, 11 Mar 2021 17:46:35 +0200
Subject: [PATCH 1159/1820] net/mlx5e: Fix error path for ethtool set-priv-flag

Expose error value when failing to comply to command:
$ ethtool --set-priv-flags eth2 rx_cqe_compress [on/off]

Fixes: be7e87f92b58 ("net/mlx5e: Fail safe cqe compressing/moderation mode setting")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 0e059d5c57ac..f5f2a8fd0046 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1887,6 +1887,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
+	int err;
 
 	if (!MLX5_CAP_GEN(mdev, cqe_compression))
 		return -EOPNOTSUPP;
@@ -1896,7 +1897,10 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev,
 		return -EINVAL;
 	}
 
-	mlx5e_modify_rx_cqe_compression_locked(priv, enable);
+	err = mlx5e_modify_rx_cqe_compression_locked(priv, enable);
+	if (err)
+		return err;
+
 	priv->channels.params.rx_cqe_compress_def = enable;
 
 	return 0;

From 846d6da1fcdb14105f86b46b4345233550a79d55 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 1 Mar 2021 20:59:59 +0200
Subject: [PATCH 1160/1820] net/mlx5e: Fix division by 0 in mlx5e_select_queue

mlx5e_select_queue compares num_tc_x_num_ch to real_num_tx_queues to
determine if HTB and/or PTP offloads are active. If they are, it
calculates netdev_pick_tx() % num_tc_x_num_ch to prevent it from
selecting HTB and PTP queues for regular traffic. However, before the
channels are first activated, num_tc_x_num_ch is zero. If
ndo_select_queue gets called at this point, the HTB/PTP check will pass,
and mlx5e_select_queue will attempt to take a modulo by num_tc_x_num_ch,
which equals to zero.

This commit fixes the bug by assigning num_tc_x_num_ch to a non-zero
value before registering the netdev.

Fixes: 214baf22870c ("net/mlx5e: Support HTB offload")
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c8b8249846a9..158f947a8503 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4979,6 +4979,11 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 				     priv->max_nch);
 	params->num_tc       = 1;
 
+	/* Set an initial non-zero value, so that mlx5e_select_queue won't
+	 * divide by zero if called before first activating channels.
+	 */
+	priv->num_tc_x_num_ch = params->num_channels * params->num_tc;
+
 	/* SQ */
 	params->log_sq_size = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :

From 7c1ef1959b6fefe616ef3e7df832bf63dfbab9cf Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Thu, 11 Mar 2021 20:19:25 +0200
Subject: [PATCH 1161/1820] net/mlx5: SF, do not use ecpu bit for vhca state
 processing

Device firmware doesn't handle ecpu bit for vhca state processing
events and commands. Instead device firmware refers to the unique
function id to distinguish SF of different PCI functions.

When ecpu bit is used, firmware returns a syndrome.

mlx5_cmd_check:780:(pid 872): MODIFY_VHCA_STATE(0xb0e) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x263211)
mlx5_sf_dev_table_create:248:(pid 872): SF DEV table create err = -22

Hence, avoid using ecpu bit.

Fixes: 8f0105418668 ("net/mlx5: SF, Add port add delete functionality")
Fixes: 90d010b8634b ("net/mlx5: SF, Add auxiliary device support")
Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/sf/dev/dev.c  |  4 +---
 .../ethernet/mellanox/mlx5/core/sf/hw_table.c |  8 +++----
 .../mellanox/mlx5/core/sf/vhca_event.c        | 22 +++++++++----------
 .../mellanox/mlx5/core/sf/vhca_event.h        |  7 +++---
 4 files changed, 17 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index b265f27b2166..90b524c59f3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -181,15 +181,13 @@ static int mlx5_sf_dev_vhca_arm_all(struct mlx5_sf_dev_table *table)
 	u16 max_functions;
 	u16 function_id;
 	int err = 0;
-	bool ecpu;
 	int i;
 
 	max_functions = mlx5_sf_max_functions(dev);
 	function_id = MLX5_CAP_GEN(dev, sf_base_id);
-	ecpu = mlx5_read_embedded_cpu(dev);
 	/* Arm the vhca context as the vhca event notifier */
 	for (i = 0; i < max_functions; i++) {
-		err = mlx5_vhca_event_arm(dev, function_id, ecpu);
+		err = mlx5_vhca_event_arm(dev, function_id);
 		if (err)
 			return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
index 0914909806cb..a5a0f60bef66 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -6,7 +6,7 @@
 #include "sf.h"
 #include "mlx5_ifc_vhca_event.h"
 #include "vhca_event.h"
-#include "ecpf.h"
+#include "mlx5_core.h"
 
 struct mlx5_sf_hw {
 	u32 usr_sfnum;
@@ -18,7 +18,6 @@ struct mlx5_sf_hw_table {
 	struct mlx5_core_dev *dev;
 	struct mlx5_sf_hw *sfs;
 	int max_local_functions;
-	u8 ecpu: 1;
 	struct mutex table_lock; /* Serializes sf deletion and vhca state change handler. */
 	struct notifier_block vhca_nb;
 };
@@ -72,7 +71,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum)
 	if (err)
 		goto err;
 
-	err = mlx5_modify_vhca_sw_id(dev, hw_fn_id, table->ecpu, usr_sfnum);
+	err = mlx5_modify_vhca_sw_id(dev, hw_fn_id, usr_sfnum);
 	if (err)
 		goto vhca_err;
 
@@ -118,7 +117,7 @@ void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u16 id)
 
 	hw_fn_id = mlx5_sf_sw_to_hw_id(dev, id);
 	mutex_lock(&table->table_lock);
-	err = mlx5_cmd_query_vhca_state(dev, hw_fn_id, table->ecpu, out, sizeof(out));
+	err = mlx5_cmd_query_vhca_state(dev, hw_fn_id, out, sizeof(out));
 	if (err)
 		goto err;
 	state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state);
@@ -164,7 +163,6 @@ int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev)
 	table->dev = dev;
 	table->sfs = sfs;
 	table->max_local_functions = max_functions;
-	table->ecpu = mlx5_read_embedded_cpu(dev);
 	dev->priv.sf_hw_table = table;
 	mlx5_core_dbg(dev, "SF HW table: max sfs = %d\n", max_functions);
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
index f1c2068d4f2a..28b14b05086f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
@@ -19,52 +19,51 @@ struct mlx5_vhca_event_work {
 	struct mlx5_vhca_state_event event;
 };
 
-int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id,
-			      bool ecpu, u32 *out, u32 outlen)
+int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id, u32 *out, u32 outlen)
 {
 	u32 in[MLX5_ST_SZ_DW(query_vhca_state_in)] = {};
 
 	MLX5_SET(query_vhca_state_in, in, opcode, MLX5_CMD_OP_QUERY_VHCA_STATE);
 	MLX5_SET(query_vhca_state_in, in, function_id, function_id);
-	MLX5_SET(query_vhca_state_in, in, embedded_cpu_function, ecpu);
+	MLX5_SET(query_vhca_state_in, in, embedded_cpu_function, 0);
 
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
 }
 
 static int mlx5_cmd_modify_vhca_state(struct mlx5_core_dev *dev, u16 function_id,
-				      bool ecpu, u32 *in, u32 inlen)
+				      u32 *in, u32 inlen)
 {
 	u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {};
 
 	MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE);
 	MLX5_SET(modify_vhca_state_in, in, function_id, function_id);
-	MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu);
+	MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, 0);
 
 	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 }
 
-int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id)
+int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, u32 sw_fn_id)
 {
 	u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {};
 
 	MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE);
 	MLX5_SET(modify_vhca_state_in, in, function_id, function_id);
-	MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu);
+	MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, 0);
 	MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.sw_function_id, 1);
 	MLX5_SET(modify_vhca_state_in, in, vhca_state_context.sw_function_id, sw_fn_id);
 
 	return mlx5_cmd_exec_inout(dev, modify_vhca_state, in, out);
 }
 
-int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu)
+int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id)
 {
 	u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {};
 
 	MLX5_SET(modify_vhca_state_in, in, vhca_state_context.arm_change_event, 1);
 	MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.arm_change_event, 1);
 
-	return mlx5_cmd_modify_vhca_state(dev, function_id, ecpu, in, sizeof(in));
+	return mlx5_cmd_modify_vhca_state(dev, function_id, in, sizeof(in));
 }
 
 static void
@@ -73,7 +72,7 @@ mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event *
 	u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {};
 	int err;
 
-	err = mlx5_cmd_query_vhca_state(dev, event->function_id, event->ecpu, out, sizeof(out));
+	err = mlx5_cmd_query_vhca_state(dev, event->function_id, out, sizeof(out));
 	if (err)
 		return;
 
@@ -82,7 +81,7 @@ mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event *
 	event->new_vhca_state = MLX5_GET(query_vhca_state_out, out,
 					 vhca_state_context.vhca_state);
 
-	mlx5_vhca_event_arm(dev, event->function_id, event->ecpu);
+	mlx5_vhca_event_arm(dev, event->function_id);
 
 	blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event);
 }
@@ -111,7 +110,6 @@ mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, v
 	INIT_WORK(&work->work, &mlx5_vhca_state_work_handler);
 	work->notifier = notifier;
 	work->event.function_id = be16_to_cpu(eqe->data.vhca_state.function_id);
-	work->event.ecpu = be16_to_cpu(eqe->data.vhca_state.ec_function);
 	mlx5_events_work_enqueue(notifier->dev, &work->work);
 	return NOTIFY_OK;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
index 1fe1ec6f4d4b..013cdfe90616 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
@@ -10,7 +10,6 @@ struct mlx5_vhca_state_event {
 	u16 function_id;
 	u16 sw_function_id;
 	u8 new_vhca_state;
-	bool ecpu;
 };
 
 static inline bool mlx5_vhca_event_supported(const struct mlx5_core_dev *dev)
@@ -25,10 +24,10 @@ void mlx5_vhca_event_start(struct mlx5_core_dev *dev);
 void mlx5_vhca_event_stop(struct mlx5_core_dev *dev);
 int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb);
 void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb);
-int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id);
-int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu);
+int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, u32 sw_fn_id);
+int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id);
 int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id,
-			      bool ecpu, u32 *out, u32 outlen);
+			      u32 *out, u32 outlen);
 #else
 
 static inline void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap)

From 6d48b7912cc72275dc7c59ff961c8bac7ef66a92 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 22 Mar 2021 12:55:25 +0100
Subject: [PATCH 1162/1820] lockdep: Address clang -Wformat warning printing
 for %hd

Clang doesn't like format strings that truncate a 32-bit
value to something shorter:

  kernel/locking/lockdep.c:709:4: error: format specifies type 'short' but the argument has type 'int' [-Werror,-Wformat]

In this case, the warning is a slightly questionable, as it could realize
that both class->wait_type_outer and class->wait_type_inner are in fact
8-bit struct members, even though the result of the ?: operator becomes an
'int'.

However, there is really no point in printing the number as a 16-bit
'short' rather than either an 8-bit or 32-bit number, so just change
it to a normal %d.

Fixes: de8f5e4f2dc1 ("lockdep: Introduce wait-type checks")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210322115531.3987555-1-arnd@kernel.org
---
 kernel/locking/lockdep.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c30eb887ca7d..f160f1c97ca1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -705,7 +705,7 @@ static void print_lock_name(struct lock_class *class)
 
 	printk(KERN_CONT " (");
 	__print_lock_name(class);
-	printk(KERN_CONT "){%s}-{%hd:%hd}", usage,
+	printk(KERN_CONT "){%s}-{%d:%d}", usage,
 			class->wait_type_outer ?: class->wait_type_inner,
 			class->wait_type_inner);
 }

From e834df6cfc71d8e5ce2c27a0184145ea125c3f0f Mon Sep 17 00:00:00 2001
From: Nathan Lynch <nathanl@linux.ibm.com>
Date: Mon, 15 Mar 2021 03:00:44 -0500
Subject: [PATCH 1163/1820] powerpc/pseries/mobility: use struct for shared
 state

The atomic_t counter is the only shared state for the join/suspend
sequence so far, but that will change. Contain it in a
struct (pseries_suspend_info), and document its intended use. No
functional change.

Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210315080045.460331-2-nathanl@linux.ibm.com
---
 arch/powerpc/platforms/pseries/mobility.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index ea4d6a660e0d..a6739ce9feac 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -452,9 +452,21 @@ static int do_suspend(void)
 	return ret;
 }
 
+/**
+ * struct pseries_suspend_info - State shared between CPUs for join/suspend.
+ * @counter: Threads are to increment this upon resuming from suspend
+ *           or if an error is received from H_JOIN. The thread which performs
+ *           the first increment (i.e. sets it to 1) is responsible for
+ *           waking the other threads.
+ */
+struct pseries_suspend_info {
+	atomic_t counter;
+};
+
 static int do_join(void *arg)
 {
-	atomic_t *counter = arg;
+	struct pseries_suspend_info *info = arg;
+	atomic_t *counter = &info->counter;
 	long hvrc;
 	int ret;
 
@@ -535,11 +547,15 @@ static int pseries_suspend(u64 handle)
 	int ret;
 
 	while (true) {
-		atomic_t counter = ATOMIC_INIT(0);
+		struct pseries_suspend_info info;
 		unsigned long vasi_state;
 		int vasi_err;
 
-		ret = stop_machine(do_join, &counter, cpu_online_mask);
+		info = (struct pseries_suspend_info) {
+			.counter = ATOMIC_INIT(0),
+		};
+
+		ret = stop_machine(do_join, &info, cpu_online_mask);
 		if (ret == 0)
 			break;
 		/*

From 274cb1ca2e7ce02cab56f5f4c61a74aeb566f931 Mon Sep 17 00:00:00 2001
From: Nathan Lynch <nathanl@linux.ibm.com>
Date: Mon, 15 Mar 2021 03:00:45 -0500
Subject: [PATCH 1164/1820] powerpc/pseries/mobility: handle premature return
 from H_JOIN

The pseries join/suspend sequence in its current form was written with
the assumption that it was the only user of H_PROD and that it needn't
handle spurious successful returns from H_JOIN. That's wrong;
powerpc's paravirt spinlock code uses H_PROD, and CPUs entering
do_join() can be woken prematurely from H_JOIN with a status of
H_SUCCESS as a result. This causes all CPUs to exit the sequence
early, preventing suspend from occurring at all.

Add a 'done' boolean flag to the pseries_suspend_info struct, and have
the waking thread set it before waking the other threads. Threads
which receive H_SUCCESS from H_JOIN retry if the 'done' flag is still
unset.

Fixes: 9327dc0aeef3 ("powerpc/pseries/mobility: use stop_machine for join/suspend")
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210315080045.460331-3-nathanl@linux.ibm.com
---
 arch/powerpc/platforms/pseries/mobility.c | 26 ++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index a6739ce9feac..e83e0891272d 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -458,9 +458,12 @@ static int do_suspend(void)
  *           or if an error is received from H_JOIN. The thread which performs
  *           the first increment (i.e. sets it to 1) is responsible for
  *           waking the other threads.
+ * @done: False if join/suspend is in progress. True if the operation is
+ *        complete (successful or not).
  */
 struct pseries_suspend_info {
 	atomic_t counter;
+	bool done;
 };
 
 static int do_join(void *arg)
@@ -470,6 +473,7 @@ static int do_join(void *arg)
 	long hvrc;
 	int ret;
 
+retry:
 	/* Must ensure MSR.EE off for H_JOIN. */
 	hard_irq_disable();
 	hvrc = plpar_hcall_norets(H_JOIN);
@@ -485,8 +489,20 @@ static int do_join(void *arg)
 	case H_SUCCESS:
 		/*
 		 * The suspend is complete and this cpu has received a
-		 * prod.
+		 * prod, or we've received a stray prod from unrelated
+		 * code (e.g. paravirt spinlocks) and we need to join
+		 * again.
+		 *
+		 * This barrier orders the return from H_JOIN above vs
+		 * the load of info->done. It pairs with the barrier
+		 * in the wakeup/prod path below.
 		 */
+		smp_mb();
+		if (READ_ONCE(info->done) == false) {
+			pr_info_ratelimited("premature return from H_JOIN on CPU %i, retrying",
+					    smp_processor_id());
+			goto retry;
+		}
 		ret = 0;
 		break;
 	case H_BAD_MODE:
@@ -500,6 +516,13 @@ static int do_join(void *arg)
 
 	if (atomic_inc_return(counter) == 1) {
 		pr_info("CPU %u waking all threads\n", smp_processor_id());
+		WRITE_ONCE(info->done, true);
+		/*
+		 * This barrier orders the store to info->done vs subsequent
+		 * H_PRODs to wake the other CPUs. It pairs with the barrier
+		 * in the H_SUCCESS case above.
+		 */
+		smp_mb();
 		prod_others();
 	}
 	/*
@@ -553,6 +576,7 @@ static int pseries_suspend(u64 handle)
 
 		info = (struct pseries_suspend_info) {
 			.counter = ATOMIC_INIT(0),
+			.done = false,
 		};
 
 		ret = stop_machine(do_join, &info, cpu_online_mask);

From 5ee7d4c7fbc9d3119a20b1c77d34003d1f82ac26 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 22 Mar 2021 17:44:29 +0100
Subject: [PATCH 1165/1820] isdn: capi: fix mismatched prototypes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

gcc-11 complains about a prototype declaration that is different
from the function definition:

drivers/isdn/capi/kcapi.c:724:44: error: argument 2 of type ‘u8 *’ {aka ‘unsigned char *’} declared as a pointer [-Werror=array-parameter=]
  724 | u16 capi20_get_manufacturer(u32 contr, u8 *buf)
      |                                        ~~~~^~~
In file included from drivers/isdn/capi/kcapi.c:13:
drivers/isdn/capi/kcapi.h:62:43: note: previously declared as an array ‘u8[64]’ {aka ‘unsigned char[64]’}
   62 | u16 capi20_get_manufacturer(u32 contr, u8 buf[CAPI_MANUFACTURER_LEN]);
      |                                        ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/isdn/capi/kcapi.c:790:38: error: argument 2 of type ‘u8 *’ {aka ‘unsigned char *’} declared as a pointer [-Werror=array-parameter=]
  790 | u16 capi20_get_serial(u32 contr, u8 *serial)
      |                                  ~~~~^~~~~~
In file included from drivers/isdn/capi/kcapi.c:13:
drivers/isdn/capi/kcapi.h:64:37: note: previously declared as an array ‘u8[8]’ {aka ‘unsigned char[8]’}
   64 | u16 capi20_get_serial(u32 contr, u8 serial[CAPI_SERIAL_LEN]);
      |                                  ~~~^~~~~~~~~~~~~~~~~~~~~~~

Change the definition to make them match.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/capi/kcapi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c
index 7168778fbbe1..cb0afe897162 100644
--- a/drivers/isdn/capi/kcapi.c
+++ b/drivers/isdn/capi/kcapi.c
@@ -721,7 +721,7 @@ u16 capi20_put_message(struct capi20_appl *ap, struct sk_buff *skb)
  * Return value: CAPI result code
  */
 
-u16 capi20_get_manufacturer(u32 contr, u8 *buf)
+u16 capi20_get_manufacturer(u32 contr, u8 buf[CAPI_MANUFACTURER_LEN])
 {
 	struct capi_ctr *ctr;
 	u16 ret;
@@ -787,7 +787,7 @@ u16 capi20_get_version(u32 contr, struct capi_version *verp)
  * Return value: CAPI result code
  */
 
-u16 capi20_get_serial(u32 contr, u8 *serial)
+u16 capi20_get_serial(u32 contr, u8 serial[CAPI_SERIAL_LEN])
 {
 	struct capi_ctr *ctr;
 	u16 ret;

From e0c755a45f6fb6e81e3a62a94db0400ef0cdc046 Mon Sep 17 00:00:00 2001
From: George McCollister <george.mccollister@gmail.com>
Date: Mon, 22 Mar 2021 15:26:50 -0500
Subject: [PATCH 1166/1820] net: dsa: don't assign an error value to tag_ops

Use a temporary variable to hold the return value from
dsa_tag_driver_get() instead of assigning it to dst->tag_ops. Leaving
an error value in dst->tag_ops can result in deferencing an invalid
pointer when a deferred switch configuration happens later.

Fixes: 357f203bb3b5 ("net: dsa: keep a copy of the tagging protocol in the DSA switch tree")

Signed-off-by: George McCollister <george.mccollister@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa2.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 4d4956ed303b..d142eb2b288b 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -1066,6 +1066,7 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master)
 {
 	struct dsa_switch *ds = dp->ds;
 	struct dsa_switch_tree *dst = ds->dst;
+	const struct dsa_device_ops *tag_ops;
 	enum dsa_tag_protocol tag_protocol;
 
 	tag_protocol = dsa_get_tag_protocol(dp, master);
@@ -1080,14 +1081,16 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master)
 		 * nothing to do here.
 		 */
 	} else {
-		dst->tag_ops = dsa_tag_driver_get(tag_protocol);
-		if (IS_ERR(dst->tag_ops)) {
-			if (PTR_ERR(dst->tag_ops) == -ENOPROTOOPT)
+		tag_ops = dsa_tag_driver_get(tag_protocol);
+		if (IS_ERR(tag_ops)) {
+			if (PTR_ERR(tag_ops) == -ENOPROTOOPT)
 				return -EPROBE_DEFER;
 			dev_warn(ds->dev, "No tagger for this switch\n");
 			dp->master = NULL;
-			return PTR_ERR(dst->tag_ops);
+			return PTR_ERR(tag_ops);
 		}
+
+		dst->tag_ops = tag_ops;
 	}
 
 	dp->master = master;

From 627dc55c273dab308303a5217bd3e767d7083ddb Mon Sep 17 00:00:00 2001
From: Kalyan Thota <kalyant@codeaurora.org>
Date: Mon, 22 Mar 2021 02:17:12 -0700
Subject: [PATCH 1167/1820] drm/msm/disp/dpu1: icc path needs to be set before
 dpu runtime resume

DPU runtime resume will request for a min vote on the AXI bus as
it is a necessary step before turning ON the AXI clock.

The change does below
1) Move the icc path set before requesting runtime get_sync.
2) remove the dependency of hw catalog for min ib vote
as it is initialized at a later point.

Signed-off-by: Kalyan Thota <kalyan_t@codeaurora.org>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 5a8e3e1fc48c..85f2c3564c96 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -43,6 +43,8 @@
 #define DPU_DEBUGFS_DIR "msm_dpu"
 #define DPU_DEBUGFS_HWMASKNAME "hw_log_mask"
 
+#define MIN_IB_BW	400000000ULL /* Min ib vote 400MB */
+
 static int dpu_kms_hw_init(struct msm_kms *kms);
 static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms);
 
@@ -931,6 +933,9 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 		DPU_DEBUG("REG_DMA is not defined");
 	}
 
+	if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss"))
+		dpu_kms_parse_data_bus_icc_path(dpu_kms);
+
 	pm_runtime_get_sync(&dpu_kms->pdev->dev);
 
 	dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0);
@@ -1032,9 +1037,6 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 
 	dpu_vbif_init_memtypes(dpu_kms);
 
-	if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss"))
-		dpu_kms_parse_data_bus_icc_path(dpu_kms);
-
 	pm_runtime_put_sync(&dpu_kms->pdev->dev);
 
 	return 0;
@@ -1191,10 +1193,10 @@ static int __maybe_unused dpu_runtime_resume(struct device *dev)
 
 	ddev = dpu_kms->dev;
 
+	WARN_ON(!(dpu_kms->num_paths));
 	/* Min vote of BW is required before turning on AXI clk */
 	for (i = 0; i < dpu_kms->num_paths; i++)
-		icc_set_bw(dpu_kms->path[i], 0,
-			dpu_kms->catalog->perf.min_dram_ib);
+		icc_set_bw(dpu_kms->path[i], 0, Bps_to_icc(MIN_IB_BW));
 
 	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
 	if (rc) {

From a61f4661fba404418a7c77e86586dc52a58a93c6 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 2 Mar 2021 15:56:16 +0200
Subject: [PATCH 1168/1820] mfd: intel_quark_i2c_gpio: Revert "Constify static
 struct resources"

The structures are used as place holders, so they are modified at run-time.
Obviously they may not be constants.

  BUG: unable to handle page fault for address: d0643220
  ...
  CPU: 0 PID: 110 Comm: modprobe Not tainted 5.11.0+ #1
  Hardware name: Intel Corp. QUARK/GalileoGen2, BIOS 0x01000200 01/01/2014
  EIP: intel_quark_mfd_probe+0x93/0x1c0 [intel_quark_i2c_gpio]

This partially reverts the commit c4a164f41554d2899bed94bdcc499263f41787b4.

While at it, add a comment to avoid similar changes in the future.

Fixes: c4a164f41554 ("mfd: Constify static struct resources")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Tested-by: Tong Zhang <ztong0001@gmail.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/intel_quark_i2c_gpio.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/mfd/intel_quark_i2c_gpio.c b/drivers/mfd/intel_quark_i2c_gpio.c
index fe8ca945f367..b67cb0a3ab05 100644
--- a/drivers/mfd/intel_quark_i2c_gpio.c
+++ b/drivers/mfd/intel_quark_i2c_gpio.c
@@ -72,7 +72,8 @@ static const struct dmi_system_id dmi_platform_info[] = {
 	{}
 };
 
-static const struct resource intel_quark_i2c_res[] = {
+/* This is used as a place holder and will be modified at run-time */
+static struct resource intel_quark_i2c_res[] = {
 	[INTEL_QUARK_IORES_MEM] = {
 		.flags = IORESOURCE_MEM,
 	},
@@ -85,7 +86,8 @@ static struct mfd_cell_acpi_match intel_quark_acpi_match_i2c = {
 	.adr = MFD_ACPI_MATCH_I2C,
 };
 
-static const struct resource intel_quark_gpio_res[] = {
+/* This is used as a place holder and will be modified at run-time */
+static struct resource intel_quark_gpio_res[] = {
 	[INTEL_QUARK_IORES_MEM] = {
 		.flags = IORESOURCE_MEM,
 	},

From 2800aadc18a64c96b051bcb7da8a7df7d505db3f Mon Sep 17 00:00:00 2001
From: Jiri Kosina <jkosina@suse.cz>
Date: Tue, 2 Mar 2021 11:26:55 +0100
Subject: [PATCH 1169/1820] iwlwifi: Fix softirq/hardirq disabling in
 iwl_pcie_enqueue_hcmd()

It's possible for iwl_pcie_enqueue_hcmd() to be called with hard IRQs
disabled (e.g. from LED core). We can't enable BHs in such a situation.

Turn the unconditional BH-enable/BH-disable code into
hardirq-disable/conditional-enable.

This fixes the warning below.

 WARNING: CPU: 1 PID: 1139 at kernel/softirq.c:178 __local_bh_enable_ip+0xa5/0xf0
 CPU: 1 PID: 1139 Comm: NetworkManager Not tainted 5.12.0-rc1-00004-gb4ded168af79 #7
 Hardware name: LENOVO 20K5S22R00/20K5S22R00, BIOS R0IET38W (1.16 ) 05/31/2017
 RIP: 0010:__local_bh_enable_ip+0xa5/0xf0
 Code: f7 69 e8 ee 23 14 00 fb 66 0f 1f 44 00 00 65 8b 05 f0 f4 f7 69 85 c0 74 3f 48 83 c4 08 5b c3 65 8b 05 9b fe f7 69 85 c0 75 8e <0f> 0b eb 8a 48 89 3c 24 e8 4e 20 14 00 48 8b 3c 24 eb 91 e8 13 4e
 RSP: 0018:ffffafd580b13298 EFLAGS: 00010046
 RAX: 0000000000000000 RBX: 0000000000000201 RCX: 0000000000000000
 RDX: 0000000000000003 RSI: 0000000000000201 RDI: ffffffffc1272389
 RBP: ffff96517ae4c018 R08: 0000000000000001 R09: 0000000000000000
 R10: ffffafd580b13178 R11: 0000000000000001 R12: ffff96517b060000
 R13: 0000000000000000 R14: ffffffff80000000 R15: 0000000000000001
 FS:  00007fc604ebefc0(0000) GS:ffff965267480000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000055fb3fef13b2 CR3: 0000000109112004 CR4: 00000000003706e0
 Call Trace:
  ? _raw_spin_unlock_bh+0x1f/0x30
  iwl_pcie_enqueue_hcmd+0x5d9/0xa00 [iwlwifi]
  iwl_trans_txq_send_hcmd+0x6c/0x430 [iwlwifi]
  iwl_trans_send_cmd+0x88/0x170 [iwlwifi]
  ? lock_acquire+0x277/0x3d0
  iwl_mvm_send_cmd+0x32/0x80 [iwlmvm]
  iwl_mvm_led_set+0xc2/0xe0 [iwlmvm]
  ? led_trigger_event+0x46/0x70
  led_trigger_event+0x46/0x70
  ieee80211_do_open+0x5c5/0xa20 [mac80211]
  ieee80211_open+0x67/0x90 [mac80211]
  __dev_open+0xd4/0x150
  __dev_change_flags+0x19e/0x1f0
  dev_change_flags+0x23/0x60
  do_setlink+0x30d/0x1230
  ? lock_is_held_type+0xb4/0x120
  ? __nla_validate_parse.part.7+0x57/0xcb0
  ? __lock_acquire+0x2e1/0x1a50
  __rtnl_newlink+0x560/0x910
  ? __lock_acquire+0x2e1/0x1a50
  ? __lock_acquire+0x2e1/0x1a50
  ? lock_acquire+0x277/0x3d0
  ? sock_def_readable+0x5/0x290
  ? lock_is_held_type+0xb4/0x120
  ? find_held_lock+0x2d/0x90
  ? sock_def_readable+0xb3/0x290
  ? lock_release+0x166/0x2a0
  ? lock_is_held_type+0x90/0x120
  rtnl_newlink+0x47/0x70
  rtnetlink_rcv_msg+0x25c/0x470
  ? netlink_deliver_tap+0x97/0x3e0
  ? validate_linkmsg+0x350/0x350
  netlink_rcv_skb+0x50/0x100
  netlink_unicast+0x1b2/0x280
  netlink_sendmsg+0x336/0x450
  sock_sendmsg+0x5b/0x60
  ____sys_sendmsg+0x1ed/0x250
  ? copy_msghdr_from_user+0x5c/0x90
  ___sys_sendmsg+0x88/0xd0
  ? lock_is_held_type+0xb4/0x120
  ? find_held_lock+0x2d/0x90
  ? lock_release+0x166/0x2a0
  ? __fget_files+0xfe/0x1d0
  ? __sys_sendmsg+0x5e/0xa0
  __sys_sendmsg+0x5e/0xa0
  ? lockdep_hardirqs_on_prepare+0xd9/0x170
  do_syscall_64+0x33/0x80
  entry_SYSCALL_64_after_hwframe+0x44/0xae
 RIP: 0033:0x7fc605c9572d
 Code: 28 89 54 24 1c 48 89 74 24 10 89 7c 24 08 e8 da ee ff ff 8b 54 24 1c 48 8b 74 24 10 41 89 c0 8b 7c 24 08 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 33 44 89 c7 48 89 44 24 08 e8 2e ef ff ff 48
 RSP: 002b:00007fffc83789f0 EFLAGS: 00000293 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 000055ef468570c0 RCX: 00007fc605c9572d
 RDX: 0000000000000000 RSI: 00007fffc8378a30 RDI: 000000000000000c
 RBP: 0000000000000010 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000293 R12: 0000000000000000
 R13: 00007fffc8378b80 R14: 00007fffc8378b7c R15: 0000000000000000
 irq event stamp: 170785
 hardirqs last  enabled at (170783): [<ffffffff9609a8c2>] __local_bh_enable_ip+0x82/0xf0
 hardirqs last disabled at (170784): [<ffffffff96a8613d>] _raw_read_lock_irqsave+0x8d/0x90
 softirqs last  enabled at (170782): [<ffffffffc1272389>] iwl_pcie_enqueue_hcmd+0x5d9/0xa00 [iwlwifi]
 softirqs last disabled at (170785): [<ffffffffc1271ec6>] iwl_pcie_enqueue_hcmd+0x116/0xa00 [iwlwifi]

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com> # LLVM/Clang v12.0.0-rc3
Acked-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/nycvar.YFH.7.76.2103021125430.12405@cbobk.fhfr.pm
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 381e8f90b6f2..7ae32491b5da 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -928,6 +928,7 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	u32 cmd_pos;
 	const u8 *cmddata[IWL_MAX_CMD_TBS_PER_TFD];
 	u16 cmdlen[IWL_MAX_CMD_TBS_PER_TFD];
+	unsigned long flags;
 
 	if (WARN(!trans->wide_cmd_header &&
 		 group_id > IWL_ALWAYS_LONG_GROUP,
@@ -1011,10 +1012,10 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 		goto free_dup_buf;
 	}
 
-	spin_lock_bh(&txq->lock);
+	spin_lock_irqsave(&txq->lock, flags);
 
 	if (iwl_txq_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
-		spin_unlock_bh(&txq->lock);
+		spin_unlock_irqrestore(&txq->lock, flags);
 
 		IWL_ERR(trans, "No space in command queue\n");
 		iwl_op_mode_cmd_queue_full(trans->op_mode);
@@ -1174,7 +1175,7 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
  unlock_reg:
 	spin_unlock(&trans_pcie->reg_lock);
  out:
-	spin_unlock_bh(&txq->lock);
+	spin_unlock_irqrestore(&txq->lock, flags);
  free_dup_buf:
 	if (idx < 0)
 		kfree(dup_buf);

From 8f6a70fd71a3d7a6b120f83681263fc370eb52ba Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 9 Mar 2021 11:09:03 +0100
Subject: [PATCH 1170/1820] mt76: mt7921: fix airtime reporting

Fix {tx,rx}_airtime reporting for mt7921 driver. Wrong register definitions
trigger a tx hangs before resetting airtime stats.

Fixes: 163f4d22c118d ("mt76: mt7921: add MAC support")
Tested-by: Leon Yen <leon.yen@mediatek.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Acked-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/c05333be0e3e85a50a71bb2de81034fe425e3701.1615284335.git.lorenzo@kernel.org
---
 drivers/net/wireless/mediatek/mt76/mt7921/regs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
index 18980bb32dee..6dad7f6ab09d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h
@@ -135,10 +135,10 @@
 
 #define MT_WTBLON_TOP_BASE		0x34000
 #define MT_WTBLON_TOP(ofs)		(MT_WTBLON_TOP_BASE + (ofs))
-#define MT_WTBLON_TOP_WDUCR		MT_WTBLON_TOP(0x0)
+#define MT_WTBLON_TOP_WDUCR		MT_WTBLON_TOP(0x200)
 #define MT_WTBLON_TOP_WDUCR_GROUP	GENMASK(2, 0)
 
-#define MT_WTBL_UPDATE			MT_WTBLON_TOP(0x030)
+#define MT_WTBL_UPDATE			MT_WTBLON_TOP(0x230)
 #define MT_WTBL_UPDATE_WLAN_IDX		GENMASK(9, 0)
 #define MT_WTBL_UPDATE_ADM_COUNT_CLEAR	BIT(12)
 #define MT_WTBL_UPDATE_BUSY		BIT(31)

From bd83a2fc05ed323d7ae38443a6d2e253ef1c4237 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sat, 13 Mar 2021 15:36:35 +0100
Subject: [PATCH 1171/1820] brcmfmac: p2p: Fix recently introduced deadlock
 issue

Commit a05829a7222e ("cfg80211: avoid holding the RTNL when calling the
driver") replaced the rtnl_lock parameter passed to various brcmf
functions with just lock, because since that commit it is not just
about the rtnl_lock but also about the wiphy_lock .

During this search/replace the "if (!rtnl_locked)" check in brcmfmac/p2p.c
was accidentally replaced with "if (locked)", dropping the inversion of
the check. This causes the code to now call rtnl_lock() while already
holding the lock, causing a deadlock.

Add back the "!" to the if-condition to fix this.

Cc: Johannes Berg <johannes.berg@intel.com>
Fixes: a05829a7222e ("cfg80211: avoid holding the RTNL when calling the driver")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210313143635.109154-1-hdegoede@redhat.com
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
index 6d30a0fcecea..34cd8a7401fe 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
@@ -2439,7 +2439,7 @@ void brcmf_p2p_ifp_removed(struct brcmf_if *ifp, bool locked)
 	vif = ifp->vif;
 	cfg = wdev_to_cfg(&vif->wdev);
 	cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif = NULL;
-	if (locked) {
+	if (!locked) {
 		rtnl_lock();
 		wiphy_lock(cfg->wiphy);
 		cfg80211_unregister_wdev(&vif->wdev);

From 8249d17d3194eac064a8ca5bc5ca0abc86feecde Mon Sep 17 00:00:00 2001
From: Isaku Yamahata <isaku.yamahata@intel.com>
Date: Thu, 18 Mar 2021 13:26:57 -0700
Subject: [PATCH 1172/1820] x86/mem_encrypt: Correct physical address
 calculation in __set_clr_pte_enc()

The pfn variable contains the page frame number as returned by the
pXX_pfn() functions, shifted to the right by PAGE_SHIFT to remove the
page bits. After page protection computations are done to it, it gets
shifted back to the physical address using page_level_shift().

That is wrong, of course, because that function determines the shift
length based on the level of the page in the page table but in all the
cases, it was shifted by PAGE_SHIFT before.

Therefore, shift it back using PAGE_SHIFT to get the correct physical
address.

 [ bp: Rewrite commit message. ]

Fixes: dfaaec9033b8 ("x86: Add support for changing memory encryption attribute in early boot")
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/81abbae1657053eccc535c16151f63cd049dcb97.1616098294.git.isaku.yamahata@intel.com
---
 arch/x86/mm/mem_encrypt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 4b01f7dbaf30..ae78cef79980 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -262,7 +262,7 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
 	if (pgprot_val(old_prot) == pgprot_val(new_prot))
 		return;
 
-	pa = pfn << page_level_shift(level);
+	pa = pfn << PAGE_SHIFT;
 	size = page_level_size(level);
 
 	/*

From 291da9d4a9eb3a1cb0610b7f4480f5b52b1825e7 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 22 Mar 2021 09:46:13 +0100
Subject: [PATCH 1173/1820] locking/mutex: Fix non debug version of
 mutex_lock_io_nested()

If CONFIG_DEBUG_LOCK_ALLOC=n then mutex_lock_io_nested() maps to
mutex_lock() which is clearly wrong because mutex_lock() lacks the
io_schedule_prepare()/finish() invocations.

Map it to mutex_lock_io().

Fixes: f21860bac05b ("locking/mutex, sched/wait: Fix the mutex_lock_io_nested() define")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/878s6fshii.fsf@nanos.tec.linutronix.de
---
 include/linux/mutex.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 0cd631a19727..515cff77a4f4 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -185,7 +185,7 @@ extern void mutex_lock_io(struct mutex *lock);
 # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
 # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
 # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
-# define mutex_lock_io_nested(lock, subclass) mutex_lock(lock)
+# define mutex_lock_io_nested(lock, subclass) mutex_lock_io(lock)
 #endif
 
 /*

From 5e4010e36a58978e42b2ee13739ff9b50209c830 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Thu, 11 Mar 2021 14:03:18 +0800
Subject: [PATCH 1174/1820] usb: dwc3: qcom: skip interconnect init for ACPI
 probe

The ACPI probe starts failing since commit bea46b981515 ("usb: dwc3:
qcom: Add interconnect support in dwc3 driver"), because there is no
interconnect support for ACPI, and of_icc_get() call in
dwc3_qcom_interconnect_init() will just return -EINVAL.

Fix the problem by skipping interconnect init for ACPI probe, and then
the NULL icc_path_ddr will simply just scheild all ICC calls.

Fixes: bea46b981515 ("usb: dwc3: qcom: Add interconnect support in dwc3 driver")
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210311060318.25418-1-shawn.guo@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-qcom.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index fcaf04483ad0..3de291ab951a 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -244,6 +244,9 @@ static int dwc3_qcom_interconnect_init(struct dwc3_qcom *qcom)
 	struct device *dev = qcom->dev;
 	int ret;
 
+	if (has_acpi_companion(dev))
+		return 0;
+
 	qcom->icc_path_ddr = of_icc_get(dev, "usb-ddr");
 	if (IS_ERR(qcom->icc_path_ddr)) {
 		dev_err(dev, "failed to get usb-ddr path: %ld\n",

From cdb651b6021ee091abc24e9fbd9774d318ab96a6 Mon Sep 17 00:00:00 2001
From: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Date: Mon, 8 Mar 2021 18:16:44 -0800
Subject: [PATCH 1175/1820] usb: dwc3: gadget: Set gadget_max_speed when set
 ssp_rate

Set the dwc->gadget_max_speed to SuperSpeed Plus if the user sets the
ssp_rate. The udc_set_ssp_rate() is intended for setting the gadget's
speed to SuperSpeed Plus at the specified rate.

Fixes: 072cab8a0fe2 ("usb: dwc3: gadget: Implement setting of SSP rate")
Cc: <stable@vger.kernel.org>
Signed-off-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/0b2732e2f380d9912ee87f39dc82c2139223bad9.1615254129.git.Thinh.Nguyen@synopsys.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/gadget.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 4a337f348651..006476a4737b 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2523,6 +2523,7 @@ static void dwc3_gadget_set_ssp_rate(struct usb_gadget *g,
 	unsigned long		flags;
 
 	spin_lock_irqsave(&dwc->lock, flags);
+	dwc->gadget_max_speed = USB_SPEED_SUPER_PLUS;
 	dwc->gadget_ssp_rate = rate;
 	spin_unlock_irqrestore(&dwc->lock, flags);
 }

From 93f1d43c5767d70a1af89f54ef16a7d3e99af048 Mon Sep 17 00:00:00 2001
From: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Date: Mon, 8 Mar 2021 18:16:50 -0800
Subject: [PATCH 1176/1820] usb: dwc3: gadget: Use max speed if unspecified

If the gadget driver doesn't specify a max_speed, then use the
controller's maximum supported speed as default. For DWC_usb32 IP, the
gadget's speed maybe limited to gen2x1 rate only if the driver's
max_speed is unknown. This scenario should not occur with the current
implementation since the default gadget driver's max_speed should always
be specified. However, to make the driver more robust and help with
readability, let's cover all the scenarios in __dwc3_gadget_set_speed().

Fixes: 450b9e9fabd8 ("usb: dwc3: gadget: Set speed only up to the max supported")
Cc: <stable@vger.kernel.org>
Signed-off-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/55ac7001af73bfe9bc750c6446ef4ac8cf6f9313.1615254129.git.Thinh.Nguyen@synopsys.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/gadget.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 006476a4737b..4c15c3fce303 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2083,7 +2083,7 @@ static void __dwc3_gadget_set_speed(struct dwc3 *dwc)
 	u32			reg;
 
 	speed = dwc->gadget_max_speed;
-	if (speed > dwc->maximum_speed)
+	if (speed == USB_SPEED_UNKNOWN || speed > dwc->maximum_speed)
 		speed = dwc->maximum_speed;
 
 	if (speed == USB_SPEED_SUPER_PLUS &&

From b522f830d35189e0283fa4d5b4b3ef8d7a78cfcb Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 22 Mar 2021 14:52:44 +0200
Subject: [PATCH 1177/1820] usb: dwc3: pci: Enable dis_uX_susphy_quirk for
 Intel Merrifield

It seems that on Intel Merrifield platform the USB PHY shouldn't be suspended.
Otherwise it can't be enabled by simply change the cable in the connector.

Enable corresponding quirk for the platform in question.

Fixes: e5f4ca3fce90 ("usb: dwc3: ulpi: Fix USB2.0 HS/FS/LS PHY suspend regression")
Suggested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20210322125244.79407-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 3d3918a8d5fb..4c5c6972124a 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -120,6 +120,8 @@ static const struct property_entry dwc3_pci_intel_properties[] = {
 static const struct property_entry dwc3_pci_mrfld_properties[] = {
 	PROPERTY_ENTRY_STRING("dr_mode", "otg"),
 	PROPERTY_ENTRY_STRING("linux,extcon-name", "mrfld_bcove_pwrsrc"),
+	PROPERTY_ENTRY_BOOL("snps,dis_u3_susphy_quirk"),
+	PROPERTY_ENTRY_BOOL("snps,dis_u2_susphy_quirk"),
 	PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"),
 	{}
 };

From 72035f4954f0bca2d8c47cf31b3629c42116f5b7 Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Wed, 17 Mar 2021 19:04:00 -0400
Subject: [PATCH 1178/1820] usb: gadget: udc: amd5536udc_pci fix
 null-ptr-dereference

init_dma_pools() calls dma_pool_create(...dev->dev) to create dma pool.
however, dev->dev is actually set after calling init_dma_pools(), which
effectively makes dma_pool_create(..NULL) and cause crash.
To fix this issue, init dma only after dev->dev is set.

[    1.317993] RIP: 0010:dma_pool_create+0x83/0x290
[    1.323257] Call Trace:
[    1.323390]  ? pci_write_config_word+0x27/0x30
[    1.323626]  init_dma_pools+0x41/0x1a0 [snps_udc_core]
[    1.323899]  udc_pci_probe+0x202/0x2b1 [amd5536udc_pci]

Fixes: 7c51247a1f62 (usb: gadget: udc: Provide correct arguments for 'dma_pool_create')
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Link: https://lore.kernel.org/r/20210317230400.357756-1-ztong0001@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/amd5536udc_pci.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/gadget/udc/amd5536udc_pci.c b/drivers/usb/gadget/udc/amd5536udc_pci.c
index 8d387e0e4d91..c80f9bd51b75 100644
--- a/drivers/usb/gadget/udc/amd5536udc_pci.c
+++ b/drivers/usb/gadget/udc/amd5536udc_pci.c
@@ -153,6 +153,11 @@ static int udc_pci_probe(
 	pci_set_master(pdev);
 	pci_try_set_mwi(pdev);
 
+	dev->phys_addr = resource;
+	dev->irq = pdev->irq;
+	dev->pdev = pdev;
+	dev->dev = &pdev->dev;
+
 	/* init dma pools */
 	if (use_dma) {
 		retval = init_dma_pools(dev);
@@ -160,11 +165,6 @@ static int udc_pci_probe(
 			goto err_dma;
 	}
 
-	dev->phys_addr = resource;
-	dev->irq = pdev->irq;
-	dev->pdev = pdev;
-	dev->dev = &pdev->dev;
-
 	/* general probing */
 	if (udc_probe(dev)) {
 		retval = -ENODEV;

From 08dff274edda54310d6f1cf27b62fddf0f8d146e Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 11 Mar 2021 14:37:14 +0100
Subject: [PATCH 1179/1820] cdc-acm: fix BREAK rx code path adding necessary
 calls

Counting break events is nice but we should actually report them to
the tty layer.

Fixes: 5a6a62bdb9257 ("cdc-acm: add TIOCMIWAIT")
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Link: https://lore.kernel.org/r/20210311133714.31881-1-oneukum@suse.com
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 39ddb5585ded..b013671261a2 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -313,8 +313,10 @@ static void acm_process_notification(struct acm *acm, unsigned char *buf)
 			acm->iocount.dsr++;
 		if (difference & ACM_CTRL_DCD)
 			acm->iocount.dcd++;
-		if (newctrl & ACM_CTRL_BRK)
+		if (newctrl & ACM_CTRL_BRK) {
 			acm->iocount.brk++;
+			tty_insert_flip_char(&acm->port, 0, TTY_BREAK);
+		}
 		if (newctrl & ACM_CTRL_RI)
 			acm->iocount.rng++;
 		if (newctrl & ACM_CTRL_FRAMING)

From 6069e3e927c8fb3a1947b07d1a561644ea960248 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 11 Mar 2021 14:01:25 +0100
Subject: [PATCH 1180/1820] USB: cdc-acm: untangle a circular dependency
 between callback and softint

We have a cycle of callbacks scheduling works which submit
URBs with thos callbacks. This needs to be blocked, stopped
and unblocked to untangle the circle.

The issue leads to faults like:

[   55.068392] Unable to handle kernel paging request at virtual address 6b6b6c03
[   55.075624] pgd = be866494
[   55.078335] [6b6b6c03] *pgd=00000000
[   55.081924] Internal error: Oops: 5 [#1] PREEMPT SMP ARM
[   55.087238] Modules linked in: ppp_async crc_ccitt ppp_generic slhc
xt_TCPMSS xt_tcpmss xt_hl nf_log_ipv6 nf_log_ipv4 nf_log_common
xt_policy xt_limit xt_conntrack xt_tcpudp xt_pkttype ip6table_mangle
iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4
iptable_mangle ip6table_filter ip6_tables iptable_filter ip_tables
des_generic md5 sch_fq_codel cdc_mbim cdc_wdm cdc_ncm usbnet mii
cdc_acm usb_storage ip_tunnel xfrm_user xfrm6_tunnel tunnel6
xfrm4_tunnel tunnel4 esp6 esp4 ah6 ah4 xfrm_algo xt_LOG xt_LED
xt_comment x_tables ipv6
[   55.134954] CPU: 0 PID: 82 Comm: kworker/0:2 Tainted: G
   T 5.8.17 #1
[   55.142526] Hardware name: Freescale i.MX7 Dual (Device Tree)
[   55.148304] Workqueue: events acm_softint [cdc_acm]
[   55.153196] PC is at kobject_get+0x10/0xa4
[   55.157302] LR is at usb_get_dev+0x14/0x1c
[   55.161402] pc : [<8047c06c>]    lr : [<80560448>]    psr: 20000193
[   55.167671] sp : bca39ea8  ip : 00007374  fp : bf6cbd80
[   55.172899] r10: 00000000  r9 : bdd92284  r8 : bdd92008
[   55.178128] r7 : 6b6b6b6b  r6 : fffffffe  r5 : 60000113  r4 : 6b6b6be3
[   55.184658] r3 : 6b6b6b6b  r2 : 00000111  r1 : 00000000  r0 : 6b6b6be3
[   55.191191] Flags: nzCv  IRQs off  FIQs on  Mode SVC_32  ISA ARM Segment none
[   55.198417] Control: 10c5387d  Table: bcf0c06a  DAC: 00000051
[   55.204168] Process kworker/0:2 (pid: 82, stack limit = 0x9bdd2a89)
[   55.210439] Stack: (0xbca39ea8 to 0xbca3a000)
[   55.214805] 9ea0:                   bf6cbd80 80769a50 6b6b6b6b 80560448 bdeb0500 8056bfe8
[   55.222991] 9ec0: 00000002 b76da000 00000000 bdeb0500 bdd92448 bca38000 bdeb0510 8056d69c
[   55.231177] 9ee0: bca38000 00000000 80c050fc 00000000 bca39f44 09d42015 00000000 00000001
[   55.239363] 9f00: bdd92448 bdd92438 bdd92000 7f1158c4 bdd92448 bca2ee00 bf6cbd80 bf6cef00
[   55.247549] 9f20: 00000000 00000000 00000000 801412d8 bf6cbd98 80c03d00 bca2ee00 bf6cbd80
[   55.255735] 9f40: bca2ee14 bf6cbd98 80c03d00 00000008 bca38000 80141568 00000000 80c446ae
[   55.263921] 9f60: 00000000 bc9ed880 bc9f0700 bca38000 bc117eb4 80141524 bca2ee00 bc9ed8a4
[   55.272107] 9f80: 00000000 80147cc8 00000000 bc9f0700 80147b84 00000000 00000000 00000000
[   55.280292] 9fa0: 00000000 00000000 00000000 80100148 00000000 00000000 00000000 00000000
[   55.288477] 9fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
[   55.296662] 9fe0: 00000000 00000000 00000000 00000000 00000013 00000000 00000000 00000000
[   55.304860] [<8047c06c>] (kobject_get) from [<80560448>] (usb_get_dev+0x14/0x1c)
[   55.312271] [<80560448>] (usb_get_dev) from [<8056bfe8>] (usb_hcd_unlink_urb+0x50/0xd8)
[   55.320286] [<8056bfe8>] (usb_hcd_unlink_urb) from [<8056d69c>] (usb_kill_urb.part.0+0x44/0xd0)
[   55.329004] [<8056d69c>] (usb_kill_urb.part.0) from [<7f1158c4>] (acm_softint+0x4c/0x10c [cdc_acm])
[   55.338082] [<7f1158c4>] (acm_softint [cdc_acm]) from [<801412d8>] (process_one_work+0x19c/0x3e8)
[   55.346969] [<801412d8>] (process_one_work) from [<80141568>] (worker_thread+0x44/0x4dc)
[   55.355072] [<80141568>] (worker_thread) from [<80147cc8>] (kthread+0x144/0x180)
[   55.362481] [<80147cc8>] (kthread) from [<80100148>] (ret_from_fork+0x14/0x2c)
[   55.369706] Exception stack(0xbca39fb0 to 0xbca39ff8)

Tested-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210311130126.15972-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 48 ++++++++++++++++++++++++-------------
 1 file changed, 32 insertions(+), 16 deletions(-)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index b013671261a2..d684cf94b1c0 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -147,17 +147,29 @@ static inline int acm_set_control(struct acm *acm, int control)
 #define acm_send_break(acm, ms) \
 	acm_ctrl_msg(acm, USB_CDC_REQ_SEND_BREAK, ms, NULL, 0)
 
-static void acm_kill_urbs(struct acm *acm)
+static void acm_poison_urbs(struct acm *acm)
 {
 	int i;
 
-	usb_kill_urb(acm->ctrlurb);
+	usb_poison_urb(acm->ctrlurb);
 	for (i = 0; i < ACM_NW; i++)
-		usb_kill_urb(acm->wb[i].urb);
+		usb_poison_urb(acm->wb[i].urb);
 	for (i = 0; i < acm->rx_buflimit; i++)
-		usb_kill_urb(acm->read_urbs[i]);
+		usb_poison_urb(acm->read_urbs[i]);
 }
 
+static void acm_unpoison_urbs(struct acm *acm)
+{
+	int i;
+
+	for (i = 0; i < acm->rx_buflimit; i++)
+		usb_unpoison_urb(acm->read_urbs[i]);
+	for (i = 0; i < ACM_NW; i++)
+		usb_unpoison_urb(acm->wb[i].urb);
+	usb_unpoison_urb(acm->ctrlurb);
+}
+
+
 /*
  * Write buffer management.
  * All of these assume proper locks taken by the caller.
@@ -226,9 +238,10 @@ static int acm_start_wb(struct acm *acm, struct acm_wb *wb)
 
 	rc = usb_submit_urb(wb->urb, GFP_ATOMIC);
 	if (rc < 0) {
-		dev_err(&acm->data->dev,
-			"%s - usb_submit_urb(write bulk) failed: %d\n",
-			__func__, rc);
+		if (rc != -EPERM)
+			dev_err(&acm->data->dev,
+				"%s - usb_submit_urb(write bulk) failed: %d\n",
+				__func__, rc);
 		acm_write_done(acm, wb);
 	}
 	return rc;
@@ -482,11 +495,6 @@ static void acm_read_bulk_callback(struct urb *urb)
 	dev_vdbg(&acm->data->dev, "got urb %d, len %d, status %d\n",
 		rb->index, urb->actual_length, status);
 
-	if (!acm->dev) {
-		dev_dbg(&acm->data->dev, "%s - disconnected\n", __func__);
-		return;
-	}
-
 	switch (status) {
 	case 0:
 		usb_mark_last_busy(acm->dev);
@@ -733,6 +741,7 @@ static void acm_port_shutdown(struct tty_port *port)
 	 * Need to grab write_lock to prevent race with resume, but no need to
 	 * hold it due to the tty-port initialised flag.
 	 */
+	acm_poison_urbs(acm);
 	spin_lock_irq(&acm->write_lock);
 	spin_unlock_irq(&acm->write_lock);
 
@@ -749,7 +758,8 @@ static void acm_port_shutdown(struct tty_port *port)
 		usb_autopm_put_interface_async(acm->control);
 	}
 
-	acm_kill_urbs(acm);
+	acm_unpoison_urbs(acm);
+
 }
 
 static void acm_tty_cleanup(struct tty_struct *tty)
@@ -1542,8 +1552,14 @@ static void acm_disconnect(struct usb_interface *intf)
 	if (!acm)
 		return;
 
-	mutex_lock(&acm->mutex);
 	acm->disconnected = true;
+	/*
+	 * there is a circular dependency. acm_softint() can resubmit
+	 * the URBs in error handling so we need to block any
+	 * submission right away
+	 */
+	acm_poison_urbs(acm);
+	mutex_lock(&acm->mutex);
 	if (acm->country_codes) {
 		device_remove_file(&acm->control->dev,
 				&dev_attr_wCountryCodes);
@@ -1562,7 +1578,6 @@ static void acm_disconnect(struct usb_interface *intf)
 		tty_kref_put(tty);
 	}
 
-	acm_kill_urbs(acm);
 	cancel_delayed_work_sync(&acm->dwork);
 
 	tty_unregister_device(acm_tty_driver, acm->minor);
@@ -1604,7 +1619,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
 	if (cnt)
 		return 0;
 
-	acm_kill_urbs(acm);
+	acm_poison_urbs(acm);
 	cancel_delayed_work_sync(&acm->dwork);
 	acm->urbs_in_error_delay = 0;
 
@@ -1617,6 +1632,7 @@ static int acm_resume(struct usb_interface *intf)
 	struct urb *urb;
 	int rv = 0;
 
+	acm_unpoison_urbs(acm);
 	spin_lock_irq(&acm->write_lock);
 
 	if (--acm->susp_count)

From e4c77070ad45fc940af1d7fb1e637c349e848951 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 11 Mar 2021 14:01:26 +0100
Subject: [PATCH 1181/1820] USB: cdc-acm: downgrade message to debug

This failure is so common that logging an error here amounts
to spamming log files.

Reviewed-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210311130126.15972-2-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index d684cf94b1c0..fd2fce072985 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -659,7 +659,8 @@ static void acm_port_dtr_rts(struct tty_port *port, int raise)
 
 	res = acm_set_control(acm, val);
 	if (res && (acm->ctrl_caps & USB_CDC_CAP_LINE))
-		dev_err(&acm->control->dev, "failed to set dtr/rts\n");
+		/* This is broken in too many devices to spam the logs */
+		dev_dbg(&acm->control->dev, "failed to set dtr/rts\n");
 }
 
 static int acm_port_activate(struct tty_port *port, struct tty_struct *tty)

From 3f3a9bc1f6df5a1a9ec39e3a5bee420328811be4 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 17 Mar 2021 20:48:59 +0200
Subject: [PATCH 1182/1820] drm/i915/ilk-glk: Fix link training on links with
 LTTPRs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The spec requires to use at least 3.2ms for the AUX timeout period if
there are LT-tunable PHY Repeaters on the link (2.11.2). An upcoming
spec update makes this more specific, by requiring a 3.2ms minimum
timeout period for the LTTPR detection reading the 0xF0000-0xF0007
range (3.6.5.1).

Accordingly disable LTTPR detection until GLK, where the maximum timeout
we can set is only 1.6ms.

Link training in the non-transparent mode is known to fail at least on
some SKL systems with a WD19 dock on the link, which exposes an LTTPR
(see the References below). While this could have different reasons
besides the too short AUX timeout used, not detecting LTTPRs (and so not
using the non-transparent LT mode) fixes link training on these systems.

While at it add a code comment about the platform specific maximum
timeout values.

v2: Add a comment about the g4x maximum timeout as well. (Ville)

Reported-by: Takashi Iwai <tiwai@suse.de>
Reported-and-tested-by: Santiago Zarate <santiago.zarate@suse.com>
Reported-and-tested-by: Bodo Graumann <mail@bodograumann.de>
References: https://gitlab.freedesktop.org/drm/intel/-/issues/3166
Fixes: b30edfd8d0b4 ("drm/i915: Switch to LTTPR non-transparent mode link training")
Cc: <stable@vger.kernel.org> # v5.11
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210317184901.4029798-2-imre.deak@intel.com
(cherry picked from commit 984982f3ef7b240cd24c2feb2762d81d9d8da3c2)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp_aux.c       |  7 +++++++
 .../gpu/drm/i915/display/intel_dp_link_training.c | 15 ++++++++++++---
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.c b/drivers/gpu/drm/i915/display/intel_dp_aux.c
index eaebf123310a..10fe17b7280d 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux.c
@@ -133,6 +133,7 @@ static u32 g4x_get_aux_send_ctl(struct intel_dp *intel_dp,
 	else
 		precharge = 5;
 
+	/* Max timeout value on G4x-BDW: 1.6ms */
 	if (IS_BROADWELL(dev_priv))
 		timeout = DP_AUX_CH_CTL_TIME_OUT_600us;
 	else
@@ -159,6 +160,12 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp,
 	enum phy phy = intel_port_to_phy(i915, dig_port->base.port);
 	u32 ret;
 
+	/*
+	 * Max timeout values:
+	 * SKL-GLK: 1.6ms
+	 * CNL: 3.2ms
+	 * ICL+: 4ms
+	 */
 	ret = DP_AUX_CH_CTL_SEND_BUSY |
 	      DP_AUX_CH_CTL_DONE |
 	      DP_AUX_CH_CTL_INTERRUPT |
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 892d7db7d94f..35cda72492d7 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -81,6 +81,18 @@ static void intel_dp_read_lttpr_phy_caps(struct intel_dp *intel_dp,
 
 static bool intel_dp_read_lttpr_common_caps(struct intel_dp *intel_dp)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
+	if (intel_dp_is_edp(intel_dp))
+		return false;
+
+	/*
+	 * Detecting LTTPRs must be avoided on platforms with an AUX timeout
+	 * period < 3.2ms. (see DP Standard v2.0, 2.11.2, 3.6.6.1).
+	 */
+	if (INTEL_GEN(i915) < 10)
+		return false;
+
 	if (drm_dp_read_lttpr_common_caps(&intel_dp->aux,
 					  intel_dp->lttpr_common_caps) < 0) {
 		memset(intel_dp->lttpr_common_caps, 0,
@@ -126,9 +138,6 @@ int intel_dp_lttpr_init(struct intel_dp *intel_dp)
 	bool ret;
 	int i;
 
-	if (intel_dp_is_edp(intel_dp))
-		return 0;
-
 	ret = intel_dp_read_lttpr_common_caps(intel_dp);
 	if (!ret)
 		return 0;

From 7dffbdedb96a076843719d4ea5b2cd666481c416 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 17 Mar 2021 21:01:49 +0200
Subject: [PATCH 1183/1820] drm/i915: Disable LTTPR support when the DPCD rev <
 1.4
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

By the specification the 0xF0000-0xF02FF range is only valid when the
DPCD revision is 1.4 or higher. Disable LTTPR support if this isn't so.

Trying to detect LTTPRs returned corrupted values for the above DPCD
range at least on a Skylake host with an LG 43UD79-B monitor with a DPCD
revision 1.2 connected.

v2: Add the actual version check.
v3: Fix s/DRPX/DPRX/ typo.

Fixes: 7b2a4ab8b0ef ("drm/i915: Switch to LTTPR transparent mode link training")
Cc: <stable@vger.kernel.org> # v5.11
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210317190149.4032966-1-imre.deak@intel.com
(cherry picked from commit 264613b406eb0d74cd9ca582c717c5e2c5a975ea)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp.c       |  4 +-
 .../drm/i915/display/intel_dp_link_training.c | 48 ++++++++++++++-----
 .../drm/i915/display/intel_dp_link_training.h |  2 +-
 3 files changed, 39 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 8c12d5375607..775d89b6c3fc 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -3619,9 +3619,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 {
 	int ret;
 
-	intel_dp_lttpr_init(intel_dp);
-
-	if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd))
+	if (intel_dp_init_lttpr_and_dprx_caps(intel_dp) < 0)
 		return false;
 
 	/*
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 35cda72492d7..c10e81a3d64f 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -34,6 +34,11 @@ intel_dp_dump_link_status(const u8 link_status[DP_LINK_STATUS_SIZE])
 		      link_status[3], link_status[4], link_status[5]);
 }
 
+static void intel_dp_reset_lttpr_common_caps(struct intel_dp *intel_dp)
+{
+	memset(&intel_dp->lttpr_common_caps, 0, sizeof(intel_dp->lttpr_common_caps));
+}
+
 static void intel_dp_reset_lttpr_count(struct intel_dp *intel_dp)
 {
 	intel_dp->lttpr_common_caps[DP_PHY_REPEATER_CNT -
@@ -95,8 +100,7 @@ static bool intel_dp_read_lttpr_common_caps(struct intel_dp *intel_dp)
 
 	if (drm_dp_read_lttpr_common_caps(&intel_dp->aux,
 					  intel_dp->lttpr_common_caps) < 0) {
-		memset(intel_dp->lttpr_common_caps, 0,
-		       sizeof(intel_dp->lttpr_common_caps));
+		intel_dp_reset_lttpr_common_caps(intel_dp);
 		return false;
 	}
 
@@ -118,30 +122,49 @@ intel_dp_set_lttpr_transparent_mode(struct intel_dp *intel_dp, bool enable)
 }
 
 /**
- * intel_dp_lttpr_init - detect LTTPRs and init the LTTPR link training mode
+ * intel_dp_init_lttpr_and_dprx_caps - detect LTTPR and DPRX caps, init the LTTPR link training mode
  * @intel_dp: Intel DP struct
  *
- * Read the LTTPR common capabilities, switch to non-transparent link training
- * mode if any is detected and read the PHY capabilities for all detected
- * LTTPRs. In case of an LTTPR detection error or if the number of
+ * Read the LTTPR common and DPRX capabilities and switch to non-transparent
+ * link training mode if any is detected and read the PHY capabilities for all
+ * detected LTTPRs. In case of an LTTPR detection error or if the number of
  * LTTPRs is more than is supported (8), fall back to the no-LTTPR,
  * transparent mode link training mode.
  *
  * Returns:
- *   >0  if LTTPRs were detected and the non-transparent LT mode was set
+ *   >0  if LTTPRs were detected and the non-transparent LT mode was set. The
+ *       DPRX capabilities are read out.
  *    0  if no LTTPRs or more than 8 LTTPRs were detected or in case of a
- *       detection failure and the transparent LT mode was set
+ *       detection failure and the transparent LT mode was set. The DPRX
+ *       capabilities are read out.
+ *   <0  Reading out the DPRX capabilities failed.
  */
-int intel_dp_lttpr_init(struct intel_dp *intel_dp)
+int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp)
 {
 	int lttpr_count;
 	bool ret;
 	int i;
 
 	ret = intel_dp_read_lttpr_common_caps(intel_dp);
+
+	/* The DPTX shall read the DPRX caps after LTTPR detection. */
+	if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd)) {
+		intel_dp_reset_lttpr_common_caps(intel_dp);
+		return -EIO;
+	}
+
 	if (!ret)
 		return 0;
 
+	/*
+	 * The 0xF0000-0xF02FF range is only valid if the DPCD revision is
+	 * at least 1.4.
+	 */
+	if (intel_dp->dpcd[DP_DPCD_REV] < 0x14) {
+		intel_dp_reset_lttpr_common_caps(intel_dp);
+		return 0;
+	}
+
 	lttpr_count = drm_dp_lttpr_count(intel_dp->lttpr_common_caps);
 	/*
 	 * Prevent setting LTTPR transparent mode explicitly if no LTTPRs are
@@ -181,7 +204,7 @@ int intel_dp_lttpr_init(struct intel_dp *intel_dp)
 
 	return lttpr_count;
 }
-EXPORT_SYMBOL(intel_dp_lttpr_init);
+EXPORT_SYMBOL(intel_dp_init_lttpr_and_dprx_caps);
 
 static u8 dp_voltage_max(u8 preemph)
 {
@@ -816,7 +839,10 @@ void intel_dp_start_link_train(struct intel_dp *intel_dp,
 	 * TODO: Reiniting LTTPRs here won't be needed once proper connector
 	 * HW state readout is added.
 	 */
-	int lttpr_count = intel_dp_lttpr_init(intel_dp);
+	int lttpr_count = intel_dp_init_lttpr_and_dprx_caps(intel_dp);
+
+	if (lttpr_count < 0)
+		return;
 
 	if (!intel_dp_link_train_all_phys(intel_dp, crtc_state, lttpr_count))
 		intel_dp_schedule_fallback_link_training(intel_dp, crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.h b/drivers/gpu/drm/i915/display/intel_dp_link_training.h
index 6a1f76bd8c75..9cb7c28027f0 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.h
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.h
@@ -11,7 +11,7 @@
 struct intel_crtc_state;
 struct intel_dp;
 
-int intel_dp_lttpr_init(struct intel_dp *intel_dp);
+int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp);
 
 void intel_dp_get_adjust_train(struct intel_dp *intel_dp,
 			       const struct intel_crtc_state *crtc_state,

From ab03631087f5c296030dd86265ea02dcdacc6802 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 17 Mar 2021 20:49:01 +0200
Subject: [PATCH 1184/1820] drm/i915: Disable LTTPR support when the LTTPR rev
 < 1.4
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

By the specification the 0xF0000 - 0xF02FF range is only valid if the
LTTPR revision at 0xF0000 is at least 1.4. Disable the LTTPR support
otherwise.

Fixes: 7b2a4ab8b0ef ("drm/i915: Switch to LTTPR transparent mode link training")
Cc: <stable@vger.kernel.org> # v5.11
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210317184901.4029798-4-imre.deak@intel.com
(cherry picked from commit 1663ad4936e0679443a315fe342f99636a2420dd)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 .../gpu/drm/i915/display/intel_dp_link_training.c  | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index c10e81a3d64f..be6ac0dd846e 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -99,17 +99,23 @@ static bool intel_dp_read_lttpr_common_caps(struct intel_dp *intel_dp)
 		return false;
 
 	if (drm_dp_read_lttpr_common_caps(&intel_dp->aux,
-					  intel_dp->lttpr_common_caps) < 0) {
-		intel_dp_reset_lttpr_common_caps(intel_dp);
-		return false;
-	}
+					  intel_dp->lttpr_common_caps) < 0)
+		goto reset_caps;
 
 	drm_dbg_kms(&dp_to_i915(intel_dp)->drm,
 		    "LTTPR common capabilities: %*ph\n",
 		    (int)sizeof(intel_dp->lttpr_common_caps),
 		    intel_dp->lttpr_common_caps);
 
+	/* The minimum value of LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV is 1.4 */
+	if (intel_dp->lttpr_common_caps[0] < 0x14)
+		goto reset_caps;
+
 	return true;
+
+reset_caps:
+	intel_dp_reset_lttpr_common_caps(intel_dp);
+	return false;
 }
 
 static bool

From ff2628ed95e42d5245119eed3c1f669db9222285 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Fri, 5 Mar 2021 17:36:05 +0200
Subject: [PATCH 1185/1820] drm/i915: Fix enabled_planes bitmask
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The enabled_planes bitmask was supposed to track logically enabled
planes (ie. fb!=NULL and crtc!=NULL), but instead we end up putting
even disabled planes into the bitmask since
intel_plane_atomic_check_with_state() only takes the early exit
if the plane was disabled and stays disabled. I think I misread
the early said codepath to exit whenever the plane is logically
disabled, which is not true.

So let's fix this up properly and set the bit only when the plane
actually is logically enabled.

Cc: Manasi Navare <manasi.d.navare@intel.com>
Fixes: ee42ec19ca2e ("drm/i915: Track logically enabled planes for hw state")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210305153610.12177-2-ville.syrjala@linux.intel.com
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
(cherry picked from commit 97bc7ffa1b1e9a8672e0a8e9a96680b0c3717427)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_atomic_plane.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index 4683f98f7e54..c3f2962aa1eb 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -317,12 +317,13 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 	if (!new_plane_state->hw.crtc && !old_plane_state->hw.crtc)
 		return 0;
 
-	new_crtc_state->enabled_planes |= BIT(plane->id);
-
 	ret = plane->check_plane(new_crtc_state, new_plane_state);
 	if (ret)
 		return ret;
 
+	if (fb)
+		new_crtc_state->enabled_planes |= BIT(plane->id);
+
 	/* FIXME pre-g4x don't work like this */
 	if (new_plane_state->uapi.visible)
 		new_crtc_state->active_planes |= BIT(plane->id);

From b61fde1beb6b1847f1743e75f4d9839acebad76a Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 19 Mar 2021 13:53:33 +0200
Subject: [PATCH 1186/1820] drm/i915/dsc: fix DSS CTL register usage for ICL
 DSI transcoders

Use the correct DSS CTL registers for ICL DSI transcoders.

As a side effect, this also brings back the sanity check for trying to
use pipe DSC registers on pipe A on ICL.

Fixes: 8a029c113b17 ("drm/i915/dp: Modify VDSC helpers to configure DSC for Bigjoiner slave")
References: http://lore.kernel.org/r/87eegxq2lq.fsf@intel.com
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Animesh Manna <animesh.manna@intel.com>
Cc: Vandita Kulkarni <vandita.kulkarni@intel.com>
Cc: <stable@vger.kernel.org> # v5.11+
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210319115333.8330-1-jani.nikula@intel.com
(cherry picked from commit 5706d02871240fdba7ddd6ab1cc31672fc95a90f)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_vdsc.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c
index f58cc5700784..a86c57d117f2 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.c
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.c
@@ -1014,20 +1014,14 @@ static i915_reg_t dss_ctl1_reg(const struct intel_crtc_state *crtc_state)
 {
 	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
 
-	if (crtc_state->cpu_transcoder == TRANSCODER_EDP)
-		return DSS_CTL1;
-
-	return ICL_PIPE_DSS_CTL1(pipe);
+	return is_pipe_dsc(crtc_state) ? ICL_PIPE_DSS_CTL1(pipe) : DSS_CTL1;
 }
 
 static i915_reg_t dss_ctl2_reg(const struct intel_crtc_state *crtc_state)
 {
 	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
 
-	if (crtc_state->cpu_transcoder == TRANSCODER_EDP)
-		return DSS_CTL2;
-
-	return ICL_PIPE_DSS_CTL2(pipe);
+	return is_pipe_dsc(crtc_state) ? ICL_PIPE_DSS_CTL2(pipe) : DSS_CTL2;
 }
 
 void intel_dsc_enable(struct intel_encoder *encoder,

From 7180495cb3d0e2a2860d282a468b4146c21da78f Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 22 Mar 2021 16:53:11 +0100
Subject: [PATCH 1187/1820] USB: cdc-acm: fix double free on probe failure

If tty-device registration fails the driver copy of any Country
Selection functional descriptor would end up being freed twice; first
explicitly in the error path and then again in the tty-port destructor.

Drop the first erroneous free that was left when fixing a tty-port
resource leak.

Fixes: cae2bc768d17 ("usb: cdc-acm: Decrement tty port's refcount if probe() fail")
Cc: stable@vger.kernel.org      # 4.19
Cc: Jaejoong Kim <climbbb.kim@gmail.com>
Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20210322155318.9837-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index fd2fce072985..d5fbb943c4c1 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1521,7 +1521,6 @@ alloc_fail6:
 				&dev_attr_wCountryCodes);
 		device_remove_file(&acm->control->dev,
 				&dev_attr_iCountryCodeRelDate);
-		kfree(acm->country_codes);
 	}
 	device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities);
 alloc_fail5:

From 4e49bf376c0451ad2eae2592e093659cde12be9a Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 22 Mar 2021 16:53:12 +0100
Subject: [PATCH 1188/1820] USB: cdc-acm: fix use-after-free after probe
 failure

If tty-device registration fails the driver would fail to release the
data interface. When the device is later disconnected, the disconnect
callback would still be called for the data interface and would go about
releasing already freed resources.

Fixes: c93d81955005 ("usb: cdc-acm: fix error handling in acm_probe()")
Cc: stable@vger.kernel.org      # 3.9
Cc: Alexey Khoroshilov <khoroshilov@ispras.ru>
Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20210322155318.9837-3-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index d5fbb943c4c1..6decf8f2b9ae 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1516,6 +1516,11 @@ skip_countries:
 
 	return 0;
 alloc_fail6:
+	if (!acm->combined_interfaces) {
+		/* Clear driver data so that disconnect() returns early. */
+		usb_set_intfdata(data_interface, NULL);
+		usb_driver_release_interface(&acm_driver, data_interface);
+	}
 	if (acm->country_codes) {
 		device_remove_file(&acm->control->dev,
 				&dev_attr_wCountryCodes);

From 8111a8cbd5dde0b6ea8c388ff4840d4e465b5edd Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 22 Mar 2021 16:53:13 +0100
Subject: [PATCH 1189/1820] USB: cdc-acm: drop redundant driver-data assignment

The interface driver data has already been set by
usb_driver_claim_interface() so drop the redundant subsequent
assignment.

Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20210322155318.9837-4-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 6decf8f2b9ae..d73570d31ed8 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1500,7 +1500,6 @@ skip_countries:
 	acm_set_line(acm, &acm->line);
 
 	usb_driver_claim_interface(&acm_driver, data_interface, acm);
-	usb_set_intfdata(data_interface, acm);
 
 	tty_dev = tty_port_register_device(&acm->port, acm_tty_driver, minor,
 			&control_interface->dev);

From dda6faaa2bdadc56b9ad034602307a51d11e26a7 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 22 Mar 2021 16:53:14 +0100
Subject: [PATCH 1190/1820] USB: cdc-acm: drop redundant driver-data reset

There's no need to clear the interface driver data on failed probe (and
driver core will clear it anyway).

Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20210322155318.9837-5-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index d73570d31ed8..104e10b4ebfa 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1528,7 +1528,6 @@ alloc_fail6:
 	}
 	device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities);
 alloc_fail5:
-	usb_set_intfdata(intf, NULL);
 	for (i = 0; i < ACM_NW; i++)
 		usb_free_urb(acm->wb[i].urb);
 alloc_fail4:

From 4cde059acd11e79b205525e5fd66175d8576ec88 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 22 Mar 2021 16:53:15 +0100
Subject: [PATCH 1191/1820] USB: cdc-acm: clean up probe error labels

Name the probe error labels after what they do rather than using
sequence numbers which is harder to review and maintain (e.g. may
require renaming unrelated labels when a label is added or removed).

Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20210322155318.9837-6-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 35 ++++++++++++++++++-----------------
 1 file changed, 18 insertions(+), 17 deletions(-)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 104e10b4ebfa..4844f50e54de 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1337,7 +1337,7 @@ made_compressed_probe:
 
 	acm = kzalloc(sizeof(struct acm), GFP_KERNEL);
 	if (acm == NULL)
-		goto alloc_fail;
+		return -ENOMEM;
 
 	tty_port_init(&acm->port);
 	acm->port.ops = &acm_port_ops;
@@ -1354,7 +1354,7 @@ made_compressed_probe:
 
 	minor = acm_alloc_minor(acm);
 	if (minor < 0)
-		goto alloc_fail1;
+		goto err_put_port;
 
 	acm->minor = minor;
 	acm->dev = usb_dev;
@@ -1385,15 +1385,15 @@ made_compressed_probe:
 
 	buf = usb_alloc_coherent(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma);
 	if (!buf)
-		goto alloc_fail1;
+		goto err_put_port;
 	acm->ctrl_buffer = buf;
 
 	if (acm_write_buffers_alloc(acm) < 0)
-		goto alloc_fail2;
+		goto err_free_ctrl_buffer;
 
 	acm->ctrlurb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!acm->ctrlurb)
-		goto alloc_fail3;
+		goto err_free_write_buffers;
 
 	for (i = 0; i < num_rx_buf; i++) {
 		struct acm_rb *rb = &(acm->read_buffers[i]);
@@ -1402,13 +1402,13 @@ made_compressed_probe:
 		rb->base = usb_alloc_coherent(acm->dev, readsize, GFP_KERNEL,
 								&rb->dma);
 		if (!rb->base)
-			goto alloc_fail4;
+			goto err_free_read_urbs;
 		rb->index = i;
 		rb->instance = acm;
 
 		urb = usb_alloc_urb(0, GFP_KERNEL);
 		if (!urb)
-			goto alloc_fail4;
+			goto err_free_read_urbs;
 
 		urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
 		urb->transfer_dma = rb->dma;
@@ -1430,7 +1430,7 @@ made_compressed_probe:
 
 		snd->urb = usb_alloc_urb(0, GFP_KERNEL);
 		if (snd->urb == NULL)
-			goto alloc_fail5;
+			goto err_free_write_urbs;
 
 		if (usb_endpoint_xfer_int(epwrite))
 			usb_fill_int_urb(snd->urb, usb_dev, acm->out,
@@ -1448,7 +1448,7 @@ made_compressed_probe:
 
 	i = device_create_file(&intf->dev, &dev_attr_bmCapabilities);
 	if (i < 0)
-		goto alloc_fail5;
+		goto err_free_write_urbs;
 
 	if (h.usb_cdc_country_functional_desc) { /* export the country data */
 		struct usb_cdc_country_functional_desc * cfd =
@@ -1505,7 +1505,7 @@ skip_countries:
 			&control_interface->dev);
 	if (IS_ERR(tty_dev)) {
 		rv = PTR_ERR(tty_dev);
-		goto alloc_fail6;
+		goto err_release_data_interface;
 	}
 
 	if (quirks & CLEAR_HALT_CONDITIONS) {
@@ -1514,7 +1514,8 @@ skip_countries:
 	}
 
 	return 0;
-alloc_fail6:
+
+err_release_data_interface:
 	if (!acm->combined_interfaces) {
 		/* Clear driver data so that disconnect() returns early. */
 		usb_set_intfdata(data_interface, NULL);
@@ -1527,21 +1528,21 @@ alloc_fail6:
 				&dev_attr_iCountryCodeRelDate);
 	}
 	device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities);
-alloc_fail5:
+err_free_write_urbs:
 	for (i = 0; i < ACM_NW; i++)
 		usb_free_urb(acm->wb[i].urb);
-alloc_fail4:
+err_free_read_urbs:
 	for (i = 0; i < num_rx_buf; i++)
 		usb_free_urb(acm->read_urbs[i]);
 	acm_read_buffers_free(acm);
 	usb_free_urb(acm->ctrlurb);
-alloc_fail3:
+err_free_write_buffers:
 	acm_write_buffers_free(acm);
-alloc_fail2:
+err_free_ctrl_buffer:
 	usb_free_coherent(usb_dev, ctrlsize, acm->ctrl_buffer, acm->ctrl_dma);
-alloc_fail1:
+err_put_port:
 	tty_port_put(&acm->port);
-alloc_fail:
+
 	return rv;
 }
 

From f8255ee192e92fdb885a9ff6bc90d74f5bfb7cd6 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 22 Mar 2021 16:53:16 +0100
Subject: [PATCH 1192/1820] USB: cdc-acm: use negation for NULL checks

Use negation consistently throughout the driver for NULL checks.

Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20210322155318.9837-7-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 4844f50e54de..1f0fcabef5d2 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1336,7 +1336,7 @@ made_compressed_probe:
 	dev_dbg(&intf->dev, "interfaces are valid\n");
 
 	acm = kzalloc(sizeof(struct acm), GFP_KERNEL);
-	if (acm == NULL)
+	if (!acm)
 		return -ENOMEM;
 
 	tty_port_init(&acm->port);
@@ -1429,7 +1429,7 @@ made_compressed_probe:
 		struct acm_wb *snd = &(acm->wb[i]);
 
 		snd->urb = usb_alloc_urb(0, GFP_KERNEL);
-		if (snd->urb == NULL)
+		if (!snd->urb)
 			goto err_free_write_urbs;
 
 		if (usb_endpoint_xfer_int(epwrite))

From 0b2b23ca20ac9329d91bdba713028cf279423383 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 22 Mar 2021 16:53:17 +0100
Subject: [PATCH 1193/1820] USB: cdc-acm: always claim data interface

Make sure to always claim the data interface and bail out if binding
fails.

Note that the driver had a check to verify that the data interface was
not already bound to a driver but would not detect other failures (e.g.
if the interface was not authorised).

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20210322155318.9837-8-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 1f0fcabef5d2..5ce525d22425 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1309,13 +1309,6 @@ skip_normal_probe:
 	if (!combined_interfaces && intf != control_interface)
 		return -ENODEV;
 
-	if (!combined_interfaces && usb_interface_claimed(data_interface)) {
-		/* valid in this context */
-		dev_dbg(&intf->dev, "The data interface isn't available\n");
-		return -EBUSY;
-	}
-
-
 	if (data_interface->cur_altsetting->desc.bNumEndpoints < 2 ||
 	    control_interface->cur_altsetting->desc.bNumEndpoints == 0)
 		return -EINVAL;
@@ -1499,7 +1492,11 @@ skip_countries:
 	acm->line.bDataBits = 8;
 	acm_set_line(acm, &acm->line);
 
-	usb_driver_claim_interface(&acm_driver, data_interface, acm);
+	if (!acm->combined_interfaces) {
+		rv = usb_driver_claim_interface(&acm_driver, data_interface, acm);
+		if (rv)
+			goto err_remove_files;
+	}
 
 	tty_dev = tty_port_register_device(&acm->port, acm_tty_driver, minor,
 			&control_interface->dev);
@@ -1521,6 +1518,7 @@ err_release_data_interface:
 		usb_set_intfdata(data_interface, NULL);
 		usb_driver_release_interface(&acm_driver, data_interface);
 	}
+err_remove_files:
 	if (acm->country_codes) {
 		device_remove_file(&acm->control->dev,
 				&dev_attr_wCountryCodes);

From 79579411826647fd573dbe301c4d933bc90e4be7 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 22 Mar 2021 16:53:18 +0100
Subject: [PATCH 1194/1820] USB: cdc-acm: do not log successful probe on later
 errors

Do not log the successful-probe message until the tty device has been
registered.

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20210322155318.9837-9-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 5ce525d22425..3fda1ec961d7 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1486,8 +1486,6 @@ skip_countries:
 	acm->nb_index = 0;
 	acm->nb_size = 0;
 
-	dev_info(&intf->dev, "ttyACM%d: USB ACM device\n", minor);
-
 	acm->line.dwDTERate = cpu_to_le32(9600);
 	acm->line.bDataBits = 8;
 	acm_set_line(acm, &acm->line);
@@ -1510,6 +1508,8 @@ skip_countries:
 		usb_clear_halt(usb_dev, acm->out);
 	}
 
+	dev_info(&intf->dev, "ttyACM%d: USB ACM device\n", minor);
+
 	return 0;
 
 err_release_data_interface:

From 0bd860493f81eb2a46173f6f5e44cc38331c8dbd Mon Sep 17 00:00:00 2001
From: Vincent Palatin <vpalatin@chromium.org>
Date: Fri, 19 Mar 2021 13:48:02 +0100
Subject: [PATCH 1195/1820] USB: quirks: ignore remote wake-up on Fibocom
 L850-GL LTE modem

This LTE modem (M.2 card) has a bug in its power management:
there is some kind of race condition for U3 wake-up between the host and
the device. The modem firmware sometimes crashes/locks when both events
happen at the same time and the modem fully drops off the USB bus (and
sometimes re-enumerates, sometimes just gets stuck until the next
reboot).

Tested with the modem wired to the XHCI controller on an AMD 3015Ce
platform. Without the patch, the modem dropped of the USB bus 5 times in
3 days. With the quirk, it stayed connected for a week while the
'runtime_suspended_time' counter incremented as excepted.

Signed-off-by: Vincent Palatin <vpalatin@chromium.org>
Link: https://lore.kernel.org/r/20210319124802.2315195-1-vpalatin@chromium.org
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 6ade3daf7858..76ac5d6555ae 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -498,6 +498,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* DJI CineSSD */
 	{ USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* Fibocom L850-GL LTE Modem */
+	{ USB_DEVICE(0x2cb7, 0x0007), .driver_info =
+			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
 	/* INTEL VALUE SSD */
 	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
 

From 72ad25fbbb78930f892b191637359ab5b94b3190 Mon Sep 17 00:00:00 2001
From: Atul Gopinathan <atulgopinathan@gmail.com>
Date: Tue, 23 Mar 2021 17:04:12 +0530
Subject: [PATCH 1196/1820] staging: rtl8192e: Fix incorrect source in memcpy()

The variable "info_element" is of the following type:

	struct rtllib_info_element *info_element

defined in drivers/staging/rtl8192e/rtllib.h:

	struct rtllib_info_element {
		u8 id;
		u8 len;
		u8 data[];
	} __packed;

The "len" field defines the size of the "data[]" array. The code is
supposed to check if "info_element->len" is greater than 4 and later
equal to 6. If this is satisfied then, the last two bytes (the 4th and
5th element of u8 "data[]" array) are copied into "network->CcxRmState".

Right now the code uses "memcpy()" with the source as "&info_element[4]"
which would copy in wrong and unintended information. The struct
"rtllib_info_element" has a size of 2 bytes for "id" and "len",
therefore indexing will be done in interval of 2 bytes. So,
"info_element[4]" would point to data which is beyond the memory
allocated for this pointer (that is, at x+8, while "info_element" has
been allocated only from x to x+7 (2 + 6 => 8 bytes)).

This patch rectifies this error by using "&info_element->data[4]" which
correctly copies the last two bytes of "data[]".

NOTE: The faulty line of code came from the following commit:

commit ecdfa44610fa ("Staging: add Realtek 8192 PCI wireless driver")

The above commit created the file `rtl8192e/ieee80211/ieee80211_rx.c`
which had the faulty line of code. This file has been deleted (or
possibly renamed) with the contents copied in to a new file
`rtl8192e/rtllib_rx.c` along with additional code in the commit
94a799425eee (tagged in Fixes).

Fixes: 94a799425eee ("From: wlanfae <wlanfae@realtek.com> [PATCH 1/8] rtl8192e: Import new version of driver from realtek")
Cc: stable@vger.kernel.org
Signed-off-by: Atul Gopinathan <atulgopinathan@gmail.com>
Link: https://lore.kernel.org/r/20210323113413.29179-1-atulgopinathan@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c
index 66c135321da4..15bbb63ca130 100644
--- a/drivers/staging/rtl8192e/rtllib_rx.c
+++ b/drivers/staging/rtl8192e/rtllib_rx.c
@@ -1967,7 +1967,7 @@ static void rtllib_parse_mife_generic(struct rtllib_device *ieee,
 	    info_element->data[2] == 0x96 &&
 	    info_element->data[3] == 0x01) {
 		if (info_element->len == 6) {
-			memcpy(network->CcxRmState, &info_element[4], 2);
+			memcpy(network->CcxRmState, &info_element->data[4], 2);
 			if (network->CcxRmState[0] != 0)
 				network->bCcxRmEnable = true;
 			else

From e78836ae76d20f38eed8c8c67f21db97529949da Mon Sep 17 00:00:00 2001
From: Atul Gopinathan <atulgopinathan@gmail.com>
Date: Tue, 23 Mar 2021 17:04:14 +0530
Subject: [PATCH 1197/1820] staging: rtl8192e: Change state information from
 u16 to u8

The "u16 CcxRmState[2];" array field in struct "rtllib_network" has 4
bytes in total while the operations performed on this array through-out
the code base are only 2 bytes.

The "CcxRmState" field is fed only 2 bytes of data using memcpy():

(In rtllib_rx.c:1972)
	memcpy(network->CcxRmState, &info_element->data[4], 2)

With "info_element->data[]" being a u8 array, if 2 bytes are written
into "CcxRmState" (whose one element is u16 size), then the 2 u8
elements from "data[]" gets squashed and written into the first element
("CcxRmState[0]") while the second element ("CcxRmState[1]") is never
fed with any data.

Same in file rtllib_rx.c:2522:
	 memcpy(dst->CcxRmState, src->CcxRmState, 2);

The above line duplicates "src" data to "dst" but only writes 2 bytes
(and not 4, which is the actual size). Again, only 1st element gets the
value while the 2nd element remains uninitialized.

This later makes operations done with CcxRmState unpredictable in the
following lines as the 1st element is having a squashed number while the
2nd element is having an uninitialized random number.

rtllib_rx.c:1973:    if (network->CcxRmState[0] != 0)
rtllib_rx.c:1977:    network->MBssidMask = network->CcxRmState[1] & 0x07;

network->MBssidMask is also of type u8 and not u16.

Fix this by changing the type of "CcxRmState" from u16 to u8 so that the
data written into this array and read from it make sense and are not
random values.

NOTE: The wrong initialization of "CcxRmState" can be seen in the
following commit:

commit ecdfa44610fa ("Staging: add Realtek 8192 PCI wireless driver")

The above commit created a file `rtl8192e/ieee80211.h` which used to
have the faulty line. The file has been deleted (or possibly renamed)
with the contents copied in to a new file `rtl8192e/rtllib.h` along with
additional code in the commit 94a799425eee (tagged in Fixes).

Fixes: 94a799425eee ("From: wlanfae <wlanfae@realtek.com> [PATCH 1/8] rtl8192e: Import new version of driver from realtek")
Cc: stable@vger.kernel.org
Signed-off-by: Atul Gopinathan <atulgopinathan@gmail.com>
Link: https://lore.kernel.org/r/20210323113413.29179-2-atulgopinathan@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8192e/rtllib.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index b84f00b8d18b..4cabaf21c1ca 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -1105,7 +1105,7 @@ struct rtllib_network {
 	bool	bWithAironetIE;
 	bool	bCkipSupported;
 	bool	bCcxRmEnable;
-	u16	CcxRmState[2];
+	u8	CcxRmState[2];
 	bool	bMBssidValid;
 	u8	MBssidMask;
 	u8	MBssid[ETH_ALEN];

From 9d03730ecbc5afabfda26d4dbb014310bc4ea4d9 Mon Sep 17 00:00:00 2001
From: Kenneth Feng <kenneth.feng@amd.com>
Date: Thu, 11 Mar 2021 12:19:57 +0800
Subject: [PATCH 1198/1820] drm/amd/pm: workaround for audio noise issue

On some Intel platforms, audio noise can be detected due to
high pcie speed switch latency.
This patch leaverages ppfeaturemask to fix to the highest pcie
speed then disable pcie switching.

v2:
coding style fix

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 .../drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c   | 54 ++++++++++++++
 .../drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 72 ++++++++++++++++---
 .../drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c | 24 +++++++
 .../drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c | 25 +++++++
 4 files changed, 165 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index a2681fe875ed..22b6a8e8bd21 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -587,6 +587,48 @@ static int smu7_force_switch_to_arbf0(struct pp_hwmgr *hwmgr)
 			tmp, MC_CG_ARB_FREQ_F0);
 }
 
+static uint16_t smu7_override_pcie_speed(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+	uint16_t pcie_gen = 0;
+
+	if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4 &&
+	    adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN4)
+		pcie_gen = 3;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3 &&
+		adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3)
+		pcie_gen = 2;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 &&
+		adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2)
+		pcie_gen = 1;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 &&
+		adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1)
+		pcie_gen = 0;
+
+	return pcie_gen;
+}
+
+static uint16_t smu7_override_pcie_width(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+	uint16_t pcie_width = 0;
+
+	if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
+		pcie_width = 16;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12)
+		pcie_width = 12;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8)
+		pcie_width = 8;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4)
+		pcie_width = 4;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2)
+		pcie_width = 2;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1)
+		pcie_width = 1;
+
+	return pcie_width;
+}
+
 static int smu7_setup_default_pcie_table(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
@@ -683,6 +725,11 @@ static int smu7_setup_default_pcie_table(struct pp_hwmgr *hwmgr)
 					PP_Min_PCIEGen),
 			get_pcie_lane_support(data->pcie_lane_cap,
 					PP_Max_PCIELane));
+
+		if (data->pcie_dpm_key_disabled)
+			phm_setup_pcie_table_entry(&data->dpm_table.pcie_speed_table,
+				data->dpm_table.pcie_speed_table.count,
+				smu7_override_pcie_speed(hwmgr), smu7_override_pcie_width(hwmgr));
 	}
 	return 0;
 }
@@ -1248,6 +1295,13 @@ static int smu7_start_dpm(struct pp_hwmgr *hwmgr)
 						NULL)),
 				"Failed to enable pcie DPM during DPM Start Function!",
 				return -EINVAL);
+	} else {
+		PP_ASSERT_WITH_CODE(
+				(0 == smum_send_msg_to_smc(hwmgr,
+						PPSMC_MSG_PCIeDPM_Disable,
+						NULL)),
+				"Failed to disble pcie DPM during DPM Start Function!",
+				return -EINVAL);
 	}
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
index 22b636e2b89b..599ec9726601 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@@ -54,6 +54,9 @@
 #include "smuio/smuio_9_0_offset.h"
 #include "smuio/smuio_9_0_sh_mask.h"
 
+#define smnPCIE_LC_SPEED_CNTL			0x11140290
+#define smnPCIE_LC_LINK_WIDTH_CNTL		0x11140288
+
 #define HBM_MEMORY_CHANNEL_WIDTH    128
 
 static const uint32_t channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2};
@@ -443,8 +446,7 @@ static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr)
 	if (PP_CAP(PHM_PlatformCaps_VCEDPM))
 		data->smu_features[GNLD_DPM_VCE].supported = true;
 
-	if (!data->registry_data.pcie_dpm_key_disabled)
-		data->smu_features[GNLD_DPM_LINK].supported = true;
+	data->smu_features[GNLD_DPM_LINK].supported = true;
 
 	if (!data->registry_data.dcefclk_dpm_key_disabled)
 		data->smu_features[GNLD_DPM_DCEFCLK].supported = true;
@@ -1544,6 +1546,13 @@ static int vega10_override_pcie_parameters(struct pp_hwmgr *hwmgr)
 			pp_table->PcieLaneCount[i] = pcie_width;
 	}
 
+	if (data->registry_data.pcie_dpm_key_disabled) {
+		for (i = 0; i < NUM_LINK_LEVELS; i++) {
+			pp_table->PcieGenSpeed[i] = pcie_gen;
+			pp_table->PcieLaneCount[i] = pcie_width;
+		}
+	}
+
 	return 0;
 }
 
@@ -2966,6 +2975,14 @@ static int vega10_start_dpm(struct pp_hwmgr *hwmgr, uint32_t bitmap)
 		}
 	}
 
+	if (data->registry_data.pcie_dpm_key_disabled) {
+		PP_ASSERT_WITH_CODE(!vega10_enable_smc_features(hwmgr,
+				false, data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap),
+		"Attempt to Disable Link DPM feature Failed!", return -EINVAL);
+		data->smu_features[GNLD_DPM_LINK].enabled = false;
+		data->smu_features[GNLD_DPM_LINK].supported = false;
+	}
+
 	return 0;
 }
 
@@ -4584,6 +4601,24 @@ static int vega10_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfe
 	return 0;
 }
 
+static int vega10_get_current_pcie_link_width_level(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	return (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) &
+		PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
+		>> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+}
+
+static int vega10_get_current_pcie_link_speed_level(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	return (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) &
+		PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK)
+		>> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT;
+}
+
 static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, char *buf)
 {
@@ -4592,8 +4627,9 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 	struct vega10_single_dpm_table *mclk_table = &(data->dpm_table.mem_table);
 	struct vega10_single_dpm_table *soc_table = &(data->dpm_table.soc_table);
 	struct vega10_single_dpm_table *dcef_table = &(data->dpm_table.dcef_table);
-	struct vega10_pcie_table *pcie_table = &(data->dpm_table.pcie_table);
 	struct vega10_odn_clock_voltage_dependency_table *podn_vdd_dep = NULL;
+	uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width;
+	PPTable_t *pptable = &(data->smc_state_table.pp_table);
 
 	int i, now, size = 0, count = 0;
 
@@ -4650,15 +4686,31 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 					"*" : "");
 		break;
 	case PP_PCIE:
-		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentLinkIndex, &now);
+		current_gen_speed =
+			vega10_get_current_pcie_link_speed_level(hwmgr);
+		current_lane_width =
+			vega10_get_current_pcie_link_width_level(hwmgr);
+		for (i = 0; i < NUM_LINK_LEVELS; i++) {
+			gen_speed = pptable->PcieGenSpeed[i];
+			lane_width = pptable->PcieLaneCount[i];
 
-		for (i = 0; i < pcie_table->count; i++)
-			size += sprintf(buf + size, "%d: %s %s\n", i,
-					(pcie_table->pcie_gen[i] == 0) ? "2.5GT/s, x1" :
-					(pcie_table->pcie_gen[i] == 1) ? "5.0GT/s, x16" :
-					(pcie_table->pcie_gen[i] == 2) ? "8.0GT/s, x16" : "",
-					(i == now) ? "*" : "");
+			size += sprintf(buf + size, "%d: %s %s %s\n", i,
+					(gen_speed == 0) ? "2.5GT/s," :
+					(gen_speed == 1) ? "5.0GT/s," :
+					(gen_speed == 2) ? "8.0GT/s," :
+					(gen_speed == 3) ? "16.0GT/s," : "",
+					(lane_width == 1) ? "x1" :
+					(lane_width == 2) ? "x2" :
+					(lane_width == 3) ? "x4" :
+					(lane_width == 4) ? "x8" :
+					(lane_width == 5) ? "x12" :
+					(lane_width == 6) ? "x16" : "",
+					(current_gen_speed == gen_speed) &&
+					(current_lane_width == lane_width) ?
+					"*" : "");
+		}
 		break;
+
 	case OD_SCLK:
 		if (hwmgr->od_enabled) {
 			size = sprintf(buf, "%s:\n", "OD_SCLK");
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
index 43e01d880f7c..4f6da11e8f10 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
@@ -133,6 +133,7 @@ static void vega12_set_default_registry_data(struct pp_hwmgr *hwmgr)
 	data->registry_data.auto_wattman_debug = 0;
 	data->registry_data.auto_wattman_sample_period = 100;
 	data->registry_data.auto_wattman_threshold = 50;
+	data->registry_data.pcie_dpm_key_disabled = !(hwmgr->feature_mask & PP_PCIE_DPM_MASK);
 }
 
 static int vega12_set_features_platform_caps(struct pp_hwmgr *hwmgr)
@@ -539,6 +540,29 @@ static int vega12_override_pcie_parameters(struct pp_hwmgr *hwmgr)
 		pp_table->PcieLaneCount[i] = pcie_width_arg;
 	}
 
+	/* override to the highest if it's disabled from ppfeaturmask */
+	if (data->registry_data.pcie_dpm_key_disabled) {
+		for (i = 0; i < NUM_LINK_LEVELS; i++) {
+			smu_pcie_arg = (i << 16) | (pcie_gen << 8) | pcie_width;
+			ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+				PPSMC_MSG_OverridePcieParameters, smu_pcie_arg,
+				NULL);
+			PP_ASSERT_WITH_CODE(!ret,
+				"[OverridePcieParameters] Attempt to override pcie params failed!",
+				return ret);
+
+			pp_table->PcieGenSpeed[i] = pcie_gen;
+			pp_table->PcieLaneCount[i] = pcie_width;
+		}
+		ret = vega12_enable_smc_features(hwmgr,
+				false,
+				data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap);
+		PP_ASSERT_WITH_CODE(!ret,
+				"Attempt to Disable DPM LINK Failed!",
+				return ret);
+		data->smu_features[GNLD_DPM_LINK].enabled = false;
+		data->smu_features[GNLD_DPM_LINK].supported = false;
+	}
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
index f19964c69a00..b6ee3a285c9d 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
@@ -171,6 +171,7 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr)
 	data->registry_data.gfxoff_controlled_by_driver = 1;
 	data->gfxoff_allowed = false;
 	data->counter_gfxoff = 0;
+	data->registry_data.pcie_dpm_key_disabled = !(hwmgr->feature_mask & PP_PCIE_DPM_MASK);
 }
 
 static int vega20_set_features_platform_caps(struct pp_hwmgr *hwmgr)
@@ -884,6 +885,30 @@ static int vega20_override_pcie_parameters(struct pp_hwmgr *hwmgr)
 		pp_table->PcieLaneCount[i] = pcie_width_arg;
 	}
 
+	/* override to the highest if it's disabled from ppfeaturmask */
+	if (data->registry_data.pcie_dpm_key_disabled) {
+		for (i = 0; i < NUM_LINK_LEVELS; i++) {
+			smu_pcie_arg = (i << 16) | (pcie_gen << 8) | pcie_width;
+			ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+				PPSMC_MSG_OverridePcieParameters, smu_pcie_arg,
+				NULL);
+			PP_ASSERT_WITH_CODE(!ret,
+				"[OverridePcieParameters] Attempt to override pcie params failed!",
+				return ret);
+
+			pp_table->PcieGenSpeed[i] = pcie_gen;
+			pp_table->PcieLaneCount[i] = pcie_width;
+		}
+		ret = vega20_enable_smc_features(hwmgr,
+				false,
+				data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap);
+		PP_ASSERT_WITH_CODE(!ret,
+				"Attempt to Disable DPM LINK Failed!",
+				return ret);
+		data->smu_features[GNLD_DPM_LINK].enabled = false;
+		data->smu_features[GNLD_DPM_LINK].supported = false;
+	}
+
 	return 0;
 }
 

From f0acf637d60ffcef3ccb6e279f743e587b3c7359 Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Fri, 19 Mar 2021 12:04:57 +0100
Subject: [PATCH 1199/1820] driver core: clear deferred probe reason on probe
 retry

When retrying a deferred probe, any old defer reason string should be
discarded. Otherwise, if the probe is deferred again at a different spot,
but without setting a message, the now incorrect probe reason will remain.

This was observed with the i.MX I2C driver, which ultimately failed
to probe due to lack of the GPIO driver. The probe defer for GPIO
doesn't record a message, but a previous probe defer to clock_get did.
This had the effect that /sys/kernel/debug/devices_deferred listed
a misleading probe deferral reason.

Cc: stable <stable@vger.kernel.org>
Fixes: d090b70ede02 ("driver core: add deferring probe reason to devices_deferred property")
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Andrzej Hajda <a.hajda@samsung.com>
Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Link: https://lore.kernel.org/r/20210319110459.19966-1-a.fatoum@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/dd.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 9179825ff646..e2cf3b29123e 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -97,6 +97,9 @@ static void deferred_probe_work_func(struct work_struct *work)
 
 		get_device(dev);
 
+		kfree(dev->p->deferred_probe_reason);
+		dev->p->deferred_probe_reason = NULL;
+
 		/*
 		 * Drop the mutex while probing each device; the probe path may
 		 * manipulate the deferred list

From 903079a54cac47ab115fa5abbde6860cf94e258f Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Fri, 26 Feb 2021 16:42:33 +0530
Subject: [PATCH 1200/1820] MAINTAINERS: Add linux-phy list and patchwork

Linux-phy subsystem gained mailing list and a patchwork instance. Add the
details to MAINTAINERS file

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Link: https://lore.kernel.org/r/20210226111233.2601369-1-vkoul@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index aa84121c5611..cc47802933f4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7476,8 +7476,9 @@ F:	include/uapi/asm-generic/
 GENERIC PHY FRAMEWORK
 M:	Kishon Vijay Abraham I <kishon@ti.com>
 M:	Vinod Koul <vkoul@kernel.org>
-L:	linux-kernel@vger.kernel.org
+L:	linux-phy@lists.infradead.org
 S:	Supported
+Q:	https://patchwork.kernel.org/project/linux-phy/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy.git
 F:	Documentation/devicetree/bindings/phy/
 F:	drivers/phy/

From ce068bc7da473e39b64d130101e178406023df0c Mon Sep 17 00:00:00 2001
From: Tomas Winkler <tomas.winkler@intel.com>
Date: Thu, 18 Mar 2021 07:59:59 +0200
Subject: [PATCH 1201/1820] mei: allow map and unmap of client dma buffer only
 for disconnected client

Allow map and unmap of the client dma buffer only when the client is not
connected. The functions return -EPROTO if the client is already connected.
This is to fix the race when traffic may start or stop when buffer
is not available.

Cc: <stable@vger.kernel.org> #v5.11+
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Link: https://lore.kernel.org/r/20210318055959.305627-1-tomas.winkler@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/client.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 4378a9b25848..2cc370adb238 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -2286,8 +2286,8 @@ int mei_cl_dma_alloc_and_map(struct mei_cl *cl, const struct file *fp,
 	if (buffer_id == 0)
 		return -EINVAL;
 
-	if (!mei_cl_is_connected(cl))
-		return -ENODEV;
+	if (mei_cl_is_connected(cl))
+		return -EPROTO;
 
 	if (cl->dma_mapped)
 		return -EPROTO;
@@ -2327,9 +2327,7 @@ int mei_cl_dma_alloc_and_map(struct mei_cl *cl, const struct file *fp,
 
 	mutex_unlock(&dev->device_lock);
 	wait_event_timeout(cl->wait,
-			   cl->dma_mapped ||
-			   cl->status ||
-			   !mei_cl_is_connected(cl),
+			   cl->dma_mapped || cl->status,
 			   mei_secs_to_jiffies(MEI_CL_CONNECT_TIMEOUT));
 	mutex_lock(&dev->device_lock);
 
@@ -2376,8 +2374,9 @@ int mei_cl_dma_unmap(struct mei_cl *cl, const struct file *fp)
 		return -EOPNOTSUPP;
 	}
 
-	if (!mei_cl_is_connected(cl))
-		return -ENODEV;
+	/* do not allow unmap for connected client */
+	if (mei_cl_is_connected(cl))
+		return -EPROTO;
 
 	if (!cl->dma_mapped)
 		return -EPROTO;
@@ -2405,9 +2404,7 @@ int mei_cl_dma_unmap(struct mei_cl *cl, const struct file *fp)
 
 	mutex_unlock(&dev->device_lock);
 	wait_event_timeout(cl->wait,
-			   !cl->dma_mapped ||
-			   cl->status ||
-			   !mei_cl_is_connected(cl),
+			   !cl->dma_mapped || cl->status,
 			   mei_secs_to_jiffies(MEI_CL_CONNECT_TIMEOUT));
 	mutex_lock(&dev->device_lock);
 

From 01faae5193d6190b7b3aa93dae43f514e866d652 Mon Sep 17 00:00:00 2001
From: Du Cheng <ducheng2@gmail.com>
Date: Fri, 12 Mar 2021 16:14:21 +0800
Subject: [PATCH 1202/1820] drivers: video: fbcon: fix NULL dereference in
 fbcon_cursor()

add null-check on function pointer before dereference on ops->cursor

Reported-by: syzbot+b67aaae8d3a927f68d20@syzkaller.appspotmail.com
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Du Cheng <ducheng2@gmail.com>
Link: https://lore.kernel.org/r/20210312081421.452405-1-ducheng2@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/video/fbdev/core/fbcon.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 44a5cd2f54cc..3406067985b1 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -1333,6 +1333,9 @@ static void fbcon_cursor(struct vc_data *vc, int mode)
 
 	ops->cursor_flash = (mode == CM_ERASE) ? 0 : 1;
 
+	if (!ops->cursor)
+		return;
+
 	ops->cursor(vc, info, mode, get_color(vc, info, c, 1),
 		    get_color(vc, info, c, 0));
 }

From 9fcb51c14da2953de585c5c6e50697b8a6e91a7b Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 23 Mar 2021 13:48:36 +0100
Subject: [PATCH 1203/1820] x86/build: Turn off -fcf-protection for realmode
 targets
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The new Ubuntu GCC packages turn on -fcf-protection globally,
which causes a build failure in the x86 realmode code:

  cc1: error: ‘-fcf-protection’ is not compatible with this target

Turn it off explicitly on compilers that understand this option.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210323124846.1584944-1-arnd@kernel.org
---
 arch/x86/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2d6d5a28c3bf..9a85eae37b17 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -27,7 +27,7 @@ endif
 REALMODE_CFLAGS	:= -m16 -g -Os -DDISABLE_BRANCH_PROFILING \
 		   -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
-		   -mno-mmx -mno-sse
+		   -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none)
 
 REALMODE_CFLAGS += -ffreestanding
 REALMODE_CFLAGS += -fno-stack-protector

From 5116784039f0421e9a619023cfba3e302c3d9adc Mon Sep 17 00:00:00 2001
From: Chris Chiu <chris.chiu@canonical.com>
Date: Tue, 23 Mar 2021 16:52:19 +0800
Subject: [PATCH 1204/1820] block: clear GD_NEED_PART_SCAN later in
 bdev_disk_changed

The GD_NEED_PART_SCAN is set by bdev_check_media_change to initiate
a partition scan while removing a block device. It should be cleared
after blk_drop_paritions because blk_drop_paritions could return
-EBUSY and then the consequence __blkdev_get has no chance to do
delete_partition if GD_NEED_PART_SCAN already cleared.

It causes some problems on some card readers. Ex. Realtek card
reader 0bda:0328 and 0bda:0158. The device node of the partition
will not disappear after the memory card removed. Thus the user
applications can not update the device mapping correctly.

BugLink: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1920874
Signed-off-by: Chris Chiu <chris.chiu@canonical.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20210323085219.24428-1-chris.chiu@canonical.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 92ed7d5df677..28d583fcdc2c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1240,13 +1240,13 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
 
 	lockdep_assert_held(&bdev->bd_mutex);
 
-	clear_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
-
 rescan:
 	ret = blk_drop_partitions(bdev);
 	if (ret)
 		return ret;
 
+	clear_bit(GD_NEED_PART_SCAN, &disk->state);
+
 	/*
 	 * Historically we only set the capacity to zero for devices that
 	 * support partitions (independ of actually having partitions created).

From a958937ff166fc60d1c3a721036f6ff41bfa2821 Mon Sep 17 00:00:00 2001
From: David Jeffery <djeffery@redhat.com>
Date: Thu, 11 Feb 2021 09:38:07 -0500
Subject: [PATCH 1205/1820] block: recalculate segment count for multi-segment
 discards correctly

When a stacked block device inserts a request into another block device
using blk_insert_cloned_request, the request's nr_phys_segments field gets
recalculated by a call to blk_recalc_rq_segments in
blk_cloned_rq_check_limits. But blk_recalc_rq_segments does not know how to
handle multi-segment discards. For disk types which can handle
multi-segment discards like nvme, this results in discard requests which
claim a single segment when it should report several, triggering a warning
in nvme and causing nvme to fail the discard from the invalid state.

 WARNING: CPU: 5 PID: 191 at drivers/nvme/host/core.c:700 nvme_setup_discard+0x170/0x1e0 [nvme_core]
 ...
 nvme_setup_cmd+0x217/0x270 [nvme_core]
 nvme_loop_queue_rq+0x51/0x1b0 [nvme_loop]
 __blk_mq_try_issue_directly+0xe7/0x1b0
 blk_mq_request_issue_directly+0x41/0x70
 ? blk_account_io_start+0x40/0x50
 dm_mq_queue_rq+0x200/0x3e0
 blk_mq_dispatch_rq_list+0x10a/0x7d0
 ? __sbitmap_queue_get+0x25/0x90
 ? elv_rb_del+0x1f/0x30
 ? deadline_remove_request+0x55/0xb0
 ? dd_dispatch_request+0x181/0x210
 __blk_mq_do_dispatch_sched+0x144/0x290
 ? bio_attempt_discard_merge+0x134/0x1f0
 __blk_mq_sched_dispatch_requests+0x129/0x180
 blk_mq_sched_dispatch_requests+0x30/0x60
 __blk_mq_run_hw_queue+0x47/0xe0
 __blk_mq_delay_run_hw_queue+0x15b/0x170
 blk_mq_sched_insert_requests+0x68/0xe0
 blk_mq_flush_plug_list+0xf0/0x170
 blk_finish_plug+0x36/0x50
 xlog_cil_committed+0x19f/0x290 [xfs]
 xlog_cil_process_committed+0x57/0x80 [xfs]
 xlog_state_do_callback+0x1e0/0x2a0 [xfs]
 xlog_ioend_work+0x2f/0x80 [xfs]
 process_one_work+0x1b6/0x350
 worker_thread+0x53/0x3e0
 ? process_one_work+0x350/0x350
 kthread+0x11b/0x140
 ? __kthread_bind_mask+0x60/0x60
 ret_from_fork+0x22/0x30

This patch fixes blk_recalc_rq_segments to be aware of devices which can
have multi-segment discards. It calculates the correct discard segment
count by counting the number of bio as each discard bio is considered its
own segment.

Fixes: 1e739730c5b9 ("block: optionally merge discontiguous discard bios into a single request")
Signed-off-by: David Jeffery <djeffery@redhat.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Laurence Oberman <loberman@redhat.com>
Link: https://lore.kernel.org/r/20210211143807.GA115624@redhat
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index ffb4aa0ea68b..4d97fb6dd226 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -382,6 +382,14 @@ unsigned int blk_recalc_rq_segments(struct request *rq)
 	switch (bio_op(rq->bio)) {
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
+		if (queue_max_discard_segments(rq->q) > 1) {
+			struct bio *bio = rq->bio;
+
+			for_each_bio(bio)
+				nr_phys_segs++;
+			return nr_phys_segs;
+		}
+		return 1;
 	case REQ_OP_WRITE_ZEROES:
 		return 0;
 	case REQ_OP_WRITE_SAME:

From 927280909fa7d8e61596800d82f18047c6cfbbe4 Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Date: Mon, 22 Mar 2021 11:37:21 -0500
Subject: [PATCH 1206/1820] ASoC: SOF: Intel: HDA: fix core status verification

When checking for enabled cores it isn't enough to check that
some of the requested cores are running, we have to check that
all of them are.

Fixes: 747503b1813a ("ASoC: SOF: Intel: Add Intel specific HDA DSP HW operations")
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210322163728.16616-2-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda-dsp.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c
index c3b757cf01a0..2543ef1b5098 100644
--- a/sound/soc/sof/intel/hda-dsp.c
+++ b/sound/soc/sof/intel/hda-dsp.c
@@ -226,10 +226,17 @@ bool hda_dsp_core_is_enabled(struct snd_sof_dev *sdev,
 
 	val = snd_sof_dsp_read(sdev, HDA_DSP_BAR, HDA_DSP_REG_ADSPCS);
 
-	is_enable = (val & HDA_DSP_ADSPCS_CPA_MASK(core_mask)) &&
-		    (val & HDA_DSP_ADSPCS_SPA_MASK(core_mask)) &&
-		    !(val & HDA_DSP_ADSPCS_CRST_MASK(core_mask)) &&
-		    !(val & HDA_DSP_ADSPCS_CSTALL_MASK(core_mask));
+#define MASK_IS_EQUAL(v, m, field) ({	\
+	u32 _m = field(m);		\
+	((v) & _m) == _m;		\
+})
+
+	is_enable = MASK_IS_EQUAL(val, core_mask, HDA_DSP_ADSPCS_CPA_MASK) &&
+		MASK_IS_EQUAL(val, core_mask, HDA_DSP_ADSPCS_SPA_MASK) &&
+		!(val & HDA_DSP_ADSPCS_CRST_MASK(core_mask)) &&
+		!(val & HDA_DSP_ADSPCS_CSTALL_MASK(core_mask));
+
+#undef MASK_IS_EQUAL
 
 	dev_dbg(sdev->dev, "DSP core(s) enabled? %d : core_mask %x\n",
 		is_enable, core_mask);

From 91ec48f540f83022377723a774a0a37a630801af Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 22 Mar 2021 11:37:22 -0500
Subject: [PATCH 1207/1820] ASoC: SOF: core: harden shutdown helper

When the probe is handled in a workqueue, we must use
cancel_work_sync() in the shutdown helper to avoid possible race
conditions.

We must also take care of possible errors happening in a probe
workqueue or during pm_runtime resume (called e.g. before shutdown for
PCI devices). We should really only try to access hardware registers
and initiate IPCs if the DSP is fully booted.

Fixes: daff7f1478e12 ("ASoC: SOF: add snd_sof_device_shutdown() helper for shutdown")
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Libin Yang <libin.yang@intel.com>
Link: https://lore.kernel.org/r/20210322163728.16616-3-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/core.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c
index 6d8f7d9fd192..4a3d522f612b 100644
--- a/sound/soc/sof/core.c
+++ b/sound/soc/sof/core.c
@@ -399,7 +399,13 @@ int snd_sof_device_shutdown(struct device *dev)
 {
 	struct snd_sof_dev *sdev = dev_get_drvdata(dev);
 
-	return snd_sof_shutdown(sdev);
+	if (IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE))
+		cancel_work_sync(&sdev->probe_work);
+
+	if (sdev->fw_state == SOF_FW_BOOT_COMPLETE)
+		return snd_sof_shutdown(sdev);
+
+	return 0;
 }
 EXPORT_SYMBOL(snd_sof_device_shutdown);
 

From 3c429f861ed483517a0a352281a16503bcc60b55 Mon Sep 17 00:00:00 2001
From: Libin Yang <libin.yang@intel.com>
Date: Mon, 22 Mar 2021 11:37:23 -0500
Subject: [PATCH 1208/1820] ASoC: SOF: Intel: TGL: fix EHL ops

EHL is derived from TGL, not CNL, so we shall use the TGL ops.

Fixes: 8d4ba1be3d22 ("ASoC: SOF: pci: split PCI into different drivers")
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Libin Yang <libin.yang@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210322163728.16616-4-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/pci-tgl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/sof/intel/pci-tgl.c b/sound/soc/sof/intel/pci-tgl.c
index 485607471181..38bc353f7313 100644
--- a/sound/soc/sof/intel/pci-tgl.c
+++ b/sound/soc/sof/intel/pci-tgl.c
@@ -65,7 +65,7 @@ static const struct sof_dev_desc ehl_desc = {
 	.default_tplg_path = "intel/sof-tplg",
 	.default_fw_filename = "sof-ehl.ri",
 	.nocodec_tplg_filename = "sof-ehl-nocodec.tplg",
-	.ops = &sof_cnl_ops,
+	.ops = &sof_tgl_ops,
 };
 
 static const struct sof_dev_desc adls_desc = {

From 22aa9e021ad1ee7ce640270e75f4bdccff65d287 Mon Sep 17 00:00:00 2001
From: Libin Yang <libin.yang@intel.com>
Date: Mon, 22 Mar 2021 11:37:24 -0500
Subject: [PATCH 1209/1820] ASoC: SOF: Intel: TGL: set shutdown callback to
 hda_dsp_shutdown

According to hardware spec and PMC FW requirement, the DSP must be
in D3 state before entering S5. Define the shutdown function to use
snd_sof_suspend as shutdown callback to make sure DSP is in D3 state.

Fixes: 44a4cfad8d78 ("ASoC: SOF: Intel: tgl: do thorough remove at .shutdown() callback")
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Pan Xiuli <xiuli.pan@linux.intel.com>
Signed-off-by: Libin Yang <libin.yang@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210322163728.16616-5-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda-dsp.c | 6 ++++++
 sound/soc/sof/intel/hda.h     | 1 +
 sound/soc/sof/intel/tgl.c     | 2 +-
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c
index 2543ef1b5098..736a54beca23 100644
--- a/sound/soc/sof/intel/hda-dsp.c
+++ b/sound/soc/sof/intel/hda-dsp.c
@@ -892,6 +892,12 @@ int hda_dsp_suspend(struct snd_sof_dev *sdev, u32 target_state)
 	return snd_sof_dsp_set_power_state(sdev, &target_dsp_state);
 }
 
+int hda_dsp_shutdown(struct snd_sof_dev *sdev)
+{
+	sdev->system_suspend_target = SOF_SUSPEND_S3;
+	return snd_sof_suspend(sdev->dev);
+}
+
 int hda_dsp_set_hw_params_upon_resume(struct snd_sof_dev *sdev)
 {
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h
index 7c7579daee7f..ae80725b0e33 100644
--- a/sound/soc/sof/intel/hda.h
+++ b/sound/soc/sof/intel/hda.h
@@ -517,6 +517,7 @@ int hda_dsp_resume(struct snd_sof_dev *sdev);
 int hda_dsp_runtime_suspend(struct snd_sof_dev *sdev);
 int hda_dsp_runtime_resume(struct snd_sof_dev *sdev);
 int hda_dsp_runtime_idle(struct snd_sof_dev *sdev);
+int hda_dsp_shutdown(struct snd_sof_dev *sdev);
 int hda_dsp_set_hw_params_upon_resume(struct snd_sof_dev *sdev);
 void hda_dsp_dump(struct snd_sof_dev *sdev, u32 flags);
 void hda_ipc_dump(struct snd_sof_dev *sdev);
diff --git a/sound/soc/sof/intel/tgl.c b/sound/soc/sof/intel/tgl.c
index 419f05ba1920..3e46fac53f78 100644
--- a/sound/soc/sof/intel/tgl.c
+++ b/sound/soc/sof/intel/tgl.c
@@ -25,7 +25,7 @@ const struct snd_sof_dsp_ops sof_tgl_ops = {
 	/* probe/remove/shutdown */
 	.probe		= hda_dsp_probe,
 	.remove		= hda_dsp_remove,
-	.shutdown	= hda_dsp_remove,
+	.shutdown	= hda_dsp_shutdown,
 
 	/* Register IO */
 	.write		= sof_io_write,

From 4939e49ea5804f89941df86d35f1a1e1cd8b435b Mon Sep 17 00:00:00 2001
From: Libin Yang <libin.yang@intel.com>
Date: Mon, 22 Mar 2021 11:37:25 -0500
Subject: [PATCH 1210/1820] ASoC: SOF: Intel: ICL: set shutdown callback to
 hda_dsp_shutdown

According to hardware spec and PMC FW requirement, the DSP must be
in D3 state before entering S5. Set shutdown call to hda_dsp_shutdown.

Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Libin Yang <libin.yang@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210322163728.16616-6-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/icl.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/soc/sof/intel/icl.c b/sound/soc/sof/intel/icl.c
index e9d5a0a58504..88a74be8a0c1 100644
--- a/sound/soc/sof/intel/icl.c
+++ b/sound/soc/sof/intel/icl.c
@@ -26,9 +26,10 @@ static const struct snd_sof_debugfs_map icl_dsp_debugfs[] = {
 
 /* Icelake ops */
 const struct snd_sof_dsp_ops sof_icl_ops = {
-	/* probe and remove */
+	/* probe/remove/shutdown */
 	.probe		= hda_dsp_probe,
 	.remove		= hda_dsp_remove,
+	.shutdown	= hda_dsp_shutdown,
 
 	/* Register IO */
 	.write		= sof_io_write,

From b0503e8410e5ee43da116772576dbdeb2a414e0b Mon Sep 17 00:00:00 2001
From: Libin Yang <libin.yang@intel.com>
Date: Mon, 22 Mar 2021 11:37:26 -0500
Subject: [PATCH 1211/1820] ASoC: SOF: Intel: CNL: set shutdown callback to
 hda_dsp_shutdown

According to hardware spec and PMC FW requirement, the DSP must be
in D3 state before entering S5. Set shutdown call to hda_dsp_shutdown.

Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Libin Yang <libin.yang@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210322163728.16616-7-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/cnl.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/soc/sof/intel/cnl.c b/sound/soc/sof/intel/cnl.c
index e38db519f38d..094cde17a1b7 100644
--- a/sound/soc/sof/intel/cnl.c
+++ b/sound/soc/sof/intel/cnl.c
@@ -232,9 +232,10 @@ void cnl_ipc_dump(struct snd_sof_dev *sdev)
 
 /* cannonlake ops */
 const struct snd_sof_dsp_ops sof_cnl_ops = {
-	/* probe and remove */
+	/* probe/remove/shutdown */
 	.probe		= hda_dsp_probe,
 	.remove		= hda_dsp_remove,
+	.shutdown	= hda_dsp_shutdown,
 
 	/* Register IO */
 	.write		= sof_io_write,

From d3aa96bf349882763b9903e5800d2e83fc086886 Mon Sep 17 00:00:00 2001
From: Libin Yang <libin.yang@intel.com>
Date: Mon, 22 Mar 2021 11:37:27 -0500
Subject: [PATCH 1212/1820] ASoC: SOF: Intel: APL: set shutdown callback to
 hda_dsp_shutdown

According to hardware spec and PMC FW requirement, the DSP must be
in D3 state before entering S5. Set shutdown call to hda_dsp_shutdown.

Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Libin Yang <libin.yang@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210322163728.16616-8-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/apl.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/soc/sof/intel/apl.c b/sound/soc/sof/intel/apl.c
index fc29b91b8932..c7ed2b3d6abc 100644
--- a/sound/soc/sof/intel/apl.c
+++ b/sound/soc/sof/intel/apl.c
@@ -27,9 +27,10 @@ static const struct snd_sof_debugfs_map apl_dsp_debugfs[] = {
 
 /* apollolake ops */
 const struct snd_sof_dsp_ops sof_apl_ops = {
-	/* probe and remove */
+	/* probe/remove/shutdown */
 	.probe		= hda_dsp_probe,
 	.remove		= hda_dsp_remove,
+	.shutdown	= hda_dsp_shutdown,
 
 	/* Register IO */
 	.write		= sof_io_write,

From 8bb84ca873d2222ca220e58a097090775b1fd8df Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 22 Mar 2021 11:37:28 -0500
Subject: [PATCH 1213/1820] ASoC: SOF: Intel: move ELH chip info

ELH is a derivative of TGL, so it should be exposed in tgl.c for
consistency.

No functional change.

Reviewed-by: Rander Wang <rander.wang@intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20210322163728.16616-9-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/cnl.c | 16 ----------------
 sound/soc/sof/intel/tgl.c | 16 ++++++++++++++++
 2 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/sound/soc/sof/intel/cnl.c b/sound/soc/sof/intel/cnl.c
index 094cde17a1b7..821f25fbcf08 100644
--- a/sound/soc/sof/intel/cnl.c
+++ b/sound/soc/sof/intel/cnl.c
@@ -350,22 +350,6 @@ const struct sof_intel_dsp_desc cnl_chip_info = {
 };
 EXPORT_SYMBOL_NS(cnl_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON);
 
-const struct sof_intel_dsp_desc ehl_chip_info = {
-	/* Elkhartlake */
-	.cores_num = 4,
-	.init_core_mask = 1,
-	.host_managed_cores_mask = BIT(0),
-	.ipc_req = CNL_DSP_REG_HIPCIDR,
-	.ipc_req_mask = CNL_DSP_REG_HIPCIDR_BUSY,
-	.ipc_ack = CNL_DSP_REG_HIPCIDA,
-	.ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
-	.ipc_ctl = CNL_DSP_REG_HIPCCTL,
-	.rom_init_timeout	= 300,
-	.ssp_count = ICL_SSP_COUNT,
-	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
-};
-EXPORT_SYMBOL_NS(ehl_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON);
-
 const struct sof_intel_dsp_desc jsl_chip_info = {
 	/* Jasperlake */
 	.cores_num = 2,
diff --git a/sound/soc/sof/intel/tgl.c b/sound/soc/sof/intel/tgl.c
index 3e46fac53f78..54ba1b88ba86 100644
--- a/sound/soc/sof/intel/tgl.c
+++ b/sound/soc/sof/intel/tgl.c
@@ -156,6 +156,22 @@ const struct sof_intel_dsp_desc tglh_chip_info = {
 };
 EXPORT_SYMBOL_NS(tglh_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON);
 
+const struct sof_intel_dsp_desc ehl_chip_info = {
+	/* Elkhartlake */
+	.cores_num = 4,
+	.init_core_mask = 1,
+	.host_managed_cores_mask = BIT(0),
+	.ipc_req = CNL_DSP_REG_HIPCIDR,
+	.ipc_req_mask = CNL_DSP_REG_HIPCIDR_BUSY,
+	.ipc_ack = CNL_DSP_REG_HIPCIDA,
+	.ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
+	.ipc_ctl = CNL_DSP_REG_HIPCCTL,
+	.rom_init_timeout	= 300,
+	.ssp_count = ICL_SSP_COUNT,
+	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
+};
+EXPORT_SYMBOL_NS(ehl_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON);
+
 const struct sof_intel_dsp_desc adls_chip_info = {
 	/* Alderlake-S */
 	.cores_num = 2,

From 16b82e75c15a7dbd564ea3654f3feb61df9e1e6f Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@nxp.com>
Date: Fri, 19 Mar 2021 18:48:46 +0800
Subject: [PATCH 1214/1820] ASoC: wm8960: Fix wrong bclk and lrclk with pll
 enabled for some chips

The input MCLK is 12.288MHz, the desired output sysclk is 11.2896MHz
and sample rate is 44100Hz, with the configuration pllprescale=2,
postscale=sysclkdiv=1, some chip may have wrong bclk
and lrclk output with pll enabled in master mode, but with the
configuration pllprescale=1, postscale=2, the output clock is correct.

>From Datasheet, the PLL performs best when f2 is between
90MHz and 100MHz when the desired sysclk output is 11.2896MHz
or 12.288MHz, so sysclkdiv = 2 (f2/8) is the best choice.

So search available sysclk_divs from 2 to 1 other than from 1 to 2.

Fixes: 84fdc00d519f ("ASoC: codec: wm9860: Refactor PLL out freq search")
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/1616150926-22892-1-git-send-email-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8960.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index df351519a3a6..cda9cd935d4f 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -707,7 +707,13 @@ int wm8960_configure_pll(struct snd_soc_component *component, int freq_in,
 	best_freq_out = -EINVAL;
 	*sysclk_idx = *dac_idx = *bclk_idx = -1;
 
-	for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) {
+	/*
+	 * From Datasheet, the PLL performs best when f2 is between
+	 * 90MHz and 100MHz, the desired sysclk output is 11.2896MHz
+	 * or 12.288MHz, then sysclkdiv = 2 is the best choice.
+	 * So search sysclk_divs from 2 to 1 other than from 1 to 2.
+	 */
+	for (i = ARRAY_SIZE(sysclk_divs) - 1; i >= 0; --i) {
 		if (sysclk_divs[i] == -1)
 			continue;
 		for (j = 0; j < ARRAY_SIZE(dac_divs); ++j) {

From daa58c8eec0a65ac8e2e77ff3ea8a233d8eec954 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 23 Mar 2021 09:56:34 -0700
Subject: [PATCH 1215/1820] Input: i8042 - fix Pegatron C15B ID entry

The Zenbook Flip entry that was added overwrites a previous one
because of a typo:

In file included from drivers/input/serio/i8042.h:23,
                 from drivers/input/serio/i8042.c:131:
drivers/input/serio/i8042-x86ia64io.h:591:28: error: initialized field overwritten [-Werror=override-init]
  591 |                 .matches = {
      |                            ^
drivers/input/serio/i8042-x86ia64io.h:591:28: note: (near initialization for 'i8042_dmi_noselftest_table[0].matches')

Add the missing separator between the two.

Fixes: b5d6e7ab7fe7 ("Input: i8042 - add ASUS Zenbook Flip to noselftest list")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Marcos Paulo de Souza <mpdesouza@suse.com>
Link: https://lore.kernel.org/r/20210323130623.2302402-1-arnd@kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-x86ia64io.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 9119e12a5778..a5a003553646 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -588,6 +588,7 @@ static const struct dmi_system_id i8042_dmi_noselftest_table[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */
 		},
+	}, {
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /* Convertible Notebook */

From 69d5ff3e9e51e23d5d81bf48480aa5671be67a71 Mon Sep 17 00:00:00 2001
From: Fabian Vogt <fabian@ritter-vogt.de>
Date: Tue, 23 Mar 2021 10:45:55 -0700
Subject: [PATCH 1216/1820] Input: nspire-keypad - enable interrupts only when
 opened

The driver registers an interrupt handler in _probe, but didn't configure
them until later when the _open function is called. In between, the keypad
can fire an IRQ due to touchpad activity, which the handler ignores. This
causes the kernel to disable the interrupt, blocking the keypad from
working.

Fix this by disabling interrupts before registering the handler.
Additionally, disable them in _close, so that they're only enabled while
open.

Fixes: fc4f31461892 ("Input: add TI-Nspire keypad support")
Signed-off-by: Fabian Vogt <fabian@ritter-vogt.de>
Link: https://lore.kernel.org/r/3383725.iizBOSrK1V@linux-e202.suse.de
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/nspire-keypad.c | 56 ++++++++++++++------------
 1 file changed, 31 insertions(+), 25 deletions(-)

diff --git a/drivers/input/keyboard/nspire-keypad.c b/drivers/input/keyboard/nspire-keypad.c
index 63d5e488137d..e9fa1423f136 100644
--- a/drivers/input/keyboard/nspire-keypad.c
+++ b/drivers/input/keyboard/nspire-keypad.c
@@ -93,9 +93,15 @@ static irqreturn_t nspire_keypad_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int nspire_keypad_chip_init(struct nspire_keypad *keypad)
+static int nspire_keypad_open(struct input_dev *input)
 {
+	struct nspire_keypad *keypad = input_get_drvdata(input);
 	unsigned long val = 0, cycles_per_us, delay_cycles, row_delay_cycles;
+	int error;
+
+	error = clk_prepare_enable(keypad->clk);
+	if (error)
+		return error;
 
 	cycles_per_us = (clk_get_rate(keypad->clk) / 1000000);
 	if (cycles_per_us == 0)
@@ -121,30 +127,6 @@ static int nspire_keypad_chip_init(struct nspire_keypad *keypad)
 	keypad->int_mask = 1 << 1;
 	writel(keypad->int_mask, keypad->reg_base + KEYPAD_INTMSK);
 
-	/* Disable GPIO interrupts to prevent hanging on touchpad */
-	/* Possibly used to detect touchpad events */
-	writel(0, keypad->reg_base + KEYPAD_UNKNOWN_INT);
-	/* Acknowledge existing interrupts */
-	writel(~0, keypad->reg_base + KEYPAD_UNKNOWN_INT_STS);
-
-	return 0;
-}
-
-static int nspire_keypad_open(struct input_dev *input)
-{
-	struct nspire_keypad *keypad = input_get_drvdata(input);
-	int error;
-
-	error = clk_prepare_enable(keypad->clk);
-	if (error)
-		return error;
-
-	error = nspire_keypad_chip_init(keypad);
-	if (error) {
-		clk_disable_unprepare(keypad->clk);
-		return error;
-	}
-
 	return 0;
 }
 
@@ -152,6 +134,11 @@ static void nspire_keypad_close(struct input_dev *input)
 {
 	struct nspire_keypad *keypad = input_get_drvdata(input);
 
+	/* Disable interrupts */
+	writel(0, keypad->reg_base + KEYPAD_INTMSK);
+	/* Acknowledge existing interrupts */
+	writel(~0, keypad->reg_base + KEYPAD_INT);
+
 	clk_disable_unprepare(keypad->clk);
 }
 
@@ -210,6 +197,25 @@ static int nspire_keypad_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	error = clk_prepare_enable(keypad->clk);
+	if (error) {
+		dev_err(&pdev->dev, "failed to enable clock\n");
+		return error;
+	}
+
+	/* Disable interrupts */
+	writel(0, keypad->reg_base + KEYPAD_INTMSK);
+	/* Acknowledge existing interrupts */
+	writel(~0, keypad->reg_base + KEYPAD_INT);
+
+	/* Disable GPIO interrupts to prevent hanging on touchpad */
+	/* Possibly used to detect touchpad events */
+	writel(0, keypad->reg_base + KEYPAD_UNKNOWN_INT);
+	/* Acknowledge existing GPIO interrupts */
+	writel(~0, keypad->reg_base + KEYPAD_UNKNOWN_INT_STS);
+
+	clk_disable_unprepare(keypad->clk);
+
 	input_set_drvdata(input, keypad);
 
 	input->id.bustype = BUS_HOST;

From fb9d62b27ab1e07d625591549c314b7d406d21df Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Tue, 23 Mar 2021 14:56:08 +0000
Subject: [PATCH 1217/1820] PM: EM: postpone creating the debugfs dir till
 fs_initcall

The debugfs directory '/sys/kernel/debug/energy_model' is needed before
the Energy Model registration can happen. With the recent change in
debugfs subsystem it's not allowed to create this directory at early
stage (core_initcall). Thus creating this directory would fail.

Postpone the creation of the EM debug dir to later stage: fs_initcall.

It should be safe since all clients: CPUFreq drivers, Devfreq drivers
will be initialized in later stages.

The custom debug log below prints the time of creation the EM debug dir
at fs_initcall and successful registration of EMs at later stages.

[    1.505717] energy_model: creating rootdir
[    3.698307] cpu cpu0: EM: created perf domain
[    3.709022] cpu cpu1: EM: created perf domain

Fixes: 56348560d495 ("debugfs: do not attempt to create a new file before the filesystem is initalized")
Reported-by: Ionela Voinescu <ionela.voinescu@arm.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/power/energy_model.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 1358fa4abfa8..0f4530b3a8cd 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -98,7 +98,7 @@ static int __init em_debug_init(void)
 
 	return 0;
 }
-core_initcall(em_debug_init);
+fs_initcall(em_debug_init);
 #else /* CONFIG_DEBUG_FS */
 static void em_debug_create_pd(struct device *dev) {}
 static void em_debug_remove_pd(struct device *dev) {}

From 7547deff8a221e6bf1e563cf1b636844a8e5378a Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Tue, 16 Mar 2021 19:44:54 -0700
Subject: [PATCH 1218/1820] platform/x86: intel_pmt_class: Initial resource to
 0

Initialize the struct resource in intel_pmt_dev_register to zero to avoid a
fault should the char *name field be non-zero.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Link: https://lore.kernel.org/r/20210317024455.3071477-1-david.e.box@linux.intel.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/intel_pmt_class.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/intel_pmt_class.c b/drivers/platform/x86/intel_pmt_class.c
index c8939fba4509..ee2b3bbeb83d 100644
--- a/drivers/platform/x86/intel_pmt_class.c
+++ b/drivers/platform/x86/intel_pmt_class.c
@@ -173,7 +173,7 @@ static int intel_pmt_dev_register(struct intel_pmt_entry *entry,
 				  struct intel_pmt_namespace *ns,
 				  struct device *parent)
 {
-	struct resource res;
+	struct resource res = {0};
 	struct device *dev;
 	int ret;
 

From 10c931cdfe64ebc38a15a485dd794915044f2111 Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Tue, 16 Mar 2021 19:44:55 -0700
Subject: [PATCH 1219/1820] platform/x86: intel_pmt_crashlog: Fix incorrect
 macros

Fixes off-by-one bugs in the macro assignments for the crashlog control
bits. Was initially tested on emulation but bug revealed after testing on
silicon.

Fixes: 5ef9998c96b0 ("platform/x86: Intel PMT Crashlog capability driver")
Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Link: https://lore.kernel.org/r/20210317024455.3071477-2-david.e.box@linux.intel.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/intel_pmt_crashlog.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/platform/x86/intel_pmt_crashlog.c b/drivers/platform/x86/intel_pmt_crashlog.c
index 97dd749c8290..92d315a16cfd 100644
--- a/drivers/platform/x86/intel_pmt_crashlog.c
+++ b/drivers/platform/x86/intel_pmt_crashlog.c
@@ -23,18 +23,17 @@
 #define CRASH_TYPE_OOBMSM	1
 
 /* Control Flags */
-#define CRASHLOG_FLAG_DISABLE		BIT(27)
+#define CRASHLOG_FLAG_DISABLE		BIT(28)
 
 /*
- * Bits 28 and 29 control the state of bit 31.
+ * Bits 29 and 30 control the state of bit 31.
  *
- * Bit 28 will clear bit 31, if set, allowing a new crashlog to be captured.
- * Bit 29 will immediately trigger a crashlog to be generated, setting bit 31.
- * Bit 30 is read-only and reserved as 0.
+ * Bit 29 will clear bit 31, if set, allowing a new crashlog to be captured.
+ * Bit 30 will immediately trigger a crashlog to be generated, setting bit 31.
  * Bit 31 is the read-only status with a 1 indicating log is complete.
  */
-#define CRASHLOG_FLAG_TRIGGER_CLEAR	BIT(28)
-#define CRASHLOG_FLAG_TRIGGER_EXECUTE	BIT(29)
+#define CRASHLOG_FLAG_TRIGGER_CLEAR	BIT(29)
+#define CRASHLOG_FLAG_TRIGGER_EXECUTE	BIT(30)
 #define CRASHLOG_FLAG_TRIGGER_COMPLETE	BIT(31)
 #define CRASHLOG_FLAG_TRIGGER_MASK	GENMASK(31, 28)
 

From 269b04a50992d8defab869079049ecfc60b6b3e5 Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Fri, 19 Mar 2021 13:18:43 -0700
Subject: [PATCH 1220/1820] platform/x86: intel_pmc_core: Update Kconfig

The intel_pmc_core driver is mostly used as a debugging driver for Intel
platforms that support SLPS0 (S0ix). But the driver may also be used to
communicate actions to the PMC in order to ensure transition to SLPS0 on
some systems and architectures. As such the driver should be built on all
platforms it supports. Indicate this in the Kconfig. Also update the list
of supported features.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Suggested-by: Mario Limonciello <mario.limonciello@dell.com>
Link: https://lore.kernel.org/r/20210319201844.3305399-1-david.e.box@linux.intel.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/Kconfig | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index ad4e630e73e2..461ec61530eb 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -1173,15 +1173,20 @@ config INTEL_PMC_CORE
 	depends on PCI
 	help
 	  The Intel Platform Controller Hub for Intel Core SoCs provides access
-	  to Power Management Controller registers via a PCI interface. This
+	  to Power Management Controller registers via various interfaces. This
 	  driver can utilize debugging capabilities and supported features as
-	  exposed by the Power Management Controller.
+	  exposed by the Power Management Controller. It also may perform some
+	  tasks in the PMC in order to enable transition into the SLPS0 state.
+	  It should be selected on all Intel platforms supported by the driver.
 
 	  Supported features:
 		- SLP_S0_RESIDENCY counter
 		- PCH IP Power Gating status
-		- LTR Ignore
+		- LTR Ignore / LTR Show
 		- MPHY/PLL gating status (Sunrisepoint PCH only)
+		- SLPS0 Debug registers (Cannonlake/Icelake PCH)
+		- Low Power Mode registers (Tigerlake and beyond)
+		- PMC quirks as needed to enable SLPS0/S0ix
 
 config INTEL_PMT_CLASS
 	tristate

From d1635448f1105e549b4041aab930dbc6945fc635 Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Fri, 19 Mar 2021 13:18:44 -0700
Subject: [PATCH 1221/1820] platform/x86: intel_pmc_core: Ignore GBE LTR on
 Tiger Lake platforms

Due to a HW limitation, the Latency Tolerance Reporting (LTR) value
programmed in the Tiger Lake GBE controller is not large enough to allow
the platform to enter Package C10, which in turn prevents the platform from
achieving its low power target during suspend-to-idle.  Ignore the GBE LTR
value on Tiger Lake. LTR ignore functionality is currently performed solely
by a debugfs write call. Split out the LTR code into its own function that
can be called by both the debugfs writer and by this work around.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Reviewed-by: Sasha Neftin <sasha.neftin@intel.com>
Cc: intel-wired-lan@lists.osuosl.org
Reviewed-by: Rajneesh Bhardwaj <irenic.rajneesh@gmail.com>
Link: https://lore.kernel.org/r/20210319201844.3305399-2-david.e.box@linux.intel.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/intel_pmc_core.c | 50 +++++++++++++++++++--------
 1 file changed, 35 insertions(+), 15 deletions(-)

diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c
index ee2f757515b0..b5888aeb4bcf 100644
--- a/drivers/platform/x86/intel_pmc_core.c
+++ b/drivers/platform/x86/intel_pmc_core.c
@@ -863,34 +863,45 @@ out_unlock:
 }
 DEFINE_SHOW_ATTRIBUTE(pmc_core_pll);
 
-static ssize_t pmc_core_ltr_ignore_write(struct file *file,
-					 const char __user *userbuf,
-					 size_t count, loff_t *ppos)
+static int pmc_core_send_ltr_ignore(u32 value)
 {
 	struct pmc_dev *pmcdev = &pmc;
 	const struct pmc_reg_map *map = pmcdev->map;
-	u32 val, buf_size, fd;
-	int err;
-
-	buf_size = count < 64 ? count : 64;
-
-	err = kstrtou32_from_user(userbuf, buf_size, 10, &val);
-	if (err)
-		return err;
+	u32 reg;
+	int err = 0;
 
 	mutex_lock(&pmcdev->lock);
 
-	if (val > map->ltr_ignore_max) {
+	if (value > map->ltr_ignore_max) {
 		err = -EINVAL;
 		goto out_unlock;
 	}
 
-	fd = pmc_core_reg_read(pmcdev, map->ltr_ignore_offset);
-	fd |= (1U << val);
-	pmc_core_reg_write(pmcdev, map->ltr_ignore_offset, fd);
+	reg = pmc_core_reg_read(pmcdev, map->ltr_ignore_offset);
+	reg |= BIT(value);
+	pmc_core_reg_write(pmcdev, map->ltr_ignore_offset, reg);
 
 out_unlock:
 	mutex_unlock(&pmcdev->lock);
+
+	return err;
+}
+
+static ssize_t pmc_core_ltr_ignore_write(struct file *file,
+					 const char __user *userbuf,
+					 size_t count, loff_t *ppos)
+{
+	u32 buf_size, value;
+	int err;
+
+	buf_size = min_t(u32, count, 64);
+
+	err = kstrtou32_from_user(userbuf, buf_size, 10, &value);
+	if (err)
+		return err;
+
+	err = pmc_core_send_ltr_ignore(value);
+
 	return err == 0 ? count : err;
 }
 
@@ -1244,6 +1255,15 @@ static int pmc_core_probe(struct platform_device *pdev)
 	pmcdev->pmc_xram_read_bit = pmc_core_check_read_lock_bit();
 	dmi_check_system(pmc_core_dmi_table);
 
+	/*
+	 * On TGL, due to a hardware limitation, the GBE LTR blocks PC10 when
+	 * a cable is attached. Tell the PMC to ignore it.
+	 */
+	if (pmcdev->map == &tgl_reg_map) {
+		dev_dbg(&pdev->dev, "ignoring GBE LTR\n");
+		pmc_core_send_ltr_ignore(3);
+	}
+
 	pmc_core_dbgfs_register(pmcdev);
 
 	device_initialized = true;

From 39f985c8f667c80a3d1eb19d31138032fa36b09e Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sat, 20 Mar 2021 05:40:38 +0000
Subject: [PATCH 1222/1820] fs/cachefiles: Remove wait_bit_key layout
 dependency

Cachefiles was relying on wait_page_key and wait_bit_key being the
same layout, which is fragile.  Now that wait_page_key is exposed in
the pagemap.h header, we can remove that fragility

A comment on the need to maintain structure layout equivalence was added by
Linus[1] and that is no longer applicable.

Fixes: 62906027091f ("mm: add PageWaiters indicating tasks are waiting for a page bit")
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: kafs-testing@auristor.com
cc: linux-cachefs@redhat.com
cc: linux-mm@kvack.org
Link: https://lore.kernel.org/r/20210320054104.1300774-2-willy@infradead.org/
Link: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=3510ca20ece0150af6b10c77a74ff1b5c198e3e2 [1]
---
 fs/cachefiles/rdwr.c    | 7 +++----
 include/linux/pagemap.h | 1 -
 2 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index e027c718ca01..8ffc40e84a59 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -24,17 +24,16 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
 		container_of(wait, struct cachefiles_one_read, monitor);
 	struct cachefiles_object *object;
 	struct fscache_retrieval *op = monitor->op;
-	struct wait_bit_key *key = _key;
+	struct wait_page_key *key = _key;
 	struct page *page = wait->private;
 
 	ASSERT(key);
 
 	_enter("{%lu},%u,%d,{%p,%u}",
 	       monitor->netfs_page->index, mode, sync,
-	       key->flags, key->bit_nr);
+	       key->page, key->bit_nr);
 
-	if (key->flags != &page->flags ||
-	    key->bit_nr != PG_locked)
+	if (key->page != page || key->bit_nr != PG_locked)
 		return 0;
 
 	_debug("--- monitor %p %lx ---", page, page->flags);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 20225b067583..8f4daac6eb4b 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -559,7 +559,6 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
 	return pgoff;
 }
 
-/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */
 struct wait_page_key {
 	struct page *page;
 	int bit_nr;

From e5dbd33218bd8d87ab69f730ab90aed5fab7eb26 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sat, 20 Mar 2021 05:40:39 +0000
Subject: [PATCH 1223/1820] mm/writeback: Add wait_on_page_writeback_killable

This is the killable version of wait_on_page_writeback.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: kafs-testing@auristor.com
cc: linux-afs@lists.infradead.org
cc: linux-mm@kvack.org
Link: https://lore.kernel.org/r/20210320054104.1300774-3-willy@infradead.org
---
 include/linux/pagemap.h |  1 +
 mm/page-writeback.c     | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 8f4daac6eb4b..8c9947fd62f3 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -682,6 +682,7 @@ static inline int wait_on_page_locked_killable(struct page *page)
 
 int put_and_wait_on_page_locked(struct page *page, int state);
 void wait_on_page_writeback(struct page *page);
+int wait_on_page_writeback_killable(struct page *page);
 extern void end_page_writeback(struct page *page);
 void wait_for_stable_page(struct page *page);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index eb34d204d4ee..9e35b636a393 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2833,6 +2833,22 @@ void wait_on_page_writeback(struct page *page)
 }
 EXPORT_SYMBOL_GPL(wait_on_page_writeback);
 
+/*
+ * Wait for a page to complete writeback.  Returns -EINTR if we get a
+ * fatal signal while waiting.
+ */
+int wait_on_page_writeback_killable(struct page *page)
+{
+	while (PageWriteback(page)) {
+		trace_wait_on_page_writeback(page, page_mapping(page));
+		if (wait_on_page_bit_killable(page, PG_writeback))
+			return -EINTR;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(wait_on_page_writeback_killable);
+
 /**
  * wait_for_stable_page() - wait for writeback to finish, if necessary.
  * @page:	The page to wait on.

From 75b69799610c2b909a18e709c402923ea61aedc0 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sat, 20 Mar 2021 05:40:40 +0000
Subject: [PATCH 1224/1820] afs: Use wait_on_page_writeback_killable

Open-coding this function meant it missed out on the recent bugfix
for waiters being woken by a delayed wake event from a previous
instantiation of the page[1].

[DH: Changed the patch to use vmf->page rather than variable page which
 doesn't exist yet upstream]

Fixes: 1cf7a1518aef ("afs: Implement shared-writeable mmap")
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: kafs-testing@auristor.com
cc: linux-afs@lists.infradead.org
cc: linux-mm@kvack.org
Link: https://lore.kernel.org/r/20210320054104.1300774-4-willy@infradead.org
Link: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=c2407cf7d22d0c0d94cf20342b3b8f06f1d904e7 [1]
---
 fs/afs/write.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/afs/write.c b/fs/afs/write.c
index c9195fc67fd8..eb737ed63afb 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -851,8 +851,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 	fscache_wait_on_page_write(vnode->cache, vmf->page);
 #endif
 
-	if (PageWriteback(vmf->page) &&
-	    wait_on_page_bit_killable(vmf->page, PG_writeback) < 0)
+	if (wait_on_page_writeback_killable(vmf->page))
 		return VM_FAULT_RETRY;
 
 	if (lock_page_killable(vmf->page) < 0)

From 8ca1b090e5c9a71abeea1dda8757f4ec3811f06e Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Mon, 22 Mar 2021 15:13:22 -0300
Subject: [PATCH 1225/1820] net/sched: act_ct: clear post_ct if doing ct_clear

Invalid detection works with two distinct moments: act_ct tries to find
a conntrack entry and set post_ct true, indicating that that was
attempted. Then, when flow dissector tries to dissect CT info and no
entry is there, it knows that it was tried and no entry was found, and
synthesizes/sets
                  key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
                                  TCA_FLOWER_KEY_CT_FLAGS_INVALID;
mimicing what OVS does.

OVS has this a bit more streamlined, as it recomputes the key after
trying to find a conntrack entry for it.

Issue here is, when we have 'tc action ct clear', it didn't clear
post_ct, causing a subsequent match on 'ct_state -trk' to fail, due to
the above. The fix, thus, is to clear it.

Reproducer rules:
tc filter add dev enp130s0f0np0_0 ingress prio 1 chain 0 \
	protocol ip flower ip_proto tcp ct_state -trk \
	action ct zone 1 pipe \
	action goto chain 2
tc filter add dev enp130s0f0np0_0 ingress prio 1 chain 2 \
	protocol ip flower \
	action ct clear pipe \
	action goto chain 4
tc filter add dev enp130s0f0np0_0 ingress prio 1 chain 4 \
	protocol ip flower ct_state -trk \
	action mirred egress redirect dev enp130s0f1np1_0

With the fix, the 3rd rule matches, like it does with OVS kernel
datapath.

Fixes: 7baf2429a1a9 ("net/sched: cls_flower add CT_FLAGS_INVALID flag support")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: wenxu <wenxu@ucloud.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ct.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index f0a0aa125b00..16e888a9601d 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -945,13 +945,14 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	tcf_lastuse_update(&c->tcf_tm);
 
 	if (clear) {
+		qdisc_skb_cb(skb)->post_ct = false;
 		ct = nf_ct_get(skb, &ctinfo);
 		if (ct) {
 			nf_conntrack_put(&ct->ct_general);
 			nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
 		}
 
-		goto out;
+		goto out_clear;
 	}
 
 	family = tcf_ct_skb_nf_family(skb);
@@ -1030,8 +1031,9 @@ out_push:
 	skb_push_rcsum(skb, nh_ofs);
 
 out:
-	tcf_action_update_bstats(&c->common, skb);
 	qdisc_skb_cb(skb)->post_ct = true;
+out_clear:
+	tcf_action_update_bstats(&c->common, skb);
 	if (defrag)
 		qdisc_skb_cb(skb)->pkt_len = skb->len;
 	return retval;

From 6ab4c3117aec4e08007d9e971fa4133e1de1082d Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 22 Mar 2021 20:21:08 +0200
Subject: [PATCH 1226/1820] net: bridge: don't notify switchdev for local FDB
 addresses

As explained in this discussion:
https://lore.kernel.org/netdev/20210117193009.io3nungdwuzmo5f7@skbuf/

the switchdev notifiers for FDB entries managed to have a zero-day bug.
The bridge would not say that this entry is local:

ip link add br0 type bridge
ip link set swp0 master br0
bridge fdb add dev swp0 00:01:02:03:04:05 master local

and the switchdev driver would be more than happy to offload it as a
normal static FDB entry. This is despite the fact that 'local' and
non-'local' entries have completely opposite directions: a local entry
is locally terminated and not forwarded, whereas a static entry is
forwarded and not locally terminated. So, for example, DSA would install
this entry on swp0 instead of installing it on the CPU port as it should.

There is an even sadder part, which is that the 'local' flag is implicit
if 'static' is not specified, meaning that this command produces the
same result of adding a 'local' entry:

bridge fdb add dev swp0 00:01:02:03:04:05 master

I've updated the man pages for 'bridge', and after reading it now, it
should be pretty clear to any user that the commands above were broken
and should have never resulted in the 00:01:02:03:04:05 address being
forwarded (this behavior is coherent with non-switchdev interfaces):
https://patchwork.kernel.org/project/netdevbpf/cover/20210211104502.2081443-1-olteanv@gmail.com/
If you're a user reading this and this is what you want, just use:

bridge fdb add dev swp0 00:01:02:03:04:05 master static

Because switchdev should have given drivers the means from day one to
classify FDB entries as local/non-local, but didn't, it means that all
drivers are currently broken. So we can just as well omit the switchdev
notifications for local FDB entries, which is exactly what this patch
does to close the bug in stable trees. For further development work
where drivers might want to trap the local FDB entries to the host, we
can add a 'bool is_local' to br_switchdev_fdb_call_notifiers(), and
selectively make drivers act upon that bit, while all the others ignore
those entries if the 'is_local' bit is set.

Fixes: 6b26b51b1d13 ("net: bridge: Add support for notifying devices about FDB add/del")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_switchdev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index b89503832fcc..1e24d9a2c9a7 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -128,6 +128,8 @@ br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
 {
 	if (!fdb->dst)
 		return;
+	if (test_bit(BR_FDB_LOCAL, &fdb->flags))
+		return;
 
 	switch (type) {
 	case RTM_DELNEIGH:

From c933b111094f2818571fc51b81b98ee0d370c035 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 18 Mar 2021 16:44:10 -0400
Subject: [PATCH 1227/1820] drm/amdgpu: Add additional Sienna Cichlid PCI ID

Add new DID.

Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 1b145a29803c..e92e7dea71da 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1107,6 +1107,7 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x73A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
 	{0x1002, 0x73AB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
 	{0x1002, 0x73AE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+	{0x1002, 0x73AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
 	{0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
 
 	/* Van Gogh */

From 5c458585c0141754cdcbf25feebb547dd671b559 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 16 Feb 2021 12:22:40 -0500
Subject: [PATCH 1228/1820] drm/amdgpu/display: restore AUX_DPHY_TX_CONTROL for
 DCN2.x

Commit 098214999c8f added fetching of the AUX_DPHY register
values from the vbios, but it also changed the default values
in the case when there are no values in the vbios.  This causes
problems with displays with high refresh rates.  To fix this,
switch back to the original default value for AUX_DPHY_TX_CONTROL.

Fixes: 098214999c8f ("drm/amd/display: Read VBIOS Golden Settings Tbl")
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1426
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Igor Kravchenko <Igor.Kravchenko@amd.com>
Cc: Aric Cyr <Aric.Cyr@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
index fa013496e26b..2f9bfaeaba8d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
@@ -341,8 +341,7 @@ void enc2_hw_init(struct link_encoder *enc)
 	} else {
 		AUX_REG_WRITE(AUX_DPHY_RX_CONTROL0, 0x103d1110);
 
-		AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c4d);
-
+		AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c7a);
 	}
 
 	//AUX_DPHY_TX_REF_CONTROL'AUX_TX_REF_DIV HW default is 0x32;

From 68dc022d04eb0fd60a540e242dcb11ec1bee07e2 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 19 Mar 2021 18:27:58 +0800
Subject: [PATCH 1229/1820] xfrm: BEET mode doesn't support fragments for inner
 packets

BEET mode replaces the IP(6) Headers with new IP(6) Headers when sending
packets. However, when it's a fragment before the replacement, currently
kernel keeps the fragment flag and replace the address field then encaps
it with ESP. It would cause in RX side the fragments to get reassembled
before decapping with ESP, which is incorrect.

In Xiumei's testing, these fragments went over an xfrm interface and got
encapped with ESP in the device driver, and the traffic was broken.

I don't have a good way to fix it, but only to warn this out in dmesg.

Reported-by: Xiumei Mu <xmu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_output.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index b81ca117dac7..e4cb0ff4dcf4 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -660,6 +660,12 @@ static int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
 
+	if (x->outer_mode.encap == XFRM_MODE_BEET &&
+	    ip_is_fragment(ip_hdr(skb))) {
+		net_warn_ratelimited("BEET mode doesn't support inner IPv4 fragments\n");
+		return -EAFNOSUPPORT;
+	}
+
 	err = xfrm4_tunnel_check_size(skb);
 	if (err)
 		return err;
@@ -705,8 +711,15 @@ out:
 static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 #if IS_ENABLED(CONFIG_IPV6)
+	unsigned int ptr = 0;
 	int err;
 
+	if (x->outer_mode.encap == XFRM_MODE_BEET &&
+	    ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL) >= 0) {
+		net_warn_ratelimited("BEET mode doesn't support inner IPv6 fragments\n");
+		return -EAFNOSUPPORT;
+	}
+
 	err = xfrm6_tunnel_check_size(skb);
 	if (err)
 		return err;

From b1e3a5607034aa0a481c6f69a6893049406665fb Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 23 Mar 2021 09:26:44 +0100
Subject: [PATCH 1230/1820] xfrm: Fix NULL pointer dereference on policy lookup

When xfrm interfaces are used in combination with namespaces
and ESP offload, we get a dst_entry NULL pointer dereference.
This is because we don't have a dst_entry attached in the ESP
offloading case and we need to do a policy lookup before the
namespace transition.

Fix this by expicit checking of skb_dst(skb) before accessing it.

Fixes: f203b76d78092 ("xfrm: Add virtual xfrm interfaces")
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index bfbc7810df94..c58a6d4eb610 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1097,7 +1097,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir,
 		return __xfrm_policy_check(sk, ndir, skb, family);
 
 	return	(!net->xfrm.policy_count[dir] && !secpath_exists(skb)) ||
-		(skb_dst(skb)->flags & DST_NOPOLICY) ||
+		(skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) ||
 		__xfrm_policy_check(sk, ndir, skb, family);
 }
 

From a3efe3f6d0eb64363f74af4b0e8ba6d19415cef2 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Wed, 24 Mar 2021 12:23:58 +0200
Subject: [PATCH 1231/1820] ARM: OMAP2+: Fix warning for omap_init_time_of()

Fix warning: no previous prototype for 'omap_init_time_of'.

Fixes: e69b4e1a7577 ("ARM: OMAP2+: Add omap_init_time_of()")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/board-generic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 7290f033fd2d..1610c567a6a3 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -33,7 +33,7 @@ static void __init __maybe_unused omap_generic_init(void)
 }
 
 /* Clocks are needed early, see drivers/clocksource for the rest */
-void __init __maybe_unused omap_init_time_of(void)
+static void __init __maybe_unused omap_init_time_of(void)
 {
 	omap_clk_init();
 	timer_probe();

From a185f1db59f13de73aa470559030e90e50b34d93 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 23 Mar 2021 10:52:38 +0000
Subject: [PATCH 1232/1820] io_uring: do ctx sqd ejection in a clear context

WARNING: CPU: 1 PID: 27907 at fs/io_uring.c:7147 io_sq_thread_park+0xb5/0xd0 fs/io_uring.c:7147
CPU: 1 PID: 27907 Comm: iou-sqp-27905 Not tainted 5.12.0-rc4-syzkaller #0
RIP: 0010:io_sq_thread_park+0xb5/0xd0 fs/io_uring.c:7147
Call Trace:
 io_ring_ctx_wait_and_kill+0x214/0x700 fs/io_uring.c:8619
 io_uring_release+0x3e/0x50 fs/io_uring.c:8646
 __fput+0x288/0x920 fs/file_table.c:280
 task_work_run+0xdd/0x1a0 kernel/task_work.c:140
 io_run_task_work fs/io_uring.c:2238 [inline]
 io_run_task_work fs/io_uring.c:2228 [inline]
 io_uring_try_cancel_requests+0x8ec/0xc60 fs/io_uring.c:8770
 io_uring_cancel_sqpoll+0x1cf/0x290 fs/io_uring.c:8974
 io_sqpoll_cancel_cb+0x87/0xb0 fs/io_uring.c:8907
 io_run_task_work_head+0x58/0xb0 fs/io_uring.c:1961
 io_sq_thread+0x3e2/0x18d0 fs/io_uring.c:6763
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294

May happen that last ctx ref is killed in io_uring_cancel_sqpoll(), so
fput callback (i.e. io_uring_release()) is enqueued through task_work,
and run by same cancellation. As it's deeply nested we can't do parking
or taking sqd->lock there, because its state is unclear. So avoid
ctx ejection from sqd list from io_ring_ctx_wait_and_kill() and do it
in a clear context in io_ring_exit_work().

Fixes: f6d54255f423 ("io_uring: halt SQO submission on ctx exit")
Reported-by: syzbot+e3a3f84f5cecf61f0583@syzkaller.appspotmail.com
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/e90df88b8ff2cabb14a7534601d35d62ab4cb8c7.1616496707.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index f3ae83a2d7bc..8c5789b96dbb 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8564,6 +8564,14 @@ static void io_ring_exit_work(struct work_struct *work)
 	struct io_tctx_node *node;
 	int ret;
 
+	/* prevent SQPOLL from submitting new requests */
+	if (ctx->sq_data) {
+		io_sq_thread_park(ctx->sq_data);
+		list_del_init(&ctx->sqd_list);
+		io_sqd_update_thread_idle(ctx->sq_data);
+		io_sq_thread_unpark(ctx->sq_data);
+	}
+
 	/*
 	 * If we're doing polled IO and end up having requests being
 	 * submitted async (out-of-line), then completions can come in while
@@ -8615,14 +8623,6 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 		io_unregister_personality(ctx, index);
 	mutex_unlock(&ctx->uring_lock);
 
-	/* prevent SQPOLL from submitting new requests */
-	if (ctx->sq_data) {
-		io_sq_thread_park(ctx->sq_data);
-		list_del_init(&ctx->sqd_list);
-		io_sqd_update_thread_idle(ctx->sq_data);
-		io_sq_thread_unpark(ctx->sq_data);
-	}
-
 	io_kill_timeouts(ctx, NULL, NULL);
 	io_poll_remove_all(ctx, NULL, NULL);
 

From a1ebdb3741993f853865d1bd8f77881916ad53a7 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Wed, 24 Mar 2021 15:10:32 +0200
Subject: [PATCH 1233/1820] ARM: dts: Fix swapped mmc order for omap3

Also some omap3 devices like n900 seem to have eMMC and micro-sd swapped
around with commit 21b2cec61c04 ("mmc: Set PROBE_PREFER_ASYNCHRONOUS for
drivers that existed in v4.4").

Let's fix the issue with aliases as discussed on the mailing lists. While
the mmc aliases should be board specific, let's first fix the issue with
minimal changes.

Cc: Aaro Koskinen <aaro.koskinen@iki.fi>
Cc: Peter Ujfalusi <peter.ujfalusi@gmail.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/boot/dts/omap3.dtsi | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index 9dcae1f2bc99..c5b9da0d7e6c 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -24,6 +24,9 @@
 		i2c0 = &i2c1;
 		i2c1 = &i2c2;
 		i2c2 = &i2c3;
+		mmc0 = &mmc1;
+		mmc1 = &mmc2;
+		mmc2 = &mmc3;
 		serial0 = &uart1;
 		serial1 = &uart2;
 		serial2 = &uart3;

From 8840e3bd981f128846b01c12d3966d115e8617c9 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 22 Mar 2021 22:28:17 +0200
Subject: [PATCH 1234/1820] drm/i915: Fix the GT fence revocation runtime PM
 logic

To optimize some task deferring it until runtime resume unless someone
holds a runtime PM reference (because in this case the task can be done
w/o the overhead of runtime resume), we have to use the runtime PM
get-if-active logic: If the runtime PM usage count is 0 (and so
get-if-in-use would return false) the runtime suspend handler is not
necessarily called yet (it could be just pending), so the device is not
necessarily powered down, and so the runtime resume handler is not
guaranteed to be called.

The fence revocation depends on the above deferral, so add a
get-if-active helper and use it during fence revocation.

v2:
- Add code comment explaining the fence reg programming deferral logic
  to i915_vma_revoke_fence(). (Chris)
- Add Cc: stable and Fixes: tags. (Chris)
- Fix the function docbook comment.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: <stable@vger.kernel.org> # v4.12+
Fixes: 181df2d458f3 ("drm/i915: Take rpm wakelock for releasing the fence on unbind")
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210322204223.919936-1-imre.deak@intel.com
(cherry picked from commit 9d58aa46291d4d696bb1eac3436d3118f7bf2573)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c | 13 ++++++++-
 drivers/gpu/drm/i915/intel_runtime_pm.c      | 29 ++++++++++++++++----
 drivers/gpu/drm/i915/intel_runtime_pm.h      |  5 ++++
 3 files changed, 41 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
index a357bb431815..67de2b189598 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
@@ -316,7 +316,18 @@ void i915_vma_revoke_fence(struct i915_vma *vma)
 	WRITE_ONCE(fence->vma, NULL);
 	vma->fence = NULL;
 
-	with_intel_runtime_pm_if_in_use(fence_to_uncore(fence)->rpm, wakeref)
+	/*
+	 * Skip the write to HW if and only if the device is currently
+	 * suspended.
+	 *
+	 * If the driver does not currently hold a wakeref (if_in_use == 0),
+	 * the device may currently be runtime suspended, or it may be woken
+	 * up before the suspend takes place. If the device is not suspended
+	 * (powered down) and we skip clearing the fence register, the HW is
+	 * left in an undefined state where we may end up with multiple
+	 * registers overlapping.
+	 */
+	with_intel_runtime_pm_if_active(fence_to_uncore(fence)->rpm, wakeref)
 		fence_write(fence);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 153ca9e65382..8b725efb2254 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -412,12 +412,20 @@ intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm)
 }
 
 /**
- * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use
+ * __intel_runtime_pm_get_if_active - grab a runtime pm reference if device is active
  * @rpm: the intel_runtime_pm structure
+ * @ignore_usecount: get a ref even if dev->power.usage_count is 0
  *
  * This function grabs a device-level runtime pm reference if the device is
- * already in use and ensures that it is powered up. It is illegal to try
- * and access the HW should intel_runtime_pm_get_if_in_use() report failure.
+ * already active and ensures that it is powered up. It is illegal to try
+ * and access the HW should intel_runtime_pm_get_if_active() report failure.
+ *
+ * If @ignore_usecount=true, a reference will be acquired even if there is no
+ * user requiring the device to be powered up (dev->power.usage_count == 0).
+ * If the function returns false in this case then it's guaranteed that the
+ * device's runtime suspend hook has been called already or that it will be
+ * called (and hence it's also guaranteed that the device's runtime resume
+ * hook will be called eventually).
  *
  * Any runtime pm reference obtained by this function must have a symmetric
  * call to intel_runtime_pm_put() to release the reference again.
@@ -425,7 +433,8 @@ intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm)
  * Returns: the wakeref cookie to pass to intel_runtime_pm_put(), evaluates
  * as True if the wakeref was acquired, or False otherwise.
  */
-intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm)
+static intel_wakeref_t __intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm,
+							bool ignore_usecount)
 {
 	if (IS_ENABLED(CONFIG_PM)) {
 		/*
@@ -434,7 +443,7 @@ intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm)
 		 * function, since the power state is undefined. This applies
 		 * atm to the late/early system suspend/resume handlers.
 		 */
-		if (pm_runtime_get_if_in_use(rpm->kdev) <= 0)
+		if (pm_runtime_get_if_active(rpm->kdev, ignore_usecount) <= 0)
 			return 0;
 	}
 
@@ -443,6 +452,16 @@ intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm)
 	return track_intel_runtime_pm_wakeref(rpm);
 }
 
+intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm)
+{
+	return __intel_runtime_pm_get_if_active(rpm, false);
+}
+
+intel_wakeref_t intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm)
+{
+	return __intel_runtime_pm_get_if_active(rpm, true);
+}
+
 /**
  * intel_runtime_pm_get_noresume - grab a runtime pm reference
  * @rpm: the intel_runtime_pm structure
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.h b/drivers/gpu/drm/i915/intel_runtime_pm.h
index ae64ff14c642..1e4ddd11c12b 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.h
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.h
@@ -177,6 +177,7 @@ void intel_runtime_pm_driver_release(struct intel_runtime_pm *rpm);
 
 intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm);
 intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm);
+intel_wakeref_t intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm);
 intel_wakeref_t intel_runtime_pm_get_noresume(struct intel_runtime_pm *rpm);
 intel_wakeref_t intel_runtime_pm_get_raw(struct intel_runtime_pm *rpm);
 
@@ -188,6 +189,10 @@ intel_wakeref_t intel_runtime_pm_get_raw(struct intel_runtime_pm *rpm);
 	for ((wf) = intel_runtime_pm_get_if_in_use(rpm); (wf); \
 	     intel_runtime_pm_put((rpm), (wf)), (wf) = 0)
 
+#define with_intel_runtime_pm_if_active(rpm, wf) \
+	for ((wf) = intel_runtime_pm_get_if_active(rpm); (wf); \
+	     intel_runtime_pm_put((rpm), (wf)), (wf) = 0)
+
 void intel_runtime_pm_put_unchecked(struct intel_runtime_pm *rpm);
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
 void intel_runtime_pm_put(struct intel_runtime_pm *rpm, intel_wakeref_t wref);

From 1833b64fee1032d1f48afaa3956bc0ea6b10d5e0 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sat, 20 Mar 2021 23:10:12 +0100
Subject: [PATCH 1235/1820] perf daemon: Force waipid for all session on
 SIGCHLD delivery

If we don't process SIGCHLD before another comes, we will see just one
SIGCHLD as a result. In this case current code will miss exit
notification for a session and wait forever.

Adding extra waitpid check for all sessions when SIGCHLD is received, to
make sure we don't miss any session exit.

Also fix close condition for signal_fd.

Reported-by: Ian Rogers <irogers@google.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210320221013.1619613-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-daemon.c | 52 +++++++++++++++++++++----------------
 1 file changed, 29 insertions(+), 23 deletions(-)

diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index ace8772a4f03..4697493842f5 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -402,35 +402,42 @@ static pid_t handle_signalfd(struct daemon *daemon)
 	int status;
 	pid_t pid;
 
+	/*
+	 * Take signal fd data as pure signal notification and check all
+	 * the sessions state. The reason is that multiple signals can get
+	 * coalesced in kernel and we can receive only single signal even
+	 * if multiple SIGCHLD were generated.
+	 */
 	err = read(daemon->signal_fd, &si, sizeof(struct signalfd_siginfo));
-	if (err != sizeof(struct signalfd_siginfo))
+	if (err != sizeof(struct signalfd_siginfo)) {
+		pr_err("failed to read signal fd\n");
 		return -1;
+	}
 
 	list_for_each_entry(session, &daemon->sessions, list) {
-
-		if (session->pid != (int) si.ssi_pid)
+		if (session->pid == -1)
 			continue;
 
-		pid = waitpid(session->pid, &status, 0);
-		if (pid == session->pid) {
-			if (WIFEXITED(status)) {
-				pr_info("session '%s' exited, status=%d\n",
-					session->name, WEXITSTATUS(status));
-			} else if (WIFSIGNALED(status)) {
-				pr_info("session '%s' killed (signal %d)\n",
-					session->name, WTERMSIG(status));
-			} else if (WIFSTOPPED(status)) {
-				pr_info("session '%s' stopped (signal %d)\n",
-					session->name, WSTOPSIG(status));
-			} else {
-				pr_info("session '%s' Unexpected status (0x%x)\n",
-					session->name, status);
-			}
+		pid = waitpid(session->pid, &status, WNOHANG);
+		if (pid <= 0)
+			continue;
+
+		if (WIFEXITED(status)) {
+			pr_info("session '%s' exited, status=%d\n",
+				session->name, WEXITSTATUS(status));
+		} else if (WIFSIGNALED(status)) {
+			pr_info("session '%s' killed (signal %d)\n",
+				session->name, WTERMSIG(status));
+		} else if (WIFSTOPPED(status)) {
+			pr_info("session '%s' stopped (signal %d)\n",
+				session->name, WSTOPSIG(status));
+		} else {
+			pr_info("session '%s' Unexpected status (0x%x)\n",
+				session->name, status);
 		}
 
 		session->state = KILL;
 		session->pid = -1;
-		return pid;
 	}
 
 	return 0;
@@ -443,7 +450,6 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
 		.fd	= daemon->signal_fd,
 		.events	= POLLIN,
 	};
-	pid_t wpid = 0, pid = session->pid;
 	time_t start;
 
 	start = time(NULL);
@@ -452,7 +458,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
 		int err = poll(&pollfd, 1, 1000);
 
 		if (err > 0) {
-			wpid = handle_signalfd(daemon);
+			handle_signalfd(daemon);
 		} else if (err < 0) {
 			perror("failed: poll\n");
 			return -1;
@@ -460,7 +466,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
 
 		if (start + secs < time(NULL))
 			return -1;
-	} while (wpid != pid);
+	} while (session->pid != -1);
 
 	return 0;
 }
@@ -1344,7 +1350,7 @@ out:
 		close(sock_fd);
 	if (conf_fd != -1)
 		close(conf_fd);
-	if (conf_fd != -1)
+	if (signal_fd != -1)
 		close(signal_fd);
 
 	pr_info("daemon exited\n");

From 9f177fd8f20b46bbd76dbcc90184caf3b8548a9f Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sat, 20 Mar 2021 23:10:13 +0100
Subject: [PATCH 1236/1820] perf daemon: Return from kill functions

We should return correctly and warn in both daemon_session__kill() and
daemon__kill() after we tried everything to kill sessions.  The current
code will keep on looping and waiting.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210320221013.1619613-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-daemon.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index 4697493842f5..7c4a9d424a64 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -908,7 +908,9 @@ static void daemon_session__kill(struct daemon_session *session,
 			daemon_session__signal(session, SIGKILL);
 			break;
 		default:
-			break;
+			pr_err("failed to wait for session %s\n",
+			       session->name);
+			return;
 		}
 		how++;
 
@@ -961,7 +963,8 @@ static void daemon__kill(struct daemon *daemon)
 			daemon__signal(daemon, SIGKILL);
 			break;
 		default:
-			break;
+			pr_err("failed to wait for sessions\n");
+			return;
 		}
 		how++;
 

From eb8f998bbc3d51042ff290b9f6480c1886f6cfb9 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Wed, 24 Mar 2021 09:37:34 +0100
Subject: [PATCH 1237/1820] perf test: Remove now useless failing sub test "BPF
 relocation checker"

For some time now the 'perf test 42: BPF filter' returns an error on bpf
relocation subtest, at least on x86 and s390. This is caused by

  d859900c4c56dc4f ("bpf, libbpf: support global data/bss/rodata sections")

which introduces support for global variables in eBPF programs.

Perf test 42.4 checks that the eBPF relocation fails when the eBPF program
contains a global variable. It returns OK when the eBPF program
could not be loaded and FAILED otherwise.

With above commit the test logic for the eBPF relocation is obsolete.
The loading of the eBPF now succeeds and the test always shows FAILED.

This patch removes the sub test completely.
Also a lot of eBPF program testing is done in the eBPF test suite,
it also contains tests for global variables.

Output before:
 42: BPF filter                          :
 42.1: Basic BPF filtering               : Ok
 42.2: BPF pinning                       : Ok
 42.3: BPF prologue generation           : Ok
 42.4: BPF relocation checker            : Failed
 #

Output after:
 # ./perf test -F 42
 42: BPF filter                          :
 42.1: Basic BPF filtering               : Ok
 42.2: BPF pinning                       : Ok
 42.3: BPF prologue generation           : Ok
 #

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: http://lore.kernel.org/lkml/20210324083734.1953123-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/bpf.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index f57e075b0ed2..c72adbd67386 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -86,7 +86,7 @@ static struct {
 		.msg_load_fail	  = "check your vmlinux setting?",
 		.target_func	  = &epoll_pwait_loop,
 		.expect_result	  = (NR_ITERS + 1) / 2,
-		.pin 		  = true,
+		.pin		  = true,
 	},
 #ifdef HAVE_BPF_PROLOGUE
 	{
@@ -99,13 +99,6 @@ static struct {
 		.expect_result	  = (NR_ITERS + 1) / 4,
 	},
 #endif
-	{
-		.prog_id	  = LLVM_TESTCASE_BPF_RELOCATION,
-		.desc		  = "BPF relocation checker",
-		.name		  = "[bpf_relocation_test]",
-		.msg_compile_fail = "fix 'perf test LLVM' first",
-		.msg_load_fail	  = "libbpf error when dealing with relocation",
-	},
 };
 
 static int do_test(struct bpf_object *obj, int (*func)(void),

From 41d585411311abf187e5f09042978fe7073a9375 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 15 Mar 2021 13:56:41 +0900
Subject: [PATCH 1238/1820] perf record: Fix memory leak in vDSO found using
 ASAN

I got several memory leak reports from Asan with a simple command.  It
was because VDSO is not released due to the refcount.  Like in
__dsos_addnew_id(), it should put the refcount after adding to the list.

  $ perf record true
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.030 MB perf.data (10 samples) ]

  =================================================================
  ==692599==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 439 byte(s) in 1 object(s) allocated from:
    #0 0x7fea52341037 in __interceptor_calloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:154
    #1 0x559bce4aa8ee in dso__new_id util/dso.c:1256
    #2 0x559bce59245a in __machine__addnew_vdso util/vdso.c:132
    #3 0x559bce59245a in machine__findnew_vdso util/vdso.c:347
    #4 0x559bce50826c in map__new util/map.c:175
    #5 0x559bce503c92 in machine__process_mmap2_event util/machine.c:1787
    #6 0x559bce512f6b in machines__deliver_event util/session.c:1481
    #7 0x559bce515107 in perf_session__deliver_event util/session.c:1551
    #8 0x559bce51d4d2 in do_flush util/ordered-events.c:244
    #9 0x559bce51d4d2 in __ordered_events__flush util/ordered-events.c:323
    #10 0x559bce519bea in __perf_session__process_events util/session.c:2268
    #11 0x559bce519bea in perf_session__process_events util/session.c:2297
    #12 0x559bce2e7a52 in process_buildids /home/namhyung/project/linux/tools/perf/builtin-record.c:1017
    #13 0x559bce2e7a52 in record__finish_output /home/namhyung/project/linux/tools/perf/builtin-record.c:1234
    #14 0x559bce2ed4f6 in __cmd_record /home/namhyung/project/linux/tools/perf/builtin-record.c:2026
    #15 0x559bce2ed4f6 in cmd_record /home/namhyung/project/linux/tools/perf/builtin-record.c:2858
    #16 0x559bce422db4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #17 0x559bce2acac8 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #18 0x559bce2acac8 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #19 0x559bce2acac8 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #20 0x7fea51e76d09 in __libc_start_main ../csu/libc-start.c:308

  Indirect leak of 32 byte(s) in 1 object(s) allocated from:
    #0 0x7fea52341037 in __interceptor_calloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:154
    #1 0x559bce520907 in nsinfo__copy util/namespaces.c:169
    #2 0x559bce50821b in map__new util/map.c:168
    #3 0x559bce503c92 in machine__process_mmap2_event util/machine.c:1787
    #4 0x559bce512f6b in machines__deliver_event util/session.c:1481
    #5 0x559bce515107 in perf_session__deliver_event util/session.c:1551
    #6 0x559bce51d4d2 in do_flush util/ordered-events.c:244
    #7 0x559bce51d4d2 in __ordered_events__flush util/ordered-events.c:323
    #8 0x559bce519bea in __perf_session__process_events util/session.c:2268
    #9 0x559bce519bea in perf_session__process_events util/session.c:2297
    #10 0x559bce2e7a52 in process_buildids /home/namhyung/project/linux/tools/perf/builtin-record.c:1017
    #11 0x559bce2e7a52 in record__finish_output /home/namhyung/project/linux/tools/perf/builtin-record.c:1234
    #12 0x559bce2ed4f6 in __cmd_record /home/namhyung/project/linux/tools/perf/builtin-record.c:2026
    #13 0x559bce2ed4f6 in cmd_record /home/namhyung/project/linux/tools/perf/builtin-record.c:2858
    #14 0x559bce422db4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:313
    #15 0x559bce2acac8 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:365
    #16 0x559bce2acac8 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:409
    #17 0x559bce2acac8 in main /home/namhyung/project/linux/tools/perf/perf.c:539
    #18 0x7fea51e76d09 in __libc_start_main ../csu/libc-start.c:308

  SUMMARY: AddressSanitizer: 471 byte(s) leaked in 2 allocation(s).

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210315045641.700430-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/vdso.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 3cc91ad048ea..43beb169631d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -133,6 +133,8 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
 	if (dso != NULL) {
 		__dsos__add(&machine->dsos, dso);
 		dso__set_long_name(dso, long_name, false);
+		/* Put dso here because __dsos_add already got it */
+		dso__put(dso);
 	}
 
 	return dso;

From 25928deeb1e4e2cdae1dccff349320c6841eb5f8 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Tue, 23 Mar 2021 14:20:33 -0700
Subject: [PATCH 1239/1820] ACPICA: Always create namespace nodes using
 acpi_ns_create_node()

ACPICA commit 29da9a2a3f5b2c60420893e5c6309a0586d7a329

ACPI is allocating an object using kmalloc(), but then frees it
using kmem_cache_free(<"Acpi-Namespace" kmem_cache>).

This is wrong and can lead to boot failures manifesting like this:

    hpet0: 3 comparators, 64-bit 100.000000 MHz counter
    clocksource: Switched to clocksource tsc-early
    BUG: unable to handle page fault for address: 000000003ffe0018
    #PF: supervisor read access in kernel mode
    #PF: error_code(0x0000) - not-present page
    PGD 0 P4D 0
    Oops: 0000 [#1] SMP PTI
    CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.6.0+ #211
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
Ubuntu-1.8.2-1ubuntu1 04/01/2014
    RIP: 0010:kmem_cache_alloc+0x70/0x1d0
    Code: 00 00 4c 8b 45 00 65 49 8b 50 08 65 4c 03 05 6f cc e7 7e 4d 8b
20 4d 85 e4 0f 84 3d 01 00 00 8b 45 20 48 8b 7d 00 48 8d 4a 01 <49> 8b
   1c 04 4c 89 e0 65 48 0f c7 0f 0f 94 c0 84 c0 74 c5 8b 45 20
    RSP: 0000:ffffc90000013df8 EFLAGS: 00010206
    RAX: 0000000000000018 RBX: ffffffff81c49200 RCX: 0000000000000002
    RDX: 0000000000000001 RSI: 0000000000000dc0 RDI: 000000000002b300
    RBP: ffff88803e403d00 R08: ffff88803ec2b300 R09: 0000000000000001
    R10: 0000000000000dc0 R11: 0000000000000006 R12: 000000003ffe0000
    R13: ffffffff8110a583 R14: 0000000000000dc0 R15: ffffffff81c49a80
    FS:  0000000000000000(0000) GS:ffff88803ec00000(0000)
knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 000000003ffe0018 CR3: 0000000001c0a001 CR4: 00000000003606f0
    DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
    DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
    Call Trace:
     __trace_define_field+0x33/0xa0
     event_trace_init+0xeb/0x2b4
     tracer_init_tracefs+0x60/0x195
     ? register_tracer+0x1e7/0x1e7
     do_one_initcall+0x74/0x160
     kernel_init_freeable+0x190/0x1f0
     ? rest_init+0x9a/0x9a
     kernel_init+0x5/0xf6
     ret_from_fork+0x35/0x40
    CR2: 000000003ffe0018
    ---[ end trace 707efa023f2ee960 ]---
    RIP: 0010:kmem_cache_alloc+0x70/0x1d0

Bisection leads to unrelated changes in slab; Vlastimil Babka
suggests an unrelated layout or slab merge change merely exposed
the underlying bug.

Link: https://lore.kernel.org/lkml/4dc93ff8-f86e-f4c9-ebeb-6d3153a78d03@oracle.com/
Link: https://lore.kernel.org/r/a1461e21-c744-767d-6dfc-6641fd3e3ce2@siemens.com
Link: https://github.com/acpica/acpica/commit/29da9a2a
Fixes: f79c8e4136ea ("ACPICA: Namespace: simplify creation of the initial/default namespace")
Reported-by: Jan Kiszka <jan.kiszka@siemens.com>
Diagnosed-by: Vlastimil Babka <vbabka@suse.cz>
Diagnosed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Erik Kaneda <erik.kaneda@intel.com>
Cc: 5.10+ <stable@vger.kernel.org> # 5.10+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/nsaccess.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index 3f045b5953b2..a0c1a665dfc1 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -99,13 +99,12 @@ acpi_status acpi_ns_root_initialize(void)
 		 * just create and link the new node(s) here.
 		 */
 		new_node =
-		    ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_namespace_node));
+		    acpi_ns_create_node(*ACPI_CAST_PTR(u32, init_val->name));
 		if (!new_node) {
 			status = AE_NO_MEMORY;
 			goto unlock_and_exit;
 		}
 
-		ACPI_COPY_NAMESEG(new_node->name.ascii, init_val->name);
 		new_node->descriptor_type = ACPI_DESC_TYPE_NAMED;
 		new_node->type = init_val->type;
 

From bf1c82a5389061d989f5e07f1c958db4efaf2141 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Wed, 24 Mar 2021 08:51:10 +0000
Subject: [PATCH 1240/1820] cachefiles: do not yet allow on idmapped mounts

Based on discussions (e.g. in [1]) my understanding of cachefiles and
the cachefiles userspace daemon is that it creates a cache on a local
filesystem (e.g. ext4, xfs etc.) for a network filesystem. The way this
is done is by writing "bind" to /dev/cachefiles and pointing it to the
directory to use as the cache.

Currently this directory can technically also be an idmapped mount but
cachefiles aren't yet fully aware of such mounts and thus don't take the
idmapping into account when creating cache entries. This could leave
users confused as the ownership of the files wouldn't match to what they
expressed in the idmapping. Block cache files on idmapped mounts until
the fscache rework is done and we have ported it to support idmapped
mounts.

Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Cc: linux-cachefs@redhat.com
Link: https://lore.kernel.org/lkml/20210303161528.n3jzg66ou2wa43qb@wittgenstein [1]
Link: https://lore.kernel.org/r/20210316112257.2974212-1-christian.brauner@ubuntu.com/ # v1
Link: https://listman.redhat.com/archives/linux-cachefs/2021-March/msg00044.html # v2
Link: https://lore.kernel.org/r/20210319114146.410329-1-christian.brauner@ubuntu.com/ # v3
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/cachefiles/bind.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
index dfb14dbddf51..38bb7764b454 100644
--- a/fs/cachefiles/bind.c
+++ b/fs/cachefiles/bind.c
@@ -118,6 +118,12 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
 	cache->mnt = path.mnt;
 	root = path.dentry;
 
+	ret = -EINVAL;
+	if (mnt_user_ns(path.mnt) != &init_user_ns) {
+		pr_warn("File cache on idmapped mounts not supported");
+		goto error_unsupported;
+	}
+
 	/* check parameters */
 	ret = -EOPNOTSUPP;
 	if (d_is_negative(root) ||

From 1d676673d665fd2162e7e466dcfbe5373bfdb73e Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Tue, 23 Mar 2021 12:06:29 +0000
Subject: [PATCH 1241/1820] KVM: arm64: Hide system instruction access to Trace
 registers

Currently we advertise the ID_AA6DFR0_EL1.TRACEVER for the guest,
when the trace register accesses are trapped (CPTR_EL2.TTA == 1).
So, the guest will get an undefined instruction, if trusts the
ID registers and access one of the trace registers.
Lets be nice to the guest and hide the feature to avoid
unexpected behavior.

Even though this can be done at KVM sysreg emulation layer,
we do this by removing the TRACEVER from the sanitised feature
register field. This is fine as long as the ETM drivers
can handle the individual trace units separately, even
when there are differences among the CPUs.

Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210323120647.454211-2-suzuki.poulose@arm.com
---
 arch/arm64/kernel/cpufeature.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 066030717a4c..a4698f09bf32 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -383,7 +383,6 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
 	 * of support.
 	 */
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
 	ARM64_FTR_END,
 };

From a354a64d91eec3e0f8ef0eed575b480fd75b999c Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Tue, 23 Mar 2021 12:06:30 +0000
Subject: [PATCH 1242/1820] KVM: arm64: Disable guest access to trace filter
 controls

Disable guest access to the Trace Filter control registers.
We do not advertise the Trace filter feature to the guest
(ID_AA64DFR0_EL1: TRACE_FILT is cleared) already, but the guest
can still access the TRFCR_EL1 unless we trap it.

This will also make sure that the guest cannot fiddle with
the filtering controls set by a nvhe host.

Cc: Marc Zyngier <maz@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210323120647.454211-3-suzuki.poulose@arm.com
---
 arch/arm64/include/asm/kvm_arm.h | 1 +
 arch/arm64/kvm/debug.c           | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 4e90c2debf70..94d4025acc0b 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -278,6 +278,7 @@
 #define CPTR_EL2_DEFAULT	CPTR_EL2_RES1
 
 /* Hyp Debug Configuration Register bits */
+#define MDCR_EL2_TTRF		(1 << 19)
 #define MDCR_EL2_TPMS		(1 << 14)
 #define MDCR_EL2_E2PB_MASK	(UL(0x3))
 #define MDCR_EL2_E2PB_SHIFT	(UL(12))
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index 7a7e425616b5..dbc890511631 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -89,6 +89,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
  *  - Debug ROM Address (MDCR_EL2_TDRA)
  *  - OS related registers (MDCR_EL2_TDOSA)
  *  - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB)
+ *  - Self-hosted Trace Filter controls (MDCR_EL2_TTRF)
  *
  * Additionally, KVM only traps guest accesses to the debug registers if
  * the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY
@@ -112,6 +113,7 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 	vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK;
 	vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM |
 				MDCR_EL2_TPMS |
+				MDCR_EL2_TTRF |
 				MDCR_EL2_TPMCR |
 				MDCR_EL2_TDRA |
 				MDCR_EL2_TDOSA);

From af22df997d71c32304d6835a8b690281063b8010 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 23 Mar 2021 16:08:18 +0000
Subject: [PATCH 1243/1820] KVM: arm64: Fix CPU interface MMIO compatibility
 detection

In order to detect whether a GICv3 CPU interface is MMIO capable,
we switch ICC_SRE_EL1.SRE to 0 and check whether it sticks.

However, this is only possible if *ALL* of the HCR_EL2 interrupt
overrides are set, and the CPU is perfectly allowed to ignore
the write to ICC_SRE_EL1 otherwise. This leads KVM to pretend
that a whole bunch of ARMv8.0 CPUs aren't MMIO-capable, and
breaks VMs that should work correctly otherwise.

Fix this by setting IMO/FMO/IMO before touching ICC_SRE_EL1,
and clear them afterwards. This allows us to reliably detect
the CPU interface capabilities.

Tested-by: Shameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com>
Fixes: 9739f6ef053f ("KVM: arm64: Workaround firmware wrongly advertising GICv2-on-v3 compatibility")
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/vgic-v3-sr.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index ee3682b9873c..39f8f7f9227c 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -429,6 +429,13 @@ u64 __vgic_v3_get_gic_config(void)
 	if (has_vhe())
 		flags = local_daif_save();
 
+	/*
+	 * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates
+	 * that to be able to set ICC_SRE_EL1.SRE to 0, all the
+	 * interrupt overrides must be set. You've got to love this.
+	 */
+	sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
+	isb();
 	write_gicreg(0, ICC_SRE_EL1);
 	isb();
 
@@ -436,6 +443,8 @@ u64 __vgic_v3_get_gic_config(void)
 
 	write_gicreg(sre, ICC_SRE_EL1);
 	isb();
+	sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
+	isb();
 
 	if (has_vhe())
 		local_daif_restore(flags);

From 7de55b7d6f09a2865279d3c41c0fbdbfdb87486a Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Date: Thu, 25 Mar 2021 00:47:26 +0900
Subject: [PATCH 1244/1820] block: support zone append bvecs

Christoph reported that we'll likely trigger the WARN_ON_ONCE() checking
that we're not submitting a bvec with REQ_OP_ZONE_APPEND in
bio_iov_iter_get_pages() some time ago using zoned btrfs, but I couldn't
reproduce it back then.

Now Naohiro was able to trigger the bug as well with xfstests generic/095
on a zoned btrfs.

There is nothing that prevents bvec submissions via REQ_OP_ZONE_APPEND if
the hardware's zone append limit is met.

Reported-by: Naohiro Aota <naohiro.aota@wdc.com>
Reported-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/10bd414d9326c90cd69029077db63b363854eee5.1616600835.git.johannes.thumshirn@wdc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 26b7f721cda8..963d1d406b3a 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -949,7 +949,7 @@ void bio_release_pages(struct bio *bio, bool mark_dirty)
 }
 EXPORT_SYMBOL_GPL(bio_release_pages);
 
-static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
+static void __bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 {
 	WARN_ON_ONCE(bio->bi_max_vecs);
 
@@ -959,11 +959,26 @@ static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 	bio->bi_iter.bi_size = iter->count;
 	bio_set_flag(bio, BIO_NO_PAGE_REF);
 	bio_set_flag(bio, BIO_CLONED);
+}
 
+static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
+{
+	__bio_iov_bvec_set(bio, iter);
 	iov_iter_advance(iter, iter->count);
 	return 0;
 }
 
+static int bio_iov_bvec_set_append(struct bio *bio, struct iov_iter *iter)
+{
+	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+	struct iov_iter i = *iter;
+
+	iov_iter_truncate(&i, queue_max_zone_append_sectors(q) << 9);
+	__bio_iov_bvec_set(bio, &i);
+	iov_iter_advance(iter, i.count);
+	return 0;
+}
+
 #define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
 
 /**
@@ -1094,8 +1109,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	int ret = 0;
 
 	if (iov_iter_is_bvec(iter)) {
-		if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND))
-			return -EINVAL;
+		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+			return bio_iov_bvec_set_append(bio, iter);
 		return bio_iov_bvec_set(bio, iter);
 	}
 

From f51d7bf1dbe5522c51c93fe8faa5f4abbdf339cd Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Tue, 23 Mar 2021 16:02:29 +0800
Subject: [PATCH 1245/1820] ptp_qoriq: fix overflow in ptp_qoriq_adjfine() u64
 calcalation

Current calculation for diff of TMR_ADD register value may have
64-bit overflow in this code line, when long type scaled_ppm is
large.

adj *= scaled_ppm;

This patch is to resolve it by using mul_u64_u64_div_u64().

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_qoriq.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index beb5f74944cd..08f4cf0ad9e3 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -189,15 +189,16 @@ int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	tmr_add = ptp_qoriq->tmr_add;
 	adj = tmr_add;
 
-	/* calculate diff as adj*(scaled_ppm/65536)/1000000
-	 * and round() to the nearest integer
+	/*
+	 * Calculate diff and round() to the nearest integer
+	 *
+	 * diff = adj * (ppb / 1000000000)
+	 *      = adj * scaled_ppm / 65536000000
 	 */
-	adj *= scaled_ppm;
-	diff = div_u64(adj, 8000000);
-	diff = (diff >> 13) + ((diff >> 12) & 1);
+	diff = mul_u64_u64_div_u64(adj, scaled_ppm, 32768000000);
+	diff = DIV64_U64_ROUND_UP(diff, 2);
 
 	tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff;
-
 	ptp_qoriq->write(&regs->ctrl_regs->tmr_add, tmr_add);
 
 	return 0;

From 9e0a537d06fc36861e4f78d0a7df1fe2b3592714 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 23 Mar 2021 12:32:45 +0000
Subject: [PATCH 1246/1820] octeontx2-af: Fix memory leak of object buf

Currently the error return path when lfs fails to allocate is not free'ing
the memory allocated to buf. Fix this by adding the missing kfree.

Addresses-Coverity: ("Resource leak")
Fixes: f7884097141b ("octeontx2-af: Formatting debugfs entry rsrc_alloc.")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index b4c53b19f535..de3968d2e5ce 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -253,8 +253,10 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
 		return -ENOSPC;
 
 	lfs = kzalloc(lf_str_size, GFP_KERNEL);
-	if (!lfs)
+	if (!lfs) {
+		kfree(buf);
 		return -ENOMEM;
+	}
 	off +=	scnprintf(&buf[off], buf_size - 1 - off, "%-*s", lf_str_size,
 			  "pcifunc");
 	for (index = 0; index < BLK_COUNT; index++)

From 6f235a69e59484e382dc31952025b0308efedc17 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 23 Mar 2021 22:52:50 +0100
Subject: [PATCH 1247/1820] ch_ktls: fix enum-conversion warning

gcc points out an incorrect enum assignment:

drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c: In function 'chcr_ktls_cpl_set_tcb_rpl':
drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c:684:22: warning: implicit conversion from 'enum <anonymous>' to 'enum ch_ktls_open_state' [-Wenum-conversion]

This appears harmless, and should apparently use 'CH_KTLS_OPEN_SUCCESS'
instead of 'false', with the same value '0'.

Fixes: efca3878a5fb ("ch_ktls: Issue if connection offload fails")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index 169e10c91378..1115b8f9ea4e 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -722,7 +722,7 @@ static int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input)
 		kvfree(tx_info);
 		return 0;
 	}
-	tx_info->open_state = false;
+	tx_info->open_state = CH_KTLS_OPEN_SUCCESS;
 	spin_unlock(&tx_info->lock);
 
 	complete(&tx_info->completion);

From aa65bacdb70e549a81de03ec72338e1047842883 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 24 Mar 2021 14:27:10 +0100
Subject: [PATCH 1248/1820] ASoC: intel: atom: Stop advertising non working
 S24LE support

The SST firmware's media and deep-buffer inputs are hardcoded to
S16LE, the corresponding DAIs don't have a hw_params callback and
their prepare callback also does not take the format into account.

So far the advertising of non working S24LE support has not caused
issues because pulseaudio defaults to S16LE, but changing pulse-audio's
config to use S24LE will result in broken sound.

Pipewire is replacing pulse now and pipewire prefers S24LE over S16LE
when available, causing the problem of the broken S24LE support to
come to the surface now.

Cc: stable@vger.kernel.org
BugLink: https://gitlab.freedesktop.org/pipewire/pipewire/-/issues/866
Fixes: 098c2cd281409 ("ASoC: Intel: Atom: add 24-bit support for media playback and capture")
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210324132711.216152-2-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/atom/sst-mfld-platform-pcm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
index 9e9b05883557..aa5dd590ddd5 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
@@ -488,14 +488,14 @@ static struct snd_soc_dai_driver sst_platform_dai[] = {
 		.channels_min = SST_STEREO,
 		.channels_max = SST_STEREO,
 		.rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000,
-		.formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE,
 	},
 	.capture = {
 		.stream_name = "Headset Capture",
 		.channels_min = 1,
 		.channels_max = 2,
 		.rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000,
-		.formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE,
 	},
 },
 {
@@ -506,7 +506,7 @@ static struct snd_soc_dai_driver sst_platform_dai[] = {
 		.channels_min = SST_STEREO,
 		.channels_max = SST_STEREO,
 		.rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000,
-		.formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE,
 	},
 },
 {

From 632aeebe1b7a3a8b193d71942a10e66919bebfb8 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 24 Mar 2021 14:27:11 +0100
Subject: [PATCH 1249/1820] ASoC: intel: atom: Remove 44100 sample-rate from
 the media and deep-buffer DAI descriptions

The media and deep-buffer DAIs only support 48000 Hz samplerate,
remove the 44100 sample-rate from their descriptions.

Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210324132711.216152-3-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/atom/sst-mfld-platform-pcm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
index aa5dd590ddd5..4124aa2fc247 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
@@ -487,14 +487,14 @@ static struct snd_soc_dai_driver sst_platform_dai[] = {
 		.stream_name = "Headset Playback",
 		.channels_min = SST_STEREO,
 		.channels_max = SST_STEREO,
-		.rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000,
+		.rates = SNDRV_PCM_RATE_48000,
 		.formats = SNDRV_PCM_FMTBIT_S16_LE,
 	},
 	.capture = {
 		.stream_name = "Headset Capture",
 		.channels_min = 1,
 		.channels_max = 2,
-		.rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000,
+		.rates = SNDRV_PCM_RATE_48000,
 		.formats = SNDRV_PCM_FMTBIT_S16_LE,
 	},
 },
@@ -505,7 +505,7 @@ static struct snd_soc_dai_driver sst_platform_dai[] = {
 		.stream_name = "Deepbuffer Playback",
 		.channels_min = SST_STEREO,
 		.channels_max = SST_STEREO,
-		.rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000,
+		.rates = SNDRV_PCM_RATE_48000,
 		.formats = SNDRV_PCM_FMTBIT_S16_LE,
 	},
 },

From 2b514ec72706a31bea0c3b97e622b81535b5323a Mon Sep 17 00:00:00 2001
From: Roger Pau Monne <roger.pau@citrix.com>
Date: Wed, 24 Mar 2021 13:24:23 +0100
Subject: [PATCH 1250/1820] xen/x86: make XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
 depend on MEMORY_HOTPLUG
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Xen memory hotplug limit should depend on the memory hotplug
generic option, rather than the Xen balloon configuration. It's
possible to have a kernel with generic memory hotplug enabled, but
without Xen balloon enabled, at which point memory hotplug won't work
correctly due to the size limitation of the p2m.

Rename the option to XEN_MEMORY_HOTPLUG_LIMIT since it's no longer
tied to ballooning.

Fixes: 9e2369c06c8a18 ("xen: add helpers to allocate unpopulated memory")
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Link: https://lore.kernel.org/r/20210324122424.58685-2-roger.pau@citrix.com
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/xen/p2m.c  | 4 ++--
 drivers/xen/Kconfig | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 17d80f751fcb..a33902d05e45 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -98,8 +98,8 @@ EXPORT_SYMBOL_GPL(xen_p2m_size);
 unsigned long xen_max_p2m_pfn __read_mostly;
 EXPORT_SYMBOL_GPL(xen_max_p2m_pfn);
 
-#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
-#define P2M_LIMIT CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
+#ifdef CONFIG_XEN_MEMORY_HOTPLUG_LIMIT
+#define P2M_LIMIT CONFIG_XEN_MEMORY_HOTPLUG_LIMIT
 #else
 #define P2M_LIMIT 0
 #endif
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 41645fe6ad48..ea0efd290c37 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -50,11 +50,11 @@ config XEN_BALLOON_MEMORY_HOTPLUG
 
 	  SUBSYSTEM=="memory", ACTION=="add", RUN+="/bin/sh -c '[ -f /sys$devpath/state ] && echo online > /sys$devpath/state'"
 
-config XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
+config XEN_MEMORY_HOTPLUG_LIMIT
 	int "Hotplugged memory limit (in GiB) for a PV guest"
 	default 512
 	depends on XEN_HAVE_PVMMU
-	depends on XEN_BALLOON_MEMORY_HOTPLUG
+	depends on MEMORY_HOTPLUG
 	help
 	  Maxmium amount of memory (in GiB) that a PV guest can be
 	  expanded to when using memory hotplug.

From af44a387e743ab7aa39d3fb5e29c0a973cf91bdc Mon Sep 17 00:00:00 2001
From: Roger Pau Monne <roger.pau@citrix.com>
Date: Wed, 24 Mar 2021 13:24:24 +0100
Subject: [PATCH 1251/1820] Revert "xen: fix p2m size in dom0 for disabled
 memory hotplug case"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This partially reverts commit 882213990d32 ("xen: fix p2m size in dom0
for disabled memory hotplug case")

There's no need to special case XEN_UNPOPULATED_ALLOC anymore in order
to correctly size the p2m. The generic memory hotplug option has
already been tied together with the Xen hotplug limit, so enabling
memory hotplug should already trigger a properly sized p2m on Xen PV.

Note that XEN_UNPOPULATED_ALLOC depends on ZONE_DEVICE which pulls in
MEMORY_HOTPLUG.

Leave the check added to __set_phys_to_machine and the adjusted
comment about EXTRA_MEM_RATIO.

Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Link: https://lore.kernel.org/r/20210324122424.58685-3-roger.pau@citrix.com

[boris: fixed formatting issues]
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/include/asm/xen/page.h | 12 ------------
 arch/x86/xen/p2m.c              |  3 ---
 arch/x86/xen/setup.c            | 16 ++++++++++++++--
 3 files changed, 14 insertions(+), 17 deletions(-)

diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 7068e4bb057d..1a162e559753 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -86,18 +86,6 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 }
 #endif
 
-/*
- * The maximum amount of extra memory compared to the base size.  The
- * main scaling factor is the size of struct page.  At extreme ratios
- * of base:extra, all the base memory can be filled with page
- * structures for the extra memory, leaving no space for anything
- * else.
- *
- * 10x seems like a reasonable balance between scaling flexibility and
- * leaving a practically usable system.
- */
-#define XEN_EXTRA_MEM_RATIO	(10)
-
 /*
  * Helper functions to write or read unsigned long values to/from
  * memory, when the access may fault.
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index a33902d05e45..ac06ca32e9ef 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -416,9 +416,6 @@ void __init xen_vmalloc_p2m_tree(void)
 	xen_p2m_last_pfn = xen_max_p2m_pfn;
 
 	p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE;
-	if (!p2m_limit && IS_ENABLED(CONFIG_XEN_UNPOPULATED_ALLOC))
-		p2m_limit = xen_start_info->nr_pages * XEN_EXTRA_MEM_RATIO;
-
 	vm.flags = VM_ALLOC;
 	vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit),
 			PMD_SIZE * PMDS_PER_MID_PAGE);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 1a3b75652fa4..8bfc10330107 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -59,6 +59,18 @@ static struct {
 } xen_remap_buf __initdata __aligned(PAGE_SIZE);
 static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;
 
+/*
+ * The maximum amount of extra memory compared to the base size.  The
+ * main scaling factor is the size of struct page.  At extreme ratios
+ * of base:extra, all the base memory can be filled with page
+ * structures for the extra memory, leaving no space for anything
+ * else.
+ *
+ * 10x seems like a reasonable balance between scaling flexibility and
+ * leaving a practically usable system.
+ */
+#define EXTRA_MEM_RATIO		(10)
+
 static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB);
 
 static void __init xen_parse_512gb(void)
@@ -778,13 +790,13 @@ char * __init xen_memory_setup(void)
 		extra_pages += max_pages - max_pfn;
 
 	/*
-	 * Clamp the amount of extra memory to a XEN_EXTRA_MEM_RATIO
+	 * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
 	 * factor the base size.
 	 *
 	 * Make sure we have no memory above max_pages, as this area
 	 * isn't handled by the p2m management.
 	 */
-	extra_pages = min3(XEN_EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
+	extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
 			   extra_pages, max_pages - max_pfn);
 	i = 0;
 	addr = xen_e820_table.entries[0].addr;

From bf45947864764548697e7515fe693e10f173f312 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 24 Mar 2021 16:42:54 -0700
Subject: [PATCH 1252/1820] math: Export mul_u64_u64_div_u64

Fixes: f51d7bf1dbe5 ("ptp_qoriq: fix overflow in ptp_qoriq_adjfine() u64 calcalation")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/math/div64.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/math/div64.c b/lib/math/div64.c
index 064d68a5391a..46866394fc84 100644
--- a/lib/math/div64.c
+++ b/lib/math/div64.c
@@ -232,4 +232,5 @@ u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 c)
 
 	return res + div64_u64(a * b, c);
 }
+EXPORT_SYMBOL(mul_u64_u64_div_u64);
 #endif

From e43accba9b071dcd106b5e7643b1b106a158cbb1 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 24 Mar 2021 21:43:32 +0200
Subject: [PATCH 1253/1820] psample: Fix user API breakage

Cited commit added a new attribute before the existing group reference
count attribute, thereby changing its value and breaking existing
applications on new kernels.

Before:

 # psample -l
 libpsample ERROR psample_group_foreach: failed to recv message: Operation not supported

After:

 # psample -l
 Group Num       Refcount        Group Seq
 1               1               0

Fix by restoring the value of the old attribute and remove the
misleading comments from the enumerator to avoid future bugs.

Cc: stable@vger.kernel.org
Fixes: d8bed686ab96 ("net: psample: Add tunnel support")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reported-by: Adiel Bidani <adielb@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/psample.h | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h
index aea26ab1431c..bff5032c98df 100644
--- a/include/uapi/linux/psample.h
+++ b/include/uapi/linux/psample.h
@@ -3,7 +3,6 @@
 #define __UAPI_PSAMPLE_H
 
 enum {
-	/* sampled packet metadata */
 	PSAMPLE_ATTR_IIFINDEX,
 	PSAMPLE_ATTR_OIFINDEX,
 	PSAMPLE_ATTR_ORIGSIZE,
@@ -11,10 +10,8 @@ enum {
 	PSAMPLE_ATTR_GROUP_SEQ,
 	PSAMPLE_ATTR_SAMPLE_RATE,
 	PSAMPLE_ATTR_DATA,
-	PSAMPLE_ATTR_TUNNEL,
-
-	/* commands attributes */
 	PSAMPLE_ATTR_GROUP_REFCOUNT,
+	PSAMPLE_ATTR_TUNNEL,
 
 	__PSAMPLE_ATTR_MAX
 };

From d3999c1f7bbbc100c167d7ad3cd79c1d10446ba2 Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Thu, 4 Mar 2021 20:52:41 -0500
Subject: [PATCH 1254/1820] drm/nouveau/kms/nve4-nv108: Limit cursors to
 128x128

While Kepler does technically support 256x256 cursors, it turns out that
Kepler actually has some additional requirements for scanout surfaces that
we're not enforcing correctly, which aren't present on Maxwell and later.
Cursor surfaces must always use small pages (4K), and overlay surfaces must
always use large pages (128K).

Fixing this correctly though will take a bit more work: as we'll need to
add some code in prepare_fb() to move cursor FBs in large pages to small
pages, and vice-versa for overlay FBs. So until we have the time to do
that, just limit cursor surfaces to 128x128 - a size small enough to always
default to small pages.

This means small ovlys are still broken on Kepler, but it is extremely
unlikely anyone cares about those anyway :).

Signed-off-by: Lyude Paul <lyude@redhat.com>
Fixes: d3b2f0f7921c ("drm/nouveau/kms/nv50-: Report max cursor size to userspace")
Cc: <stable@vger.kernel.org> # v5.11+
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/dispnv50/disp.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 196612addfd6..1c9c0cdf85db 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2693,9 +2693,20 @@ nv50_display_create(struct drm_device *dev)
 	else
 		nouveau_display(dev)->format_modifiers = disp50xx_modifiers;
 
-	if (disp->disp->object.oclass >= GK104_DISP) {
+	/* FIXME: 256x256 cursors are supported on Kepler, however unlike Maxwell and later
+	 * generations Kepler requires that we use small pages (4K) for cursor scanout surfaces. The
+	 * proper fix for this is to teach nouveau to migrate fbs being used for the cursor plane to
+	 * small page allocations in prepare_fb(). When this is implemented, we should also force
+	 * large pages (128K) for ovly fbs in order to fix Kepler ovlys.
+	 * But until then, just limit cursors to 128x128 - which is small enough to avoid ever using
+	 * large pages.
+	 */
+	if (disp->disp->object.oclass >= GM107_DISP) {
 		dev->mode_config.cursor_width = 256;
 		dev->mode_config.cursor_height = 256;
+	} else if (disp->disp->object.oclass >= GK104_DISP) {
+		dev->mode_config.cursor_width = 128;
+		dev->mode_config.cursor_height = 128;
 	} else {
 		dev->mode_config.cursor_width = 64;
 		dev->mode_config.cursor_height = 64;

From 8b1c9b2025491d7c86255fb773b00ecf94b53acc Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.ibm.com>
Date: Fri, 19 Mar 2021 14:50:28 -0600
Subject: [PATCH 1255/1820] scsi: ibmvfc: Fix potential race in
 ibmvfc_wait_for_ops()

For various EH activities the ibmvfc driver uses ibmvfc_wait_for_ops() to
wait for the completion of commands that match a given criteria be it
cancel key, or specific LUN. With recent changes commands are completed
outside the lock in bulk by removing them from the sent list and adding
them to a private completion list. This introduces a potential race in
ibmvfc_wait_for_ops() since the criteria for a command to be outstanding is
no longer simply being on the sent list, but instead not being on the free
list.

Avoid this race by scanning the entire command event pool and checking that
any matching command that ibmvfc needs to wait on is not already on the
free list.

Link: https://lore.kernel.org/r/20210319205029.312969-2-tyreld@linux.ibm.com
Fixes: 1f4a4a19508d ("scsi: ibmvfc: Complete commands outside the host/queue lock")
Reviewed-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ibmvscsi/ibmvfc.c | 42 ++++++++++++++++++++++++++--------
 1 file changed, 33 insertions(+), 9 deletions(-)

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 6a92891ac488..94c07cc82563 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -2371,6 +2371,24 @@ static int ibmvfc_match_lun(struct ibmvfc_event *evt, void *device)
 	return 0;
 }
 
+/**
+ * ibmvfc_event_is_free - Check if event is free or not
+ * @evt:	ibmvfc event struct
+ *
+ * Returns:
+ *	true / false
+ **/
+static bool ibmvfc_event_is_free(struct ibmvfc_event *evt)
+{
+	struct ibmvfc_event *loop_evt;
+
+	list_for_each_entry(loop_evt, &evt->queue->free, queue_list)
+		if (loop_evt == evt)
+			return true;
+
+	return false;
+}
+
 /**
  * ibmvfc_wait_for_ops - Wait for ops to complete
  * @vhost:	ibmvfc host struct
@@ -2385,7 +2403,7 @@ static int ibmvfc_wait_for_ops(struct ibmvfc_host *vhost, void *device,
 {
 	struct ibmvfc_event *evt;
 	DECLARE_COMPLETION_ONSTACK(comp);
-	int wait;
+	int wait, i;
 	unsigned long flags;
 	signed long timeout = IBMVFC_ABORT_WAIT_TIMEOUT * HZ;
 
@@ -2393,10 +2411,13 @@ static int ibmvfc_wait_for_ops(struct ibmvfc_host *vhost, void *device,
 	do {
 		wait = 0;
 		spin_lock_irqsave(&vhost->crq.l_lock, flags);
-		list_for_each_entry(evt, &vhost->crq.sent, queue_list) {
-			if (match(evt, device)) {
-				evt->eh_comp = &comp;
-				wait++;
+		for (i = 0; i < vhost->crq.evt_pool.size; i++) {
+			evt = &vhost->crq.evt_pool.events[i];
+			if (!ibmvfc_event_is_free(evt)) {
+				if (match(evt, device)) {
+					evt->eh_comp = &comp;
+					wait++;
+				}
 			}
 		}
 		spin_unlock_irqrestore(&vhost->crq.l_lock, flags);
@@ -2407,10 +2428,13 @@ static int ibmvfc_wait_for_ops(struct ibmvfc_host *vhost, void *device,
 			if (!timeout) {
 				wait = 0;
 				spin_lock_irqsave(&vhost->crq.l_lock, flags);
-				list_for_each_entry(evt, &vhost->crq.sent, queue_list) {
-					if (match(evt, device)) {
-						evt->eh_comp = NULL;
-						wait++;
+				for (i = 0; i < vhost->crq.evt_pool.size; i++) {
+					evt = &vhost->crq.evt_pool.events[i];
+					if (!ibmvfc_event_is_free(evt)) {
+						if (match(evt, device)) {
+							evt->eh_comp = NULL;
+							wait++;
+						}
 					}
 				}
 				spin_unlock_irqrestore(&vhost->crq.l_lock, flags);

From 62fc2661482b6beccfab8a5987419e96a9499fb4 Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.ibm.com>
Date: Fri, 19 Mar 2021 14:50:29 -0600
Subject: [PATCH 1256/1820] scsi: ibmvfc: Make ibmvfc_wait_for_ops() MQ aware

During MQ enablement of the ibmvfc driver ibmvfc_wait_for_ops() was
missed. This function is responsible for waiting on commands to complete
that match a certain criteria such as LUN or cancel key. The implementation
as is only scans the CRQ for events ignoring any sub-queues and as a result
will exit successfully without doing anything when operating in MQ
channelized mode.

Check the MQ and channel use flags to determine which queues are
applicable, and scan each queue accordingly. Note in MQ mode SCSI commands
are only issued down sub-queues and the CRQ is only used for driver
specific management commands. As such the CRQ events are ignored when
operating in MQ mode with channels.

Link: https://lore.kernel.org/r/20210319205029.312969-3-tyreld@linux.ibm.com
Fixes: 9000cb998bcf ("scsi: ibmvfc: Enable MQ and set reasonable defaults")
Reviewed-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ibmvscsi/ibmvfc.c | 51 ++++++++++++++++++++++------------
 1 file changed, 34 insertions(+), 17 deletions(-)

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 94c07cc82563..bb64e3247a6c 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -2403,41 +2403,58 @@ static int ibmvfc_wait_for_ops(struct ibmvfc_host *vhost, void *device,
 {
 	struct ibmvfc_event *evt;
 	DECLARE_COMPLETION_ONSTACK(comp);
-	int wait, i;
+	int wait, i, q_index, q_size;
 	unsigned long flags;
 	signed long timeout = IBMVFC_ABORT_WAIT_TIMEOUT * HZ;
+	struct ibmvfc_queue *queues;
 
 	ENTER;
+	if (vhost->mq_enabled && vhost->using_channels) {
+		queues = vhost->scsi_scrqs.scrqs;
+		q_size = vhost->scsi_scrqs.active_queues;
+	} else {
+		queues = &vhost->crq;
+		q_size = 1;
+	}
+
 	do {
 		wait = 0;
-		spin_lock_irqsave(&vhost->crq.l_lock, flags);
-		for (i = 0; i < vhost->crq.evt_pool.size; i++) {
-			evt = &vhost->crq.evt_pool.events[i];
-			if (!ibmvfc_event_is_free(evt)) {
-				if (match(evt, device)) {
-					evt->eh_comp = &comp;
-					wait++;
+		spin_lock_irqsave(vhost->host->host_lock, flags);
+		for (q_index = 0; q_index < q_size; q_index++) {
+			spin_lock(&queues[q_index].l_lock);
+			for (i = 0; i < queues[q_index].evt_pool.size; i++) {
+				evt = &queues[q_index].evt_pool.events[i];
+				if (!ibmvfc_event_is_free(evt)) {
+					if (match(evt, device)) {
+						evt->eh_comp = &comp;
+						wait++;
+					}
 				}
 			}
+			spin_unlock(&queues[q_index].l_lock);
 		}
-		spin_unlock_irqrestore(&vhost->crq.l_lock, flags);
+		spin_unlock_irqrestore(vhost->host->host_lock, flags);
 
 		if (wait) {
 			timeout = wait_for_completion_timeout(&comp, timeout);
 
 			if (!timeout) {
 				wait = 0;
-				spin_lock_irqsave(&vhost->crq.l_lock, flags);
-				for (i = 0; i < vhost->crq.evt_pool.size; i++) {
-					evt = &vhost->crq.evt_pool.events[i];
-					if (!ibmvfc_event_is_free(evt)) {
-						if (match(evt, device)) {
-							evt->eh_comp = NULL;
-							wait++;
+				spin_lock_irqsave(vhost->host->host_lock, flags);
+				for (q_index = 0; q_index < q_size; q_index++) {
+					spin_lock(&queues[q_index].l_lock);
+					for (i = 0; i < queues[q_index].evt_pool.size; i++) {
+						evt = &queues[q_index].evt_pool.events[i];
+						if (!ibmvfc_event_is_free(evt)) {
+							if (match(evt, device)) {
+								evt->eh_comp = NULL;
+								wait++;
+							}
 						}
 					}
+					spin_unlock(&queues[q_index].l_lock);
 				}
-				spin_unlock_irqrestore(&vhost->crq.l_lock, flags);
+				spin_unlock_irqrestore(vhost->host->host_lock, flags);
 				if (wait)
 					dev_err(vhost->dev, "Timed out waiting for aborted commands\n");
 				LEAVE;

From 39c0c8553bfb5a3d108aa47f1256076d507605e3 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Sat, 20 Mar 2021 16:23:53 -0700
Subject: [PATCH 1257/1820] scsi: Revert "qla2xxx: Make sure that aborted
 commands are freed"

Calling vha->hw->tgt.tgt_ops->free_cmd() from qlt_xmit_response() is wrong
since the command for which a response is sent must remain valid until the
SCSI target core calls .release_cmd(). It has been observed that the
following scenario triggers a kernel crash:

 - qlt_xmit_response() calls qlt_check_reserve_free_req()

 - qlt_check_reserve_free_req() returns -EAGAIN

 - qlt_xmit_response() calls vha->hw->tgt.tgt_ops->free_cmd(cmd)

 - transport_handle_queue_full() tries to retransmit the response

Fix this crash by reverting the patch that introduced it.

Link: https://lore.kernel.org/r/20210320232359.941-2-bvanassche@acm.org
Fixes: 0dcec41acb85 ("scsi: qla2xxx: Make sure that aborted commands are freed")
Cc: Quinn Tran <qutran@marvell.com>
Cc: Mike Christie <michael.christie@oracle.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_target.c  | 13 +++++--------
 drivers/scsi/qla2xxx/tcm_qla2xxx.c |  4 ----
 2 files changed, 5 insertions(+), 12 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index c48daf52725d..480e7d2dcf3e 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -3222,8 +3222,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 	if (!qpair->fw_started || (cmd->reset_count != qpair->chip_reset) ||
 	    (cmd->sess && cmd->sess->deleted)) {
 		cmd->state = QLA_TGT_STATE_PROCESSED;
-		res = 0;
-		goto free;
+		return 0;
 	}
 
 	ql_dbg_qp(ql_dbg_tgt, qpair, 0xe018,
@@ -3234,8 +3233,9 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 
 	res = qlt_pre_xmit_response(cmd, &prm, xmit_type, scsi_status,
 	    &full_req_cnt);
-	if (unlikely(res != 0))
-		goto free;
+	if (unlikely(res != 0)) {
+		return res;
+	}
 
 	spin_lock_irqsave(qpair->qp_lock_ptr, flags);
 
@@ -3255,8 +3255,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 			vha->flags.online, qla2x00_reset_active(vha),
 			cmd->reset_count, qpair->chip_reset);
 		spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
-		res = 0;
-		goto free;
+		return 0;
 	}
 
 	/* Does F/W have an IOCBs for this request */
@@ -3359,8 +3358,6 @@ out_unmap_unlock:
 	qlt_unmap_sg(vha, cmd);
 	spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
 
-free:
-	vha->hw->tgt.tgt_ops->free_cmd(cmd);
 	return res;
 }
 EXPORT_SYMBOL(qlt_xmit_response);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index b55fc768a2a7..8b4890cdd4ca 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -644,7 +644,6 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	struct scsi_qla_host *vha = cmd->vha;
 
 	if (cmd->aborted) {
 		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
@@ -657,7 +656,6 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 			cmd->se_cmd.transport_state,
 			cmd->se_cmd.t_state,
 			cmd->se_cmd.se_cmd_flags);
-		vha->hw->tgt.tgt_ops->free_cmd(cmd);
 		return 0;
 	}
 
@@ -685,7 +683,6 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	struct scsi_qla_host *vha = cmd->vha;
 	int xmit_type = QLA_TGT_XMIT_STATUS;
 
 	if (cmd->aborted) {
@@ -699,7 +696,6 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd)
 		    cmd, kref_read(&cmd->se_cmd.cmd_kref),
 		    cmd->se_cmd.transport_state, cmd->se_cmd.t_state,
 		    cmd->se_cmd.se_cmd_flags);
-		vha->hw->tgt.tgt_ops->free_cmd(cmd);
 		return 0;
 	}
 	cmd->bufflen = se_cmd->data_length;

From f69953837ca5d98aa983a138dc0b90a411e9c763 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Sun, 7 Mar 2021 19:30:24 -0800
Subject: [PATCH 1258/1820] scsi: qedi: Fix error return code of
 qedi_alloc_global_queues()

When kzalloc() returns NULL to qedi->global_queues[i], no error return code
of qedi_alloc_global_queues() is assigned.  To fix this bug, status is
assigned with -ENOMEM in this case.

Link: https://lore.kernel.org/r/20210308033024.27147-1-baijiaju1990@gmail.com
Fixes: ace7f46ba5fd ("scsi: qedi: Add QLogic FastLinQ offload iSCSI driver framework.")
Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Acked-by: Manish Rangankar <mrangankar@marvell.com>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qedi/qedi_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index 47ad64b06623..69c5b5ee2169 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -1675,6 +1675,7 @@ static int qedi_alloc_global_queues(struct qedi_ctx *qedi)
 		if (!qedi->global_queues[i]) {
 			QEDI_ERR(&qedi->dbg_ctx,
 				 "Unable to allocation global queue %d.\n", i);
+			status = -ENOMEM;
 			goto mem_alloc_failure;
 		}
 

From 3401ecf7fc1b9458a19d42c0e26a228f18ac7dda Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Sun, 7 Mar 2021 19:52:41 -0800
Subject: [PATCH 1259/1820] scsi: mpt3sas: Fix error return code of
 mpt3sas_base_attach()

When kzalloc() returns NULL, no error return code of mpt3sas_base_attach()
is assigned. To fix this bug, r is assigned with -ENOMEM in this case.

Link: https://lore.kernel.org/r/20210308035241.3288-1-baijiaju1990@gmail.com
Fixes: c696f7b83ede ("scsi: mpt3sas: Implement device_remove_in_progress check in IOCTL path")
Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index ac066f86bb14..ac0eef975f17 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -7806,14 +7806,18 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 		ioc->pend_os_device_add_sz++;
 	ioc->pend_os_device_add = kzalloc(ioc->pend_os_device_add_sz,
 	    GFP_KERNEL);
-	if (!ioc->pend_os_device_add)
+	if (!ioc->pend_os_device_add) {
+		r = -ENOMEM;
 		goto out_free_resources;
+	}
 
 	ioc->device_remove_in_progress_sz = ioc->pend_os_device_add_sz;
 	ioc->device_remove_in_progress =
 		kzalloc(ioc->device_remove_in_progress_sz, GFP_KERNEL);
-	if (!ioc->device_remove_in_progress)
+	if (!ioc->device_remove_in_progress) {
+		r = -ENOMEM;
 		goto out_free_resources;
+	}
 
 	ioc->fwfault_debug = mpt3sas_fwfault_debug;
 

From 077ce028b8e0684d5ee7da573bd835b14b591546 Mon Sep 17 00:00:00 2001
From: Martin Wilck <mwilck@suse.com>
Date: Tue, 23 Mar 2021 22:24:30 +0100
Subject: [PATCH 1260/1820] scsi: target: pscsi: Avoid OOM in pscsi_map_sg()

pscsi_map_sg() uses the variable nr_pages as a hint for bio_kmalloc() how
many vector elements to allocate. If nr_pages is < BIO_MAX_PAGES, it will
be reset to 0 after successful allocation of the bio.

If bio_add_pc_page() fails later for whatever reason, pscsi_map_sg() tries
to allocate another bio, passing nr_vecs = 0. This causes bio_add_pc_page()
to fail immediately in the next call. pci_map_sg() continues to allocate
zero-length bios until memory is exhausted and the kernel crashes with
OOM. This can be easily observed by exporting a SATA DVD drive via pscsi.
The target crashes as soon as the client tries to access the DVD LUN. In
the case I analyzed, bio_add_pc_page() would fail because the DVD device's
max_sectors_kb (128) was exceeded.

Avoid this by simply not resetting nr_pages to 0 after allocating the
bio. This way, the client receives an I/O error when it tries to send
requests exceeding the devices max_sectors_kb, and eventually gets it
right. The client must still limit max_sectors_kb e.g. by an udev rule if
(like in my case) the driver doesn't report valid block limits, otherwise
it encounters I/O errors.

Link: https://lore.kernel.org/r/20210323212431.15306-1-mwilck@suse.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Lee Duncan <lduncan@suse.com>
Signed-off-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_pscsi.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 3cbc074992bc..6fa9fddc2e1e 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -882,7 +882,6 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 			if (!bio) {
 new_bio:
 				nr_vecs = bio_max_segs(nr_pages);
-				nr_pages -= nr_vecs;
 				/*
 				 * Calls bio_kmalloc() and sets bio->bi_end_io()
 				 */

From 36fa766faa0c822c860e636fe82b1affcd022974 Mon Sep 17 00:00:00 2001
From: Martin Wilck <mwilck@suse.com>
Date: Tue, 23 Mar 2021 22:24:31 +0100
Subject: [PATCH 1261/1820] scsi: target: pscsi: Clean up after failure in
 pscsi_map_sg()

If pscsi_map_sg() fails, make sure to drop references to already allocated
bios.

Link: https://lore.kernel.org/r/20210323212431.15306-2-mwilck@suse.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Lee Duncan <lduncan@suse.com>
Signed-off-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_pscsi.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 6fa9fddc2e1e..9ee797b8cb7e 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -938,6 +938,14 @@ new_bio:
 
 	return 0;
 fail:
+	if (bio)
+		bio_put(bio);
+	while (req->bio) {
+		bio = req->bio;
+		req->bio = bio->bi_next;
+		bio_put(bio);
+	}
+	req->biotail = NULL;
 	return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 }
 

From 69c3ed7282a143439bbc2d03dc00d49c68fcb629 Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Wed, 20 Jan 2021 01:16:08 -0800
Subject: [PATCH 1262/1820] drm/imx: fix memory leak when fails to init

Put DRM device on initialization failure path rather than directly
return error code.

Fixes: a67d5088ceb8 ("drm/imx: drop explicit drm_mode_config_cleanup")
Signed-off-by: Pan Bian <bianpan2016@163.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/drm/imx/imx-drm-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index d1a9841adeed..e6a88c8cbd69 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -215,7 +215,7 @@ static int imx_drm_bind(struct device *dev)
 
 	ret = drmm_mode_config_init(drm);
 	if (ret)
-		return ret;
+		goto err_kms;
 
 	ret = drm_vblank_init(drm, MAX_CRTC);
 	if (ret)

From 12d0ca80bffdad9e9b2a7a68784bfca54c8cf1a1 Mon Sep 17 00:00:00 2001
From: Liu Ying <victor.liu@nxp.com>
Date: Mon, 22 Mar 2021 10:56:40 +0800
Subject: [PATCH 1263/1820] drm/imx: imx-ldb: Register LDB channel1 when it is
 the only channel to be used

LDB channel1 should be registered if it is the only channel to be used.
Without this patch, imx_ldb_bind() would skip registering LDB channel1
if LDB channel0 is not used, no matter LDB channel1 needs to be used or
not.

Fixes: 8767f4711b2b (drm/imx: imx-ldb: move initialization into probe)
Signed-off-by: Liu Ying <victor.liu@nxp.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/drm/imx/imx-ldb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index dbfe39e2f7f6..b794ed448ea3 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -583,7 +583,7 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 		struct imx_ldb_channel *channel = &imx_ldb->channel[i];
 
 		if (!channel->ldb)
-			break;
+			continue;
 
 		ret = imx_ldb_register(drm, channel);
 		if (ret)

From 33ce7f2f95cabb5834cf0906308a5cb6103976da Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 24 Mar 2021 17:47:41 +0100
Subject: [PATCH 1264/1820] drm/imx: imx-ldb: fix out of bounds array access
 warning

When CONFIG_OF is disabled, building with 'make W=1' produces warnings
about out of bounds array access:

drivers/gpu/drm/imx/imx-ldb.c: In function 'imx_ldb_set_clock.constprop':
drivers/gpu/drm/imx/imx-ldb.c:186:8: error: array subscript -22 is below array bounds of 'struct clk *[4]' [-Werror=array-bounds]

Add an error check before the index is used, which helps with the
warning, as well as any possible other error condition that may be
triggered at runtime.

The warning could be fixed by adding a Kconfig depedency on CONFIG_OF,
but Liu Ying points out that the driver may hit the out-of-bounds
problem at runtime anyway.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Liu Ying <victor.liu@nxp.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/drm/imx/imx-ldb.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index b794ed448ea3..ffdc492c5bc5 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -197,6 +197,11 @@ static void imx_ldb_encoder_enable(struct drm_encoder *encoder)
 	int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN;
 	int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder);
 
+	if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) {
+		dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux);
+		return;
+	}
+
 	drm_panel_prepare(imx_ldb_ch->panel);
 
 	if (dual) {
@@ -255,6 +260,11 @@ imx_ldb_encoder_atomic_mode_set(struct drm_encoder *encoder,
 	int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder);
 	u32 bus_format = imx_ldb_ch->bus_format;
 
+	if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) {
+		dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux);
+		return;
+	}
+
 	if (mode->clock > 170000) {
 		dev_warn(ldb->dev,
 			 "%s: mode exceeds 170 MHz pixel clock\n", __func__);

From 58b5ada8c465b5f1300bc021ebd3d3b8149124b4 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 23 Mar 2021 14:17:13 +0100
Subject: [PATCH 1265/1820] pinctrl: qcom: fix unintentional string
 concatenation

clang is clearly correct to point out a typo in a silly
array of strings:

drivers/pinctrl/qcom/pinctrl-sdx55.c:426:61: error: suspicious concatenation of string literals in an array initialization; did you mean to separate the elements with a comma? [-Werror,-Wstring-concatenation]
        "gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19" "gpio20", "gpio21", "gpio22",
                                                                   ^
Add the missing comma that must have accidentally been removed.

Fixes: ac43c44a7a37 ("pinctrl: qcom: Add SDX55 pincontrol driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20210323131728.2702789-1-arnd@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-sdx55.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-sdx55.c b/drivers/pinctrl/qcom/pinctrl-sdx55.c
index 2b5b0e2b03ad..5aaf57b40407 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdx55.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdx55.c
@@ -423,7 +423,7 @@ static const char * const gpio_groups[] = {
 
 static const char * const qdss_stm_groups[] = {
 	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7", "gpio12", "gpio13",
-	"gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19" "gpio20", "gpio21", "gpio22",
+	"gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21", "gpio22",
 	"gpio23", "gpio44", "gpio45", "gpio52", "gpio53", "gpio56", "gpio57", "gpio61", "gpio62",
 	"gpio63", "gpio64", "gpio65", "gpio66",
 };

From baa96377bc7b5aa7b8cf038db09cb99642321490 Mon Sep 17 00:00:00 2001
From: Maninder Singh <maninder1.s@samsung.com>
Date: Wed, 24 Mar 2021 12:24:58 +0530
Subject: [PATCH 1266/1820] arm64/process.c: fix Wmissing-prototypes build
 warnings

Fix GCC warnings reported when building with "-Wmissing-prototypes":

  arch/arm64/kernel/process.c:261:6: warning: no previous prototype for '__show_regs' [-Wmissing-prototypes]
      261 | void __show_regs(struct pt_regs *regs)
          |      ^~~~~~~~~~~
  arch/arm64/kernel/process.c:307:6: warning: no previous prototype for '__show_regs_alloc_free' [-Wmissing-prototypes]
      307 | void __show_regs_alloc_free(struct pt_regs *regs)
          |      ^~~~~~~~~~~~~~~~~~~~~~
  arch/arm64/kernel/process.c:365:5: warning: no previous prototype for 'arch_dup_task_struct' [-Wmissing-prototypes]
      365 | int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
          |     ^~~~~~~~~~~~~~~~~~~~
  arch/arm64/kernel/process.c:546:41: warning: no previous prototype for '__switch_to' [-Wmissing-prototypes]
      546 | __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
          |                                         ^~~~~~~~~~~
  arch/arm64/kernel/process.c:710:25: warning: no previous prototype for 'arm64_preempt_schedule_irq' [-Wmissing-prototypes]
      710 | asmlinkage void __sched arm64_preempt_schedule_irq(void)
          |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~

Link: https://lore.kernel.org/lkml/202103192250.AennsfXM-lkp@intel.com
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Maninder Singh <maninder1.s@samsung.com>
Link: https://lore.kernel.org/r/1616568899-986-1-git-send-email-maninder1.s@samsung.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/processor.h   | 2 ++
 arch/arm64/include/asm/thread_info.h | 2 ++
 arch/arm64/kernel/process.c          | 2 ++
 3 files changed, 6 insertions(+)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ca2cd75d3286..efc10e9041a0 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -251,6 +251,8 @@ unsigned long get_wchan(struct task_struct *p);
 extern struct task_struct *cpu_switch_to(struct task_struct *prev,
 					 struct task_struct *next);
 
+asmlinkage void arm64_preempt_schedule_irq(void);
+
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
 
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 9f4e3b266f21..6623c99f0984 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -55,6 +55,8 @@ void arch_setup_new_exec(void);
 #define arch_setup_new_exec     arch_setup_new_exec
 
 void arch_release_task_struct(struct task_struct *tsk);
+int arch_dup_task_struct(struct task_struct *dst,
+				struct task_struct *src);
 
 #endif
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 325c83b1a24d..6e60aa3b5ea9 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -57,6 +57,8 @@
 #include <asm/processor.h>
 #include <asm/pointer_auth.h>
 #include <asm/stacktrace.h>
+#include <asm/switch_to.h>
+#include <asm/system_misc.h>
 
 #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
 #include <linux/stackprotector.h>

From 20109a859a9b514eb10c22b8a14b5704ffe93897 Mon Sep 17 00:00:00 2001
From: Rich Wiley <rwiley@nvidia.com>
Date: Tue, 23 Mar 2021 17:28:09 -0700
Subject: [PATCH 1267/1820] arm64: kernel: disable CNP on Carmel

On NVIDIA Carmel cores, CNP behaves differently than it does on standard
ARM cores. On Carmel, if two cores have CNP enabled and share an L2 TLB
entry created by core0 for a specific ASID, a non-shareable TLBI from
core1 may still see the shared entry. On standard ARM cores, that TLBI
will invalidate the shared entry as well.

This causes issues with patchsets that attempt to do local TLBIs based
on cpumasks instead of broadcast TLBIs. Avoid these issues by disabling
CNP support for NVIDIA Carmel cores.

Signed-off-by: Rich Wiley <rwiley@nvidia.com>
Link: https://lore.kernel.org/r/20210324002809.30271-1-rwiley@nvidia.com
[will: Fix pre-existing whitespace issue]
Signed-off-by: Will Deacon <will@kernel.org>
---
 Documentation/arm64/silicon-errata.rst |  3 +++
 arch/arm64/Kconfig                     | 10 ++++++++++
 arch/arm64/include/asm/cpucaps.h       |  3 ++-
 arch/arm64/kernel/cpu_errata.c         |  8 ++++++++
 arch/arm64/kernel/cpufeature.c         |  5 ++++-
 5 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index 719510247292..d410a47ffa57 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -130,6 +130,9 @@ stable kernels.
 | Marvell        | ARM-MMU-500     | #582743         | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
+| NVIDIA         | Carmel Core     | N/A             | NVIDIA_CARMEL_CNP_ERRATUM   |
++----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
 | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5656e7aacd69..e4e1b6550115 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -810,6 +810,16 @@ config QCOM_FALKOR_ERRATUM_E1041
 
 	  If unsure, say Y.
 
+config NVIDIA_CARMEL_CNP_ERRATUM
+	bool "NVIDIA Carmel CNP: CNP on Carmel semantically different than ARM cores"
+	default y
+	help
+	  If CNP is enabled on Carmel cores, non-sharable TLBIs on a core will not
+	  invalidate shared TLB entries installed by a different core, as it would
+	  on standard ARM cores.
+
+	  If unsure, say Y.
+
 config SOCIONEXT_SYNQUACER_PREITS
 	bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
 	default y
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index b77d997b173b..c40f2490cd7b 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -66,7 +66,8 @@
 #define ARM64_WORKAROUND_1508412		58
 #define ARM64_HAS_LDAPR				59
 #define ARM64_KVM_PROTECTED_MODE		60
+#define ARM64_WORKAROUND_NVIDIA_CARMEL_CNP	61
 
-#define ARM64_NCAPS				61
+#define ARM64_NCAPS				62
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 506a1cd37973..e2c20c036442 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -525,6 +525,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 				  0, 0,
 				  1, 0),
 	},
+#endif
+#ifdef CONFIG_NVIDIA_CARMEL_CNP_ERRATUM
+	{
+		/* NVIDIA Carmel */
+		.desc = "NVIDIA Carmel CNP erratum",
+		.capability = ARM64_WORKAROUND_NVIDIA_CARMEL_CNP,
+		ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
+	},
 #endif
 	{
 	}
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 066030717a4c..2a5d9854d664 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1321,7 +1321,10 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope)
 	 * may share TLB entries with a CPU stuck in the crashed
 	 * kernel.
 	 */
-	 if (is_kdump_kernel())
+	if (is_kdump_kernel())
+		return false;
+
+	if (cpus_have_const_cap(ARM64_WORKAROUND_NVIDIA_CARMEL_CNP))
 		return false;
 
 	return has_cpuid_feature(entry, scope);

From d624833f5984d484c5e3196f34b926f9e71dafee Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 17 Feb 2021 20:26:23 +0100
Subject: [PATCH 1268/1820] ARM: 9063/1: mm: reduce maximum number of CPUs if
 DEBUG_KMAP_LOCAL is enabled

The debugging code for kmap_local() doubles the number of per-CPU fixmap
slots allocated for kmap_local(), in order to use half of them as guard
regions. This causes the fixmap region to grow downwards beyond the start
of its reserved window if the supported number of CPUs is large, and collide
with the newly added virtual DT mapping right below it, which is obviously
not good.

One manifestation of this is EFI boot on a kernel built with NR_CPUS=32
and CONFIG_DEBUG_KMAP_LOCAL=y, which may pass the FDT in highmem, resulting
in block entries below the fixmap region that the fixmap code misidentifies
as fixmap table entries, and subsequently tries to dereference using a
phys-to-virt translation that is only valid for lowmem. This results in a
cryptic splat such as the one below.

  ftrace: allocating 45548 entries in 89 pages
  8<--- cut here ---
  Unable to handle kernel paging request at virtual address fc6006f0
  pgd = (ptrval)
  [fc6006f0] *pgd=80000040207003, *pmd=00000000
  Internal error: Oops: a06 [#1] SMP ARM
  Modules linked in:
  CPU: 0 PID: 0 Comm: swapper Not tainted 5.11.0+ #382
  Hardware name: Generic DT based system
  PC is at cpu_ca15_set_pte_ext+0x24/0x30
  LR is at __set_fixmap+0xe4/0x118
  pc : [<c041ac9c>]    lr : [<c04189d8>]    psr: 400000d3
  sp : c1601ed8  ip : 00400000  fp : 00800000
  r10: 0000071f  r9 : 00421000  r8 : 00c00000
  r7 : 00c00000  r6 : 0000071f  r5 : ffade000  r4 : 4040171f
  r3 : 00c00000  r2 : 4040171f  r1 : c041ac78  r0 : fc6006f0
  Flags: nZcv  IRQs off  FIQs off  Mode SVC_32  ISA ARM  Segment none
  Control: 30c5387d  Table: 40203000  DAC: 00000001
  Process swapper (pid: 0, stack limit = 0x(ptrval))

So let's limit CONFIG_NR_CPUS to 16 when CONFIG_DEBUG_KMAP_LOCAL=y. Also,
fix the BUILD_BUG_ON() check that was supposed to catch this, by checking
whether the region grows below the start address rather than above the end
address.

Fixes: 2a15ba82fa6ca3f3 ("ARM: highmem: Switch to generic kmap atomic")
Reported-by: Peter Robinson <pbrobinson@gmail.com>
Tested-by: Peter Robinson <pbrobinson@gmail.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/Kconfig  | 8 +++++++-
 arch/arm/mm/mmu.c | 3 +--
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 853aab5ab327..becc6d684051 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1292,9 +1292,15 @@ config KASAN_SHADOW_OFFSET
 
 config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
-	range 2 32
+	range 2 16 if DEBUG_KMAP_LOCAL
+	range 2 32 if !DEBUG_KMAP_LOCAL
 	depends on SMP
 	default "4"
+	help
+	  The maximum number of CPUs that the kernel can support.
+	  Up to 32 CPUs can be supported, or up to 16 if kmap_local()
+	  debugging is enabled, which uses half of the per-CPU fixmap
+	  slots as guard regions.
 
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index a25b660c3017..c1e12aab67b8 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -387,8 +387,7 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
 	pte_t *pte = pte_offset_fixmap(pmd_off_k(vaddr), vaddr);
 
 	/* Make sure fixmap region does not exceed available allocation. */
-	BUILD_BUG_ON(FIXADDR_START + (__end_of_fixed_addresses * PAGE_SIZE) >
-		     FIXADDR_END);
+	BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) < FIXADDR_START);
 	BUG_ON(idx >= __end_of_fixed_addresses);
 
 	/* we only support device mappings until pgprot_kernel has been set */

From 45c2f70cba3a7eff34574103b2e2b901a5f771aa Mon Sep 17 00:00:00 2001
From: Vladimir Murzin <vladimir.murzin@arm.com>
Date: Thu, 11 Mar 2021 13:32:16 +0100
Subject: [PATCH 1269/1820] ARM: 9069/1: NOMMU: Fix conversion
 for_each_membock() to for_each_mem_range()

for_each_mem_range() uses a loop variable, yet looking into code it is
not just iteration counter but more complex entity which encodes
information about memblock. Thus condition i == 0 looks fragile.
Indeed, it broke boot of R-class platforms since it never took i == 0
path (due to i was set to 1). Fix that with restoring original flag
check.

Fixes: b10d6bca8720 ("arch, drivers: replace for_each_membock() with for_each_mem_range()")
Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/mm/pmsa-v7.c | 4 +++-
 arch/arm/mm/pmsa-v8.c | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c
index 88950e41a3a9..59d916ccdf25 100644
--- a/arch/arm/mm/pmsa-v7.c
+++ b/arch/arm/mm/pmsa-v7.c
@@ -235,6 +235,7 @@ void __init pmsav7_adjust_lowmem_bounds(void)
 	phys_addr_t mem_end;
 	phys_addr_t reg_start, reg_end;
 	unsigned int mem_max_regions;
+	bool first = true;
 	int num;
 	u64 i;
 
@@ -263,7 +264,7 @@ void __init pmsav7_adjust_lowmem_bounds(void)
 #endif
 
 	for_each_mem_range(i, &reg_start, &reg_end) {
-		if (i == 0) {
+		if (first) {
 			phys_addr_t phys_offset = PHYS_OFFSET;
 
 			/*
@@ -275,6 +276,7 @@ void __init pmsav7_adjust_lowmem_bounds(void)
 			mem_start = reg_start;
 			mem_end = reg_end;
 			specified_mem_size = mem_end - mem_start;
+			first = false;
 		} else {
 			/*
 			 * memblock auto merges contiguous blocks, remove
diff --git a/arch/arm/mm/pmsa-v8.c b/arch/arm/mm/pmsa-v8.c
index 2de019f7503e..8359748a19a1 100644
--- a/arch/arm/mm/pmsa-v8.c
+++ b/arch/arm/mm/pmsa-v8.c
@@ -95,10 +95,11 @@ void __init pmsav8_adjust_lowmem_bounds(void)
 {
 	phys_addr_t mem_end;
 	phys_addr_t reg_start, reg_end;
+	bool first = true;
 	u64 i;
 
 	for_each_mem_range(i, &reg_start, &reg_end) {
-		if (i == 0) {
+		if (first) {
 			phys_addr_t phys_offset = PHYS_OFFSET;
 
 			/*
@@ -107,6 +108,7 @@ void __init pmsav8_adjust_lowmem_bounds(void)
 			if (reg_start != phys_offset)
 				panic("First memory bank must be contiguous from PHYS_OFFSET");
 			mem_end = reg_end;
+			first = false;
 		} else {
 			/*
 			 * memblock auto merges contiguous blocks, remove

From 30e3b4f256b4e366a61658c294f6a21b8626dda7 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 25 Mar 2021 10:26:21 +0000
Subject: [PATCH 1270/1820] ARM: footbridge: fix PCI interrupt mapping

Since commit 30fdfb929e82 ("PCI: Add a call to pci_assign_irq() in
pci_device_probe()"), the PCI code will call the IRQ mapping function
whenever a PCI driver is probed. If these are marked as __init, this
causes an oops if a PCI driver is loaded or bound after the kernel has
initialised.

Fixes: 30fdfb929e82 ("PCI: Add a call to pci_assign_irq() in pci_device_probe()")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/mach-footbridge/cats-pci.c      | 4 ++--
 arch/arm/mach-footbridge/ebsa285-pci.c   | 4 ++--
 arch/arm/mach-footbridge/netwinder-pci.c | 2 +-
 arch/arm/mach-footbridge/personal-pci.c  | 5 ++---
 4 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/arch/arm/mach-footbridge/cats-pci.c b/arch/arm/mach-footbridge/cats-pci.c
index 0b2fd7e2e9b4..90b1e9be430e 100644
--- a/arch/arm/mach-footbridge/cats-pci.c
+++ b/arch/arm/mach-footbridge/cats-pci.c
@@ -15,14 +15,14 @@
 #include <asm/mach-types.h>
 
 /* cats host-specific stuff */
-static int irqmap_cats[] __initdata = { IRQ_PCI, IRQ_IN0, IRQ_IN1, IRQ_IN3 };
+static int irqmap_cats[] = { IRQ_PCI, IRQ_IN0, IRQ_IN1, IRQ_IN3 };
 
 static u8 cats_no_swizzle(struct pci_dev *dev, u8 *pin)
 {
 	return 0;
 }
 
-static int __init cats_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int cats_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	if (dev->irq >= 255)
 		return -1;	/* not a valid interrupt. */
diff --git a/arch/arm/mach-footbridge/ebsa285-pci.c b/arch/arm/mach-footbridge/ebsa285-pci.c
index 6f28aaa9ca79..c3f280d08fa7 100644
--- a/arch/arm/mach-footbridge/ebsa285-pci.c
+++ b/arch/arm/mach-footbridge/ebsa285-pci.c
@@ -14,9 +14,9 @@
 #include <asm/mach/pci.h>
 #include <asm/mach-types.h>
 
-static int irqmap_ebsa285[] __initdata = { IRQ_IN3, IRQ_IN1, IRQ_IN0, IRQ_PCI };
+static int irqmap_ebsa285[] = { IRQ_IN3, IRQ_IN1, IRQ_IN0, IRQ_PCI };
 
-static int __init ebsa285_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int ebsa285_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	if (dev->vendor == PCI_VENDOR_ID_CONTAQ &&
 	    dev->device == PCI_DEVICE_ID_CONTAQ_82C693)
diff --git a/arch/arm/mach-footbridge/netwinder-pci.c b/arch/arm/mach-footbridge/netwinder-pci.c
index 9473aa0305e5..e8304392074b 100644
--- a/arch/arm/mach-footbridge/netwinder-pci.c
+++ b/arch/arm/mach-footbridge/netwinder-pci.c
@@ -18,7 +18,7 @@
  * We now use the slot ID instead of the device identifiers to select
  * which interrupt is routed where.
  */
-static int __init netwinder_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int netwinder_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	switch (slot) {
 	case 0:  /* host bridge */
diff --git a/arch/arm/mach-footbridge/personal-pci.c b/arch/arm/mach-footbridge/personal-pci.c
index 4391e433a4b2..9d19aa98a663 100644
--- a/arch/arm/mach-footbridge/personal-pci.c
+++ b/arch/arm/mach-footbridge/personal-pci.c
@@ -14,13 +14,12 @@
 #include <asm/mach/pci.h>
 #include <asm/mach-types.h>
 
-static int irqmap_personal_server[] __initdata = {
+static int irqmap_personal_server[] = {
 	IRQ_IN0, IRQ_IN1, IRQ_IN2, IRQ_IN3, 0, 0, 0,
 	IRQ_DOORBELLHOST, IRQ_DMA1, IRQ_DMA2, IRQ_PCI
 };
 
-static int __init personal_server_map_irq(const struct pci_dev *dev, u8 slot,
-	u8 pin)
+static int personal_server_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	unsigned char line;
 

From 39c1f1bd8adf29840ef52225ce95f390e3d7b2cf Mon Sep 17 00:00:00 2001
From: Roger Pau Monne <roger.pau@citrix.com>
Date: Thu, 25 Mar 2021 10:09:47 +0100
Subject: [PATCH 1271/1820] pinctrl: intel: check REVID register value for
 device presence
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the value read from the REVID register in order to check for the
presence of the device. A read of all ones is treated as if the device
is not present, and hence probing is ended.

This fixes an issue when running as a Xen PVH dom0, where the ACPI
DSDT table is provided unmodified to dom0 and hence contains the
pinctrl devices, but the MMIO region(s) containing the device
registers might not be mapped in the guest physical memory map if such
region(s) are not exposed on a PCI device BAR or marked as reserved in
the host memory map.

Fixes: 91d898e51e60 ("pinctrl: intel: Convert capability list to features")
Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 7283203861ae..9f3361c13ded 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1493,8 +1493,13 @@ static int intel_pinctrl_probe(struct platform_device *pdev,
 		if (IS_ERR(regs))
 			return PTR_ERR(regs);
 
-		/* Determine community features based on the revision */
+		/*
+		 * Determine community features based on the revision.
+		 * A value of all ones means the device is not present.
+		 */
 		value = readl(regs + REVID);
+		if (value == ~0u)
+			return -ENODEV;
 		if (((value & REVID_MASK) >> REVID_SHIFT) >= 0x94) {
 			community->features |= PINCTRL_FEATURE_DEBOUNCE;
 			community->features |= PINCTRL_FEATURE_1K_PD;

From 3408be145a5d6418ff955fe5badde652be90e700 Mon Sep 17 00:00:00 2001
From: Potnuri Bharat Teja <bharat@chelsio.com>
Date: Thu, 25 Mar 2021 00:34:53 +0530
Subject: [PATCH 1272/1820] RDMA/cxgb4: Fix adapter LE hash errors while
 destroying ipv6 listening server

Not setting the ipv6 bit while destroying ipv6 listening servers may
result in potential fatal adapter errors due to lookup engine memory hash
errors. Therefore always set ipv6 field while destroying ipv6 listening
servers.

Fixes: 830662f6f032 ("RDMA/cxgb4: Add support for active and passive open connection with IPv6 address")
Link: https://lore.kernel.org/r/20210324190453.8171-1-bharat@chelsio.com
Signed-off-by: Potnuri Bharat Teja <bharat@chelsio.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/cxgb4/cm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 8769e7aa097f..81903749d241 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -3610,13 +3610,13 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id)
 	    ep->com.local_addr.ss_family == AF_INET) {
 		err = cxgb4_remove_server_filter(
 			ep->com.dev->rdev.lldi.ports[0], ep->stid,
-			ep->com.dev->rdev.lldi.rxq_ids[0], 0);
+			ep->com.dev->rdev.lldi.rxq_ids[0], false);
 	} else {
 		struct sockaddr_in6 *sin6;
 		c4iw_init_wr_wait(ep->com.wr_waitp);
 		err = cxgb4_remove_server(
 				ep->com.dev->rdev.lldi.ports[0], ep->stid,
-				ep->com.dev->rdev.lldi.rxq_ids[0], 0);
+				ep->com.dev->rdev.lldi.rxq_ids[0], true);
 		if (err)
 			goto done;
 		err = c4iw_wait_for_reply(&ep->com.dev->rdev, ep->com.wr_waitp,

From 37df9f3fedb6aeaff5564145e8162aab912c9284 Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Wed, 24 Mar 2021 03:37:24 -0700
Subject: [PATCH 1273/1820] video: hyperv_fb: Fix a double free in hvfb_probe

Function hvfb_probe() calls hvfb_getmem(), expecting upon return that
info->apertures is either NULL or points to memory that should be freed
by framebuffer_release().  But hvfb_getmem() is freeing the memory and
leaving the pointer non-NULL, resulting in a double free if an error
occurs or later if hvfb_remove() is called.

Fix this by removing all kfree(info->apertures) calls in hvfb_getmem().
This will allow framebuffer_release() to free the memory, which follows
the pattern of other fbdev drivers.

Fixes: 3a6fb6c4255c ("video: hyperv: hyperv_fb: Use physical memory for fb on HyperV Gen 1 VMs.")
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20210324103724.4189-1-lyl2019@mail.ustc.edu.cn
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/video/fbdev/hyperv_fb.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index c8b0ae676809..4dc9077dd2ac 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -1031,7 +1031,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 			PCI_DEVICE_ID_HYPERV_VIDEO, NULL);
 		if (!pdev) {
 			pr_err("Unable to find PCI Hyper-V video\n");
-			kfree(info->apertures);
 			return -ENODEV;
 		}
 
@@ -1129,7 +1128,6 @@ getmem_done:
 	} else {
 		pci_dev_put(pdev);
 	}
-	kfree(info->apertures);
 
 	return 0;
 
@@ -1141,7 +1139,6 @@ err2:
 err1:
 	if (!gen2vm)
 		pci_dev_put(pdev);
-	kfree(info->apertures);
 
 	return -ENOMEM;
 }

From a23f9099ff1541f15704e96b784d3846d2a4483d Mon Sep 17 00:00:00 2001
From: Ryan Lee <ryans.lee@maximintegrated.com>
Date: Wed, 24 Mar 2021 20:35:53 -0700
Subject: [PATCH 1274/1820] ASoC: max98373: Changed amp shutdown register as
 volatile

0x20FF(amp global enable) register was defined as non-volatile,
but it is not. Overheating, overcurrent can cause amp shutdown
in hardware.
'regmap_write' compare register readback value before writing
to avoid same value writing. 'regmap_read' just read cache
not actual hardware value for the non-volatile register.
When amp is internally shutdown by some reason, next 'AMP ON'
command can be ignored because regmap think amp is already ON.

Signed-off-by: Ryan Lee <ryans.lee@maximintegrated.com>
Link: https://lore.kernel.org/r/20210325033555.29377-1-ryans.lee@maximintegrated.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/max98373-i2c.c | 1 +
 sound/soc/codecs/max98373-sdw.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/sound/soc/codecs/max98373-i2c.c b/sound/soc/codecs/max98373-i2c.c
index 85f6865019d4..ddb6436835d7 100644
--- a/sound/soc/codecs/max98373-i2c.c
+++ b/sound/soc/codecs/max98373-i2c.c
@@ -446,6 +446,7 @@ static bool max98373_volatile_reg(struct device *dev, unsigned int reg)
 	case MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK:
 	case MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK:
 	case MAX98373_R20B6_BDE_CUR_STATE_READBACK:
+	case MAX98373_R20FF_GLOBAL_SHDN:
 	case MAX98373_R21FF_REV_ID:
 		return true;
 	default:
diff --git a/sound/soc/codecs/max98373-sdw.c b/sound/soc/codecs/max98373-sdw.c
index d8c47667a9ea..f3a12205cd48 100644
--- a/sound/soc/codecs/max98373-sdw.c
+++ b/sound/soc/codecs/max98373-sdw.c
@@ -220,6 +220,7 @@ static bool max98373_volatile_reg(struct device *dev, unsigned int reg)
 	case MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK:
 	case MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK:
 	case MAX98373_R20B6_BDE_CUR_STATE_READBACK:
+	case MAX98373_R20FF_GLOBAL_SHDN:
 	case MAX98373_R21FF_REV_ID:
 	/* SoundWire Control Port Registers */
 	case MAX98373_R0040_SCP_INIT_STAT_1 ... MAX98373_R0070_SCP_FRAME_CTLR:

From 3a27875e91fb9c29de436199d20b33f9413aea77 Mon Sep 17 00:00:00 2001
From: Ryan Lee <ryans.lee@maximintegrated.com>
Date: Wed, 24 Mar 2021 20:35:54 -0700
Subject: [PATCH 1275/1820] ASoC: max98373: Added 30ms turn on/off time delay

Amp requires 10 ~ 30ms for the power ON and OFF.
Added 30ms delay for stability.

Signed-off-by: Ryan Lee <ryans.lee@maximintegrated.com>
Link: https://lore.kernel.org/r/20210325033555.29377-2-ryans.lee@maximintegrated.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/max98373.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c
index 746c829312b8..1346a98ce8a1 100644
--- a/sound/soc/codecs/max98373.c
+++ b/sound/soc/codecs/max98373.c
@@ -28,11 +28,13 @@ static int max98373_dac_event(struct snd_soc_dapm_widget *w,
 		regmap_update_bits(max98373->regmap,
 			MAX98373_R20FF_GLOBAL_SHDN,
 			MAX98373_GLOBAL_EN_MASK, 1);
+		usleep_range(30000, 31000);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
 		regmap_update_bits(max98373->regmap,
 			MAX98373_R20FF_GLOBAL_SHDN,
 			MAX98373_GLOBAL_EN_MASK, 0);
+		usleep_range(30000, 31000);
 		max98373->tdm_mode = false;
 		break;
 	default:

From f5d2d23bf0d948ce0b9307b7bacae7ff0bc03c71 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 25 Mar 2021 10:16:12 -0600
Subject: [PATCH 1276/1820] io-wq: fix race around pending work on teardown

syzbot reports that it's triggering the warning condition on having
pending work on shutdown:

WARNING: CPU: 1 PID: 12346 at fs/io-wq.c:1061 io_wq_destroy fs/io-wq.c:1061 [inline]
WARNING: CPU: 1 PID: 12346 at fs/io-wq.c:1061 io_wq_put+0x153/0x260 fs/io-wq.c:1072
Modules linked in:
CPU: 1 PID: 12346 Comm: syz-executor.5 Not tainted 5.12.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:io_wq_destroy fs/io-wq.c:1061 [inline]
RIP: 0010:io_wq_put+0x153/0x260 fs/io-wq.c:1072
Code: 8d e8 71 90 ea 01 49 89 c4 41 83 fc 40 7d 4f e8 33 4d 97 ff 42 80 7c 2d 00 00 0f 85 77 ff ff ff e9 7a ff ff ff e8 1d 4d 97 ff <0f> 0b eb b9 8d 6b ff 89 ee 09 de bf ff ff ff ff e8 18 51 97 ff 09
RSP: 0018:ffffc90001ebfb08 EFLAGS: 00010293
RAX: ffffffff81e16083 RBX: ffff888019038040 RCX: ffff88801e86b780
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000040
RBP: 1ffff1100b2f8a80 R08: ffffffff81e15fce R09: ffffed100b2f8a82
R10: ffffed100b2f8a82 R11: 0000000000000000 R12: 0000000000000000
R13: dffffc0000000000 R14: ffff8880597c5400 R15: ffff888019038000
FS:  00007f8dcd89c700(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055e9a054e160 CR3: 000000001dfb8000 CR4: 00000000001506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 io_uring_clean_tctx+0x1b7/0x210 fs/io_uring.c:8802
 __io_uring_files_cancel+0x13c/0x170 fs/io_uring.c:8820
 io_uring_files_cancel include/linux/io_uring.h:47 [inline]
 do_exit+0x258/0x2340 kernel/exit.c:780
 do_group_exit+0x168/0x2d0 kernel/exit.c:922
 get_signal+0x1734/0x1ef0 kernel/signal.c:2773
 arch_do_signal_or_restart+0x3c/0x610 arch/x86/kernel/signal.c:811
 handle_signal_work kernel/entry/common.c:147 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:171 [inline]
 exit_to_user_mode_prepare+0xac/0x1e0 kernel/entry/common.c:208
 __syscall_exit_to_user_mode_work kernel/entry/common.c:290 [inline]
 syscall_exit_to_user_mode+0x48/0x180 kernel/entry/common.c:301
 entry_SYSCALL_64_after_hwframe+0x44/0xae
RIP: 0033:0x465f69

which shouldn't happen, but seems to be possible due to a race on whether
or not the io-wq manager sees a fatal signal first, or whether the io-wq
workers do. If we race with queueing work and then send a fatal signal to
the owning task, and the io-wq worker sees that before the manager sets
IO_WQ_BIT_EXIT, then it's possible to have the worker exit and leave work
behind.

Just turn the WARN_ON_ONCE() into a cancelation condition instead.

Reported-by: syzbot+77a738a6bc947bf639ca@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 2dd43bdb9c7b..b7c1fa932cb3 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -1063,7 +1063,11 @@ static void io_wq_destroy(struct io_wq *wq)
 
 	for_each_node(node) {
 		struct io_wqe *wqe = wq->wqes[node];
-		WARN_ON_ONCE(!wq_list_empty(&wqe->work_list));
+		struct io_cb_cancel_data match = {
+			.fn		= io_wq_work_match_all,
+			.cancel_all	= true,
+		};
+		io_wqe_cancel_pending_work(wqe, &match);
 		kfree(wqe);
 	}
 	io_wq_put_hash(wq->hash);

From d85aecf2844ff02a0e5f077252b2461d4f10c9f0 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Wed, 24 Mar 2021 21:37:17 -0700
Subject: [PATCH 1277/1820] hugetlb_cgroup: fix imbalanced css_get and css_put
 pair for shared mappings

The current implementation of hugetlb_cgroup for shared mappings could
have different behavior.  Consider the following two scenarios:

 1.Assume initial css reference count of hugetlb_cgroup is 1:
  1.1 Call hugetlb_reserve_pages with from = 1, to = 2. So css reference
      count is 2 associated with 1 file_region.
  1.2 Call hugetlb_reserve_pages with from = 2, to = 3. So css reference
      count is 3 associated with 2 file_region.
  1.3 coalesce_file_region will coalesce these two file_regions into
      one. So css reference count is 3 associated with 1 file_region
      now.

 2.Assume initial css reference count of hugetlb_cgroup is 1 again:
  2.1 Call hugetlb_reserve_pages with from = 1, to = 3. So css reference
      count is 2 associated with 1 file_region.

Therefore, we might have one file_region while holding one or more css
reference counts. This inconsistency could lead to imbalanced css_get()
and css_put() pair. If we do css_put one by one (i.g. hole punch case),
scenario 2 would put one more css reference. If we do css_put all
together (i.g. truncate case), scenario 1 will leak one css reference.

The imbalanced css_get() and css_put() pair would result in a non-zero
reference when we try to destroy the hugetlb cgroup. The hugetlb cgroup
directory is removed __but__ associated resource is not freed. This
might result in OOM or can not create a new hugetlb cgroup in a busy
workload ultimately.

In order to fix this, we have to make sure that one file_region must
hold exactly one css reference. So in coalesce_file_region case, we
should release one css reference before coalescence. Also only put css
reference when the entire file_region is removed.

The last thing to note is that the caller of region_add() will only hold
one reference to h_cg->css for the whole contiguous reservation region.
But this area might be scattered when there are already some
file_regions reside in it. As a result, many file_regions may share only
one h_cg->css reference. In order to ensure that one file_region must
hold exactly one css reference, we should do css_get() for each
file_region and release the reference held by caller when they are done.

[linmiaohe@huawei.com: fix imbalanced css_get and css_put pair for shared mappings]
  Link: https://lkml.kernel.org/r/20210316023002.53921-1-linmiaohe@huawei.com

Link: https://lkml.kernel.org/r/20210301120540.37076-1-linmiaohe@huawei.com
Fixes: 075a61d07a8e ("hugetlb_cgroup: add accounting for shared mappings")
Reported-by: kernel test robot <lkp@intel.com> (auto build test ERROR)
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Wanpeng Li <liwp.linux@gmail.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb_cgroup.h | 15 +++++++++++--
 mm/hugetlb.c                   | 41 ++++++++++++++++++++++++++++++----
 mm/hugetlb_cgroup.c            | 10 +++++++--
 3 files changed, 58 insertions(+), 8 deletions(-)

diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 2ad6e92f124a..0bff345c4bc6 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -113,6 +113,11 @@ static inline bool hugetlb_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(hugetlb_cgrp_subsys);
 }
 
+static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg)
+{
+	css_put(&h_cg->css);
+}
+
 extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 					struct hugetlb_cgroup **ptr);
 extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages,
@@ -138,7 +143,8 @@ extern void hugetlb_cgroup_uncharge_counter(struct resv_map *resv,
 
 extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
 						struct file_region *rg,
-						unsigned long nr_pages);
+						unsigned long nr_pages,
+						bool region_del);
 
 extern void hugetlb_cgroup_file_init(void) __init;
 extern void hugetlb_cgroup_migrate(struct page *oldhpage,
@@ -147,7 +153,8 @@ extern void hugetlb_cgroup_migrate(struct page *oldhpage,
 #else
 static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
 						       struct file_region *rg,
-						       unsigned long nr_pages)
+						       unsigned long nr_pages,
+						       bool region_del)
 {
 }
 
@@ -185,6 +192,10 @@ static inline bool hugetlb_cgroup_disabled(void)
 	return true;
 }
 
+static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg)
+{
+}
+
 static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 					       struct hugetlb_cgroup **ptr)
 {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5b1ab1f427c5..a86a58ef132d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -280,6 +280,17 @@ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
 		nrg->reservation_counter =
 			&h_cg->rsvd_hugepage[hstate_index(h)];
 		nrg->css = &h_cg->css;
+		/*
+		 * The caller will hold exactly one h_cg->css reference for the
+		 * whole contiguous reservation region. But this area might be
+		 * scattered when there are already some file_regions reside in
+		 * it. As a result, many file_regions may share only one css
+		 * reference. In order to ensure that one file_region must hold
+		 * exactly one h_cg->css reference, we should do css_get for
+		 * each file_region and leave the reference held by caller
+		 * untouched.
+		 */
+		css_get(&h_cg->css);
 		if (!resv->pages_per_hpage)
 			resv->pages_per_hpage = pages_per_huge_page(h);
 		/* pages_per_hpage should be the same for all entries in
@@ -293,6 +304,14 @@ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
 #endif
 }
 
+static void put_uncharge_info(struct file_region *rg)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+	if (rg->css)
+		css_put(rg->css);
+#endif
+}
+
 static bool has_same_uncharge_info(struct file_region *rg,
 				   struct file_region *org)
 {
@@ -316,6 +335,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
 		prg->to = rg->to;
 
 		list_del(&rg->link);
+		put_uncharge_info(rg);
 		kfree(rg);
 
 		rg = prg;
@@ -327,6 +347,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
 		nrg->from = rg->from;
 
 		list_del(&rg->link);
+		put_uncharge_info(rg);
 		kfree(rg);
 	}
 }
@@ -662,7 +683,7 @@ retry:
 
 			del += t - f;
 			hugetlb_cgroup_uncharge_file_region(
-				resv, rg, t - f);
+				resv, rg, t - f, false);
 
 			/* New entry for end of split region */
 			nrg->from = t;
@@ -683,7 +704,7 @@ retry:
 		if (f <= rg->from && t >= rg->to) { /* Remove entire region */
 			del += rg->to - rg->from;
 			hugetlb_cgroup_uncharge_file_region(resv, rg,
-							    rg->to - rg->from);
+							    rg->to - rg->from, true);
 			list_del(&rg->link);
 			kfree(rg);
 			continue;
@@ -691,13 +712,13 @@ retry:
 
 		if (f <= rg->from) {	/* Trim beginning of region */
 			hugetlb_cgroup_uncharge_file_region(resv, rg,
-							    t - rg->from);
+							    t - rg->from, false);
 
 			del += t - rg->from;
 			rg->from = t;
 		} else {		/* Trim end of region */
 			hugetlb_cgroup_uncharge_file_region(resv, rg,
-							    rg->to - f);
+							    rg->to - f, false);
 
 			del += rg->to - f;
 			rg->to = f;
@@ -5187,6 +5208,10 @@ bool hugetlb_reserve_pages(struct inode *inode,
 			 */
 			long rsv_adjust;
 
+			/*
+			 * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the
+			 * reference to h_cg->css. See comment below for detail.
+			 */
 			hugetlb_cgroup_uncharge_cgroup_rsvd(
 				hstate_index(h),
 				(chg - add) * pages_per_huge_page(h), h_cg);
@@ -5194,6 +5219,14 @@ bool hugetlb_reserve_pages(struct inode *inode,
 			rsv_adjust = hugepage_subpool_put_pages(spool,
 								chg - add);
 			hugetlb_acct_memory(h, -rsv_adjust);
+		} else if (h_cg) {
+			/*
+			 * The file_regions will hold their own reference to
+			 * h_cg->css. So we should release the reference held
+			 * via hugetlb_cgroup_charge_cgroup_rsvd() when we are
+			 * done.
+			 */
+			hugetlb_cgroup_put_rsvd_cgroup(h_cg);
 		}
 	}
 	return true;
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index f68b51fcda3d..603a131e262d 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -391,7 +391,8 @@ void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start,
 
 void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
 					 struct file_region *rg,
-					 unsigned long nr_pages)
+					 unsigned long nr_pages,
+					 bool region_del)
 {
 	if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages)
 		return;
@@ -400,7 +401,12 @@ void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
 	    !resv->reservation_counter) {
 		page_counter_uncharge(rg->reservation_counter,
 				      nr_pages * resv->pages_per_hpage);
-		css_put(rg->css);
+		/*
+		 * Only do css_put(rg->css) when we delete the entire region
+		 * because one file_region must hold exactly one css reference.
+		 */
+		if (region_del)
+			css_put(rg->css);
 	}
 }
 

From cf10bd4c4aff8dd64d1aa7f2a529d0c672bc16af Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Wed, 24 Mar 2021 21:37:20 -0700
Subject: [PATCH 1278/1820] kasan: fix per-page tags for non-page_alloc pages

To allow performing tag checks on page_alloc addresses obtained via
page_address(), tag-based KASAN modes store tags for page_alloc
allocations in page->flags.

Currently, the default tag value stored in page->flags is 0x00.
Therefore, page_address() returns a 0x00ffff...  address for pages that
were not allocated via page_alloc.

This might cause problems.  A particular case we encountered is a
conflict with KFENCE.  If a KFENCE-allocated slab object is being freed
via kfree(page_address(page) + offset), the address passed to kfree()
will get tagged with 0x00 (as slab pages keep the default per-page
tags).  This leads to is_kfence_address() check failing, and a KFENCE
object ending up in normal slab freelist, which causes memory
corruptions.

This patch changes the way KASAN stores tag in page-flags: they are now
stored xor'ed with 0xff.  This way, KASAN doesn't need to initialize
per-page flags for every created page, which might be slow.

With this change, page_address() returns natively-tagged (with 0xff)
pointers for pages that didn't have tags set explicitly.

This patch fixes the encountered conflict with KFENCE and prevents more
similar issues that can occur in the future.

Link: https://lkml.kernel.org/r/1a41abb11c51b264511d9e71c303bb16d5cb367b.1615475452.git.andreyknvl@google.com
Fixes: 2813b9c02962 ("kasan, mm, arm64: tag non slab memory allocated via pagealloc")
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 64a71bf20536..8ba434287387 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1461,16 +1461,28 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid)
 
 #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
 
+/*
+ * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid
+ * setting tags for all pages to native kernel tag value 0xff, as the default
+ * value 0x00 maps to 0xff.
+ */
+
 static inline u8 page_kasan_tag(const struct page *page)
 {
-	if (kasan_enabled())
-		return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
-	return 0xff;
+	u8 tag = 0xff;
+
+	if (kasan_enabled()) {
+		tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
+		tag ^= 0xff;
+	}
+
+	return tag;
 }
 
 static inline void page_kasan_tag_set(struct page *page, u8 tag)
 {
 	if (kasan_enabled()) {
+		tag ^= 0xff;
 		page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT);
 		page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT;
 	}

From c2655835fd8cabdfe7dab737253de3ffb88da126 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 24 Mar 2021 21:37:23 -0700
Subject: [PATCH 1279/1820] mm/mmu_notifiers: ensure range_end() is paired with
 range_start()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If one or more notifiers fails .invalidate_range_start(), invoke
.invalidate_range_end() for "all" notifiers.  If there are multiple
notifiers, those that did not fail are expecting _start() and _end() to
be paired, e.g.  KVM's mmu_notifier_count would become imbalanced.
Disallow notifiers that can fail _start() from implementing _end() so
that it's unnecessary to either track which notifiers rejected _start(),
or had already succeeded prior to a failed _start().

Note, the existing behavior of calling _start() on all notifiers even
after a previous notifier failed _start() was an unintented "feature".
Make it canon now that the behavior is depended on for correctness.

As of today, the bug is likely benign:

  1. The only caller of the non-blocking notifier is OOM kill.
  2. The only notifiers that can fail _start() are the i915 and Nouveau
     drivers.
  3. The only notifiers that utilize _end() are the SGI UV GRU driver
     and KVM.
  4. The GRU driver will never coincide with the i195/Nouveau drivers.
  5. An imbalanced kvm->mmu_notifier_count only causes soft lockup in the
     _guest_, and the guest is already doomed due to being an OOM victim.

Fix the bug now to play nice with future usage, e.g.  KVM has a
potential use case for blocking memslot updates in KVM while an
invalidation is in-progress, and failure to unblock would result in said
updates being blocked indefinitely and hanging.

Found by inspection.  Verified by adding a second notifier in KVM that
periodically returns -EAGAIN on non-blockable ranges, triggering OOM,
and observing that KVM exits with an elevated notifier count.

Link: https://lkml.kernel.org/r/20210311180057.1582638-1-seanjc@google.com
Fixes: 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Suggested-by: Jason Gunthorpe <jgg@ziepe.ca>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Ben Gardon <bgardon@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmu_notifier.h | 10 +++++-----
 mm/mmu_notifier.c            | 23 +++++++++++++++++++++++
 2 files changed, 28 insertions(+), 5 deletions(-)

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index b8200782dede..1a6a9eb6d3fa 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -169,11 +169,11 @@ struct mmu_notifier_ops {
 	 * the last refcount is dropped.
 	 *
 	 * If blockable argument is set to false then the callback cannot
-	 * sleep and has to return with -EAGAIN. 0 should be returned
-	 * otherwise. Please note that if invalidate_range_start approves
-	 * a non-blocking behavior then the same applies to
-	 * invalidate_range_end.
-	 *
+	 * sleep and has to return with -EAGAIN if sleeping would be required.
+	 * 0 should be returned otherwise. Please note that notifiers that can
+	 * fail invalidate_range_start are not allowed to implement
+	 * invalidate_range_end, as there is no mechanism for informing the
+	 * notifier that its start failed.
 	 */
 	int (*invalidate_range_start)(struct mmu_notifier *subscription,
 				      const struct mmu_notifier_range *range);
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 61ee40ed804e..459d195d2ff6 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -501,10 +501,33 @@ static int mn_hlist_invalidate_range_start(
 						"");
 				WARN_ON(mmu_notifier_range_blockable(range) ||
 					_ret != -EAGAIN);
+				/*
+				 * We call all the notifiers on any EAGAIN,
+				 * there is no way for a notifier to know if
+				 * its start method failed, thus a start that
+				 * does EAGAIN can't also do end.
+				 */
+				WARN_ON(ops->invalidate_range_end);
 				ret = _ret;
 			}
 		}
 	}
+
+	if (ret) {
+		/*
+		 * Must be non-blocking to get here.  If there are multiple
+		 * notifiers and one or more failed start, any that succeeded
+		 * start are expecting their end to be called.  Do so now.
+		 */
+		hlist_for_each_entry_rcu(subscription, &subscriptions->list,
+					 hlist, srcu_read_lock_held(&srcu)) {
+			if (!subscription->ops->invalidate_range_end)
+				continue;
+
+			subscription->ops->invalidate_range_end(subscription,
+								range);
+		}
+	}
 	srcu_read_unlock(&srcu, id);
 
 	return ret;

From 19ec368cbc7ee1915e78c120b7a49c7f14734192 Mon Sep 17 00:00:00 2001
From: Rong Chen <rong.a.chen@intel.com>
Date: Wed, 24 Mar 2021 21:37:26 -0700
Subject: [PATCH 1280/1820] selftests/vm: fix out-of-tree build

When building out-of-tree, attempting to make target from $(OUTPUT) directory:

  make[1]: *** No rule to make target '$(OUTPUT)/protection_keys.c', needed by '$(OUTPUT)/protection_keys_32'.

Link: https://lkml.kernel.org/r/20210315094700.522753-1-rong.a.chen@intel.com
Signed-off-by: Rong Chen <rong.a.chen@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index d42115e4284d..8b0cd421ebd3 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -101,7 +101,7 @@ endef
 ifeq ($(CAN_BUILD_I386),1)
 $(BINARIES_32): CFLAGS += -m32
 $(BINARIES_32): LDLIBS += -lrt -ldl -lm
-$(BINARIES_32): %_32: %.c
+$(BINARIES_32): $(OUTPUT)/%_32: %.c
 	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
 $(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t))))
 endif
@@ -109,7 +109,7 @@ endif
 ifeq ($(CAN_BUILD_X86_64),1)
 $(BINARIES_64): CFLAGS += -m64
 $(BINARIES_64): LDLIBS += -lrt -ldl
-$(BINARIES_64): %_64: %.c
+$(BINARIES_64): $(OUTPUT)/%_64: %.c
 	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
 $(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t))))
 endif

From 6d679578fe9c762c8fbc3d796a067cbba84a7884 Mon Sep 17 00:00:00 2001
From: Thomas Hebb <tommyhebb@gmail.com>
Date: Wed, 24 Mar 2021 21:37:29 -0700
Subject: [PATCH 1281/1820] z3fold: prevent reclaim/free race for headless
 pages

Commit ca0246bb97c2 ("z3fold: fix possible reclaim races") introduced
the PAGE_CLAIMED flag "to avoid racing on a z3fold 'headless' page
release." By atomically testing and setting the bit in each of
z3fold_free() and z3fold_reclaim_page(), a double-free was avoided.

However, commit dcf5aedb24f8 ("z3fold: stricter locking and more careful
reclaim") appears to have unintentionally broken this behavior by moving
the PAGE_CLAIMED check in z3fold_reclaim_page() to after the page lock
gets taken, which only happens for non-headless pages.  For headless
pages, the check is now skipped entirely and races can occur again.

I have observed such a race on my system:

    page:00000000ffbd76b7 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x165316
    flags: 0x2ffff0000000000()
    raw: 02ffff0000000000 ffffea0004535f48 ffff8881d553a170 0000000000000000
    raw: 0000000000000000 0000000000000011 00000000ffffffff 0000000000000000
    page dumped because: VM_BUG_ON_PAGE(page_ref_count(page) == 0)
    ------------[ cut here ]------------
    kernel BUG at include/linux/mm.h:707!
    invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI
    CPU: 2 PID: 291928 Comm: kworker/2:0 Tainted: G    B             5.10.7-arch1-1-kasan #1
    Hardware name: Gigabyte Technology Co., Ltd. H97N-WIFI/H97N-WIFI, BIOS F9b 03/03/2016
    Workqueue: zswap-shrink shrink_worker
    RIP: 0010:__free_pages+0x10a/0x130
    Code: c1 e7 06 48 01 ef 45 85 e4 74 d1 44 89 e6 31 d2 41 83 ec 01 e8 e7 b0 ff ff eb da 48 c7 c6 e0 32 91 88 48 89 ef e8 a6 89 f8 ff <0f> 0b 4c 89 e7 e8 fc 79 07 00 e9 33 ff ff ff 48 89 ef e8 ff 79 07
    RSP: 0000:ffff88819a2ffb98 EFLAGS: 00010296
    RAX: 0000000000000000 RBX: ffffea000594c5a8 RCX: 0000000000000000
    RDX: 1ffffd4000b298b7 RSI: 0000000000000000 RDI: ffffea000594c5b8
    RBP: ffffea000594c580 R08: 000000000000003e R09: ffff8881d5520bbb
    R10: ffffed103aaa4177 R11: 0000000000000001 R12: ffffea000594c5b4
    R13: 0000000000000000 R14: ffff888165316000 R15: ffffea000594c588
    FS:  0000000000000000(0000) GS:ffff8881d5500000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 00007f7c8c3654d8 CR3: 0000000103f42004 CR4: 00000000001706e0
    Call Trace:
     z3fold_zpool_shrink+0x9b6/0x1240
     shrink_worker+0x35/0x90
     process_one_work+0x70c/0x1210
     worker_thread+0x539/0x1200
     kthread+0x330/0x400
     ret_from_fork+0x22/0x30
    Modules linked in: rfcomm ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter ccm algif_aead des_generic libdes ecb algif_skcipher cmac bnep md4 algif_hash af_alg vfat fat intel_rapl_msr intel_rapl_common x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel iwlmvm hid_logitech_hidpp kvm at24 mac80211 snd_hda_codec_realtek iTCO_wdt snd_hda_codec_generic intel_pmc_bxt snd_hda_codec_hdmi ledtrig_audio iTCO_vendor_support mei_wdt mei_hdcp snd_hda_intel snd_intel_dspcfg libarc4 soundwire_intel irqbypass iwlwifi soundwire_generic_allocation rapl soundwire_cadence intel_cstate snd_hda_codec intel_uncore btusb joydev mousedev snd_usb_audio pcspkr btrtl uvcvideo nouveau btbcm i2c_i801 btintel snd_hda_core videobuf2_vmalloc i2c_smbus snd_usbmidi_lib videobuf2_memops bluetooth snd_hwdep soundwire_bus snd_soc_rt5640 videobuf2_v4l2 cfg80211 snd_soc_rl6231 videobuf2_common snd_rawmidi lpc_ich alx videodev mdio snd_seq_device snd_soc_core mc ecdh_generic mxm_wmi mei_me
     hid_logitech_dj wmi snd_compress e1000e ac97_bus mei ttm rfkill snd_pcm_dmaengine ecc snd_pcm snd_timer snd soundcore mac_hid acpi_pad pkcs8_key_parser it87 hwmon_vid crypto_user fuse ip_tables x_tables ext4 crc32c_generic crc16 mbcache jbd2 dm_crypt cbc encrypted_keys trusted tpm rng_core usbhid dm_mod crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel aesni_intel crypto_simd cryptd glue_helper xhci_pci xhci_pci_renesas i915 video intel_gtt i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops cec drm agpgart
    ---[ end trace 126d646fc3dc0ad8 ]---

To fix the issue, re-add the earlier test and set in the case where we
have a headless page.

Link: https://lkml.kernel.org/r/c8106dbe6d8390b290cd1d7f873a2942e805349e.1615452048.git.tommyhebb@gmail.com
Fixes: dcf5aedb24f8 ("z3fold: stricter locking and more careful reclaim")
Signed-off-by: Thomas Hebb <tommyhebb@gmail.com>
Reviewed-by: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Jongseok Kim <ks77sj@gmail.com>
Cc: Snild Dolkow <snild@sony.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/z3fold.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/mm/z3fold.c b/mm/z3fold.c
index b5dafa7e44e4..9d889ad2bb86 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -1346,8 +1346,22 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 			page = list_entry(pos, struct page, lru);
 
 			zhdr = page_address(page);
-			if (test_bit(PAGE_HEADLESS, &page->private))
+			if (test_bit(PAGE_HEADLESS, &page->private)) {
+				/*
+				 * For non-headless pages, we wait to do this
+				 * until we have the page lock to avoid racing
+				 * with __z3fold_alloc(). Headless pages don't
+				 * have a lock (and __z3fold_alloc() will never
+				 * see them), but we still need to test and set
+				 * PAGE_CLAIMED to avoid racing with
+				 * z3fold_free(), so just do it now before
+				 * leaving the loop.
+				 */
+				if (test_and_set_bit(PAGE_CLAIMED, &page->private))
+					continue;
+
 				break;
+			}
 
 			if (kref_get_unless_zero(&zhdr->refcount) == 0) {
 				zhdr = NULL;

From c1b2028315c6b15e8d6725e0d5884b15887d3daa Mon Sep 17 00:00:00 2001
From: Sean Nyekjaer <sean@geanix.com>
Date: Wed, 24 Mar 2021 21:37:32 -0700
Subject: [PATCH 1282/1820] squashfs: fix inode lookup sanity checks

When mouting a squashfs image created without inode compression it fails
with: "unable to read inode lookup table"

It turns out that the BLOCK_OFFSET is missing when checking the
SQUASHFS_METADATA_SIZE agaist the actual size.

Link: https://lkml.kernel.org/r/20210226092903.1473545-1-sean@geanix.com
Fixes: eabac19e40c0 ("squashfs: add more sanity checks in inode lookup")
Signed-off-by: Sean Nyekjaer <sean@geanix.com>
Acked-by: Phillip Lougher <phillip@squashfs.org.uk>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/squashfs/export.c      | 8 ++++++--
 fs/squashfs/squashfs_fs.h | 1 +
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c
index eb02072d28dd..723763746238 100644
--- a/fs/squashfs/export.c
+++ b/fs/squashfs/export.c
@@ -152,14 +152,18 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb,
 		start = le64_to_cpu(table[n]);
 		end = le64_to_cpu(table[n + 1]);
 
-		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+		if (start >= end
+		    || (end - start) >
+		    (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 			kfree(table);
 			return ERR_PTR(-EINVAL);
 		}
 	}
 
 	start = le64_to_cpu(table[indexes - 1]);
-	if (start >= lookup_table_start || (lookup_table_start - start) > SQUASHFS_METADATA_SIZE) {
+	if (start >= lookup_table_start ||
+	    (lookup_table_start - start) >
+	    (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index 8d64edb80ebf..b3fdc8212c5f 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -17,6 +17,7 @@
 
 /* size of metadata (inode and directory) blocks */
 #define SQUASHFS_METADATA_SIZE		8192
+#define SQUASHFS_BLOCK_OFFSET		2
 
 /* default size of block device I/O */
 #ifdef CONFIG_SQUASHFS_4K_DEVBLK_SIZE

From 8b44ca2b634527151af07447a8090a5f3a043321 Mon Sep 17 00:00:00 2001
From: Phillip Lougher <phillip@squashfs.org.uk>
Date: Wed, 24 Mar 2021 21:37:35 -0700
Subject: [PATCH 1283/1820] squashfs: fix xattr id and id lookup sanity checks

The checks for maximum metadata block size is missing
SQUASHFS_BLOCK_OFFSET (the two byte length count).

Link: https://lkml.kernel.org/r/2069685113.2081245.1614583677427@webmail.123-reg.co.uk
Fixes: f37aa4c7366e23f ("squashfs: add more sanity checks in id lookup")
Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk>
Cc: Sean Nyekjaer <sean@geanix.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/squashfs/id.c       | 6 ++++--
 fs/squashfs/xattr_id.c | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c
index 11581bf31af4..ea5387679723 100644
--- a/fs/squashfs/id.c
+++ b/fs/squashfs/id.c
@@ -97,14 +97,16 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb,
 		start = le64_to_cpu(table[n]);
 		end = le64_to_cpu(table[n + 1]);
 
-		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+		if (start >= end || (end - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 			kfree(table);
 			return ERR_PTR(-EINVAL);
 		}
 	}
 
 	start = le64_to_cpu(table[indexes - 1]);
-	if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) {
+	if (start >= id_table_start || (id_table_start - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}
diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c
index ead66670b41a..087cab8c78f4 100644
--- a/fs/squashfs/xattr_id.c
+++ b/fs/squashfs/xattr_id.c
@@ -109,14 +109,16 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start,
 		start = le64_to_cpu(table[n]);
 		end = le64_to_cpu(table[n + 1]);
 
-		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+		if (start >= end || (end - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 			kfree(table);
 			return ERR_PTR(-EINVAL);
 		}
 	}
 
 	start = le64_to_cpu(table[indexes - 1]);
-	if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) {
+	if (start >= table_start || (table_start - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}

From f2a419cf495f95cac49ea289318b833477e1a0e2 Mon Sep 17 00:00:00 2001
From: Sergei Trofimovich <slyfox@gentoo.org>
Date: Wed, 24 Mar 2021 21:37:38 -0700
Subject: [PATCH 1284/1820] ia64: mca: allocate early mca with GFP_ATOMIC

The sleep warning happens at early boot right at secondary CPU
activation bootup:

    smp: Bringing up secondary CPUs ...
    BUG: sleeping function called from invalid context at mm/page_alloc.c:4942
    in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 0, name: swapper/1
    CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.12.0-rc2-00007-g79e228d0b611-dirty #99
    ..
    Call Trace:
      show_stack+0x90/0xc0
      dump_stack+0x150/0x1c0
      ___might_sleep+0x1c0/0x2a0
      __might_sleep+0xa0/0x160
      __alloc_pages_nodemask+0x1a0/0x600
      alloc_page_interleave+0x30/0x1c0
      alloc_pages_current+0x2c0/0x340
      __get_free_pages+0x30/0xa0
      ia64_mca_cpu_init+0x2d0/0x3a0
      cpu_init+0x8b0/0x1440
      start_secondary+0x60/0x700
      start_ap+0x750/0x780
    Fixed BSP b0 value from CPU 1

As I understand interrupts are not enabled yet and system has a lot of
memory.  There is little chance to sleep and switch to GFP_ATOMIC should
be a no-op.

Link: https://lkml.kernel.org/r/20210315085045.204414-1-slyfox@gentoo.org
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/kernel/mca.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index d4cae2fc69ca..adf6521525f4 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1824,7 +1824,7 @@ ia64_mca_cpu_init(void *cpu_data)
 			data = mca_bootmem();
 			first_time = 0;
 		} else
-			data = (void *)__get_free_pages(GFP_KERNEL,
+			data = (void *)__get_free_pages(GFP_ATOMIC,
 							get_order(sz));
 		if (!data)
 			panic("Could not allocate MCA memory for cpu %d\n",

From 95d44a470a6814207d52dd6312203b0f4ef12710 Mon Sep 17 00:00:00 2001
From: Sergei Trofimovich <slyfox@gentoo.org>
Date: Wed, 24 Mar 2021 21:37:41 -0700
Subject: [PATCH 1285/1820] ia64: fix format strings for err_inject

Fix warning with %lx / u64 mismatch:

  arch/ia64/kernel/err_inject.c: In function 'show_resources':
  arch/ia64/kernel/err_inject.c:62:22: warning:
    format '%lx' expects argument of type 'long unsigned int',
    but argument 3 has type 'u64' {aka 'long long unsigned int'}
     62 |  return sprintf(buf, "%lx", name[cpu]);   \
        |                      ^~~~~~~

Link: https://lkml.kernel.org/r/20210313104312.1548232-1-slyfox@gentoo.org
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/kernel/err_inject.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c
index 8b5b8e6bc9d9..dd5bfed52031 100644
--- a/arch/ia64/kernel/err_inject.c
+++ b/arch/ia64/kernel/err_inject.c
@@ -59,7 +59,7 @@ show_##name(struct device *dev, struct device_attribute *attr,	\
 		char *buf)						\
 {									\
 	u32 cpu=dev->id;						\
-	return sprintf(buf, "%lx\n", name[cpu]);			\
+	return sprintf(buf, "%llx\n", name[cpu]);			\
 }
 
 #define store(name)							\
@@ -86,9 +86,9 @@ store_call_start(struct device *dev, struct device_attribute *attr,
 
 #ifdef ERR_INJ_DEBUG
 	printk(KERN_DEBUG "pal_mc_err_inject for cpu%d:\n", cpu);
-	printk(KERN_DEBUG "err_type_info=%lx,\n", err_type_info[cpu]);
-	printk(KERN_DEBUG "err_struct_info=%lx,\n", err_struct_info[cpu]);
-	printk(KERN_DEBUG "err_data_buffer=%lx, %lx, %lx.\n",
+	printk(KERN_DEBUG "err_type_info=%llx,\n", err_type_info[cpu]);
+	printk(KERN_DEBUG "err_struct_info=%llx,\n", err_struct_info[cpu]);
+	printk(KERN_DEBUG "err_data_buffer=%llx, %llx, %llx.\n",
 			  err_data_buffer[cpu].data1,
 			  err_data_buffer[cpu].data2,
 			  err_data_buffer[cpu].data3);
@@ -117,8 +117,8 @@ store_call_start(struct device *dev, struct device_attribute *attr,
 
 #ifdef ERR_INJ_DEBUG
 	printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]);
-	printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]);
-	printk(KERN_DEBUG "resources=%lx\n", resources[cpu]);
+	printk(KERN_DEBUG "capabilities=%llx,\n", capabilities[cpu]);
+	printk(KERN_DEBUG "resources=%llx\n", resources[cpu]);
 #endif
 	return size;
 }
@@ -131,7 +131,7 @@ show_virtual_to_phys(struct device *dev, struct device_attribute *attr,
 			char *buf)
 {
 	unsigned int cpu=dev->id;
-	return sprintf(buf, "%lx\n", phys_addr[cpu]);
+	return sprintf(buf, "%llx\n", phys_addr[cpu]);
 }
 
 static ssize_t
@@ -145,7 +145,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr,
 	ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL);
 	if (ret<=0) {
 #ifdef ERR_INJ_DEBUG
-		printk("Virtual address %lx is not existing.\n",virt_addr);
+		printk("Virtual address %llx is not existing.\n", virt_addr);
 #endif
 		return -EINVAL;
 	}
@@ -163,7 +163,7 @@ show_err_data_buffer(struct device *dev,
 {
 	unsigned int cpu=dev->id;
 
-	return sprintf(buf, "%lx, %lx, %lx\n",
+	return sprintf(buf, "%llx, %llx, %llx\n",
 			err_data_buffer[cpu].data1,
 			err_data_buffer[cpu].data2,
 			err_data_buffer[cpu].data3);
@@ -178,13 +178,13 @@ store_err_data_buffer(struct device *dev,
 	int ret;
 
 #ifdef ERR_INJ_DEBUG
-	printk("write err_data_buffer=[%lx,%lx,%lx] on cpu%d\n",
+	printk("write err_data_buffer=[%llx,%llx,%llx] on cpu%d\n",
 		 err_data_buffer[cpu].data1,
 		 err_data_buffer[cpu].data2,
 		 err_data_buffer[cpu].data3,
 		 cpu);
 #endif
-	ret=sscanf(buf, "%lx, %lx, %lx",
+	ret = sscanf(buf, "%llx, %llx, %llx",
 			&err_data_buffer[cpu].data1,
 			&err_data_buffer[cpu].data2,
 			&err_data_buffer[cpu].data3);

From 60bcf728ee7c60ac2a1f9a0eaceb3a7b3954cd2b Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Wed, 24 Mar 2021 21:37:44 -0700
Subject: [PATCH 1286/1820] gcov: fix clang-11+ support

LLVM changed the expected function signatures for llvm_gcda_start_file()
and llvm_gcda_emit_function() in the clang-11 release.  Users of
clang-11 or newer may have noticed their kernels failing to boot due to
a panic when enabling CONFIG_GCOV_KERNEL=y +CONFIG_GCOV_PROFILE_ALL=y.
Fix up the function signatures so calling these functions doesn't panic
the kernel.

Link: https://reviews.llvm.org/rGcdd683b516d147925212724b09ec6fb792a40041
Link: https://reviews.llvm.org/rG13a633b438b6500ecad9e4f936ebadf3411d0f44
Link: https://lkml.kernel.org/r/20210312224132.3413602-2-ndesaulniers@google.com
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Reported-by: Prasad Sodagudi <psodagud@quicinc.com>
Suggested-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Fangrui Song <maskray@google.com>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Cc: <stable@vger.kernel.org>	[5.4+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/gcov/clang.c | 69 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c
index c94b820a1b62..8743150db2ac 100644
--- a/kernel/gcov/clang.c
+++ b/kernel/gcov/clang.c
@@ -75,7 +75,9 @@ struct gcov_fn_info {
 
 	u32 num_counters;
 	u64 *counters;
+#if CONFIG_CLANG_VERSION < 110000
 	const char *function_name;
+#endif
 };
 
 static struct gcov_info *current_info;
@@ -105,6 +107,7 @@ void llvm_gcov_init(llvm_gcov_callback writeout, llvm_gcov_callback flush)
 }
 EXPORT_SYMBOL(llvm_gcov_init);
 
+#if CONFIG_CLANG_VERSION < 110000
 void llvm_gcda_start_file(const char *orig_filename, const char version[4],
 		u32 checksum)
 {
@@ -113,7 +116,17 @@ void llvm_gcda_start_file(const char *orig_filename, const char version[4],
 	current_info->checksum = checksum;
 }
 EXPORT_SYMBOL(llvm_gcda_start_file);
+#else
+void llvm_gcda_start_file(const char *orig_filename, u32 version, u32 checksum)
+{
+	current_info->filename = orig_filename;
+	current_info->version = version;
+	current_info->checksum = checksum;
+}
+EXPORT_SYMBOL(llvm_gcda_start_file);
+#endif
 
+#if CONFIG_CLANG_VERSION < 110000
 void llvm_gcda_emit_function(u32 ident, const char *function_name,
 		u32 func_checksum, u8 use_extra_checksum, u32 cfg_checksum)
 {
@@ -133,6 +146,24 @@ void llvm_gcda_emit_function(u32 ident, const char *function_name,
 	list_add_tail(&info->head, &current_info->functions);
 }
 EXPORT_SYMBOL(llvm_gcda_emit_function);
+#else
+void llvm_gcda_emit_function(u32 ident, u32 func_checksum,
+		u8 use_extra_checksum, u32 cfg_checksum)
+{
+	struct gcov_fn_info *info = kzalloc(sizeof(*info), GFP_KERNEL);
+
+	if (!info)
+		return;
+
+	INIT_LIST_HEAD(&info->head);
+	info->ident = ident;
+	info->checksum = func_checksum;
+	info->use_extra_checksum = use_extra_checksum;
+	info->cfg_checksum = cfg_checksum;
+	list_add_tail(&info->head, &current_info->functions);
+}
+EXPORT_SYMBOL(llvm_gcda_emit_function);
+#endif
 
 void llvm_gcda_emit_arcs(u32 num_counters, u64 *counters)
 {
@@ -295,6 +326,7 @@ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src)
 	}
 }
 
+#if CONFIG_CLANG_VERSION < 110000
 static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn)
 {
 	size_t cv_size; /* counter values size */
@@ -322,6 +354,28 @@ err_name:
 	kfree(fn_dup);
 	return NULL;
 }
+#else
+static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn)
+{
+	size_t cv_size; /* counter values size */
+	struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn),
+			GFP_KERNEL);
+	if (!fn_dup)
+		return NULL;
+	INIT_LIST_HEAD(&fn_dup->head);
+
+	cv_size = fn->num_counters * sizeof(fn->counters[0]);
+	fn_dup->counters = vmalloc(cv_size);
+	if (!fn_dup->counters) {
+		kfree(fn_dup);
+		return NULL;
+	}
+
+	memcpy(fn_dup->counters, fn->counters, cv_size);
+
+	return fn_dup;
+}
+#endif
 
 /**
  * gcov_info_dup - duplicate profiling data set
@@ -362,6 +416,7 @@ err:
  * gcov_info_free - release memory for profiling data set duplicate
  * @info: profiling data set duplicate to free
  */
+#if CONFIG_CLANG_VERSION < 110000
 void gcov_info_free(struct gcov_info *info)
 {
 	struct gcov_fn_info *fn, *tmp;
@@ -375,6 +430,20 @@ void gcov_info_free(struct gcov_info *info)
 	kfree(info->filename);
 	kfree(info);
 }
+#else
+void gcov_info_free(struct gcov_info *info)
+{
+	struct gcov_fn_info *fn, *tmp;
+
+	list_for_each_entry_safe(fn, tmp, &info->functions, head) {
+		vfree(fn->counters);
+		list_del(&fn->head);
+		kfree(fn);
+	}
+	kfree(info->filename);
+	kfree(info);
+}
+#endif
 
 #define ITER_STRIDE	PAGE_SIZE
 

From 9551158069ba8fcc893798d42dc4f978b62ef60f Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Wed, 24 Mar 2021 21:37:47 -0700
Subject: [PATCH 1287/1820] kfence: make compatible with kmemleak

Because memblock allocations are registered with kmemleak, the KFENCE
pool was seen by kmemleak as one large object.  Later allocations
through kfence_alloc() that were registered with kmemleak via
slab_post_alloc_hook() would then overlap and trigger a warning.
Therefore, once the pool is initialized, we can remove (free) it from
kmemleak again, since it should be treated as allocator-internal and be
seen as "free memory".

The second problem is that kmemleak is passed the rounded size, and not
the originally requested size, which is also the size of KFENCE objects.
To avoid kmemleak scanning past the end of an object and trigger a
KFENCE out-of-bounds error, fix the size if it is a KFENCE object.

For simplicity, to avoid a call to kfence_ksize() in
slab_post_alloc_hook() (and avoid new IS_ENABLED(CONFIG_DEBUG_KMEMLEAK)
guard), just call kfence_ksize() in mm/kmemleak.c:create_object().

Link: https://lkml.kernel.org/r/20210317084740.3099921-1-elver@google.com
Signed-off-by: Marco Elver <elver@google.com>
Reported-by: Luis Henriques <lhenriques@suse.de>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Luis Henriques <lhenriques@suse.de>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/kfence/core.c | 9 +++++++++
 mm/kmemleak.c    | 3 ++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 3b8ec938470a..d53c91f881a4 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -12,6 +12,7 @@
 #include <linux/debugfs.h>
 #include <linux/kcsan-checks.h>
 #include <linux/kfence.h>
+#include <linux/kmemleak.h>
 #include <linux/list.h>
 #include <linux/lockdep.h>
 #include <linux/memblock.h>
@@ -480,6 +481,14 @@ static bool __init kfence_init_pool(void)
 		addr += 2 * PAGE_SIZE;
 	}
 
+	/*
+	 * The pool is live and will never be deallocated from this point on.
+	 * Remove the pool object from the kmemleak object tree, as it would
+	 * otherwise overlap with allocations returned by kfence_alloc(), which
+	 * are registered with kmemleak through the slab post-alloc hook.
+	 */
+	kmemleak_free(__kfence_pool);
+
 	return true;
 
 err:
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index c0014d3b91c1..fe6e3ae8e8c6 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -97,6 +97,7 @@
 #include <linux/atomic.h>
 
 #include <linux/kasan.h>
+#include <linux/kfence.h>
 #include <linux/kmemleak.h>
 #include <linux/memory_hotplug.h>
 
@@ -589,7 +590,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
 	atomic_set(&object->use_count, 1);
 	object->flags = OBJECT_ALLOCATED;
 	object->pointer = ptr;
-	object->size = size;
+	object->size = kfence_ksize((void *)ptr) ?: size;
 	object->excess_ref = 0;
 	object->min_count = min_count;
 	object->count = 0;			/* white color initially */

From a024b7c2850dddd01e65b8270f0971deaf272f27 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Wed, 24 Mar 2021 21:37:50 -0700
Subject: [PATCH 1288/1820] mm: memblock: fix section mismatch warning again

Commit 34dc2efb39a2 ("memblock: fix section mismatch warning") marked
memblock_bottom_up() and memblock_set_bottom_up() as __init, but they
could be referenced from non-init functions like
memblock_find_in_range_node() on architectures that enable
CONFIG_ARCH_KEEP_MEMBLOCK.

For such builds kernel test robot reports:

   WARNING: modpost: vmlinux.o(.text+0x74fea4): Section mismatch in reference from the function memblock_find_in_range_node() to the function .init.text:memblock_bottom_up()
   The function memblock_find_in_range_node() references the function __init memblock_bottom_up().
   This is often because memblock_find_in_range_node lacks a __init  annotation or the annotation of memblock_bottom_up is wrong.

Replace __init annotations with __init_memblock annotations so that the
appropriate section will be selected depending on
CONFIG_ARCH_KEEP_MEMBLOCK.

Link: https://lore.kernel.org/lkml/202103160133.UzhgY0wt-lkp@intel.com
Link: https://lkml.kernel.org/r/20210316171347.14084-1-rppt@kernel.org
Fixes: 34dc2efb39a2 ("memblock: fix section mismatch warning")
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memblock.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index d13e3cd938b4..5984fff3f175 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -460,7 +460,7 @@ static inline void memblock_free_late(phys_addr_t base, phys_addr_t size)
 /*
  * Set the allocation direction to bottom-up or top-down.
  */
-static inline __init void memblock_set_bottom_up(bool enable)
+static inline __init_memblock void memblock_set_bottom_up(bool enable)
 {
 	memblock.bottom_up = enable;
 }
@@ -470,7 +470,7 @@ static inline __init void memblock_set_bottom_up(bool enable)
  * if this is true, that said, memblock will allocate memory
  * in bottom-up direction.
  */
-static inline __init bool memblock_bottom_up(void)
+static inline __init_memblock bool memblock_bottom_up(void)
 {
 	return memblock.bottom_up;
 }

From 487cfade12fae0eb707bdce71c4d585128238a7d Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 24 Mar 2021 21:37:53 -0700
Subject: [PATCH 1289/1820] mm/highmem: fix CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP

The kernel test robot found that __kmap_local_sched_out() was not
correctly skipping the guard pages when DEBUG_KMAP_LOCAL_FORCE_MAP was
set.[1] This was due to DEBUG_HIGHMEM check being used.

Change the configuration check to be correct.

[1] https://lore.kernel.org/lkml/20210304083825.GB17830@xsang-OptiPlex-9020/

Link: https://lkml.kernel.org/r/20210318230657.1497881-1-ira.weiny@intel.com
Fixes: 0e91a0c6984c ("mm/highmem: Provide CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP")
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Oliver Sang <oliver.sang@intel.com>
Cc: Chaitanya Kulkarni <Chaitanya.Kulkarni@wdc.com>
Cc: David Sterba <dsterba@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/highmem.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/highmem.c b/mm/highmem.c
index 86f2b9495f9c..6ef8f5e05e7e 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -618,7 +618,7 @@ void __kmap_local_sched_out(void)
 		int idx;
 
 		/* With debug all even slots are unmapped and act as guard */
-		if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+		if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
 			WARN_ON_ONCE(!pte_none(pteval));
 			continue;
 		}
@@ -654,7 +654,7 @@ void __kmap_local_sched_in(void)
 		int idx;
 
 		/* With debug all even slots are unmapped and act as guard */
-		if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+		if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
 			WARN_ON_ONCE(!pte_none(pteval));
 			continue;
 		}

From d3e2ff28ca27352d43a41053263d620202324c1f Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Wed, 24 Mar 2021 21:37:56 -0700
Subject: [PATCH 1290/1820] mailmap: update Andrey Konovalov's email address

Use my personal email, the @google.com one will stop functioning soon.

Link: https://lkml.kernel.org/r/ead0e9c32a2f70e0bde6f63b3b9470e0ef13d2ee.1616107969.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index 85b93cdefc87..11219fa3b62b 100644
--- a/.mailmap
+++ b/.mailmap
@@ -36,6 +36,7 @@ Andrew Morton <akpm@linux-foundation.org>
 Andrew Murray <amurray@thegoodpenguin.co.uk> <amurray@embedded-bits.co.uk>
 Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com>
 Andrew Vasquez <andrew.vasquez@qlogic.com>
+Andrey Konovalov <andreyknvl@gmail.com> <andreyknvl@google.com>
 Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
 Andrey Ryabinin <ryabinin.a.a@gmail.com> <aryabinin@virtuozzo.com>
 Andy Adamson <andros@citi.umich.edu>

From 22f8b5df881e9f1302514bbbbbb8649c2051de55 Mon Sep 17 00:00:00 2001
From: Norbert Ciosek <norbertx.ciosek@intel.com>
Date: Thu, 28 Jan 2021 10:17:02 -0800
Subject: [PATCH 1291/1820] virtchnl: Fix layout of RSS structures

Remove padding from RSS structures. Previous layout
could lead to unwanted compiler optimizations
in loops when iterating over key and lut arrays.

Fixes: 65ece6de0114 ("virtchnl: Add missing explicit padding to structures")
Signed-off-by: Norbert Ciosek <norbertx.ciosek@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 include/linux/avf/virtchnl.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 40bad71865ea..532bcbfc4716 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -476,7 +476,6 @@ struct virtchnl_rss_key {
 	u16 vsi_id;
 	u16 key_len;
 	u8 key[1];         /* RSS hash key, packed bytes */
-	u8 pad[1];
 };
 
 VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key);
@@ -485,7 +484,6 @@ struct virtchnl_rss_lut {
 	u16 vsi_id;
 	u16 lut_entries;
 	u8 lut[1];        /* RSS lookup table */
-	u8 pad[1];
 };
 
 VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut);

From 90449e98c265296329446c7abcd2aae3b20c0bc9 Mon Sep 17 00:00:00 2001
From: Mateusz Palczewski <mateusz.palczewski@intel.com>
Date: Mon, 4 Jan 2021 15:00:02 +0000
Subject: [PATCH 1292/1820] i40e: Added Asym_Pause to supported link modes

Add Asym_Pause to supported link modes (it is supported by HW).
Lack of Asym_Pause in supported modes can cause several problems,
i.e. it won't be possible to turn the autonegotiation on
with asymmetric pause settings (i.e. Tx on, Rx off).

Fixes: 4e91bcd5d47a ("i40e: Finish implementation of ethtool get settings")
Signed-off-by: Dawid Lukwinski <dawid.lukwinski@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Przemyslaw Patynowski <przemyslawx.patynowski@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index c70dec65a572..2c637a5678b3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1101,6 +1101,7 @@ static int i40e_get_link_ksettings(struct net_device *netdev,
 
 	/* Set flow control settings */
 	ethtool_link_ksettings_add_link_mode(ks, supported, Pause);
+	ethtool_link_ksettings_add_link_mode(ks, supported, Asym_Pause);
 
 	switch (hw->fc.requested_mode) {
 	case I40E_FC_FULL:

From ff132c5f93c06bd4432bbab5c369e468653bdec4 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Thu, 25 Mar 2021 08:51:13 -0400
Subject: [PATCH 1293/1820] gfs2: report "already frozen/thawed" errors

Before this patch, gfs2's freeze function failed to report an error
when the target file system was already frozen as it should (and as
generic vfs function freeze_super does. Similarly, gfs2's thaw function
failed to report an error when trying to thaw a file system that is not
frozen, as vfs function thaw_super does. The errors were checked, but
it always returned a 0 return code.

This patch adds the missing error return codes to gfs2 freeze and thaw.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/super.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 9e91c9d92bd6..8fb9602d79b4 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -752,11 +752,13 @@ void gfs2_freeze_func(struct work_struct *work)
 static int gfs2_freeze(struct super_block *sb)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
-	int error = 0;
+	int error;
 
 	mutex_lock(&sdp->sd_freeze_mutex);
-	if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN)
+	if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN) {
+		error = -EBUSY;
 		goto out;
+	}
 
 	for (;;) {
 		if (gfs2_withdrawn(sdp)) {
@@ -797,10 +799,10 @@ static int gfs2_unfreeze(struct super_block *sb)
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 
 	mutex_lock(&sdp->sd_freeze_mutex);
-        if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN ||
+	if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN ||
 	    !gfs2_holder_initialized(&sdp->sd_freeze_gh)) {
 		mutex_unlock(&sdp->sd_freeze_mutex);
-                return 0;
+		return -EINVAL;
 	}
 
 	gfs2_freeze_unlock(&sdp->sd_freeze_gh);

From 7aae5432ac61ffae3e5afadbd2713bb73177f11d Mon Sep 17 00:00:00 2001
From: Chris Chiu <chris.chiu@canonical.com>
Date: Thu, 25 Mar 2021 22:04:19 +0800
Subject: [PATCH 1294/1820] mailmap: update the email address for Chris Chiu

Redirect my older email addresses in the git logs.

Signed-off-by: Chris Chiu <chris.chiu@canonical.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .mailmap | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/.mailmap b/.mailmap
index 85b93cdefc87..1f8579db5a3f 100644
--- a/.mailmap
+++ b/.mailmap
@@ -65,6 +65,8 @@ Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
 Changbin Du <changbin.du@intel.com> <changbin.du@intel.com>
 Chao Yu <chao@kernel.org> <chao2.yu@samsung.com>
 Chao Yu <chao@kernel.org> <yuchao0@huawei.com>
+Chris Chiu <chris.chiu@canonical.com> <chiu@endlessm.com>
+Chris Chiu <chris.chiu@canonical.com> <chiu@endlessos.org>
 Christophe Ricard <christophe.ricard@gmail.com>
 Christoph Hellwig <hch@lst.de>
 Corey Minyard <minyard@acm.org>

From 60c988bc154108bd522a21289e389143006a1ff0 Mon Sep 17 00:00:00 2001
From: Daniel Jordan <daniel.m.jordan@oracle.com>
Date: Wed, 24 Mar 2021 21:05:52 -0400
Subject: [PATCH 1295/1820] vfio/type1: Empty batch for pfnmap pages

When vfio_pin_pages_remote() returns with a partial batch consisting of
a single VM_PFNMAP pfn, a subsequent call will unfortunately try
restoring it from batch->pages, resulting in vfio mapping the wrong page
and unbalancing the page refcount.

Prevent the function from returning with this kind of partial batch to
avoid the issue.  There's no explicit check for a VM_PFNMAP pfn because
it's awkward to do so, so infer it from characteristics of the batch
instead.  This may result in occasional false positives but keeps the
code simpler.

Fixes: 4d83de6da265 ("vfio/type1: Batch page pinning")
Link: https://lkml.kernel.org/r/20210323133254.33ed9161@omen.home.shazbot.org/
Reported-by: Alex Williamson <alex.williamson@redhat.com>
Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Message-Id: <20210325010552.185481-1-daniel.m.jordan@oracle.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio_iommu_type1.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index be444407664a..45cbfd4879a5 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -739,6 +739,12 @@ out:
 	ret = vfio_lock_acct(dma, lock_acct, false);
 
 unpin_out:
+	if (batch->size == 1 && !batch->offset) {
+		/* May be a VM_PFNMAP pfn, which the batch can't remember. */
+		put_pfn(pfn, dma->prot);
+		batch->size = 0;
+	}
+
 	if (ret < 0) {
 		if (pinned && !rsvd) {
 			for (pfn = *pfn_base ; pinned ; pfn++, pinned--)

From 90b8749022bbdd0c94a13182a78f4903b98fd0d7 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 25 Mar 2021 19:05:14 +0000
Subject: [PATCH 1296/1820] io_uring: maintain CQE order of a failed link

Arguably we want CQEs of linked requests be in a strict order of
submission as it always was. Now if init of a request fails its CQE may
be posted before all prior linked requests including the head of the
link. Fix it by failing it last.

Fixes: de59bc104c24f ("io_uring: fail links more in io_submit_sqe()")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/b7a96b05832e7ab23ad55f84092a2548c4a888b0.1616699075.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 8c5789b96dbb..54ea561db4a5 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6480,8 +6480,6 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	ret = io_init_req(ctx, req, sqe);
 	if (unlikely(ret)) {
 fail_req:
-		io_put_req(req);
-		io_req_complete(req, ret);
 		if (link->head) {
 			/* fail even hard links since we don't submit */
 			link->head->flags |= REQ_F_FAIL_LINK;
@@ -6489,6 +6487,8 @@ fail_req:
 			io_req_complete(link->head, -ECANCELED);
 			link->head = NULL;
 		}
+		io_put_req(req);
+		io_req_complete(req, ret);
 		return ret;
 	}
 	ret = io_req_prep(req, sqe);

From 347b5650cd158d1d953487cc2bec567af5c5bf96 Mon Sep 17 00:00:00 2001
From: Eryk Rybak <eryk.roch.rybak@intel.com>
Date: Thu, 18 Feb 2021 11:15:26 +0000
Subject: [PATCH 1297/1820] i40e: Fix kernel oops when i40e driver removes VF's

Fix the reason of kernel oops when i40e driver removed VFs.
Added new __I40E_VFS_RELEASING state to signalize releasing
process by PF, that it makes possible to exit of reset VF procedure.
Without this patch, it is possible to suspend the VFs reset by
releasing VFs resources procedure. Retrying the reset after the
timeout works on the freed VF memory causing a kernel oops.

Fixes: d43d60e5eb95 ("i40e: ensure reset occurs when disabling VF")
Signed-off-by: Eryk Rybak <eryk.roch.rybak@intel.com>
Signed-off-by: Grzegorz Szczurek <grzegorzx.szczurek@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h             | 1 +
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 9 +++++++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index cd53981fa5e0..15f93b355099 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -142,6 +142,7 @@ enum i40e_state_t {
 	__I40E_VIRTCHNL_OP_PENDING,
 	__I40E_RECOVERY_MODE,
 	__I40E_VF_RESETS_DISABLED,	/* disable resets during i40e_remove */
+	__I40E_VFS_RELEASING,
 	/* This must be last as it determines the size of the BITMAP */
 	__I40E_STATE_SIZE__,
 };
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 1b6ec9be155a..5d301a466f5c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -137,6 +137,7 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf)
  **/
 static inline void i40e_vc_disable_vf(struct i40e_vf *vf)
 {
+	struct i40e_pf *pf = vf->pf;
 	int i;
 
 	i40e_vc_notify_vf_reset(vf);
@@ -147,6 +148,11 @@ static inline void i40e_vc_disable_vf(struct i40e_vf *vf)
 	 * ensure a reset.
 	 */
 	for (i = 0; i < 20; i++) {
+		/* If PF is in VFs releasing state reset VF is impossible,
+		 * so leave it.
+		 */
+		if (test_bit(__I40E_VFS_RELEASING, pf->state))
+			return;
 		if (i40e_reset_vf(vf, false))
 			return;
 		usleep_range(10000, 20000);
@@ -1574,6 +1580,8 @@ void i40e_free_vfs(struct i40e_pf *pf)
 
 	if (!pf->vf)
 		return;
+
+	set_bit(__I40E_VFS_RELEASING, pf->state);
 	while (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
 		usleep_range(1000, 2000);
 
@@ -1631,6 +1639,7 @@ void i40e_free_vfs(struct i40e_pf *pf)
 		}
 	}
 	clear_bit(__I40E_VF_DISABLE, pf->state);
+	clear_bit(__I40E_VFS_RELEASING, pf->state);
 }
 
 #ifdef CONFIG_PCI_IOV

From f2916ae9a1bc80aa8e9e8a00b75682f5df6fd59c Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Thu, 18 Feb 2021 21:55:35 +0000
Subject: [PATCH 1298/1820] i40e: Fix oops at i40e_rebuild()

Setup TC before the i40e_setup_pf_switch() call.
Memory must be initialized for all the queues
before using its resources.

Previously it could be possible that a call:
xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
rx_ring->queue_index, rx_ring->q_vector->napi.napi_id);
was made with q_vector being null.

Oops could show up with the following sequence:
- no driver loaded
- FW LLDP agent is on (flag disable-fw-lldp:off)
- link is up
- DCB configured with number of Traffic Classes that will not divide
  completely the default number of queues (usually cpu cores)
- driver load
- set private flag: disable-fw-lldp:on

Fixes: 4b208eaa8078 ("i40e: Add init and default config of software based DCB")
Fixes: b02e5a0ebb17 ("xsk: Propagate napi_id to XDP socket Rx path")
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 17f3b800640e..f67f0cc9dadf 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -10573,12 +10573,6 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 		goto end_core_reset;
 	}
 
-	if (!lock_acquired)
-		rtnl_lock();
-	ret = i40e_setup_pf_switch(pf, reinit);
-	if (ret)
-		goto end_unlock;
-
 #ifdef CONFIG_I40E_DCB
 	/* Enable FW to write a default DCB config on link-up
 	 * unless I40E_FLAG_TC_MQPRIO was enabled or DCB
@@ -10607,6 +10601,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	}
 
 #endif /* CONFIG_I40E_DCB */
+	if (!lock_acquired)
+		rtnl_lock();
+	ret = i40e_setup_pf_switch(pf, reinit);
+	if (ret)
+		goto end_unlock;
 
 	/* The driver only wants link up/down and module qualification
 	 * reports from firmware.  Note the negative logic.

From 72bbc226ed2ef0a46c165a482861fff00dd6d4e1 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Tue, 23 Mar 2021 21:40:11 +0100
Subject: [PATCH 1299/1820] s390/vdso: copy tod_steering_delta value to
 vdso_data page

When converting the vdso assembler code to C it was forgotten to
actually copy the tod_steering_delta value to vdso_data page.

Which in turn means that tod clock steering will not work correctly.

Fix this by simply copying the value whenever it is updated.

Fixes: 4bff8cb54502 ("s390: convert to GENERIC_VDSO")
Cc: <stable@vger.kernel.org> # 5.10
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/time.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 165da961f901..e37285a5101b 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -382,6 +382,7 @@ static void clock_sync_global(unsigned long delta)
 		      tod_steering_delta);
 	tod_steering_end = now + (abs(tod_steering_delta) << 15);
 	vdso_data->arch_data.tod_steering_end = tod_steering_end;
+	vdso_data->arch_data.tod_steering_delta = tod_steering_delta;
 
 	/* Update LPAR offset. */
 	if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)

From b24bacd67ffddd9192c4745500fd6f73dbfe565e Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 24 Mar 2021 20:22:42 +0100
Subject: [PATCH 1300/1820] s390/vdso: fix tod_steering_delta type

The s390 specific vdso function __arch_get_hw_counter() is supposed to
consider tod clock steering.

If a tod clock steering event happens and the tod clock is set to a
new value __arch_get_hw_counter() will not return the real tod clock
value but slowly drift it from the old delta until the returned value
finally matches the real tod clock value again.

Unfortunately the type of tod_steering_delta unsigned while it is
supposed to be signed. It depends on if tod_steering_delta is negative
or positive in which direction the vdso code drifts the clock value.

Worst case is now that instead of drifting the clock slowly it will
jump into the opposite direction by a factor of two.

Fix this by simply making tod_steering_delta signed.

Fixes: 4bff8cb54502 ("s390: convert to GENERIC_VDSO")
Cc: <stable@vger.kernel.org> # 5.10
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/vdso/data.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/vdso/data.h b/arch/s390/include/asm/vdso/data.h
index 7b3cdb4a5f48..73ee89142666 100644
--- a/arch/s390/include/asm/vdso/data.h
+++ b/arch/s390/include/asm/vdso/data.h
@@ -6,7 +6,7 @@
 #include <vdso/datapage.h>
 
 struct arch_vdso_data {
-	__u64 tod_steering_delta;
+	__s64 tod_steering_delta;
 	__u64 tod_steering_end;
 };
 

From 5b43bd184530af6b868d8273b0a743a138d37ee8 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 24 Mar 2021 20:23:55 +0100
Subject: [PATCH 1301/1820] s390/vdso: fix initializing and updating of
 vdso_data

Li Wang reported that clock_gettime(CLOCK_MONOTONIC_RAW, ...) returns
incorrect values when time is provided via vdso instead of system call:

vdso_ts_nsec = 4484351380985507, vdso_ts.tv_sec = 4484351, vdso_ts.tv_nsec = 380985507
sys_ts_nsec  = 1446923235377, sys_ts.tv_sec  = 1446, sys_ts.tv_nsec  = 923235377

Within the s390 specific vdso function __arch_get_hw_counter() reads
tod clock steering values from the arch_data member of the passed in
vdso_data structure.

Problem is that only for the CS_HRES_COARSE vdso_data arch_data is
initialized and gets updated. The CS_RAW specific vdso_data does not
contain any valid tod_clock_steering information, which explains the
different values.

Fix this by initializing and updating all vdso_datas.

Reported-by: Li Wang <liwang@redhat.com>
Tested-by: Li Wang <liwang@redhat.com>
Fixes: 1ba2d6c0fd4e ("s390/vdso: simplify __arch_get_hw_counter()")
Link: https://lore.kernel.org/linux-s390/YFnxr1ZlMIOIqjfq@osiris
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/time.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index e37285a5101b..326cb8f75f58 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -80,10 +80,12 @@ void __init time_early_init(void)
 {
 	struct ptff_qto qto;
 	struct ptff_qui qui;
+	int cs;
 
 	/* Initialize TOD steering parameters */
 	tod_steering_end = tod_clock_base.tod;
-	vdso_data->arch_data.tod_steering_end = tod_steering_end;
+	for (cs = 0; cs < CS_BASES; cs++)
+		vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
 
 	if (!test_facility(28))
 		return;
@@ -366,6 +368,7 @@ static void clock_sync_global(unsigned long delta)
 {
 	unsigned long now, adj;
 	struct ptff_qto qto;
+	int cs;
 
 	/* Fixup the monotonic sched clock. */
 	tod_clock_base.eitod += delta;
@@ -381,8 +384,10 @@ static void clock_sync_global(unsigned long delta)
 		panic("TOD clock sync offset %li is too large to drift\n",
 		      tod_steering_delta);
 	tod_steering_end = now + (abs(tod_steering_delta) << 15);
-	vdso_data->arch_data.tod_steering_end = tod_steering_end;
-	vdso_data->arch_data.tod_steering_delta = tod_steering_delta;
+	for (cs = 0; cs < CS_BASES; cs++) {
+		vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
+		vdso_data[cs].arch_data.tod_steering_delta = tod_steering_delta;
+	}
 
 	/* Update LPAR offset. */
 	if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)

From 7f6c411c9b50cfab41cc798e003eff27608c7016 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 25 Mar 2021 14:12:34 -0400
Subject: [PATCH 1302/1820] hostfs: fix memory handling in follow_link()

1) argument should not be freed in any case - the caller already has
it as ->s_fs_info (and uses it a lot afterwards)
2) allocate readlink buffer with kmalloc() - the caller has no way
to tell if it's got that (on absolute symlink) or a result of
kasprintf().  Sure, for SLAB and SLUB kfree() works on results of
kmem_cache_alloc(), but that's not documented anywhere, might change
in the future *and* is already not true for SLOB.

Fixes: 52b209f7b848 ("get rid of hostfs_read_inode()")
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/hostfs/hostfs_kern.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 29e407762626..743a005a5c64 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -144,7 +144,7 @@ static char *follow_link(char *link)
 	char *name, *resolved, *end;
 	int n;
 
-	name = __getname();
+	name = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (!name) {
 		n = -ENOMEM;
 		goto out_free;
@@ -173,12 +173,11 @@ static char *follow_link(char *link)
 		goto out_free;
 	}
 
-	__putname(name);
-	kfree(link);
+	kfree(name);
 	return resolved;
 
  out_free:
-	__putname(name);
+	kfree(name);
 	return ERR_PTR(n);
 }
 

From 479dc497db8322ae486f8ee49020f5600a77a680 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 24 Mar 2021 11:56:39 +0200
Subject: [PATCH 1303/1820] net: dsa: only unset VLAN filtering when last port
 leaves last VLAN-aware bridge

DSA is aware of switches with global VLAN filtering since the blamed
commit, but it makes a bad decision when multiple bridges are spanning
the same switch:

ip link add br0 type bridge vlan_filtering 1
ip link add br1 type bridge vlan_filtering 1
ip link set swp2 master br0
ip link set swp3 master br0
ip link set swp4 master br1
ip link set swp5 master br1
ip link set swp5 nomaster
ip link set swp4 nomaster
[138665.939930] sja1105 spi0.1: port 3: dsa_core: VLAN filtering is a global setting
[138665.947514] DSA: failed to notify DSA_NOTIFIER_BRIDGE_LEAVE

When all ports leave br1, DSA blindly attempts to disable VLAN filtering
on the switch, ignoring the fact that br0 still exists and is VLAN-aware
too. It fails while doing that.

This patch checks whether any port exists at all and is under a
VLAN-aware bridge.

Fixes: d371b7c92d19 ("net: dsa: Unset vlan_filtering when ports leave the bridge")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/switch.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 4b5da89dc27a..32963276452f 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -107,7 +107,7 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds,
 	bool unset_vlan_filtering = br_vlan_enabled(info->br);
 	struct dsa_switch_tree *dst = ds->dst;
 	struct netlink_ext_ack extack = {0};
-	int err, i;
+	int err, port;
 
 	if (dst->index == info->tree_index && ds->index == info->sw_index &&
 	    ds->ops->port_bridge_join)
@@ -124,13 +124,16 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds,
 	 * it. That is a good thing, because that lets us handle it and also
 	 * handle the case where the switch's vlan_filtering setting is global
 	 * (not per port). When that happens, the correct moment to trigger the
-	 * vlan_filtering callback is only when the last port left this bridge.
+	 * vlan_filtering callback is only when the last port leaves the last
+	 * VLAN-aware bridge.
 	 */
 	if (unset_vlan_filtering && ds->vlan_filtering_is_global) {
-		for (i = 0; i < ds->num_ports; i++) {
-			if (i == info->port)
-				continue;
-			if (dsa_to_port(ds, i)->bridge_dev == info->br) {
+		for (port = 0; port < ds->num_ports; port++) {
+			struct net_device *bridge_dev;
+
+			bridge_dev = dsa_to_port(ds, port)->bridge_dev;
+
+			if (bridge_dev && br_vlan_enabled(bridge_dev)) {
 				unset_vlan_filtering = false;
 				break;
 			}

From de9c7854e6e1589f639c6352112956d08243b659 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 24 Mar 2021 14:05:36 +0100
Subject: [PATCH 1304/1820] net: axienet: allow setups without MDIO

In setups with fixed-link settings there is no mdio node in DTS.
axienet_probe() already handles that gracefully but lp->mii_bus is
then NULL.

Fix code that tries to blindly grab the MDIO lock by introducing two helper
functions that make the locking conditional.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Reviewed-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/xilinx_axienet.h      | 12 ++++++++++++
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 12 ++++++------
 2 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index 1e966a39967e..aca7f82f6791 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -504,6 +504,18 @@ static inline u32 axinet_ior_read_mcr(struct axienet_local *lp)
 	return axienet_ior(lp, XAE_MDIO_MCR_OFFSET);
 }
 
+static inline void axienet_lock_mii(struct axienet_local *lp)
+{
+	if (lp->mii_bus)
+		mutex_lock(&lp->mii_bus->mdio_lock);
+}
+
+static inline void axienet_unlock_mii(struct axienet_local *lp)
+{
+	if (lp->mii_bus)
+		mutex_unlock(&lp->mii_bus->mdio_lock);
+}
+
 /**
  * axienet_iow - Memory mapped Axi Ethernet register write
  * @lp:         Pointer to axienet local structure
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 5d677db0aee5..f8f8654ea728 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1053,9 +1053,9 @@ static int axienet_open(struct net_device *ndev)
 	 * including the MDIO. MDIO must be disabled before resetting.
 	 * Hold MDIO bus lock to avoid MDIO accesses during the reset.
 	 */
-	mutex_lock(&lp->mii_bus->mdio_lock);
+	axienet_lock_mii(lp);
 	ret = axienet_device_reset(ndev);
-	mutex_unlock(&lp->mii_bus->mdio_lock);
+	axienet_unlock_mii(lp);
 
 	ret = phylink_of_phy_connect(lp->phylink, lp->dev->of_node, 0);
 	if (ret) {
@@ -1148,9 +1148,9 @@ static int axienet_stop(struct net_device *ndev)
 	}
 
 	/* Do a reset to ensure DMA is really stopped */
-	mutex_lock(&lp->mii_bus->mdio_lock);
+	axienet_lock_mii(lp);
 	__axienet_device_reset(lp);
-	mutex_unlock(&lp->mii_bus->mdio_lock);
+	axienet_unlock_mii(lp);
 
 	cancel_work_sync(&lp->dma_err_task);
 
@@ -1709,9 +1709,9 @@ static void axienet_dma_err_handler(struct work_struct *work)
 	 * including the MDIO. MDIO must be disabled before resetting.
 	 * Hold MDIO bus lock to avoid MDIO accesses during the reset.
 	 */
-	mutex_lock(&lp->mii_bus->mdio_lock);
+	axienet_lock_mii(lp);
 	__axienet_device_reset(lp);
-	mutex_unlock(&lp->mii_bus->mdio_lock);
+	axienet_unlock_mii(lp);
 
 	for (i = 0; i < lp->tx_bd_num; i++) {
 		cur_p = &lp->tx_bd_v[i];

From 3ed14d8d47bff8cd70c357da9b72b1f698bf553b Mon Sep 17 00:00:00 2001
From: Dinh Nguyen <dinguyen@kernel.org>
Date: Wed, 24 Mar 2021 08:52:19 -0500
Subject: [PATCH 1305/1820] dt-bindings: net: micrel-ksz90x1.txt: correct
 documentation

Correct the Micrel phy documentation for the ksz9021 and ksz9031 phys
for how the phy skews are set.

Signed-off-by: Dinh Nguyen <dinguyen@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../bindings/net/micrel-ksz90x1.txt           | 96 ++++++++++++++++++-
 1 file changed, 94 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
index b921731cd970..df9e844dd6bc 100644
--- a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
+++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
@@ -65,6 +65,71 @@ KSZ9031:
   step is 60ps. The default value is the neutral setting, so setting
   rxc-skew-ps=<0> actually results in -900 picoseconds adjustment.
 
+  The KSZ9031 hardware supports a range of skew values from negative to
+  positive, where the specific range is property dependent. All values
+  specified in the devicetree are offset by the minimum value so they
+  can be represented as positive integers in the devicetree since it's
+  difficult to represent a negative number in the devictree.
+
+  The following 5-bit values table apply to rxc-skew-ps and txc-skew-ps.
+
+  Pad Skew Value	Delay (ps)	Devicetree Value
+  ------------------------------------------------------
+  0_0000		-900ps		0
+  0_0001		-840ps		60
+  0_0010		-780ps		120
+  0_0011		-720ps		180
+  0_0100		-660ps		240
+  0_0101		-600ps		300
+  0_0110		-540ps		360
+  0_0111		-480ps		420
+  0_1000		-420ps		480
+  0_1001		-360ps		540
+  0_1010		-300ps		600
+  0_1011		-240ps		660
+  0_1100		-180ps		720
+  0_1101		-120ps		780
+  0_1110		-60ps		840
+  0_1111		0ps		900
+  1_0000		60ps		960
+  1_0001		120ps		1020
+  1_0010		180ps		1080
+  1_0011		240ps		1140
+  1_0100		300ps		1200
+  1_0101		360ps		1260
+  1_0110		420ps		1320
+  1_0111		480ps		1380
+  1_1000		540ps		1440
+  1_1001		600ps		1500
+  1_1010		660ps		1560
+  1_1011		720ps		1620
+  1_1100		780ps		1680
+  1_1101		840ps		1740
+  1_1110		900ps		1800
+  1_1111		960ps		1860
+
+  The following 4-bit values table apply to the txdX-skew-ps, rxdX-skew-ps
+  data pads, and the rxdv-skew-ps, txen-skew-ps control pads.
+
+  Pad Skew Value	Delay (ps)	Devicetree Value
+  ------------------------------------------------------
+  0000			-420ps		0
+  0001			-360ps		60
+  0010			-300ps		120
+  0011			-240ps		180
+  0100			-180ps		240
+  0101			-120ps		300
+  0110			-60ps		360
+  0111			0ps		420
+  1000			60ps		480
+  1001			120ps		540
+  1010			180ps		600
+  1011			240ps		660
+  1100			300ps		720
+  1101			360ps		780
+  1110			420ps		840
+  1111			480ps		900
+
   Optional properties:
 
     Maximum value of 1860, default value 900:
@@ -120,11 +185,21 @@ KSZ9131:
 
 Examples:
 
+	/* Attach to an Ethernet device with autodetected PHY */
+	&enet {
+		rxc-skew-ps = <1800>;
+		rxdv-skew-ps = <0>;
+		txc-skew-ps = <1800>;
+		txen-skew-ps = <0>;
+		status = "okay";
+	};
+
+	/* Attach to an explicitly-specified PHY */
 	mdio {
 		phy0: ethernet-phy@0 {
-			rxc-skew-ps = <3000>;
+			rxc-skew-ps = <1800>;
 			rxdv-skew-ps = <0>;
-			txc-skew-ps = <3000>;
+			txc-skew-ps = <1800>;
 			txen-skew-ps = <0>;
 			reg = <0>;
 		};
@@ -133,3 +208,20 @@ Examples:
 		phy = <&phy0>;
 		phy-mode = "rgmii-id";
 	};
+
+References
+
+  Micrel ksz9021rl/rn Data Sheet, Revision 1.2. Dated 2/13/2014.
+  http://www.micrel.com/_PDF/Ethernet/datasheets/ksz9021rl-rn_ds.pdf
+
+  Micrel ksz9031rnx Data Sheet, Revision 2.1. Dated 11/20/2014.
+  http://www.micrel.com/_PDF/Ethernet/datasheets/KSZ9031RNX.pdf
+
+Notes:
+
+  Note that a previous version of the Micrel ksz9021rl/rn Data Sheet
+  was missing extended register 106 (transmit data pad skews), and
+  incorrectly specified the ps per step as 200ps/step instead of
+  120ps/step. The latest update to this document reflects the latest
+  revision of the Micrel specification even though usage in the kernel
+  still reflects that incorrect document.

From 3e6fdeb28f4c331acbd27bdb0effc4befd4ef8e8 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Wed, 24 Mar 2021 20:36:04 +0100
Subject: [PATCH 1306/1820] net: dsa: lantiq_gswip: Let GSWIP automatically set
 the xMII clock

The xMII interface clock depends on the PHY interface (MII, RMII, RGMII)
as well as the current link speed. Explicitly configure the GSWIP to
automatically select the appropriate xMII interface clock.

This fixes an issue seen by some users where ports using an external
RMII or RGMII PHY were deaf (no RX or TX traffic could be seen). Most
likely this is due to an "invalid" xMII clock being selected either by
the bootloader or hardware-defaults.

Fixes: 14fceff4771e51 ("net: dsa: Add Lantiq / Intel DSA driver for vrx200")
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/lantiq_gswip.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
index 52e865a3912c..809dfa3be6bb 100644
--- a/drivers/net/dsa/lantiq_gswip.c
+++ b/drivers/net/dsa/lantiq_gswip.c
@@ -799,10 +799,15 @@ static int gswip_setup(struct dsa_switch *ds)
 	/* Configure the MDIO Clock 2.5 MHz */
 	gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1);
 
-	/* Disable the xMII link */
-	for (i = 0; i < priv->hw_info->max_ports; i++)
+	for (i = 0; i < priv->hw_info->max_ports; i++) {
+		/* Disable the xMII link */
 		gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, i);
 
+		/* Automatically select the xMII interface clock */
+		gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_RATE_MASK,
+				   GSWIP_MII_CFG_RATE_AUTO, i);
+	}
+
 	/* enable special tag insertion on cpu port */
 	gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN,
 			  GSWIP_FDMA_PCTRLp(cpu_port));

From d75135082698140a26a56defe1bbc1b06f26a41f Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Thu, 25 Mar 2021 08:39:12 +0530
Subject: [PATCH 1307/1820] amd-xgbe: Update DMA coherency values

Based on the IOMMU configuration, the current cache control settings can
result in possible coherency issues. The hardware team has recommended
new settings for the PCI device path to eliminate the issue.

Fixes: 6f595959c095 ("amd-xgbe: Adjust register settings to improve performance")
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index ba8321ec1ee7..3305979a9f7c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -180,9 +180,9 @@
 #define XGBE_DMA_SYS_AWCR	0x30303030
 
 /* DMA cache settings - PCI device */
-#define XGBE_DMA_PCI_ARCR	0x00000003
-#define XGBE_DMA_PCI_AWCR	0x13131313
-#define XGBE_DMA_PCI_AWARCR	0x00000313
+#define XGBE_DMA_PCI_ARCR	0x000f0f0f
+#define XGBE_DMA_PCI_AWCR	0x0f0f0f0f
+#define XGBE_DMA_PCI_AWARCR	0x00000f0f
 
 /* DMA channel interrupt modes */
 #define XGBE_IRQ_MODE_EDGE	0

From c33b1cc62ac05c1dbb1cdafe2eb66da01c76ca8d Mon Sep 17 00:00:00 2001
From: Xiaoming Ni <nixiaoming@huawei.com>
Date: Thu, 25 Mar 2021 11:51:10 +0800
Subject: [PATCH 1308/1820] nfc: fix refcount leak in llcp_sock_bind()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

nfc_llcp_local_get() is invoked in llcp_sock_bind(),
but nfc_llcp_local_put() is not invoked in subsequent failure branches.
As a result, refcount leakage occurs.
To fix it, add calling nfc_llcp_local_put().

fix CVE-2020-25670
Fixes: c7aa12252f51 ("NFC: Take a reference on the LLCP local pointer when creating a socket")
Reported-by: "kiyin(尹亮)" <kiyin@tencent.com>
Link: https://www.openwall.com/lists/oss-security/2020/11/01/1
Cc: <stable@vger.kernel.org> #v3.6
Signed-off-by: Xiaoming Ni <nixiaoming@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/llcp_sock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index d257ed3b732a..68832ee4b9f8 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -108,11 +108,13 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 					  llcp_sock->service_name_len,
 					  GFP_KERNEL);
 	if (!llcp_sock->service_name) {
+		nfc_llcp_local_put(llcp_sock->local);
 		ret = -ENOMEM;
 		goto put_dev;
 	}
 	llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock);
 	if (llcp_sock->ssap == LLCP_SAP_MAX) {
+		nfc_llcp_local_put(llcp_sock->local);
 		kfree(llcp_sock->service_name);
 		llcp_sock->service_name = NULL;
 		ret = -EADDRINUSE;

From 8a4cd82d62b5ec7e5482333a72b58a4eea4979f0 Mon Sep 17 00:00:00 2001
From: Xiaoming Ni <nixiaoming@huawei.com>
Date: Thu, 25 Mar 2021 11:51:11 +0800
Subject: [PATCH 1309/1820] nfc: fix refcount leak in llcp_sock_connect()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

nfc_llcp_local_get() is invoked in llcp_sock_connect(),
but nfc_llcp_local_put() is not invoked in subsequent failure branches.
As a result, refcount leakage occurs.
To fix it, add calling nfc_llcp_local_put().

fix CVE-2020-25671
Fixes: c7aa12252f51 ("NFC: Take a reference on the LLCP local pointer when creating a socket")
Reported-by: "kiyin(尹亮)" <kiyin@tencent.com>
Link: https://www.openwall.com/lists/oss-security/2020/11/01/1
Cc: <stable@vger.kernel.org> #v3.6
Signed-off-by: Xiaoming Ni <nixiaoming@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/llcp_sock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 68832ee4b9f8..9e2799ee1595 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -704,6 +704,7 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr,
 	llcp_sock->local = nfc_llcp_local_get(local);
 	llcp_sock->ssap = nfc_llcp_get_local_ssap(local);
 	if (llcp_sock->ssap == LLCP_SAP_MAX) {
+		nfc_llcp_local_put(llcp_sock->local);
 		ret = -ENOMEM;
 		goto put_dev;
 	}
@@ -748,6 +749,7 @@ sock_unlink:
 
 sock_llcp_release:
 	nfc_llcp_put_ssap(local, llcp_sock->ssap);
+	nfc_llcp_local_put(llcp_sock->local);
 
 put_dev:
 	nfc_put_device(dev);

From 7574fcdbdcb335763b6b322f6928dc0fd5730451 Mon Sep 17 00:00:00 2001
From: Xiaoming Ni <nixiaoming@huawei.com>
Date: Thu, 25 Mar 2021 11:51:12 +0800
Subject: [PATCH 1310/1820] nfc: fix memory leak in llcp_sock_connect()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In llcp_sock_connect(), use kmemdup to allocate memory for
 "llcp_sock->service_name". The memory is not released in the sock_unlink
label of the subsequent failure branch.
As a result, memory leakage occurs.

fix CVE-2020-25672

Fixes: d646960f7986 ("NFC: Initial LLCP support")
Reported-by: "kiyin(尹亮)" <kiyin@tencent.com>
Link: https://www.openwall.com/lists/oss-security/2020/11/01/1
Cc: <stable@vger.kernel.org> #v3.3
Signed-off-by: Xiaoming Ni <nixiaoming@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/llcp_sock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 9e2799ee1595..59172614b249 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -746,6 +746,8 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr,
 
 sock_unlink:
 	nfc_llcp_sock_unlink(&local->connecting_sockets, sk);
+	kfree(llcp_sock->service_name);
+	llcp_sock->service_name = NULL;
 
 sock_llcp_release:
 	nfc_llcp_put_ssap(local, llcp_sock->ssap);

From 4b5db93e7f2afbdfe3b78e37879a85290187e6f1 Mon Sep 17 00:00:00 2001
From: Xiaoming Ni <nixiaoming@huawei.com>
Date: Thu, 25 Mar 2021 11:51:13 +0800
Subject: [PATCH 1311/1820] nfc: Avoid endless loops caused by repeated
 llcp_sock_connect()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When sock_wait_state() returns -EINPROGRESS, "sk->sk_state" is
 LLCP_CONNECTING. In this case, llcp_sock_connect() is repeatedly invoked,
 nfc_llcp_sock_link() will add sk to local->connecting_sockets twice.
 sk->sk_node->next will point to itself, that will make an endless loop
 and hang-up the system.
To fix it, check whether sk->sk_state is LLCP_CONNECTING in
 llcp_sock_connect() to avoid repeated invoking.

Fixes: b4011239a08e ("NFC: llcp: Fix non blocking sockets connections")
Reported-by: "kiyin(尹亮)" <kiyin@tencent.com>
Link: https://www.openwall.com/lists/oss-security/2020/11/01/1
Cc: <stable@vger.kernel.org> #v3.11
Signed-off-by: Xiaoming Ni <nixiaoming@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/llcp_sock.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 59172614b249..a3b46f888803 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -673,6 +673,10 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr,
 		ret = -EISCONN;
 		goto error;
 	}
+	if (sk->sk_state == LLCP_CONNECTING) {
+		ret = -EINPROGRESS;
+		goto error;
+	}
 
 	dev = nfc_get_device(addr->dev_idx);
 	if (dev == NULL) {

From 30a93d2b7d5a7cbb53ac19c9364a256d1aa6c08a Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Thu, 25 Mar 2021 16:35:32 +0100
Subject: [PATCH 1312/1820] vxlan: do not modify the shared tunnel info when
 PMTU triggers an ICMP reply

When the interface is part of a bridge or an Open vSwitch port and a
packet exceed a PMTU estimate, an ICMP reply is sent to the sender. When
using the external mode (collect metadata) the source and destination
addresses are reversed, so that Open vSwitch can match the packet
against an existing (reverse) flow.

But inverting the source and destination addresses in the shared
ip_tunnel_info will make following packets of the flow to use a wrong
destination address (packets will be tunnelled to itself), if the flow
isn't updated. Which happens with Open vSwitch, until the flow times
out.

Fixes this by uncloning the skb's ip_tunnel_info before inverting its
source and destination addresses, so that the modification will only be
made for the PTMU packet, not the following ones.

Fixes: fc68c99577cc ("vxlan: Support for PMTU discovery on directly bridged links")
Tested-by: Eelco Chaudron <echaudro@redhat.com>
Reviewed-by: Eelco Chaudron <echaudro@redhat.com>
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 666dd201c3d5..53dbc67e8a34 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2725,12 +2725,17 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 		} else if (err) {
 			if (info) {
+				struct ip_tunnel_info *unclone;
 				struct in_addr src, dst;
 
+				unclone = skb_tunnel_info_unclone(skb);
+				if (unlikely(!unclone))
+					goto tx_error;
+
 				src = remote_ip.sin.sin_addr;
 				dst = local_ip.sin.sin_addr;
-				info->key.u.ipv4.src = src.s_addr;
-				info->key.u.ipv4.dst = dst.s_addr;
+				unclone->key.u.ipv4.src = src.s_addr;
+				unclone->key.u.ipv4.dst = dst.s_addr;
 			}
 			vxlan_encap_bypass(skb, vxlan, vxlan, vni, false);
 			dst_release(ndst);
@@ -2781,12 +2786,17 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 		} else if (err) {
 			if (info) {
+				struct ip_tunnel_info *unclone;
 				struct in6_addr src, dst;
 
+				unclone = skb_tunnel_info_unclone(skb);
+				if (unlikely(!unclone))
+					goto tx_error;
+
 				src = remote_ip.sin6.sin6_addr;
 				dst = local_ip.sin6.sin6_addr;
-				info->key.u.ipv6.src = src;
-				info->key.u.ipv6.dst = dst;
+				unclone->key.u.ipv6.src = src;
+				unclone->key.u.ipv6.dst = dst;
 			}
 
 			vxlan_encap_bypass(skb, vxlan, vxlan, vni, false);

From 68c1a943ef37bafde5ea2383e8ca224c7169ee31 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Thu, 25 Mar 2021 16:35:33 +0100
Subject: [PATCH 1313/1820] geneve: do not modify the shared tunnel info when
 PMTU triggers an ICMP reply

When the interface is part of a bridge or an Open vSwitch port and a
packet exceed a PMTU estimate, an ICMP reply is sent to the sender. When
using the external mode (collect metadata) the source and destination
addresses are reversed, so that Open vSwitch can match the packet
against an existing (reverse) flow.

But inverting the source and destination addresses in the shared
ip_tunnel_info will make following packets of the flow to use a wrong
destination address (packets will be tunnelled to itself), if the flow
isn't updated. Which happens with Open vSwitch, until the flow times
out.

Fixes this by uncloning the skb's ip_tunnel_info before inverting its
source and destination addresses, so that the modification will only be
made for the PTMU packet, not the following ones.

Fixes: c1a800e88dbf ("geneve: Support for PMTU discovery on directly bridged links")
Tested-by: Eelco Chaudron <echaudro@redhat.com>
Reviewed-by: Eelco Chaudron <echaudro@redhat.com>
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 4ac0373326ef..d5b1e48e0c09 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -908,8 +908,16 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 
 		info = skb_tunnel_info(skb);
 		if (info) {
-			info->key.u.ipv4.dst = fl4.saddr;
-			info->key.u.ipv4.src = fl4.daddr;
+			struct ip_tunnel_info *unclone;
+
+			unclone = skb_tunnel_info_unclone(skb);
+			if (unlikely(!unclone)) {
+				dst_release(&rt->dst);
+				return -ENOMEM;
+			}
+
+			unclone->key.u.ipv4.dst = fl4.saddr;
+			unclone->key.u.ipv4.src = fl4.daddr;
 		}
 
 		if (!pskb_may_pull(skb, ETH_HLEN)) {
@@ -993,8 +1001,16 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		struct ip_tunnel_info *info = skb_tunnel_info(skb);
 
 		if (info) {
-			info->key.u.ipv6.dst = fl6.saddr;
-			info->key.u.ipv6.src = fl6.daddr;
+			struct ip_tunnel_info *unclone;
+
+			unclone = skb_tunnel_info_unclone(skb);
+			if (unlikely(!unclone)) {
+				dst_release(dst);
+				return -ENOMEM;
+			}
+
+			unclone->key.u.ipv6.dst = fl6.saddr;
+			unclone->key.u.ipv6.src = fl6.daddr;
 		}
 
 		if (!pskb_may_pull(skb, ETH_HLEN)) {

From 3a87571f0ffc51ba3bf3ecdb6032861d0154b164 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 25 Mar 2021 11:14:53 -0700
Subject: [PATCH 1314/1820] sch_red: fix off-by-one checks in
 red_check_params()

This fixes following syzbot report:

UBSAN: shift-out-of-bounds in ./include/net/red.h:237:23
shift exponent 32 is too large for 32-bit type 'unsigned int'
CPU: 1 PID: 8418 Comm: syz-executor170 Not tainted 5.12.0-rc4-next-20210324-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:79 [inline]
 dump_stack+0x141/0x1d7 lib/dump_stack.c:120
 ubsan_epilogue+0xb/0x5a lib/ubsan.c:148
 __ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:327
 red_set_parms include/net/red.h:237 [inline]
 choke_change.cold+0x3c/0xc8 net/sched/sch_choke.c:414
 qdisc_create+0x475/0x12f0 net/sched/sch_api.c:1247
 tc_modify_qdisc+0x4c8/0x1a50 net/sched/sch_api.c:1663
 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5553
 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2502
 netlink_unicast_kernel net/netlink/af_netlink.c:1312 [inline]
 netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1338
 netlink_sendmsg+0x856/0xd90 net/netlink/af_netlink.c:1927
 sock_sendmsg_nosec net/socket.c:654 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:674
 ____sys_sendmsg+0x6e8/0x810 net/socket.c:2350
 ___sys_sendmsg+0xf3/0x170 net/socket.c:2404
 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2433
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xae
RIP: 0033:0x43f039
Code: 28 c3 e8 2a 14 00 00 66 2e 0f 1f 84 00 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffdfa725168 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000400488 RCX: 000000000043f039
RDX: 0000000000000000 RSI: 0000000020000040 RDI: 0000000000000004
RBP: 0000000000403020 R08: 0000000000400488 R09: 0000000000400488
R10: 0000000000400488 R11: 0000000000000246 R12: 00000000004030b0
R13: 0000000000000000 R14: 00000000004ac018 R15: 0000000000400488

Fixes: 8afa10cbe281 ("net_sched: red: Avoid illegal values")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/red.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/red.h b/include/net/red.h
index 0b39eff1d50a..be11dbd26492 100644
--- a/include/net/red.h
+++ b/include/net/red.h
@@ -171,9 +171,9 @@ static inline void red_set_vars(struct red_vars *v)
 static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog,
 				    u8 Scell_log, u8 *stab)
 {
-	if (fls(qth_min) + Wlog > 32)
+	if (fls(qth_min) + Wlog >= 32)
 		return false;
-	if (fls(qth_max) + Wlog > 32)
+	if (fls(qth_max) + Wlog >= 32)
 		return false;
 	if (Scell_log >= 32)
 		return false;

From 6032ebb54c60cae24329f6aba3ce0c1ca8ad6abe Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@gmail.com>
Date: Thu, 25 Mar 2021 12:01:15 -0300
Subject: [PATCH 1315/1820] libbpf: Fix bail out from 'ringbuf_process_ring()'
 on error

The current code bails out with negative and positive returns.
If the callback returns a positive return code, 'ring_buffer__consume()'
and 'ring_buffer__poll()' will return a spurious number of records
consumed, but mostly important will continue the processing loop.

This patch makes positive returns from the callback a no-op.

Fixes: bf99c936f947 ("libbpf: Add BPF ring buffer support")
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210325150115.138750-1-pctammela@mojatatu.com
---
 tools/lib/bpf/ringbuf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 8caaafe7e312..e7a8d847161f 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -227,7 +227,7 @@ static int ringbuf_process_ring(struct ring* r)
 			if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) {
 				sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ;
 				err = r->sample_cb(r->ctx, sample, len);
-				if (err) {
+				if (err < 0) {
 					/* update consumer pos and bail out */
 					smp_store_release(r->consumer_pos,
 							  cons_pos);

From 52762efa2b256ed1c5274e5177cbd52ee11a2f6a Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Mon, 22 Mar 2021 18:46:56 -0700
Subject: [PATCH 1316/1820] gpu/xen: Fix a use after free in xen_drm_drv_init

In function displback_changed, has the call chain
displback_connect(front_info)->xen_drm_drv_init(front_info).
We can see that drm_info is assigned to front_info->drm_info
and drm_info is freed in fail branch in xen_drm_drv_init().

Later displback_disconnect(front_info) is called and it calls
xen_drm_drv_fini(front_info) cause a use after free by
drm_info = front_info->drm_info statement.

My patch has done two things. First fixes the fail label which
drm_info = kzalloc() failed and still free the drm_info.
Second sets front_info->drm_info to NULL to avoid uaf.

Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Reviewed-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210323014656.10068-1-lyl2019@mail.ustc.edu.cn
---
 drivers/gpu/drm/xen/xen_drm_front.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
index 30d9adf31c84..9f14d99c763c 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.c
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -521,7 +521,7 @@ static int xen_drm_drv_init(struct xen_drm_front_info *front_info)
 	drm_dev = drm_dev_alloc(&xen_drm_driver, dev);
 	if (IS_ERR(drm_dev)) {
 		ret = PTR_ERR(drm_dev);
-		goto fail;
+		goto fail_dev;
 	}
 
 	drm_info->drm_dev = drm_dev;
@@ -551,8 +551,10 @@ fail_modeset:
 	drm_kms_helper_poll_fini(drm_dev);
 	drm_mode_config_cleanup(drm_dev);
 	drm_dev_put(drm_dev);
-fail:
+fail_dev:
 	kfree(drm_info);
+	front_info->drm_info = NULL;
+fail:
 	return ret;
 }
 

From 014305d001987a0eeada6bac610a8665f92aae24 Mon Sep 17 00:00:00 2001
From: Wan Jiabing <wanjiabing@vivo.com>
Date: Thu, 25 Mar 2021 14:19:01 +0800
Subject: [PATCH 1317/1820] drivers: gpu: drm: xen_drm_front_drm_info is
 declared twice

struct xen_drm_front_drm_info has been declared.
Remove the duplicate.

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
Reviewed-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210325061901.851273-1-wanjiabing@vivo.com
---
 drivers/gpu/drm/xen/xen_drm_front_conn.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/xen/xen_drm_front_conn.h b/drivers/gpu/drm/xen/xen_drm_front_conn.h
index 3adacba9a23b..e5f4314899ee 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_conn.h
+++ b/drivers/gpu/drm/xen/xen_drm_front_conn.h
@@ -16,7 +16,6 @@
 struct drm_connector;
 struct xen_drm_front_drm_info;
 
-struct xen_drm_front_drm_info;
 
 int xen_drm_front_conn_init(struct xen_drm_front_drm_info *drm_info,
 			    struct drm_connector *connector);

From 53f1d31708f6240e4615b0927df31f182e389e2f Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Date: Fri, 26 Mar 2021 12:37:55 +0530
Subject: [PATCH 1318/1820] powerpc/mm/book3s64: Use the correct storage key
 value when calling H_PROTECT

H_PROTECT expects the flag value to include flags:
  AVPN, pp0, pp1, pp2, key0-key4, Noexec, CMO Option flags

This patch updates hpte_updatepp() to fetch the storage key value from
the linux page table and use the same in H_PROTECT hcall.

native_hpte_updatepp() is not updated because the kernel doesn't clear
the existing storage key value there. The kernel also doesn't use
hpte_updatepp() callback for updating storage keys.

This fixes the below kernel crash observed with KUAP enabled.

  BUG: Unable to handle kernel data access on write at 0xc009fffffc440000
  Faulting instruction address: 0xc0000000000b7030
  Key fault AMR: 0xfcffffffffffffff IAMR: 0xc0000077bc498100
  Found HPTE: v = 0x40070adbb6fffc05 r = 0x1ffffffffff1194
  Oops: Kernel access of bad area, sig: 11 [#1]
  LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
  ...
  CFAR: c000000000010100 DAR: c009fffffc440000 DSISR: 02200000 IRQMASK: 0
  ...
  NIP memset+0x68/0x104
  LR  pcpu_alloc+0x54c/0xb50
  Call Trace:
    pcpu_alloc+0x55c/0xb50 (unreliable)
    blk_stat_alloc_callback+0x94/0x150
    blk_mq_init_allocated_queue+0x64/0x560
    blk_mq_init_queue+0x54/0xb0
    scsi_mq_alloc_queue+0x30/0xa0
    scsi_alloc_sdev+0x1cc/0x300
    scsi_probe_and_add_lun+0xb50/0x1020
    __scsi_scan_target+0x17c/0x790
    scsi_scan_channel+0x90/0xe0
    scsi_scan_host_selected+0x148/0x1f0
    do_scan_async+0x2c/0x2a0
    async_run_entry_fn+0x78/0x220
    process_one_work+0x264/0x540
    worker_thread+0xa8/0x600
    kthread+0x190/0x1a0
    ret_from_kernel_thread+0x5c/0x6c

With KUAP enabled the kernel uses storage key 3 for all its
translations. But as shown by the debug print, in this specific case we
have the hash page table entry created with key value 0.

  Found HPTE: v = 0x40070adbb6fffc05 r = 0x1ffffffffff1194

and DSISR indicates a key fault.

This can happen due to parallel fault on the same EA by different CPUs:

  CPU 0					CPU 1
  fault on X

  H_PAGE_BUSY set
  					fault on X

  finish fault handling and
  clear H_PAGE_BUSY
  					check for H_PAGE_BUSY
  					continue with fault handling.

This implies CPU1 will end up calling hpte_updatepp for address X and
the kernel updated the hash pte entry with key 0

Fixes: d94b827e89dc ("powerpc/book3s64/kuap: Use Key 3 for kernel mapping with hash translation")
Reported-by: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Debugged-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210326070755.304625-1-aneesh.kumar@linux.ibm.com
---
 arch/powerpc/platforms/pseries/lpar.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 764170fdb0f7..3805519a6469 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -887,7 +887,8 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot,
 
 	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
-	flags = (newpp & 7) | H_AVPN;
+	flags = (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO)) | H_AVPN;
+	flags |= (newpp & HPTE_R_KEY_HI) >> 48;
 	if (mmu_has_feature(MMU_FTR_KERNEL_RO))
 		/* Move pp0 into bit 8 (IBM 55) */
 		flags |= (newpp & HPTE_R_PP0) >> 55;

From 1dc481c0b0cf18d3952d93a73c4ece90dec277f0 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Sat, 20 Mar 2021 18:45:54 +0800
Subject: [PATCH 1319/1820] perf test: Change to use bash for daemon test

When executing the daemon test on Arm64 and x86 with Debian (Buster)
distro, both skip the test case with the log:

  # ./perf test -v 76
  76: daemon operations                                               :
  --- start ---
  test child forked, pid 11687
  test daemon list
  trap: SIGINT: bad trap
  ./tests/shell/daemon.sh: 173: local: cpu-clock: bad variable name
  test child finished with -2
  ---- end ----
  daemon operations: Skip

So the error happens for the variable expansion when use local variable
in the shell script.  Since Debian Buster uses dash but not bash as
non-interactive shell, when execute the daemon testing, it hits a known
issue for dash which was reported [1].

To resolve this issue, one option is to add double quotes for all local
variables assignment, so need to change the code from:

  local line=`perf daemon --config ${config} -x: | head -2 | tail -1`

  ... to:

  local line="`perf daemon --config ${config} -x: | head -2 | tail -1`"

But the testing script has bunch of local variables, this leads to big
changes for whole script.

On the other hand, the testing script asks to use the "local" feature
which is bash-specific, so this patch explicitly uses "#!/bin/bash" to
ensure running the script with bash.

After:

  # ./perf test -v 76
  76: daemon operations                                               :
  --- start ---
  test child forked, pid 11329
  test daemon list
  test daemon reconfig
  test daemon stop
  test daemon signal
  signal 12 sent to session 'test [11596]'
  signal 12 sent to session 'test [11596]'
  test daemon ping
  test daemon lock
  test child finished with 0
  ---- end ----
  daemon operations: Ok

[1] https://bugs.launchpad.net/ubuntu/+source/dash/+bug/139097

Fixes: 2291bb915b55 ("perf tests: Add daemon 'list' command test")
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210320104554.529213-1-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/daemon.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh
index 5ad3ca8d681b..58984380b211 100755
--- a/tools/perf/tests/shell/daemon.sh
+++ b/tools/perf/tests/shell/daemon.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # daemon operations
 # SPDX-License-Identifier: GPL-2.0
 

From 45a4546c6167a2da348a31ca439d8a8ff773b6ea Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Thu, 25 Mar 2021 12:34:54 +0000
Subject: [PATCH 1320/1820] cifs: Adjust key sizes and key generation routines
 for AES256 encryption

For AES256 encryption (GCM and CCM), we need to adjust the size of a few
fields to 32 bytes instead of 16 to accommodate the larger keys.

Also, the L value supplied to the key generator needs to be changed from
to 256 when these algorithms are used.

Keeping the ioctl struct for dumping keys of the same size for now.
Will send out a different patch for that one.

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
CC: <stable@vger.kernel.org> # v5.10+
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cifsglob.h      |  4 ++--
 fs/cifs/cifspdu.h       |  5 +++++
 fs/cifs/smb2glob.h      |  1 +
 fs/cifs/smb2ops.c       |  9 +++++----
 fs/cifs/smb2transport.c | 37 ++++++++++++++++++++++++++++---------
 5 files changed, 41 insertions(+), 15 deletions(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 31fc8695abd6..67c056a9a519 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -919,8 +919,8 @@ struct cifs_ses {
 	bool binding:1; /* are we binding the session? */
 	__u16 session_flags;
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
-	__u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
-	__u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
+	__u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE];
+	__u8 smb3decryptionkey[SMB3_ENC_DEC_KEY_SIZE];
 	__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
 
 	__u8 binding_preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index 64fe5a47b5e8..9adc74bd9f8f 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -147,6 +147,11 @@
  */
 #define SMB3_SIGN_KEY_SIZE (16)
 
+/*
+ * Size of the smb3 encryption/decryption keys
+ */
+#define SMB3_ENC_DEC_KEY_SIZE (32)
+
 #define CIFS_CLIENT_CHALLENGE_SIZE (8)
 #define CIFS_SERVER_CHALLENGE_SIZE (8)
 #define CIFS_HMAC_MD5_HASH_SIZE (16)
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index 99a1951a01ec..d9a990c99121 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -58,6 +58,7 @@
 #define SMB2_HMACSHA256_SIZE (32)
 #define SMB2_CMACAES_SIZE (16)
 #define SMB3_SIGNKEY_SIZE (16)
+#define SMB3_GCM128_CRYPTKEY_SIZE (16)
 #define SMB3_GCM256_CRYPTKEY_SIZE (32)
 
 /* Maximum buffer size value we can send with 1 credit */
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 9bae7e8deb09..3e94f83897e9 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -4158,7 +4158,7 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
 			if (ses->Suid == ses_id) {
 				ses_enc_key = enc ? ses->smb3encryptionkey :
 					ses->smb3decryptionkey;
-				memcpy(key, ses_enc_key, SMB3_SIGN_KEY_SIZE);
+				memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE);
 				spin_unlock(&cifs_tcp_ses_lock);
 				return 0;
 			}
@@ -4185,7 +4185,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst,
 	int rc = 0;
 	struct scatterlist *sg;
 	u8 sign[SMB2_SIGNATURE_SIZE] = {};
-	u8 key[SMB3_SIGN_KEY_SIZE];
+	u8 key[SMB3_ENC_DEC_KEY_SIZE];
 	struct aead_request *req;
 	char *iv;
 	unsigned int iv_len;
@@ -4209,10 +4209,11 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst,
 	tfm = enc ? server->secmech.ccmaesencrypt :
 						server->secmech.ccmaesdecrypt;
 
-	if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)
+	if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+		(server->cipher_type == SMB2_ENCRYPTION_AES256_GCM))
 		rc = crypto_aead_setkey(tfm, key, SMB3_GCM256_CRYPTKEY_SIZE);
 	else
-		rc = crypto_aead_setkey(tfm, key, SMB3_SIGN_KEY_SIZE);
+		rc = crypto_aead_setkey(tfm, key, SMB3_GCM128_CRYPTKEY_SIZE);
 
 	if (rc) {
 		cifs_server_dbg(VFS, "%s: Failed to set aead key %d\n", __func__, rc);
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index ebccd71cc60a..e6fa76ab70be 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -298,7 +298,8 @@ static int generate_key(struct cifs_ses *ses, struct kvec label,
 {
 	unsigned char zero = 0x0;
 	__u8 i[4] = {0, 0, 0, 1};
-	__u8 L[4] = {0, 0, 0, 128};
+	__u8 L128[4] = {0, 0, 0, 128};
+	__u8 L256[4] = {0, 0, 1, 0};
 	int rc = 0;
 	unsigned char prfhash[SMB2_HMACSHA256_SIZE];
 	unsigned char *hashptr = prfhash;
@@ -354,8 +355,14 @@ static int generate_key(struct cifs_ses *ses, struct kvec label,
 		goto smb3signkey_ret;
 	}
 
-	rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
-				L, 4);
+	if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+		(server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) {
+		rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+				L256, 4);
+	} else {
+		rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+				L128, 4);
+	}
 	if (rc) {
 		cifs_server_dbg(VFS, "%s: Could not update with L\n", __func__);
 		goto smb3signkey_ret;
@@ -390,6 +397,9 @@ generate_smb3signingkey(struct cifs_ses *ses,
 			const struct derivation_triplet *ptriplet)
 {
 	int rc;
+#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS
+	struct TCP_Server_Info *server = ses->server;
+#endif
 
 	/*
 	 * All channels use the same encryption/decryption keys but
@@ -422,11 +432,11 @@ generate_smb3signingkey(struct cifs_ses *ses,
 		rc = generate_key(ses, ptriplet->encryption.label,
 				  ptriplet->encryption.context,
 				  ses->smb3encryptionkey,
-				  SMB3_SIGN_KEY_SIZE);
+				  SMB3_ENC_DEC_KEY_SIZE);
 		rc = generate_key(ses, ptriplet->decryption.label,
 				  ptriplet->decryption.context,
 				  ses->smb3decryptionkey,
-				  SMB3_SIGN_KEY_SIZE);
+				  SMB3_ENC_DEC_KEY_SIZE);
 		if (rc)
 			return rc;
 	}
@@ -442,14 +452,23 @@ generate_smb3signingkey(struct cifs_ses *ses,
 	 */
 	cifs_dbg(VFS, "Session Id    %*ph\n", (int)sizeof(ses->Suid),
 			&ses->Suid);
+	cifs_dbg(VFS, "Cipher type   %d\n", server->cipher_type);
 	cifs_dbg(VFS, "Session Key   %*ph\n",
 		 SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response);
 	cifs_dbg(VFS, "Signing Key   %*ph\n",
 		 SMB3_SIGN_KEY_SIZE, ses->smb3signingkey);
-	cifs_dbg(VFS, "ServerIn Key  %*ph\n",
-		 SMB3_SIGN_KEY_SIZE, ses->smb3encryptionkey);
-	cifs_dbg(VFS, "ServerOut Key %*ph\n",
-		 SMB3_SIGN_KEY_SIZE, ses->smb3decryptionkey);
+	if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+		(server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) {
+		cifs_dbg(VFS, "ServerIn Key  %*ph\n",
+				SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3encryptionkey);
+		cifs_dbg(VFS, "ServerOut Key %*ph\n",
+				SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3decryptionkey);
+	} else {
+		cifs_dbg(VFS, "ServerIn Key  %*ph\n",
+				SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3encryptionkey);
+		cifs_dbg(VFS, "ServerOut Key %*ph\n",
+				SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3decryptionkey);
+	}
 #endif
 	return rc;
 }

From 1cc5ed25bdade86de2650a82b2730108a76de20c Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Wed, 24 Mar 2021 17:06:54 -0600
Subject: [PATCH 1321/1820] usbip: vhci_hcd fix shift out-of-bounds in
 vhci_hub_control()

Fix shift out-of-bounds in vhci_hub_control() SetPortFeature handling.

UBSAN: shift-out-of-bounds in drivers/usb/usbip/vhci_hcd.c:605:42
shift exponent 768 is too large for 32-bit type 'int'

Reported-by: syzbot+3dea30b047f41084de66@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/20210324230654.34798-1-skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/vhci_hcd.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index 3209b5ddd30c..a20a8380ca0c 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -594,6 +594,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 				pr_err("invalid port number %d\n", wIndex);
 				goto error;
 			}
+			if (wValue >= 32)
+				goto error;
 			if (hcd->speed == HCD_USB3) {
 				if ((vhci_hcd->port_status[rhport] &
 				     USB_SS_PORT_STAT_POWER) != 0) {

From 5aef629704ad4d983ecf5c8a25840f16e45b6d59 Mon Sep 17 00:00:00 2001
From: Wesley Cheng <wcheng@codeaurora.org>
Date: Wed, 24 Mar 2021 11:31:04 -0700
Subject: [PATCH 1322/1820] usb: dwc3: gadget: Clear DEP flags after stop
 transfers in ep disable

Ensure that dep->flags are cleared until after stop active transfers
is completed.  Otherwise, the ENDXFER command will not be executed
during ep disable.

Fixes: f09ddcfcb8c5 ("usb: dwc3: gadget: Prevent EP queuing while stopping transfers")
Cc: stable <stable@vger.kernel.org>
Reported-and-tested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Wesley Cheng <wcheng@codeaurora.org>
Link: https://lore.kernel.org/r/1616610664-16495-1-git-send-email-wcheng@codeaurora.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/gadget.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 4c15c3fce303..c7ef218e7a8c 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -791,10 +791,6 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep)
 	reg &= ~DWC3_DALEPENA_EP(dep->number);
 	dwc3_writel(dwc->regs, DWC3_DALEPENA, reg);
 
-	dep->stream_capable = false;
-	dep->type = 0;
-	dep->flags = 0;
-
 	/* Clear out the ep descriptors for non-ep0 */
 	if (dep->number > 1) {
 		dep->endpoint.comp_desc = NULL;
@@ -803,6 +799,10 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep)
 
 	dwc3_remove_requests(dwc, dep);
 
+	dep->stream_capable = false;
+	dep->type = 0;
+	dep->flags = 0;
+
 	return 0;
 }
 

From 6f978a30c9bb12dab1302d0f06951ee290f5e600 Mon Sep 17 00:00:00 2001
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
Date: Tue, 23 Mar 2021 15:02:46 +0800
Subject: [PATCH 1323/1820] usb: xhci-mtk: fix broken streams issue on 0.96
 xHCI

The MediaTek 0.96 xHCI controller on some platforms does not
support bulk stream even HCCPARAMS says supporting, due to MaxPSASize
is set a default value 1 by mistake, here use XHCI_BROKEN_STREAMS
quirk to fix it.

Fixes: 94a631d91ad3 ("usb: xhci-mtk: check hcc_params after adding primary hcd")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/1616482975-17841-4-git-send-email-chunfeng.yun@mediatek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-mtk.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c
index fe010cc61f19..2f27dc0d9c6b 100644
--- a/drivers/usb/host/xhci-mtk.c
+++ b/drivers/usb/host/xhci-mtk.c
@@ -397,6 +397,13 @@ static void xhci_mtk_quirks(struct device *dev, struct xhci_hcd *xhci)
 	xhci->quirks |= XHCI_SPURIOUS_SUCCESS;
 	if (mtk->lpm_support)
 		xhci->quirks |= XHCI_LPM_SUPPORT;
+
+	/*
+	 * MTK xHCI 0.96: PSA is 1 by default even if doesn't support stream,
+	 * and it's 3 when support it.
+	 */
+	if (xhci->hci_version < 0x100 && HCC_MAX_PSA(xhci->hcc_params) == 4)
+		xhci->quirks |= XHCI_BROKEN_STREAMS;
 }
 
 /* called during probe() after chip reset completes */
@@ -548,7 +555,8 @@ static int xhci_mtk_probe(struct platform_device *pdev)
 	if (ret)
 		goto put_usb3_hcd;
 
-	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+	if (HCC_MAX_PSA(xhci->hcc_params) >= 4 &&
+	    !(xhci->quirks & XHCI_BROKEN_STREAMS))
 		xhci->shared_hcd->can_do_streams = 1;
 
 	ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED);

From 92af4fc6ec331228aca322ca37c8aea7b150a151 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Wed, 24 Mar 2021 09:11:41 +0200
Subject: [PATCH 1324/1820] usb: musb: Fix suspend with devices connected for
 a64

Pinephone running on Allwinner A64 fails to suspend with USB devices
connected as reported by Bhushan Shah <bshah@kde.org>. Reverting
commit 5fbf7a253470 ("usb: musb: fix idling for suspend after
disconnect interrupt") fixes the issue.

Let's add suspend checks also for suspend after disconnect interrupt
quirk handling like we already do elsewhere.

Fixes: 5fbf7a253470 ("usb: musb: fix idling for suspend after disconnect interrupt")
Reported-by: Bhushan Shah <bshah@kde.org>
Tested-by: Bhushan Shah <bshah@kde.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20210324071142.42264-1-tony@atomide.com
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/musb/musb_core.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 1cd87729ba60..fc0457db62e1 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -2004,10 +2004,14 @@ static void musb_pm_runtime_check_session(struct musb *musb)
 		MUSB_DEVCTL_HR;
 	switch (devctl & ~s) {
 	case MUSB_QUIRK_B_DISCONNECT_99:
-		musb_dbg(musb, "Poll devctl in case of suspend after disconnect\n");
-		schedule_delayed_work(&musb->irq_work,
-				      msecs_to_jiffies(1000));
-		break;
+		if (musb->quirk_retries && !musb->flush_irq_work) {
+			musb_dbg(musb, "Poll devctl in case of suspend after disconnect\n");
+			schedule_delayed_work(&musb->irq_work,
+					      msecs_to_jiffies(1000));
+			musb->quirk_retries--;
+			break;
+		}
+		fallthrough;
 	case MUSB_QUIRK_B_INVALID_VBUS_91:
 		if (musb->quirk_retries && !musb->flush_irq_work) {
 			musb_dbg(musb,

From 5e3bbae8ee3d677a0aa2919dc62b5c60ea01ba61 Mon Sep 17 00:00:00 2001
From: Artur Petrosyan <Arthur.Petrosyan@synopsys.com>
Date: Fri, 26 Mar 2021 14:24:46 +0400
Subject: [PATCH 1325/1820] usb: dwc2: Fix HPRT0.PrtSusp bit setting for HiKey
 960 board.

Increased the waiting timeout for HPRT0.PrtSusp register field
to be set, because on HiKey 960 board HPRT0.PrtSusp wasn't
generated with the existing timeout.

Cc: <stable@vger.kernel.org> # 4.18
Fixes: 22bb5cfdf13a ("usb: dwc2: Fix host exit from hibernation flow.")
Signed-off-by: Artur Petrosyan <Arthur.Petrosyan@synopsys.com>
Acked-by: Minas Harutyunyan <Minas.Harutyunyan@synopsys.com>
Link: https://lore.kernel.org/r/20210326102447.8F7FEA005D@mailhost.synopsys.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc2/hcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index fc3269f5faf1..40e5655921bf 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -5398,7 +5398,7 @@ int dwc2_host_enter_hibernation(struct dwc2_hsotg *hsotg)
 	dwc2_writel(hsotg, hprt0, HPRT0);
 
 	/* Wait for the HPRT0.PrtSusp register field to be set */
-	if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 3000))
+	if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 5000))
 		dev_warn(hsotg->dev, "Suspend wasn't generated\n");
 
 	/*

From 93f672804bf2d7a49ef3fd96827ea6290ca1841e Mon Sep 17 00:00:00 2001
From: Artur Petrosyan <Arthur.Petrosyan@synopsys.com>
Date: Fri, 26 Mar 2021 14:25:09 +0400
Subject: [PATCH 1326/1820] usb: dwc2: Prevent core suspend when port
 connection flag is 0

In host mode port connection status flag is "0" when loading
the driver. After loading the driver system asserts suspend
which is handled by "_dwc2_hcd_suspend()" function. Before
the system suspend the port connection status is "0". As
result need to check the "port_connect_status" if it is "0",
then skipping entering to suspend.

Cc: <stable@vger.kernel.org> # 5.2
Fixes: 6f6d70597c15 ("usb: dwc2: bus suspend/resume for hosts with DWC2_POWER_DOWN_PARAM_NONE")
Signed-off-by: Artur Petrosyan <Arthur.Petrosyan@synopsys.com>
Link: https://lore.kernel.org/r/20210326102510.BDEDEA005D@mailhost.synopsys.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc2/hcd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index 40e5655921bf..1a9789ec5847 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -4322,7 +4322,8 @@ static int _dwc2_hcd_suspend(struct usb_hcd *hcd)
 	if (hsotg->op_state == OTG_STATE_B_PERIPHERAL)
 		goto unlock;
 
-	if (hsotg->params.power_down > DWC2_POWER_DOWN_PARAM_PARTIAL)
+	if (hsotg->params.power_down != DWC2_POWER_DOWN_PARAM_PARTIAL ||
+	    hsotg->flags.b.port_connect_status == 0)
 		goto skip_power_saving;
 
 	/*

From 29d96eb261345c8d888e248ae79484e681be2faa Mon Sep 17 00:00:00 2001
From: Roja Rani Yarubandi <rojay@codeaurora.org>
Date: Wed, 24 Mar 2021 15:48:35 +0530
Subject: [PATCH 1327/1820] soc: qcom-geni-se: Cleanup the code to remove proxy
 votes

This reverts commit 048eb908a1f2 ("soc: qcom-geni-se: Add interconnect
support to fix earlycon crash")

ICC core and platforms drivers supports sync_state feature, which
ensures that the default ICC BW votes from the bootloader is not
removed until all it's consumers are probes.

The proxy votes were needed in case other QUP child drivers
I2C, SPI probes before UART, they can turn off the QUP-CORE clock
which is shared resources for all QUP driver, this causes unclocked
access to HW from earlycon.

Given above support from ICC there is no longer need to maintain
proxy votes on QUP-CORE ICC node from QUP wrapper driver for early
console usecase, the default votes won't be removed until real
console is probed.

Cc: stable@vger.kernel.org
Fixes: 266cd33b5913 ("interconnect: qcom: Ensure that the floor bandwidth value is enforced")
Fixes: 7d3b0b0d8184 ("interconnect: qcom: Use icc_sync_state")
Signed-off-by: Roja Rani Yarubandi <rojay@codeaurora.org>
Signed-off-by: Akash Asthana <akashast@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Link: https://lore.kernel.org/r/20210324101836.25272-2-rojay@codeaurora.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/soc/qcom/qcom-geni-se.c       | 74 ---------------------------
 drivers/tty/serial/qcom_geni_serial.c |  7 ---
 include/linux/qcom-geni-se.h          |  2 -
 3 files changed, 83 deletions(-)

diff --git a/drivers/soc/qcom/qcom-geni-se.c b/drivers/soc/qcom/qcom-geni-se.c
index f42954e2c98e..1fd29f93ff6d 100644
--- a/drivers/soc/qcom/qcom-geni-se.c
+++ b/drivers/soc/qcom/qcom-geni-se.c
@@ -3,7 +3,6 @@
 
 #include <linux/acpi.h>
 #include <linux/clk.h>
-#include <linux/console.h>
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
@@ -92,14 +91,11 @@ struct geni_wrapper {
 	struct device *dev;
 	void __iomem *base;
 	struct clk_bulk_data ahb_clks[NUM_AHB_CLKS];
-	struct geni_icc_path to_core;
 };
 
 static const char * const icc_path_names[] = {"qup-core", "qup-config",
 						"qup-memory"};
 
-static struct geni_wrapper *earlycon_wrapper;
-
 #define QUP_HW_VER_REG			0x4
 
 /* Common SE registers */
@@ -843,44 +839,11 @@ int geni_icc_disable(struct geni_se *se)
 }
 EXPORT_SYMBOL(geni_icc_disable);
 
-void geni_remove_earlycon_icc_vote(void)
-{
-	struct platform_device *pdev;
-	struct geni_wrapper *wrapper;
-	struct device_node *parent;
-	struct device_node *child;
-
-	if (!earlycon_wrapper)
-		return;
-
-	wrapper = earlycon_wrapper;
-	parent = of_get_next_parent(wrapper->dev->of_node);
-	for_each_child_of_node(parent, child) {
-		if (!of_device_is_compatible(child, "qcom,geni-se-qup"))
-			continue;
-
-		pdev = of_find_device_by_node(child);
-		if (!pdev)
-			continue;
-
-		wrapper = platform_get_drvdata(pdev);
-		icc_put(wrapper->to_core.path);
-		wrapper->to_core.path = NULL;
-
-	}
-	of_node_put(parent);
-
-	earlycon_wrapper = NULL;
-}
-EXPORT_SYMBOL(geni_remove_earlycon_icc_vote);
-
 static int geni_se_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct resource *res;
 	struct geni_wrapper *wrapper;
-	struct console __maybe_unused *bcon;
-	bool __maybe_unused has_earlycon = false;
 	int ret;
 
 	wrapper = devm_kzalloc(dev, sizeof(*wrapper), GFP_KERNEL);
@@ -903,43 +866,6 @@ static int geni_se_probe(struct platform_device *pdev)
 		}
 	}
 
-#ifdef CONFIG_SERIAL_EARLYCON
-	for_each_console(bcon) {
-		if (!strcmp(bcon->name, "qcom_geni")) {
-			has_earlycon = true;
-			break;
-		}
-	}
-	if (!has_earlycon)
-		goto exit;
-
-	wrapper->to_core.path = devm_of_icc_get(dev, "qup-core");
-	if (IS_ERR(wrapper->to_core.path))
-		return PTR_ERR(wrapper->to_core.path);
-	/*
-	 * Put minmal BW request on core clocks on behalf of early console.
-	 * The vote will be removed earlycon exit function.
-	 *
-	 * Note: We are putting vote on each QUP wrapper instead only to which
-	 * earlycon is connected because QUP core clock of different wrapper
-	 * share same voltage domain. If core1 is put to 0, then core2 will
-	 * also run at 0, if not voted. Default ICC vote will be removed ASA
-	 * we touch any of the core clock.
-	 * core1 = core2 = max(core1, core2)
-	 */
-	ret = icc_set_bw(wrapper->to_core.path, GENI_DEFAULT_BW,
-				GENI_DEFAULT_BW);
-	if (ret) {
-		dev_err(&pdev->dev, "%s: ICC BW voting failed for core: %d\n",
-			__func__, ret);
-		return ret;
-	}
-
-	if (of_get_compatible_child(pdev->dev.of_node, "qcom,geni-debug-uart"))
-		earlycon_wrapper = wrapper;
-	of_node_put(pdev->dev.of_node);
-exit:
-#endif
 	dev_set_drvdata(dev, wrapper);
 	dev_dbg(dev, "GENI SE Driver probed\n");
 	return devm_of_platform_populate(dev);
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 291649f02821..0d85b55ea823 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -1177,12 +1177,6 @@ static inline void qcom_geni_serial_enable_early_read(struct geni_se *se,
 						      struct console *con) { }
 #endif
 
-static int qcom_geni_serial_earlycon_exit(struct console *con)
-{
-	geni_remove_earlycon_icc_vote();
-	return 0;
-}
-
 static struct qcom_geni_private_data earlycon_private_data;
 
 static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev,
@@ -1233,7 +1227,6 @@ static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev,
 	writel(stop_bit_len, uport->membase + SE_UART_TX_STOP_BIT_LEN);
 
 	dev->con->write = qcom_geni_serial_earlycon_write;
-	dev->con->exit = qcom_geni_serial_earlycon_exit;
 	dev->con->setup = NULL;
 	qcom_geni_serial_enable_early_read(&se, dev->con);
 
diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h
index ec2ad4b0fe14..c4fdb4463f7d 100644
--- a/include/linux/qcom-geni-se.h
+++ b/include/linux/qcom-geni-se.h
@@ -460,7 +460,5 @@ void geni_icc_set_tag(struct geni_se *se, u32 tag);
 int geni_icc_enable(struct geni_se *se);
 
 int geni_icc_disable(struct geni_se *se);
-
-void geni_remove_earlycon_icc_vote(void);
 #endif
 #endif

From a846738f8c3788d846ed1f587270d2f2e3d32432 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@suse.com>
Date: Fri, 26 Mar 2021 16:33:53 +0100
Subject: [PATCH 1328/1820] xen-blkback: don't leak persistent grants from
 xen_blkbk_map()

The fix for XSA-365 zapped too many of the ->persistent_gnt[] entries.
Ones successfully obtained should not be overwritten, but instead left
for xen_blkbk_unmap_prepare() to pick up and put.

This is XSA-371.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Cc: stable@vger.kernel.org
Reviewed-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Wei Liu <wl@xen.org>
Signed-off-by: Juergen Gross <jgross@suse.com>
---
 drivers/block/xen-blkback/blkback.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index da16121140ca..3874233f7194 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -891,7 +891,7 @@ next:
 out:
 	for (i = last_map; i < num; i++) {
 		/* Don't zap current batch's valid persistent grants. */
-		if(i >= last_map + segs_to_map)
+		if(i >= map_until)
 			pages[i]->persistent_gnt = NULL;
 		pages[i]->handle = BLKBACK_INVALID_HANDLE;
 	}

From a95d8f581901c560ff1b63bc02107eb34a6efb1b Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 26 Mar 2021 13:07:21 +0100
Subject: [PATCH 1329/1820] cpufreq: Fix
 scaling_{available,boost}_frequencies_show() comments

The function names in the comment blocks for the functions
scaling_available_frequencies_show() and
scaling_boost_frequencies_show() do not match the actual names.

Fixes: 6f19efc0a1ca08bc ("cpufreq: Add boost frequency support in core")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/freq_table.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index d3f756f7b5a0..67e56cf638ef 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -267,7 +267,7 @@ struct freq_attr cpufreq_freq_attr_##_name##_freqs =     \
 __ATTR_RO(_name##_frequencies)
 
 /*
- * show_scaling_available_frequencies - show available normal frequencies for
+ * scaling_available_frequencies_show - show available normal frequencies for
  * the specified CPU
  */
 static ssize_t scaling_available_frequencies_show(struct cpufreq_policy *policy,
@@ -279,7 +279,7 @@ cpufreq_attr_available_freq(scaling_available);
 EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs);
 
 /*
- * show_available_boost_freqs - show available boost frequencies for
+ * scaling_boost_frequencies_show - show available boost frequencies for
  * the specified CPU
  */
 static ssize_t scaling_boost_frequencies_show(struct cpufreq_policy *policy,

From 12aa8a9467b354ef893ce0fc5719a4de4949a9fb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Fri, 26 Mar 2021 11:03:13 +0100
Subject: [PATCH 1330/1820] bpf: Enforce that struct_ops programs be GPL-only
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With the introduction of the struct_ops program type, it became possible to
implement kernel functionality in BPF, making it viable to use BPF in place
of a regular kernel module for these particular operations.

Thus far, the only user of this mechanism is for implementing TCP
congestion control algorithms. These are clearly marked as GPL-only when
implemented as modules (as seen by the use of EXPORT_SYMBOL_GPL for
tcp_register_congestion_control()), so it seems like an oversight that this
was not carried over to BPF implementations. Since this is the only user
of the struct_ops mechanism, just enforcing GPL-only for the struct_ops
program type seems like the simplest way to fix this.

Fixes: 0baf26b0fcd7 ("bpf: tcp: Support tcp_congestion_ops in bpf")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210326100314.121853-1-toke@redhat.com
---
 kernel/bpf/verifier.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 44e4ec1640f1..3a738724a380 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12158,6 +12158,11 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 	u32 btf_id, member_idx;
 	const char *mname;
 
+	if (!prog->gpl_compatible) {
+		verbose(env, "struct ops programs must have a GPL compatible license\n");
+		return -EINVAL;
+	}
+
 	btf_id = prog->aux->attach_btf_id;
 	st_ops = bpf_struct_ops_find(btf_id);
 	if (!st_ops) {

From d8e8052e42d0f8ff59898b9b4142b16958627ac9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Fri, 26 Mar 2021 11:03:14 +0100
Subject: [PATCH 1331/1820] bpf/selftests: Test that kernel rejects a TCP CC
 with an invalid license
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds a selftest to check that the verifier rejects a TCP CC struct_ops
with a non-GPL license.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210326100314.121853-2-toke@redhat.com
---
 .../selftests/bpf/prog_tests/bpf_tcp_ca.c     | 44 +++++++++++++++++++
 .../selftests/bpf/progs/bpf_tcp_nogpl.c       | 19 ++++++++
 2 files changed, 63 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 37c5494a0381..e25917f04602 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -6,6 +6,7 @@
 #include <test_progs.h>
 #include "bpf_dctcp.skel.h"
 #include "bpf_cubic.skel.h"
+#include "bpf_tcp_nogpl.skel.h"
 
 #define min(a, b) ((a) < (b) ? (a) : (b))
 
@@ -227,10 +228,53 @@ static void test_dctcp(void)
 	bpf_dctcp__destroy(dctcp_skel);
 }
 
+static char *err_str;
+static bool found;
+
+static int libbpf_debug_print(enum libbpf_print_level level,
+			      const char *format, va_list args)
+{
+	char *log_buf;
+
+	if (level != LIBBPF_WARN ||
+	    strcmp(format, "libbpf: \n%s\n")) {
+		vprintf(format, args);
+		return 0;
+	}
+
+	log_buf = va_arg(args, char *);
+	if (!log_buf)
+		goto out;
+	if (err_str && strstr(log_buf, err_str) != NULL)
+		found = true;
+out:
+	printf(format, log_buf);
+	return 0;
+}
+
+static void test_invalid_license(void)
+{
+	libbpf_print_fn_t old_print_fn;
+	struct bpf_tcp_nogpl *skel;
+
+	err_str = "struct ops programs must have a GPL compatible license";
+	found = false;
+	old_print_fn = libbpf_set_print(libbpf_debug_print);
+
+	skel = bpf_tcp_nogpl__open_and_load();
+	ASSERT_NULL(skel, "bpf_tcp_nogpl");
+	ASSERT_EQ(found, true, "expected_err_msg");
+
+	bpf_tcp_nogpl__destroy(skel);
+	libbpf_set_print(old_print_fn);
+}
+
 void test_bpf_tcp_ca(void)
 {
 	if (test__start_subtest("dctcp"))
 		test_dctcp();
 	if (test__start_subtest("cubic"))
 		test_cubic();
+	if (test__start_subtest("invalid_license"))
+		test_invalid_license();
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c
new file mode 100644
index 000000000000..2ecd833dcd41
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "X";
+
+void BPF_STRUCT_OPS(nogpltcp_init, struct sock *sk)
+{
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops bpf_nogpltcp = {
+	.init           = (void *)nogpltcp_init,
+	.name           = "bpf_nogpltcp",
+};

From d6fe1cf89026d3111112ee29ef8d93cd7a8aaa24 Mon Sep 17 00:00:00 2001
From: Xu Kuohai <xukuohai@huawei.com>
Date: Thu, 25 Mar 2021 13:41:41 +0000
Subject: [PATCH 1332/1820] bpf: Fix a spelling typo in bpf_atomic_alu_string
 disasm

The name string for BPF_XOR is "xor", not "or". Fix it.

Fixes: 981f94c3e921 ("bpf: Add bitwise atomic instructions")
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Brendan Jackman <jackmanb@google.com>
Link: https://lore.kernel.org/bpf/20210325134141.8533-1-xukuohai@huawei.com
---
 kernel/bpf/disasm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index 3acc7e0b6916..faa54d58972c 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -84,7 +84,7 @@ static const char *const bpf_atomic_alu_string[16] = {
 	[BPF_ADD >> 4]  = "add",
 	[BPF_AND >> 4]  = "and",
 	[BPF_OR >> 4]  = "or",
-	[BPF_XOR >> 4]  = "or",
+	[BPF_XOR >> 4]  = "xor",
 };
 
 static const char *const bpf_ldst_string[] = {

From 57a9006240b229b9d77ef60fadb30d2067438437 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Fri, 26 Mar 2021 10:01:52 +0100
Subject: [PATCH 1333/1820] remove Dan Murphy from TI from MAINTAINERS

Dan's address bounces, and has been bouncing for some time as he moved
to other projects.

I believe TI should be more careful with this, and should assign
alternate contacts for their drivers.

Anyway what we can do now is to remove the obsolete address.

Signed-off-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 MAINTAINERS | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8d23b0ec0c90..e6d62569f4ec 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10030,7 +10030,6 @@ F:	scripts/leaking_addresses.pl
 
 LED SUBSYSTEM
 M:	Pavel Machek <pavel@ucw.cz>
-R:	Dan Murphy <dmurphy@ti.com>
 L:	linux-leds@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pavel/linux-leds.git
@@ -10906,7 +10905,6 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/radio/radio-maxiradio*
 
 MCAN MMIO DEVICE DRIVER
-M:	Dan Murphy <dmurphy@ti.com>
 M:	Pankaj Sharma <pankj.sharma@samsung.com>
 L:	linux-can@vger.kernel.org
 S:	Maintained
@@ -17845,7 +17843,6 @@ S:	Maintained
 F:	drivers/thermal/ti-soc-thermal/
 
 TI BQ27XXX POWER SUPPLY DRIVER
-R:	Dan Murphy <dmurphy@ti.com>
 F:	drivers/power/supply/bq27xxx_battery.c
 F:	drivers/power/supply/bq27xxx_battery_i2c.c
 F:	include/linux/power/bq27xxx_battery.h
@@ -17980,7 +17977,6 @@ S:	Odd Fixes
 F:	sound/soc/codecs/tas571x*
 
 TI TCAN4X5X DEVICE DRIVER
-M:	Dan Murphy <dmurphy@ti.com>
 L:	linux-can@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/can/tcan4x5x.txt

From 4edbe1d7bcffcd6269f3b5eb63f710393ff2ec7a Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Fri, 26 Mar 2021 14:32:32 -0400
Subject: [PATCH 1334/1820] dm ioctl: fix out of bounds array access when no
 devices

If there are not any dm devices, we need to zero the "dev" argument in
the first structure dm_name_list. However, this can cause out of
bounds write, because the "needed" variable is zero and len may be
less than eight.

Fix this bug by reporting DM_BUFFER_FULL_FLAG if the result buffer is
too small to hold the "nl->dev" value.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-ioctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 5e306bba4375..1ca65b434f1f 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -529,7 +529,7 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_
 	 * Grab our output buffer.
 	 */
 	nl = orig_nl = get_result_buffer(param, param_size, &len);
-	if (len < needed) {
+	if (len < needed || len < sizeof(nl->dev)) {
 		param->flags |= DM_BUFFER_FULL_FLAG;
 		goto out;
 	}

From 10442994ba195efef6fdcc0c3699e4633cb5161b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 26 Mar 2021 08:57:10 -0600
Subject: [PATCH 1335/1820] kernel: don't call do_exit() for PF_IO_WORKER
 threads

Right now we're never calling get_signal() from PF_IO_WORKER threads, but
in preparation for doing so, don't handle a fatal signal for them. The
workers have state they need to cleanup when exiting, so just return
instead of calling do_exit() on their behalf. The threads themselves will
detect a fatal signal and do proper shutdown.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/signal.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/kernel/signal.c b/kernel/signal.c
index f2a1b898da29..d22177d37b21 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2771,6 +2771,14 @@ relock:
 			do_coredump(&ksig->info);
 		}
 
+		/*
+		 * PF_IO_WORKER threads will catch and exit on fatal signals
+		 * themselves. They have cleanup that must be performed, so
+		 * we cannot call do_exit() on their behalf.
+		 */
+		if (current->flags & PF_IO_WORKER)
+			goto out;
+
 		/*
 		 * Death signals, no core dump.
 		 */
@@ -2778,7 +2786,7 @@ relock:
 		/* NOTREACHED */
 	}
 	spin_unlock_irq(&sighand->siglock);
-
+out:
 	ksig->sig = signr;
 
 	if (!(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS))

From 3bffbe9e0b2721bb62d226a4d4211bddae52b00a Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Fri, 26 Mar 2021 10:28:16 +0000
Subject: [PATCH 1336/1820] cifs: Fix chmod with modefromsid when an older ACE
 already exists.

My recent fixes to cifsacl to maintain inherited ACEs had
regressed modefromsid when an older ACL already exists.

Found testing xfstest 495 with modefromsid mount option

Fixes: f5065508897a ("cifs: Retain old ACEs when converting between mode bits and ACL")

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Reviewed-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cifsacl.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 2be22a5c690f..d178cf85e926 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1130,8 +1130,7 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl,
 		}
 
 		/* If it's any one of the ACE we're replacing, skip! */
-		if (!mode_from_sid &&
-				((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
+		if (((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
 				(compare_sids(&pntace->sid, pownersid) == 0) ||
 				(compare_sids(&pntace->sid, pgrpsid) == 0) ||
 				(compare_sids(&pntace->sid, &sid_everyone) == 0) ||

From cee8f4f6fcabfdf229542926128e9874d19016d5 Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Thu, 25 Mar 2021 16:26:35 +1000
Subject: [PATCH 1337/1820] cifs: revalidate mapping when we open files for
 SMB1 POSIX

RHBZ: 1933527

Under SMB1 + POSIX, if an inode is reused on a server after we have read and
cached a part of a file, when we then open the new file with the
re-cycled inode there is a chance that we may serve the old data out of cache
to the application.
This only happens for SMB1 (deprecated) and when posix are used.
The simplest solution to avoid this race is to force a revalidate
on smb1-posix open.

Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Reviewed-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/file.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 26de4329d161..042e24aad410 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -165,6 +165,7 @@ int cifs_posix_open(char *full_path, struct inode **pinode,
 			goto posix_open_ret;
 		}
 	} else {
+		cifs_revalidate_mapping(*pinode);
 		cifs_fattr_to_inode(*pinode, &fattr);
 	}
 

From 219481a8f90ec3a5eed9638fb35609e4b1aeece7 Mon Sep 17 00:00:00 2001
From: Vincent Whitchurch <vincent.whitchurch@axis.com>
Date: Fri, 19 Mar 2021 14:57:11 +0100
Subject: [PATCH 1338/1820] cifs: Silently ignore unknown oplock break handle

Make SMB2 not print out an error when an oplock break is received for an
unknown handle, similar to SMB1.  The debug message which is printed for
these unknown handles may also be misleading, so fix that too.

The SMB2 lease break path is not affected by this patch.

Without this, a program which writes to a file from one thread, and
opens, reads, and writes the same file from another thread triggers the
below errors several times a minute when run against a Samba server
configured with "smb2 leases = no".

 CIFS: VFS: \\192.168.0.1 No task to wake, unknown frame received! NumMids 2
 00000000: 424d53fe 00000040 00000000 00000012  .SMB@...........
 00000010: 00000001 00000000 ffffffff ffffffff  ................
 00000020: 00000000 00000000 00000000 00000000  ................
 00000030: 00000000 00000000 00000000 00000000  ................

Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com>
Reviewed-by: Tom Talpey <tom@talpey.com>
Reviewed-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/smb2misc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index b50164e2c88d..aac384f69f74 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -754,8 +754,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 		}
 	}
 	spin_unlock(&cifs_tcp_ses_lock);
-	cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
-	return false;
+	cifs_dbg(FYI, "No file id matched, oplock break ignored\n");
+	return true;
 }
 
 void

From cfc63fc8126a93cbf95379bc4cad79a7b15b6ece Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Fri, 26 Mar 2021 18:41:55 -0500
Subject: [PATCH 1339/1820] smb3: fix cached file size problems in duplicate
 extents (reflink)

There were two problems (one of which could cause data corruption)
that were noticed with duplicate extents (ie reflink)
when debugging why various xfstests were being incorrectly skipped
(e.g. generic/138, generic/140, generic/142). First, we were not
updating the file size locally in the cache when extending a
file due to reflink (it would refresh after actimeo expires)
but xfstest was checking the size immediately which was still
0 so caused the test to be skipped.  Second, we were setting
the target file size (which could shrink the file) in all cases
to the end of the reflinked range rather than only setting the
target file size when reflink would extend the file.

CC: <stable@vger.kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/smb2ops.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 3e94f83897e9..f703204fb185 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -2038,6 +2038,7 @@ smb2_duplicate_extents(const unsigned int xid,
 {
 	int rc;
 	unsigned int ret_data_len;
+	struct inode *inode;
 	struct duplicate_extents_to_file dup_ext_buf;
 	struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink);
 
@@ -2054,10 +2055,21 @@ smb2_duplicate_extents(const unsigned int xid,
 	cifs_dbg(FYI, "Duplicate extents: src off %lld dst off %lld len %lld\n",
 		src_off, dest_off, len);
 
-	rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
-	if (rc)
-		goto duplicate_extents_out;
+	inode = d_inode(trgtfile->dentry);
+	if (inode->i_size < dest_off + len) {
+		rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
+		if (rc)
+			goto duplicate_extents_out;
 
+		/*
+		 * Although also could set plausible allocation size (i_blocks)
+		 * here in addition to setting the file size, in reflink
+		 * it is likely that the target file is sparse. Its allocation
+		 * size will be queried on next revalidate, but it is important
+		 * to make sure that file's cached size is updated immediately
+		 */
+		cifs_setsize(inode, dest_off + len);
+	}
 	rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
 			trgtfile->fid.volatile_fid,
 			FSCTL_DUPLICATE_EXTENTS_TO_FILE,

From cf97d7af246831ea23c216f17205f91319afc85f Mon Sep 17 00:00:00 2001
From: Pawel Laszczak <pawell@cadence.com>
Date: Mon, 22 Mar 2021 06:47:14 +0100
Subject: [PATCH 1340/1820] usb: cdnsp: Fixes issue with dequeuing requests
 after disabling endpoint

Patch fixes the bug:
BUG: kernel NULL pointer dereference, address: 0000000000000050
PGD 0 P4D 0
Oops: 0002 [#1] SMP PTI
CPU: 0 PID: 4137 Comm: uvc-gadget Tainted: G           OE     5.10.0-next-20201214+ #3
Hardware name: ASUS All Series/Q87T, BIOS 0908 07/22/2014
RIP: 0010:cdnsp_remove_request+0xe9/0x530 [cdnsp_udc_pci]
Code: 01 00 00 31 f6 48 89 df e8 64 d4 ff ff 48 8b 43 08 48 8b 13 45 31 f6 48 89 42 08 48 89 10 b8 98 ff ff ff 48 89 1b 48 89 5b 08 <41> 83 6d 50 01 41 83 af d0 00 00 00 01 41 f6 84 24 78 20 00 00 08
RSP: 0018:ffffb68d00d07b60 EFLAGS: 00010046
RAX: 00000000ffffff98 RBX: ffff9d29c57fbf00 RCX: 0000000000001400
RDX: ffff9d29c57fbf00 RSI: 0000000000000000 RDI: ffff9d29c57fbf00
RBP: ffffb68d00d07bb0 R08: ffff9d2ad9510a00 R09: ffff9d2ac011c000
R10: ffff9d2a12b6e760 R11: 0000000000000000 R12: ffff9d29d3fb8000
R13: 0000000000000000 R14: 0000000000000000 R15: ffff9d29d3fb88c0
FS:  0000000000000000(0000) GS:ffff9d2adba00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000050 CR3: 0000000102164005 CR4: 00000000001706f0
Call Trace:
 cdnsp_ep_dequeue+0x3c/0x90 [cdnsp_udc_pci]
 cdnsp_gadget_ep_dequeue+0x3f/0x80 [cdnsp_udc_pci]
 usb_ep_dequeue+0x21/0x70 [udc_core]
 uvcg_video_enable+0x19d/0x220 [usb_f_uvc]
 uvc_v4l2_release+0x49/0x90 [usb_f_uvc]
 v4l2_release+0xa5/0x100 [videodev]
 __fput+0x99/0x250
 ____fput+0xe/0x10
 task_work_run+0x75/0xb0
 do_exit+0x370/0xb80
 do_group_exit+0x43/0xa0
 get_signal+0x12d/0x820
 arch_do_signal_or_restart+0xb2/0x870
 ? __switch_to_asm+0x36/0x70
 ? kern_select+0xc6/0x100
 exit_to_user_mode_prepare+0xfc/0x170
 syscall_exit_to_user_mode+0x2a/0x40
 do_syscall_64+0x43/0x80
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7fe969cf5dd7
Code: Unable to access opcode bytes at RIP 0x7fe969cf5dad.

Problem occurs for UVC class. During disconnecting the UVC class disable
endpoints and then start dequeuing all requests. This leads to situation
where requests are removed twice. The first one in
cdnsp_gadget_ep_disable and the second in cdnsp_gadget_ep_dequeue
function.
Patch adds condition in cdnsp_gadget_ep_dequeue function which allows
dequeue requests only from enabled endpoint.

Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver")
Signed-off-by: Pawel Laszczak <pawell@cadence.com>
Signed-off-by: Peter Chen <peter.chen@kernel.org>
---
 drivers/usb/cdns3/cdnsp-gadget.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c
index f2ebbacd932e..d7d4bdd57f46 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.c
+++ b/drivers/usb/cdns3/cdnsp-gadget.c
@@ -1128,6 +1128,10 @@ static int cdnsp_gadget_ep_dequeue(struct usb_ep *ep,
 		return -ESHUTDOWN;
 	}
 
+	/* Requests has been dequeued during disabling endpoint. */
+	if (!(pep->ep_state & EP_ENABLED))
+		return 0;
+
 	spin_lock_irqsave(&pdev->lock, flags);
 	ret = cdnsp_ep_dequeue(pep, to_cdnsp_request(request));
 	spin_unlock_irqrestore(&pdev->lock, flags);

From 861de02e5f3f2a104eecc5af1d248cb7bf8c5f75 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 26 Mar 2021 11:59:00 +0100
Subject: [PATCH 1341/1820] bpf: Take module reference for trampoline in module

Currently module can be unloaded even if there's a trampoline
register in it. It's easily reproduced by running in parallel:

  # while :; do ./test_progs -t module_attach; done
  # while :; do rmmod bpf_testmod; sleep 0.5; done

Taking the module reference in case the trampoline's ip is
within the module code. Releasing it when the trampoline's
ip is unregistered.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210326105900.151466-1-jolsa@kernel.org
---
 include/linux/bpf.h     |  2 ++
 kernel/bpf/trampoline.c | 30 ++++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3625f019767d..fdac0534ce79 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -40,6 +40,7 @@ struct bpf_local_storage;
 struct bpf_local_storage_map;
 struct kobject;
 struct mem_cgroup;
+struct module;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -623,6 +624,7 @@ struct bpf_trampoline {
 	/* Executable image of trampoline */
 	struct bpf_tramp_image *cur_image;
 	u64 selector;
+	struct module *mod;
 };
 
 struct bpf_attach_target_info {
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 1f3a4be4b175..4aa8b52adf25 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -9,6 +9,7 @@
 #include <linux/btf.h>
 #include <linux/rcupdate_trace.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/module.h>
 
 /* dummy _ops. The verifier will operate on target program's ops. */
 const struct bpf_verifier_ops bpf_extension_verifier_ops = {
@@ -87,6 +88,26 @@ out:
 	return tr;
 }
 
+static int bpf_trampoline_module_get(struct bpf_trampoline *tr)
+{
+	struct module *mod;
+	int err = 0;
+
+	preempt_disable();
+	mod = __module_text_address((unsigned long) tr->func.addr);
+	if (mod && !try_module_get(mod))
+		err = -ENOENT;
+	preempt_enable();
+	tr->mod = mod;
+	return err;
+}
+
+static void bpf_trampoline_module_put(struct bpf_trampoline *tr)
+{
+	module_put(tr->mod);
+	tr->mod = NULL;
+}
+
 static int is_ftrace_location(void *ip)
 {
 	long addr;
@@ -108,6 +129,9 @@ static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
 		ret = unregister_ftrace_direct((long)ip, (long)old_addr);
 	else
 		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
+
+	if (!ret)
+		bpf_trampoline_module_put(tr);
 	return ret;
 }
 
@@ -134,10 +158,16 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 		return ret;
 	tr->func.ftrace_managed = ret;
 
+	if (bpf_trampoline_module_get(tr))
+		return -ENOENT;
+
 	if (tr->func.ftrace_managed)
 		ret = register_ftrace_direct((long)ip, (long)new_addr);
 	else
 		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
+
+	if (ret)
+		bpf_trampoline_module_put(tr);
 	return ret;
 }
 

From e82fc7855749aa197740a60ef22c492c41ea5d5f Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sat, 27 Mar 2021 15:13:09 +0800
Subject: [PATCH 1342/1820] block: don't create too many partitions

Commit a33df75c6328 ("block: use an xarray for disk->part_tbl") drops the
check on max supported number of partitionsr, and allows partition with
bigger partition numbers to be added. However, ->bd_partno is defined as
u8, so partition index of xarray table may not match with ->bd_partno.
Then delete_partition() may delete one unmatched partition, and caused
use-after-free.

Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reported-by: syzbot+8fede7e30c7cee0de139@syzkaller.appspotmail.com
Fixes: a33df75c6328 ("block: use an xarray for disk->part_tbl")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/core.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/block/partitions/core.c b/block/partitions/core.c
index 1a7558917c47..46f055bc7ecb 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -322,6 +322,13 @@ static struct block_device *add_partition(struct gendisk *disk, int partno,
 	const char *dname;
 	int err;
 
+	/*
+	 * disk_max_parts() won't be zero, either GENHD_FL_EXT_DEVT is set
+	 * or 'minors' is passed to alloc_disk().
+	 */
+	if (partno >= disk_max_parts(disk))
+		return ERR_PTR(-EINVAL);
+
 	/*
 	 * Partitions are not supported on zoned block devices that are used as
 	 * such.

From dbe1bdbb39db7dfe80a903f0d267f62cf3f093d2 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 25 Mar 2021 18:16:06 -0600
Subject: [PATCH 1343/1820] io_uring: handle signals for IO threads like a
 normal thread

We go through various hoops to disallow signals for the IO threads, but
there's really no reason why we cannot just allow them. The IO threads
never return to userspace like a normal thread, and hence don't go through
normal signal processing. Instead, just check for a pending signal as part
of the work loop, and call get_signal() to handle it for us if anything
is pending.

With that, we can support receiving signals, including special ones like
SIGSTOP.

Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c    | 20 ++++++++++++++------
 fs/io_uring.c |  9 ++++++---
 2 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index b7c1fa932cb3..7434eb40ca8c 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -16,7 +16,6 @@
 #include <linux/rculist_nulls.h>
 #include <linux/cpu.h>
 #include <linux/tracehook.h>
-#include <linux/freezer.h>
 
 #include "../kernel/sched/sched.h"
 #include "io-wq.h"
@@ -503,10 +502,15 @@ loop:
 		if (io_flush_signals())
 			continue;
 		ret = schedule_timeout(WORKER_IDLE_TIMEOUT);
-		if (try_to_freeze() || ret)
-			continue;
-		if (fatal_signal_pending(current))
+		if (signal_pending(current)) {
+			struct ksignal ksig;
+
+			if (!get_signal(&ksig))
+				continue;
 			break;
+		}
+		if (ret)
+			continue;
 		/* timed out, exit unless we're the fixed worker */
 		if (test_bit(IO_WQ_BIT_EXIT, &wq->state) ||
 		    !(worker->flags & IO_WORKER_F_FIXED))
@@ -714,9 +718,13 @@ static int io_wq_manager(void *data)
 		set_current_state(TASK_INTERRUPTIBLE);
 		io_wq_check_workers(wq);
 		schedule_timeout(HZ);
-		try_to_freeze();
-		if (fatal_signal_pending(current))
+		if (signal_pending(current)) {
+			struct ksignal ksig;
+
+			if (!get_signal(&ksig))
+				continue;
 			set_bit(IO_WQ_BIT_EXIT, &wq->state);
+		}
 	} while (!test_bit(IO_WQ_BIT_EXIT, &wq->state));
 
 	io_wq_check_workers(wq);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 54ea561db4a5..2d43f7b87083 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -78,7 +78,6 @@
 #include <linux/task_work.h>
 #include <linux/pagemap.h>
 #include <linux/io_uring.h>
-#include <linux/freezer.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -6765,8 +6764,13 @@ static int io_sq_thread(void *data)
 			timeout = jiffies + sqd->sq_thread_idle;
 			continue;
 		}
-		if (fatal_signal_pending(current))
+		if (signal_pending(current)) {
+			struct ksignal ksig;
+
+			if (!get_signal(&ksig))
+				continue;
 			break;
+		}
 		sqt_spin = false;
 		cap_entries = !list_is_singular(&sqd->ctx_list);
 		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
@@ -6809,7 +6813,6 @@ static int io_sq_thread(void *data)
 
 			mutex_unlock(&sqd->lock);
 			schedule();
-			try_to_freeze();
 			mutex_lock(&sqd->lock);
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				io_ring_clear_wakeup_flag(ctx);

From b16b3855d89fba640996fefdd3a113c0aa0e380d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 26 Mar 2021 09:05:22 -0600
Subject: [PATCH 1344/1820] kernel: stop masking signals in create_io_thread()

This is racy - move the blocking into when the task is created and
we're marking it as PF_IO_WORKER anyway. The IO threads are now
prepared to handle signals like SIGSTOP as well, so clear that from
the mask to allow proper stopping of IO threads.

Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Reported-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/fork.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index d3171e8e88e5..ddaa15227071 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1940,8 +1940,14 @@ static __latent_entropy struct task_struct *copy_process(
 	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
-	if (args->io_thread)
+	if (args->io_thread) {
+		/*
+		 * Mark us an IO worker, and block any signal that isn't
+		 * fatal or STOP
+		 */
 		p->flags |= PF_IO_WORKER;
+		siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
+	}
 
 	/*
 	 * This _must_ happen before we call free_task(), i.e. before we jump
@@ -2430,14 +2436,8 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 		.stack_size	= (unsigned long)arg,
 		.io_thread	= 1,
 	};
-	struct task_struct *tsk;
 
-	tsk = copy_process(NULL, 0, node, &args);
-	if (!IS_ERR(tsk)) {
-		sigfillset(&tsk->blocked);
-		sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
-	}
-	return tsk;
+	return copy_process(NULL, 0, node, &args);
 }
 
 /*

From 5a842a7448bbfa9bda0a74ca4f239c1b02bb98d8 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 25 Mar 2021 18:18:15 -0600
Subject: [PATCH 1345/1820] Revert "signal: don't allow sending any signals to
 PF_IO_WORKER threads"

This reverts commit 5be28c8f85ce99ed2d329d2ad8bdd18ea19473a5.

IO threads now take signals just fine, so there's no reason to limit them
specifically. Revert the change that prevented that from happening.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/signal.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/kernel/signal.c b/kernel/signal.c
index d22177d37b21..9e172b9341f4 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -834,9 +834,6 @@ static int check_kill_permission(int sig, struct kernel_siginfo *info,
 
 	if (!valid_signal(sig))
 		return -EINVAL;
-	/* PF_IO_WORKER threads don't take any signals */
-	if (t->flags & PF_IO_WORKER)
-		return -ESRCH;
 
 	if (!si_fromuser(info))
 		return 0;

From e8b33b8cfafcfcef287ae4c0f23a173bfcf617f3 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 25 Mar 2021 18:18:59 -0600
Subject: [PATCH 1346/1820] Revert "kernel: treat PF_IO_WORKER like PF_KTHREAD
 for ptrace/signals"

This reverts commit 6fb8f43cede0e4bd3ead847de78d531424a96be9.

The IO threads do allow signals now, including SIGSTOP, and we can allow
ptrace attach. Attaching won't reveal anything interesting for the IO
threads, but it will allow eg gdb to attach to a task with io_urings
and IO threads without complaining. And once attached, it will allow
the usual introspection into regular threads.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/ptrace.c | 2 +-
 kernel/signal.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 821cf1723814..61db50f7ca86 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -375,7 +375,7 @@ static int ptrace_attach(struct task_struct *task, long request,
 	audit_ptrace(task);
 
 	retval = -EPERM;
-	if (unlikely(task->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if (unlikely(task->flags & PF_KTHREAD))
 		goto out;
 	if (same_thread_group(task, current))
 		goto out;
diff --git a/kernel/signal.c b/kernel/signal.c
index 9e172b9341f4..dd86841cce94 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -91,7 +91,7 @@ static bool sig_task_ignored(struct task_struct *t, int sig, bool force)
 		return true;
 
 	/* Only allow kernel generated signals to this kthread */
-	if (unlikely((t->flags & (PF_KTHREAD | PF_IO_WORKER)) &&
+	if (unlikely((t->flags & PF_KTHREAD) &&
 		     (handler == SIG_KTHREAD_KERNEL) && !force))
 		return true;
 
@@ -1097,7 +1097,7 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc
 	/*
 	 * Skip useless siginfo allocation for SIGKILL and kernel threads.
 	 */
-	if ((sig == SIGKILL) || (t->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if ((sig == SIGKILL) || (t->flags & PF_KTHREAD))
 		goto out_set;
 
 	/*

From d3dc04cd81e0eaf50b2d09ab051a13300e587439 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 25 Mar 2021 18:22:11 -0600
Subject: [PATCH 1347/1820] Revert "kernel: freezer should treat PF_IO_WORKER
 like PF_KTHREAD for freezing"

This reverts commit 15b2219facadec583c24523eed40fa45865f859f.

Before IO threads accepted signals, the freezer using take signals to wake
up an IO thread would cause them to loop without any way to clear the
pending signal. That is no longer the case, so stop special casing
PF_IO_WORKER in the freezer.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/freezer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/freezer.c b/kernel/freezer.c
index 1a2d57d1327c..dc520f01f99d 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -134,7 +134,7 @@ bool freeze_task(struct task_struct *p)
 		return false;
 	}
 
-	if (!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if (!(p->flags & PF_KTHREAD))
 		fake_signal_wake_up(p);
 	else
 		wake_up_state(p, TASK_INTERRUPTIBLE);

From 1e4cf0d3d072173ee70757ee4aec11b2839705f9 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 25 Mar 2021 18:23:44 -0600
Subject: [PATCH 1348/1820] Revert "signal: don't allow STOP on PF_IO_WORKER
 threads"

This reverts commit 4db4b1a0d1779dc159f7b87feb97030ec0b12597.

The IO threads allow and handle SIGSTOP now, so don't special case them
anymore in task_set_jobctl_pending().

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/signal.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/signal.c b/kernel/signal.c
index dd86841cce94..f2718350bf4b 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -288,8 +288,7 @@ bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask)
 			JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING));
 	BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK));
 
-	if (unlikely(fatal_signal_pending(task) ||
-		     (task->flags & (PF_EXITING | PF_IO_WORKER))))
+	if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING)))
 		return false;
 
 	if (mask & JOBCTL_STOP_SIGMASK)

From 1ee4160c73b2102a52bc97a4128a89c34821414f Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 25 Mar 2021 18:32:42 +0000
Subject: [PATCH 1349/1820] io_uring: fix timeout cancel return code

When we cancel a timeout we should emit a sensible return code, like
-ECANCELED but not 0, otherwise it may trick users.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/7b0ad1065e3bd1994722702bd0ba9e7bc9b0683b.1616696997.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2d43f7b87083..229ab9bfb45b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1247,7 +1247,7 @@ static void io_queue_async_work(struct io_kiocb *req)
 		io_queue_linked_timeout(link);
 }
 
-static void io_kill_timeout(struct io_kiocb *req)
+static void io_kill_timeout(struct io_kiocb *req, int status)
 {
 	struct io_timeout_data *io = req->async_data;
 	int ret;
@@ -1257,7 +1257,7 @@ static void io_kill_timeout(struct io_kiocb *req)
 		atomic_set(&req->ctx->cq_timeouts,
 			atomic_read(&req->ctx->cq_timeouts) + 1);
 		list_del_init(&req->timeout.list);
-		io_cqring_fill_event(req, 0);
+		io_cqring_fill_event(req, status);
 		io_put_req_deferred(req, 1);
 	}
 }
@@ -1274,7 +1274,7 @@ static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
 	spin_lock_irq(&ctx->completion_lock);
 	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
 		if (io_match_task(req, tsk, files)) {
-			io_kill_timeout(req);
+			io_kill_timeout(req, -ECANCELED);
 			canceled++;
 		}
 	}
@@ -1326,7 +1326,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 			break;
 
 		list_del_init(&req->timeout.list);
-		io_kill_timeout(req);
+		io_kill_timeout(req, 0);
 	} while (!list_empty(&ctx->timeout_list));
 
 	ctx->cq_last_tm_flush = seq;

From 80c4cbdb5ee604712e59fe304d7bf084b562f705 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 25 Mar 2021 18:32:43 +0000
Subject: [PATCH 1350/1820] io_uring: do post-completion chore on t-out cancel

Don't forget about io_commit_cqring() + io_cqring_ev_posted() after
exit/exec cancelling timeouts. Both functions declared only after
io_kill_timeouts(), so to avoid tons of forward declarations move
it down.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/72ace588772c0f14834a6a4185d56c445a366fb4.1616696997.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 42 ++++++++++++++++++++++--------------------
 1 file changed, 22 insertions(+), 20 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 229ab9bfb45b..8498f74595f3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1262,26 +1262,6 @@ static void io_kill_timeout(struct io_kiocb *req, int status)
 	}
 }
 
-/*
- * Returns true if we found and killed one or more timeouts
- */
-static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
-			     struct files_struct *files)
-{
-	struct io_kiocb *req, *tmp;
-	int canceled = 0;
-
-	spin_lock_irq(&ctx->completion_lock);
-	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
-		if (io_match_task(req, tsk, files)) {
-			io_kill_timeout(req, -ECANCELED);
-			canceled++;
-		}
-	}
-	spin_unlock_irq(&ctx->completion_lock);
-	return canceled != 0;
-}
-
 static void __io_queue_deferred(struct io_ring_ctx *ctx)
 {
 	do {
@@ -8611,6 +8591,28 @@ static void io_ring_exit_work(struct work_struct *work)
 	io_ring_ctx_free(ctx);
 }
 
+/* Returns true if we found and killed one or more timeouts */
+static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
+			     struct files_struct *files)
+{
+	struct io_kiocb *req, *tmp;
+	int canceled = 0;
+
+	spin_lock_irq(&ctx->completion_lock);
+	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
+		if (io_match_task(req, tsk, files)) {
+			io_kill_timeout(req, -ECANCELED);
+			canceled++;
+		}
+	}
+	io_commit_cqring(ctx);
+	spin_unlock_irq(&ctx->completion_lock);
+
+	if (canceled != 0)
+		io_cqring_ev_posted(ctx);
+	return canceled != 0;
+}
+
 static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 {
 	unsigned long index;

From 2482b58ffbdc80cfaae969ad19cb32803056505b Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 25 Mar 2021 18:32:44 +0000
Subject: [PATCH 1351/1820] io_uring: don't cancel-track common timeouts

Don't account usual timeouts (i.e. not linked) as REQ_F_INFLIGHT but
keep behaviour prior to dd59a3d595cc1 ("io_uring: reliably cancel linked
timeouts").

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/104441ef5d97e3932113d44501fda0df88656b83.1616696997.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 8498f74595f3..87d198d223a2 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -5563,7 +5563,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 
 	data->mode = io_translate_timeout_mode(flags);
 	hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode);
-	io_req_track_inflight(req);
+	if (is_timeout_link)
+		io_req_track_inflight(req);
 	return 0;
 }
 

From 78d9d7c2a331fb7a68a86e53ef7e12966459e0c5 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 25 Mar 2021 18:32:45 +0000
Subject: [PATCH 1352/1820] io_uring: don't cancel extra on files match

As tasks always wait and kill their io-wq on exec/exit, files are of no
more concern to us, so we don't need to specifically cancel them by hand
in those cases. Moreover we should not, because io_match_task() looks at
req->task->files now, which is always true and so leads to extra
cancellations, that wasn't a case before per-task io-wq.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/0566c1de9b9dd417f5de345c817ca953580e0e2e.1616696997.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 87d198d223a2..880abd8b6d31 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1094,8 +1094,6 @@ static bool io_match_task(struct io_kiocb *head,
 	io_for_each_link(req, head) {
 		if (req->flags & REQ_F_INFLIGHT)
 			return true;
-		if (req->task->files == files)
-			return true;
 	}
 	return false;
 }

From 2b8ed1c94182dbbd0163d0eb443a934cbf6b0d85 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 26 Mar 2021 19:52:51 +0000
Subject: [PATCH 1353/1820] io_uring: remove unsued assignment to pointer io

There is an assignment to io that is never read after the assignment,
the assignment is redundant and can be removed.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 880abd8b6d31..1949b80677e7 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4798,7 +4798,6 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags)
 			ret = -ENOMEM;
 			goto out;
 		}
-		io = req->async_data;
 		memcpy(req->async_data, &__io, sizeof(__io));
 		return -EAGAIN;
 	}

From 4e53d1701b574b1ee9d500b4913a1ece2fac8911 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 26 Mar 2021 10:05:25 -0600
Subject: [PATCH 1354/1820] tomoyo: don't special case PF_IO_WORKER for
 PF_KTHREAD

Since commit 3bfe6106693b6b4b ("io-wq: fork worker threads from original
task") stopped using PF_KTHREAD flag for the io_uring PF_IO_WORKER threads,
tomoyo_kernel_service() no longer needs to check PF_IO_WORKER flag.

(This is a 5.12+ patch. Please don't send to stable kernels.)

Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
---
 security/tomoyo/network.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/tomoyo/network.c b/security/tomoyo/network.c
index 478f757ff843..8dc61335f65e 100644
--- a/security/tomoyo/network.c
+++ b/security/tomoyo/network.c
@@ -613,7 +613,7 @@ static int tomoyo_check_unix_address(struct sockaddr *addr,
 static bool tomoyo_kernel_service(void)
 {
 	/* Nothing to do if I am a kernel service. */
-	return (current->flags & (PF_KTHREAD | PF_IO_WORKER)) == PF_KTHREAD;
+	return current->flags & PF_KTHREAD;
 }
 
 /**

From 781bab3238c21c8cc6d1999a6ee43de76252fdfd Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Fri, 26 Mar 2021 15:19:27 -0700
Subject: [PATCH 1355/1820] Input: elants_i2c - fix division by zero if
 firmware reports zero phys size

Touchscreen firmware of ASUS Transformer TF700T reports zeros for the phys
size. Hence check whether the size is zero and don't set the resolution in
this case.

Reported-by: Jasper Korten <jja2000@gmail.com>
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210302100824.3423-1-digetx@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/elants_i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c
index 4c2b579f6c8b..78172c31529a 100644
--- a/drivers/input/touchscreen/elants_i2c.c
+++ b/drivers/input/touchscreen/elants_i2c.c
@@ -1441,7 +1441,7 @@ static int elants_i2c_probe(struct i2c_client *client,
 
 	touchscreen_parse_properties(ts->input, true, &ts->prop);
 
-	if (ts->chip_id == EKTF3624) {
+	if (ts->chip_id == EKTF3624 && ts->phy_x && ts->phy_y) {
 		/* calculate resolution from size */
 		ts->x_res = DIV_ROUND_CLOSEST(ts->prop.max_x, ts->phy_x);
 		ts->y_res = DIV_ROUND_CLOSEST(ts->prop.max_y, ts->phy_y);

From 84d572e634e28827d105746c922d8ada425e2d8b Mon Sep 17 00:00:00 2001
From: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Thu, 25 Mar 2021 09:41:52 -0400
Subject: [PATCH 1356/1820] MAINTAINERS: add backups for s390 vfio drivers

Add a backup for s390 vfio-pci, an additional backup for vfio-ccw
and replace the backup for vfio-ap as Pierre is focusing on other
areas.

Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Acked-by: Eric Farman <farman@linux.ibm.com>
Acked-by: Halil Pasic <pasic@linux.ibm.com>
Acked-by: Pierre Morel <pmorel@linux.ibm.com>
Acked-by: Jason J. Herne <jjherne@linux.ibm.com>
Link: https://lore.kernel.org/r/1616679712-7139-1-git-send-email-mjrosato@linux.ibm.com
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 MAINTAINERS | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 9e876927c60d..68a562374b85 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15634,8 +15634,8 @@ F:	Documentation/s390/pci.rst
 
 S390 VFIO AP DRIVER
 M:	Tony Krowiak <akrowiak@linux.ibm.com>
-M:	Pierre Morel <pmorel@linux.ibm.com>
 M:	Halil Pasic <pasic@linux.ibm.com>
+M:	Jason Herne <jjherne@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
 W:	http://www.ibm.com/developerworks/linux/linux390/
@@ -15647,6 +15647,7 @@ F:	drivers/s390/crypto/vfio_ap_private.h
 S390 VFIO-CCW DRIVER
 M:	Cornelia Huck <cohuck@redhat.com>
 M:	Eric Farman <farman@linux.ibm.com>
+M:	Matthew Rosato <mjrosato@linux.ibm.com>
 R:	Halil Pasic <pasic@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	kvm@vger.kernel.org
@@ -15657,6 +15658,7 @@ F:	include/uapi/linux/vfio_ccw.h
 
 S390 VFIO-PCI DRIVER
 M:	Matthew Rosato <mjrosato@linux.ibm.com>
+M:	Eric Farman <farman@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	kvm@vger.kernel.org
 S:	Supported

From a5e13c6df0e41702d2b2c77c8ad41677ebb065b3 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 28 Mar 2021 15:48:16 -0700
Subject: [PATCH 1357/1820] Linux 5.12-rc5

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index d4784d181123..73add16f9898 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Frozen Wasteland
 
 # *DOCUMENTATION*

From 5a978dcfc0f054e4f6983a0a26355a65e34708cb Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sat, 27 Mar 2021 09:59:30 +0000
Subject: [PATCH 1358/1820] io_uring: always go for cancellation spin on exec

Always try to do cancellation in __io_uring_task_cancel() at least once,
so it actually goes and cleans its sqpoll tasks (i.e. via
io_sqpoll_cancel_sync()), otherwise sqpoll task may submit new requests
after cancellation and it's racy for many reasons.

Fixes: 521d6a737a31c ("io_uring: cancel sqpoll via task_work")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/0a21bd6d794bb1629bc906dd57a57b2c2985a8ac.1616839147.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 1949b80677e7..a4a944da95a0 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -9002,6 +9002,8 @@ void __io_uring_task_cancel(void)
 
 	/* make sure overflow events are dropped */
 	atomic_inc(&tctx->in_idle);
+	__io_uring_files_cancel(NULL);
+
 	do {
 		/* read completions before cancelations */
 		inflight = tctx_inflight(tctx);

From 1b479fb801602b22512f53c19b1f93a4fc5d5d9d Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Sun, 28 Mar 2021 00:50:08 -0700
Subject: [PATCH 1359/1820] drivers/net/wan/hdlc_fr: Fix a double free in
 pvc_xmit

In pvc_xmit, if __skb_pad(skb, pad, false) failed, it will free
the skb in the first time and goto drop. But the same skb is freed
by kfree_skb(skb) in the second time in drop.

Maintaining the original function unchanged, my patch adds a new
label out to avoid the double free if __skb_pad() failed.

Fixes: f5083d0cee08a ("drivers/net/wan/hdlc_fr: Improvements to the code of pvc_xmit")
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/hdlc_fr.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index 0720f5f92caa..4d9dc7d15908 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -415,7 +415,7 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		if (pad > 0) { /* Pad the frame with zeros */
 			if (__skb_pad(skb, pad, false))
-				goto drop;
+				goto out;
 			skb_put(skb, pad);
 		}
 	}
@@ -448,8 +448,9 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 
 drop:
-	dev->stats.tx_dropped++;
 	kfree_skb(skb);
+out:
+	dev->stats.tx_dropped++;
 	return NETDEV_TX_OK;
 }
 

From 5cfad4f45806f6f898b63b8c77cea7452c704cb3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Oliver=20St=C3=A4bler?= <oliver.staebler@bytesatwork.ch>
Date: Wed, 24 Mar 2021 14:28:41 +0100
Subject: [PATCH 1360/1820] arm64: dts: imx8mm/q: Fix pad control of SD1_DATA0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix address of the pad control register
(IOMUXC_SW_PAD_CTL_PAD_SD1_DATA0) for SD1_DATA0_GPIO2_IO2.  This seems
to be a typo but it leads to an exception when pinctrl is applied due to
wrong memory address access.

Signed-off-by: Oliver Stäbler <oliver.staebler@bytesatwork.ch>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Acked-by: Rob Herring <robh@kernel.org>
Fixes: c1c9d41319c3 ("dt-bindings: imx: Add pinctrl binding doc for imx8mm")
Fixes: 748f908cc882 ("arm64: add basic DTS for i.MX8MQ")
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h | 2 +-
 arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h
index 5ccc4cc91959..a003e6af3353 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h
+++ b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h
@@ -124,7 +124,7 @@
 #define MX8MM_IOMUXC_SD1_CMD_USDHC1_CMD                                     0x0A4 0x30C 0x000 0x0 0x0
 #define MX8MM_IOMUXC_SD1_CMD_GPIO2_IO1                                      0x0A4 0x30C 0x000 0x5 0x0
 #define MX8MM_IOMUXC_SD1_DATA0_USDHC1_DATA0                                 0x0A8 0x310 0x000 0x0 0x0
-#define MX8MM_IOMUXC_SD1_DATA0_GPIO2_IO2                                    0x0A8 0x31  0x000 0x5 0x0
+#define MX8MM_IOMUXC_SD1_DATA0_GPIO2_IO2                                    0x0A8 0x310 0x000 0x5 0x0
 #define MX8MM_IOMUXC_SD1_DATA1_USDHC1_DATA1                                 0x0AC 0x314 0x000 0x0 0x0
 #define MX8MM_IOMUXC_SD1_DATA1_GPIO2_IO3                                    0x0AC 0x314 0x000 0x5 0x0
 #define MX8MM_IOMUXC_SD1_DATA2_USDHC1_DATA2                                 0x0B0 0x318 0x000 0x0 0x0
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h
index b94b02080a34..68e8fa172974 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h
+++ b/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h
@@ -130,7 +130,7 @@
 #define MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD                                     0x0A4 0x30C 0x000 0x0 0x0
 #define MX8MQ_IOMUXC_SD1_CMD_GPIO2_IO1                                      0x0A4 0x30C 0x000 0x5 0x0
 #define MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0                                 0x0A8 0x310 0x000 0x0 0x0
-#define MX8MQ_IOMUXC_SD1_DATA0_GPIO2_IO2                                    0x0A8 0x31  0x000 0x5 0x0
+#define MX8MQ_IOMUXC_SD1_DATA0_GPIO2_IO2                                    0x0A8 0x310 0x000 0x5 0x0
 #define MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1                                 0x0AC 0x314 0x000 0x0 0x0
 #define MX8MQ_IOMUXC_SD1_DATA1_GPIO2_IO3                                    0x0AC 0x314 0x000 0x5 0x0
 #define MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2                                 0x0B0 0x318 0x000 0x0 0x0

From 56cfe6f820a6315291eb5a1b82bb49633b993d3b Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Sun, 28 Mar 2021 22:57:48 -0700
Subject: [PATCH 1361/1820] Input: elants_i2c - drop zero-checking of
 ABS_MT_TOUCH_MAJOR resolution

Drop unnecessary zero-checking of ABS_MT_TOUCH_MAJOR resolution since
there is no difference between setting resolution to 0 vs not setting
it at all. This change makes code cleaner a tad.

Suggested-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210328235507.19240-1-digetx@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/elants_i2c.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c
index 78172c31529a..5f7706febcb0 100644
--- a/drivers/input/touchscreen/elants_i2c.c
+++ b/drivers/input/touchscreen/elants_i2c.c
@@ -1449,8 +1449,7 @@ static int elants_i2c_probe(struct i2c_client *client,
 
 	input_abs_set_res(ts->input, ABS_MT_POSITION_X, ts->x_res);
 	input_abs_set_res(ts->input, ABS_MT_POSITION_Y, ts->y_res);
-	if (ts->major_res > 0)
-		input_abs_set_res(ts->input, ABS_MT_TOUCH_MAJOR, ts->major_res);
+	input_abs_set_res(ts->input, ABS_MT_TOUCH_MAJOR, ts->major_res);
 
 	error = input_mt_init_slots(ts->input, MAX_CONTACT_NUM,
 				    INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED);

From c7dbf4c08868d9db89b8bfe8f8245ca61b01ed2f Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Fri, 26 Mar 2021 09:44:48 +0100
Subject: [PATCH 1362/1820] xfrm: Provide private skb extensions for segmented
 and hw offloaded ESP packets

Commit 94579ac3f6d0 ("xfrm: Fix double ESP trailer insertion in IPsec
crypto offload.") added a XFRM_XMIT flag to avoid duplicate ESP trailer
insertion on HW offload. This flag is set on the secpath that is shared
amongst segments. This lead to a situation where some segments are
not transformed correctly when segmentation happens at layer 3.

Fix this by using private skb extensions for segmented and hw offloaded
ESP packets.

Fixes: 94579ac3f6d0 ("xfrm: Fix double ESP trailer insertion in IPsec crypto offload.")
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv4/esp4_offload.c | 11 ++++++++++-
 net/ipv6/esp6_offload.c | 11 ++++++++++-
 net/xfrm/xfrm_device.c  |  2 --
 3 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index ed3de486ea34..33687cf58286 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -314,8 +314,17 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_
 	ip_hdr(skb)->tot_len = htons(skb->len);
 	ip_send_check(ip_hdr(skb));
 
-	if (hw_offload)
+	if (hw_offload) {
+		if (!skb_ext_add(skb, SKB_EXT_SEC_PATH))
+			return -ENOMEM;
+
+		xo = xfrm_offload(skb);
+		if (!xo)
+			return -EINVAL;
+
+		xo->flags |= XFRM_XMIT;
 		return 0;
+	}
 
 	err = esp_output_tail(x, skb, &esp);
 	if (err)
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index f35203ab39f5..4af56affaafd 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -348,8 +348,17 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features
 
 	ipv6_hdr(skb)->payload_len = htons(len);
 
-	if (hw_offload)
+	if (hw_offload) {
+		if (!skb_ext_add(skb, SKB_EXT_SEC_PATH))
+			return -ENOMEM;
+
+		xo = xfrm_offload(skb);
+		if (!xo)
+			return -EINVAL;
+
+		xo->flags |= XFRM_XMIT;
 		return 0;
+	}
 
 	err = esp6_output_tail(x, skb, &esp);
 	if (err)
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index edf11893dbe8..6d6917b68856 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -134,8 +134,6 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 		return skb;
 	}
 
-	xo->flags |= XFRM_XMIT;
-
 	if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) {
 		struct sk_buff *segs;
 

From 9e9714742fb70467464359693a73b911a630226f Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Thu, 25 Mar 2021 13:58:48 +0100
Subject: [PATCH 1363/1820] can: bcm/raw: fix msg_namelen values depending on
 CAN_REQUIRED_SIZE

Since commit f5223e9eee65 ("can: extend sockaddr_can to include j1939
members") the sockaddr_can has been extended in size and a new
CAN_REQUIRED_SIZE macro has been introduced to calculate the protocol
specific needed size.

The ABI for the msg_name and msg_namelen has not been adapted to the
new CAN_REQUIRED_SIZE macro for the other CAN protocols which leads to
a problem when an existing binary reads the (increased) struct
sockaddr_can in msg_name.

Fixes: f5223e9eee65 ("can: extend sockaddr_can to include j1939 members")
Reported-by: Richard Weinberger <richard@nod.at>
Tested-by: Richard Weinberger <richard@nod.at>
Acked-by: Kurt Van Dijck <dev.kurt@vandijck-laurijssen.be>
Link: https://lore.kernel.org/linux-can/1135648123.112255.1616613706554.JavaMail.zimbra@nod.at/T/#t
Link: https://lore.kernel.org/r/20210325125850.1620-1-socketcan@hartkopp.net
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 10 ++++++----
 net/can/raw.c | 14 ++++++++------
 2 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index 0e5c37be4a2b..909b9e684e04 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -86,6 +86,8 @@ MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>");
 MODULE_ALIAS("can-proto-2");
 
+#define BCM_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex)
+
 /*
  * easy access to the first 64 bit of can(fd)_frame payload. cp->data is
  * 64 bit aligned so the offset has to be multiples of 8 which is ensured
@@ -1292,7 +1294,7 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		/* no bound device as default => check msg_name */
 		DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name);
 
-		if (msg->msg_namelen < CAN_REQUIRED_SIZE(*addr, can_ifindex))
+		if (msg->msg_namelen < BCM_MIN_NAMELEN)
 			return -EINVAL;
 
 		if (addr->can_family != AF_CAN)
@@ -1534,7 +1536,7 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
 	struct net *net = sock_net(sk);
 	int ret = 0;
 
-	if (len < CAN_REQUIRED_SIZE(*addr, can_ifindex))
+	if (len < BCM_MIN_NAMELEN)
 		return -EINVAL;
 
 	lock_sock(sk);
@@ -1616,8 +1618,8 @@ static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (msg->msg_name) {
-		__sockaddr_check_size(sizeof(struct sockaddr_can));
-		msg->msg_namelen = sizeof(struct sockaddr_can);
+		__sockaddr_check_size(BCM_MIN_NAMELEN);
+		msg->msg_namelen = BCM_MIN_NAMELEN;
 		memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
 	}
 
diff --git a/net/can/raw.c b/net/can/raw.c
index 37b47a39a3ed..139d9471ddcf 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -60,6 +60,8 @@ MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>");
 MODULE_ALIAS("can-proto-1");
 
+#define RAW_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex)
+
 #define MASK_ALL 0
 
 /* A raw socket has a list of can_filters attached to it, each receiving
@@ -394,7 +396,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	int err = 0;
 	int notify_enetdown = 0;
 
-	if (len < CAN_REQUIRED_SIZE(*addr, can_ifindex))
+	if (len < RAW_MIN_NAMELEN)
 		return -EINVAL;
 	if (addr->can_family != AF_CAN)
 		return -EINVAL;
@@ -475,11 +477,11 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr,
 	if (peer)
 		return -EOPNOTSUPP;
 
-	memset(addr, 0, sizeof(*addr));
+	memset(addr, 0, RAW_MIN_NAMELEN);
 	addr->can_family  = AF_CAN;
 	addr->can_ifindex = ro->ifindex;
 
-	return sizeof(*addr);
+	return RAW_MIN_NAMELEN;
 }
 
 static int raw_setsockopt(struct socket *sock, int level, int optname,
@@ -739,7 +741,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	if (msg->msg_name) {
 		DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name);
 
-		if (msg->msg_namelen < CAN_REQUIRED_SIZE(*addr, can_ifindex))
+		if (msg->msg_namelen < RAW_MIN_NAMELEN)
 			return -EINVAL;
 
 		if (addr->can_family != AF_CAN)
@@ -832,8 +834,8 @@ static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (msg->msg_name) {
-		__sockaddr_check_size(sizeof(struct sockaddr_can));
-		msg->msg_namelen = sizeof(struct sockaddr_can);
+		__sockaddr_check_size(RAW_MIN_NAMELEN);
+		msg->msg_namelen = RAW_MIN_NAMELEN;
 		memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
 	}
 

From f522d9559b07854c231cf8f0b8cb5a3578f8b44e Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Thu, 25 Mar 2021 13:58:49 +0100
Subject: [PATCH 1364/1820] can: isotp: fix msg_namelen values depending on
 CAN_REQUIRED_SIZE

Since commit f5223e9eee65 ("can: extend sockaddr_can to include j1939
members") the sockaddr_can has been extended in size and a new
CAN_REQUIRED_SIZE macro has been introduced to calculate the protocol
specific needed size.

The ABI for the msg_name and msg_namelen has not been adapted to the
new CAN_REQUIRED_SIZE macro for the other CAN protocols which leads to
a problem when an existing binary reads the (increased) struct
sockaddr_can in msg_name.

Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol")
Reported-by: Richard Weinberger <richard@nod.at>
Acked-by: Kurt Van Dijck <dev.kurt@vandijck-laurijssen.be>
Link: https://lore.kernel.org/linux-can/1135648123.112255.1616613706554.JavaMail.zimbra@nod.at/T/#t
Link: https://lore.kernel.org/r/20210325125850.1620-2-socketcan@hartkopp.net
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/isotp.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/can/isotp.c b/net/can/isotp.c
index 15ea1234d457..9f94ad3caee9 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -77,6 +77,8 @@ MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>");
 MODULE_ALIAS("can-proto-6");
 
+#define ISOTP_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp)
+
 #define SINGLE_MASK(id) (((id) & CAN_EFF_FLAG) ? \
 			 (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
 			 (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
@@ -986,7 +988,8 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	sock_recv_timestamp(msg, sk, skb);
 
 	if (msg->msg_name) {
-		msg->msg_namelen = sizeof(struct sockaddr_can);
+		__sockaddr_check_size(ISOTP_MIN_NAMELEN);
+		msg->msg_namelen = ISOTP_MIN_NAMELEN;
 		memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
 	}
 
@@ -1056,7 +1059,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	int notify_enetdown = 0;
 	int do_rx_reg = 1;
 
-	if (len < CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp))
+	if (len < ISOTP_MIN_NAMELEN)
 		return -EINVAL;
 
 	/* do not register frame reception for functional addressing */
@@ -1152,13 +1155,13 @@ static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 	if (peer)
 		return -EOPNOTSUPP;
 
-	memset(addr, 0, sizeof(*addr));
+	memset(addr, 0, ISOTP_MIN_NAMELEN);
 	addr->can_family = AF_CAN;
 	addr->can_ifindex = so->ifindex;
 	addr->can_addr.tp.rx_id = so->rxid;
 	addr->can_addr.tp.tx_id = so->txid;
 
-	return sizeof(*addr);
+	return ISOTP_MIN_NAMELEN;
 }
 
 static int isotp_setsockopt(struct socket *sock, int level, int optname,

From f5076c6ba02e8e24c61c40bbf48078929bc0fc79 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Mon, 22 Mar 2021 10:44:54 +0100
Subject: [PATCH 1365/1820] can: uapi: can.h: mark union inside struct
 can_frame packed

In commit ea7800565a12 ("can: add optional DLC element to Classical
CAN frame structure") the struct can_frame::can_dlc was put into an
anonymous union with another u8 variable.

For various reasons some members in struct can_frame and canfd_frame
including the first 8 byes of data are expected to have the same
memory layout. This is enforced by a BUILD_BUG_ON check in af_can.c.

Since the above mentioned commit this check fails on ARM kernels
compiled with the ARM OABI (which means CONFIG_AEABI not set). In this
case -mabi=apcs-gnu is passed to the compiler, which leads to a
structure size boundary of 32, instead of 8 compared to CONFIG_AEABI
enabled. This means the the union in struct can_frame takes 4 bytes
instead of the expected 1.

Rong Chen illustrates the problem with pahole in the ARM OABI case:

| struct can_frame {
|          canid_t                    can_id;               /* 0     4 */
|          union {
|                  __u8               len;                  /* 4     1 */
|                  __u8               can_dlc;              /* 4     1 */
|          };                                               /* 4     4 */
|          __u8                       __pad;                /* 8     1 */
|          __u8                       __res0;               /* 9     1 */
|          __u8                       len8_dlc;             /* 10    1 */
|
|          /* XXX 5 bytes hole, try to pack */
|
|          __u8                       data[8]
| __attribute__((__aligned__(8))); /*    16     8 */
|
|          /* size: 24, cachelines: 1, members: 6 */
|          /* sum members: 19, holes: 1, sum holes: 5 */
|          /* forced alignments: 1, forced holes: 1, sum forced holes: 5 */
|          /* last cacheline: 24 bytes */
| } __attribute__((__aligned__(8)));

Marking the anonymous union as __attribute__((packed)) fixes the
BUILD_BUG_ON problem on these compilers.

Fixes: ea7800565a12 ("can: add optional DLC element to Classical CAN frame structure")
Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Rong Chen <rong.a.chen@intel.com>
Link: https://lore.kernel.org/linux-can/2c82ec23-3551-61b5-1bd8-178c3407ee83@hartkopp.net/
Link: https://lore.kernel.org/r/20210325125850.1620-3-socketcan@hartkopp.net
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/uapi/linux/can.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
index f75238ac6dce..c7535352fef6 100644
--- a/include/uapi/linux/can.h
+++ b/include/uapi/linux/can.h
@@ -113,7 +113,7 @@ struct can_frame {
 		 */
 		__u8 len;
 		__u8 can_dlc; /* deprecated */
-	};
+	} __attribute__((packed)); /* disable padding added in some ABIs */
 	__u8 __pad; /* padding */
 	__u8 __res0; /* reserved / padding */
 	__u8 len8_dlc; /* optional DLC for 8 byte payload length (9 .. 15) */

From 6161a435c1910d07ee00cc25af010889010e1f08 Mon Sep 17 00:00:00 2001
From: Tian Tao <tiantao6@hisilicon.com>
Date: Mon, 15 Mar 2021 14:41:26 +0800
Subject: [PATCH 1366/1820] drm/exynos/decon5433: Remove the unused include
 statements

This driver doesn't reference of_gpio.h, so drop it.

Signed-off-by: Tian Tao <tiantao6@hisilicon.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos5433_drm_decon.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 1f79bc2a881e..1510e4e2973c 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -13,7 +13,6 @@
 #include <linux/irq.h>
 #include <linux/mfd/syscon.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>

From 625bd5a616ceda4840cd28f82e957c8ced394b6a Mon Sep 17 00:00:00 2001
From: Ikjoon Jang <ikjn@chromium.org>
Date: Wed, 24 Mar 2021 18:51:52 +0800
Subject: [PATCH 1367/1820] ALSA: usb-audio: Apply sample rate quirk to
 Logitech Connect

Logitech ConferenceCam Connect is a compound USB device with UVC and
UAC. Not 100% reproducible but sometimes it keeps responding STALL to
every control transfer once it receives get_freq request.

This patch adds 046d:0x084c to a snd_usb_get_sample_rate_quirk list.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203419
Signed-off-by: Ikjoon Jang <ikjn@chromium.org>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210324105153.2322881-1-ikjn@chromium.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index d3001fb18141..176437a441e6 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1521,6 +1521,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
 	case USB_ID(0x21b4, 0x0081): /* AudioQuest DragonFly */
 	case USB_ID(0x2912, 0x30c8): /* Audioengine D1 */
 	case USB_ID(0x413c, 0xa506): /* Dell AE515 sound bar */
+	case USB_ID(0x046d, 0x084c): /* Logitech ConferenceCam Connect */
 		return true;
 	}
 

From 51520426f4bc3e61cbbf7a39ccf4e411b665002d Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Mon, 29 Mar 2021 11:39:29 +0100
Subject: [PATCH 1368/1820] io_uring: handle setup-failed ctx in kill_timeouts

general protection fault, probably for non-canonical address
	0xdffffc0000000018: 0000 [#1] KASAN: null-ptr-deref
	in range [0x00000000000000c0-0x00000000000000c7]
RIP: 0010:io_commit_cqring+0x37f/0xc10 fs/io_uring.c:1318
Call Trace:
 io_kill_timeouts+0x2b5/0x320 fs/io_uring.c:8606
 io_ring_ctx_wait_and_kill+0x1da/0x400 fs/io_uring.c:8629
 io_uring_create fs/io_uring.c:9572 [inline]
 io_uring_setup+0x10da/0x2ae0 fs/io_uring.c:9599
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xae

It can get into wait_and_kill() before setting up ctx->rings, and hence
io_commit_cqring() fails. Mimic poll cancel and do it only when we
completed events, there can't be any requests if it failed before
initialising rings.

Fixes: 80c4cbdb5ee60 ("io_uring: do post-completion chore on t-out cancel")
Reported-by: syzbot+0e905eb8228070c457a0@syzkaller.appspotmail.com
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/660261a48f0e7abf260c8e43c87edab3c16736fa.1617014345.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index a4a944da95a0..088a9d3c420a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8603,9 +8603,9 @@ static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
 			canceled++;
 		}
 	}
-	io_commit_cqring(ctx);
+	if (canceled != 0)
+		io_commit_cqring(ctx);
 	spin_unlock_irq(&ctx->completion_lock);
-
 	if (canceled != 0)
 		io_cqring_ev_posted(ctx);
 	return canceled != 0;

From aa320c7cd45647b75af2233430d36a8d154703d4 Mon Sep 17 00:00:00 2001
From: kernel test robot <lkp@intel.com>
Date: Sun, 28 Mar 2021 16:54:45 +0200
Subject: [PATCH 1369/1820] ASoC: cygnus: fix for_each_child.cocci warnings

Function "for_each_available_child_of_node" should have of_node_put()
before return around line 1352.

Generated by: scripts/coccinelle/iterators/for_each_child.cocci

CC: Sumera Priyadarsini <sylphrenadin@gmail.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: kernel test robot <lkp@intel.com>
Signed-off-by: Julia Lawall <julia.lawall@inria.fr>
Link: https://lore.kernel.org/r/alpine.DEB.2.22.394.2103281651320.2854@hadrien
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/bcm/cygnus-ssp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/sound/soc/bcm/cygnus-ssp.c b/sound/soc/bcm/cygnus-ssp.c
index 6e634b448293..aa16a2375134 100644
--- a/sound/soc/bcm/cygnus-ssp.c
+++ b/sound/soc/bcm/cygnus-ssp.c
@@ -1348,8 +1348,10 @@ static int cygnus_ssp_probe(struct platform_device *pdev)
 					&cygnus_ssp_dai[active_port_count]);
 
 		/* negative is err, 0 is active and good, 1 is disabled */
-		if (err < 0)
+		if (err < 0) {
+			of_node_put(child_node);
 			return err;
+		}
 		else if (!err) {
 			dev_dbg(dev, "Activating DAI: %s\n",
 				cygnus_ssp_dai[active_port_count].name);

From 08771bce330036d473be6ce851cd00bcd351ebf6 Mon Sep 17 00:00:00 2001
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Date: Fri, 26 Feb 2021 13:19:22 -0800
Subject: [PATCH 1370/1820] ice: Continue probe on link/PHY errors

An incorrect NVM update procedure can result in the driver failing probe.
In this case, the recommended resolution method is to update the NVM
using the right procedure. However, if the driver fails probe, the user
will not be able to update the NVM. So do not fail probe on link/PHY
errors.

Fixes: 1a3571b5938c ("ice: restore PHY settings on media insertion")
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 2c23c8f468a5..53e053c997eb 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4192,28 +4192,25 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		goto err_send_version_unroll;
 	}
 
+	/* not a fatal error if this fails */
 	err = ice_init_nvm_phy_type(pf->hw.port_info);
-	if (err) {
+	if (err)
 		dev_err(dev, "ice_init_nvm_phy_type failed: %d\n", err);
-		goto err_send_version_unroll;
-	}
 
+	/* not a fatal error if this fails */
 	err = ice_update_link_info(pf->hw.port_info);
-	if (err) {
+	if (err)
 		dev_err(dev, "ice_update_link_info failed: %d\n", err);
-		goto err_send_version_unroll;
-	}
 
 	ice_init_link_dflt_override(pf->hw.port_info);
 
 	/* if media available, initialize PHY settings */
 	if (pf->hw.port_info->phy.link_info.link_info &
 	    ICE_AQ_MEDIA_AVAILABLE) {
+		/* not a fatal error if this fails */
 		err = ice_init_phy_user_cfg(pf->hw.port_info);
-		if (err) {
+		if (err)
 			dev_err(dev, "ice_init_phy_user_cfg failed: %d\n", err);
-			goto err_send_version_unroll;
-		}
 
 		if (!test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, pf->flags)) {
 			struct ice_vsi *vsi = ice_get_main_vsi(pf);

From f88c529ac77b3c21819d2cf1dfcfae1937849743 Mon Sep 17 00:00:00 2001
From: Fabio Pricoco <fabio.pricoco@intel.com>
Date: Fri, 26 Feb 2021 13:19:24 -0800
Subject: [PATCH 1371/1820] ice: Increase control queue timeout

250 msec timeout is insufficient for some AQ commands. Advice from FW
team was to increase the timeout. Increase to 1 second.

Fixes: 7ec59eeac804 ("ice: Add support for control queues")
Signed-off-by: Fabio Pricoco <fabio.pricoco@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_controlq.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h
index faaa08e8171b..68866f4f0eb0 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.h
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.h
@@ -31,8 +31,8 @@ enum ice_ctl_q {
 	ICE_CTL_Q_MAILBOX,
 };
 
-/* Control Queue timeout settings - max delay 250ms */
-#define ICE_CTL_Q_SQ_CMD_TIMEOUT	2500  /* Count 2500 times */
+/* Control Queue timeout settings - max delay 1s */
+#define ICE_CTL_Q_SQ_CMD_TIMEOUT	10000 /* Count 10000 times */
 #define ICE_CTL_Q_SQ_CMD_USEC		100   /* Check every 100usec */
 #define ICE_CTL_Q_ADMIN_INIT_TIMEOUT	10    /* Count 10 times */
 #define ICE_CTL_Q_ADMIN_INIT_MSEC	100   /* Check every 100msec */

From aeac8ce864d9c0836e12ed5b5cc80f62f3cccb7c Mon Sep 17 00:00:00 2001
From: Chinh T Cao <chinh.t.cao@intel.com>
Date: Fri, 26 Feb 2021 13:19:25 -0800
Subject: [PATCH 1372/1820] ice: Recognize 860 as iSCSI port in CEE mode

iSCSI can use both TCP ports 860 and 3260. However, in our current
implementation, the ice_aqc_opc_get_cee_dcb_cfg (0x0A07) AQ command
doesn't provide a way to communicate the protocol port number to the
AQ's caller. Thus, we assume that 3260 is the iSCSI port number at the
AQ's caller layer.

Rely on the dcbx-willing mode, desired QoS and remote QoS configuration to
determine which port number that iSCSI will use.

Fixes: 0ebd3ff13cca ("ice: Add code for DCB initialization part 2/4")
Signed-off-by: Chinh T Cao <chinh.t.cao@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_dcb.c  | 38 +++++++++++++++++------
 drivers/net/ethernet/intel/ice/ice_type.h |  1 +
 2 files changed, 30 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c
index e42727941ef5..211ac6f907ad 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.c
@@ -738,22 +738,27 @@ ice_aq_get_cee_dcb_cfg(struct ice_hw *hw,
 /**
  * ice_cee_to_dcb_cfg
  * @cee_cfg: pointer to CEE configuration struct
- * @dcbcfg: DCB configuration struct
+ * @pi: port information structure
  *
  * Convert CEE configuration from firmware to DCB configuration
  */
 static void
 ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg,
-		   struct ice_dcbx_cfg *dcbcfg)
+		   struct ice_port_info *pi)
 {
 	u32 status, tlv_status = le32_to_cpu(cee_cfg->tlv_status);
 	u32 ice_aqc_cee_status_mask, ice_aqc_cee_status_shift;
+	u8 i, j, err, sync, oper, app_index, ice_app_sel_type;
 	u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio);
-	u8 i, err, sync, oper, app_index, ice_app_sel_type;
 	u16 ice_aqc_cee_app_mask, ice_aqc_cee_app_shift;
+	struct ice_dcbx_cfg *cmp_dcbcfg, *dcbcfg;
 	u16 ice_app_prot_id_type;
 
-	/* CEE PG data to ETS config */
+	dcbcfg = &pi->qos_cfg.local_dcbx_cfg;
+	dcbcfg->dcbx_mode = ICE_DCBX_MODE_CEE;
+	dcbcfg->tlv_status = tlv_status;
+
+	/* CEE PG data */
 	dcbcfg->etscfg.maxtcs = cee_cfg->oper_num_tc;
 
 	/* Note that the FW creates the oper_prio_tc nibbles reversed
@@ -780,10 +785,16 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg,
 		}
 	}
 
-	/* CEE PFC data to ETS config */
+	/* CEE PFC data */
 	dcbcfg->pfc.pfcena = cee_cfg->oper_pfc_en;
 	dcbcfg->pfc.pfccap = ICE_MAX_TRAFFIC_CLASS;
 
+	/* CEE APP TLV data */
+	if (dcbcfg->app_mode == ICE_DCBX_APPS_NON_WILLING)
+		cmp_dcbcfg = &pi->qos_cfg.desired_dcbx_cfg;
+	else
+		cmp_dcbcfg = &pi->qos_cfg.remote_dcbx_cfg;
+
 	app_index = 0;
 	for (i = 0; i < 3; i++) {
 		if (i == 0) {
@@ -802,6 +813,18 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg,
 			ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_ISCSI_S;
 			ice_app_sel_type = ICE_APP_SEL_TCPIP;
 			ice_app_prot_id_type = ICE_APP_PROT_ID_ISCSI;
+
+			for (j = 0; j < cmp_dcbcfg->numapps; j++) {
+				u16 prot_id = cmp_dcbcfg->app[j].prot_id;
+				u8 sel = cmp_dcbcfg->app[j].selector;
+
+				if  (sel == ICE_APP_SEL_TCPIP &&
+				     (prot_id == ICE_APP_PROT_ID_ISCSI ||
+				      prot_id == ICE_APP_PROT_ID_ISCSI_860)) {
+					ice_app_prot_id_type = prot_id;
+					break;
+				}
+			}
 		} else {
 			/* FIP APP */
 			ice_aqc_cee_status_mask = ICE_AQC_CEE_FIP_STATUS_M;
@@ -892,11 +915,8 @@ enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi)
 	ret = ice_aq_get_cee_dcb_cfg(pi->hw, &cee_cfg, NULL);
 	if (!ret) {
 		/* CEE mode */
-		dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg;
-		dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_CEE;
-		dcbx_cfg->tlv_status = le32_to_cpu(cee_cfg.tlv_status);
-		ice_cee_to_dcb_cfg(&cee_cfg, dcbx_cfg);
 		ret = ice_get_ieee_or_cee_dcb_cfg(pi, ICE_DCBX_MODE_CEE);
+		ice_cee_to_dcb_cfg(&cee_cfg, pi);
 	} else if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT) {
 		/* CEE mode not enabled try querying IEEE data */
 		dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg;
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index a6cb0c35748c..266036b7a49a 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -535,6 +535,7 @@ struct ice_dcb_app_priority_table {
 #define ICE_TLV_STATUS_ERR	0x4
 #define ICE_APP_PROT_ID_FCOE	0x8906
 #define ICE_APP_PROT_ID_ISCSI	0x0cbc
+#define ICE_APP_PROT_ID_ISCSI_860 0x035c
 #define ICE_APP_PROT_ID_FIP	0x8914
 #define ICE_APP_SEL_ETHTYPE	0x1
 #define ICE_APP_SEL_TCPIP	0x2

From e95fc8573e07c5e4825df4650fd8b8c93fad27a7 Mon Sep 17 00:00:00 2001
From: Krzysztof Goreczny <krzysztof.goreczny@intel.com>
Date: Fri, 26 Feb 2021 13:19:26 -0800
Subject: [PATCH 1373/1820] ice: prevent ice_open and ice_stop during reset

There is a possibility of race between ice_open or ice_stop calls
performed by OS and reset handling routine both trying to modify VSI
resources. Observed scenarios:
- reset handler deallocates memory in ice_vsi_free_arrays and ice_open
  tries to access it in ice_vsi_cfg_txq leading to driver crash
- reset handler deallocates memory in ice_vsi_free_arrays and ice_close
  tries to access it in ice_down leading to driver crash
- reset handler clears port scheduler topology and sets port state to
  ICE_SCHED_PORT_STATE_INIT leading to ice_ena_vsi_txq fail in ice_open

To prevent this additional checks in ice_open and ice_stop are
introduced to make sure that OS is not allowed to alter VSI config while
reset is in progress.

Fixes: cdedef59deb0 ("ice: Configure VSIs for Tx/Rx")
Signed-off-by: Krzysztof Goreczny <krzysztof.goreczny@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h      |  1 +
 drivers/net/ethernet/intel/ice/ice_lib.c  |  4 ++--
 drivers/net/ethernet/intel/ice/ice_main.c | 28 +++++++++++++++++++++++
 3 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 357706444dd5..1d4518638215 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -642,6 +642,7 @@ int ice_fdir_create_dflt_rules(struct ice_pf *pf);
 int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout,
 			  struct ice_rq_event_info *event);
 int ice_open(struct net_device *netdev);
+int ice_open_internal(struct net_device *netdev);
 int ice_stop(struct net_device *netdev);
 void ice_service_task_schedule(struct ice_pf *pf);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 8d4e2ad4328d..7ac2beaed95c 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2620,7 +2620,7 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
 			if (!locked)
 				rtnl_lock();
 
-			err = ice_open(vsi->netdev);
+			err = ice_open_internal(vsi->netdev);
 
 			if (!locked)
 				rtnl_unlock();
@@ -2649,7 +2649,7 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
 			if (!locked)
 				rtnl_lock();
 
-			ice_stop(vsi->netdev);
+			ice_vsi_close(vsi);
 
 			if (!locked)
 				rtnl_unlock();
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 53e053c997eb..255a07c1e33a 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -6632,6 +6632,28 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
  * Returns 0 on success, negative value on failure
  */
 int ice_open(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_pf *pf = np->vsi->back;
+
+	if (ice_is_reset_in_progress(pf->state)) {
+		netdev_err(netdev, "can't open net device while reset is in progress");
+		return -EBUSY;
+	}
+
+	return ice_open_internal(netdev);
+}
+
+/**
+ * ice_open_internal - Called when a network interface becomes active
+ * @netdev: network interface device structure
+ *
+ * Internal ice_open implementation. Should not be used directly except for ice_open and reset
+ * handling routine
+ *
+ * Returns 0 on success, negative value on failure
+ */
+int ice_open_internal(struct net_device *netdev)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
@@ -6712,6 +6734,12 @@ int ice_stop(struct net_device *netdev)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+
+	if (ice_is_reset_in_progress(pf->state)) {
+		netdev_err(netdev, "can't stop net device while reset is in progress");
+		return -EBUSY;
+	}
 
 	ice_vsi_close(vsi);
 

From 59df14f9cc2326bd6432d60eca0df8201d9d3d4b Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Fri, 26 Feb 2021 13:19:27 -0800
Subject: [PATCH 1374/1820] ice: fix memory allocation call

Fix the order of number of array members and member size parameters in a
*calloc() call.

Fixes: b3c3890489f6 ("ice: avoid unnecessary single-member variable-length structs")
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 3d9475e222cd..a20edf1538a0 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -717,8 +717,8 @@ static enum ice_status ice_cfg_fw_log(struct ice_hw *hw, bool enable)
 
 			if (!data) {
 				data = devm_kcalloc(ice_hw_to_dev(hw),
-						    sizeof(*data),
 						    ICE_AQC_FW_LOG_ID_MAX,
+						    sizeof(*data),
 						    GFP_KERNEL);
 				if (!data)
 					return ICE_ERR_NO_MEMORY;

From 1a1c130ab7575498eed5bcf7220037ae09cd1f8a Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 23 Mar 2021 20:26:52 +0100
Subject: [PATCH 1375/1820] ACPI: tables: x86: Reserve memory occupied by ACPI
 tables

The following problem has been reported by George Kennedy:

 Since commit 7fef431be9c9 ("mm/page_alloc: place pages to tail
 in __free_pages_core()") the following use after free occurs
 intermittently when ACPI tables are accessed.

 BUG: KASAN: use-after-free in ibft_init+0x134/0xc49
 Read of size 4 at addr ffff8880be453004 by task swapper/0/1
 CPU: 3 PID: 1 Comm: swapper/0 Not tainted 5.12.0-rc1-7a7fd0d #1
 Call Trace:
  dump_stack+0xf6/0x158
  print_address_description.constprop.9+0x41/0x60
  kasan_report.cold.14+0x7b/0xd4
  __asan_report_load_n_noabort+0xf/0x20
  ibft_init+0x134/0xc49
  do_one_initcall+0xc4/0x3e0
  kernel_init_freeable+0x5af/0x66b
  kernel_init+0x16/0x1d0
  ret_from_fork+0x22/0x30

 ACPI tables mapped via kmap() do not have their mapped pages
 reserved and the pages can be "stolen" by the buddy allocator.

Apparently, on the affected system, the ACPI table in question is
not located in "reserved" memory, like ACPI NVS or ACPI Data, that
will not be used by the buddy allocator, so the memory occupied by
that table has to be explicitly reserved to prevent the buddy
allocator from using it.

In order to address this problem, rearrange the initialization of the
ACPI tables on x86 to locate the initial tables earlier and reserve
the memory occupied by them.

The other architectures using ACPI should not be affected by this
change.

Link: https://lore.kernel.org/linux-acpi/1614802160-29362-1-git-send-email-george.kennedy@oracle.com/
Reported-by: George Kennedy <george.kennedy@oracle.com>
Tested-by: George Kennedy <george.kennedy@oracle.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: 5.10+ <stable@vger.kernel.org> # 5.10+
---
 arch/x86/kernel/acpi/boot.c | 25 +++++++++++-----------
 arch/x86/kernel/setup.c     |  8 +++----
 drivers/acpi/tables.c       | 42 ++++++++++++++++++++++++++++++++++---
 include/linux/acpi.h        |  9 +++++++-
 4 files changed, 62 insertions(+), 22 deletions(-)

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 7bdc0239a943..14cd3186dc77 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1554,10 +1554,18 @@ void __init acpi_boot_table_init(void)
 	/*
 	 * Initialize the ACPI boot-time table parser.
 	 */
-	if (acpi_table_init()) {
+	if (acpi_locate_initial_tables())
 		disable_acpi();
-		return;
-	}
+	else
+		acpi_reserve_initial_tables();
+}
+
+int __init early_acpi_boot_init(void)
+{
+	if (acpi_disabled)
+		return 1;
+
+	acpi_table_init_complete();
 
 	acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf);
 
@@ -1570,18 +1578,9 @@ void __init acpi_boot_table_init(void)
 		} else {
 			printk(KERN_WARNING PREFIX "Disabling ACPI support\n");
 			disable_acpi();
-			return;
+			return 1;
 		}
 	}
-}
-
-int __init early_acpi_boot_init(void)
-{
-	/*
-	 * If acpi_disabled, bail out
-	 */
-	if (acpi_disabled)
-		return 1;
 
 	/*
 	 * Process the Multiple APIC Description Table (MADT), if present
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d883176ef2ce..5ecd69a48393 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1045,6 +1045,9 @@ void __init setup_arch(char **cmdline_p)
 
 	cleanup_highmap();
 
+	/* Look for ACPI tables and reserve memory occupied by them. */
+	acpi_boot_table_init();
+
 	memblock_set_current_limit(ISA_END_ADDRESS);
 	e820__memblock_setup();
 
@@ -1136,11 +1139,6 @@ void __init setup_arch(char **cmdline_p)
 
 	early_platform_quirks();
 
-	/*
-	 * Parse the ACPI tables for possible boot-time SMP configuration.
-	 */
-	acpi_boot_table_init();
-
 	early_acpi_boot_init();
 
 	initmem_init();
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index e48690a006a4..9d581045acff 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -780,7 +780,7 @@ acpi_status acpi_os_table_override(struct acpi_table_header *existing_table,
 }
 
 /*
- * acpi_table_init()
+ * acpi_locate_initial_tables()
  *
  * find RSDP, find and checksum SDT/XSDT.
  * checksum all tables, print SDT/XSDT
@@ -788,7 +788,7 @@ acpi_status acpi_os_table_override(struct acpi_table_header *existing_table,
  * result: sdt_entry[] is initialized
  */
 
-int __init acpi_table_init(void)
+int __init acpi_locate_initial_tables(void)
 {
 	acpi_status status;
 
@@ -803,9 +803,45 @@ int __init acpi_table_init(void)
 	status = acpi_initialize_tables(initial_tables, ACPI_MAX_TABLES, 0);
 	if (ACPI_FAILURE(status))
 		return -EINVAL;
-	acpi_table_initrd_scan();
 
+	return 0;
+}
+
+void __init acpi_reserve_initial_tables(void)
+{
+	int i;
+
+	for (i = 0; i < ACPI_MAX_TABLES; i++) {
+		struct acpi_table_desc *table_desc = &initial_tables[i];
+		u64 start = table_desc->address;
+		u64 size = table_desc->length;
+
+		if (!start || !size)
+			break;
+
+		pr_info("Reserving %4s table memory at [mem 0x%llx-0x%llx]\n",
+			table_desc->signature.ascii, start, start + size - 1);
+
+		memblock_reserve(start, size);
+	}
+}
+
+void __init acpi_table_init_complete(void)
+{
+	acpi_table_initrd_scan();
 	check_multiple_madt();
+}
+
+int __init acpi_table_init(void)
+{
+	int ret;
+
+	ret = acpi_locate_initial_tables();
+	if (ret)
+		return ret;
+
+	acpi_table_init_complete();
+
 	return 0;
 }
 
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index fcdaab723916..3bdcfc4401b7 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -222,10 +222,14 @@ void __iomem *__acpi_map_table(unsigned long phys, unsigned long size);
 void __acpi_unmap_table(void __iomem *map, unsigned long size);
 int early_acpi_boot_init(void);
 int acpi_boot_init (void);
+void acpi_boot_table_prepare (void);
 void acpi_boot_table_init (void);
 int acpi_mps_check (void);
 int acpi_numa_init (void);
 
+int acpi_locate_initial_tables (void);
+void acpi_reserve_initial_tables (void);
+void acpi_table_init_complete (void);
 int acpi_table_init (void);
 int acpi_table_parse(char *id, acpi_tbl_table_handler handler);
 int __init acpi_table_parse_entries(char *id, unsigned long table_size,
@@ -814,9 +818,12 @@ static inline int acpi_boot_init(void)
 	return 0;
 }
 
+static inline void acpi_boot_table_prepare(void)
+{
+}
+
 static inline void acpi_boot_table_init(void)
 {
-	return;
 }
 
 static inline int acpi_mps_check(void)

From c0c33442f7203704aef345647e14c2fb86071001 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 26 Mar 2021 12:56:18 +0200
Subject: [PATCH 1376/1820] PM: runtime: Fix ordering in
 pm_runtime_get_suppliers()

rpm_active indicates how many times the supplier usage_count has been
incremented. Consequently it must be updated after pm_runtime_get_sync() of
the supplier, not before.

Fixes: 4c06c4e6cf63 ("driver core: Fix possible supplier PM-usage counter imbalance")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: 5.1+ <stable@vger.kernel.org> # 5.1+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/runtime.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index d54e540067bf..4fde37713c58 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1690,8 +1690,8 @@ void pm_runtime_get_suppliers(struct device *dev)
 				device_links_read_lock_held())
 		if (link->flags & DL_FLAG_PM_RUNTIME) {
 			link->supplier_preactivated = true;
-			refcount_inc(&link->rpm_active);
 			pm_runtime_get_sync(link->supplier);
+			refcount_inc(&link->rpm_active);
 		}
 
 	device_links_read_unlock(idx);

From 9dfacc54a8661bc8be6e08cffee59596ec59f263 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 26 Mar 2021 12:56:19 +0200
Subject: [PATCH 1377/1820] PM: runtime: Fix race getting/putting suppliers at
 probe

pm_runtime_put_suppliers() must not decrement rpm_active unless the
consumer is suspended. That is because, otherwise, it could suspend
suppliers for an active consumer.

That can happen as follows:

 static int driver_probe_device(struct device_driver *drv, struct device *dev)
 {
	int ret = 0;

	if (!device_is_registered(dev))
		return -ENODEV;

	dev->can_match = true;
	pr_debug("bus: '%s': %s: matched device %s with driver %s\n",
		 drv->bus->name, __func__, dev_name(dev), drv->name);

	pm_runtime_get_suppliers(dev);
	if (dev->parent)
		pm_runtime_get_sync(dev->parent);

 At this point, dev can runtime suspend so rpm_put_suppliers() can run,
 rpm_active becomes 1 (the lowest value).

	pm_runtime_barrier(dev);
	if (initcall_debug)
		ret = really_probe_debug(dev, drv);
	else
		ret = really_probe(dev, drv);

 Probe callback can have runtime resumed dev, and then runtime put
 so dev is awaiting autosuspend, but rpm_active is 2.

	pm_request_idle(dev);

	if (dev->parent)
		pm_runtime_put(dev->parent);

	pm_runtime_put_suppliers(dev);

 Now pm_runtime_put_suppliers() will put the supplier
 i.e. rpm_active 2 -> 1, but consumer can still be active.

	return ret;
 }

Fix by checking the runtime status. For any status other than
RPM_SUSPENDED, rpm_active can be considered to be "owned" by
rpm_[get/put]_suppliers() and pm_runtime_put_suppliers() need do nothing.

Reported-by: Asutosh Das <asutoshd@codeaurora.org>
Fixes: 4c06c4e6cf63 ("driver core: Fix possible supplier PM-usage counter imbalance")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: 5.1+ <stable@vger.kernel.org> # 5.1+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/runtime.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 4fde37713c58..fe1dad68aee4 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1704,6 +1704,8 @@ void pm_runtime_get_suppliers(struct device *dev)
 void pm_runtime_put_suppliers(struct device *dev)
 {
 	struct device_link *link;
+	unsigned long flags;
+	bool put;
 	int idx;
 
 	idx = device_links_read_lock();
@@ -1712,7 +1714,11 @@ void pm_runtime_put_suppliers(struct device *dev)
 				device_links_read_lock_held())
 		if (link->supplier_preactivated) {
 			link->supplier_preactivated = false;
-			if (refcount_dec_not_one(&link->rpm_active))
+			spin_lock_irqsave(&dev->power.lock, flags);
+			put = pm_runtime_status_suspended(dev) &&
+			      refcount_dec_not_one(&link->rpm_active);
+			spin_unlock_irqrestore(&dev->power.lock, flags);
+			if (put)
 				pm_runtime_put(link->supplier);
 		}
 

From 741b7b743bbcb5a3848e4e55982064214f900d2f Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Fri, 26 Feb 2021 13:19:28 -0800
Subject: [PATCH 1378/1820] ice: remove DCBNL_DEVRESET bit from PF state

The original purpose of the ICE_DCBNL_DEVRESET was to protect
the driver during DCBNL device resets.  But, the flow for
DCBNL device resets now consists of only calls up the stack
such as dev_close() and dev_open() that will result in NDO calls
to the driver.  These will be handled with state changes from the
stack.  Also, there is a problem of the dev_close and dev_open
being blocked by checks for reset in progress also using the
ICE_DCBNL_DEVRESET bit.

Since the ICE_DCBNL_DEVRESET bit is not necessary for protecting
the driver from DCBNL device resets and it is actually blocking
changes coming from the DCBNL interface, remove the bit from the
PF state and don't block driver function based on DCBNL reset in
progress.

Fixes: b94b013eb626 ("ice: Implement DCBNL support")
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h        | 1 -
 drivers/net/ethernet/intel/ice/ice_dcb_nl.c | 2 --
 drivers/net/ethernet/intel/ice/ice_lib.c    | 1 -
 3 files changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 1d4518638215..7934f0d17277 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -196,7 +196,6 @@ enum ice_state {
 	__ICE_NEEDS_RESTART,
 	__ICE_PREPARED_FOR_RESET,	/* set by driver when prepared */
 	__ICE_RESET_OICR_RECV,		/* set by driver after rcv reset OICR */
-	__ICE_DCBNL_DEVRESET,		/* set by dcbnl devreset */
 	__ICE_PFR_REQ,			/* set by driver and peers */
 	__ICE_CORER_REQ,		/* set by driver and peers */
 	__ICE_GLOBR_REQ,		/* set by driver and peers */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
index 468a63f7eff9..4180f1f35fb8 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
@@ -18,12 +18,10 @@ static void ice_dcbnl_devreset(struct net_device *netdev)
 	while (ice_is_reset_in_progress(pf->state))
 		usleep_range(1000, 2000);
 
-	set_bit(__ICE_DCBNL_DEVRESET, pf->state);
 	dev_close(netdev);
 	netdev_state_change(netdev);
 	dev_open(netdev, NULL);
 	netdev_state_change(netdev);
-	clear_bit(__ICE_DCBNL_DEVRESET, pf->state);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 7ac2beaed95c..d13c7fc8fb0a 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -3078,7 +3078,6 @@ err_vsi:
 bool ice_is_reset_in_progress(unsigned long *state)
 {
 	return test_bit(__ICE_RESET_OICR_RECV, state) ||
-	       test_bit(__ICE_DCBNL_DEVRESET, state) ||
 	       test_bit(__ICE_PFR_REQ, state) ||
 	       test_bit(__ICE_CORER_REQ, state) ||
 	       test_bit(__ICE_GLOBR_REQ, state);

From 7a91d3f02b04b2fb18c2dfa8b6c4e5a40a2753f5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jacek=20Bu=C5=82atek?= <jacekx.bulatek@intel.com>
Date: Fri, 26 Feb 2021 13:19:29 -0800
Subject: [PATCH 1379/1820] ice: Fix for dereference of NULL pointer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add handling of allocation fault for ice_vsi_list_map_info.

Also *fi should not be NULL pointer, it is a reference to raw
data field, so remove this variable and use the reference
directly.

Fixes: 9daf8208dd4d ("ice: Add support for switch filter programming")
Signed-off-by: Jacek Bułatek <jacekx.bulatek@intel.com>
Co-developed-by: Haiyue Wang <haiyue.wang@intel.com>
Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_switch.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 67c965a3f5d2..387d3f6cd71e 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -1238,6 +1238,9 @@ ice_add_update_vsi_list(struct ice_hw *hw,
 			ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2,
 						vsi_list_id);
 
+		if (!m_entry->vsi_list_info)
+			return ICE_ERR_NO_MEMORY;
+
 		/* If this entry was large action then the large action needs
 		 * to be updated to point to FWD to VSI list
 		 */
@@ -2220,6 +2223,7 @@ ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_handle)
 	return ((fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI &&
 		 fm_entry->fltr_info.vsi_handle == vsi_handle) ||
 		(fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST &&
+		 fm_entry->vsi_list_info &&
 		 (test_bit(vsi_handle, fm_entry->vsi_list_info->vsi_map))));
 }
 
@@ -2292,14 +2296,12 @@ ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle,
 		return ICE_ERR_PARAM;
 
 	list_for_each_entry(fm_entry, lkup_list_head, list_entry) {
-		struct ice_fltr_info *fi;
-
-		fi = &fm_entry->fltr_info;
-		if (!fi || !ice_vsi_uses_fltr(fm_entry, vsi_handle))
+		if (!ice_vsi_uses_fltr(fm_entry, vsi_handle))
 			continue;
 
 		status = ice_add_entry_to_vsi_fltr_list(hw, vsi_handle,
-							vsi_list_head, fi);
+							vsi_list_head,
+							&fm_entry->fltr_info);
 		if (status)
 			return status;
 	}

From 3176551979b92b02756979c0f1e2d03d1fc82b1e Mon Sep 17 00:00:00 2001
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Date: Fri, 26 Feb 2021 13:19:30 -0800
Subject: [PATCH 1380/1820] ice: Use port number instead of PF ID for WoL

As per the spec, the WoL control word read from the NVM should be
interpreted as port numbers, and not PF numbers. So when checking
if WoL supported, use the port number instead of the PF ID.

Also, ice_is_wol_supported doesn't really need a pointer to the pf
struct, but just needs a pointer to the hw instance.

Fixes: 769c500dcc1e ("ice: Add advanced power mgmt for WoL")
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h         | 2 +-
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 4 ++--
 drivers/net/ethernet/intel/ice/ice_main.c    | 9 ++++-----
 3 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 7934f0d17277..17101c45cbcd 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -623,7 +623,7 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
 const char *ice_stat_str(enum ice_status stat_err);
 const char *ice_aq_str(enum ice_aq_err aq_err);
-bool ice_is_wol_supported(struct ice_pf *pf);
+bool ice_is_wol_supported(struct ice_hw *hw);
 int
 ice_fdir_write_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool add,
 		    bool is_tun);
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 2dcfa685b763..32ba71a16165 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3472,7 +3472,7 @@ static void ice_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 		netdev_warn(netdev, "Wake on LAN is not supported on this interface!\n");
 
 	/* Get WoL settings based on the HW capability */
-	if (ice_is_wol_supported(pf)) {
+	if (ice_is_wol_supported(&pf->hw)) {
 		wol->supported = WAKE_MAGIC;
 		wol->wolopts = pf->wol_ena ? WAKE_MAGIC : 0;
 	} else {
@@ -3492,7 +3492,7 @@ static int ice_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
 
-	if (vsi->type != ICE_VSI_PF || !ice_is_wol_supported(pf))
+	if (vsi->type != ICE_VSI_PF || !ice_is_wol_supported(&pf->hw))
 		return -EOPNOTSUPP;
 
 	/* only magic packet is supported */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 255a07c1e33a..9f1adff85be7 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3537,15 +3537,14 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 }
 
 /**
- * ice_is_wol_supported - get NVM state of WoL
- * @pf: board private structure
+ * ice_is_wol_supported - check if WoL is supported
+ * @hw: pointer to hardware info
  *
  * Check if WoL is supported based on the HW configuration.
  * Returns true if NVM supports and enables WoL for this port, false otherwise
  */
-bool ice_is_wol_supported(struct ice_pf *pf)
+bool ice_is_wol_supported(struct ice_hw *hw)
 {
-	struct ice_hw *hw = &pf->hw;
 	u16 wol_ctrl;
 
 	/* A bit set to 1 in the NVM Software Reserved Word 2 (WoL control
@@ -3554,7 +3553,7 @@ bool ice_is_wol_supported(struct ice_pf *pf)
 	if (ice_read_sr_word(hw, ICE_SR_NVM_WOL_CFG, &wol_ctrl))
 		return false;
 
-	return !(BIT(hw->pf_id) & wol_ctrl);
+	return !(BIT(hw->port_info->lport) & wol_ctrl);
 }
 
 /**

From b7eeb52721fe417730fc5adc5cbeeb5fe349ab26 Mon Sep 17 00:00:00 2001
From: Robert Malz <robertx.malz@intel.com>
Date: Fri, 26 Feb 2021 13:19:32 -0800
Subject: [PATCH 1381/1820] ice: Cleanup fltr list in case of allocation issues

When ice_remove_vsi_lkup_fltr is called, by calling
ice_add_to_vsi_fltr_list local copy of vsi filter list
is created. If any issues during creation of vsi filter
list occurs it up for the caller to free already
allocated memory. This patch ensures proper memory
deallocation in these cases.

Fixes: 80d144c9ac82 ("ice: Refactor switch rule management structures and functions")
Signed-off-by: Robert Malz <robertx.malz@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_switch.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 387d3f6cd71e..834cbd3f7b31 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -2624,7 +2624,7 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_handle,
 					  &remove_list_head);
 	mutex_unlock(rule_lock);
 	if (status)
-		return;
+		goto free_fltr_list;
 
 	switch (lkup) {
 	case ICE_SW_LKUP_MAC:
@@ -2647,6 +2647,7 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_handle,
 		break;
 	}
 
+free_fltr_list:
 	list_for_each_entry_safe(fm_entry, tmp, &remove_list_head, list_entry) {
 		list_del(&fm_entry->list_entry);
 		devm_kfree(ice_hw_to_dev(hw), fm_entry);

From acc7baafeb0b52a5b91be64c4776f827a163dda1 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Tue, 23 Mar 2021 16:30:38 +0800
Subject: [PATCH 1382/1820] drm/amd/pm: no need to force MCLK to highest when
 no display connected

Correct the check for vblank short.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index 22b6a8e8bd21..d0ec83881fc5 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -3330,7 +3330,8 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 
 	disable_mclk_switching_for_display = ((1 < hwmgr->display_config->num_display) &&
 						!hwmgr->display_config->multi_monitor_in_sync) ||
-						smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time);
+						(hwmgr->display_config->num_display &&
+						smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time));
 
 	disable_mclk_switching = disable_mclk_switching_for_frame_lock ||
 					 disable_mclk_switching_for_display;

From 5e61b84f9d3ddfba73091f9fbc940caae1c9eb22 Mon Sep 17 00:00:00 2001
From: Nirmoy Das <nirmoy.das@amd.com>
Date: Fri, 26 Mar 2021 16:08:10 +0100
Subject: [PATCH 1383/1820] drm/amdgpu: fix offset calculation in
 amdgpu_vm_bo_clear_mappings()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Offset calculation wasn't correct as start addresses are in pfn
not in bytes.

CC: stable@vger.kernel.org
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index ad91c0c3c423..10de2cf344d5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2409,7 +2409,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
 			after->start = eaddr + 1;
 			after->last = tmp->last;
 			after->offset = tmp->offset;
-			after->offset += after->start - tmp->start;
+			after->offset += (after->start - tmp->start) << PAGE_SHIFT;
 			after->flags = tmp->flags;
 			after->bo_va = tmp->bo_va;
 			list_add(&after->list, &tmp->bo_va->invalids);

From 7b9acbb6aad4f54623dcd4bd4b1a60fe0c727b09 Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Sun, 7 Feb 2021 04:57:58 -0800
Subject: [PATCH 1384/1820] xtensa: fix uaccess-related livelock in
 do_page_fault

If a uaccess (e.g. get_user()) triggers a fault and there's a
fault signal pending, the handler will return to the uaccess without
having performed a uaccess fault fixup, and so the CPU will immediately
execute the uaccess instruction again, whereupon it will livelock
bouncing between that instruction and the fault handler.

https://lore.kernel.org/lkml/20210121123140.GD48431@C02TD0UTHF1T.local/

Cc: stable@vger.kernel.org
Reported-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/mm/fault.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 7666408ce12a..95a74890c7e9 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -112,8 +112,11 @@ good_area:
 	 */
 	fault = handle_mm_fault(vma, address, flags, regs);
 
-	if (fault_signal_pending(fault, regs))
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			goto bad_page_fault;
 		return;
+	}
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)

From 2867b9746cef78745c594894aece6f8ef826e0b4 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Date: Sun, 14 Mar 2021 12:07:09 +0100
Subject: [PATCH 1385/1820] clk: socfpga: fix iomem pointer cast on 64-bit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Pointers should be cast with uintptr_t instead of integer.  This fixes
warning when compile testing on ARM64:

  drivers/clk/socfpga/clk-gate.c: In function ‘socfpga_clk_recalc_rate’:
  drivers/clk/socfpga/clk-gate.c:102:7: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]

Fixes: b7cec13f082f ("clk: socfpga: Look for the GPIO_DB_CLK by its offset")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Acked-by: Dinh Nguyen <dinguyen@kernel.org>
Link: https://lore.kernel.org/r/20210314110709.32599-1-krzysztof.kozlowski@canonical.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/socfpga/clk-gate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/socfpga/clk-gate.c b/drivers/clk/socfpga/clk-gate.c
index 43ecd507bf83..cf94a12459ea 100644
--- a/drivers/clk/socfpga/clk-gate.c
+++ b/drivers/clk/socfpga/clk-gate.c
@@ -99,7 +99,7 @@ static unsigned long socfpga_clk_recalc_rate(struct clk_hw *hwclk,
 		val = readl(socfpgaclk->div_reg) >> socfpgaclk->shift;
 		val &= GENMASK(socfpgaclk->width - 1, 0);
 		/* Check for GPIO_DB_CLK by its offset */
-		if ((int) socfpgaclk->div_reg & SOCFPGA_GPIO_DB_CLK_OFFSET)
+		if ((uintptr_t) socfpgaclk->div_reg & SOCFPGA_GPIO_DB_CLK_OFFSET)
 			div = val + 1;
 		else
 			div = (1 << val);

From 66167c310deb4ac1725f81004fb4b504676ad0bf Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 29 Mar 2021 11:29:23 +0300
Subject: [PATCH 1386/1820] mlxsw: spectrum: Fix ECN marking in tunnel
 decapsulation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Cited commit changed the behavior of the software data path with regards
to the ECN marking of decapsulated packets. However, the commit did not
change other callers of __INET_ECN_decapsulate(), namely mlxsw. The
driver is using the function in order to ensure that the hardware and
software data paths act the same with regards to the ECN marking of
decapsulated packets.

The discrepancy was uncovered by commit 5aa3c334a449 ("selftests:
forwarding: vxlan_bridge_1d: Fix vxlan ecn decapsulate value") that
aligned the selftest to the new behavior. Without this patch the
selftest passes when used with veth pairs, but fails when used with
mlxsw netdevs.

Fix this by instructing the device to propagate the ECT(1) mark from the
outer header to the inner header when the inner header is ECT(0), for
both NVE and IP-in-IP tunnels.

A helper is added in order not to duplicate the code between both tunnel
types.

Fixes: b723748750ec ("tunnel: Propagate ECT(1) when decapsulating as recommended by RFC6040")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h    | 15 +++++++++++++++
 .../net/ethernet/mellanox/mlxsw/spectrum_ipip.c   |  7 +++----
 .../net/ethernet/mellanox/mlxsw/spectrum_nve.c    |  7 +++----
 3 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index d9d9e1f488f9..ba28ac7e79bc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -21,6 +21,7 @@
 #include <net/red.h>
 #include <net/vxlan.h>
 #include <net/flow_offload.h>
+#include <net/inet_ecn.h>
 
 #include "port.h"
 #include "core.h"
@@ -347,6 +348,20 @@ struct mlxsw_sp_port_type_speed_ops {
 	u32 (*ptys_proto_cap_masked_get)(u32 eth_proto_cap);
 };
 
+static inline u8 mlxsw_sp_tunnel_ecn_decap(u8 outer_ecn, u8 inner_ecn,
+					   bool *trap_en)
+{
+	bool set_ce = false;
+
+	*trap_en = !!__INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce);
+	if (set_ce)
+		return INET_ECN_CE;
+	else if (outer_ecn == INET_ECN_ECT_1 && inner_ecn == INET_ECN_ECT_0)
+		return INET_ECN_ECT_1;
+	else
+		return inner_ecn;
+}
+
 static inline struct net_device *
 mlxsw_sp_bridge_vxlan_dev_find(struct net_device *br_dev)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
index 6ccca39bae84..64a8f838eb53 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
@@ -335,12 +335,11 @@ static int mlxsw_sp_ipip_ecn_decap_init_one(struct mlxsw_sp *mlxsw_sp,
 					    u8 inner_ecn, u8 outer_ecn)
 {
 	char tidem_pl[MLXSW_REG_TIDEM_LEN];
-	bool trap_en, set_ce = false;
 	u8 new_inner_ecn;
+	bool trap_en;
 
-	trap_en = __INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce);
-	new_inner_ecn = set_ce ? INET_ECN_CE : inner_ecn;
-
+	new_inner_ecn = mlxsw_sp_tunnel_ecn_decap(outer_ecn, inner_ecn,
+						  &trap_en);
 	mlxsw_reg_tidem_pack(tidem_pl, outer_ecn, inner_ecn, new_inner_ecn,
 			     trap_en, trap_en ? MLXSW_TRAP_ID_DECAP_ECN0 : 0);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tidem), tidem_pl);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
index e5ec595593f4..9eba8fa684ae 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
@@ -909,12 +909,11 @@ static int __mlxsw_sp_nve_ecn_decap_init(struct mlxsw_sp *mlxsw_sp,
 					 u8 inner_ecn, u8 outer_ecn)
 {
 	char tndem_pl[MLXSW_REG_TNDEM_LEN];
-	bool trap_en, set_ce = false;
 	u8 new_inner_ecn;
+	bool trap_en;
 
-	trap_en = !!__INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce);
-	new_inner_ecn = set_ce ? INET_ECN_CE : inner_ecn;
-
+	new_inner_ecn = mlxsw_sp_tunnel_ecn_decap(outer_ecn, inner_ecn,
+						  &trap_en);
 	mlxsw_reg_tndem_pack(tndem_pl, outer_ecn, inner_ecn, new_inner_ecn,
 			     trap_en, trap_en ? MLXSW_TRAP_ID_DECAP_ECN0 : 0);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tndem), tndem_pl);

From 4bfd0de590300d3e3889ee9833bec8cc4059fae6 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 29 Mar 2021 11:29:27 +0300
Subject: [PATCH 1387/1820] selftests: forwarding: vxlan_bridge_1d: Add more
 ECN decap test cases

Test that all possible combinations of inner and outer ECN bits result
in the correct inner ECN marking according to RFC 6040 4.2.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1d.sh     | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 0ccb1dda099a..eb307ca37bfa 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -657,10 +657,21 @@ test_ecn_decap()
 {
 	# In accordance with INET_ECN_decapsulate()
 	__test_ecn_decap 00 00 0x00
+	__test_ecn_decap 00 01 0x00
+	__test_ecn_decap 00 02 0x00
+	# 00 03 is tested in test_ecn_decap_error()
+	__test_ecn_decap 01 00 0x01
 	__test_ecn_decap 01 01 0x01
-	__test_ecn_decap 02 01 0x01
+	__test_ecn_decap 01 02 0x01
 	__test_ecn_decap 01 03 0x03
+	__test_ecn_decap 02 00 0x02
+	__test_ecn_decap 02 01 0x01
+	__test_ecn_decap 02 02 0x02
 	__test_ecn_decap 02 03 0x03
+	__test_ecn_decap 03 00 0x03
+	__test_ecn_decap 03 01 0x03
+	__test_ecn_decap 03 02 0x03
+	__test_ecn_decap 03 03 0x03
 	test_ecn_decap_error
 }
 

From 5954846d09e4a210b6c761ab09388cfd41f58342 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Mon, 29 Mar 2021 16:55:37 +0530
Subject: [PATCH 1388/1820] MAINTAINERS: Add entry for Qualcomm IPC Router
 (QRTR) driver

Add MAINTAINERS entry for Qualcomm IPC Router (QRTR) driver.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8d23b0ec0c90..1cc3976040d5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14853,6 +14853,14 @@ L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
 F:	drivers/iommu/arm/arm-smmu/qcom_iommu.c
 
+QUALCOMM IPC ROUTER (QRTR) DRIVER
+M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+L:	linux-arm-msm@vger.kernel.org
+S:	Maintained
+F:	include/trace/events/qrtr.h
+F:	include/uapi/linux/qrtr.h
+F:	net/qrtr/
+
 QUALCOMM IPCC MAILBOX DRIVER
 M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
 L:	linux-arm-msm@vger.kernel.org

From 63415767a2446136372e777cde5bb351f21ec21d Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Mon, 29 Mar 2021 05:36:48 -0700
Subject: [PATCH 1389/1820] ethernet: myri10ge: Fix a use after free in
 myri10ge_sw_tso

In myri10ge_sw_tso, the skb_list_walk_safe macro will set
(curr) = (segs) and (next) = (curr)->next. If status!=0 is true,
the memory pointed by curr and segs will be free by dev_kfree_skb_any(curr).
But later, the segs is used by segs = segs->next and causes a uaf.

As (next) = (curr)->next, my patch replaces seg->next to next.

Fixes: 536577f36ff7a ("net: myri10ge: use skb_list_walk_safe helper for gso segments")
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 1634ca6d4a8f..c84c8bf2bc20 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -2897,7 +2897,7 @@ static netdev_tx_t myri10ge_sw_tso(struct sk_buff *skb,
 			dev_kfree_skb_any(curr);
 			if (segs != NULL) {
 				curr = segs;
-				segs = segs->next;
+				segs = next;
 				curr->next = NULL;
 				dev_kfree_skb_any(segs);
 			}

From bff5b62585123823842833ab20b1c0a7fa437f8c Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Mon, 29 Mar 2021 17:08:47 +0300
Subject: [PATCH 1390/1820] gianfar: Handle error code at MAC address change

Handle return error code of eth_mac_addr();

Fixes: 3d23a05c75c7 ("gianfar: Enable changing mac addr when if up")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/gianfar.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 1cf8ef717453..3ec4d9fddd52 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -363,7 +363,11 @@ static void gfar_set_mac_for_addr(struct net_device *dev, int num,
 
 static int gfar_set_mac_addr(struct net_device *dev, void *p)
 {
-	eth_mac_addr(dev, p);
+	int ret;
+
+	ret = eth_mac_addr(dev, p);
+	if (ret)
+		return ret;
 
 	gfar_set_mac_for_addr(dev, 0, dev->dev_addr);
 

From e0146a108ce4d2c22b9510fd12268e3ee72a0161 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 29 Mar 2021 16:00:16 -0300
Subject: [PATCH 1391/1820] vfio/nvlink: Add missing SPAPR_TCE_IOMMU depends

Compiling the nvlink stuff relies on the SPAPR_TCE_IOMMU otherwise there
are compile errors:

 drivers/vfio/pci/vfio_pci_nvlink2.c:101:10: error: implicit declaration of function 'mm_iommu_put' [-Werror,-Wimplicit-function-declaration]
                            ret = mm_iommu_put(data->mm, data->mem);

As PPC only defines these functions when the config is set.

Previously this wasn't a problem by chance as SPAPR_TCE_IOMMU was the only
IOMMU that could have satisfied IOMMU_API on POWERNV.

Fixes: 179209fa1270 ("vfio: IOMMU_API should be selected")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Message-Id: <0-v1-83dba9768fc3+419-vfio_nvlink2_kconfig_jgg@nvidia.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index ac3c1dd3edef..4abddbebd4b2 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -42,6 +42,6 @@ config VFIO_PCI_IGD
 
 config VFIO_PCI_NVLINK2
 	def_bool y
-	depends on VFIO_PCI && PPC_POWERNV
+	depends on VFIO_PCI && PPC_POWERNV && SPAPR_TCE_IOMMU
 	help
 	  VFIO PCI support for P9 Witherspoon machine with NVIDIA V100 GPUs

From fb6ec87f7229b92baa81b35cbc76f2626d5bfadb Mon Sep 17 00:00:00 2001
From: Maxim Kochetkov <fido_max@inbox.ru>
Date: Mon, 29 Mar 2021 18:30:16 +0300
Subject: [PATCH 1392/1820] net: dsa: Fix type was not set for devlink port

If PHY is not available on DSA port (described at devicetree but absent or
failed to detect) then kernel prints warning after 3700 secs:

[ 3707.948771] ------------[ cut here ]------------
[ 3707.948784] Type was not set for devlink port.
[ 3707.948894] WARNING: CPU: 1 PID: 17 at net/core/devlink.c:8097 0xc083f9d8

We should unregister the devlink port as a user port and
re-register it as an unused port before executing "continue" in case of
dsa_port_setup error.

Fixes: 86f8b1c01a0a ("net: dsa: Do not make user port errors fatal")
Signed-off-by: Maxim Kochetkov <fido_max@inbox.ru>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa2.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index d142eb2b288b..3c3e56a1f34d 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -795,8 +795,14 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst)
 
 	list_for_each_entry(dp, &dst->ports, list) {
 		err = dsa_port_setup(dp);
-		if (err)
+		if (err) {
+			dsa_port_devlink_teardown(dp);
+			dp->type = DSA_PORT_TYPE_UNUSED;
+			err = dsa_port_devlink_setup(dp);
+			if (err)
+				goto teardown;
 			continue;
+		}
 	}
 
 	return 0;

From e5c359f70e4b5e7b6c2bf4b0ca2d2686d543a37b Mon Sep 17 00:00:00 2001
From: Taniya Das <tdas@codeaurora.org>
Date: Sat, 27 Mar 2021 07:11:05 +0530
Subject: [PATCH 1393/1820] clk: qcom: camcc: Update the clock ops for the
 SC7180

Some of the RCGs could be always ON from the XO source and could be used
as the clock on signal for the GDSC to be operational. In the cases where
the GDSCs are parked at different source with the source clock disabled,
it could lead to the GDSC to be stuck at ON/OFF during gdsc disable/enable.
Thus park the RCGs at XO during clock disable and update the rcg_ops to
use the shared_ops.

Fixes: 15d09e830bbc ("clk: qcom: camcc: Add camera clock controller driver for SC7180")
Signed-off-by: Taniya Das <tdas@codeaurora.org>
Link: https://lore.kernel.org/r/1616809265-11912-1-git-send-email-tdas@codeaurora.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/camcc-sc7180.c | 50 ++++++++++++++++-----------------
 1 file changed, 25 insertions(+), 25 deletions(-)

diff --git a/drivers/clk/qcom/camcc-sc7180.c b/drivers/clk/qcom/camcc-sc7180.c
index dbac5651ab85..9bcf2f8ed4de 100644
--- a/drivers/clk/qcom/camcc-sc7180.c
+++ b/drivers/clk/qcom/camcc-sc7180.c
@@ -304,7 +304,7 @@ static struct clk_rcg2 cam_cc_bps_clk_src = {
 		.name = "cam_cc_bps_clk_src",
 		.parent_data = cam_cc_parent_data_2,
 		.num_parents = 5,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -325,7 +325,7 @@ static struct clk_rcg2 cam_cc_cci_0_clk_src = {
 		.name = "cam_cc_cci_0_clk_src",
 		.parent_data = cam_cc_parent_data_5,
 		.num_parents = 3,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -339,7 +339,7 @@ static struct clk_rcg2 cam_cc_cci_1_clk_src = {
 		.name = "cam_cc_cci_1_clk_src",
 		.parent_data = cam_cc_parent_data_5,
 		.num_parents = 3,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -360,7 +360,7 @@ static struct clk_rcg2 cam_cc_cphy_rx_clk_src = {
 		.name = "cam_cc_cphy_rx_clk_src",
 		.parent_data = cam_cc_parent_data_3,
 		.num_parents = 6,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -379,7 +379,7 @@ static struct clk_rcg2 cam_cc_csi0phytimer_clk_src = {
 		.name = "cam_cc_csi0phytimer_clk_src",
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = 4,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -393,7 +393,7 @@ static struct clk_rcg2 cam_cc_csi1phytimer_clk_src = {
 		.name = "cam_cc_csi1phytimer_clk_src",
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = 4,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -407,7 +407,7 @@ static struct clk_rcg2 cam_cc_csi2phytimer_clk_src = {
 		.name = "cam_cc_csi2phytimer_clk_src",
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = 4,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -421,7 +421,7 @@ static struct clk_rcg2 cam_cc_csi3phytimer_clk_src = {
 		.name = "cam_cc_csi3phytimer_clk_src",
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = 4,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -443,7 +443,7 @@ static struct clk_rcg2 cam_cc_fast_ahb_clk_src = {
 		.name = "cam_cc_fast_ahb_clk_src",
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = 4,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -466,7 +466,7 @@ static struct clk_rcg2 cam_cc_icp_clk_src = {
 		.name = "cam_cc_icp_clk_src",
 		.parent_data = cam_cc_parent_data_2,
 		.num_parents = 5,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -488,7 +488,7 @@ static struct clk_rcg2 cam_cc_ife_0_clk_src = {
 		.name = "cam_cc_ife_0_clk_src",
 		.parent_data = cam_cc_parent_data_4,
 		.num_parents = 4,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -510,7 +510,7 @@ static struct clk_rcg2 cam_cc_ife_0_csid_clk_src = {
 		.name = "cam_cc_ife_0_csid_clk_src",
 		.parent_data = cam_cc_parent_data_3,
 		.num_parents = 6,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -524,7 +524,7 @@ static struct clk_rcg2 cam_cc_ife_1_clk_src = {
 		.name = "cam_cc_ife_1_clk_src",
 		.parent_data = cam_cc_parent_data_4,
 		.num_parents = 4,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -538,7 +538,7 @@ static struct clk_rcg2 cam_cc_ife_1_csid_clk_src = {
 		.name = "cam_cc_ife_1_csid_clk_src",
 		.parent_data = cam_cc_parent_data_3,
 		.num_parents = 6,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -553,7 +553,7 @@ static struct clk_rcg2 cam_cc_ife_lite_clk_src = {
 		.parent_data = cam_cc_parent_data_4,
 		.num_parents = 4,
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -567,7 +567,7 @@ static struct clk_rcg2 cam_cc_ife_lite_csid_clk_src = {
 		.name = "cam_cc_ife_lite_csid_clk_src",
 		.parent_data = cam_cc_parent_data_3,
 		.num_parents = 6,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -590,7 +590,7 @@ static struct clk_rcg2 cam_cc_ipe_0_clk_src = {
 		.name = "cam_cc_ipe_0_clk_src",
 		.parent_data = cam_cc_parent_data_2,
 		.num_parents = 5,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -613,7 +613,7 @@ static struct clk_rcg2 cam_cc_jpeg_clk_src = {
 		.name = "cam_cc_jpeg_clk_src",
 		.parent_data = cam_cc_parent_data_2,
 		.num_parents = 5,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -635,7 +635,7 @@ static struct clk_rcg2 cam_cc_lrme_clk_src = {
 		.name = "cam_cc_lrme_clk_src",
 		.parent_data = cam_cc_parent_data_6,
 		.num_parents = 5,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -656,7 +656,7 @@ static struct clk_rcg2 cam_cc_mclk0_clk_src = {
 		.name = "cam_cc_mclk0_clk_src",
 		.parent_data = cam_cc_parent_data_1,
 		.num_parents = 3,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -670,7 +670,7 @@ static struct clk_rcg2 cam_cc_mclk1_clk_src = {
 		.name = "cam_cc_mclk1_clk_src",
 		.parent_data = cam_cc_parent_data_1,
 		.num_parents = 3,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -684,7 +684,7 @@ static struct clk_rcg2 cam_cc_mclk2_clk_src = {
 		.name = "cam_cc_mclk2_clk_src",
 		.parent_data = cam_cc_parent_data_1,
 		.num_parents = 3,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -698,7 +698,7 @@ static struct clk_rcg2 cam_cc_mclk3_clk_src = {
 		.name = "cam_cc_mclk3_clk_src",
 		.parent_data = cam_cc_parent_data_1,
 		.num_parents = 3,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -712,7 +712,7 @@ static struct clk_rcg2 cam_cc_mclk4_clk_src = {
 		.name = "cam_cc_mclk4_clk_src",
 		.parent_data = cam_cc_parent_data_1,
 		.num_parents = 3,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -732,7 +732,7 @@ static struct clk_rcg2 cam_cc_slow_ahb_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = 4,
 		.flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 

From 1bfb3dea965ff9f6226fd1709338f227363b6061 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Sat, 27 Mar 2021 23:49:08 +0530
Subject: [PATCH 1394/1820] cxgb4: avoid collecting SGE_QBASE regs during
 traffic

Accessing SGE_QBASE_MAP[0-3] and SGE_QBASE_INDEX registers can lead
to SGE missing doorbells under heavy traffic. So, only collect them
when adapter is idle. Also update the regdump range to skip collecting
these registers.

Fixes: 80a95a80d358 ("cxgb4: collect SGE PF/VF queue map")
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/chelsio/cxgb4/cudbg_lib.c    | 23 +++++++++++++++----
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c    |  3 ++-
 2 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index 6c85a10f465c..23a2ebdfd503 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -1794,11 +1794,25 @@ int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init,
 	struct cudbg_buffer temp_buff = { 0 };
 	struct sge_qbase_reg_field *sge_qbase;
 	struct ireg_buf *ch_sge_dbg;
+	u8 padap_running = 0;
 	int i, rc;
+	u32 size;
 
-	rc = cudbg_get_buff(pdbg_init, dbg_buff,
-			    sizeof(*ch_sge_dbg) * 2 + sizeof(*sge_qbase),
-			    &temp_buff);
+	/* Accessing SGE_QBASE_MAP[0-3] and SGE_QBASE_INDEX regs can
+	 * lead to SGE missing doorbells under heavy traffic. So, only
+	 * collect them when adapter is idle.
+	 */
+	for_each_port(padap, i) {
+		padap_running = netif_running(padap->port[i]);
+		if (padap_running)
+			break;
+	}
+
+	size = sizeof(*ch_sge_dbg) * 2;
+	if (!padap_running)
+		size += sizeof(*sge_qbase);
+
+	rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
 	if (rc)
 		return rc;
 
@@ -1820,7 +1834,8 @@ int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init,
 		ch_sge_dbg++;
 	}
 
-	if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5) {
+	if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5 &&
+	    !padap_running) {
 		sge_qbase = (struct sge_qbase_reg_field *)ch_sge_dbg;
 		/* 1 addr reg SGE_QBASE_INDEX and 4 data reg
 		 * SGE_QBASE_MAP[0-3]
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 98829e482bfa..80882cfc370f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -2090,7 +2090,8 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x1190, 0x1194,
 		0x11a0, 0x11a4,
 		0x11b0, 0x11b4,
-		0x11fc, 0x1274,
+		0x11fc, 0x123c,
+		0x1254, 0x1274,
 		0x1280, 0x133c,
 		0x1800, 0x18fc,
 		0x3000, 0x302c,

From 6bf24dc0cc0cc43b29ba344b66d78590e687e046 Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Sun, 28 Mar 2021 00:30:29 -0700
Subject: [PATCH 1395/1820] net:tipc: Fix a double free in tipc_sk_mcast_rcv

In the if(skb_peek(arrvq) == skb) branch, it calls __skb_dequeue(arrvq) to get
the skb by skb = skb_peek(arrvq). Then __skb_dequeue() unlinks the skb from arrvq
and returns the skb which equals to skb_peek(arrvq). After __skb_dequeue(arrvq)
finished, the skb is freed by kfree_skb(__skb_dequeue(arrvq)) in the first time.

Unfortunately, the same skb is freed in the second time by kfree_skb(skb) after
the branch completed.

My patch removes kfree_skb() in the if(skb_peek(arrvq) == skb) branch, because
this skb will be freed by kfree_skb(skb) finally.

Fixes: cb1b728096f54 ("tipc: eliminate race condition at multicast reception")
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index cebcc104dc70..022999e0202d 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1265,7 +1265,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 		spin_lock_bh(&inputq->lock);
 		if (skb_peek(arrvq) == skb) {
 			skb_queue_splice_tail_init(&tmpq, inputq);
-			kfree_skb(__skb_dequeue(arrvq));
+			__skb_dequeue(arrvq);
 		}
 		spin_unlock_bh(&inputq->lock);
 		__skb_queue_purge(&tmpq);

From af9d316f3dd6d1385fbd1631b5103e620fc4298a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Mon, 29 Mar 2021 16:03:17 +0200
Subject: [PATCH 1396/1820] dt-bindings: net: ethernet-controller: fix typo in
 NVMEM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The correct property name is "nvmem-cell-names". This is what:
1. Was originally documented in the ethernet.txt
2. Is used in DTS files
3. Matches standard syntax for phandles
4. Linux net subsystem checks for

Fixes: 9d3de3c58347 ("dt-bindings: net: Add YAML schemas for the generic Ethernet options")
Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/ethernet-controller.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 4b7d1e5d003c..e8f04687a3e0 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -49,7 +49,7 @@ properties:
     description:
       Reference to an nvmem node for the MAC address
 
-  nvmem-cells-names:
+  nvmem-cell-names:
     const: mac-address
 
   phy-connection-type:

From 4cd7bd599e273bb75804a406b50cd2c58c40e2e0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <rafal@milecki.pl>
Date: Mon, 29 Mar 2021 17:33:28 +0200
Subject: [PATCH 1397/1820] dt-bindings: net: bcm4908-enet: fix Ethernet
 generic properties
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This binding file uses $ref: ethernet-controller.yaml# so it's required
to use "unevaluatedProperties" (instead of "additionalProperties") to
make Ethernet properties validate.

Fixes: f08b5cf1eb1f ("dt-bindings: net: bcm4908-enet: include ethernet-controller.yaml")
Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml b/Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml
index 79c38ea14237..13c26f23a820 100644
--- a/Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml
+++ b/Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml
@@ -32,7 +32,7 @@ required:
   - interrupts
   - interrupt-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |

From 6e5a03bcba44e080a6bf300194a68ce9bb1e5184 Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Mon, 29 Mar 2021 04:50:02 -0700
Subject: [PATCH 1398/1820] ethernet/netronome/nfp: Fix a use after free in
 nfp_bpf_ctrl_msg_rx

In nfp_bpf_ctrl_msg_rx, if
nfp_ccm_get_type(skb) == NFP_CCM_TYPE_BPF_BPF_EVENT is true, the skb
will be freed. But the skb is still used by nfp_ccm_rx(&bpf->ccm, skb).

My patch adds a return when the skb was freed.

Fixes: bcf0cafab44fd ("nfp: split out common control message handling code")
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/cmsg.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
index 0e2db6ea79e9..2ec62c8d86e1 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
@@ -454,6 +454,7 @@ void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb)
 			dev_consume_skb_any(skb);
 		else
 			dev_kfree_skb_any(skb);
+		return;
 	}
 
 	nfp_ccm_rx(&bpf->ccm, skb);

From 9e67600ed6b8565da4b85698ec659b5879a6c1c6 Mon Sep 17 00:00:00 2001
From: Gulam Mohamed <gulam.mohamed@oracle.com>
Date: Thu, 25 Mar 2021 09:32:48 +0000
Subject: [PATCH 1399/1820] scsi: iscsi: Fix race condition between login and
 sync thread

A kernel panic was observed due to a timing issue between the sync thread
and the initiator processing a login response from the target. The session
reopen can be invoked both from the session sync thread when iscsid
restarts and from iscsid through the error handler. Before the initiator
receives the response to a login, another reopen request can be sent from
the error handler/sync session. When the initial login response is
subsequently processed, the connection has been closed and the socket has
been released.

To fix this a new connection state, ISCSI_CONN_BOUND, is added:

 - Set the connection state value to ISCSI_CONN_DOWN upon
   iscsi_if_ep_disconnect() and iscsi_if_stop_conn()

 - Set the connection state to the newly created value ISCSI_CONN_BOUND
   after bind connection (transport->bind_conn())

 - In iscsi_set_param(), return -ENOTCONN if the connection state is not
   either ISCSI_CONN_BOUND or ISCSI_CONN_UP

Link: https://lore.kernel.org/r/20210325093248.284678-1-gulam.mohamed@oracle.com
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Gulam Mohamed <gulam.mohamed@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

index 91074fd97f64..f4bf62b007a0 100644
---
 drivers/scsi/scsi_transport_iscsi.c | 14 +++++++++++++-
 include/scsi/scsi_transport_iscsi.h |  1 +
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 969d24d580e2..bebfb355abdf 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2471,6 +2471,7 @@ static void iscsi_if_stop_conn(struct iscsi_cls_conn *conn, int flag)
 	 */
 	mutex_lock(&conn_mutex);
 	conn->transport->stop_conn(conn, flag);
+	conn->state = ISCSI_CONN_DOWN;
 	mutex_unlock(&conn_mutex);
 
 }
@@ -2894,6 +2895,13 @@ iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev)
 	default:
 		err = transport->set_param(conn, ev->u.set_param.param,
 					   data, ev->u.set_param.len);
+		if ((conn->state == ISCSI_CONN_BOUND) ||
+			(conn->state == ISCSI_CONN_UP)) {
+			err = transport->set_param(conn, ev->u.set_param.param,
+					data, ev->u.set_param.len);
+		} else {
+			return -ENOTCONN;
+		}
 	}
 
 	return err;
@@ -2953,6 +2961,7 @@ static int iscsi_if_ep_disconnect(struct iscsi_transport *transport,
 		mutex_lock(&conn->ep_mutex);
 		conn->ep = NULL;
 		mutex_unlock(&conn->ep_mutex);
+		conn->state = ISCSI_CONN_DOWN;
 	}
 
 	transport->ep_disconnect(ep);
@@ -3713,6 +3722,8 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
 		ev->r.retcode =	transport->bind_conn(session, conn,
 						ev->u.b_conn.transport_eph,
 						ev->u.b_conn.is_leading);
+		if (!ev->r.retcode)
+			conn->state = ISCSI_CONN_BOUND;
 		mutex_unlock(&conn_mutex);
 
 		if (ev->r.retcode || !transport->ep_connect)
@@ -3944,7 +3955,8 @@ iscsi_conn_attr(local_ipaddr, ISCSI_PARAM_LOCAL_IPADDR);
 static const char *const connection_state_names[] = {
 	[ISCSI_CONN_UP] = "up",
 	[ISCSI_CONN_DOWN] = "down",
-	[ISCSI_CONN_FAILED] = "failed"
+	[ISCSI_CONN_FAILED] = "failed",
+	[ISCSI_CONN_BOUND] = "bound"
 };
 
 static ssize_t show_conn_state(struct device *dev,
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index 8a26a2ffa952..fc5a39839b4b 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -193,6 +193,7 @@ enum iscsi_connection_state {
 	ISCSI_CONN_UP = 0,
 	ISCSI_CONN_DOWN,
 	ISCSI_CONN_FAILED,
+	ISCSI_CONN_BOUND,
 };
 
 struct iscsi_cls_conn {

From ef19e111337f6c3dca7019a8bad5fbc6fb18d635 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Tue, 30 Mar 2021 00:25:06 +0100
Subject: [PATCH 1400/1820] xfrm/compat: Cleanup WARN()s that can be
 user-triggered

Replace WARN_ONCE() that can be triggered from userspace with
pr_warn_once(). Those still give user a hint what's the issue.

I've left WARN()s that are not possible to trigger with current
code-base and that would mean that the code has issues:
- relying on current compat_msg_min[type] <= xfrm_msg_min[type]
- expected 4-byte padding size difference between
  compat_msg_min[type] and xfrm_msg_min[type]
- compat_policy[type].len <= xfrma_policy[type].len
(for every type)

Reported-by: syzbot+834ffd1afc7212eb8147@syzkaller.appspotmail.com
Fixes: 5f3eea6b7e8f ("xfrm/compat: Attach xfrm dumps to 64=>32 bit translator")
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: netdev@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_compat.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
index d8e8a11ca845..a20aec9d7393 100644
--- a/net/xfrm/xfrm_compat.c
+++ b/net/xfrm/xfrm_compat.c
@@ -216,7 +216,7 @@ static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb,
 	case XFRM_MSG_GETSADINFO:
 	case XFRM_MSG_GETSPDINFO:
 	default:
-		WARN_ONCE(1, "unsupported nlmsg_type %d", nlh_src->nlmsg_type);
+		pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type);
 		return ERR_PTR(-EOPNOTSUPP);
 	}
 
@@ -277,7 +277,7 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src)
 		return xfrm_nla_cpy(dst, src, nla_len(src));
 	default:
 		BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID);
-		WARN_ONCE(1, "unsupported nla_type %d", src->nla_type);
+		pr_warn_once("unsupported nla_type %d\n", src->nla_type);
 		return -EOPNOTSUPP;
 	}
 }
@@ -315,8 +315,10 @@ static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src
 	struct sk_buff *new = NULL;
 	int err;
 
-	if (WARN_ON_ONCE(type >= ARRAY_SIZE(xfrm_msg_min)))
+	if (type >= ARRAY_SIZE(xfrm_msg_min)) {
+		pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type);
 		return -EOPNOTSUPP;
+	}
 
 	if (skb_shinfo(skb)->frag_list == NULL) {
 		new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC);
@@ -378,6 +380,10 @@ static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src,
 	struct nlmsghdr *nlmsg = dst;
 	struct nlattr *nla;
 
+	/* xfrm_user_rcv_msg_compat() relies on fact that 32-bit messages
+	 * have the same len or shorted than 64-bit ones.
+	 * 32-bit translation that is bigger than 64-bit original is unexpected.
+	 */
 	if (WARN_ON_ONCE(copy_len > payload))
 		copy_len = payload;
 

From f57011e72f5fe0421ec7a812beb1b57bdf4bb47f Mon Sep 17 00:00:00 2001
From: Stefan Riedmueller <s.riedmueller@phytec.de>
Date: Mon, 29 Mar 2021 15:01:03 +0200
Subject: [PATCH 1401/1820] ARM: dts: imx6: pbab01: Set vmmc supply for both SD
 interfaces

Setting the vmmc supplies is crucial since otherwise the supplying
regulators get disabled and the SD interfaces are no longer powered
which leads to system failures if the system is booted from that SD
interface.

Fixes: 1e44d3f880d5 ("ARM i.MX6Q: dts: Enable I2C1 with EEPROM and PMIC on Phytec phyFLEX-i.MX6 Ouad module")
Signed-off-by: Stefan Riedmueller <s.riedmueller@phytec.de>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
index 7a1e53195785..f28a96fcf23e 100644
--- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
@@ -433,6 +433,7 @@
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
+	vmmc-supply = <&vdd_sd1_reg>;
 	status = "disabled";
 };
 
@@ -442,5 +443,6 @@
 		     &pinctrl_usdhc3_cdwp>;
 	cd-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>;
+	vmmc-supply = <&vdd_sd0_reg>;
 	status = "disabled";
 };

From bec4d7c93afc07dd0454ae41c559513f858cfb83 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 29 Mar 2021 09:07:18 +0300
Subject: [PATCH 1402/1820] thunderbolt: Fix a leak in tb_retimer_add()

After the device_register() succeeds, then the correct way to clean up
is to call device_unregister().  The unregister calls both device_del()
and device_put().  Since this code was only device_del() it results in
a memory leak.

Fixes: dacb12877d92 ("thunderbolt: Add support for on-board retimers")
Cc: stable@vger.kernel.org
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/retimer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c
index 620bcf586ee2..7a5d61604c8b 100644
--- a/drivers/thunderbolt/retimer.c
+++ b/drivers/thunderbolt/retimer.c
@@ -347,7 +347,7 @@ static int tb_retimer_add(struct tb_port *port, u8 index, u32 auth_status)
 	ret = tb_retimer_nvm_add(rt);
 	if (ret) {
 		dev_err(&rt->dev, "failed to add NVM devices: %d\n", ret);
-		device_del(&rt->dev);
+		device_unregister(&rt->dev);
 		return ret;
 	}
 

From 08fe7ae1857080f5075df5ac7fef2ecd4e289117 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 29 Mar 2021 09:08:01 +0300
Subject: [PATCH 1403/1820] thunderbolt: Fix off by one in
 tb_port_find_retimer()

This array uses 1-based indexing so it corrupts memory one element
beyond of the array.  Fix it by making the array one element larger.

Fixes: dacb12877d92 ("thunderbolt: Add support for on-board retimers")
Cc: stable@vger.kernel.org
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/retimer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c
index 7a5d61604c8b..c44fad2b9fbb 100644
--- a/drivers/thunderbolt/retimer.c
+++ b/drivers/thunderbolt/retimer.c
@@ -406,7 +406,7 @@ static struct tb_retimer *tb_port_find_retimer(struct tb_port *port, u8 index)
  */
 int tb_retimer_scan(struct tb_port *port)
 {
-	u32 status[TB_MAX_RETIMER_INDEX] = {};
+	u32 status[TB_MAX_RETIMER_INDEX + 1] = {};
 	int ret, i, last_idx = 0;
 
 	if (!port->cap_usb4)

From c8f79808cd8eb5bc8d14de129bd6d586d3fce0aa Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 29 Mar 2021 13:30:58 +0200
Subject: [PATCH 1404/1820] ALSA: hda: Re-add dropped snd_poewr_change_state()
 calls

The card power state change via snd_power_change_state() at the system
suspend/resume seems dropped mistakenly during the PM code rewrite.
The card power state doesn't play much role nowadays but it's still
referred in a few places such as the HDMI codec driver.

This patch restores them, but in a more appropriate place now in the
prepare and complete callbacks.

Fixes: f5dac54d9d93 ("ALSA: hda: Separate runtime and system suspend")
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210329113059.25035-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_intel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 5eea130dcf0a..c4146e8617de 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1025,6 +1025,7 @@ static int azx_prepare(struct device *dev)
 
 	chip = card->private_data;
 	chip->pm_prepared = 1;
+	snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
 
 	flush_work(&azx_bus(chip)->unsol_work);
 
@@ -1040,6 +1041,7 @@ static void azx_complete(struct device *dev)
 	struct azx *chip;
 
 	chip = card->private_data;
+	snd_power_change_state(card, SNDRV_CTL_POWER_D0);
 	chip->pm_prepared = 0;
 }
 

From 66affb7bb0dc0905155a1b2475261aa704d1ddb5 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 29 Mar 2021 13:30:59 +0200
Subject: [PATCH 1405/1820] ALSA: hda: Add missing sanity checks in PM
 prepare/complete callbacks

The recently added PM prepare and complete callbacks don't have the
sanity check whether the card instance has been properly initialized,
which may potentially lead to Oops.

This patch adds the azx_is_pm_ready() call in each place
appropriately like other PM callbacks.

Fixes: f5dac54d9d93 ("ALSA: hda: Separate runtime and system suspend")
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210329113059.25035-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_intel.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index c4146e8617de..65551eea6752 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1023,6 +1023,9 @@ static int azx_prepare(struct device *dev)
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip;
 
+	if (!azx_is_pm_ready(card))
+		return 0;
+
 	chip = card->private_data;
 	chip->pm_prepared = 1;
 	snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
@@ -1040,6 +1043,9 @@ static void azx_complete(struct device *dev)
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip;
 
+	if (!azx_is_pm_ready(card))
+		return;
+
 	chip = card->private_data;
 	snd_power_change_state(card, SNDRV_CTL_POWER_D0);
 	chip->pm_prepared = 0;

From 417eadfdd9e25188465280edf3668ed163fda2d0 Mon Sep 17 00:00:00 2001
From: Jeremy Szu <jeremy.szu@canonical.com>
Date: Tue, 30 Mar 2021 19:44:27 +0800
Subject: [PATCH 1406/1820] ALSA: hda/realtek: fix mute/micmute LEDs for HP 640
 G8

The HP EliteBook 640 G8 Notebook PC is using ALC236 codec which is
using 0x02 to control mute LED and 0x01 to control micmute LED.
Therefore, add a quirk to make it works.

Signed-off-by: Jeremy Szu <jeremy.szu@canonical.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210330114428.40490-1-jeremy.szu@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index fc2f60c58ad8..58946d069ee5 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -8058,6 +8058,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 		      ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x87f2, "HP ProBook 640 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),

From 9ae31e2ab293bf4d9c42e7079b156072f8a7f8ca Mon Sep 17 00:00:00 2001
From: Mauri Sandberg <sandberg@mailfence.com>
Date: Mon, 29 Mar 2021 15:31:36 +0300
Subject: [PATCH 1407/1820] MIPS: kernel: setup.c: fix compilation error

With ath79_defconfig enabling CONFIG_MIPS_ELF_APPENDED_DTB gives a
compilation error. This patch fixes it.

Build log:
...
  CC      kernel/locking/percpu-rwsem.o
../arch/mips/kernel/setup.c:46:39: error: conflicting types for
'__appended_dtb'
 const char __section(".appended_dtb") __appended_dtb[0x100000];
                                       ^~~~~~~~~~~~~~
In file included from ../arch/mips/kernel/setup.c:34:
../arch/mips/include/asm/bootinfo.h:118:13: note: previous declaration
of '__appended_dtb' was here
 extern char __appended_dtb[];
             ^~~~~~~~~~~~~~
  CC      fs/attr.o
make[4]: *** [../scripts/Makefile.build:271: arch/mips/kernel/setup.o]
 Error 1
...

Root cause seems to be:
Fixes: b83ba0b9df56 ("MIPS: of: Introduce helper function to get DTB")

Signed-off-by: Mauri Sandberg <sandberg@mailfence.com>
Reviewed-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: trivial@kernel.org
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/kernel/setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 279be0153f8b..23a140327a0b 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -43,7 +43,7 @@
 #include <asm/prom.h>
 
 #ifdef CONFIG_MIPS_ELF_APPENDED_DTB
-const char __section(".appended_dtb") __appended_dtb[0x100000];
+char __section(".appended_dtb") __appended_dtb[0x100000];
 #endif /* CONFIG_MIPS_ELF_APPENDED_DTB */
 
 struct cpuinfo_mips cpu_data[NR_CPUS] __read_mostly;

From 59300b36f85f254260c81d9dd09195fa49eb0f98 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Tue, 30 Mar 2021 09:58:38 -0400
Subject: [PATCH 1408/1820] ftrace: Check if pages were allocated before
 calling free_pages()

It is possible that on error pg->size can be zero when getting its order,
which would return a -1 value. It is dangerous to pass in an order of -1
to free_pages(). Check if order is greater than or equal to zero before
calling free_pages().

Link: https://lore.kernel.org/lkml/20210330093916.432697c7@gandalf.local.home/

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4d8e35575549..12223132eff4 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3231,7 +3231,8 @@ ftrace_allocate_pages(unsigned long num_to_init)
 	pg = start_pg;
 	while (pg) {
 		order = get_count_order(pg->size / ENTRIES_PER_PAGE);
-		free_pages((unsigned long)pg->records, order);
+		if (order >= 0)
+			free_pages((unsigned long)pg->records, order);
 		start_pg = pg->next;
 		kfree(pg);
 		pg = start_pg;
@@ -6418,7 +6419,8 @@ void ftrace_release_mod(struct module *mod)
 		clear_mod_from_hashes(pg);
 
 		order = get_count_order(pg->size / ENTRIES_PER_PAGE);
-		free_pages((unsigned long)pg->records, order);
+		if (order >= 0)
+			free_pages((unsigned long)pg->records, order);
 		tmp_page = pg->next;
 		kfree(pg);
 		ftrace_number_of_pages -= 1 << order;
@@ -6778,7 +6780,8 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr)
 		if (!pg->index) {
 			*last_pg = pg->next;
 			order = get_count_order(pg->size / ENTRIES_PER_PAGE);
-			free_pages((unsigned long)pg->records, order);
+			if (order >= 0)
+				free_pages((unsigned long)pg->records, order);
 			ftrace_number_of_pages -= 1 << order;
 			ftrace_number_of_groups--;
 			kfree(pg);

From e720e7d0e983bf05de80b231bccc39f1487f0f16 Mon Sep 17 00:00:00 2001
From: Ilya Lipnitskiy <ilya.lipnitskiy@gmail.com>
Date: Mon, 29 Mar 2021 21:42:08 -0700
Subject: [PATCH 1409/1820] mm: fix race by making init_zero_pfn()
 early_initcall
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are code paths that rely on zero_pfn to be fully initialized
before core_initcall.  For example, wq_sysfs_init() is a core_initcall
function that eventually results in a call to kernel_execve, which
causes a page fault with a subsequent mmput.  If zero_pfn is not
initialized by then it may not get cleaned up properly and result in an
error:

  BUG: Bad rss-counter state mm:(ptrval) type:MM_ANONPAGES val:1

Here is an analysis of the race as seen on a MIPS device. On this
particular MT7621 device (Ubiquiti ER-X), zero_pfn is PFN 0 until
initialized, at which point it becomes PFN 5120:

  1. wq_sysfs_init calls into kobject_uevent_env at core_initcall:
       kobject_uevent_env+0x7e4/0x7ec
       kset_register+0x68/0x88
       bus_register+0xdc/0x34c
       subsys_virtual_register+0x34/0x78
       wq_sysfs_init+0x1c/0x4c
       do_one_initcall+0x50/0x1a8
       kernel_init_freeable+0x230/0x2c8
       kernel_init+0x10/0x100
       ret_from_kernel_thread+0x14/0x1c

  2. kobject_uevent_env() calls call_usermodehelper_exec() which executes
     kernel_execve asynchronously.

  3. Memory allocations in kernel_execve cause a page fault, bumping the
     MM reference counter:
       add_mm_counter_fast+0xb4/0xc0
       handle_mm_fault+0x6e4/0xea0
       __get_user_pages.part.78+0x190/0x37c
       __get_user_pages_remote+0x128/0x360
       get_arg_page+0x34/0xa0
       copy_string_kernel+0x194/0x2a4
       kernel_execve+0x11c/0x298
       call_usermodehelper_exec_async+0x114/0x194

  4. In case zero_pfn has not been initialized yet, zap_pte_range does
     not decrement the MM_ANONPAGES RSS counter and the BUG message is
     triggered shortly afterwards when __mmdrop checks the ref counters:
       __mmdrop+0x98/0x1d0
       free_bprm+0x44/0x118
       kernel_execve+0x160/0x1d8
       call_usermodehelper_exec_async+0x114/0x194
       ret_from_kernel_thread+0x14/0x1c

To avoid races such as described above, initialize init_zero_pfn at
early_initcall level.  Depending on the architecture, ZERO_PAGE is
either constant or gets initialized even earlier, at paging_init, so
there is no issue with initializing zero_pfn earlier.

Link: https://lkml.kernel.org/r/CALCv0x2YqOXEAy2Q=hafjhHCtTHVodChv1qpM=niAXOpqEbt7w@mail.gmail.com
Signed-off-by: Ilya Lipnitskiy <ilya.lipnitskiy@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: stable@vger.kernel.org
Tested-by: 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memory.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/memory.c b/mm/memory.c
index 5efa07fb6cdc..550405fc3b5e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -166,7 +166,7 @@ static int __init init_zero_pfn(void)
 	zero_pfn = page_to_pfn(ZERO_PAGE(0));
 	return 0;
 }
-core_initcall(init_zero_pfn);
+early_initcall(init_zero_pfn);
 
 void mm_trace_rss_stat(struct mm_struct *mm, int member, long count)
 {

From 75f94ecbd0dfd2ac4e671f165f5ae864b7301422 Mon Sep 17 00:00:00 2001
From: Stefan Raspl <raspl@linux.ibm.com>
Date: Thu, 25 Mar 2021 13:29:49 +0100
Subject: [PATCH 1410/1820] tools/kvm_stat: Add restart delay

If this service is enabled and the system rebooted, Systemd's initial
attempt to start this unit file may fail in case the kvm module is not
loaded. Since we did not specify a delay for the retries, Systemd
restarts with a minimum delay a number of times before giving up and
disabling the service. Which means a subsequent kvm module load will
have kvm running without monitoring.
Adding a delay to fix this.

Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Message-Id: <20210325122949.1433271-1-raspl@linux.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/kvm/kvm_stat/kvm_stat.service | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/kvm/kvm_stat/kvm_stat.service b/tools/kvm/kvm_stat/kvm_stat.service
index 71aabaffe779..8f13b843d5b4 100644
--- a/tools/kvm/kvm_stat/kvm_stat.service
+++ b/tools/kvm/kvm_stat/kvm_stat.service
@@ -9,6 +9,7 @@ Type=simple
 ExecStart=/usr/bin/kvm_stat -dtcz -s 10 -L /var/log/kvm_stat.csv
 ExecReload=/bin/kill -HUP $MAINPID
 Restart=always
+RestartSec=60s
 SyslogIdentifier=kvm_stat
 SyslogLevel=debug
 

From d632826f26f2361e6ef18881611928036fac30e6 Mon Sep 17 00:00:00 2001
From: Haiwei Li <lihaiwei@tencent.com>
Date: Sat, 13 Mar 2021 13:10:32 +0800
Subject: [PATCH 1411/1820] KVM: clean up the unused argument

kvm_msr_ignored_check function never uses vcpu argument. Clean up the
function and invokers.

Signed-off-by: Haiwei Li <lihaiwei@tencent.com>
Message-Id: <20210313051032.4171-1-lihaiwei.kernel@gmail.com>
Reviewed-by: Keqian Zhu <zhukeqian1@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fe806e894212..f7d12fca397b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -271,8 +271,7 @@ static struct kmem_cache *x86_emulator_cache;
  * When called, it means the previous get/set msr reached an invalid msr.
  * Return true if we want to ignore/silent this failed msr access.
  */
-static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
-				  u64 data, bool write)
+static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write)
 {
 	const char *op = write ? "wrmsr" : "rdmsr";
 
@@ -1445,7 +1444,7 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	if (r == KVM_MSR_RET_INVALID) {
 		/* Unconditionally clear the output for simplicity */
 		*data = 0;
-		if (kvm_msr_ignored_check(vcpu, index, 0, false))
+		if (kvm_msr_ignored_check(index, 0, false))
 			r = 0;
 	}
 
@@ -1620,7 +1619,7 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu,
 	int ret = __kvm_set_msr(vcpu, index, data, host_initiated);
 
 	if (ret == KVM_MSR_RET_INVALID)
-		if (kvm_msr_ignored_check(vcpu, index, data, true))
+		if (kvm_msr_ignored_check(index, data, true))
 			ret = 0;
 
 	return ret;
@@ -1658,7 +1657,7 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu,
 	if (ret == KVM_MSR_RET_INVALID) {
 		/* Unconditionally clear *data for simplicity */
 		*data = 0;
-		if (kvm_msr_ignored_check(vcpu, index, 0, false))
+		if (kvm_msr_ignored_check(index, 0, false))
 			ret = 0;
 	}
 

From ecaf088f53fcc893cd00c846f53042a536b9630d Mon Sep 17 00:00:00 2001
From: Dongli Zhang <dongli.zhang@oracle.com>
Date: Fri, 26 Mar 2021 00:03:34 -0700
Subject: [PATCH 1412/1820] KVM: x86: remove unused declaration of
 kvm_write_tsc()

kvm_write_tsc() was renamed and made static since commit 0c899c25d754
("KVM: x86: do not attempt TSC synchronization on guest writes"). Remove
its unused declaration.

Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Message-Id: <20210326070334.12310-1-dongli.zhang@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 39eb04887141..9035e34aa156 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -250,7 +250,6 @@ static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu)
 void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs);
 void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
 
-void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr);
 u64 get_kvmclock_ns(struct kvm *kvm);
 
 int kvm_read_guest_virt(struct kvm_vcpu *vcpu,

From 1973cadd4cca08eaeca944f60598f04ab0d80682 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 23 Mar 2021 09:45:15 +0100
Subject: [PATCH 1413/1820] KVM: x86/vPMU: Forbid writing to MSR_F15H_PERF MSRs
 when guest doesn't have X86_FEATURE_PERFCTR_CORE

MSR_F15H_PERF_CTL0-5, MSR_F15H_PERF_CTR0-5 MSRs are only available when
X86_FEATURE_PERFCTR_CORE CPUID bit was exposed to the guest. KVM, however,
allows these MSRs unconditionally because kvm_pmu_is_valid_msr() ->
amd_msr_idx_to_pmc() check always passes and because kvm_pmu_set_msr() ->
amd_pmu_set_msr() doesn't fail.

In case of a counter (CTRn), no big harm is done as we only increase
internal PMC's value but in case of an eventsel (CTLn), we go deep into
perf internals with a non-existing counter.

Note, kvm_get_msr_common() just returns '0' when these MSRs don't exist
and this also seems to contradict architectural behavior which is #GP
(I did check one old Opteron host) but changing this status quo is a bit
scarier.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210323084515.1346540-1-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/pmu.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 035da07500e8..fdf587f19c5f 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -98,6 +98,8 @@ static enum index msr_to_index(u32 msr)
 static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 					     enum pmu_type type)
 {
+	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+
 	switch (msr) {
 	case MSR_F15H_PERF_CTL0:
 	case MSR_F15H_PERF_CTL1:
@@ -105,6 +107,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 	case MSR_F15H_PERF_CTL3:
 	case MSR_F15H_PERF_CTL4:
 	case MSR_F15H_PERF_CTL5:
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+			return NULL;
+		fallthrough;
 	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
 		if (type != PMU_TYPE_EVNTSEL)
 			return NULL;
@@ -115,6 +120,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 	case MSR_F15H_PERF_CTR3:
 	case MSR_F15H_PERF_CTR4:
 	case MSR_F15H_PERF_CTR5:
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+			return NULL;
+		fallthrough;
 	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
 		if (type != PMU_TYPE_COUNTER)
 			return NULL;

From f982fb62a304235397ec092936432199ca50ac4d Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 23 Mar 2021 11:43:31 +0100
Subject: [PATCH 1414/1820] selftests: kvm: make hardware_disable_test less
 verbose

hardware_disable_test produces 512 snippets like
...
 main: [511] waiting semaphore
 run_test: [511] start vcpus
 run_test: [511] all threads launched
 main: [511] waiting 368us
 main: [511] killing child

and this doesn't have much value, let's print this info with pr_debug().

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210323104331.1354800-1-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/hardware_disable_test.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c
index 2f2eeb8a1d86..5aadf84c91c0 100644
--- a/tools/testing/selftests/kvm/hardware_disable_test.c
+++ b/tools/testing/selftests/kvm/hardware_disable_test.c
@@ -108,7 +108,7 @@ static void run_test(uint32_t run)
 	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
 	vm_create_irqchip(vm);
 
-	fprintf(stderr, "%s: [%d] start vcpus\n", __func__, run);
+	pr_debug("%s: [%d] start vcpus\n", __func__, run);
 	for (i = 0; i < VCPU_NUM; ++i) {
 		vm_vcpu_add_default(vm, i, guest_code);
 		payloads[i].vm = vm;
@@ -124,7 +124,7 @@ static void run_test(uint32_t run)
 			check_set_affinity(throw_away, &cpu_set);
 		}
 	}
-	fprintf(stderr, "%s: [%d] all threads launched\n", __func__, run);
+	pr_debug("%s: [%d] all threads launched\n", __func__, run);
 	sem_post(sem);
 	for (i = 0; i < VCPU_NUM; ++i)
 		check_join(threads[i], &b);
@@ -147,16 +147,16 @@ int main(int argc, char **argv)
 		if (pid == 0)
 			run_test(i); /* This function always exits */
 
-		fprintf(stderr, "%s: [%d] waiting semaphore\n", __func__, i);
+		pr_debug("%s: [%d] waiting semaphore\n", __func__, i);
 		sem_wait(sem);
 		r = (rand() % DELAY_US_MAX) + 1;
-		fprintf(stderr, "%s: [%d] waiting %dus\n", __func__, i, r);
+		pr_debug("%s: [%d] waiting %dus\n", __func__, i, r);
 		usleep(r);
 		r = waitpid(pid, &s, WNOHANG);
 		TEST_ASSERT(r != pid,
 			    "%s: [%d] child exited unexpectedly status: [%d]",
 			    __func__, i, s);
-		fprintf(stderr, "%s: [%d] killing child\n", __func__, i);
+		pr_debug("%s: [%d] killing child\n", __func__, i);
 		kill(pid, SIGKILL);
 	}
 

From 6fb3084ab5d9331cfadf07c59cf4a0bd4059bf4a Mon Sep 17 00:00:00 2001
From: Siddharth Chandrasekaran <sidcha@amazon.de>
Date: Wed, 24 Mar 2021 13:43:47 +0100
Subject: [PATCH 1415/1820] KVM: make: Fix out-of-source module builds

Building kvm module out-of-source with,

    make -C $SRC O=$BIN M=arch/x86/kvm

fails to find "irq.h" as the include dir passed to cflags-y does not
prefix the source dir. Fix this by prefixing $(srctree) to the include
dir path.

Signed-off-by: Siddharth Chandrasekaran <sidcha@amazon.de>
Message-Id: <20210324124347.18336-1-sidcha@amazon.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 1b4766fe1de2..eafc4d601f25 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
-ccflags-y += -Iarch/x86/kvm
+ccflags-y += -I $(srctree)/arch/x86/kvm
 ccflags-$(CONFIG_KVM_WERROR) += -Werror
 
 ifeq ($(CONFIG_FRAME_POINTER),y)

From a835429cda91621fca915d80672a157b47738afb Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 25 Mar 2021 13:01:17 -0700
Subject: [PATCH 1416/1820] KVM: x86/mmu: Ensure TLBs are flushed when yielding
 during GFN range zap

When flushing a range of GFNs across multiple roots, ensure any pending
flush from a previous root is honored before yielding while walking the
tables of the current root.

Note, kvm_tdp_mmu_zap_gfn_range() now intentionally overwrites its local
"flush" with the result to avoid redundant flushes.  zap_gfn_range()
preserves and return the incoming "flush", unless of course the flush was
performed prior to yielding and no new flush was triggered.

Fixes: 1af4a96025b3 ("KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed")
Cc: stable@vger.kernel.org
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210325200119.1359384-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/tdp_mmu.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index d78915019b08..f80648ac1d15 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -86,7 +86,7 @@ static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 	list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link)
 
 static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
-			  gfn_t start, gfn_t end, bool can_yield);
+			  gfn_t start, gfn_t end, bool can_yield, bool flush);
 
 void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
@@ -99,7 +99,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 
 	list_del(&root->link);
 
-	zap_gfn_range(kvm, root, 0, max_gfn, false);
+	zap_gfn_range(kvm, root, 0, max_gfn, false, false);
 
 	free_page((unsigned long)root->spt);
 	kmem_cache_free(mmu_page_header_cache, root);
@@ -678,20 +678,21 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
  * scheduler needs the CPU or there is contention on the MMU lock. If this
  * function cannot yield, it will not release the MMU lock or reschedule and
  * the caller must ensure it does not supply too large a GFN range, or the
- * operation can cause a soft lockup.
+ * operation can cause a soft lockup.  Note, in some use cases a flush may be
+ * required by prior actions.  Ensure the pending flush is performed prior to
+ * yielding.
  */
 static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
-			  gfn_t start, gfn_t end, bool can_yield)
+			  gfn_t start, gfn_t end, bool can_yield, bool flush)
 {
 	struct tdp_iter iter;
-	bool flush_needed = false;
 
 	rcu_read_lock();
 
 	tdp_root_for_each_pte(iter, root, start, end) {
 		if (can_yield &&
-		    tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) {
-			flush_needed = false;
+		    tdp_mmu_iter_cond_resched(kvm, &iter, flush)) {
+			flush = false;
 			continue;
 		}
 
@@ -709,11 +710,11 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 			continue;
 
 		tdp_mmu_set_spte(kvm, &iter, 0);
-		flush_needed = true;
+		flush = true;
 	}
 
 	rcu_read_unlock();
-	return flush_needed;
+	return flush;
 }
 
 /*
@@ -728,7 +729,7 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
 	bool flush = false;
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root)
-		flush |= zap_gfn_range(kvm, root, start, end, true);
+		flush = zap_gfn_range(kvm, root, start, end, true, flush);
 
 	return flush;
 }
@@ -940,7 +941,7 @@ static int zap_gfn_range_hva_wrapper(struct kvm *kvm,
 				     struct kvm_mmu_page *root, gfn_t start,
 				     gfn_t end, unsigned long unused)
 {
-	return zap_gfn_range(kvm, root, start, end, false);
+	return zap_gfn_range(kvm, root, start, end, false, false);
 }
 
 int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start,

From 048f49809c526348775425420fb5b8e84fd9a133 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 25 Mar 2021 13:01:18 -0700
Subject: [PATCH 1417/1820] KVM: x86/mmu: Ensure TLBs are flushed for TDP MMU
 during NX zapping

Honor the "flush needed" return from kvm_tdp_mmu_zap_gfn_range(), which
does the flush itself if and only if it yields (which it will never do in
this particular scenario), and otherwise expects the caller to do the
flush.  If pages are zapped from the TDP MMU but not the legacy MMU, then
no flush will occur.

Fixes: 29cf0f5007a2 ("kvm: x86/mmu: NX largepage recovery for TDP MMU")
Cc: stable@vger.kernel.org
Cc: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210325200119.1359384-3-seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d75524bc8423..2705f9fa22b9 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5884,6 +5884,8 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 	struct kvm_mmu_page *sp;
 	unsigned int ratio;
 	LIST_HEAD(invalid_list);
+	bool flush = false;
+	gfn_t gfn_end;
 	ulong to_zap;
 
 	rcu_idx = srcu_read_lock(&kvm->srcu);
@@ -5905,19 +5907,20 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 				      lpage_disallowed_link);
 		WARN_ON_ONCE(!sp->lpage_disallowed);
 		if (is_tdp_mmu_page(sp)) {
-			kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn,
-				sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level));
+			gfn_end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level);
+			flush = kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, gfn_end);
 		} else {
 			kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
 			WARN_ON_ONCE(sp->lpage_disallowed);
 		}
 
 		if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
-			kvm_mmu_commit_zap_page(kvm, &invalid_list);
+			kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
 			cond_resched_rwlock_write(&kvm->mmu_lock);
+			flush = false;
 		}
 	}
-	kvm_mmu_commit_zap_page(kvm, &invalid_list);
+	kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
 
 	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, rcu_idx);

From 33a3164161fc86b9cc238f7f2aa2ccb1d5559b1c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 25 Mar 2021 13:01:19 -0700
Subject: [PATCH 1418/1820] KVM: x86/mmu: Don't allow TDP MMU to yield when
 recovering NX pages

Prevent the TDP MMU from yielding when zapping a gfn range during NX
page recovery.  If a flush is pending from a previous invocation of the
zapping helper, either in the TDP MMU or the legacy MMU, but the TDP MMU
has not accumulated a flush for the current invocation, then yielding
will release mmu_lock with stale TLB entries.

That being said, this isn't technically a bug fix in the current code, as
the TDP MMU will never yield in this case.  tdp_mmu_iter_cond_resched()
will yield if and only if it has made forward progress, as defined by the
current gfn vs. the last yielded (or starting) gfn.  Because zapping a
single shadow page is guaranteed to (a) find that page and (b) step
sideways at the level of the shadow page, the TDP iter will break its loop
before getting a chance to yield.

But that is all very, very subtle, and will break at the slightest sneeze,
e.g. zapping while holding mmu_lock for read would break as the TDP MMU
wouldn't be guaranteed to see the present shadow page, and thus could step
sideways at a lower level.

Cc: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210325200119.1359384-4-seanjc@google.com>
[Add lockdep assertion. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c     |  4 +---
 arch/x86/kvm/mmu/tdp_mmu.c |  5 +++--
 arch/x86/kvm/mmu/tdp_mmu.h | 24 +++++++++++++++++++++++-
 3 files changed, 27 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2705f9fa22b9..486aa94ecf1d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5885,7 +5885,6 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 	unsigned int ratio;
 	LIST_HEAD(invalid_list);
 	bool flush = false;
-	gfn_t gfn_end;
 	ulong to_zap;
 
 	rcu_idx = srcu_read_lock(&kvm->srcu);
@@ -5907,8 +5906,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 				      lpage_disallowed_link);
 		WARN_ON_ONCE(!sp->lpage_disallowed);
 		if (is_tdp_mmu_page(sp)) {
-			gfn_end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level);
-			flush = kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, gfn_end);
+			flush = kvm_tdp_mmu_zap_sp(kvm, sp);
 		} else {
 			kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
 			WARN_ON_ONCE(sp->lpage_disallowed);
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index f80648ac1d15..81352cd428fa 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -723,13 +723,14 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
  * SPTEs have been cleared and a TLB flush is needed before releasing the
  * MMU lock.
  */
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+				 bool can_yield)
 {
 	struct kvm_mmu_page *root;
 	bool flush = false;
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root)
-		flush = zap_gfn_range(kvm, root, start, end, true, flush);
+		flush = zap_gfn_range(kvm, root, start, end, can_yield, flush);
 
 	return flush;
 }
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 3b761c111bff..31096ece9b14 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -8,7 +8,29 @@
 hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
 void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root);
 
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end);
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+				 bool can_yield);
+static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start,
+					     gfn_t end)
+{
+	return __kvm_tdp_mmu_zap_gfn_range(kvm, start, end, true);
+}
+static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level);
+
+	/*
+	 * Don't allow yielding, as the caller may have a flush pending.  Note,
+	 * if mmu_lock is held for write, zapping will never yield in this case,
+	 * but explicitly disallow it for safety.  The TDP MMU does not yield
+	 * until it has made forward progress (steps sideways), and when zapping
+	 * a single shadow page that it's guaranteed to see (thus the mmu_lock
+	 * requirement), its "step sideways" will always step beyond the bounds
+	 * of the shadow page's gfn range and stop iterating before yielding.
+	 */
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	return __kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, end, false);
+}
 void kvm_tdp_mmu_zap_all(struct kvm *kvm);
 
 int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,

From f8fb97c915954fc6de6513cdf277103b5c6df7b3 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Tue, 2 Mar 2021 16:15:06 +0300
Subject: [PATCH 1419/1820] drm/tegra: dc: Don't set PLL clock to 0Hz

RGB output doesn't allow to change parent clock rate of the display and
PCLK rate is set to 0Hz in this case. The tegra_dc_commit_state() shall
not set the display clock to 0Hz since this change propagates to the
parent clock. The DISP clock is defined as a NODIV clock by the tegra-clk
driver and all NODIV clocks use the CLK_SET_RATE_PARENT flag.

This bug stayed unnoticed because by default PLLP is used as the parent
clock for the display controller and PLLP silently skips the erroneous 0Hz
rate changes because it always has active child clocks that don't permit
rate changes. The PLLP isn't acceptable for some devices that we want to
upstream (like Samsung Galaxy Tab and ASUS TF700T) due to a display panel
clock rate requirements that can't be fulfilled by using PLLP and then the
bug pops up in this case since parent clock is set to 0Hz, killing the
display output.

Don't touch DC clock if pclk=0 in order to fix the problem.

Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/tegra/dc.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 0ae3a025efe9..24362533e14c 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -1688,6 +1688,11 @@ static void tegra_dc_commit_state(struct tegra_dc *dc,
 			dev_err(dc->dev,
 				"failed to set clock rate to %lu Hz\n",
 				state->pclk);
+
+		err = clk_set_rate(dc->clk, state->pclk);
+		if (err < 0)
+			dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n",
+				dc->clk, state->pclk, err);
 	}
 
 	DRM_DEBUG_KMS("rate: %lu, div: %u\n", clk_get_rate(dc->clk),
@@ -1698,11 +1703,6 @@ static void tegra_dc_commit_state(struct tegra_dc *dc,
 		value = SHIFT_CLK_DIVIDER(state->div) | PIXEL_CLK_DIVIDER_PCD1;
 		tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL);
 	}
-
-	err = clk_set_rate(dc->clk, state->pclk);
-	if (err < 0)
-		dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n",
-			dc->clk, state->pclk, err);
 }
 
 static void tegra_dc_stop(struct tegra_dc *dc)

From a24f98176d1efae2c37d3438c57a624d530d9c33 Mon Sep 17 00:00:00 2001
From: Mikko Perttunen <mperttunen@nvidia.com>
Date: Mon, 29 Mar 2021 16:38:27 +0300
Subject: [PATCH 1420/1820] gpu: host1x: Use different lock classes for each
 client

To avoid false lockdep warnings, give each client lock a different
lock class, passed from the initialization site by macro.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/host1x/bus.c | 10 ++++++----
 include/linux/host1x.h   |  9 ++++++++-
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index 347fb962b6c9..68a766ff0e9d 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -705,8 +705,9 @@ void host1x_driver_unregister(struct host1x_driver *driver)
 EXPORT_SYMBOL(host1x_driver_unregister);
 
 /**
- * host1x_client_register() - register a host1x client
+ * __host1x_client_register() - register a host1x client
  * @client: host1x client
+ * @key: lock class key for the client-specific mutex
  *
  * Registers a host1x client with each host1x controller instance. Note that
  * each client will only match their parent host1x controller and will only be
@@ -715,13 +716,14 @@ EXPORT_SYMBOL(host1x_driver_unregister);
  * device and call host1x_device_init(), which will in turn call each client's
  * &host1x_client_ops.init implementation.
  */
-int host1x_client_register(struct host1x_client *client)
+int __host1x_client_register(struct host1x_client *client,
+			     struct lock_class_key *key)
 {
 	struct host1x *host1x;
 	int err;
 
 	INIT_LIST_HEAD(&client->list);
-	mutex_init(&client->lock);
+	__mutex_init(&client->lock, "host1x client lock", key);
 	client->usecount = 0;
 
 	mutex_lock(&devices_lock);
@@ -742,7 +744,7 @@ int host1x_client_register(struct host1x_client *client)
 
 	return 0;
 }
-EXPORT_SYMBOL(host1x_client_register);
+EXPORT_SYMBOL(__host1x_client_register);
 
 /**
  * host1x_client_unregister() - unregister a host1x client
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index ce59a6a6a008..9eb77c87a83b 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -320,7 +320,14 @@ static inline struct host1x_device *to_host1x_device(struct device *dev)
 int host1x_device_init(struct host1x_device *device);
 int host1x_device_exit(struct host1x_device *device);
 
-int host1x_client_register(struct host1x_client *client);
+int __host1x_client_register(struct host1x_client *client,
+			     struct lock_class_key *key);
+#define host1x_client_register(class) \
+	({ \
+		static struct lock_class_key __key; \
+		__host1x_client_register(class, &__key); \
+	})
+
 int host1x_client_unregister(struct host1x_client *client);
 
 int host1x_client_suspend(struct host1x_client *client);

From a31500fe7055451ed9043c8fff938dfa6f70ee37 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Fri, 19 Mar 2021 08:06:37 +0100
Subject: [PATCH 1421/1820] drm/tegra: dc: Restore coupling of display
 controllers

Coupling of display controllers used to rely on runtime PM to take the
companion controller out of reset. Commit fd67e9c6ed5a ("drm/tegra: Do
not implement runtime PM") accidentally broke this when runtime PM was
removed.

Restore this functionality by reusing the hierarchical host1x client
suspend/resume infrastructure that's similar to runtime PM and which
perfectly fits this use-case.

Fixes: fd67e9c6ed5a ("drm/tegra: Do not implement runtime PM")
Reported-by: Dmitry Osipenko <digetx@gmail.com>
Reported-by: Paul Fertser <fercerpav@gmail.com>
Tested-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/tegra/dc.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 24362533e14c..134986dc2783 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -2501,22 +2501,18 @@ static int tegra_dc_couple(struct tegra_dc *dc)
 	 * POWER_CONTROL registers during CRTC enabling.
 	 */
 	if (dc->soc->coupled_pm && dc->pipe == 1) {
-		u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER;
-		struct device_link *link;
-		struct device *partner;
+		struct device *companion;
+		struct tegra_dc *parent;
 
-		partner = driver_find_device(dc->dev->driver, NULL, NULL,
-					     tegra_dc_match_by_pipe);
-		if (!partner)
+		companion = driver_find_device(dc->dev->driver, NULL, (const void *)0,
+					       tegra_dc_match_by_pipe);
+		if (!companion)
 			return -EPROBE_DEFER;
 
-		link = device_link_add(dc->dev, partner, flags);
-		if (!link) {
-			dev_err(dc->dev, "failed to link controllers\n");
-			return -EINVAL;
-		}
+		parent = dev_get_drvdata(companion);
+		dc->client.parent = &parent->client;
 
-		dev_dbg(dc->dev, "coupled to %s\n", dev_name(partner));
+		dev_dbg(dc->dev, "coupled to %s\n", dev_name(companion));
 	}
 
 	return 0;

From 12efebab09e383bf366bec323bd296b7d90e1c43 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sat, 10 Oct 2020 11:17:44 -0400
Subject: [PATCH 1422/1820] XArray: Fix split documentation

I wrote the documentation backwards; the new order of the entry is stored
in the xas and the caller passes the old entry.

Reported-by: Zi Yan <ziy@nvidia.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 lib/xarray.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/lib/xarray.c b/lib/xarray.c
index 5fa51614802a..fb3a0ccebb7e 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -987,7 +987,7 @@ static void node_set_marks(struct xa_node *node, unsigned int offset,
  * xas_split_alloc() - Allocate memory for splitting an entry.
  * @xas: XArray operation state.
  * @entry: New entry which will be stored in the array.
- * @order: New entry order.
+ * @order: Current entry order.
  * @gfp: Memory allocation flags.
  *
  * This function should be called before calling xas_split().
@@ -1041,9 +1041,10 @@ EXPORT_SYMBOL_GPL(xas_split_alloc);
  * xas_split() - Split a multi-index entry into smaller entries.
  * @xas: XArray operation state.
  * @entry: New entry to store in the array.
- * @order: New entry order.
+ * @order: Current entry order.
  *
- * The value in the entry is copied to all the replacement entries.
+ * The size of the new entries is set in @xas.  The value in @entry is
+ * copied to all the replacement entries.
  *
  * Context: Any context.  The caller should hold the xa_lock.
  */

From 3012110d71f41410932924e1d188f9eb57f1f824 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 19 Nov 2020 08:32:31 -0500
Subject: [PATCH 1423/1820] XArray: Fix splitting to non-zero orders

Splitting an order-4 entry into order-2 entries would leave the array
containing pointers to 000040008000c000 instead of 000044448888cccc.
This is a one-character fix, but enhance the test suite to check this
case.

Reported-by: Zi Yan <ziy@nvidia.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 lib/test_xarray.c | 26 ++++++++++++++------------
 lib/xarray.c      |  4 ++--
 2 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 8294f43f4981..8b1c318189ce 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1530,24 +1530,24 @@ static noinline void check_store_range(struct xarray *xa)
 
 #ifdef CONFIG_XARRAY_MULTI
 static void check_split_1(struct xarray *xa, unsigned long index,
-							unsigned int order)
+				unsigned int order, unsigned int new_order)
 {
-	XA_STATE(xas, xa, index);
-	void *entry;
-	unsigned int i = 0;
+	XA_STATE_ORDER(xas, xa, index, new_order);
+	unsigned int i;
 
 	xa_store_order(xa, index, order, xa, GFP_KERNEL);
 
 	xas_split_alloc(&xas, xa, order, GFP_KERNEL);
 	xas_lock(&xas);
 	xas_split(&xas, xa, order);
+	for (i = 0; i < (1 << order); i += (1 << new_order))
+		__xa_store(xa, index + i, xa_mk_index(index + i), 0);
 	xas_unlock(&xas);
 
-	xa_for_each(xa, index, entry) {
-		XA_BUG_ON(xa, entry != xa);
-		i++;
+	for (i = 0; i < (1 << order); i++) {
+		unsigned int val = index + (i & ~((1 << new_order) - 1));
+		XA_BUG_ON(xa, xa_load(xa, index + i) != xa_mk_index(val));
 	}
-	XA_BUG_ON(xa, i != 1 << order);
 
 	xa_set_mark(xa, index, XA_MARK_0);
 	XA_BUG_ON(xa, !xa_get_mark(xa, index, XA_MARK_0));
@@ -1557,14 +1557,16 @@ static void check_split_1(struct xarray *xa, unsigned long index,
 
 static noinline void check_split(struct xarray *xa)
 {
-	unsigned int order;
+	unsigned int order, new_order;
 
 	XA_BUG_ON(xa, !xa_empty(xa));
 
 	for (order = 1; order < 2 * XA_CHUNK_SHIFT; order++) {
-		check_split_1(xa, 0, order);
-		check_split_1(xa, 1UL << order, order);
-		check_split_1(xa, 3UL << order, order);
+		for (new_order = 0; new_order < order; new_order++) {
+			check_split_1(xa, 0, order, new_order);
+			check_split_1(xa, 1UL << order, order, new_order);
+			check_split_1(xa, 3UL << order, order, new_order);
+		}
 	}
 }
 #else
diff --git a/lib/xarray.c b/lib/xarray.c
index fb3a0ccebb7e..f5d8f54907b4 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1011,7 +1011,7 @@ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order,
 
 	do {
 		unsigned int i;
-		void *sibling;
+		void *sibling = NULL;
 		struct xa_node *node;
 
 		node = kmem_cache_alloc(radix_tree_node_cachep, gfp);
@@ -1021,7 +1021,7 @@ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order,
 		for (i = 0; i < XA_CHUNK_SIZE; i++) {
 			if ((i & mask) == 0) {
 				RCU_INIT_POINTER(node->slots[i], entry);
-				sibling = xa_mk_sibling(0);
+				sibling = xa_mk_sibling(i);
 			} else {
 				RCU_INIT_POINTER(node->slots[i], sibling);
 			}

From df59d0a461bc5935232bf56a279e4d7a71c566a5 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 30 Mar 2021 13:40:27 -0400
Subject: [PATCH 1424/1820] XArray: Add xa_limit_16b

A 16-bit limit is a more common limit than I had realised.  Make it
generally available.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/xarray.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 92c0160b3352..a91e3d90df8a 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -229,9 +229,10 @@ static inline int xa_err(void *entry)
  *
  * This structure is used either directly or via the XA_LIMIT() macro
  * to communicate the range of IDs that are valid for allocation.
- * Two common ranges are predefined for you:
+ * Three common ranges are predefined for you:
  * * xa_limit_32b	- [0 - UINT_MAX]
  * * xa_limit_31b	- [0 - INT_MAX]
+ * * xa_limit_16b	- [0 - USHRT_MAX]
  */
 struct xa_limit {
 	u32 max;
@@ -242,6 +243,7 @@ struct xa_limit {
 
 #define xa_limit_32b	XA_LIMIT(0, UINT_MAX)
 #define xa_limit_31b	XA_LIMIT(0, INT_MAX)
+#define xa_limit_16b	XA_LIMIT(0, USHRT_MAX)
 
 typedef unsigned __bitwise xa_mark_t;
 #define XA_MARK_0		((__force xa_mark_t)0U)

From 7487de534dcbe143e6f41da751dd3ffcf93b00ee Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 30 Mar 2021 13:44:35 -0400
Subject: [PATCH 1425/1820] radix tree test suite: Fix compilation

Commit 4bba4c4bb09a added tools/include/linux/compiler_types.h which
includes linux/compiler-gcc.h.  Unfortunately, we had our own (empty)
compiler_types.h which overrode the one added by that commit, and
so we lost the definition of __must_be_array().  Removing our empty
compiler_types.h fixes the problem and reduces our divergence from the
rest of the tools.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 tools/testing/radix-tree/linux/compiler_types.h | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 delete mode 100644 tools/testing/radix-tree/linux/compiler_types.h

diff --git a/tools/testing/radix-tree/linux/compiler_types.h b/tools/testing/radix-tree/linux/compiler_types.h
deleted file mode 100644
index e69de29bb2d1..000000000000

From ac097aecfef0bb289ca53d2fe0b73fc7e1612a05 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Fri, 19 Mar 2021 14:17:22 +0100
Subject: [PATCH 1426/1820] drm/tegra: sor: Grab runtime PM reference across
 reset

The SOR resets are exclusively shared with the SOR power domain. This
means that exclusive access can only be granted temporarily and in order
for that to work, a rigorous sequence must be observed. To ensure that a
single consumer gets exclusive access to a reset, each consumer must
implement a rigorous protocol using the reset_control_acquire() and
reset_control_release() functions.

However, these functions alone don't provide any guarantees at the
system level. Drivers need to ensure that the only a single consumer has
access to the reset at the same time. In order for the SOR to be able to
exclusively access its reset, it must therefore ensure that the SOR
power domain is not powered off by holding on to a runtime PM reference
to that power domain across the reset assert/deassert operation.

This used to work fine by accident, but was revealed when recently more
devices started to rely on the SOR power domain.

Fixes: 11c632e1cfd3 ("drm/tegra: sor: Implement acquire/release for reset")
Reported-by: Jonathan Hunter <jonathanh@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/tegra/sor.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c
index f02a035dda45..7b88261f57bb 100644
--- a/drivers/gpu/drm/tegra/sor.c
+++ b/drivers/gpu/drm/tegra/sor.c
@@ -3115,6 +3115,12 @@ static int tegra_sor_init(struct host1x_client *client)
 	 * kernel is possible.
 	 */
 	if (sor->rst) {
+		err = pm_runtime_resume_and_get(sor->dev);
+		if (err < 0) {
+			dev_err(sor->dev, "failed to get runtime PM: %d\n", err);
+			return err;
+		}
+
 		err = reset_control_acquire(sor->rst);
 		if (err < 0) {
 			dev_err(sor->dev, "failed to acquire SOR reset: %d\n",
@@ -3148,6 +3154,7 @@ static int tegra_sor_init(struct host1x_client *client)
 		}
 
 		reset_control_release(sor->rst);
+		pm_runtime_put(sor->dev);
 	}
 
 	err = clk_prepare_enable(sor->clk_safe);

From 3e759425cc3cf9a43392309819d34c65a3644c59 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 30 Mar 2021 20:49:32 +0200
Subject: [PATCH 1427/1820] ACPI: scan: Fix _STA getting called on devices with
 unmet dependencies

Commit 71da201f38df ("ACPI: scan: Defer enumeration of devices with
_DEP lists") dropped the following 2 lines from acpi_init_device_object():

	/* Assume there are unmet deps until acpi_device_dep_initialize() runs */
	device->dep_unmet = 1;

Leaving the initial value of dep_unmet at the 0 from the kzalloc(). This
causes the acpi_bus_get_status() call in acpi_add_single_object() to
actually call _STA, even though there maybe unmet deps, leading to errors
like these:

[    0.123579] ACPI Error: No handler for Region [ECRM] (00000000ba9edc4c)
               [GenericSerialBus] (20170831/evregion-166)
[    0.123601] ACPI Error: Region GenericSerialBus (ID=9) has no handler
               (20170831/exfldio-299)
[    0.123618] ACPI Error: Method parse/execution failed
               \_SB.I2C1.BAT1._STA, AE_NOT_EXIST (20170831/psparse-550)

Fix this by re-adding the dep_unmet = 1 initialization to
acpi_init_device_object() and modifying acpi_bus_check_add() to make sure
that dep_unmet always gets setup there, overriding the initial 1 value.

This re-fixes the issue initially fixed by
commit 63347db0affa ("ACPI / scan: Use acpi_bus_get_status() to initialize
ACPI_TYPE_DEVICE devs"), which introduced the removed
"device->dep_unmet = 1;" statement.

This issue was noticed; and the fix tested on a Dell Venue 10 Pro 5055.

Fixes: 71da201f38df ("ACPI: scan: Defer enumeration of devices with _DEP lists")
Suggested-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Cc: 5.11+ <stable@vger.kernel.org> # 5.11+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/scan.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 84bb7c1929f1..6efe7edd7b1e 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1670,6 +1670,8 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 	device_initialize(&device->dev);
 	dev_set_uevent_suppress(&device->dev, true);
 	acpi_init_coherency(device);
+	/* Assume there are unmet deps to start with. */
+	device->dep_unmet = 1;
 }
 
 void acpi_device_add_finalize(struct acpi_device *device)
@@ -1933,6 +1935,8 @@ static void acpi_scan_dep_init(struct acpi_device *adev)
 {
 	struct acpi_dep_data *dep;
 
+	adev->dep_unmet = 0;
+
 	mutex_lock(&acpi_dep_list_lock);
 
 	list_for_each_entry(dep, &acpi_dep_list, node) {
@@ -1980,7 +1984,13 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep,
 		return AE_CTRL_DEPTH;
 
 	acpi_scan_init_hotplug(device);
-	if (!check_dep)
+	/*
+	 * If check_dep is true at this point, the device has no dependencies,
+	 * or the creation of the device object would have been postponed above.
+	 */
+	if (check_dep)
+		device->dep_unmet = 0;
+	else
 		acpi_scan_dep_init(device);
 
 out:

From 03cb4d05b4ea9a3491674ca40952adb708d549fa Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@us.ibm.com>
Date: Mon, 29 Mar 2021 10:20:39 -0500
Subject: [PATCH 1428/1820] net/ncsi: Avoid channel_monitor hrtimer deadlock

Calling ncsi_stop_channel_monitor from channel_monitor is a guaranteed
deadlock on SMP because stop calls del_timer_sync on the timer that
invoked channel_monitor as its timer function.

Recognise the inherent race of marking the monitor disabled before
deleting the timer by just returning if enable was cleared.  After
a timeout (the default case -- reset to START when response received)
just mark the monitor.enabled false.

If the channel has an entry on the channel_queue list, or if the
state is not ACTIVE or INACTIVE, then warn and mark the timer stopped
and don't restart, as the locking is broken somehow.

Fixes: 0795fb2021f0 ("net/ncsi: Stop monitor if channel times out or is inactive")
Signed-off-by: Milton Miller <miltonm@us.ibm.com>
Signed-off-by: Eddie James <eajames@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ncsi/ncsi-manage.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index a9cb355324d1..ffff8da707b8 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -105,13 +105,20 @@ static void ncsi_channel_monitor(struct timer_list *t)
 	monitor_state = nc->monitor.state;
 	spin_unlock_irqrestore(&nc->lock, flags);
 
-	if (!enabled || chained) {
-		ncsi_stop_channel_monitor(nc);
-		return;
-	}
+	if (!enabled)
+		return;		/* expected race disabling timer */
+	if (WARN_ON_ONCE(chained))
+		goto bad_state;
+
 	if (state != NCSI_CHANNEL_INACTIVE &&
 	    state != NCSI_CHANNEL_ACTIVE) {
-		ncsi_stop_channel_monitor(nc);
+bad_state:
+		netdev_warn(ndp->ndev.dev,
+			    "Bad NCSI monitor state channel %d 0x%x %s queue\n",
+			    nc->id, state, chained ? "on" : "off");
+		spin_lock_irqsave(&nc->lock, flags);
+		nc->monitor.enabled = false;
+		spin_unlock_irqrestore(&nc->lock, flags);
 		return;
 	}
 
@@ -136,10 +143,9 @@ static void ncsi_channel_monitor(struct timer_list *t)
 		ncsi_report_link(ndp, true);
 		ndp->flags |= NCSI_DEV_RESHUFFLE;
 
-		ncsi_stop_channel_monitor(nc);
-
 		ncm = &nc->modes[NCSI_MODE_LINK];
 		spin_lock_irqsave(&nc->lock, flags);
+		nc->monitor.enabled = false;
 		nc->state = NCSI_CHANNEL_INVISIBLE;
 		ncm->data[2] &= ~0x1;
 		spin_unlock_irqrestore(&nc->lock, flags);

From 6855e8213e06efcaf7c02a15e12b1ae64b9a7149 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Tue, 30 Mar 2021 04:23:23 +0530
Subject: [PATCH 1429/1820] net: sched: bump refcount for new action in ACT
 replace mode

Currently, action creation using ACT API in replace mode is buggy.
When invoking for non-existent action index 42,

	tc action replace action bpf obj foo.o sec <xyz> index 42

kernel creates the action, fills up the netlink response, and then just
deletes the action after notifying userspace.

	tc action show action bpf

doesn't list the action.

This happens due to the following sequence when ovr = 1 (replace mode)
is enabled:

tcf_idr_check_alloc is used to atomically check and either obtain
reference for existing action at index, or reserve the index slot using
a dummy entry (ERR_PTR(-EBUSY)).

This is necessary as pointers to these actions will be held after
dropping the idrinfo lock, so bumping the reference count is necessary
as we need to insert the actions, and notify userspace by dumping their
attributes. Finally, we drop the reference we took using the
tcf_action_put_many call in tcf_action_add. However, for the case where
a new action is created due to free index, its refcount remains one.
This when paired with the put_many call leads to the kernel setting up
the action, notifying userspace of its creation, and then tearing it
down. For existing actions, the refcount is still held so they remain
unaffected.

Fortunately due to rtnl_lock serialization requirement, such an action
with refcount == 1 will not be concurrently deleted by anything else, at
best CLS API can move its refcount up and down by binding to it after it
has been published from tcf_idr_insert_many. Since refcount is atleast
one until put_many call, CLS API cannot delete it. Also __tcf_action_put
release path already ensures deterministic outcome (either new action
will be created or existing action will be reused in case CLS API tries
to bind to action concurrently) due to idr lock serialization.

We fix this by making refcount of newly created actions as 2 in ACT API
replace mode. A relaxed store will suffice as visibility is ensured only
after the tcf_idr_insert_many call.

Note that in case of creation or overwriting using CLS API only (i.e.
bind = 1), overwriting existing action object is not allowed, and any
such request is silently ignored (without error).

The refcount bump that occurs in tcf_idr_check_alloc call there for
existing action will pair with tcf_exts_destroy call made from the
owner module for the same action. In case of action creation, there
is no existing action, so no tcf_exts_destroy callback happens.

This means no code changes for CLS API.

Fixes: cae422f379f3 ("net: sched: use reference counting action init")
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index b919826939e0..43cceb924976 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1042,6 +1042,9 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	if (err != ACT_P_CREATED)
 		module_put(a_o->owner);
 
+	if (!bind && ovr && err == ACT_P_CREATED)
+		refcount_set(&a->tcfa_refcnt, 2);
+
 	return a;
 
 err_out:

From 82734c5b1b24c020d701cf90ccb075e43a5ccb07 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 29 Mar 2021 06:52:44 -0600
Subject: [PATCH 1430/1820] io_uring: drop sqd lock before handling signals for
 SQPOLL

Don't call into get_signal() with the sqd mutex held, it'll fail if we're
freezing the task and we'll get complaints on locks still being held:

====================================
WARNING: iou-sqp-8386/8387 still has locks held!
5.12.0-rc4-syzkaller #0 Not tainted
------------------------------------
1 lock held by iou-sqp-8386/8387:
 #0: ffff88801e1d2470 (&sqd->lock){+.+.}-{3:3}, at: io_sq_thread+0x24c/0x13a0 fs/io_uring.c:6731

 stack backtrace:
 CPU: 1 PID: 8387 Comm: iou-sqp-8386 Not tainted 5.12.0-rc4-syzkaller #0
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
 Call Trace:
  __dump_stack lib/dump_stack.c:79 [inline]
  dump_stack+0x141/0x1d7 lib/dump_stack.c:120
  try_to_freeze include/linux/freezer.h:66 [inline]
  get_signal+0x171a/0x2150 kernel/signal.c:2576
  io_sq_thread+0x8d2/0x13a0 fs/io_uring.c:6748

Fold the get_signal() case in with the parking checks, as we need to drop
the lock in both cases, and since we need to be checking for parking when
juggling the lock anyway.

Reported-by: syzbot+796d767eb376810256f5@syzkaller.appspotmail.com
Fixes: dbe1bdbb39db ("io_uring: handle signals for IO threads like a normal thread")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 088a9d3c420a..6d7a1b69712b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6733,22 +6733,25 @@ static int io_sq_thread(void *data)
 		int ret;
 		bool cap_entries, sqt_spin, needs_sched;
 
-		if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) {
+		if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) ||
+		    signal_pending(current)) {
+			bool did_sig = false;
+
 			mutex_unlock(&sqd->lock);
+			if (signal_pending(current)) {
+				struct ksignal ksig;
+
+				did_sig = get_signal(&ksig);
+			}
 			cond_resched();
 			mutex_lock(&sqd->lock);
+			if (did_sig)
+				break;
 			io_run_task_work();
 			io_run_task_work_head(&sqd->park_task_work);
 			timeout = jiffies + sqd->sq_thread_idle;
 			continue;
 		}
-		if (signal_pending(current)) {
-			struct ksignal ksig;
-
-			if (!get_signal(&ksig))
-				continue;
-			break;
-		}
 		sqt_spin = false;
 		cap_entries = !list_is_singular(&sqd->ctx_list);
 		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {

From 8a03dd925786bdc3834d56ccc980bb70668efa35 Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Tue, 30 Mar 2021 16:11:08 +0200
Subject: [PATCH 1431/1820] net: qrtr: Fix memory leak on qrtr_tx_wait failure

qrtr_tx_wait does not check for radix_tree_insert failure, causing
the 'flow' object to be unreferenced after qrtr_tx_wait return. Fix
that by releasing flow on radix_tree_insert failure.

Fixes: 5fdeb0d372ab ("net: qrtr: Implement outgoing flow control")
Reported-by: syzbot+739016799a89c530b32a@syzkaller.appspotmail.com
Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index dfc820ee553a..1e4fb568fa84 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -271,7 +271,10 @@ static int qrtr_tx_wait(struct qrtr_node *node, int dest_node, int dest_port,
 		flow = kzalloc(sizeof(*flow), GFP_KERNEL);
 		if (flow) {
 			init_waitqueue_head(&flow->resume_tx);
-			radix_tree_insert(&node->qrtr_tx_flow, key, flow);
+			if (radix_tree_insert(&node->qrtr_tx_flow, key, flow)) {
+				kfree(flow);
+				flow = NULL;
+			}
 		}
 	}
 	mutex_unlock(&node->qrtr_tx_lock);

From ae81feb7338c89cee4e6aa0424bdab2ce2b52da2 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Tue, 30 Mar 2021 22:27:48 +0800
Subject: [PATCH 1432/1820] sch_htb: fix null pointer dereference on a null
 new_q

sch_htb: fix null pointer dereference on a null new_q

Currently if new_q is null, the null new_q pointer will be
dereference when 'q->offload' is true. Fix this by adding
a braces around htb_parent_to_leaf_offload() to avoid it.

Addresses-Coverity: ("Dereference after null check")
Fixes: d03b195b5aa0 ("sch_htb: Hierarchical QoS hardware offload")

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_htb.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 62e12cb41a3e..081c11d5717c 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1675,9 +1675,10 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg,
 					  cl->parent->common.classid,
 					  NULL);
 		if (q->offload) {
-			if (new_q)
+			if (new_q) {
 				htb_set_lockdep_class_child(new_q);
-			htb_parent_to_leaf_offload(sch, dev_queue, new_q);
+				htb_parent_to_leaf_offload(sch, dev_queue, new_q);
+			}
 		}
 	}
 

From 9adc89af724f12a03b47099cd943ed54e877cd59 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 30 Mar 2021 18:43:54 +0200
Subject: [PATCH 1433/1820] net: let skb_orphan_partial wake-up waiters.

Currently the mentioned helper can end-up freeing the socket wmem
without waking-up any processes waiting for more write memory.

If the partially orphaned skb is attached to an UDP (or raw) socket,
the lack of wake-up can hang the user-space.

Even for TCP sockets not calling the sk destructor could have bad
effects on TSQ.

Address the issue using skb_orphan to release the sk wmem before
setting the new sock_efree destructor. Additionally bundle the
whole ownership update in a new helper, so that later other
potential users could avoid duplicate code.

v1 -> v2:
 - use skb_orphan() instead of sort of open coding it (Eric)
 - provide an helper for the ownership change (Eric)

Fixes: f6ba8d33cfbb ("netem: fix skb_orphan_partial()")
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h |  9 +++++++++
 net/core/sock.c    | 12 +++---------
 2 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 0b6266fd6bf6..3e3a5da2ce5a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2221,6 +2221,15 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
+static inline void skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk)
+{
+	if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) {
+		skb_orphan(skb);
+		skb->destructor = sock_efree;
+		skb->sk = sk;
+	}
+}
+
 void sk_reset_timer(struct sock *sk, struct timer_list *timer,
 		    unsigned long expires);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index cc31b601ae10..5ec90f99e102 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2132,16 +2132,10 @@ void skb_orphan_partial(struct sk_buff *skb)
 	if (skb_is_tcp_pure_ack(skb))
 		return;
 
-	if (can_skb_orphan_partial(skb)) {
-		struct sock *sk = skb->sk;
-
-		if (refcount_inc_not_zero(&sk->sk_refcnt)) {
-			WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc));
-			skb->destructor = sock_efree;
-		}
-	} else {
+	if (can_skb_orphan_partial(skb))
+		skb_set_owner_sk_safe(skb, skb->sk);
+	else
 		skb_orphan(skb);
-	}
 }
 EXPORT_SYMBOL(skb_orphan_partial);
 

From 5e46d1b78a03d52306f21f77a4e4a144b6d31486 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Date: Sun, 21 Mar 2021 23:37:49 +0900
Subject: [PATCH 1434/1820] reiserfs: update reiserfs_xattrs_initialized()
 condition

syzbot is reporting NULL pointer dereference at reiserfs_security_init()
[1], for commit ab17c4f02156c4f7 ("reiserfs: fixup xattr_root caching")
is assuming that REISERFS_SB(s)->xattr_root != NULL in
reiserfs_xattr_jcreate_nblocks() despite that commit made
REISERFS_SB(sb)->priv_root != NULL && REISERFS_SB(s)->xattr_root == NULL
case possible.

I guess that commit 6cb4aff0a77cc0e6 ("reiserfs: fix oops while creating
privroot with selinux enabled") wanted to check xattr_root != NULL
before reiserfs_xattr_jcreate_nblocks(), for the changelog is talking
about the xattr root.

  The issue is that while creating the privroot during mount
  reiserfs_security_init calls reiserfs_xattr_jcreate_nblocks which
  dereferences the xattr root. The xattr root doesn't exist, so we get
  an oops.

Therefore, update reiserfs_xattrs_initialized() to check both the
privroot and the xattr root.

Link: https://syzkaller.appspot.com/bug?id=8abaedbdeb32c861dc5340544284167dd0e46cde # [1]
Reported-and-tested-by: syzbot <syzbot+690cb1e51970435f9775@syzkaller.appspotmail.com>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Fixes: 6cb4aff0a77c ("reiserfs: fix oops while creating privroot with selinux enabled")
Acked-by: Jeff Mahoney <jeffm@suse.com>
Acked-by: Jan Kara <jack@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/reiserfs/xattr.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h
index 9b3b06da568c..e47fde1182de 100644
--- a/fs/reiserfs/xattr.h
+++ b/fs/reiserfs/xattr.h
@@ -44,7 +44,7 @@ void reiserfs_security_free(struct reiserfs_security_handle *sec);
 
 static inline int reiserfs_xattrs_initialized(struct super_block *sb)
 {
-	return REISERFS_SB(sb)->priv_root != NULL;
+	return REISERFS_SB(sb)->priv_root && REISERFS_SB(sb)->xattr_root;
 }
 
 #define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header))

From 0e07e25b481aa021e4b48085ecb8a049e9614510 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 30 Mar 2021 16:24:11 +0200
Subject: [PATCH 1435/1820] netfilter: flowtable: fix NAT IPv6 offload mangling

Fix out-of-bound access in the address array.

Fixes: 5c27d8d76ce8 ("netfilter: nf_flow_table_offload: add IPv6 support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_flow_table_offload.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 2a6993fa40d7..1c5460e7bce8 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -305,12 +305,12 @@ static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule,
 				     const __be32 *addr, const __be32 *mask)
 {
 	struct flow_action_entry *entry;
-	int i;
+	int i, j;
 
-	for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32)) {
+	for (i = 0, j = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32), j++) {
 		entry = flow_action_entry_next(flow_rule);
 		flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6,
-				    offset + i, &addr[i], mask);
+				    offset + i, &addr[j], mask);
 	}
 }
 

From fbea31808ca124dd73ff6bb1e67c9af4607c3e32 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 31 Mar 2021 01:04:45 +0200
Subject: [PATCH 1436/1820] netfilter: conntrack: do not print icmpv6 as
 unknown via /proc

/proc/net/nf_conntrack shows icmpv6 as unknown.

Fixes: 09ec82f5af99 ("netfilter: conntrack: remove protocol name from l4proto struct")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_standalone.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 0ee702d374b0..c6c0cb465664 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -266,6 +266,7 @@ static const char* l4proto_name(u16 proto)
 	case IPPROTO_GRE: return "gre";
 	case IPPROTO_SCTP: return "sctp";
 	case IPPROTO_UDPLITE: return "udplite";
+	case IPPROTO_ICMPV6: return "icmpv6";
 	}
 
 	return "unknown";

From 2ea538dbee1c79f6f6c24a6f2f82986e4b7ccb78 Mon Sep 17 00:00:00 2001
From: Yinjun Zhang <yinjun.zhang@corigine.com>
Date: Tue, 30 Mar 2021 10:30:23 +0200
Subject: [PATCH 1437/1820] nfp: flower: ignore duplicate merge hints from FW

A merge hint message needs some time to process before the merged
flow actually reaches the firmware, during which we may get duplicate
merge hints if there're more than one packet that hit the pre-merged
flow. And processing duplicate merge hints will cost extra host_ctx's
which are a limited resource.

Avoid the duplicate merge by using hash table to store the sub_flows
to be merged.

Fixes: 8af56f40e53b ("nfp: flower: offload merge flows")
Signed-off-by: Yinjun Zhang <yinjun.zhang@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/netronome/nfp/flower/main.h  |  8 ++++
 .../ethernet/netronome/nfp/flower/metadata.c  | 16 ++++++-
 .../ethernet/netronome/nfp/flower/offload.c   | 48 ++++++++++++++++++-
 3 files changed, 69 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index caf12eec9945..56833a41f3d2 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -190,6 +190,7 @@ struct nfp_fl_internal_ports {
  * @qos_rate_limiters:	Current active qos rate limiters
  * @qos_stats_lock:	Lock on qos stats updates
  * @pre_tun_rule_cnt:	Number of pre-tunnel rules offloaded
+ * @merge_table:	Hash table to store merged flows
  */
 struct nfp_flower_priv {
 	struct nfp_app *app;
@@ -223,6 +224,7 @@ struct nfp_flower_priv {
 	unsigned int qos_rate_limiters;
 	spinlock_t qos_stats_lock; /* Protect the qos stats */
 	int pre_tun_rule_cnt;
+	struct rhashtable merge_table;
 };
 
 /**
@@ -350,6 +352,12 @@ struct nfp_fl_payload_link {
 };
 
 extern const struct rhashtable_params nfp_flower_table_params;
+extern const struct rhashtable_params merge_table_params;
+
+struct nfp_merge_info {
+	u64 parent_ctx;
+	struct rhash_head ht_node;
+};
 
 struct nfp_fl_stats_frame {
 	__be32 stats_con_id;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index aa06fcb38f8b..327bb56b3ef5 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -490,6 +490,12 @@ const struct rhashtable_params nfp_flower_table_params = {
 	.automatic_shrinking	= true,
 };
 
+const struct rhashtable_params merge_table_params = {
+	.key_offset	= offsetof(struct nfp_merge_info, parent_ctx),
+	.head_offset	= offsetof(struct nfp_merge_info, ht_node),
+	.key_len	= sizeof(u64),
+};
+
 int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
 			     unsigned int host_num_mems)
 {
@@ -506,6 +512,10 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
 	if (err)
 		goto err_free_flow_table;
 
+	err = rhashtable_init(&priv->merge_table, &merge_table_params);
+	if (err)
+		goto err_free_stats_ctx_table;
+
 	get_random_bytes(&priv->mask_id_seed, sizeof(priv->mask_id_seed));
 
 	/* Init ring buffer and unallocated mask_ids. */
@@ -513,7 +523,7 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
 		kmalloc_array(NFP_FLOWER_MASK_ENTRY_RS,
 			      NFP_FLOWER_MASK_ELEMENT_RS, GFP_KERNEL);
 	if (!priv->mask_ids.mask_id_free_list.buf)
-		goto err_free_stats_ctx_table;
+		goto err_free_merge_table;
 
 	priv->mask_ids.init_unallocated = NFP_FLOWER_MASK_ENTRY_RS - 1;
 
@@ -550,6 +560,8 @@ err_free_last_used:
 	kfree(priv->mask_ids.last_used);
 err_free_mask_id:
 	kfree(priv->mask_ids.mask_id_free_list.buf);
+err_free_merge_table:
+	rhashtable_destroy(&priv->merge_table);
 err_free_stats_ctx_table:
 	rhashtable_destroy(&priv->stats_ctx_table);
 err_free_flow_table:
@@ -568,6 +580,8 @@ void nfp_flower_metadata_cleanup(struct nfp_app *app)
 				    nfp_check_rhashtable_empty, NULL);
 	rhashtable_free_and_destroy(&priv->stats_ctx_table,
 				    nfp_check_rhashtable_empty, NULL);
+	rhashtable_free_and_destroy(&priv->merge_table,
+				    nfp_check_rhashtable_empty, NULL);
 	kvfree(priv->stats);
 	kfree(priv->mask_ids.mask_id_free_list.buf);
 	kfree(priv->mask_ids.last_used);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index d72225d64a75..e95969c462e4 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1009,6 +1009,8 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
 	struct netlink_ext_ack *extack = NULL;
 	struct nfp_fl_payload *merge_flow;
 	struct nfp_fl_key_ls merge_key_ls;
+	struct nfp_merge_info *merge_info;
+	u64 parent_ctx = 0;
 	int err;
 
 	ASSERT_RTNL();
@@ -1019,6 +1021,15 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
 	    nfp_flower_is_merge_flow(sub_flow2))
 		return -EINVAL;
 
+	/* check if the two flows are already merged */
+	parent_ctx = (u64)(be32_to_cpu(sub_flow1->meta.host_ctx_id)) << 32;
+	parent_ctx |= (u64)(be32_to_cpu(sub_flow2->meta.host_ctx_id));
+	if (rhashtable_lookup_fast(&priv->merge_table,
+				   &parent_ctx, merge_table_params)) {
+		nfp_flower_cmsg_warn(app, "The two flows are already merged.\n");
+		return 0;
+	}
+
 	err = nfp_flower_can_merge(sub_flow1, sub_flow2);
 	if (err)
 		return err;
@@ -1060,16 +1071,33 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
 	if (err)
 		goto err_release_metadata;
 
+	merge_info = kmalloc(sizeof(*merge_info), GFP_KERNEL);
+	if (!merge_info) {
+		err = -ENOMEM;
+		goto err_remove_rhash;
+	}
+	merge_info->parent_ctx = parent_ctx;
+	err = rhashtable_insert_fast(&priv->merge_table, &merge_info->ht_node,
+				     merge_table_params);
+	if (err)
+		goto err_destroy_merge_info;
+
 	err = nfp_flower_xmit_flow(app, merge_flow,
 				   NFP_FLOWER_CMSG_TYPE_FLOW_MOD);
 	if (err)
-		goto err_remove_rhash;
+		goto err_remove_merge_info;
 
 	merge_flow->in_hw = true;
 	sub_flow1->in_hw = false;
 
 	return 0;
 
+err_remove_merge_info:
+	WARN_ON_ONCE(rhashtable_remove_fast(&priv->merge_table,
+					    &merge_info->ht_node,
+					    merge_table_params));
+err_destroy_merge_info:
+	kfree(merge_info);
 err_remove_rhash:
 	WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table,
 					    &merge_flow->fl_node,
@@ -1359,7 +1387,9 @@ nfp_flower_remove_merge_flow(struct nfp_app *app,
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_payload_link *link, *temp;
+	struct nfp_merge_info *merge_info;
 	struct nfp_fl_payload *origin;
+	u64 parent_ctx = 0;
 	bool mod = false;
 	int err;
 
@@ -1396,8 +1426,22 @@ nfp_flower_remove_merge_flow(struct nfp_app *app,
 err_free_links:
 	/* Clean any links connected with the merged flow. */
 	list_for_each_entry_safe(link, temp, &merge_flow->linked_flows,
-				 merge_flow.list)
+				 merge_flow.list) {
+		u32 ctx_id = be32_to_cpu(link->sub_flow.flow->meta.host_ctx_id);
+
+		parent_ctx = (parent_ctx << 32) | (u64)(ctx_id);
 		nfp_flower_unlink_flow(link);
+	}
+
+	merge_info = rhashtable_lookup_fast(&priv->merge_table,
+					    &parent_ctx,
+					    merge_table_params);
+	if (merge_info) {
+		WARN_ON_ONCE(rhashtable_remove_fast(&priv->merge_table,
+						    &merge_info->ht_node,
+						    merge_table_params));
+		kfree(merge_info);
+	}
 
 	kfree(merge_flow->action_data);
 	kfree(merge_flow->mask_data);

From c056d480b40a68f2520ccc156c7fae672d69d57d Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 30 Mar 2021 15:00:24 -0700
Subject: [PATCH 1438/1820] net: phy: broadcom: Only advertise EEE for
 supported modes

We should not be advertising EEE for modes that we do not support,
correct that oversight by looking at the PHY device supported linkmodes.

Fixes: 99cec8a4dda2 ("net: phy: broadcom: Allow enabling or disabling of EEE")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm-phy-lib.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c
index 53282a6d5928..287cccf8f7f4 100644
--- a/drivers/net/phy/bcm-phy-lib.c
+++ b/drivers/net/phy/bcm-phy-lib.c
@@ -369,7 +369,7 @@ EXPORT_SYMBOL_GPL(bcm_phy_enable_apd);
 
 int bcm_phy_set_eee(struct phy_device *phydev, bool enable)
 {
-	int val;
+	int val, mask = 0;
 
 	/* Enable EEE at PHY level */
 	val = phy_read_mmd(phydev, MDIO_MMD_AN, BRCM_CL45VEN_EEE_CONTROL);
@@ -388,10 +388,17 @@ int bcm_phy_set_eee(struct phy_device *phydev, bool enable)
 	if (val < 0)
 		return val;
 
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+			      phydev->supported))
+		mask |= MDIO_EEE_1000T;
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+			      phydev->supported))
+		mask |= MDIO_EEE_100TX;
+
 	if (enable)
-		val |= (MDIO_EEE_100TX | MDIO_EEE_1000T);
+		val |= mask;
 	else
-		val &= ~(MDIO_EEE_100TX | MDIO_EEE_1000T);
+		val &= ~mask;
 
 	phy_write_mmd(phydev, MDIO_MMD_AN, BCM_CL45VEN_EEE_ADV, (u32)val);
 

From 61431a5907fc36d0738e9a547c7e1556349a03e9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 30 Mar 2021 16:43:43 -0700
Subject: [PATCH 1439/1820] net: ensure mac header is set in
 virtio_net_hdr_to_skb()

Commit 924a9bc362a5 ("net: check if protocol extracted by virtio_net_hdr_set_proto is correct")
added a call to dev_parse_header_protocol() but mac_header is not yet set.

This means that eth_hdr() reads complete garbage, and syzbot complained about it [1]

This patch resets mac_header earlier, to get more coverage about this change.

Audit of virtio_net_hdr_to_skb() callers shows that this change should be safe.

[1]

BUG: KASAN: use-after-free in eth_header_parse_protocol+0xdc/0xe0 net/ethernet/eth.c:282
Read of size 2 at addr ffff888017a6200b by task syz-executor313/8409

CPU: 1 PID: 8409 Comm: syz-executor313 Not tainted 5.12.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:79 [inline]
 dump_stack+0x141/0x1d7 lib/dump_stack.c:120
 print_address_description.constprop.0.cold+0x5b/0x2f8 mm/kasan/report.c:232
 __kasan_report mm/kasan/report.c:399 [inline]
 kasan_report.cold+0x7c/0xd8 mm/kasan/report.c:416
 eth_header_parse_protocol+0xdc/0xe0 net/ethernet/eth.c:282
 dev_parse_header_protocol include/linux/netdevice.h:3177 [inline]
 virtio_net_hdr_to_skb.constprop.0+0x99d/0xcd0 include/linux/virtio_net.h:83
 packet_snd net/packet/af_packet.c:2994 [inline]
 packet_sendmsg+0x2325/0x52b0 net/packet/af_packet.c:3031
 sock_sendmsg_nosec net/socket.c:654 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:674
 sock_no_sendpage+0xf3/0x130 net/core/sock.c:2860
 kernel_sendpage.part.0+0x1ab/0x350 net/socket.c:3631
 kernel_sendpage net/socket.c:3628 [inline]
 sock_sendpage+0xe5/0x140 net/socket.c:947
 pipe_to_sendpage+0x2ad/0x380 fs/splice.c:364
 splice_from_pipe_feed fs/splice.c:418 [inline]
 __splice_from_pipe+0x43e/0x8a0 fs/splice.c:562
 splice_from_pipe fs/splice.c:597 [inline]
 generic_splice_sendpage+0xd4/0x140 fs/splice.c:746
 do_splice_from fs/splice.c:767 [inline]
 do_splice+0xb7e/0x1940 fs/splice.c:1079
 __do_splice+0x134/0x250 fs/splice.c:1144
 __do_sys_splice fs/splice.c:1350 [inline]
 __se_sys_splice fs/splice.c:1332 [inline]
 __x64_sys_splice+0x198/0x250 fs/splice.c:1332
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46

Fixes: 924a9bc362a5 ("net: check if protocol extracted by virtio_net_hdr_set_proto is correct")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Balazs Nemeth <bnemeth@redhat.com>
Cc: Willem de Bruijn <willemb@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 6b5fcfa1e555..98775d7fa696 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -62,6 +62,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 			return -EINVAL;
 	}
 
+	skb_reset_mac_header(skb);
+
 	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
 		u16 start = __virtio16_to_cpu(little_endian, hdr->csum_start);
 		u16 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);

From fc85dc42a38405099f97aa2af709fe9504a82508 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Wed, 31 Mar 2021 09:27:41 +0300
Subject: [PATCH 1440/1820] ARM: OMAP2+: Fix uninitialized sr_inst

Fix uninitialized sr_inst.

Fixes: fbfa463be8dc ("ARM: OMAP2+: Fix smartreflex init regression after dropping legacy data")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/sr_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/mach-omap2/sr_device.c b/arch/arm/mach-omap2/sr_device.c
index 17b66f0d0dee..605925684b0a 100644
--- a/arch/arm/mach-omap2/sr_device.c
+++ b/arch/arm/mach-omap2/sr_device.c
@@ -188,7 +188,7 @@ static const char * const dra7_sr_instances[] = {
 
 int __init omap_devinit_smartreflex(void)
 {
-	const char * const *sr_inst;
+	const char * const *sr_inst = NULL;
 	int i, nr_sr = 0;
 
 	if (soc_is_omap44xx()) {

From 942bfbecc0281c75db84f744b9b77b0f2396f484 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=91=A8=E7=90=B0=E6=9D=B0=20=28Zhou=20Yanjie=29?=
 <zhouyanjie@wanyeetech.com>
Date: Fri, 19 Mar 2021 18:12:13 +0800
Subject: [PATCH 1441/1820] I2C: JZ4780: Fix bug for Ingenic X1000.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Only send "X1000_I2C_DC_STOP" when last byte, or it will cause
error when I2C write operation which should look like this:

device_addr + w, reg_addr, data;

But without this patch, it looks like this:

device_addr + w, reg_addr, device_addr + w, data;

Fixes: 21575a7a8d4c ("I2C: JZ4780: Add support for the X1000.")
Reported-by: 杨文龙 (Yang Wenlong) <ywltyut@sina.cn>
Tested-by: 杨文龙 (Yang Wenlong) <ywltyut@sina.cn>
Signed-off-by: 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-jz4780.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c
index 8509c5f11356..55177eb21d7b 100644
--- a/drivers/i2c/busses/i2c-jz4780.c
+++ b/drivers/i2c/busses/i2c-jz4780.c
@@ -525,8 +525,8 @@ static irqreturn_t jz4780_i2c_irq(int irqno, void *dev_id)
 				i2c_sta = jz4780_i2c_readw(i2c, JZ4780_I2C_STA);
 				data = *i2c->wbuf;
 				data &= ~JZ4780_I2C_DC_READ;
-				if ((!i2c->stop_hold) && (i2c->cdata->version >=
-						ID_X1000))
+				if ((i2c->wt_len == 1) && (!i2c->stop_hold) &&
+						(i2c->cdata->version >= ID_X1000))
 					data |= X1000_I2C_DC_STOP;
 				jz4780_i2c_writew(i2c, JZ4780_I2C_DC, data);
 				i2c->wbuf++;

From 67ff1d98652ac141f46b3871ebc34350ddffa2ef Mon Sep 17 00:00:00 2001
From: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Date: Wed, 24 Mar 2021 19:36:10 +0530
Subject: [PATCH 1442/1820] i2c: stm32f4: Mundane typo fix

s/postion/position/

Signed-off-by: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Alain Volmat <alain.volmat@foss.st.com>
Reviewed-by: Pierre-Yves MORDRET <pierre-yves.mordret@foss.st.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-stm32f4.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-stm32f4.c b/drivers/i2c/busses/i2c-stm32f4.c
index 937c2c8fd349..4933fc8ce3fd 100644
--- a/drivers/i2c/busses/i2c-stm32f4.c
+++ b/drivers/i2c/busses/i2c-stm32f4.c
@@ -534,7 +534,7 @@ static void stm32f4_i2c_handle_rx_addr(struct stm32f4_i2c_dev *i2c_dev)
 	default:
 		/*
 		 * N-byte reception:
-		 * Enable ACK, reset POS (ACK postion) and clear ADDR flag.
+		 * Enable ACK, reset POS (ACK position) and clear ADDR flag.
 		 * In that way, ACK will be sent as soon as the current byte
 		 * will be received in the shift register
 		 */

From 1ae6b3780848c6b1efc6b994963082cfd04ac114 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@kernel.org>
Date: Mon, 29 Mar 2021 21:24:09 +0200
Subject: [PATCH 1443/1820] i2c: imx: drop me as maintainer of binding docs

I dunno why I got added here, but I haven't been using this driver for
years. Remove me to make space for interested parties.

Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 Documentation/devicetree/bindings/i2c/i2c-imx.yaml | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx.yaml b/Documentation/devicetree/bindings/i2c/i2c-imx.yaml
index f23966b0d6c6..f33c6b29966b 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-imx.yaml
+++ b/Documentation/devicetree/bindings/i2c/i2c-imx.yaml
@@ -6,9 +6,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Freescale Inter IC (I2C) and High Speed Inter IC (HS-I2C) for i.MX
 
-maintainers:
-  - Wolfram Sang <wolfram@the-dreams.de>
-
 allOf:
   - $ref: /schemas/i2c/i2c-controller.yaml#
 

From 98a479991dc5b986d9d48a1b73f568e58e3d82b6 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@kernel.org>
Date: Mon, 29 Mar 2021 21:25:41 +0200
Subject: [PATCH 1444/1820] i2c: gpio: update email address in binding docs

Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 Documentation/devicetree/bindings/i2c/i2c-gpio.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml b/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml
index ff99344788ab..fd040284561f 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml
+++ b/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Bindings for GPIO bitbanged I2C
 
 maintainers:
-  - Wolfram Sang <wolfram@the-dreams.de>
+  - Wolfram Sang <wsa@kernel.org>
 
 allOf:
   - $ref: /schemas/i2c/i2c-controller.yaml#

From 629a411f7e71afeee34edd4c1418c4e7f7d5575a Mon Sep 17 00:00:00 2001
From: Hao Fang <fanghao11@huawei.com>
Date: Tue, 30 Mar 2021 14:37:14 +0800
Subject: [PATCH 1445/1820] i2c: hix5hd2: use the correct HiSilicon copyright

s/Hisilicon/HiSilicon/g.
It should use capital S, according to
https://www.hisilicon.com/en/terms-of-use.

Signed-off-by: Hao Fang <fanghao11@huawei.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-hix5hd2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-hix5hd2.c b/drivers/i2c/busses/i2c-hix5hd2.c
index c45f226c2b85..aa00ba8bcb70 100644
--- a/drivers/i2c/busses/i2c-hix5hd2.c
+++ b/drivers/i2c/busses/i2c-hix5hd2.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014 Linaro Ltd.
- * Copyright (c) 2014 Hisilicon Limited.
+ * Copyright (c) 2014 HiSilicon Limited.
  *
  * Now only support 7 bit address.
  */

From 7c0d6e482062eb5c06ecccfab340abc523bdca00 Mon Sep 17 00:00:00 2001
From: Bastian Germann <bage@linutronix.de>
Date: Wed, 31 Mar 2021 17:18:43 +0200
Subject: [PATCH 1446/1820] ASoC: sunxi: sun4i-codec: fill ASoC card owner

card->owner is a required property and since commit 81033c6b584b ("ALSA:
core: Warn on empty module") a warning is issued if it is empty. Add it.
This fixes following warning observed on Lamobo R1:

WARNING: CPU: 1 PID: 190 at sound/core/init.c:207 snd_card_new+0x430/0x480 [snd]
Modules linked in: sun4i_codec(E+) sun4i_backend(E+) snd_soc_core(E) ...
CPU: 1 PID: 190 Comm: systemd-udevd Tainted: G         C  E     5.10.0-1-armmp #1 Debian 5.10.4-1
Hardware name: Allwinner sun7i (A20) Family
Call trace:
 (snd_card_new [snd])
 (snd_soc_bind_card [snd_soc_core])
 (snd_soc_register_card [snd_soc_core])
 (sun4i_codec_probe [sun4i_codec])

Fixes: 45fb6b6f2aa3 ("ASoC: sunxi: add support for the on-chip codec on early Allwinner SoCs")
Related: commit 3c27ea23ffb4 ("ASoC: qcom: Set card->owner to avoid warnings")
Related: commit ec653df2a0cb ("drm/vc4/vc4_hdmi: fill ASoC card owner")
Cc: linux-arm-kernel@lists.infradead.org
Cc: alsa-devel@alsa-project.org
Signed-off-by: Bastian Germann <bage@linutronix.de>
Link: https://lore.kernel.org/r/20210331151843.30583-1-bage@linutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sunxi/sun4i-codec.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c
index 6c13cc84b3fb..2173991c13db 100644
--- a/sound/soc/sunxi/sun4i-codec.c
+++ b/sound/soc/sunxi/sun4i-codec.c
@@ -1364,6 +1364,7 @@ static struct snd_soc_card *sun4i_codec_create_card(struct device *dev)
 		return ERR_PTR(-ENOMEM);
 
 	card->dev		= dev;
+	card->owner		= THIS_MODULE;
 	card->name		= "sun4i-codec";
 	card->dapm_widgets	= sun4i_codec_card_dapm_widgets;
 	card->num_dapm_widgets	= ARRAY_SIZE(sun4i_codec_card_dapm_widgets);
@@ -1396,6 +1397,7 @@ static struct snd_soc_card *sun6i_codec_create_card(struct device *dev)
 		return ERR_PTR(-ENOMEM);
 
 	card->dev		= dev;
+	card->owner		= THIS_MODULE;
 	card->name		= "A31 Audio Codec";
 	card->dapm_widgets	= sun6i_codec_card_dapm_widgets;
 	card->num_dapm_widgets	= ARRAY_SIZE(sun6i_codec_card_dapm_widgets);
@@ -1449,6 +1451,7 @@ static struct snd_soc_card *sun8i_a23_codec_create_card(struct device *dev)
 		return ERR_PTR(-ENOMEM);
 
 	card->dev		= dev;
+	card->owner		= THIS_MODULE;
 	card->name		= "A23 Audio Codec";
 	card->dapm_widgets	= sun6i_codec_card_dapm_widgets;
 	card->num_dapm_widgets	= ARRAY_SIZE(sun6i_codec_card_dapm_widgets);
@@ -1487,6 +1490,7 @@ static struct snd_soc_card *sun8i_h3_codec_create_card(struct device *dev)
 		return ERR_PTR(-ENOMEM);
 
 	card->dev		= dev;
+	card->owner		= THIS_MODULE;
 	card->name		= "H3 Audio Codec";
 	card->dapm_widgets	= sun6i_codec_card_dapm_widgets;
 	card->num_dapm_widgets	= ARRAY_SIZE(sun6i_codec_card_dapm_widgets);
@@ -1525,6 +1529,7 @@ static struct snd_soc_card *sun8i_v3s_codec_create_card(struct device *dev)
 		return ERR_PTR(-ENOMEM);
 
 	card->dev		= dev;
+	card->owner		= THIS_MODULE;
 	card->name		= "V3s Audio Codec";
 	card->dapm_widgets	= sun6i_codec_card_dapm_widgets;
 	card->num_dapm_widgets	= ARRAY_SIZE(sun6i_codec_card_dapm_widgets);

From 23cf00ddd2e1aacf1873e43f5e0c519c120daf7a Mon Sep 17 00:00:00 2001
From: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Date: Mon, 29 Mar 2021 14:41:12 +0300
Subject: [PATCH 1447/1820] gpio: sysfs: Obey valid_mask

Do not allow exporting GPIOs which are set invalid
by the driver's valid mask.

Fixes: 726cb3ba4969 ("gpiolib: Support 'gpio-reserved-ranges' property")
Signed-off-by: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 drivers/gpio/gpiolib-sysfs.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index 26c5466b8179..ae49bb23c6ed 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -458,6 +458,8 @@ static ssize_t export_store(struct class *class,
 	long			gpio;
 	struct gpio_desc	*desc;
 	int			status;
+	struct gpio_chip	*gc;
+	int			offset;
 
 	status = kstrtol(buf, 0, &gpio);
 	if (status < 0)
@@ -469,6 +471,12 @@ static ssize_t export_store(struct class *class,
 		pr_warn("%s: invalid GPIO %ld\n", __func__, gpio);
 		return -EINVAL;
 	}
+	gc = desc->gdev->chip;
+	offset = gpio_chip_hwgpio(desc);
+	if (!gpiochip_line_is_valid(gc, offset)) {
+		pr_warn("%s: GPIO %ld masked\n", __func__, gpio);
+		return -EINVAL;
+	}
 
 	/* No extra locking here; FLAG_SYSFS just signifies that the
 	 * request and export were done by on behalf of userspace, so

From d24f847e54214049814b9515771622eaab3f42ab Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@nvidia.com>
Date: Tue, 9 Mar 2021 01:29:01 +0200
Subject: [PATCH 1448/1820] net/mlx5e: Fix mapping of ct_label zero

ct_label 0 is a default label each flow has and therefore
there can be rules that match on ct_label=0 without a prior
rule that set the ct_label to this value.

The ct_label value is not used directly in the HW rules and
instead it is mapped to some id within a defined range and this
id is used to set and match the metadata register which carries
the ct_label.

If we have a rule that matches on ct_label=0, the hw rule will
perform matching on a value that is != 0 because of the mapping
from label to id. Since the metadata register default value is
0 and it was never set before to anything else by an action that
sets the ct_label, there will always be a mismatch between that
register and the value in the rule.

To support such rule, a forced mapping of ct_label 0 to id=0
is done so that it will match the metadata register default
value of 0.

Fixes: 54b154ecfb8c ("net/mlx5e: CT: Map 128 bits labels to 32 bit map ID")
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en/tc_ct.c    | 36 +++++++++++++++----
 1 file changed, 29 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index b2cd29847a37..68e54cc1cd16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -185,6 +185,28 @@ mlx5_tc_ct_entry_has_nat(struct mlx5_ct_entry *entry)
 	return !!(entry->tuple_nat_node.next);
 }
 
+static int
+mlx5_get_label_mapping(struct mlx5_tc_ct_priv *ct_priv,
+		       u32 *labels, u32 *id)
+{
+	if (!memchr_inv(labels, 0, sizeof(u32) * 4)) {
+		*id = 0;
+		return 0;
+	}
+
+	if (mapping_add(ct_priv->labels_mapping, labels, id))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static void
+mlx5_put_label_mapping(struct mlx5_tc_ct_priv *ct_priv, u32 id)
+{
+	if (id)
+		mapping_remove(ct_priv->labels_mapping, id);
+}
+
 static int
 mlx5_tc_ct_rule_to_tuple(struct mlx5_ct_tuple *tuple, struct flow_rule *rule)
 {
@@ -436,7 +458,7 @@ mlx5_tc_ct_entry_del_rule(struct mlx5_tc_ct_priv *ct_priv,
 	mlx5_tc_rule_delete(netdev_priv(ct_priv->netdev), zone_rule->rule, attr);
 	mlx5e_mod_hdr_detach(ct_priv->dev,
 			     ct_priv->mod_hdr_tbl, zone_rule->mh);
-	mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id);
+	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
 	kfree(attr);
 }
 
@@ -639,8 +661,8 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
 	if (!meta)
 		return -EOPNOTSUPP;
 
-	err = mapping_add(ct_priv->labels_mapping, meta->ct_metadata.labels,
-			  &attr->ct_attr.ct_labels_id);
+	err = mlx5_get_label_mapping(ct_priv, meta->ct_metadata.labels,
+				     &attr->ct_attr.ct_labels_id);
 	if (err)
 		return -EOPNOTSUPP;
 	if (nat) {
@@ -677,7 +699,7 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
 
 err_mapping:
 	dealloc_mod_hdr_actions(&mod_acts);
-	mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id);
+	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
 	return err;
 }
 
@@ -745,7 +767,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 err_rule:
 	mlx5e_mod_hdr_detach(ct_priv->dev,
 			     ct_priv->mod_hdr_tbl, zone_rule->mh);
-	mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id);
+	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
 err_mod_hdr:
 	kfree(attr);
 err_attr:
@@ -1197,7 +1219,7 @@ void mlx5_tc_ct_match_del(struct mlx5_tc_ct_priv *priv, struct mlx5_ct_attr *ct_
 	if (!priv || !ct_attr->ct_labels_id)
 		return;
 
-	mapping_remove(priv->labels_mapping, ct_attr->ct_labels_id);
+	mlx5_put_label_mapping(priv, ct_attr->ct_labels_id);
 }
 
 int
@@ -1280,7 +1302,7 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv,
 		ct_labels[1] = key->ct_labels[1] & mask->ct_labels[1];
 		ct_labels[2] = key->ct_labels[2] & mask->ct_labels[2];
 		ct_labels[3] = key->ct_labels[3] & mask->ct_labels[3];
-		if (mapping_add(priv->labels_mapping, ct_labels, &ct_attr->ct_labels_id))
+		if (mlx5_get_label_mapping(priv, ct_labels, &ct_attr->ct_labels_id))
 			return -EOPNOTSUPP;
 		mlx5e_tc_match_to_reg_match(spec, LABELS_TO_REG, ct_attr->ct_labels_id,
 					    MLX5_CT_LABELS_MASK);

From 1f90aedfb496ccccf862c7b7c0889af20c2fc61a Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@nvidia.com>
Date: Mon, 22 Mar 2021 17:22:03 +0200
Subject: [PATCH 1449/1820] net/mlx5: Delete auxiliary bus driver eth-rep first

Delete auxiliary bus drivers flow deletes the eth driver
first and then the eth-reps driver but eth-reps devices resources
are depend on eth device.

Fixed by changing the delete order of auxiliary bus drivers to delete
the eth-rep driver first and after it the eth driver.

Fixes: 601c10c89cbb ("net/mlx5: Delete custom device management logic")
Signed-off-by: Maor Dickman <maord@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index b051417ede67..9153c9bda96f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -191,12 +191,12 @@ static bool is_ib_supported(struct mlx5_core_dev *dev)
 }
 
 enum {
-	MLX5_INTERFACE_PROTOCOL_ETH_REP,
 	MLX5_INTERFACE_PROTOCOL_ETH,
+	MLX5_INTERFACE_PROTOCOL_ETH_REP,
 
+	MLX5_INTERFACE_PROTOCOL_IB,
 	MLX5_INTERFACE_PROTOCOL_IB_REP,
 	MLX5_INTERFACE_PROTOCOL_MPIB,
-	MLX5_INTERFACE_PROTOCOL_IB,
 
 	MLX5_INTERFACE_PROTOCOL_VNET,
 };

From 3211434dfe7a66fcf55e43961ea524b78336c04c Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Wed, 24 Mar 2021 12:25:06 +0200
Subject: [PATCH 1450/1820] net/mlx5e: Fix ethtool indication of connector type

Use connector_type read from PTYS register when it's valid, based on
corresponding capability bit.

Fixes: 5b4793f81745 ("net/mlx5e: Add support for reading connector type from PTYS")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Eran Ben Elisha <eranbe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_ethtool.c  | 22 +++++++++----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index f5f2a8fd0046..53802e18af90 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -758,11 +758,11 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev,
 	return 0;
 }
 
-static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings *link_ksettings,
-						   u32 eth_proto_cap,
-						   u8 connector_type, bool ext)
+static void ptys2ethtool_supported_advertised_port(struct mlx5_core_dev *mdev,
+						   struct ethtool_link_ksettings *link_ksettings,
+						   u32 eth_proto_cap, u8 connector_type)
 {
-	if ((!connector_type && !ext) || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) {
+	if (!MLX5_CAP_PCAM_FEATURE(mdev, ptys_connector_type)) {
 		if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR)
 				   | MLX5E_PROT_MASK(MLX5E_10GBASE_SR)
 				   | MLX5E_PROT_MASK(MLX5E_40GBASE_CR4)
@@ -898,9 +898,9 @@ static int ptys2connector_type[MLX5E_CONNECTOR_TYPE_NUMBER] = {
 		[MLX5E_PORT_OTHER]              = PORT_OTHER,
 	};
 
-static u8 get_connector_port(u32 eth_proto, u8 connector_type, bool ext)
+static u8 get_connector_port(struct mlx5_core_dev *mdev, u32 eth_proto, u8 connector_type)
 {
-	if ((connector_type || ext) && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER)
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ptys_connector_type))
 		return ptys2connector_type[connector_type];
 
 	if (eth_proto &
@@ -1001,11 +1001,11 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 			 data_rate_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
-
-	link_ksettings->base.port = get_connector_port(eth_proto_oper,
-						       connector_type, ext);
-	ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin,
-					       connector_type, ext);
+	connector_type = connector_type < MLX5E_CONNECTOR_TYPE_NUMBER ?
+			 connector_type : MLX5E_PORT_UNKNOWN;
+	link_ksettings->base.port = get_connector_port(mdev, eth_proto_oper, connector_type);
+	ptys2ethtool_supported_advertised_port(mdev, link_ksettings, eth_proto_admin,
+					       connector_type);
 	get_lp_advertising(mdev, eth_proto_lp, link_ksettings);
 
 	if (an_status == MLX5_AN_COMPLETE)

From e929e3da537e3c2d97aabbd00530040997dde9ce Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@nvidia.com>
Date: Mon, 15 Mar 2021 15:20:29 +0200
Subject: [PATCH 1451/1820] net/mlx5: E-switch, Create vport miss group only if
 src rewrite is supported

Create send to vport miss group was added in order to support traffic
recirculation to root table with metadata source rewrite.
This group is created also in case source rewrite isn't supported.

Fixed by creating send to vport miss group only if source rewrite is
supported by FW.

Fixes: 8e404fefa58b ("net/mlx5e: Match recirculated packet miss in slow table using reg_c1")
Signed-off-by: Maor Dickman <maord@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 66 +++++++++++--------
 1 file changed, 38 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 8694b83968b4..d4a2f8d1ee9f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -537,6 +537,14 @@ esw_setup_vport_dests(struct mlx5_flow_destination *dest, struct mlx5_flow_act *
 	return i;
 }
 
+static bool
+esw_src_port_rewrite_supported(struct mlx5_eswitch *esw)
+{
+	return MLX5_CAP_GEN(esw->dev, reg_c_preserve) &&
+	       mlx5_eswitch_vport_match_metadata_enabled(esw) &&
+	       MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level);
+}
+
 static int
 esw_setup_dests(struct mlx5_flow_destination *dest,
 		struct mlx5_flow_act *flow_act,
@@ -550,9 +558,7 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
 	int err = 0;
 
 	if (!mlx5_eswitch_termtbl_required(esw, attr, flow_act, spec) &&
-	    MLX5_CAP_GEN(esw_attr->in_mdev, reg_c_preserve) &&
-	    mlx5_eswitch_vport_match_metadata_enabled(esw) &&
-	    MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level))
+	    esw_src_port_rewrite_supported(esw))
 		attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE;
 
 	if (attr->dest_ft) {
@@ -1716,36 +1722,40 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	}
 	esw->fdb_table.offloads.send_to_vport_grp = g;
 
-	/* meta send to vport */
-	memset(flow_group_in, 0, inlen);
-	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
-		 MLX5_MATCH_MISC_PARAMETERS_2);
+	if (esw_src_port_rewrite_supported(esw)) {
+		/* meta send to vport */
+		memset(flow_group_in, 0, inlen);
+		MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+			 MLX5_MATCH_MISC_PARAMETERS_2);
 
-	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
+		match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
 
-	MLX5_SET(fte_match_param, match_criteria,
-		 misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask());
-	MLX5_SET(fte_match_param, match_criteria,
-		 misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK);
+		MLX5_SET(fte_match_param, match_criteria,
+			 misc_parameters_2.metadata_reg_c_0,
+			 mlx5_eswitch_get_vport_metadata_mask());
+		MLX5_SET(fte_match_param, match_criteria,
+			 misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK);
 
-	num_vfs = esw->esw_funcs.num_vfs;
-	if (num_vfs) {
-		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
-		MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + num_vfs - 1);
-		ix += num_vfs;
+		num_vfs = esw->esw_funcs.num_vfs;
+		if (num_vfs) {
+			MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
+			MLX5_SET(create_flow_group_in, flow_group_in,
+				 end_flow_index, ix + num_vfs - 1);
+			ix += num_vfs;
 
-		g = mlx5_create_flow_group(fdb, flow_group_in);
-		if (IS_ERR(g)) {
-			err = PTR_ERR(g);
-			esw_warn(dev, "Failed to create send-to-vport meta flow group err(%d)\n",
-				 err);
-			goto send_vport_meta_err;
+			g = mlx5_create_flow_group(fdb, flow_group_in);
+			if (IS_ERR(g)) {
+				err = PTR_ERR(g);
+				esw_warn(dev, "Failed to create send-to-vport meta flow group err(%d)\n",
+					 err);
+				goto send_vport_meta_err;
+			}
+			esw->fdb_table.offloads.send_to_vport_meta_grp = g;
+
+			err = mlx5_eswitch_add_send_to_vport_meta_rules(esw);
+			if (err)
+				goto meta_rule_err;
 		}
-		esw->fdb_table.offloads.send_to_vport_meta_grp = g;
-
-		err = mlx5_eswitch_add_send_to_vport_meta_rules(esw);
-		if (err)
-			goto meta_rule_err;
 	}
 
 	if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {

From a51bce9698e951fec3fc0624060f124794ec3558 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Sun, 28 Feb 2021 13:50:17 +0200
Subject: [PATCH 1452/1820] net/mlx5e: kTLS, Fix TX counters atomicity

Some TLS TX counters increment per socket/connection, and are not
protected against parallel modifications from several cores.
Switch them to atomic counters by taking them out of the SQ stats into
the global atomic TLS stats.

In this patch, we touch a single counter 'tx_tls_ctx' that counts the
number of device-offloaded TX TLS connections added.
Now that this counter can be increased without the for having the SQ
context in hand, move it to the mlx5e_ktls_add_tx() callback where it
really belongs, out of the fast data-path.

This change is not needed for counters that increment only in NAPI
context or under the TX lock, as they are already protected.
Keep them as tls_* counters under 'struct mlx5e_sq_stats'.

Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ktls_tx.c     |  5 +-
 .../mellanox/mlx5/core/en_accel/tls.h         |  1 +
 .../mellanox/mlx5/core/en_accel/tls_stats.c   | 47 +++++++++++--------
 .../ethernet/mellanox/mlx5/core/en_stats.c    |  4 --
 .../ethernet/mellanox/mlx5/core/en_stats.h    |  2 -
 5 files changed, 33 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index d16def68ecff..51bdf71073f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 // Copyright (c) 2019 Mellanox Technologies.
 
+#include "en_accel/tls.h"
 #include "en_accel/ktls_txrx.h"
 #include "en_accel/ktls_utils.h"
 
@@ -50,6 +51,7 @@ static int mlx5e_ktls_create_tis(struct mlx5_core_dev *mdev, u32 *tisn)
 struct mlx5e_ktls_offload_context_tx {
 	struct tls_offload_context_tx *tx_ctx;
 	struct tls12_crypto_info_aes_gcm_128 crypto_info;
+	struct mlx5e_tls_sw_stats *sw_stats;
 	u32 expected_seq;
 	u32 tisn;
 	u32 key_id;
@@ -99,6 +101,7 @@ int mlx5e_ktls_add_tx(struct net_device *netdev, struct sock *sk,
 	if (err)
 		goto err_create_key;
 
+	priv_tx->sw_stats = &priv->tls->sw_stats;
 	priv_tx->expected_seq = start_offload_tcp_sn;
 	priv_tx->crypto_info  =
 		*(struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
@@ -111,6 +114,7 @@ int mlx5e_ktls_add_tx(struct net_device *netdev, struct sock *sk,
 		goto err_create_tis;
 
 	priv_tx->ctx_post_pending = true;
+	atomic64_inc(&priv_tx->sw_stats->tx_tls_ctx);
 
 	return 0;
 
@@ -452,7 +456,6 @@ bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *s
 
 	if (unlikely(mlx5e_ktls_tx_offload_test_and_clear_pending(priv_tx))) {
 		mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, false, false);
-		stats->tls_ctx++;
 	}
 
 	seq = ntohl(tcp_hdr(skb)->seq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index bd270a85c804..5b408904df14 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -41,6 +41,7 @@
 #include "en.h"
 
 struct mlx5e_tls_sw_stats {
+	atomic64_t tx_tls_ctx;
 	atomic64_t tx_tls_drop_metadata;
 	atomic64_t tx_tls_drop_resync_alloc;
 	atomic64_t tx_tls_drop_no_sync_data;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
index b949b9a7538b..a5aabc5c5236 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
@@ -45,49 +45,58 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_bypass_required) },
 };
 
+static const struct counter_desc mlx5e_ktls_sw_stats_desc[] = {
+	{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_ctx) },
+};
+
 #define MLX5E_READ_CTR_ATOMIC64(ptr, dsc, i) \
 	atomic64_read((atomic64_t *)((char *)(ptr) + (dsc)[i].offset))
 
-#define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc)
-
-static bool is_tls_atomic_stats(struct mlx5e_priv *priv)
+static const struct counter_desc *get_tls_atomic_stats(struct mlx5e_priv *priv)
 {
-	return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev);
+	if (!priv->tls)
+		return NULL;
+	if (mlx5_accel_is_ktls_device(priv->mdev))
+		return mlx5e_ktls_sw_stats_desc;
+	return mlx5e_tls_sw_stats_desc;
 }
 
 int mlx5e_tls_get_count(struct mlx5e_priv *priv)
 {
-	if (!is_tls_atomic_stats(priv))
+	if (!priv->tls)
 		return 0;
-
-	return NUM_TLS_SW_COUNTERS;
+	if (mlx5_accel_is_ktls_device(priv->mdev))
+		return ARRAY_SIZE(mlx5e_ktls_sw_stats_desc);
+	return ARRAY_SIZE(mlx5e_tls_sw_stats_desc);
 }
 
 int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data)
 {
-	unsigned int i, idx = 0;
+	const struct counter_desc *stats_desc;
+	unsigned int i, n, idx = 0;
 
-	if (!is_tls_atomic_stats(priv))
-		return 0;
+	stats_desc = get_tls_atomic_stats(priv);
+	n = mlx5e_tls_get_count(priv);
 
-	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
+	for (i = 0; i < n; i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       mlx5e_tls_sw_stats_desc[i].format);
+		       stats_desc[i].format);
 
-	return NUM_TLS_SW_COUNTERS;
+	return n;
 }
 
 int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data)
 {
-	int i, idx = 0;
+	const struct counter_desc *stats_desc;
+	unsigned int i, n, idx = 0;
 
-	if (!is_tls_atomic_stats(priv))
-		return 0;
+	stats_desc = get_tls_atomic_stats(priv);
+	n = mlx5e_tls_get_count(priv);
 
-	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
+	for (i = 0; i < n; i++)
 		data[idx++] =
 		    MLX5E_READ_CTR_ATOMIC64(&priv->tls->sw_stats,
-					    mlx5e_tls_sw_stats_desc, i);
+					    stats_desc, i);
 
-	return NUM_TLS_SW_COUNTERS;
+	return n;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 92c5b81427b9..74adaa58189a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -116,7 +116,6 @@ static const struct counter_desc sw_stats_desc[] = {
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ctx) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_bytes) },
@@ -390,7 +389,6 @@ static void mlx5e_stats_grp_sw_update_stats_sq(struct mlx5e_sw_stats *s,
 #ifdef CONFIG_MLX5_EN_TLS
 	s->tx_tls_encrypted_packets += sq_stats->tls_encrypted_packets;
 	s->tx_tls_encrypted_bytes   += sq_stats->tls_encrypted_bytes;
-	s->tx_tls_ctx               += sq_stats->tls_ctx;
 	s->tx_tls_ooo               += sq_stats->tls_ooo;
 	s->tx_tls_dump_bytes        += sq_stats->tls_dump_bytes;
 	s->tx_tls_dump_packets      += sq_stats->tls_dump_packets;
@@ -1650,7 +1648,6 @@ static const struct counter_desc sq_stats_desc[] = {
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_packets) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ctx) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ooo) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) },
@@ -1776,7 +1773,6 @@ static const struct counter_desc qos_sq_stats_desc[] = {
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_packets) },
 	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) },
-	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_ctx) },
 	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_ooo) },
 	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) },
 	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 93c41312fb03..8eb056af79ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -191,7 +191,6 @@ struct mlx5e_sw_stats {
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tx_tls_encrypted_packets;
 	u64 tx_tls_encrypted_bytes;
-	u64 tx_tls_ctx;
 	u64 tx_tls_ooo;
 	u64 tx_tls_dump_packets;
 	u64 tx_tls_dump_bytes;
@@ -364,7 +363,6 @@ struct mlx5e_sq_stats {
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tls_encrypted_packets;
 	u64 tls_encrypted_bytes;
-	u64 tls_ctx;
 	u64 tls_ooo;
 	u64 tls_dump_packets;
 	u64 tls_dump_bytes;

From 6f4fdd530a09c8e2c7368ba5a5b1711e6e5ced10 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Sun, 28 Feb 2021 15:00:45 +0200
Subject: [PATCH 1453/1820] net/mlx5e: kTLS, Fix RX counters atomicity

Some TLS RX counters increment per socket/connection, and are not
protected against parallel modifications from several cores.
Switch them to atomic counters by taking them out of the RQ stats into
the global atomic TLS stats.

In this patch, we touch 'rx_tls_ctx/del' that count the number of
device-offloaded RX TLS connections added/deleted.
These counters are updated in the add/del callbacks, out of the fast
data-path.

This change is not needed for counters that increment only in NAPI
context, as they are protected by the NAPI mechanism.
Keep them as tls_* counters under 'struct mlx5e_rq_stats'.

Fixes: 76c1e1ac2aae ("net/mlx5e: kTLS, Add kTLS RX stats")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ktls_rx.c     | 22 ++++++++++---------
 .../mellanox/mlx5/core/en_accel/tls.h         |  2 ++
 .../mellanox/mlx5/core/en_accel/tls_stats.c   |  2 ++
 .../ethernet/mellanox/mlx5/core/en_stats.c    |  6 -----
 .../ethernet/mellanox/mlx5/core/en_stats.h    |  4 ----
 5 files changed, 16 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index d06532d0baa4..57c5ebd597a7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -46,7 +46,8 @@ struct mlx5e_ktls_offload_context_rx {
 	struct tls12_crypto_info_aes_gcm_128 crypto_info;
 	struct accel_rule rule;
 	struct sock *sk;
-	struct mlx5e_rq_stats *stats;
+	struct mlx5e_rq_stats *rq_stats;
+	struct mlx5e_tls_sw_stats *sw_stats;
 	struct completion add_ctx;
 	u32 tirn;
 	u32 key_id;
@@ -218,7 +219,7 @@ unlock:
 	return err;
 
 err_out:
-	priv_rx->stats->tls_resync_req_skip++;
+	priv_rx->rq_stats->tls_resync_req_skip++;
 	err = PTR_ERR(cseg);
 	complete(&priv_rx->add_ctx);
 	goto unlock;
@@ -322,7 +323,7 @@ err_dma_unmap:
 err_free:
 	kfree(buf);
 err_out:
-	priv_rx->stats->tls_resync_req_skip++;
+	priv_rx->rq_stats->tls_resync_req_skip++;
 	return err;
 }
 
@@ -378,13 +379,13 @@ static int resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_rx
 
 	cseg = post_static_params(sq, priv_rx);
 	if (IS_ERR(cseg)) {
-		priv_rx->stats->tls_resync_res_skip++;
+		priv_rx->rq_stats->tls_resync_res_skip++;
 		err = PTR_ERR(cseg);
 		goto unlock;
 	}
 	/* Do not increment priv_rx refcnt, CQE handling is empty */
 	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
-	priv_rx->stats->tls_resync_res_ok++;
+	priv_rx->rq_stats->tls_resync_res_ok++;
 unlock:
 	spin_unlock_bh(&c->async_icosq_lock);
 
@@ -420,13 +421,13 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 	auth_state = MLX5_GET(tls_progress_params, ctx, auth_state);
 	if (tracker_state != MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_TRACKING ||
 	    auth_state != MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD) {
-		priv_rx->stats->tls_resync_req_skip++;
+		priv_rx->rq_stats->tls_resync_req_skip++;
 		goto out;
 	}
 
 	hw_seq = MLX5_GET(tls_progress_params, ctx, hw_resync_tcp_sn);
 	tls_offload_rx_resync_async_request_end(priv_rx->sk, cpu_to_be32(hw_seq));
-	priv_rx->stats->tls_resync_req_end++;
+	priv_rx->rq_stats->tls_resync_req_end++;
 out:
 	mlx5e_ktls_priv_rx_put(priv_rx);
 	dma_unmap_single(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
@@ -609,7 +610,8 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk,
 	priv_rx->rxq = rxq;
 	priv_rx->sk = sk;
 
-	priv_rx->stats = &priv->channel_stats[rxq].rq;
+	priv_rx->rq_stats = &priv->channel_stats[rxq].rq;
+	priv_rx->sw_stats = &priv->tls->sw_stats;
 	mlx5e_set_ktls_rx_priv_ctx(tls_ctx, priv_rx);
 
 	rqtn = priv->direct_tir[rxq].rqt.rqtn;
@@ -630,7 +632,7 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk,
 	if (err)
 		goto err_post_wqes;
 
-	priv_rx->stats->tls_ctx++;
+	atomic64_inc(&priv_rx->sw_stats->rx_tls_ctx);
 
 	return 0;
 
@@ -666,7 +668,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx)
 	if (cancel_work_sync(&resync->work))
 		mlx5e_ktls_priv_rx_put(priv_rx);
 
-	priv_rx->stats->tls_del++;
+	atomic64_inc(&priv_rx->sw_stats->rx_tls_del);
 	if (priv_rx->rule.rule)
 		mlx5e_accel_fs_del_sk(priv_rx->rule.rule);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index 5b408904df14..4c9274d390da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -46,6 +46,8 @@ struct mlx5e_tls_sw_stats {
 	atomic64_t tx_tls_drop_resync_alloc;
 	atomic64_t tx_tls_drop_no_sync_data;
 	atomic64_t tx_tls_drop_bypass_required;
+	atomic64_t rx_tls_ctx;
+	atomic64_t rx_tls_del;
 	atomic64_t rx_tls_drop_resync_request;
 	atomic64_t rx_tls_resync_request;
 	atomic64_t rx_tls_resync_reply;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
index a5aabc5c5236..29463bdb7715 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
@@ -47,6 +47,8 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = {
 
 static const struct counter_desc mlx5e_ktls_sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_ctx) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, rx_tls_ctx) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, rx_tls_del) },
 };
 
 #define MLX5E_READ_CTR_ATOMIC64(ptr, dsc, i) \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 74adaa58189a..88a01c59ce61 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -179,8 +179,6 @@ static const struct counter_desc sw_stats_desc[] = {
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_ctx) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_del) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_pkt) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_start) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_end) },
@@ -341,8 +339,6 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
 #ifdef CONFIG_MLX5_EN_TLS
 	s->rx_tls_decrypted_packets   += rq_stats->tls_decrypted_packets;
 	s->rx_tls_decrypted_bytes     += rq_stats->tls_decrypted_bytes;
-	s->rx_tls_ctx                 += rq_stats->tls_ctx;
-	s->rx_tls_del                 += rq_stats->tls_del;
 	s->rx_tls_resync_req_pkt      += rq_stats->tls_resync_req_pkt;
 	s->rx_tls_resync_req_start    += rq_stats->tls_resync_req_start;
 	s->rx_tls_resync_req_end      += rq_stats->tls_resync_req_end;
@@ -1620,8 +1616,6 @@ static const struct counter_desc rq_stats_desc[] = {
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_bytes) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_ctx) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_del) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_pkt) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_start) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_end) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 8eb056af79ba..adf9b7b8b712 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -201,8 +201,6 @@ struct mlx5e_sw_stats {
 
 	u64 rx_tls_decrypted_packets;
 	u64 rx_tls_decrypted_bytes;
-	u64 rx_tls_ctx;
-	u64 rx_tls_del;
 	u64 rx_tls_resync_req_pkt;
 	u64 rx_tls_resync_req_start;
 	u64 rx_tls_resync_req_end;
@@ -333,8 +331,6 @@ struct mlx5e_rq_stats {
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tls_decrypted_packets;
 	u64 tls_decrypted_bytes;
-	u64 tls_ctx;
-	u64 tls_del;
 	u64 tls_resync_req_pkt;
 	u64 tls_resync_req_start;
 	u64 tls_resync_req_end;

From a7b76002ae78cd230ee652ccdfedf21aa94fcecc Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@mellanox.com>
Date: Thu, 5 Dec 2019 16:58:10 -0600
Subject: [PATCH 1454/1820] net/mlx5: Don't request more than supported EQs

Calculating the number of compeltion EQs based on the number of
available IRQ vectors doesn't work now that all async EQs share one IRQ.
Thus the max number of EQs can be exceeded on systems with more than
approximately 256 CPUs. Take this into account when calculating the
number of available completion EQs.

Fixes: 81bfa206032a ("net/mlx5: Use a single IRQ for all async EQs")
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 174dfbc996c6..1fa9c18563da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -931,13 +931,24 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 	mutex_unlock(&table->lock);
 }
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#define MLX5_MAX_ASYNC_EQS 4
+#else
+#define MLX5_MAX_ASYNC_EQS 3
+#endif
+
 int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+		      MLX5_CAP_GEN(dev, max_num_eqs) :
+		      1 << MLX5_CAP_GEN(dev, log_max_eq);
 	int err;
 
 	eq_table->num_comp_eqs =
-		mlx5_irq_get_num_comp(eq_table->irq_table);
+		min_t(int,
+		      mlx5_irq_get_num_comp(eq_table->irq_table),
+		      num_eqs - MLX5_MAX_ASYNC_EQS);
 
 	err = create_async_eqs(dev);
 	if (err) {

From 929a2faddd55290fbb0b73f453b200ed1b2b2947 Mon Sep 17 00:00:00 2001
From: Dima Chumak <dchumak@nvidia.com>
Date: Thu, 11 Feb 2021 09:36:33 +0200
Subject: [PATCH 1455/1820] net/mlx5e: Consider geneve_opts for encap contexts

Current algorithm for encap keys is legacy from initial vxlan
implementation and doesn't take into account all possible fields of a
tunnel. For example, for a Geneve tunnel, which may have additional TLV
options, they are ignored when comparing encap keys and a rule can be
attached to an incorrect encap entry.

Fix that by introducing encap_info_equal() operation in
struct mlx5e_tc_tunnel. Geneve tunnel type uses custom implementation,
which extends generic algorithm and considers options if they are set.

Fixes: 7f1a546e3222 ("net/mlx5e: Consider tunnel type for encap contexts")
Signed-off-by: Dima Chumak <dchumak@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en/tc_tun.h   | 10 +++++++
 .../mellanox/mlx5/core/en/tc_tun_encap.c      | 23 ++++++---------
 .../mellanox/mlx5/core/en/tc_tun_geneve.c     | 29 +++++++++++++++++++
 .../mellanox/mlx5/core/en/tc_tun_gre.c        |  1 +
 .../mellanox/mlx5/core/en/tc_tun_mplsoudp.c   |  1 +
 .../mellanox/mlx5/core/en/tc_tun_vxlan.c      |  1 +
 6 files changed, 51 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
index 67de2bf36861..e1271998b937 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -21,6 +21,11 @@ enum {
 	MLX5E_TC_TUNNEL_TYPE_MPLSOUDP,
 };
 
+struct mlx5e_encap_key {
+	const struct ip_tunnel_key *ip_tun_key;
+	struct mlx5e_tc_tunnel     *tc_tunnel;
+};
+
 struct mlx5e_tc_tunnel {
 	int tunnel_type;
 	enum mlx5_flow_match_level match_level;
@@ -44,6 +49,8 @@ struct mlx5e_tc_tunnel {
 			    struct flow_cls_offload *f,
 			    void *headers_c,
 			    void *headers_v);
+	bool (*encap_info_equal)(struct mlx5e_encap_key *a,
+				 struct mlx5e_encap_key *b);
 };
 
 extern struct mlx5e_tc_tunnel vxlan_tunnel;
@@ -101,6 +108,9 @@ int mlx5e_tc_tun_parse_udp_ports(struct mlx5e_priv *priv,
 				 void *headers_c,
 				 void *headers_v);
 
+bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a,
+					   struct mlx5e_encap_key *b);
+
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif //__MLX5_EN_TC_TUNNEL_H__
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index 7f7b0f6dcdf9..9f16ad2c0710 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -476,16 +476,11 @@ void mlx5e_detach_decap(struct mlx5e_priv *priv,
 	mlx5e_decap_dealloc(priv, d);
 }
 
-struct encap_key {
-	const struct ip_tunnel_key *ip_tun_key;
-	struct mlx5e_tc_tunnel *tc_tunnel;
-};
-
-static int cmp_encap_info(struct encap_key *a,
-			  struct encap_key *b)
+bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a,
+					   struct mlx5e_encap_key *b)
 {
-	return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) ||
-		a->tc_tunnel->tunnel_type != b->tc_tunnel->tunnel_type;
+	return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) == 0 &&
+		a->tc_tunnel->tunnel_type == b->tc_tunnel->tunnel_type;
 }
 
 static int cmp_decap_info(struct mlx5e_decap_key *a,
@@ -494,7 +489,7 @@ static int cmp_decap_info(struct mlx5e_decap_key *a,
 	return memcmp(&a->key, &b->key, sizeof(b->key));
 }
 
-static int hash_encap_info(struct encap_key *key)
+static int hash_encap_info(struct mlx5e_encap_key *key)
 {
 	return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key),
 		     key->tc_tunnel->tunnel_type);
@@ -516,18 +511,18 @@ static bool mlx5e_decap_take(struct mlx5e_decap_entry *e)
 }
 
 static struct mlx5e_encap_entry *
-mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key,
+mlx5e_encap_get(struct mlx5e_priv *priv, struct mlx5e_encap_key *key,
 		uintptr_t hash_key)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5e_encap_key e_key;
 	struct mlx5e_encap_entry *e;
-	struct encap_key e_key;
 
 	hash_for_each_possible_rcu(esw->offloads.encap_tbl, e,
 				   encap_hlist, hash_key) {
 		e_key.ip_tun_key = &e->tun_info->key;
 		e_key.tc_tunnel = e->tunnel;
-		if (!cmp_encap_info(&e_key, key) &&
+		if (e->tunnel->encap_info_equal(&e_key, key) &&
 		    mlx5e_encap_take(e))
 			return e;
 	}
@@ -694,8 +689,8 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	struct mlx5_flow_attr *attr = flow->attr;
 	const struct ip_tunnel_info *tun_info;
 	unsigned long tbl_time_before = 0;
-	struct encap_key key;
 	struct mlx5e_encap_entry *e;
+	struct mlx5e_encap_key key;
 	bool entry_created = false;
 	unsigned short family;
 	uintptr_t hash_key;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
index 7ed3f9f79f11..f5b26f5a7de4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
@@ -329,6 +329,34 @@ static int mlx5e_tc_tun_parse_geneve(struct mlx5e_priv *priv,
 	return mlx5e_tc_tun_parse_geneve_options(priv, spec, f);
 }
 
+static bool mlx5e_tc_tun_encap_info_equal_geneve(struct mlx5e_encap_key *a,
+						 struct mlx5e_encap_key *b)
+{
+	struct ip_tunnel_info *a_info;
+	struct ip_tunnel_info *b_info;
+	bool a_has_opts, b_has_opts;
+
+	if (!mlx5e_tc_tun_encap_info_equal_generic(a, b))
+		return false;
+
+	a_has_opts = !!(a->ip_tun_key->tun_flags & TUNNEL_GENEVE_OPT);
+	b_has_opts = !!(b->ip_tun_key->tun_flags & TUNNEL_GENEVE_OPT);
+
+	/* keys are equal when both don't have any options attached */
+	if (!a_has_opts && !b_has_opts)
+		return true;
+
+	if (a_has_opts != b_has_opts)
+		return false;
+
+	/* geneve options stored in memory next to ip_tunnel_info struct */
+	a_info = container_of(a->ip_tun_key, struct ip_tunnel_info, key);
+	b_info = container_of(b->ip_tun_key, struct ip_tunnel_info, key);
+
+	return a_info->options_len == b_info->options_len &&
+		memcmp(a_info + 1, b_info + 1, a_info->options_len) == 0;
+}
+
 struct mlx5e_tc_tunnel geneve_tunnel = {
 	.tunnel_type          = MLX5E_TC_TUNNEL_TYPE_GENEVE,
 	.match_level          = MLX5_MATCH_L4,
@@ -338,4 +366,5 @@ struct mlx5e_tc_tunnel geneve_tunnel = {
 	.generate_ip_tun_hdr  = mlx5e_gen_ip_tunnel_header_geneve,
 	.parse_udp_ports      = mlx5e_tc_tun_parse_udp_ports_geneve,
 	.parse_tunnel         = mlx5e_tc_tun_parse_geneve,
+	.encap_info_equal     = mlx5e_tc_tun_encap_info_equal_geneve,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c
index 2805416c32a3..ada14f0574dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c
@@ -94,4 +94,5 @@ struct mlx5e_tc_tunnel gre_tunnel = {
 	.generate_ip_tun_hdr  = mlx5e_gen_ip_tunnel_header_gretap,
 	.parse_udp_ports      = NULL,
 	.parse_tunnel         = mlx5e_tc_tun_parse_gretap,
+	.encap_info_equal     = mlx5e_tc_tun_encap_info_equal_generic,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
index 3479672e84cf..60952b33b568 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
@@ -131,4 +131,5 @@ struct mlx5e_tc_tunnel mplsoudp_tunnel = {
 	.generate_ip_tun_hdr  = generate_ip_tun_hdr,
 	.parse_udp_ports      = parse_udp_ports,
 	.parse_tunnel         = parse_tunnel,
+	.encap_info_equal     = mlx5e_tc_tun_encap_info_equal_generic,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index 038a0f1cecec..4267f3a1059e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -150,4 +150,5 @@ struct mlx5e_tc_tunnel vxlan_tunnel = {
 	.generate_ip_tun_hdr  = mlx5e_gen_ip_tunnel_header_vxlan,
 	.parse_udp_ports      = mlx5e_tc_tun_parse_udp_ports_vxlan,
 	.parse_tunnel         = mlx5e_tc_tun_parse_vxlan,
+	.encap_info_equal     = mlx5e_tc_tun_encap_info_equal_generic,
 };

From 3ff3874fa0b261ef74f2bfb008a82ab1601c11eb Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Wed, 10 Feb 2021 14:58:01 +0200
Subject: [PATCH 1456/1820] net/mlx5e: Guarantee room for XSK wakeup NOP on
 async ICOSQ

XSK wakeup flow triggers an IRQ by posting a NOP WQE and hitting
the doorbell on the async ICOSQ.
It maintains its state so that it doesn't issue another NOP WQE
if it has an outstanding one already.

For this flow to work properly, the NOP post must not fail.
Make sure to reserve room for the NOP WQE in all WQE posts to the
async ICOSQ.

Fixes: 8d94b590f1e4 ("net/mlx5e: Turn XSK ICOSQ into a general asynchronous one")
Fixes: 1182f3659357 ("net/mlx5e: kTLS, Add kTLS RX HW offload support")
Fixes: 0419d8c9d8f8 ("net/mlx5e: kTLS, Add kTLS RX resync support")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  1 +
 .../net/ethernet/mellanox/mlx5/core/en/txrx.h |  6 ++++++
 .../mellanox/mlx5/core/en_accel/ktls_rx.c     | 18 +++++++---------
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 21 ++++++++++++++++++-
 4 files changed, 34 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 304b296fe8b9..bc6f77ea0a31 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -516,6 +516,7 @@ struct mlx5e_icosq {
 	struct mlx5_wq_cyc         wq;
 	void __iomem              *uar_map;
 	u32                        sqn;
+	u16                        reserved_room;
 	unsigned long              state;
 
 	/* control path */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 2371b83dad9c..055c3bc23733 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -441,4 +441,10 @@ static inline u16 mlx5e_stop_room_for_wqe(u16 wqe_size)
 	return wqe_size * 2 - 1;
 }
 
+static inline bool mlx5e_icosq_can_post_wqe(struct mlx5e_icosq *sq, u16 wqe_size)
+{
+	u16 room = sq->reserved_room + mlx5e_stop_room_for_wqe(wqe_size);
+
+	return mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room);
+}
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index 57c5ebd597a7..19d22a63313f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -138,11 +138,10 @@ post_static_params(struct mlx5e_icosq *sq,
 {
 	struct mlx5e_set_tls_static_params_wqe *wqe;
 	struct mlx5e_icosq_wqe_info wi;
-	u16 pi, num_wqebbs, room;
+	u16 pi, num_wqebbs;
 
 	num_wqebbs = MLX5E_TLS_SET_STATIC_PARAMS_WQEBBS;
-	room = mlx5e_stop_room_for_wqe(num_wqebbs);
-	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room)))
+	if (unlikely(!mlx5e_icosq_can_post_wqe(sq, num_wqebbs)))
 		return ERR_PTR(-ENOSPC);
 
 	pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs);
@@ -169,11 +168,10 @@ post_progress_params(struct mlx5e_icosq *sq,
 {
 	struct mlx5e_set_tls_progress_params_wqe *wqe;
 	struct mlx5e_icosq_wqe_info wi;
-	u16 pi, num_wqebbs, room;
+	u16 pi, num_wqebbs;
 
 	num_wqebbs = MLX5E_TLS_SET_PROGRESS_PARAMS_WQEBBS;
-	room = mlx5e_stop_room_for_wqe(num_wqebbs);
-	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room)))
+	if (unlikely(!mlx5e_icosq_can_post_wqe(sq, num_wqebbs)))
 		return ERR_PTR(-ENOSPC);
 
 	pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs);
@@ -278,17 +276,15 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 
 	buf->priv_rx = priv_rx;
 
-	BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1);
-
 	spin_lock_bh(&sq->channel->async_icosq_lock);
 
-	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
+	if (unlikely(!mlx5e_icosq_can_post_wqe(sq, MLX5E_KTLS_GET_PROGRESS_WQEBBS))) {
 		spin_unlock_bh(&sq->channel->async_icosq_lock);
 		err = -ENOSPC;
 		goto err_dma_unmap;
 	}
 
-	pi = mlx5e_icosq_get_next_pi(sq, 1);
+	pi = mlx5e_icosq_get_next_pi(sq, MLX5E_KTLS_GET_PROGRESS_WQEBBS);
 	wqe = MLX5E_TLS_FETCH_GET_PROGRESS_PARAMS_WQE(sq, pi);
 
 #define GET_PSV_DS_CNT (DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS))
@@ -308,7 +304,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 
 	wi = (struct mlx5e_icosq_wqe_info) {
 		.wqe_type = MLX5E_ICOSQ_WQE_GET_PSV_TLS,
-		.num_wqebbs = 1,
+		.num_wqebbs = MLX5E_KTLS_GET_PROGRESS_WQEBBS,
 		.tls_get_params.buf = buf,
 	};
 	icosq_fill_wi(sq, pi, &wi);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 158f947a8503..5db63b9f3b70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1091,6 +1091,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
+	sq->reserved_room = param->stop_room;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
@@ -2350,6 +2351,24 @@ void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
 	mlx5e_build_ico_cq_param(priv, log_wq_size, &param->cqp);
 }
 
+static void mlx5e_build_async_icosq_param(struct mlx5e_priv *priv,
+					  struct mlx5e_params *params,
+					  u8 log_wq_size,
+					  struct mlx5e_sq_param *param)
+{
+	void *sqc = param->sqc;
+	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
+
+	mlx5e_build_sq_param_common(priv, param);
+
+	/* async_icosq is used by XSK only if xdp_prog is active */
+	if (params->xdp_prog)
+		param->stop_room = mlx5e_stop_room_for_wqe(1); /* for XSK NOP */
+	MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq));
+	MLX5_SET(wq, wq, log_wq_sz, log_wq_size);
+	mlx5e_build_ico_cq_param(priv, log_wq_size, &param->cqp);
+}
+
 void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
 			     struct mlx5e_params *params,
 			     struct mlx5e_sq_param *param)
@@ -2398,7 +2417,7 @@ static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
 	mlx5e_build_sq_param(priv, params, &cparam->txq_sq);
 	mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq);
 	mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq);
-	mlx5e_build_icosq_param(priv, async_icosq_log_wq_sz, &cparam->async_icosq);
+	mlx5e_build_async_icosq_param(priv, params, async_icosq_log_wq_sz, &cparam->async_icosq);
 }
 
 int mlx5e_open_channels(struct mlx5e_priv *priv,

From d47ec7a0a7271dda08932d6208e4ab65ab0c987c Mon Sep 17 00:00:00 2001
From: Tong Zhu <zhutong@amazon.com>
Date: Fri, 19 Mar 2021 14:33:37 -0400
Subject: [PATCH 1457/1820] neighbour: Disregard DEAD dst in neigh_update

After a short network outage, the dst_entry is timed out and put
in DST_OBSOLETE_DEAD. We are in this code because arp reply comes
from this neighbour after network recovers. There is a potential
race condition that dst_entry is still in DST_OBSOLETE_DEAD.
With that, another neighbour lookup causes more harm than good.

In best case all packets in arp_queue are lost. This is
counterproductive to the original goal of finding a better path
for those packets.

I observed a worst case with 4.x kernel where a dst_entry in
DST_OBSOLETE_DEAD state is associated with loopback net_device.
It leads to an ethernet header with all zero addresses.
A packet with all zero source MAC address is quite deadly with
mac80211, ath9k and 802.11 block ack.  It fails
ieee80211_find_sta_by_ifaddr in ath9k (xmit.c). Ath9k flushes tx
queue (ath_tx_complete_aggr). BAW (block ack window) is not
updated. BAW logic is damaged and ath9k transmission is disabled.

Signed-off-by: Tong Zhu <zhutong@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e2982b3970b8..8379719d1dce 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1379,7 +1379,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
 			 * we can reinject the packet there.
 			 */
 			n2 = NULL;
-			if (dst) {
+			if (dst && dst->obsolete != DST_OBSOLETE_DEAD) {
 				n2 = dst_neigh_lookup_skb(dst, skb);
 				if (n2)
 					n1 = n2;

From bdc2ab5c61a5c07388f4820ff21e787b4dfd1ced Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Tue, 30 Mar 2021 18:59:59 -0700
Subject: [PATCH 1458/1820] net/rds: Fix a use after free in
 rds_message_map_pages
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In rds_message_map_pages, the rm is freed by rds_message_put(rm).
But rm is still used by rm->data.op_sg in return value.

My patch assigns ERR_CAST(rm->data.op_sg) to err before the rm is
freed to avoid the uaf.

Fixes: 7dba92037baf3 ("net/rds: Use ERR_PTR for rds_message_alloc_sgs()")
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Reviewed-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/message.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/rds/message.c b/net/rds/message.c
index 071a261fdaab..799034e0f513 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -347,8 +347,9 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in
 	rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE);
 	rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs);
 	if (IS_ERR(rm->data.op_sg)) {
+		void *err = ERR_CAST(rm->data.op_sg);
 		rds_message_put(rm);
-		return ERR_CAST(rm->data.op_sg);
+		return err;
 	}
 
 	for (i = 0; i < rm->data.op_nents; ++i) {

From c609e6aae4efcf383fe86b195d1b060befcb3666 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 31 Mar 2021 09:35:12 -0700
Subject: [PATCH 1459/1820] Revert "net: correct sk_acceptq_is_full()"

This reverts commit f211ac154577ec9ccf07c15f18a6abf0d9bdb4ab.

We had similar attempt in the past, and we reverted it.

History:

64a146513f8f12ba204b7bf5cb7e9505594ead42 [NET]: Revert incorrect accept queue backlog changes.
8488df894d05d6fa41c2bd298c335f944bb0e401 [NET]: Fix bugs in "Whether sock accept queue is full" checking

I am adding a fat comment so that future attempts will
be much harder.

Fixes: f211ac154577 ("net: correct sk_acceptq_is_full()")
Cc: iuyacan <yacanliu@163.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 3e3a5da2ce5a..8487f58da36d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -934,9 +934,13 @@ static inline void sk_acceptq_added(struct sock *sk)
 	WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1);
 }
 
+/* Note: If you think the test should be:
+ *	return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog);
+ * Then please take a look at commit 64a146513f8f ("[NET]: Revert incorrect accept queue backlog changes.")
+ */
 static inline bool sk_acceptq_is_full(const struct sock *sk)
 {
-	return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog);
+	return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog);
 }
 
 /*

From 622d13694b5f048c01caa7ba548498d9880d4cb0 Mon Sep 17 00:00:00 2001
From: Ong Boon Leong <boon.leong.ong@intel.com>
Date: Wed, 31 Mar 2021 21:25:03 +0800
Subject: [PATCH 1460/1820] xdp: fix xdp_return_frame() kernel BUG throw for
 page_pool memory model

xdp_return_frame() may be called outside of NAPI context to return
xdpf back to page_pool. xdp_return_frame() calls __xdp_return() with
napi_direct = false. For page_pool memory model, __xdp_return() calls
xdp_return_frame_no_direct() unconditionally and below false negative
kernel BUG throw happened under preempt-rt build:

[  430.450355] BUG: using smp_processor_id() in preemptible [00000000] code: modprobe/3884
[  430.451678] caller is __xdp_return+0x1ff/0x2e0
[  430.452111] CPU: 0 PID: 3884 Comm: modprobe Tainted: G     U      E     5.12.0-rc2+ #45

Changes in v2:
 - This patch fixes the issue by making xdp_return_frame_no_direct() is
   only called if napi_direct = true, as recommended for better by
   Jesper Dangaard Brouer. Thanks!

Fixes: 2539650fadbf ("xdp: Helpers for disabling napi_direct of xdp_return_frame")
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/xdp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/xdp.c b/net/core/xdp.c
index 05354976c1fc..858276e72c68 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -350,7 +350,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
 		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
 		page = virt_to_head_page(data);
-		napi_direct &= !xdp_return_frame_no_direct();
+		if (napi_direct && xdp_return_frame_no_direct())
+			napi_direct = false;
 		page_pool_put_full_page(xa->page_pool, page, napi_direct);
 		rcu_read_unlock();
 		break;

From 3edf5346e4f2ce2fa0c94651a90a8dda169565ee Mon Sep 17 00:00:00 2001
From: Yufen Yu <yuyufen@huawei.com>
Date: Wed, 31 Mar 2021 07:53:59 -0400
Subject: [PATCH 1461/1820] block: only update parent bi_status when bio fail

For multiple split bios, if one of the bio is fail, the whole
should return error to application. But we found there is a race
between bio_integrity_verify_fn and bio complete, which return
io success to application after one of the bio fail. The race as
following:

split bio(READ)          kworker

nvme_complete_rq
blk_update_request //split error=0
  bio_endio
    bio_integrity_endio
      queue_work(kintegrityd_wq, &bip->bip_work);

                         bio_integrity_verify_fn
                         bio_endio //split bio
                          __bio_chain_endio
                             if (!parent->bi_status)

                               <interrupt entry>
                               nvme_irq
                                 blk_update_request //parent error=7
                                 req_bio_endio
                                    bio->bi_status = 7 //parent bio
                               <interrupt exit>

                               parent->bi_status = 0
                        parent->bi_end_io() // return bi_status=0

The bio has been split as two: split and parent. When split
bio completed, it depends on kworker to do endio, while
bio_integrity_verify_fn have been interrupted by parent bio
complete irq handler. Then, parent bio->bi_status which have
been set in irq handler will overwrite by kworker.

In fact, even without the above race, we also need to conside
the concurrency beteen mulitple split bio complete and update
the same parent bi_status. Normally, multiple split bios will
be issued to the same hctx and complete from the same irq
vector. But if we have updated queue map between multiple split
bios, these bios may complete on different hw queue and different
irq vector. Then the concurrency update parent bi_status may
cause the final status error.

Suggested-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20210331115359.1125679-1-yuyufen@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/bio.c b/block/bio.c
index 963d1d406b3a..50e579088aca 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -277,7 +277,7 @@ static struct bio *__bio_chain_endio(struct bio *bio)
 {
 	struct bio *parent = bio->bi_private;
 
-	if (!parent->bi_status)
+	if (bio->bi_status && !parent->bi_status)
 		parent->bi_status = bio->bi_status;
 	bio_put(bio);
 	return parent;

From e92049ae4548ba09e53eaa9c8f6964b07ea274c9 Mon Sep 17 00:00:00 2001
From: Qu Huang <jinsdb@126.com>
Date: Thu, 28 Jan 2021 20:14:25 +0800
Subject: [PATCH 1462/1820] drm/amdkfd: dqm fence memory corruption

Amdgpu driver uses 4-byte data type as DQM fence memory,
and transmits GPU address of fence memory to microcode
through query status PM4 message. However, query status
PM4 message definition and microcode processing are all
processed according to 8 bytes. Fence memory only allocates
4 bytes of memory, but microcode does write 8 bytes of memory,
so there is a memory corruption.

Changes since v1:
  * Change dqm->fence_addr as a u64 pointer to fix this issue,
also fix up query_status and amdkfd_fence_wait_timeout function
uses 64 bit fence value to make them consistent.

Signed-off-by: Qu Huang <jinsdb@126.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c               | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 6 +++---
 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c       | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c    | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c    | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h                 | 8 ++++----
 7 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index b258a3dae767..159add0f5aaa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -155,7 +155,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
 
 	/* Wait till CP writes sync code: */
 	status = amdkfd_fence_wait_timeout(
-			(unsigned int *) rm_state,
+			rm_state,
 			QUEUESTATE__ACTIVE, 1500);
 
 	kfd_gtt_sa_free(dbgdev->dev, mem_obj);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index e686ce2bf3b3..4598a9a58125 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1167,7 +1167,7 @@ static int start_cpsch(struct device_queue_manager *dqm)
 	if (retval)
 		goto fail_allocate_vidmem;
 
-	dqm->fence_addr = dqm->fence_mem->cpu_ptr;
+	dqm->fence_addr = (uint64_t *)dqm->fence_mem->cpu_ptr;
 	dqm->fence_gpu_addr = dqm->fence_mem->gpu_addr;
 
 	init_interrupts(dqm);
@@ -1340,8 +1340,8 @@ out:
 	return retval;
 }
 
-int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
-				unsigned int fence_value,
+int amdkfd_fence_wait_timeout(uint64_t *fence_addr,
+				uint64_t fence_value,
 				unsigned int timeout_ms)
 {
 	unsigned long end_jiffies = msecs_to_jiffies(timeout_ms) + jiffies;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 7351dd195274..45f815946554 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -192,7 +192,7 @@ struct device_queue_manager {
 	uint16_t		vmid_pasid[VMID_NUM];
 	uint64_t		pipelines_addr;
 	uint64_t		fence_gpu_addr;
-	unsigned int		*fence_addr;
+	uint64_t		*fence_addr;
 	struct kfd_mem_obj	*fence_mem;
 	bool			active_runlist;
 	int			sched_policy;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 5d541e0cc8ca..f71a7fa6680c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -347,7 +347,7 @@ fail_create_runlist_ib:
 }
 
 int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
-			uint32_t fence_value)
+			uint64_t fence_value)
 {
 	uint32_t *buffer, size;
 	int retval = 0;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
index dfaf771a42e6..e3ba0cd3b6fa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
@@ -283,7 +283,7 @@ static int pm_unmap_queues_v9(struct packet_manager *pm, uint32_t *buffer,
 }
 
 static int pm_query_status_v9(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t fence_address,	uint32_t fence_value)
+			uint64_t fence_address,	uint64_t fence_value)
 {
 	struct pm4_mes_query_status *packet;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c
index a852e0d7d804..08442e7d9944 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c
@@ -263,7 +263,7 @@ static int pm_unmap_queues_vi(struct packet_manager *pm, uint32_t *buffer,
 }
 
 static int pm_query_status_vi(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t fence_address,	uint32_t fence_value)
+			uint64_t fence_address,	uint64_t fence_value)
 {
 	struct pm4_mes_query_status *packet;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 09599efa41fc..f304d1f8df5f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1003,8 +1003,8 @@ int pqm_get_wave_state(struct process_queue_manager *pqm,
 		       u32 *ctl_stack_used_size,
 		       u32 *save_area_used_size);
 
-int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
-			      unsigned int fence_value,
+int amdkfd_fence_wait_timeout(uint64_t *fence_addr,
+			      uint64_t fence_value,
 			      unsigned int timeout_ms);
 
 /* Packet Manager */
@@ -1040,7 +1040,7 @@ struct packet_manager_funcs {
 			uint32_t filter_param, bool reset,
 			unsigned int sdma_engine);
 	int (*query_status)(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t fence_address,	uint32_t fence_value);
+			uint64_t fence_address,	uint64_t fence_value);
 	int (*release_mem)(uint64_t gpu_addr, uint32_t *buffer);
 
 	/* Packet sizes */
@@ -1062,7 +1062,7 @@ int pm_send_set_resources(struct packet_manager *pm,
 				struct scheduling_resources *res);
 int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues);
 int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
-				uint32_t fence_value);
+				uint64_t fence_value);
 
 int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 			enum kfd_unmap_queues_filter mode,

From 6951c3e4a260f65a16433833d2511e8796dc8625 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 26 Mar 2021 16:56:07 -0400
Subject: [PATCH 1463/1820] drm/amdgpu/vangogh: don't check for dpm in
 is_dpm_running when in suspend

Do the same thing we do for Renoir.  We can check, but since
the sbios has started DPM, it will always return true which
causes the driver to skip some of the SMU init when it shouldn't.

Reviewed-by: Zhan Liu <zhan.liu@amd.com>
Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 7ddbaecb11c2..101eaa20db9b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -384,10 +384,15 @@ static int vangogh_dpm_set_jpeg_enable(struct smu_context *smu, bool enable)
 
 static bool vangogh_is_dpm_running(struct smu_context *smu)
 {
+	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 	uint32_t feature_mask[2];
 	uint64_t feature_enabled;
 
+	/* we need to re-init after suspend so return false */
+	if (adev->in_suspend)
+		return false;
+
 	ret = smu_cmn_get_enabled_32_bits_mask(smu, feature_mask, 2);
 
 	if (ret)

From 566c6e25f957ebdb0b6e8073ee291049118f47fb Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Tue, 30 Mar 2021 23:33:33 +0800
Subject: [PATCH 1464/1820] drm/amdgpu: Set a suitable dev_info.gart_page_size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In Mesa, dev_info.gart_page_size is used for alignment and it was
set to AMDGPU_GPU_PAGE_SIZE(4KB). However, the page table of AMDGPU
driver requires an alignment on CPU pages.  So, for non-4KB page system,
gart_page_size should be max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE).

Signed-off-by: Rui Wang <wangr@lemote.com>
Signed-off-by: Huacai Chen <chenhc@lemote.com>
Link: https://github.com/loongson-community/linux-stable/commit/caa9c0a1
[Xi: rebased for drm-next, use max_t for checkpatch,
     and reworded commit message.]
Signed-off-by: Xi Ruoyao <xry111@mengyan1223.wang>
BugLink: https://gitlab.freedesktop.org/drm/amd/-/issues/1549
Tested-by: Dan Horák <dan@danny.cz>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 64beb3399604..a4e2cf7cada1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -778,9 +778,9 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			dev_info->high_va_offset = AMDGPU_GMC_HOLE_END;
 			dev_info->high_va_max = AMDGPU_GMC_HOLE_END | vm_size;
 		}
-		dev_info->virtual_address_alignment = max((int)PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE);
+		dev_info->virtual_address_alignment = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE);
 		dev_info->pte_fragment_size = (1 << adev->vm_manager.fragment_size) * AMDGPU_GPU_PAGE_SIZE;
-		dev_info->gart_page_size = AMDGPU_GPU_PAGE_SIZE;
+		dev_info->gart_page_size = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE);
 		dev_info->cu_active_number = adev->gfx.cu_info.number;
 		dev_info->cu_ao_mask = adev->gfx.cu_info.ao_cu_mask;
 		dev_info->ce_ram_size = adev->gfx.ce_ram_size;

From e3512fb67093fabdf27af303066627b921ee9bd8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?X=E2=84=B9=20Ruoyao?= <xry111@mengyan1223.wang>
Date: Tue, 30 Mar 2021 23:33:34 +0800
Subject: [PATCH 1465/1820] drm/amdgpu: check alignment on CPU page for bo map
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The page table of AMDGPU requires an alignment to CPU page so we should
check ioctl parameters for it.  Return -EINVAL if some parameter is
unaligned to CPU page, instead of corrupt the page table sliently.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Xi Ruoyao <xry111@mengyan1223.wang>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 10de2cf344d5..7d2c8b169827 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2197,8 +2197,8 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 	uint64_t eaddr;
 
 	/* validate the parameters */
-	if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK ||
-	    size == 0 || size & AMDGPU_GPU_PAGE_MASK)
+	if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK ||
+	    size == 0 || size & ~PAGE_MASK)
 		return -EINVAL;
 
 	/* make sure object fit at this offset */
@@ -2263,8 +2263,8 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
 	int r;
 
 	/* validate the parameters */
-	if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK ||
-	    size == 0 || size & AMDGPU_GPU_PAGE_MASK)
+	if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK ||
+	    size == 0 || size & ~PAGE_MASK)
 		return -EINVAL;
 
 	/* make sure object fit at this offset */

From a58d9166a756a0f4a6618e4f593232593d6df134 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 31 Mar 2021 06:24:43 -0400
Subject: [PATCH 1466/1820] KVM: SVM: load control fields from VMCB12 before
 checking them

Avoid races between check and use of the nested VMCB controls.  This
for example ensures that the VMRUN intercept is always reflected to the
nested hypervisor, instead of being processed by the host.  Without this
patch, it is possible to end up with svm->nested.hsave pointing to
the MSR permission bitmap for nested guests.

This bug is CVE-2021-29657.

Reported-by: Felix Wilhelm <fwilhelm@google.com>
Cc: stable@vger.kernel.org
Fixes: 2fcf4876ada ("KVM: nSVM: implement on demand allocation of the nested state")
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/nested.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 9e4c226dbf7d..061a00f91af5 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -225,7 +225,7 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control)
 	return true;
 }
 
-static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
+static bool nested_vmcb_check_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 {
 	bool vmcb12_lma;
 
@@ -257,7 +257,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	if (kvm_valid_cr4(&svm->vcpu, vmcb12->save.cr4))
 		return false;
 
-	return nested_vmcb_check_controls(&vmcb12->control);
+	return true;
 }
 
 static void load_nested_vmcb_control(struct vcpu_svm *svm,
@@ -440,7 +440,6 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa,
 	int ret;
 
 	svm->nested.vmcb12_gpa = vmcb12_gpa;
-	load_nested_vmcb_control(svm, &vmcb12->control);
 	nested_prepare_vmcb_save(svm, vmcb12);
 	nested_prepare_vmcb_control(svm);
 
@@ -484,7 +483,10 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
 	if (WARN_ON_ONCE(!svm->nested.initialized))
 		return -EINVAL;
 
-	if (!nested_vmcb_checks(svm, vmcb12)) {
+	load_nested_vmcb_control(svm, &vmcb12->control);
+
+	if (!nested_vmcb_check_save(svm, vmcb12) ||
+	    !nested_vmcb_check_controls(&svm->nested.ctl)) {
 		vmcb12->control.exit_code    = SVM_EXIT_ERR;
 		vmcb12->control.exit_code_hi = 0;
 		vmcb12->control.exit_info_1  = 0;

From 3c346c0c60ab06a021d1c0884a0ef494bc4ee3a7 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 31 Mar 2021 06:28:01 -0400
Subject: [PATCH 1467/1820] KVM: SVM: ensure that EFER.SVME is set when running
 nested guest or on nested vmexit

Fixing nested_vmcb_check_save to avoid all TOC/TOU races
is a bit harder in released kernels, so do the bare minimum
by avoiding that EFER.SVME is cleared.  This is problematic
because svm_set_efer frees the data structures for nested
virtualization if EFER.SVME is cleared.

Also check that EFER.SVME remains set after a nested vmexit;
clearing it could happen if the bit is zero in the save area
that is passed to KVM_SET_NESTED_STATE (the save area of the
nested state corresponds to the nested hypervisor's state
and is restored on the next nested vmexit).

Cc: stable@vger.kernel.org
Fixes: 2fcf4876ada ("KVM: nSVM: implement on demand allocation of the nested state")
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/nested.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 061a00f91af5..c9e7b86350d6 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -229,6 +229,13 @@ static bool nested_vmcb_check_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 {
 	bool vmcb12_lma;
 
+	/*
+	 * FIXME: these should be done after copying the fields,
+	 * to avoid TOC/TOU races.  For these save area checks
+	 * the possible damage is limited since kvm_set_cr0 and
+	 * kvm_set_cr4 handle failure; EFER_SVME is an exception
+	 * so it is force-set later in nested_prepare_vmcb_save.
+	 */
 	if ((vmcb12->save.efer & EFER_SVME) == 0)
 		return false;
 
@@ -382,7 +389,14 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	svm->vmcb->save.gdtr = vmcb12->save.gdtr;
 	svm->vmcb->save.idtr = vmcb12->save.idtr;
 	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags);
-	svm_set_efer(&svm->vcpu, vmcb12->save.efer);
+
+	/*
+	 * Force-set EFER_SVME even though it is checked earlier on the
+	 * VMCB12, because the guest can flip the bit between the check
+	 * and now.  Clearing EFER_SVME would call svm_free_nested.
+	 */
+	svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME);
+
 	svm_set_cr0(&svm->vcpu, vmcb12->save.cr0);
 	svm_set_cr4(&svm->vcpu, vmcb12->save.cr4);
 	svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = vmcb12->save.cr2;
@@ -1188,6 +1202,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	 */
 	if (!(save->cr0 & X86_CR0_PG))
 		goto out_free;
+	if (!(save->efer & EFER_SVME))
+		goto out_free;
 
 	/*
 	 * All checks done, we can enter guest mode.  L1 control fields

From c2c647f91aec192f45f0849c225f134183cf4e90 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 25 Mar 2021 14:05:11 -0400
Subject: [PATCH 1468/1820] KVM: x86: reduce pvclock_gtod_sync_lock critical
 sections

There is no need to include changes to vcpu->requests into
the pvclock_gtod_sync_lock critical section.  The changes to
the shared data structures (in pvclock_update_vm_gtod_copy)
already occur under the lock.

Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f7d12fca397b..2301623d3c53 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2561,10 +2561,12 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 
 	kvm_hv_invalidate_tsc_page(kvm);
 
-	spin_lock(&ka->pvclock_gtod_sync_lock);
 	kvm_make_mclock_inprogress_request(kvm);
+
 	/* no guest entries from this point */
+	spin_lock(&ka->pvclock_gtod_sync_lock);
 	pvclock_update_vm_gtod_copy(kvm);
+	spin_unlock(&ka->pvclock_gtod_sync_lock);
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -2572,8 +2574,6 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 	/* guest entries allowed */
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
-
-	spin_unlock(&ka->pvclock_gtod_sync_lock);
 #endif
 }
 
@@ -7739,16 +7739,14 @@ static void kvm_hyperv_tsc_notifier(void)
 		struct kvm_arch *ka = &kvm->arch;
 
 		spin_lock(&ka->pvclock_gtod_sync_lock);
-
 		pvclock_update_vm_gtod_copy(kvm);
+		spin_unlock(&ka->pvclock_gtod_sync_lock);
 
 		kvm_for_each_vcpu(cpu, vcpu, kvm)
 			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 
 		kvm_for_each_vcpu(cpu, vcpu, kvm)
 			kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
-
-		spin_unlock(&ka->pvclock_gtod_sync_lock);
 	}
 	mutex_unlock(&kvm_lock);
 }

From a83829f56c7ce17d5d05370820e185d9a23d3090 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 25 Mar 2021 14:11:14 -0400
Subject: [PATCH 1469/1820] KVM: x86: disable interrupts while
 pvclock_gtod_sync_lock is taken

pvclock_gtod_sync_lock can be taken with interrupts disabled if the
preempt notifier calls get_kvmclock_ns to update the Xen
runstate information:

   spin_lock include/linux/spinlock.h:354 [inline]
   get_kvmclock_ns+0x25/0x390 arch/x86/kvm/x86.c:2587
   kvm_xen_update_runstate+0x3d/0x2c0 arch/x86/kvm/xen.c:69
   kvm_xen_update_runstate_guest+0x74/0x320 arch/x86/kvm/xen.c:100
   kvm_xen_runstate_set_preempted arch/x86/kvm/xen.h:96 [inline]
   kvm_arch_vcpu_put+0x2d8/0x5a0 arch/x86/kvm/x86.c:4062

So change the users of the spinlock to spin_lock_irqsave and
spin_unlock_irqrestore.

Reported-by: syzbot+b282b65c2c68492df769@syzkaller.appspotmail.com
Fixes: 30b5c851af79 ("KVM: x86/xen: Add support for vCPU runstate information")
Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2301623d3c53..e1960eed921f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2328,7 +2328,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
 	kvm_vcpu_write_tsc_offset(vcpu, offset);
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
-	spin_lock(&kvm->arch.pvclock_gtod_sync_lock);
+	spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
 	if (!matched) {
 		kvm->arch.nr_vcpus_matched_tsc = 0;
 	} else if (!already_matched) {
@@ -2336,7 +2336,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
 	}
 
 	kvm_track_tsc_matching(vcpu);
-	spin_unlock(&kvm->arch.pvclock_gtod_sync_lock);
+	spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
 }
 
 static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
@@ -2558,15 +2558,16 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 	int i;
 	struct kvm_vcpu *vcpu;
 	struct kvm_arch *ka = &kvm->arch;
+	unsigned long flags;
 
 	kvm_hv_invalidate_tsc_page(kvm);
 
 	kvm_make_mclock_inprogress_request(kvm);
 
 	/* no guest entries from this point */
-	spin_lock(&ka->pvclock_gtod_sync_lock);
+	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	pvclock_update_vm_gtod_copy(kvm);
-	spin_unlock(&ka->pvclock_gtod_sync_lock);
+	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -2581,17 +2582,18 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 {
 	struct kvm_arch *ka = &kvm->arch;
 	struct pvclock_vcpu_time_info hv_clock;
+	unsigned long flags;
 	u64 ret;
 
-	spin_lock(&ka->pvclock_gtod_sync_lock);
+	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	if (!ka->use_master_clock) {
-		spin_unlock(&ka->pvclock_gtod_sync_lock);
+		spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 		return get_kvmclock_base_ns() + ka->kvmclock_offset;
 	}
 
 	hv_clock.tsc_timestamp = ka->master_cycle_now;
 	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
-	spin_unlock(&ka->pvclock_gtod_sync_lock);
+	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	/* both __this_cpu_read() and rdtsc() should be on the same cpu */
 	get_cpu();
@@ -2685,13 +2687,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	 * If the host uses TSC clock, then passthrough TSC as stable
 	 * to the guest.
 	 */
-	spin_lock(&ka->pvclock_gtod_sync_lock);
+	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	use_master_clock = ka->use_master_clock;
 	if (use_master_clock) {
 		host_tsc = ka->master_cycle_now;
 		kernel_ns = ka->master_kernel_ns;
 	}
-	spin_unlock(&ka->pvclock_gtod_sync_lock);
+	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
@@ -7723,6 +7725,7 @@ static void kvm_hyperv_tsc_notifier(void)
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
 	int cpu;
+	unsigned long flags;
 
 	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
@@ -7738,9 +7741,9 @@ static void kvm_hyperv_tsc_notifier(void)
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		struct kvm_arch *ka = &kvm->arch;
 
-		spin_lock(&ka->pvclock_gtod_sync_lock);
+		spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 		pvclock_update_vm_gtod_copy(kvm);
-		spin_unlock(&ka->pvclock_gtod_sync_lock);
+		spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 		kvm_for_each_vcpu(cpu, vcpu, kvm)
 			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);

From 77fcbe823f002ad18426545351fa2fb94f8d5e61 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Wed, 31 Mar 2021 14:41:29 +0200
Subject: [PATCH 1470/1820] KVM: x86: Prevent 'hv_clock->system_time' from
 going negative in kvm_guest_time_update()

When guest time is reset with KVM_SET_CLOCK(0), it is possible for
'hv_clock->system_time' to become a small negative number. This happens
because in KVM_SET_CLOCK handling we set 'kvm->arch.kvmclock_offset' based
on get_kvmclock_ns(kvm) but when KVM_REQ_CLOCK_UPDATE is handled,
kvm_guest_time_update() does (masterclock in use case):

hv_clock.system_time = ka->master_kernel_ns + v->kvm->arch.kvmclock_offset;

And 'master_kernel_ns' represents the last time when masterclock
got updated, it can precede KVM_SET_CLOCK() call. Normally, this is not a
problem, the difference is very small, e.g. I'm observing
hv_clock.system_time = -70 ns. The issue comes from the fact that
'hv_clock.system_time' is stored as unsigned and 'system_time / 100' in
compute_tsc_page_parameters() becomes a very big number.

Use 'master_kernel_ns' instead of get_kvmclock_ns() when masterclock is in
use and get_kvmclock_base_ns() when it's not to prevent 'system_time' from
going negative.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210331124130.337992-2-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e1960eed921f..eca63625aee4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5727,6 +5727,7 @@ set_pit2_out:
 	}
 #endif
 	case KVM_SET_CLOCK: {
+		struct kvm_arch *ka = &kvm->arch;
 		struct kvm_clock_data user_ns;
 		u64 now_ns;
 
@@ -5745,8 +5746,22 @@ set_pit2_out:
 		 * pvclock_update_vm_gtod_copy().
 		 */
 		kvm_gen_update_masterclock(kvm);
-		now_ns = get_kvmclock_ns(kvm);
-		kvm->arch.kvmclock_offset += user_ns.clock - now_ns;
+
+		/*
+		 * This pairs with kvm_guest_time_update(): when masterclock is
+		 * in use, we use master_kernel_ns + kvmclock_offset to set
+		 * unsigned 'system_time' so if we use get_kvmclock_ns() (which
+		 * is slightly ahead) here we risk going negative on unsigned
+		 * 'system_time' when 'user_ns.clock' is very small.
+		 */
+		spin_lock_irq(&ka->pvclock_gtod_sync_lock);
+		if (kvm->arch.use_master_clock)
+			now_ns = ka->master_kernel_ns;
+		else
+			now_ns = get_kvmclock_base_ns();
+		ka->kvmclock_offset = user_ns.clock - now_ns;
+		spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
+
 		kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
 		break;
 	}

From 55626ca9c6909d077eca71bccbe15fef6e5ad917 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 26 Mar 2021 16:55:51 +0100
Subject: [PATCH 1471/1820] selftests: kvm: Check that TSC page value is small
 after KVM_SET_CLOCK(0)

Add a test for the issue when KVM_SET_CLOCK(0) call could cause
TSC page value to go very big because of a signedness issue around
hv_clock->system_time.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210326155551.17446-3-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/x86_64/hyperv_clock.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
index ffbc4555c6e2..7f1d2765572c 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -80,19 +80,24 @@ static inline void check_tsc_msr_rdtsc(void)
 	GUEST_ASSERT(delta_ns * 100 < (t2 - t1) * 100);
 }
 
+static inline u64 get_tscpage_ts(struct ms_hyperv_tsc_page *tsc_page)
+{
+	return mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset;
+}
+
 static inline void check_tsc_msr_tsc_page(struct ms_hyperv_tsc_page *tsc_page)
 {
 	u64 r1, r2, t1, t2;
 
 	/* Compare TSC page clocksource with HV_X64_MSR_TIME_REF_COUNT */
-	t1 = mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset;
+	t1 = get_tscpage_ts(tsc_page);
 	r1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
 
 	/* 10 ms tolerance */
 	GUEST_ASSERT(r1 >= t1 && r1 - t1 < 100000);
 	nop_loop();
 
-	t2 = mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset;
+	t2 = get_tscpage_ts(tsc_page);
 	r2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
 	GUEST_ASSERT(r2 >= t1 && r2 - t2 < 100000);
 }
@@ -130,7 +135,11 @@ static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_
 
 	tsc_offset = tsc_page->tsc_offset;
 	/* Call KVM_SET_CLOCK from userspace, check that TSC page was updated */
+
 	GUEST_SYNC(7);
+	/* Sanity check TSC page timestamp, it should be close to 0 */
+	GUEST_ASSERT(get_tscpage_ts(tsc_page) < 100000);
+
 	GUEST_ASSERT(tsc_page->tsc_offset != tsc_offset);
 
 	nop_loop();

From b861106f3cd693f944ba46d9ea8744a3fbfd14db Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Wed, 31 Mar 2021 18:12:34 +0100
Subject: [PATCH 1472/1820] ASoC: codecs: lpass-tx-macro: set npl clock rate
 correctly

NPL clock rate is twice the MCLK rate, so set this correctly to
avoid soundwire timeouts.

Fixes: c39667ddcfc5 ("ASoC: codecs: lpass-tx-macro: add support for lpass tx macro")
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20210331171235.24824-1-srinivas.kandagatla@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/lpass-tx-macro.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c
index 36d7a6442cdb..e8c6c738bbaa 100644
--- a/sound/soc/codecs/lpass-tx-macro.c
+++ b/sound/soc/codecs/lpass-tx-macro.c
@@ -1811,7 +1811,7 @@ static int tx_macro_probe(struct platform_device *pdev)
 
 	/* set MCLK and NPL rates */
 	clk_set_rate(tx->clks[2].clk, MCLK_FREQ);
-	clk_set_rate(tx->clks[3].clk, MCLK_FREQ);
+	clk_set_rate(tx->clks[3].clk, 2 * MCLK_FREQ);
 
 	ret = clk_bulk_prepare_enable(TX_NUM_CLKS_MAX, tx->clks);
 	if (ret)

From adfc3ed7dcb98f7411d3632e3bdf81690294fe7d Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Wed, 31 Mar 2021 18:12:35 +0100
Subject: [PATCH 1473/1820] ASoC: codecs: lpass-rx-macro: set npl clock rate
 correctly

NPL clock rate is twice the MCLK rate, so set this correctly to
avoid soundwire timeouts.

Fixes: af3d54b99764 ("ASoC: codecs: lpass-rx-macro: add support for lpass rx macro")
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20210331171235.24824-2-srinivas.kandagatla@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/lpass-rx-macro.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c
index 8c04b3b2c907..7878da89d8e0 100644
--- a/sound/soc/codecs/lpass-rx-macro.c
+++ b/sound/soc/codecs/lpass-rx-macro.c
@@ -3551,7 +3551,7 @@ static int rx_macro_probe(struct platform_device *pdev)
 
 	/* set MCLK and NPL rates */
 	clk_set_rate(rx->clks[2].clk, MCLK_FREQ);
-	clk_set_rate(rx->clks[3].clk, MCLK_FREQ);
+	clk_set_rate(rx->clks[3].clk, 2 * MCLK_FREQ);
 
 	ret = clk_bulk_prepare_enable(RX_NUM_CLKS_MAX, rx->clks);
 	if (ret)

From 8cdddd182bd7befae6af49c5fd612893f55d6ccb Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Wed, 24 Mar 2021 16:22:19 +0100
Subject: [PATCH 1474/1820] ACPI: processor: Fix CPU0 wakeup in
 acpi_idle_play_dead()

Commit 496121c02127 ("ACPI: processor: idle: Allow probing on platforms
with one ACPI C-state") broke CPU0 hotplug on certain systems, e.g.
I'm observing the following on AWS Nitro (e.g r5b.xlarge but other
instance types are affected as well):

 # echo 0 > /sys/devices/system/cpu/cpu0/online
 # echo 1 > /sys/devices/system/cpu/cpu0/online
 <10 seconds delay>
 -bash: echo: write error: Input/output error

In fact, the above mentioned commit only revealed the problem and did
not introduce it. On x86, to wakeup CPU an NMI is being used and
hlt_play_dead()/mwait_play_dead() loops are prepared to handle it:

	/*
	 * If NMI wants to wake up CPU0, start CPU0.
	 */
	if (wakeup_cpu0())
		start_cpu0();

cpuidle_play_dead() -> acpi_idle_play_dead() (which is now being called on
systems where it wasn't called before the above mentioned commit) serves
the same purpose but it doesn't have a path for CPU0. What happens now on
wakeup is:
 - NMI is sent to CPU0
 - wakeup_cpu0_nmi() works as expected
 - we get back to while (1) loop in acpi_idle_play_dead()
 - safe_halt() puts CPU0 to sleep again.

The straightforward/minimal fix is add the special handling for CPU0 on x86
and that's what the patch is doing.

Fixes: 496121c02127 ("ACPI: processor: idle: Allow probing on platforms with one ACPI C-state")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: 5.10+ <stable@vger.kernel.org> # 5.10+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/include/asm/smp.h    | 1 +
 arch/x86/kernel/smpboot.c     | 2 +-
 drivers/acpi/processor_idle.c | 7 +++++++
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index c0538f82c9a2..57ef2094af93 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -132,6 +132,7 @@ void native_play_dead(void);
 void play_dead_common(void);
 void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
+bool wakeup_cpu0(void);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 02813a7f3a7c..f877150a91da 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1659,7 +1659,7 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
-static bool wakeup_cpu0(void)
+bool wakeup_cpu0(void)
 {
 	if (smp_processor_id() == 0 && enable_start_cpu0)
 		return true;
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index d93e400940a3..768a6b4d2368 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -29,6 +29,7 @@
  */
 #ifdef CONFIG_X86
 #include <asm/apic.h>
+#include <asm/cpu.h>
 #endif
 
 #define _COMPONENT              ACPI_PROCESSOR_COMPONENT
@@ -541,6 +542,12 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 			wait_for_freeze();
 		} else
 			return -ENODEV;
+
+#if defined(CONFIG_X86) && defined(CONFIG_HOTPLUG_CPU)
+		/* If NMI wants to wake up CPU0, start CPU0. */
+		if (wakeup_cpu0())
+			start_cpu0();
+#endif
 	}
 
 	/* Never reached */

From 1bb4bd266cf39fd2fa711f2d265c558b92df1119 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Wed, 31 Mar 2021 14:59:19 -0400
Subject: [PATCH 1475/1820] radix tree test suite: Register the main thread
 with the RCU library

Several test runners register individual worker threads with the
RCU library, but neglect to register the main thread, which can lead
to objects being freed while the main thread is in what appears to be
an RCU critical section.

Reported-by: Chris von Recklinghausen <crecklin@redhat.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 tools/testing/radix-tree/idr-test.c   | 2 ++
 tools/testing/radix-tree/multiorder.c | 2 ++
 tools/testing/radix-tree/xarray.c     | 2 ++
 3 files changed, 6 insertions(+)

diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 3b796dd5e577..44ceff95a9b3 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -577,6 +577,7 @@ void ida_tests(void)
 
 int __weak main(void)
 {
+	rcu_register_thread();
 	radix_tree_init();
 	idr_checks();
 	ida_tests();
@@ -584,5 +585,6 @@ int __weak main(void)
 	rcu_barrier();
 	if (nr_allocated)
 		printf("nr_allocated = %d\n", nr_allocated);
+	rcu_unregister_thread();
 	return 0;
 }
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 9eae0fb5a67d..e00520cc6349 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -224,7 +224,9 @@ void multiorder_checks(void)
 
 int __weak main(void)
 {
+	rcu_register_thread();
 	radix_tree_init();
 	multiorder_checks();
+	rcu_unregister_thread();
 	return 0;
 }
diff --git a/tools/testing/radix-tree/xarray.c b/tools/testing/radix-tree/xarray.c
index e61e43efe463..f20e12cbbfd4 100644
--- a/tools/testing/radix-tree/xarray.c
+++ b/tools/testing/radix-tree/xarray.c
@@ -25,11 +25,13 @@ void xarray_tests(void)
 
 int __weak main(void)
 {
+	rcu_register_thread();
 	radix_tree_init();
 	xarray_tests();
 	radix_tree_cpu_dead(1);
 	rcu_barrier();
 	if (nr_allocated)
 		printf("nr_allocated = %d\n", nr_allocated);
+	rcu_unregister_thread();
 	return 0;
 }

From 703586410da69eb40062e64d413ca33bd735917a Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 1 Apr 2021 07:44:48 -0400
Subject: [PATCH 1476/1820] idr test suite: Take RCU read lock in
 idr_find_test_1

When run on a single CPU, this test would frequently access already-freed
memory.  Due to timing, this bug never showed up on multi-CPU tests.

Reported-by: Chris von Recklinghausen <crecklin@redhat.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 tools/testing/radix-tree/idr-test.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 44ceff95a9b3..4a9b451b7ba0 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -306,11 +306,15 @@ void idr_find_test_1(int anchor_id, int throbber_id)
 	BUG_ON(idr_alloc(&find_idr, xa_mk_value(anchor_id), anchor_id,
 				anchor_id + 1, GFP_KERNEL) != anchor_id);
 
+	rcu_read_lock();
 	do {
 		int id = 0;
 		void *entry = idr_get_next(&find_idr, &id);
+		rcu_read_unlock();
 		BUG_ON(entry != xa_mk_value(id));
+		rcu_read_lock();
 	} while (time(NULL) < start + 11);
+	rcu_read_unlock();
 
 	pthread_join(throbber, NULL);
 

From 094ffbd1d8eaa27ed426feb8530cb1456348b018 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 1 Apr 2021 07:46:49 -0400
Subject: [PATCH 1477/1820] idr test suite: Create anchor before launching
 throbber

The throbber could race with creation of the anchor entry and cause the
IDR to have zero entries in it, which would cause the test to fail.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 tools/testing/radix-tree/idr-test.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 4a9b451b7ba0..6ce7460f3c7a 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -301,11 +301,11 @@ void idr_find_test_1(int anchor_id, int throbber_id)
 	pthread_t throbber;
 	time_t start = time(NULL);
 
-	pthread_create(&throbber, NULL, idr_throbber, &throbber_id);
-
 	BUG_ON(idr_alloc(&find_idr, xa_mk_value(anchor_id), anchor_id,
 				anchor_id + 1, GFP_KERNEL) != anchor_id);
 
+	pthread_create(&throbber, NULL, idr_throbber, &throbber_id);
+
 	rcu_read_lock();
 	do {
 		int id = 0;

From 2c7e57a02708a69d0194f9ef2a7b7e54f5a0484a Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 1 Apr 2021 07:50:42 -0400
Subject: [PATCH 1478/1820] idr test suite: Improve reporting from
 idr_find_test_1

Instead of just reporting an assertion failure, report enough information
that we can start diagnosing exactly went wrong.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 tools/testing/radix-tree/idr-test.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 6ce7460f3c7a..ca24f6839d50 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -296,6 +296,10 @@ static void *idr_throbber(void *arg)
 	return NULL;
 }
 
+/*
+ * There are always either 1 or 2 objects in the IDR.  If we find nothing,
+ * or we find something at an ID we didn't expect, that's a bug.
+ */
 void idr_find_test_1(int anchor_id, int throbber_id)
 {
 	pthread_t throbber;
@@ -311,7 +315,12 @@ void idr_find_test_1(int anchor_id, int throbber_id)
 		int id = 0;
 		void *entry = idr_get_next(&find_idr, &id);
 		rcu_read_unlock();
-		BUG_ON(entry != xa_mk_value(id));
+		if ((id != anchor_id && id != throbber_id) ||
+		    entry != xa_mk_value(id)) {
+			printf("%s(%d, %d): %p at %d\n", __func__, anchor_id,
+				throbber_id, entry, id);
+			abort();
+		}
 		rcu_read_lock();
 	} while (time(NULL) < start + 11);
 	rcu_read_unlock();

From de3510e52b0a398261271455562458003b8eea62 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@wdc.com>
Date: Thu, 1 Apr 2021 07:52:44 +0900
Subject: [PATCH 1479/1820] null_blk: fix command timeout completion handling

Memory backed or zoned null block devices may generate actual request
timeout errors due to the submission path being blocked on memory
allocation or zone locking. Unlike fake timeouts or injected timeouts,
the request submission path will call blk_mq_complete_request() or
blk_mq_end_request() for these real timeout errors, causing a double
completion and use after free situation as the block layer timeout
handler executes blk_mq_rq_timed_out() and __blk_mq_free_request() in
blk_mq_check_expired(). This problem often triggers a NULL pointer
dereference such as:

BUG: kernel NULL pointer dereference, address: 0000000000000050
RIP: 0010:blk_mq_sched_mark_restart_hctx+0x5/0x20
...
Call Trace:
  dd_finish_request+0x56/0x80
  blk_mq_free_request+0x37/0x130
  null_handle_cmd+0xbf/0x250 [null_blk]
  ? null_queue_rq+0x67/0xd0 [null_blk]
  blk_mq_dispatch_rq_list+0x122/0x850
  __blk_mq_do_dispatch_sched+0xbb/0x2c0
  __blk_mq_sched_dispatch_requests+0x13d/0x190
  blk_mq_sched_dispatch_requests+0x30/0x60
  __blk_mq_run_hw_queue+0x49/0x90
  process_one_work+0x26c/0x580
  worker_thread+0x55/0x3c0
  ? process_one_work+0x580/0x580
  kthread+0x134/0x150
  ? kthread_create_worker_on_cpu+0x70/0x70
  ret_from_fork+0x1f/0x30

This problem very often triggers when running the full btrfs xfstests
on a memory-backed zoned null block device in a VM with limited amount
of memory.

Avoid this by executing blk_mq_complete_request() in null_timeout_rq()
only for commands that are marked for a fake timeout completion using
the fake_timeout boolean in struct null_cmd. For timeout errors injected
through debugfs, the timeout handler will execute
blk_mq_complete_request()i as before. This is safe as the submission
path does not execute complete requests in this case.

In null_timeout_rq(), also make sure to set the command error field to
BLK_STS_TIMEOUT and to propagate this error through to the request
completion.

Reported-by: Johannes Thumshirn <Johannes.Thumshirn@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Tested-by: Johannes Thumshirn <Johannes.Thumshirn@wdc.com>
Reviewed-by: Johannes Thumshirn <Johannes.Thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20210331225244.126426-1-damien.lemoal@wdc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/null_blk/main.c     | 26 +++++++++++++++++++++-----
 drivers/block/null_blk/null_blk.h |  1 +
 2 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index d6c821d48090..51bfd7737552 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1369,10 +1369,13 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
 	}
 
 	if (dev->zoned)
-		cmd->error = null_process_zoned_cmd(cmd, op,
-						    sector, nr_sectors);
+		sts = null_process_zoned_cmd(cmd, op, sector, nr_sectors);
 	else
-		cmd->error = null_process_cmd(cmd, op, sector, nr_sectors);
+		sts = null_process_cmd(cmd, op, sector, nr_sectors);
+
+	/* Do not overwrite errors (e.g. timeout errors) */
+	if (cmd->error == BLK_STS_OK)
+		cmd->error = sts;
 
 out:
 	nullb_complete_cmd(cmd);
@@ -1451,8 +1454,20 @@ static bool should_requeue_request(struct request *rq)
 
 static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
 {
+	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
 	pr_info("rq %p timed out\n", rq);
-	blk_mq_complete_request(rq);
+
+	/*
+	 * If the device is marked as blocking (i.e. memory backed or zoned
+	 * device), the submission path may be blocked waiting for resources
+	 * and cause real timeouts. For these real timeouts, the submission
+	 * path will complete the request using blk_mq_complete_request().
+	 * Only fake timeouts need to execute blk_mq_complete_request() here.
+	 */
+	cmd->error = BLK_STS_TIMEOUT;
+	if (cmd->fake_timeout)
+		blk_mq_complete_request(rq);
 	return BLK_EH_DONE;
 }
 
@@ -1473,6 +1488,7 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 	cmd->rq = bd->rq;
 	cmd->error = BLK_STS_OK;
 	cmd->nq = nq;
+	cmd->fake_timeout = should_timeout_request(bd->rq);
 
 	blk_mq_start_request(bd->rq);
 
@@ -1489,7 +1505,7 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 			return BLK_STS_OK;
 		}
 	}
-	if (should_timeout_request(bd->rq))
+	if (cmd->fake_timeout)
 		return BLK_STS_OK;
 
 	return null_handle_cmd(cmd, sector, nr_sectors, req_op(bd->rq));
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
index 83504f3cc9d6..4876d5adb12d 100644
--- a/drivers/block/null_blk/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -22,6 +22,7 @@ struct nullb_cmd {
 	blk_status_t error;
 	struct nullb_queue *nq;
 	struct hrtimer timer;
+	bool fake_timeout;
 };
 
 struct nullb_queue {

From 3618250c8399cb36f4a0fbc48610a178307e1c64 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Wed, 31 Mar 2021 14:14:58 +0000
Subject: [PATCH 1480/1820] powerpc/ptrace: Don't return error when
 getting/setting FP regs without CONFIG_PPC_FPU_REGS

An #ifdef CONFIG_PPC_FPU_REGS is missing in arch_ptrace() leading
to the following Oops because [REGSET_FPR] entry is not initialised in
native_regsets[].

[   41.917608] BUG: Unable to handle kernel instruction fetch
[   41.922849] Faulting instruction address: 0xff8fd228
[   41.927760] Oops: Kernel access of bad area, sig: 11 [#1]
[   41.933089] BE PAGE_SIZE=4K PREEMPT CMPC885
[   41.940753] Modules linked in:
[   41.943768] CPU: 0 PID: 366 Comm: gdb Not tainted 5.12.0-rc5-s3k-dev-01666-g7aac86a0f057-dirty #4835
[   41.952800] NIP:  ff8fd228 LR: c004d9e0 CTR: ff8fd228
[   41.957790] REGS: caae9df0 TRAP: 0400   Not tainted  (5.12.0-rc5-s3k-dev-01666-g7aac86a0f057-dirty)
[   41.966741] MSR:  40009032 <EE,ME,IR,DR,RI>  CR: 82004248  XER: 20000000
[   41.973540]
[   41.973540] GPR00: c004d9b4 caae9eb0 c1b64f60 c1b64520 c0713cd4 caae9eb8 c1bacdfc 00000004
[   41.973540] GPR08: 00000200 ff8fd228 c1bac700 00001032 28004242 1061aaf4 00000001 106d64a0
[   41.973540] GPR16: 00000000 00000000 7fa0a774 10610000 7fa0aef9 00000000 10610000 7fa0a538
[   41.973540] GPR24: 7fa0a580 7fa0a570 c1bacc00 c1b64520 c1bacc00 caae9ee8 00000108 c0713cd4
[   42.009685] NIP [ff8fd228] 0xff8fd228
[   42.013300] LR [c004d9e0] __regset_get+0x100/0x124
[   42.018036] Call Trace:
[   42.020443] [caae9eb0] [c004d9b4] __regset_get+0xd4/0x124 (unreliable)
[   42.026899] [caae9ee0] [c004da94] copy_regset_to_user+0x5c/0xb0
[   42.032751] [caae9f10] [c002f640] sys_ptrace+0xe4/0x588
[   42.037915] [caae9f30] [c0011010] ret_from_syscall+0x0/0x28
[   42.043422] --- interrupt: c00 at 0xfd1f8e4
[   42.047553] NIP:  0fd1f8e4 LR: 1004a688 CTR: 00000000
[   42.052544] REGS: caae9f40 TRAP: 0c00   Not tainted  (5.12.0-rc5-s3k-dev-01666-g7aac86a0f057-dirty)
[   42.061494] MSR:  0000d032 <EE,PR,ME,IR,DR,RI>  CR: 48004442  XER: 00000000
[   42.068551]
[   42.068551] GPR00: 0000001a 7fa0a040 77dad7e0 0000000e 00000170 00000000 7fa0a078 00000004
[   42.068551] GPR08: 00000000 108deb88 108dda40 106d6010 44004442 1061aaf4 00000001 106d64a0
[   42.068551] GPR16: 00000000 00000000 7fa0a774 10610000 7fa0aef9 00000000 10610000 7fa0a538
[   42.068551] GPR24: 7fa0a580 7fa0a570 1078fe00 1078fd70 1078fd70 00000170 0fdd3244 0000000d
[   42.104696] NIP [0fd1f8e4] 0xfd1f8e4
[   42.108225] LR [1004a688] 0x1004a688
[   42.111753] --- interrupt: c00
[   42.114768] Instruction dump:
[   42.117698] XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX
[   42.125443] XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX
[   42.133195] ---[ end trace d35616f22ab2100c ]---

Adding the missing #ifdef is not good because gdb doesn't like getting
an error when getting registers.

Instead, make ptrace return 0s when CONFIG_PPC_FPU_REGS is not set.

Fixes: b6254ced4da6 ("powerpc/signal: Don't manage floating point regs when no FPU")
Cc: stable@vger.kernel.org
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/9121a44a2d50ba1af18d8aa5ada06c9a3bea8afd.1617200085.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/kernel/ptrace/Makefile       |  4 ++--
 arch/powerpc/kernel/ptrace/ptrace-decl.h  | 14 --------------
 arch/powerpc/kernel/ptrace/ptrace-fpu.c   | 10 ++++++++++
 arch/powerpc/kernel/ptrace/ptrace-novsx.c |  8 ++++++++
 arch/powerpc/kernel/ptrace/ptrace-view.c  |  2 --
 5 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/kernel/ptrace/Makefile b/arch/powerpc/kernel/ptrace/Makefile
index 8ebc11d1168d..77abd1a5a508 100644
--- a/arch/powerpc/kernel/ptrace/Makefile
+++ b/arch/powerpc/kernel/ptrace/Makefile
@@ -6,11 +6,11 @@
 CFLAGS_ptrace-view.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 obj-y				+= ptrace.o ptrace-view.o
-obj-$(CONFIG_PPC_FPU_REGS)	+= ptrace-fpu.o
+obj-y				+= ptrace-fpu.o
 obj-$(CONFIG_COMPAT)		+= ptrace32.o
 obj-$(CONFIG_VSX)		+= ptrace-vsx.o
 ifneq ($(CONFIG_VSX),y)
-obj-$(CONFIG_PPC_FPU_REGS)	+= ptrace-novsx.o
+obj-y				+= ptrace-novsx.o
 endif
 obj-$(CONFIG_ALTIVEC)		+= ptrace-altivec.o
 obj-$(CONFIG_SPE)		+= ptrace-spe.o
diff --git a/arch/powerpc/kernel/ptrace/ptrace-decl.h b/arch/powerpc/kernel/ptrace/ptrace-decl.h
index 3487f2c9735c..eafe5f0f6289 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-decl.h
+++ b/arch/powerpc/kernel/ptrace/ptrace-decl.h
@@ -165,22 +165,8 @@ int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data);
 extern const struct user_regset_view user_ppc_native_view;
 
 /* ptrace-fpu */
-#ifdef CONFIG_PPC_FPU_REGS
 int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data);
 int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data);
-#else
-static inline int
-ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data)
-{
-	return -EIO;
-}
-
-static inline int
-ptrace_put_fpr(struct task_struct *child, int index, unsigned long data)
-{
-	return -EIO;
-}
-#endif
 
 /* ptrace-(no)adv */
 void ppc_gethwdinfo(struct ppc_debug_info *dbginfo);
diff --git a/arch/powerpc/kernel/ptrace/ptrace-fpu.c b/arch/powerpc/kernel/ptrace/ptrace-fpu.c
index 8301cb52dd99..5dca19361316 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-fpu.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-fpu.c
@@ -8,32 +8,42 @@
 
 int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data)
 {
+#ifdef CONFIG_PPC_FPU_REGS
 	unsigned int fpidx = index - PT_FPR0;
+#endif
 
 	if (index > PT_FPSCR)
 		return -EIO;
 
+#ifdef CONFIG_PPC_FPU_REGS
 	flush_fp_to_thread(child);
 	if (fpidx < (PT_FPSCR - PT_FPR0))
 		memcpy(data, &child->thread.TS_FPR(fpidx), sizeof(long));
 	else
 		*data = child->thread.fp_state.fpscr;
+#else
+	*data = 0;
+#endif
 
 	return 0;
 }
 
 int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data)
 {
+#ifdef CONFIG_PPC_FPU_REGS
 	unsigned int fpidx = index - PT_FPR0;
+#endif
 
 	if (index > PT_FPSCR)
 		return -EIO;
 
+#ifdef CONFIG_PPC_FPU_REGS
 	flush_fp_to_thread(child);
 	if (fpidx < (PT_FPSCR - PT_FPR0))
 		memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long));
 	else
 		child->thread.fp_state.fpscr = data;
+#endif
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/ptrace/ptrace-novsx.c b/arch/powerpc/kernel/ptrace/ptrace-novsx.c
index b3b36835658a..7433f3db979a 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-novsx.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-novsx.c
@@ -21,12 +21,16 @@
 int fpr_get(struct task_struct *target, const struct user_regset *regset,
 	    struct membuf to)
 {
+#ifdef CONFIG_PPC_FPU_REGS
 	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
 		     offsetof(struct thread_fp_state, fpr[32]));
 
 	flush_fp_to_thread(target);
 
 	return membuf_write(&to, &target->thread.fp_state, 33 * sizeof(u64));
+#else
+	return membuf_write(&to, &empty_zero_page, 33 * sizeof(u64));
+#endif
 }
 
 /*
@@ -46,6 +50,7 @@ int fpr_set(struct task_struct *target, const struct user_regset *regset,
 	    unsigned int pos, unsigned int count,
 	    const void *kbuf, const void __user *ubuf)
 {
+#ifdef CONFIG_PPC_FPU_REGS
 	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
 		     offsetof(struct thread_fp_state, fpr[32]));
 
@@ -53,4 +58,7 @@ int fpr_set(struct task_struct *target, const struct user_regset *regset,
 
 	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				  &target->thread.fp_state, 0, -1);
+#else
+	return 0;
+#endif
 }
diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c
index 2bad8068f598..6ccffc65ac97 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-view.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@ -522,13 +522,11 @@ static const struct user_regset native_regsets[] = {
 		.size = sizeof(long), .align = sizeof(long),
 		.regset_get = gpr_get, .set = gpr_set
 	},
-#ifdef CONFIG_PPC_FPU_REGS
 	[REGSET_FPR] = {
 		.core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
 		.size = sizeof(double), .align = sizeof(double),
 		.regset_get = fpr_get, .set = fpr_set
 	},
-#endif
 #ifdef CONFIG_ALTIVEC
 	[REGSET_VMX] = {
 		.core_note_type = NT_PPC_VMX, .n = 34,

From acca57217c688c5bbbd5140974533d81e8757cc9 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Wed, 31 Mar 2021 14:07:04 +0000
Subject: [PATCH 1481/1820] powerpc/signal32: Fix Oops on sigreturn with
 unmapped VDSO

PPC32 encounters a KUAP fault when trying to handle a signal with
VDSO unmapped.

	Kernel attempted to read user page (7fc07ec0) - exploit attempt? (uid: 0)
	BUG: Unable to handle kernel data access on read at 0x7fc07ec0
	Faulting instruction address: 0xc00111d4
	Oops: Kernel access of bad area, sig: 11 [#1]
	BE PAGE_SIZE=16K PREEMPT CMPC885
	CPU: 0 PID: 353 Comm: sigreturn_vdso Not tainted 5.12.0-rc4-s3k-dev-01553-gb30c310ea220 #4814
	NIP:  c00111d4 LR: c0005a28 CTR: 00000000
	REGS: cadb3dd0 TRAP: 0300   Not tainted  (5.12.0-rc4-s3k-dev-01553-gb30c310ea220)
	MSR:  00009032 <EE,ME,IR,DR,RI>  CR: 48000884  XER: 20000000
	DAR: 7fc07ec0 DSISR: 88000000
	GPR00: c0007788 cadb3e90 c28d4a40 7fc07ec0 7fc07ed0 000004e0 7fc07ce0 00000000
	GPR08: 00000001 00000001 7fc07ec0 00000000 28000282 1001b828 100a0920 00000000
	GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e
	GPR24: ffffffff 105c43c8 00000000 7fc07ec8 cadb3f40 cadb3ec8 c28d4a40 00000000
	NIP [c00111d4] flush_icache_range+0x90/0xb4
	LR [c0005a28] handle_signal32+0x1bc/0x1c4
	Call Trace:
	[cadb3e90] [100d0000] 0x100d0000 (unreliable)
	[cadb3ec0] [c0007788] do_notify_resume+0x260/0x314
	[cadb3f20] [c000c764] syscall_exit_prepare+0x120/0x184
	[cadb3f30] [c00100b4] ret_from_syscall+0xc/0x28
	--- interrupt: c00 at 0xfe807f8
	NIP:  0fe807f8 LR: 10001060 CTR: c0139378
	REGS: cadb3f40 TRAP: 0c00   Not tainted  (5.12.0-rc4-s3k-dev-01553-gb30c310ea220)
	MSR:  0000d032 <EE,PR,ME,IR,DR,RI>  CR: 28000482  XER: 20000000

	GPR00: 00000025 7fc081c0 77bb1690 00000000 0000000a 28000482 00000001 0ff03a38
	GPR08: 0000d032 00006de5 c28d4a40 00000009 88000482 1001b828 100a0920 00000000
	GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e
	GPR24: ffffffff 105c43c8 00000000 77ba7628 10002398 10010000 10002124 00024000
	NIP [0fe807f8] 0xfe807f8
	LR [10001060] 0x10001060
	--- interrupt: c00
	Instruction dump:
	38630010 7c001fac 38630010 4200fff0 7c0004ac 4c00012c 4e800020 7c001fac
	2c0a0000 38630010 4082ffcc 4bffffe4 <7c00186c> 2c070000 39430010 4082ff8c
	---[ end trace 3973fb72b049cb06 ]---

This is because flush_icache_range() is called on user addresses.

The same problem was detected some time ago on PPC64. It was fixed by
enabling KUAP in commit 59bee45b9712 ("powerpc/mm: Fix missing KUAP
disable in flush_coherent_icache()").

PPC32 doesn't use flush_coherent_icache() and fallbacks on
clean_dcache_range() and invalidate_icache_range().

We could fix it similarly by enabling user access in those functions,
but this is overkill for just flushing two instructions.

The two instructions are 8 bytes aligned, so a single dcbst/icbi is
enough to flush them. Do like __patch_instruction() and inline
a dcbst followed by an icbi just after the write of the instructions,
while user access is still allowed. The isync is not required because
rfi will be used to return to user.

icbi() is handled as a read so read-write user access is needed.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/bde9154e5351a5ac7bca3d59cdb5a5e8edacbb79.1617199569.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/kernel/signal_32.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 75ee918a120a..f651b992fe01 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -775,7 +775,7 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset,
 	else
 		prepare_save_user_regs(1);
 
-	if (!user_write_access_begin(frame, sizeof(*frame)))
+	if (!user_access_begin(frame, sizeof(*frame)))
 		goto badframe;
 
 	/* Put the siginfo & fill in most of the ucontext */
@@ -809,17 +809,15 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset,
 		unsafe_put_user(PPC_INST_ADDI + __NR_rt_sigreturn, &mctx->mc_pad[0],
 				failed);
 		unsafe_put_user(PPC_INST_SC, &mctx->mc_pad[1], failed);
+		asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0]));
 	}
 	unsafe_put_sigset_t(&frame->uc.uc_sigmask, oldset, failed);
 
-	user_write_access_end();
+	user_access_end();
 
 	if (copy_siginfo_to_user(&frame->info, &ksig->info))
 		goto badframe;
 
-	if (tramp == (unsigned long)mctx->mc_pad)
-		flush_icache_range(tramp, tramp + 2 * sizeof(unsigned long));
-
 	regs->link = tramp;
 
 #ifdef CONFIG_PPC_FPU_REGS
@@ -844,7 +842,7 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset,
 	return 0;
 
 failed:
-	user_write_access_end();
+	user_access_end();
 
 badframe:
 	signal_fault(tsk, regs, "handle_rt_signal32", frame);
@@ -879,7 +877,7 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset,
 	else
 		prepare_save_user_regs(1);
 
-	if (!user_write_access_begin(frame, sizeof(*frame)))
+	if (!user_access_begin(frame, sizeof(*frame)))
 		goto badframe;
 	sc = (struct sigcontext __user *) &frame->sctx;
 
@@ -908,11 +906,9 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset,
 		/* Set up the sigreturn trampoline: li r0,sigret; sc */
 		unsafe_put_user(PPC_INST_ADDI + __NR_sigreturn, &mctx->mc_pad[0], failed);
 		unsafe_put_user(PPC_INST_SC, &mctx->mc_pad[1], failed);
+		asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0]));
 	}
-	user_write_access_end();
-
-	if (tramp == (unsigned long)mctx->mc_pad)
-		flush_icache_range(tramp, tramp + 2 * sizeof(unsigned long));
+	user_access_end();
 
 	regs->link = tramp;
 
@@ -935,7 +931,7 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset,
 	return 0;
 
 failed:
-	user_write_access_end();
+	user_access_end();
 
 badframe:
 	signal_fault(tsk, regs, "handle_signal32", frame);

From 791f9e36599d94af5a76d3f74d04e16326761aae Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Wed, 31 Mar 2021 09:12:19 +0000
Subject: [PATCH 1482/1820] powerpc/vdso: Make sure vdso_wrapper.o is rebuilt
 everytime vdso.so is rebuilt

Commit bce74491c300 ("powerpc/vdso: fix unnecessary rebuilds of
vgettimeofday.o") moved vdso32_wrapper.o and vdso64_wrapper.o out
of arch/powerpc/kernel/vdso[32/64]/ and removed the dependencies in
the Makefile. This leads to the wrappers not being re-build hence the
kernel embedding the old vdso library.

Add back missing dependencies to ensure vdso32_wrapper.o and vdso64_wrapper.o
are rebuilt when vdso32.so.dbg and vdso64.so.dbg are changed.

Fixes: bce74491c300 ("powerpc/vdso: fix unnecessary rebuilds of vgettimeofday.o")
Cc: stable@vger.kernel.org
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/8bb015bc98c51d8ced581415b7e3d157e18da7c9.1617181918.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/kernel/Makefile | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 6084fa499aa3..f66b63e81c3b 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -191,3 +191,7 @@ $(obj)/prom_init_check: $(src)/prom_init_check.sh $(obj)/prom_init.o FORCE
 targets += prom_init_check
 
 clean-files := vmlinux.lds
+
+# Force dependency (incbin is bad)
+$(obj)/vdso32_wrapper.o : $(obj)/vdso32/vdso32.so.dbg
+$(obj)/vdso64_wrapper.o : $(obj)/vdso64/vdso64.so.dbg

From 844b85dda2f569943e1e018fdd63b6f7d1d6f08e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 23 Mar 2021 14:18:05 +0100
Subject: [PATCH 1483/1820] ARM: keystone: fix integer overflow warning

clang warns about an impossible condition when building with 32-bit
phys_addr_t:

arch/arm/mach-keystone/keystone.c:79:16: error: result of comparison of constant 51539607551 with expression of type 'phys_addr_t' (aka 'unsigned int') is always false [-Werror,-Wtautological-constant-out-of-range-compare]
            mem_end   > KEYSTONE_HIGH_PHYS_END) {
            ~~~~~~~   ^ ~~~~~~~~~~~~~~~~~~~~~~
arch/arm/mach-keystone/keystone.c:78:16: error: result of comparison of constant 34359738368 with expression of type 'phys_addr_t' (aka 'unsigned int') is always true [-Werror,-Wtautological-constant-out-of-range-compare]
        if (mem_start < KEYSTONE_HIGH_PHYS_START ||
            ~~~~~~~~~ ^ ~~~~~~~~~~~~~~~~~~~~~~~~

Change the temporary variable to a fixed-size u64 to avoid the warning.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: Santosh Shilimkar <ssantosh@kernel.org>
Link: https://lore.kernel.org/r/20210323131814.2751750-1-arnd@kernel.org'
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-keystone/keystone.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index cd711bfc591f..2c647bdf8d25 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -65,7 +65,7 @@ static void __init keystone_init(void)
 static long long __init keystone_pv_fixup(void)
 {
 	long long offset;
-	phys_addr_t mem_start, mem_end;
+	u64 mem_start, mem_end;
 
 	mem_start = memblock_start_of_DRAM();
 	mem_end = memblock_end_of_DRAM();
@@ -78,7 +78,7 @@ static long long __init keystone_pv_fixup(void)
 	if (mem_start < KEYSTONE_HIGH_PHYS_START ||
 	    mem_end   > KEYSTONE_HIGH_PHYS_END) {
 		pr_crit("Invalid address space for memory (%08llx-%08llx)\n",
-		        (u64)mem_start, (u64)mem_end);
+		        mem_start, mem_end);
 		return 0;
 	}
 

From 040f31196e8b2609613f399793b9225271b79471 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 23 Mar 2021 14:15:23 +0100
Subject: [PATCH 1484/1820] soc/fsl: qbman: fix conflicting alignment
 attributes

When building with W=1, gcc points out that the __packed attribute
on struct qm_eqcr_entry conflicts with the 8-byte alignment
attribute on struct qm_fd inside it:

drivers/soc/fsl/qbman/qman.c:189:1: error: alignment 1 of 'struct qm_eqcr_entry' is less than 8 [-Werror=packed-not-aligned]

I assume that the alignment attribute is the correct one, and
that qm_eqcr_entry cannot actually be unaligned in memory,
so add the same alignment on the outer struct.

Fixes: c535e923bb97 ("soc/fsl: Introduce DPAA 1.x QMan device driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20210323131530.2619900-1-arnd@kernel.org'
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/soc/fsl/qbman/qman.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index a1b9be1d105a..fde4edd83c14 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -186,7 +186,7 @@ struct qm_eqcr_entry {
 	__be32 tag;
 	struct qm_fd fd;
 	u8 __reserved3[32];
-} __packed;
+} __packed __aligned(8);
 #define QM_EQCR_VERB_VBIT		0x80
 #define QM_EQCR_VERB_CMD_MASK		0x61	/* but only one value; */
 #define QM_EQCR_VERB_CMD_ENQUEUE	0x01

From 28399a5a6d569c9bdb612345e4933046ca37cde5 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 8 Mar 2021 16:34:21 +0100
Subject: [PATCH 1485/1820] ARM: omap1: fix building with clang IAS

The clang integrated assembler fails to build one file with
a complex asm instruction:

arch/arm/mach-omap1/ams-delta-fiq-handler.S:249:2: error: invalid instruction, any one of the following would fix this:
 mov r10, #(1 << (((NR_IRQS_LEGACY + 12) - NR_IRQS_LEGACY) % 32)) @ set deferred_fiq bit
 ^
arch/arm/mach-omap1/ams-delta-fiq-handler.S:249:2: note: instruction requires: armv6t2
 mov r10, #(1 << (((NR_IRQS_LEGACY + 12) - NR_IRQS_LEGACY) % 32)) @ set deferred_fiq bit
 ^
arch/arm/mach-omap1/ams-delta-fiq-handler.S:249:2: note: instruction requires: thumb2
 mov r10, #(1 << (((NR_IRQS_LEGACY + 12) - NR_IRQS_LEGACY) % 32)) @ set deferred_fiq bit
 ^

The problem is that 'NR_IRQS_LEGACY' is not defined here. Apparently
gas does not care because we first add and then subtract this number,
leading to the immediate value to be the same regardless of the
specific definition of NR_IRQS_LEGACY.

Neither the way that 'gas' just silently builds this file, nor the
way that clang IAS makes nonsensical suggestions for how to fix it
is great. Fortunately there is an easy fix, which is to #include
the header that contains the definition.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20210308153430.2530616-1-arnd@kernel.org'
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-omap1/ams-delta-fiq-handler.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/mach-omap1/ams-delta-fiq-handler.S b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
index 14a6c3eb3298..f745a65d3bd7 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq-handler.S
+++ b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
@@ -15,6 +15,7 @@
 #include <linux/platform_data/gpio-omap.h>
 
 #include <asm/assembler.h>
+#include <asm/irq.h>
 
 #include "ams-delta-fiq.h"
 #include "board-ams-delta.h"

From 230ea4c761fc1a8da36044ec358e20b71441efee Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 23 Mar 2021 14:08:27 +0100
Subject: [PATCH 1486/1820] ARM: pxa: mainstone: avoid -Woverride-init warning

The default initializer at the start of the array causes a warning
when building with W=1:

In file included from arch/arm/mach-pxa/mainstone.c:47:
arch/arm/mach-pxa/mainstone.h:124:33: error: initialized field overwritten [-Werror=override-init]
  124 | #define MAINSTONE_IRQ(x)        (MAINSTONE_NR_IRQS + (x))
      |                                 ^
arch/arm/mach-pxa/mainstone.h:133:33: note: in expansion of macro 'MAINSTONE_IRQ'
  133 | #define MAINSTONE_S0_CD_IRQ     MAINSTONE_IRQ(9)
      |                                 ^~~~~~~~~~~~~
arch/arm/mach-pxa/mainstone.c:506:15: note: in expansion of macro 'MAINSTONE_S0_CD_IRQ'
  506 |         [5] = MAINSTONE_S0_CD_IRQ,
      |               ^~~~~~~~~~~~~~~~~~~

Rework the initializer to list each element explicitly and only once.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20210323130849.2362001-1-arnd@kernel.org'
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-pxa/mainstone.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index d1010ec26e9f..d237bd030238 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -502,16 +502,20 @@ static inline void mainstone_init_keypad(void) {}
 #endif
 
 static int mst_pcmcia0_irqs[11] = {
-	[0 ... 10] = -1,
+	[0 ... 4] = -1,
 	[5] = MAINSTONE_S0_CD_IRQ,
+	[6 ... 7] = -1,
 	[8] = MAINSTONE_S0_STSCHG_IRQ,
+	[9] = -1,
 	[10] = MAINSTONE_S0_IRQ,
 };
 
 static int mst_pcmcia1_irqs[11] = {
-	[0 ... 10] = -1,
+	[0 ... 4] = -1,
 	[5] = MAINSTONE_S1_CD_IRQ,
+	[6 ... 7] = -1,
 	[8] = MAINSTONE_S1_STSCHG_IRQ,
+	[9] = -1,
 	[10] = MAINSTONE_S1_IRQ,
 };
 

From a2fa9e57a68cd108777ded8f0443483a5fa179ed Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 23 Mar 2021 14:19:42 +0100
Subject: [PATCH 1487/1820] ARM: mvebu: avoid clang -Wtautological-constant
 warning

Clang warns about the comparison when using a 32-bit phys_addr_t:

drivers/bus/mvebu-mbus.c:621:17: error: result of comparison of constant 4294967296 with expression of type 'phys_addr_t' (aka 'unsigned int') is always false [-Werror,-Wtautological-constant-out-of-range-compare]
                if (reg_start >= 0x100000000ULL)

Add a cast to shut up the warning.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20210323131952.2835509-1-arnd@kernel.org'
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/bus/mvebu-mbus.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index dd9e7343a5e3..ea0424922de7 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -618,7 +618,7 @@ mvebu_mbus_find_bridge_hole(uint64_t *start, uint64_t *end)
 		 * This part of the memory is above 4 GB, so we don't
 		 * care for the MBus bridge hole.
 		 */
-		if (reg_start >= 0x100000000ULL)
+		if ((u64)reg_start >= 0x100000000ULL)
 			continue;
 
 		/*

From 4b982bd0f383db9132e892c0c5144117359a6289 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 1 Apr 2021 08:38:34 -0600
Subject: [PATCH 1488/1820] io_uring: don't mark S_ISBLK async work as
 unbounded

S_ISBLK is marked as unbounded work for async preparation, because it
doesn't match S_ISREG. That is incorrect, as any read/write to a block
device is also a bounded operation. Fix it up and ensure that S_ISBLK
isn't marked unbounded.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 6d7a1b69712b..a16b7df934d1 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1213,7 +1213,7 @@ static void io_prep_async_work(struct io_kiocb *req)
 	if (req->flags & REQ_F_ISREG) {
 		if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
 			io_wq_hash_work(&req->work, file_inode(req->file));
-	} else {
+	} else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) {
 		if (def->unbound_nonreg_file)
 			req->work.flags |= IO_WQ_WORK_UNBOUND;
 	}

From 696ee88a7c50f96573f98aa76cc74286033140c1 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 1 Apr 2021 09:55:04 +0100
Subject: [PATCH 1489/1820] io_uring/io-wq: protect against sprintf overflow

task_pid may be large enough to not fit into the left space of
TASK_COMM_LEN-sized buffers and overflow in sprintf. We not so care
about uniqueness, so replace it with safer snprintf().

Reported-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/1702c6145d7e1c46fbc382f28334c02e1a3d3994.1617267273.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c    | 4 ++--
 fs/io_uring.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 7434eb40ca8c..433c4d3c3c1c 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -484,7 +484,7 @@ static int io_wqe_worker(void *data)
 	worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
 	io_wqe_inc_running(worker);
 
-	sprintf(buf, "iou-wrk-%d", wq->task_pid);
+	snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task_pid);
 	set_task_comm(current, buf);
 
 	while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
@@ -711,7 +711,7 @@ static int io_wq_manager(void *data)
 	char buf[TASK_COMM_LEN];
 	int node;
 
-	sprintf(buf, "iou-mgr-%d", wq->task_pid);
+	snprintf(buf, sizeof(buf), "iou-mgr-%d", wq->task_pid);
 	set_task_comm(current, buf);
 
 	do {
diff --git a/fs/io_uring.c b/fs/io_uring.c
index a16b7df934d1..4a6701b5065e 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6718,7 +6718,7 @@ static int io_sq_thread(void *data)
 	char buf[TASK_COMM_LEN];
 	DEFINE_WAIT(wait);
 
-	sprintf(buf, "iou-sqp-%d", sqd->task_pid);
+	snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
 	set_task_comm(current, buf);
 	current->pf_io_worker = NULL;
 

From 07204f21577a1d882f0259590c3553fe6a476381 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 1 Apr 2021 12:18:48 +0100
Subject: [PATCH 1490/1820] io_uring: fix EIOCBQUEUED iter revert

iov_iter_revert() is done in completion handlers that happensf before
read/write returns -EIOCBQUEUED, no need to repeat reverting afterwards.
Moreover, even though it may appear being just a no-op, it's actually
races with 1) user forging a new iovec of a different size 2) reissue,
that is done via io-wq continues completely asynchronously.

Fixes: 3e6a0d3c7571c ("io_uring: fix -EAGAIN retry with IOPOLL")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 4a6701b5065e..717942474fa9 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3284,8 +3284,6 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 	ret = io_iter_do_read(req, iter);
 
 	if (ret == -EIOCBQUEUED) {
-		if (req->async_data)
-			iov_iter_revert(iter, io_size - iov_iter_count(iter));
 		goto out_free;
 	} else if (ret == -EAGAIN) {
 		/* IOPOLL retry should happen for io-wq threads */
@@ -3418,8 +3416,6 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
 	/* no retry on NONBLOCK nor RWF_NOWAIT */
 	if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT))
 		goto done;
-	if (ret2 == -EIOCBQUEUED && req->async_data)
-		iov_iter_revert(iter, io_size - iov_iter_count(iter));
 	if (!force_nonblock || ret2 != -EAGAIN) {
 		/* IOPOLL retry should happen for io-wq threads */
 		if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN)

From 7a75a8412fdd52a64ee860bd9708d16b1b2aa77a Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Wed, 17 Feb 2021 20:21:19 +0000
Subject: [PATCH 1491/1820] i40e: Fix inconsistent indenting

Fixed new static analysis findings:
"warn: inconsistent indenting" - introduced lately,
reported with lkp and smatch build.

Fixes: 4b208eaa8078 ("i40e: Add init and default config of software based DCB")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Tested-by: Dave Switzer <david.switzer@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index f67f0cc9dadf..af6c25fa493c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -6738,9 +6738,9 @@ out:
 			set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
 			set_bit(__I40E_CLIENT_L2_CHANGE, pf->state);
 		}
-	/* registers are set, lets apply */
-	if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB)
-		ret = i40e_hw_set_dcb_config(pf, new_cfg);
+		/* registers are set, lets apply */
+		if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB)
+			ret = i40e_hw_set_dcb_config(pf, new_cfg);
 	}
 
 err:
@@ -10587,7 +10587,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 			i40e_aq_set_dcb_parameters(hw, false, NULL);
 			dev_warn(&pf->pdev->dev,
 				 "DCB is not supported for X710-T*L 2.5/5G speeds\n");
-				 pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+			pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
 		} else {
 			i40e_aq_set_dcb_parameters(hw, true, NULL);
 			ret = i40e_init_pf_dcb(pf);

From 528060ef3e1105c5c3eba66ffbfc80e0825e2cce Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 19 Mar 2021 10:44:10 +0100
Subject: [PATCH 1492/1820] i40e: fix receiving of single packets in xsk
 zero-copy mode

Fix so that single packets are received immediately instead of in
batches of 8. If you sent 1 pps to a system, you received 8 packets
every 8 seconds instead of 1 packet every second. The problem behind
this was that the work_done reporting from the Tx part of the driver
was broken. The work_done reporting in i40e controls not only the
reporting back to the napi logic but also the setting of the interrupt
throttling logic. When Tx or Rx reports that it has more to do,
interrupts are throttled or coalesced and when they both report that
they are done, interrupts are armed right away. If the wrong work_done
value is returned, the logic will start to throttle interrupts in a
situation where it should have just enabled them. This leads to the
undesired batching behavior seen in user-space.

Fix this by returning the correct boolean value from the Tx xsk
zero-copy path. Return true if there is nothing to do or if we got
fewer packets to process than we asked for. Return false if we got as
many packets as the budget since there might be more packets we can
process.

Fixes: 3106c580fb7c ("i40e: Use batched xsk Tx interfaces to increase performance")
Reported-by: Sreedevi Joshi <sreedevi.joshi@intel.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_xsk.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index fc32c5019b0f..12ca84113587 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -471,7 +471,7 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 
 	nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, descs, budget);
 	if (!nb_pkts)
-		return false;
+		return true;
 
 	if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
 		nb_processed = xdp_ring->count - xdp_ring->next_to_use;
@@ -488,7 +488,7 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 
 	i40e_update_tx_stats(xdp_ring, nb_pkts, total_bytes);
 
-	return true;
+	return nb_pkts < budget;
 }
 
 /**

From c3214de929dbf1b7374add8bbed30ce82b197bbb Mon Sep 17 00:00:00 2001
From: Eryk Rybak <eryk.roch.rybak@intel.com>
Date: Tue, 2 Mar 2021 08:46:27 +0100
Subject: [PATCH 1493/1820] i40e: Fix display statistics for veb_tc

If veb-stats was enabled, the ethtool stats triggered a warning
due to invalid size: 'unexpected stat size for veb.tc_%u_tx_packets'.
This was due to an incorrect structure definition for the statistics.
Structures and functions have been improved in line with requirements
for the presentation of statistics, in particular for the functions:
'i40e_add_ethtool_stats' and 'i40e_add_stat_strings'.

Fixes: 1510ae0be2a4 ("i40e: convert VEB TC stats to use an i40e_stats array")
Signed-off-by: Eryk Rybak <eryk.roch.rybak@intel.com>
Signed-off-by: Grzegorz Szczurek <grzegorzx.szczurek@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Dave Switzer <david.switzer@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/i40e/i40e_ethtool.c    | 52 ++++++++++++++++---
 1 file changed, 46 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 2c637a5678b3..96d5202a73e8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -232,6 +232,8 @@ static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[],
 	I40E_STAT(struct i40e_vsi, _name, _stat)
 #define I40E_VEB_STAT(_name, _stat) \
 	I40E_STAT(struct i40e_veb, _name, _stat)
+#define I40E_VEB_TC_STAT(_name, _stat) \
+	I40E_STAT(struct i40e_cp_veb_tc_stats, _name, _stat)
 #define I40E_PFC_STAT(_name, _stat) \
 	I40E_STAT(struct i40e_pfc_stats, _name, _stat)
 #define I40E_QUEUE_STAT(_name, _stat) \
@@ -266,11 +268,18 @@ static const struct i40e_stats i40e_gstrings_veb_stats[] = {
 	I40E_VEB_STAT("veb.rx_unknown_protocol", stats.rx_unknown_protocol),
 };
 
+struct i40e_cp_veb_tc_stats {
+	u64 tc_rx_packets;
+	u64 tc_rx_bytes;
+	u64 tc_tx_packets;
+	u64 tc_tx_bytes;
+};
+
 static const struct i40e_stats i40e_gstrings_veb_tc_stats[] = {
-	I40E_VEB_STAT("veb.tc_%u_tx_packets", tc_stats.tc_tx_packets),
-	I40E_VEB_STAT("veb.tc_%u_tx_bytes", tc_stats.tc_tx_bytes),
-	I40E_VEB_STAT("veb.tc_%u_rx_packets", tc_stats.tc_rx_packets),
-	I40E_VEB_STAT("veb.tc_%u_rx_bytes", tc_stats.tc_rx_bytes),
+	I40E_VEB_TC_STAT("veb.tc_%u_tx_packets", tc_tx_packets),
+	I40E_VEB_TC_STAT("veb.tc_%u_tx_bytes", tc_tx_bytes),
+	I40E_VEB_TC_STAT("veb.tc_%u_rx_packets", tc_rx_packets),
+	I40E_VEB_TC_STAT("veb.tc_%u_rx_bytes", tc_rx_bytes),
 };
 
 static const struct i40e_stats i40e_gstrings_misc_stats[] = {
@@ -2217,6 +2226,29 @@ static int i40e_get_sset_count(struct net_device *netdev, int sset)
 	}
 }
 
+/**
+ * i40e_get_veb_tc_stats - copy VEB TC statistics to formatted structure
+ * @tc: the TC statistics in VEB structure (veb->tc_stats)
+ * @i: the index of traffic class in (veb->tc_stats) structure to copy
+ *
+ * Copy VEB TC statistics from structure of arrays (veb->tc_stats) to
+ * one dimensional structure i40e_cp_veb_tc_stats.
+ * Produce formatted i40e_cp_veb_tc_stats structure of the VEB TC
+ * statistics for the given TC.
+ **/
+static struct i40e_cp_veb_tc_stats
+i40e_get_veb_tc_stats(struct i40e_veb_tc_stats *tc, unsigned int i)
+{
+	struct i40e_cp_veb_tc_stats veb_tc = {
+		.tc_rx_packets = tc->tc_rx_packets[i],
+		.tc_rx_bytes = tc->tc_rx_bytes[i],
+		.tc_tx_packets = tc->tc_tx_packets[i],
+		.tc_tx_bytes = tc->tc_tx_bytes[i],
+	};
+
+	return veb_tc;
+}
+
 /**
  * i40e_get_pfc_stats - copy HW PFC statistics to formatted structure
  * @pf: the PF device structure
@@ -2301,8 +2333,16 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 			       i40e_gstrings_veb_stats);
 
 	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
-		i40e_add_ethtool_stats(&data, veb_stats ? veb : NULL,
-				       i40e_gstrings_veb_tc_stats);
+		if (veb_stats) {
+			struct i40e_cp_veb_tc_stats veb_tc =
+				i40e_get_veb_tc_stats(&veb->tc_stats, i);
+
+			i40e_add_ethtool_stats(&data, &veb_tc,
+					       i40e_gstrings_veb_tc_stats);
+		} else {
+			i40e_add_ethtool_stats(&data, NULL,
+					       i40e_gstrings_veb_tc_stats);
+		}
 
 	i40e_add_ethtool_stats(&data, pf, i40e_gstrings_stats);
 

From 185f2e5f51c2029efd9dd26cceb968a44fe053c6 Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Thu, 1 Apr 2021 09:51:10 -0700
Subject: [PATCH 1494/1820] arm64: fix inline asm in load_unaligned_zeropad()

The inline asm's addr operand is marked as input-only, however in
the case where an exception is taken it may be modified by the BIC
instruction on the exception path. Fix the problem by using a temporary
register as the destination register for the BIC instruction.

Signed-off-by: Peter Collingbourne <pcc@google.com>
Cc: stable@vger.kernel.org
Link: https://linux-review.googlesource.com/id/I84538c8a2307d567b4f45bb20b715451005f9617
Link: https://lore.kernel.org/r/20210401165110.3952103-1-pcc@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/word-at-a-time.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h
index 3333950b5909..ea487218db79 100644
--- a/arch/arm64/include/asm/word-at-a-time.h
+++ b/arch/arm64/include/asm/word-at-a-time.h
@@ -53,7 +53,7 @@ static inline unsigned long find_zero(unsigned long mask)
  */
 static inline unsigned long load_unaligned_zeropad(const void *addr)
 {
-	unsigned long ret, offset;
+	unsigned long ret, tmp;
 
 	/* Load word from unaligned pointer addr */
 	asm(
@@ -61,9 +61,9 @@ static inline unsigned long load_unaligned_zeropad(const void *addr)
 	"2:\n"
 	"	.pushsection .fixup,\"ax\"\n"
 	"	.align 2\n"
-	"3:	and	%1, %2, #0x7\n"
-	"	bic	%2, %2, #0x7\n"
-	"	ldr	%0, [%2]\n"
+	"3:	bic	%1, %2, #0x7\n"
+	"	ldr	%0, [%1]\n"
+	"	and	%1, %2, #0x7\n"
 	"	lsl	%1, %1, #0x3\n"
 #ifndef __AARCH64EB__
 	"	lsr	%0, %0, %1\n"
@@ -73,7 +73,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr)
 	"	b	2b\n"
 	"	.popsection\n"
 	_ASM_EXTABLE(1b, 3b)
-	: "=&r" (ret), "=&r" (offset)
+	: "=&r" (ret), "=&r" (tmp)
 	: "r" (addr), "Q" (*(unsigned long *)addr));
 
 	return ret;

From 9deb193af69d3fd6dd8e47f292b67c805a787010 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 1 Apr 2021 13:54:40 -0400
Subject: [PATCH 1495/1820] tracing: Fix stack trace event size

Commit cbc3b92ce037 fixed an issue to modify the macros of the stack trace
event so that user space could parse it properly. Originally the stack
trace format to user space showed that the called stack was a dynamic
array. But it is not actually a dynamic array, in the way that other
dynamic event arrays worked, and this broke user space parsing for it. The
update was to make the array look to have 8 entries in it. Helper
functions were added to make it parse it correctly, as the stack was
dynamic, but was determined by the size of the event stored.

Although this fixed user space on how it read the event, it changed the
internal structure used for the stack trace event. It changed the array
size from [0] to [8] (added 8 entries). This increased the size of the
stack trace event by 8 words. The size reserved on the ring buffer was the
size of the stack trace event plus the number of stack entries found in
the stack trace. That commit caused the amount to be 8 more than what was
needed because it did not expect the caller field to have any size. This
produced 8 entries of garbage (and reading random data) from the stack
trace event:

          <idle>-0       [002] d... 1976396.837549: <stack trace>
 => trace_event_raw_event_sched_switch
 => __traceiter_sched_switch
 => __schedule
 => schedule_idle
 => do_idle
 => cpu_startup_entry
 => secondary_startup_64_no_verify
 => 0xc8c5e150ffff93de
 => 0xffff93de
 => 0
 => 0
 => 0xc8c5e17800000000
 => 0x1f30affff93de
 => 0x00000004
 => 0x200000000

Instead, subtract the size of the caller field from the size of the event
to make sure that only the amount needed to store the stack trace is
reserved.

Link: https://lore.kernel.org/lkml/your-ad-here.call-01617191565-ext-9692@work.hours/

Cc: stable@vger.kernel.org
Fixes: cbc3b92ce037 ("tracing: Set kernel_stack's caller size properly")
Reported-by: Vasily Gorbik <gor@linux.ibm.com>
Tested-by: Vasily Gorbik <gor@linux.ibm.com>
Acked-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index eccb4e1187cc..5c777627212f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2984,7 +2984,8 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 
 	size = nr_entries * sizeof(unsigned long);
 	event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
-					    sizeof(*entry) + size, trace_ctx);
+				    (sizeof(*entry) - sizeof(entry->caller)) + size,
+				    trace_ctx);
 	if (!event)
 		goto out;
 	entry = ring_buffer_event_data(event);

From 7582207b1059129e59eb92026fca2cfc088a74fc Mon Sep 17 00:00:00 2001
From: Md Haris Iqbal <haris.iqbal@cloud.ionos.com>
Date: Thu, 25 Mar 2021 16:32:57 +0100
Subject: [PATCH 1496/1820] RDMA/rtrs-clt: Close rtrs client conn before
 destroying rtrs clt session files

KASAN detected the following BUG:

  BUG: KASAN: use-after-free in rtrs_clt_update_wc_stats+0x41/0x100 [rtrs_client]
  Read of size 8 at addr ffff88bf2fb4adc0 by task swapper/0/0

  CPU: 0 PID: 0 Comm: swapper/0 Tainted: G           O      5.4.84-pserver #5.4.84-1+feature+linux+5.4.y+dbg+20201216.1319+b6b887b~deb10
  Hardware name: Supermicro H8QG6/H8QG6, BIOS 3.00       09/04/2012
  Call Trace:
   <IRQ>
   dump_stack+0x96/0xe0
   print_address_description.constprop.4+0x1f/0x300
   ? irq_work_claim+0x2e/0x50
   __kasan_report.cold.8+0x78/0x92
   ? rtrs_clt_update_wc_stats+0x41/0x100 [rtrs_client]
   kasan_report+0x10/0x20
   rtrs_clt_update_wc_stats+0x41/0x100 [rtrs_client]
   rtrs_clt_rdma_done+0xb1/0x760 [rtrs_client]
   ? lockdep_hardirqs_on+0x1a8/0x290
   ? process_io_rsp+0xb0/0xb0 [rtrs_client]
   ? mlx4_ib_destroy_cq+0x100/0x100 [mlx4_ib]
   ? add_interrupt_randomness+0x1a2/0x340
   __ib_process_cq+0x97/0x100 [ib_core]
   ib_poll_handler+0x41/0xb0 [ib_core]
   irq_poll_softirq+0xe0/0x260
   __do_softirq+0x127/0x672
   irq_exit+0xd1/0xe0
   do_IRQ+0xa3/0x1d0
   common_interrupt+0xf/0xf
   </IRQ>
  RIP: 0010:cpuidle_enter_state+0xea/0x780
  Code: 31 ff e8 99 48 47 ff 80 7c 24 08 00 74 12 9c 58 f6 c4 02 0f 85 53 05 00 00 31 ff e8 b0 6f 53 ff e8 ab 4f 5e ff fb 8b 44 24 04 <85> c0 0f 89 f3 01 00 00 48 8d 7b 14 e8 65 1e 77 ff c7 43 14 00 00
  RSP: 0018:ffffffffab007d58 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffca
  RAX: 0000000000000002 RBX: ffff88b803d69800 RCX: ffffffffa91a8298
  RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffffffffab021414
  RBP: ffffffffab6329e0 R08: 0000000000000002 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000002
  R13: 000000bf39d82466 R14: ffffffffab632aa0 R15: ffffffffab632ae0
   ? lockdep_hardirqs_on+0x1a8/0x290
   ? cpuidle_enter_state+0xe5/0x780
   cpuidle_enter+0x3c/0x60
   do_idle+0x2fb/0x390
   ? arch_cpu_idle_exit+0x40/0x40
   ? schedule+0x94/0x120
   cpu_startup_entry+0x19/0x1b
   start_kernel+0x5da/0x61b
   ? thread_stack_cache_init+0x6/0x6
   ? load_ucode_amd_bsp+0x6f/0xc4
   ? init_amd_microcode+0xa6/0xa6
   ? x86_family+0x5/0x20
   ? load_ucode_bsp+0x182/0x1fd
   secondary_startup_64+0xa4/0xb0

  Allocated by task 5730:
   save_stack+0x19/0x80
   __kasan_kmalloc.constprop.9+0xc1/0xd0
   kmem_cache_alloc_trace+0x15b/0x350
   alloc_sess+0xf4/0x570 [rtrs_client]
   rtrs_clt_open+0x3b4/0x780 [rtrs_client]
   find_and_get_or_create_sess+0x649/0x9d0 [rnbd_client]
   rnbd_clt_map_device+0xd7/0xf50 [rnbd_client]
   rnbd_clt_map_device_store+0x4ee/0x970 [rnbd_client]
   kernfs_fop_write+0x141/0x240
   vfs_write+0xf3/0x280
   ksys_write+0xba/0x150
   do_syscall_64+0x68/0x270
   entry_SYSCALL_64_after_hwframe+0x49/0xbe

  Freed by task 5822:
   save_stack+0x19/0x80
   __kasan_slab_free+0x125/0x170
   kfree+0xe7/0x3f0
   kobject_put+0xd3/0x240
   rtrs_clt_destroy_sess_files+0x3f/0x60 [rtrs_client]
   rtrs_clt_close+0x3c/0x80 [rtrs_client]
   close_rtrs+0x45/0x80 [rnbd_client]
   rnbd_client_exit+0x10f/0x2bd [rnbd_client]
   __x64_sys_delete_module+0x27b/0x340
   do_syscall_64+0x68/0x270
   entry_SYSCALL_64_after_hwframe+0x49/0xbe

When rtrs_clt_close is triggered, it iterates over all the present
rtrs_clt_sess and triggers close on them. However, the call to
rtrs_clt_destroy_sess_files is done before the rtrs_clt_close_conns. This
is incorrect since during the initialization phase we allocate
rtrs_clt_sess first, and then we go ahead and create rtrs_clt_con for it.

If we free the rtrs_clt_sess structure before closing the rtrs_clt_con, it
may so happen that an inflight IO completion would trigger the function
rtrs_clt_rdma_done, which would lead to the above UAF case.

Hence close the rtrs_clt_con connections first, and then trigger the
destruction of session files.

Fixes: 6a98d71daea1 ("RDMA/rtrs: client: main functionality")
Link: https://lore.kernel.org/r/20210325153308.1214057-12-gi-oh.kim@ionos.com
Signed-off-by: Md Haris Iqbal <haris.iqbal@ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
Signed-off-by: Gioh Kim <gi-oh.kim@ionos.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/ulp/rtrs/rtrs-clt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 0a08b4b742a3..6734329cca33 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -2720,8 +2720,8 @@ void rtrs_clt_close(struct rtrs_clt *clt)
 
 	/* Now it is safe to iterate over all paths without locks */
 	list_for_each_entry_safe(sess, tmp, &clt->paths_list, s.entry) {
-		rtrs_clt_destroy_sess_files(sess, NULL);
 		rtrs_clt_close_conns(sess, true);
+		rtrs_clt_destroy_sess_files(sess, NULL);
 		kobject_put(&sess->kobj);
 	}
 	free_clt(clt);

From 06ab134ce8ecfa5a69e850f88f81c8a4c3fa91df Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Wed, 31 Mar 2021 17:07:47 -0700
Subject: [PATCH 1497/1820] bpf: Refcount task stack in bpf_get_task_stack

On x86 the struct pt_regs * grabbed by task_pt_regs() points to an
offset of task->stack. The pt_regs are later dereferenced in
__bpf_get_stack (e.g. by user_mode() check). This can cause a fault if
the task in question exits while bpf_get_task_stack is executing, as
warned by task_stack_page's comment:

* When accessing the stack of a non-current task that might exit, use
* try_get_task_stack() instead.  task_stack_page will return a pointer
* that could get freed out from under you.

Taking the comment's advice and using try_get_task_stack() and
put_task_stack() to hold task->stack refcount, or bail early if it's
already 0. Incrementing stack_refcount will ensure the task's stack
sticks around while we're using its data.

I noticed this bug while testing a bpf task iter similar to
bpf_iter_task_stack in selftests, except mine grabbed user stack, and
getting intermittent crashes, which resulted in dumps like:

  BUG: unable to handle page fault for address: 0000000000003fe0
  \#PF: supervisor read access in kernel mode
  \#PF: error_code(0x0000) - not-present page
  RIP: 0010:__bpf_get_stack+0xd0/0x230
  <snip...>
  Call Trace:
  bpf_prog_0a2be35c092cb190_get_task_stacks+0x5d/0x3ec
  bpf_iter_run_prog+0x24/0x81
  __task_seq_show+0x58/0x80
  bpf_seq_read+0xf7/0x3d0
  vfs_read+0x91/0x140
  ksys_read+0x59/0xd0
  do_syscall_64+0x48/0x120
  entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: fa28dcb82a38 ("bpf: Introduce helper bpf_get_task_stack()")
Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20210401000747.3648767-1-davemarchevsky@fb.com
---
 kernel/bpf/stackmap.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index be35bfb7fb13..6fbc2abe9c91 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -517,9 +517,17 @@ const struct bpf_func_proto bpf_get_stack_proto = {
 BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 	   u32, size, u64, flags)
 {
-	struct pt_regs *regs = task_pt_regs(task);
+	struct pt_regs *regs;
+	long res;
 
-	return __bpf_get_stack(regs, task, NULL, buf, size, flags);
+	if (!try_get_task_stack(task))
+		return -EFAULT;
+
+	regs = task_pt_regs(task);
+	res = __bpf_get_stack(regs, task, NULL, buf, size, flags);
+	put_task_stack(task);
+
+	return res;
 }
 
 BTF_ID_LIST_SINGLE(bpf_get_task_stack_btf_ids, struct, task_struct)

From 6a3193cdd5e5b96ac65f04ee42555c216da332af Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 22 Mar 2021 16:44:38 -0700
Subject: [PATCH 1498/1820] kbuild: lto: Merge module sections if and only if
 CONFIG_LTO_CLANG is enabled

Merge module sections only when using Clang LTO. With ld.bfd, merging
sections does not appear to update the symbol tables for the module,
e.g. 'readelf -s' shows the value that a symbol would have had, if
sections were not merged. ld.lld does not show this problem.

The stale symbol table breaks gdb's function disassembler, and presumably
other things, e.g.

  gdb -batch -ex "file arch/x86/kvm/kvm.ko" -ex "disassemble kvm_init"

reads the wrong bytes and dumps garbage.

Fixes: dd2776222abb ("kbuild: lto: merge module sections")
Cc: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20210322234438.502582-1-seanjc@google.com
---
 scripts/module.lds.S | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/module.lds.S b/scripts/module.lds.S
index 168cd27e6122..2c52535f9b56 100644
--- a/scripts/module.lds.S
+++ b/scripts/module.lds.S
@@ -20,6 +20,7 @@ SECTIONS {
 
 	__patchable_function_entries : { *(__patchable_function_entries) }
 
+#ifdef CONFIG_LTO_CLANG
 	/*
 	 * With CONFIG_LTO_CLANG, LLD always enables -fdata-sections and
 	 * -ffunction-sections, which increases the size of the final module.
@@ -41,6 +42,7 @@ SECTIONS {
 	}
 
 	.text : { *(.text .text.[0-9a-zA-Z_]*) }
+#endif
 }
 
 /* bring in arch-specific sections */

From 5620b135aea49a8f41c86aaecfcb1598a7774121 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Thu, 25 Mar 2021 14:28:22 -0700
Subject: [PATCH 1499/1820] drm/msm: Set drvdata to NULL when msm_drm_init()
 fails

We should set the platform device's driver data to NULL here so that
code doesn't assume the struct drm_device pointer is valid when it could
have been destroyed. The lifetime of this pointer is managed by a kref
but when msm_drm_init() fails we call drm_dev_put() on the pointer which
will free the pointer's memory. This driver uses the component model, so
there's sort of two "probes" in this file, one for the platform device
i.e. msm_pdev_probe() and one for the component i.e. msm_drm_bind(). The
msm_drm_bind() code is using the platform device's driver data to store
struct drm_device so the two functions are intertwined.

This relationship becomes a problem for msm_pdev_shutdown() when it
tests the NULL-ness of the pointer to see if it should call
drm_atomic_helper_shutdown(). The NULL test is a proxy check for if the
pointer has been freed by kref_put(). If the drm_device has been
destroyed, then we shouldn't call the shutdown helper, and we know that
is the case if msm_drm_init() failed, therefore set the driver data to
NULL so that this pointer liveness is tracked properly.

Fixes: 9d5cbf5fe46e ("drm/msm: add shutdown support for display platform_driver")
Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Cc: Fabio Estevam <festevam@gmail.com>
Cc: Krishna Manikandan <mkrishn@codeaurora.org>
Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Message-Id: <20210325212822.3663144-1-swboyd@chromium.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/msm_drv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index a5c6b8c23336..196907689c82 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -570,6 +570,7 @@ err_free_priv:
 	kfree(priv);
 err_put_drm_dev:
 	drm_dev_put(ddev);
+	platform_set_drvdata(pdev, NULL);
 	return ret;
 }
 

From 2b0b219e5ff8bcc673d3a2cb6f327b3c62c5637d Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Tue, 30 Mar 2021 01:34:08 +0000
Subject: [PATCH 1500/1820] drm/msm: Fix removal of valid error case when
 checking speed_bin

Commit 7bf168c8fe8c  ("drm/msm: Fix speed-bin support not to
access outside valid memory"), reworked the nvmem reading of
"speed_bin", but in doing so dropped handling of the -ENOENT
case which was previously documented as "fine".

That change resulted in the db845c board display to fail to
start, with the following error:

adreno 5000000.gpu: [drm:a6xx_gpu_init] *ERROR* failed to read speed-bin (-2). Some OPPs may not be supported by hardware

Thus, this patch simply re-adds the ENOENT handling so the lack
of the speed_bin entry isn't fatal for display, and gets things
working on db845c.

Cc: Rob Clark <robdclark@gmail.com>
Cc: Sean Paul <sean@poorly.run>
Cc: Jordan Crouse <jcrouse@codeaurora.org>
Cc: Eric Anholt <eric@anholt.net>
Cc: Douglas Anderson <dianders@chromium.org>
Cc: linux-arm-msm@vger.kernel.org
Cc: freedreno@lists.freedesktop.org
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Cc: YongQin Liu <yongqin.liu@linaro.org>
Reported-by: YongQin Liu <yongqin.liu@linaro.org>
Fixes: 7bf168c8fe8c  ("drm/msm: Fix speed-bin support not to access outside valid memory")
Signed-off-by: John Stultz <john.stultz@linaro.org>
Reviewed-by: Akhil P Oommen <akhilpo@codeaurora.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Message-Id: <20210330013408.2532048-1-john.stultz@linaro.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 690409ca8a18..cb2df8736ca8 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1406,7 +1406,13 @@ static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
 	int ret;
 
 	ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin);
-	if (ret) {
+	/*
+	 * -ENOENT means that the platform doesn't support speedbin which is
+	 * fine
+	 */
+	if (ret == -ENOENT) {
+		return 0;
+	} else if (ret) {
 		DRM_DEV_ERROR(dev,
 			      "failed to read speed-bin (%d). Some OPPs may not be supported by hardware",
 			      ret);

From 25fc94b2f02d832fa8e29419699dcc20b0b05c6a Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Fri, 26 Mar 2021 16:05:00 +0000
Subject: [PATCH 1501/1820] bpf: link: Refuse non-O_RDWR flags in BPF_OBJ_GET

Invoking BPF_OBJ_GET on a pinned bpf_link checks the path access
permissions based on file_flags, but the returned fd ignores flags.
This means that any user can acquire a "read-write" fd for a pinned
link with mode 0664 by invoking BPF_OBJ_GET with BPF_F_RDONLY in
file_flags. The fd can be used to invoke BPF_LINK_DETACH, etc.

Fix this by refusing non-O_RDWR flags in BPF_OBJ_GET. This works
because OBJ_GET by default returns a read write mapping and libbpf
doesn't expose a way to override this behaviour for programs
and links.

Fixes: 70ed506c3bbc ("bpf: Introduce pinnable bpf_link abstraction")
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210326160501.46234-1-lmb@cloudflare.com
---
 kernel/bpf/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 1576ff331ee4..dc56237d6960 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -547,7 +547,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags)
 	else if (type == BPF_TYPE_MAP)
 		ret = bpf_map_new_fd(raw, f_flags);
 	else if (type == BPF_TYPE_LINK)
-		ret = bpf_link_new_fd(raw);
+		ret = (f_flags != O_RDWR) ? -EINVAL : bpf_link_new_fd(raw);
 	else
 		return -ENOENT;
 

From d37300ed182131f1757895a62e556332857417e5 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Fri, 26 Mar 2021 16:05:01 +0000
Subject: [PATCH 1502/1820] bpf: program: Refuse non-O_RDWR flags in
 BPF_OBJ_GET

As for bpf_link, refuse creating a non-O_RDWR fd. Since program fds
currently don't allow modifications this is a precaution, not a
straight up bug fix.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210326160501.46234-2-lmb@cloudflare.com
---
 kernel/bpf/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index dc56237d6960..d2de2abec35b 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -543,7 +543,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags)
 		return PTR_ERR(raw);
 
 	if (type == BPF_TYPE_PROG)
-		ret = bpf_prog_new_fd(raw);
+		ret = (f_flags != O_RDWR) ? -EINVAL : bpf_prog_new_fd(raw);
 	else if (type == BPF_TYPE_MAP)
 		ret = bpf_map_new_fd(raw, f_flags);
 	else if (type == BPF_TYPE_LINK)

From df662016310aa4475d7986fd726af45c8fe4f362 Mon Sep 17 00:00:00 2001
From: Ciara Loftus <ciara.loftus@intel.com>
Date: Wed, 31 Mar 2021 06:12:16 +0000
Subject: [PATCH 1503/1820] libbpf: Ensure umem pointer is non-NULL before
 dereferencing

Calls to xsk_socket__create dereference the umem to access the
fill_save and comp_save pointers. Make sure the umem is non-NULL
before doing this.

Fixes: 2f6324a3937f ("libbpf: Support shared umems between queues and devices")
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20210331061218.1647-2-ciara.loftus@intel.com
---
 tools/lib/bpf/xsk.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 526fc35c0b23..443b0cfb45e8 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -1019,6 +1019,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 		       struct xsk_ring_cons *rx, struct xsk_ring_prod *tx,
 		       const struct xsk_socket_config *usr_config)
 {
+	if (!umem)
+		return -EFAULT;
+
 	return xsk_socket__create_shared(xsk_ptr, ifname, queue_id, umem,
 					 rx, tx, umem->fill_save,
 					 umem->comp_save, usr_config);

From 43f1bc1efff16f553dd573d02eb7a15750925568 Mon Sep 17 00:00:00 2001
From: Ciara Loftus <ciara.loftus@intel.com>
Date: Wed, 31 Mar 2021 06:12:17 +0000
Subject: [PATCH 1504/1820] libbpf: Restore umem state after socket create
 failure

If the call to xsk_socket__create fails, the user may want to retry the
socket creation using the same umem. Ensure that the umem is in the
same state on exit if the call fails by:
1. ensuring the umem _save pointers are unmodified.
2. not unmapping the set of umem rings that were set up with the umem
during xsk_umem__create, since those maps existed before the call to
xsk_socket__create and should remain in tact even in the event of
failure.

Fixes: 2f6324a3937f ("libbpf: Support shared umems between queues and devices")
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331061218.1647-3-ciara.loftus@intel.com
---
 tools/lib/bpf/xsk.c | 41 +++++++++++++++++++++++------------------
 1 file changed, 23 insertions(+), 18 deletions(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 443b0cfb45e8..5098d9e3b55a 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -743,26 +743,30 @@ static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex,
 	return NULL;
 }
 
-static void xsk_put_ctx(struct xsk_ctx *ctx)
+static void xsk_put_ctx(struct xsk_ctx *ctx, bool unmap)
 {
 	struct xsk_umem *umem = ctx->umem;
 	struct xdp_mmap_offsets off;
 	int err;
 
-	if (--ctx->refcount == 0) {
-		err = xsk_get_mmap_offsets(umem->fd, &off);
-		if (!err) {
-			munmap(ctx->fill->ring - off.fr.desc,
-			       off.fr.desc + umem->config.fill_size *
-			       sizeof(__u64));
-			munmap(ctx->comp->ring - off.cr.desc,
-			       off.cr.desc + umem->config.comp_size *
-			       sizeof(__u64));
-		}
+	if (--ctx->refcount)
+		return;
 
-		list_del(&ctx->list);
-		free(ctx);
-	}
+	if (!unmap)
+		goto out_free;
+
+	err = xsk_get_mmap_offsets(umem->fd, &off);
+	if (err)
+		goto out_free;
+
+	munmap(ctx->fill->ring - off.fr.desc, off.fr.desc + umem->config.fill_size *
+	       sizeof(__u64));
+	munmap(ctx->comp->ring - off.cr.desc, off.cr.desc + umem->config.comp_size *
+	       sizeof(__u64));
+
+out_free:
+	list_del(&ctx->list);
+	free(ctx);
 }
 
 static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
@@ -797,8 +801,6 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
 	memcpy(ctx->ifname, ifname, IFNAMSIZ - 1);
 	ctx->ifname[IFNAMSIZ - 1] = '\0';
 
-	umem->fill_save = NULL;
-	umem->comp_save = NULL;
 	ctx->fill = fill;
 	ctx->comp = comp;
 	list_add(&ctx->list, &umem->ctx_list);
@@ -854,6 +856,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	struct xsk_socket *xsk;
 	struct xsk_ctx *ctx;
 	int err, ifindex;
+	bool unmap = umem->fill_save != fill;
 
 	if (!umem || !xsk_ptr || !(rx || tx))
 		return -EFAULT;
@@ -994,6 +997,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	}
 
 	*xsk_ptr = xsk;
+	umem->fill_save = NULL;
+	umem->comp_save = NULL;
 	return 0;
 
 out_mmap_tx:
@@ -1005,7 +1010,7 @@ out_mmap_rx:
 		munmap(rx_map, off.rx.desc +
 		       xsk->config.rx_size * sizeof(struct xdp_desc));
 out_put_ctx:
-	xsk_put_ctx(ctx);
+	xsk_put_ctx(ctx, unmap);
 out_socket:
 	if (--umem->refcount)
 		close(xsk->fd);
@@ -1071,7 +1076,7 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 		}
 	}
 
-	xsk_put_ctx(ctx);
+	xsk_put_ctx(ctx, true);
 
 	umem->refcount--;
 	/* Do not close an fd that also has an associated umem connected

From ca7a83e2487ad0bc9a3e0e7a8645354aa1782f13 Mon Sep 17 00:00:00 2001
From: Ciara Loftus <ciara.loftus@intel.com>
Date: Wed, 31 Mar 2021 06:12:18 +0000
Subject: [PATCH 1505/1820] libbpf: Only create rx and tx XDP rings when
 necessary

Prior to this commit xsk_socket__create(_shared) always attempted to create
the rx and tx rings for the socket. However this causes an issue when the
socket being setup is that which shares the fd with the UMEM. If a
previous call to this function failed with this socket after the rings were
set up, a subsequent call would always fail because the rings are not torn
down after the first call and when we try to set them up again we encounter
an error because they already exist. Solve this by remembering whether the
rings were set up by introducing new bools to struct xsk_umem which
represent the ring setup status and using them to determine whether or
not to set up the rings.

Fixes: 1cad07884239 ("libbpf: add support for using AF_XDP sockets")
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331061218.1647-4-ciara.loftus@intel.com
---
 tools/lib/bpf/xsk.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 5098d9e3b55a..d24b5cc720ec 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -59,6 +59,8 @@ struct xsk_umem {
 	int fd;
 	int refcount;
 	struct list_head ctx_list;
+	bool rx_ring_setup_done;
+	bool tx_ring_setup_done;
 };
 
 struct xsk_ctx {
@@ -857,6 +859,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	struct xsk_ctx *ctx;
 	int err, ifindex;
 	bool unmap = umem->fill_save != fill;
+	bool rx_setup_done = false, tx_setup_done = false;
 
 	if (!umem || !xsk_ptr || !(rx || tx))
 		return -EFAULT;
@@ -884,6 +887,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 		}
 	} else {
 		xsk->fd = umem->fd;
+		rx_setup_done = umem->rx_ring_setup_done;
+		tx_setup_done = umem->tx_ring_setup_done;
 	}
 
 	ctx = xsk_get_ctx(umem, ifindex, queue_id);
@@ -902,7 +907,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	}
 	xsk->ctx = ctx;
 
-	if (rx) {
+	if (rx && !rx_setup_done) {
 		err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
 				 &xsk->config.rx_size,
 				 sizeof(xsk->config.rx_size));
@@ -910,8 +915,10 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 			err = -errno;
 			goto out_put_ctx;
 		}
+		if (xsk->fd == umem->fd)
+			umem->rx_ring_setup_done = true;
 	}
-	if (tx) {
+	if (tx && !tx_setup_done) {
 		err = setsockopt(xsk->fd, SOL_XDP, XDP_TX_RING,
 				 &xsk->config.tx_size,
 				 sizeof(xsk->config.tx_size));
@@ -919,6 +926,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 			err = -errno;
 			goto out_put_ctx;
 		}
+		if (xsk->fd == umem->fd)
+			umem->rx_ring_setup_done = true;
 	}
 
 	err = xsk_get_mmap_offsets(xsk->fd, &off);

From 6b9fbe16955152626557ec6f439f3407b7769941 Mon Sep 17 00:00:00 2001
From: Pavel Skripkin <paskripkin@gmail.com>
Date: Thu, 1 Apr 2021 07:46:24 +0300
Subject: [PATCH 1506/1820] drivers: net: fix memory leak in atusb_probe

syzbot reported memory leak in atusb_probe()[1].
The problem was in atusb_alloc_urbs().
Since urb is anchored, we need to release the reference
to correctly free the urb

backtrace:
    [<ffffffff82ba0466>] kmalloc include/linux/slab.h:559 [inline]
    [<ffffffff82ba0466>] usb_alloc_urb+0x66/0xe0 drivers/usb/core/urb.c:74
    [<ffffffff82ad3888>] atusb_alloc_urbs drivers/net/ieee802154/atusb.c:362 [inline][2]
    [<ffffffff82ad3888>] atusb_probe+0x158/0x820 drivers/net/ieee802154/atusb.c:1038 [1]

Reported-by: syzbot+28a246747e0a465127f3@syzkaller.appspotmail.com
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ieee802154/atusb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c
index 0dd0ba915ab9..23ee0b14cbfa 100644
--- a/drivers/net/ieee802154/atusb.c
+++ b/drivers/net/ieee802154/atusb.c
@@ -365,6 +365,7 @@ static int atusb_alloc_urbs(struct atusb *atusb, int n)
 			return -ENOMEM;
 		}
 		usb_anchor_urb(urb, &atusb->idle_urbs);
+		usb_free_urb(urb);
 		n--;
 	}
 	return 0;

From 98184612aca0a9ee42b8eb0262a49900ee9eef0d Mon Sep 17 00:00:00 2001
From: Norman Maurer <norman_maurer@apple.com>
Date: Thu, 1 Apr 2021 08:59:17 +0200
Subject: [PATCH 1507/1820] net: udp: Add support for getsockopt(..., ...,
 UDP_GRO, ..., ...);

Support for UDP_GRO was added in the past but the implementation for
getsockopt was missed which did lead to an error when we tried to
retrieve the setting for UDP_GRO. This patch adds the missing switch
case for UDP_GRO

Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.")
Signed-off-by: Norman Maurer <norman_maurer@apple.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 4a0478b17243..99d743eb9dc4 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2754,6 +2754,10 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
 		val = up->gso_size;
 		break;
 
+	case UDP_GRO:
+		val = up->gro_enabled;
+		break;
+
 	/* The following two cannot be changed on UDP sockets, the return is
 	 * always 0 (which corresponds to the full checksum coverage of UDP). */
 	case UDPLITE_SEND_CSCOV:

From a0b96b4a62745397aee662670cfc2157bac03f55 Mon Sep 17 00:00:00 2001
From: Pavel Skripkin <paskripkin@gmail.com>
Date: Thu, 1 Apr 2021 16:27:52 +0300
Subject: [PATCH 1508/1820] drivers: net: fix memory leak in
 peak_usb_create_dev

syzbot reported memory leak in peak_usb.
The problem was in case of failure after calling
->dev_init()[2] in peak_usb_create_dev()[1]. The data
allocated int dev_init() wasn't freed, so simple
->dev_free() call fix this problem.

backtrace:
    [<0000000079d6542a>] kmalloc include/linux/slab.h:552 [inline]
    [<0000000079d6542a>] kzalloc include/linux/slab.h:682 [inline]
    [<0000000079d6542a>] pcan_usb_fd_init+0x156/0x210 drivers/net/can/usb/peak_usb/pcan_usb_fd.c:868   [2]
    [<00000000c09f9057>] peak_usb_create_dev drivers/net/can/usb/peak_usb/pcan_usb_core.c:851 [inline] [1]
    [<00000000c09f9057>] peak_usb_probe+0x389/0x490 drivers/net/can/usb/peak_usb/pcan_usb_core.c:949

Reported-by: syzbot+91adee8d9ebb9193d22d@syzkaller.appspotmail.com
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/can/usb/peak_usb/pcan_usb_core.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 573b11559d73..28e916a04047 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -857,7 +857,7 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter,
 	if (dev->adapter->dev_set_bus) {
 		err = dev->adapter->dev_set_bus(dev, 0);
 		if (err)
-			goto lbl_unregister_candev;
+			goto adap_dev_free;
 	}
 
 	/* get device number early */
@@ -869,6 +869,10 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter,
 
 	return 0;
 
+adap_dev_free:
+	if (dev->adapter->dev_free)
+		dev->adapter->dev_free(dev);
+
 lbl_unregister_candev:
 	unregister_candev(netdev);
 

From 86581852d7710990d8af9dadfe9a661f0abf2114 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 1 Apr 2021 18:57:44 +0200
Subject: [PATCH 1509/1820] mptcp: forbit mcast-related sockopt on MPTCP
 sockets

Unrolling mcast state at msk dismantel time is bug prone, as
syzkaller reported:

======================================================
WARNING: possible circular locking dependency detected
5.11.0-syzkaller #0 Not tainted
------------------------------------------------------
syz-executor905/8822 is trying to acquire lock:
ffffffff8d678fe8 (rtnl_mutex){+.+.}-{3:3}, at: ipv6_sock_mc_close+0xd7/0x110 net/ipv6/mcast.c:323

but task is already holding lock:
ffff888024390120 (sk_lock-AF_INET6){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1600 [inline]
ffff888024390120 (sk_lock-AF_INET6){+.+.}-{0:0}, at: mptcp6_release+0x57/0x130 net/mptcp/protocol.c:3507

which lock already depends on the new lock.

Instead we can simply forbit any mcast-related setsockopt

Fixes: 717e79c867ca5 ("mptcp: Add setsockopt()/getsockopt() socket operations")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 45 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 1590b9d4cde2..e06cea0a3c54 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2878,6 +2878,48 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 	return ret;
 }
 
+static bool mptcp_unsupported(int level, int optname)
+{
+	if (level == SOL_IP) {
+		switch (optname) {
+		case IP_ADD_MEMBERSHIP:
+		case IP_ADD_SOURCE_MEMBERSHIP:
+		case IP_DROP_MEMBERSHIP:
+		case IP_DROP_SOURCE_MEMBERSHIP:
+		case IP_BLOCK_SOURCE:
+		case IP_UNBLOCK_SOURCE:
+		case MCAST_JOIN_GROUP:
+		case MCAST_LEAVE_GROUP:
+		case MCAST_JOIN_SOURCE_GROUP:
+		case MCAST_LEAVE_SOURCE_GROUP:
+		case MCAST_BLOCK_SOURCE:
+		case MCAST_UNBLOCK_SOURCE:
+		case MCAST_MSFILTER:
+			return true;
+		}
+		return false;
+	}
+	if (level == SOL_IPV6) {
+		switch (optname) {
+		case IPV6_ADDRFORM:
+		case IPV6_ADD_MEMBERSHIP:
+		case IPV6_DROP_MEMBERSHIP:
+		case IPV6_JOIN_ANYCAST:
+		case IPV6_LEAVE_ANYCAST:
+		case MCAST_JOIN_GROUP:
+		case MCAST_LEAVE_GROUP:
+		case MCAST_JOIN_SOURCE_GROUP:
+		case MCAST_LEAVE_SOURCE_GROUP:
+		case MCAST_BLOCK_SOURCE:
+		case MCAST_UNBLOCK_SOURCE:
+		case MCAST_MSFILTER:
+			return true;
+		}
+		return false;
+	}
+	return false;
+}
+
 static int mptcp_setsockopt(struct sock *sk, int level, int optname,
 			    sockptr_t optval, unsigned int optlen)
 {
@@ -2886,6 +2928,9 @@ static int mptcp_setsockopt(struct sock *sk, int level, int optname,
 
 	pr_debug("msk=%p", msk);
 
+	if (mptcp_unsupported(level, optname))
+		return -ENOPROTOOPT;
+
 	if (level == SOL_SOCKET)
 		return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);
 

From 0a3cc57978d1d1448312f8973bd84dca4a71433a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 1 Apr 2021 18:57:45 +0200
Subject: [PATCH 1510/1820] mptcp: revert "mptcp: provide subflow aware release
 function"

This change reverts commit ad98dd37051e ("mptcp: provide subflow aware
release function"). The latter introduced a deadlock spotted by
syzkaller and is not needed anymore after the previous commit.

Fixes: ad98dd37051e ("mptcp: provide subflow aware release function")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 55 ++------------------------------------------
 1 file changed, 2 insertions(+), 53 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e06cea0a3c54..4bde960e19dc 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -11,7 +11,6 @@
 #include <linux/netdevice.h>
 #include <linux/sched/signal.h>
 #include <linux/atomic.h>
-#include <linux/igmp.h>
 #include <net/sock.h>
 #include <net/inet_common.h>
 #include <net/inet_hashtables.h>
@@ -20,7 +19,6 @@
 #include <net/tcp_states.h>
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 #include <net/transp_v6.h>
-#include <net/addrconf.h>
 #endif
 #include <net/mptcp.h>
 #include <net/xfrm.h>
@@ -3464,34 +3462,10 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	return mask;
 }
 
-static int mptcp_release(struct socket *sock)
-{
-	struct mptcp_subflow_context *subflow;
-	struct sock *sk = sock->sk;
-	struct mptcp_sock *msk;
-
-	if (!sk)
-		return 0;
-
-	lock_sock(sk);
-
-	msk = mptcp_sk(sk);
-
-	mptcp_for_each_subflow(msk, subflow) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
-		ip_mc_drop_socket(ssk);
-	}
-
-	release_sock(sk);
-
-	return inet_release(sock);
-}
-
 static const struct proto_ops mptcp_stream_ops = {
 	.family		   = PF_INET,
 	.owner		   = THIS_MODULE,
-	.release	   = mptcp_release,
+	.release	   = inet_release,
 	.bind		   = mptcp_bind,
 	.connect	   = mptcp_stream_connect,
 	.socketpair	   = sock_no_socketpair,
@@ -3583,35 +3557,10 @@ void __init mptcp_proto_init(void)
 }
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-static int mptcp6_release(struct socket *sock)
-{
-	struct mptcp_subflow_context *subflow;
-	struct mptcp_sock *msk;
-	struct sock *sk = sock->sk;
-
-	if (!sk)
-		return 0;
-
-	lock_sock(sk);
-
-	msk = mptcp_sk(sk);
-
-	mptcp_for_each_subflow(msk, subflow) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
-		ip_mc_drop_socket(ssk);
-		ipv6_sock_mc_close(ssk);
-		ipv6_sock_ac_close(ssk);
-	}
-
-	release_sock(sk);
-	return inet6_release(sock);
-}
-
 static const struct proto_ops mptcp_v6_stream_ops = {
 	.family		   = PF_INET6,
 	.owner		   = THIS_MODULE,
-	.release	   = mptcp6_release,
+	.release	   = inet6_release,
 	.bind		   = mptcp_bind,
 	.connect	   = mptcp_stream_connect,
 	.socketpair	   = sock_no_socketpair,

From 5482a9a1a8fd23fbb57afc6d409e12713aa93fa5 Mon Sep 17 00:00:00 2001
From: Sergei Trofimovich <slyfox@gentoo.org>
Date: Tue, 30 Mar 2021 08:19:56 +0100
Subject: [PATCH 1511/1820] scsi: hpsa: Use __packed on individual structs, not
 header-wide

The hpsa driver uses data structures which contain a combination of driver
internals and commands sent directly to the hardware. To manage alignment
for the hardware portions the driver used #pragma pack(1).

Commit f749d8b7a989 ("scsi: hpsa: Correct dev cmds outstanding for retried
cmds") switched an existing variable from int to bool. Due to the pragma an
atomic_t in the same data structure ended up being misaligned and broke
boot on ia64.

Add __packed to every struct and union in the header file. Subsequent
commits will address the actual atomic_t misalignment regression.

The commit is a no-op at least on ia64:
    $ diff -u <(objdump -d -r old.o) <(objdump -d -r new.o)

Link: https://lore.kernel.org/r/20210330071958.3788214-1-slyfox@gentoo.org
Fixes: f749d8b7a989 ("scsi: hpsa: Correct dev cmds outstanding for retried cmds")
CC: linux-ia64@vger.kernel.org
CC: storagedev@microchip.com
CC: linux-scsi@vger.kernel.org
CC: Joe Szczypek <jszczype@redhat.com>
CC: Scott Benesh <scott.benesh@microchip.com>
CC: Scott Teel <scott.teel@microchip.com>
CC: Tomas Henzl <thenzl@redhat.com>
CC: "Martin K. Petersen" <martin.petersen@oracle.com>
CC: Don Brace <don.brace@microchip.com>
Reported-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Suggested-by: Don Brace <don.brace@microchip.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hpsa_cmd.h | 68 ++++++++++++++++++++---------------------
 1 file changed, 34 insertions(+), 34 deletions(-)

diff --git a/drivers/scsi/hpsa_cmd.h b/drivers/scsi/hpsa_cmd.h
index d126bb877250..280e933d27e7 100644
--- a/drivers/scsi/hpsa_cmd.h
+++ b/drivers/scsi/hpsa_cmd.h
@@ -20,6 +20,8 @@
 #ifndef HPSA_CMD_H
 #define HPSA_CMD_H
 
+#include <linux/compiler.h>
+
 /* general boundary defintions */
 #define SENSEINFOBYTES          32 /* may vary between hbas */
 #define SG_ENTRIES_IN_CMD	32 /* Max SG entries excluding chain blocks */
@@ -200,12 +202,10 @@ union u64bit {
 	MAX_EXT_TARGETS + 1) /* + 1 is for the controller itself */
 
 /* SCSI-3 Commands */
-#pragma pack(1)
-
 #define HPSA_INQUIRY 0x12
 struct InquiryData {
 	u8 data_byte[36];
-};
+} __packed;
 
 #define HPSA_REPORT_LOG 0xc2    /* Report Logical LUNs */
 #define HPSA_REPORT_PHYS 0xc3   /* Report Physical LUNs */
@@ -221,7 +221,7 @@ struct raid_map_disk_data {
 	u8    xor_mult[2];            /**< XOR multipliers for this position,
 					*  valid for data disks only */
 	u8    reserved[2];
-};
+} __packed;
 
 struct raid_map_data {
 	__le32   structure_size;	/* Size of entire structure in bytes */
@@ -247,14 +247,14 @@ struct raid_map_data {
 	__le16   dekindex;		/* Data encryption key index. */
 	u8    reserved[16];
 	struct raid_map_disk_data data[RAID_MAP_MAX_ENTRIES];
-};
+} __packed;
 
 struct ReportLUNdata {
 	u8 LUNListLength[4];
 	u8 extended_response_flag;
 	u8 reserved[3];
 	u8 LUN[HPSA_MAX_LUN][8];
-};
+} __packed;
 
 struct ext_report_lun_entry {
 	u8 lunid[8];
@@ -269,20 +269,20 @@ struct ext_report_lun_entry {
 	u8 lun_count; /* multi-lun device, how many luns */
 	u8 redundant_paths;
 	u32 ioaccel_handle; /* ioaccel1 only uses lower 16 bits */
-};
+} __packed;
 
 struct ReportExtendedLUNdata {
 	u8 LUNListLength[4];
 	u8 extended_response_flag;
 	u8 reserved[3];
 	struct ext_report_lun_entry LUN[HPSA_MAX_PHYS_LUN];
-};
+} __packed;
 
 struct SenseSubsystem_info {
 	u8 reserved[36];
 	u8 portname[8];
 	u8 reserved1[1108];
-};
+} __packed;
 
 /* BMIC commands */
 #define BMIC_READ 0x26
@@ -317,7 +317,7 @@ union SCSI3Addr {
 		u8 Targ:6;
 		u8 Mode:2;        /* b10 */
 	} LogUnit;
-};
+} __packed;
 
 struct PhysDevAddr {
 	u32             TargetId:24;
@@ -325,20 +325,20 @@ struct PhysDevAddr {
 	u32             Mode:2;
 	/* 2 level target device addr */
 	union SCSI3Addr  Target[2];
-};
+} __packed;
 
 struct LogDevAddr {
 	u32            VolId:30;
 	u32            Mode:2;
 	u8             reserved[4];
-};
+} __packed;
 
 union LUNAddr {
 	u8               LunAddrBytes[8];
 	union SCSI3Addr    SCSI3Lun[4];
 	struct PhysDevAddr PhysDev;
 	struct LogDevAddr  LogDev;
-};
+} __packed;
 
 struct CommandListHeader {
 	u8              ReplyQueue;
@@ -346,7 +346,7 @@ struct CommandListHeader {
 	__le16          SGTotal;
 	__le64		tag;
 	union LUNAddr     LUN;
-};
+} __packed;
 
 struct RequestBlock {
 	u8   CDBLen;
@@ -365,18 +365,18 @@ struct RequestBlock {
 #define GET_DIR(tad) (((tad) >> 6) & 0x03)
 	u16  Timeout;
 	u8   CDB[16];
-};
+} __packed;
 
 struct ErrDescriptor {
 	__le64 Addr;
 	__le32 Len;
-};
+} __packed;
 
 struct SGDescriptor {
 	__le64 Addr;
 	__le32 Len;
 	__le32 Ext;
-};
+} __packed;
 
 union MoreErrInfo {
 	struct {
@@ -390,7 +390,8 @@ union MoreErrInfo {
 		u8  offense_num;  /* byte # of offense 0-base */
 		u32 offense_value;
 	} Invalid_Cmd;
-};
+} __packed;
+
 struct ErrorInfo {
 	u8               ScsiStatus;
 	u8               SenseLen;
@@ -398,7 +399,7 @@ struct ErrorInfo {
 	u32              ResidualCnt;
 	union MoreErrInfo  MoreErrInfo;
 	u8               SenseInfo[SENSEINFOBYTES];
-};
+} __packed;
 /* Command types */
 #define CMD_IOCTL_PEND  0x01
 #define CMD_SCSI	0x03
@@ -451,7 +452,7 @@ struct CommandList {
 	bool retry_pending;
 	struct hpsa_scsi_dev_t *device;
 	atomic_t refcount; /* Must be last to avoid memset in hpsa_cmd_init() */
-} __aligned(COMMANDLIST_ALIGNMENT);
+} __packed __aligned(COMMANDLIST_ALIGNMENT);
 
 /* Max S/G elements in I/O accelerator command */
 #define IOACCEL1_MAXSGENTRIES           24
@@ -489,7 +490,7 @@ struct io_accel1_cmd {
 	__le64 host_addr;		/* 0x70 - 0x77 */
 	u8  CISS_LUN[8];		/* 0x78 - 0x7F */
 	struct SGDescriptor SG[IOACCEL1_MAXSGENTRIES];
-} __aligned(IOACCEL1_COMMANDLIST_ALIGNMENT);
+} __packed __aligned(IOACCEL1_COMMANDLIST_ALIGNMENT);
 
 #define IOACCEL1_FUNCTION_SCSIIO        0x00
 #define IOACCEL1_SGLOFFSET              32
@@ -519,7 +520,7 @@ struct ioaccel2_sg_element {
 	u8 chain_indicator;
 #define IOACCEL2_CHAIN 0x80
 #define IOACCEL2_LAST_SG 0x40
-};
+} __packed;
 
 /*
  * SCSI Response Format structure for IO Accelerator Mode 2
@@ -559,7 +560,7 @@ struct io_accel2_scsi_response {
 	u8 sense_data_len;		/* sense/response data length */
 	u8 resid_cnt[4];		/* residual count */
 	u8 sense_data_buff[32];		/* sense/response data buffer */
-};
+} __packed;
 
 /*
  * Structure for I/O accelerator (mode 2 or m2) commands.
@@ -592,7 +593,7 @@ struct io_accel2_cmd {
 	__le32 tweak_upper;		/* Encryption tweak, upper 4 bytes */
 	struct ioaccel2_sg_element sg[IOACCEL2_MAXSGENTRIES];
 	struct io_accel2_scsi_response error_data;
-} __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT);
+} __packed __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT);
 
 /*
  * defines for Mode 2 command struct
@@ -618,7 +619,7 @@ struct hpsa_tmf_struct {
 	__le64 abort_tag;	/* cciss tag of SCSI cmd or TMF to abort */
 	__le64 error_ptr;		/* Error Pointer */
 	__le32 error_len;		/* Error Length */
-} __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT);
+} __packed __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT);
 
 /* Configuration Table Structure */
 struct HostWrite {
@@ -626,7 +627,7 @@ struct HostWrite {
 	__le32		command_pool_addr_hi;
 	__le32		CoalIntDelay;
 	__le32		CoalIntCount;
-};
+} __packed;
 
 #define SIMPLE_MODE     0x02
 #define PERFORMANT_MODE 0x04
@@ -675,7 +676,7 @@ struct CfgTable {
 #define		HPSA_EVENT_NOTIFY_ACCEL_IO_PATH_STATE_CHANGE (1 << 30)
 #define		HPSA_EVENT_NOTIFY_ACCEL_IO_PATH_CONFIG_CHANGE (1 << 31)
 	__le32		clear_event_notify;
-};
+} __packed;
 
 #define NUM_BLOCKFETCH_ENTRIES 8
 struct TransTable_struct {
@@ -686,14 +687,14 @@ struct TransTable_struct {
 	__le32		RepQCtrAddrHigh32;
 #define MAX_REPLY_QUEUES 64
 	struct vals32  RepQAddr[MAX_REPLY_QUEUES];
-};
+} __packed;
 
 struct hpsa_pci_info {
 	unsigned char	bus;
 	unsigned char	dev_fn;
 	unsigned short	domain;
 	u32		board_id;
-};
+} __packed;
 
 struct bmic_identify_controller {
 	u8	configured_logical_drive_count;	/* offset 0 */
@@ -702,7 +703,7 @@ struct bmic_identify_controller {
 	u8	pad2[136];
 	u8	controller_mode;	/* offset 292 */
 	u8	pad3[32];
-};
+} __packed;
 
 
 struct bmic_identify_physical_device {
@@ -845,7 +846,7 @@ struct bmic_identify_physical_device {
 	u8     max_link_rate[256];
 	u8     neg_phys_link_rate[256];
 	u8     box_conn_name[8];
-} __attribute((aligned(512)));
+} __packed __attribute((aligned(512)));
 
 struct bmic_sense_subsystem_info {
 	u8	primary_slot_number;
@@ -858,7 +859,7 @@ struct bmic_sense_subsystem_info {
 	u8	secondary_array_serial_number[32];
 	u8	secondary_cache_serial_number[32];
 	u8	pad[332];
-};
+} __packed;
 
 struct bmic_sense_storage_box_params {
 	u8	reserved[36];
@@ -870,7 +871,6 @@ struct bmic_sense_storage_box_params {
 	u8	reserver_3[84];
 	u8	phys_connector[2];
 	u8	reserved_4[296];
-};
+} __packed;
 
-#pragma pack()
 #endif /* HPSA_CMD_H */

From 02ec144292bc424a5800d45d4cb472c66e97c520 Mon Sep 17 00:00:00 2001
From: Sergei Trofimovich <slyfox@gentoo.org>
Date: Tue, 30 Mar 2021 08:19:57 +0100
Subject: [PATCH 1512/1820] scsi: hpsa: Fix boot on ia64 (atomic_t alignment)

Boot failure was observed on an HP rx3600 ia64 machine with RAID bus
controller: Hewlett-Packard Company Smart Array P600:

    kernel unaligned access to 0xe000000105dd8b95, ip=0xa000000100b87551
    kernel unaligned access to 0xe000000105dd8e95, ip=0xa000000100b87551
    hpsa 0000:14:01.0: Controller reports max supported commands of 0 Using 16 instead. Ensure that firmware is up to date.
    swapper/0[1]: error during unaligned kernel access

The unaligned access comes from 'struct CommandList' that happens to be
packed. Commit f749d8b7a989 ("scsi: hpsa: Correct dev cmds outstanding for
retried cmds") introduced unexpected padding and unaligned atomic_t from
natural alignment to something else.

This change removes packing annotation from a struct not intended to be
sent to controller as is. This restores natural `atomic_t` alignment.

The change was tested on the same rx3600 machine.

Link: https://lore.kernel.org/r/20210330071958.3788214-2-slyfox@gentoo.org
Fixes: f749d8b7a989 ("scsi: hpsa: Correct dev cmds outstanding for retried cmds")
CC: linux-ia64@vger.kernel.org
CC: linux-kernel@vger.kernel.org
CC: storagedev@microchip.com
CC: linux-scsi@vger.kernel.org
CC: Joe Szczypek <jszczype@redhat.com>
CC: Scott Benesh <scott.benesh@microchip.com>
CC: Scott Teel <scott.teel@microchip.com>
CC: Tomas Henzl <thenzl@redhat.com>
CC: "Martin K. Petersen" <martin.petersen@oracle.com>
CC: Don Brace <don.brace@microchip.com>
Reported-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Suggested-by: Don Brace <don.brace@microchip.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hpsa_cmd.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/hpsa_cmd.h b/drivers/scsi/hpsa_cmd.h
index 280e933d27e7..885b1f1fb20a 100644
--- a/drivers/scsi/hpsa_cmd.h
+++ b/drivers/scsi/hpsa_cmd.h
@@ -452,7 +452,7 @@ struct CommandList {
 	bool retry_pending;
 	struct hpsa_scsi_dev_t *device;
 	atomic_t refcount; /* Must be last to avoid memset in hpsa_cmd_init() */
-} __packed __aligned(COMMANDLIST_ALIGNMENT);
+} __aligned(COMMANDLIST_ALIGNMENT);
 
 /* Max S/G elements in I/O accelerator command */
 #define IOACCEL1_MAXSGENTRIES           24

From e01a00ff62adca8ec464f3c8d82cfa0e8d8728dd Mon Sep 17 00:00:00 2001
From: Sergei Trofimovich <slyfox@gentoo.org>
Date: Tue, 30 Mar 2021 08:19:58 +0100
Subject: [PATCH 1513/1820] scsi: hpsa: Add an assert to prevent __packed
 reintroduction

Link: https://lore.kernel.org/r/20210330071958.3788214-3-slyfox@gentoo.org
Fixes: f749d8b7a989 ("scsi: hpsa: Correct dev cmds outstanding for retried cmds")
CC: linux-ia64@vger.kernel.org
CC: storagedev@microchip.com
CC: linux-scsi@vger.kernel.org
CC: Joe Szczypek <jszczype@redhat.com>
CC: Scott Benesh <scott.benesh@microchip.com>
CC: Scott Teel <scott.teel@microchip.com>
CC: Tomas Henzl <thenzl@redhat.com>
CC: "Martin K. Petersen" <martin.petersen@oracle.com>
CC: Don Brace <don.brace@microchip.com>
Reported-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Suggested-by: Don Brace <don.brace@microchip.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hpsa_cmd.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/scsi/hpsa_cmd.h b/drivers/scsi/hpsa_cmd.h
index 885b1f1fb20a..ba6a3aa8d954 100644
--- a/drivers/scsi/hpsa_cmd.h
+++ b/drivers/scsi/hpsa_cmd.h
@@ -22,6 +22,9 @@
 
 #include <linux/compiler.h>
 
+#include <linux/build_bug.h> /* static_assert */
+#include <linux/stddef.h> /* offsetof */
+
 /* general boundary defintions */
 #define SENSEINFOBYTES          32 /* may vary between hbas */
 #define SG_ENTRIES_IN_CMD	32 /* Max SG entries excluding chain blocks */
@@ -454,6 +457,15 @@ struct CommandList {
 	atomic_t refcount; /* Must be last to avoid memset in hpsa_cmd_init() */
 } __aligned(COMMANDLIST_ALIGNMENT);
 
+/*
+ * Make sure our embedded atomic variable is aligned. Otherwise we break atomic
+ * operations on architectures that don't support unaligned atomics like IA64.
+ *
+ * The assert guards against reintroductin against unwanted __packed to
+ * the struct CommandList.
+ */
+static_assert(offsetof(struct CommandList, refcount) % __alignof__(atomic_t) == 0);
+
 /* Max S/G elements in I/O accelerator command */
 #define IOACCEL1_MAXSGENTRIES           24
 #define IOACCEL2_MAXSGENTRIES		28

From 1235fc569e0bf541ddda0a1224d4c6fa6d914890 Mon Sep 17 00:00:00 2001
From: Can Guo <cang@codeaurora.org>
Date: Thu, 1 Apr 2021 00:39:08 -0700
Subject: [PATCH 1514/1820] scsi: ufs: core: Fix task management request
 completion timeout

ufshcd_tmc_handler() calls blk_mq_tagset_busy_iter(fn = ufshcd_compl_tm()),
but since blk_mq_tagset_busy_iter() only iterates over all reserved tags
and requests which are not in IDLE state, ufshcd_compl_tm() never gets a
chance to run. Thus, TMR always ends up with completion timeout. Fix it by
calling blk_mq_start_request() in __ufshcd_issue_tm_cmd().

Link: https://lore.kernel.org/r/1617262750-4864-2-git-send-email-cang@codeaurora.org
Fixes: 69a6c269c097 ("scsi: ufs: Use blk_{get,put}_request() to allocate and free TMFs")
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/ufshcd.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index c86760788c72..564918ffc026 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -6404,6 +6404,7 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 
 	spin_lock_irqsave(host->host_lock, flags);
 	task_tag = hba->nutrs + free_slot;
+	blk_mq_start_request(req);
 
 	treq->req_header.dword_0 |= cpu_to_be32(task_tag);
 

From 4b42d557a8add52b9a9924fb31e40a218aab7801 Mon Sep 17 00:00:00 2001
From: Can Guo <cang@codeaurora.org>
Date: Thu, 1 Apr 2021 00:39:09 -0700
Subject: [PATCH 1515/1820] scsi: ufs: core: Fix wrong Task Tag used in task
 management request UPIUs

In __ufshcd_issue_tm_cmd(), it is not correct to use hba->nutrs + req->tag
as the Task Tag in a TMR UPIU. Directly use req->tag as the Task Tag.

Fixes: e293313262d3 ("scsi: ufs: Fix broken task management command implementation")
Link: https://lore.kernel.org/r/1617262750-4864-3-git-send-email-cang@codeaurora.org
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/ufshcd.c | 30 +++++++++++++-----------------
 1 file changed, 13 insertions(+), 17 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 564918ffc026..d3d05e997c13 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -6386,38 +6386,34 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 	DECLARE_COMPLETION_ONSTACK(wait);
 	struct request *req;
 	unsigned long flags;
-	int free_slot, task_tag, err;
+	int task_tag, err;
 
 	/*
-	 * Get free slot, sleep if slots are unavailable.
-	 * Even though we use wait_event() which sleeps indefinitely,
-	 * the maximum wait time is bounded by %TM_CMD_TIMEOUT.
+	 * blk_get_request() is used here only to get a free tag.
 	 */
 	req = blk_get_request(q, REQ_OP_DRV_OUT, 0);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
 	req->end_io_data = &wait;
-	free_slot = req->tag;
-	WARN_ON_ONCE(free_slot < 0 || free_slot >= hba->nutmrs);
 	ufshcd_hold(hba, false);
 
 	spin_lock_irqsave(host->host_lock, flags);
-	task_tag = hba->nutrs + free_slot;
 	blk_mq_start_request(req);
 
+	task_tag = req->tag;
 	treq->req_header.dword_0 |= cpu_to_be32(task_tag);
 
-	memcpy(hba->utmrdl_base_addr + free_slot, treq, sizeof(*treq));
-	ufshcd_vops_setup_task_mgmt(hba, free_slot, tm_function);
+	memcpy(hba->utmrdl_base_addr + task_tag, treq, sizeof(*treq));
+	ufshcd_vops_setup_task_mgmt(hba, task_tag, tm_function);
 
 	/* send command to the controller */
-	__set_bit(free_slot, &hba->outstanding_tasks);
+	__set_bit(task_tag, &hba->outstanding_tasks);
 
 	/* Make sure descriptors are ready before ringing the task doorbell */
 	wmb();
 
-	ufshcd_writel(hba, 1 << free_slot, REG_UTP_TASK_REQ_DOOR_BELL);
+	ufshcd_writel(hba, 1 << task_tag, REG_UTP_TASK_REQ_DOOR_BELL);
 	/* Make sure that doorbell is committed immediately */
 	wmb();
 
@@ -6437,24 +6433,24 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 		ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_ERR);
 		dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n",
 				__func__, tm_function);
-		if (ufshcd_clear_tm_cmd(hba, free_slot))
-			dev_WARN(hba->dev, "%s: unable clear tm cmd (slot %d) after timeout\n",
-					__func__, free_slot);
+		if (ufshcd_clear_tm_cmd(hba, task_tag))
+			dev_WARN(hba->dev, "%s: unable to clear tm cmd (slot %d) after timeout\n",
+					__func__, task_tag);
 		err = -ETIMEDOUT;
 	} else {
 		err = 0;
-		memcpy(treq, hba->utmrdl_base_addr + free_slot, sizeof(*treq));
+		memcpy(treq, hba->utmrdl_base_addr + task_tag, sizeof(*treq));
 
 		ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_COMP);
 	}
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
-	__clear_bit(free_slot, &hba->outstanding_tasks);
+	__clear_bit(task_tag, &hba->outstanding_tasks);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
+	ufshcd_release(hba);
 	blk_put_request(req);
 
-	ufshcd_release(hba);
 	return err;
 }
 

From 23c1075ae83adaf14ea3f727c40368799f80bccc Mon Sep 17 00:00:00 2001
From: Kefeng Wang <wangkefeng.wang@huawei.com>
Date: Wed, 17 Mar 2021 23:08:38 +0800
Subject: [PATCH 1516/1820] riscv: Drop const annotation for sp

The const annotation should not be used for 'sp', or it will
become read only and lead to bad stack output.

Fixes: dec822771b01 ("riscv: stacktrace: Move register keyword to beginning of declaration")
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/kernel/stacktrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 3f893c9d9d85..2b3e0cb90d78 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -14,7 +14,7 @@
 
 #include <asm/stacktrace.h>
 
-register const unsigned long sp_in_global __asm__("sp");
+register unsigned long sp_in_global __asm__("sp");
 
 #ifdef CONFIG_FRAME_POINTER
 

From 285a76bb2cf51b0c74c634f2aaccdb93e1f2a359 Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Mon, 29 Mar 2021 10:57:49 +0100
Subject: [PATCH 1517/1820] riscv: evaluate put_user() arg before enabling user
 access

The <asm/uaccess.h> header has a problem with put_user(a, ptr) if
the 'a' is not a simple variable, such as a function. This can lead
to the compiler producing code as so:

1:	enable_user_access()
2:	evaluate 'a' into register 'r'
3:	put 'r' to 'ptr'
4:	disable_user_acess()

The issue is that 'a' is now being evaluated with the user memory
protections disabled. So we try and force the evaulation by assigning
'x' to __val at the start, and hoping the compiler barriers in
 enable_user_access() do the job of ordering step 2 before step 1.

This has shown up in a bug where 'a' sleeps and thus schedules out
and loses the SR_SUM flag. This isn't sufficient to fully fix, but
should reduce the window of opportunity. The first instance of this
we found is in scheudle_tail() where the code does:

$ less -N kernel/sched/core.c

4263  if (current->set_child_tid)
4264         put_user(task_pid_vnr(current), current->set_child_tid);

Here, the task_pid_vnr(current) is called within the block that has
enabled the user memory access. This can be made worse with KASAN
which makes task_pid_vnr() a rather large call with plenty of
opportunity to sleep.

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Reported-by: syzbot+e74b94fe601ab9552d69@syzkaller.appspotmail.com
Suggested-by: Arnd Bergman <arnd@arndb.de>

--
Changes since v1:
- fixed formatting and updated the patch description with more info

Changes since v2:
- fixed commenting on __put_user() (schwab@linux-m68k.org)

Change since v3:
- fixed RFC in patch title. Should be ready to merge.

Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/include/asm/uaccess.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 824b2c9da75b..f944062c9d99 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -306,7 +306,9 @@ do {								\
  * data types like structures or arrays.
  *
  * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
+ * to the result of dereferencing @ptr. The value of @x is copied to avoid
+ * re-ordering where @x is evaluated inside the block that enables user-space
+ * access (thus bypassing user space protection if @x is a function).
  *
  * Caller must check the pointer with access_ok() before calling this
  * function.
@@ -316,12 +318,13 @@ do {								\
 #define __put_user(x, ptr)					\
 ({								\
 	__typeof__(*(ptr)) __user *__gu_ptr = (ptr);		\
+	__typeof__(*__gu_ptr) __val = (x);			\
 	long __pu_err = 0;					\
 								\
 	__chk_user_ptr(__gu_ptr);				\
 								\
 	__enable_user_access();					\
-	__put_user_nocheck(x, __gu_ptr, __pu_err);		\
+	__put_user_nocheck(__val, __gu_ptr, __pu_err);		\
 	__disable_user_access();				\
 								\
 	__pu_err;						\

From ac8d0b901f0033b783156ab2dc1a0e73ec42409b Mon Sep 17 00:00:00 2001
From: Zihao Yu <yuzihao@ict.ac.cn>
Date: Wed, 17 Mar 2021 16:17:25 +0800
Subject: [PATCH 1518/1820] riscv,entry: fix misaligned base for
 excp_vect_table

In RV64, the size of each entry in excp_vect_table is 8 bytes. If the
base of the table is not 8-byte aligned, loading an entry in the table
will raise a misaligned exception. Although such exception will be
handled by opensbi/bbl, this still causes performance degradation.

Signed-off-by: Zihao Yu <yuzihao@ict.ac.cn>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/kernel/entry.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 744f3209c48d..76274a4a1d8e 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -447,6 +447,7 @@ ENDPROC(__switch_to)
 #endif
 
 	.section ".rodata"
+	.align LGREG
 	/* Exception vector table */
 ENTRY(excp_vect_table)
 	RISCV_PTR do_trap_insn_misaligned

From 9d8c7d92015ece9a2139a259cef781a41845d2c0 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Mon, 22 Mar 2021 16:38:36 +0800
Subject: [PATCH 1519/1820] riscv: remove unneeded semicolon

Eliminate the following coccicheck warning:
./arch/riscv/mm/kasan_init.c:219:2-3: Unneeded semicolon

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/mm/kasan_init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 4f85c6d0ddf8..937d13ce9ab8 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -216,7 +216,7 @@ void __init kasan_init(void)
 			break;
 
 		kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end));
-	};
+	}
 
 	for (i = 0; i < PTRS_PER_PTE; i++)
 		set_pte(&kasan_early_shadow_pte[i],

From 1adbc2941eee8acbe3c7dc6b51cdbc5a9bf19565 Mon Sep 17 00:00:00 2001
From: Kefeng Wang <wangkefeng.wang@huawei.com>
Date: Tue, 30 Mar 2021 21:25:31 +0800
Subject: [PATCH 1520/1820] riscv: Make NUMA depend on MMU

NUMA is useless when NOMMU, and it leads some build error,
make it depend on MMU.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 87d7b52f278f..0d0cf67359cb 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -314,7 +314,7 @@ endchoice
 # Common NUMA Features
 config NUMA
 	bool "NUMA Memory Allocation and Scheduler Support"
-	depends on SMP
+	depends on SMP && MMU
 	select GENERIC_ARCH_NUMA
 	select OF_NUMA
 	select ARCH_SUPPORTS_NUMA_BALANCING

From 9b5b872215fe6d1ca6a1ef411f130bd58e269012 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Fri, 2 Apr 2021 10:29:36 +0200
Subject: [PATCH 1521/1820] file: fix close_range() for unshare+cloexec

syzbot reported a bug when putting the last reference to a tasks file
descriptor table. Debugging this showed we didn't recalculate the
current maximum fd number for CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC
after we unshared the file descriptors table. So max_fd could exceed the
current fdtable maximum causing us to set excessive bits. As a concrete
example, let's say the user requested everything from fd 4 to ~0UL to be
closed and their current fdtable size is 256 with their highest open fd
being 4. With CLOSE_RANGE_UNSHARE the caller will end up with a new
fdtable which has room for 64 file descriptors since that is the lowest
fdtable size we accept. But now max_fd will still point to 255 and needs
to be adjusted. Fix this by retrieving the correct maximum fd value in
__range_cloexec().

Reported-by: syzbot+283ce5a46486d6acdbaf@syzkaller.appspotmail.com
Fixes: 582f1fb6b721 ("fs, close_range: add flag CLOSE_RANGE_CLOEXEC")
Fixes: fec8a6a69103 ("close_range: unshare all fds for CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC")
Cc: Christoph Hellwig <hch@lst.de>
Cc: Giuseppe Scrivano <gscrivan@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/file.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/fs/file.c b/fs/file.c
index f3a4bac2cbe9..f633348029a5 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -629,17 +629,30 @@ int close_fd(unsigned fd)
 }
 EXPORT_SYMBOL(close_fd); /* for ksys_close() */
 
+/**
+ * last_fd - return last valid index into fd table
+ * @cur_fds: files struct
+ *
+ * Context: Either rcu read lock or files_lock must be held.
+ *
+ * Returns: Last valid index into fdtable.
+ */
+static inline unsigned last_fd(struct fdtable *fdt)
+{
+	return fdt->max_fds - 1;
+}
+
 static inline void __range_cloexec(struct files_struct *cur_fds,
 				   unsigned int fd, unsigned int max_fd)
 {
 	struct fdtable *fdt;
 
-	if (fd > max_fd)
-		return;
-
+	/* make sure we're using the correct maximum value */
 	spin_lock(&cur_fds->file_lock);
 	fdt = files_fdtable(cur_fds);
-	bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
+	max_fd = min(last_fd(fdt), max_fd);
+	if (fd <= max_fd)
+		bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
 	spin_unlock(&cur_fds->file_lock);
 }
 

From f8b78caf21d5bc3fcfc40c18898f9d52ed1451a5 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Fri, 20 Nov 2020 17:10:28 +0000
Subject: [PATCH 1522/1820] block: don't ignore REQ_NOWAIT for direct IO

If IOCB_NOWAIT is set on submission, then that needs to get propagated to
REQ_NOWAIT on the block side. Otherwise we completely lose this
information, and any issuer of IOCB_NOWAIT IO will potentially end up
blocking on eg request allocation on the storage side.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 28d583fcdc2c..09d6f7229db9 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -275,6 +275,8 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 		bio.bi_opf = dio_bio_write_op(iocb);
 		task_io_account_write(ret);
 	}
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		bio.bi_opf |= REQ_NOWAIT;
 	if (iocb->ki_flags & IOCB_HIPRI)
 		bio_set_polled(&bio, iocb);
 
@@ -428,6 +430,8 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			bio->bi_opf = dio_bio_write_op(iocb);
 			task_io_account_write(bio->bi_iter.bi_size);
 		}
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			bio->bi_opf |= REQ_NOWAIT;
 
 		dio->size += bio->bi_iter.bi_size;
 		pos += bio->bi_iter.bi_size;

From 9fbd3088351b92e8c2cef6e37a39decb12a8d5bb Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Wed, 24 Mar 2021 18:23:52 -0700
Subject: [PATCH 1523/1820] drm/msm: Fix a5xx/a6xx timestamps

They were reading a counter that was configured to ALWAYS_COUNT (ie.
cycles that the GPU is doing something) rather than ALWAYS_ON.  This
isn't the thing that userspace is looking for.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Jordan Crouse <jordan@cosmicpenguin.net>
Message-Id: <20210325012358.1759770-2-robdclark@gmail.com>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 4 ++--
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 7e553d3efeb2..ce13d49e615b 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1386,8 +1386,8 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu)
 
 static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 {
-	*value = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_CP_0_LO,
-		REG_A5XX_RBBM_PERFCTR_CP_0_HI);
+	*value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO,
+		REG_A5XX_RBBM_ALWAYSON_COUNTER_HI);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index cb2df8736ca8..5b438f3e4bf9 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1228,8 +1228,8 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 	/* Force the GPU power on so we can read this register */
 	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
 
-	*value = gpu_read64(gpu, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
-		REG_A6XX_RBBM_PERFCTR_CP_0_HI);
+	*value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
+		REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);
 
 	a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
 	mutex_unlock(&perfcounter_oob);

From 6ddbfa1f5adbd5dea14ff66778ca58257f09f17d Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Wed, 31 Mar 2021 17:02:23 +0300
Subject: [PATCH 1524/1820] drm/msm: a6xx: fix version check for the A650 SQE
 microcode

I suppose the microcode version check for a650 is incorrect. It checks
for the version 1.95, while the firmware released have major version of 0:
0.91 (vulnerable), 0.99 (fixing the issue).

Lower version requirements to accept firmware 0.99.

Fixes: 8490f02a3ca4 ("drm/msm: a6xx: Make sure the SQE microcode is safe")
Cc: Akhil P Oommen <akhilpo@codeaurora.org>
Cc: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Acked-by: Jordan Crouse <jordan@cosmicpenguin.net>
Message-Id: <20210331140223.3771449-1-dmitry.baryshkov@linaro.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 5b438f3e4bf9..d553f62f4eeb 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -567,17 +567,17 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 	}  else {
 		/*
 		 * a650 tier targets don't need whereami but still need to be
-		 * equal to or newer than 1.95 for other security fixes
+		 * equal to or newer than 0.95 for other security fixes
 		 */
 		if (adreno_is_a650(adreno_gpu)) {
-			if ((buf[0] & 0xfff) >= 0x195) {
+			if ((buf[0] & 0xfff) >= 0x095) {
 				ret = true;
 				goto out;
 			}
 
 			DRM_DEV_ERROR(&gpu->pdev->dev,
 				"a650 SQE ucode is too old. Have version %x need at least %x\n",
-				buf[0] & 0xfff, 0x195);
+				buf[0] & 0xfff, 0x095);
 		}
 
 		/*

From 12aca1ce9ee33af3751aec5e55a5900747cbdd4b Mon Sep 17 00:00:00 2001
From: Kalyan Thota <kalyan_t@codeaurora.org>
Date: Fri, 2 Apr 2021 04:54:53 -0700
Subject: [PATCH 1525/1820] drm/msm/disp/dpu1: program 3d_merge only if block
 is attached

Update the 3d merge as active in the data path only if
the hw block is selected in the configuration.

Reported-by: Stephen Boyd <swboyd@chromium.org>
Fixes: 73bfb790ac78 ("msm:disp:dpu1: setup display datapath for SC7180 target")
Signed-off-by: Kalyan Thota <kalyan_t@codeaurora.org>
Message-Id: <1617364493-13518-1-git-send-email-kalyan_t@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
index 8981cfa9dbc3..92e6f1b94738 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -496,7 +496,9 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx,
 
 	DPU_REG_WRITE(c, CTL_TOP, mode_sel);
 	DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active);
-	DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE, BIT(cfg->merge_3d - MERGE_3D_0));
+	if (cfg->merge_3d)
+		DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE,
+			      BIT(cfg->merge_3d - MERGE_3D_0));
 }
 
 static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx,

From e7a48c710defa0e0fef54d42b7d9e4ab596e2761 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Fri, 2 Apr 2021 11:14:05 +0300
Subject: [PATCH 1526/1820] ASoC: fsl_esai: Fix TDM slot setup for I2S mode

When using the driver in I2S TDM mode, the fsl_esai_startup()
function rewrites the number of slots previously set by the
fsl_esai_set_dai_tdm_slot() function to 2.
To fix this, let's use the saved slot count value or, if TDM
is not used and the number of slots is not set, the driver will use
the default value (2), which is set by fsl_esai_probe().

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Acked-by: Nicolin Chen <nicoleotsuka@gmail.com>
Link: https://lore.kernel.org/r/20210402081405.9892-1-shc_work@mail.ru
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_esai.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index 08056fa0a0fa..a857a624864f 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -519,11 +519,13 @@ static int fsl_esai_startup(struct snd_pcm_substream *substream,
 				   ESAI_SAICR_SYNC, esai_priv->synchronous ?
 				   ESAI_SAICR_SYNC : 0);
 
-		/* Set a default slot number -- 2 */
+		/* Set slots count */
 		regmap_update_bits(esai_priv->regmap, REG_ESAI_TCCR,
-				   ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(2));
+				   ESAI_xCCR_xDC_MASK,
+				   ESAI_xCCR_xDC(esai_priv->slots));
 		regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR,
-				   ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(2));
+				   ESAI_xCCR_xDC_MASK,
+				   ESAI_xCCR_xDC(esai_priv->slots));
 	}
 
 	return 0;

From 230d50d448acb6639991440913299e50cacf1daf Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 1 Apr 2021 20:41:15 -0600
Subject: [PATCH 1527/1820] io_uring: move reissue into regular IO path

It's non-obvious how retry is done for block backed files, when it happens
off the kiocb done path. It also makes it tricky to deal with the iov_iter
handling.

Just mark the req as needing a reissue, and handling it from the
submission path instead. This makes it directly obvious that we're not
re-importing the iovec from userspace past the submit point, and it means
that we can just reuse our usual -EAGAIN retry path from the read/write
handling.

At some point in the future, we'll gain the ability to always reliably
return -EAGAIN through the stack. A previous attempt on the block side
didn't pan out and got reverted, hence the need to check for this
information out-of-band right now.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 717942474fa9..8be542050648 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -697,6 +697,7 @@ enum {
 	REQ_F_NO_FILE_TABLE_BIT,
 	REQ_F_LTIMEOUT_ACTIVE_BIT,
 	REQ_F_COMPLETE_INLINE_BIT,
+	REQ_F_REISSUE_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -740,6 +741,8 @@ enum {
 	REQ_F_LTIMEOUT_ACTIVE	= BIT(REQ_F_LTIMEOUT_ACTIVE_BIT),
 	/* completion is deferred through io_comp_state */
 	REQ_F_COMPLETE_INLINE	= BIT(REQ_F_COMPLETE_INLINE_BIT),
+	/* caller should reissue async */
+	REQ_F_REISSUE		= BIT(REQ_F_REISSUE_BIT),
 };
 
 struct async_poll {
@@ -2503,8 +2506,10 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
 
 	if (req->rw.kiocb.ki_flags & IOCB_WRITE)
 		kiocb_end_write(req);
-	if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_reissue(req))
+	if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) {
+		req->flags |= REQ_F_REISSUE;
 		return;
+	}
 	if (res != req->result)
 		req_set_fail_links(req);
 	if (req->flags & REQ_F_BUFFER_SELECTED)
@@ -3283,9 +3288,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 
 	ret = io_iter_do_read(req, iter);
 
-	if (ret == -EIOCBQUEUED) {
-		goto out_free;
-	} else if (ret == -EAGAIN) {
+	if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
 		/* IOPOLL retry should happen for io-wq threads */
 		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
 			goto done;
@@ -3295,6 +3298,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 		/* some cases will consume bytes even on error returns */
 		iov_iter_revert(iter, io_size - iov_iter_count(iter));
 		ret = 0;
+	} else if (ret == -EIOCBQUEUED) {
+		goto out_free;
 	} else if (ret <= 0 || ret == io_size || !force_nonblock ||
 		   (req->flags & REQ_F_NOWAIT) || !(req->flags & REQ_F_ISREG)) {
 		/* read all, failed, already did sync or don't want to retry */
@@ -3407,6 +3412,9 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
 	else
 		ret2 = -EINVAL;
 
+	if (req->flags & REQ_F_REISSUE)
+		ret2 = -EAGAIN;
+
 	/*
 	 * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
 	 * retry them without IOCB_NOWAIT.
@@ -6160,6 +6168,7 @@ static void io_wq_submit_work(struct io_wq_work *work)
 		ret = -ECANCELED;
 
 	if (!ret) {
+		req->flags &= ~REQ_F_REISSUE;
 		do {
 			ret = io_issue_sqe(req, 0);
 			/*

From 442dc00f82a9727dc0c48c44f792c168f593c6df Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Fri, 2 Apr 2021 10:56:18 +0200
Subject: [PATCH 1528/1820] selinux: make nslot handling in avtab more robust

1. Make sure all fileds are initialized in avtab_init().
2. Slightly refactor avtab_alloc() to use the above fact.
3. Use h->nslot == 0 as a sentinel in the access functions to prevent
   dereferencing h->htable when it's not allocated.

Cc: stable@vger.kernel.org
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/ss/avtab.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c
index 6dcb6aa4db7f..2aee4c965c25 100644
--- a/security/selinux/ss/avtab.c
+++ b/security/selinux/ss/avtab.c
@@ -109,7 +109,7 @@ static int avtab_insert(struct avtab *h, struct avtab_key *key, struct avtab_dat
 	struct avtab_node *prev, *cur, *newnode;
 	u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
 
-	if (!h)
+	if (!h || !h->nslot)
 		return -EINVAL;
 
 	hvalue = avtab_hash(key, h->mask);
@@ -154,7 +154,7 @@ avtab_insert_nonunique(struct avtab *h, struct avtab_key *key, struct avtab_datu
 	struct avtab_node *prev, *cur;
 	u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
 
-	if (!h)
+	if (!h || !h->nslot)
 		return NULL;
 	hvalue = avtab_hash(key, h->mask);
 	for (prev = NULL, cur = h->htable[hvalue];
@@ -184,7 +184,7 @@ struct avtab_datum *avtab_search(struct avtab *h, struct avtab_key *key)
 	struct avtab_node *cur;
 	u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
 
-	if (!h)
+	if (!h || !h->nslot)
 		return NULL;
 
 	hvalue = avtab_hash(key, h->mask);
@@ -220,7 +220,7 @@ avtab_search_node(struct avtab *h, struct avtab_key *key)
 	struct avtab_node *cur;
 	u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
 
-	if (!h)
+	if (!h || !h->nslot)
 		return NULL;
 
 	hvalue = avtab_hash(key, h->mask);
@@ -295,6 +295,7 @@ void avtab_destroy(struct avtab *h)
 	}
 	kvfree(h->htable);
 	h->htable = NULL;
+	h->nel = 0;
 	h->nslot = 0;
 	h->mask = 0;
 }
@@ -303,14 +304,15 @@ void avtab_init(struct avtab *h)
 {
 	h->htable = NULL;
 	h->nel = 0;
+	h->nslot = 0;
+	h->mask = 0;
 }
 
 int avtab_alloc(struct avtab *h, u32 nrules)
 {
-	u32 mask = 0;
 	u32 shift = 0;
 	u32 work = nrules;
-	u32 nslot = 0;
+	u32 nslot;
 
 	if (nrules == 0)
 		goto avtab_alloc_out;
@@ -324,16 +326,15 @@ int avtab_alloc(struct avtab *h, u32 nrules)
 	nslot = 1 << shift;
 	if (nslot > MAX_AVTAB_HASH_BUCKETS)
 		nslot = MAX_AVTAB_HASH_BUCKETS;
-	mask = nslot - 1;
 
 	h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL);
 	if (!h->htable)
 		return -ENOMEM;
 
- avtab_alloc_out:
-	h->nel = 0;
 	h->nslot = nslot;
-	h->mask = mask;
+	h->mask = nslot - 1;
+
+avtab_alloc_out:
 	pr_debug("SELinux: %d avtab hash slots, %d rules.\n",
 	       h->nslot, nrules);
 	return 0;

From d8f5f0ea5b86300390b026b6c6e7836b7150814a Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Fri, 2 Apr 2021 10:56:19 +0200
Subject: [PATCH 1529/1820] selinux: fix cond_list corruption when changing
 booleans

Currently, duplicate_policydb_cond_list() first copies the whole
conditional avtab and then tries to link to the correct entries in
cond_dup_av_list() using avtab_search(). However, since the conditional
avtab may contain multiple entries with the same key, this approach
often fails to find the right entry, potentially leading to wrong rules
being activated/deactivated when booleans are changed.

To fix this, instead start with an empty conditional avtab and add the
individual entries one-by-one while building the new av_lists. This
approach leads to the correct result, since each entry is present in the
av_lists exactly once.

The issue can be reproduced with Fedora policy as follows:

    # sesearch -s ftpd_t -t public_content_rw_t -c dir -p create -A
    allow ftpd_t non_security_file_type:dir { add_name create getattr ioctl link lock open read remove_name rename reparent rmdir search setattr unlink watch watch_reads write }; [ ftpd_full_access ]:True
    allow ftpd_t public_content_rw_t:dir { add_name create link remove_name rename reparent rmdir setattr unlink watch watch_reads write }; [ ftpd_anon_write ]:True
    # setsebool ftpd_anon_write=off ftpd_connect_all_unreserved=off ftpd_connect_db=off ftpd_full_access=off

On fixed kernels, the sesearch output is the same after the setsebool
command:

    # sesearch -s ftpd_t -t public_content_rw_t -c dir -p create -A
    allow ftpd_t non_security_file_type:dir { add_name create getattr ioctl link lock open read remove_name rename reparent rmdir search setattr unlink watch watch_reads write }; [ ftpd_full_access ]:True
    allow ftpd_t public_content_rw_t:dir { add_name create link remove_name rename reparent rmdir setattr unlink watch watch_reads write }; [ ftpd_anon_write ]:True

While on the broken kernels, it will be different:

    # sesearch -s ftpd_t -t public_content_rw_t -c dir -p create -A
    allow ftpd_t non_security_file_type:dir { add_name create getattr ioctl link lock open read remove_name rename reparent rmdir search setattr unlink watch watch_reads write }; [ ftpd_full_access ]:True
    allow ftpd_t non_security_file_type:dir { add_name create getattr ioctl link lock open read remove_name rename reparent rmdir search setattr unlink watch watch_reads write }; [ ftpd_full_access ]:True
    allow ftpd_t non_security_file_type:dir { add_name create getattr ioctl link lock open read remove_name rename reparent rmdir search setattr unlink watch watch_reads write }; [ ftpd_full_access ]:True

While there, also simplify the computation of nslots. This changes the
nslots values for nrules 2 or 3 to just two slots instead of 4, which
makes the sequence more consistent.

Cc: stable@vger.kernel.org
Fixes: c7c556f1e81b ("selinux: refactor changing booleans")
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/ss/avtab.c       | 86 +++++++++----------------------
 security/selinux/ss/avtab.h       |  2 +-
 security/selinux/ss/conditional.c | 12 ++---
 3 files changed, 32 insertions(+), 68 deletions(-)

diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c
index 2aee4c965c25..75df32906055 100644
--- a/security/selinux/ss/avtab.c
+++ b/security/selinux/ss/avtab.c
@@ -308,24 +308,10 @@ void avtab_init(struct avtab *h)
 	h->mask = 0;
 }
 
-int avtab_alloc(struct avtab *h, u32 nrules)
+static int avtab_alloc_common(struct avtab *h, u32 nslot)
 {
-	u32 shift = 0;
-	u32 work = nrules;
-	u32 nslot;
-
-	if (nrules == 0)
-		goto avtab_alloc_out;
-
-	while (work) {
-		work  = work >> 1;
-		shift++;
-	}
-	if (shift > 2)
-		shift = shift - 2;
-	nslot = 1 << shift;
-	if (nslot > MAX_AVTAB_HASH_BUCKETS)
-		nslot = MAX_AVTAB_HASH_BUCKETS;
+	if (!nslot)
+		return 0;
 
 	h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL);
 	if (!h->htable)
@@ -333,59 +319,37 @@ int avtab_alloc(struct avtab *h, u32 nrules)
 
 	h->nslot = nslot;
 	h->mask = nslot - 1;
-
-avtab_alloc_out:
-	pr_debug("SELinux: %d avtab hash slots, %d rules.\n",
-	       h->nslot, nrules);
 	return 0;
 }
 
-int avtab_duplicate(struct avtab *new, struct avtab *orig)
+int avtab_alloc(struct avtab *h, u32 nrules)
 {
-	int i;
-	struct avtab_node *node, *tmp, *tail;
+	int rc;
+	u32 nslot = 0;
 
-	memset(new, 0, sizeof(*new));
-
-	new->htable = kvcalloc(orig->nslot, sizeof(void *), GFP_KERNEL);
-	if (!new->htable)
-		return -ENOMEM;
-	new->nslot = orig->nslot;
-	new->mask = orig->mask;
-
-	for (i = 0; i < orig->nslot; i++) {
-		tail = NULL;
-		for (node = orig->htable[i]; node; node = node->next) {
-			tmp = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL);
-			if (!tmp)
-				goto error;
-			tmp->key = node->key;
-			if (tmp->key.specified & AVTAB_XPERMS) {
-				tmp->datum.u.xperms =
-					kmem_cache_zalloc(avtab_xperms_cachep,
-							GFP_KERNEL);
-				if (!tmp->datum.u.xperms) {
-					kmem_cache_free(avtab_node_cachep, tmp);
-					goto error;
-				}
-				tmp->datum.u.xperms = node->datum.u.xperms;
-			} else
-				tmp->datum.u.data = node->datum.u.data;
-
-			if (tail)
-				tail->next = tmp;
-			else
-				new->htable[i] = tmp;
-
-			tail = tmp;
-			new->nel++;
+	if (nrules != 0) {
+		u32 shift = 1;
+		u32 work = nrules >> 3;
+		while (work) {
+			work >>= 1;
+			shift++;
 		}
+		nslot = 1 << shift;
+		if (nslot > MAX_AVTAB_HASH_BUCKETS)
+			nslot = MAX_AVTAB_HASH_BUCKETS;
+
+		rc = avtab_alloc_common(h, nslot);
+		if (rc)
+			return rc;
 	}
 
+	pr_debug("SELinux: %d avtab hash slots, %d rules.\n", nslot, nrules);
 	return 0;
-error:
-	avtab_destroy(new);
-	return -ENOMEM;
+}
+
+int avtab_alloc_dup(struct avtab *new, const struct avtab *orig)
+{
+	return avtab_alloc_common(new, orig->nslot);
 }
 
 void avtab_hash_eval(struct avtab *h, char *tag)
diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h
index 4c4445ca9118..f2eeb36265d1 100644
--- a/security/selinux/ss/avtab.h
+++ b/security/selinux/ss/avtab.h
@@ -89,7 +89,7 @@ struct avtab {
 
 void avtab_init(struct avtab *h);
 int avtab_alloc(struct avtab *, u32);
-int avtab_duplicate(struct avtab *new, struct avtab *orig);
+int avtab_alloc_dup(struct avtab *new, const struct avtab *orig);
 struct avtab_datum *avtab_search(struct avtab *h, struct avtab_key *k);
 void avtab_destroy(struct avtab *h);
 void avtab_hash_eval(struct avtab *h, char *tag);
diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
index 0b32f3ab025e..1ef74c085f2b 100644
--- a/security/selinux/ss/conditional.c
+++ b/security/selinux/ss/conditional.c
@@ -605,7 +605,6 @@ static int cond_dup_av_list(struct cond_av_list *new,
 			struct cond_av_list *orig,
 			struct avtab *avtab)
 {
-	struct avtab_node *avnode;
 	u32 i;
 
 	memset(new, 0, sizeof(*new));
@@ -615,10 +614,11 @@ static int cond_dup_av_list(struct cond_av_list *new,
 		return -ENOMEM;
 
 	for (i = 0; i < orig->len; i++) {
-		avnode = avtab_search_node(avtab, &orig->nodes[i]->key);
-		if (WARN_ON(!avnode))
-			return -EINVAL;
-		new->nodes[i] = avnode;
+		new->nodes[i] = avtab_insert_nonunique(avtab,
+						       &orig->nodes[i]->key,
+						       &orig->nodes[i]->datum);
+		if (!new->nodes[i])
+			return -ENOMEM;
 		new->len++;
 	}
 
@@ -630,7 +630,7 @@ static int duplicate_policydb_cond_list(struct policydb *newp,
 {
 	int rc, i, j;
 
-	rc = avtab_duplicate(&newp->te_cond_avtab, &origp->te_cond_avtab);
+	rc = avtab_alloc_dup(&newp->te_cond_avtab, &origp->te_cond_avtab);
 	if (rc)
 		return rc;
 

From b9c6cdc37ee1fe5866d3b1c10efb9d03191a76af Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 2 Apr 2021 19:17:31 +0200
Subject: [PATCH 1530/1820] block: update a few comments in uapi/linux/blkpg.h

The big top of the file comment talk about grand plans that never
happened, so remove them to not confuse the readers.  Also mark the
devname and volname fields as ignored as they were never used by the
kernel.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/blkpg.h | 28 ++--------------------------
 1 file changed, 2 insertions(+), 26 deletions(-)

diff --git a/include/uapi/linux/blkpg.h b/include/uapi/linux/blkpg.h
index ac6474e4f29d..d0a64ee97c6d 100644
--- a/include/uapi/linux/blkpg.h
+++ b/include/uapi/linux/blkpg.h
@@ -2,29 +2,6 @@
 #ifndef _UAPI__LINUX_BLKPG_H
 #define _UAPI__LINUX_BLKPG_H
 
-/*
- * Partition table and disk geometry handling
- *
- * A single ioctl with lots of subfunctions:
- *
- * Device number stuff:
- *    get_whole_disk()		(given the device number of a partition,
- *                               find the device number of the encompassing disk)
- *    get_all_partitions()	(given the device number of a disk, return the
- *				 device numbers of all its known partitions)
- *
- * Partition stuff:
- *    add_partition()
- *    delete_partition()
- *    test_partition_in_use()	(also for test_disk_in_use)
- *
- * Geometry stuff:
- *    get_geometry()
- *    set_geometry()
- *    get_bios_drivedata()
- *
- * For today, only the partition stuff - aeb, 990515
- */
 #include <linux/compiler.h>
 #include <linux/ioctl.h>
 
@@ -52,9 +29,8 @@ struct blkpg_partition {
 	long long start;		/* starting offset in bytes */
 	long long length;		/* length in bytes */
 	int pno;			/* partition number */
-	char devname[BLKPG_DEVNAMELTH];	/* partition name, like sda5 or c0d1p2,
-					   to be used in kernel messages */
-	char volname[BLKPG_VOLNAMELTH];	/* volume label */
+	char devname[BLKPG_DEVNAMELTH];	/* unused / ignored */
+	char volname[BLKPG_VOLNAMELTH];	/* unused / ignore */
 };
 
 #endif /* _UAPI__LINUX_BLKPG_H */

From f06c609645ecd043c79380fac94145926603fb33 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 2 Apr 2021 19:17:46 +0200
Subject: [PATCH 1531/1820] block: remove the unused RQF_ALLOCED flag

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c | 1 -
 include/linux/blkdev.h | 2 --
 2 files changed, 3 deletions(-)

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 9ebb344e2585..271f6596435b 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -302,7 +302,6 @@ static const char *const rqf_name[] = {
 	RQF_NAME(QUIET),
 	RQF_NAME(ELVPRIV),
 	RQF_NAME(IO_STAT),
-	RQF_NAME(ALLOCED),
 	RQF_NAME(PM),
 	RQF_NAME(HASHED),
 	RQF_NAME(STATS),
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bc6bc8383b43..158aefae1030 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -85,8 +85,6 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_ELVPRIV		((__force req_flags_t)(1 << 12))
 /* account into disk and partition IO statistics */
 #define RQF_IO_STAT		((__force req_flags_t)(1 << 13))
-/* request came from our alloc pool */
-#define RQF_ALLOCED		((__force req_flags_t)(1 << 14))
 /* runtime pm request */
 #define RQF_PM			((__force req_flags_t)(1 << 15))
 /* on IO scheduler merge hash */

From 967ff33eb0efcd48e4df11ab9aee51c41e0f44d0 Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@bootlin.com>
Date: Fri, 2 Apr 2021 21:58:26 +0200
Subject: [PATCH 1532/1820] Revert "arm64: dts: marvell: armada-cp110: Switch
 to per-port SATA interrupts"

The driver part of this support was not merged which leads to break
AHCI on all Marvell Armada 7k8k / CN913x platforms as it was reported
by Marcin Wojtas.

So for now let's remove it in order to fix the issue waiting for the
driver part really be merged.

This reverts commit 53e950d597e3578da84238b86424bfcc9e101d87.
Fixes: 53e950d597e3 ("arm64: dts: marvell: armada-cp110: Switch to per-port SATA interrupts")

Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
---
 arch/arm64/boot/dts/marvell/armada-cp11x.dtsi | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
index 64179a372ecf..c6f5df2deccf 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
@@ -310,9 +310,11 @@
 		};
 
 		CP11X_LABEL(sata0): sata@540000 {
-			compatible = "marvell,armada-8k-ahci";
+			compatible = "marvell,armada-8k-ahci",
+			"generic-ahci";
 			reg = <0x540000 0x30000>;
 			dma-coherent;
+			interrupts = <107 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&CP11X_LABEL(clk) 1 15>,
 				 <&CP11X_LABEL(clk) 1 16>;
 			#address-cells = <1>;
@@ -320,12 +322,10 @@
 			status = "disabled";
 
 			sata-port@0 {
-				interrupts = <109 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0>;
 			};
 
 			sata-port@1 {
-				interrupts = <107 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <1>;
 			};
 		};

From 5b2c7e0ae762fff2b172caf16b2766cc3e1ad859 Mon Sep 17 00:00:00 2001
From: Rui Salvaterra <rsalvaterra@gmail.com>
Date: Wed, 17 Feb 2021 15:30:38 +0000
Subject: [PATCH 1533/1820] ARM: dts: turris-omnia: fix hardware buffer
 management
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Hardware buffer management has never worked on the Turris Omnia, as the
required MBus window hadn't been reserved. Fix thusly.

Fixes: 018b88eee1a2 ("ARM: dts: turris-omnia: enable HW buffer management")

Signed-off-by: Rui Salvaterra <rsalvaterra@gmail.com>
Reviewed-by: Marek Behún <kabel@kernel.org>
Tested-by: Klaus Kudielka <klaus.kudielka@gmail.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
---
 arch/arm/boot/dts/armada-385-turris-omnia.dts | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/armada-385-turris-omnia.dts b/arch/arm/boot/dts/armada-385-turris-omnia.dts
index 646a06420c77..dc80a909ea88 100644
--- a/arch/arm/boot/dts/armada-385-turris-omnia.dts
+++ b/arch/arm/boot/dts/armada-385-turris-omnia.dts
@@ -32,7 +32,8 @@
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000
 			  MBUS_ID(0x01, 0x1d) 0 0xfff00000 0x100000
 			  MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000
-			  MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>;
+			  MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000
+			  MBUS_ID(0x0c, 0x04) 0 0xf1200000 0x100000>;
 
 		internal-regs {
 

From a26c56ae67fa9fbb45a8a232dcd7ebaa7af16086 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Sun, 21 Feb 2021 00:11:44 +0100
Subject: [PATCH 1534/1820] ARM: dts: turris-omnia: configure LED[2]/INTn pin
 as interrupt pin
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the `marvell,reg-init` DT property to configure the LED[2]/INTn pin
of the Marvell 88E1514 ethernet PHY on Turris Omnia into interrupt mode.

Without this the pin is by default in LED[2] mode, and the Marvell PHY
driver configures LED[2] into "On - Link, Blink - Activity" mode.

This fixes the issue where the pca9538 GPIO/interrupt controller (which
can't mask interrupts in HW) received too many interrupts and after a
time started ignoring the interrupt with error message:
  IRQ 71: nobody cared

There is a work in progress to have the Marvell PHY driver support
parsing PHY LED nodes from OF and registering the LEDs as Linux LED
class devices. Once this is done the PHY driver can also automatically
set the pin into INTn mode if it does not find LED[2] in OF.

Until then, though, we fix this via `marvell,reg-init` DT property.

Signed-off-by: Marek Behún <kabel@kernel.org>
Reported-by: Rui Salvaterra <rsalvaterra@gmail.com>
Fixes: 26ca8b52d6e1 ("ARM: dts: add support for Turris Omnia")
Cc: Uwe Kleine-König <uwe@kleine-koenig.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Gregory CLEMENT <gregory.clement@bootlin.com>
Cc: <stable@vger.kernel.org>
Tested-by: Rui Salvaterra <rsalvaterra@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
---
 arch/arm/boot/dts/armada-385-turris-omnia.dts | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/boot/dts/armada-385-turris-omnia.dts b/arch/arm/boot/dts/armada-385-turris-omnia.dts
index dc80a909ea88..5bd6a66d2c2b 100644
--- a/arch/arm/boot/dts/armada-385-turris-omnia.dts
+++ b/arch/arm/boot/dts/armada-385-turris-omnia.dts
@@ -390,6 +390,7 @@
 	phy1: ethernet-phy@1 {
 		compatible = "ethernet-phy-ieee802.3-c22";
 		reg = <1>;
+		marvell,reg-init = <3 18 0 0x4985>;
 
 		/* irq is connected to &pcawan pin 7 */
 	};

From 990b03b05b2fba79de2a1ee9dc359fc552d95ba6 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Thu, 1 Apr 2021 12:52:48 +0800
Subject: [PATCH 1535/1820] net: cls_api: Fix uninitialised struct field
 bo->unlocked_driver_cb

The 'unlocked_driver_cb' struct field in 'bo' is not being initialized
in tcf_block_offload_init(). The uninitialized 'unlocked_driver_cb'
will be used when calling unlocked_driver_cb(). So initialize 'bo' to
zero to avoid the issue.

Addresses-Coverity: ("Uninitialized scalar variable")
Fixes: 0fdcf78d5973 ("net: use flow_indr_dev_setup_offload()")
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 13341e7fb077..9332ec6863e8 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -646,7 +646,7 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb)
 	struct net_device *dev = block_cb->indr.dev;
 	struct Qdisc *sch = block_cb->indr.sch;
 	struct netlink_ext_ack extack = {};
-	struct flow_block_offload bo;
+	struct flow_block_offload bo = {};
 
 	tcf_block_offload_init(&bo, dev, sch, FLOW_BLOCK_UNBIND,
 			       block_cb->indr.binder_type,

From a14d273ba15968495896a38b7b3399dba66d0270 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Fri, 2 Apr 2021 15:42:53 +0300
Subject: [PATCH 1536/1820] net: macb: restore cmp registers on resume path

Restore CMP screener registers on resume path.

Fixes: c1e85c6ce57ef ("net: macb: save/restore the remaining registers and features")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 15362d016a87..6e5cf490c01d 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3239,6 +3239,9 @@ static void gem_prog_cmp_regs(struct macb *bp, struct ethtool_rx_flow_spec *fs)
 	bool cmp_b = false;
 	bool cmp_c = false;
 
+	if (!macb_is_gem(bp))
+		return;
+
 	tp4sp_v = &(fs->h_u.tcp_ip4_spec);
 	tp4sp_m = &(fs->m_u.tcp_ip4_spec);
 
@@ -3607,6 +3610,7 @@ static void macb_restore_features(struct macb *bp)
 {
 	struct net_device *netdev = bp->dev;
 	netdev_features_t features = netdev->features;
+	struct ethtool_rx_fs_item *item;
 
 	/* TX checksum offload */
 	macb_set_txcsum_feature(bp, features);
@@ -3615,6 +3619,9 @@ static void macb_restore_features(struct macb *bp)
 	macb_set_rxcsum_feature(bp, features);
 
 	/* RX Flow Filters */
+	list_for_each_entry(item, &bp->rx_fs_list.list, list)
+		gem_prog_cmp_regs(bp, &item->fs);
+
 	macb_set_rxflow_feature(bp, features);
 }
 

From e82ad4853948382d37ac512b27a3e70b6f01c103 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 2 Apr 2021 19:45:34 -0600
Subject: [PATCH 1537/1820] io_uring: fix !CONFIG_BLOCK compilation failure

kernel test robot correctly pinpoints a compilation failure if
CONFIG_BLOCK isn't set:

fs/io_uring.c: In function '__io_complete_rw':
>> fs/io_uring.c:2509:48: error: implicit declaration of function 'io_rw_should_reissue'; did you mean 'io_rw_reissue'? [-Werror=implicit-function-declaration]
    2509 |  if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) {
         |                                                ^~~~~~~~~~~~~~~~~~~~
         |                                                io_rw_reissue
    cc1: some warnings being treated as errors

Ensure that we have a stub declaration of io_rw_should_reissue() for
!CONFIG_BLOCK.

Fixes: 230d50d448ac ("io_uring: move reissue into regular IO path")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 8be542050648..65a17d560a73 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2479,6 +2479,11 @@ static bool io_rw_should_reissue(struct io_kiocb *req)
 		return false;
 	return true;
 }
+#else
+static bool io_rw_should_reissue(struct io_kiocb *req)
+{
+	return false;
+}
 #endif
 
 static bool io_rw_reissue(struct io_kiocb *req)

From 8d3c0c01cb2e36b2bf3c06a82b18b228d0c8f5d0 Mon Sep 17 00:00:00 2001
From: Lukasz Bartosik <lb@semihalf.com>
Date: Fri, 2 Apr 2021 00:51:48 +0200
Subject: [PATCH 1538/1820] clk: fix invalid usage of list cursor in register

Fix invalid usage of a list_for_each_entry cursor in
clk_notifier_register(). When list is empty or if the list
is completely traversed (without breaking from the loop on one
of the entries) then the list cursor does not point to a valid
entry and therefore should not be used.

The issue was dicovered when running 5.12-rc1 kernel on x86_64
with KASAN enabled:
BUG: KASAN: global-out-of-bounds in clk_notifier_register+0xab/0x230
Read of size 8 at addr ffffffffa0d10588 by task swapper/0/1

CPU: 1 PID: 1 Comm: swapper/0 Not tainted 5.12.0-rc1 #1
Hardware name: Google Caroline/Caroline,
BIOS Google_Caroline.7820.430.0 07/20/2018
Call Trace:
 dump_stack+0xee/0x15c
 print_address_description+0x1e/0x2dc
 kasan_report+0x188/0x1ce
 ? clk_notifier_register+0xab/0x230
 ? clk_prepare_lock+0x15/0x7b
 ? clk_notifier_register+0xab/0x230
 clk_notifier_register+0xab/0x230
 dw8250_probe+0xc01/0x10d4
...
Memory state around the buggy address:
 ffffffffa0d10480: 00 00 00 00 00 03 f9 f9 f9 f9 f9 f9 00 00 00 00
 ffffffffa0d10500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 f9 f9
>ffffffffa0d10580: f9 f9 f9 f9 00 00 00 00 00 00 00 00 00 00 00 00
                      ^
 ffffffffa0d10600: 00 00 00 00 00 00 f9 f9 f9 f9 f9 f9 00 00 00 00
 ffffffffa0d10680: 00 00 00 00 00 00 00 00 f9 f9 f9 f9 00 00 00 00
 ==================================================================

Fixes: b2476490ef11 ("clk: introduce the common clock framework")
Reported-by: Lukasz Majczak <lma@semihalf.com>
Signed-off-by: Lukasz Bartosik <lb@semihalf.com>
Link: https://lore.kernel.org/r/20210401225149.18826-1-lb@semihalf.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 5052541a0986..16634d5912be 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -4357,20 +4357,19 @@ int clk_notifier_register(struct clk *clk, struct notifier_block *nb)
 	/* search the list of notifiers for this clk */
 	list_for_each_entry(cn, &clk_notifier_list, node)
 		if (cn->clk == clk)
-			break;
+			goto found;
 
 	/* if clk wasn't in the notifier list, allocate new clk_notifier */
-	if (cn->clk != clk) {
-		cn = kzalloc(sizeof(*cn), GFP_KERNEL);
-		if (!cn)
-			goto out;
+	cn = kzalloc(sizeof(*cn), GFP_KERNEL);
+	if (!cn)
+		goto out;
 
-		cn->clk = clk;
-		srcu_init_notifier_head(&cn->notifier_head);
+	cn->clk = clk;
+	srcu_init_notifier_head(&cn->notifier_head);
 
-		list_add(&cn->node, &clk_notifier_list);
-	}
+	list_add(&cn->node, &clk_notifier_list);
 
+found:
 	ret = srcu_notifier_chain_register(&cn->notifier_head, nb);
 
 	clk->core->notifier_count++;

From 7045465500e465b09f09d6e5bdc260a9f1aab97b Mon Sep 17 00:00:00 2001
From: Lukasz Bartosik <lb@semihalf.com>
Date: Fri, 2 Apr 2021 00:51:49 +0200
Subject: [PATCH 1539/1820] clk: fix invalid usage of list cursor in unregister

Fix invalid usage of a list_for_each_entry cursor in
clk_notifier_unregister(). When list is empty or if the list
is completely traversed (without breaking from the loop on one
of the entries) then the list cursor does not point to a valid
entry and therefore should not be used. The patch fixes a logical
bug that hasn't been seen in pratice however it is analogus
to the bug fixed in clk_notifier_register().

The issue was dicovered when running 5.12-rc1 kernel on x86_64
with KASAN enabled:
BUG: KASAN: global-out-of-bounds in clk_notifier_register+0xab/0x230
Read of size 8 at addr ffffffffa0d10588 by task swapper/0/1

CPU: 1 PID: 1 Comm: swapper/0 Not tainted 5.12.0-rc1 #1
Hardware name: Google Caroline/Caroline,
BIOS Google_Caroline.7820.430.0 07/20/2018
Call Trace:
 dump_stack+0xee/0x15c
 print_address_description+0x1e/0x2dc
 kasan_report+0x188/0x1ce
 ? clk_notifier_register+0xab/0x230
 ? clk_prepare_lock+0x15/0x7b
 ? clk_notifier_register+0xab/0x230
 clk_notifier_register+0xab/0x230
 dw8250_probe+0xc01/0x10d4
 ...
 Memory state around the buggy address:
  ffffffffa0d10480: 00 00 00 00 00 03 f9 f9 f9 f9 f9 f9 00 00 00 00
  ffffffffa0d10500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 f9 f9
 >ffffffffa0d10580: f9 f9 f9 f9 00 00 00 00 00 00 00 00 00 00 00 00
                          ^
  ffffffffa0d10600: 00 00 00 00 00 00 f9 f9 f9 f9 f9 f9 00 00 00 00
  ffffffffa0d10680: 00 00 00 00 00 00 00 00 f9 f9 f9 f9 00 00 00 00
  ==================================================================

Fixes: b2476490ef11 ("clk: introduce the common clock framework")
Reported-by: Lukasz Majczak <lma@semihalf.com>
Signed-off-by: Lukasz Bartosik <lb@semihalf.com>
Link: https://lore.kernel.org/r/20210401225149.18826-2-lb@semihalf.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk.c | 32 ++++++++++++++------------------
 1 file changed, 14 insertions(+), 18 deletions(-)

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 16634d5912be..39cfc6c6a8d2 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -4394,32 +4394,28 @@ EXPORT_SYMBOL_GPL(clk_notifier_register);
  */
 int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb)
 {
-	struct clk_notifier *cn = NULL;
-	int ret = -EINVAL;
+	struct clk_notifier *cn;
+	int ret = -ENOENT;
 
 	if (!clk || !nb)
 		return -EINVAL;
 
 	clk_prepare_lock();
 
-	list_for_each_entry(cn, &clk_notifier_list, node)
-		if (cn->clk == clk)
+	list_for_each_entry(cn, &clk_notifier_list, node) {
+		if (cn->clk == clk) {
+			ret = srcu_notifier_chain_unregister(&cn->notifier_head, nb);
+
+			clk->core->notifier_count--;
+
+			/* XXX the notifier code should handle this better */
+			if (!cn->notifier_head.head) {
+				srcu_cleanup_notifier_head(&cn->notifier_head);
+				list_del(&cn->node);
+				kfree(cn);
+			}
 			break;
-
-	if (cn->clk == clk) {
-		ret = srcu_notifier_chain_unregister(&cn->notifier_head, nb);
-
-		clk->core->notifier_count--;
-
-		/* XXX the notifier code should handle this better */
-		if (!cn->notifier_head.head) {
-			srcu_cleanup_notifier_head(&cn->notifier_head);
-			list_del(&cn->node);
-			kfree(cn);
 		}
-
-	} else {
-		ret = -ENOENT;
 	}
 
 	clk_prepare_unlock();

From 1683f7de65dbf0a2c6a7d639173fe92430a28930 Mon Sep 17 00:00:00 2001
From: Zhen Lei <thunder.leizhen@huawei.com>
Date: Wed, 31 Mar 2021 15:06:43 +0200
Subject: [PATCH 1540/1820] soc: litex: Remove duplicated header file inclusion

The header file <linux/errno.h> is already included above and can be
removed here.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Mateusz Holenko <mholenko@antmicro.com>
Signed-off-by: Stafford Horne <shorne@gmail.com>
---
 drivers/soc/litex/litex_soc_ctrl.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/soc/litex/litex_soc_ctrl.c b/drivers/soc/litex/litex_soc_ctrl.c
index 6268bfa7f0d6..c3e379a990f2 100644
--- a/drivers/soc/litex/litex_soc_ctrl.c
+++ b/drivers/soc/litex/litex_soc_ctrl.c
@@ -13,7 +13,6 @@
 #include <linux/platform_device.h>
 #include <linux/printk.h>
 #include <linux/module.h>
-#include <linux/errno.h>
 #include <linux/io.h>
 #include <linux/reboot.h>
 

From 0687c66b5f666b5ad433f4e94251590d9bc9d10e Mon Sep 17 00:00:00 2001
From: Zqiang <qiang.zhang@windriver.com>
Date: Thu, 18 Feb 2021 11:16:49 +0800
Subject: [PATCH 1541/1820] workqueue: Move the position of
 debug_work_activate() in __queue_work()

The debug_work_activate() is called on the premise that
the work can be inserted, because if wq be in WQ_DRAINING
status, insert work may be failed.

Fixes: e41e704bc4f4 ("workqueue: improve destroy_workqueue() debuggability")
Signed-off-by: Zqiang <qiang.zhang@windriver.com>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0d150da252e8..21fb00b52def 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1412,7 +1412,6 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	 */
 	lockdep_assert_irqs_disabled();
 
-	debug_work_activate(work);
 
 	/* if draining, only works from the same workqueue are allowed */
 	if (unlikely(wq->flags & __WQ_DRAINING) &&
@@ -1494,6 +1493,7 @@ retry:
 		worklist = &pwq->delayed_works;
 	}
 
+	debug_work_activate(work);
 	insert_work(pwq, work, worklist, work_flags);
 
 out:

From 89e28ce60cb65971c73359c66d076aa20a395cd5 Mon Sep 17 00:00:00 2001
From: Wang Qing <wangqing@vivo.com>
Date: Wed, 24 Mar 2021 19:40:29 +0800
Subject: [PATCH 1542/1820] workqueue/watchdog: Make unbound workqueues aware
 of touch_softlockup_watchdog() 84;0;0c84;0;0c There are two
 workqueue-specific watchdog timestamps:

    + @wq_watchdog_touched_cpu (per-CPU) updated by
      touch_softlockup_watchdog()

    + @wq_watchdog_touched (global) updated by
      touch_all_softlockup_watchdogs()

watchdog_timer_fn() checks only the global @wq_watchdog_touched for
unbound workqueues. As a result, unbound workqueues are not aware
of touch_softlockup_watchdog(). The watchdog might report a stall
even when the unbound workqueues are blocked by a known slow code.

Solution:
touch_softlockup_watchdog() must touch also the global @wq_watchdog_touched
timestamp.

The global timestamp can no longer be used for bound workqueues because
it is now updated from all CPUs. Instead, bound workqueues have to check
only @wq_watchdog_touched_cpu and these timestamps have to be updated for
all CPUs in touch_all_softlockup_watchdogs().

Beware:
The change might cause the opposite problem. An unbound workqueue
might get blocked on CPU A because of a real softlockup. The workqueue
watchdog would miss it when the timestamp got touched on CPU B.

It is acceptable because softlockups are detected by softlockup
watchdog. The workqueue watchdog is there to detect stalls where
a work never finishes, for example, because of dependencies of works
queued into the same workqueue.

V3:
- Modify the commit message clearly according to Petr's suggestion.

Signed-off-by: Wang Qing <wangqing@vivo.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/watchdog.c  |  5 +++--
 kernel/workqueue.c | 17 ++++++-----------
 2 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 71109065bd8e..107bc38b1945 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -278,9 +278,10 @@ void touch_all_softlockup_watchdogs(void)
 	 * update as well, the only side effect might be a cycle delay for
 	 * the softlockup check.
 	 */
-	for_each_cpu(cpu, &watchdog_allowed_mask)
+	for_each_cpu(cpu, &watchdog_allowed_mask) {
 		per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET;
-	wq_watchdog_touch(-1);
+		wq_watchdog_touch(cpu);
+	}
 }
 
 void touch_softlockup_watchdog_sync(void)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 21fb00b52def..79f2319543ce 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -5787,22 +5787,17 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 			continue;
 
 		/* get the latest of pool and touched timestamps */
+		if (pool->cpu >= 0)
+			touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu));
+		else
+			touched = READ_ONCE(wq_watchdog_touched);
 		pool_ts = READ_ONCE(pool->watchdog_ts);
-		touched = READ_ONCE(wq_watchdog_touched);
 
 		if (time_after(pool_ts, touched))
 			ts = pool_ts;
 		else
 			ts = touched;
 
-		if (pool->cpu >= 0) {
-			unsigned long cpu_touched =
-				READ_ONCE(per_cpu(wq_watchdog_touched_cpu,
-						  pool->cpu));
-			if (time_after(cpu_touched, ts))
-				ts = cpu_touched;
-		}
-
 		/* did we stall? */
 		if (time_after(jiffies, ts + thresh)) {
 			lockup_detected = true;
@@ -5826,8 +5821,8 @@ notrace void wq_watchdog_touch(int cpu)
 {
 	if (cpu >= 0)
 		per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies;
-	else
-		wq_watchdog_touched = jiffies;
+
+	wq_watchdog_touched = jiffies;
 }
 
 static void wq_watchdog_set_thresh(unsigned long thresh)

From 829933ef05a951c8ff140e814656d73e74915faf Mon Sep 17 00:00:00 2001
From: Zheyu Ma <zheyuma97@gmail.com>
Date: Sat, 3 Apr 2021 06:58:36 +0000
Subject: [PATCH 1543/1820] firewire: nosy: Fix a use-after-free bug in
 nosy_ioctl()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For each device, the nosy driver allocates a pcilynx structure.
A use-after-free might happen in the following scenario:

 1. Open nosy device for the first time and call ioctl with command
    NOSY_IOC_START, then a new client A will be malloced and added to
    doubly linked list.
 2. Open nosy device for the second time and call ioctl with command
    NOSY_IOC_START, then a new client B will be malloced and added to
    doubly linked list.
 3. Call ioctl with command NOSY_IOC_START for client A, then client A
    will be readded to the doubly linked list. Now the doubly linked
    list is messed up.
 4. Close the first nosy device and nosy_release will be called. In
    nosy_release, client A will be unlinked and freed.
 5. Close the second nosy device, and client A will be referenced,
    resulting in UAF.

The root cause of this bug is that the element in the doubly linked list
is reentered into the list.

Fix this bug by adding a check before inserting a client.  If a client
is already in the linked list, don't insert it.

The following KASAN report reveals it:

   BUG: KASAN: use-after-free in nosy_release+0x1ea/0x210
   Write of size 8 at addr ffff888102ad7360 by task poc
   CPU: 3 PID: 337 Comm: poc Not tainted 5.12.0-rc5+ #6
   Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014
   Call Trace:
     nosy_release+0x1ea/0x210
     __fput+0x1e2/0x840
     task_work_run+0xe8/0x180
     exit_to_user_mode_prepare+0x114/0x120
     syscall_exit_to_user_mode+0x1d/0x40
     entry_SYSCALL_64_after_hwframe+0x44/0xae

   Allocated by task 337:
     nosy_open+0x154/0x4d0
     misc_open+0x2ec/0x410
     chrdev_open+0x20d/0x5a0
     do_dentry_open+0x40f/0xe80
     path_openat+0x1cf9/0x37b0
     do_filp_open+0x16d/0x390
     do_sys_openat2+0x11d/0x360
     __x64_sys_open+0xfd/0x1a0
     do_syscall_64+0x33/0x40
     entry_SYSCALL_64_after_hwframe+0x44/0xae

   Freed by task 337:
     kfree+0x8f/0x210
     nosy_release+0x158/0x210
     __fput+0x1e2/0x840
     task_work_run+0xe8/0x180
     exit_to_user_mode_prepare+0x114/0x120
     syscall_exit_to_user_mode+0x1d/0x40
     entry_SYSCALL_64_after_hwframe+0x44/0xae

   The buggy address belongs to the object at ffff888102ad7300 which belongs to the cache kmalloc-128 of size 128
   The buggy address is located 96 bytes inside of 128-byte region [ffff888102ad7300, ffff888102ad7380)

[ Modified to use 'list_empty()' inside proper lock  - Linus ]

Link: https://lore.kernel.org/lkml/1617433116-5930-1-git-send-email-zheyuma97@gmail.com/
Reported-and-tested-by: 马哲宇 (Zheyu Ma) <zheyuma97@gmail.com>
Signed-off-by: Zheyu Ma <zheyuma97@gmail.com>
Cc: Greg Kroah-Hartman <greg@kroah.com>
Cc: Stefan Richter <stefanr@s5r6.in-berlin.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/firewire/nosy.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c
index 5fd6a60b6741..88ed971e32c0 100644
--- a/drivers/firewire/nosy.c
+++ b/drivers/firewire/nosy.c
@@ -346,6 +346,7 @@ nosy_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct client *client = file->private_data;
 	spinlock_t *client_list_lock = &client->lynx->client_list_lock;
 	struct nosy_stats stats;
+	int ret;
 
 	switch (cmd) {
 	case NOSY_IOC_GET_STATS:
@@ -360,11 +361,15 @@ nosy_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			return 0;
 
 	case NOSY_IOC_START:
+		ret = -EBUSY;
 		spin_lock_irq(client_list_lock);
-		list_add_tail(&client->link, &client->lynx->client_list);
+		if (list_empty(&client->link)) {
+			list_add_tail(&client->link, &client->lynx->client_list);
+			ret = 0;
+		}
 		spin_unlock_irq(client_list_lock);
 
-		return 0;
+		return ret;
 
 	case NOSY_IOC_STOP:
 		spin_lock_irq(client_list_lock);

From e49d033bddf5b565044e2abe4241353959bc9120 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 4 Apr 2021 14:15:36 -0700
Subject: [PATCH 1544/1820] Linux 5.12-rc6

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 73add16f9898..cc77fd45ca64 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Frozen Wasteland
 
 # *DOCUMENTATION*

From 4e9c93af7279b059faf5bb1897ee90512b258a12 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Mon, 29 Mar 2021 19:36:48 -0600
Subject: [PATCH 1545/1820] usbip: add sysfs_lock to synchronize sysfs code
 paths

Fuzzing uncovered race condition between sysfs code paths in usbip
drivers. Device connect/disconnect code paths initiated through
sysfs interface are prone to races if disconnect happens during
connect and vice versa.

This problem is common to all drivers while it can be reproduced easily
in vhci_hcd. Add a sysfs_lock to usbip_device struct to protect the paths.

Use this in vhci_hcd to protect sysfs paths. For a complete fix, usip_host
and usip-vudc drivers and the event handler will have to use this lock to
protect the paths. These changes will be done in subsequent patches.

Cc: stable@vger.kernel.org
Reported-and-tested-by: syzbot+a93fba6d384346a761e3@syzkaller.appspotmail.com
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/b6568f7beae702bbc236a545d3c020106ca75eac.1616807117.git.skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/usbip_common.h |  3 +++
 drivers/usb/usbip/vhci_hcd.c     |  1 +
 drivers/usb/usbip/vhci_sysfs.c   | 30 +++++++++++++++++++++++++-----
 3 files changed, 29 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h
index d60ce17d3dd2..ea2a20e6d27d 100644
--- a/drivers/usb/usbip/usbip_common.h
+++ b/drivers/usb/usbip/usbip_common.h
@@ -263,6 +263,9 @@ struct usbip_device {
 	/* lock for status */
 	spinlock_t lock;
 
+	/* mutex for synchronizing sysfs store paths */
+	struct mutex sysfs_lock;
+
 	int sockfd;
 	struct socket *tcp_socket;
 
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index a20a8380ca0c..4ba6bcdaa8e9 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -1101,6 +1101,7 @@ static void vhci_device_init(struct vhci_device *vdev)
 	vdev->ud.side   = USBIP_VHCI;
 	vdev->ud.status = VDEV_ST_NULL;
 	spin_lock_init(&vdev->ud.lock);
+	mutex_init(&vdev->ud.sysfs_lock);
 
 	INIT_LIST_HEAD(&vdev->priv_rx);
 	INIT_LIST_HEAD(&vdev->priv_tx);
diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c
index c4b4256e5dad..e2847cd3e6e3 100644
--- a/drivers/usb/usbip/vhci_sysfs.c
+++ b/drivers/usb/usbip/vhci_sysfs.c
@@ -185,6 +185,8 @@ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport)
 
 	usbip_dbg_vhci_sysfs("enter\n");
 
+	mutex_lock(&vdev->ud.sysfs_lock);
+
 	/* lock */
 	spin_lock_irqsave(&vhci->lock, flags);
 	spin_lock(&vdev->ud.lock);
@@ -195,6 +197,7 @@ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport)
 		/* unlock */
 		spin_unlock(&vdev->ud.lock);
 		spin_unlock_irqrestore(&vhci->lock, flags);
+		mutex_unlock(&vdev->ud.sysfs_lock);
 
 		return -EINVAL;
 	}
@@ -205,6 +208,8 @@ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport)
 
 	usbip_event_add(&vdev->ud, VDEV_EVENT_DOWN);
 
+	mutex_unlock(&vdev->ud.sysfs_lock);
+
 	return 0;
 }
 
@@ -349,30 +354,36 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr,
 	else
 		vdev = &vhci->vhci_hcd_hs->vdev[rhport];
 
+	mutex_lock(&vdev->ud.sysfs_lock);
+
 	/* Extract socket from fd. */
 	socket = sockfd_lookup(sockfd, &err);
 	if (!socket) {
 		dev_err(dev, "failed to lookup sock");
-		return -EINVAL;
+		err = -EINVAL;
+		goto unlock_mutex;
 	}
 	if (socket->type != SOCK_STREAM) {
 		dev_err(dev, "Expecting SOCK_STREAM - found %d",
 			socket->type);
 		sockfd_put(socket);
-		return -EINVAL;
+		err = -EINVAL;
+		goto unlock_mutex;
 	}
 
 	/* create threads before locking */
 	tcp_rx = kthread_create(vhci_rx_loop, &vdev->ud, "vhci_rx");
 	if (IS_ERR(tcp_rx)) {
 		sockfd_put(socket);
-		return -EINVAL;
+		err = -EINVAL;
+		goto unlock_mutex;
 	}
 	tcp_tx = kthread_create(vhci_tx_loop, &vdev->ud, "vhci_tx");
 	if (IS_ERR(tcp_tx)) {
 		kthread_stop(tcp_rx);
 		sockfd_put(socket);
-		return -EINVAL;
+		err = -EINVAL;
+		goto unlock_mutex;
 	}
 
 	/* get task structs now */
@@ -397,7 +408,8 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr,
 		 * Will be retried from userspace
 		 * if there's another free port.
 		 */
-		return -EBUSY;
+		err = -EBUSY;
+		goto unlock_mutex;
 	}
 
 	dev_info(dev, "pdev(%u) rhport(%u) sockfd(%d)\n",
@@ -423,7 +435,15 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr,
 
 	rh_port_connect(vdev, speed);
 
+	dev_info(dev, "Device attached\n");
+
+	mutex_unlock(&vdev->ud.sysfs_lock);
+
 	return count;
+
+unlock_mutex:
+	mutex_unlock(&vdev->ud.sysfs_lock);
+	return err;
 }
 static DEVICE_ATTR_WO(attach);
 

From 9dbf34a834563dada91366c2ac266f32ff34641a Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Mon, 29 Mar 2021 19:36:49 -0600
Subject: [PATCH 1546/1820] usbip: stub-dev synchronize sysfs code paths

Fuzzing uncovered race condition between sysfs code paths in usbip
drivers. Device connect/disconnect code paths initiated through
sysfs interface are prone to races if disconnect happens during
connect and vice versa.

Use sysfs_lock to protect sysfs paths in stub-dev.

Cc: stable@vger.kernel.org
Reported-and-tested-by: syzbot+a93fba6d384346a761e3@syzkaller.appspotmail.com
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/2b182f3561b4a065bf3bf6dce3b0e9944ba17b3f.1616807117.git.skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/stub_dev.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index 8f1de1fbbeed..d8d3892e5a69 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -63,6 +63,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 
 		dev_info(dev, "stub up\n");
 
+		mutex_lock(&sdev->ud.sysfs_lock);
 		spin_lock_irq(&sdev->ud.lock);
 
 		if (sdev->ud.status != SDEV_ST_AVAILABLE) {
@@ -87,13 +88,13 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 		tcp_rx = kthread_create(stub_rx_loop, &sdev->ud, "stub_rx");
 		if (IS_ERR(tcp_rx)) {
 			sockfd_put(socket);
-			return -EINVAL;
+			goto unlock_mutex;
 		}
 		tcp_tx = kthread_create(stub_tx_loop, &sdev->ud, "stub_tx");
 		if (IS_ERR(tcp_tx)) {
 			kthread_stop(tcp_rx);
 			sockfd_put(socket);
-			return -EINVAL;
+			goto unlock_mutex;
 		}
 
 		/* get task structs now */
@@ -112,6 +113,8 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 		wake_up_process(sdev->ud.tcp_rx);
 		wake_up_process(sdev->ud.tcp_tx);
 
+		mutex_unlock(&sdev->ud.sysfs_lock);
+
 	} else {
 		dev_info(dev, "stub down\n");
 
@@ -122,6 +125,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a
 		spin_unlock_irq(&sdev->ud.lock);
 
 		usbip_event_add(&sdev->ud, SDEV_EVENT_DOWN);
+		mutex_unlock(&sdev->ud.sysfs_lock);
 	}
 
 	return count;
@@ -130,6 +134,8 @@ sock_err:
 	sockfd_put(socket);
 err:
 	spin_unlock_irq(&sdev->ud.lock);
+unlock_mutex:
+	mutex_unlock(&sdev->ud.sysfs_lock);
 	return -EINVAL;
 }
 static DEVICE_ATTR_WO(usbip_sockfd);
@@ -270,6 +276,7 @@ static struct stub_device *stub_device_alloc(struct usb_device *udev)
 	sdev->ud.side		= USBIP_STUB;
 	sdev->ud.status		= SDEV_ST_AVAILABLE;
 	spin_lock_init(&sdev->ud.lock);
+	mutex_init(&sdev->ud.sysfs_lock);
 	sdev->ud.tcp_socket	= NULL;
 	sdev->ud.sockfd		= -1;
 

From bd8b82042269a95db48074b8bb400678dbac1815 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Mon, 29 Mar 2021 19:36:50 -0600
Subject: [PATCH 1547/1820] usbip: vudc synchronize sysfs code paths

Fuzzing uncovered race condition between sysfs code paths in usbip
drivers. Device connect/disconnect code paths initiated through
sysfs interface are prone to races if disconnect happens during
connect and vice versa.

Use sysfs_lock to protect sysfs paths in vudc.

Cc: stable@vger.kernel.org
Reported-and-tested-by: syzbot+a93fba6d384346a761e3@syzkaller.appspotmail.com
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/caabcf3fc87bdae970509b5ff32d05bb7ce2fb15.1616807117.git.skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/vudc_dev.c   | 1 +
 drivers/usb/usbip/vudc_sysfs.c | 5 +++++
 2 files changed, 6 insertions(+)

diff --git a/drivers/usb/usbip/vudc_dev.c b/drivers/usb/usbip/vudc_dev.c
index c8eeabdd9b56..2bc428f2e261 100644
--- a/drivers/usb/usbip/vudc_dev.c
+++ b/drivers/usb/usbip/vudc_dev.c
@@ -572,6 +572,7 @@ static int init_vudc_hw(struct vudc *udc)
 	init_waitqueue_head(&udc->tx_waitq);
 
 	spin_lock_init(&ud->lock);
+	mutex_init(&ud->sysfs_lock);
 	ud->status = SDEV_ST_AVAILABLE;
 	ud->side = USBIP_VUDC;
 
diff --git a/drivers/usb/usbip/vudc_sysfs.c b/drivers/usb/usbip/vudc_sysfs.c
index 7383a543c6d1..f7633ee655a1 100644
--- a/drivers/usb/usbip/vudc_sysfs.c
+++ b/drivers/usb/usbip/vudc_sysfs.c
@@ -112,6 +112,7 @@ static ssize_t usbip_sockfd_store(struct device *dev,
 		dev_err(dev, "no device");
 		return -ENODEV;
 	}
+	mutex_lock(&udc->ud.sysfs_lock);
 	spin_lock_irqsave(&udc->lock, flags);
 	/* Don't export what we don't have */
 	if (!udc->driver || !udc->pullup) {
@@ -187,6 +188,8 @@ static ssize_t usbip_sockfd_store(struct device *dev,
 
 		wake_up_process(udc->ud.tcp_rx);
 		wake_up_process(udc->ud.tcp_tx);
+
+		mutex_unlock(&udc->ud.sysfs_lock);
 		return count;
 
 	} else {
@@ -207,6 +210,7 @@ static ssize_t usbip_sockfd_store(struct device *dev,
 	}
 
 	spin_unlock_irqrestore(&udc->lock, flags);
+	mutex_unlock(&udc->ud.sysfs_lock);
 
 	return count;
 
@@ -216,6 +220,7 @@ unlock_ud:
 	spin_unlock_irq(&udc->ud.lock);
 unlock:
 	spin_unlock_irqrestore(&udc->lock, flags);
+	mutex_unlock(&udc->ud.sysfs_lock);
 
 	return ret;
 }

From 363eaa3a450abb4e63bd6e3ad79d1f7a0f717814 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Mon, 29 Mar 2021 19:36:51 -0600
Subject: [PATCH 1548/1820] usbip: synchronize event handler with sysfs code
 paths

Fuzzing uncovered race condition between sysfs code paths in usbip
drivers. Device connect/disconnect code paths initiated through
sysfs interface are prone to races if disconnect happens during
connect and vice versa.

Use sysfs_lock to synchronize event handler with sysfs paths
in usbip drivers.

Cc: stable@vger.kernel.org
Reported-and-tested-by: syzbot+a93fba6d384346a761e3@syzkaller.appspotmail.com
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/c5c8723d3f29dfe3d759cfaafa7dd16b0dfe2918.1616807117.git.skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/usbip_event.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/usbip/usbip_event.c b/drivers/usb/usbip/usbip_event.c
index 5d88917c9631..086ca76dd053 100644
--- a/drivers/usb/usbip/usbip_event.c
+++ b/drivers/usb/usbip/usbip_event.c
@@ -70,6 +70,7 @@ static void event_handler(struct work_struct *work)
 	while ((ud = get_event()) != NULL) {
 		usbip_dbg_eh("pending event %lx\n", ud->event);
 
+		mutex_lock(&ud->sysfs_lock);
 		/*
 		 * NOTE: shutdown must come first.
 		 * Shutdown the device.
@@ -90,6 +91,7 @@ static void event_handler(struct work_struct *work)
 			ud->eh_ops.unusable(ud);
 			unset_event(ud, USBIP_EH_UNUSABLE);
 		}
+		mutex_unlock(&ud->sysfs_lock);
 
 		wake_up(&ud->eh_waitq);
 	}

From eed6e41813deb9ee622cd9242341f21430d7789f Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Thu, 1 Apr 2021 21:03:40 -0700
Subject: [PATCH 1549/1820] driver core: Fix locking bug in
 deferred_probe_timeout_work_func()

list_for_each_entry_safe() is only useful if we are deleting nodes in a
linked list within the loop. It doesn't protect against other threads
adding/deleting nodes to the list in parallel. We need to grab
deferred_probe_mutex when traversing the deferred_probe_pending_list.

Cc: stable@vger.kernel.org
Fixes: 25b4e70dcce9 ("driver core: allow stopping deferred probe after init")
Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20210402040342.2944858-2-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/dd.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index e2cf3b29123e..37a5e5f8b221 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -292,14 +292,16 @@ int driver_deferred_probe_check_state(struct device *dev)
 
 static void deferred_probe_timeout_work_func(struct work_struct *work)
 {
-	struct device_private *private, *p;
+	struct device_private *p;
 
 	driver_deferred_probe_timeout = 0;
 	driver_deferred_probe_trigger();
 	flush_work(&deferred_probe_work);
 
-	list_for_each_entry_safe(private, p, &deferred_probe_pending_list, deferred_probe)
-		dev_info(private->device, "deferred probe pending\n");
+	mutex_lock(&deferred_probe_mutex);
+	list_for_each_entry(p, &deferred_probe_pending_list, deferred_probe)
+		dev_info(p->device, "deferred probe pending\n");
+	mutex_unlock(&deferred_probe_mutex);
 	wake_up_all(&probe_timeout_waitqueue);
 }
 static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func);

From 7a2f91441b2c1d81b77c1cd816a4659f4abc9cbe Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Mon, 29 Mar 2021 18:35:07 +0200
Subject: [PATCH 1550/1820] s390/cpcmd: fix inline assembly register clobbering

Register variables initialized using arithmetic. That leads to
kasan instrumentaton code corrupting the registers contents.
Follow GCC guidlines and use temporary variables for assigning
init values to register variables.

Fixes: 94c12cc7d196 ("[S390] Inline assembly cleanup.")
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Link: https://gcc.gnu.org/onlinedocs/gcc-10.2.0/gcc/Local-Register-Variables.html
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/cpcmd.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index af013b4244d3..2da027359798 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -37,10 +37,12 @@ static int diag8_noresponse(int cmdlen)
 
 static int diag8_response(int cmdlen, char *response, int *rlen)
 {
+	unsigned long _cmdlen = cmdlen | 0x40000000L;
+	unsigned long _rlen = *rlen;
 	register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf;
 	register unsigned long reg3 asm ("3") = (addr_t) response;
-	register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L;
-	register unsigned long reg5 asm ("5") = *rlen;
+	register unsigned long reg4 asm ("4") = _cmdlen;
+	register unsigned long reg5 asm ("5") = _rlen;
 
 	asm volatile(
 		"	diag	%2,%0,0x8\n"

From 08edb9683e47f5183aed9aa3f926292b54c278c1 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 31 Mar 2021 11:44:50 +0200
Subject: [PATCH 1551/1820] s390/unwind: add machine check handler stack

Fixes: b61b1595124a ("s390: add stack for machine check handler")
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/stacktrace.h |  1 +
 arch/s390/kernel/dumpstack.c       | 12 +++++++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
index ee056f4a4fa3..2b543163d90a 100644
--- a/arch/s390/include/asm/stacktrace.h
+++ b/arch/s390/include/asm/stacktrace.h
@@ -12,6 +12,7 @@ enum stack_type {
 	STACK_TYPE_IRQ,
 	STACK_TYPE_NODAT,
 	STACK_TYPE_RESTART,
+	STACK_TYPE_MCCK,
 };
 
 struct stack_info {
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 0dc4b258b98d..db1bc00229ca 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -79,6 +79,15 @@ static bool in_nodat_stack(unsigned long sp, struct stack_info *info)
 	return in_stack(sp, info, STACK_TYPE_NODAT, top - THREAD_SIZE, top);
 }
 
+static bool in_mcck_stack(unsigned long sp, struct stack_info *info)
+{
+	unsigned long frame_size, top;
+
+	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+	top = S390_lowcore.mcck_stack + frame_size;
+	return in_stack(sp, info, STACK_TYPE_MCCK, top - THREAD_SIZE, top);
+}
+
 static bool in_restart_stack(unsigned long sp, struct stack_info *info)
 {
 	unsigned long frame_size, top;
@@ -108,7 +117,8 @@ int get_stack_info(unsigned long sp, struct task_struct *task,
 	/* Check per-cpu stacks */
 	if (!in_irq_stack(sp, info) &&
 	    !in_nodat_stack(sp, info) &&
-	    !in_restart_stack(sp, info))
+	    !in_restart_stack(sp, info) &&
+	    !in_mcck_stack(sp, info))
 		goto unknown;
 
 recursion_check:

From 85012e764d3a1be02297b23c1aa3467f0df212aa Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Sat, 3 Apr 2021 12:15:13 +0200
Subject: [PATCH 1552/1820] s390/irq: fix reading of ext_params2 field from
 lowcore

The contents of the ext_params2 field of the lowcore should just be
copied to the pt_regs structure, not dereferenced.

Fixes crashes / program check loops like this:

Krnl PSW : 0404c00180000000 00000000d6d02b3c (do_ext_irq+0x74/0x170)
           R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:3 CC:0 PM:0 RI:0 EA:3
Krnl GPRS: 0000000000000000 80000000000b974e 00000000d71abee0 00000000d71abee0
           0000000080030000 000000000000000f 0000000000000000 0000000000000000
           0000000000000001 00000380000bf918 00000000d73ef780 00000380000bf518
           0000000080348000 00000000d6d13350 00000000d6d02b1e 00000380000bf428
Krnl Code: 00000000d6d02b2e: 58100080            l       %r1,128
           00000000d6d02b32: 5010b0a4            st      %r1,164(%r11)
          #00000000d6d02b36: e31001b80104        lg      %r1,4536
          >00000000d6d02b3c: e31010000004        lg      %r1,0(%r1)
           00000000d6d02b42: e310b0a80024        stg     %r1,168(%r11)
           00000000d6d02b48: c01000242270        larl    %r1,00000000d7187028
           00000000d6d02b4e: d5071000b010        clc     0(8,%r1),16(%r11)
           00000000d6d02b54: a784001b            brc     8,00000000d6d02b8a
Call Trace:
 [<00000000d6d02b3c>] do_ext_irq+0x74/0x170
 [<00000000d6d0ea5c>] ext_int_handler+0xc4/0xf4
 [<00000000d621d266>] die+0x106/0x188
 [<00000000d62305b8>] do_no_context+0xc8/0x100
 [<00000000d6d02790>] __do_pgm_check+0xe0/0x1f0
 [<00000000d6d0e950>] pgm_check_handler+0x118/0x160
 [<00000000d6d02b3c>] do_ext_irq+0x74/0x170
 [<00000000d6d0ea5c>] ext_int_handler+0xc4/0xf4
 [<00000000d621d266>] die+0x106/0x188
 [<00000000d62305b8>] do_no_context+0xc8/0x100
 [<00000000d6d02790>] __do_pgm_check+0xe0/0x1f0
 [<00000000d6d0e950>] pgm_check_handler+0x118/0x160
 [<00000000d6d02b3c>] do_ext_irq+0x74/0x170
 [<00000000d6d0ea5c>] ext_int_handler+0xc4/0xf4
 [<0000000000000000>] 0x0
 [<00000000d6d0e57a>] default_idle_call+0x42/0x110
 [<00000000d629856e>] do_idle+0xce/0x160
 [<00000000d62987be>] cpu_startup_entry+0x36/0x40
 [<00000000d621f2f2>] smp_start_secondary+0x82/0x88

Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Fixes: 56e62a737028 ("s390: convert to generic entry")
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/irq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 601c21791338..714269e10eec 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -174,7 +174,7 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 
 	memcpy(&regs->int_code, &S390_lowcore.ext_cpu_addr, 4);
 	regs->int_parm = S390_lowcore.ext_params;
-	regs->int_parm_long = *(unsigned long *)S390_lowcore.ext_params2;
+	regs->int_parm_long = S390_lowcore.ext_params2;
 
 	from_idle = !user_mode(regs) && regs->psw.addr == (unsigned long)psw_idle_exit;
 	if (from_idle)

From 026334a3bb6a3919b42aba9fc11843db2b77fd41 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 1 Apr 2021 13:36:05 +0300
Subject: [PATCH 1553/1820] perf inject: Fix repipe usage

Since commit 14d3d54052539a1e ("perf session: Try to read pipe data from
file") 'perf inject' has started printing "PERFILE2h" when not processing
pipes.

The commit exposed perf to the possiblity that the input is not a pipe
but the 'repipe' parameter gets used. That causes the printing because
perf inject sets 'repipe' to true always.

The 'repipe' parameter of perf_session__new() is used by 2 functions:

	- perf_file_header__read_pipe()
	- trace_report()

In both cases, the functions copy data to STDOUT_FILENO when 'repipe' is
true.

Fix by setting 'repipe' to true only if the output is a pipe.

Fixes: e558a5bd8b74aff4 ("perf inject: Work with files")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Andrew Vagin <avagin@openvz.org>
Link: http://lore.kernel.org/lkml/20210401103605.9000-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-inject.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 6fe44d97fde5..ddccc0eb7390 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -906,7 +906,7 @@ int cmd_inject(int argc, const char **argv)
 	}
 
 	data.path = inject.input_name;
-	inject.session = perf_session__new(&data, true, &inject.tool);
+	inject.session = perf_session__new(&data, inject.output.is_pipe, &inject.tool);
 	if (IS_ERR(inject.session))
 		return PTR_ERR(inject.session);
 

From 4d51419d49930be2701c2633ae271b350397c3ca Mon Sep 17 00:00:00 2001
From: Ilya Maximets <i.maximets@ovn.org>
Date: Sun, 4 Apr 2021 19:50:31 +0200
Subject: [PATCH 1554/1820] openvswitch: fix send of uninitialized stack memory
 in ct limit reply

'struct ovs_zone_limit' has more members than initialized in
ovs_ct_limit_get_default_limit().  The rest of the memory is a random
kernel stack content that ends up being sent to userspace.

Fix that by using designated initializer that will clear all
non-specified fields.

Fixes: 11efd5cb04a1 ("openvswitch: Support conntrack zone limit")
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
Acked-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 71cec03e8612..d217bd91176b 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -2034,10 +2034,10 @@ static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit,
 static int ovs_ct_limit_get_default_limit(struct ovs_ct_limit_info *info,
 					  struct sk_buff *reply)
 {
-	struct ovs_zone_limit zone_limit;
-
-	zone_limit.zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE;
-	zone_limit.limit = info->default_limit;
+	struct ovs_zone_limit zone_limit = {
+		.zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE,
+		.limit   = info->default_limit,
+	};
 
 	return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit);
 }

From 630e4576f83accf90366686f39808d665d8dbecc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= <maze@google.com>
Date: Mon, 5 Apr 2021 00:06:52 -0700
Subject: [PATCH 1555/1820] net-ipv6: bugfix - raw & sctp - switch to
 ipv6_can_nonlocal_bind()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Found by virtue of ipv6 raw sockets not honouring the per-socket
IP{,V6}_FREEBIND setting.

Based on hits found via:
  git grep '[.]ip_nonlocal_bind'
We fix both raw ipv6 sockets to honour IP{,V6}_FREEBIND and IP{,V6}_TRANSPARENT,
and we fix sctp sockets to honour IP{,V6}_TRANSPARENT (they already honoured
FREEBIND), and not just the ipv6 'ip_nonlocal_bind' sysctl.

The helper is defined as:
  static inline bool ipv6_can_nonlocal_bind(struct net *net, struct inet_sock *inet) {
    return net->ipv6.sysctl.ip_nonlocal_bind || inet->freebind || inet->transparent;
  }
so this change only widens the accepted opt-outs and is thus a clean bugfix.

I'm not entirely sure what 'fixes' tag to add, since this is AFAICT an ancient bug,
but IMHO this should be applied to stable kernels as far back as possible.
As such I'm adding a 'fixes' tag with the commit that originally added the helper,
which happened in 4.19.  Backporting to older LTS kernels (at least 4.9 and 4.14)
would presumably require open-coding it or backporting the helper as well.

Other possibly relevant commits:
  v4.18-rc6-1502-g83ba4645152d net: add helpers checking if socket can be bound to nonlocal address
  v4.18-rc6-1431-gd0c1f01138c4 net/ipv6: allow any source address for sendmsg pktinfo with ip_nonlocal_bind
  v4.14-rc5-271-gb71d21c274ef sctp: full support for ipv6 ip_nonlocal_bind & IP_FREEBIND
  v4.7-rc7-1883-g9b9742022888 sctp: support ipv6 nonlocal bind
  v4.1-12247-g35a256fee52c ipv6: Nonlocal bind

Cc: Lorenzo Colitti <lorenzo@google.com>
Fixes: 83ba4645152d ("net: add helpers checking if socket can be bound to nonlocal address")
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Reviewed-By: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/raw.c  | 2 +-
 net/sctp/ipv6.c | 7 +++----
 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 1f56d9aae589..bf3646b57c68 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -298,7 +298,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		 */
 		v4addr = LOOPBACK4_IPV6;
 		if (!(addr_type & IPV6_ADDR_MULTICAST) &&
-		    !sock_net(sk)->ipv6.sysctl.ip_nonlocal_bind) {
+		    !ipv6_can_nonlocal_bind(sock_net(sk), inet)) {
 			err = -EADDRNOTAVAIL;
 			if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr,
 					   dev, 0)) {
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index c3e89c776e66..bd08807c9e44 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -664,8 +664,8 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp)
 	if (!(type & IPV6_ADDR_UNICAST))
 		return 0;
 
-	return sp->inet.freebind || net->ipv6.sysctl.ip_nonlocal_bind ||
-		ipv6_chk_addr(net, in6, NULL, 0);
+	return ipv6_can_nonlocal_bind(net, &sp->inet) ||
+	       ipv6_chk_addr(net, in6, NULL, 0);
 }
 
 /* This function checks if the address is a valid address to be used for
@@ -954,8 +954,7 @@ static int sctp_inet6_bind_verify(struct sctp_sock *opt, union sctp_addr *addr)
 			net = sock_net(&opt->inet.sk);
 			rcu_read_lock();
 			dev = dev_get_by_index_rcu(net, addr->v6.sin6_scope_id);
-			if (!dev || !(opt->inet.freebind ||
-				      net->ipv6.sysctl.ip_nonlocal_bind ||
+			if (!dev || !(ipv6_can_nonlocal_bind(net, &opt->inet) ||
 				      ipv6_chk_addr(net, &addr->v6.sin6_addr,
 						    dev, 0))) {
 				rcu_read_unlock();

From 5e729bc54bda705f64941008b018b4e41a4322bf Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 31 Mar 2021 14:05:10 +0300
Subject: [PATCH 1556/1820] i2c: designware: Adjust bus_freq_hz when refuse
 high speed mode set

When hardware doesn't support High Speed Mode, we forget bus_freq_hz
timing adjustment. This makes the timings and real registers being
unsynchronized. Adjust bus_freq_hz when refuse high speed mode set.

Fixes: b6e67145f149 ("i2c: designware: Enable high speed mode")
Reported-by: "Song Bao Hua (Barry Song)" <song.bao.hua@hisilicon.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-designware-master.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index dd27b9dbe931..873ef38eb1c8 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -129,6 +129,7 @@ static int i2c_dw_set_timings_master(struct dw_i2c_dev *dev)
 		if ((comp_param1 & DW_IC_COMP_PARAM_1_SPEED_MODE_MASK)
 			!= DW_IC_COMP_PARAM_1_SPEED_MODE_HIGH) {
 			dev_err(dev->dev, "High Speed not supported!\n");
+			t->bus_freq_hz = I2C_MAX_FAST_MODE_FREQ;
 			dev->master_cfg &= ~DW_IC_CON_SPEED_MASK;
 			dev->master_cfg |= DW_IC_CON_SPEED_FAST;
 			dev->hs_hcnt = 0;

From 9a6aaf61487e6d96ce0bf9b84a784c528dbf6e5e Mon Sep 17 00:00:00 2001
From: Salil Mehta <salil.mehta@huawei.com>
Date: Mon, 5 Apr 2021 18:06:44 +0100
Subject: [PATCH 1557/1820] net: hns3: Remove the left over redundant check &
 assignment

This removes the left over check and assignment which is no longer used
anywhere in the function and should have been removed as part of the
below mentioned patch.

Fixes: 012fcb52f67c ("net: hns3: activate reset timer when calling reset_event")
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index e3f81c7e0ce7..58d210bbb311 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3966,7 +3966,6 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
 	 *    normalcy is to reset.
 	 * 2. A new reset request from the stack due to timeout
 	 *
-	 * For the first case,error event might not have ae handle available.
 	 * check if this is a new reset request and we are not here just because
 	 * last reset attempt did not succeed and watchdog hit us again. We will
 	 * know this if last reset request did not occur very recently (watchdog
@@ -3976,8 +3975,6 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
 	 * want to make sure we throttle the reset request. Therefore, we will
 	 * not allow it again before 3*HZ times.
 	 */
-	if (!handle)
-		handle = &hdev->vport[0].nic;
 
 	if (time_before(jiffies, (hdev->last_reset_time +
 				  HCLGE_RESET_INTERVAL))) {

From 0600771fa6b231e801ba1ff5d7adfcf7659dbbf3 Mon Sep 17 00:00:00 2001
From: Salil Mehta <salil.mehta@huawei.com>
Date: Mon, 5 Apr 2021 18:06:45 +0100
Subject: [PATCH 1558/1820] net: hns3: Remove un-necessary 'else-if' in the
 hclge_reset_event()

Code to defer the reset(which caps the frequency of the reset) schedules the
timer and returns. Hence, following 'else-if' looks un-necessary.

Fixes: 9de0b86f6444 ("net: hns3: Prevent to request reset frequently")
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 58d210bbb311..2dd2af269b46 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3980,7 +3980,9 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
 				  HCLGE_RESET_INTERVAL))) {
 		mod_timer(&hdev->reset_timer, jiffies + HCLGE_RESET_INTERVAL);
 		return;
-	} else if (hdev->default_reset_request) {
+	}
+
+	if (hdev->default_reset_request) {
 		hdev->reset_level =
 			hclge_get_reset_level(ae_dev,
 					      &hdev->default_reset_request);

From 08c27f3322fec11950b8f1384aa0f3b11d028528 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Mon, 5 Apr 2021 19:16:50 +0900
Subject: [PATCH 1559/1820] batman-adv: initialize "struct
 batadv_tvlv_tt_vlan_data"->reserved field

KMSAN found uninitialized value at batadv_tt_prepare_tvlv_local_data()
[1], for commit ced72933a5e8ab52 ("batman-adv: use CRC32C instead of CRC16
in TT code") inserted 'reserved' field into "struct batadv_tvlv_tt_data"
and commit 7ea7b4a142758dea ("batman-adv: make the TT CRC logic VLAN
specific") moved that field to "struct batadv_tvlv_tt_vlan_data" but left
that field uninitialized.

[1] https://syzkaller.appspot.com/bug?id=07f3e6dba96f0eb3cabab986adcd8a58b9bdbe9d

Reported-by: syzbot <syzbot+50ee810676e6a089487b@syzkaller.appspotmail.com>
Tested-by: syzbot <syzbot+50ee810676e6a089487b@syzkaller.appspotmail.com>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Fixes: ced72933a5e8ab52 ("batman-adv: use CRC32C instead of CRC16 in TT code")
Fixes: 7ea7b4a142758dea ("batman-adv: make the TT CRC logic VLAN specific")
Acked-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/batman-adv/translation-table.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index f8761281aab0..434b4f042909 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -890,6 +890,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node,
 	hlist_for_each_entry(vlan, &orig_node->vlan_list, list) {
 		tt_vlan->vid = htons(vlan->vid);
 		tt_vlan->crc = htonl(vlan->tt.crc);
+		tt_vlan->reserved = 0;
 
 		tt_vlan++;
 	}
@@ -973,6 +974,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
 
 		tt_vlan->vid = htons(vlan->vid);
 		tt_vlan->crc = htonl(vlan->tt.crc);
+		tt_vlan->reserved = 0;
 
 		tt_vlan++;
 	}

From 65df7d1986a1909a0869419919e7d9c78d70407e Mon Sep 17 00:00:00 2001
From: Viswas G <Viswas.G@microchip.com>
Date: Fri, 2 Apr 2021 11:12:12 +0530
Subject: [PATCH 1560/1820] scsi: pm80xx: Fix chip initialization failure

Inbound and outbound queues were not properly configured and that lead to
MPI configuration failure.

Fixes: 05c6c029a44d ("scsi: pm80xx: Increase number of supported queues")
Cc: stable@vger.kernel.org # 5.10+
Link: https://lore.kernel.org/r/20210402054212.17834-1-Viswas.G@microchip.com.com
Reported-and-tested-by: Ash Izat <ash@ai0.uk>
Signed-off-by: Viswas G <Viswas.G@microchip.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/pm8001/pm8001_hwi.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c
index 49bf2f70a470..31e5455d280c 100644
--- a/drivers/scsi/pm8001/pm8001_hwi.c
+++ b/drivers/scsi/pm8001/pm8001_hwi.c
@@ -223,7 +223,7 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha)
 		PM8001_EVENT_LOG_SIZE;
 	pm8001_ha->main_cfg_tbl.pm8001_tbl.iop_event_log_option		= 0x01;
 	pm8001_ha->main_cfg_tbl.pm8001_tbl.fatal_err_interrupt		= 0x01;
-	for (i = 0; i < PM8001_MAX_INB_NUM; i++) {
+	for (i = 0; i < pm8001_ha->max_q_num; i++) {
 		pm8001_ha->inbnd_q_tbl[i].element_pri_size_cnt	=
 			PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x00<<30);
 		pm8001_ha->inbnd_q_tbl[i].upper_base_addr	=
@@ -249,7 +249,7 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha)
 		pm8001_ha->inbnd_q_tbl[i].producer_idx		= 0;
 		pm8001_ha->inbnd_q_tbl[i].consumer_index	= 0;
 	}
-	for (i = 0; i < PM8001_MAX_OUTB_NUM; i++) {
+	for (i = 0; i < pm8001_ha->max_q_num; i++) {
 		pm8001_ha->outbnd_q_tbl[i].element_size_cnt	=
 			PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x01<<30);
 		pm8001_ha->outbnd_q_tbl[i].upper_base_addr	=
@@ -671,9 +671,9 @@ static int pm8001_chip_init(struct pm8001_hba_info *pm8001_ha)
 	read_outbnd_queue_table(pm8001_ha);
 	/* update main config table ,inbound table and outbound table */
 	update_main_config_table(pm8001_ha);
-	for (i = 0; i < PM8001_MAX_INB_NUM; i++)
+	for (i = 0; i < pm8001_ha->max_q_num; i++)
 		update_inbnd_queue_table(pm8001_ha, i);
-	for (i = 0; i < PM8001_MAX_OUTB_NUM; i++)
+	for (i = 0; i < pm8001_ha->max_q_num; i++)
 		update_outbnd_queue_table(pm8001_ha, i);
 	/* 8081 controller donot require these operations */
 	if (deviceid != 0x8081 && deviceid != 0x0042) {

From 0352c3d3959a6cf543075b88c7e662fd3546f12e Mon Sep 17 00:00:00 2001
From: Roman Bolshakov <r.bolshakov@yadro.com>
Date: Sun, 4 Apr 2021 00:54:15 +0300
Subject: [PATCH 1561/1820] scsi: target: iscsi: Fix zero tag inside a trace
 event

target_sequencer_start event is triggered inside target_cmd_init_cdb().
se_cmd.tag is not initialized with ITT at the moment so the event always
prints zero tag.

Link: https://lore.kernel.org/r/20210403215415.95077-1-r.bolshakov@yadro.com
Cc: stable@vger.kernel.org # 5.10+
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/iscsi/iscsi_target.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index d0e7ed8f28cc..e5c443bfbdf9 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1166,6 +1166,7 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 
 	target_get_sess_cmd(&cmd->se_cmd, true);
 
+	cmd->se_cmd.tag = (__force u32)cmd->init_task_tag;
 	cmd->sense_reason = target_cmd_init_cdb(&cmd->se_cmd, hdr->cdb);
 	if (cmd->sense_reason) {
 		if (cmd->sense_reason == TCM_OUT_OF_RESOURCES) {
@@ -1180,8 +1181,6 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	if (cmd->sense_reason)
 		goto attach_cmd;
 
-	/* only used for printks or comparing with ->ref_task_tag */
-	cmd->se_cmd.tag = (__force u32)cmd->init_task_tag;
 	cmd->sense_reason = target_cmd_parse_cdb(&cmd->se_cmd);
 	if (cmd->sense_reason)
 		goto attach_cmd;

From 5cd0f6f57639c5afbb36100c69281fee82c95ee7 Mon Sep 17 00:00:00 2001
From: Martin Wilck <mwilck@suse.com>
Date: Thu, 1 Apr 2021 11:11:05 +0200
Subject: [PATCH 1562/1820] scsi: scsi_transport_srp: Don't block target in
 SRP_PORT_LOST state

rport_dev_loss_timedout() sets the rport state to SRP_PORT_LOST and the
SCSI target state to SDEV_TRANSPORT_OFFLINE. If this races with
srp_reconnect_work(), a warning is printed:

Mar 27 18:48:07 ictm1604s01h4 kernel: dev_loss_tmo expired for SRP port-18:1 / host18.
Mar 27 18:48:07 ictm1604s01h4 kernel: ------------[ cut here ]------------
Mar 27 18:48:07 ictm1604s01h4 kernel: scsi_internal_device_block(18:0:0:100) failed: ret = -22
Mar 27 18:48:07 ictm1604s01h4 kernel: Call Trace:
Mar 27 18:48:07 ictm1604s01h4 kernel:  ? scsi_target_unblock+0x50/0x50 [scsi_mod]
Mar 27 18:48:07 ictm1604s01h4 kernel:  starget_for_each_device+0x80/0xb0 [scsi_mod]
Mar 27 18:48:07 ictm1604s01h4 kernel:  target_block+0x24/0x30 [scsi_mod]
Mar 27 18:48:07 ictm1604s01h4 kernel:  device_for_each_child+0x57/0x90
Mar 27 18:48:07 ictm1604s01h4 kernel:  srp_reconnect_rport+0xe4/0x230 [scsi_transport_srp]
Mar 27 18:48:07 ictm1604s01h4 kernel:  srp_reconnect_work+0x40/0xc0 [scsi_transport_srp]

Avoid this by not trying to block targets for rports in SRP_PORT_LOST
state.

Link: https://lore.kernel.org/r/20210401091105.8046-1-mwilck@suse.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_transport_srp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index 1e939a2a387f..98a34ed10f1a 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -541,7 +541,7 @@ int srp_reconnect_rport(struct srp_rport *rport)
 	res = mutex_lock_interruptible(&rport->mutex);
 	if (res)
 		goto out;
-	if (rport->state != SRP_RPORT_FAIL_FAST)
+	if (rport->state != SRP_RPORT_FAIL_FAST && rport->state != SRP_RPORT_LOST)
 		/*
 		 * sdev state must be SDEV_TRANSPORT_OFFLINE, transition
 		 * to SDEV_BLOCK is illegal. Calling scsi_target_unblock()

From 4033e76a7abd102eaa84d7adc232f53b9da8709a Mon Sep 17 00:00:00 2001
From: Wan Jiabing <wanjiabing@vivo.com>
Date: Wed, 31 Mar 2021 09:28:50 +0800
Subject: [PATCH 1563/1820] parisc: Remove duplicate struct task_struct
 declaration

struct task_struct is declared twice. One has been declared
at 154th line. Remove the duplicate.

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/asm/processor.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 11ece0d07374..b5fbcd2c1780 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -272,7 +272,6 @@ on downward growing arches, it looks like this:
 	regs->gr[23] = 0;				\
 } while(0)
 
-struct task_struct;
 struct mm_struct;
 
 /* Free all resources held by a thread. */

From 9054284e8846b0105aad43a4e7174ca29fffbc44 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Tue, 6 Apr 2021 11:32:52 +0200
Subject: [PATCH 1564/1820] parisc: parisc-agp requires SBA IOMMU driver

Add a dependency to the SBA IOMMU driver to avoid:
ERROR: modpost: "sba_list" [drivers/char/agp/parisc-agp.ko] undefined!

Reported-by: kernel test robot <lkp@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/char/agp/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/char/agp/Kconfig b/drivers/char/agp/Kconfig
index a086dd34f932..4f501e4842ab 100644
--- a/drivers/char/agp/Kconfig
+++ b/drivers/char/agp/Kconfig
@@ -125,7 +125,7 @@ config AGP_HP_ZX1
 
 config AGP_PARISC
 	tristate "HP Quicksilver AGP support"
-	depends on AGP && PARISC && 64BIT
+	depends on AGP && PARISC && 64BIT && IOMMU_SBA
 	help
 	  This option gives you AGP GART support for the HP Quicksilver
 	  AGP bus adapter on HP PA-RISC machines (Ok, just on the C8000

From 07cc40fec9a85e669ea12e161a438d2cbd76f1ed Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Fri, 26 Mar 2021 12:57:17 +0200
Subject: [PATCH 1565/1820] iwlwifi: fix 11ax disabled bit in the regulatory
 capability flags

When version 2 of the regulatory capability flags API was implemented,
the flag to disable 11ax was defined as bit 13, but this was later
changed and the bit remained as bit 10, like in version 1.  This was
never changed in the driver, so we were checking for the wrong bit in
newer devices.  Fix it.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Fixes: e27c506a985c ("iwlwifi: regulatory: regulatory capabilities api change")
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/iwlwifi.20210326125611.6d28516b59cd.Id0248d5e4662695254f49ce37b0268834ed52918@changeid
---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index af684f80b0cc..c5a1e84dc1ab 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -232,7 +232,7 @@ enum iwl_reg_capa_flags_v2 {
 	REG_CAPA_V2_MCS_9_ALLOWED	= BIT(6),
 	REG_CAPA_V2_WEATHER_DISABLED	= BIT(7),
 	REG_CAPA_V2_40MHZ_ALLOWED	= BIT(8),
-	REG_CAPA_V2_11AX_DISABLED	= BIT(13),
+	REG_CAPA_V2_11AX_DISABLED	= BIT(10),
 };
 
 /*

From 25628bc08d4526d3673ca7d039eb636aa9006076 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 26 Mar 2021 12:57:18 +0200
Subject: [PATCH 1566/1820] iwlwifi: pcie: properly set LTR workarounds on
 22000 devices

As the context info gen3 code is only called for >=AX210 devices
(from iwl_trans_pcie_gen2_start_fw()) the code there to set LTR
on 22000 devices cannot actually do anything (22000 < AX210).

Fix this by moving the LTR code to iwl_trans_pcie_gen2_start_fw()
where it can handle both devices. This then requires that we kick
the firmware only after that rather than doing it from the context
info code.

Note that this again had a dead branch in gen3 code, which I've
removed here.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Fixes: ed0022da8bd9 ("iwlwifi: pcie: set LTR on more devices")
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/iwlwifi.20210326125611.675486178ed1.Ib61463aba6920645059e366dcdca4c4c77f0ff58@changeid
---
 .../intel/iwlwifi/pcie/ctxt-info-gen3.c       | 31 +---------------
 .../wireless/intel/iwlwifi/pcie/ctxt-info.c   |  3 +-
 .../wireless/intel/iwlwifi/pcie/trans-gen2.c  | 35 +++++++++++++++++++
 3 files changed, 37 insertions(+), 32 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
index 8fba190e84cf..cecc32e7dbe8 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
  */
 #include "iwl-trans.h"
 #include "iwl-fh.h"
@@ -75,15 +75,6 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 				 const struct fw_img *fw)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	u32 ltr_val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ |
-		      u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC,
-				      CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) |
-		      u32_encode_bits(250,
-				      CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) |
-		      CSR_LTR_LONG_VAL_AD_SNOOP_REQ |
-		      u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC,
-				      CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) |
-		      u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL);
 	struct iwl_context_info_gen3 *ctxt_info_gen3;
 	struct iwl_prph_scratch *prph_scratch;
 	struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl;
@@ -217,26 +208,6 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 	iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL,
 		    CSR_AUTO_FUNC_BOOT_ENA);
 
-	/*
-	 * To workaround hardware latency issues during the boot process,
-	 * initialize the LTR to ~250 usec (see ltr_val above).
-	 * The firmware initializes this again later (to a smaller value).
-	 */
-	if ((trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210 ||
-	     trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) &&
-	    !trans->trans_cfg->integrated) {
-		iwl_write32(trans, CSR_LTR_LONG_VAL_AD, ltr_val);
-	} else if (trans->trans_cfg->integrated &&
-		   trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) {
-		iwl_write_prph(trans, HPM_MAC_LTR_CSR, HPM_MAC_LRT_ENABLE_ALL);
-		iwl_write_prph(trans, HPM_UMAC_LTR, ltr_val);
-	}
-
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
-		iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1);
-	else
-		iwl_set_bit(trans, CSR_GP_CNTRL, CSR_AUTO_FUNC_INIT);
-
 	return 0;
 
 err_free_ctxt_info:
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
index d1bb273d6b6d..74ce31fdf45e 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
  */
 #include "iwl-trans.h"
 #include "iwl-fh.h"
@@ -240,7 +240,6 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 
 	/* kick FW self load */
 	iwl_write64(trans, CSR_CTXT_INFO_BA, trans_pcie->ctxt_info_dma_addr);
-	iwl_write_prph(trans, UREG_CPU_INIT_RUN, 1);
 
 	/* Context info will be released upon alive or failure to get one */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index 497ef3405da3..94ffc1ae484d 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -266,6 +266,34 @@ void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans, u32 scd_addr)
 	mutex_unlock(&trans_pcie->mutex);
 }
 
+static void iwl_pcie_set_ltr(struct iwl_trans *trans)
+{
+	u32 ltr_val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ |
+		      u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC,
+				      CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) |
+		      u32_encode_bits(250,
+				      CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) |
+		      CSR_LTR_LONG_VAL_AD_SNOOP_REQ |
+		      u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC,
+				      CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) |
+		      u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL);
+
+	/*
+	 * To workaround hardware latency issues during the boot process,
+	 * initialize the LTR to ~250 usec (see ltr_val above).
+	 * The firmware initializes this again later (to a smaller value).
+	 */
+	if ((trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210 ||
+	     trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) &&
+	    !trans->trans_cfg->integrated) {
+		iwl_write32(trans, CSR_LTR_LONG_VAL_AD, ltr_val);
+	} else if (trans->trans_cfg->integrated &&
+		   trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) {
+		iwl_write_prph(trans, HPM_MAC_LTR_CSR, HPM_MAC_LRT_ENABLE_ALL);
+		iwl_write_prph(trans, HPM_UMAC_LTR, ltr_val);
+	}
+}
+
 int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 				 const struct fw_img *fw, bool run_in_rfkill)
 {
@@ -332,6 +360,13 @@ int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 	if (ret)
 		goto out;
 
+	iwl_pcie_set_ltr(trans);
+
+	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+		iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1);
+	else
+		iwl_write_prph(trans, UREG_CPU_INIT_RUN, 1);
+
 	/* re-check RF-Kill state since we may have missed the interrupt */
 	hw_rfkill = iwl_pcie_check_hw_rf_kill(trans);
 	if (hw_rfkill && !run_in_rfkill)

From 97195d3cad852063208a1cd4f4d073459547a415 Mon Sep 17 00:00:00 2001
From: Matt Chen <matt.chen@intel.com>
Date: Fri, 26 Mar 2021 12:57:19 +0200
Subject: [PATCH 1567/1820] iwlwifi: add support for Qu with AX201 device

Add this specific Samsung AX201 sku to driver so it can be
detected and initialized successfully.

Signed-off-by: Matt Chen <matt.chen@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/iwlwifi.20210326125611.30b622037714.Id9fd709cf1c8261c097bbfd7453f6476077dcafc@changeid
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index ffaf973dae94..4e2219b46db2 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -592,6 +592,7 @@ static const struct iwl_dev_info iwl_dev_info_table[] = {
 	IWL_DEV_INFO(0x4DF0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0, NULL),
 	IWL_DEV_INFO(0x4DF0, 0x2074, iwl_ax201_cfg_qu_hr, NULL),
 	IWL_DEV_INFO(0x4DF0, 0x4070, iwl_ax201_cfg_qu_hr, NULL),
+	IWL_DEV_INFO(0x4DF0, 0x6074, iwl_ax201_cfg_qu_hr, NULL),
 
 	/* So with HR */
 	IWL_DEV_INFO(0x2725, 0x0090, iwlax211_2ax_cfg_so_gf_a0, NULL),

From 9c04fd95fa830d60e5bdb08bcd7ff68d7e120e5b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 26 Mar 2021 12:57:20 +0200
Subject: [PATCH 1568/1820] iwlwifi: fw: fix notification wait locking

Since we now call iwl_notification_wait_notify() from the
NAPI poll in soft-IRQ, we get a (valid) lockdep complaint
that we could get a deadlock by taking the spinlock from
sleeping context and then getting the soft-IRQ that also
tries to take it (in NAPI polling).

Fix this by disabling soft-IRQs for this lock.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Fixes: 25edc8f259c7 ("iwlwifi: pcie: properly implement NAPI")
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/iwlwifi.20210326125611.c3b2e3d6b58b.Ic56f351d04674df70567bab0269cba91bdbc853c@changeid
---
 drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c b/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c
index 3dbc6f3f92cc..231d2517f398 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014 Intel Corporation
+ * Copyright (C) 2005-2014, 2021 Intel Corporation
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
 #include <linux/sched.h>
@@ -26,7 +26,7 @@ bool iwl_notification_wait(struct iwl_notif_wait_data *notif_wait,
 	if (!list_empty(&notif_wait->notif_waits)) {
 		struct iwl_notification_wait *w;
 
-		spin_lock(&notif_wait->notif_wait_lock);
+		spin_lock_bh(&notif_wait->notif_wait_lock);
 		list_for_each_entry(w, &notif_wait->notif_waits, list) {
 			int i;
 			bool found = false;
@@ -59,7 +59,7 @@ bool iwl_notification_wait(struct iwl_notif_wait_data *notif_wait,
 				triggered = true;
 			}
 		}
-		spin_unlock(&notif_wait->notif_wait_lock);
+		spin_unlock_bh(&notif_wait->notif_wait_lock);
 	}
 
 	return triggered;
@@ -70,10 +70,10 @@ void iwl_abort_notification_waits(struct iwl_notif_wait_data *notif_wait)
 {
 	struct iwl_notification_wait *wait_entry;
 
-	spin_lock(&notif_wait->notif_wait_lock);
+	spin_lock_bh(&notif_wait->notif_wait_lock);
 	list_for_each_entry(wait_entry, &notif_wait->notif_waits, list)
 		wait_entry->aborted = true;
-	spin_unlock(&notif_wait->notif_wait_lock);
+	spin_unlock_bh(&notif_wait->notif_wait_lock);
 
 	wake_up_all(&notif_wait->notif_waitq);
 }

From 08f4b0b1c07bcb70247931d81233fb9c59f50c35 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Fri, 26 Mar 2021 12:57:21 +0200
Subject: [PATCH 1569/1820] iwlwifi: pcie: add support for So-F devices

We have a new type of device that has a different MAC ID, but is
otherwise identical to So devices.  Add rules to match this new ID
accordingly.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/iwlwifi.20210326125611.4feea3560def.I2b6ef794c2073a18779dd40fb53f8c942d1ab42d@changeid
---
 .../net/wireless/intel/iwlwifi/iwl-config.h   |  1 +
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 26 ++++++++++++++++++-
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 75f99ff7f908..c4f5da76f1c0 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -414,6 +414,7 @@ struct iwl_cfg {
 #define IWL_CFG_MAC_TYPE_QNJ		0x36
 #define IWL_CFG_MAC_TYPE_SO		0x37
 #define IWL_CFG_MAC_TYPE_SNJ		0x42
+#define IWL_CFG_MAC_TYPE_SOF		0x43
 #define IWL_CFG_MAC_TYPE_MA		0x44
 
 #define IWL_CFG_RF_TYPE_TH		0x105
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 4e2219b46db2..558a0b2ef0fc 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1041,7 +1041,31 @@ static const struct iwl_dev_info iwl_dev_info_table[] = {
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY,
 		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_so_a0_hr_a0, iwl_ax201_name)
+		      iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
+
+/* So-F with Hr */
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY,
+		      IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      iwl_cfg_so_a0_hr_a0, iwl_ax203_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY,
+		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      iwl_cfg_so_a0_hr_a0, iwl_ax101_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY,
+		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
+
+/* So-F with Gf */
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY,
+		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name),
 
 #endif /* CONFIG_IWLMVM */
 };

From 39fb06f791429eaee8374ef12634c0fbf68a5a9f Mon Sep 17 00:00:00 2001
From: Gregory Greenman <gregory.greenman@intel.com>
Date: Fri, 26 Mar 2021 12:57:22 +0200
Subject: [PATCH 1570/1820] iwlwifi: mvm: rfi: don't lock mvm->mutex when
 sending config command

The mutex is already locked in iwl_mvm_mac_start.

Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Fixes: 21254908cbe9 ("iwlwifi: mvm: add RFI-M support")
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/iwlwifi.20210326125611.703288ea058d.I82a0312389032d07c3b478bef3e938e06bfa7df6@changeid
---
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c | 7 +++++--
 drivers/net/wireless/intel/iwlwifi/mvm/rfi.c     | 6 +++---
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 130760572262..34ddef97b099 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1786,10 +1786,13 @@ static ssize_t iwl_dbgfs_rfi_freq_table_write(struct iwl_mvm *mvm, char *buf,
 		return -EINVAL;
 
 	/* value zero triggers re-sending the default table to the device */
-	if (!op_id)
+	if (!op_id) {
+		mutex_lock(&mvm->mutex);
 		ret = iwl_rfi_send_config_cmd(mvm, NULL);
-	else
+		mutex_unlock(&mvm->mutex);
+	} else {
 		ret = -EOPNOTSUPP; /* in the future a new table will be added */
+	}
 
 	return ret ?: count;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c
index 873919048143..0b818067067c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2020 Intel Corporation
+ * Copyright (C) 2020 - 2021 Intel Corporation
  */
 
 #include "mvm.h"
@@ -66,6 +66,8 @@ int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_t
 	if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_RFIM_SUPPORT))
 		return -EOPNOTSUPP;
 
+	lockdep_assert_held(&mvm->mutex);
+
 	/* in case no table is passed, use the default one */
 	if (!rfi_table) {
 		memcpy(cmd.table, iwl_rfi_table, sizeof(cmd.table));
@@ -75,9 +77,7 @@ int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_t
 		cmd.oem = 1;
 	}
 
-	mutex_lock(&mvm->mutex);
 	ret = iwl_mvm_send_cmd(mvm, &hcmd);
-	mutex_unlock(&mvm->mutex);
 
 	if (ret)
 		IWL_ERR(mvm, "Failed to send RFI config cmd %d\n", ret);

From 65db391dd874db42279713405f29f4ac93682d13 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 26 Mar 2021 12:57:23 +0200
Subject: [PATCH 1571/1820] iwlwifi: mvm: fix beacon protection checks

Unfortunately, since beacon protection isn't fully available
yet, we didn't notice that there are problems with it and
that the replay detection isn't working correctly. We were
relying only on mac80211, since iwl_mvm_rx_crypto() exits
when !ieee80211_has_protected(), which is of course true for
protected (but not encrypted) management frames.

Fix this to properly detect protected (but not encrypted)
management frames and handle them - we continue to only care
about beacons since for others everything can and will be
checked in mac80211.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Fixes: b1fdc2505abc ("iwlwifi: mvm: advertise BIGTK client support if available")
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/iwlwifi.20210326125611.23c990843369.I09c262a8f6f9852cc8f513cdcb31a7f8f87dd8af@changeid
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index c21736f80c29..af5a6dd81c41 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -272,10 +272,10 @@ static void iwl_mvm_get_signal_strength(struct iwl_mvm *mvm,
 	rx_status->chain_signal[2] = S8_MIN;
 }
 
-static int iwl_mvm_rx_mgmt_crypto(struct ieee80211_sta *sta,
-				  struct ieee80211_hdr *hdr,
-				  struct iwl_rx_mpdu_desc *desc,
-				  u32 status)
+static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta,
+				struct ieee80211_hdr *hdr,
+				struct iwl_rx_mpdu_desc *desc,
+				u32 status)
 {
 	struct iwl_mvm_sta *mvmsta;
 	struct iwl_mvm_vif *mvmvif;
@@ -285,6 +285,9 @@ static int iwl_mvm_rx_mgmt_crypto(struct ieee80211_sta *sta,
 	u32 len = le16_to_cpu(desc->mpdu_len);
 	const u8 *frame = (void *)hdr;
 
+	if ((status & IWL_RX_MPDU_STATUS_SEC_MASK) == IWL_RX_MPDU_STATUS_SEC_NONE)
+		return 0;
+
 	/*
 	 * For non-beacon, we don't really care. But beacons may
 	 * be filtered out, and we thus need the firmware's replay
@@ -356,6 +359,10 @@ static int iwl_mvm_rx_crypto(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 	    IWL_RX_MPDU_STATUS_SEC_UNKNOWN && !mvm->monitor_on)
 		return -1;
 
+	if (unlikely(ieee80211_is_mgmt(hdr->frame_control) &&
+		     !ieee80211_has_protected(hdr->frame_control)))
+		return iwl_mvm_rx_mgmt_prot(sta, hdr, desc, status);
+
 	if (!ieee80211_has_protected(hdr->frame_control) ||
 	    (status & IWL_RX_MPDU_STATUS_SEC_MASK) ==
 	    IWL_RX_MPDU_STATUS_SEC_NONE)
@@ -411,7 +418,7 @@ static int iwl_mvm_rx_crypto(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 		stats->flag |= RX_FLAG_DECRYPTED;
 		return 0;
 	case RX_MPDU_RES_STATUS_SEC_CMAC_GMAC_ENC:
-		return iwl_mvm_rx_mgmt_crypto(sta, hdr, desc, status);
+		break;
 	default:
 		/*
 		 * Sometimes we can get frames that were not decrypted

From 617085fca6375e2c1667d1fbfc6adc4034c85f04 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Tue, 30 Mar 2021 11:46:07 +0200
Subject: [PATCH 1572/1820] can: mcp251x: fix support for half duplex SPI host
 controllers

Some SPI host controllers do not support full-duplex SPI transfers.

The function mcp251x_spi_trans() does a full duplex transfer. It is
used in several places in the driver, where a TX half duplex transfer
is sufficient.

To fix support for half duplex SPI host controllers, this patch
introduces a new function mcp251x_spi_write() and changes all callers
that do a TX half duplex transfer to use mcp251x_spi_write().

Fixes: e0e25001d088 ("can: mcp251x: add support for half duplex controllers")
Link: https://lore.kernel.org/r/20210330100246.1074375-1-mkl@pengutronix.de
Cc: Tim Harvey <tharvey@gateworks.com>
Tested-By: Tim Harvey <tharvey@gateworks.com>
Reported-by: Gerhard Bertelsmann <info@gerhard-bertelsmann.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/spi/mcp251x.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index f69fb4238a65..a57da43680d8 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -314,6 +314,18 @@ static int mcp251x_spi_trans(struct spi_device *spi, int len)
 	return ret;
 }
 
+static int mcp251x_spi_write(struct spi_device *spi, int len)
+{
+	struct mcp251x_priv *priv = spi_get_drvdata(spi);
+	int ret;
+
+	ret = spi_write(spi, priv->spi_tx_buf, len);
+	if (ret)
+		dev_err(&spi->dev, "spi write failed: ret = %d\n", ret);
+
+	return ret;
+}
+
 static u8 mcp251x_read_reg(struct spi_device *spi, u8 reg)
 {
 	struct mcp251x_priv *priv = spi_get_drvdata(spi);
@@ -361,7 +373,7 @@ static void mcp251x_write_reg(struct spi_device *spi, u8 reg, u8 val)
 	priv->spi_tx_buf[1] = reg;
 	priv->spi_tx_buf[2] = val;
 
-	mcp251x_spi_trans(spi, 3);
+	mcp251x_spi_write(spi, 3);
 }
 
 static void mcp251x_write_2regs(struct spi_device *spi, u8 reg, u8 v1, u8 v2)
@@ -373,7 +385,7 @@ static void mcp251x_write_2regs(struct spi_device *spi, u8 reg, u8 v1, u8 v2)
 	priv->spi_tx_buf[2] = v1;
 	priv->spi_tx_buf[3] = v2;
 
-	mcp251x_spi_trans(spi, 4);
+	mcp251x_spi_write(spi, 4);
 }
 
 static void mcp251x_write_bits(struct spi_device *spi, u8 reg,
@@ -386,7 +398,7 @@ static void mcp251x_write_bits(struct spi_device *spi, u8 reg,
 	priv->spi_tx_buf[2] = mask;
 	priv->spi_tx_buf[3] = val;
 
-	mcp251x_spi_trans(spi, 4);
+	mcp251x_spi_write(spi, 4);
 }
 
 static u8 mcp251x_read_stat(struct spi_device *spi)
@@ -618,7 +630,7 @@ static void mcp251x_hw_tx_frame(struct spi_device *spi, u8 *buf,
 					  buf[i]);
 	} else {
 		memcpy(priv->spi_tx_buf, buf, TXBDAT_OFF + len);
-		mcp251x_spi_trans(spi, TXBDAT_OFF + len);
+		mcp251x_spi_write(spi, TXBDAT_OFF + len);
 	}
 }
 
@@ -650,7 +662,7 @@ static void mcp251x_hw_tx(struct spi_device *spi, struct can_frame *frame,
 
 	/* use INSTRUCTION_RTS, to avoid "repeated frame problem" */
 	priv->spi_tx_buf[0] = INSTRUCTION_RTS(1 << tx_buf_idx);
-	mcp251x_spi_trans(priv->spi, 1);
+	mcp251x_spi_write(priv->spi, 1);
 }
 
 static void mcp251x_hw_rx_frame(struct spi_device *spi, u8 *buf,
@@ -888,7 +900,7 @@ static int mcp251x_hw_reset(struct spi_device *spi)
 	mdelay(MCP251X_OST_DELAY_MS);
 
 	priv->spi_tx_buf[0] = INSTRUCTION_RESET;
-	ret = mcp251x_spi_trans(spi, 1);
+	ret = mcp251x_spi_write(spi, 1);
 	if (ret)
 		return ret;
 

From c6423ed2da6214a68527446b5f8e09cf7162b2ce Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 1 Apr 2021 19:13:14 +0200
Subject: [PATCH 1573/1820] ALSA: hda/conexant: Apply quirk for another HP
 ZBook G5 model

There is another HP ZBook G5 model with the PCI SSID 103c:844f that
requires the same quirk for controlling the mute LED.  Add the
corresponding entry to the quirk table.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=212407
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210401171314.667-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_conexant.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index c20dad46a7c9..dfef9c17e140 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -944,6 +944,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8402, "HP ProBook 645 G4", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x8427, "HP ZBook Studio G5", CXT_FIXUP_HP_ZBOOK_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x844f, "HP ZBook Studio G5", CXT_FIXUP_HP_ZBOOK_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8456, "HP Z2 G4 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE),

From 4d752e5af63753ab5140fc282929b98eaa4bd12e Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@redhat.com>
Date: Tue, 6 Apr 2021 12:59:29 +0800
Subject: [PATCH 1574/1820] parisc: avoid a warning on u8 cast for cmpxchg on
 u8 pointers

commit b344d6a83d01 ("parisc: add support for cmpxchg on u8 pointers")
can generate a sparse warning ("cast truncates bits from constant
value"), which has been reported several times [1] [2] [3].

The original code worked as expected, but anyway, let silence such
sparse warning as what others did [4].

[1] https://lore.kernel.org/r/202104061220.nRMBwCXw-lkp@intel.com
[2] https://lore.kernel.org/r/202012291914.T5Agcn99-lkp@intel.com
[3] https://lore.kernel.org/r/202008210829.KVwn7Xeh%25lkp@intel.com
[4] https://lore.kernel.org/r/20210315131512.133720-2-jacopo+renesas@jmondi.org
Cc: Liam Beguin <liambeguin@gmail.com>
Cc: Helge Deller <deller@gmx.de>
Cc: stable@vger.kernel.org # v5.8+
Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/asm/cmpxchg.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index cf5ee9b0b393..84ee232278a6 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -72,7 +72,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
 #endif
 	case 4: return __cmpxchg_u32((unsigned int *)ptr,
 				     (unsigned int)old, (unsigned int)new_);
-	case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_);
+	case 1: return __cmpxchg_u8((u8 *)ptr, old & 0xff, new_ & 0xff);
 	}
 	__cmpxchg_called_with_bad_pointer();
 	return old;

From 0aa2ddc9af44bf9032098a587aeabada4da181a7 Mon Sep 17 00:00:00 2001
From: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Date: Thu, 18 Mar 2021 00:54:27 +0530
Subject: [PATCH 1575/1820] parisc: math-emu: Few spelling fixes in the file
 fpu.h

with some additional cleanups by Helge.

Signed-off-by: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/math-emu/fpu.h | 32 +++-----------------------------
 1 file changed, 3 insertions(+), 29 deletions(-)

diff --git a/arch/parisc/math-emu/fpu.h b/arch/parisc/math-emu/fpu.h
index 853c19c03828..dec951d40286 100644
--- a/arch/parisc/math-emu/fpu.h
+++ b/arch/parisc/math-emu/fpu.h
@@ -5,34 +5,10 @@
  * Floating-point emulation code
  *  Copyright (C) 2001 Hewlett-Packard (Paul Bame) <bame@debian.org>
  */
-/*
- * BEGIN_DESC
- * 
- *  File: 
- *      @(#)	pa/fp/fpu.h		$Revision: 1.1 $
- * 
- *  Purpose:
- *      <<please update with a synopis of the functionality provided by this file>>
- * 
- * 
- * END_DESC  
-*/
-
-#ifdef __NO_PA_HDRS
-    PA header file -- do not include this header file for non-PA builds.
-#endif
-
 
 #ifndef _MACHINE_FPU_INCLUDED /* allows multiple inclusion */
 #define _MACHINE_FPU_INCLUDED
 
-#if 0
-#ifndef _SYS_STDSYMS_INCLUDED
-#    include <sys/stdsyms.h>
-#endif   /* _SYS_STDSYMS_INCLUDED  */
-#include  <machine/pdc/pdc_rqsts.h>
-#endif
-
 #define PA83_FPU_FLAG    0x00000001
 #define PA89_FPU_FLAG    0x00000002
 #define PA2_0_FPU_FLAG   0x00000010
@@ -43,21 +19,19 @@
 #define COPR_FP 	0x00000080	/* Floating point -- Coprocessor 0 */
 #define SFU_MPY_DIVIDE	0x00008000	/* Multiply/Divide __ SFU 0 */
 
-
 #define EM_FPU_TYPE_OFFSET 272
 
 /* version of EMULATION software for COPR,0,0 instruction */
 #define EMULATION_VERSION 4
 
 /*
- * The only was to differeniate between TIMEX and ROLEX (or PCX-S and PCX-T)
- * is thorough the potential type field from the PDC_MODEL call.  The 
- * following flags are used at assist this differeniation.
+ * The only way to differentiate between TIMEX and ROLEX (or PCX-S and PCX-T)
+ * is through the potential type field from the PDC_MODEL call.
+ * The following flags are used to assist this differentiation.
  */
 
 #define ROLEX_POTENTIAL_KEY_FLAGS	PDC_MODEL_CPU_KEY_WORD_TO_IO
 #define TIMEX_POTENTIAL_KEY_FLAGS	(PDC_MODEL_CPU_KEY_QUAD_STORE | \
 					 PDC_MODEL_CPU_KEY_RECIP_SQRT)
 
-
 #endif /* ! _MACHINE_FPU_INCLUDED */

From 3b943360a20f3e4b2e0133c7cd7138b51fd93de6 Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sre@kernel.org>
Date: Sat, 27 Feb 2021 22:45:42 +0100
Subject: [PATCH 1576/1820] drm/panel: panel-dsi-cm: disable TE for now

Disable TE for Droid 4 panel, since implementation is currently
broken. Also disable it for N950 panel, which is untested.

Reported-by: Tony Lindgren <tony@atomide.com>
Reported-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Fixes: 4c1b935fea54 ("drm/omap: dsi: move TE GPIO handling into core")
Signed-off-by: Sebastian Reichel <sre@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210227214542.99961-1-sebastian.reichel@collabora.com
---
 drivers/gpu/drm/panel/panel-dsi-cm.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-dsi-cm.c b/drivers/gpu/drm/panel/panel-dsi-cm.c
index af381d756ac1..5fbfb71ca3d9 100644
--- a/drivers/gpu/drm/panel/panel-dsi-cm.c
+++ b/drivers/gpu/drm/panel/panel-dsi-cm.c
@@ -37,6 +37,7 @@ struct dsic_panel_data {
 	u32 height_mm;
 	u32 max_hs_rate;
 	u32 max_lp_rate;
+	bool te_support;
 };
 
 struct panel_drv_data {
@@ -334,9 +335,11 @@ static int dsicm_power_on(struct panel_drv_data *ddata)
 	if (r)
 		goto err;
 
-	r = mipi_dsi_dcs_set_tear_on(ddata->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK);
-	if (r)
-		goto err;
+	if (ddata->panel_data->te_support) {
+		r = mipi_dsi_dcs_set_tear_on(ddata->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK);
+		if (r)
+			goto err;
+	}
 
 	/* possible panel bug */
 	msleep(100);
@@ -619,6 +622,7 @@ static const struct dsic_panel_data taal_data = {
 	.height_mm = 0,
 	.max_hs_rate = 300000000,
 	.max_lp_rate = 10000000,
+	.te_support = true,
 };
 
 static const struct dsic_panel_data himalaya_data = {
@@ -629,6 +633,7 @@ static const struct dsic_panel_data himalaya_data = {
 	.height_mm = 88,
 	.max_hs_rate = 300000000,
 	.max_lp_rate = 10000000,
+	.te_support = false,
 };
 
 static const struct dsic_panel_data droid4_data = {
@@ -639,6 +644,7 @@ static const struct dsic_panel_data droid4_data = {
 	.height_mm = 89,
 	.max_hs_rate = 300000000,
 	.max_lp_rate = 10000000,
+	.te_support = false,
 };
 
 static const struct of_device_id dsicm_of_match[] = {

From 7d01ef7585c07afaf487759a48486228cd065726 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 6 Apr 2021 12:33:07 -0400
Subject: [PATCH 1577/1820] Make sure nd->path.mnt and nd->path.dentry are
 always valid pointers

Initialize them in set_nameidata() and make sure that terminate_walk() clears them
once the pointers become potentially invalid (i.e. we leave RCU mode or drop them
in non-RCU one).  Currently we have "path_init() always initializes them and nobody
accesses them outside of path_init()/terminate_walk() segments", which is asking
for trouble.

With that change we would have nd->path.{mnt,dentry}
	1) always valid - NULL or pointing to currently allocated objects.
	2) non-NULL while we are successfully walking
	3) NULL when we are not walking at all
	4) contributing to refcounts whenever non-NULL outside of RCU mode.

Fixes: 6c6ec2b0a3e0 ("fs: add support for LOOKUP_CACHED")
Reported-by: syzbot+c88a7030da47945a3cc3@syzkaller.appspotmail.com
Tested-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 216f16e74351..fc8760d4314e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -579,6 +579,8 @@ static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
 	p->stack = p->internal;
 	p->dfd = dfd;
 	p->name = name;
+	p->path.mnt = NULL;
+	p->path.dentry = NULL;
 	p->total_link_count = old ? old->total_link_count : 0;
 	p->saved = old;
 	current->nameidata = p;
@@ -652,6 +654,8 @@ static void terminate_walk(struct nameidata *nd)
 		rcu_read_unlock();
 	}
 	nd->depth = 0;
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
 }
 
 /* path_put is needed afterwards regardless of success or failure */
@@ -2322,8 +2326,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	}
 
 	nd->root.mnt = NULL;
-	nd->path.mnt = NULL;
-	nd->path.dentry = NULL;
 
 	/* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */
 	if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) {

From 6eff5721933c08c3b76d6126aee24d8f134518ef Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 1 Apr 2021 07:33:14 -0700
Subject: [PATCH 1578/1820] cxl/mem: Use sysfs_emit() for attribute show
 routines

While none the CXL sysfs attributes are threatening to overrun a
PAGE_SIZE of output, it is good form to use the recommended helpers.

Fixes: b39cb1052a5c ("cxl/mem: Register CXL memX devices")
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Ben Widawsky <ben.widawsky@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/161728759424.2474381.11231441014951343463.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/mem.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 244cb7d89678..832582033683 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -1066,7 +1066,7 @@ static ssize_t firmware_version_show(struct device *dev,
 	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
 	struct cxl_mem *cxlm = cxlmd->cxlm;
 
-	return sprintf(buf, "%.16s\n", cxlm->firmware_version);
+	return sysfs_emit(buf, "%.16s\n", cxlm->firmware_version);
 }
 static DEVICE_ATTR_RO(firmware_version);
 
@@ -1076,7 +1076,7 @@ static ssize_t payload_max_show(struct device *dev,
 	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
 	struct cxl_mem *cxlm = cxlmd->cxlm;
 
-	return sprintf(buf, "%zu\n", cxlm->payload_size);
+	return sysfs_emit(buf, "%zu\n", cxlm->payload_size);
 }
 static DEVICE_ATTR_RO(payload_max);
 
@@ -1087,7 +1087,7 @@ static ssize_t ram_size_show(struct device *dev, struct device_attribute *attr,
 	struct cxl_mem *cxlm = cxlmd->cxlm;
 	unsigned long long len = range_len(&cxlm->ram_range);
 
-	return sprintf(buf, "%#llx\n", len);
+	return sysfs_emit(buf, "%#llx\n", len);
 }
 
 static struct device_attribute dev_attr_ram_size =
@@ -1100,7 +1100,7 @@ static ssize_t pmem_size_show(struct device *dev, struct device_attribute *attr,
 	struct cxl_mem *cxlm = cxlmd->cxlm;
 	unsigned long long len = range_len(&cxlm->pmem_range);
 
-	return sprintf(buf, "%#llx\n", len);
+	return sysfs_emit(buf, "%#llx\n", len);
 }
 
 static struct device_attribute dev_attr_pmem_size =

From 5877515912cc4f0d67071b7cee15076ebef24708 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 1 Apr 2021 07:33:19 -0700
Subject: [PATCH 1579/1820] cxl/mem: Fix synchronization mechanism for device
 removal vs ioctl operations

The percpu_ref to gate whether cxl_memdev_ioctl() is free to use the
driver context (@cxlm) to issue I/O is overkill, implemented incorrectly
(missing a device reference before accessing the percpu_ref), and the
complexities of shutting down a percpu_ref contributed to a bug in the
error unwind in cxl_mem_add_memdev() (missing put_device() to be fixed
separately).

Use an rwsem to explicitly synchronize the usage of cxlmd->cxlm, and add
the missing reference counting for cxlmd in cxl_memdev_open() and
cxl_memdev_release_file().

Fixes: b39cb1052a5c ("cxl/mem: Register CXL memX devices")
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/161728759948.2474381.17481500816783671817.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/mem.c | 101 ++++++++++++++++++++++++----------------------
 1 file changed, 52 insertions(+), 49 deletions(-)

diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 832582033683..438f0861c46c 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -96,21 +96,18 @@ struct mbox_cmd {
  * @dev: driver core device object
  * @cdev: char dev core object for ioctl operations
  * @cxlm: pointer to the parent device driver data
- * @ops_active: active user of @cxlm in ops handlers
- * @ops_dead: completion when all @cxlm ops users have exited
  * @id: id number of this memdev instance.
  */
 struct cxl_memdev {
 	struct device dev;
 	struct cdev cdev;
 	struct cxl_mem *cxlm;
-	struct percpu_ref ops_active;
-	struct completion ops_dead;
 	int id;
 };
 
 static int cxl_mem_major;
 static DEFINE_IDA(cxl_memdev_ida);
+static DECLARE_RWSEM(cxl_memdev_rwsem);
 static struct dentry *cxl_debugfs;
 static bool cxl_raw_allow_all;
 
@@ -776,26 +773,43 @@ static long __cxl_memdev_ioctl(struct cxl_memdev *cxlmd, unsigned int cmd,
 static long cxl_memdev_ioctl(struct file *file, unsigned int cmd,
 			     unsigned long arg)
 {
-	struct cxl_memdev *cxlmd;
-	struct inode *inode;
-	int rc = -ENOTTY;
+	struct cxl_memdev *cxlmd = file->private_data;
+	int rc = -ENXIO;
 
-	inode = file_inode(file);
-	cxlmd = container_of(inode->i_cdev, typeof(*cxlmd), cdev);
-
-	if (!percpu_ref_tryget_live(&cxlmd->ops_active))
-		return -ENXIO;
-
-	rc = __cxl_memdev_ioctl(cxlmd, cmd, arg);
-
-	percpu_ref_put(&cxlmd->ops_active);
+	down_read(&cxl_memdev_rwsem);
+	if (cxlmd->cxlm)
+		rc = __cxl_memdev_ioctl(cxlmd, cmd, arg);
+	up_read(&cxl_memdev_rwsem);
 
 	return rc;
 }
 
+static int cxl_memdev_open(struct inode *inode, struct file *file)
+{
+	struct cxl_memdev *cxlmd =
+		container_of(inode->i_cdev, typeof(*cxlmd), cdev);
+
+	get_device(&cxlmd->dev);
+	file->private_data = cxlmd;
+
+	return 0;
+}
+
+static int cxl_memdev_release_file(struct inode *inode, struct file *file)
+{
+	struct cxl_memdev *cxlmd =
+		container_of(inode->i_cdev, typeof(*cxlmd), cdev);
+
+	put_device(&cxlmd->dev);
+
+	return 0;
+}
+
 static const struct file_operations cxl_memdev_fops = {
 	.owner = THIS_MODULE,
 	.unlocked_ioctl = cxl_memdev_ioctl,
+	.open = cxl_memdev_open,
+	.release = cxl_memdev_release_file,
 	.compat_ioctl = compat_ptr_ioctl,
 	.llseek = noop_llseek,
 };
@@ -1049,7 +1063,6 @@ static void cxl_memdev_release(struct device *dev)
 {
 	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
 
-	percpu_ref_exit(&cxlmd->ops_active);
 	ida_free(&cxl_memdev_ida, cxlmd->id);
 	kfree(cxlmd);
 }
@@ -1150,26 +1163,23 @@ static const struct device_type cxl_memdev_type = {
 	.groups = cxl_memdev_attribute_groups,
 };
 
-static void cxlmdev_unregister(void *_cxlmd)
+static void cxl_memdev_shutdown(struct cxl_memdev *cxlmd)
+{
+	down_write(&cxl_memdev_rwsem);
+	cxlmd->cxlm = NULL;
+	up_write(&cxl_memdev_rwsem);
+}
+
+static void cxl_memdev_unregister(void *_cxlmd)
 {
 	struct cxl_memdev *cxlmd = _cxlmd;
 	struct device *dev = &cxlmd->dev;
 
-	percpu_ref_kill(&cxlmd->ops_active);
 	cdev_device_del(&cxlmd->cdev, dev);
-	wait_for_completion(&cxlmd->ops_dead);
-	cxlmd->cxlm = NULL;
+	cxl_memdev_shutdown(cxlmd);
 	put_device(dev);
 }
 
-static void cxlmdev_ops_active_release(struct percpu_ref *ref)
-{
-	struct cxl_memdev *cxlmd =
-		container_of(ref, typeof(*cxlmd), ops_active);
-
-	complete(&cxlmd->ops_dead);
-}
-
 static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
 {
 	struct pci_dev *pdev = cxlm->pdev;
@@ -1181,17 +1191,6 @@ static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
 	cxlmd = kzalloc(sizeof(*cxlmd), GFP_KERNEL);
 	if (!cxlmd)
 		return -ENOMEM;
-	init_completion(&cxlmd->ops_dead);
-
-	/*
-	 * @cxlm is deallocated when the driver unbinds so operations
-	 * that are using it need to hold a live reference.
-	 */
-	cxlmd->cxlm = cxlm;
-	rc = percpu_ref_init(&cxlmd->ops_active, cxlmdev_ops_active_release, 0,
-			     GFP_KERNEL);
-	if (rc)
-		goto err_ref;
 
 	rc = ida_alloc_range(&cxl_memdev_ida, 0, CXL_MEM_MAX_DEVS, GFP_KERNEL);
 	if (rc < 0)
@@ -1209,23 +1208,27 @@ static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
 	cdev = &cxlmd->cdev;
 	cdev_init(cdev, &cxl_memdev_fops);
 
+	/*
+	 * Activate ioctl operations, no cxl_memdev_rwsem manipulation
+	 * needed as this is ordered with cdev_add() publishing the device.
+	 */
+	cxlmd->cxlm = cxlm;
+
 	rc = cdev_device_add(cdev, dev);
 	if (rc)
 		goto err_add;
 
-	return devm_add_action_or_reset(dev->parent, cxlmdev_unregister, cxlmd);
+	return devm_add_action_or_reset(dev->parent, cxl_memdev_unregister,
+					cxlmd);
 
 err_add:
+	/*
+	 * The cdev was briefly live, shutdown any ioctl operations that
+	 * saw that state.
+	 */
+	cxl_memdev_shutdown(cxlmd);
 	ida_free(&cxl_memdev_ida, cxlmd->id);
 err_id:
-	/*
-	 * Theoretically userspace could have already entered the fops,
-	 * so flush ops_active.
-	 */
-	percpu_ref_kill(&cxlmd->ops_active);
-	wait_for_completion(&cxlmd->ops_dead);
-	percpu_ref_exit(&cxlmd->ops_active);
-err_ref:
 	kfree(cxlmd);
 
 	return rc;

From 1c3333a28d4532cfc37d4d25bfc76654a0c76643 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 1 Apr 2021 07:33:25 -0700
Subject: [PATCH 1580/1820] cxl/mem: Do not rely on device_add() side effects
 for dev_set_name() failures

While device_add() will happen to catch dev_set_name() failures it is a
broken pattern to follow given that the core may try to fall back to a
different name.

Add explicit checking for dev_set_name() failures to be cleaned up by
put_device(). Skip cdev_device_add() and proceed directly to
put_device() if the name set fails.

This type of bug is easier to see if 'alloc' is split from 'add'
operations that require put_device() on failure. So cxl_memdev_alloc()
is split out as a result.

Fixes: b39cb1052a5c ("cxl/mem: Register CXL memX devices")
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/161728760514.2474381.1163928273337158134.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/mem.c | 39 +++++++++++++++++++++++++++++----------
 1 file changed, 29 insertions(+), 10 deletions(-)

diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 438f0861c46c..da93b633531f 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -1180,7 +1180,7 @@ static void cxl_memdev_unregister(void *_cxlmd)
 	put_device(dev);
 }
 
-static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
+static struct cxl_memdev *cxl_memdev_alloc(struct cxl_mem *cxlm)
 {
 	struct pci_dev *pdev = cxlm->pdev;
 	struct cxl_memdev *cxlmd;
@@ -1190,11 +1190,11 @@ static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
 
 	cxlmd = kzalloc(sizeof(*cxlmd), GFP_KERNEL);
 	if (!cxlmd)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	rc = ida_alloc_range(&cxl_memdev_ida, 0, CXL_MEM_MAX_DEVS, GFP_KERNEL);
 	if (rc < 0)
-		goto err_id;
+		goto err;
 	cxlmd->id = rc;
 
 	dev = &cxlmd->dev;
@@ -1203,10 +1203,31 @@ static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
 	dev->bus = &cxl_bus_type;
 	dev->devt = MKDEV(cxl_mem_major, cxlmd->id);
 	dev->type = &cxl_memdev_type;
-	dev_set_name(dev, "mem%d", cxlmd->id);
 
 	cdev = &cxlmd->cdev;
 	cdev_init(cdev, &cxl_memdev_fops);
+	return cxlmd;
+
+err:
+	kfree(cxlmd);
+	return ERR_PTR(rc);
+}
+
+static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
+{
+	struct cxl_memdev *cxlmd;
+	struct device *dev;
+	struct cdev *cdev;
+	int rc;
+
+	cxlmd = cxl_memdev_alloc(cxlm);
+	if (IS_ERR(cxlmd))
+		return PTR_ERR(cxlmd);
+
+	dev = &cxlmd->dev;
+	rc = dev_set_name(dev, "mem%d", cxlmd->id);
+	if (rc)
+		goto err;
 
 	/*
 	 * Activate ioctl operations, no cxl_memdev_rwsem manipulation
@@ -1214,23 +1235,21 @@ static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
 	 */
 	cxlmd->cxlm = cxlm;
 
+	cdev = &cxlmd->cdev;
 	rc = cdev_device_add(cdev, dev);
 	if (rc)
-		goto err_add;
+		goto err;
 
 	return devm_add_action_or_reset(dev->parent, cxl_memdev_unregister,
 					cxlmd);
 
-err_add:
+err:
 	/*
 	 * The cdev was briefly live, shutdown any ioctl operations that
 	 * saw that state.
 	 */
 	cxl_memdev_shutdown(cxlmd);
-	ida_free(&cxl_memdev_ida, cxlmd->id);
-err_id:
-	kfree(cxlmd);
-
+	put_device(dev);
 	return rc;
 }
 

From 7eda6457a9ca4dc9754e1158c3794e4487ea4392 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 1 Apr 2021 07:33:30 -0700
Subject: [PATCH 1581/1820] cxl/mem: Disable cxl device power management

There is no power management of cxl virtual devices, disable
device-power-management and runtime-power-management to prevent
userspace from growing expectations of those attributes appearing. They
can be added back in the future if needed.

Reviewed-by: Ben Widawsky <ben.widawsky@intel.com>
Link: https://lore.kernel.org/r/161728761025.2474381.808344500111924819.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/mem.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index da93b633531f..52f7da49c560 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -1203,6 +1203,7 @@ static struct cxl_memdev *cxl_memdev_alloc(struct cxl_mem *cxlm)
 	dev->bus = &cxl_bus_type;
 	dev->devt = MKDEV(cxl_mem_major, cxlmd->id);
 	dev->type = &cxl_memdev_type;
+	device_set_pm_not_required(dev);
 
 	cdev = &cxlmd->cdev;
 	cdev_init(cdev, &cxl_memdev_fops);

From 392be0bda730df3c71241b2a16bbecac78ee627d Mon Sep 17 00:00:00 2001
From: Robert Richter <rrichter@amd.com>
Date: Wed, 24 Mar 2021 15:16:35 +0100
Subject: [PATCH 1582/1820] cxl/mem: Force array size of mem_commands[] to
 CXL_MEM_COMMAND_ID_MAX

Typically the mem_commands[] array is in sync with 'enum { CXL_CMDS }'.
Current code works well.

However, the array size of mem_commands[] may not strictly be the same
as CXL_MEM_COMMAND_ID_MAX. E.g. if a new CXL_CMD() is added that is
guarded by #ifdefs, the array could be shorter. This could lead then
further to an out-of-bounds array access in cxl_validate_cmd_from_user().

Fix this by forcing the array size to CXL_MEM_COMMAND_ID_MAX. This
also adds range checks for array items in mem_commands[] at compile
time.

Signed-off-by: Robert Richter <rrichter@amd.com>
Link: https://lore.kernel.org/r/20210324141635.22335-1-rrichter@amd.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/mem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 52f7da49c560..e3003f49b329 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -166,7 +166,7 @@ struct cxl_mem_command {
  * table will be validated against the user's input. For example, if size_in is
  * 0, and the user passed in 1, it is an error.
  */
-static struct cxl_mem_command mem_commands[] = {
+static struct cxl_mem_command mem_commands[CXL_MEM_COMMAND_ID_MAX] = {
 	CXL_CMD(IDENTIFY, 0, 0x43, CXL_CMD_FLAG_FORCE_ENABLE),
 #ifdef CONFIG_CXL_MEM_RAW_COMMANDS
 	CXL_CMD(RAW, ~0, ~0, 0),

From 88c17855ac4291fb462e13a86b7516773b6c932e Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:41 -0400
Subject: [PATCH 1583/1820] net: ieee802154: forbid monitor for set llsec
 params

This patch forbids to set llsec params for monitor interfaces which we
don't support yet.

Reported-by: syzbot+8b6719da8a04beeafcc3@syzkaller.appspotmail.com
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-3-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 1600edb98107..ce8956f31ef9 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1384,6 +1384,9 @@ static int nl802154_set_llsec_params(struct sk_buff *skb,
 	u32 changed = 0;
 	int ret;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EOPNOTSUPP;
+
 	if (info->attrs[NL802154_ATTR_SEC_ENABLED]) {
 		u8 enabled;
 

From fb3c5cdf88cd504ef11d59e8d656f4bc896c6922 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:42 -0400
Subject: [PATCH 1584/1820] net: ieee802154: stop dump llsec keys for monitors

This patch stops dumping llsec keys for monitors which we don't support
yet. Otherwise we will access llsec mib which isn't initialized for
monitors.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-4-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index ce8956f31ef9..7815f253c8a3 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1493,6 +1493,11 @@ nl802154_dump_llsec_key(struct sk_buff *skb, struct netlink_callback *cb)
 	if (err)
 		return err;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) {
+		err = skb->len;
+		goto out_err;
+	}
+
 	if (!wpan_dev->netdev) {
 		err = -EINVAL;
 		goto out_err;

From 08470c5453339369bd3d590c4cbb0b5961cdcbb6 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:43 -0400
Subject: [PATCH 1585/1820] net: ieee802154: forbid monitor for add llsec key

This patch forbids to add llsec key for monitor interfaces which we
don't support yet. Otherwise we will access llsec mib which isn't
initialized for monitors.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-5-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 7815f253c8a3..42a246b6f9cb 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1552,6 +1552,9 @@ static int nl802154_add_llsec_key(struct sk_buff *skb, struct genl_info *info)
 	struct ieee802154_llsec_key_id id = { };
 	u32 commands[NL802154_CMD_FRAME_NR_IDS / 32] = { };
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EOPNOTSUPP;
+
 	if (!info->attrs[NL802154_ATTR_SEC_KEY] ||
 	    nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
 		return -EINVAL;

From b6e2949544a183f590ae6f3ef2d1aaaa2c44e38a Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:44 -0400
Subject: [PATCH 1586/1820] net: ieee802154: forbid monitor for del llsec key

This patch forbids to del llsec key for monitor interfaces which we
don't support yet. Otherwise we will access llsec mib which isn't
initialized for monitors.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-6-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 42a246b6f9cb..bfc0eca774e3 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1604,6 +1604,9 @@ static int nl802154_del_llsec_key(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1];
 	struct ieee802154_llsec_key_id id;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EOPNOTSUPP;
+
 	if (!info->attrs[NL802154_ATTR_SEC_KEY] ||
 	    nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
 		return -EINVAL;

From 5582d641e6740839c9b83efd1fbf9bcd00b6f5fc Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:45 -0400
Subject: [PATCH 1587/1820] net: ieee802154: stop dump llsec devs for monitors

This patch stops dumping llsec devs for monitors which we don't support
yet. Otherwise we will access llsec mib which isn't initialized for
monitors.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-7-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index bfc0eca774e3..ef0becc9faa7 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1672,6 +1672,11 @@ nl802154_dump_llsec_dev(struct sk_buff *skb, struct netlink_callback *cb)
 	if (err)
 		return err;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) {
+		err = skb->len;
+		goto out_err;
+	}
+
 	if (!wpan_dev->netdev) {
 		err = -EINVAL;
 		goto out_err;

From a3790a8a94fc0234c5d38013b48e74ef221ec84c Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 4 Apr 2021 16:38:31 +0200
Subject: [PATCH 1588/1820] platform/x86: intel-hid: Fix spurious wakeups
 caused by tablet-mode events during suspend

Some devices send (duplicate) tablet-mode events when moved around even
though the mode has not changed; and they do this even when suspended.

Change the tablet-mode event handling when priv->wakeup_mode is set to
update the switch state in case it changed and then return immediately
(without calling pm_wakeup_hard_event()) to avoid spurious wakeups.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=212537
Fixes: 537b0dd4729e ("platform/x86: intel-hid: Add support for SW_TABLET_MODE")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Elia Devito <eliadevito@gmail.com>
Link: https://lore.kernel.org/r/20210404143831.25173-1-hdegoede@redhat.com
---
 drivers/platform/x86/intel-hid.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index 57cc92891a57..078648a9201b 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -483,11 +483,16 @@ static void notify_handler(acpi_handle handle, u32 event, void *context)
 			goto wakeup;
 
 		/*
-		 * Switch events will wake the device and report the new switch
-		 * position to the input subsystem.
+		 * Some devices send (duplicate) tablet-mode events when moved
+		 * around even though the mode has not changed; and they do this
+		 * even when suspended.
+		 * Update the switch state in case it changed and then return
+		 * without waking up to avoid spurious wakeups.
 		 */
-		if (priv->switches && (event == 0xcc || event == 0xcd))
-			goto wakeup;
+		if (event == 0xcc || event == 0xcd) {
+			report_tablet_mode_event(priv->switches, event);
+			return;
+		}
 
 		/* Wake up on 5-button array events only. */
 		if (event == 0xc0 || !priv->array)
@@ -501,9 +506,6 @@ static void notify_handler(acpi_handle handle, u32 event, void *context)
 wakeup:
 		pm_wakeup_hard_event(&device->dev);
 
-		if (report_tablet_mode_event(priv->switches, event))
-			return;
-
 		return;
 	}
 

From 5303f956b05a2886ff42890908156afaec0f95ac Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:46 -0400
Subject: [PATCH 1589/1820] net: ieee802154: forbid monitor for add llsec dev

This patch forbids to add llsec dev for monitor interfaces which we
don't support yet. Otherwise we will access llsec mib which isn't
initialized for monitors.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-8-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index ef0becc9faa7..0d7dc9478b56 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1763,6 +1763,9 @@ static int nl802154_add_llsec_dev(struct sk_buff *skb, struct genl_info *info)
 	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
 	struct ieee802154_llsec_device dev_desc;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EOPNOTSUPP;
+
 	if (ieee802154_llsec_parse_device(info->attrs[NL802154_ATTR_SEC_DEVICE],
 					  &dev_desc) < 0)
 		return -EINVAL;

From ad8f9de1f3566686af35b1c6b43240726541da61 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:47 -0400
Subject: [PATCH 1590/1820] net: ieee802154: forbid monitor for del llsec dev

This patch forbids to del llsec dev for monitor interfaces which we
don't support yet. Otherwise we will access llsec mib which isn't
initialized for monitors.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-9-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 0d7dc9478b56..17c782d4cdae 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1781,6 +1781,9 @@ static int nl802154_del_llsec_dev(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1];
 	__le64 extended_addr;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EOPNOTSUPP;
+
 	if (!info->attrs[NL802154_ATTR_SEC_DEVICE] ||
 	    nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVICE], nl802154_dev_policy, info->extack))
 		return -EINVAL;

From 080d1a57a94d93e70f84b7a360baa351388c574f Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:48 -0400
Subject: [PATCH 1591/1820] net: ieee802154: stop dump llsec devkeys for
 monitors

This patch stops dumping llsec devkeys for monitors which we don't support
yet. Otherwise we will access llsec mib which isn't initialized for
monitors.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-10-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 17c782d4cdae..6f9cb6c0cafc 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1853,6 +1853,11 @@ nl802154_dump_llsec_devkey(struct sk_buff *skb, struct netlink_callback *cb)
 	if (err)
 		return err;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) {
+		err = skb->len;
+		goto out_err;
+	}
+
 	if (!wpan_dev->netdev) {
 		err = -EINVAL;
 		goto out_err;

From a347b3b394868fef15b16f143719df56184be81d Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:49 -0400
Subject: [PATCH 1592/1820] net: ieee802154: forbid monitor for add llsec
 devkey

This patch forbids to add llsec devkey for monitor interfaces which we
don't support yet. Otherwise we will access llsec mib which isn't
initialized for monitors.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-11-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 6f9cb6c0cafc..c3f9bff7a557 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1915,6 +1915,9 @@ static int nl802154_add_llsec_devkey(struct sk_buff *skb, struct genl_info *info
 	struct ieee802154_llsec_device_key key;
 	__le64 extended_addr;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EOPNOTSUPP;
+
 	if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] ||
 	    nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack) < 0)
 		return -EINVAL;

From 6fb8045319ef172dc88a8142e7f8b58c7608137e Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:50 -0400
Subject: [PATCH 1593/1820] net: ieee802154: forbid monitor for del llsec
 devkey

This patch forbids to del llsec devkey for monitor interfaces which we
don't support yet. Otherwise we will access llsec mib which isn't
initialized for monitors.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-12-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index c3f9bff7a557..88735f03b73e 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1949,6 +1949,9 @@ static int nl802154_del_llsec_devkey(struct sk_buff *skb, struct genl_info *info
 	struct ieee802154_llsec_device_key key;
 	__le64 extended_addr;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EOPNOTSUPP;
+
 	if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] ||
 	    nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack))
 		return -EINVAL;

From 4c9b4f55ad1f5a4b6206ac4ea58f273126d21925 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:51 -0400
Subject: [PATCH 1594/1820] net: ieee802154: stop dump llsec seclevels for
 monitors

This patch stops dumping llsec seclevels for monitors which we don't
support yet. Otherwise we will access llsec mib which isn't initialized
for monitors.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-13-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 88735f03b73e..9158b095ccf9 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -2026,6 +2026,11 @@ nl802154_dump_llsec_seclevel(struct sk_buff *skb, struct netlink_callback *cb)
 	if (err)
 		return err;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) {
+		err = skb->len;
+		goto out_err;
+	}
+
 	if (!wpan_dev->netdev) {
 		err = -EINVAL;
 		goto out_err;

From 9ec87e322428d4734ac647d1a8e507434086993d Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:52 -0400
Subject: [PATCH 1595/1820] net: ieee802154: forbid monitor for add llsec
 seclevel

This patch forbids to add llsec seclevel for monitor interfaces which we
don't support yet. Otherwise we will access llsec mib which isn't
initialized for monitors.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-14-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 9158b095ccf9..28427ce52a9b 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -2115,6 +2115,9 @@ static int nl802154_add_llsec_seclevel(struct sk_buff *skb,
 	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
 	struct ieee802154_llsec_seclevel sl;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EOPNOTSUPP;
+
 	if (llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL],
 				 &sl) < 0)
 		return -EINVAL;

From 56b4c6515a367718ced8595debf1567c052ea0b2 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Date: Mon, 5 Apr 2021 20:14:05 +0200
Subject: [PATCH 1596/1820] i2c: exynos5: correct top kerneldoc

The top comment is not a kerneldoc, as W=1 build reports:

  drivers/i2c/busses/i2c-exynos5.c:39: warning:
    expecting prototype for i2c(). Prototype was for HSI2C_CTL() instead

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-exynos5.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c
index 5ac30d95650c..97d4f3ac0abd 100644
--- a/drivers/i2c/busses/i2c-exynos5.c
+++ b/drivers/i2c/busses/i2c-exynos5.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * i2c-exynos5.c - Samsung Exynos5 I2C Controller Driver
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.

From 9dde130937e95b72adfae64ab21d6e7e707e2dac Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:53 -0400
Subject: [PATCH 1597/1820] net: ieee802154: forbid monitor for del llsec
 seclevel

This patch forbids to del llsec seclevel for monitor interfaces which we
don't support yet. Otherwise we will access llsec mib which isn't
initialized for monitors.

Reported-by: syzbot+fbf4fc11a819824e027b@syzkaller.appspotmail.com
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-15-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 28427ce52a9b..effc4c1a4780 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -2133,6 +2133,9 @@ static int nl802154_del_llsec_seclevel(struct sk_buff *skb,
 	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
 	struct ieee802154_llsec_seclevel sl;
 
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EOPNOTSUPP;
+
 	if (!info->attrs[NL802154_ATTR_SEC_LEVEL] ||
 	    llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL],
 				 &sl) < 0)

From 1534efc7bbc1121e92c86c2dabebaf2c9dcece19 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Sun, 4 Apr 2021 20:30:54 -0400
Subject: [PATCH 1598/1820] net: ieee802154: stop dump llsec params for
 monitors

This patch stops dumping llsec params for monitors which we don't support
yet. Otherwise we will access llsec mib which isn't initialized for
monitors.

Reported-by: syzbot+cde43a581a8e5f317bc2@syzkaller.appspotmail.com
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210405003054.256017-16-aahringo@redhat.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/nl802154.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index effc4c1a4780..05f6bd89a7dd 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -820,8 +820,13 @@ nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags,
 		goto nla_put_failure;
 
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		goto out;
+
 	if (nl802154_get_llsec_params(msg, rdev, wpan_dev) < 0)
 		goto nla_put_failure;
+
+out:
 #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
 
 	genlmsg_end(msg, hdr);

From 1165affd484889d4986cf3b724318935a0b120d8 Mon Sep 17 00:00:00 2001
From: Pavel Skripkin <paskripkin@gmail.com>
Date: Thu, 4 Mar 2021 18:21:25 +0300
Subject: [PATCH 1599/1820] net: mac802154: Fix general protection fault

syzbot found general protection fault in crypto_destroy_tfm()[1].
It was caused by wrong clean up loop in llsec_key_alloc().
If one of the tfm array members is in IS_ERR() range it will
cause general protection fault in clean up function [1].

Call Trace:
 crypto_free_aead include/crypto/aead.h:191 [inline] [1]
 llsec_key_alloc net/mac802154/llsec.c:156 [inline]
 mac802154_llsec_key_add+0x9e0/0xcc0 net/mac802154/llsec.c:249
 ieee802154_add_llsec_key+0x56/0x80 net/mac802154/cfg.c:338
 rdev_add_llsec_key net/ieee802154/rdev-ops.h:260 [inline]
 nl802154_add_llsec_key+0x3d3/0x560 net/ieee802154/nl802154.c:1584
 genl_family_rcv_msg_doit+0x228/0x320 net/netlink/genetlink.c:739
 genl_family_rcv_msg net/netlink/genetlink.c:783 [inline]
 genl_rcv_msg+0x328/0x580 net/netlink/genetlink.c:800
 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2502
 genl_rcv+0x24/0x40 net/netlink/genetlink.c:811
 netlink_unicast_kernel net/netlink/af_netlink.c:1312 [inline]
 netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1338
 netlink_sendmsg+0x856/0xd90 net/netlink/af_netlink.c:1927
 sock_sendmsg_nosec net/socket.c:654 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:674
 ____sys_sendmsg+0x6e8/0x810 net/socket.c:2350
 ___sys_sendmsg+0xf3/0x170 net/socket.c:2404
 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2433
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xae

Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Reported-by: syzbot+9ec037722d2603a9f52e@syzkaller.appspotmail.com
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20210304152125.1052825-1-paskripkin@gmail.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/mac802154/llsec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
index 585d33144c33..55550ead2ced 100644
--- a/net/mac802154/llsec.c
+++ b/net/mac802154/llsec.c
@@ -152,7 +152,7 @@ err_tfm0:
 	crypto_free_sync_skcipher(key->tfm0);
 err_tfm:
 	for (i = 0; i < ARRAY_SIZE(key->tfm); i++)
-		if (key->tfm[i])
+		if (!IS_ERR_OR_NULL(key->tfm[i]))
 			crypto_free_aead(key->tfm[i]);
 
 	kfree_sensitive(key);

From b25b343db0526669947a427e9a31bac91d29bb06 Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Fri, 2 Apr 2021 10:40:19 -0700
Subject: [PATCH 1600/1820] net: broadcom: bcm4908enet: Fix a double free in
 bcm4908_enet_dma_alloc

In bcm4908_enet_dma_alloc, if callee bcm4908_dma_alloc_buf_descs() failed,
it will free the ring->cpu_addr by dma_free_coherent() and return error.
Then bcm4908_enet_dma_free() will be called, and free the same cpu_addr
by dma_free_coherent() again.

My patch set ring->cpu_addr to NULL after it is freed in
bcm4908_dma_alloc_buf_descs() to avoid the double free.

Fixes: 4feffeadbcb2e ("net: broadcom: bcm4908enet: add BCM4908 controller driver")
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcm4908_enet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c
index 98cf82dea3e4..65981931a798 100644
--- a/drivers/net/ethernet/broadcom/bcm4908_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c
@@ -172,6 +172,7 @@ static int bcm4908_dma_alloc_buf_descs(struct bcm4908_enet *enet,
 
 err_free_buf_descs:
 	dma_free_coherent(dev, size, ring->cpu_addr, ring->dma_addr);
+	ring->cpu_addr = NULL;
 	return -ENOMEM;
 }
 

From 0f6925b3e8da0dbbb52447ca8a8b42b371aac7db Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Apr 2021 06:26:02 -0700
Subject: [PATCH 1601/1820] virtio_net: Do not pull payload in skb->head

Xuan Zhuo reported that commit 3226b158e67c ("net: avoid 32 x truesize
under-estimation for tiny skbs") brought  a ~10% performance drop.

The reason for the performance drop was that GRO was forced
to chain sk_buff (using skb_shinfo(skb)->frag_list), which
uses more memory but also cause packet consumers to go over
a lot of overhead handling all the tiny skbs.

It turns out that virtio_net page_to_skb() has a wrong strategy :
It allocates skbs with GOOD_COPY_LEN (128) bytes in skb->head, then
copies 128 bytes from the page, before feeding the packet to GRO stack.

This was suboptimal before commit 3226b158e67c ("net: avoid 32 x truesize
under-estimation for tiny skbs") because GRO was using 2 frags per MSS,
meaning we were not packing MSS with 100% efficiency.

Fix is to pull only the ethernet header in page_to_skb()

Then, we change virtio_net_hdr_to_skb() to pull the missing
headers, instead of assuming they were already pulled by callers.

This fixes the performance regression, but could also allow virtio_net
to accept packets with more than 128bytes of headers.

Many thanks to Xuan Zhuo for his report, and his tests/help.

Fixes: 3226b158e67c ("net: avoid 32 x truesize under-estimation for tiny skbs")
Reported-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Link: https://www.spinics.net/lists/netdev/msg731397.html
Co-Developed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c   | 10 +++++++---
 include/linux/virtio_net.h | 14 +++++++++-----
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 82e520d2cb12..0824e6999e49 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -406,9 +406,13 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	offset += hdr_padded_len;
 	p += hdr_padded_len;
 
-	copy = len;
-	if (copy > skb_tailroom(skb))
-		copy = skb_tailroom(skb);
+	/* Copy all frame if it fits skb->head, otherwise
+	 * we let virtio_net_hdr_to_skb() and GRO pull headers as needed.
+	 */
+	if (len <= skb_tailroom(skb))
+		copy = len;
+	else
+		copy = ETH_HLEN + metasize;
 	skb_put_data(skb, p, copy);
 
 	if (metasize) {
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 98775d7fa696..b465f8f3e554 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -65,14 +65,18 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 	skb_reset_mac_header(skb);
 
 	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-		u16 start = __virtio16_to_cpu(little_endian, hdr->csum_start);
-		u16 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
+		u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start);
+		u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
+		u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16));
+
+		if (!pskb_may_pull(skb, needed))
+			return -EINVAL;
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
 
 		p_off = skb_transport_offset(skb) + thlen;
-		if (p_off > skb_headlen(skb))
+		if (!pskb_may_pull(skb, p_off))
 			return -EINVAL;
 	} else {
 		/* gso packets without NEEDS_CSUM do not set transport_offset.
@@ -102,14 +106,14 @@ retry:
 			}
 
 			p_off = keys.control.thoff + thlen;
-			if (p_off > skb_headlen(skb) ||
+			if (!pskb_may_pull(skb, p_off) ||
 			    keys.basic.ip_proto != ip_proto)
 				return -EINVAL;
 
 			skb_set_transport_header(skb, keys.control.thoff);
 		} else if (gso_type) {
 			p_off = thlen;
-			if (p_off > skb_headlen(skb))
+			if (!pskb_may_pull(skb, p_off))
 				return -EINVAL;
 		}
 	}

From 2a2403ca3add03f542f6b34bef9f74649969b06d Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 6 Apr 2021 10:45:23 +0800
Subject: [PATCH 1602/1820] tipc: increment the tmp aead refcnt before
 attaching it

Li Shuang found a NULL pointer dereference crash in her testing:

  [] BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
  [] RIP: 0010:tipc_crypto_rcv_complete+0xc8/0x7e0 [tipc]
  [] Call Trace:
  []  <IRQ>
  []  tipc_crypto_rcv+0x2d9/0x8f0 [tipc]
  []  tipc_rcv+0x2fc/0x1120 [tipc]
  []  tipc_udp_recv+0xc6/0x1e0 [tipc]
  []  udpv6_queue_rcv_one_skb+0x16a/0x460
  []  udp6_unicast_rcv_skb.isra.35+0x41/0xa0
  []  ip6_protocol_deliver_rcu+0x23b/0x4c0
  []  ip6_input+0x3d/0xb0
  []  ipv6_rcv+0x395/0x510
  []  __netif_receive_skb_core+0x5fc/0xc40

This is caused by NULL returned by tipc_aead_get(), and then crashed when
dereferencing it later in tipc_crypto_rcv_complete(). This might happen
when tipc_crypto_rcv_complete() is called by two threads at the same time:
the tmp attached by tipc_crypto_key_attach() in one thread may be released
by the one attached by that in the other thread.

This patch is to fix it by incrementing the tmp's refcnt before attaching
it instead of calling tipc_aead_get() after attaching it.

Fixes: fc1b6d6de220 ("tipc: introduce TIPC encryption & authentication")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/crypto.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index f4fca8f7f63f..97710ce36047 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -1941,12 +1941,13 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead,
 			goto rcv;
 		if (tipc_aead_clone(&tmp, aead) < 0)
 			goto rcv;
+		WARN_ON(!refcount_inc_not_zero(&tmp->refcnt));
 		if (tipc_crypto_key_attach(rx, tmp, ehdr->tx_key, false) < 0) {
 			tipc_aead_free(&tmp->rcu);
 			goto rcv;
 		}
 		tipc_aead_put(aead);
-		aead = tipc_aead_get(tmp);
+		aead = tmp;
 	}
 
 	if (unlikely(err)) {

From 1c84b33101c82683dee8b06761ca1f69e78c8ee7 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 1 Apr 2021 15:00:19 -0700
Subject: [PATCH 1603/1820] bpf, sockmap: Fix sk->prot unhash op reset

In '4da6a196f93b1' we fixed a potential unhash loop caused when
a TLS socket in a sockmap was removed from the sockmap. This
happened because the unhash operation on the TLS ctx continued
to point at the sockmap implementation of unhash even though the
psock has already been removed. The sockmap unhash handler when a
psock is removed does the following,

 void sock_map_unhash(struct sock *sk)
 {
	void (*saved_unhash)(struct sock *sk);
	struct sk_psock *psock;

	rcu_read_lock();
	psock = sk_psock(sk);
	if (unlikely(!psock)) {
		rcu_read_unlock();
		if (sk->sk_prot->unhash)
			sk->sk_prot->unhash(sk);
		return;
	}
        [...]
 }

The unlikely() case is there to handle the case where psock is detached
but the proto ops have not been updated yet. But, in the above case
with TLS and removed psock we never fixed sk_prot->unhash() and unhash()
points back to sock_map_unhash resulting in a loop. To fix this we added
this bit of code,

 static inline void sk_psock_restore_proto(struct sock *sk,
                                          struct sk_psock *psock)
 {
       sk->sk_prot->unhash = psock->saved_unhash;

This will set the sk_prot->unhash back to its saved value. This is the
correct callback for a TLS socket that has been removed from the sock_map.
Unfortunately, this also overwrites the unhash pointer for all psocks.
We effectively break sockmap unhash handling for any future socks.
Omitting the unhash operation will leave stale entries in the map if
a socket transition through unhash, but does not do close() op.

To fix set unhash correctly before calling into tls_update. This way the
TLS enabled socket will point to the saved unhash() handler.

Fixes: 4da6a196f93b1 ("bpf: Sockmap/tls, during free we may call tcp_bpf_unhash() in loop")
Reported-by: Cong Wang <xiyou.wangcong@gmail.com>
Reported-by: Lorenz Bauer <lmb@cloudflare.com>
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/161731441904.68884.15593917809745631972.stgit@john-XPS-13-9370
---
 include/linux/skmsg.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 8edbbf5f2f93..822c048934e3 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -349,8 +349,13 @@ static inline void sk_psock_update_proto(struct sock *sk,
 static inline void sk_psock_restore_proto(struct sock *sk,
 					  struct sk_psock *psock)
 {
-	sk->sk_prot->unhash = psock->saved_unhash;
 	if (inet_csk_has_ulp(sk)) {
+		/* TLS does not have an unhash proto in SW cases, but we need
+		 * to ensure we stop using the sock_map unhash routine because
+		 * the associated psock is being removed. So use the original
+		 * unhash handler.
+		 */
+		WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash);
 		tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space);
 	} else {
 		sk->sk_write_space = psock->saved_write_space;

From 144748eb0c445091466c9b741ebd0bfcc5914f3d Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 1 Apr 2021 15:00:40 -0700
Subject: [PATCH 1604/1820] bpf, sockmap: Fix incorrect fwd_alloc accounting

Incorrect accounting fwd_alloc can result in a warning when the socket
is torn down,

 [18455.319240] WARNING: CPU: 0 PID: 24075 at net/core/stream.c:208 sk_stream_kill_queues+0x21f/0x230
 [...]
 [18455.319543] Call Trace:
 [18455.319556]  inet_csk_destroy_sock+0xba/0x1f0
 [18455.319577]  tcp_rcv_state_process+0x1b4e/0x2380
 [18455.319593]  ? lock_downgrade+0x3a0/0x3a0
 [18455.319617]  ? tcp_finish_connect+0x1e0/0x1e0
 [18455.319631]  ? sk_reset_timer+0x15/0x70
 [18455.319646]  ? tcp_schedule_loss_probe+0x1b2/0x240
 [18455.319663]  ? lock_release+0xb2/0x3f0
 [18455.319676]  ? __release_sock+0x8a/0x1b0
 [18455.319690]  ? lock_downgrade+0x3a0/0x3a0
 [18455.319704]  ? lock_release+0x3f0/0x3f0
 [18455.319717]  ? __tcp_close+0x2c6/0x790
 [18455.319736]  ? tcp_v4_do_rcv+0x168/0x370
 [18455.319750]  tcp_v4_do_rcv+0x168/0x370
 [18455.319767]  __release_sock+0xbc/0x1b0
 [18455.319785]  __tcp_close+0x2ee/0x790
 [18455.319805]  tcp_close+0x20/0x80

This currently happens because on redirect case we do skb_set_owner_r()
with the original sock. This increments the fwd_alloc memory accounting
on the original sock. Then on redirect we may push this into the queue
of the psock we are redirecting to. When the skb is flushed from the
queue we give the memory back to the original sock. The problem is if
the original sock is destroyed/closed with skbs on another psocks queue
then the original sock will not have a way to reclaim the memory before
being destroyed. Then above warning will be thrown

  sockA                          sockB

  sk_psock_strp_read()
   sk_psock_verdict_apply()
     -- SK_REDIRECT --
     sk_psock_skb_redirect()
                                skb_queue_tail(psock_other->ingress_skb..)

  sk_close()
   sock_map_unref()
     sk_psock_put()
       sk_psock_drop()
         sk_psock_zap_ingress()

At this point we have torn down our own psock, but have the outstanding
skb in psock_other. Note that SK_PASS doesn't have this problem because
the sk_psock_drop() logic releases the skb, its still associated with
our psock.

To resolve lets only account for sockets on the ingress queue that are
still associated with the current socket. On the redirect case we will
check memory limits per 6fa9201a89898, but will omit fwd_alloc accounting
until skb is actually enqueued. When the skb is sent via skb_send_sock_locked
or received with sk_psock_skb_ingress memory will be claimed on psock_other.

Fixes: 6fa9201a89898 ("bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self")
Reported-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/161731444013.68884.4021114312848535993.stgit@john-XPS-13-9370
---
 net/core/skmsg.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 1261512d6807..5def3a2e85be 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -488,6 +488,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 	if (unlikely(!msg))
 		return -EAGAIN;
 	sk_msg_init(msg);
+	skb_set_owner_r(skb, sk);
 	return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
 }
 
@@ -790,7 +791,6 @@ static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int
 {
 	switch (verdict) {
 	case __SK_REDIRECT:
-		skb_set_owner_r(skb, sk);
 		sk_psock_skb_redirect(skb);
 		break;
 	case __SK_PASS:
@@ -808,10 +808,6 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
 	rcu_read_lock();
 	prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
-		/* We skip full set_owner_r here because if we do a SK_PASS
-		 * or SK_DROP we can skip skb memory accounting and use the
-		 * TLS context.
-		 */
 		skb->sk = psock->sk;
 		tcp_skb_bpf_redirect_clear(skb);
 		ret = sk_psock_bpf_run(psock, prog, skb);
@@ -880,12 +876,13 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 		kfree_skb(skb);
 		goto out;
 	}
-	skb_set_owner_r(skb, sk);
 	prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
+		skb->sk = sk;
 		tcp_skb_bpf_redirect_clear(skb);
 		ret = sk_psock_bpf_run(psock, prog, skb);
 		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+		skb->sk = NULL;
 	}
 	sk_psock_verdict_apply(psock, skb, ret);
 out:
@@ -956,12 +953,13 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
 		kfree_skb(skb);
 		goto out;
 	}
-	skb_set_owner_r(skb, sk);
 	prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
+		skb->sk = sk;
 		tcp_skb_bpf_redirect_clear(skb);
 		ret = sk_psock_bpf_run(psock, prog, skb);
 		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+		skb->sk = NULL;
 	}
 	sk_psock_verdict_apply(psock, skb, ret);
 out:

From 66c3f05ddc538ee796321210c906b6ae6fc0792a Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Mon, 5 Apr 2021 21:29:22 -0700
Subject: [PATCH 1605/1820] pcnet32: Use pci_resource_len to validate PCI
 resource

pci_resource_start() is not a good indicator to determine if a PCI
resource exists or not, since the resource may start at address 0.
This is seen when trying to instantiate the driver in qemu for riscv32
or riscv64.

pci 0000:00:01.0: reg 0x10: [io  0x0000-0x001f]
pci 0000:00:01.0: reg 0x14: [mem 0x00000000-0x0000001f]
...
pcnet32: card has no PCI IO resources, aborting

Use pci_resouce_len() instead.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/pcnet32.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index 187b0b9a6e1d..f78daba60b35 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1534,8 +1534,7 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	pci_set_master(pdev);
 
-	ioaddr = pci_resource_start(pdev, 0);
-	if (!ioaddr) {
+	if (!pci_resource_len(pdev, 0)) {
 		if (pcnet32_debug & NETIF_MSG_PROBE)
 			pr_err("card has no PCI IO resources, aborting\n");
 		err = -ENODEV;
@@ -1548,6 +1547,8 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent)
 			pr_err("architecture does not support 32bit PCI busmaster DMA\n");
 		goto err_disable_dev;
 	}
+
+	ioaddr = pci_resource_start(pdev, 0);
 	if (!request_region(ioaddr, PCNET32_TOTAL_SIZE, "pcnet32_probe_pci")) {
 		if (pcnet32_debug & NETIF_MSG_PROBE)
 			pr_err("io address range already allocated\n");

From ed7bedd2c3ca040f1e8ea02c6590a93116b1ec78 Mon Sep 17 00:00:00 2001
From: Guangbin Huang <huangguangbin2@huawei.com>
Date: Tue, 6 Apr 2021 21:10:43 +0800
Subject: [PATCH 1606/1820] net: hns3: clear VF down state bit before request
 link status

Currently, the VF down state bit is cleared after VF sending
link status request command. There is problem that when VF gets
link status replied from PF, the down state bit may still set
as 1. In this case, the link status replied from PF will be
ignored and always set VF link status to down.

To fix this problem, clear VF down state bit before VF requests
link status.

Fixes: e2cb1dec9779 ("net: hns3: Add HNS3 VF HCL(Hardware Compatibility Layer) Support")
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 700e068764c8..14b83eca0a5e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2624,14 +2624,14 @@ static int hclgevf_ae_start(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 
+	clear_bit(HCLGEVF_STATE_DOWN, &hdev->state);
+
 	hclgevf_reset_tqp_stats(handle);
 
 	hclgevf_request_link_info(hdev);
 
 	hclgevf_update_link_mode(hdev);
 
-	clear_bit(HCLGEVF_STATE_DOWN, &hdev->state);
-
 	return 0;
 }
 

From 63cf32389925e234d166fb1a336b46de7f846003 Mon Sep 17 00:00:00 2001
From: Wong Vee Khee <vee.khee.wong@linux.intel.com>
Date: Tue, 6 Apr 2021 21:17:30 +0800
Subject: [PATCH 1607/1820] ethtool: fix incorrect datatype in set_eee ops

The member 'tx_lpi_timer' is defined with __u32 datatype in the ethtool
header file. Hence, we should use ethnl_update_u32() in set_eee ops.

Fixes: fd77be7bd43c ("ethtool: set EEE settings with EEE_SET request")
Cc: <stable@vger.kernel.org> # 5.10.x
Cc: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Wong Vee Khee <vee.khee.wong@linux.intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/eee.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c
index 901b7de941ab..e10bfcc07853 100644
--- a/net/ethtool/eee.c
+++ b/net/ethtool/eee.c
@@ -169,8 +169,8 @@ int ethnl_set_eee(struct sk_buff *skb, struct genl_info *info)
 	ethnl_update_bool32(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod);
 	ethnl_update_bool32(&eee.tx_lpi_enabled,
 			    tb[ETHTOOL_A_EEE_TX_LPI_ENABLED], &mod);
-	ethnl_update_bool32(&eee.tx_lpi_timer, tb[ETHTOOL_A_EEE_TX_LPI_TIMER],
-			    &mod);
+	ethnl_update_u32(&eee.tx_lpi_timer, tb[ETHTOOL_A_EEE_TX_LPI_TIMER],
+			 &mod);
 	ret = 0;
 	if (!mod)
 		goto out_ops;

From cca8ea3b05c972ffb5295367e6c544369b45fbdd Mon Sep 17 00:00:00 2001
From: Phillip Potter <phil@philpotter.co.uk>
Date: Tue, 6 Apr 2021 18:45:54 +0100
Subject: [PATCH 1608/1820] net: tun: set tun->dev->addr_len during TUNSETLINK
 processing

When changing type with TUNSETLINK ioctl command, set tun->dev->addr_len
to match the appropriate type, using new tun_get_addr_len utility function
which returns appropriate address length for given type. Fixes a
KMSAN-found uninit-value bug reported by syzbot at:
https://syzkaller.appspot.com/bug?id=0766d38c656abeace60621896d705743aeefed51

Reported-by: syzbot+001516d86dbe88862cec@syzkaller.appspotmail.com
Diagnosed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Phillip Potter <phil@philpotter.co.uk>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index fc86da7f1628..4cf38be26dc9 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -69,6 +69,14 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/mutex.h>
+#include <linux/ieee802154.h>
+#include <linux/if_ltalk.h>
+#include <uapi/linux/if_fddi.h>
+#include <uapi/linux/if_hippi.h>
+#include <uapi/linux/if_fc.h>
+#include <net/ax25.h>
+#include <net/rose.h>
+#include <net/6lowpan.h>
 
 #include <linux/uaccess.h>
 #include <linux/proc_fs.h>
@@ -2919,6 +2927,45 @@ static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p,
 	return __tun_set_ebpf(tun, prog_p, prog);
 }
 
+/* Return correct value for tun->dev->addr_len based on tun->dev->type. */
+static unsigned char tun_get_addr_len(unsigned short type)
+{
+	switch (type) {
+	case ARPHRD_IP6GRE:
+	case ARPHRD_TUNNEL6:
+		return sizeof(struct in6_addr);
+	case ARPHRD_IPGRE:
+	case ARPHRD_TUNNEL:
+	case ARPHRD_SIT:
+		return 4;
+	case ARPHRD_ETHER:
+		return ETH_ALEN;
+	case ARPHRD_IEEE802154:
+	case ARPHRD_IEEE802154_MONITOR:
+		return IEEE802154_EXTENDED_ADDR_LEN;
+	case ARPHRD_PHONET_PIPE:
+	case ARPHRD_PPP:
+	case ARPHRD_NONE:
+		return 0;
+	case ARPHRD_6LOWPAN:
+		return EUI64_ADDR_LEN;
+	case ARPHRD_FDDI:
+		return FDDI_K_ALEN;
+	case ARPHRD_HIPPI:
+		return HIPPI_ALEN;
+	case ARPHRD_IEEE802:
+		return FC_ALEN;
+	case ARPHRD_ROSE:
+		return ROSE_ADDR_LEN;
+	case ARPHRD_NETROM:
+		return AX25_ADDR_LEN;
+	case ARPHRD_LOCALTLK:
+		return LTALK_ALEN;
+	default:
+		return 0;
+	}
+}
+
 static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			    unsigned long arg, int ifreq_len)
 {
@@ -3082,6 +3129,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 				break;
 			}
 			tun->dev->type = (int) arg;
+			tun->dev->addr_len = tun_get_addr_len(tun->dev->type);
 			netif_info(tun, drv, tun->dev, "linktype set to %d\n",
 				   tun->dev->type);
 			call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE,

From 5219d6012d46ec1fa3397e50bfeb7b8c16df72cf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 Apr 2021 15:58:15 -0700
Subject: [PATCH 1609/1820] docs: ethtool: fix some copy-paste errors

Fix incorrect documentation. Mostly referring to other objects,
likely because the text was copied and not adjusted.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ethtool-netlink.rst | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 05073482db05..dc03ff884541 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -976,9 +976,9 @@ constraints on coalescing parameters and their values.
 
 
 PAUSE_GET
-============
+=========
 
-Gets channel counts like ``ETHTOOL_GPAUSE`` ioctl request.
+Gets pause frame settings like ``ETHTOOL_GPAUSEPARAM`` ioctl request.
 
 Request contents:
 
@@ -1007,7 +1007,7 @@ the statistics in the following structure:
 Each member has a corresponding attribute defined.
 
 PAUSE_SET
-============
+=========
 
 Sets pause parameters like ``ETHTOOL_GPAUSEPARAM`` ioctl request.
 
@@ -1024,7 +1024,7 @@ Request contents:
 EEE_GET
 =======
 
-Gets channel counts like ``ETHTOOL_GEEE`` ioctl request.
+Gets Energy Efficient Ethernet settings like ``ETHTOOL_GEEE`` ioctl request.
 
 Request contents:
 
@@ -1054,7 +1054,7 @@ first 32 are provided by the ``ethtool_ops`` callback.
 EEE_SET
 =======
 
-Sets pause parameters like ``ETHTOOL_GEEEPARAM`` ioctl request.
+Sets Energy Efficient Ethernet parameters like ``ETHTOOL_SEEE`` ioctl request.
 
 Request contents:
 

From 4f0ed93fb92d3528c73c80317509df3f800a222b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 6 Apr 2021 19:46:51 -0400
Subject: [PATCH 1610/1820] LOOKUP_MOUNTPOINT: we are cleaning "jumped" flag
 too late

That (and traversals in case of umount .) should be done before
complete_walk().  Either a braino or mismerge damage on queue
reorders - either way, I should've spotted that much earlier.

Fucked-up-by: Al Viro <viro@zeniv.linux.org.uk>
X-Paperbag: Brown
Fixes: 161aff1d93ab "LOOKUP_MOUNTPOINT: fold path_mountpointat() into path_lookupat()"
Cc: stable@vger.kernel.org # v5.7+
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index fc8760d4314e..48a2f288e802 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2421,16 +2421,16 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 	while (!(err = link_path_walk(s, nd)) &&
 	       (s = lookup_last(nd)) != NULL)
 		;
+	if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
+		err = handle_lookup_down(nd);
+		nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please...
+	}
 	if (!err)
 		err = complete_walk(nd);
 
 	if (!err && nd->flags & LOOKUP_DIRECTORY)
 		if (!d_can_lookup(nd->path.dentry))
 			err = -ENOTDIR;
-	if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
-		err = handle_lookup_down(nd);
-		nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please...
-	}
 	if (!err) {
 		*path = nd->path;
 		nd->path.mnt = NULL;

From 1a73704c82ed4ee95532ac04645d02075bd1ce3d Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Wed, 24 Mar 2021 09:46:09 +0200
Subject: [PATCH 1611/1820] net/mlx5: Fix HW spec violation configuring uplink

Make sure to modify uplink port to follow only if the uplink_follow
capability is set as required by the HW spec. Failure to do so causes
traffic to the uplink representor net device to cease after switching to
switchdev mode.

Fixes: 7d0314b11cdd ("net/mlx5e: Modify uplink state on interface up/down")
Signed-off-by: Eli Cohen <elic@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index a132fff7a980..8d39bfee84a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1107,8 +1107,9 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 
 	mlx5e_rep_tc_enable(priv);
 
-	mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK,
-				      0, 0, MLX5_VPORT_ADMIN_STATE_AUTO);
+	if (MLX5_CAP_GEN(mdev, uplink_follow))
+		mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK,
+					      0, 0, MLX5_VPORT_ADMIN_STATE_AUTO);
 	mlx5_lag_add(mdev, netdev);
 	priv->events_nb.notifier_call = uplink_rep_async_event;
 	mlx5_notifier_register(mdev, &priv->events_nb);

From a14587dfc5ad2312dabdd42a610d80ecd0dc8bea Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@nvidia.com>
Date: Thu, 21 Jan 2021 16:01:37 +0200
Subject: [PATCH 1612/1820] net/mlx5: Fix placement of log_max_flow_counter

The cited commit wrongly placed log_max_flow_counter field of
mlx5_ifc_flow_table_prop_layout_bits, align it to the HW spec intended
placement.

Fixes: 16f1c5bb3ed7 ("net/mlx5: Check device capability for maximum flow counters")
Signed-off-by: Raed Salem <raeds@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index df5d91c8b2d4..1ccedb7816d0 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -437,11 +437,11 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         reserved_at_60[0x18];
 	u8         log_max_ft_num[0x8];
 
-	u8         reserved_at_80[0x18];
+	u8         reserved_at_80[0x10];
+	u8         log_max_flow_counter[0x8];
 	u8         log_max_destination[0x8];
 
-	u8         log_max_flow_counter[0x8];
-	u8         reserved_at_a8[0x10];
+	u8         reserved_at_a0[0x18];
 	u8         log_max_flow[0x8];
 
 	u8         reserved_at_c0[0x40];

From ce28f0fd670ddffcd564ce7119bdefbaf08f02d3 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Sun, 4 Apr 2021 10:50:50 +0300
Subject: [PATCH 1613/1820] net/mlx5: Fix PPLM register mapping

Add reserved mapping to cover all the register in order to avoid
setting arbitrary values to newer FW which implements the reserved
fields.

Fixes: a58837f52d43 ("net/mlx5e: Expose FEC feilds and related capability bit")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 1ccedb7816d0..9940070cda8f 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -8835,6 +8835,8 @@ struct mlx5_ifc_pplm_reg_bits {
 
 	u8         fec_override_admin_100g_2x[0x10];
 	u8         fec_override_admin_50g_1x[0x10];
+
+	u8         reserved_at_140[0x140];
 };
 
 struct mlx5_ifc_ppcnt_reg_bits {

From 534b1204ca4694db1093b15cf3e79a99fcb6a6da Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Sun, 4 Apr 2021 12:55:00 +0300
Subject: [PATCH 1614/1820] net/mlx5: Fix PBMC register mapping

Add reserved mapping to cover all the register in order to avoid setting
arbitrary values to newer FW which implements the reserved fields.

Fixes: 50b4a3c23646 ("net/mlx5: PPTB and PBMC register firmware command support")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 9940070cda8f..9c68b2da14c6 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10200,7 +10200,7 @@ struct mlx5_ifc_pbmc_reg_bits {
 
 	struct mlx5_ifc_bufferx_reg_bits buffer[10];
 
-	u8         reserved_at_2e0[0x40];
+	u8         reserved_at_2e0[0x80];
 };
 
 struct mlx5_ifc_qtct_reg_bits {

From d5f9b005c3062d6d96872896b695e5116b921f52 Mon Sep 17 00:00:00 2001
From: Xiaoming Ni <nixiaoming@huawei.com>
Date: Mon, 5 Apr 2021 10:53:39 +0800
Subject: [PATCH 1615/1820] net/mlx5: fix kfree mismatch in indir_table.c

Memory allocated by kvzalloc() should be freed by kvfree().

Fixes: 34ca65352ddf2 ("net/mlx5: E-Switch, Indirect table infrastructur")
Signed-off-by: Xiaoming Ni <nixiaoming@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/esw/indir_table.c  | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c
index 6f6772bf61a2..3da7becc1069 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c
@@ -248,7 +248,7 @@ err_mod_hdr_regc0:
 err_ethertype:
 	kfree(rule);
 out:
-	kfree(rule_spec);
+	kvfree(rule_spec);
 	return err;
 }
 
@@ -328,7 +328,7 @@ static int mlx5_create_indir_recirc_group(struct mlx5_eswitch *esw,
 	e->recirc_cnt = 0;
 
 out:
-	kfree(in);
+	kvfree(in);
 	return err;
 }
 
@@ -347,7 +347,7 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw,
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec) {
-		kfree(in);
+		kvfree(in);
 		return -ENOMEM;
 	}
 
@@ -371,8 +371,8 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw,
 	}
 
 err_out:
-	kfree(spec);
-	kfree(in);
+	kvfree(spec);
+	kvfree(in);
 	return err;
 }
 

From 168632a495f49f33a18c2d502fc249d7610375e9 Mon Sep 17 00:00:00 2001
From: Jonas Holmberg <jonashg@axis.com>
Date: Wed, 7 Apr 2021 09:54:28 +0200
Subject: [PATCH 1616/1820] ALSA: aloop: Fix initialization of controls

Add a control to the card before copying the id so that the numid field
is initialized in the copy. Otherwise the numid field of active_id,
format_id, rate_id and channels_id will be the same (0) and
snd_ctl_notify() will not queue the events properly.

Signed-off-by: Jonas Holmberg <jonashg@axis.com>
Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210407075428.2666787-1-jonashg@axis.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/drivers/aloop.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c
index 8a24e5ae7cef..ef0cdfddfd3f 100644
--- a/sound/drivers/aloop.c
+++ b/sound/drivers/aloop.c
@@ -1572,6 +1572,14 @@ static int loopback_mixer_new(struct loopback *loopback, int notify)
 					return -ENOMEM;
 				kctl->id.device = dev;
 				kctl->id.subdevice = substr;
+
+				/* Add the control before copying the id so that
+				 * the numid field of the id is set in the copy.
+				 */
+				err = snd_ctl_add(card, kctl);
+				if (err < 0)
+					return err;
+
 				switch (idx) {
 				case ACTIVE_IDX:
 					setup->active_id = kctl->id;
@@ -1588,9 +1596,6 @@ static int loopback_mixer_new(struct loopback *loopback, int notify)
 				default:
 					break;
 				}
-				err = snd_ctl_add(card, kctl);
-				if (err < 0)
-					return err;
 			}
 		}
 	}

From 3a62583c2853b0ab37a57dde79decea210b5fb89 Mon Sep 17 00:00:00 2001
From: William Roche <william.roche@oracle.com>
Date: Tue, 6 Apr 2021 11:28:59 -0400
Subject: [PATCH 1617/1820] RAS/CEC: Correct ce_add_elem()'s returned values

ce_add_elem() uses different return values to signal a result from
adding an element to the collector. Commit in Fixes: broke the case
where the element being added is not found in the array. Correct that.

 [ bp: Rewrite commit message, add kernel-doc comments. ]

Fixes: de0e0624d86f ("RAS/CEC: Check count_threshold unconditionally")
Signed-off-by: William Roche <william.roche@oracle.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/1617722939-29670-1-git-send-email-william.roche@oracle.com
---
 drivers/ras/cec.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
index ddecf25b5dd4..d7894f178bd4 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -309,11 +309,20 @@ static bool sanity_check(struct ce_array *ca)
 	return ret;
 }
 
+/**
+ * cec_add_elem - Add an element to the CEC array.
+ * @pfn:	page frame number to insert
+ *
+ * Return values:
+ * - <0:	on error
+ * -  0:	on success
+ * - >0:	when the inserted pfn was offlined
+ */
 static int cec_add_elem(u64 pfn)
 {
 	struct ce_array *ca = &ce_arr;
+	int count, err, ret = 0;
 	unsigned int to = 0;
-	int count, ret = 0;
 
 	/*
 	 * We can be called very early on the identify_cpu() path where we are
@@ -330,8 +339,8 @@ static int cec_add_elem(u64 pfn)
 	if (ca->n == MAX_ELEMS)
 		WARN_ON(!del_lru_elem_unlocked(ca));
 
-	ret = find_elem(ca, pfn, &to);
-	if (ret < 0) {
+	err = find_elem(ca, pfn, &to);
+	if (err < 0) {
 		/*
 		 * Shift range [to-end] to make room for one more element.
 		 */

From fbb9e86636ba8aa4d890091ab06cc7b2f4751322 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 4 Jan 2021 16:19:17 +0800
Subject: [PATCH 1618/1820] arm64: dts: allwinner: h6: Switch to macros for RSB
 clock/reset indices

The macros for the clock and reset indices for the RSB hardware block
were replaced with raw numbers when the RSB controller node was added.
This was done to avoid cross-tree dependencies.

Now that both the clk and DT changes have been merged, we can switch
back to using the macros.

Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
---
 arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
index 49e979794094..af8b7d0ef750 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
@@ -995,9 +995,9 @@
 			compatible = "allwinner,sun8i-a23-rsb";
 			reg = <0x07083000 0x400>;
 			interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&r_ccu 13>;
+			clocks = <&r_ccu CLK_R_APB2_RSB>;
 			clock-frequency = <3000000>;
-			resets = <&r_ccu 7>;
+			resets = <&r_ccu RST_R_APB2_RSB>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&r_rsb_pins>;
 			status = "disabled";

From 3dd4ce4185df6798dcdcc3669bddb35899d7d5e1 Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@arm.com>
Date: Tue, 16 Mar 2021 14:42:19 +0000
Subject: [PATCH 1619/1820] arm64: dts: allwinner: Fix SD card CD GPIO for
 SOPine systems

Commit 941432d00768 ("arm64: dts: allwinner: Drop non-removable from
SoPine/LTS SD card") enabled the card detect GPIO for the SOPine module,
along the way with the Pine64-LTS, which share the same base .dtsi.

However while both boards indeed have a working CD GPIO on PF6, the
polarity is different: the SOPine modules uses a "push-pull" socket,
which has an active-high switch, while the Pine64-LTS use the more
traditional push-push socket and the common active-low switch.

Fix the polarity in the sopine.dtsi, and overwrite it in the LTS
board .dts, to make the SD card work again on systems using SOPine
modules.

Fixes: 941432d00768 ("arm64: dts: allwinner: Drop non-removable from SoPine/LTS SD card")
Reported-by: Ashley <contact@victorianfox.com>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Link: https://lore.kernel.org/r/20210316144219.5973-1-andre.przywara@arm.com
---
 arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-lts.dts | 4 ++++
 arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi    | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-lts.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-lts.dts
index 437ffe3628a5..e79ce49e7e6a 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-lts.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-lts.dts
@@ -19,3 +19,7 @@
 		};
 	};
 };
+
+&mmc0 {
+	cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 push-push switch */
+};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi
index 3402cec87035..df62044ff7a7 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi
@@ -34,7 +34,7 @@
 	vmmc-supply = <&reg_dcdc1>;
 	disable-wp;
 	bus-width = <4>;
-	cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 */
+	cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>; /* PF6 push-pull switch */
 	status = "okay";
 };
 

From c89f3af3b5ba4d8b232c7b397e54dd228c49f6b1 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime@cerno.tech>
Date: Wed, 31 Mar 2021 15:08:29 +0200
Subject: [PATCH 1620/1820] MAINTAINERS: Add our new mailing-list

We've been struggling to get an LF-hosted mailing list for a while, but
now that lists.linux.dev is there we opted in.

Let's add it to MAINTAINERS.

Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Acked-by: Chen-Yu Tsai <wens@csie.org>
Acked-by: Jernej Skrabec <jernej.skrabec@siol.net>
Link: https://lore.kernel.org/r/20210331130830.64182-1-maxime@cerno.tech
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index d92f85ca831d..d8c00df4045c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1576,6 +1576,7 @@ R:	Jernej Skrabec <jernej.skrabec@siol.net>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git
+L:	linux-sunxi@lists.linux.dev
 F:	arch/arm/mach-sunxi/
 F:	arch/arm64/boot/dts/allwinner/
 F:	drivers/clk/sunxi-ng/

From 2a996ecd142df9ff2369241fd62ab7778ef07874 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime@cerno.tech>
Date: Wed, 31 Mar 2021 15:08:30 +0200
Subject: [PATCH 1621/1820] MAINTAINERS: Match on allwinner keyword

Some drivers (phy, crypto, net) folders don't have sunxi in it but
allwinner. Add that keyword to match on it too.

Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Acked-by: Chen-Yu Tsai <wens@csie.org>
Acked-by: Jernej Skrabec <jernej.skrabec@siol.net>
Link: https://lore.kernel.org/r/20210331130830.64182-2-maxime@cerno.tech
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index d8c00df4045c..5e808daae799 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1582,6 +1582,7 @@ F:	arch/arm64/boot/dts/allwinner/
 F:	drivers/clk/sunxi-ng/
 F:	drivers/pinctrl/sunxi/
 F:	drivers/soc/sunxi/
+N:	allwinner
 N:	sun[x456789]i
 N:	sun50i
 

From 7a2f6e69e9c1060a7a09c1f8322ccb8d942b3078 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 30 Mar 2021 20:42:18 +0200
Subject: [PATCH 1622/1820] arm64: dts: allwinner: h6: beelink-gs1: Remove ext.
 32 kHz osc reference
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Although every Beelink GS1 seems to have external 32768 Hz oscillator,
it works only on one from four tested. There are more reports of RTC
issues elsewhere, like Armbian forum.

One Beelink GS1 owner read RTC osc status register on Android which
shipped with the box. Reported value indicated problems with external
oscillator.

In order to fix RTC and related issues (HDMI-CEC and suspend/resume with
Crust) on all boards, switch to internal oscillator.

Fixes: 32507b868119 ("arm64: dts: allwinner: h6: Move ext. oscillator to board DTs")
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Tested-by: Clément Péron <peron.clem@gmail.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Link: https://lore.kernel.org/r/20210330184218.279738-1-jernej.skrabec@siol.net
---
 arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
index 4f4755152fce..b5808047d6e4 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
@@ -289,10 +289,6 @@
 	vcc-pm-supply = <&reg_aldo1>;
 };
 
-&rtc {
-	clocks = <&ext_osc32k>;
-};
-
 &spdif {
 	status = "okay";
 };

From ad31a8c05196a3dc5283b193e9c74a72022d3c65 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 5 Apr 2021 22:32:27 +0200
Subject: [PATCH 1623/1820] s390/setup: use memblock_free_late() to free old
 stack

Use memblock_free_late() to free the old machine check stack to the
buddy allocator instead of leaking it.

Fixes: b61b1595124a ("s390: add stack for machine check handler")
Cc: Vasily Gorbik <gor@linux.ibm.com>
Acked-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 60da976eee6f..72134f9f6ff5 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -354,7 +354,7 @@ static int __init stack_realloc(void)
 	if (!new)
 		panic("Couldn't allocate machine check stack");
 	WRITE_ONCE(S390_lowcore.mcck_stack, new + STACK_INIT_OFFSET);
-	memblock_free(old, THREAD_SIZE);
+	memblock_free_late(old, THREAD_SIZE);
 	return 0;
 }
 early_initcall(stack_realloc);

From d120198bd5ff1d41808b6914e1eb89aff937415c Mon Sep 17 00:00:00 2001
From: Luca Fancellu <luca.fancellu@arm.com>
Date: Tue, 6 Apr 2021 11:51:04 +0100
Subject: [PATCH 1624/1820] xen/evtchn: Change irq_info lock to raw_spinlock_t

Unmask operation must be called with interrupt disabled,
on preempt_rt spin_lock_irqsave/spin_unlock_irqrestore
don't disable/enable interrupts, so use raw_* implementation
and change lock variable in struct irq_info from spinlock_t
to raw_spinlock_t

Cc: stable@vger.kernel.org
Fixes: 25da4618af24 ("xen/events: don't unmask an event channel when an eoi is pending")
Signed-off-by: Luca Fancellu <luca.fancellu@arm.com>
Reviewed-by: Julien Grall <jgrall@amazon.com>
Reviewed-by: Wei Liu <wei.liu@kernel.org>
Link: https://lore.kernel.org/r/20210406105105.10141-1-luca.fancellu@arm.com
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/events/events_base.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 8236e2364eeb..7bbfd58958bc 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -110,7 +110,7 @@ struct irq_info {
 	unsigned short eoi_cpu; /* EOI must happen on this cpu-1 */
 	unsigned int irq_epoch; /* If eoi_cpu valid: irq_epoch of event */
 	u64 eoi_time;           /* Time in jiffies when to EOI. */
-	spinlock_t lock;
+	raw_spinlock_t lock;
 
 	union {
 		unsigned short virq;
@@ -312,7 +312,7 @@ static int xen_irq_info_common_setup(struct irq_info *info,
 	info->evtchn = evtchn;
 	info->cpu = cpu;
 	info->mask_reason = EVT_MASK_REASON_EXPLICIT;
-	spin_lock_init(&info->lock);
+	raw_spin_lock_init(&info->lock);
 
 	ret = set_evtchn_to_irq(evtchn, irq);
 	if (ret < 0)
@@ -472,28 +472,28 @@ static void do_mask(struct irq_info *info, u8 reason)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&info->lock, flags);
+	raw_spin_lock_irqsave(&info->lock, flags);
 
 	if (!info->mask_reason)
 		mask_evtchn(info->evtchn);
 
 	info->mask_reason |= reason;
 
-	spin_unlock_irqrestore(&info->lock, flags);
+	raw_spin_unlock_irqrestore(&info->lock, flags);
 }
 
 static void do_unmask(struct irq_info *info, u8 reason)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&info->lock, flags);
+	raw_spin_lock_irqsave(&info->lock, flags);
 
 	info->mask_reason &= ~reason;
 
 	if (!info->mask_reason)
 		unmask_evtchn(info->evtchn);
 
-	spin_unlock_irqrestore(&info->lock, flags);
+	raw_spin_unlock_irqrestore(&info->lock, flags);
 }
 
 #ifdef CONFIG_X86

From fa26d0c778b432d3d9814ea82552e813b33eeb5c Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 6 Apr 2021 17:56:40 +0200
Subject: [PATCH 1625/1820] ACPI: processor: Fix build when
 CONFIG_ACPI_PROCESSOR=m

Commit 8cdddd182bd7 ("ACPI: processor: Fix CPU0 wakeup in
acpi_idle_play_dead()") tried to fix CPU0 hotplug breakage by copying
wakeup_cpu0() + start_cpu0() logic from hlt_play_dead()//mwait_play_dead()
into acpi_idle_play_dead(). The problem is that these functions are not
exported to modules so when CONFIG_ACPI_PROCESSOR=m build fails.

The issue could've been fixed by exporting both wakeup_cpu0()/start_cpu0()
(the later from assembly) but it seems putting the whole pattern into a
new function and exporting it instead is better.

Reported-by: kernel test robot <lkp@intel.com>
Fixes: 8cdddd182bd7 ("CPI: processor: Fix CPU0 wakeup in acpi_idle_play_dead()")
Cc: <stable@vger.kernel.org> # 5.10+
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/include/asm/smp.h    |  2 +-
 arch/x86/kernel/smpboot.c     | 26 ++++++++++++--------------
 drivers/acpi/processor_idle.c |  4 +---
 3 files changed, 14 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 57ef2094af93..630ff08532be 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -132,7 +132,7 @@ void native_play_dead(void);
 void play_dead_common(void);
 void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
-bool wakeup_cpu0(void);
+void cond_wakeup_cpu0(void);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f877150a91da..16703c35a944 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1659,13 +1659,17 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
-bool wakeup_cpu0(void)
+/**
+ * cond_wakeup_cpu0 - Wake up CPU0 if needed.
+ *
+ * If NMI wants to wake up CPU0, start CPU0.
+ */
+void cond_wakeup_cpu0(void)
 {
 	if (smp_processor_id() == 0 && enable_start_cpu0)
-		return true;
-
-	return false;
+		start_cpu0();
 }
+EXPORT_SYMBOL_GPL(cond_wakeup_cpu0);
 
 /*
  * We need to flush the caches before going to sleep, lest we have
@@ -1734,11 +1738,8 @@ static inline void mwait_play_dead(void)
 		__monitor(mwait_ptr, 0, 0);
 		mb();
 		__mwait(eax, 0);
-		/*
-		 * If NMI wants to wake up CPU0, start CPU0.
-		 */
-		if (wakeup_cpu0())
-			start_cpu0();
+
+		cond_wakeup_cpu0();
 	}
 }
 
@@ -1749,11 +1750,8 @@ void hlt_play_dead(void)
 
 	while (1) {
 		native_halt();
-		/*
-		 * If NMI wants to wake up CPU0, start CPU0.
-		 */
-		if (wakeup_cpu0())
-			start_cpu0();
+
+		cond_wakeup_cpu0();
 	}
 }
 
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 768a6b4d2368..4e2d76b8b697 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -544,9 +544,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 			return -ENODEV;
 
 #if defined(CONFIG_X86) && defined(CONFIG_HOTPLUG_CPU)
-		/* If NMI wants to wake up CPU0, start CPU0. */
-		if (wakeup_cpu0())
-			start_cpu0();
+		cond_wakeup_cpu0();
 #endif
 	}
 

From 649cab56de8eb2952498de9b752761ca980cb88a Mon Sep 17 00:00:00 2001
From: Frank Rowand <frank.rowand@sony.com>
Date: Sun, 4 Apr 2021 22:28:45 -0500
Subject: [PATCH 1626/1820] of: properly check for error returned by
 fdt_get_name()

fdt_get_name() returns error values via a parameter pointer
instead of in function return.  Fix check for this error value
in populate_node() and callers of populate_node().

Chasing up the caller tree showed callers of various functions
failing to initialize the value of pointer parameters that
can return error values.  Initialize those values to NULL.

The bug was introduced by
commit e6a6928c3ea1 ("of/fdt: Convert FDT functions to use libfdt")
but this patch can not be backported directly to that commit
because the relevant code has further been restructured by
commit dfbd4c6eff35 ("drivers/of: Split unflatten_dt_node()")

The bug became visible by triggering a crash on openrisc with:
commit 79edff12060f ("scripts/dtc: Update to upstream version v1.6.0-51-g183df9e9c2b9")
as reported in:
https://lore.kernel.org/lkml/20210327224116.69309-1-linux@roeck-us.net/

Fixes: 79edff12060f ("scripts/dtc: Update to upstream version v1.6.0-51-g183df9e9c2b9")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Frank Rowand <frank.rowand@sony.com>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20210405032845.1942533-1-frowand.list@gmail.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/fdt.c      | 36 +++++++++++++++++++++++-------------
 drivers/of/overlay.c  |  2 +-
 drivers/of/unittest.c | 15 ++++++++++-----
 3 files changed, 34 insertions(+), 19 deletions(-)

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index dcc1dd96911a..adb26aff481d 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -205,7 +205,7 @@ static void populate_properties(const void *blob,
 		*pprev = NULL;
 }
 
-static bool populate_node(const void *blob,
+static int populate_node(const void *blob,
 			  int offset,
 			  void **mem,
 			  struct device_node *dad,
@@ -214,24 +214,24 @@ static bool populate_node(const void *blob,
 {
 	struct device_node *np;
 	const char *pathp;
-	unsigned int l, allocl;
+	int len;
 
-	pathp = fdt_get_name(blob, offset, &l);
+	pathp = fdt_get_name(blob, offset, &len);
 	if (!pathp) {
 		*pnp = NULL;
-		return false;
+		return len;
 	}
 
-	allocl = ++l;
+	len++;
 
-	np = unflatten_dt_alloc(mem, sizeof(struct device_node) + allocl,
+	np = unflatten_dt_alloc(mem, sizeof(struct device_node) + len,
 				__alignof__(struct device_node));
 	if (!dryrun) {
 		char *fn;
 		of_node_init(np);
 		np->full_name = fn = ((char *)np) + sizeof(*np);
 
-		memcpy(fn, pathp, l);
+		memcpy(fn, pathp, len);
 
 		if (dad != NULL) {
 			np->parent = dad;
@@ -295,6 +295,7 @@ static int unflatten_dt_nodes(const void *blob,
 	struct device_node *nps[FDT_MAX_DEPTH];
 	void *base = mem;
 	bool dryrun = !base;
+	int ret;
 
 	if (nodepp)
 		*nodepp = NULL;
@@ -322,9 +323,10 @@ static int unflatten_dt_nodes(const void *blob,
 		    !of_fdt_device_is_available(blob, offset))
 			continue;
 
-		if (!populate_node(blob, offset, &mem, nps[depth],
-				   &nps[depth+1], dryrun))
-			return mem - base;
+		ret = populate_node(blob, offset, &mem, nps[depth],
+				   &nps[depth+1], dryrun);
+		if (ret < 0)
+			return ret;
 
 		if (!dryrun && nodepp && !*nodepp)
 			*nodepp = nps[depth+1];
@@ -372,6 +374,10 @@ void *__unflatten_device_tree(const void *blob,
 {
 	int size;
 	void *mem;
+	int ret;
+
+	if (mynodes)
+		*mynodes = NULL;
 
 	pr_debug(" -> unflatten_device_tree()\n");
 
@@ -392,7 +398,7 @@ void *__unflatten_device_tree(const void *blob,
 
 	/* First pass, scan for size */
 	size = unflatten_dt_nodes(blob, NULL, dad, NULL);
-	if (size < 0)
+	if (size <= 0)
 		return NULL;
 
 	size = ALIGN(size, 4);
@@ -410,12 +416,16 @@ void *__unflatten_device_tree(const void *blob,
 	pr_debug("  unflattening %p...\n", mem);
 
 	/* Second pass, do actual unflattening */
-	unflatten_dt_nodes(blob, mem, dad, mynodes);
+	ret = unflatten_dt_nodes(blob, mem, dad, mynodes);
+
 	if (be32_to_cpup(mem + size) != 0xdeadbeef)
 		pr_warn("End of tree marker overwritten: %08x\n",
 			be32_to_cpup(mem + size));
 
-	if (detached && mynodes) {
+	if (ret <= 0)
+		return NULL;
+
+	if (detached && mynodes && *mynodes) {
 		of_node_set_flag(*mynodes, OF_DETACHED);
 		pr_debug("unflattened tree is detached\n");
 	}
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index 50bbe0edf538..e12c643b6ba8 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -1017,7 +1017,7 @@ int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size,
 	const void *new_fdt;
 	int ret;
 	u32 size;
-	struct device_node *overlay_root;
+	struct device_node *overlay_root = NULL;
 
 	*ovcs_id = 0;
 	ret = 0;
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index eb100627c186..f9b5b698249f 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -1408,7 +1408,7 @@ static void attach_node_and_children(struct device_node *np)
 static int __init unittest_data_add(void)
 {
 	void *unittest_data;
-	struct device_node *unittest_data_node, *np;
+	struct device_node *unittest_data_node = NULL, *np;
 	/*
 	 * __dtb_testcases_begin[] and __dtb_testcases_end[] are magically
 	 * created by cmd_dt_S_dtb in scripts/Makefile.lib
@@ -1417,10 +1417,10 @@ static int __init unittest_data_add(void)
 	extern uint8_t __dtb_testcases_end[];
 	const int size = __dtb_testcases_end - __dtb_testcases_begin;
 	int rc;
+	void *ret;
 
 	if (!size) {
-		pr_warn("%s: No testcase data to attach; not running tests\n",
-			__func__);
+		pr_warn("%s: testcases is empty\n", __func__);
 		return -ENODATA;
 	}
 
@@ -1429,9 +1429,14 @@ static int __init unittest_data_add(void)
 	if (!unittest_data)
 		return -ENOMEM;
 
-	of_fdt_unflatten_tree(unittest_data, NULL, &unittest_data_node);
+	ret = of_fdt_unflatten_tree(unittest_data, NULL, &unittest_data_node);
+	if (!ret) {
+		pr_warn("%s: unflatten testcases tree failed\n", __func__);
+		kfree(unittest_data);
+		return -ENODATA;
+	}
 	if (!unittest_data_node) {
-		pr_warn("%s: No tree to attach; not running tests\n", __func__);
+		pr_warn("%s: testcases tree is empty\n", __func__);
 		kfree(unittest_data);
 		return -ENODATA;
 	}

From 603c4690b01aaffe3a6c3605a429f6dac39852ae Mon Sep 17 00:00:00 2001
From: Potnuri Bharat Teja <bharat@chelsio.com>
Date: Wed, 31 Mar 2021 19:27:15 +0530
Subject: [PATCH 1627/1820] RDMA/cxgb4: check for ipv6 address properly while
 destroying listener

ipv6 bit is wrongly set by the below which causes fatal adapter lookup
engine errors for ipv4 connections while destroying a listener.  Fix it to
properly check the local address for ipv6.

Fixes: 3408be145a5d ("RDMA/cxgb4: Fix adapter LE hash errors while destroying ipv6 listening server")
Link: https://lore.kernel.org/r/20210331135715.30072-1-bharat@chelsio.com
Signed-off-by: Potnuri Bharat Teja <bharat@chelsio.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/cxgb4/cm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 81903749d241..e42c812e74c3 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -3616,7 +3616,8 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id)
 		c4iw_init_wr_wait(ep->com.wr_waitp);
 		err = cxgb4_remove_server(
 				ep->com.dev->rdev.lldi.ports[0], ep->stid,
-				ep->com.dev->rdev.lldi.rxq_ids[0], true);
+				ep->com.dev->rdev.lldi.rxq_ids[0],
+				ep->com.local_addr.ss_family == AF_INET6);
 		if (err)
 			goto done;
 		err = c4iw_wait_for_reply(&ep->com.dev->rdev, ep->com.wr_waitp,

From 5de61a47eb9064cbbc5f3360d639e8e34a690a54 Mon Sep 17 00:00:00 2001
From: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
Date: Mon, 29 Mar 2021 09:48:19 -0400
Subject: [PATCH 1628/1820] IB/hfi1: Fix probe time panic when AIP is enabled
 with a buggy BIOS

A panic can result when AIP is enabled:

  BUG: unable to handle kernel NULL pointer dereference at 000000000000000
  PGD 0 P4D 0
  Oops: 0000 1 SMP PTI
  CPU: 70 PID: 981 Comm: systemd-udevd Tainted: G OE --------- - - 4.18.0-240.el8.x86_64 #1
  Hardware name: Intel Corporation S2600KP/S2600KP, BIOS SE5C610.86B.01.01.0005.101720141054 10/17/2014
  RIP: 0010:__bitmap_and+0x1b/0x70
  RSP: 0018:ffff99aa0845f9f0 EFLAGS: 00010246
  RAX: 0000000000000000 RBX: ffff8d5a6fc18000 RCX: 0000000000000048
  RDX: 0000000000000000 RSI: ffffffffc06336f0 RDI: ffff8d5a8fa67750
  RBP: 0000000000000079 R08: 0000000fffffffff R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000001 R12: ffffffffc06336f0
  R13: 00000000000000a0 R14: ffff8d5a6fc18000 R15: 0000000000000003
  FS: 00007fec137a5980(0000) GS:ffff8d5a9fa80000(0000) knlGS:0000000000000000
  CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000000 CR3: 0000000a04b48002 CR4: 00000000001606e0
  Call Trace:
  hfi1_num_netdev_contexts+0x7c/0x110 [hfi1]
  hfi1_init_dd+0xd7f/0x1a90 [hfi1]
  ? pci_bus_read_config_dword+0x49/0x70
  ? pci_mmcfg_read+0x3e/0xe0
  do_init_one.isra.18+0x336/0x640 [hfi1]
  local_pci_probe+0x41/0x90
  pci_device_probe+0x105/0x1c0
  really_probe+0x212/0x440
  driver_probe_device+0x49/0xc0
  device_driver_attach+0x50/0x60
  __driver_attach+0x61/0x130
  ? device_driver_attach+0x60/0x60
  bus_for_each_dev+0x77/0xc0
  ? klist_add_tail+0x3b/0x70
  bus_add_driver+0x14d/0x1e0
  ? dev_init+0x10b/0x10b [hfi1]
  driver_register+0x6b/0xb0
  ? dev_init+0x10b/0x10b [hfi1]
  hfi1_mod_init+0x1e6/0x20a [hfi1]
  do_one_initcall+0x46/0x1c3
  ? free_unref_page_commit+0x91/0x100
  ? _cond_resched+0x15/0x30
  ? kmem_cache_alloc_trace+0x140/0x1c0
  do_init_module+0x5a/0x220
  load_module+0x14b4/0x17e0
  ? __do_sys_finit_module+0xa8/0x110
  __do_sys_finit_module+0xa8/0x110
  do_syscall_64+0x5b/0x1a0

The issue happens when pcibus_to_node() returns NO_NUMA_NODE.

Fix this issue by moving the initialization of dd->node to hfi1_devdata
allocation and remove the other pcibus_to_node() calls in the probe path
and use dd->node instead.

Affinity logic is adjusted to use a new field dd->affinity_entry as a
guard instead of dd->node.

Fixes: 4730f4a6c6b2 ("IB/hfi1: Activate the dummy netdev")
Link: https://lore.kernel.org/r/1617025700-31865-4-git-send-email-dennis.dalessandro@cornelisnetworks.com
Cc: stable@vger.kernel.org
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/hfi1/affinity.c  | 21 +++++----------------
 drivers/infiniband/hw/hfi1/hfi.h       |  1 +
 drivers/infiniband/hw/hfi1/init.c      | 10 +++++++++-
 drivers/infiniband/hw/hfi1/netdev_rx.c |  3 +--
 4 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 2a91b8d95e12..04b1e8f021f6 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -632,22 +632,11 @@ static void _dev_comp_vect_cpu_mask_clean_up(struct hfi1_devdata *dd,
  */
 int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
 {
-	int node = pcibus_to_node(dd->pcidev->bus);
 	struct hfi1_affinity_node *entry;
 	const struct cpumask *local_mask;
 	int curr_cpu, possible, i, ret;
 	bool new_entry = false;
 
-	/*
-	 * If the BIOS does not have the NUMA node information set, select
-	 * NUMA 0 so we get consistent performance.
-	 */
-	if (node < 0) {
-		dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n");
-		node = 0;
-	}
-	dd->node = node;
-
 	local_mask = cpumask_of_node(dd->node);
 	if (cpumask_first(local_mask) >= nr_cpu_ids)
 		local_mask = topology_core_cpumask(0);
@@ -660,7 +649,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
 	 * create an entry in the global affinity structure and initialize it.
 	 */
 	if (!entry) {
-		entry = node_affinity_allocate(node);
+		entry = node_affinity_allocate(dd->node);
 		if (!entry) {
 			dd_dev_err(dd,
 				   "Unable to allocate global affinity node\n");
@@ -751,6 +740,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
 	if (new_entry)
 		node_affinity_add_tail(entry);
 
+	dd->affinity_entry = entry;
 	mutex_unlock(&node_affinity.lock);
 
 	return 0;
@@ -766,10 +756,9 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd)
 {
 	struct hfi1_affinity_node *entry;
 
-	if (dd->node < 0)
-		return;
-
 	mutex_lock(&node_affinity.lock);
+	if (!dd->affinity_entry)
+		goto unlock;
 	entry = node_affinity_lookup(dd->node);
 	if (!entry)
 		goto unlock;
@@ -780,8 +769,8 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd)
 	 */
 	_dev_comp_vect_cpu_mask_clean_up(dd, entry);
 unlock:
+	dd->affinity_entry = NULL;
 	mutex_unlock(&node_affinity.lock);
-	dd->node = NUMA_NO_NODE;
 }
 
 /*
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index e09e8244a94c..2a9a040569eb 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1409,6 +1409,7 @@ struct hfi1_devdata {
 	spinlock_t irq_src_lock;
 	int vnic_num_vports;
 	struct net_device *dummy_netdev;
+	struct hfi1_affinity_node *affinity_entry;
 
 	/* Keeps track of IPoIB RSM rule users */
 	atomic_t ipoib_rsm_usr_num;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index cb7ad1288821..786c6316273f 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1277,7 +1277,6 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev,
 	dd->pport = (struct hfi1_pportdata *)(dd + 1);
 	dd->pcidev = pdev;
 	pci_set_drvdata(pdev, dd);
-	dd->node = NUMA_NO_NODE;
 
 	ret = xa_alloc_irq(&hfi1_dev_table, &dd->unit, dd, xa_limit_32b,
 			GFP_KERNEL);
@@ -1287,6 +1286,15 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev,
 		goto bail;
 	}
 	rvt_set_ibdev_name(&dd->verbs_dev.rdi, "%s_%d", class_name(), dd->unit);
+	/*
+	 * If the BIOS does not have the NUMA node information set, select
+	 * NUMA 0 so we get consistent performance.
+	 */
+	dd->node = pcibus_to_node(pdev->bus);
+	if (dd->node == NUMA_NO_NODE) {
+		dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n");
+		dd->node = 0;
+	}
 
 	/*
 	 * Initialize all locks for the device. This needs to be as early as
diff --git a/drivers/infiniband/hw/hfi1/netdev_rx.c b/drivers/infiniband/hw/hfi1/netdev_rx.c
index 1fb6e1a0e4e1..1bcab992ac26 100644
--- a/drivers/infiniband/hw/hfi1/netdev_rx.c
+++ b/drivers/infiniband/hw/hfi1/netdev_rx.c
@@ -173,8 +173,7 @@ u32 hfi1_num_netdev_contexts(struct hfi1_devdata *dd, u32 available_contexts,
 		return 0;
 	}
 
-	cpumask_and(node_cpu_mask, cpu_mask,
-		    cpumask_of_node(pcibus_to_node(dd->pcidev->bus)));
+	cpumask_and(node_cpu_mask, cpu_mask, cpumask_of_node(dd->node));
 
 	available_cpus = cpumask_weight(node_cpu_mask);
 

From f2013278ae40b89cc27916366c407ce5261815ef Mon Sep 17 00:00:00 2001
From: Jin Yao <yao.jin@linux.intel.com>
Date: Wed, 7 Apr 2021 10:44:52 +0800
Subject: [PATCH 1629/1820] perf report: Fix wrong LBR block sorting

When '--total-cycles' is specified, it supports sorting for all blocks
by 'Sampled Cycles%'. This is useful to concentrate on the globally
hottest blocks.

'Sampled Cycles%' - block sampled cycles aggregation / total sampled cycles

But in current code, it doesn't use the cycles aggregation. Part of
'cycles' counting is possibly dropped for some overlap jumps. But for
identifying the hot block, we always need the full cycles.

  # perf record -b ./triad_loop
  # perf report --total-cycles --stdio

Before:

  #
  # Sampled Cycles%  Sampled Cycles  Avg Cycles%  Avg Cycles                                          [Program Block Range]      Shared Object
  # ...............  ..............  ...........  ..........  .............................................................  .................
  #
              0.81%             793        4.32%         793                           [setup-vdso.h:34 -> setup-vdso.h:40]         ld-2.27.so
              0.49%             480        0.87%         160                    [native_write_msr+0 -> native_write_msr+16]  [kernel.kallsyms]
              0.48%             476        0.52%          95                      [native_read_msr+0 -> native_read_msr+29]  [kernel.kallsyms]
              0.31%             303        1.65%         303                              [nmi_restore+0 -> nmi_restore+37]  [kernel.kallsyms]
              0.26%             255        1.39%         255      [nohz_balance_exit_idle+75 -> nohz_balance_exit_idle+162]  [kernel.kallsyms]
              0.24%             234        1.28%         234                       [end_repeat_nmi+67 -> end_repeat_nmi+83]  [kernel.kallsyms]
              0.23%             227        1.24%         227            [__irqentry_text_end+96 -> __irqentry_text_end+126]  [kernel.kallsyms]
              0.20%             194        1.06%         194             [native_set_debugreg+52 -> native_set_debugreg+56]  [kernel.kallsyms]
              0.11%             106        0.14%          26                [native_sched_clock+0 -> native_sched_clock+98]  [kernel.kallsyms]
              0.10%              97        0.53%          97            [trigger_load_balance+0 -> trigger_load_balance+67]  [kernel.kallsyms]
              0.09%              85        0.46%          85             [get-dynamic-info.h:102 -> get-dynamic-info.h:111]         ld-2.27.so
  ...
              0.00%           92.7K        0.02%           4                           [triad_loop.c:64 -> triad_loop.c:65]         triad_loop

The hottest block '[triad_loop.c:64 -> triad_loop.c:65]' is not at
the top of output.

After:

  # Sampled Cycles%  Sampled Cycles  Avg Cycles%  Avg Cycles                                           [Program Block Range]      Shared Object
  # ...............  ..............  ...........  ..........  ..............................................................  .................
  #
             94.35%           92.7K        0.02%           4                            [triad_loop.c:64 -> triad_loop.c:65]         triad_loop
              0.81%             793        4.32%         793                            [setup-vdso.h:34 -> setup-vdso.h:40]         ld-2.27.so
              0.49%             480        0.87%         160                     [native_write_msr+0 -> native_write_msr+16]  [kernel.kallsyms]
              0.48%             476        0.52%          95                       [native_read_msr+0 -> native_read_msr+29]  [kernel.kallsyms]
              0.31%             303        1.65%         303                               [nmi_restore+0 -> nmi_restore+37]  [kernel.kallsyms]
              0.26%             255        1.39%         255       [nohz_balance_exit_idle+75 -> nohz_balance_exit_idle+162]  [kernel.kallsyms]
              0.24%             234        1.28%         234                        [end_repeat_nmi+67 -> end_repeat_nmi+83]  [kernel.kallsyms]
              0.23%             227        1.24%         227             [__irqentry_text_end+96 -> __irqentry_text_end+126]  [kernel.kallsyms]
              0.20%             194        1.06%         194              [native_set_debugreg+52 -> native_set_debugreg+56]  [kernel.kallsyms]
              0.11%             106        0.14%          26                 [native_sched_clock+0 -> native_sched_clock+98]  [kernel.kallsyms]
              0.10%              97        0.53%          97             [trigger_load_balance+0 -> trigger_load_balance+67]  [kernel.kallsyms]
              0.09%              85        0.46%          85              [get-dynamic-info.h:102 -> get-dynamic-info.h:111]         ld-2.27.so
              0.08%              82        0.06%          11  [intel_pmu_drain_pebs_nhm+580 -> intel_pmu_drain_pebs_nhm+627]  [kernel.kallsyms]
              0.08%              77        0.42%          77                  [lru_add_drain_cpu+0 -> lru_add_drain_cpu+133]  [kernel.kallsyms]
              0.08%              74        0.10%          18                [handle_pmi_common+271 -> handle_pmi_common+310]  [kernel.kallsyms]
              0.08%              74        0.40%          74              [get-dynamic-info.h:131 -> get-dynamic-info.h:157]         ld-2.27.so
              0.07%              69        0.09%          17  [intel_pmu_drain_pebs_nhm+432 -> intel_pmu_drain_pebs_nhm+468]  [kernel.kallsyms]

Now the hottest block is reported at the top of output.

Fixes: b65a7d372b1a55db ("perf hist: Support block formats with compare/sort/display")
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210407024452.29988-1-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/block-info.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index 423ec69bda6c..5ecd4f401f32 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -201,7 +201,7 @@ static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt,
 	double ratio = 0.0;
 
 	if (block_fmt->total_cycles)
-		ratio = (double)bi->cycles / (double)block_fmt->total_cycles;
+		ratio = (double)bi->cycles_aggr / (double)block_fmt->total_cycles;
 
 	return color_pct(hpp, block_fmt->width, 100.0 * ratio);
 }
@@ -216,9 +216,9 @@ static int64_t block_total_cycles_pct_sort(struct perf_hpp_fmt *fmt,
 	double l, r;
 
 	if (block_fmt->total_cycles) {
-		l = ((double)bi_l->cycles /
+		l = ((double)bi_l->cycles_aggr /
 			(double)block_fmt->total_cycles) * 100000.0;
-		r = ((double)bi_r->cycles /
+		r = ((double)bi_r->cycles_aggr /
 			(double)block_fmt->total_cycles) * 100000.0;
 		return (int64_t)l - (int64_t)r;
 	}

From 92f1e8adf7db2ef9b90e5662182810c0cf8ac22e Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 7 Apr 2021 08:39:55 -0700
Subject: [PATCH 1630/1820] perf arm-spe: Avoid potential buffer overrun

SPE extended headers are > 1 byte so ensure the buffer contains at least
this before reading. This issue was detected by fuzzing.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andre Przywara <andre.przywara@arm.com>
Cc: Dave Martin <dave.martin@arm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Will Deacon <will@kernel.org>
Link: http://lore.kernel.org/lkml/20210407153955.317215-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
index f3ac9d40cebf..2e5eff4f8f03 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
@@ -210,8 +210,10 @@ static int arm_spe_do_get_packet(const unsigned char *buf, size_t len,
 
 	if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_EXTENDED) {
 		/* 16-bit extended format header */
-		ext_hdr = 1;
+		if (len == 1)
+			return ARM_SPE_BAD_PACKET;
 
+		ext_hdr = 1;
 		hdr = buf[1];
 		if (hdr == SPE_HEADER1_ALIGNMENT)
 			return arm_spe_get_alignment(buf, len, packet);

From 0c85a7e87465f2d4cbc768e245f4f45b2f299b05 Mon Sep 17 00:00:00 2001
From: Aditya Pakki <pakki001@umn.edu>
Date: Tue, 6 Apr 2021 19:09:12 -0500
Subject: [PATCH 1631/1820] net/rds: Avoid potential use after free in
 rds_send_remove_from_sock

In case of rs failure in rds_send_remove_from_sock(), the 'rm' resource
is freed and later under spinlock, causing potential use-after-free.
Set the free pointer to NULL to avoid undefined behavior.

Signed-off-by: Aditya Pakki <pakki001@umn.edu>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/message.c | 1 +
 net/rds/send.c    | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/rds/message.c b/net/rds/message.c
index 799034e0f513..4fc66ff0f1ec 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -180,6 +180,7 @@ void rds_message_put(struct rds_message *rm)
 		rds_message_purge(rm);
 
 		kfree(rm);
+		rm = NULL;
 	}
 }
 EXPORT_SYMBOL_GPL(rds_message_put);
diff --git a/net/rds/send.c b/net/rds/send.c
index 985d0b7713ac..fe5264b9d4b3 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -665,7 +665,7 @@ static void rds_send_remove_from_sock(struct list_head *messages, int status)
 unlock_and_drop:
 		spin_unlock_irqrestore(&rm->m_rs_lock, flags);
 		rds_message_put(rm);
-		if (was_on_sock)
+		if (was_on_sock && rm)
 			rds_message_put(rm);
 	}
 

From f0ebc2b6b7df7716749445cda26734b3826a48cf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 Apr 2021 17:28:25 -0700
Subject: [PATCH 1632/1820] ethtool: un-kdocify extended link state

Extended link state structures and enums use kdoc headers
but then do not describe any of the members.

Convert to normal comments.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h      |  4 +---
 include/uapi/linux/ethtool.h | 26 ++++++--------------------
 2 files changed, 7 insertions(+), 23 deletions(-)

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index ec4cd3921c67..a2b1a21ee7fd 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -87,9 +87,7 @@ u32 ethtool_op_get_link(struct net_device *dev);
 int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *eti);
 
 
-/**
- * struct ethtool_link_ext_state_info - link extended state and substate.
- */
+/* Link extended state and substate. */
 struct ethtool_link_ext_state_info {
 	enum ethtool_link_ext_state link_ext_state;
 	union {
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index cde753bb2093..dc87ba092891 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -579,9 +579,7 @@ struct ethtool_pauseparam {
 	__u32	tx_pause;
 };
 
-/**
- * enum ethtool_link_ext_state - link extended state
- */
+/* Link extended state */
 enum ethtool_link_ext_state {
 	ETHTOOL_LINK_EXT_STATE_AUTONEG,
 	ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE,
@@ -595,10 +593,7 @@ enum ethtool_link_ext_state {
 	ETHTOOL_LINK_EXT_STATE_OVERHEAT,
 };
 
-/**
- * enum ethtool_link_ext_substate_autoneg - more information in addition to
- * ETHTOOL_LINK_EXT_STATE_AUTONEG.
- */
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */
 enum ethtool_link_ext_substate_autoneg {
 	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1,
 	ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED,
@@ -608,9 +603,7 @@ enum ethtool_link_ext_substate_autoneg {
 	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD,
 };
 
-/**
- * enum ethtool_link_ext_substate_link_training - more information in addition to
- * ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE.
  */
 enum ethtool_link_ext_substate_link_training {
 	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1,
@@ -619,9 +612,7 @@ enum ethtool_link_ext_substate_link_training {
 	ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT,
 };
 
-/**
- * enum ethtool_link_ext_substate_logical_mismatch - more information in addition
- * to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH.
  */
 enum ethtool_link_ext_substate_link_logical_mismatch {
 	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1,
@@ -631,19 +622,14 @@ enum ethtool_link_ext_substate_link_logical_mismatch {
 	ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED,
 };
 
-/**
- * enum ethtool_link_ext_substate_bad_signal_integrity - more information in
- * addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY.
  */
 enum ethtool_link_ext_substate_bad_signal_integrity {
 	ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1,
 	ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE,
 };
 
-/**
- * enum ethtool_link_ext_substate_cable_issue - more information in
- * addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE.
- */
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */
 enum ethtool_link_ext_substate_cable_issue {
 	ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1,
 	ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE,

From 83e5feeb385e6d69ae95dd30e0c424afaa17cc6b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 Apr 2021 17:28:26 -0700
Subject: [PATCH 1633/1820] ethtool: document reserved fields in the uAPI

Add a note on expected handling of reserved fields,
and references to all kdocs. This fixes a bunch
of kdoc warnings.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ethtool.h | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index dc87ba092891..c9c18e88c215 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -26,6 +26,14 @@
  * have the same layout for 32-bit and 64-bit userland.
  */
 
+/* Note on reserved space.
+ * Reserved fields must not be accessed directly by user space because
+ * they may be replaced by a different field in the future. They must
+ * be initialized to zero before making the request, e.g. via memset
+ * of the entire structure or implicitly by not being set in a structure
+ * initializer.
+ */
+
 /**
  * struct ethtool_cmd - DEPRECATED, link control and status
  * This structure is DEPRECATED, please use struct ethtool_link_settings.
@@ -67,6 +75,7 @@
  *	and other link features that the link partner advertised
  *	through autonegotiation; 0 if unknown or not applicable.
  *	Read-only.
+ * @reserved: Reserved for future use; see the note on reserved space.
  *
  * The link speed in Mbps is split between @speed and @speed_hi.  Use
  * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to
@@ -155,6 +164,7 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep)
  * @bus_info: Device bus address.  This should match the dev_name()
  *	string for the underlying bus device, if there is one.  May be
  *	an empty string.
+ * @reserved2: Reserved for future use; see the note on reserved space.
  * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and
  *	%ETHTOOL_SPFLAGS commands; also the number of strings in the
  *	%ETH_SS_PRIV_FLAGS set
@@ -356,6 +366,7 @@ struct ethtool_eeprom {
  * @tx_lpi_timer: Time in microseconds the interface delays prior to asserting
  *	its tx lpi (after reaching 'idle' state). Effective only when eee
  *	was negotiated and tx_lpi_enabled was set.
+ * @reserved: Reserved for future use; see the note on reserved space.
  */
 struct ethtool_eee {
 	__u32	cmd;
@@ -374,6 +385,7 @@ struct ethtool_eee {
  * @cmd: %ETHTOOL_GMODULEINFO
  * @type: Standard the module information conforms to %ETH_MODULE_SFF_xxxx
  * @eeprom_len: Length of the eeprom
+ * @reserved: Reserved for future use; see the note on reserved space.
  *
  * This structure is used to return the information to
  * properly size memory for a subsequent call to %ETHTOOL_GMODULEEEPROM.
@@ -701,6 +713,7 @@ struct ethtool_gstrings {
 /**
  * struct ethtool_sset_info - string set information
  * @cmd: Command number = %ETHTOOL_GSSET_INFO
+ * @reserved: Reserved for future use; see the note on reserved space.
  * @sset_mask: On entry, a bitmask of string sets to query, with bits
  *	numbered according to &enum ethtool_stringset.  On return, a
  *	bitmask of those string sets queried that are supported.
@@ -745,6 +758,7 @@ enum ethtool_test_flags {
  * @flags: A bitmask of flags from &enum ethtool_test_flags.  Some
  *	flags may be set by the user on entry; others may be set by
  *	the driver on return.
+ * @reserved: Reserved for future use; see the note on reserved space.
  * @len: On return, the number of test results
  * @data: Array of test results
  *
@@ -945,6 +959,7 @@ union ethtool_flow_union {
  * @vlan_etype: VLAN EtherType
  * @vlan_tci: VLAN tag control information
  * @data: user defined data
+ * @padding: Reserved for future use; see the note on reserved space.
  *
  * Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT
  * is set in &struct ethtool_rx_flow_spec @flow_type.
@@ -1120,7 +1135,8 @@ struct ethtool_rxfh_indir {
  *	hardware hash key.
  * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
  *	Valid values are one of the %ETH_RSS_HASH_*.
- * @rsvd:	Reserved for future extensions.
+ * @rsvd8: Reserved for future use; see the note on reserved space.
+ * @rsvd32: Reserved for future use; see the note on reserved space.
  * @rss_config: RX ring/queue index for each hash value i.e., indirection table
  *	of @indir_size __u32 elements, followed by hash key of @key_size
  *	bytes.
@@ -1288,7 +1304,9 @@ struct ethtool_sfeatures {
  * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags
  * @phc_index: device index of the associated PHC, or -1 if there is none
  * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values
+ * @tx_reserved: Reserved for future use; see the note on reserved space.
  * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values
+ * @rx_reserved: Reserved for future use; see the note on reserved space.
  *
  * The bits in the 'tx_types' and 'rx_filters' fields correspond to
  * the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values,
@@ -1944,6 +1962,8 @@ enum ethtool_reset_flags {
  *	autonegotiation; 0 if unknown or not applicable.  Read-only.
  * @transceiver: Used to distinguish different possible PHY types,
  *	reported consistently by PHYLIB.  Read-only.
+ * @reserved: Reserved for future use; see the note on reserved space.
+ * @reserved1: Reserved for future use; see the note on reserved space.
  *
  * If autonegotiation is disabled, the speed and @duplex represent the
  * fixed link mode and are writable if the driver supports multiple

From d9c65de0c1e1574d2cc8007dbe02291fe47db1d9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 Apr 2021 17:28:27 -0700
Subject: [PATCH 1634/1820] ethtool: fix kdoc in headers

Fix remaining issues with kdoc in the ethtool headers.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h      | 9 +++++++--
 include/uapi/linux/ethtool.h | 6 ++++++
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index a2b1a21ee7fd..7c88dfff7420 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -290,6 +290,9 @@ struct ethtool_pause_stats {
  *	do not attach ext_substate attribute to netlink message). If link_ext_state
  *	and link_ext_substate are unknown, return -ENODATA. If not implemented,
  *	link_ext_state and link_ext_substate will not be sent to userspace.
+ * @get_eeprom_len: Read range of EEPROM addresses for validation of
+ *	@get_eeprom and @set_eeprom requests.
+ *	Returns 0 if device does not support EEPROM access.
  * @get_eeprom: Read data from the device EEPROM.
  *	Should fill in the magic field.  Don't need to check len for zero
  *	or wraparound.  Fill in the data argument with the eeprom values
@@ -382,6 +385,8 @@ struct ethtool_pause_stats {
  * @get_module_eeprom: Get the eeprom information from the plug-in module
  * @get_eee: Get Energy-Efficient (EEE) supported and status.
  * @set_eee: Set EEE status (enable/disable) as well as LPI timers.
+ * @get_tunable: Read the value of a driver / device tunable.
+ * @set_tunable: Set the value of a driver / device tunable.
  * @get_per_queue_coalesce: Get interrupt coalescing parameters per queue.
  *	It must check that the given queue number is valid. If neither a RX nor
  *	a TX queue has this number, return -EINVAL. If only a RX queue or a TX
@@ -545,8 +550,8 @@ struct phy_tdr_config;
  * @get_sset_count: Get number of strings that @get_strings will write.
  * @get_strings: Return a set of strings that describe the requested objects
  * @get_stats: Return extended statistics about the PHY device.
- * @start_cable_test - Start a cable test
- * @start_cable_test_tdr - Start a Time Domain Reflectometry cable test
+ * @start_cable_test: Start a cable test
+ * @start_cable_test_tdr: Start a Time Domain Reflectometry cable test
  *
  * All operations are optional (i.e. the function pointer may be set to %NULL)
  * and callers must take this into account. Callers must hold the RTNL lock.
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index c9c18e88c215..5afea692a3f7 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -659,6 +659,7 @@ enum ethtool_link_ext_substate_cable_issue {
  *	now deprecated
  * @ETH_SS_FEATURES: Device feature names
  * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names
+ * @ETH_SS_TUNABLES: tunable names
  * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS
  * @ETH_SS_PHY_TUNABLES: PHY tunable names
  * @ETH_SS_LINK_MODES: link mode names
@@ -668,6 +669,8 @@ enum ethtool_link_ext_substate_cable_issue {
  * @ETH_SS_TS_TX_TYPES: timestamping Tx types
  * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters
  * @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types
+ *
+ * @ETH_SS_COUNT: number of defined string sets
  */
 enum ethtool_stringset {
 	ETH_SS_TEST		= 0,
@@ -1962,8 +1965,11 @@ enum ethtool_reset_flags {
  *	autonegotiation; 0 if unknown or not applicable.  Read-only.
  * @transceiver: Used to distinguish different possible PHY types,
  *	reported consistently by PHYLIB.  Read-only.
+ * @master_slave_cfg: Master/slave port mode.
+ * @master_slave_state: Master/slave port state.
  * @reserved: Reserved for future use; see the note on reserved space.
  * @reserved1: Reserved for future use; see the note on reserved space.
+ * @link_mode_masks: Variable length bitmaps.
  *
  * If autonegotiation is disabled, the speed and @duplex represent the
  * fixed link mode and are writable if the driver supports multiple

From 9d6803921a16f4d768dc41a75375629828f4d91e Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Tue, 6 Apr 2021 09:35:09 +0200
Subject: [PATCH 1635/1820] net: hsr: Reset MAC header for Tx path

Reset MAC header in HSR Tx path. This is needed, because direct packet
transmission, e.g. by specifying PACKET_QDISC_BYPASS does not reset the MAC
header.

This has been observed using the following setup:

|$ ip link add name hsr0 type hsr slave1 lan0 slave2 lan1 supervision 45 version 1
|$ ifconfig hsr0 up
|$ ./test hsr0

The test binary is using mmap'ed sockets and is specifying the
PACKET_QDISC_BYPASS socket option.

This patch resolves the following warning on a non-patched kernel:

|[  112.725394] ------------[ cut here ]------------
|[  112.731418] WARNING: CPU: 1 PID: 257 at net/hsr/hsr_forward.c:560 hsr_forward_skb+0x484/0x568
|[  112.739962] net/hsr/hsr_forward.c:560: Malformed frame (port_src hsr0)

The warning can be safely removed, because the other call sites of
hsr_forward_skb() make sure that the skb is prepared correctly.

Fixes: d346a3fae3ff ("packet: introduce PACKET_QDISC_BYPASS socket option")
Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_device.c  | 1 +
 net/hsr/hsr_forward.c | 6 ------
 2 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 7444ec6e298e..bfcdc75fc01e 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -217,6 +217,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
 	if (master) {
 		skb->dev = master->dev;
+		skb_reset_mac_header(skb);
 		hsr_forward_skb(skb, master);
 	} else {
 		atomic_long_inc(&dev->tx_dropped);
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index ed82a470b6e1..b218e4594009 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -555,12 +555,6 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port)
 {
 	struct hsr_frame_info frame;
 
-	if (skb_mac_header(skb) != skb->data) {
-		WARN_ONCE(1, "%s:%d: Malformed frame (port_src %s)\n",
-			  __FILE__, __LINE__, port->dev->name);
-		goto out_drop;
-	}
-
 	if (fill_frame_info(&frame, skb, port) < 0)
 		goto out_drop;
 

From a79ace4b312953c5835fafb12adc3cb6878b26bd Mon Sep 17 00:00:00 2001
From: Zheng Yongjun <zhengyongjun3@huawei.com>
Date: Wed, 7 Apr 2021 09:59:45 +0800
Subject: [PATCH 1636/1820] net: tipc: Fix spelling errors in net/tipc module

These patches fix a series of spelling errors in net/tipc module.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zheng Yongjun <zhengyongjun3@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/bearer.h | 6 +++---
 net/tipc/net.c    | 2 +-
 net/tipc/node.c   | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 6bf4550aa1ac..57c6a1a719e2 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -154,9 +154,9 @@ struct tipc_media {
  * care of initializing all other fields.
  */
 struct tipc_bearer {
-	void __rcu *media_ptr;			/* initalized by media */
-	u32 mtu;				/* initalized by media */
-	struct tipc_media_addr addr;		/* initalized by media */
+	void __rcu *media_ptr;			/* initialized by media */
+	u32 mtu;				/* initialized by media */
+	struct tipc_media_addr addr;		/* initialized by media */
 	char name[TIPC_MAX_BEARER_NAME];
 	struct tipc_media *media;
 	struct tipc_media_addr bcast_addr;
diff --git a/net/tipc/net.c b/net/tipc/net.c
index a129f661bee3..faf6bf554514 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -89,7 +89,7 @@
  *     - A spin lock to protect the registry of kernel/driver users (reg.c)
  *     - A global spin_lock (tipc_port_lock), which only task is to ensure
  *       consistency where more than one port is involved in an operation,
- *       i.e., whe a port is part of a linked list of ports.
+ *       i.e., when a port is part of a linked list of ports.
  *       There are two such lists; 'port_list', which is used for management,
  *       and 'wait_list', which is used to queue ports during congestion.
  *
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 136338b85504..e0ee83263a39 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1734,7 +1734,7 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list,
 }
 
 /* tipc_node_xmit_skb(): send single buffer to destination
- * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE
+ * Buffers sent via this function are generally TIPC_SYSTEM_IMPORTANCE
  * messages, which will not be rejected
  * The only exception is datagram messages rerouted after secondary
  * lookup, which are rare and safe to dispose of anyway.

From df7232c4c676be29f1cf45058ec156c1183539ff Mon Sep 17 00:00:00 2001
From: Qingqing Zhuo <qingqing.zhuo@amd.com>
Date: Thu, 25 Mar 2021 03:44:11 -0400
Subject: [PATCH 1637/1820] drm/amd/display: Add missing mask for DCN3

[Why]
DCN3 is not reusing DCN1 mask_sh_list, causing
SURFACE_FLIP_INT_MASK missing in the mapping.

[How]
Add the corresponding entry to DCN3 list.

Signed-off-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h
index 705fbfc37502..8a32772d4e91 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h
@@ -134,6 +134,7 @@
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_EN, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_BLK, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_BLK_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_FLIP_INTERRUPT, SURFACE_FLIP_INT_MASK, mask_sh),\
 	HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\
 	HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\
 	HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\

From a975d7d8a356ce92872af0b007b101183f0224e2 Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Wed, 7 Apr 2021 13:06:51 +0300
Subject: [PATCH 1638/1820] ethtool: Remove link_mode param and derive link
 params from driver

Some drivers clear the 'ethtool_link_ksettings' struct in their
get_link_ksettings() callback, before populating it with actual values.
Such drivers will set the new 'link_mode' field to zero, resulting in
user space receiving wrong link mode information given that zero is a
valid value for the field.

Another problem is that some drivers (notably tun) can report random
values in the 'link_mode' field. This can result in a general protection
fault when the field is used as an index to the 'link_mode_params' array
[1].

This happens because such drivers implement their set_link_ksettings()
callback by simply overwriting their private copy of
'ethtool_link_ksettings' struct with the one they get from the stack,
which is not always properly initialized.

Fix these problems by removing 'link_mode' from 'ethtool_link_ksettings'
and instead have drivers call ethtool_params_from_link_mode() with the
current link mode. The function will derive the link parameters (e.g.,
speed) from the link mode and fill them in the 'ethtool_link_ksettings'
struct.

v3:
	* Remove link_mode parameter and derive the link parameters in
	  the driver instead of passing link_mode parameter to ethtool
	  and derive it there.

v2:
	* Introduce 'cap_link_mode_supported' instead of adding a
	  validity field to 'ethtool_link_ksettings' struct.

[1]
general protection fault, probably for non-canonical address 0xdffffc00f14cc32c: 0000 [#1] PREEMPT SMP KASAN
KASAN: probably user-memory-access in range [0x000000078a661960-0x000000078a661967]
CPU: 0 PID: 8452 Comm: syz-executor360 Not tainted 5.11.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__ethtool_get_link_ksettings+0x1a3/0x3a0 net/ethtool/ioctl.c:446
Code: b7 3e fa 83 fd ff 0f 84 30 01 00 00 e8 16 b0 3e fa 48 8d 3c ed 60 d5 69 8a 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48 89 f8 83 e0 07 83 c0 03
+38 d0 7c 08 84 d2 0f 85 b9
RSP: 0018:ffffc900019df7a0 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: ffff888026136008 RCX: 0000000000000000
RDX: 00000000f14cc32c RSI: ffffffff873439ca RDI: 000000078a661960
RBP: 00000000ffff8880 R08: 00000000ffffffff R09: ffff88802613606f
R10: ffffffff873439bc R11: 0000000000000000 R12: 0000000000000000
R13: ffff88802613606c R14: ffff888011d0c210 R15: ffff888011d0c210
FS:  0000000000749300(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004b60f0 CR3: 00000000185c2000 CR4: 00000000001506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 linkinfo_prepare_data+0xfd/0x280 net/ethtool/linkinfo.c:37
 ethnl_default_notify+0x1dc/0x630 net/ethtool/netlink.c:586
 ethtool_notify+0xbd/0x1f0 net/ethtool/netlink.c:656
 ethtool_set_link_ksettings+0x277/0x330 net/ethtool/ioctl.c:620
 dev_ethtool+0x2b35/0x45d0 net/ethtool/ioctl.c:2842
 dev_ioctl+0x463/0xb70 net/core/dev_ioctl.c:440
 sock_do_ioctl+0x148/0x2d0 net/socket.c:1060
 sock_ioctl+0x477/0x6a0 net/socket.c:1177
 vfs_ioctl fs/ioctl.c:48 [inline]
 __do_sys_ioctl fs/ioctl.c:753 [inline]
 __se_sys_ioctl fs/ioctl.c:739 [inline]
 __x64_sys_ioctl+0x193/0x200 fs/ioctl.c:739
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: c8907043c6ac9 ("ethtool: Get link mode in use instead of speed and duplex parameters")
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlxsw/spectrum_ethtool.c         | 19 ++++++++++++++-----
 include/linux/ethtool.h                       |  9 ++++++++-
 net/ethtool/common.c                          | 16 ++++++++++++++++
 net/ethtool/ioctl.c                           | 18 +-----------------
 4 files changed, 39 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
index 0bd64169bf81..078601d31cde 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
@@ -1230,16 +1230,22 @@ mlxsw_sp1_from_ptys_link_mode(struct mlxsw_sp *mlxsw_sp, bool carrier_ok,
 			      u32 ptys_eth_proto,
 			      struct ethtool_link_ksettings *cmd)
 {
+	struct mlxsw_sp1_port_link_mode link;
 	int i;
 
-	cmd->link_mode = -1;
+	cmd->base.speed = SPEED_UNKNOWN;
+	cmd->base.duplex = DUPLEX_UNKNOWN;
+	cmd->lanes = 0;
 
 	if (!carrier_ok)
 		return;
 
 	for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
-		if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask)
-			cmd->link_mode = mlxsw_sp1_port_link_mode[i].mask_ethtool;
+		if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask) {
+			link = mlxsw_sp1_port_link_mode[i];
+			ethtool_params_from_link_mode(cmd,
+						      link.mask_ethtool);
+		}
 	}
 }
 
@@ -1672,7 +1678,9 @@ mlxsw_sp2_from_ptys_link_mode(struct mlxsw_sp *mlxsw_sp, bool carrier_ok,
 	struct mlxsw_sp2_port_link_mode link;
 	int i;
 
-	cmd->link_mode = -1;
+	cmd->base.speed = SPEED_UNKNOWN;
+	cmd->base.duplex = DUPLEX_UNKNOWN;
+	cmd->lanes = 0;
 
 	if (!carrier_ok)
 		return;
@@ -1680,7 +1688,8 @@ mlxsw_sp2_from_ptys_link_mode(struct mlxsw_sp *mlxsw_sp, bool carrier_ok,
 	for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
 		if (ptys_eth_proto & mlxsw_sp2_port_link_mode[i].mask) {
 			link = mlxsw_sp2_port_link_mode[i];
-			cmd->link_mode = link.mask_ethtool[1];
+			ethtool_params_from_link_mode(cmd,
+						      link.mask_ethtool[1]);
 		}
 	}
 }
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 7c88dfff7420..cdca84e6dd6b 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -127,7 +127,6 @@ struct ethtool_link_ksettings {
 		__ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising);
 	} link_modes;
 	u32	lanes;
-	enum ethtool_link_mode_bit_indices link_mode;
 };
 
 /**
@@ -574,4 +573,12 @@ struct ethtool_phy_ops {
  */
 void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops);
 
+/*
+ * ethtool_params_from_link_mode - Derive link parameters from a given link mode
+ * @link_ksettings: Link parameters to be derived from the link mode
+ * @link_mode: Link mode
+ */
+void
+ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings,
+			      enum ethtool_link_mode_bit_indices link_mode);
 #endif /* _LINUX_ETHTOOL_H */
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index c6a383dfd6c2..030aa7984a91 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -562,3 +562,19 @@ void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops)
 	rtnl_unlock();
 }
 EXPORT_SYMBOL_GPL(ethtool_set_ethtool_phy_ops);
+
+void
+ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings,
+			      enum ethtool_link_mode_bit_indices link_mode)
+{
+	const struct link_mode_info *link_info;
+
+	if (WARN_ON_ONCE(link_mode >= __ETHTOOL_LINK_MODE_MASK_NBITS))
+		return;
+
+	link_info = &link_mode_params[link_mode];
+	link_ksettings->base.speed = link_info->speed;
+	link_ksettings->lanes = link_info->lanes;
+	link_ksettings->base.duplex = link_info->duplex;
+}
+EXPORT_SYMBOL_GPL(ethtool_params_from_link_mode);
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 24783b71c584..771688e1b0da 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -426,29 +426,13 @@ struct ethtool_link_usettings {
 int __ethtool_get_link_ksettings(struct net_device *dev,
 				 struct ethtool_link_ksettings *link_ksettings)
 {
-	const struct link_mode_info *link_info;
-	int err;
-
 	ASSERT_RTNL();
 
 	if (!dev->ethtool_ops->get_link_ksettings)
 		return -EOPNOTSUPP;
 
 	memset(link_ksettings, 0, sizeof(*link_ksettings));
-
-	link_ksettings->link_mode = -1;
-	err = dev->ethtool_ops->get_link_ksettings(dev, link_ksettings);
-	if (err)
-		return err;
-
-	if (link_ksettings->link_mode != -1) {
-		link_info = &link_mode_params[link_ksettings->link_mode];
-		link_ksettings->base.speed = link_info->speed;
-		link_ksettings->lanes = link_info->lanes;
-		link_ksettings->base.duplex = link_info->duplex;
-	}
-
-	return 0;
+	return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings);
 }
 EXPORT_SYMBOL(__ethtool_get_link_ksettings);
 

From fde32dbe712bc7cea61d8c5ed14e10e17eec8257 Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Wed, 7 Apr 2021 13:06:52 +0300
Subject: [PATCH 1639/1820] ethtool: Add lanes parameter for
 ETHTOOL_LINK_MODE_10000baseR_FEC_BIT

Lanes field is missing for ETHTOOL_LINK_MODE_10000baseR_FEC_BIT
link mode and it causes a failure when trying to set
'speed 10000 lanes 1' on Spectrum-2 machines when autoneg is set to on.

Add the lanes parameter for ETHTOOL_LINK_MODE_10000baseR_FEC_BIT
link mode.

Fixes: c8907043c6ac9 ("ethtool: Get link mode in use instead of speed and duplex parameters")
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/common.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 030aa7984a91..f9dcbad84788 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -273,6 +273,7 @@ const struct link_mode_info link_mode_params[] = {
 	__DEFINE_LINK_MODE_PARAMS(10000, KR, Full),
 	[ETHTOOL_LINK_MODE_10000baseR_FEC_BIT] = {
 		.speed	= SPEED_10000,
+		.lanes	= 1,
 		.duplex = DUPLEX_FULL,
 	},
 	__DEFINE_LINK_MODE_PARAMS(20000, MLD2, Full),

From 8a12f8836145ffe37e9c8733dce18c22fb668b66 Mon Sep 17 00:00:00 2001
From: Anirudh Rayabharam <mail@anirudhrb.com>
Date: Wed, 7 Apr 2021 22:57:22 +0530
Subject: [PATCH 1640/1820] net: hso: fix null-ptr-deref during tty device
 unregistration

Multiple ttys try to claim the same the minor number causing a double
unregistration of the same device. The first unregistration succeeds
but the next one results in a null-ptr-deref.

The get_free_serial_index() function returns an available minor number
but doesn't assign it immediately. The assignment is done by the caller
later. But before this assignment, calls to get_free_serial_index()
would return the same minor number.

Fix this by modifying get_free_serial_index to assign the minor number
immediately after one is found to be and rename it to obtain_minor()
to better reflect what it does. Similary, rename set_serial_by_index()
to release_minor() and modify it to free up the minor number of the
given hso_serial. Every obtain_minor() should have corresponding
release_minor() call.

Fixes: 72dc1c096c705 ("HSO: add option hso driver")
Reported-by: syzbot+c49fe6089f295a05e6f8@syzkaller.appspotmail.com
Tested-by: syzbot+c49fe6089f295a05e6f8@syzkaller.appspotmail.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Anirudh Rayabharam <mail@anirudhrb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/hso.c | 33 ++++++++++++---------------------
 1 file changed, 12 insertions(+), 21 deletions(-)

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 31d51346786a..9bc58e64b5b7 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -611,7 +611,7 @@ static struct hso_serial *get_serial_by_index(unsigned index)
 	return serial;
 }
 
-static int get_free_serial_index(void)
+static int obtain_minor(struct hso_serial *serial)
 {
 	int index;
 	unsigned long flags;
@@ -619,8 +619,10 @@ static int get_free_serial_index(void)
 	spin_lock_irqsave(&serial_table_lock, flags);
 	for (index = 0; index < HSO_SERIAL_TTY_MINORS; index++) {
 		if (serial_table[index] == NULL) {
+			serial_table[index] = serial->parent;
+			serial->minor = index;
 			spin_unlock_irqrestore(&serial_table_lock, flags);
-			return index;
+			return 0;
 		}
 	}
 	spin_unlock_irqrestore(&serial_table_lock, flags);
@@ -629,15 +631,12 @@ static int get_free_serial_index(void)
 	return -1;
 }
 
-static void set_serial_by_index(unsigned index, struct hso_serial *serial)
+static void release_minor(struct hso_serial *serial)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&serial_table_lock, flags);
-	if (serial)
-		serial_table[index] = serial->parent;
-	else
-		serial_table[index] = NULL;
+	serial_table[serial->minor] = NULL;
 	spin_unlock_irqrestore(&serial_table_lock, flags);
 }
 
@@ -2230,6 +2229,7 @@ static int hso_stop_serial_device(struct hso_device *hso_dev)
 static void hso_serial_tty_unregister(struct hso_serial *serial)
 {
 	tty_unregister_device(tty_drv, serial->minor);
+	release_minor(serial);
 }
 
 static void hso_serial_common_free(struct hso_serial *serial)
@@ -2253,24 +2253,22 @@ static void hso_serial_common_free(struct hso_serial *serial)
 static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
 				    int rx_size, int tx_size)
 {
-	int minor;
 	int i;
 
 	tty_port_init(&serial->port);
 
-	minor = get_free_serial_index();
-	if (minor < 0)
+	if (obtain_minor(serial))
 		goto exit2;
 
 	/* register our minor number */
 	serial->parent->dev = tty_port_register_device_attr(&serial->port,
-			tty_drv, minor, &serial->parent->interface->dev,
+			tty_drv, serial->minor, &serial->parent->interface->dev,
 			serial->parent, hso_serial_dev_groups);
-	if (IS_ERR(serial->parent->dev))
+	if (IS_ERR(serial->parent->dev)) {
+		release_minor(serial);
 		goto exit2;
+	}
 
-	/* fill in specific data for later use */
-	serial->minor = minor;
 	serial->magic = HSO_SERIAL_MAGIC;
 	spin_lock_init(&serial->serial_lock);
 	serial->num_rx_urbs = num_urbs;
@@ -2667,9 +2665,6 @@ static struct hso_device *hso_create_bulk_serial_device(
 
 	serial->write_data = hso_std_serial_write_data;
 
-	/* and record this serial */
-	set_serial_by_index(serial->minor, serial);
-
 	/* setup the proc dirs and files if needed */
 	hso_log_port(hso_dev);
 
@@ -2726,9 +2721,6 @@ struct hso_device *hso_create_mux_serial_device(struct usb_interface *interface,
 	serial->shared_int->ref_count++;
 	mutex_unlock(&serial->shared_int->shared_int_lock);
 
-	/* and record this serial */
-	set_serial_by_index(serial->minor, serial);
-
 	/* setup the proc dirs and files if needed */
 	hso_log_port(hso_dev);
 
@@ -3113,7 +3105,6 @@ static void hso_free_interface(struct usb_interface *interface)
 			cancel_work_sync(&serial_table[i]->async_get_intf);
 			hso_serial_tty_unregister(serial);
 			kref_put(&serial_table[i]->ref, hso_serial_ref_free);
-			set_serial_by_index(i, NULL);
 		}
 	}
 

From 50ce6826a48f119baf2794fa384a64efe9bd84a5 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Wed, 7 Apr 2021 02:06:06 +0300
Subject: [PATCH 1641/1820] clk: fixed: fix double free in resource managed
 fixed-factor clock

devm_clk_hw_register_fixed_factor_release(), the release function for
the devm_clk_hw_register_fixed_factor(), calls
clk_hw_unregister_fixed_factor(), which will kfree() the clock. However
after that the devres functions will also kfree the allocated data,
resulting in double free/memory corruption. Just call
clk_hw_unregister() instead, leaving kfree() to devres code.

Reported-by: Rob Clark <robdclark@chromium.org>
Cc: Daniel Palmer <daniel@0x0f.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20210406230606.3007138-1-dmitry.baryshkov@linaro.org
Fixes: 0b9266d295ce ("clk: fixed: add devm helper for clk_hw_register_fixed_factor()")
[sboyd@kernel.org: Remove ugly cast]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-fixed-factor.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c
index 4f7bf3929d6d..4e4b6d367612 100644
--- a/drivers/clk/clk-fixed-factor.c
+++ b/drivers/clk/clk-fixed-factor.c
@@ -66,7 +66,14 @@ EXPORT_SYMBOL_GPL(clk_fixed_factor_ops);
 
 static void devm_clk_hw_register_fixed_factor_release(struct device *dev, void *res)
 {
-	clk_hw_unregister_fixed_factor(&((struct clk_fixed_factor *)res)->hw);
+	struct clk_fixed_factor *fix = res;
+
+	/*
+	 * We can not use clk_hw_unregister_fixed_factor, since it will kfree()
+	 * the hw, resulting in double free. Just unregister the hw and let
+	 * devres code kfree() it.
+	 */
+	clk_hw_unregister(&fix->hw);
 }
 
 static struct clk_hw *

From b6a37a93c9ac3900987c79b726d0bb3699d8db4e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 2 Apr 2021 10:23:17 +0200
Subject: [PATCH 1642/1820] drm/i915: Fix invalid access to ACPI _DSM objects
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

intel_dsm_platform_mux_info() tries to parse the ACPI package data
from _DSM for the debug information, but it assumes the fixed format
without checking what values are stored in the elements actually.
When an unexpected value is returned from BIOS, it may lead to GPF or
NULL dereference, as reported recently.

Add the checks of the contents in the returned values and skip the
values for invalid cases.

v1->v2: Check the info contents before dereferencing, too

BugLink: http://bugzilla.opensuse.org/show_bug.cgi?id=1184074
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210402082317.871-1-tiwai@suse.de
(cherry picked from commit 337d7a1621c7f02af867229990ac67c97da1b53a)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_acpi.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_acpi.c b/drivers/gpu/drm/i915/display/intel_acpi.c
index e21fb14d5e07..833d0c1be4f1 100644
--- a/drivers/gpu/drm/i915/display/intel_acpi.c
+++ b/drivers/gpu/drm/i915/display/intel_acpi.c
@@ -84,13 +84,31 @@ static void intel_dsm_platform_mux_info(acpi_handle dhandle)
 		return;
 	}
 
+	if (!pkg->package.count) {
+		DRM_DEBUG_DRIVER("no connection in _DSM\n");
+		return;
+	}
+
 	connector_count = &pkg->package.elements[0];
 	DRM_DEBUG_DRIVER("MUX info connectors: %lld\n",
 		  (unsigned long long)connector_count->integer.value);
 	for (i = 1; i < pkg->package.count; i++) {
 		union acpi_object *obj = &pkg->package.elements[i];
-		union acpi_object *connector_id = &obj->package.elements[0];
-		union acpi_object *info = &obj->package.elements[1];
+		union acpi_object *connector_id;
+		union acpi_object *info;
+
+		if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < 2) {
+			DRM_DEBUG_DRIVER("Invalid object for MUX #%d\n", i);
+			continue;
+		}
+
+		connector_id = &obj->package.elements[0];
+		info = &obj->package.elements[1];
+		if (info->type != ACPI_TYPE_BUFFER || info->buffer.length < 4) {
+			DRM_DEBUG_DRIVER("Invalid info for MUX obj #%d\n", i);
+			continue;
+		}
+
 		DRM_DEBUG_DRIVER("Connector id: 0x%016llx\n",
 			  (unsigned long long)connector_id->integer.value);
 		DRM_DEBUG_DRIVER("  port id: %s\n",

From e1ad897b9c738d5550be6762bf3a6ef1672259a4 Mon Sep 17 00:00:00 2001
From: Kamal Heib <kamalheib1@gmail.com>
Date: Sun, 4 Apr 2021 15:55:01 +0300
Subject: [PATCH 1643/1820] RDMA/qedr: Fix kernel panic when trying to access
 recv_cq

As INI QP does not require a recv_cq, avoid the following null pointer
dereference by checking if the qp_type is not INI before trying to extract
the recv_cq.

BUG: kernel NULL pointer dereference, address: 00000000000000e0
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: 0000 [#1] SMP PTI
 CPU: 0 PID: 54250 Comm: mpitests-IMB-MP Not tainted 5.12.0-rc5 #1
 Hardware name: Dell Inc. PowerEdge R320/0KM5PX, BIOS 2.7.0 08/19/2019
 RIP: 0010:qedr_create_qp+0x378/0x820 [qedr]
 Code: 02 00 00 50 e8 29 d4 a9 d1 48 83 c4 18 e9 65 fe ff ff 48 8b 53 10 48 8b 43 18 44 8b 82 e0 00 00 00 45 85 c0 0f 84 10 74 00 00 <8b> b8 e0 00 00 00 85 ff 0f 85 50 fd ff ff e9 fd 73 00 00 48 8d bd
 RSP: 0018:ffff9c8f056f7a70 EFLAGS: 00010202
 RAX: 0000000000000000 RBX: ffff9c8f056f7b58 RCX: 0000000000000009
 RDX: ffff8c41a9744c00 RSI: ffff9c8f056f7b58 RDI: ffff8c41c0dfa280
 RBP: ffff8c41c0dfa280 R08: 0000000000000002 R09: 0000000000000001
 R10: 0000000000000000 R11: ffff8c41e06fc608 R12: ffff8c4194052000
 R13: 0000000000000000 R14: ffff8c4191546070 R15: ffff8c41c0dfa280
 FS:  00007f78b2787b80(0000) GS:ffff8c43a3200000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00000000000000e0 CR3: 00000001011d6002 CR4: 00000000001706f0
 Call Trace:
  ib_uverbs_handler_UVERBS_METHOD_QP_CREATE+0x4e4/0xb90 [ib_uverbs]
  ? ib_uverbs_cq_event_handler+0x30/0x30 [ib_uverbs]
  ib_uverbs_run_method+0x6f6/0x7a0 [ib_uverbs]
  ? ib_uverbs_handler_UVERBS_METHOD_QP_DESTROY+0x70/0x70 [ib_uverbs]
  ? __cond_resched+0x15/0x30
  ? __kmalloc+0x5a/0x440
  ib_uverbs_cmd_verbs+0x195/0x360 [ib_uverbs]
  ? xa_load+0x6e/0x90
  ? cred_has_capability+0x7c/0x130
  ? avc_has_extended_perms+0x17f/0x440
  ? vma_link+0xae/0xb0
  ? vma_set_page_prot+0x2a/0x60
  ? mmap_region+0x298/0x6c0
  ? do_mmap+0x373/0x520
  ? selinux_file_ioctl+0x17f/0x220
  ib_uverbs_ioctl+0xa7/0x110 [ib_uverbs]
  __x64_sys_ioctl+0x84/0xc0
  do_syscall_64+0x33/0x40
  entry_SYSCALL_64_after_hwframe+0x44/0xae
 RIP: 0033:0x7f78b120262b

Fixes: 06e8d1df46ed ("RDMA/qedr: Add support for user mode XRC-SRQ's")
Link: https://lore.kernel.org/r/20210404125501.154789-1-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/qedr/verbs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 0eb6a7a618e0..9ea542270ed4 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -1244,7 +1244,8 @@ static int qedr_check_qp_attrs(struct ib_pd *ibpd, struct qedr_dev *dev,
 	 * TGT QP isn't associated with RQ/SQ
 	 */
 	if ((attrs->qp_type != IB_QPT_GSI) && (dev->gsi_qp_created) &&
-	    (attrs->qp_type != IB_QPT_XRC_TGT)) {
+	    (attrs->qp_type != IB_QPT_XRC_TGT) &&
+	    (attrs->qp_type != IB_QPT_XRC_INI)) {
 		struct qedr_cq *send_cq = get_qedr_cq(attrs->send_cq);
 		struct qedr_cq *recv_cq = get_qedr_cq(attrs->recv_cq);
 

From 9ad6e9cb39c66366bf7b9aece114aca277981a1f Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Wed, 7 Apr 2021 09:24:43 +0200
Subject: [PATCH 1644/1820] selinux: fix race between old and new sidtab

Since commit 1b8b31a2e612 ("selinux: convert policy read-write lock to
RCU"), there is a small window during policy load where the new policy
pointer has already been installed, but some threads may still be
holding the old policy pointer in their read-side RCU critical sections.
This means that there may be conflicting attempts to add a new SID entry
to both tables via sidtab_context_to_sid().

See also (and the rest of the thread):
https://lore.kernel.org/selinux/CAFqZXNvfux46_f8gnvVvRYMKoes24nwm2n3sPbMjrB8vKTW00g@mail.gmail.com/

Fix this by installing the new policy pointer under the old sidtab's
spinlock along with marking the old sidtab as "frozen". Then, if an
attempt to add new entry to a "frozen" sidtab is detected, make
sidtab_context_to_sid() return -ESTALE to indicate that a new policy
has been installed and that the caller will have to abort the policy
transaction and try again after re-taking the policy pointer (which is
guaranteed to be a newer policy). This requires adding a retry-on-ESTALE
logic to all callers of sidtab_context_to_sid(), but fortunately these
are easy to determine and aren't that many.

This seems to be the simplest solution for this problem, even if it
looks somewhat ugly. Note that other places in the kernel (e.g.
do_mknodat() in fs/namei.c) use similar stale-retry patterns, so I think
it's reasonable.

Cc: stable@vger.kernel.org
Fixes: 1b8b31a2e612 ("selinux: convert policy read-write lock to RCU")
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/ss/services.c | 157 +++++++++++++++++++++++++--------
 security/selinux/ss/sidtab.c   |  21 +++++
 security/selinux/ss/sidtab.h   |   4 +
 3 files changed, 145 insertions(+), 37 deletions(-)

diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 4a907e008a98..6f095c0dc658 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1551,6 +1551,7 @@ static int security_context_to_sid_core(struct selinux_state *state,
 		if (!str)
 			goto out;
 	}
+retry:
 	rcu_read_lock();
 	policy = rcu_dereference(state->policy);
 	policydb = &policy->policydb;
@@ -1564,6 +1565,15 @@ static int security_context_to_sid_core(struct selinux_state *state,
 	} else if (rc)
 		goto out_unlock;
 	rc = sidtab_context_to_sid(sidtab, &context, sid);
+	if (rc == -ESTALE) {
+		rcu_read_unlock();
+		if (context.str) {
+			str = context.str;
+			context.str = NULL;
+		}
+		context_destroy(&context);
+		goto retry;
+	}
 	context_destroy(&context);
 out_unlock:
 	rcu_read_unlock();
@@ -1713,7 +1723,7 @@ static int security_compute_sid(struct selinux_state *state,
 	struct selinux_policy *policy;
 	struct policydb *policydb;
 	struct sidtab *sidtab;
-	struct class_datum *cladatum = NULL;
+	struct class_datum *cladatum;
 	struct context *scontext, *tcontext, newcontext;
 	struct sidtab_entry *sentry, *tentry;
 	struct avtab_key avkey;
@@ -1735,6 +1745,8 @@ static int security_compute_sid(struct selinux_state *state,
 		goto out;
 	}
 
+retry:
+	cladatum = NULL;
 	context_init(&newcontext);
 
 	rcu_read_lock();
@@ -1879,6 +1891,11 @@ static int security_compute_sid(struct selinux_state *state,
 	}
 	/* Obtain the sid for the context. */
 	rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid);
+	if (rc == -ESTALE) {
+		rcu_read_unlock();
+		context_destroy(&newcontext);
+		goto retry;
+	}
 out_unlock:
 	rcu_read_unlock();
 	context_destroy(&newcontext);
@@ -2190,6 +2207,7 @@ void selinux_policy_commit(struct selinux_state *state,
 			   struct selinux_load_state *load_state)
 {
 	struct selinux_policy *oldpolicy, *newpolicy = load_state->policy;
+	unsigned long flags;
 	u32 seqno;
 
 	oldpolicy = rcu_dereference_protected(state->policy,
@@ -2211,7 +2229,13 @@ void selinux_policy_commit(struct selinux_state *state,
 	seqno = newpolicy->latest_granting;
 
 	/* Install the new policy. */
-	rcu_assign_pointer(state->policy, newpolicy);
+	if (oldpolicy) {
+		sidtab_freeze_begin(oldpolicy->sidtab, &flags);
+		rcu_assign_pointer(state->policy, newpolicy);
+		sidtab_freeze_end(oldpolicy->sidtab, &flags);
+	} else {
+		rcu_assign_pointer(state->policy, newpolicy);
+	}
 
 	/* Load the policycaps from the new policy */
 	security_load_policycaps(state, newpolicy);
@@ -2355,13 +2379,15 @@ int security_port_sid(struct selinux_state *state,
 	struct policydb *policydb;
 	struct sidtab *sidtab;
 	struct ocontext *c;
-	int rc = 0;
+	int rc;
 
 	if (!selinux_initialized(state)) {
 		*out_sid = SECINITSID_PORT;
 		return 0;
 	}
 
+retry:
+	rc = 0;
 	rcu_read_lock();
 	policy = rcu_dereference(state->policy);
 	policydb = &policy->policydb;
@@ -2380,6 +2406,10 @@ int security_port_sid(struct selinux_state *state,
 		if (!c->sid[0]) {
 			rc = sidtab_context_to_sid(sidtab, &c->context[0],
 						   &c->sid[0]);
+			if (rc == -ESTALE) {
+				rcu_read_unlock();
+				goto retry;
+			}
 			if (rc)
 				goto out;
 		}
@@ -2406,13 +2436,15 @@ int security_ib_pkey_sid(struct selinux_state *state,
 	struct policydb *policydb;
 	struct sidtab *sidtab;
 	struct ocontext *c;
-	int rc = 0;
+	int rc;
 
 	if (!selinux_initialized(state)) {
 		*out_sid = SECINITSID_UNLABELED;
 		return 0;
 	}
 
+retry:
+	rc = 0;
 	rcu_read_lock();
 	policy = rcu_dereference(state->policy);
 	policydb = &policy->policydb;
@@ -2433,6 +2465,10 @@ int security_ib_pkey_sid(struct selinux_state *state,
 			rc = sidtab_context_to_sid(sidtab,
 						   &c->context[0],
 						   &c->sid[0]);
+			if (rc == -ESTALE) {
+				rcu_read_unlock();
+				goto retry;
+			}
 			if (rc)
 				goto out;
 		}
@@ -2458,13 +2494,15 @@ int security_ib_endport_sid(struct selinux_state *state,
 	struct policydb *policydb;
 	struct sidtab *sidtab;
 	struct ocontext *c;
-	int rc = 0;
+	int rc;
 
 	if (!selinux_initialized(state)) {
 		*out_sid = SECINITSID_UNLABELED;
 		return 0;
 	}
 
+retry:
+	rc = 0;
 	rcu_read_lock();
 	policy = rcu_dereference(state->policy);
 	policydb = &policy->policydb;
@@ -2485,6 +2523,10 @@ int security_ib_endport_sid(struct selinux_state *state,
 		if (!c->sid[0]) {
 			rc = sidtab_context_to_sid(sidtab, &c->context[0],
 						   &c->sid[0]);
+			if (rc == -ESTALE) {
+				rcu_read_unlock();
+				goto retry;
+			}
 			if (rc)
 				goto out;
 		}
@@ -2508,7 +2550,7 @@ int security_netif_sid(struct selinux_state *state,
 	struct selinux_policy *policy;
 	struct policydb *policydb;
 	struct sidtab *sidtab;
-	int rc = 0;
+	int rc;
 	struct ocontext *c;
 
 	if (!selinux_initialized(state)) {
@@ -2516,6 +2558,8 @@ int security_netif_sid(struct selinux_state *state,
 		return 0;
 	}
 
+retry:
+	rc = 0;
 	rcu_read_lock();
 	policy = rcu_dereference(state->policy);
 	policydb = &policy->policydb;
@@ -2532,10 +2576,18 @@ int security_netif_sid(struct selinux_state *state,
 		if (!c->sid[0] || !c->sid[1]) {
 			rc = sidtab_context_to_sid(sidtab, &c->context[0],
 						   &c->sid[0]);
+			if (rc == -ESTALE) {
+				rcu_read_unlock();
+				goto retry;
+			}
 			if (rc)
 				goto out;
 			rc = sidtab_context_to_sid(sidtab, &c->context[1],
 						   &c->sid[1]);
+			if (rc == -ESTALE) {
+				rcu_read_unlock();
+				goto retry;
+			}
 			if (rc)
 				goto out;
 		}
@@ -2585,6 +2637,7 @@ int security_node_sid(struct selinux_state *state,
 		return 0;
 	}
 
+retry:
 	rcu_read_lock();
 	policy = rcu_dereference(state->policy);
 	policydb = &policy->policydb;
@@ -2633,6 +2686,10 @@ int security_node_sid(struct selinux_state *state,
 			rc = sidtab_context_to_sid(sidtab,
 						   &c->context[0],
 						   &c->sid[0]);
+			if (rc == -ESTALE) {
+				rcu_read_unlock();
+				goto retry;
+			}
 			if (rc)
 				goto out;
 		}
@@ -2674,18 +2731,24 @@ int security_get_user_sids(struct selinux_state *state,
 	struct sidtab *sidtab;
 	struct context *fromcon, usercon;
 	u32 *mysids = NULL, *mysids2, sid;
-	u32 mynel = 0, maxnel = SIDS_NEL;
+	u32 i, j, mynel, maxnel = SIDS_NEL;
 	struct user_datum *user;
 	struct role_datum *role;
 	struct ebitmap_node *rnode, *tnode;
-	int rc = 0, i, j;
+	int rc;
 
 	*sids = NULL;
 	*nel = 0;
 
 	if (!selinux_initialized(state))
-		goto out;
+		return 0;
 
+	mysids = kcalloc(maxnel, sizeof(*mysids), GFP_KERNEL);
+	if (!mysids)
+		return -ENOMEM;
+
+retry:
+	mynel = 0;
 	rcu_read_lock();
 	policy = rcu_dereference(state->policy);
 	policydb = &policy->policydb;
@@ -2705,11 +2768,6 @@ int security_get_user_sids(struct selinux_state *state,
 
 	usercon.user = user->value;
 
-	rc = -ENOMEM;
-	mysids = kcalloc(maxnel, sizeof(*mysids), GFP_ATOMIC);
-	if (!mysids)
-		goto out_unlock;
-
 	ebitmap_for_each_positive_bit(&user->roles, rnode, i) {
 		role = policydb->role_val_to_struct[i];
 		usercon.role = i + 1;
@@ -2721,6 +2779,10 @@ int security_get_user_sids(struct selinux_state *state,
 				continue;
 
 			rc = sidtab_context_to_sid(sidtab, &usercon, &sid);
+			if (rc == -ESTALE) {
+				rcu_read_unlock();
+				goto retry;
+			}
 			if (rc)
 				goto out_unlock;
 			if (mynel < maxnel) {
@@ -2743,14 +2805,14 @@ out_unlock:
 	rcu_read_unlock();
 	if (rc || !mynel) {
 		kfree(mysids);
-		goto out;
+		return rc;
 	}
 
 	rc = -ENOMEM;
 	mysids2 = kcalloc(mynel, sizeof(*mysids2), GFP_KERNEL);
 	if (!mysids2) {
 		kfree(mysids);
-		goto out;
+		return rc;
 	}
 	for (i = 0, j = 0; i < mynel; i++) {
 		struct av_decision dummy_avd;
@@ -2763,12 +2825,10 @@ out_unlock:
 			mysids2[j++] = mysids[i];
 		cond_resched();
 	}
-	rc = 0;
 	kfree(mysids);
 	*sids = mysids2;
 	*nel = j;
-out:
-	return rc;
+	return 0;
 }
 
 /**
@@ -2781,6 +2841,9 @@ out:
  * Obtain a SID to use for a file in a filesystem that
  * cannot support xattr or use a fixed labeling behavior like
  * transition SIDs or task SIDs.
+ *
+ * WARNING: This function may return -ESTALE, indicating that the caller
+ * must retry the operation after re-acquiring the policy pointer!
  */
 static inline int __security_genfs_sid(struct selinux_policy *policy,
 				       const char *fstype,
@@ -2859,11 +2922,13 @@ int security_genfs_sid(struct selinux_state *state,
 		return 0;
 	}
 
-	rcu_read_lock();
-	policy = rcu_dereference(state->policy);
-	retval = __security_genfs_sid(policy,
-				fstype, path, orig_sclass, sid);
-	rcu_read_unlock();
+	do {
+		rcu_read_lock();
+		policy = rcu_dereference(state->policy);
+		retval = __security_genfs_sid(policy, fstype, path,
+					      orig_sclass, sid);
+		rcu_read_unlock();
+	} while (retval == -ESTALE);
 	return retval;
 }
 
@@ -2886,7 +2951,7 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb)
 	struct selinux_policy *policy;
 	struct policydb *policydb;
 	struct sidtab *sidtab;
-	int rc = 0;
+	int rc;
 	struct ocontext *c;
 	struct superblock_security_struct *sbsec = sb->s_security;
 	const char *fstype = sb->s_type->name;
@@ -2897,6 +2962,8 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb)
 		return 0;
 	}
 
+retry:
+	rc = 0;
 	rcu_read_lock();
 	policy = rcu_dereference(state->policy);
 	policydb = &policy->policydb;
@@ -2914,6 +2981,10 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb)
 		if (!c->sid[0]) {
 			rc = sidtab_context_to_sid(sidtab, &c->context[0],
 						   &c->sid[0]);
+			if (rc == -ESTALE) {
+				rcu_read_unlock();
+				goto retry;
+			}
 			if (rc)
 				goto out;
 		}
@@ -2921,6 +2992,10 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb)
 	} else {
 		rc = __security_genfs_sid(policy, fstype, "/",
 					SECCLASS_DIR, &sbsec->sid);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			goto retry;
+		}
 		if (rc) {
 			sbsec->behavior = SECURITY_FS_USE_NONE;
 			rc = 0;
@@ -3130,12 +3205,13 @@ int security_sid_mls_copy(struct selinux_state *state,
 	u32 len;
 	int rc;
 
-	rc = 0;
 	if (!selinux_initialized(state)) {
 		*new_sid = sid;
-		goto out;
+		return 0;
 	}
 
+retry:
+	rc = 0;
 	context_init(&newcon);
 
 	rcu_read_lock();
@@ -3194,10 +3270,14 @@ int security_sid_mls_copy(struct selinux_state *state,
 		}
 	}
 	rc = sidtab_context_to_sid(sidtab, &newcon, new_sid);
+	if (rc == -ESTALE) {
+		rcu_read_unlock();
+		context_destroy(&newcon);
+		goto retry;
+	}
 out_unlock:
 	rcu_read_unlock();
 	context_destroy(&newcon);
-out:
 	return rc;
 }
 
@@ -3790,6 +3870,8 @@ int security_netlbl_secattr_to_sid(struct selinux_state *state,
 		return 0;
 	}
 
+retry:
+	rc = 0;
 	rcu_read_lock();
 	policy = rcu_dereference(state->policy);
 	policydb = &policy->policydb;
@@ -3816,23 +3898,24 @@ int security_netlbl_secattr_to_sid(struct selinux_state *state,
 				goto out;
 		}
 		rc = -EIDRM;
-		if (!mls_context_isvalid(policydb, &ctx_new))
-			goto out_free;
+		if (!mls_context_isvalid(policydb, &ctx_new)) {
+			ebitmap_destroy(&ctx_new.range.level[0].cat);
+			goto out;
+		}
 
 		rc = sidtab_context_to_sid(sidtab, &ctx_new, sid);
+		ebitmap_destroy(&ctx_new.range.level[0].cat);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			goto retry;
+		}
 		if (rc)
-			goto out_free;
+			goto out;
 
 		security_netlbl_cache_add(secattr, *sid);
-
-		ebitmap_destroy(&ctx_new.range.level[0].cat);
 	} else
 		*sid = SECSID_NULL;
 
-	rcu_read_unlock();
-	return 0;
-out_free:
-	ebitmap_destroy(&ctx_new.range.level[0].cat);
 out:
 	rcu_read_unlock();
 	return rc;
diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c
index 5ee190bd30f5..656d50b09f76 100644
--- a/security/selinux/ss/sidtab.c
+++ b/security/selinux/ss/sidtab.c
@@ -39,6 +39,7 @@ int sidtab_init(struct sidtab *s)
 	for (i = 0; i < SECINITSID_NUM; i++)
 		s->isids[i].set = 0;
 
+	s->frozen = false;
 	s->count = 0;
 	s->convert = NULL;
 	hash_init(s->context_to_sid);
@@ -281,6 +282,15 @@ int sidtab_context_to_sid(struct sidtab *s, struct context *context,
 	if (*sid)
 		goto out_unlock;
 
+	if (unlikely(s->frozen)) {
+		/*
+		 * This sidtab is now frozen - tell the caller to abort and
+		 * get the new one.
+		 */
+		rc = -ESTALE;
+		goto out_unlock;
+	}
+
 	count = s->count;
 	convert = s->convert;
 
@@ -474,6 +484,17 @@ void sidtab_cancel_convert(struct sidtab *s)
 	spin_unlock_irqrestore(&s->lock, flags);
 }
 
+void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock)
+{
+	spin_lock_irqsave(&s->lock, *flags);
+	s->frozen = true;
+	s->convert = NULL;
+}
+void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock)
+{
+	spin_unlock_irqrestore(&s->lock, *flags);
+}
+
 static void sidtab_destroy_entry(struct sidtab_entry *entry)
 {
 	context_destroy(&entry->context);
diff --git a/security/selinux/ss/sidtab.h b/security/selinux/ss/sidtab.h
index 80c744d07ad6..4eff0e49dcb2 100644
--- a/security/selinux/ss/sidtab.h
+++ b/security/selinux/ss/sidtab.h
@@ -86,6 +86,7 @@ struct sidtab {
 	u32 count;
 	/* access only under spinlock */
 	struct sidtab_convert_params *convert;
+	bool frozen;
 	spinlock_t lock;
 
 #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0
@@ -125,6 +126,9 @@ int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params);
 
 void sidtab_cancel_convert(struct sidtab *s);
 
+void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock);
+void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock);
+
 int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid);
 
 void sidtab_destroy(struct sidtab *s);

From 0dcf8febcb7b9d42bec98bc068e01d1a6ea578b8 Mon Sep 17 00:00:00 2001
From: Mike Christie <michael.christie@oracle.com>
Date: Tue, 6 Apr 2021 12:17:46 -0500
Subject: [PATCH 1645/1820] scsi: iscsi: Fix iSCSI cls conn state

In commit 9e67600ed6b8 ("scsi: iscsi: Fix race condition between login and
sync thread") I missed that libiscsi was now setting the iSCSI class state,
and that patch ended up resetting the state during conn stoppage and using
the wrong state value during ep_disconnect. This patch moves the setting of
the class state to the class module and then fixes the two issues above.

Link: https://lore.kernel.org/r/20210406171746.5016-1-michael.christie@oracle.com
Fixes: 9e67600ed6b8 ("scsi: iscsi: Fix race condition between login and sync thread")
Cc: Gulam Mohamed <gulam.mohamed@oracle.com>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/libiscsi.c             | 26 +++-----------------------
 drivers/scsi/scsi_transport_iscsi.c | 20 ++++++++++++++++----
 2 files changed, 19 insertions(+), 27 deletions(-)

diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 7ad11e42306d..bfd2aaa9b66b 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -3179,9 +3179,10 @@ fail_mgmt_tasks(struct iscsi_session *session, struct iscsi_conn *conn)
 	}
 }
 
-static void iscsi_start_session_recovery(struct iscsi_session *session,
-					 struct iscsi_conn *conn, int flag)
+void iscsi_conn_stop(struct iscsi_cls_conn *cls_conn, int flag)
 {
+	struct iscsi_conn *conn = cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
 	int old_stop_stage;
 
 	mutex_lock(&session->eh_mutex);
@@ -3239,27 +3240,6 @@ static void iscsi_start_session_recovery(struct iscsi_session *session,
 	spin_unlock_bh(&session->frwd_lock);
 	mutex_unlock(&session->eh_mutex);
 }
-
-void iscsi_conn_stop(struct iscsi_cls_conn *cls_conn, int flag)
-{
-	struct iscsi_conn *conn = cls_conn->dd_data;
-	struct iscsi_session *session = conn->session;
-
-	switch (flag) {
-	case STOP_CONN_RECOVER:
-		cls_conn->state = ISCSI_CONN_FAILED;
-		break;
-	case STOP_CONN_TERM:
-		cls_conn->state = ISCSI_CONN_DOWN;
-		break;
-	default:
-		iscsi_conn_printk(KERN_ERR, conn,
-				  "invalid stop flag %d\n", flag);
-		return;
-	}
-
-	iscsi_start_session_recovery(session, conn, flag);
-}
 EXPORT_SYMBOL_GPL(iscsi_conn_stop);
 
 int iscsi_conn_bind(struct iscsi_cls_session *cls_session,
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index bebfb355abdf..21a2d997a72e 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2470,10 +2470,22 @@ static void iscsi_if_stop_conn(struct iscsi_cls_conn *conn, int flag)
 	 * it works.
 	 */
 	mutex_lock(&conn_mutex);
-	conn->transport->stop_conn(conn, flag);
-	conn->state = ISCSI_CONN_DOWN;
-	mutex_unlock(&conn_mutex);
+	switch (flag) {
+	case STOP_CONN_RECOVER:
+		conn->state = ISCSI_CONN_FAILED;
+		break;
+	case STOP_CONN_TERM:
+		conn->state = ISCSI_CONN_DOWN;
+		break;
+	default:
+		iscsi_cls_conn_printk(KERN_ERR, conn,
+				      "invalid stop flag %d\n", flag);
+		goto unlock;
+	}
 
+	conn->transport->stop_conn(conn, flag);
+unlock:
+	mutex_unlock(&conn_mutex);
 }
 
 static void stop_conn_work_fn(struct work_struct *work)
@@ -2961,7 +2973,7 @@ static int iscsi_if_ep_disconnect(struct iscsi_transport *transport,
 		mutex_lock(&conn->ep_mutex);
 		conn->ep = NULL;
 		mutex_unlock(&conn->ep_mutex);
-		conn->state = ISCSI_CONN_DOWN;
+		conn->state = ISCSI_CONN_FAILED;
 	}
 
 	transport->ep_disconnect(ep);

From 176ddd89171ddcf661862d90c5d257877f7326d6 Mon Sep 17 00:00:00 2001
From: Jolly Shah <jollys@google.com>
Date: Thu, 18 Mar 2021 15:56:32 -0700
Subject: [PATCH 1646/1820] scsi: libsas: Reset num_scatter if libata marks qc
 as NODATA

When the cache_type for the SCSI device is changed, the SCSI layer issues a
MODE_SELECT command. The caching mode details are communicated via a
request buffer associated with the SCSI command with data direction set as
DMA_TO_DEVICE (scsi_mode_select()). When this command reaches the libata
layer, as a part of generic initial setup, libata layer sets up the
scatterlist for the command using the SCSI command (ata_scsi_qc_new()).
This command is then translated by the libata layer into
ATA_CMD_SET_FEATURES (ata_scsi_mode_select_xlat()). The libata layer treats
this as a non-data command (ata_mselect_caching()), since it only needs an
ATA taskfile to pass the caching on/off information to the device. It does
not need the scatterlist that has been setup, so it does not perform
dma_map_sg() on the scatterlist (ata_qc_issue()). Unfortunately, when this
command reaches the libsas layer (sas_ata_qc_issue()), libsas layer sees it
as a non-data command with a scatterlist. It cannot extract the correct DMA
length since the scatterlist has not been mapped with dma_map_sg() for a
DMA operation. When this partially constructed SAS task reaches pm80xx
LLDD, it results in the following warning:

"pm80xx_chip_sata_req 6058: The sg list address
start_addr=0x0000000000000000 data_len=0x0end_addr_high=0xffffffff
end_addr_low=0xffffffff has crossed 4G boundary"

Update libsas to handle ATA non-data commands separately so num_scatter and
total_xfer_len remain 0.

Link: https://lore.kernel.org/r/20210318225632.2481291-1-jollys@google.com
Fixes: 53de092f47ff ("scsi: libsas: Set data_dir as DMA_NONE if libata marks qc as NODATA")
Tested-by: Luo Jiaxing <luojiaxing@huawei.com>
Reviewed-by: John Garry <john.garry@huawei.com>
Signed-off-by: Jolly Shah <jollys@google.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/libsas/sas_ata.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 024e5a550759..8b9a39077dba 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -201,18 +201,17 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 		memcpy(task->ata_task.atapi_packet, qc->cdb, qc->dev->cdb_len);
 		task->total_xfer_len = qc->nbytes;
 		task->num_scatter = qc->n_elem;
+		task->data_dir = qc->dma_dir;
+	} else if (qc->tf.protocol == ATA_PROT_NODATA) {
+		task->data_dir = DMA_NONE;
 	} else {
 		for_each_sg(qc->sg, sg, qc->n_elem, si)
 			xfer += sg_dma_len(sg);
 
 		task->total_xfer_len = xfer;
 		task->num_scatter = si;
-	}
-
-	if (qc->tf.protocol == ATA_PROT_NODATA)
-		task->data_dir = DMA_NONE;
-	else
 		task->data_dir = qc->dma_dir;
+	}
 	task->scatter = qc->sg;
 	task->ata_task.retry_count = 1;
 	task->task_state_flags = SAS_TASK_STATE_PENDING;

From 4e456b30f78c429b183db420e23b26cde7e03a78 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 31 Mar 2021 14:35:24 +0000
Subject: [PATCH 1647/1820] cifs: On cifs_reconnect, resolve the hostname
 again.

On cifs_reconnect, make sure that DNS resolution happens again.
It could be the cause of connection to go dead in the first place.

This also contains the fix for a build issue identified by Intel bot.
Reported-by: kernel test robot <lkp@intel.com>

Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Reviewed-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
CC: <stable@vger.kernel.org> # 5.11+
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/Kconfig   |  3 +--
 fs/cifs/Makefile  |  5 +++--
 fs/cifs/connect.c | 17 ++++++++++++++++-
 3 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index fe03cbdae959..bf52e9326ebe 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -18,6 +18,7 @@ config CIFS
 	select CRYPTO_AES
 	select CRYPTO_LIB_DES
 	select KEYS
+	select DNS_RESOLVER
 	help
 	  This is the client VFS module for the SMB3 family of NAS protocols,
 	  (including support for the most recent, most secure dialect SMB3.1.1)
@@ -112,7 +113,6 @@ config CIFS_WEAK_PW_HASH
 config CIFS_UPCALL
 	bool "Kerberos/SPNEGO advanced session setup"
 	depends on CIFS
-	select DNS_RESOLVER
 	help
 	  Enables an upcall mechanism for CIFS which accesses userspace helper
 	  utilities to provide SPNEGO packaged (RFC 4178) Kerberos tickets
@@ -179,7 +179,6 @@ config CIFS_DEBUG_DUMP_KEYS
 config CIFS_DFS_UPCALL
 	bool "DFS feature support"
 	depends on CIFS
-	select DNS_RESOLVER
 	help
 	  Distributed File System (DFS) support is used to access shares
 	  transparently in an enterprise name space, even if the share
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index 5213b20843b5..3ee3b7de4ded 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -10,13 +10,14 @@ cifs-y := trace.o cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o \
 	  cifs_unicode.o nterr.o cifsencrypt.o \
 	  readdir.o ioctl.o sess.o export.o smb1ops.o unc.o winucase.o \
 	  smb2ops.o smb2maperror.o smb2transport.o \
-	  smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o
+	  smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o \
+	  dns_resolve.o
 
 cifs-$(CONFIG_CIFS_XATTR) += xattr.o
 
 cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o
 
-cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o dfs_cache.o
+cifs-$(CONFIG_CIFS_DFS_UPCALL) += cifs_dfs_ref.o dfs_cache.o
 
 cifs-$(CONFIG_CIFS_SWN_UPCALL) += netlink.o cifs_swn.o
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index eec8a2052da2..24668eb006c6 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -87,7 +87,6 @@ static void cifs_prune_tlinks(struct work_struct *work);
  *
  * This should be called with server->srv_mutex held.
  */
-#ifdef CONFIG_CIFS_DFS_UPCALL
 static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
 {
 	int rc;
@@ -124,6 +123,7 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
 	return !rc ? -1 : 0;
 }
 
+#ifdef CONFIG_CIFS_DFS_UPCALL
 /* These functions must be called with server->srv_mutex held */
 static void reconn_set_next_dfs_target(struct TCP_Server_Info *server,
 				       struct cifs_sb_info *cifs_sb,
@@ -321,13 +321,28 @@ cifs_reconnect(struct TCP_Server_Info *server)
 #endif
 
 #ifdef CONFIG_CIFS_DFS_UPCALL
+		if (cifs_sb && cifs_sb->origin_fullpath)
 			/*
 			 * Set up next DFS target server (if any) for reconnect. If DFS
 			 * feature is disabled, then we will retry last server we
 			 * connected to before.
 			 */
 			reconn_set_next_dfs_target(server, cifs_sb, &tgt_list, &tgt_it);
+		else {
 #endif
+			/*
+			 * Resolve the hostname again to make sure that IP address is up-to-date.
+			 */
+			rc = reconn_set_ipaddr_from_hostname(server);
+			if (rc) {
+				cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
+						__func__, rc);
+			}
+
+#ifdef CONFIG_CIFS_DFS_UPCALL
+		}
+#endif
+
 
 #ifdef CONFIG_CIFS_SWN_UPCALL
 		}

From d135be0a7fb83f4dd68721b3355fec6de686834c Mon Sep 17 00:00:00 2001
From: Wan Jiabing <wanjiabing@vivo.com>
Date: Thu, 1 Apr 2021 15:51:17 +0800
Subject: [PATCH 1648/1820] fs: cifs: Remove unnecessary struct declaration

struct cifs_readdata is declared twice. One is declared
at 208th line.
And struct cifs_readdata is defined blew.
The declaration here is not needed. Remove the duplicate.

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cifsglob.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 67c056a9a519..ec824ab8c5ca 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1283,8 +1283,6 @@ struct cifs_aio_ctx {
 	bool			direct_io;
 };
 
-struct cifs_readdata;
-
 /* asynchronous read support */
 struct cifs_readdata {
 	struct kref			refcount;

From 0fc9322ab5e1fe6910c9673e1a7ff29f7dd72611 Mon Sep 17 00:00:00 2001
From: Maciek Borzecki <maciek.borzecki@gmail.com>
Date: Tue, 6 Apr 2021 17:02:29 +0200
Subject: [PATCH 1649/1820] cifs: escape spaces in share names

Commit 653a5efb849a ("cifs: update super_operations to show_devname")
introduced the display of devname for cifs mounts. However, when mounting
a share which has a whitespace in the name, that exact share name is also
displayed in mountinfo. Make sure that all whitespace is escaped.

Signed-off-by: Maciek Borzecki <maciek.borzecki@gmail.com>
CC: <stable@vger.kernel.org> # 5.11+
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cifsfs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 099ad9f3660b..5ddd20b62484 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -476,7 +476,8 @@ static int cifs_show_devname(struct seq_file *m, struct dentry *root)
 		seq_puts(m, "none");
 	else {
 		convert_delimiter(devname, '/');
-		seq_puts(m, devname);
+		/* escape all spaces in share names */
+		seq_escape(m, devname, " \t");
 		kfree(devname);
 	}
 	return 0;

From 6ad7f2332e84c46f0c94e73e05b5b7c2bc1a6b74 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 8 Apr 2021 01:54:39 +0100
Subject: [PATCH 1650/1820] io_uring: clear F_REISSUE right after getting it

There are lots of ways r/w request may continue its path after getting
REQ_F_REISSUE, it's not necessarily io-wq and can be, e.g. apoll,
and submitted via  io_async_task_func() -> __io_req_task_submit()

Clear the flag right after getting it, so the next attempt is well
prepared regardless how the request will be executed.

Fixes: 230d50d448ac ("io_uring: move reissue into regular IO path")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/11dcead939343f4e27cab0074d34afcab771bfa4.1617842918.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 65a17d560a73..f1881ac0744b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3294,6 +3294,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 	ret = io_iter_do_read(req, iter);
 
 	if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
+		req->flags &= ~REQ_F_REISSUE;
 		/* IOPOLL retry should happen for io-wq threads */
 		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
 			goto done;
@@ -3417,8 +3418,10 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
 	else
 		ret2 = -EINVAL;
 
-	if (req->flags & REQ_F_REISSUE)
+	if (req->flags & REQ_F_REISSUE) {
+		req->flags &= ~REQ_F_REISSUE;
 		ret2 = -EAGAIN;
+	}
 
 	/*
 	 * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
@@ -6173,7 +6176,6 @@ static void io_wq_submit_work(struct io_wq_work *work)
 		ret = -ECANCELED;
 
 	if (!ret) {
-		req->flags &= ~REQ_F_REISSUE;
 		do {
 			ret = io_issue_sqe(req, 0);
 			/*

From 1b0b6e939f112949089e32ec89fd27796677263a Mon Sep 17 00:00:00 2001
From: xinhui pan <xinhui.pan@amd.com>
Date: Wed, 7 Apr 2021 19:29:39 +0800
Subject: [PATCH 1651/1820] drm/amdgpu: Fix size overflow
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ttm->num_pages is uint32. Hit overflow when << PAGE_SHIFT directly

Fixes: 230c079fdcf4 ("drm/ttm: make num_pages uint32_t")
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 9fd2157b133a..5efa331e3ee8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -906,7 +906,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_bo_device *bdev,
 
 	/* Allocate an SG array and squash pages into it */
 	r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0,
-				      ttm->num_pages << PAGE_SHIFT,
+				      (u64)ttm->num_pages << PAGE_SHIFT,
 				      GFP_KERNEL);
 	if (r)
 		goto release_sg;

From 2efc021060c2aa55e1e8f7b98249d3ea63232fc7 Mon Sep 17 00:00:00 2001
From: xinhui pan <xinhui.pan@amd.com>
Date: Wed, 7 Apr 2021 20:57:50 +0800
Subject: [PATCH 1652/1820] drm/radeon: Fix size overflow
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ttm->num_pages is uint32. Hit overflow when << PAGE_SHIFT directly

Fixes: 230c079fdcf4 ("drm/ttm: make num_pages uint32_t")
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/radeon/radeon_ttm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index e8c66d10478f..78893bea85ae 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -364,7 +364,7 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, struct ttm_tt *
 	if (gtt->userflags & RADEON_GEM_USERPTR_ANONONLY) {
 		/* check that we only pin down anonymous memory
 		   to prevent problems with writeback */
-		unsigned long end = gtt->userptr + ttm->num_pages * PAGE_SIZE;
+		unsigned long end = gtt->userptr + (u64)ttm->num_pages * PAGE_SIZE;
 		struct vm_area_struct *vma;
 		vma = find_vma(gtt->usermm, gtt->userptr);
 		if (!vma || vma->vm_file || vma->vm_end < end)
@@ -386,7 +386,7 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, struct ttm_tt *
 	} while (pinned < ttm->num_pages);
 
 	r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0,
-				      ttm->num_pages << PAGE_SHIFT,
+				      (u64)ttm->num_pages << PAGE_SHIFT,
 				      GFP_KERNEL);
 	if (r)
 		goto release_sg;

From cdcc108a2aced5f9cbc45920e29bf49819e5477f Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 7 Apr 2021 09:28:23 -0400
Subject: [PATCH 1653/1820] drm/amdgpu/smu7: fix CAC setting on TOPAZ

We need to enable MC CAC for mclk switching to work.

Fixes: d765129a719f ("drm/amd/pm: correct sclk/mclk dpm enablement")
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1561
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index d0ec83881fc5..c0565a932a12 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -1224,7 +1224,8 @@ static int smu7_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 		    (hwmgr->chip_id == CHIP_POLARIS10) ||
 		    (hwmgr->chip_id == CHIP_POLARIS11) ||
 		    (hwmgr->chip_id == CHIP_POLARIS12) ||
-		    (hwmgr->chip_id == CHIP_TONGA))
+		    (hwmgr->chip_id == CHIP_TONGA) ||
+		    (hwmgr->chip_id == CHIP_TOPAZ))
 			PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1);
 
 

From c8426b2700b57d2760ff335840a02f66a64b6044 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 7 Apr 2021 11:57:30 +0200
Subject: [PATCH 1654/1820] ALSA: hda/realtek: Fix speaker amp setup on Acer
 Aspire E1

We've got a report about Acer Aspire E1 (PCI SSID 1025:0840) that
loses the speaker output after resume.  With the comparison of COEF
dumps, it was identified that the COEF 0x0d bits 0x6000 corresponds to
the speaker amp.

This patch adds the specific quirk for the device to restore the COEF
bits at the codec (re-)initialization.

BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1183869
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210407095730.12560-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 58946d069ee5..a7544b77d3f7 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3927,6 +3927,15 @@ static void alc271_fixup_dmic(struct hda_codec *codec,
 		snd_hda_sequence_write(codec, verbs);
 }
 
+/* Fix the speaker amp after resume, etc */
+static void alc269vb_fixup_aspire_e1_coef(struct hda_codec *codec,
+					  const struct hda_fixup *fix,
+					  int action)
+{
+	if (action == HDA_FIXUP_ACT_INIT)
+		alc_update_coef_idx(codec, 0x0d, 0x6000, 0x6000);
+}
+
 static void alc269_fixup_pcm_44k(struct hda_codec *codec,
 				 const struct hda_fixup *fix, int action)
 {
@@ -6301,6 +6310,7 @@ enum {
 	ALC283_FIXUP_HEADSET_MIC,
 	ALC255_FIXUP_MIC_MUTE_LED,
 	ALC282_FIXUP_ASPIRE_V5_PINS,
+	ALC269VB_FIXUP_ASPIRE_E1_COEF,
 	ALC280_FIXUP_HP_GPIO4,
 	ALC286_FIXUP_HP_GPIO_LED,
 	ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY,
@@ -6979,6 +6989,10 @@ static const struct hda_fixup alc269_fixups[] = {
 			{ },
 		},
 	},
+	[ALC269VB_FIXUP_ASPIRE_E1_COEF] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269vb_fixup_aspire_e1_coef,
+	},
 	[ALC280_FIXUP_HP_GPIO4] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc280_fixup_hp_gpio4,
@@ -7901,6 +7915,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x0762, "Acer Aspire E1-472", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
 	SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
 	SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
+	SND_PCI_QUIRK(0x1025, 0x0840, "Acer Aspire E1", ALC269VB_FIXUP_ASPIRE_E1_COEF),
 	SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK),
 	SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x1065, "Acer Aspire C20-820", ALC269VC_FIXUP_ACER_HEADSET_MIC),
@@ -8395,6 +8410,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC283_FIXUP_HEADSET_MIC, .name = "alc283-headset"},
 	{.id = ALC255_FIXUP_MIC_MUTE_LED, .name = "alc255-dell-mute"},
 	{.id = ALC282_FIXUP_ASPIRE_V5_PINS, .name = "aspire-v5"},
+	{.id = ALC269VB_FIXUP_ASPIRE_E1_COEF, .name = "aspire-e1-coef"},
 	{.id = ALC280_FIXUP_HP_GPIO4, .name = "hp-gpio4"},
 	{.id = ALC286_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"},
 	{.id = ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY, .name = "hp-gpio2-hotkey"},

From dd0b45538146cb6a54d6da7663b8c3afd16ebcfd Mon Sep 17 00:00:00 2001
From: Seevalamuthu Mariappan <seevalam@codeaurora.org>
Date: Fri, 19 Mar 2021 19:48:52 +0530
Subject: [PATCH 1655/1820] mac80211: clear sta->fast_rx when STA removed from
 4-addr VLAN

In some race conditions, with more clients and traffic configuration,
below crash is seen when making the interface down. sta->fast_rx wasn't
cleared when STA gets removed from 4-addr AP_VLAN interface. The crash is
due to try accessing 4-addr AP_VLAN interface's net_device (fast_rx->dev)
which has been deleted already.

Resolve this by clearing sta->fast_rx pointer when STA removes
from a 4-addr VLAN.

[  239.449529] Unable to handle kernel NULL pointer dereference at virtual address 00000004
[  239.449531] pgd = 80204000
...
[  239.481496] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.4.60 #227
[  239.481591] Hardware name: Generic DT based system
[  239.487665] task: be05b700 ti: be08e000 task.ti: be08e000
[  239.492360] PC is at get_rps_cpu+0x2d4/0x31c
[  239.497823] LR is at 0xbe08fc54
...
[  239.778574] [<80739740>] (get_rps_cpu) from [<8073cb10>] (netif_receive_skb_internal+0x8c/0xac)
[  239.786722] [<8073cb10>] (netif_receive_skb_internal) from [<8073d578>] (napi_gro_receive+0x48/0xc4)
[  239.795267] [<8073d578>] (napi_gro_receive) from [<c7b83e8c>] (ieee80211_mark_rx_ba_filtered_frames+0xbcc/0x12d4 [mac80211])
[  239.804776] [<c7b83e8c>] (ieee80211_mark_rx_ba_filtered_frames [mac80211]) from [<c7b84d4c>] (ieee80211_rx_napi+0x7b8/0x8c8 [mac8
            0211])
[  239.815857] [<c7b84d4c>] (ieee80211_rx_napi [mac80211]) from [<c7f63d7c>] (ath11k_dp_process_rx+0x7bc/0x8c8 [ath11k])
[  239.827757] [<c7f63d7c>] (ath11k_dp_process_rx [ath11k]) from [<c7f5b6c4>] (ath11k_dp_service_srng+0x2c0/0x2e0 [ath11k])
[  239.838484] [<c7f5b6c4>] (ath11k_dp_service_srng [ath11k]) from [<7f55b7dc>] (ath11k_ahb_ext_grp_napi_poll+0x20/0x84 [ath11k_ahb]
            )
[  239.849419] [<7f55b7dc>] (ath11k_ahb_ext_grp_napi_poll [ath11k_ahb]) from [<8073ce1c>] (net_rx_action+0xe0/0x28c)
[  239.860945] [<8073ce1c>] (net_rx_action) from [<80324868>] (__do_softirq+0xe4/0x228)
[  239.871269] [<80324868>] (__do_softirq) from [<80324c48>] (irq_exit+0x98/0x108)
[  239.879080] [<80324c48>] (irq_exit) from [<8035c59c>] (__handle_domain_irq+0x90/0xb4)
[  239.886114] [<8035c59c>] (__handle_domain_irq) from [<8030137c>] (gic_handle_irq+0x50/0x94)
[  239.894100] [<8030137c>] (gic_handle_irq) from [<803024c0>] (__irq_svc+0x40/0x74)

Signed-off-by: Seevalamuthu Mariappan <seevalam@codeaurora.org>
Link: https://lore.kernel.org/r/1616163532-3881-1-git-send-email-seevalam@codeaurora.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 68a0de02b561..860bc35383d5 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1788,8 +1788,10 @@ static int ieee80211_change_station(struct wiphy *wiphy,
 		}
 
 		if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
-		    sta->sdata->u.vlan.sta)
+		    sta->sdata->u.vlan.sta) {
+			ieee80211_clear_fast_rx(sta);
 			RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL);
+		}
 
 		if (test_sta_flag(sta, WLAN_STA_AUTHORIZED))
 			ieee80211_vif_dec_num_mcast(sta->sdata);

From 71826654ce40112f0651b6f4e94c422354f4adb6 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 19 Mar 2021 23:25:11 +0100
Subject: [PATCH 1656/1820] rfkill: revert back to old userspace API by default

Recompiling with the new extended version of struct rfkill_event
broke systemd in *two* ways:
 - It used "sizeof(struct rfkill_event)" to read the event, but
   then complained if it actually got something != 8, this broke
   it on new kernels (that include the updated API);
 - It used sizeof(struct rfkill_event) to write a command, but
   didn't implement the intended expansion protocol where the
   kernel returns only how many bytes it accepted, and errored
   out due to the unexpected smaller size on kernels that didn't
   include the updated API.

Even though systemd has now been fixed, that fix may not be always
deployed, and other applications could potentially have similar
issues.

As such, in the interest of avoiding regressions, revert the
default API "struct rfkill_event" back to the original size.

Instead, add a new "struct rfkill_event_ext" that extends it by
the new field, and even more clearly document that applications
should be prepared for extensions in two ways:
 * write might only accept fewer bytes on older kernels, and
   will return how many to let userspace know which data may
   have been ignored;
 * read might return anything between 8 (the original size) and
   whatever size the application sized its buffer at, indicating
   how much event data was supported by the kernel.

Perhaps that will help avoid such issues in the future and we
won't have to come up with another version of the struct if we
ever need to extend it again.

Applications that want to take advantage of the new field will
have to be modified to use struct rfkill_event_ext instead now,
which comes with the danger of them having already been updated
to use it from 'struct rfkill_event', but I found no evidence
of that, and it's still relatively new.

Cc: stable@vger.kernel.org # 5.11
Reported-by: Takashi Iwai <tiwai@suse.de>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com> # LLVM/Clang v12.0.0-r4 (x86-64)
Link: https://lore.kernel.org/r/20210319232510.f1a139cfdd9c.Ic5c7c9d1d28972059e132ea653a21a427c326678@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/rfkill.h | 82 +++++++++++++++++++++++++++++++------
 net/rfkill/core.c           |  7 ++--
 2 files changed, 73 insertions(+), 16 deletions(-)

diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h
index 03e8af87b364..9b77cfc42efa 100644
--- a/include/uapi/linux/rfkill.h
+++ b/include/uapi/linux/rfkill.h
@@ -86,8 +86,6 @@ enum rfkill_hard_block_reasons {
  * @op: operation code
  * @hard: hard state (0/1)
  * @soft: soft state (0/1)
- * @hard_block_reasons: valid if hard is set. One or several reasons from
- *	&enum rfkill_hard_block_reasons.
  *
  * Structure used for userspace communication on /dev/rfkill,
  * used for events from the kernel and control to the kernel.
@@ -98,22 +96,80 @@ struct rfkill_event {
 	__u8  op;
 	__u8  soft;
 	__u8  hard;
+} __attribute__((packed));
+
+/**
+ * struct rfkill_event_ext - events for userspace on /dev/rfkill
+ * @idx: index of dev rfkill
+ * @type: type of the rfkill struct
+ * @op: operation code
+ * @hard: hard state (0/1)
+ * @soft: soft state (0/1)
+ * @hard_block_reasons: valid if hard is set. One or several reasons from
+ *	&enum rfkill_hard_block_reasons.
+ *
+ * Structure used for userspace communication on /dev/rfkill,
+ * used for events from the kernel and control to the kernel.
+ *
+ * See the extensibility docs below.
+ */
+struct rfkill_event_ext {
+	__u32 idx;
+	__u8  type;
+	__u8  op;
+	__u8  soft;
+	__u8  hard;
+
+	/*
+	 * older kernels will accept/send only up to this point,
+	 * and if extended further up to any chunk marked below
+	 */
+
 	__u8  hard_block_reasons;
 } __attribute__((packed));
 
-/*
- * We are planning to be backward and forward compatible with changes
- * to the event struct, by adding new, optional, members at the end.
- * When reading an event (whether the kernel from userspace or vice
- * versa) we need to accept anything that's at least as large as the
- * version 1 event size, but might be able to accept other sizes in
- * the future.
+/**
+ * DOC: Extensibility
  *
- * One exception is the kernel -- we already have two event sizes in
- * that we've made the 'hard' member optional since our only option
- * is to ignore it anyway.
+ * Originally, we had planned to allow backward and forward compatible
+ * changes by just adding fields at the end of the structure that are
+ * then not reported on older kernels on read(), and not written to by
+ * older kernels on write(), with the kernel reporting the size it did
+ * accept as the result.
+ *
+ * This would have allowed userspace to detect on read() and write()
+ * which kernel structure version it was dealing with, and if was just
+ * recompiled it would have gotten the new fields, but obviously not
+ * accessed them, but things should've continued to work.
+ *
+ * Unfortunately, while actually exercising this mechanism to add the
+ * hard block reasons field, we found that userspace (notably systemd)
+ * did all kinds of fun things not in line with this scheme:
+ *
+ * 1. treat the (expected) short writes as an error;
+ * 2. ask to read sizeof(struct rfkill_event) but then compare the
+ *    actual return value to RFKILL_EVENT_SIZE_V1 and treat any
+ *    mismatch as an error.
+ *
+ * As a consequence, just recompiling with a new struct version caused
+ * things to no longer work correctly on old and new kernels.
+ *
+ * Hence, we've rolled back &struct rfkill_event to the original version
+ * and added &struct rfkill_event_ext. This effectively reverts to the
+ * old behaviour for all userspace, unless it explicitly opts in to the
+ * rules outlined here by using the new &struct rfkill_event_ext.
+ *
+ * Userspace using &struct rfkill_event_ext must adhere to the following
+ * rules
+ *
+ * 1. accept short writes, optionally using them to detect that it's
+ *    running on an older kernel;
+ * 2. accept short reads, knowing that this means it's running on an
+ *    older kernel;
+ * 3. treat reads that are as long as requested as acceptable, not
+ *    checking against RFKILL_EVENT_SIZE_V1 or such.
  */
-#define RFKILL_EVENT_SIZE_V1	8
+#define RFKILL_EVENT_SIZE_V1	sizeof(struct rfkill_event)
 
 /* ioctl for turning off rfkill-input (if present) */
 #define RFKILL_IOC_MAGIC	'R'
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 68d6ef9e59fc..ac15a944573f 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -69,7 +69,7 @@ struct rfkill {
 
 struct rfkill_int_event {
 	struct list_head	list;
-	struct rfkill_event	ev;
+	struct rfkill_event_ext	ev;
 };
 
 struct rfkill_data {
@@ -253,7 +253,8 @@ static void rfkill_global_led_trigger_unregister(void)
 }
 #endif /* CONFIG_RFKILL_LEDS */
 
-static void rfkill_fill_event(struct rfkill_event *ev, struct rfkill *rfkill,
+static void rfkill_fill_event(struct rfkill_event_ext *ev,
+			      struct rfkill *rfkill,
 			      enum rfkill_operation op)
 {
 	unsigned long flags;
@@ -1237,7 +1238,7 @@ static ssize_t rfkill_fop_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *pos)
 {
 	struct rfkill *rfkill;
-	struct rfkill_event ev;
+	struct rfkill_event_ext ev;
 	int ret;
 
 	/* we don't need the 'hard' variable but accept it */

From 1153a74768a9212daadbb50767aa400bc6a0c9b0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 23 Mar 2021 21:05:01 +0100
Subject: [PATCH 1657/1820] mac80211: fix TXQ AC confusion
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Normally, TXQs have

  txq->tid = tid;
  txq->ac = ieee80211_ac_from_tid(tid);

However, the special management TXQ actually has

  txq->tid = IEEE80211_NUM_TIDS; // 16
  txq->ac = IEEE80211_AC_VO;

This makes sense, but ieee80211_ac_from_tid(16) is the same
as ieee80211_ac_from_tid(0) which is just IEEE80211_AC_BE.

Now, normally this is fine. However, if the netdev queues
were stopped, then the code in ieee80211_tx_dequeue() will
propagate the stop from the interface (vif->txqs_stopped[])
if the AC 2 (ieee80211_ac_from_tid(txq->tid)) is marked as
stopped. On wake, however, __ieee80211_wake_txqs() will wake
the TXQ if AC 0 (txq->ac) is woken up.

If a driver stops all queues with ieee80211_stop_tx_queues()
and then wakes them again with ieee80211_wake_tx_queues(),
the ieee80211_wake_txqs() tasklet will run to resync queue
and TXQ state. If all queues were woken, then what'll happen
is that _ieee80211_wake_txqs() will run in order of HW queues
0-3, typically (and certainly for iwlwifi) corresponding to
ACs 0-3, so it'll call __ieee80211_wake_txqs() for each AC in
order 0-3.

When __ieee80211_wake_txqs() is called for AC 0 (VO) that'll
wake up the management TXQ (remember its tid is 16), and the
driver's wake_tx_queue() will be called. That tries to get a
frame, which will immediately *stop* the TXQ again, because
now we check against AC 2, and AC 2 hasn't yet been marked as
woken up again in sdata->vif.txqs_stopped[] since we're only
in the __ieee80211_wake_txqs() call for AC 0.

Thus, the management TXQ will never be started again.

Fix this by checking txq->ac directly instead of calculating
the AC as ieee80211_ac_from_tid(txq->tid).

Fixes: adf8ed01e4fd ("mac80211: add an optional TXQ for other PS-buffered frames")
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20210323210500.bf4d50afea4a.I136ffde910486301f8818f5442e3c9bf8670a9c4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 5d06de61047a..3b3bcefbf657 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3573,7 +3573,7 @@ begin:
 	    test_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags))
 		goto out;
 
-	if (vif->txqs_stopped[ieee80211_ac_from_tid(txq->tid)]) {
+	if (vif->txqs_stopped[txq->ac]) {
 		set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags);
 		goto out;
 	}

From 7d73cd946d4bc7d44cdc5121b1c61d5d71425dea Mon Sep 17 00:00:00 2001
From: Ben Greear <greearb@candelatech.com>
Date: Tue, 30 Mar 2021 16:07:49 -0700
Subject: [PATCH 1658/1820] mac80211: fix time-is-after bug in mlme

The incorrect timeout check caused probing to happen when it did
not need to happen.  This in turn caused tx performance drop
for around 5 seconds in ath10k-ct driver.  Possibly that tx drop
is due to a secondary issue, but fixing the probe to not happen
when traffic is running fixes the symptom.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Fixes: 9abf4e49830d ("mac80211: optimize station connection monitor")
Acked-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/20210330230749.14097-1-greearb@candelatech.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index ce4e3855fec1..96f487fc0071 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4707,7 +4707,10 @@ static void ieee80211_sta_conn_mon_timer(struct timer_list *t)
 		timeout = sta->rx_stats.last_rx;
 	timeout += IEEE80211_CONNECTION_IDLE_TIME;
 
-	if (time_is_before_jiffies(timeout)) {
+	/* If timeout is after now, then update timer to fire at
+	 * the later date, but do not actually probe at this time.
+	 */
+	if (time_is_after_jiffies(timeout)) {
 		mod_timer(&ifmgd->conn_mon_timer, round_jiffies_up(timeout));
 		return;
 	}

From 1b5ab825d9acc0f27d2f25c6252f3526832a9626 Mon Sep 17 00:00:00 2001
From: Du Cheng <ducheng2@gmail.com>
Date: Thu, 8 Apr 2021 00:27:56 +0800
Subject: [PATCH 1659/1820] cfg80211: remove WARN_ON() in cfg80211_sme_connect

A WARN_ON(wdev->conn) would trigger in cfg80211_sme_connect(), if multiple
send_msg(NL80211_CMD_CONNECT) system calls are made from the userland, which
should be anticipated and handled by the wireless driver. Remove this WARN_ON()
to prevent kernel panic if kernel is configured to "panic_on_warn".

Bug reported by syzbot.

Reported-by: syzbot+5f9392825de654244975@syzkaller.appspotmail.com
Signed-off-by: Du Cheng <ducheng2@gmail.com>
Link: https://lore.kernel.org/r/20210407162756.6101-1-ducheng2@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/sme.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 07756ca5e3b5..08a70b4f090c 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -529,7 +529,7 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev,
 		cfg80211_sme_free(wdev);
 	}
 
-	if (WARN_ON(wdev->conn))
+	if (wdev->conn)
 		return -EINPROGRESS;
 
 	wdev->conn = kzalloc(sizeof(*wdev->conn), GFP_KERNEL);

From b57aa17f07c9270e576ef7df09f142978b5a75f0 Mon Sep 17 00:00:00 2001
From: "A. Cody Schuffelen" <schuffelen@google.com>
Date: Thu, 18 Mar 2021 13:04:19 -0700
Subject: [PATCH 1660/1820] virt_wifi: Return micros for BSS TSF values

cfg80211_inform_bss expects to receive a TSF value, but is given the
time since boot in nanoseconds. TSF values are expected to be at
microsecond scale rather than nanosecond scale.

Signed-off-by: A. Cody Schuffelen <schuffelen@google.com>
Link: https://lore.kernel.org/r/20210318200419.1421034-1-schuffelen@google.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/virt_wifi.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c
index c878097f0dda..1df959532c7d 100644
--- a/drivers/net/wireless/virt_wifi.c
+++ b/drivers/net/wireless/virt_wifi.c
@@ -12,6 +12,7 @@
 #include <net/cfg80211.h>
 #include <net/rtnetlink.h>
 #include <linux/etherdevice.h>
+#include <linux/math64.h>
 #include <linux/module.h>
 
 static struct wiphy *common_wiphy;
@@ -168,11 +169,11 @@ static void virt_wifi_scan_result(struct work_struct *work)
 			     scan_result.work);
 	struct wiphy *wiphy = priv_to_wiphy(priv);
 	struct cfg80211_scan_info scan_info = { .aborted = false };
+	u64 tsf = div_u64(ktime_get_boottime_ns(), 1000);
 
 	informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz,
 					   CFG80211_BSS_FTYPE_PRESP,
-					   fake_router_bssid,
-					   ktime_get_boottime_ns(),
+					   fake_router_bssid, tsf,
 					   WLAN_CAPABILITY_ESS, 0,
 					   (void *)&ssid, sizeof(ssid),
 					   DBM_TO_MBM(-50), GFP_KERNEL);

From 315f02c60d9425b38eb8ad7f21b8a35e40db23f9 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Tue, 6 Apr 2021 11:08:51 -0400
Subject: [PATCH 1661/1820] KVM: x86/mmu: preserve pending TLB flush across
 calls to kvm_tdp_mmu_zap_sp

Right now, if a call to kvm_tdp_mmu_zap_sp returns false, the caller
will skip the TLB flush, which is wrong.  There are two ways to fix
it:

- since kvm_tdp_mmu_zap_sp will not yield and therefore will not flush
  the TLB itself, we could change the call to kvm_tdp_mmu_zap_sp to
  use "flush |= ..."

- or we can chain the flush argument through kvm_tdp_mmu_zap_sp down
  to __kvm_tdp_mmu_zap_gfn_range.  Note that kvm_tdp_mmu_zap_sp will
  neither yield nor flush, so flush would never go from true to
  false.

This patch does the former to simplify application to stable kernels,
and to make it further clearer that kvm_tdp_mmu_zap_sp will not flush.

Cc: seanjc@google.com
Fixes: 048f49809c526 ("KVM: x86/mmu: Ensure TLBs are flushed for TDP MMU during NX zapping")
Cc: <stable@vger.kernel.org> # 5.10.x: 048f49809c: KVM: x86/mmu: Ensure TLBs are flushed for TDP MMU during NX zapping
Cc: <stable@vger.kernel.org> # 5.10.x: 33a3164161: KVM: x86/mmu: Don't allow TDP MMU to yield when recovering NX pages
Cc: <stable@vger.kernel.org>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 486aa94ecf1d..951dae4e7175 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5906,7 +5906,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 				      lpage_disallowed_link);
 		WARN_ON_ONCE(!sp->lpage_disallowed);
 		if (is_tdp_mmu_page(sp)) {
-			flush = kvm_tdp_mmu_zap_sp(kvm, sp);
+			flush |= kvm_tdp_mmu_zap_sp(kvm, sp);
 		} else {
 			kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
 			WARN_ON_ONCE(sp->lpage_disallowed);

From b5ac0146492fc5c199de767e492be8a66471011a Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 8 Apr 2021 14:28:27 +0200
Subject: [PATCH 1662/1820] cfg80211: check S1G beacon compat element length

We need to check the length of this element so that we don't
access data beyond its end. Fix that.

Fixes: 9eaffe5078ca ("cfg80211: convert S1G beacon to scan results")
Link: https://lore.kernel.org/r/20210408142826.f6f4525012de.I9fdeff0afdc683a6024e5ea49d2daa3cd2459d11@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/scan.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 019952d4fc7d..758eb7d2a706 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2352,14 +2352,16 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 		return NULL;
 
 	if (ext) {
-		struct ieee80211_s1g_bcn_compat_ie *compat;
-		u8 *ie;
+		const struct ieee80211_s1g_bcn_compat_ie *compat;
+		const struct element *elem;
 
-		ie = (void *)cfg80211_find_ie(WLAN_EID_S1G_BCN_COMPAT,
-					      variable, ielen);
-		if (!ie)
+		elem = cfg80211_find_elem(WLAN_EID_S1G_BCN_COMPAT,
+					  variable, ielen);
+		if (!elem)
 			return NULL;
-		compat = (void *)(ie + 2);
+		if (elem->datalen < sizeof(*compat))
+			return NULL;
+		compat = (void *)elem->data;
 		bssid = ext->u.s1g_beacon.sa;
 		capability = le16_to_cpu(compat->compat_info);
 		beacon_int = le16_to_cpu(compat->beacon_int);

From abaf94ecc9c356d0b885a84edef4905cdd89cfdd Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 8 Apr 2021 14:28:34 +0200
Subject: [PATCH 1663/1820] nl80211: fix potential leak of ACL params

In case nl80211_parse_unsol_bcast_probe_resp() results in an
error, need to "goto out" instead of just returning to free
possibly allocated data.

Fixes: 7443dcd1f171 ("nl80211: Unsolicited broadcast probe response support")
Link: https://lore.kernel.org/r/20210408142833.d8bc2e2e454a.If290b1ba85789726a671ff0b237726d4851b5b0f@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 034af85f79d8..0d34cca38702 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2015-2017	Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
  */
 
 #include <linux/if.h>
@@ -5485,7 +5485,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 			rdev, info->attrs[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP],
 			&params);
 		if (err)
-			return err;
+			goto out;
 	}
 
 	nl80211_calculate_ap_params(&params);

From 35d65ab3fdba1bdecde9ac3424d6d634ea038729 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime@cerno.tech>
Date: Thu, 18 Mar 2021 17:13:27 +0100
Subject: [PATCH 1664/1820] drm/vc4: plane: Remove redundant assignment

The vc4_plane_atomic_async_update function assigns twice in a row the
src_h field in the drm_plane_state structure to the same value. Remove
the second one.

Reviewed-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Link: https://patchwork.freedesktop.org/patch/msgid/20210318161328.1471556-2-maxime@cerno.tech
---
 drivers/gpu/drm/vc4/vc4_plane.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 7322169c0682..1e9c84cf614a 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -1146,7 +1146,6 @@ static void vc4_plane_atomic_async_update(struct drm_plane *plane,
 	plane->state->src_y = state->src_y;
 	plane->state->src_w = state->src_w;
 	plane->state->src_h = state->src_h;
-	plane->state->src_h = state->src_h;
 	plane->state->alpha = state->alpha;
 	plane->state->pixel_blend_mode = state->pixel_blend_mode;
 	plane->state->rotation = state->rotation;

From eb9dfdd1ed40357b99a4201c8534c58c562e48c9 Mon Sep 17 00:00:00 2001
From: Dom Cobley <popcornmix@gmail.com>
Date: Thu, 18 Mar 2021 17:13:28 +0100
Subject: [PATCH 1665/1820] drm/vc4: crtc: Reduce PV fifo threshold on hvs4

Experimentally have found PV on hvs4 reports fifo full
error with expected settings and does not with one less

This appears as:
[drm:drm_atomic_helper_wait_for_flip_done] *ERROR* [CRTC:82:crtc-3] flip_done timed out

with bit 10 of PV_STAT set "HVS driving pixels when the PV FIFO is full"

Fixes: c8b75bca92cb ("drm/vc4: Add KMS support for Raspberry Pi.")
Signed-off-by: Dom Cobley <popcornmix@gmail.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Link: https://patchwork.freedesktop.org/patch/msgid/20210318161328.1471556-3-maxime@cerno.tech
---
 drivers/gpu/drm/vc4/vc4_crtc.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 269390bc586e..76657dcdf9b0 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -210,6 +210,7 @@ static u32 vc4_get_fifo_full_level(struct vc4_crtc *vc4_crtc, u32 format)
 {
 	const struct vc4_crtc_data *crtc_data = vc4_crtc_to_vc4_crtc_data(vc4_crtc);
 	const struct vc4_pv_data *pv_data = vc4_crtc_to_vc4_pv_data(vc4_crtc);
+	struct vc4_dev *vc4 = to_vc4_dev(vc4_crtc->base.dev);
 	u32 fifo_len_bytes = pv_data->fifo_depth;
 
 	/*
@@ -238,6 +239,22 @@ static u32 vc4_get_fifo_full_level(struct vc4_crtc *vc4_crtc, u32 format)
 		if (crtc_data->hvs_output == 5)
 			return 32;
 
+		/*
+		 * It looks like in some situations, we will overflow
+		 * the PixelValve FIFO (with the bit 10 of PV stat being
+		 * set) and stall the HVS / PV, eventually resulting in
+		 * a page flip timeout.
+		 *
+		 * Displaying the video overlay during a playback with
+		 * Kodi on an RPi3 seems to be a great solution with a
+		 * failure rate around 50%.
+		 *
+		 * Removing 1 from the FIFO full level however
+		 * seems to completely remove that issue.
+		 */
+		if (!vc4->hvs->hvs5)
+			return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX - 1;
+
 		return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX;
 	}
 }

From e4d4d456436bfb2fe412ee2cd489f7658449b098 Mon Sep 17 00:00:00 2001
From: Piotr Krysiuk <piotras@gmail.com>
Date: Mon, 5 Apr 2021 22:52:15 +0100
Subject: [PATCH 1666/1820] bpf, x86: Validate computation of branch
 displacements for x86-64

The branch displacement logic in the BPF JIT compilers for x86 assumes
that, for any generated branch instruction, the distance cannot
increase between optimization passes.

But this assumption can be violated due to how the distances are
computed. Specifically, whenever a backward branch is processed in
do_jit(), the distance is computed by subtracting the positions in the
machine code from different optimization passes. This is because part
of addrs[] is already updated for the current optimization pass, before
the branch instruction is visited.

And so the optimizer can expand blocks of machine code in some cases.

This can confuse the optimizer logic, where it assumes that a fixed
point has been reached for all machine code blocks once the total
program size stops changing. And then the JIT compiler can output
abnormal machine code containing incorrect branch displacements.

To mitigate this issue, we assert that a fixed point is reached while
populating the output image. This rejects any problematic programs.
The issue affects both x86-32 and x86-64. We mitigate separately to
ease backporting.

Signed-off-by: Piotr Krysiuk <piotras@gmail.com>
Reviewed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/x86/net/bpf_jit_comp.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b35fc8023884..7f1b3a862e14 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1689,7 +1689,16 @@ emit_jmp:
 		}
 
 		if (image) {
-			if (unlikely(proglen + ilen > oldproglen)) {
+			/*
+			 * When populating the image, assert that:
+			 *
+			 *  i) We do not write beyond the allocated space, and
+			 * ii) addrs[i] did not change from the prior run, in order
+			 *     to validate assumptions made for computing branch
+			 *     displacements.
+			 */
+			if (unlikely(proglen + ilen > oldproglen ||
+				     proglen + ilen != addrs[i])) {
 				pr_err("bpf_jit: fatal error\n");
 				return -EFAULT;
 			}

From 26f55a59dc65ff77cd1c4b37991e26497fc68049 Mon Sep 17 00:00:00 2001
From: Piotr Krysiuk <piotras@gmail.com>
Date: Tue, 6 Apr 2021 21:59:39 +0100
Subject: [PATCH 1667/1820] bpf, x86: Validate computation of branch
 displacements for x86-32

The branch displacement logic in the BPF JIT compilers for x86 assumes
that, for any generated branch instruction, the distance cannot
increase between optimization passes.

But this assumption can be violated due to how the distances are
computed. Specifically, whenever a backward branch is processed in
do_jit(), the distance is computed by subtracting the positions in the
machine code from different optimization passes. This is because part
of addrs[] is already updated for the current optimization pass, before
the branch instruction is visited.

And so the optimizer can expand blocks of machine code in some cases.

This can confuse the optimizer logic, where it assumes that a fixed
point has been reached for all machine code blocks once the total
program size stops changing. And then the JIT compiler can output
abnormal machine code containing incorrect branch displacements.

To mitigate this issue, we assert that a fixed point is reached while
populating the output image. This rejects any problematic programs.
The issue affects both x86-32 and x86-64. We mitigate separately to
ease backporting.

Signed-off-by: Piotr Krysiuk <piotras@gmail.com>
Reviewed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/x86/net/bpf_jit_comp32.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index d17b67c69f89..6a99def7d315 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -2276,7 +2276,16 @@ notyet:
 		}
 
 		if (image) {
-			if (unlikely(proglen + ilen > oldproglen)) {
+			/*
+			 * When populating the image, assert that:
+			 *
+			 *  i) We do not write beyond the allocated space, and
+			 * ii) addrs[i] did not change from the prior run, in order
+			 *     to validate assumptions made for computing branch
+			 *     displacements.
+			 */
+			if (unlikely(proglen + ilen > oldproglen ||
+				     proglen + ilen != addrs[i])) {
 				pr_err("bpf_jit: fatal error\n");
 				return -EFAULT;
 			}

From 9a6847ba1747858ccac53c5aba3e25c54fbdf846 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 8 Apr 2021 15:45:20 +0200
Subject: [PATCH 1668/1820] nl80211: fix beacon head validation

If the beacon head attribute (NL80211_ATTR_BEACON_HEAD)
is too short to even contain the frame control field,
we access uninitialized data beyond the buffer. Fix this
by checking the minimal required size first. We used to
do this until S1G support was added, where the fixed
data portion has a different size.

Reported-and-tested-by: syzbot+72b99dcf4607e8c770f3@syzkaller.appspotmail.com
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: 1d47f1198d58 ("nl80211: correctly validate S1G beacon head")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://lore.kernel.org/r/20210408154518.d9b06d39b4ee.Iff908997b2a4067e8d456b3cb96cab9771d252b8@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 0d34cca38702..b1df42e4f1eb 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -229,9 +229,13 @@ static int validate_beacon_head(const struct nlattr *attr,
 	unsigned int len = nla_len(attr);
 	const struct element *elem;
 	const struct ieee80211_mgmt *mgmt = (void *)data;
-	bool s1g_bcn = ieee80211_is_s1g_beacon(mgmt->frame_control);
 	unsigned int fixedlen, hdrlen;
+	bool s1g_bcn;
 
+	if (len < offsetofend(typeof(*mgmt), frame_control))
+		goto err;
+
+	s1g_bcn = ieee80211_is_s1g_beacon(mgmt->frame_control);
 	if (s1g_bcn) {
 		fixedlen = offsetof(struct ieee80211_ext,
 				    u.s1g_beacon.variable);

From b2d0efc4be7ed320e33eaa9b6dd6f3f6011ffb8e Mon Sep 17 00:00:00 2001
From: Grzegorz Siwik <grzegorz.siwik@intel.com>
Date: Wed, 24 Mar 2021 09:58:27 +0100
Subject: [PATCH 1669/1820] i40e: Fix parameters in aq_get_phy_register()

Change parameters order in aq_get_phy_register() due to wrong
statistics in PHY reported by ethtool. Previously all PHY statistics were
exactly the same for all interfaces
Now statistics are reported correctly - different for different interfaces

Fixes: 0514db37dd78 ("i40e: Extend PHY access with page change flag")
Signed-off-by: Grzegorz Siwik <grzegorz.siwik@intel.com>
Tested-by: Dave Switzer <david.switzer@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 96d5202a73e8..0e92668012e3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -5480,7 +5480,7 @@ static int i40e_get_module_eeprom(struct net_device *netdev,
 
 		status = i40e_aq_get_phy_register(hw,
 				I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE,
-				true, addr, offset, &value, NULL);
+				addr, true, offset, &value, NULL);
 		if (status)
 			return -EIO;
 		data[i] = value;

From 12738ac4754ec92a6a45bf3677d8da780a1412b3 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Fri, 26 Mar 2021 19:43:40 +0100
Subject: [PATCH 1670/1820] i40e: Fix sparse errors in i40e_txrx.c

Remove error handling through pointers. Instead use plain int
to return value from i40e_run_xdp(...).

Previously:
- sparse errors were produced during compilation:
i40e_txrx.c:2338 i40e_run_xdp() error: (-2147483647) too low for ERR_PTR
i40e_txrx.c:2558 i40e_clean_rx_irq() error: 'skb' dereferencing possible ERR_PTR()

- sk_buff* was used to return value, but it has never had valid
pointer to sk_buff. Returned value was always int handled as
a pointer.

Fixes: 0c8493d90b6b ("i40e: add XDP support for pass and drop actions")
Fixes: 2e6893123830 ("i40e: split XDP_TX tail and XDP_REDIRECT map flushing")
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Tested-by: Dave Switzer <david.switzer@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 5747a99122fb..06b4271219b1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2295,8 +2295,7 @@ int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring)
  * @rx_ring: Rx ring being processed
  * @xdp: XDP buffer containing the frame
  **/
-static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
-				    struct xdp_buff *xdp)
+static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 {
 	int err, result = I40E_XDP_PASS;
 	struct i40e_ring *xdp_ring;
@@ -2335,7 +2334,7 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
 	}
 xdp_out:
 	rcu_read_unlock();
-	return ERR_PTR(-result);
+	return result;
 }
 
 /**
@@ -2448,6 +2447,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	unsigned int xdp_xmit = 0;
 	bool failure = false;
 	struct xdp_buff xdp;
+	int xdp_res = 0;
 
 #if (PAGE_SIZE < 8192)
 	frame_sz = i40e_rx_frame_truesize(rx_ring, 0);
@@ -2513,12 +2513,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 			/* At larger PAGE_SIZE, frame_sz depend on len size */
 			xdp.frame_sz = i40e_rx_frame_truesize(rx_ring, size);
 #endif
-			skb = i40e_run_xdp(rx_ring, &xdp);
+			xdp_res = i40e_run_xdp(rx_ring, &xdp);
 		}
 
-		if (IS_ERR(skb)) {
-			unsigned int xdp_res = -PTR_ERR(skb);
-
+		if (xdp_res) {
 			if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
 				xdp_xmit |= xdp_res;
 				i40e_rx_buffer_flip(rx_ring, rx_buffer, size);

From d6d04ee6d2c9bb5084c8f6074195d6aa0024e825 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Fri, 26 Mar 2021 19:43:41 +0100
Subject: [PATCH 1671/1820] i40e: Fix sparse error: uninitialized symbol 'ring'

Init pointer with NULL in default switch case statement.

Previously the error was produced when compiling against sparse.
i40e_debugfs.c:582 i40e_dbg_dump_desc() error: uninitialized symbol 'ring'.

Fixes: 44ea803e2fa7 ("i40e: introduce new dump desc XDP command")
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Tested-by: Dave Switzer <david.switzer@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index d7c13ca9be7d..d627b59ad446 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -578,6 +578,9 @@ static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n,
 	case RING_TYPE_XDP:
 		ring = kmemdup(vsi->xdp_rings[ring_id], sizeof(*ring), GFP_KERNEL);
 		break;
+	default:
+		ring = NULL;
+		break;
 	}
 	if (!ring)
 		return;

From 6b5674fe6b9bf05394886ebcec62b2d7dae88c42 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Fri, 26 Mar 2021 19:43:42 +0100
Subject: [PATCH 1672/1820] i40e: Fix sparse error: 'vsi->netdev' could be null

Remove vsi->netdev->name from the trace.
This is redundant information. With the devinfo trace, the adapter
is already identifiable.

Previously following error was produced when compiling against sparse.
i40e_main.c:2571 i40e_sync_vsi_filters() error:
	we previously assumed 'vsi->netdev' could be null (see line 2323)

Fixes: b603f9dc20af ("i40e: Log info when PF is entering and leaving Allmulti mode.")
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Tested-by: Dave Switzer <david.switzer@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index af6c25fa493c..c0a4bc2caae9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -2560,8 +2560,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 				 i40e_stat_str(hw, aq_ret),
 				 i40e_aq_str(hw, hw->aq.asq_last_status));
 		} else {
-			dev_info(&pf->pdev->dev, "%s is %s allmulti mode.\n",
-				 vsi->netdev->name,
+			dev_info(&pf->pdev->dev, "%s allmulti mode.\n",
 				 cur_multipromisc ? "entering" : "leaving");
 		}
 	}

From 8a1e918d833ca5c391c4ded5dc006e2d1ce6d37c Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Fri, 26 Mar 2021 19:43:43 +0100
Subject: [PATCH 1673/1820] i40e: Fix sparse warning: missing error code 'err'

Set proper return values inside error checking if-statements.

Previously following warning was produced when compiling against sparse.
i40e_main.c:15162 i40e_init_recovery_mode() warn: missing error code 'err'

Fixes: 4ff0ee1af0169 ("i40e: Introduce recovery mode support")
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Tested-by: Dave Switzer <david.switzer@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index c0a4bc2caae9..30ad7c08d0fb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -15138,12 +15138,16 @@ static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw)
 	 * in order to register the netdev
 	 */
 	v_idx = i40e_vsi_mem_alloc(pf, I40E_VSI_MAIN);
-	if (v_idx < 0)
+	if (v_idx < 0) {
+		err = v_idx;
 		goto err_switch_setup;
+	}
 	pf->lan_vsi = v_idx;
 	vsi = pf->vsi[v_idx];
-	if (!vsi)
+	if (!vsi) {
+		err = -EFAULT;
 		goto err_switch_setup;
+	}
 	vsi->alloc_queue_pairs = 1;
 	err = i40e_config_netdev(vsi);
 	if (err)

From 1831da7ea5bdf5531d78bcf81f526faa4c4375fa Mon Sep 17 00:00:00 2001
From: Yongxin Liu <yongxin.liu@windriver.com>
Date: Thu, 1 Apr 2021 11:59:15 -0700
Subject: [PATCH 1674/1820] ice: fix memory leak of aRFS after resuming from
 suspend

In ice_suspend(), ice_clear_interrupt_scheme() is called, and then
irq_free_descs() will be eventually called to free irq and its descriptor.

In ice_resume(), ice_init_interrupt_scheme() is called to allocate new
irqs. However, in ice_rebuild_arfs(), struct irq_glue and struct cpu_rmap
maybe cannot be freed, if the irqs that released in ice_suspend() were
reassigned to other devices, which makes irq descriptor's affinity_notify
lost.

So call ice_free_cpu_rx_rmap() before ice_clear_interrupt_scheme(), which
can make sure all irq_glue and cpu_rmap can be correctly released before
corresponding irq and descriptor are released.

Fix the following memory leak.

unreferenced object 0xffff95bd951afc00 (size 512):
  comm "kworker/0:1", pid 134, jiffies 4294684283 (age 13051.958s)
  hex dump (first 32 bytes):
    18 00 00 00 18 00 18 00 70 fc 1a 95 bd 95 ff ff  ........p.......
    00 00 ff ff 01 00 ff ff 02 00 ff ff 03 00 ff ff  ................
  backtrace:
    [<0000000072e4b914>] __kmalloc+0x336/0x540
    [<0000000054642a87>] alloc_cpu_rmap+0x3b/0xb0
    [<00000000f220deec>] ice_set_cpu_rx_rmap+0x6a/0x110 [ice]
    [<000000002370a632>] ice_probe+0x941/0x1180 [ice]
    [<00000000d692edba>] local_pci_probe+0x47/0xa0
    [<00000000503934f0>] work_for_cpu_fn+0x1a/0x30
    [<00000000555a9e4a>] process_one_work+0x1dd/0x410
    [<000000002c4b414a>] worker_thread+0x221/0x3f0
    [<00000000bb2b556b>] kthread+0x14c/0x170
    [<00000000ad2cf1cd>] ret_from_fork+0x1f/0x30
unreferenced object 0xffff95bd81b0a2a0 (size 96):
  comm "kworker/0:1", pid 134, jiffies 4294684283 (age 13051.958s)
  hex dump (first 32 bytes):
    38 00 00 00 01 00 00 00 e0 ff ff ff 0f 00 00 00  8...............
    b0 a2 b0 81 bd 95 ff ff b0 a2 b0 81 bd 95 ff ff  ................
  backtrace:
    [<00000000582dd5c5>] kmem_cache_alloc_trace+0x31f/0x4c0
    [<000000002659850d>] irq_cpu_rmap_add+0x25/0xe0
    [<00000000495a3055>] ice_set_cpu_rx_rmap+0xb4/0x110 [ice]
    [<000000002370a632>] ice_probe+0x941/0x1180 [ice]
    [<00000000d692edba>] local_pci_probe+0x47/0xa0
    [<00000000503934f0>] work_for_cpu_fn+0x1a/0x30
    [<00000000555a9e4a>] process_one_work+0x1dd/0x410
    [<000000002c4b414a>] worker_thread+0x221/0x3f0
    [<00000000bb2b556b>] kthread+0x14c/0x170
    [<00000000ad2cf1cd>] ret_from_fork+0x1f/0x30

Fixes: 769c500dcc1e ("ice: Add advanced power mgmt for WoL")
Signed-off-by: Yongxin Liu <yongxin.liu@windriver.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 9f1adff85be7..d821c687f239 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4564,6 +4564,7 @@ static int __maybe_unused ice_suspend(struct device *dev)
 			continue;
 		ice_vsi_free_q_vectors(pf->vsi[v]);
 	}
+	ice_free_cpu_rx_rmap(ice_get_main_vsi(pf));
 	ice_clear_interrupt_scheme(pf);
 
 	pci_save_state(pdev);

From d1c803a9ccd7bd3aff5e989ccfb39ed3b799b975 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 5 Apr 2021 10:44:34 +0300
Subject: [PATCH 1675/1820] RDMA/addr: Be strict with gid size

The nla_len() is less than or equal to 16.  If it's less than 16 then end
of the "gid" buffer is uninitialized.

Fixes: ae43f8286730 ("IB/core: Add IP to GID netlink offload")
Link: https://lore.kernel.org/r/20210405074434.264221-1-leon@kernel.org
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/addr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 0abce004a959..65e3e7df8a4b 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -76,7 +76,9 @@ static struct workqueue_struct *addr_wq;
 
 static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = {
 	[LS_NLA_TYPE_DGID] = {.type = NLA_BINARY,
-		.len = sizeof(struct rdma_nla_ls_gid)},
+		.len = sizeof(struct rdma_nla_ls_gid),
+		.validation_type = NLA_VALIDATE_MIN,
+		.min = sizeof(struct rdma_nla_ls_gid)},
 };
 
 static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh)

From 9728463737db027557e8ba315cbbca6b81122c04 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 8 Apr 2021 19:28:03 +0100
Subject: [PATCH 1676/1820] io_uring: fix rw req completion

WARNING: at fs/io_uring.c:8578 io_ring_exit_work.cold+0x0/0x18

As reissuing is now passed back by REQ_F_REISSUE and kiocb_done()
internally uses __io_complete_rw(), it may stop after setting the flag
so leaving a dangling request.

There are tricky edge cases, e.g. reading beyound file, boundary, so
the easiest way is to hand code reissue in kiocb_done() as
__io_complete_rw() was doing for us before.

Fixes: 230d50d448ac ("io_uring: move reissue into regular IO path")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/f602250d292f8a84cca9a01d747744d1e797be26.1617842918.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index f1881ac0744b..bd14327c8e7e 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2762,6 +2762,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
 	struct io_async_rw *io = req->async_data;
+	bool check_reissue = kiocb->ki_complete == io_complete_rw;
 
 	/* add previously done IO, if any */
 	if (io && io->bytes_done > 0) {
@@ -2777,6 +2778,18 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
 		__io_complete_rw(req, ret, 0, issue_flags);
 	else
 		io_rw_done(kiocb, ret);
+
+	if (check_reissue && req->flags & REQ_F_REISSUE) {
+		req->flags &= ~REQ_F_REISSUE;
+		if (!io_rw_reissue(req)) {
+			int cflags = 0;
+
+			req_set_fail_links(req);
+			if (req->flags & REQ_F_BUFFER_SELECTED)
+				cflags = io_put_rw_kbuf(req);
+			__io_req_complete(req, issue_flags, ret, cflags);
+		}
+	}
 }
 
 static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)

From c60eb049f4a19ddddcd3ee97a9c79ab8066a6a03 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 8 Apr 2021 01:54:42 +0100
Subject: [PATCH 1677/1820] io-wq: cancel unbounded works on io-wq destroy

WARNING: CPU: 5 PID: 227 at fs/io_uring.c:8578 io_ring_exit_work+0xe6/0x470
RIP: 0010:io_ring_exit_work+0xe6/0x470
Call Trace:
 process_one_work+0x206/0x400
 worker_thread+0x4a/0x3d0
 kthread+0x129/0x170
 ret_from_fork+0x22/0x30

INFO: task lfs-openat:2359 blocked for more than 245 seconds.
task:lfs-openat      state:D stack:    0 pid: 2359 ppid:     1 flags:0x00000004
Call Trace:
 ...
 wait_for_completion+0x8b/0xf0
 io_wq_destroy_manager+0x24/0x60
 io_wq_put_and_exit+0x18/0x30
 io_uring_clean_tctx+0x76/0xa0
 __io_uring_files_cancel+0x1b9/0x2e0
 do_exit+0xc0/0xb40
 ...

Even after io-wq destroy has been issued io-wq worker threads will
continue executing all left work items as usual, and may hang waiting
for I/O that won't ever complete (aka unbounded).

[<0>] pipe_read+0x306/0x450
[<0>] io_iter_do_read+0x1e/0x40
[<0>] io_read+0xd5/0x330
[<0>] io_issue_sqe+0xd21/0x18a0
[<0>] io_wq_submit_work+0x6c/0x140
[<0>] io_worker_handle_work+0x17d/0x400
[<0>] io_wqe_worker+0x2c0/0x330
[<0>] ret_from_fork+0x22/0x30

Cancel all unbounded I/O instead of executing them. This changes the
user visible behaviour, but that's inevitable as io-wq is not per task.

Suggested-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/cd4b543154154cba055cf86f351441c2174d7f71.1617842918.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 433c4d3c3c1c..4eba531bea5a 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -415,6 +415,7 @@ static void io_worker_handle_work(struct io_worker *worker)
 {
 	struct io_wqe *wqe = worker->wqe;
 	struct io_wq *wq = wqe->wq;
+	bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state);
 
 	do {
 		struct io_wq_work *work;
@@ -444,6 +445,9 @@ get_next:
 			unsigned int hash = io_get_work_hash(work);
 
 			next_hashed = wq_next_work(work);
+
+			if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND))
+				work->flags |= IO_WQ_WORK_CANCEL;
 			wq->do_work(work);
 			io_assign_current_work(worker, NULL);
 

From df8a39f2911a4c7769e0f760509f556a9e9d37af Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@kernel.org>
Date: Wed, 7 Apr 2021 20:35:32 +0200
Subject: [PATCH 1678/1820] i2c: imx: mention Oleksij as maintainer of the
 binding docs

When I removed myself as a maintainer of the yaml file, I missed that
some maintainer is required. Oleksij is already listed in MAINTAINERS
for this file, so add him here as well.

Fixes: 1ae6b3780848 ("i2c: imx: drop me as maintainer of binding docs")
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 Documentation/devicetree/bindings/i2c/i2c-imx.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx.yaml b/Documentation/devicetree/bindings/i2c/i2c-imx.yaml
index f33c6b29966b..3592d49235e0 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-imx.yaml
+++ b/Documentation/devicetree/bindings/i2c/i2c-imx.yaml
@@ -6,6 +6,9 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Freescale Inter IC (I2C) and High Speed Inter IC (HS-I2C) for i.MX
 
+maintainers:
+  - Oleksij Rempel <o.rempel@pengutronix.de>
+
 allOf:
   - $ref: /schemas/i2c/i2c-controller.yaml#
 

From 4ba86128ba077fbb7d86516ae24ed642e6c3adef Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Wed, 7 Apr 2021 18:36:02 +0300
Subject: [PATCH 1679/1820] Revert "net: sched: bump refcount for new action in
 ACT replace mode"

This reverts commit 6855e8213e06efcaf7c02a15e12b1ae64b9a7149.

Following commit in series fixes the issue without introducing regression
in error rollback of tcf_action_destroy().

Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 43cceb924976..b919826939e0 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1042,9 +1042,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	if (err != ACT_P_CREATED)
 		module_put(a_o->owner);
 
-	if (!bind && ovr && err == ACT_P_CREATED)
-		refcount_set(&a->tcfa_refcnt, 2);
-
 	return a;
 
 err_out:

From 87c750e8c38bce706eb32e4d8f1e3402f2cebbd4 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Wed, 7 Apr 2021 18:36:03 +0300
Subject: [PATCH 1680/1820] net: sched: fix action overwrite reference counting

Action init code increments reference counter when it changes an action.
This is the desired behavior for cls API which needs to obtain action
reference for every classifier that points to action. However, act API just
needs to change the action and releases the reference before returning.
This sequence breaks when the requested action doesn't exist, which causes
act API init code to create new action with specified index, but action is
still released before returning and is deleted (unless it was referenced
concurrently by cls API).

Reproduction:

$ sudo tc actions ls action gact
$ sudo tc actions change action gact drop index 1
$ sudo tc actions ls action gact

Extend tcf_action_init() to accept 'init_res' array and initialize it with
action->ops->init() result. In tcf_action_add() remove pointers to created
actions from actions array before passing it to tcf_action_put_many().

Fixes: cae422f379f3 ("net: sched: use reference counting action init")
Reported-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h |  5 +++--
 net/sched/act_api.c   | 22 +++++++++++++++-------
 net/sched/cls_api.c   |  9 +++++----
 3 files changed, 23 insertions(+), 13 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 2bf3092ae7ec..312f0f6554a0 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -185,7 +185,7 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 		    int nr_actions, struct tcf_result *res);
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
-		    struct tc_action *actions[], size_t *attr_size,
+		    struct tc_action *actions[], int init_res[], size_t *attr_size,
 		    bool rtnl_held, struct netlink_ext_ack *extack);
 struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla,
 					 bool rtnl_held,
@@ -193,7 +193,8 @@ struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla,
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
 				    char *name, int ovr, int bind,
-				    struct tc_action_ops *ops, bool rtnl_held,
+				    struct tc_action_ops *a_o, int *init_res,
+				    bool rtnl_held,
 				    struct netlink_ext_ack *extack);
 int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind,
 		    int ref, bool terse);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index b919826939e0..50854cfbfcdb 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -992,7 +992,8 @@ struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla,
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
 				    char *name, int ovr, int bind,
-				    struct tc_action_ops *a_o, bool rtnl_held,
+				    struct tc_action_ops *a_o, int *init_res,
+				    bool rtnl_held,
 				    struct netlink_ext_ack *extack)
 {
 	struct nla_bitfield32 flags = { 0, 0 };
@@ -1028,6 +1029,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	}
 	if (err < 0)
 		goto err_out;
+	*init_res = err;
 
 	if (!name && tb[TCA_ACT_COOKIE])
 		tcf_set_action_cookie(&a->act_cookie, cookie);
@@ -1056,7 +1058,7 @@ err_out:
 
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
-		    struct tc_action *actions[], size_t *attr_size,
+		    struct tc_action *actions[], int init_res[], size_t *attr_size,
 		    bool rtnl_held, struct netlink_ext_ack *extack)
 {
 	struct tc_action_ops *ops[TCA_ACT_MAX_PRIO] = {};
@@ -1084,7 +1086,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
 		act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind,
-					ops[i - 1], rtnl_held, extack);
+					ops[i - 1], &init_res[i - 1], rtnl_held,
+					extack);
 		if (IS_ERR(act)) {
 			err = PTR_ERR(act);
 			goto err;
@@ -1497,12 +1500,13 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 			  struct netlink_ext_ack *extack)
 {
 	size_t attr_size = 0;
-	int loop, ret;
+	int loop, ret, i;
 	struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
+	int init_res[TCA_ACT_MAX_PRIO] = {};
 
 	for (loop = 0; loop < 10; loop++) {
 		ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0,
-				      actions, &attr_size, true, extack);
+				      actions, init_res, &attr_size, true, extack);
 		if (ret != -EAGAIN)
 			break;
 	}
@@ -1510,8 +1514,12 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 	if (ret < 0)
 		return ret;
 	ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
-	if (ovr)
-		tcf_action_put_many(actions);
+
+	/* only put existing actions */
+	for (i = 0; i < TCA_ACT_MAX_PRIO; i++)
+		if (init_res[i] == ACT_P_CREATED)
+			actions[i] = NULL;
+	tcf_action_put_many(actions);
 
 	return ret;
 }
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 9332ec6863e8..9ecb91ebf094 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3040,6 +3040,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 {
 #ifdef CONFIG_NET_CLS_ACT
 	{
+		int init_res[TCA_ACT_MAX_PRIO] = {};
 		struct tc_action *act;
 		size_t attr_size = 0;
 
@@ -3051,8 +3052,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 				return PTR_ERR(a_o);
 			act = tcf_action_init_1(net, tp, tb[exts->police],
 						rate_tlv, "police", ovr,
-						TCA_ACT_BIND, a_o, rtnl_held,
-						extack);
+						TCA_ACT_BIND, a_o, init_res,
+						rtnl_held, extack);
 			if (IS_ERR(act)) {
 				module_put(a_o->owner);
 				return PTR_ERR(act);
@@ -3067,8 +3068,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 
 			err = tcf_action_init(net, tp, tb[exts->action],
 					      rate_tlv, NULL, ovr, TCA_ACT_BIND,
-					      exts->actions, &attr_size,
-					      rtnl_held, extack);
+					      exts->actions, init_res,
+					      &attr_size, rtnl_held, extack);
 			if (err < 0)
 				return err;
 			exts->nr_actions = err;

From b3650bf76a32380d4d80a3e21b5583e7303f216c Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Wed, 7 Apr 2021 18:36:04 +0300
Subject: [PATCH 1681/1820] net: sched: fix err handler in tcf_action_init()

With recent changes that separated action module load from action
initialization tcf_action_init() function error handling code was modified
to manually release the loaded modules if loading/initialization of any
further action in same batch failed. For the case when all modules
successfully loaded and some of the actions were initialized before one of
them failed in init handler. In this case for all previous actions the
module will be released twice by the error handler: First time by the loop
that manually calls module_put() for all ops, and second time by the action
destroy code that puts the module after destroying the action.

Reproduction:

$ sudo tc actions add action simple sdata \"2\" index 2
$ sudo tc actions add action simple sdata \"1\" index 1 \
                      action simple sdata \"2\" index 2
RTNETLINK answers: File exists
We have an error talking to the kernel
$ sudo tc actions ls action simple
total acts 1

        action order 0: Simple <"2">
         index 2 ref 1 bind 0
$ sudo tc actions flush action simple
$ sudo tc actions ls action simple
$ sudo tc actions add action simple sdata \"2\" index 2
Error: Failed to load TC action module.
We have an error talking to the kernel
$ lsmod | grep simple
act_simple             20480  -1

Fix the issue by modifying module reference counting handling in action
initialization code:

- Get module reference in tcf_idr_create() and put it in tcf_idr_release()
instead of taking over the reference held by the caller.

- Modify users of tcf_action_init_1() to always release the module
reference which they obtain before calling init function instead of
assuming that created action takes over the reference.

- Finally, modify tcf_action_init_1() to not release the module reference
when overwriting existing action as this is no longer necessary since both
upper and lower layers obtain and manage their own module references
independently.

Fixes: d349f9976868 ("net_sched: fix RTNL deadlock again caused by request_module()")
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h |  7 +------
 net/sched/act_api.c   | 26 ++++++++++++++++----------
 net/sched/cls_api.c   |  5 ++---
 3 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 312f0f6554a0..086b291e9530 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -170,12 +170,7 @@ void tcf_idr_insert_many(struct tc_action *actions[]);
 void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
 int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
 			struct tc_action **a, int bind);
-int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
-
-static inline int tcf_idr_release(struct tc_action *a, bool bind)
-{
-	return __tcf_idr_release(a, bind, false);
-}
+int tcf_idr_release(struct tc_action *a, bool bind);
 
 int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
 int tcf_unregister_action(struct tc_action_ops *a,
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 50854cfbfcdb..f6d5755d669e 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -158,7 +158,7 @@ static int __tcf_action_put(struct tc_action *p, bool bind)
 	return 0;
 }
 
-int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
+static int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
 {
 	int ret = 0;
 
@@ -184,7 +184,18 @@ int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
 
 	return ret;
 }
-EXPORT_SYMBOL(__tcf_idr_release);
+
+int tcf_idr_release(struct tc_action *a, bool bind)
+{
+	const struct tc_action_ops *ops = a->ops;
+	int ret;
+
+	ret = __tcf_idr_release(a, bind, false);
+	if (ret == ACT_P_DELETED)
+		module_put(ops->owner);
+	return ret;
+}
+EXPORT_SYMBOL(tcf_idr_release);
 
 static size_t tcf_action_shared_attrs_size(const struct tc_action *act)
 {
@@ -493,6 +504,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 	}
 
 	p->idrinfo = idrinfo;
+	__module_get(ops->owner);
 	p->ops = ops;
 	*a = p;
 	return 0;
@@ -1037,13 +1049,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	if (!name)
 		a->hw_stats = hw_stats;
 
-	/* module count goes up only when brand new policy is created
-	 * if it exists and is only bound to in a_o->init() then
-	 * ACT_P_CREATED is not returned (a zero is).
-	 */
-	if (err != ACT_P_CREATED)
-		module_put(a_o->owner);
-
 	return a;
 
 err_out:
@@ -1103,7 +1108,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 	tcf_idr_insert_many(actions);
 
 	*attr_size = tcf_action_full_attrs_size(sz);
-	return i - 1;
+	err = i - 1;
+	goto err_mod;
 
 err:
 	tcf_action_destroy(actions, bind);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 9ecb91ebf094..340d5af86e87 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3054,10 +3054,9 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 						rate_tlv, "police", ovr,
 						TCA_ACT_BIND, a_o, init_res,
 						rtnl_held, extack);
-			if (IS_ERR(act)) {
-				module_put(a_o->owner);
+			module_put(a_o->owner);
+			if (IS_ERR(act))
 				return PTR_ERR(act);
-			}
 
 			act->type = exts->type = TCA_OLD_COMPAT;
 			exts->actions[0] = act;

From 3583a4e8d77d44697a21437227dd53fc6e7b2cb5 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Wed, 7 Apr 2021 08:59:12 -0700
Subject: [PATCH 1682/1820] ipv6: report errors for iftoken via netlink extack

Setting iftoken can fail for several different reasons but there
and there was no report to user as to the cause. Add netlink
extended errors to the processing of the request.

This requires adding additional argument through rtnl_af_ops
set_link_af callback.

Reported-by: Hongren Zheng <li@zenithal.me>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rtnetlink.h |  4 ++--
 net/core/rtnetlink.c    |  2 +-
 net/ipv4/devinet.c      |  3 ++-
 net/ipv6/addrconf.c     | 32 ++++++++++++++++++++++++++------
 4 files changed, 31 insertions(+), 10 deletions(-)

diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 4da61c950e93..479f60ef54c0 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -147,8 +147,8 @@ struct rtnl_af_ops {
 	int			(*validate_link_af)(const struct net_device *dev,
 						    const struct nlattr *attr);
 	int			(*set_link_af)(struct net_device *dev,
-					       const struct nlattr *attr);
-
+					       const struct nlattr *attr,
+					       struct netlink_ext_ack *extack);
 	int			(*fill_stats_af)(struct sk_buff *skb,
 						 const struct net_device *dev);
 	size_t			(*get_stats_af_size)(const struct net_device *dev);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1bdcb33fb561..3485b16a7ff3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2863,7 +2863,7 @@ static int do_setlink(const struct sk_buff *skb,
 
 			BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af))));
 
-			err = af_ops->set_link_af(dev, af);
+			err = af_ops->set_link_af(dev, af, extack);
 			if (err < 0) {
 				rcu_read_unlock();
 				goto errout;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 75f67994fc85..2e35f68da40a 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1978,7 +1978,8 @@ static int inet_validate_link_af(const struct net_device *dev,
 	return 0;
 }
 
-static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla)
+static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla,
+			    struct netlink_ext_ack *extack)
 {
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
 	struct nlattr *a, *tb[IFLA_INET_MAX+1];
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f2337fb756ac..a9e53f5942fa 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5669,7 +5669,8 @@ static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev,
 	return 0;
 }
 
-static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
+static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token,
+			     struct netlink_ext_ack *extack)
 {
 	struct inet6_ifaddr *ifp;
 	struct net_device *dev = idev->dev;
@@ -5680,12 +5681,29 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
 
 	if (!token)
 		return -EINVAL;
-	if (dev->flags & (IFF_LOOPBACK | IFF_NOARP))
+
+	if (dev->flags & IFF_LOOPBACK) {
+		NL_SET_ERR_MSG_MOD(extack, "Device is loopback");
 		return -EINVAL;
-	if (!ipv6_accept_ra(idev))
+	}
+
+	if (dev->flags & IFF_NOARP) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Device does not do neighbour discovery");
 		return -EINVAL;
-	if (idev->cnf.rtr_solicits == 0)
+	}
+
+	if (!ipv6_accept_ra(idev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Router advertisement is disabled on device");
 		return -EINVAL;
+	}
+
+	if (idev->cnf.rtr_solicits == 0) {
+		NL_SET_ERR_MSG(extack,
+			       "Router solicitation is disabled on device");
+		return -EINVAL;
+	}
 
 	write_lock_bh(&idev->lock);
 
@@ -5793,7 +5811,8 @@ static int inet6_validate_link_af(const struct net_device *dev,
 	return 0;
 }
 
-static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
+static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla,
+			     struct netlink_ext_ack *extack)
 {
 	struct inet6_dev *idev = __in6_dev_get(dev);
 	struct nlattr *tb[IFLA_INET6_MAX + 1];
@@ -5806,7 +5825,8 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
 		BUG();
 
 	if (tb[IFLA_INET6_TOKEN]) {
-		err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]));
+		err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]),
+					extack);
 		if (err)
 			return err;
 	}

From 1ffbc7ea91606e4abd10eb60de5367f1c86daf5e Mon Sep 17 00:00:00 2001
From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Date: Thu, 8 Apr 2021 18:14:31 +0300
Subject: [PATCH 1683/1820] net: sched: sch_teql: fix null-pointer dereference

Reproduce:

  modprobe sch_teql
  tc qdisc add dev teql0 root teql0

This leads to (for instance in Centos 7 VM) OOPS:

[  532.366633] BUG: unable to handle kernel NULL pointer dereference at 00000000000000a8
[  532.366733] IP: [<ffffffffc06124a8>] teql_destroy+0x18/0x100 [sch_teql]
[  532.366825] PGD 80000001376d5067 PUD 137e37067 PMD 0
[  532.366906] Oops: 0000 [#1] SMP
[  532.366987] Modules linked in: sch_teql ...
[  532.367945] CPU: 1 PID: 3026 Comm: tc Kdump: loaded Tainted: G               ------------ T 3.10.0-1062.7.1.el7.x86_64 #1
[  532.368041] Hardware name: Virtuozzo KVM, BIOS 1.11.0-2.vz7.2 04/01/2014
[  532.368125] task: ffff8b7d37d31070 ti: ffff8b7c9fdbc000 task.ti: ffff8b7c9fdbc000
[  532.368224] RIP: 0010:[<ffffffffc06124a8>]  [<ffffffffc06124a8>] teql_destroy+0x18/0x100 [sch_teql]
[  532.368320] RSP: 0018:ffff8b7c9fdbf8e0  EFLAGS: 00010286
[  532.368394] RAX: ffffffffc0612490 RBX: ffff8b7cb1565e00 RCX: ffff8b7d35ba2000
[  532.368476] RDX: ffff8b7d35ba2000 RSI: 0000000000000000 RDI: ffff8b7cb1565e00
[  532.368557] RBP: ffff8b7c9fdbf8f8 R08: ffff8b7d3fd1f140 R09: ffff8b7d3b001600
[  532.368638] R10: ffff8b7d3b001600 R11: ffffffff84c7d65b R12: 00000000ffffffd8
[  532.368719] R13: 0000000000008000 R14: ffff8b7d35ba2000 R15: ffff8b7c9fdbf9a8
[  532.368800] FS:  00007f6a4e872740(0000) GS:ffff8b7d3fd00000(0000) knlGS:0000000000000000
[  532.368885] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  532.368961] CR2: 00000000000000a8 CR3: 00000001396ee000 CR4: 00000000000206e0
[  532.369046] Call Trace:
[  532.369159]  [<ffffffff84c8192e>] qdisc_create+0x36e/0x450
[  532.369268]  [<ffffffff846a9b49>] ? ns_capable+0x29/0x50
[  532.369366]  [<ffffffff849afde2>] ? nla_parse+0x32/0x120
[  532.369442]  [<ffffffff84c81b4c>] tc_modify_qdisc+0x13c/0x610
[  532.371508]  [<ffffffff84c693e7>] rtnetlink_rcv_msg+0xa7/0x260
[  532.372668]  [<ffffffff84907b65>] ? sock_has_perm+0x75/0x90
[  532.373790]  [<ffffffff84c69340>] ? rtnl_newlink+0x890/0x890
[  532.374914]  [<ffffffff84c8da7b>] netlink_rcv_skb+0xab/0xc0
[  532.376055]  [<ffffffff84c63708>] rtnetlink_rcv+0x28/0x30
[  532.377204]  [<ffffffff84c8d400>] netlink_unicast+0x170/0x210
[  532.378333]  [<ffffffff84c8d7a8>] netlink_sendmsg+0x308/0x420
[  532.379465]  [<ffffffff84c2f3a6>] sock_sendmsg+0xb6/0xf0
[  532.380710]  [<ffffffffc034a56e>] ? __xfs_filemap_fault+0x8e/0x1d0 [xfs]
[  532.381868]  [<ffffffffc034a75c>] ? xfs_filemap_fault+0x2c/0x30 [xfs]
[  532.383037]  [<ffffffff847ec23a>] ? __do_fault.isra.61+0x8a/0x100
[  532.384144]  [<ffffffff84c30269>] ___sys_sendmsg+0x3e9/0x400
[  532.385268]  [<ffffffff847f3fad>] ? handle_mm_fault+0x39d/0x9b0
[  532.386387]  [<ffffffff84d88678>] ? __do_page_fault+0x238/0x500
[  532.387472]  [<ffffffff84c31921>] __sys_sendmsg+0x51/0x90
[  532.388560]  [<ffffffff84c31972>] SyS_sendmsg+0x12/0x20
[  532.389636]  [<ffffffff84d8dede>] system_call_fastpath+0x25/0x2a
[  532.390704]  [<ffffffff84d8de21>] ? system_call_after_swapgs+0xae/0x146
[  532.391753] Code: 00 00 00 00 00 00 5b 5d c3 66 2e 0f 1f 84 00 00 00 00 00 66 66 66 66 90 55 48 89 e5 41 55 41 54 53 48 8b b7 48 01 00 00 48 89 fb <48> 8b 8e a8 00 00 00 48 85 c9 74 43 48 89 ca eb 0f 0f 1f 80 00
[  532.394036] RIP  [<ffffffffc06124a8>] teql_destroy+0x18/0x100 [sch_teql]
[  532.395127]  RSP <ffff8b7c9fdbf8e0>
[  532.396179] CR2: 00000000000000a8

Null pointer dereference happens on master->slaves dereference in
teql_destroy() as master is null-pointer.

When qdisc_create() calls teql_qdisc_init() it imediately fails after
check "if (m->dev == dev)" because both devices are teql0, and it does
not set qdisc_priv(sch)->m leaving it zero on error path, then
qdisc_create() imediately calls teql_destroy() which does not expect
zero master pointer and we get OOPS.

Fixes: 87b60cfacf9f ("net_sched: fix error recovery at qdisc creation")
Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_teql.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 2f1f0a378408..6af6b95bdb67 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -134,6 +134,9 @@ teql_destroy(struct Qdisc *sch)
 	struct teql_sched_data *dat = qdisc_priv(sch);
 	struct teql_master *master = dat->m;
 
+	if (!master)
+		return;
+
 	prev = master->slaves;
 	if (prev) {
 		do {

From afd0be7299533bb2e2b09104399d8a467ecbd2c5 Mon Sep 17 00:00:00 2001
From: Ciara Loftus <ciara.loftus@intel.com>
Date: Thu, 8 Apr 2021 05:20:09 +0000
Subject: [PATCH 1684/1820] libbpf: Fix potential NULL pointer dereference

Wait until after the UMEM is checked for null to dereference it.

Fixes: 43f1bc1efff1 ("libbpf: Restore umem state after socket create failure")
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210408052009.7844-1-ciara.loftus@intel.com
---
 tools/lib/bpf/xsk.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index d24b5cc720ec..007fe5d59438 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -852,18 +852,19 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 			      struct xsk_ring_cons *comp,
 			      const struct xsk_socket_config *usr_config)
 {
+	bool unmap, rx_setup_done = false, tx_setup_done = false;
 	void *rx_map = NULL, *tx_map = NULL;
 	struct sockaddr_xdp sxdp = {};
 	struct xdp_mmap_offsets off;
 	struct xsk_socket *xsk;
 	struct xsk_ctx *ctx;
 	int err, ifindex;
-	bool unmap = umem->fill_save != fill;
-	bool rx_setup_done = false, tx_setup_done = false;
 
 	if (!umem || !xsk_ptr || !(rx || tx))
 		return -EFAULT;
 
+	unmap = umem->fill_save != fill;
+
 	xsk = calloc(1, sizeof(*xsk));
 	if (!xsk)
 		return -ENOMEM;

From 48d499bd89191b359a6dbe44d32107e3021571c2 Mon Sep 17 00:00:00 2001
From: Frank Rowand <frank.rowand@sony.com>
Date: Thu, 8 Apr 2021 15:45:08 -0500
Subject: [PATCH 1685/1820] of: unittest: overlay: ensure proper alignment of
 copied FDT

The Devicetree standard specifies an 8 byte alignment of the FDT.
Code in libfdt expects this alignment for an FDT image in memory.
kmemdup() returns 4 byte alignment on openrisc.  Replace kmemdup()
with kmalloc(), align pointer, memcpy() to get proper alignment.

The 4 byte alignment exposed a related bug which triggered a crash
on openrisc with:
commit 79edff12060f ("scripts/dtc: Update to upstream version v1.6.0-51-g183df9e9c2b9")
as reported in:
https://lore.kernel.org/lkml/20210327224116.69309-1-linux@roeck-us.net/

Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Frank Rowand <frank.rowand@sony.com>
Link: https://lore.kernel.org/r/20210408204508.2276230-1-frowand.list@gmail.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/of_private.h |  2 ++
 drivers/of/overlay.c    | 22 ++++++++++++++--------
 drivers/of/unittest.c   |  9 +++++++--
 3 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index d9e6a324de0a..d717efbd637d 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -8,6 +8,8 @@
  * Copyright (C) 1996-2005 Paul Mackerras.
  */
 
+#define FDT_ALIGN_SIZE 8
+
 /**
  * struct alias_prop - Alias property in 'aliases' node
  * @link:	List node to link the structure in aliases_lookup list
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index e12c643b6ba8..23effe5e50ec 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -57,7 +57,7 @@ struct fragment {
  * struct overlay_changeset
  * @id:			changeset identifier
  * @ovcs_list:		list on which we are located
- * @fdt:		FDT that was unflattened to create @overlay_tree
+ * @fdt:		base of memory allocated to hold aligned FDT that was unflattened to create @overlay_tree
  * @overlay_tree:	expanded device tree that contains the fragment nodes
  * @count:		count of fragment structures
  * @fragments:		fragment nodes in the overlay expanded device tree
@@ -719,8 +719,8 @@ static struct device_node *find_target(struct device_node *info_node)
 /**
  * init_overlay_changeset() - initialize overlay changeset from overlay tree
  * @ovcs:	Overlay changeset to build
- * @fdt:	the FDT that was unflattened to create @tree
- * @tree:	Contains all the overlay fragments and overlay fixup nodes
+ * @fdt:	base of memory allocated to hold aligned FDT that was unflattened to create @tree
+ * @tree:	Contains the overlay fragments and overlay fixup nodes
  *
  * Initialize @ovcs.  Populate @ovcs->fragments with node information from
  * the top level of @tree.  The relevant top level nodes are the fragment
@@ -873,7 +873,7 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs)
  * internal documentation
  *
  * of_overlay_apply() - Create and apply an overlay changeset
- * @fdt:	the FDT that was unflattened to create @tree
+ * @fdt:	base of memory allocated to hold the aligned FDT
  * @tree:	Expanded overlay device tree
  * @ovcs_id:	Pointer to overlay changeset id
  *
@@ -953,7 +953,9 @@ static int of_overlay_apply(const void *fdt, struct device_node *tree,
 	/*
 	 * after overlay_notify(), ovcs->overlay_tree related pointers may have
 	 * leaked to drivers, so can not kfree() tree, aka ovcs->overlay_tree;
-	 * and can not free fdt, aka ovcs->fdt
+	 * and can not free memory containing aligned fdt.  The aligned fdt
+	 * is contained within the memory at ovcs->fdt, possibly at an offset
+	 * from ovcs->fdt.
 	 */
 	ret = overlay_notify(ovcs, OF_OVERLAY_PRE_APPLY);
 	if (ret) {
@@ -1014,7 +1016,8 @@ out:
 int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size,
 			 int *ovcs_id)
 {
-	const void *new_fdt;
+	void *new_fdt;
+	void *new_fdt_align;
 	int ret;
 	u32 size;
 	struct device_node *overlay_root = NULL;
@@ -1036,11 +1039,14 @@ int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size,
 	 * Must create permanent copy of FDT because of_fdt_unflatten_tree()
 	 * will create pointers to the passed in FDT in the unflattened tree.
 	 */
-	new_fdt = kmemdup(overlay_fdt, size, GFP_KERNEL);
+	new_fdt = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL);
 	if (!new_fdt)
 		return -ENOMEM;
 
-	of_fdt_unflatten_tree(new_fdt, NULL, &overlay_root);
+	new_fdt_align = PTR_ALIGN(new_fdt, FDT_ALIGN_SIZE);
+	memcpy(new_fdt_align, overlay_fdt, size);
+
+	of_fdt_unflatten_tree(new_fdt_align, NULL, &overlay_root);
 	if (!overlay_root) {
 		pr_err("unable to unflatten overlay_fdt\n");
 		ret = -EINVAL;
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index f9b5b698249f..819a20acaa93 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -22,6 +22,7 @@
 #include <linux/slab.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
+#include <linux/kernel.h>
 
 #include <linux/i2c.h>
 #include <linux/i2c-mux.h>
@@ -1408,6 +1409,7 @@ static void attach_node_and_children(struct device_node *np)
 static int __init unittest_data_add(void)
 {
 	void *unittest_data;
+	void *unittest_data_align;
 	struct device_node *unittest_data_node = NULL, *np;
 	/*
 	 * __dtb_testcases_begin[] and __dtb_testcases_end[] are magically
@@ -1425,11 +1427,14 @@ static int __init unittest_data_add(void)
 	}
 
 	/* creating copy */
-	unittest_data = kmemdup(__dtb_testcases_begin, size, GFP_KERNEL);
+	unittest_data = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL);
 	if (!unittest_data)
 		return -ENOMEM;
 
-	ret = of_fdt_unflatten_tree(unittest_data, NULL, &unittest_data_node);
+	unittest_data_align = PTR_ALIGN(unittest_data, FDT_ALIGN_SIZE);
+	memcpy(unittest_data_align, __dtb_testcases_begin, size);
+
+	ret = of_fdt_unflatten_tree(unittest_data_align, NULL, &unittest_data_node);
 	if (!ret) {
 		pr_warn("%s: unflatten testcases tree failed\n", __func__);
 		kfree(unittest_data);

From 3e9005be87777afc902b9f5497495898202d335d Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Thu, 8 Apr 2021 20:38:27 +0200
Subject: [PATCH 1686/1820] net: dsa: lantiq_gswip: Don't use PHY auto polling

PHY auto polling on the GSWIP hardware can be used so link changes
(speed, link up/down, etc.) can be detected automatically. Internally
GSWIP reads the PHY's registers for this functionality. Based on this
automatic detection GSWIP can also automatically re-configure it's port
settings. Unfortunately this auto polling (and configuration) mechanism
seems to cause various issues observed by different people on different
devices:
- FritzBox 7360v2: the two Gbit/s ports (connected to the two internal
  PHY11G instances) are working fine but the two Fast Ethernet ports
  (using an AR8030 RMII PHY) are completely dead (neither RX nor TX are
  received). It turns out that the AR8030 PHY sets the BMSR_ESTATEN bit
  as well as the ESTATUS_1000_TFULL and ESTATUS_1000_XFULL bits. This
  makes the PHY auto polling state machine (rightfully?) think that the
  established link speed (when the other side is Gbit/s capable) is
  1Gbit/s.
- None of the Ethernet ports on the Zyxel P-2812HNU-F1 (two are
  connected to the internal PHY11G GPHYs while the other three are
  external RGMII PHYs) are working. Neither RX nor TX traffic was
  observed. It is not clear which part of the PHY auto polling state-
  machine caused this.
- FritzBox 7412 (only one LAN port which is connected to one of the
  internal GPHYs running in PHY22F / Fast Ethernet mode) was seeing
  random disconnects (link down events could be seen). Sometimes all
  traffic would stop after such disconnect. It is not clear which part
  of the PHY auto polling state-machine cauased this.
- TP-Link TD-W9980 (two ports are connected to the internal GPHYs
  running in PHY11G / Gbit/s mode, the other two are external RGMII
  PHYs) was affected by similar issues as the FritzBox 7412 just without
  the "link down" events

Switch to software based configuration instead of PHY auto polling (and
letting the GSWIP hardware configure the ports automatically) for the
following link parameters:
- link up/down
- link speed
- full/half duplex
- flow control (RX / TX pause)

After a big round of manual testing by various people (who helped test
this on OpenWrt) it turns out that this fixes all reported issues.

Additionally it can be considered more future proof because any
"quirk" which is implemented for a PHY on the driver side can now be
used with the GSWIP hardware as well because Linux is in control of the
link parameters.

As a nice side-effect this also solves a problem where fixed-links were
not supported previously because we were relying on the PHY auto polling
mechanism, which cannot work for fixed-links as there's no PHY from
where it can read the registers. Configuring the link settings on the
GSWIP ports means that we now use the settings from device-tree also for
ports with fixed-links.

Fixes: 14fceff4771e51 ("net: dsa: Add Lantiq / Intel DSA driver for vrx200")
Fixes: 3e6fdeb28f4c33 ("net: dsa: lantiq_gswip: Let GSWIP automatically set the xMII clock")
Cc: stable@vger.kernel.org
Acked-by: Hauke Mehrtens <hauke@hauke-m.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/lantiq_gswip.c | 183 ++++++++++++++++++++++++++++-----
 1 file changed, 158 insertions(+), 25 deletions(-)

diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
index 809dfa3be6bb..126d4ea868ba 100644
--- a/drivers/net/dsa/lantiq_gswip.c
+++ b/drivers/net/dsa/lantiq_gswip.c
@@ -190,6 +190,23 @@
 #define GSWIP_PCE_DEFPVID(p)		(0x486 + ((p) * 0xA))
 
 #define GSWIP_MAC_FLEN			0x8C5
+#define GSWIP_MAC_CTRL_0p(p)		(0x903 + ((p) * 0xC))
+#define  GSWIP_MAC_CTRL_0_PADEN		BIT(8)
+#define  GSWIP_MAC_CTRL_0_FCS_EN	BIT(7)
+#define  GSWIP_MAC_CTRL_0_FCON_MASK	0x0070
+#define  GSWIP_MAC_CTRL_0_FCON_AUTO	0x0000
+#define  GSWIP_MAC_CTRL_0_FCON_RX	0x0010
+#define  GSWIP_MAC_CTRL_0_FCON_TX	0x0020
+#define  GSWIP_MAC_CTRL_0_FCON_RXTX	0x0030
+#define  GSWIP_MAC_CTRL_0_FCON_NONE	0x0040
+#define  GSWIP_MAC_CTRL_0_FDUP_MASK	0x000C
+#define  GSWIP_MAC_CTRL_0_FDUP_AUTO	0x0000
+#define  GSWIP_MAC_CTRL_0_FDUP_EN	0x0004
+#define  GSWIP_MAC_CTRL_0_FDUP_DIS	0x000C
+#define  GSWIP_MAC_CTRL_0_GMII_MASK	0x0003
+#define  GSWIP_MAC_CTRL_0_GMII_AUTO	0x0000
+#define  GSWIP_MAC_CTRL_0_GMII_MII	0x0001
+#define  GSWIP_MAC_CTRL_0_GMII_RGMII	0x0002
 #define GSWIP_MAC_CTRL_2p(p)		(0x905 + ((p) * 0xC))
 #define GSWIP_MAC_CTRL_2_MLEN		BIT(3) /* Maximum Untagged Frame Lnegth */
 
@@ -653,16 +670,13 @@ static int gswip_port_enable(struct dsa_switch *ds, int port,
 			  GSWIP_SDMA_PCTRLp(port));
 
 	if (!dsa_is_cpu_port(ds, port)) {
-		u32 macconf = GSWIP_MDIO_PHY_LINK_AUTO |
-			      GSWIP_MDIO_PHY_SPEED_AUTO |
-			      GSWIP_MDIO_PHY_FDUP_AUTO |
-			      GSWIP_MDIO_PHY_FCONTX_AUTO |
-			      GSWIP_MDIO_PHY_FCONRX_AUTO |
-			      (phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK);
+		u32 mdio_phy = 0;
 
-		gswip_mdio_w(priv, macconf, GSWIP_MDIO_PHYp(port));
-		/* Activate MDIO auto polling */
-		gswip_mdio_mask(priv, 0, BIT(port), GSWIP_MDIO_MDC_CFG0);
+		if (phydev)
+			mdio_phy = phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK;
+
+		gswip_mdio_mask(priv, GSWIP_MDIO_PHY_ADDR_MASK, mdio_phy,
+				GSWIP_MDIO_PHYp(port));
 	}
 
 	return 0;
@@ -675,14 +689,6 @@ static void gswip_port_disable(struct dsa_switch *ds, int port)
 	if (!dsa_is_user_port(ds, port))
 		return;
 
-	if (!dsa_is_cpu_port(ds, port)) {
-		gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_DOWN,
-				GSWIP_MDIO_PHY_LINK_MASK,
-				GSWIP_MDIO_PHYp(port));
-		/* Deactivate MDIO auto polling */
-		gswip_mdio_mask(priv, BIT(port), 0, GSWIP_MDIO_MDC_CFG0);
-	}
-
 	gswip_switch_mask(priv, GSWIP_FDMA_PCTRL_EN, 0,
 			  GSWIP_FDMA_PCTRLp(port));
 	gswip_switch_mask(priv, GSWIP_SDMA_PCTRL_EN, 0,
@@ -794,20 +800,31 @@ static int gswip_setup(struct dsa_switch *ds)
 	gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP2);
 	gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP3);
 
-	/* disable PHY auto polling */
+	/* Deactivate MDIO PHY auto polling. Some PHYs as the AR8030 have an
+	 * interoperability problem with this auto polling mechanism because
+	 * their status registers think that the link is in a different state
+	 * than it actually is. For the AR8030 it has the BMSR_ESTATEN bit set
+	 * as well as ESTATUS_1000_TFULL and ESTATUS_1000_XFULL. This makes the
+	 * auto polling state machine consider the link being negotiated with
+	 * 1Gbit/s. Since the PHY itself is a Fast Ethernet RMII PHY this leads
+	 * to the switch port being completely dead (RX and TX are both not
+	 * working).
+	 * Also with various other PHY / port combinations (PHY11G GPHY, PHY22F
+	 * GPHY, external RGMII PEF7071/7072) any traffic would stop. Sometimes
+	 * it would work fine for a few minutes to hours and then stop, on
+	 * other device it would no traffic could be sent or received at all.
+	 * Testing shows that when PHY auto polling is disabled these problems
+	 * go away.
+	 */
 	gswip_mdio_w(priv, 0x0, GSWIP_MDIO_MDC_CFG0);
+
 	/* Configure the MDIO Clock 2.5 MHz */
 	gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1);
 
-	for (i = 0; i < priv->hw_info->max_ports; i++) {
-		/* Disable the xMII link */
+	/* Disable the xMII link */
+	for (i = 0; i < priv->hw_info->max_ports; i++)
 		gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, i);
 
-		/* Automatically select the xMII interface clock */
-		gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_RATE_MASK,
-				   GSWIP_MII_CFG_RATE_AUTO, i);
-	}
-
 	/* enable special tag insertion on cpu port */
 	gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN,
 			  GSWIP_FDMA_PCTRLp(cpu_port));
@@ -1455,6 +1472,112 @@ unsupported:
 	return;
 }
 
+static void gswip_port_set_link(struct gswip_priv *priv, int port, bool link)
+{
+	u32 mdio_phy;
+
+	if (link)
+		mdio_phy = GSWIP_MDIO_PHY_LINK_UP;
+	else
+		mdio_phy = GSWIP_MDIO_PHY_LINK_DOWN;
+
+	gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_MASK, mdio_phy,
+			GSWIP_MDIO_PHYp(port));
+}
+
+static void gswip_port_set_speed(struct gswip_priv *priv, int port, int speed,
+				 phy_interface_t interface)
+{
+	u32 mdio_phy = 0, mii_cfg = 0, mac_ctrl_0 = 0;
+
+	switch (speed) {
+	case SPEED_10:
+		mdio_phy = GSWIP_MDIO_PHY_SPEED_M10;
+
+		if (interface == PHY_INTERFACE_MODE_RMII)
+			mii_cfg = GSWIP_MII_CFG_RATE_M50;
+		else
+			mii_cfg = GSWIP_MII_CFG_RATE_M2P5;
+
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII;
+		break;
+
+	case SPEED_100:
+		mdio_phy = GSWIP_MDIO_PHY_SPEED_M100;
+
+		if (interface == PHY_INTERFACE_MODE_RMII)
+			mii_cfg = GSWIP_MII_CFG_RATE_M50;
+		else
+			mii_cfg = GSWIP_MII_CFG_RATE_M25;
+
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII;
+		break;
+
+	case SPEED_1000:
+		mdio_phy = GSWIP_MDIO_PHY_SPEED_G1;
+
+		mii_cfg = GSWIP_MII_CFG_RATE_M125;
+
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_RGMII;
+		break;
+	}
+
+	gswip_mdio_mask(priv, GSWIP_MDIO_PHY_SPEED_MASK, mdio_phy,
+			GSWIP_MDIO_PHYp(port));
+	gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_RATE_MASK, mii_cfg, port);
+	gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_GMII_MASK, mac_ctrl_0,
+			  GSWIP_MAC_CTRL_0p(port));
+}
+
+static void gswip_port_set_duplex(struct gswip_priv *priv, int port, int duplex)
+{
+	u32 mac_ctrl_0, mdio_phy;
+
+	if (duplex == DUPLEX_FULL) {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_EN;
+		mdio_phy = GSWIP_MDIO_PHY_FDUP_EN;
+	} else {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_DIS;
+		mdio_phy = GSWIP_MDIO_PHY_FDUP_DIS;
+	}
+
+	gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FDUP_MASK, mac_ctrl_0,
+			  GSWIP_MAC_CTRL_0p(port));
+	gswip_mdio_mask(priv, GSWIP_MDIO_PHY_FDUP_MASK, mdio_phy,
+			GSWIP_MDIO_PHYp(port));
+}
+
+static void gswip_port_set_pause(struct gswip_priv *priv, int port,
+				 bool tx_pause, bool rx_pause)
+{
+	u32 mac_ctrl_0, mdio_phy;
+
+	if (tx_pause && rx_pause) {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RXTX;
+		mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN |
+			   GSWIP_MDIO_PHY_FCONRX_EN;
+	} else if (tx_pause) {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_TX;
+		mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN |
+			   GSWIP_MDIO_PHY_FCONRX_DIS;
+	} else if (rx_pause) {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RX;
+		mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS |
+			   GSWIP_MDIO_PHY_FCONRX_EN;
+	} else {
+		mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_NONE;
+		mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS |
+			   GSWIP_MDIO_PHY_FCONRX_DIS;
+	}
+
+	gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FCON_MASK,
+			  mac_ctrl_0, GSWIP_MAC_CTRL_0p(port));
+	gswip_mdio_mask(priv,
+			GSWIP_MDIO_PHY_FCONTX_MASK |
+			GSWIP_MDIO_PHY_FCONRX_MASK,
+			mdio_phy, GSWIP_MDIO_PHYp(port));
+}
+
 static void gswip_phylink_mac_config(struct dsa_switch *ds, int port,
 				     unsigned int mode,
 				     const struct phylink_link_state *state)
@@ -1511,6 +1634,9 @@ static void gswip_phylink_mac_link_down(struct dsa_switch *ds, int port,
 	struct gswip_priv *priv = ds->priv;
 
 	gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, port);
+
+	if (!dsa_is_cpu_port(ds, port))
+		gswip_port_set_link(priv, port, false);
 }
 
 static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port,
@@ -1522,6 +1648,13 @@ static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port,
 {
 	struct gswip_priv *priv = ds->priv;
 
+	if (!dsa_is_cpu_port(ds, port)) {
+		gswip_port_set_link(priv, port, true);
+		gswip_port_set_speed(priv, port, speed, interface);
+		gswip_port_set_duplex(priv, port, duplex);
+		gswip_port_set_pause(priv, port, tx_pause, rx_pause);
+	}
+
 	gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port);
 }
 

From 4b5923249b8fa427943b50b8f35265176472be38 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Thu, 8 Apr 2021 20:38:28 +0200
Subject: [PATCH 1687/1820] net: dsa: lantiq_gswip: Configure all remaining
 GSWIP_MII_CFG bits

There are a few more bits in the GSWIP_MII_CFG register for which we
did rely on the boot-loader (or the hardware defaults) to set them up
properly.

For some external RMII PHYs we need to select the GSWIP_MII_CFG_RMII_CLK
bit and also we should un-set it for non-RMII PHYs. The
GSWIP_MII_CFG_RMII_CLK bit is ignored for other PHY connection modes.

The GSWIP IP also supports in-band auto-negotiation for RGMII PHYs when
the GSWIP_MII_CFG_RGMII_IBS bit is set. Clear this bit always as there's
no known hardware which uses this (so it is not tested yet).

Clear the xMII isolation bit when set at initialization time if it was
previously set by the bootloader. Not doing so could lead to no traffic
(neither RX nor TX) on a port with this bit set.

While here, also add the GSWIP_MII_CFG_RESET bit. We don't need to
manage it because this bit is self-clearning when set. We still add it
here to get a better overview of the GSWIP_MII_CFG register.

Fixes: 14fceff4771e51 ("net: dsa: Add Lantiq / Intel DSA driver for vrx200")
Cc: stable@vger.kernel.org
Suggested-by: Hauke Mehrtens <hauke@hauke-m.de>
Acked-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/lantiq_gswip.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
index 126d4ea868ba..bf5c62e5c0b0 100644
--- a/drivers/net/dsa/lantiq_gswip.c
+++ b/drivers/net/dsa/lantiq_gswip.c
@@ -93,8 +93,12 @@
 
 /* GSWIP MII Registers */
 #define GSWIP_MII_CFGp(p)		(0x2 * (p))
+#define  GSWIP_MII_CFG_RESET		BIT(15)
 #define  GSWIP_MII_CFG_EN		BIT(14)
+#define  GSWIP_MII_CFG_ISOLATE		BIT(13)
 #define  GSWIP_MII_CFG_LDCLKDIS		BIT(12)
+#define  GSWIP_MII_CFG_RGMII_IBS	BIT(8)
+#define  GSWIP_MII_CFG_RMII_CLK		BIT(7)
 #define  GSWIP_MII_CFG_MODE_MIIP	0x0
 #define  GSWIP_MII_CFG_MODE_MIIM	0x1
 #define  GSWIP_MII_CFG_MODE_RMIIP	0x2
@@ -821,9 +825,11 @@ static int gswip_setup(struct dsa_switch *ds)
 	/* Configure the MDIO Clock 2.5 MHz */
 	gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1);
 
-	/* Disable the xMII link */
+	/* Disable the xMII interface and clear it's isolation bit */
 	for (i = 0; i < priv->hw_info->max_ports; i++)
-		gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, i);
+		gswip_mii_mask_cfg(priv,
+				   GSWIP_MII_CFG_EN | GSWIP_MII_CFG_ISOLATE,
+				   0, i);
 
 	/* enable special tag insertion on cpu port */
 	gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN,
@@ -1597,6 +1603,9 @@ static void gswip_phylink_mac_config(struct dsa_switch *ds, int port,
 		break;
 	case PHY_INTERFACE_MODE_RMII:
 		miicfg |= GSWIP_MII_CFG_MODE_RMIIM;
+
+		/* Configure the RMII clock as output: */
+		miicfg |= GSWIP_MII_CFG_RMII_CLK;
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
@@ -1609,7 +1618,11 @@ static void gswip_phylink_mac_config(struct dsa_switch *ds, int port,
 			"Unsupported interface: %d\n", state->interface);
 		return;
 	}
-	gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_MODE_MASK, miicfg, port);
+
+	gswip_mii_mask_cfg(priv,
+			   GSWIP_MII_CFG_MODE_MASK | GSWIP_MII_CFG_RMII_CLK |
+			   GSWIP_MII_CFG_RGMII_IBS | GSWIP_MII_CFG_LDCLKDIS,
+			   miicfg, port);
 
 	switch (state->interface) {
 	case PHY_INTERFACE_MODE_RGMII_ID:

From 864db232dc7036aa2de19749c3d5be0143b24f8f Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <musamaanjum@gmail.com>
Date: Fri, 9 Apr 2021 03:01:29 +0500
Subject: [PATCH 1688/1820] net: ipv6: check for validity before dereferencing
 cfg->fc_nlinfo.nlh

nlh is being checked for validtity two times when it is dereferenced in
this function. Check for validity again when updating the flags through
nlh pointer to make the dereferencing safe.

CC: <stable@vger.kernel.org>
Addresses-Coverity: ("NULL pointer dereference")
Signed-off-by: Muhammad Usama Anjum <musamaanjum@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1056b0229ffd..373d48073106 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5209,9 +5209,11 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		 * nexthops have been replaced by first new, the rest should
 		 * be added to it.
 		 */
-		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
-						     NLM_F_REPLACE);
-		cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE;
+		if (cfg->fc_nlinfo.nlh) {
+			cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
+							     NLM_F_REPLACE);
+			cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE;
+		}
 		nhn++;
 	}
 

From 2361db89aaadfb671db6911b0063e01ec8922c28 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 9 Mar 2021 17:43:38 -0800
Subject: [PATCH 1689/1820] libnvdimm: Notify disk drivers to revalidate region
 read-only

Previous kernels allowed the BLKROSET to override the disk's read-only
status. With that situation fixed the pmem driver needs to rely on
notification events to reevaluate the disk read-only status after the
host region has been marked read-write.

Recall that when libnvdimm determines that the persistent memory has
lost persistence (for example lack of energy to flush from DRAM to FLASH
on an NVDIMM-N device) it marks the region read-only, but that state can
be overridden by the user via:

   echo 0 > /sys/bus/nd/devices/regionX/read_only

...to date there is no notification that the region has restored
persistence, so the user override is the only recovery.

Fixes: 52f019d43c22 ("block: add a hard-readonly flag to struct gendisk")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Vishal Verma <vishal.l.verma@intel.com>
Tested-by: Vishal Verma <vishal.l.verma@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Jens Axboe <axboe@kernel.dk>
Link: https://lore.kernel.org/r/161534060720.528671.2341213328968989192.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/bus.c         | 14 ++++++--------
 drivers/nvdimm/pmem.c        | 37 ++++++++++++++++++++++++++++++++----
 drivers/nvdimm/region_devs.c |  7 +++++++
 include/linux/nd.h           |  1 +
 4 files changed, 47 insertions(+), 12 deletions(-)

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 48f0985ca8a0..3a777d0073b7 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -631,16 +631,14 @@ void nvdimm_check_and_set_ro(struct gendisk *disk)
 	struct nd_region *nd_region = to_nd_region(dev->parent);
 	int disk_ro = get_disk_ro(disk);
 
-	/*
-	 * Upgrade to read-only if the region is read-only preserve as
-	 * read-only if the disk is already read-only.
-	 */
-	if (disk_ro || nd_region->ro == disk_ro)
+	/* catch the disk up with the region ro state */
+	if (disk_ro == nd_region->ro)
 		return;
 
-	dev_info(dev, "%s read-only, marking %s read-only\n",
-			dev_name(&nd_region->dev), disk->disk_name);
-	set_disk_ro(disk, 1);
+	dev_info(dev, "%s read-%s, marking %s read-%s\n",
+		 dev_name(&nd_region->dev), nd_region->ro ? "only" : "write",
+		 disk->disk_name, nd_region->ro ? "only" : "write");
+	set_disk_ro(disk, nd_region->ro);
 }
 EXPORT_SYMBOL(nvdimm_check_and_set_ro);
 
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index b8a85bfb2e95..7daac795db39 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -26,6 +26,7 @@
 #include <linux/mm.h>
 #include <asm/cacheflush.h>
 #include "pmem.h"
+#include "btt.h"
 #include "pfn.h"
 #include "nd.h"
 
@@ -585,7 +586,7 @@ static void nd_pmem_shutdown(struct device *dev)
 	nvdimm_flush(to_nd_region(dev->parent), NULL);
 }
 
-static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
+static void pmem_revalidate_poison(struct device *dev)
 {
 	struct nd_region *nd_region;
 	resource_size_t offset = 0, end_trunc = 0;
@@ -595,9 +596,6 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 	struct range range;
 	struct kernfs_node *bb_state;
 
-	if (event != NVDIMM_REVALIDATE_POISON)
-		return;
-
 	if (is_nd_btt(dev)) {
 		struct nd_btt *nd_btt = to_nd_btt(dev);
 
@@ -635,6 +633,37 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 		sysfs_notify_dirent(bb_state);
 }
 
+static void pmem_revalidate_region(struct device *dev)
+{
+	struct pmem_device *pmem;
+
+	if (is_nd_btt(dev)) {
+		struct nd_btt *nd_btt = to_nd_btt(dev);
+		struct btt *btt = nd_btt->btt;
+
+		nvdimm_check_and_set_ro(btt->btt_disk);
+		return;
+	}
+
+	pmem = dev_get_drvdata(dev);
+	nvdimm_check_and_set_ro(pmem->disk);
+}
+
+static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
+{
+	switch (event) {
+	case NVDIMM_REVALIDATE_POISON:
+		pmem_revalidate_poison(dev);
+		break;
+	case NVDIMM_REVALIDATE_REGION:
+		pmem_revalidate_region(dev);
+		break;
+	default:
+		dev_WARN_ONCE(dev, 1, "notify: unknown event: %d\n", event);
+		break;
+	}
+}
+
 MODULE_ALIAS("pmem");
 MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO);
 MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM);
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index ef23119db574..51870eb51da6 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -518,6 +518,12 @@ static ssize_t read_only_show(struct device *dev,
 	return sprintf(buf, "%d\n", nd_region->ro);
 }
 
+static int revalidate_read_only(struct device *dev, void *data)
+{
+	nd_device_notify(dev, NVDIMM_REVALIDATE_REGION);
+	return 0;
+}
+
 static ssize_t read_only_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
@@ -529,6 +535,7 @@ static ssize_t read_only_store(struct device *dev,
 		return rc;
 
 	nd_region->ro = ro;
+	device_for_each_child(dev, NULL, revalidate_read_only);
 	return len;
 }
 static DEVICE_ATTR_RW(read_only);
diff --git a/include/linux/nd.h b/include/linux/nd.h
index cec526c8043d..ee9ad76afbba 100644
--- a/include/linux/nd.h
+++ b/include/linux/nd.h
@@ -11,6 +11,7 @@
 
 enum nvdimm_event {
 	NVDIMM_REVALIDATE_POISON,
+	NVDIMM_REVALIDATE_REGION,
 };
 
 enum nvdimm_claim_class {

From 632a1c209b8773cb0119fe3aada9f1db14fa357c Mon Sep 17 00:00:00 2001
From: Thomas Tai <thomas.tai@oracle.com>
Date: Thu, 8 Apr 2021 13:28:33 -0400
Subject: [PATCH 1690/1820] x86/traps: Correct exc_general_protection() and
 math_error() return paths

Commit

  334872a09198 ("x86/traps: Attempt to fixup exceptions in vDSO before signaling")

added return statements which bypass calling cond_local_irq_disable().

According to

  ca4c6a9858c2 ("x86/traps: Make interrupt enable/disable symmetric in C code"),

cond_local_irq_disable() is needed because the asm return code no longer
disables interrupts. Follow the existing code as an example to use "goto
exit" instead of "return" statement.

 [ bp: Massage commit message. ]

Fixes: 334872a09198 ("x86/traps: Attempt to fixup exceptions in vDSO before signaling")
Signed-off-by: Thomas Tai <thomas.tai@oracle.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com>
Link: https://lkml.kernel.org/r/1617902914-83245-1-git-send-email-thomas.tai@oracle.com
---
 arch/x86/kernel/traps.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ac1874a2a70e..651e3e508959 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -556,7 +556,7 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection)
 		tsk->thread.trap_nr = X86_TRAP_GP;
 
 		if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0))
-			return;
+			goto exit;
 
 		show_signal(tsk, SIGSEGV, "", desc, regs, error_code);
 		force_sig(SIGSEGV);
@@ -1057,7 +1057,7 @@ static void math_error(struct pt_regs *regs, int trapnr)
 		goto exit;
 
 	if (fixup_vdso_exception(regs, trapnr, 0, 0))
-		return;
+		goto exit;
 
 	force_sig_fault(SIGFPE, si_code,
 			(void __user *)uprobe_get_trap_addr(regs));

From 0760fa3d8f7fceeea508b98899f1c826e10ffe78 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Wed, 7 Apr 2021 20:57:33 -0700
Subject: [PATCH 1691/1820] percpu: make pcpu_nr_empty_pop_pages per chunk type

nr_empty_pop_pages is used to guarantee that there are some free
populated pages to satisfy atomic allocations. Accounted and
non-accounted allocations are using separate sets of chunks,
so both need to have a surplus of empty pages.

This commit makes pcpu_nr_empty_pop_pages and the corresponding logic
per chunk type.

[Dennis]
This issue came up as I was reviewing [1] and realized I missed this.
Simultaneously, it was reported btrfs was seeing failed atomic
allocations in fsstress tests [2] and [3].

[1] https://lore.kernel.org/linux-mm/20210324190626.564297-1-guro@fb.com/
[2] https://lore.kernel.org/linux-mm/20210401185158.3275.409509F4@e16-tech.com/
[3] https://lore.kernel.org/linux-mm/CAL3q7H5RNBjCi708GH7jnczAOe0BLnacT9C+OBgA-Dx9jhB6SQ@mail.gmail.com/

Fixes: 3c7be18ac9a0 ("mm: memcg/percpu: account percpu memory to memory cgroups")
Cc: stable@vger.kernel.org # 5.9+
Signed-off-by: Roman Gushchin <guro@fb.com>
Tested-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
---
 mm/percpu-internal.h |  2 +-
 mm/percpu-stats.c    |  9 +++++++--
 mm/percpu.c          | 14 +++++++-------
 3 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index 18b768ac7dca..095d7eaa0db4 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -87,7 +87,7 @@ extern spinlock_t pcpu_lock;
 
 extern struct list_head *pcpu_chunk_lists;
 extern int pcpu_nr_slots;
-extern int pcpu_nr_empty_pop_pages;
+extern int pcpu_nr_empty_pop_pages[];
 
 extern struct pcpu_chunk *pcpu_first_chunk;
 extern struct pcpu_chunk *pcpu_reserved_chunk;
diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
index c8400a2adbc2..f6026dbcdf6b 100644
--- a/mm/percpu-stats.c
+++ b/mm/percpu-stats.c
@@ -145,6 +145,7 @@ static int percpu_stats_show(struct seq_file *m, void *v)
 	int slot, max_nr_alloc;
 	int *buffer;
 	enum pcpu_chunk_type type;
+	int nr_empty_pop_pages;
 
 alloc_buffer:
 	spin_lock_irq(&pcpu_lock);
@@ -165,7 +166,11 @@ alloc_buffer:
 		goto alloc_buffer;
 	}
 
-#define PL(X) \
+	nr_empty_pop_pages = 0;
+	for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
+		nr_empty_pop_pages += pcpu_nr_empty_pop_pages[type];
+
+#define PL(X)								\
 	seq_printf(m, "  %-20s: %12lld\n", #X, (long long int)pcpu_stats_ai.X)
 
 	seq_printf(m,
@@ -196,7 +201,7 @@ alloc_buffer:
 	PU(nr_max_chunks);
 	PU(min_alloc_size);
 	PU(max_alloc_size);
-	P("empty_pop_pages", pcpu_nr_empty_pop_pages);
+	P("empty_pop_pages", nr_empty_pop_pages);
 	seq_putc(m, '\n');
 
 #undef PU
diff --git a/mm/percpu.c b/mm/percpu.c
index 6596a0a4286e..23308113a5ff 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -173,10 +173,10 @@ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */
 static LIST_HEAD(pcpu_map_extend_chunks);
 
 /*
- * The number of empty populated pages, protected by pcpu_lock.  The
- * reserved chunk doesn't contribute to the count.
+ * The number of empty populated pages by chunk type, protected by pcpu_lock.
+ * The reserved chunk doesn't contribute to the count.
  */
-int pcpu_nr_empty_pop_pages;
+int pcpu_nr_empty_pop_pages[PCPU_NR_CHUNK_TYPES];
 
 /*
  * The number of populated pages in use by the allocator, protected by
@@ -556,7 +556,7 @@ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr)
 {
 	chunk->nr_empty_pop_pages += nr;
 	if (chunk != pcpu_reserved_chunk)
-		pcpu_nr_empty_pop_pages += nr;
+		pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr;
 }
 
 /*
@@ -1832,7 +1832,7 @@ area_found:
 		mutex_unlock(&pcpu_alloc_mutex);
 	}
 
-	if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
+	if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_LOW)
 		pcpu_schedule_balance_work();
 
 	/* clear the areas and return address relative to base address */
@@ -2000,7 +2000,7 @@ retry_pop:
 		pcpu_atomic_alloc_failed = false;
 	} else {
 		nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
-				  pcpu_nr_empty_pop_pages,
+				  pcpu_nr_empty_pop_pages[type],
 				  0, PCPU_EMPTY_POP_PAGES_HIGH);
 	}
 
@@ -2580,7 +2580,7 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 	/* link the first chunk in */
 	pcpu_first_chunk = chunk;
-	pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages;
+	pcpu_nr_empty_pop_pages[PCPU_CHUNK_ROOT] = pcpu_first_chunk->nr_empty_pop_pages;
 	pcpu_chunk_relocate(pcpu_first_chunk, -1);
 
 	/* include all regions of the first chunk */

From 895915226a598394fe9bf57fe97612bdfcb2fb86 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 9 Apr 2021 15:58:50 +0200
Subject: [PATCH 1692/1820] Bluetooth: btusb: Revert Fix the autosuspend enable
 and disable

drivers/usb/core/hub.c: usb_new_device() contains the following:

        /* By default, forbid autosuspend for all devices.  It will be
         * allowed for hubs during binding.
         */
        usb_disable_autosuspend(udev);

So for anything which is not a hub, such as btusb devices, autosuspend is
disabled by default and we must call usb_enable_autosuspend(udev) to
enable it.

This means that the "Fix the autosuspend enable and disable" commit,
which drops the usb_enable_autosuspend() call when the enable_autosuspend
module option is true, is completely wrong, revert it.

This reverts commit 7bd9fb058d77213130e4b3e594115c028b708e7e.

Cc: Hui Wang <hui.wang@canonical.com>
Fixes: 7bd9fb058d77 ("Bluetooth: btusb: Fix the autosuspend enable and disable")
Acked-by: Hui Wang <hui.wang@canonical.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/bluetooth/btusb.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 52683fd22e05..5cbfbd948f67 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -4849,8 +4849,8 @@ static int btusb_probe(struct usb_interface *intf,
 			data->diag = NULL;
 	}
 
-	if (!enable_autosuspend)
-		usb_disable_autosuspend(data->udev);
+	if (enable_autosuspend)
+		usb_enable_autosuspend(data->udev);
 
 	err = hci_register_dev(hdev);
 	if (err < 0)
@@ -4910,9 +4910,6 @@ static void btusb_disconnect(struct usb_interface *intf)
 		gpiod_put(data->reset_gpio);
 
 	hci_free_dev(hdev);
-
-	if (!enable_autosuspend)
-		usb_enable_autosuspend(data->udev);
 }
 
 #ifdef CONFIG_PM

From d084d996aaf53c0cc583dc75a4fc2a67fe485846 Mon Sep 17 00:00:00 2001
From: Si-Wei Liu <si-wei.liu@oracle.com>
Date: Thu, 8 Apr 2021 12:10:43 +0300
Subject: [PATCH 1693/1820] vdpa/mlx5: should exclude header length and fcs
 from mtu

When feature VIRTIO_NET_F_MTU is negotiated on mlx5_vdpa,
22 extra bytes worth of MTU length is shown in guest.
This is because the mlx5_query_port_max_mtu API returns
the "hardware" MTU value, which does not just contain the
 Ethernet payload, but includes extra lengths starting
from the Ethernet header up to the FCS altogether.

Fix the MTU so packets won't get dropped silently.

Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eli Cohen <elic@nvidia.com>
Link: https://lore.kernel.org/r/20210408091047.4269-2-elic@nvidia.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/core/mlx5_vdpa.h |  4 ++++
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 15 ++++++++++++++-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 08f742fd2409..b6cc53ba980c 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -4,9 +4,13 @@
 #ifndef __MLX5_VDPA_H__
 #define __MLX5_VDPA_H__
 
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
 #include <linux/vdpa.h>
 #include <linux/mlx5/driver.h>
 
+#define MLX5V_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
+
 struct mlx5_vdpa_direct_mr {
 	u64 start;
 	u64 end;
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 71397fdafa6a..a49ebb250253 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1907,6 +1907,19 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = {
 	.free = mlx5_vdpa_free,
 };
 
+static int query_mtu(struct mlx5_core_dev *mdev, u16 *mtu)
+{
+	u16 hw_mtu;
+	int err;
+
+	err = mlx5_query_nic_vport_mtu(mdev, &hw_mtu);
+	if (err)
+		return err;
+
+	*mtu = hw_mtu - MLX5V_ETH_HARD_MTU;
+	return 0;
+}
+
 static int alloc_resources(struct mlx5_vdpa_net *ndev)
 {
 	struct mlx5_vdpa_net_resources *res = &ndev->res;
@@ -1992,7 +2005,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
 	init_mvqs(ndev);
 	mutex_init(&ndev->reslock);
 	config = &ndev->config;
-	err = mlx5_query_nic_vport_mtu(mdev, &ndev->mtu);
+	err = query_mtu(mdev, &ndev->mtu);
 	if (err)
 		goto err_mtu;
 

From d13a15d544ce51c0d83744ccb638c954e645feea Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Thu, 8 Apr 2021 12:10:44 +0300
Subject: [PATCH 1694/1820] vdpa/mlx5: Use the correct dma device when
 registering memory

In cases where the vdpa instance uses a SF (sub function), the DMA
device is the parent device. Use a function to retrieve the correct DMA
device.

Fixes: 1958fc2f0712 ("net/mlx5: SF, Add auxiliary device driver")
Signed-off-by: Eli Cohen <elic@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Link: https://lore.kernel.org/r/20210408091047.4269-3-elic@nvidia.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/mlx5/core/mr.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index d300f799efcd..3908ff28eec0 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -219,6 +219,11 @@ static void destroy_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_m
 	mlx5_vdpa_destroy_mkey(mvdev, &mkey->mkey);
 }
 
+static struct device *get_dma_device(struct mlx5_vdpa_dev *mvdev)
+{
+	return &mvdev->mdev->pdev->dev;
+}
+
 static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr,
 			 struct vhost_iotlb *iotlb)
 {
@@ -234,7 +239,7 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr
 	u64 pa;
 	u64 paend;
 	struct scatterlist *sg;
-	struct device *dma = mvdev->mdev->device;
+	struct device *dma = get_dma_device(mvdev);
 
 	for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1);
 	     map; map = vhost_iotlb_itree_next(map, start, mr->end - 1)) {
@@ -291,7 +296,7 @@ err_map:
 
 static void unmap_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr)
 {
-	struct device *dma = mvdev->mdev->device;
+	struct device *dma = get_dma_device(mvdev);
 
 	destroy_direct_mr(mvdev, mr);
 	dma_unmap_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0);

From b2ae0a2db8a2d42a643590c4935faf61fedf553b Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Thu, 8 Apr 2021 12:10:45 +0300
Subject: [PATCH 1695/1820] vdpa/mlx5: Retrieve BAR address suitable any
 function

struct mlx5_core_dev has a bar_addr field that contains the correct bar
address for the function regardless of whether it is pci function or sub
function. Use it.

Fixes: 1958fc2f0712 ("net/mlx5: SF, Add auxiliary device driver")
Signed-off-by: Eli Cohen <elic@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Link: https://lore.kernel.org/r/20210408091047.4269-4-elic@nvidia.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/mlx5/core/resources.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c
index 96e6421c5d1c..6521cbd0f5c2 100644
--- a/drivers/vdpa/mlx5/core/resources.c
+++ b/drivers/vdpa/mlx5/core/resources.c
@@ -246,7 +246,8 @@ int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev)
 	if (err)
 		goto err_key;
 
-	kick_addr = pci_resource_start(mdev->pdev, 0) + offset;
+	kick_addr = mdev->bar_addr + offset;
+
 	res->kick_addr = ioremap(kick_addr, PAGE_SIZE);
 	if (!res->kick_addr) {
 		err = -ENOMEM;

From 4b454a82418dd76d8c0590bb3f7a99a63ea57dc5 Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Thu, 8 Apr 2021 12:10:46 +0300
Subject: [PATCH 1696/1820] vdpa/mlx5: Fix wrong use of bit numbers

VIRTIO_F_VERSION_1 is a bit number. Use BIT_ULL() with mask
conditionals.

Also, in mlx5_vdpa_is_little_endian() use BIT_ULL for consistency with
the rest of the code.

Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
Signed-off-by: Eli Cohen <elic@nvidia.com>
Link: https://lore.kernel.org/r/20210408091047.4269-5-elic@nvidia.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index a49ebb250253..6fe61fc57790 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -820,7 +820,7 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 	MLX5_SET(virtio_q, vq_ctx, event_qpn_or_msix, mvq->fwqp.mqp.qpn);
 	MLX5_SET(virtio_q, vq_ctx, queue_size, mvq->num_ent);
 	MLX5_SET(virtio_q, vq_ctx, virtio_version_1_0,
-		 !!(ndev->mvdev.actual_features & VIRTIO_F_VERSION_1));
+		 !!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_F_VERSION_1)));
 	MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr);
 	MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr);
 	MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr);
@@ -1554,7 +1554,7 @@ static void clear_virtqueues(struct mlx5_vdpa_net *ndev)
 static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev)
 {
 	return virtio_legacy_is_little_endian() ||
-		(mvdev->actual_features & (1ULL << VIRTIO_F_VERSION_1));
+		(mvdev->actual_features & BIT_ULL(VIRTIO_F_VERSION_1));
 }
 
 static __virtio16 cpu_to_mlx5vdpa16(struct mlx5_vdpa_dev *mvdev, u16 val)

From bc04d93ea30a0a8eb2a2648b848cef35d1f6f798 Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Thu, 8 Apr 2021 12:10:47 +0300
Subject: [PATCH 1697/1820] vdpa/mlx5: Fix suspend/resume index restoration

When we suspend the VM, the VDPA interface will be reset. When the VM is
resumed again, clear_virtqueues() will clear the available and used
indices resulting in hardware virqtqueue objects becoming out of sync.
We can avoid this function alltogether since qemu will clear them if
required, e.g. when the VM went through a reboot.

Moreover, since the hw available and used indices should always be
identical on query and should be restored to the same value same value
for virtqueues that complete in order, we set the single value provided
by set_vq_state(). In get_vq_state() we return the value of hardware
used index.

Fixes: b35ccebe3ef7 ("vdpa/mlx5: Restore the hardware used index after change map")
Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
Signed-off-by: Eli Cohen <elic@nvidia.com>
Link: https://lore.kernel.org/r/20210408091047.4269-6-elic@nvidia.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c | 21 ++++++++-------------
 1 file changed, 8 insertions(+), 13 deletions(-)

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 6fe61fc57790..4d2809c7d4e3 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1169,6 +1169,7 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m
 		return;
 	}
 	mvq->avail_idx = attr.available_index;
+	mvq->used_idx = attr.used_index;
 }
 
 static void suspend_vqs(struct mlx5_vdpa_net *ndev)
@@ -1426,6 +1427,7 @@ static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx,
 		return -EINVAL;
 	}
 
+	mvq->used_idx = state->avail_index;
 	mvq->avail_idx = state->avail_index;
 	return 0;
 }
@@ -1443,7 +1445,11 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
 	 * that cares about emulating the index after vq is stopped.
 	 */
 	if (!mvq->initialized) {
-		state->avail_index = mvq->avail_idx;
+		/* Firmware returns a wrong value for the available index.
+		 * Since both values should be identical, we take the value of
+		 * used_idx which is reported correctly.
+		 */
+		state->avail_index = mvq->used_idx;
 		return 0;
 	}
 
@@ -1452,7 +1458,7 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
 		mlx5_vdpa_warn(mvdev, "failed to query virtqueue\n");
 		return err;
 	}
-	state->avail_index = attr.available_index;
+	state->avail_index = attr.used_index;
 	return 0;
 }
 
@@ -1540,16 +1546,6 @@ static void teardown_virtqueues(struct mlx5_vdpa_net *ndev)
 	}
 }
 
-static void clear_virtqueues(struct mlx5_vdpa_net *ndev)
-{
-	int i;
-
-	for (i = ndev->mvdev.max_vqs - 1; i >= 0; i--) {
-		ndev->vqs[i].avail_idx = 0;
-		ndev->vqs[i].used_idx = 0;
-	}
-}
-
 /* TODO: cross-endian support */
 static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev)
 {
@@ -1785,7 +1781,6 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
 	if (!status) {
 		mlx5_vdpa_info(mvdev, "performing device reset\n");
 		teardown_driver(ndev);
-		clear_virtqueues(ndev);
 		mlx5_vdpa_destroy_mr(&ndev->mvdev);
 		ndev->mvdev.status = 0;
 		ndev->mvdev.mlx_features = 0;

From f6d6c6993a30af46c3a2c323589611890c10ecda Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 9 Apr 2021 14:47:45 +0200
Subject: [PATCH 1698/1820] dt-bindings: don't use ../dir for doc references

As documents have been renamed and moved around, their
references will break, but this will be unnoticed, as the
script which checks for it won't handle "../" references.

So, replace them by the full patch.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/68d3a1244119d1f2829c375b0ef554cf348bc89f.1617972339.git.mchehab+huawei@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../input/touchscreen/resistive-adc-touch.txt    |  2 +-
 .../devicetree/bindings/mfd/motorola-cpcap.txt   | 16 ++++++++--------
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt b/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt
index 51456c0e9a27..fee0da12474e 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt
@@ -5,7 +5,7 @@ Required properties:
  - compatible: must be "resistive-adc-touch"
 The device must be connected to an ADC device that provides channels for
 position measurement and optional pressure.
-Refer to ../iio/iio-bindings.txt for details
+Refer to Documentation/devicetree/bindings/iio/iio-bindings.txt for details
  - iio-channels: must have at least two channels connected to an ADC device.
 These should correspond to the channels exposed by the ADC device and should
 have the right index as the ADC device registers them. These channels
diff --git a/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt b/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
index 5ddcc8f4febc..ebdccfb600b9 100644
--- a/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
+++ b/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
@@ -16,14 +16,14 @@ Optional subnodes:
 The sub-functions of CPCAP get their own node with their own compatible values,
 which are described in the following files:
 
-- ../power/supply/cpcap-battery.txt
-- ../power/supply/cpcap-charger.txt
-- ../regulator/cpcap-regulator.txt
-- ../phy/phy-cpcap-usb.txt
-- ../input/cpcap-pwrbutton.txt
-- ../rtc/cpcap-rtc.txt
-- ../leds/leds-cpcap.txt
-- ../iio/adc/cpcap-adc.txt
+- Documentation/devicetree/bindings/power/supply/cpcap-battery.txt
+- Documentation/devicetree/bindings/power/supply/cpcap-charger.txt
+- Documentation/devicetree/bindings/regulator/cpcap-regulator.txt
+- Documentation/devicetree/bindings/phy/phy-cpcap-usb.txt
+- Documentation/devicetree/bindings/input/cpcap-pwrbutton.txt
+- Documentation/devicetree/bindings/rtc/cpcap-rtc.txt
+- Documentation/devicetree/bindings/leds/leds-cpcap.txt
+- Documentation/devicetree/bindings/iio/adc/cpcap-adc.txt
 
 The only exception is the audio codec. Instead of a compatible value its
 node must be named "audio-codec".

From 8235ef155d00d903ff46df099175517ff08f34c9 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 9 Apr 2021 14:47:46 +0200
Subject: [PATCH 1699/1820] dt-bindings: fix references for iio-bindings.txt

The iio-bindings.txt was converted into two files and merged
at the dt-schema git tree at:

	https://github.com/devicetree-org/dt-schema

Yet, some documents still refer to the old file. Fix their
references, in order to point to the right URL.

Fixes: dba91f82d580 ("dt-bindings:iio:iio-binding.txt Drop file as content now in dt-schema")
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/4efd81eca266ca0875d3bf9d1672097444146c69.1617972339.git.mchehab+huawei@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt   | 2 +-
 Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml   | 5 +++--
 Documentation/devicetree/bindings/input/adc-joystick.yaml    | 4 +++-
 .../bindings/input/touchscreen/resistive-adc-touch.txt       | 5 ++++-
 Documentation/devicetree/bindings/mfd/ab8500.txt             | 4 +++-
 5 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
index 37f18d684f6a..4c5c3712970e 100644
--- a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
+++ b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
@@ -32,7 +32,7 @@ Optional node properties:
 - "#thermal-sensor-cells" Used to expose itself to thermal fw.
 
 Read more about iio bindings at
-	Documentation/devicetree/bindings/iio/iio-bindings.txt
+	https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/
 
 Example:
 	ncp15wb473@0 {
diff --git a/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml b/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml
index 9f414dbdae86..433a3fb55a2e 100644
--- a/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml
@@ -14,8 +14,9 @@ description: >
   Industrial I/O subsystem bindings for ADC controller found in
   Ingenic JZ47xx SoCs.
 
-  ADC clients must use the format described in iio-bindings.txt, giving
-  a phandle and IIO specifier pair ("io-channels") to the ADC controller.
+  ADC clients must use the format described in
+  https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml,
+  giving a phandle and IIO specifier pair ("io-channels") to the ADC controller.
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/input/adc-joystick.yaml b/Documentation/devicetree/bindings/input/adc-joystick.yaml
index 054406bbd22b..721878d5b7af 100644
--- a/Documentation/devicetree/bindings/input/adc-joystick.yaml
+++ b/Documentation/devicetree/bindings/input/adc-joystick.yaml
@@ -24,7 +24,9 @@ properties:
     description: >
       List of phandle and IIO specifier pairs.
       Each pair defines one ADC channel to which a joystick axis is connected.
-      See Documentation/devicetree/bindings/iio/iio-bindings.txt for details.
+      See
+      https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml
+      for details.
 
   '#address-cells':
     const: 1
diff --git a/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt b/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt
index fee0da12474e..af5223bb5bdd 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt
@@ -5,7 +5,10 @@ Required properties:
  - compatible: must be "resistive-adc-touch"
 The device must be connected to an ADC device that provides channels for
 position measurement and optional pressure.
-Refer to Documentation/devicetree/bindings/iio/iio-bindings.txt for details
+Refer to
+https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml
+for details
+
  - iio-channels: must have at least two channels connected to an ADC device.
 These should correspond to the channels exposed by the ADC device and should
 have the right index as the ADC device registers them. These channels
diff --git a/Documentation/devicetree/bindings/mfd/ab8500.txt b/Documentation/devicetree/bindings/mfd/ab8500.txt
index d2a6e835c257..937b3e5505e0 100644
--- a/Documentation/devicetree/bindings/mfd/ab8500.txt
+++ b/Documentation/devicetree/bindings/mfd/ab8500.txt
@@ -72,7 +72,9 @@ Required child device properties:
                                                pwm|regulator|rtc|sysctrl|usb]";
 
   A few child devices require ADC channels from the GPADC node. Those follow the
-  standard bindings from iio/iio-bindings.txt and iio/adc/adc.txt
+  standard bindings from
+  https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml
+  and Documentation/devicetree/bindings/iio/adc/adc.yaml
 
   abx500-temp		 : io-channels "aux1" and "aux2" for measuring external
 			   temperatures.

From 21d6ff39e1692b1f8c0d17331b15f76b40a3c726 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 9 Apr 2021 14:47:47 +0200
Subject: [PATCH 1700/1820] dt-bindings:iio:adc: update motorola,cpcap-adc.yaml
 reference

Changeset 1ca9d1b1342d ("dt-bindings:iio:adc:motorola,cpcap-adc yaml conversion")
renamed: Documentation/devicetree/bindings/iio/adc/cpcap-adc.txt
to: Documentation/devicetree/bindings/iio/adc/motorola,cpcap-adc.yaml.

Update its cross-reference accordingly.

Fixes: 1ca9d1b1342d ("dt-bindings:iio:adc:motorola,cpcap-adc yaml conversion")
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/3e205e5fa701e4bc15d39d6ac1f57717df2bb4c6.1617972339.git.mchehab+huawei@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/mfd/motorola-cpcap.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt b/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
index ebdccfb600b9..b52e7a33f0f9 100644
--- a/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
+++ b/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
@@ -23,7 +23,7 @@ which are described in the following files:
 - Documentation/devicetree/bindings/input/cpcap-pwrbutton.txt
 - Documentation/devicetree/bindings/rtc/cpcap-rtc.txt
 - Documentation/devicetree/bindings/leds/leds-cpcap.txt
-- Documentation/devicetree/bindings/iio/adc/cpcap-adc.txt
+- Documentation/devicetree/bindings/iio/adc/motorola,cpcap-adc.yaml
 
 The only exception is the audio codec. Instead of a compatible value its
 node must be named "audio-codec".

From d473d32c2fbac2d1d7082c61899cfebd34eb267a Mon Sep 17 00:00:00 2001
From: Ilya Lipnitskiy <ilya.lipnitskiy@gmail.com>
Date: Mon, 5 Apr 2021 15:25:40 -0700
Subject: [PATCH 1701/1820] of: property: fw_devlink: do not link ".*,nr-gpios"

[<vendor>,]nr-gpios property is used by some GPIO drivers[0] to indicate
the number of GPIOs present on a system, not define a GPIO. nr-gpios is
not configured by #gpio-cells and can't be parsed along with other
"*-gpios" properties.

nr-gpios without the "<vendor>," prefix is not allowed by the DT
spec[1], so only add exception for the ",nr-gpios" suffix and let the
error message continue being printed for non-compliant implementations.

[0] nr-gpios is referenced in Documentation/devicetree/bindings/gpio:
 - gpio-adnp.txt
 - gpio-xgene-sb.txt
 - gpio-xlp.txt
 - snps,dw-apb-gpio.yaml

[1] Link: https://github.com/devicetree-org/dt-schema/blob/cb53a16a1eb3e2169ce170c071e47940845ec26e/schemas/gpio/gpio-consumer.yaml#L20

Fixes errors such as:
  OF: /palmbus@300000/gpio@600: could not find phandle

Fixes: 7f00be96f125 ("of: property: Add device link support for interrupt-parent, dmas and -gpio(s)")
Signed-off-by: Ilya Lipnitskiy <ilya.lipnitskiy@gmail.com>
Cc: Saravana Kannan <saravanak@google.com>
Cc: stable@vger.kernel.org # v5.5+
Link: https://lore.kernel.org/r/20210405222540.18145-1-ilya.lipnitskiy@gmail.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/property.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/of/property.c b/drivers/of/property.c
index 5f9eed79a8aa..6d8368bf88ca 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1260,7 +1260,16 @@ DEFINE_SIMPLE_PROP(pinctrl7, "pinctrl-7", NULL)
 DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL)
 DEFINE_SUFFIX_PROP(regulators, "-supply", NULL)
 DEFINE_SUFFIX_PROP(gpio, "-gpio", "#gpio-cells")
-DEFINE_SUFFIX_PROP(gpios, "-gpios", "#gpio-cells")
+
+static struct device_node *parse_gpios(struct device_node *np,
+				       const char *prop_name, int index)
+{
+	if (!strcmp_suffix(prop_name, ",nr-gpios"))
+		return NULL;
+
+	return parse_suffix_prop_cells(np, prop_name, index, "-gpios",
+				       "#gpio-cells");
+}
 
 static struct device_node *parse_iommu_maps(struct device_node *np,
 					    const char *prop_name, int index)

From 3bc41d6d2721d5168a8f7fea34028a5332068f5e Mon Sep 17 00:00:00 2001
From: Sven Van Asbroeck <thesven73@gmail.com>
Date: Thu, 8 Apr 2021 20:39:04 -0400
Subject: [PATCH 1702/1820] lan743x: fix ethernet frame cutoff issue

The ethernet frame length is calculated incorrectly. Depending on
the value of RX_HEAD_PADDING, this may result in ethernet frames
that are too short (cut off at the end), or too long (garbage added
to the end).

Fix by calculating the ethernet frame length correctly. For added
clarity, use the ETH_FCS_LEN constant in the calculation.

Many thanks to Heiner Kallweit for suggesting this solution.

Suggested-by: Heiner Kallweit <hkallweit1@gmail.com>
Fixes: 3e21a10fdea3 ("lan743x: trim all 4 bytes of the FCS; not just 2")
Link: https://lore.kernel.org/lkml/20210408172353.21143-1-TheSven73@gmail.com/
Signed-off-by: Sven Van Asbroeck <thesven73@gmail.com>
Reviewed-by: George McCollister <george.mccollister@gmail.com>
Tested-by: George McCollister <george.mccollister@gmail.com>
Link: https://lore.kernel.org/r/20210409003904.8957-1-TheSven73@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 1c3e204d727c..7b6794aa8ea9 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -885,8 +885,8 @@ static int lan743x_mac_set_mtu(struct lan743x_adapter *adapter, int new_mtu)
 	}
 
 	mac_rx &= ~(MAC_RX_MAX_SIZE_MASK_);
-	mac_rx |= (((new_mtu + ETH_HLEN + 4) << MAC_RX_MAX_SIZE_SHIFT_) &
-		  MAC_RX_MAX_SIZE_MASK_);
+	mac_rx |= (((new_mtu + ETH_HLEN + ETH_FCS_LEN)
+		  << MAC_RX_MAX_SIZE_SHIFT_) & MAC_RX_MAX_SIZE_MASK_);
 	lan743x_csr_write(adapter, MAC_RX, mac_rx);
 
 	if (enabled) {
@@ -1944,7 +1944,7 @@ static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index)
 	struct sk_buff *skb;
 	dma_addr_t dma_ptr;
 
-	buffer_length = netdev->mtu + ETH_HLEN + 4 + RX_HEAD_PADDING;
+	buffer_length = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + RX_HEAD_PADDING;
 
 	descriptor = &rx->ring_cpu_ptr[index];
 	buffer_info = &rx->buffer_info[index];
@@ -2040,7 +2040,7 @@ lan743x_rx_trim_skb(struct sk_buff *skb, int frame_length)
 		dev_kfree_skb_irq(skb);
 		return NULL;
 	}
-	frame_length = max_t(int, 0, frame_length - RX_HEAD_PADDING - 4);
+	frame_length = max_t(int, 0, frame_length - ETH_FCS_LEN);
 	if (skb->len > frame_length) {
 		skb->tail -= skb->len - frame_length;
 		skb->len = frame_length;

From cd7e963d2f0875789ddb5c3746b628716bd0a8c9 Mon Sep 17 00:00:00 2001
From: Salil Mehta <salil.mehta@huawei.com>
Date: Fri, 9 Apr 2021 08:42:23 +0100
Subject: [PATCH 1703/1820] net: hns3: Trivial spell fix in hns3 driver

Some trivial spelling mistakes which caught my eye during the
review of the code.

Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Link: https://lore.kernel.org/r/20210409074223.32480-1-salil.mehta@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c   | 2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 2dd2af269b46..b0dbe6dcaa7b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -11210,7 +11210,7 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num,
 	if (ret)
 		return ret;
 
-	/* RSS indirection table has been configuared by user */
+	/* RSS indirection table has been configured by user */
 	if (rxfh_configured)
 		goto out;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 14b83eca0a5e..e295d359e912 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2193,7 +2193,7 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev)
 
 	if (test_and_clear_bit(HCLGEVF_RESET_PENDING,
 			       &hdev->reset_state)) {
-		/* PF has initmated that it is about to reset the hardware.
+		/* PF has intimated that it is about to reset the hardware.
 		 * We now have to poll & check if hardware has actually
 		 * completed the reset sequence. On hardware reset completion,
 		 * VF needs to reset the client and ae device.
@@ -3497,7 +3497,7 @@ static int hclgevf_set_channels(struct hnae3_handle *handle, u32 new_tqps_num,
 	if (ret)
 		return ret;
 
-	/* RSS indirection table has been configuared by user */
+	/* RSS indirection table has been configured by user */
 	if (rxfh_configured)
 		goto out;
 

From 27f0ad71699de41bae013c367b95a6b319cc46a9 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 9 Apr 2021 17:24:17 +0200
Subject: [PATCH 1704/1820] net: fix hangup on napi_disable for threaded napi

napi_disable() is subject to an hangup, when the threaded
mode is enabled and the napi is under heavy traffic.

If the relevant napi has been scheduled and the napi_disable()
kicks in before the next napi_threaded_wait() completes - so
that the latter quits due to the napi_disable_pending() condition,
the existing code leaves the NAPI_STATE_SCHED bit set and the
napi_disable() loop waiting for such bit will hang.

This patch addresses the issue by dropping the NAPI_STATE_DISABLE
bit test in napi_thread_wait(). The later napi_threaded_poll()
iteration will take care of clearing the NAPI_STATE_SCHED.

This also addresses a related problem reported by Jakub:
before this patch a napi_disable()/napi_enable() pair killed
the napi thread, effectively disabling the threaded mode.
On the patched kernel napi_disable() simply stops scheduling
the relevant thread.

v1 -> v2:
  - let the main napi_thread_poll() loop clear the SCHED bit

Reported-by: Jakub Kicinski <kuba@kernel.org>
Fixes: 29863d41bb6e ("net: implement threaded-able napi poll loop support")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/883923fa22745a9589e8610962b7dc59df09fb1f.1617981844.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 0f72ff5d34ba..af8c1ea040b9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6992,7 +6992,7 @@ static int napi_thread_wait(struct napi_struct *napi)
 
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	while (!kthread_should_stop() && !napi_disable_pending(napi)) {
+	while (!kthread_should_stop()) {
 		/* Testing SCHED_THREADED bit here to make sure the current
 		 * kthread owns this napi and could poll on this napi.
 		 * Testing SCHED bit is not enough because SCHED bit might be
@@ -7010,6 +7010,7 @@ static int napi_thread_wait(struct napi_struct *napi)
 		set_current_state(TASK_INTERRUPTIBLE);
 	}
 	__set_current_state(TASK_RUNNING);
+
 	return -1;
 }
 

From 4873d8cc141e76aa5f3e7ef6e98dfb3823fcbe6d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Fri, 9 Apr 2021 13:27:01 -0700
Subject: [PATCH 1705/1820] MAINTAINERS: update CZ.NIC's Turris information
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add all the files maintained by Turris team, not only for MOX, but also
for Omnia.  Change website.

Link: https://lkml.kernel.org/r/20210325171123.28093-1-kabel@kernel.org
Signed-off-by: Marek Behún <kabel@kernel.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Jassi Brar <jassisinghbrar@gmail.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 MAINTAINERS | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index c80ad735b384..2a6f7f5edd5a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1790,19 +1790,26 @@ F:	drivers/net/ethernet/cortina/
 F:	drivers/pinctrl/pinctrl-gemini.c
 F:	drivers/rtc/rtc-ftrtc010.c
 
-ARM/CZ.NIC TURRIS MOX SUPPORT
+ARM/CZ.NIC TURRIS SUPPORT
 M:	Marek Behun <marek.behun@nic.cz>
 S:	Maintained
-W:	http://mox.turris.cz
+W:	https://www.turris.cz/
 F:	Documentation/ABI/testing/debugfs-moxtet
 F:	Documentation/ABI/testing/sysfs-bus-moxtet-devices
 F:	Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm
 F:	Documentation/devicetree/bindings/bus/moxtet.txt
 F:	Documentation/devicetree/bindings/firmware/cznic,turris-mox-rwtm.txt
 F:	Documentation/devicetree/bindings/gpio/gpio-moxtet.txt
+F:	Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml
+F:	Documentation/devicetree/bindings/watchdog/armada-37xx-wdt.txt
 F:	drivers/bus/moxtet.c
 F:	drivers/firmware/turris-mox-rwtm.c
+F:	drivers/leds/leds-turris-omnia.c
+F:	drivers/mailbox/armada-37xx-rwtm-mailbox.c
 F:	drivers/gpio/gpio-moxtet.c
+F:	drivers/watchdog/armada_37xx_wdt.c
+F:	include/dt-bindings/bus/moxtet.h
+F:	include/linux/armada-37xx-rwtm-mailbox.h
 F:	include/linux/moxtet.h
 
 ARM/EZX SMARTPHONES (A780, A910, A1200, E680, ROKR E2 and ROKR E6)

From b37c38484375f5a204500e0b10b40da268090995 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Fri, 9 Apr 2021 13:27:04 -0700
Subject: [PATCH 1706/1820] treewide: change my e-mail address, fix my name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Change my e-mail address to kabel@kernel.org, and fix my name in
non-code parts (add diacritical mark).

Link: https://lkml.kernel.org/r/20210325171123.28093-2-kabel@kernel.org
Signed-off-by: Marek Behún <kabel@kernel.org>
Cc: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jassi Brar <jassisinghbrar@gmail.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/ABI/testing/debugfs-moxtet               |  4 ++--
 Documentation/ABI/testing/debugfs-turris-mox-rwtm      |  2 +-
 Documentation/ABI/testing/sysfs-bus-moxtet-devices     |  6 +++---
 .../ABI/testing/sysfs-class-led-driver-turris-omnia    |  2 +-
 .../ABI/testing/sysfs-firmware-turris-mox-rwtm         | 10 +++++-----
 .../bindings/leds/cznic,turris-omnia-leds.yaml         |  2 +-
 MAINTAINERS                                            |  2 +-
 arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts |  2 +-
 drivers/bus/moxtet.c                                   |  4 ++--
 drivers/firmware/turris-mox-rwtm.c                     |  4 ++--
 drivers/gpio/gpio-moxtet.c                             |  4 ++--
 drivers/leds/leds-turris-omnia.c                       |  4 ++--
 drivers/mailbox/armada-37xx-rwtm-mailbox.c             |  4 ++--
 drivers/watchdog/armada_37xx_wdt.c                     |  4 ++--
 include/dt-bindings/bus/moxtet.h                       |  2 +-
 include/linux/armada-37xx-rwtm-mailbox.h               |  2 +-
 include/linux/moxtet.h                                 |  2 +-
 17 files changed, 30 insertions(+), 30 deletions(-)

diff --git a/Documentation/ABI/testing/debugfs-moxtet b/Documentation/ABI/testing/debugfs-moxtet
index 6eee10c3d5a1..637d8587d03d 100644
--- a/Documentation/ABI/testing/debugfs-moxtet
+++ b/Documentation/ABI/testing/debugfs-moxtet
@@ -1,7 +1,7 @@
 What:		/sys/kernel/debug/moxtet/input
 Date:		March 2019
 KernelVersion:	5.3
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:	(Read) Read input from the shift registers, in hexadecimal.
 		Returns N+1 bytes, where N is the number of Moxtet connected
 		modules. The first byte is from the CPU board itself.
@@ -19,7 +19,7 @@ Description:	(Read) Read input from the shift registers, in hexadecimal.
 What:		/sys/kernel/debug/moxtet/output
 Date:		March 2019
 KernelVersion:	5.3
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:	(RW) Read last written value to the shift registers, in
 		hexadecimal, or write values to the shift registers, also
 		in hexadecimal.
diff --git a/Documentation/ABI/testing/debugfs-turris-mox-rwtm b/Documentation/ABI/testing/debugfs-turris-mox-rwtm
index 326df1b74707..813987d5de4e 100644
--- a/Documentation/ABI/testing/debugfs-turris-mox-rwtm
+++ b/Documentation/ABI/testing/debugfs-turris-mox-rwtm
@@ -1,7 +1,7 @@
 What:		/sys/kernel/debug/turris-mox-rwtm/do_sign
 Date:		Jun 2020
 KernelVersion:	5.8
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:
 
 		======= ===========================================================
diff --git a/Documentation/ABI/testing/sysfs-bus-moxtet-devices b/Documentation/ABI/testing/sysfs-bus-moxtet-devices
index 4a6d61b44f3f..32dccc00d57d 100644
--- a/Documentation/ABI/testing/sysfs-bus-moxtet-devices
+++ b/Documentation/ABI/testing/sysfs-bus-moxtet-devices
@@ -1,17 +1,17 @@
 What:		/sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_description
 Date:		March 2019
 KernelVersion:	5.3
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:	(Read) Moxtet module description. Format: string
 
 What:		/sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_id
 Date:		March 2019
 KernelVersion:	5.3
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:	(Read) Moxtet module ID. Format: %x
 
 What:		/sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_name
 Date:		March 2019
 KernelVersion:	5.3
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:	(Read) Moxtet module name. Format: string
diff --git a/Documentation/ABI/testing/sysfs-class-led-driver-turris-omnia b/Documentation/ABI/testing/sysfs-class-led-driver-turris-omnia
index 795a5de12fc1..c4d46970c1cf 100644
--- a/Documentation/ABI/testing/sysfs-class-led-driver-turris-omnia
+++ b/Documentation/ABI/testing/sysfs-class-led-driver-turris-omnia
@@ -1,7 +1,7 @@
 What:		/sys/class/leds/<led>/device/brightness
 Date:		July 2020
 KernelVersion:	5.9
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:	(RW) On the front panel of the Turris Omnia router there is also
 		a button which can be used to control the intensity of all the
 		LEDs at once, so that if they are too bright, user can dim them.
diff --git a/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm b/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm
index b8631f5a29c4..ea5e5b489bc7 100644
--- a/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm
+++ b/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm
@@ -1,21 +1,21 @@
 What:		/sys/firmware/turris-mox-rwtm/board_version
 Date:		August 2019
 KernelVersion:	5.4
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:	(Read) Board version burned into eFuses of this Turris Mox board.
 		Format: %i
 
 What:		/sys/firmware/turris-mox-rwtm/mac_address*
 Date:		August 2019
 KernelVersion:	5.4
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:	(Read) MAC addresses burned into eFuses of this Turris Mox board.
 		Format: %pM
 
 What:		/sys/firmware/turris-mox-rwtm/pubkey
 Date:		August 2019
 KernelVersion:	5.4
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:	(Read) ECDSA public key (in pubkey hex compressed form) computed
 		as pair to the ECDSA private key burned into eFuses of this
 		Turris Mox Board.
@@ -24,7 +24,7 @@ Description:	(Read) ECDSA public key (in pubkey hex compressed form) computed
 What:		/sys/firmware/turris-mox-rwtm/ram_size
 Date:		August 2019
 KernelVersion:	5.4
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:	(Read) RAM size in MiB of this Turris Mox board as was detected
 		during manufacturing and burned into eFuses. Can be 512 or 1024.
 		Format: %i
@@ -32,6 +32,6 @@ Description:	(Read) RAM size in MiB of this Turris Mox board as was detected
 What:		/sys/firmware/turris-mox-rwtm/serial_number
 Date:		August 2019
 KernelVersion:	5.4
-Contact:	Marek Behún <marek.behun@nic.cz>
+Contact:	Marek Behún <kabel@kernel.org>
 Description:	(Read) Serial number burned into eFuses of this Turris Mox device.
 		Format: %016X
diff --git a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml
index fe7fa25877fd..c7ed2871da06 100644
--- a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml
+++ b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: CZ.NIC's Turris Omnia LEDs driver
 
 maintainers:
-  - Marek Behún <marek.behun@nic.cz>
+  - Marek Behún <kabel@kernel.org>
 
 description:
   This module adds support for the RGB LEDs found on the front panel of the
diff --git a/MAINTAINERS b/MAINTAINERS
index 2a6f7f5edd5a..ba5cd29d2a48 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1791,7 +1791,7 @@ F:	drivers/pinctrl/pinctrl-gemini.c
 F:	drivers/rtc/rtc-ftrtc010.c
 
 ARM/CZ.NIC TURRIS SUPPORT
-M:	Marek Behun <marek.behun@nic.cz>
+M:	Marek Behun <kabel@kernel.org>
 S:	Maintained
 W:	https://www.turris.cz/
 F:	Documentation/ABI/testing/debugfs-moxtet
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
index d239ab70ed99..53e817c5f6f3 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0+ OR MIT)
 /*
  * Device Tree file for CZ.NIC Turris Mox Board
- * 2019 by Marek Behun <marek.behun@nic.cz>
+ * 2019 by Marek Behún <kabel@kernel.org>
  */
 
 /dts-v1/;
diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c
index b20fdcbd035b..fd87a59837fa 100644
--- a/drivers/bus/moxtet.c
+++ b/drivers/bus/moxtet.c
@@ -2,7 +2,7 @@
 /*
  * Turris Mox module configuration bus driver
  *
- * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz>
+ * Copyright (C) 2019 Marek Behún <kabel@kernel.org>
  */
 
 #include <dt-bindings/bus/moxtet.h>
@@ -879,6 +879,6 @@ static void __exit moxtet_exit(void)
 }
 module_exit(moxtet_exit);
 
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
 MODULE_DESCRIPTION("CZ.NIC's Turris Mox module configuration bus");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c
index 50bb2a6d6ccf..62f0d1a5dd32 100644
--- a/drivers/firmware/turris-mox-rwtm.c
+++ b/drivers/firmware/turris-mox-rwtm.c
@@ -2,7 +2,7 @@
 /*
  * Turris Mox rWTM firmware driver
  *
- * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz>
+ * Copyright (C) 2019 Marek Behún <kabel@kernel.org>
  */
 
 #include <linux/armada-37xx-rwtm-mailbox.h>
@@ -547,4 +547,4 @@ module_platform_driver(turris_mox_rwtm_driver);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Turris Mox rWTM firmware driver");
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
diff --git a/drivers/gpio/gpio-moxtet.c b/drivers/gpio/gpio-moxtet.c
index 8299909318f4..61f9efd6c64f 100644
--- a/drivers/gpio/gpio-moxtet.c
+++ b/drivers/gpio/gpio-moxtet.c
@@ -2,7 +2,7 @@
 /*
  *  Turris Mox Moxtet GPIO expander
  *
- *  Copyright (C) 2018 Marek Behun <marek.behun@nic.cz>
+ *  Copyright (C) 2018 Marek Behún <kabel@kernel.org>
  */
 
 #include <linux/bitops.h>
@@ -174,6 +174,6 @@ static struct moxtet_driver moxtet_gpio_driver = {
 };
 module_moxtet_driver(moxtet_gpio_driver);
 
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
 MODULE_DESCRIPTION("Turris Mox Moxtet GPIO expander");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/leds-turris-omnia.c b/drivers/leds/leds-turris-omnia.c
index 7b2f4d0ae3fe..2f9a289ab245 100644
--- a/drivers/leds/leds-turris-omnia.c
+++ b/drivers/leds/leds-turris-omnia.c
@@ -2,7 +2,7 @@
 /*
  * CZ.NIC's Turris Omnia LEDs driver
  *
- * 2020 by Marek Behun <marek.behun@nic.cz>
+ * 2020 by Marek Behún <kabel@kernel.org>
  */
 
 #include <linux/i2c.h>
@@ -287,6 +287,6 @@ static struct i2c_driver omnia_leds_driver = {
 
 module_i2c_driver(omnia_leds_driver);
 
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
 MODULE_DESCRIPTION("CZ.NIC's Turris Omnia LEDs");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mailbox/armada-37xx-rwtm-mailbox.c b/drivers/mailbox/armada-37xx-rwtm-mailbox.c
index 9f2ce7f03c67..456a117a65fd 100644
--- a/drivers/mailbox/armada-37xx-rwtm-mailbox.c
+++ b/drivers/mailbox/armada-37xx-rwtm-mailbox.c
@@ -2,7 +2,7 @@
 /*
  * rWTM BIU Mailbox driver for Armada 37xx
  *
- * Author: Marek Behun <marek.behun@nic.cz>
+ * Author: Marek Behún <kabel@kernel.org>
  */
 
 #include <linux/device.h>
@@ -203,4 +203,4 @@ module_platform_driver(armada_37xx_mbox_driver);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("rWTM BIU Mailbox driver for Armada 37xx");
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
diff --git a/drivers/watchdog/armada_37xx_wdt.c b/drivers/watchdog/armada_37xx_wdt.c
index e5dcb26d85f0..1635f421ef2c 100644
--- a/drivers/watchdog/armada_37xx_wdt.c
+++ b/drivers/watchdog/armada_37xx_wdt.c
@@ -2,7 +2,7 @@
 /*
  * Watchdog driver for Marvell Armada 37xx SoCs
  *
- * Author: Marek Behun <marek.behun@nic.cz>
+ * Author: Marek Behún <kabel@kernel.org>
  */
 
 #include <linux/clk.h>
@@ -366,7 +366,7 @@ static struct platform_driver armada_37xx_wdt_driver = {
 
 module_platform_driver(armada_37xx_wdt_driver);
 
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
 MODULE_DESCRIPTION("Armada 37xx CPU Watchdog");
 
 MODULE_LICENSE("GPL v2");
diff --git a/include/dt-bindings/bus/moxtet.h b/include/dt-bindings/bus/moxtet.h
index dc9345440ebe..10528de7b3ef 100644
--- a/include/dt-bindings/bus/moxtet.h
+++ b/include/dt-bindings/bus/moxtet.h
@@ -2,7 +2,7 @@
 /*
  * Constant for device tree bindings for Turris Mox module configuration bus
  *
- * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz>
+ * Copyright (C) 2019 Marek Behún <kabel@kernel.org>
  */
 
 #ifndef _DT_BINDINGS_BUS_MOXTET_H
diff --git a/include/linux/armada-37xx-rwtm-mailbox.h b/include/linux/armada-37xx-rwtm-mailbox.h
index 57bb54f6767a..ef4bd705eb65 100644
--- a/include/linux/armada-37xx-rwtm-mailbox.h
+++ b/include/linux/armada-37xx-rwtm-mailbox.h
@@ -2,7 +2,7 @@
 /*
  * rWTM BIU Mailbox driver for Armada 37xx
  *
- * Author: Marek Behun <marek.behun@nic.cz>
+ * Author: Marek Behún <kabel@kernel.org>
  */
 
 #ifndef _LINUX_ARMADA_37XX_RWTM_MAILBOX_H_
diff --git a/include/linux/moxtet.h b/include/linux/moxtet.h
index 490db6886dcc..79184948fab4 100644
--- a/include/linux/moxtet.h
+++ b/include/linux/moxtet.h
@@ -2,7 +2,7 @@
 /*
  * Turris Mox module configuration bus driver
  *
- * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz>
+ * Copyright (C) 2019 Marek Behún <kabel@kernel.org>
  */
 
 #ifndef __LINUX_MOXTET_H

From 620ff418ef440f2d585d8c8b2e9396ccfacaacd7 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jordan@cosmicpenguin.net>
Date: Fri, 9 Apr 2021 13:27:07 -0700
Subject: [PATCH 1707/1820] mailmap: update email address for Jordan Crouse

jcrouse at codeaurora.org has started bouncing.  Redirect to a more
permanent address.

Link: https://lkml.kernel.org/r/20210325143700.1490518-1-jordan@cosmicpenguin.net
Signed-off-by: Jordan Crouse <jordan@cosmicpenguin.net>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index 541635d2e02e..c5642d66ce72 100644
--- a/.mailmap
+++ b/.mailmap
@@ -168,6 +168,7 @@ Johan Hovold <johan@kernel.org> <jhovold@gmail.com>
 Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
 John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
 John Stultz <johnstul@us.ibm.com>
+Jordan Crouse <jordan@cosmicpenguin.net> <jcrouse@codeaurora.org>
 <josh@joshtriplett.org> <josh@freedesktop.org>
 <josh@joshtriplett.org> <josh@kernel.org>
 <josh@joshtriplett.org> <josht@linux.vnet.ibm.com>

From a5c5e441518f1f39da7ed3ef8e61361a9ea90c8b Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Fri, 9 Apr 2021 13:27:10 -0700
Subject: [PATCH 1708/1820] .mailmap: fix old email addresses

Update Nick & Nadia's old addresses.

Link: https://lkml.kernel.org/r/20210406134036.GQ2531743@casper.infradead.org
Signed-off-by: Matthew Wilcox <willy@infradead.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Nadia Yvette Chambers <nyc@holomorphy.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .mailmap | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/.mailmap b/.mailmap
index c5642d66ce72..2d93232ed72b 100644
--- a/.mailmap
+++ b/.mailmap
@@ -254,8 +254,14 @@ Morten Welinder <welinder@anemone.rentec.com>
 Morten Welinder <welinder@darter.rentec.com>
 Morten Welinder <welinder@troll.com>
 Mythri P K <mythripk@ti.com>
+Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com>
 Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com>
 Nguyen Anh Quynh <aquynh@gmail.com>
+Nicholas Piggin <npiggin@gmail.com> <npiggen@suse.de>
+Nicholas Piggin <npiggin@gmail.com> <npiggin@kernel.dk>
+Nicholas Piggin <npiggin@gmail.com> <npiggin@suse.de>
+Nicholas Piggin <npiggin@gmail.com> <nickpiggin@yahoo.com.au>
+Nicholas Piggin <npiggin@gmail.com> <piggin@cyberone.com.au>
 Nicolas Ferre <nicolas.ferre@microchip.com> <nicolas.ferre@atmel.com>
 Nicolas Pitre <nico@fluxnic.net> <nicolas.pitre@linaro.org>
 Nicolas Pitre <nico@fluxnic.net> <nico@linaro.org>

From d3378e86d1822b6d0bebfbc18a8348691c05dfa0 Mon Sep 17 00:00:00 2001
From: Aili Yao <yaoaili@kingsoft.com>
Date: Fri, 9 Apr 2021 13:27:19 -0700
Subject: [PATCH 1709/1820] mm/gup: check page posion status for coredump.

When we do coredump for user process signal, this may be an SIGBUS signal
with BUS_MCEERR_AR or BUS_MCEERR_AO code, which means this signal is
resulted from ECC memory fail like SRAR or SRAO, we expect the memory
recovery work is finished correctly, then the get_dump_page() will not
return the error page as its process pte is set invalid by
memory_failure().

But memory_failure() may fail, and the process's related pte may not be
correctly set invalid, for current code, we will return the poison page,
get it dumped, and then lead to system panic as its in kernel code.

So check the poison status in get_dump_page(), and if TRUE, return NULL.

There maybe other scenario that is also better to check the posion status
and not to panic, so make a wrapper for this check, Thanks to David's
suggestion(<david@redhat.com>).

[akpm@linux-foundation.org: s/0/false/]
[yaoaili@kingsoft.com: is_page_poisoned() arg cannot be null, per Matthew]

Link: https://lkml.kernel.org/r/20210322115233.05e4e82a@alex-virtual-machine
Link: https://lkml.kernel.org/r/20210319104437.6f30e80d@alex-virtual-machine
Signed-off-by: Aili Yao <yaoaili@kingsoft.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Aili Yao <yaoaili@kingsoft.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/gup.c      |  4 ++++
 mm/internal.h | 20 ++++++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/mm/gup.c b/mm/gup.c
index e40579624f10..ef7d2da9f03f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1535,6 +1535,10 @@ struct page *get_dump_page(unsigned long addr)
 				      FOLL_FORCE | FOLL_DUMP | FOLL_GET);
 	if (locked)
 		mmap_read_unlock(mm);
+
+	if (ret == 1 && is_page_poisoned(page))
+		return NULL;
+
 	return (ret == 1) ? page : NULL;
 }
 #endif /* CONFIG_ELF_CORE */
diff --git a/mm/internal.h b/mm/internal.h
index 1432feec62df..cb3c5e0a7799 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -97,6 +97,26 @@ static inline void set_page_refcounted(struct page *page)
 	set_page_count(page, 1);
 }
 
+/*
+ * When kernel touch the user page, the user page may be have been marked
+ * poison but still mapped in user space, if without this page, the kernel
+ * can guarantee the data integrity and operation success, the kernel is
+ * better to check the posion status and avoid touching it, be good not to
+ * panic, coredump for process fatal signal is a sample case matching this
+ * scenario. Or if kernel can't guarantee the data integrity, it's better
+ * not to call this function, let kernel touch the poison page and get to
+ * panic.
+ */
+static inline bool is_page_poisoned(struct page *page)
+{
+	if (PageHWPoison(page))
+		return true;
+	else if (PageHuge(page) && PageHWPoison(compound_head(page)))
+		return true;
+
+	return false;
+}
+
 extern unsigned long highest_memmap_pfn;
 
 /*

From a3a8833dffb7e7329c2586b8bfc531adb503f123 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Fri, 9 Apr 2021 13:27:23 -0700
Subject: [PATCH 1710/1820] nds32: flush_dcache_page: use page_mapping_file to
 avoid races with swapoff

Commit cb9f753a3731 ("mm: fix races between swapoff and flush dcache")
updated flush_dcache_page implementations on several architectures to
use page_mapping_file() in order to avoid races between page_mapping()
and swapoff().

This update missed arch/nds32 and there is a possibility of a race
there.

Replace page_mapping() with page_mapping_file() in nds32 implementation
of flush_dcache_page().

Link: https://lkml.kernel.org/r/20210330175126.26500-1-rppt@kernel.org
Fixes: cb9f753a3731 ("mm: fix races between swapoff and flush dcache")
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Greentime Hu <green.hu@gmail.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/nds32/mm/cacheflush.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c
index 6eb98a7ad27d..ad5344ef5d33 100644
--- a/arch/nds32/mm/cacheflush.c
+++ b/arch/nds32/mm/cacheflush.c
@@ -238,7 +238,7 @@ void flush_dcache_page(struct page *page)
 {
 	struct address_space *mapping;
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 	if (mapping && !mapping_mapped(mapping))
 		set_bit(PG_dcache_dirty, &page->flags);
 	else {

From 9562fd132985ea9185388a112e50f2a51557827d Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Fri, 9 Apr 2021 13:27:26 -0700
Subject: [PATCH 1711/1820] gcov: re-fix clang-11+ support

LLVM changed the expected function signature for llvm_gcda_emit_function()
in the clang-11 release.  Users of clang-11 or newer may have noticed
their kernels producing invalid coverage information:

  $ llvm-cov gcov -a -c -u -f -b <input>.gcda -- gcno=<input>.gcno
  1 <func>: checksum mismatch, \
    (<lineno chksum A>, <cfg chksum B>) != (<lineno chksum A>, <cfg chksum C>)
  2 Invalid .gcda File!
  ...

Fix up the function signatures so calling this function interprets its
parameters correctly and computes the correct cfg checksum.  In
particular, in clang-11, the additional checksum is no longer optional.

Link: https://reviews.llvm.org/rG25544ce2df0daa4304c07e64b9c8b0f7df60c11d
Link: https://lkml.kernel.org/r/20210408184631.1156669-1-ndesaulniers@google.com
Reported-by: Prasad Sodagudi <psodagud@quicinc.com>
Tested-by: Prasad Sodagudi <psodagud@quicinc.com>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Cc: <stable@vger.kernel.org>	[5.4+]

Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/gcov/clang.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c
index 8743150db2ac..c466c7fbdece 100644
--- a/kernel/gcov/clang.c
+++ b/kernel/gcov/clang.c
@@ -70,7 +70,9 @@ struct gcov_fn_info {
 
 	u32 ident;
 	u32 checksum;
+#if CONFIG_CLANG_VERSION < 110000
 	u8 use_extra_checksum;
+#endif
 	u32 cfg_checksum;
 
 	u32 num_counters;
@@ -145,10 +147,8 @@ void llvm_gcda_emit_function(u32 ident, const char *function_name,
 
 	list_add_tail(&info->head, &current_info->functions);
 }
-EXPORT_SYMBOL(llvm_gcda_emit_function);
 #else
-void llvm_gcda_emit_function(u32 ident, u32 func_checksum,
-		u8 use_extra_checksum, u32 cfg_checksum)
+void llvm_gcda_emit_function(u32 ident, u32 func_checksum, u32 cfg_checksum)
 {
 	struct gcov_fn_info *info = kzalloc(sizeof(*info), GFP_KERNEL);
 
@@ -158,12 +158,11 @@ void llvm_gcda_emit_function(u32 ident, u32 func_checksum,
 	INIT_LIST_HEAD(&info->head);
 	info->ident = ident;
 	info->checksum = func_checksum;
-	info->use_extra_checksum = use_extra_checksum;
 	info->cfg_checksum = cfg_checksum;
 	list_add_tail(&info->head, &current_info->functions);
 }
-EXPORT_SYMBOL(llvm_gcda_emit_function);
 #endif
+EXPORT_SYMBOL(llvm_gcda_emit_function);
 
 void llvm_gcda_emit_arcs(u32 num_counters, u64 *counters)
 {
@@ -293,11 +292,16 @@ int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2)
 		!list_is_last(&fn_ptr2->head, &info2->functions)) {
 		if (fn_ptr1->checksum != fn_ptr2->checksum)
 			return false;
+#if CONFIG_CLANG_VERSION < 110000
 		if (fn_ptr1->use_extra_checksum != fn_ptr2->use_extra_checksum)
 			return false;
 		if (fn_ptr1->use_extra_checksum &&
 			fn_ptr1->cfg_checksum != fn_ptr2->cfg_checksum)
 			return false;
+#else
+		if (fn_ptr1->cfg_checksum != fn_ptr2->cfg_checksum)
+			return false;
+#endif
 		fn_ptr1 = list_next_entry(fn_ptr1, head);
 		fn_ptr2 = list_next_entry(fn_ptr2, head);
 	}
@@ -529,17 +533,22 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info)
 
 	list_for_each_entry(fi_ptr, &info->functions, head) {
 		u32 i;
-		u32 len = 2;
-
-		if (fi_ptr->use_extra_checksum)
-			len++;
 
 		pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION);
-		pos += store_gcov_u32(buffer, pos, len);
+#if CONFIG_CLANG_VERSION < 110000
+		pos += store_gcov_u32(buffer, pos,
+			fi_ptr->use_extra_checksum ? 3 : 2);
+#else
+		pos += store_gcov_u32(buffer, pos, 3);
+#endif
 		pos += store_gcov_u32(buffer, pos, fi_ptr->ident);
 		pos += store_gcov_u32(buffer, pos, fi_ptr->checksum);
+#if CONFIG_CLANG_VERSION < 110000
 		if (fi_ptr->use_extra_checksum)
 			pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum);
+#else
+		pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum);
+#endif
 
 		pos += store_gcov_u32(buffer, pos, GCOV_TAG_COUNTER_BASE);
 		pos += store_gcov_u32(buffer, pos, fi_ptr->num_counters * 2);

From 90bd070aae6c4fb5d302f9c4b9c88be60c8197ec Mon Sep 17 00:00:00 2001
From: Wengang Wang <wen.gang.wang@oracle.com>
Date: Fri, 9 Apr 2021 13:27:29 -0700
Subject: [PATCH 1712/1820] ocfs2: fix deadlock between setattr and
 dio_end_io_write

The following deadlock is detected:

  truncate -> setattr path is waiting for pending direct IO to be done (inode->i_dio_count become zero) with inode->i_rwsem held (down_write).

  PID: 14827  TASK: ffff881686a9af80  CPU: 20  COMMAND: "ora_p005_hrltd9"
   #0  __schedule at ffffffff818667cc
   #1  schedule at ffffffff81866de6
   #2  inode_dio_wait at ffffffff812a2d04
   #3  ocfs2_setattr at ffffffffc05f322e [ocfs2]
   #4  notify_change at ffffffff812a5a09
   #5  do_truncate at ffffffff812808f5
   #6  do_sys_ftruncate.constprop.18 at ffffffff81280cf2
   #7  sys_ftruncate at ffffffff81280d8e
   #8  do_syscall_64 at ffffffff81003949
   #9  entry_SYSCALL_64_after_hwframe at ffffffff81a001ad

dio completion path is going to complete one direct IO (decrement
inode->i_dio_count), but before that it hung at locking inode->i_rwsem:

   #0  __schedule+700 at ffffffff818667cc
   #1  schedule+54 at ffffffff81866de6
   #2  rwsem_down_write_failed+536 at ffffffff8186aa28
   #3  call_rwsem_down_write_failed+23 at ffffffff8185a1b7
   #4  down_write+45 at ffffffff81869c9d
   #5  ocfs2_dio_end_io_write+180 at ffffffffc05d5444 [ocfs2]
   #6  ocfs2_dio_end_io+85 at ffffffffc05d5a85 [ocfs2]
   #7  dio_complete+140 at ffffffff812c873c
   #8  dio_aio_complete_work+25 at ffffffff812c89f9
   #9  process_one_work+361 at ffffffff810b1889
  #10  worker_thread+77 at ffffffff810b233d
  #11  kthread+261 at ffffffff810b7fd5
  #12  ret_from_fork+62 at ffffffff81a0035e

Thus above forms ABBA deadlock.  The same deadlock was mentioned in
upstream commit 28f5a8a7c033 ("ocfs2: should wait dio before inode lock
in ocfs2_setattr()").  It seems that that commit only removed the
cluster lock (the victim of above dead lock) from the ABBA deadlock
party.

End-user visible effects: Process hang in truncate -> ocfs2_setattr path
and other processes hang at ocfs2_dio_end_io_write path.

This is to fix the deadlock itself.  It removes inode_lock() call from
dio completion path to remove the deadlock and add ip_alloc_sem lock in
setattr path to synchronize the inode modifications.

[wen.gang.wang@oracle.com: remove the "had_alloc_lock" as suggested]
  Link: https://lkml.kernel.org/r/20210402171344.1605-1-wen.gang.wang@oracle.com

Link: https://lkml.kernel.org/r/20210331203654.3911-1-wen.gang.wang@oracle.com
Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Gang He <ghe@suse.com>
Cc: Jun Piao <piaojun@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ocfs2/aops.c | 11 +----------
 fs/ocfs2/file.c |  8 ++++++--
 2 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 3bfb4147895a..ad20403b383f 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2295,7 +2295,7 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
 	struct ocfs2_alloc_context *meta_ac = NULL;
 	handle_t *handle = NULL;
 	loff_t end = offset + bytes;
-	int ret = 0, credits = 0, locked = 0;
+	int ret = 0, credits = 0;
 
 	ocfs2_init_dealloc_ctxt(&dealloc);
 
@@ -2306,13 +2306,6 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
 	    !dwc->dw_orphaned)
 		goto out;
 
-	/* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
-	 * are in that context. */
-	if (dwc->dw_writer_pid != task_pid_nr(current)) {
-		inode_lock(inode);
-		locked = 1;
-	}
-
 	ret = ocfs2_inode_lock(inode, &di_bh, 1);
 	if (ret < 0) {
 		mlog_errno(ret);
@@ -2393,8 +2386,6 @@ out:
 	if (meta_ac)
 		ocfs2_free_alloc_context(meta_ac);
 	ocfs2_run_deallocs(osb, &dealloc);
-	if (locked)
-		inode_unlock(inode);
 	ocfs2_dio_free_write_ctx(inode, dwc);
 
 	return ret;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 6611c64ca0be..5edc1d0cf115 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1245,22 +1245,24 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 				goto bail_unlock;
 			}
 		}
+		down_write(&OCFS2_I(inode)->ip_alloc_sem);
 		handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS +
 					   2 * ocfs2_quota_trans_credits(sb));
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
 			mlog_errno(status);
-			goto bail_unlock;
+			goto bail_unlock_alloc;
 		}
 		status = __dquot_transfer(inode, transfer_to);
 		if (status < 0)
 			goto bail_commit;
 	} else {
+		down_write(&OCFS2_I(inode)->ip_alloc_sem);
 		handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
 			mlog_errno(status);
-			goto bail_unlock;
+			goto bail_unlock_alloc;
 		}
 	}
 
@@ -1273,6 +1275,8 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 
 bail_commit:
 	ocfs2_commit_trans(osb, handle);
+bail_unlock_alloc:
+	up_write(&OCFS2_I(inode)->ip_alloc_sem);
 bail_unlock:
 	if (status && inode_locked) {
 		ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);

From 7ad1e366167837daeb93d0bacb57dee820b0b898 Mon Sep 17 00:00:00 2001
From: Sergei Trofimovich <slyfox@gentoo.org>
Date: Fri, 9 Apr 2021 13:27:32 -0700
Subject: [PATCH 1713/1820] ia64: fix user_stack_pointer() for ptrace()

ia64 has two stacks:

 - memory stack (or stack), pointed at by by r12

 - register backing store (register stack), pointed at by
   ar.bsp/ar.bspstore with complications around dirty
   register frame on CPU.

In [1] Dmitry noticed that PTRACE_GET_SYSCALL_INFO returns the register
stack instead memory stack.

The bug comes from the fact that user_stack_pointer() and
current_user_stack_pointer() don't return the same register:

  ulong user_stack_pointer(struct pt_regs *regs) { return regs->ar_bspstore; }
  #define current_user_stack_pointer() (current_pt_regs()->r12)

The change gets both back in sync.

I think ptrace(PTRACE_GET_SYSCALL_INFO) is the only affected user by
this bug on ia64.

The change fixes 'rt_sigreturn.gen.test' strace test where it was
observed initially.

Link: https://bugs.gentoo.org/769614 [1]
Link: https://lkml.kernel.org/r/20210331084447.2561532-1-slyfox@gentoo.org
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Reported-by: Dmitry V. Levin <ldv@altlinux.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/include/asm/ptrace.h | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/arch/ia64/include/asm/ptrace.h b/arch/ia64/include/asm/ptrace.h
index b3aa46090101..08179135905c 100644
--- a/arch/ia64/include/asm/ptrace.h
+++ b/arch/ia64/include/asm/ptrace.h
@@ -54,8 +54,7 @@
 
 static inline unsigned long user_stack_pointer(struct pt_regs *regs)
 {
-	/* FIXME: should this be bspstore + nr_dirty regs? */
-	return regs->ar_bspstore;
+	return regs->r12;
 }
 
 static inline int is_syscall_success(struct pt_regs *regs)
@@ -79,11 +78,6 @@ static inline long regs_return_value(struct pt_regs *regs)
 	unsigned long __ip = instruction_pointer(regs);			\
 	(__ip & ~3UL) + ((__ip & 3UL) << 2);				\
 })
-/*
- * Why not default?  Because user_stack_pointer() on ia64 gives register
- * stack backing store instead...
- */
-#define current_user_stack_pointer() (current_pt_regs()->r12)
 
   /* given a pointer to a task_struct, return the user's pt_regs */
 # define task_pt_regs(t)		(((struct pt_regs *) ((char *) (t) + IA64_STK_OFFSET)) - 1)

From df41872b68601059dd4a84858952dcae58acd331 Mon Sep 17 00:00:00 2001
From: Jack Qiu <jack.qiu@huawei.com>
Date: Fri, 9 Apr 2021 13:27:35 -0700
Subject: [PATCH 1714/1820] fs: direct-io: fix missing sdio->boundary

I encountered a hung task issue, but not a performance one.  I run DIO
on a device (need lba continuous, for example open channel ssd), maybe
hungtask in below case:

  DIO:						Checkpoint:
  get addr A(at boundary), merge into BIO,
  no submit because boundary missing
						flush dirty data(get addr A+1), wait IO(A+1)
						writeback timeout, because DIO(A) didn't submit
  get addr A+2 fail, because checkpoint is doing

dio_send_cur_page() may clear sdio->boundary, so prevent it from missing
a boundary.

Link: https://lkml.kernel.org/r/20210322042253.38312-1-jack.qiu@huawei.com
Fixes: b1058b981272 ("direct-io: submit bio after boundary buffer is added to it")
Signed-off-by: Jack Qiu <jack.qiu@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/direct-io.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/direct-io.c b/fs/direct-io.c
index b61491bf3166..b2e86e739d7a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -812,6 +812,7 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 		    struct buffer_head *map_bh)
 {
 	int ret = 0;
+	int boundary = sdio->boundary;	/* dio_send_cur_page may clear it */
 
 	if (dio->op == REQ_OP_WRITE) {
 		/*
@@ -850,10 +851,10 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 	sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits;
 out:
 	/*
-	 * If sdio->boundary then we want to schedule the IO now to
+	 * If boundary then we want to schedule the IO now to
 	 * avoid metadata seeks.
 	 */
-	if (sdio->boundary) {
+	if (boundary) {
 		ret = dio_send_cur_page(dio, sdio, map_bh);
 		if (sdio->bio)
 			dio_bio_submit(dio, sdio);

From 06b1f85588948bd4c772845e5d6891b8f6082248 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Fri, 9 Apr 2021 13:27:38 -0700
Subject: [PATCH 1715/1820] kasan: fix conflict with page poisoning

When page poisoning is enabled, it accesses memory that is marked as
poisoned by KASAN, which leas to false-positive KASAN reports.

Suppress the reports by adding KASAN annotations to unpoison_page()
(poison_page() already has them).

Link: https://lkml.kernel.org/r/2dc799014d31ac13fd97bd906bad33e16376fc67.1617118501.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_poison.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/mm/page_poison.c b/mm/page_poison.c
index 65cdf844c8ad..655dc5895604 100644
--- a/mm/page_poison.c
+++ b/mm/page_poison.c
@@ -77,12 +77,14 @@ static void unpoison_page(struct page *page)
 	void *addr;
 
 	addr = kmap_atomic(page);
+	kasan_disable_current();
 	/*
 	 * Page poisoning when enabled poisons each and every page
 	 * that is freed to buddy. Thus no extra check is done to
 	 * see if a page was poisoned.
 	 */
-	check_poison_mem(addr, PAGE_SIZE);
+	check_poison_mem(kasan_reset_tag(addr), PAGE_SIZE);
+	kasan_enable_current();
 	kunmap_atomic(addr);
 }
 

From e156656717b810202914b77557de8112df4dad0d Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Fri, 9 Apr 2021 13:27:41 -0700
Subject: [PATCH 1716/1820] lib/test_kasan_module.c: suppress unused var
 warning

Local `unused' is intentionally unused - it is there to suppress
__must_check warnings.

Reported-by: kernel test robot <lkp@intel.com>
Link: https://lkml.kernel.org/r/202104050216.HflRxfJm-lkp@intel.com
Cc: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/test_kasan_module.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/test_kasan_module.c b/lib/test_kasan_module.c
index eee017ff8980..f1017f345d6c 100644
--- a/lib/test_kasan_module.c
+++ b/lib/test_kasan_module.c
@@ -22,7 +22,7 @@ static noinline void __init copy_user_test(void)
 	char *kmem;
 	char __user *usermem;
 	size_t size = 10;
-	int unused;
+	int __maybe_unused unused;
 
 	kmem = kmalloc(size, GFP_KERNEL);
 	if (!kmem)

From 6a77d38efcda40f555a920909eab22ee0917fd0d Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Fri, 9 Apr 2021 13:27:44 -0700
Subject: [PATCH 1717/1820] kfence, x86: fix preemptible warning on
 KPTI-enabled systems

On systems with KPTI enabled, we can currently observe the following
warning:

  BUG: using smp_processor_id() in preemptible
  caller is invalidate_user_asid+0x13/0x50
  CPU: 6 PID: 1075 Comm: dmesg Not tainted 5.12.0-rc4-gda4a2b1a5479-kfence_1+ #1
  Hardware name: Hewlett-Packard HP Pro 3500 Series/2ABF, BIOS 8.11 10/24/2012
  Call Trace:
   dump_stack+0x7f/0xad
   check_preemption_disabled+0xc8/0xd0
   invalidate_user_asid+0x13/0x50
   flush_tlb_one_kernel+0x5/0x20
   kfence_protect+0x56/0x80
   ...

While it normally makes sense to require preemption to be off, so that
the expected CPU's TLB is flushed and not another, in our case it really
is best-effort (see comments in kfence_protect_page()).

Avoid the warning by disabling preemption around flush_tlb_one_kernel().

Link: https://lore.kernel.org/lkml/YGIDBAboELGgMgXy@elver.google.com/
Link: https://lkml.kernel.org/r/20210330065737.652669-1-elver@google.com
Signed-off-by: Marco Elver <elver@google.com>
Reported-by: Tomi Sarvela <tomi.p.sarvela@intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/kfence.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h
index 97bbb4a9083a..05b48b33baf0 100644
--- a/arch/x86/include/asm/kfence.h
+++ b/arch/x86/include/asm/kfence.h
@@ -56,8 +56,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 	else
 		set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
 
-	/* Flush this CPU's TLB. */
+	/*
+	 * Flush this CPU's TLB, assuming whoever did the allocation/free is
+	 * likely to continue running on this CPU.
+	 */
+	preempt_disable();
 	flush_tlb_one_kernel(addr);
+	preempt_enable();
 	return true;
 }
 

From 7d37cb2c912dc5c25ffac784a4f9b98c06c6bd08 Mon Sep 17 00:00:00 2001
From: Julian Braha <julianbraha@gmail.com>
Date: Fri, 9 Apr 2021 13:27:47 -0700
Subject: [PATCH 1718/1820] lib: fix kconfig dependency on
 ARCH_WANT_FRAME_POINTERS

When LATENCYTOP, LOCKDEP, or FAULT_INJECTION_STACKTRACE_FILTER is
enabled and ARCH_WANT_FRAME_POINTERS is disabled, Kbuild gives a warning
such as:

  WARNING: unmet direct dependencies detected for FRAME_POINTER
    Depends on [n]: DEBUG_KERNEL [=y] && (M68K || UML || SUPERH) || ARCH_WANT_FRAME_POINTERS [=n] || MCOUNT [=n]
    Selected by [y]:
    - LATENCYTOP [=y] && DEBUG_KERNEL [=y] && STACKTRACE_SUPPORT [=y] && PROC_FS [=y] && !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM && !ARC && !X86

Depending on ARCH_WANT_FRAME_POINTERS causes a recursive dependency
error.  ARCH_WANT_FRAME_POINTERS is to be selected by the architecture,
and is not supposed to be overridden by other config options.

Link: https://lkml.kernel.org/r/20210329165329.27994-1-julianbraha@gmail.com
Signed-off-by: Julian Braha <julianbraha@gmail.com>
Cc: Andreas Schwab <schwab@linux-m68k.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Necip Fazil Yildiran <fazilyildiran@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/Kconfig.debug | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 2779c29d9981..417c3d3e521b 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1363,7 +1363,7 @@ config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
 	select STACKTRACE
-	select FRAME_POINTER if !MIPS && !PPC && !ARM && !S390 && !MICROBLAZE && !ARC && !X86
+	depends on FRAME_POINTER || MIPS || PPC || S390 || MICROBLAZE || ARM || ARC || X86
 	select KALLSYMS
 	select KALLSYMS_ALL
 
@@ -1665,7 +1665,7 @@ config LATENCYTOP
 	depends on DEBUG_KERNEL
 	depends on STACKTRACE_SUPPORT
 	depends on PROC_FS
-	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM && !ARC && !X86
+	depends on FRAME_POINTER || MIPS || PPC || S390 || MICROBLAZE || ARM || ARC || X86
 	select KALLSYMS
 	select KALLSYMS_ALL
 	select STACKTRACE
@@ -1918,7 +1918,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER
 	depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
 	depends on !X86_64
 	select STACKTRACE
-	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM && !ARC && !X86
+	depends on FRAME_POINTER || MIPS || PPC || S390 || MICROBLAZE || ARM || ARC || X86
 	help
 	  Provide stacktrace filter for fault-injection capabilities
 

From a2948b17f6b936fc52f86c0f92c46d2f91928b79 Mon Sep 17 00:00:00 2001
From: Vaibhav Jain <vaibhav@linux.ibm.com>
Date: Fri, 2 Apr 2021 14:55:55 +0530
Subject: [PATCH 1719/1820] libnvdimm/region: Fix nvdimm_has_flush() to handle
 ND_REGION_ASYNC

In case a platform doesn't provide explicit flush-hints but provides an
explicit flush callback via ND_REGION_ASYNC region flag, then
nvdimm_has_flush() still returns '0' indicating that writes do not
require flushing. This happens on PPC64 with patch at [1] applied, where
'deep_flush' of a region was denied even though an explicit flush
function was provided.

Fix this by adding a condition to nvdimm_has_flush() to test for the
ND_REGION_ASYNC flag on the region and see if a 'region->flush' callback
is assigned.

Link: http://lore.kernel.org/r/161703936121.36.7260632399582101498.stgit@e1fbed493c87 [1]
Fixes: c5d4355d10d4 ("libnvdimm: nd_region flush callback support")
Reported-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Link: https://lore.kernel.org/r/20210402092555.208590-1-vaibhav@linux.ibm.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/region_devs.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 51870eb51da6..9ccf3d608799 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -1246,6 +1246,11 @@ int nvdimm_has_flush(struct nd_region *nd_region)
 			|| !IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API))
 		return -ENXIO;
 
+	/* Test if an explicit flush function is defined */
+	if (test_bit(ND_REGION_ASYNC, &nd_region->flags) && nd_region->flush)
+		return 1;
+
+	/* Test if any flush hints for the region are available */
 	for (i = 0; i < nd_region->ndr_mappings; i++) {
 		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
 		struct nvdimm *nvdimm = nd_mapping->nvdimm;
@@ -1256,8 +1261,8 @@ int nvdimm_has_flush(struct nd_region *nd_region)
 	}
 
 	/*
-	 * The platform defines dimm devices without hints, assume
-	 * platform persistence mechanism like ADR
+	 * The platform defines dimm devices without hints nor explicit flush,
+	 * assume platform persistence mechanism like ADR
 	 */
 	return 0;
 }

From 53b74fa990bf76f290aa5930abfcf37424a1a865 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Thu, 8 Apr 2021 17:25:28 +0900
Subject: [PATCH 1720/1820] btrfs: zoned: move superblock logging zone location

Moves the location of the superblock logging zones. The new locations of
the logging zones are now determined based on fixed block addresses
instead of on fixed zone numbers.

The old placement method based on fixed zone numbers causes problems when
one needs to inspect a file system image without access to the drive zone
information. In such case, the super block locations cannot be reliably
determined as the zone size is unknown. By locating the superblock logging
zones using fixed addresses, we can scan a dumped file system image without
the zone information since a super block copy will always be present at or
after the fixed known locations.

Introduce the following three pairs of zones containing fixed offset
locations, regardless of the device zone size.

  - primary superblock: offset   0B (and the following zone)
  - first copy:         offset 512G (and the following zone)
  - Second copy:        offset   4T (4096G, and the following zone)

If a logging zone is outside of the disk capacity, we do not record the
superblock copy.

The first copy position is much larger than for a non-zoned filesystem,
which is at 64M.  This is to avoid overlapping with the log zones for
the primary superblock. This higher location is arbitrary but allows
supporting devices with very large zone sizes, plus some space around in
between.

Such large zone size is unrealistic and very unlikely to ever be seen in
real devices. Currently, SMR disks have a zone size of 256MB, and we are
expecting ZNS drives to be in the 1-4GB range, so this limit gives us
room to breathe. For now, we only allow zone sizes up to 8GB. The
maximum zone size that would still fit in the space is 256G.

The fixed location addresses are somewhat arbitrary, with the intent of
maintaining superblock reliability for smaller and larger devices, with
the preference for the latter. For this reason, there are two superblocks
under the first 1T. This should cover use cases for physical devices and
for emulated/device-mapper devices.

The superblock logging zones are reserved for superblock logging and
never used for data or metadata blocks. Note that we only reserve the
two zones per primary/copy actually used for superblock logging. We do
not reserve the ranges of zones possibly containing superblocks with the
largest supported zone size (0-16GB, 512G-528GB, 4096G-4112G).

The zones containing the fixed location offsets used to store
superblocks on a non-zoned volume are also reserved to avoid confusion.

Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zoned.c | 53 ++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 42 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 43948bd40e02..ba7a303300a3 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -21,9 +21,30 @@
 /* Pseudo write pointer value for conventional zone */
 #define WP_CONVENTIONAL ((u64)-2)
 
+/*
+ * Location of the first zone of superblock logging zone pairs.
+ *
+ * - primary superblock:    0B (zone 0)
+ * - first copy:          512G (zone starting at that offset)
+ * - second copy:           4T (zone starting at that offset)
+ */
+#define BTRFS_SB_LOG_PRIMARY_OFFSET	(0ULL)
+#define BTRFS_SB_LOG_FIRST_OFFSET	(512ULL * SZ_1G)
+#define BTRFS_SB_LOG_SECOND_OFFSET	(4096ULL * SZ_1G)
+
+#define BTRFS_SB_LOG_FIRST_SHIFT	const_ilog2(BTRFS_SB_LOG_FIRST_OFFSET)
+#define BTRFS_SB_LOG_SECOND_SHIFT	const_ilog2(BTRFS_SB_LOG_SECOND_OFFSET)
+
 /* Number of superblock log zones */
 #define BTRFS_NR_SB_LOG_ZONES 2
 
+/*
+ * Maximum supported zone size. Currently, SMR disks have a zone size of
+ * 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. We do not
+ * expect the zone size to become larger than 8GiB in the near future.
+ */
+#define BTRFS_MAX_ZONE_SIZE		SZ_8G
+
 static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data)
 {
 	struct blk_zone *zones = data;
@@ -111,23 +132,22 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
 }
 
 /*
- * The following zones are reserved as the circular buffer on ZONED btrfs.
- *  - The primary superblock: zones 0 and 1
- *  - The first copy: zones 16 and 17
- *  - The second copy: zones 1024 or zone at 256GB which is minimum, and
- *                     the following one
+ * Get the first zone number of the superblock mirror
  */
 static inline u32 sb_zone_number(int shift, int mirror)
 {
-	ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
+	u64 zone;
 
+	ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
 	switch (mirror) {
-	case 0: return 0;
-	case 1: return 16;
-	case 2: return min_t(u64, btrfs_sb_offset(mirror) >> shift, 1024);
+	case 0: zone = 0; break;
+	case 1: zone = 1ULL << (BTRFS_SB_LOG_FIRST_SHIFT - shift); break;
+	case 2: zone = 1ULL << (BTRFS_SB_LOG_SECOND_SHIFT - shift); break;
 	}
 
-	return 0;
+	ASSERT(zone <= U32_MAX);
+
+	return (u32)zone;
 }
 
 /*
@@ -300,10 +320,21 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 		zone_sectors = bdev_zone_sectors(bdev);
 	}
 
-	nr_sectors = bdev_nr_sectors(bdev);
 	/* Check if it's power of 2 (see is_power_of_2) */
 	ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0);
 	zone_info->zone_size = zone_sectors << SECTOR_SHIFT;
+
+	/* We reject devices with a zone size larger than 8GB */
+	if (zone_info->zone_size > BTRFS_MAX_ZONE_SIZE) {
+		btrfs_err_in_rcu(fs_info,
+		"zoned: %s: zone size %llu larger than supported maximum %llu",
+				 rcu_str_deref(device->name),
+				 zone_info->zone_size, BTRFS_MAX_ZONE_SIZE);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	nr_sectors = bdev_nr_sectors(bdev);
 	zone_info->zone_size_shift = ilog2(zone_info->zone_size);
 	zone_info->max_zone_append_size =
 		(u64)queue_max_zone_append_sectors(queue) << SECTOR_SHIFT;

From b895bdf5d643b6feb7c60856326dd4feb6981560 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 9 Apr 2021 08:49:39 -0700
Subject: [PATCH 1721/1820] netfilter: nft_limit: avoid possible divide error
 in nft_limit_init

div_u64() divides u64 by u32.

nft_limit_init() wants to divide u64 by u64, use the appropriate
math function (div64_u64)

divide error: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 8390 Comm: syz-executor188 Not tainted 5.12.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:div_u64_rem include/linux/math64.h:28 [inline]
RIP: 0010:div_u64 include/linux/math64.h:127 [inline]
RIP: 0010:nft_limit_init+0x2a2/0x5e0 net/netfilter/nft_limit.c:85
Code: ef 4c 01 eb 41 0f 92 c7 48 89 de e8 38 a5 22 fa 4d 85 ff 0f 85 97 02 00 00 e8 ea 9e 22 fa 4c 0f af f3 45 89 ed 31 d2 4c 89 f0 <49> f7 f5 49 89 c6 e8 d3 9e 22 fa 48 8d 7d 48 48 b8 00 00 00 00 00
RSP: 0018:ffffc90009447198 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000200000000000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff875152e6 RDI: 0000000000000003
RBP: ffff888020f80908 R08: 0000200000000000 R09: 0000000000000000
R10: ffffffff875152d8 R11: 0000000000000000 R12: ffffc90009447270
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
FS:  000000000097a300(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000200001c4 CR3: 0000000026a52000 CR4: 00000000001506e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 nf_tables_newexpr net/netfilter/nf_tables_api.c:2675 [inline]
 nft_expr_init+0x145/0x2d0 net/netfilter/nf_tables_api.c:2713
 nft_set_elem_expr_alloc+0x27/0x280 net/netfilter/nf_tables_api.c:5160
 nf_tables_newset+0x1997/0x3150 net/netfilter/nf_tables_api.c:4321
 nfnetlink_rcv_batch+0x85a/0x21b0 net/netfilter/nfnetlink.c:456
 nfnetlink_rcv_skb_batch net/netfilter/nfnetlink.c:580 [inline]
 nfnetlink_rcv+0x3af/0x420 net/netfilter/nfnetlink.c:598
 netlink_unicast_kernel net/netlink/af_netlink.c:1312 [inline]
 netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1338
 netlink_sendmsg+0x856/0xd90 net/netlink/af_netlink.c:1927
 sock_sendmsg_nosec net/socket.c:654 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:674
 ____sys_sendmsg+0x6e8/0x810 net/socket.c:2350
 ___sys_sendmsg+0xf3/0x170 net/socket.c:2404
 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2433
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xae

Fixes: c26844eda9d4 ("netfilter: nf_tables: Fix nft limit burst handling")
Fixes: 3e0f64b7dd31 ("netfilter: nft_limit: fix packet ratelimiting")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Diagnosed-by: Luigi Rizzo <lrizzo@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_limit.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index 0e2c315c3b5e..82ec27bdf941 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -76,13 +76,13 @@ static int nft_limit_init(struct nft_limit *limit,
 		return -EOVERFLOW;
 
 	if (pkts) {
-		tokens = div_u64(limit->nsecs, limit->rate) * limit->burst;
+		tokens = div64_u64(limit->nsecs, limit->rate) * limit->burst;
 	} else {
 		/* The token bucket size limits the number of tokens can be
 		 * accumulated. tokens_max specifies the bucket size.
 		 * tokens_max = unit * (rate + burst) / rate.
 		 */
-		tokens = div_u64(limit->nsecs * (limit->rate + limit->burst),
+		tokens = div64_u64(limit->nsecs * (limit->rate + limit->burst),
 				 limit->rate);
 	}
 

From 7ee3c61dcd28bf6e290e06ad382f13511dc790e9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Apr 2021 21:43:39 +0200
Subject: [PATCH 1722/1820] netfilter: bridge: add pre_exit hooks for ebtable
 unregistration

Just like ip/ip6/arptables, the hooks have to be removed, then
synchronize_rcu() has to be called to make sure no more packets are being
processed before the ruleset data is released.

Place the hook unregistration in the pre_exit hook, then call the new
ebtables pre_exit function from there.

Years ago, when first netns support got added for netfilter+ebtables,
this used an older (now removed) netfilter hook unregister API, that did
a unconditional synchronize_rcu().

Now that all is done with call_rcu, ebtable_{filter,nat,broute} pernet exit
handlers may free the ebtable ruleset while packets are still in flight.

This can only happens on module removal, not during netns exit.

The new function expects the table name, not the table struct.

This is because upcoming patch set (targeting -next) will remove all
net->xt.{nat,filter,broute}_table instances, this makes it necessary
to avoid external references to those member variables.

The existing APIs will be converted, so follow the upcoming scheme of
passing name + hook type instead.

Fixes: aee12a0a3727e ("ebtables: remove nf_hook_register usage")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_bridge/ebtables.h |  5 ++--
 net/bridge/netfilter/ebtable_broute.c     |  8 +++++-
 net/bridge/netfilter/ebtable_filter.c     |  8 +++++-
 net/bridge/netfilter/ebtable_nat.c        |  8 +++++-
 net/bridge/netfilter/ebtables.c           | 30 ++++++++++++++++++++---
 5 files changed, 51 insertions(+), 8 deletions(-)

diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h
index 2f5c4e6ecd8a..3a956145a25c 100644
--- a/include/linux/netfilter_bridge/ebtables.h
+++ b/include/linux/netfilter_bridge/ebtables.h
@@ -110,8 +110,9 @@ extern int ebt_register_table(struct net *net,
 			      const struct ebt_table *table,
 			      const struct nf_hook_ops *ops,
 			      struct ebt_table **res);
-extern void ebt_unregister_table(struct net *net, struct ebt_table *table,
-				 const struct nf_hook_ops *);
+extern void ebt_unregister_table(struct net *net, struct ebt_table *table);
+void ebt_unregister_table_pre_exit(struct net *net, const char *tablename,
+				   const struct nf_hook_ops *ops);
 extern unsigned int ebt_do_table(struct sk_buff *skb,
 				 const struct nf_hook_state *state,
 				 struct ebt_table *table);
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 66e7af165494..32bc2821027f 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -105,14 +105,20 @@ static int __net_init broute_net_init(struct net *net)
 				  &net->xt.broute_table);
 }
 
+static void __net_exit broute_net_pre_exit(struct net *net)
+{
+	ebt_unregister_table_pre_exit(net, "broute", &ebt_ops_broute);
+}
+
 static void __net_exit broute_net_exit(struct net *net)
 {
-	ebt_unregister_table(net, net->xt.broute_table, &ebt_ops_broute);
+	ebt_unregister_table(net, net->xt.broute_table);
 }
 
 static struct pernet_operations broute_net_ops = {
 	.init = broute_net_init,
 	.exit = broute_net_exit,
+	.pre_exit = broute_net_pre_exit,
 };
 
 static int __init ebtable_broute_init(void)
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index 78cb9b21022d..bcf982e12f16 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -99,14 +99,20 @@ static int __net_init frame_filter_net_init(struct net *net)
 				  &net->xt.frame_filter);
 }
 
+static void __net_exit frame_filter_net_pre_exit(struct net *net)
+{
+	ebt_unregister_table_pre_exit(net, "filter", ebt_ops_filter);
+}
+
 static void __net_exit frame_filter_net_exit(struct net *net)
 {
-	ebt_unregister_table(net, net->xt.frame_filter, ebt_ops_filter);
+	ebt_unregister_table(net, net->xt.frame_filter);
 }
 
 static struct pernet_operations frame_filter_net_ops = {
 	.init = frame_filter_net_init,
 	.exit = frame_filter_net_exit,
+	.pre_exit = frame_filter_net_pre_exit,
 };
 
 static int __init ebtable_filter_init(void)
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 0888936ef853..0d092773f816 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -99,14 +99,20 @@ static int __net_init frame_nat_net_init(struct net *net)
 				  &net->xt.frame_nat);
 }
 
+static void __net_exit frame_nat_net_pre_exit(struct net *net)
+{
+	ebt_unregister_table_pre_exit(net, "nat", ebt_ops_nat);
+}
+
 static void __net_exit frame_nat_net_exit(struct net *net)
 {
-	ebt_unregister_table(net, net->xt.frame_nat, ebt_ops_nat);
+	ebt_unregister_table(net, net->xt.frame_nat);
 }
 
 static struct pernet_operations frame_nat_net_ops = {
 	.init = frame_nat_net_init,
 	.exit = frame_nat_net_exit,
+	.pre_exit = frame_nat_net_pre_exit,
 };
 
 static int __init ebtable_nat_init(void)
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index ebe33b60efd6..d481ff24a150 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1232,10 +1232,34 @@ out:
 	return ret;
 }
 
-void ebt_unregister_table(struct net *net, struct ebt_table *table,
-			  const struct nf_hook_ops *ops)
+static struct ebt_table *__ebt_find_table(struct net *net, const char *name)
+{
+	struct ebt_table *t;
+
+	mutex_lock(&ebt_mutex);
+
+	list_for_each_entry(t, &net->xt.tables[NFPROTO_BRIDGE], list) {
+		if (strcmp(t->name, name) == 0) {
+			mutex_unlock(&ebt_mutex);
+			return t;
+		}
+	}
+
+	mutex_unlock(&ebt_mutex);
+	return NULL;
+}
+
+void ebt_unregister_table_pre_exit(struct net *net, const char *name, const struct nf_hook_ops *ops)
+{
+	struct ebt_table *table = __ebt_find_table(net, name);
+
+	if (table)
+		nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+}
+EXPORT_SYMBOL(ebt_unregister_table_pre_exit);
+
+void ebt_unregister_table(struct net *net, struct ebt_table *table)
 {
-	nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
 	__ebt_unregister_table(net, table);
 }
 

From d163a925ebbc6eb5b562b0f1d72c7e817aa75c40 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Apr 2021 21:43:40 +0200
Subject: [PATCH 1723/1820] netfilter: arp_tables: add pre_exit hook for table
 unregister

Same problem that also existed in iptables/ip(6)tables, when
arptable_filter is removed there is no longer a wait period before the
table/ruleset is free'd.

Unregister the hook in pre_exit, then remove the table in the exit
function.
This used to work correctly because the old nf_hook_unregister API
did unconditional synchronize_net.

The per-net hook unregister function uses call_rcu instead.

Fixes: b9e69e127397 ("netfilter: xtables: don't hook tables by default")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_arp/arp_tables.h |  5 +++--
 net/ipv4/netfilter/arp_tables.c          |  9 +++++++--
 net/ipv4/netfilter/arptable_filter.c     | 10 +++++++++-
 3 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h
index 7d3537c40ec9..26a13294318c 100644
--- a/include/linux/netfilter_arp/arp_tables.h
+++ b/include/linux/netfilter_arp/arp_tables.h
@@ -52,8 +52,9 @@ extern void *arpt_alloc_initial_table(const struct xt_table *);
 int arpt_register_table(struct net *net, const struct xt_table *table,
 			const struct arpt_replace *repl,
 			const struct nf_hook_ops *ops, struct xt_table **res);
-void arpt_unregister_table(struct net *net, struct xt_table *table,
-			   const struct nf_hook_ops *ops);
+void arpt_unregister_table(struct net *net, struct xt_table *table);
+void arpt_unregister_table_pre_exit(struct net *net, struct xt_table *table,
+				    const struct nf_hook_ops *ops);
 extern unsigned int arpt_do_table(struct sk_buff *skb,
 				  const struct nf_hook_state *state,
 				  struct xt_table *table);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index d1e04d2b5170..6c26533480dd 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1539,10 +1539,15 @@ out_free:
 	return ret;
 }
 
-void arpt_unregister_table(struct net *net, struct xt_table *table,
-			   const struct nf_hook_ops *ops)
+void arpt_unregister_table_pre_exit(struct net *net, struct xt_table *table,
+				    const struct nf_hook_ops *ops)
 {
 	nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+}
+EXPORT_SYMBOL(arpt_unregister_table_pre_exit);
+
+void arpt_unregister_table(struct net *net, struct xt_table *table)
+{
 	__arpt_unregister_table(net, table);
 }
 
diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index c216b9ad3bb2..6c300ba5634e 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -56,16 +56,24 @@ static int __net_init arptable_filter_table_init(struct net *net)
 	return err;
 }
 
+static void __net_exit arptable_filter_net_pre_exit(struct net *net)
+{
+	if (net->ipv4.arptable_filter)
+		arpt_unregister_table_pre_exit(net, net->ipv4.arptable_filter,
+					       arpfilter_ops);
+}
+
 static void __net_exit arptable_filter_net_exit(struct net *net)
 {
 	if (!net->ipv4.arptable_filter)
 		return;
-	arpt_unregister_table(net, net->ipv4.arptable_filter, arpfilter_ops);
+	arpt_unregister_table(net, net->ipv4.arptable_filter);
 	net->ipv4.arptable_filter = NULL;
 }
 
 static struct pernet_operations arptable_filter_net_ops = {
 	.exit = arptable_filter_net_exit,
+	.pre_exit = arptable_filter_net_pre_exit,
 };
 
 static int __init arptable_filter_init(void)

From d434405aaab7d0ebc516b68a8fc4100922d7f5ef Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 11 Apr 2021 15:16:13 -0700
Subject: [PATCH 1724/1820] Linux 5.12-rc7

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index cc77fd45ca64..4730cf156f6b 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Frozen Wasteland
 
 # *DOCUMENTATION*

From d2bd44c4c05d043fb65cfdf26c54e6d8b94a4b41 Mon Sep 17 00:00:00 2001
From: Angelo Dureghello <angelo@kernel-space.org>
Date: Sun, 28 Feb 2021 20:08:28 +0100
Subject: [PATCH 1725/1820] m68k: fix flatmem memory model setup

Detected a broken boot on mcf54415, likely introduced from

commit 4bfc848e0981
("m68k/mm: enable use of generic memory_model.h for !DISCONTIGMEM")

Fix ARCH_PFN_OFFSET to be a pfn.

Signed-off-by: Angelo Dureghello <angelo@kernel-space.org>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Greg Ungerer <gerg@linux-m68k.org>
---
 arch/m68k/include/asm/page_mm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/m68k/include/asm/page_mm.h b/arch/m68k/include/asm/page_mm.h
index 9e8f0cc30a2c..2411ea9ef578 100644
--- a/arch/m68k/include/asm/page_mm.h
+++ b/arch/m68k/include/asm/page_mm.h
@@ -167,7 +167,7 @@ static inline __attribute_const__ int __virt_to_node_shift(void)
 	((__p) - pgdat->node_mem_map) + pgdat->node_start_pfn;		\
 })
 #else
-#define ARCH_PFN_OFFSET (m68k_memory[0].addr)
+#define ARCH_PFN_OFFSET (m68k_memory[0].addr >> PAGE_SHIFT)
 #include <asm-generic/memory_model.h>
 #endif
 

From 4af2178ac605faf32ebe638f7ac17d841d40ea9b Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang@nxp.com>
Date: Fri, 9 Apr 2021 17:11:45 +0800
Subject: [PATCH 1726/1820] MAINTAINERS: update maintainer entry for freescale
 fec driver

Update maintainer entry for freescale fec driver.

Suggested-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index ccd9228350cf..163264c282eb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7089,7 +7089,7 @@ S:	Maintained
 F:	drivers/i2c/busses/i2c-cpm.c
 
 FREESCALE IMX / MXC FEC DRIVER
-M:	Fugang Duan <fugang.duan@nxp.com>
+M:	Joakim Zhang <qiangqing.zhang@nxp.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/fsl-fec.txt

From 31457db3750c0b0ed229d836f2609fdb8a5b790e Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 11 Apr 2021 11:02:08 +0200
Subject: [PATCH 1727/1820] net: davicom: Fix regulator not turned off on
 failed probe

When the probe fails, we must disable the regulator that was previously
enabled.

This patch is a follow-up to commit ac88c531a5b3
("net: davicom: Fix regulator not turned off on failed probe") which missed
one case.

Fixes: 7994fe55a4a2 ("dm9000: Add regulator and reset support to dm9000")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/davicom/dm9000.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 252adfa5d837..8a9096aa85cd 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1471,8 +1471,10 @@ dm9000_probe(struct platform_device *pdev)
 
 	/* Init network device */
 	ndev = alloc_etherdev(sizeof(struct board_info));
-	if (!ndev)
-		return -ENOMEM;
+	if (!ndev) {
+		ret = -ENOMEM;
+		goto out_regulator_disable;
+	}
 
 	SET_NETDEV_DEV(ndev, &pdev->dev);
 

From 6628ddfec7580882f11fdc5c194a8ea781fdadfa Mon Sep 17 00:00:00 2001
From: Phillip Potter <phil@philpotter.co.uk>
Date: Sun, 11 Apr 2021 12:28:24 +0100
Subject: [PATCH 1728/1820] net: geneve: check skb is large enough for
 IPv4/IPv6 header

Check within geneve_xmit_skb/geneve6_xmit_skb that sk_buff structure
is large enough to include IPv4 or IPv6 header, and reject if not. The
geneve_xmit_skb portion and overall idea was contributed by Eric Dumazet.
Fixes a KMSAN-found uninit-value bug reported by syzbot at:
https://syzkaller.appspot.com/bug?id=abe95dc3e3e9667fc23b8d81f29ecad95c6f106f

Suggested-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+2e406a9ac75bb71d4b7a@syzkaller.appspotmail.com
Signed-off-by: Phillip Potter <phil@philpotter.co.uk>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index d5b1e48e0c09..42f31c681846 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -891,6 +891,9 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
+	if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
+		return -EINVAL;
+
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
 			      geneve->cfg.info.key.tp_dst, sport);
@@ -985,6 +988,9 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
+	if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr)))
+		return -EINVAL;
+
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
 				geneve->cfg.info.key.tp_dst, sport);

From ea941ac294d75d0ace50797aebf0056f6f8f7a7f Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Tue, 16 Feb 2021 17:13:42 -0700
Subject: [PATCH 1729/1820] dmaengine: idxd: Fix clobbering of SWERR overflow
 bit on writeback

Current code blindly writes over the SWERR and the OVERFLOW bits. Write
back the bits actually read instead so the driver avoids clobbering the
OVERFLOW bit that comes after the register is read.

Fixes: bfe1d56091c1 ("dmaengine: idxd: Init and probe for Intel data accelerators")
Reported-by: Sanjay Kumar <sanjay.k.kumar@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161352082229.3511254.1002151220537623503.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/irq.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index a60ca11a5784..f1463fc58112 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -124,7 +124,9 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
 		for (i = 0; i < 4; i++)
 			idxd->sw_err.bits[i] = ioread64(idxd->reg_base +
 					IDXD_SWERR_OFFSET + i * sizeof(u64));
-		iowrite64(IDXD_SWERR_ACK, idxd->reg_base + IDXD_SWERR_OFFSET);
+
+		iowrite64(idxd->sw_err.bits[0] & IDXD_SWERR_ACK,
+			  idxd->reg_base + IDXD_SWERR_OFFSET);
 
 		if (idxd->sw_err.valid && idxd->sw_err.wq_idx_valid) {
 			int id = idxd->sw_err.wq_idx;

From 4ac823e9cd85f66da274c951d21bf9f6b714b729 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Mon, 22 Mar 2021 16:36:25 -0700
Subject: [PATCH 1730/1820] dmaengine: idxd: fix delta_rec and crc size field
 for completion record

The delta_rec_size and crc_val in the completion record should
be 32bits and not 16bits.

Fixes: bfe1d56091c1 ("dmaengine: idxd: Init and probe for Intel data accelerators")
Reported-by: Nikhil Rao <nikhil.rao@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161645618572.2003490.14466173451736323035.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/uapi/linux/idxd.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h
index 236d437947bc..e33997b4d750 100644
--- a/include/uapi/linux/idxd.h
+++ b/include/uapi/linux/idxd.h
@@ -247,8 +247,8 @@ struct dsa_completion_record {
 			uint32_t	rsvd2:8;
 		};
 
-		uint16_t	delta_rec_size;
-		uint16_t	crc_val;
+		uint32_t	delta_rec_size;
+		uint32_t	crc_val;
 
 		/* DIF check & strip */
 		struct {

From ea6a5735d2a61b938a302eb3629272342a9e7c46 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Mon, 22 Mar 2021 16:37:29 -0700
Subject: [PATCH 1731/1820] dmaengine: idxd: fix opcap sysfs attribute output

The operation capability register is 256bits. The current output only
prints out the first 64bits. Fix to output the entire 256bits. The current
code omits operation caps from IAX devices.

Fixes: c52ca478233c ("dmaengine: idxd: add configuration component of driver")
Reported-by: Lucas Van <lucas.van@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161645624963.2003736.829798666998490151.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/sysfs.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 4dbb03c545e4..c27ca01cf8b2 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -1449,8 +1449,14 @@ static ssize_t op_cap_show(struct device *dev,
 {
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
+	int i, rc = 0;
 
-	return sprintf(buf, "%#llx\n", idxd->hw.opcap.bits[0]);
+	for (i = 0; i < 4; i++)
+		rc += sysfs_emit_at(buf, rc, "%#llx ", idxd->hw.opcap.bits[i]);
+
+	rc--;
+	rc += sysfs_emit_at(buf, rc, "\n");
+	return rc;
 }
 static DEVICE_ATTR_RO(op_cap);
 

From 0fff71c5a311e1264988179f7dcc217fda15fadd Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Wed, 7 Apr 2021 12:59:47 -0700
Subject: [PATCH 1732/1820] dmaengine: idxd: fix wq size store permission state

WQ size can only be changed when the device is disabled. Current code
allows change when device is enabled but wq is disabled. Change the check
to detect device state.

Fixes: c52ca478233c ("dmaengine: idxd: add configuration component of driver")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161782558755.107710.18138252584838406025.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/sysfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index c27ca01cf8b2..5f7bc4b1621a 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -989,7 +989,7 @@ static ssize_t wq_size_store(struct device *dev,
 	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
 		return -EPERM;
 
-	if (wq->state != IDXD_WQ_DISABLED)
+	if (idxd->state == IDXD_DEV_ENABLED)
 		return -EPERM;
 
 	if (size + total_claimed_wq_size(idxd) - wq->size > idxd->max_wq_size)

From 88cd1d6191b13689094310c2405394e4ce36d061 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 24 Mar 2021 16:17:57 +0200
Subject: [PATCH 1733/1820] dmaengine: dw: Make it dependent to HAS_IOMEM

Some architectures do not provide devm_*() APIs. Hence make the driver
dependent on HAVE_IOMEM.

Fixes: dbde5c2934d1 ("dw_dmac: use devm_* functions to simplify code")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Link: https://lore.kernel.org/r/20210324141757.24710-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dw/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig
index e5162690de8f..db25f9b7778c 100644
--- a/drivers/dma/dw/Kconfig
+++ b/drivers/dma/dw/Kconfig
@@ -10,6 +10,7 @@ config DW_DMAC_CORE
 
 config DW_DMAC
 	tristate "Synopsys DesignWare AHB DMA platform driver"
+	depends on HAS_IOMEM
 	select DW_DMAC_CORE
 	help
 	  Support the Synopsys DesignWare AHB DMA controller. This
@@ -18,6 +19,7 @@ config DW_DMAC
 config DW_DMAC_PCI
 	tristate "Synopsys DesignWare AHB DMA PCI driver"
 	depends on PCI
+	depends on HAS_IOMEM
 	select DW_DMAC_CORE
 	help
 	  Support the Synopsys DesignWare AHB DMA controller on the

From ea45b6008f8095db0cc09ad6e03c7785c2986197 Mon Sep 17 00:00:00 2001
From: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Date: Tue, 30 Mar 2021 18:44:58 -0700
Subject: [PATCH 1734/1820] dmaengine: Fix a double free in
 dma_async_device_register

In the first list_for_each_entry() macro of dma_async_device_register,
it gets the chan from list and calls __dma_async_device_channel_register
(..,chan). We can see that chan->local is allocated by alloc_percpu() and
it is freed chan->local by free_percpu(chan->local) when
__dma_async_device_channel_register() failed.

But after __dma_async_device_channel_register() failed, the caller will
goto err_out and freed the chan->local in the second time by free_percpu().

The cause of this problem is forget to set chan->local to NULL when
chan->local was freed in __dma_async_device_channel_register(). My
patch sets chan->local to NULL when the callee failed to avoid double free.

Fixes: d2fb0a0438384 ("dmaengine: break out channel registration")
Signed-off-by: Lv Yunlong <lyl2019@mail.ustc.edu.cn>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/20210331014458.3944-1-lyl2019@mail.ustc.edu.cn
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dmaengine.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index fe6a460c4373..af3ee288bc11 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1086,6 +1086,7 @@ static int __dma_async_device_channel_register(struct dma_device *device,
 	kfree(chan->dev);
  err_free_local:
 	free_percpu(chan->local);
+	chan->local = NULL;
 	return rc;
 }
 

From 917a3200b9f467a154999c7572af345f2470aaf4 Mon Sep 17 00:00:00 2001
From: Dinghao Liu <dinghao.liu@zju.edu.cn>
Date: Fri, 9 Apr 2021 16:28:05 +0800
Subject: [PATCH 1735/1820] dmaengine: tegra20: Fix runtime PM imbalance on
 error

pm_runtime_get_sync() will increase the runtime PM counter
even it returns an error. Thus a pairing decrement is needed
to prevent refcount leak. Fix this by replacing this API with
pm_runtime_resume_and_get(), which will not change the runtime
PM counter on error.

Signed-off-by: Dinghao Liu <dinghao.liu@zju.edu.cn>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20210409082805.23643-1-dinghao.liu@zju.edu.cn
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/tegra20-apb-dma.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 71827d9b0aa1..b7260749e8ee 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -723,7 +723,7 @@ static void tegra_dma_issue_pending(struct dma_chan *dc)
 		goto end;
 	}
 	if (!tdc->busy) {
-		err = pm_runtime_get_sync(tdc->tdma->dev);
+		err = pm_runtime_resume_and_get(tdc->tdma->dev);
 		if (err < 0) {
 			dev_err(tdc2dev(tdc), "Failed to enable DMA\n");
 			goto end;
@@ -818,7 +818,7 @@ static void tegra_dma_synchronize(struct dma_chan *dc)
 	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
 	int err;
 
-	err = pm_runtime_get_sync(tdc->tdma->dev);
+	err = pm_runtime_resume_and_get(tdc->tdma->dev);
 	if (err < 0) {
 		dev_err(tdc2dev(tdc), "Failed to synchronize DMA: %d\n", err);
 		return;

From 07503e6aefe4a6efd777062191944a14f03b3a18 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 23 Mar 2021 16:19:59 +0300
Subject: [PATCH 1736/1820] dmaengine: plx_dma: add a missing put_device() on
 error path

Add a missing put_device(&pdev->dev) if the call to
dma_async_device_register(dma); fails.

Fixes: 905ca51e63be ("dmaengine: plx-dma: Introduce PLX DMA engine PCI driver skeleton")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Link: https://lore.kernel.org/r/YFnq/0IQzixtAbC1@mwanda
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/plx_dma.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/dma/plx_dma.c b/drivers/dma/plx_dma.c
index f387c5bbc170..166934544161 100644
--- a/drivers/dma/plx_dma.c
+++ b/drivers/dma/plx_dma.c
@@ -507,10 +507,8 @@ static int plx_dma_create(struct pci_dev *pdev)
 
 	rc = request_irq(pci_irq_vector(pdev, 0), plx_dma_isr, 0,
 			 KBUILD_MODNAME, plxdev);
-	if (rc) {
-		kfree(plxdev);
-		return rc;
-	}
+	if (rc)
+		goto free_plx;
 
 	spin_lock_init(&plxdev->ring_lock);
 	tasklet_setup(&plxdev->desc_task, plx_dma_desc_task);
@@ -540,14 +538,20 @@ static int plx_dma_create(struct pci_dev *pdev)
 	rc = dma_async_device_register(dma);
 	if (rc) {
 		pci_err(pdev, "Failed to register dma device: %d\n", rc);
-		free_irq(pci_irq_vector(pdev, 0),  plxdev);
-		kfree(plxdev);
-		return rc;
+		goto put_device;
 	}
 
 	pci_set_drvdata(pdev, plxdev);
 
 	return 0;
+
+put_device:
+	put_device(&pdev->dev);
+	free_irq(pci_irq_vector(pdev, 0),  plxdev);
+free_plx:
+	kfree(plxdev);
+
+	return rc;
 }
 
 static int plx_dma_probe(struct pci_dev *pdev,

From b74e409ea1b18128b877a50883d92a12eba83c33 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Fri, 9 Apr 2021 00:13:18 +0200
Subject: [PATCH 1737/1820] s390/entry: avoid setting up backchain in ext|io
 handlers

Currently when interrupt arrives to cpu while in kernel context
INT_HANDLER macro (used for ext_int_handler and io_int_handler)
allocates new stack frame and pt_regs on the kernel stack and
sets up the backchain to jump over the pt_regs to the frame which has
been interrupted. This is not ideal to two reasons:

1. This hides the fact that kernel stack contains interrupt frame in it
   and hence breaks arch_stack_walk_reliable(), which needs to know that to
   guarantee "reliability" and checks that there are no pt_regs on the way.

2. It breaks the backchain unwinder logic, which assumes that the next
   stack frame after an interrupt frame is reliable, while it is not.
   In some cases (when r14 contains garbage) this leads to early unwinding
   termination with an error, instead of marking frame as unreliable
   and continuing.

To address that, only set backchain to 0.

Fixes: 56e62a737028 ("s390: convert to generic entry")
Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/entry.S | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index c10b9f31eef7..235bf2ac3359 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -401,15 +401,13 @@ ENTRY(\name)
 	brasl	%r14,.Lcleanup_sie_int
 #endif
 0:	CHECK_STACK __LC_SAVE_AREA_ASYNC
-	lgr	%r11,%r15
 	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	stg	%r11,__SF_BACKCHAIN(%r15)
 	j	2f
 1:	BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
 	lctlg	%c1,%c1,__LC_KERNEL_ASCE
 	lg	%r15,__LC_KERNEL_STACK
-	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
-2:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+2:	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
 	# clear user controlled registers to prevent speculative use
 	xgr	%r0,%r0

From a994eddb947ea9ebb7b14d9a1267001699f0a136 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Fri, 9 Apr 2021 00:15:21 +0200
Subject: [PATCH 1738/1820] s390/entry: save the caller of psw_idle

Currently psw_idle does not allocate a stack frame and does not
save its r14 and r15 into the save area. Even though this is valid from
call ABI point of view, because psw_idle does not make any calls
explicitly, in reality psw_idle is an entry point for controlled
transition into serving interrupts. So, in practice, psw_idle stack
frame is analyzed during stack unwinding. Depending on build options
that r14 slot in the save area of psw_idle might either contain a value
saved by previous sibling call or complete garbage.

  [task    0000038000003c28] do_ext_irq+0xd6/0x160
  [task    0000038000003c78] ext_int_handler+0xba/0xe8
  [task   *0000038000003dd8] psw_idle_exit+0x0/0x8 <-- pt_regs
 ([task    0000038000003dd8] 0x0)
  [task    0000038000003e10] default_idle_call+0x42/0x148
  [task    0000038000003e30] do_idle+0xce/0x160
  [task    0000038000003e70] cpu_startup_entry+0x36/0x40
  [task    0000038000003ea0] arch_call_rest_init+0x76/0x80

So, to make a stacktrace nicer and actually point for the real caller of
psw_idle in this frequently occurring case, make psw_idle save its r14.

  [task    0000038000003c28] do_ext_irq+0xd6/0x160
  [task    0000038000003c78] ext_int_handler+0xba/0xe8
  [task   *0000038000003dd8] psw_idle_exit+0x0/0x6 <-- pt_regs
 ([task    0000038000003dd8] arch_cpu_idle+0x3c/0xd0)
  [task    0000038000003e10] default_idle_call+0x42/0x148
  [task    0000038000003e30] do_idle+0xce/0x160
  [task    0000038000003e70] cpu_startup_entry+0x36/0x40
  [task    0000038000003ea0] arch_call_rest_init+0x76/0x80

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kernel/entry.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 235bf2ac3359..12de7a9c85b3 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -443,6 +443,7 @@ INT_HANDLER io_int_handler,__LC_IO_OLD_PSW,do_io_irq
  * Load idle PSW.
  */
 ENTRY(psw_idle)
+	stg	%r14,(__SF_GPRS+8*8)(%r15)
 	stg	%r3,__SF_EMPTY(%r15)
 	larl	%r1,psw_idle_exit
 	stg	%r1,__SF_EMPTY+8(%r15)

From 11664169981a025b7f6072d136ac724294b7b65c Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Thu, 18 Mar 2021 13:02:02 -0400
Subject: [PATCH 1739/1820] drm/i915/dpcd_bl: Don't try vesa interface unless
 specified by VBT

Looks like that there actually are another subset of laptops on the market
that don't support the Intel HDR backlight interface, but do advertise
support for the VESA DPCD backlight interface despite the fact it doesn't
seem to work.

Note though I'm not entirely clear on this - on one of the machines where
this issue was observed, I also noticed that we appeared to be rejecting
the VBT defined backlight frequency in
intel_dp_aux_vesa_calc_max_backlight(). It's noted in this function that:

/* Use highest possible value of Pn for more granularity of brightness
 * adjustment while satifying the conditions below.
 * ...
 * - FxP is within 25% of desired value.
 *   Note: 25% is arbitrary value and may need some tweak.
 */

So it's possible that this value might just need to be tweaked, but for now
let's just disable the VESA backlight interface unless it's specified in
the VBT just to be safe. We might be able to try enabling this again by
default in the future.

Fixes: 2227816e647a ("drm/i915/dp: Allow forcing specific interfaces through enable_dpcd_backlight")
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Bugzilla: https://gitlab.freedesktop.org/drm/intel/-/issues/3169
Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210318170204.513000-1-lyude@redhat.com
(cherry picked from commit 9e2eb6d5380e9dadcd2baecb51f238e5eba94bee)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
index 651884390137..4f8337c7fd2e 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
@@ -646,7 +646,6 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *connector)
 			break;
 		case INTEL_BACKLIGHT_DISPLAY_DDI:
 			try_intel_interface = true;
-			try_vesa_interface = true;
 			break;
 		default:
 			return -ENODEV;

From bf52dc49ba0101f648b4c3ea26b812061406b0d4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Sat, 27 Mar 2021 02:59:45 +0200
Subject: [PATCH 1740/1820] drm/i915: Don't zero out the Y plane's watermarks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Don't zero out the watermarks for the Y plane since we've already
computed them when computing the UV plane's watermarks (since the
UV plane always appears before ethe Y plane when iterating through
the planes).

This leads to allocating no DDB for the Y plane since .min_ddb_alloc
also gets zeroed. And that of course leads to underruns when scanning
out planar formats.

Cc: stable@vger.kernel.org
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Fixes: dbf71381d733 ("drm/i915: Nuke intel_atomic_crtc_state_for_each_plane_state() from skl+ wm code")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210327005945.4929-1-ville.syrjala@linux.intel.com
Reviewed-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
(cherry picked from commit f99b805fb9413ff007ca0b6add871737664117dd)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/intel_pm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 97b57acc02e2..4b4d8d034782 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5471,12 +5471,12 @@ static int icl_build_plane_wm(struct intel_crtc_state *crtc_state,
 	struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id];
 	int ret;
 
-	memset(wm, 0, sizeof(*wm));
-
 	/* Watermarks calculated in master */
 	if (plane_state->planar_slave)
 		return 0;
 
+	memset(wm, 0, sizeof(*wm));
+
 	if (plane_state->planar_linked_plane) {
 		const struct drm_framebuffer *fb = plane_state->hw.fb;
 		enum plane_id y_plane_id = plane_state->planar_linked_plane->id;

From aee6f25e9c911323aa89a200e1bb160c1613ed3d Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 25 Mar 2021 12:48:22 +0100
Subject: [PATCH 1741/1820] drm/i915/display/vlv_dsi: Do not skip
 panel_pwr_cycle_delay when disabling the panel
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After the recently added commit fe0f1e3bfdfe ("drm/i915: Shut down
displays gracefully on reboot"), the DSI panel on a Cherry Trail based
Predia Basic tablet would no longer properly light up after reboot.

I've managed to reproduce this without rebooting by doing:
chvt 3; echo 1 > /sys/class/graphics/fb0/blank;\
echo 0 > /sys/class/graphics/fb0/blank

Which rapidly turns the panel off and back on again.

The vlv_dsi.c code uses an intel_dsi_msleep() helper for the various delays
used for panel on/off, since starting with MIPI-sequences version >= 3 the
delays are already included inside the MIPI-sequences.

The problems exposed by the "Shut down displays gracefully on reboot"
change, show that using this helper for the panel_pwr_cycle_delay is
not the right thing to do. This has not been noticed until now because
normally the panel never is cycled off and directly on again in quick
succession.

Change the msleep for the panel_pwr_cycle_delay to a normal msleep()
call to avoid the panel staying black after a quick off + on cycle.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Fixes: fe0f1e3bfdfe ("drm/i915: Shut down displays gracefully on reboot")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210325114823.44922-1-hdegoede@redhat.com
(cherry picked from commit 2878b29fc25a0dac0e1c6c94177f07c7f94240f0)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/vlv_dsi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index f94025ec603a..a9a8ba1d3aba 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -992,14 +992,14 @@ static void intel_dsi_post_disable(struct intel_atomic_state *state,
 	 * FIXME As we do with eDP, just make a note of the time here
 	 * and perform the wait before the next panel power on.
 	 */
-	intel_dsi_msleep(intel_dsi, intel_dsi->panel_pwr_cycle_delay);
+	msleep(intel_dsi->panel_pwr_cycle_delay);
 }
 
 static void intel_dsi_shutdown(struct intel_encoder *encoder)
 {
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 
-	intel_dsi_msleep(intel_dsi, intel_dsi->panel_pwr_cycle_delay);
+	msleep(intel_dsi->panel_pwr_cycle_delay);
 }
 
 static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,

From 2decad92f4731fac9755a083fcfefa66edb7d67d Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Fri, 9 Apr 2021 18:37:10 +0100
Subject: [PATCH 1742/1820] arm64: mte: Ensure TIF_MTE_ASYNC_FAULT is set
 atomically

The entry from EL0 code checks the TFSRE0_EL1 register for any
asynchronous tag check faults in user space and sets the
TIF_MTE_ASYNC_FAULT flag. This is not done atomically, potentially
racing with another CPU calling set_tsk_thread_flag().

Replace the non-atomic ORR+STR with an STSET instruction. While STSET
requires ARMv8.1 and an assembler that understands LSE atomics, the MTE
feature is part of ARMv8.5 and already requires an updated assembler.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Fixes: 637ec831ea4f ("arm64: mte: Handle synchronous and asynchronous tag check faults")
Cc: <stable@vger.kernel.org> # 5.10.x
Reported-by: Will Deacon <will@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20210409173710.18582-1-catalin.marinas@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig        |  6 +++++-
 arch/arm64/kernel/entry.S | 10 ++++++----
 2 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index e4e1b6550115..dfdc3e0af5e1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1406,10 +1406,13 @@ config ARM64_PAN
 config AS_HAS_LDAPR
 	def_bool $(as-instr,.arch_extension rcpc)
 
+config AS_HAS_LSE_ATOMICS
+	def_bool $(as-instr,.arch_extension lse)
+
 config ARM64_LSE_ATOMICS
 	bool
 	default ARM64_USE_LSE_ATOMICS
-	depends on $(as-instr,.arch_extension lse)
+	depends on AS_HAS_LSE_ATOMICS
 
 config ARM64_USE_LSE_ATOMICS
 	bool "Atomic instructions"
@@ -1666,6 +1669,7 @@ config ARM64_MTE
 	default y
 	depends on ARM64_AS_HAS_MTE && ARM64_TAGGED_ADDR_ABI
 	depends on AS_HAS_ARMV8_5
+	depends on AS_HAS_LSE_ATOMICS
 	# Required for tag checking in the uaccess routines
 	depends on ARM64_PAN
 	select ARCH_USES_HIGH_VMA_FLAGS
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a31a0a713c85..6acfc5e6b5e0 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -148,16 +148,18 @@ alternative_cb_end
 	.endm
 
 	/* Check for MTE asynchronous tag check faults */
-	.macro check_mte_async_tcf, flgs, tmp
+	.macro check_mte_async_tcf, tmp, ti_flags
 #ifdef CONFIG_ARM64_MTE
+	.arch_extension lse
 alternative_if_not ARM64_MTE
 	b	1f
 alternative_else_nop_endif
 	mrs_s	\tmp, SYS_TFSRE0_EL1
 	tbz	\tmp, #SYS_TFSR_EL1_TF0_SHIFT, 1f
 	/* Asynchronous TCF occurred for TTBR0 access, set the TI flag */
-	orr	\flgs, \flgs, #_TIF_MTE_ASYNC_FAULT
-	str	\flgs, [tsk, #TSK_TI_FLAGS]
+	mov	\tmp, #_TIF_MTE_ASYNC_FAULT
+	add	\ti_flags, tsk, #TSK_TI_FLAGS
+	stset	\tmp, [\ti_flags]
 	msr_s	SYS_TFSRE0_EL1, xzr
 1:
 #endif
@@ -244,7 +246,7 @@ alternative_else_nop_endif
 	disable_step_tsk x19, x20
 
 	/* Check for asynchronous tag check faults in user space */
-	check_mte_async_tcf x19, x22
+	check_mte_async_tcf x22, x23
 	apply_ssbd 1, x22, x23
 
 	ptrauth_keys_install_kernel tsk, x20, x22, x23

From 6df0e6c57dfc064af330071f372f11aa8c584997 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Mon, 12 Apr 2021 09:23:27 -0700
Subject: [PATCH 1743/1820] dmaengine: idxd: clear MSIX permission entry on
 shutdown

Add disabling/clearing of MSIX permission entries on device shutdown to
mirror the enabling of the MSIX entries on probe. Current code left the
MSIX enabled and the pasid entries still programmed at device shutdown.

Fixes: 8e50d392652f ("dmaengine: idxd: Add shared workqueue support")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161824457969.882533.6020239898682672311.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/device.c | 30 ++++++++++++++++++++++++++++++
 drivers/dma/idxd/idxd.h   |  2 ++
 drivers/dma/idxd/init.c   | 11 ++---------
 3 files changed, 34 insertions(+), 9 deletions(-)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 84a6ea60ecf0..c09687013d29 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -574,6 +574,36 @@ void idxd_device_drain_pasid(struct idxd_device *idxd, int pasid)
 }
 
 /* Device configuration bits */
+void idxd_msix_perm_setup(struct idxd_device *idxd)
+{
+	union msix_perm mperm;
+	int i, msixcnt;
+
+	msixcnt = pci_msix_vec_count(idxd->pdev);
+	if (msixcnt < 0)
+		return;
+
+	mperm.bits = 0;
+	mperm.pasid = idxd->pasid;
+	mperm.pasid_en = device_pasid_enabled(idxd);
+	for (i = 1; i < msixcnt; i++)
+		iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
+}
+
+void idxd_msix_perm_clear(struct idxd_device *idxd)
+{
+	union msix_perm mperm;
+	int i, msixcnt;
+
+	msixcnt = pci_msix_vec_count(idxd->pdev);
+	if (msixcnt < 0)
+		return;
+
+	mperm.bits = 0;
+	for (i = 1; i < msixcnt; i++)
+		iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
+}
+
 static void idxd_group_config_write(struct idxd_group *group)
 {
 	struct idxd_device *idxd = group->idxd;
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 81a0e65fd316..eda2ee10501f 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -316,6 +316,8 @@ void idxd_unregister_driver(void);
 struct bus_type *idxd_get_bus_type(struct idxd_device *idxd);
 
 /* device interrupt control */
+void idxd_msix_perm_setup(struct idxd_device *idxd);
+void idxd_msix_perm_clear(struct idxd_device *idxd);
 irqreturn_t idxd_irq_handler(int vec, void *data);
 irqreturn_t idxd_misc_thread(int vec, void *data);
 irqreturn_t idxd_wq_thread(int irq, void *data);
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 085a0c3b62c6..6584b0ec07d5 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -65,7 +65,6 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 	struct idxd_irq_entry *irq_entry;
 	int i, msixcnt;
 	int rc = 0;
-	union msix_perm mperm;
 
 	msixcnt = pci_msix_vec_count(pdev);
 	if (msixcnt < 0) {
@@ -144,14 +143,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 	}
 
 	idxd_unmask_error_interrupts(idxd);
-
-	/* Setup MSIX permission table */
-	mperm.bits = 0;
-	mperm.pasid = idxd->pasid;
-	mperm.pasid_en = device_pasid_enabled(idxd);
-	for (i = 1; i < msixcnt; i++)
-		iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
-
+	idxd_msix_perm_setup(idxd);
 	return 0;
 
  err_no_irq:
@@ -510,6 +502,7 @@ static void idxd_shutdown(struct pci_dev *pdev)
 		idxd_flush_work_list(irq_entry);
 	}
 
+	idxd_msix_perm_clear(idxd);
 	destroy_workqueue(idxd->wq);
 }
 

From ea9aadc06a9f10ad20a90edc0a484f1147d88a7a Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Mon, 12 Apr 2021 09:02:36 -0700
Subject: [PATCH 1744/1820] dmaengine: idxd: fix wq cleanup of WQCFG registers

A pre-release silicon erratum workaround where wq reset does not clear
WQCFG registers was leaked into upstream code. Use wq reset command
instead of blasting the MMIO region. This also address an issue where
we clobber registers in future devices.

Fixes: da32b28c95a7 ("dmaengine: idxd: cleanup workqueue config after disabling")
Reported-by: Shreenivaas Devarajan <shreenivaas.devarajan@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161824330020.881560.16375921906426627033.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/device.c | 35 ++++++++++++++++++++++++-----------
 drivers/dma/idxd/idxd.h   |  1 +
 drivers/dma/idxd/sysfs.c  |  9 ++-------
 3 files changed, 27 insertions(+), 18 deletions(-)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index c09687013d29..31c819544a22 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -282,6 +282,22 @@ void idxd_wq_drain(struct idxd_wq *wq)
 	idxd_cmd_exec(idxd, IDXD_CMD_DRAIN_WQ, operand, NULL);
 }
 
+void idxd_wq_reset(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	u32 operand;
+
+	if (wq->state != IDXD_WQ_ENABLED) {
+		dev_dbg(dev, "WQ %d in wrong state: %d\n", wq->id, wq->state);
+		return;
+	}
+
+	operand = BIT(wq->id % 16) | ((wq->id / 16) << 16);
+	idxd_cmd_exec(idxd, IDXD_CMD_RESET_WQ, operand, NULL);
+	wq->state = IDXD_WQ_DISABLED;
+}
+
 int idxd_wq_map_portal(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
@@ -363,8 +379,6 @@ int idxd_wq_disable_pasid(struct idxd_wq *wq)
 void idxd_wq_disable_cleanup(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
-	struct device *dev = &idxd->pdev->dev;
-	int i, wq_offset;
 
 	lockdep_assert_held(&idxd->dev_lock);
 	memset(wq->wqcfg, 0, idxd->wqcfg_size);
@@ -376,14 +390,6 @@ void idxd_wq_disable_cleanup(struct idxd_wq *wq)
 	wq->ats_dis = 0;
 	clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
 	memset(wq->name, 0, WQ_NAME_SIZE);
-
-	for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
-		wq_offset = WQCFG_OFFSET(idxd, wq->id, i);
-		iowrite32(0, idxd->reg_base + wq_offset);
-		dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n",
-			wq->id, i, wq_offset,
-			ioread32(idxd->reg_base + wq_offset));
-	}
 }
 
 /* Device control bits */
@@ -672,7 +678,14 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
 	if (!wq->group)
 		return 0;
 
-	memset(wq->wqcfg, 0, idxd->wqcfg_size);
+	/*
+	 * Instead of memset the entire shadow copy of WQCFG, copy from the hardware after
+	 * wq reset. This will copy back the sticky values that are present on some devices.
+	 */
+	for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
+		wq_offset = WQCFG_OFFSET(idxd, wq->id, i);
+		wq->wqcfg->bits[i] = ioread32(idxd->reg_base + wq_offset);
+	}
 
 	/* byte 0-3 */
 	wq->wqcfg->wq_size = wq->size;
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index eda2ee10501f..76014c14f473 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -343,6 +343,7 @@ void idxd_wq_free_resources(struct idxd_wq *wq);
 int idxd_wq_enable(struct idxd_wq *wq);
 int idxd_wq_disable(struct idxd_wq *wq);
 void idxd_wq_drain(struct idxd_wq *wq);
+void idxd_wq_reset(struct idxd_wq *wq);
 int idxd_wq_map_portal(struct idxd_wq *wq);
 void idxd_wq_unmap_portal(struct idxd_wq *wq);
 void idxd_wq_disable_cleanup(struct idxd_wq *wq);
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 5f7bc4b1621a..18bf4d148989 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -275,7 +275,6 @@ static void disable_wq(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
 	struct device *dev = &idxd->pdev->dev;
-	int rc;
 
 	mutex_lock(&wq->wq_lock);
 	dev_dbg(dev, "%s removing WQ %s\n", __func__, dev_name(&wq->conf_dev));
@@ -296,17 +295,13 @@ static void disable_wq(struct idxd_wq *wq)
 	idxd_wq_unmap_portal(wq);
 
 	idxd_wq_drain(wq);
-	rc = idxd_wq_disable(wq);
+	idxd_wq_reset(wq);
 
 	idxd_wq_free_resources(wq);
 	wq->client_count = 0;
 	mutex_unlock(&wq->wq_lock);
 
-	if (rc < 0)
-		dev_warn(dev, "Failed to disable %s: %d\n",
-			 dev_name(&wq->conf_dev), rc);
-	else
-		dev_info(dev, "wq %s disabled\n", dev_name(&wq->conf_dev));
+	dev_info(dev, "wq %s disabled\n", dev_name(&wq->conf_dev));
 }
 
 static int idxd_config_bus_remove(struct device *dev)

From 1fe976d308acb6374c899a4ee8025a0a016e453e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pali=20Roh=C3=A1r?= <pali@kernel.org>
Date: Mon, 12 Apr 2021 18:57:39 +0200
Subject: [PATCH 1745/1820] net: phy: marvell: fix detection of PHY on Topaz
 switches
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since commit fee2d546414d ("net: phy: marvell: mv88e6390 temperature
sensor reading"), Linux reports the temperature of Topaz hwmon as
constant -75°C.

This is because switches from the Topaz family (88E6141 / 88E6341) have
the address of the temperature sensor register different from Peridot.

This address is instead compatible with 88E1510 PHYs, as was used for
Topaz before the above mentioned commit.

Create a new mapping table between switch family and PHY ID for families
which don't have a model number. And define PHY IDs for Topaz and Peridot
families.

Create a new PHY ID and a new PHY driver for Topaz's internal PHY.
The only difference from Peridot's PHY driver is the HWMON probing
method.

Prior this change Topaz's internal PHY is detected by kernel as:

  PHY [...] driver [Marvell 88E6390] (irq=63)

And afterwards as:

  PHY [...] driver [Marvell 88E6341 Family] (irq=63)

Signed-off-by: Pali Rohár <pali@kernel.org>
BugLink: https://github.com/globalscaletechnologies/linux/issues/1
Fixes: fee2d546414d ("net: phy: marvell: mv88e6390 temperature sensor reading")
Reviewed-by: Marek Behún <kabel@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 30 +++++++++++++-----------------
 drivers/net/phy/marvell.c        | 32 +++++++++++++++++++++++++++++---
 include/linux/marvell_phy.h      |  5 +++--
 3 files changed, 45 insertions(+), 22 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 903d619e08ed..e08bf9377140 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3026,10 +3026,17 @@ out_resources:
 	return err;
 }
 
+/* prod_id for switch families which do not have a PHY model number */
+static const u16 family_prod_id_table[] = {
+	[MV88E6XXX_FAMILY_6341] = MV88E6XXX_PORT_SWITCH_ID_PROD_6341,
+	[MV88E6XXX_FAMILY_6390] = MV88E6XXX_PORT_SWITCH_ID_PROD_6390,
+};
+
 static int mv88e6xxx_mdio_read(struct mii_bus *bus, int phy, int reg)
 {
 	struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv;
 	struct mv88e6xxx_chip *chip = mdio_bus->chip;
+	u16 prod_id;
 	u16 val;
 	int err;
 
@@ -3040,23 +3047,12 @@ static int mv88e6xxx_mdio_read(struct mii_bus *bus, int phy, int reg)
 	err = chip->info->ops->phy_read(chip, bus, phy, reg, &val);
 	mv88e6xxx_reg_unlock(chip);
 
-	if (reg == MII_PHYSID2) {
-		/* Some internal PHYs don't have a model number. */
-		if (chip->info->family != MV88E6XXX_FAMILY_6165)
-			/* Then there is the 6165 family. It gets is
-			 * PHYs correct. But it can also have two
-			 * SERDES interfaces in the PHY address
-			 * space. And these don't have a model
-			 * number. But they are not PHYs, so we don't
-			 * want to give them something a PHY driver
-			 * will recognise.
-			 *
-			 * Use the mv88e6390 family model number
-			 * instead, for anything which really could be
-			 * a PHY,
-			 */
-			if (!(val & 0x3f0))
-				val |= MV88E6XXX_PORT_SWITCH_ID_PROD_6390 >> 4;
+	/* Some internal PHYs don't have a model number. */
+	if (reg == MII_PHYSID2 && !(val & 0x3f0) &&
+	    chip->info->family < ARRAY_SIZE(family_prod_id_table)) {
+		prod_id = family_prod_id_table[chip->info->family];
+		if (prod_id)
+			val |= prod_id >> 4;
 	}
 
 	return err ? err : val;
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index e26a5d663f8a..8018ddf7f316 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -3021,9 +3021,34 @@ static struct phy_driver marvell_drivers[] = {
 		.get_stats = marvell_get_stats,
 	},
 	{
-		.phy_id = MARVELL_PHY_ID_88E6390,
+		.phy_id = MARVELL_PHY_ID_88E6341_FAMILY,
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
-		.name = "Marvell 88E6390",
+		.name = "Marvell 88E6341 Family",
+		/* PHY_GBIT_FEATURES */
+		.flags = PHY_POLL_CABLE_TEST,
+		.probe = m88e1510_probe,
+		.config_init = marvell_config_init,
+		.config_aneg = m88e6390_config_aneg,
+		.read_status = marvell_read_status,
+		.config_intr = marvell_config_intr,
+		.handle_interrupt = marvell_handle_interrupt,
+		.resume = genphy_resume,
+		.suspend = genphy_suspend,
+		.read_page = marvell_read_page,
+		.write_page = marvell_write_page,
+		.get_sset_count = marvell_get_sset_count,
+		.get_strings = marvell_get_strings,
+		.get_stats = marvell_get_stats,
+		.get_tunable = m88e1540_get_tunable,
+		.set_tunable = m88e1540_set_tunable,
+		.cable_test_start = marvell_vct7_cable_test_start,
+		.cable_test_tdr_start = marvell_vct5_cable_test_tdr_start,
+		.cable_test_get_status = marvell_vct7_cable_test_get_status,
+	},
+	{
+		.phy_id = MARVELL_PHY_ID_88E6390_FAMILY,
+		.phy_id_mask = MARVELL_PHY_ID_MASK,
+		.name = "Marvell 88E6390 Family",
 		/* PHY_GBIT_FEATURES */
 		.flags = PHY_POLL_CABLE_TEST,
 		.probe = m88e6390_probe,
@@ -3107,7 +3132,8 @@ static struct mdio_device_id __maybe_unused marvell_tbl[] = {
 	{ MARVELL_PHY_ID_88E1540, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E1545, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E3016, MARVELL_PHY_ID_MASK },
-	{ MARVELL_PHY_ID_88E6390, MARVELL_PHY_ID_MASK },
+	{ MARVELL_PHY_ID_88E6341_FAMILY, MARVELL_PHY_ID_MASK },
+	{ MARVELL_PHY_ID_88E6390_FAMILY, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E1340S, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E1548P, MARVELL_PHY_ID_MASK },
 	{ }
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index 52b1610eae68..c544b70dfbd2 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -28,11 +28,12 @@
 /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */
 #define MARVELL_PHY_ID_88E1111_FINISAR	0x01ff0cc0
 
-/* The MV88e6390 Ethernet switch contains embedded PHYs. These PHYs do
+/* These Ethernet switch families contain embedded PHYs, but they do
  * not have a model ID. So the switch driver traps reads to the ID2
  * register and returns the switch family ID
  */
-#define MARVELL_PHY_ID_88E6390		0x01410f90
+#define MARVELL_PHY_ID_88E6341_FAMILY	0x01410f41
+#define MARVELL_PHY_ID_88E6390_FAMILY	0x01410f90
 
 #define MARVELL_PHY_FAMILY_ID(id)	((id) >> 4)
 

From f33b0e196ed7aa3dc285b26db7768c1db1eb3a41 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 12 Apr 2021 11:47:07 -0700
Subject: [PATCH 1746/1820] ethtool: fix kdoc attr name

Add missing 't' in attrtype.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/netlink.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 6eabd58d81bf..cde9f3169ae5 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -36,9 +36,9 @@ static inline int ethnl_strz_size(const char *s)
 
 /**
  * ethnl_put_strz() - put string attribute with fixed size string
- * @skb:     skb with the message
- * @attrype: attribute type
- * @s:       ETH_GSTRING_LEN sized string (may not be null terminated)
+ * @skb:      skb with the message
+ * @attrtype: attribute type
+ * @s:        ETH_GSTRING_LEN sized string (may not be null terminated)
  *
  * Puts an attribute with null terminated string from @s into the message.
  *

From b29c457a6511435960115c0f548c4360d5f4801d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Apr 2021 21:38:57 +0200
Subject: [PATCH 1747/1820] netfilter: x_tables: fix compat match/target pad
 out-of-bound write

xt_compat_match/target_from_user doesn't check that zeroing the area
to start of next rule won't write past end of allocated ruleset blob.

Remove this code and zero the entire blob beforehand.

Reported-by: syzbot+cfc0247ac173f597aaaa@syzkaller.appspotmail.com
Reported-by: Andy Nguyen <theflow@google.com>
Fixes: 9fa492cdc160c ("[NETFILTER]: x_tables: simplify compat API")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/arp_tables.c |  2 ++
 net/ipv4/netfilter/ip_tables.c  |  2 ++
 net/ipv6/netfilter/ip6_tables.c |  2 ++
 net/netfilter/x_tables.c        | 10 ++--------
 4 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 6c26533480dd..d6d45d820d79 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1193,6 +1193,8 @@ static int translate_compat_table(struct net *net,
 	if (!newinfo)
 		goto out_unlock;
 
+	memset(newinfo->entries, 0, size);
+
 	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
 		newinfo->hook_entry[i] = compatr->hook_entry[i];
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index f15bc21d7301..f77ea0dbe656 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1428,6 +1428,8 @@ translate_compat_table(struct net *net,
 	if (!newinfo)
 		goto out_unlock;
 
+	memset(newinfo->entries, 0, size);
+
 	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
 		newinfo->hook_entry[i] = compatr->hook_entry[i];
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 2e2119bfcf13..eb2b5404806c 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1443,6 +1443,8 @@ translate_compat_table(struct net *net,
 	if (!newinfo)
 		goto out_unlock;
 
+	memset(newinfo->entries, 0, size);
+
 	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
 		newinfo->hook_entry[i] = compatr->hook_entry[i];
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 6bd31a7a27fc..92e9d4ebc5e8 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -733,7 +733,7 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
 {
 	const struct xt_match *match = m->u.kernel.match;
 	struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m;
-	int pad, off = xt_compat_match_offset(match);
+	int off = xt_compat_match_offset(match);
 	u_int16_t msize = cm->u.user.match_size;
 	char name[sizeof(m->u.user.name)];
 
@@ -743,9 +743,6 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
 		match->compat_from_user(m->data, cm->data);
 	else
 		memcpy(m->data, cm->data, msize - sizeof(*cm));
-	pad = XT_ALIGN(match->matchsize) - match->matchsize;
-	if (pad > 0)
-		memset(m->data + match->matchsize, 0, pad);
 
 	msize += off;
 	m->u.user.match_size = msize;
@@ -1116,7 +1113,7 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
 {
 	const struct xt_target *target = t->u.kernel.target;
 	struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t;
-	int pad, off = xt_compat_target_offset(target);
+	int off = xt_compat_target_offset(target);
 	u_int16_t tsize = ct->u.user.target_size;
 	char name[sizeof(t->u.user.name)];
 
@@ -1126,9 +1123,6 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
 		target->compat_from_user(t->data, ct->data);
 	else
 		memcpy(t->data, ct->data, tsize - sizeof(*ct));
-	pad = XT_ALIGN(target->targetsize) - target->targetsize;
-	if (pad > 0)
-		memset(t->data + target->targetsize, 0, pad);
 
 	tsize += off;
 	t->u.user.target_size = tsize;

From 4d8f9065830e526c83199186c5f56a6514f457d2 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Sat, 10 Apr 2021 21:29:38 +0200
Subject: [PATCH 1748/1820] netfilter: nftables: clone set element expression
 template

memcpy() breaks when using connlimit in set elements. Use
nft_expr_clone() to initialize the connlimit expression list, otherwise
connlimit garbage collector crashes when walking on the list head copy.

[  493.064656] Workqueue: events_power_efficient nft_rhash_gc [nf_tables]
[  493.064685] RIP: 0010:find_or_evict+0x5a/0x90 [nf_conncount]
[  493.064694] Code: 2b 43 40 83 f8 01 77 0d 48 c7 c0 f5 ff ff ff 44 39 63 3c 75 df 83 6d 18 01 48 8b 43 08 48 89 de 48 8b 13 48 8b 3d ee 2f 00 00 <48> 89 42 08 48 89 10 48 b8 00 01 00 00 00 00 ad de 48 89 03 48 83
[  493.064699] RSP: 0018:ffffc90000417dc0 EFLAGS: 00010297
[  493.064704] RAX: 0000000000000000 RBX: ffff888134f38410 RCX: 0000000000000000
[  493.064708] RDX: 0000000000000000 RSI: ffff888134f38410 RDI: ffff888100060cc0
[  493.064711] RBP: ffff88812ce594a8 R08: ffff888134f38438 R09: 00000000ebb9025c
[  493.064714] R10: ffffffff8219f838 R11: 0000000000000017 R12: 0000000000000001
[  493.064718] R13: ffffffff82146740 R14: ffff888134f38410 R15: 0000000000000000
[  493.064721] FS:  0000000000000000(0000) GS:ffff88840e440000(0000) knlGS:0000000000000000
[  493.064725] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  493.064729] CR2: 0000000000000008 CR3: 00000001330aa002 CR4: 00000000001706e0
[  493.064733] Call Trace:
[  493.064737]  nf_conncount_gc_list+0x8f/0x150 [nf_conncount]
[  493.064746]  nft_rhash_gc+0x106/0x390 [nf_tables]

Reported-by: Laura Garcia Liebana <nevola@gmail.com>
Fixes: 409444522976 ("netfilter: nf_tables: add elements with stateful expressions")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 46 ++++++++++++++++++++++++++---------
 1 file changed, 34 insertions(+), 12 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index f57f1a6ba96f..589d2f6978d3 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5295,16 +5295,35 @@ err_expr:
 	return -ENOMEM;
 }
 
-static void nft_set_elem_expr_setup(const struct nft_set_ext *ext, int i,
-				    struct nft_expr *expr_array[])
+static int nft_set_elem_expr_setup(struct nft_ctx *ctx,
+				   const struct nft_set_ext *ext,
+				   struct nft_expr *expr_array[],
+				   u32 num_exprs)
 {
 	struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext);
-	struct nft_expr *expr = nft_setelem_expr_at(elem_expr, elem_expr->size);
+	struct nft_expr *expr;
+	int i, err;
 
-	memcpy(expr, expr_array[i], expr_array[i]->ops->size);
-	elem_expr->size += expr_array[i]->ops->size;
-	kfree(expr_array[i]);
-	expr_array[i] = NULL;
+	for (i = 0; i < num_exprs; i++) {
+		expr = nft_setelem_expr_at(elem_expr, elem_expr->size);
+		err = nft_expr_clone(expr, expr_array[i]);
+		if (err < 0)
+			goto err_elem_expr_setup;
+
+		elem_expr->size += expr_array[i]->ops->size;
+		nft_expr_destroy(ctx, expr_array[i]);
+		expr_array[i] = NULL;
+	}
+
+	return 0;
+
+err_elem_expr_setup:
+	for (; i < num_exprs; i++) {
+		nft_expr_destroy(ctx, expr_array[i]);
+		expr_array[i] = NULL;
+	}
+
+	return -ENOMEM;
 }
 
 static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
@@ -5556,12 +5575,15 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		*nft_set_ext_obj(ext) = obj;
 		obj->use++;
 	}
-	for (i = 0; i < num_exprs; i++)
-		nft_set_elem_expr_setup(ext, i, expr_array);
+	err = nft_set_elem_expr_setup(ctx, ext, expr_array, num_exprs);
+	if (err < 0)
+		goto err_elem_expr;
 
 	trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
-	if (trans == NULL)
-		goto err_trans;
+	if (trans == NULL) {
+		err = -ENOMEM;
+		goto err_elem_expr;
+	}
 
 	ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK;
 	err = set->ops->insert(ctx->net, set, &elem, &ext2);
@@ -5605,7 +5627,7 @@ err_set_full:
 	set->ops->remove(ctx->net, set, &elem);
 err_element_clash:
 	kfree(trans);
-err_trans:
+err_elem_expr:
 	if (obj)
 		obj->use--;
 

From 738fa58ee1328481d1d7889e7c430b3401c571b9 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Mon, 12 Apr 2021 17:41:01 +0800
Subject: [PATCH 1749/1820] arm64: kprobes: Restore local irqflag if kprobes is
 cancelled

If instruction being single stepped caused a page fault, the kprobes
is cancelled to let the page fault handler continue as a normal page
fault. But the local irqflags are disabled so cpu will restore pstate
with DAIF masked. After pagefault is serviced, the kprobes is
triggerred again, we overwrite the saved_irqflag by calling
kprobes_save_local_irqflag(). NOTE, DAIF is masked in this new saved
irqflag. After kprobes is serviced, the cpu pstate is retored with
DAIF masked.

This patch is inspired by one patch for riscv from Liao Chang.

Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20210412174101.6bfb0594@xhacker.debian
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/probes/kprobes.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 66aac2881ba8..85645b2b0c7a 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -267,10 +267,12 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
 		if (!instruction_pointer(regs))
 			BUG();
 
-		if (kcb->kprobe_status == KPROBE_REENTER)
+		if (kcb->kprobe_status == KPROBE_REENTER) {
 			restore_previous_kprobe(kcb);
-		else
+		} else {
+			kprobes_restore_local_irqflag(kcb, regs);
 			reset_current_kprobe();
+		}
 
 		break;
 	case KPROBE_HIT_ACTIVE:

From 6998a8800d73116187aad542391ce3b2dd0f9e30 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 13 Apr 2021 16:01:00 +0200
Subject: [PATCH 1750/1820] ACPI: x86: Call acpi_boot_table_init() after
 acpi_table_upgrade()

Commit 1a1c130ab757 ("ACPI: tables: x86: Reserve memory occupied by
ACPI tables") attempted to address an issue with reserving the memory
occupied by ACPI tables, but it broke the initrd-based table override
mechanism relied on by multiple users.

To restore the initrd-based ACPI table override functionality, move
the acpi_boot_table_init() invocation in setup_arch() on x86 after
the acpi_table_upgrade() one.

Fixes: 1a1c130ab757 ("ACPI: tables: x86: Reserve memory occupied by ACPI tables")
Reported-by: Hans de Goede <hdegoede@redhat.com>
Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/kernel/setup.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5ecd69a48393..ccab6cf91283 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1045,9 +1045,6 @@ void __init setup_arch(char **cmdline_p)
 
 	cleanup_highmap();
 
-	/* Look for ACPI tables and reserve memory occupied by them. */
-	acpi_boot_table_init();
-
 	memblock_set_current_limit(ISA_END_ADDRESS);
 	e820__memblock_setup();
 
@@ -1132,6 +1129,8 @@ void __init setup_arch(char **cmdline_p)
 	reserve_initrd();
 
 	acpi_table_upgrade();
+	/* Look for ACPI tables and reserve memory occupied by them. */
+	acpi_boot_table_init();
 
 	vsmp_init();
 

From 909290786ea335366e21d7f1ed5812b90f2f0a92 Mon Sep 17 00:00:00 2001
From: "Christian A. Ehrhardt" <lk@c--e.de>
Date: Mon, 12 Apr 2021 23:41:24 +0200
Subject: [PATCH 1751/1820] vfio/pci: Add missing range check in vfio_pci_mmap

When mmaping an extra device region verify that the region index
derived from the mmap offset is valid.

Fixes: a15b1883fee1 ("vfio_pci: Allow mapping extra regions")
Cc: stable@vger.kernel.org
Signed-off-by: Christian A. Ehrhardt <lk@c--e.de>
Message-Id: <20210412214124.GA241759@lisa.in-ulm.de>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 65e7e6b44578..5023e23db3bc 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1656,6 +1656,8 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 
 	index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT);
 
+	if (index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions)
+		return -EINVAL;
 	if (vma->vm_end < vma->vm_start)
 		return -EINVAL;
 	if ((vma->vm_flags & VM_SHARED) == 0)
@@ -1664,7 +1666,7 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 		int regnum = index - VFIO_PCI_NUM_REGIONS;
 		struct vfio_pci_region *region = vdev->region + regnum;
 
-		if (region && region->ops && region->ops->mmap &&
+		if (region->ops && region->ops->mmap &&
 		    (region->flags & VFIO_REGION_INFO_FLAG_MMAP))
 			return region->ops->mmap(vdev, region, vma);
 		return -EINVAL;

From 8db403b9631331ef1d5e302cdf353c48849ca9d5 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 11 Apr 2021 12:21:54 +0200
Subject: [PATCH 1752/1820] tracing/dynevent: Fix a memory leak in an error
 handling path

We must free 'argv' before returning, as already done in all the other
paths of this function.

Link: https://lkml.kernel.org/r/21e3594ccd7fc88c5c162c98450409190f304327.1618136448.git.christophe.jaillet@wanadoo.fr

Fixes: d262271d0483 ("tracing/dynevent: Delegate parsing to create function")
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_dynevent.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index dc971a68dda4..e57cc0870892 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -63,8 +63,10 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type
 		event = p + 1;
 		*p = '\0';
 	}
-	if (event[0] == '\0')
-		return -EINVAL;
+	if (event[0] == '\0') {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	mutex_lock(&event_mutex);
 	for_each_dyn_event_safe(pos, n) {

From 31166efb1cee348eb6314e9c0095d84cbeb66b9d Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Mon, 8 Mar 2021 12:41:56 -0800
Subject: [PATCH 1753/1820] ixgbe: Fix NULL pointer dereference in ethtool
 loopback test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ixgbe driver currently generates a NULL pointer dereference when
performing the ethtool loopback test. This is due to the fact that there
isn't a q_vector associated with the test ring when it is setup as
interrupts are not normally added to the test rings.

To address this I have added code that will check for a q_vector before
returning a napi_id value. If a q_vector is not present it will return a
value of 0.

Fixes: b02e5a0ebb17 ("xsk: Propagate napi_id to XDP socket Rx path")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Dave Switzer <david.switzer@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 03d9aad516d4..45d2c8f37c01 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6536,6 +6536,13 @@ err_setup_tx:
 	return err;
 }
 
+static int ixgbe_rx_napi_id(struct ixgbe_ring *rx_ring)
+{
+	struct ixgbe_q_vector *q_vector = rx_ring->q_vector;
+
+	return q_vector ? q_vector->napi.napi_id : 0;
+}
+
 /**
  * ixgbe_setup_rx_resources - allocate Rx resources (Descriptors)
  * @adapter: pointer to ixgbe_adapter
@@ -6583,7 +6590,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
 
 	/* XDP RX-queue info */
 	if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev,
-			     rx_ring->queue_index, rx_ring->q_vector->napi.napi_id) < 0)
+			     rx_ring->queue_index, ixgbe_rx_napi_id(rx_ring)) < 0)
 		goto err;
 
 	rx_ring->xdp_prog = adapter->xdp_prog;

From debb9df311582c83fe369baa35fa4b92e8a9c58a Mon Sep 17 00:00:00 2001
From: Yongxin Liu <yongxin.liu@windriver.com>
Date: Mon, 22 Mar 2021 15:14:48 +0800
Subject: [PATCH 1754/1820] ixgbe: fix unbalanced device enable/disable in
 suspend/resume

pci_disable_device() called in __ixgbe_shutdown() decreases
dev->enable_cnt by 1. pci_enable_device_mem() which increases
dev->enable_cnt by 1, was removed from ixgbe_resume() in commit
6f82b2558735 ("ixgbe: use generic power management"). This caused
unbalanced increase/decrease. So add pci_enable_device_mem() back.

Fix the following call trace.

  ixgbe 0000:17:00.1: disabling already-disabled device
  Call Trace:
   __ixgbe_shutdown+0x10a/0x1e0 [ixgbe]
   ixgbe_suspend+0x32/0x70 [ixgbe]
   pci_pm_suspend+0x87/0x160
   ? pci_pm_freeze+0xd0/0xd0
   dpm_run_callback+0x42/0x170
   __device_suspend+0x114/0x460
   async_suspend+0x1f/0xa0
   async_run_entry_fn+0x3c/0xf0
   process_one_work+0x1dd/0x410
   worker_thread+0x34/0x3f0
   ? cancel_delayed_work+0x90/0x90
   kthread+0x14c/0x170
   ? kthread_park+0x90/0x90
   ret_from_fork+0x1f/0x30

Fixes: 6f82b2558735 ("ixgbe: use generic power management")
Signed-off-by: Yongxin Liu <yongxin.liu@windriver.com>
Tested-by: Dave Switzer <david.switzer@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 45d2c8f37c01..cffb95f8f632 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6899,6 +6899,11 @@ static int __maybe_unused ixgbe_resume(struct device *dev_d)
 
 	adapter->hw.hw_addr = adapter->io_addr;
 
+	err = pci_enable_device_mem(pdev);
+	if (err) {
+		e_dev_err("Cannot enable PCI device from suspend\n");
+		return err;
+	}
 	smp_mb__before_atomic();
 	clear_bit(__IXGBE_DISABLED, &adapter->state);
 	pci_set_master(pdev);

From ef963ae427aa4669905e0a96b3bd9d44dc85db32 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 31 Mar 2021 15:46:28 +0100
Subject: [PATCH 1755/1820] ice: Fix potential infinite loop when using u8 loop
 counter

A for-loop is using a u8 loop counter that is being compared to
a u32 cmp_dcbcfg->numapp to check for the end of the loop. If
cmp_dcbcfg->numapp is larger than 255 then the counter j will wrap
around to zero and hence an infinite loop occurs. Fix this by making
counter j the same type as cmp_dcbcfg->numapp.

Addresses-Coverity: ("Infinite loop")
Fixes: aeac8ce864d9 ("ice: Recognize 860 as iSCSI port in CEE mode")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_dcb.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c
index 211ac6f907ad..28e834a128c0 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.c
@@ -747,8 +747,8 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg,
 		   struct ice_port_info *pi)
 {
 	u32 status, tlv_status = le32_to_cpu(cee_cfg->tlv_status);
-	u32 ice_aqc_cee_status_mask, ice_aqc_cee_status_shift;
-	u8 i, j, err, sync, oper, app_index, ice_app_sel_type;
+	u32 ice_aqc_cee_status_mask, ice_aqc_cee_status_shift, j;
+	u8 i, err, sync, oper, app_index, ice_app_sel_type;
 	u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio);
 	u16 ice_aqc_cee_app_mask, ice_aqc_cee_app_shift;
 	struct ice_dcbx_cfg *cmp_dcbcfg, *dcbcfg;

From 610f8c0fc8d46e0933955ce13af3d64484a4630a Mon Sep 17 00:00:00 2001
From: Hristo Venev <hristo@venev.name>
Date: Mon, 12 Apr 2021 20:41:16 +0300
Subject: [PATCH 1756/1820] net: sit: Unregister catch-all devices

A sit interface created without a local or a remote address is linked
into the `sit_net::tunnels_wc` list of its original namespace. When
deleting a network namespace, delete the devices that have been moved.

The following script triggers a null pointer dereference if devices
linked in a deleted `sit_net` remain:

    for i in `seq 1 30`; do
        ip netns add ns-test
        ip netns exec ns-test ip link add dev veth0 type veth peer veth1
        ip netns exec ns-test ip link add dev sit$i type sit dev veth0
        ip netns exec ns-test ip link set dev sit$i netns $$
        ip netns del ns-test
    done
    for i in `seq 1 30`; do
        ip link del dev sit$i
    done

Fixes: 5e6700b3bf98f ("sit: add support of x-netns")
Signed-off-by: Hristo Venev <hristo@venev.name>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 63ccd9f2dccc..9fdccf0718b5 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1867,9 +1867,9 @@ static void __net_exit sit_destroy_tunnels(struct net *net,
 		if (dev->rtnl_link_ops == &sit_link_ops)
 			unregister_netdevice_queue(dev, head);
 
-	for (prio = 1; prio < 4; prio++) {
+	for (prio = 0; prio < 4; prio++) {
 		int h;
-		for (h = 0; h < IP6_SIT_HASH_SIZE; h++) {
+		for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) {
 			struct ip_tunnel *t;
 
 			t = rtnl_dereference(sitn->tunnels[prio][h]);

From 941ea91e87a6e879ed82dad4949f6234f2702bec Mon Sep 17 00:00:00 2001
From: Hristo Venev <hristo@venev.name>
Date: Mon, 12 Apr 2021 20:41:17 +0300
Subject: [PATCH 1757/1820] net: ip6_tunnel: Unregister catch-all devices

Similarly to the sit case, we need to remove the tunnels with no
addresses that have been moved to another network namespace.

Fixes: 0bd8762824e73 ("ip6tnl: add x-netns support")
Signed-off-by: Hristo Venev <hristo@venev.name>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 3fa0eca5a06f..42fe7db6bbb3 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2244,6 +2244,16 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head
 			t = rtnl_dereference(t->next);
 		}
 	}
+
+	t = rtnl_dereference(ip6n->tnls_wc[0]);
+	while (t) {
+		/* If dev is in the same netns, it has already
+		 * been added to the list by the previous loop.
+		 */
+		if (!net_eq(dev_net(t->dev), net))
+			unregister_netdevice_queue(t->dev, list);
+		t = rtnl_dereference(t->next);
+	}
 }
 
 static int __net_init ip6_tnl_init_net(struct net *net)

From 97684f0970f6e112926de631fdd98d9693c7e5c1 Mon Sep 17 00:00:00 2001
From: Jonathon Reinhart <jonathon.reinhart@gmail.com>
Date: Tue, 13 Apr 2021 03:08:48 -0400
Subject: [PATCH 1758/1820] net: Make tcp_allowed_congestion_control readonly
 in non-init netns

Currently, tcp_allowed_congestion_control is global and writable;
writing to it in any net namespace will leak into all other net
namespaces.

tcp_available_congestion_control and tcp_allowed_congestion_control are
the only sysctls in ipv4_net_table (the per-netns sysctl table) with a
NULL data pointer; their handlers (proc_tcp_available_congestion_control
and proc_allowed_congestion_control) have no other way of referencing a
struct net. Thus, they operate globally.

Because ipv4_net_table does not use designated initializers, there is no
easy way to fix up this one "bad" table entry. However, the data pointer
updating logic shouldn't be applied to NULL pointers anyway, so we
instead force these entries to be read-only.

These sysctls used to exist in ipv4_table (init-net only), but they were
moved to the per-net ipv4_net_table, presumably without realizing that
tcp_allowed_congestion_control was writable and thus introduced a leak.

Because the intent of that commit was only to know (i.e. read) "which
congestion algorithms are available or allowed", this read-only solution
should be sufficient.

The logic added in recent commit
31c4d2f160eb: ("net: Ensure net namespace isolation of sysctls")
does not and cannot check for NULL data pointers, because
other table entries (e.g. /proc/sys/net/netfilter/nf_log/) have
.data=NULL but use other methods (.extra2) to access the struct net.

Fixes: 9cb8e048e5d9 ("net/ipv4/sysctl: show tcp_{allowed, available}_congestion_control in non-initial netns")
Signed-off-by: Jonathon Reinhart <jonathon.reinhart@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index f55095d3ed16..60465f077497 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1378,9 +1378,19 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 		if (!table)
 			goto err_alloc;
 
-		/* Update the variables to point into the current struct net */
-		for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++)
-			table[i].data += (void *)net - (void *)&init_net;
+		for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) {
+			if (table[i].data) {
+				/* Update the variables to point into
+				 * the current struct net
+				 */
+				table[i].data += (void *)net - (void *)&init_net;
+			} else {
+				/* Entries without data pointer are global;
+				 * Make them read-only in non-init_net ns
+				 */
+				table[i].mode &= ~0222;
+			}
+		}
 	}
 
 	net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);

From ca09bf7bb109a37a7ff05f230bb3fa3627e6625f Mon Sep 17 00:00:00 2001
From: Lijun Pan <lijunp213@gmail.com>
Date: Tue, 13 Apr 2021 03:33:25 -0500
Subject: [PATCH 1759/1820] ibmvnic: correctly use dev_consume/free_skb_irq

It is more correct to use dev_kfree_skb_irq when packets are dropped,
and to use dev_consume_skb_irq when packets are consumed.

Fixes: 0d973388185d ("ibmvnic: Introduce xmit_more support using batched subCRQ hcalls")
Suggested-by: Thomas Falcon <tlfalcon@linux.ibm.com>
Signed-off-by: Lijun Pan <lijunp213@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 9c6438d3b3a5..110a0d0eaabb 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -3204,9 +3204,6 @@ restart_loop:
 
 		next = ibmvnic_next_scrq(adapter, scrq);
 		for (i = 0; i < next->tx_comp.num_comps; i++) {
-			if (next->tx_comp.rcs[i])
-				dev_err(dev, "tx error %x\n",
-					next->tx_comp.rcs[i]);
 			index = be32_to_cpu(next->tx_comp.correlators[i]);
 			if (index & IBMVNIC_TSO_POOL_MASK) {
 				tx_pool = &adapter->tso_pool[pool];
@@ -3220,7 +3217,13 @@ restart_loop:
 			num_entries += txbuff->num_entries;
 			if (txbuff->skb) {
 				total_bytes += txbuff->skb->len;
-				dev_consume_skb_irq(txbuff->skb);
+				if (next->tx_comp.rcs[i]) {
+					dev_err(dev, "tx error %x\n",
+						next->tx_comp.rcs[i]);
+					dev_kfree_skb_irq(txbuff->skb);
+				} else {
+					dev_consume_skb_irq(txbuff->skb);
+				}
 				txbuff->skb = NULL;
 			} else {
 				netdev_warn(adapter->netdev,

From b166a20b07382b8bc1dcee2a448715c9c2c81b5b Mon Sep 17 00:00:00 2001
From: Or Cohen <orcohen@paloaltonetworks.com>
Date: Tue, 13 Apr 2021 21:10:31 +0300
Subject: [PATCH 1760/1820] net/sctp: fix race condition in sctp_destroy_sock

If sctp_destroy_sock is called without sock_net(sk)->sctp.addr_wq_lock
held and sp->do_auto_asconf is true, then an element is removed
from the auto_asconf_splist without any proper locking.

This can happen in the following functions:
1. In sctp_accept, if sctp_sock_migrate fails.
2. In inet_create or inet6_create, if there is a bpf program
   attached to BPF_CGROUP_INET_SOCK_CREATE which denies
   creation of the sctp socket.

The bug is fixed by acquiring addr_wq_lock in sctp_destroy_sock
instead of sctp_close.

This addresses CVE-2021-23133.

Reported-by: Or Cohen <orcohen@paloaltonetworks.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Fixes: 610236587600 ("bpf: Add new cgroup attach type to enable sock modifications")
Signed-off-by: Or Cohen <orcohen@paloaltonetworks.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index a710917c5ac7..b9b3d899a611 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1520,11 +1520,9 @@ static void sctp_close(struct sock *sk, long timeout)
 
 	/* Supposedly, no process has access to the socket, but
 	 * the net layers still may.
-	 * Also, sctp_destroy_sock() needs to be called with addr_wq_lock
-	 * held and that should be grabbed before socket lock.
 	 */
-	spin_lock_bh(&net->sctp.addr_wq_lock);
-	bh_lock_sock_nested(sk);
+	local_bh_disable();
+	bh_lock_sock(sk);
 
 	/* Hold the sock, since sk_common_release() will put sock_put()
 	 * and we have just a little more cleanup.
@@ -1533,7 +1531,7 @@ static void sctp_close(struct sock *sk, long timeout)
 	sk_common_release(sk);
 
 	bh_unlock_sock(sk);
-	spin_unlock_bh(&net->sctp.addr_wq_lock);
+	local_bh_enable();
 
 	sock_put(sk);
 
@@ -4993,9 +4991,6 @@ static int sctp_init_sock(struct sock *sk)
 	sk_sockets_allocated_inc(sk);
 	sock_prot_inuse_add(net, sk->sk_prot, 1);
 
-	/* Nothing can fail after this block, otherwise
-	 * sctp_destroy_sock() will be called without addr_wq_lock held
-	 */
 	if (net->sctp.default_auto_asconf) {
 		spin_lock(&sock_net(sk)->sctp.addr_wq_lock);
 		list_add_tail(&sp->auto_asconf_list,
@@ -5030,7 +5025,9 @@ static void sctp_destroy_sock(struct sock *sk)
 
 	if (sp->do_auto_asconf) {
 		sp->do_auto_asconf = 0;
+		spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 		list_del(&sp->auto_asconf_list);
+		spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	}
 	sctp_endpoint_free(sp->ep);
 	local_bh_disable();

From 38ec4944b593fd90c5ef42aaaa53e66ae5769d04 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 13 Apr 2021 05:41:35 -0700
Subject: [PATCH 1761/1820] gro: ensure frag0 meets IP header alignment

After commit 0f6925b3e8da ("virtio_net: Do not pull payload in skb->head")
Guenter Roeck reported one failure in his tests using sh architecture.

After much debugging, we have been able to spot silent unaligned accesses
in inet_gro_receive()

The issue at hand is that upper networking stacks assume their header
is word-aligned. Low level drivers are supposed to reserve NET_IP_ALIGN
bytes before the Ethernet header to make that happen.

This patch hardens skb_gro_reset_offset() to not allow frag0 fast-path
if the fragment is not properly aligned.

Some arches like x86, arm64 and powerpc do not care and define NET_IP_ALIGN
as 0, this extra check will be a NOP for them.

Note that if frag0 is not used, GRO will call pskb_may_pull()
as many times as needed to pull network and transport headers.

Fixes: 0f6925b3e8da ("virtio_net: Do not pull payload in skb->head")
Fixes: 78a478d0efd9 ("gro: Inline skb_gro_header and cache frag0 virtual address")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index af8c1ea040b9..1f79b9aa9a3f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5924,7 +5924,8 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
 	NAPI_GRO_CB(skb)->frag0_len = 0;
 
 	if (!skb_headlen(skb) && pinfo->nr_frags &&
-	    !PageHighMem(skb_frag_page(frag0))) {
+	    !PageHighMem(skb_frag_page(frag0)) &&
+	    (!NET_IP_ALIGN || !(skb_frag_off(frag0) & 3))) {
 		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
 		NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
 						    skb_frag_size(frag0),

From 04c4f2ee3f68c9a4bf1653d15f1a9a435ae33f7a Mon Sep 17 00:00:00 2001
From: Reiji Watanabe <reijiw@google.com>
Date: Tue, 13 Apr 2021 15:47:40 +0000
Subject: [PATCH 1762/1820] KVM: VMX: Don't use vcpu->run->internal.ndata as an
 array index

__vmx_handle_exit() uses vcpu->run->internal.ndata as an index for
an array access.  Since vcpu->run is (can be) mapped to a user address
space with a writer permission, the 'ndata' could be updated by the
user process at anytime (the user process can set it to outside the
bounds of the array).
So, it is not safe that __vmx_handle_exit() uses the 'ndata' that way.

Fixes: 1aa561b1a4c0 ("kvm: x86: Add "last CPU" to some KVM_EXIT information")
Signed-off-by: Reiji Watanabe <reijiw@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Message-Id: <20210413154739.490299-1-reijiw@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/vmx.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 32cf8287d4a7..29b40e092d13 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6027,19 +6027,19 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	     exit_reason.basic != EXIT_REASON_PML_FULL &&
 	     exit_reason.basic != EXIT_REASON_APIC_ACCESS &&
 	     exit_reason.basic != EXIT_REASON_TASK_SWITCH)) {
+		int ndata = 3;
+
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
-		vcpu->run->internal.ndata = 3;
 		vcpu->run->internal.data[0] = vectoring_info;
 		vcpu->run->internal.data[1] = exit_reason.full;
 		vcpu->run->internal.data[2] = vcpu->arch.exit_qualification;
 		if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) {
-			vcpu->run->internal.ndata++;
-			vcpu->run->internal.data[3] =
+			vcpu->run->internal.data[ndata++] =
 				vmcs_read64(GUEST_PHYSICAL_ADDRESS);
 		}
-		vcpu->run->internal.data[vcpu->run->internal.ndata++] =
-			vcpu->arch.last_vmentry_cpu;
+		vcpu->run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu;
+		vcpu->run->internal.ndata = ndata;
 		return 0;
 	}
 

From 2afeec08ab5c86ae21952151f726bfe184f6b23d Mon Sep 17 00:00:00 2001
From: Michael Brown <mbrown@fensystems.co.uk>
Date: Tue, 13 Apr 2021 16:25:12 +0100
Subject: [PATCH 1763/1820] xen-netback: Check for hotplug-status existence
 before watching

The logic in connect() is currently written with the assumption that
xenbus_watch_pathfmt() will return an error for a node that does not
exist.  This assumption is incorrect: xenstore does allow a watch to
be registered for a nonexistent node (and will send notifications
should the node be subsequently created).

As of commit 1f2565780 ("xen-netback: remove 'hotplug-status' once it
has served its purpose"), this leads to a failure when a domU
transitions into XenbusStateConnected more than once.  On the first
domU transition into Connected state, the "hotplug-status" node will
be deleted by the hotplug_status_changed() callback in dom0.  On the
second or subsequent domU transition into Connected state, the
hotplug_status_changed() callback will therefore never be invoked, and
so the backend will remain stuck in InitWait.

This failure prevents scenarios such as reloading the xen-netfront
module within a domU, or booting a domU via iPXE.  There is
unfortunately no way for the domU to work around this dom0 bug.

Fix by explicitly checking for existence of the "hotplug-status" node,
thereby creating the behaviour that was previously assumed to exist.

Signed-off-by: Michael Brown <mbrown@fensystems.co.uk>
Reviewed-by: Paul Durrant <paul@xen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/xenbus.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index a5439c130130..d24b7a7993aa 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -824,11 +824,15 @@ static void connect(struct backend_info *be)
 	xenvif_carrier_on(be->vif);
 
 	unregister_hotplug_status_watch(be);
-	err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch, NULL,
-				   hotplug_status_changed,
-				   "%s/%s", dev->nodename, "hotplug-status");
-	if (!err)
+	if (xenbus_exists(XBT_NIL, dev->nodename, "hotplug-status")) {
+		err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
+					   NULL, hotplug_status_changed,
+					   "%s/%s", dev->nodename,
+					   "hotplug-status");
+		if (err)
+			goto err;
 		be->have_hotplug_status_watch = 1;
+	}
 
 	netif_tx_wake_all_queues(be->vif->dev);
 

From 8ca7cab82bda4eb0b8064befeeeaa38106cac637 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@google.com>
Date: Wed, 14 Apr 2021 08:28:28 -0700
Subject: [PATCH 1764/1820] dm verity fec: fix misaligned RS roots IO

commit df7b59ba9245 ("dm verity: fix FEC for RS roots unaligned to
block size") introduced the possibility for misaligned roots IO
relative to the underlying device's logical block size. E.g. Android's
default RS roots=2 results in dm_bufio->block_size=1024, which causes
the following EIO if the logical block size of the device is 4096,
given v->data_dev_block_bits=12:

E sd 0    : 0:0:0: [sda] tag#30 request not aligned to the logical block size
E blk_update_request: I/O error, dev sda, sector 10368424 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 0
E device-mapper: verity-fec: 254:8: FEC 9244672: parity read failed (block 18056): -5

Fix this by onlu using f->roots for dm_bufio blocksize IFF it is
aligned to v->data_dev_block_bits.

Fixes: df7b59ba9245 ("dm verity: fix FEC for RS roots unaligned to block size")
Cc: stable@vger.kernel.org
Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-verity-fec.c | 11 ++++++++---
 drivers/md/dm-verity-fec.h |  1 +
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 66f4c6398f67..cea2b3789736 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -65,7 +65,7 @@ static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index,
 	u8 *res;
 
 	position = (index + rsb) * v->fec->roots;
-	block = div64_u64_rem(position, v->fec->roots << SECTOR_SHIFT, &rem);
+	block = div64_u64_rem(position, v->fec->io_size, &rem);
 	*offset = (unsigned)rem;
 
 	res = dm_bufio_read(v->fec->bufio, block, buf);
@@ -154,7 +154,7 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio,
 
 		/* read the next block when we run out of parity bytes */
 		offset += v->fec->roots;
-		if (offset >= v->fec->roots << SECTOR_SHIFT) {
+		if (offset >= v->fec->io_size) {
 			dm_bufio_release(buf);
 
 			par = fec_read_parity(v, rsb, block_offset, &offset, &buf);
@@ -742,8 +742,13 @@ int verity_fec_ctr(struct dm_verity *v)
 		return -E2BIG;
 	}
 
+	if ((f->roots << SECTOR_SHIFT) & ((1 << v->data_dev_block_bits) - 1))
+		f->io_size = 1 << v->data_dev_block_bits;
+	else
+		f->io_size = v->fec->roots << SECTOR_SHIFT;
+
 	f->bufio = dm_bufio_client_create(f->dev->bdev,
-					  f->roots << SECTOR_SHIFT,
+					  f->io_size,
 					  1, 0, NULL, NULL);
 	if (IS_ERR(f->bufio)) {
 		ti->error = "Cannot initialize FEC bufio client";
diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h
index 42fbd3a7fc9f..3c46c8d61883 100644
--- a/drivers/md/dm-verity-fec.h
+++ b/drivers/md/dm-verity-fec.h
@@ -36,6 +36,7 @@ struct dm_verity_fec {
 	struct dm_dev *dev;	/* parity data device */
 	struct dm_bufio_client *data_bufio;	/* for data dev access */
 	struct dm_bufio_client *bufio;		/* for parity data access */
+	size_t io_size;		/* IO size for roots */
 	sector_t start;		/* parity data start in blocks */
 	sector_t blocks;	/* number of blocks covered */
 	sector_t rounds;	/* number of interleaving rounds */

From c7d95613c7d6e003969722a290397b8271bdad17 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 13 Apr 2021 11:43:00 +0100
Subject: [PATCH 1765/1820] io_uring: fix early sqd_list removal sqpoll hangs

[  245.463317] INFO: task iou-sqp-1374:1377 blocked for more than 122 seconds.
[  245.463334] task:iou-sqp-1374    state:D flags:0x00004000
[  245.463345] Call Trace:
[  245.463352]  __schedule+0x36b/0x950
[  245.463376]  schedule+0x68/0xe0
[  245.463385]  __io_uring_cancel+0xfb/0x1a0
[  245.463407]  do_exit+0xc0/0xb40
[  245.463423]  io_sq_thread+0x49b/0x710
[  245.463445]  ret_from_fork+0x22/0x30

It happens when sqpoll forgot to run park_task_work and goes to exit,
then exiting user may remove ctx from sqd_list, and so corresponding
io_sq_thread() -> io_uring_cancel_sqpoll() won't be executed. Hopefully
it just stucks in do_exit() in this case.

Fixes: dbe1bdbb39db ("io_uring: handle signals for IO threads like a normal thread")
Reported-by: Joakim Hassila <joj@mac.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index bd14327c8e7e..dff34975d86b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6754,6 +6754,9 @@ static int io_sq_thread(void *data)
 	current->flags |= PF_NO_SETAFFINITY;
 
 	mutex_lock(&sqd->lock);
+	/* a user may had exited before the thread started */
+	io_run_task_work_head(&sqd->park_task_work);
+
 	while (!test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)) {
 		int ret;
 		bool cap_entries, sqt_spin, needs_sched;
@@ -6770,10 +6773,10 @@ static int io_sq_thread(void *data)
 			}
 			cond_resched();
 			mutex_lock(&sqd->lock);
-			if (did_sig)
-				break;
 			io_run_task_work();
 			io_run_task_work_head(&sqd->park_task_work);
+			if (did_sig)
+				break;
 			timeout = jiffies + sqd->sq_thread_idle;
 			continue;
 		}

From 16756d3e77ad58cd07e36cbed724aa13ae5a0278 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 13 Apr 2021 20:46:14 -0700
Subject: [PATCH 1766/1820] ethtool: pause: make sure we init driver stats

The intention was for pause statistics to not be reported
when driver does not have the relevant callback (only
report an empty netlink nest). What happens currently
we report all 0s instead. Make sure statistics are
initialized to "not set" (which is -1) so the dumping
code skips them.

Fixes: 9a27a33027f2 ("ethtool: add standard pause stats")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/pause.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c
index 09998dc5c185..d4ac02718b72 100644
--- a/net/ethtool/pause.c
+++ b/net/ethtool/pause.c
@@ -38,16 +38,16 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base,
 	if (!dev->ethtool_ops->get_pauseparam)
 		return -EOPNOTSUPP;
 
+	ethtool_stats_init((u64 *)&data->pausestat,
+			   sizeof(data->pausestat) / 8);
+
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
 		return ret;
 	dev->ethtool_ops->get_pauseparam(dev, &data->pauseparam);
 	if (req_base->flags & ETHTOOL_FLAG_STATS &&
-	    dev->ethtool_ops->get_pause_stats) {
-		ethtool_stats_init((u64 *)&data->pausestat,
-				   sizeof(data->pausestat) / 8);
+	    dev->ethtool_ops->get_pause_stats)
 		dev->ethtool_ops->get_pause_stats(dev, &data->pausestat);
-	}
 	ethnl_ops_complete(dev);
 
 	return 0;

From 453a77894efa4d9b6ef9644d74b9419c47ac427c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 14 Apr 2021 10:47:10 +0200
Subject: [PATCH 1767/1820] r8169: don't advertise pause in jumbo mode

It has been reported [0] that using pause frames in jumbo mode impacts
performance. There's no available chip documentation, but vendor
drivers r8168 and r8125 don't advertise pause in jumbo mode. So let's
do the same, according to Roman it fixes the issue.

[0] https://bugzilla.kernel.org/show_bug.cgi?id=212617

Fixes: 9cf9b84cc701 ("r8169: make use of phy_set_asym_pause")
Reported-by: Roman Mamedov <rm+bko@romanrm.net>
Tested-by: Roman Mamedov <rm+bko@romanrm.net>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 581a92fc3292..1df2c002c9f6 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2350,6 +2350,13 @@ static void rtl_jumbo_config(struct rtl8169_private *tp)
 
 	if (pci_is_pcie(tp->pci_dev) && tp->supports_gmii)
 		pcie_set_readrq(tp->pci_dev, readrq);
+
+	/* Chip doesn't support pause in jumbo mode */
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+			 tp->phydev->advertising, !jumbo);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+			 tp->phydev->advertising, !jumbo);
+	phy_start_aneg(tp->phydev);
 }
 
 DECLARE_RTL_COND(rtl_chipcmd_cond)
@@ -4630,8 +4637,6 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
 	if (!tp->supports_gmii)
 		phy_set_max_speed(phydev, SPEED_100);
 
-	phy_support_asym_pause(phydev);
-
 	phy_attached_info(phydev);
 
 	return 0;

From 0775ebc4cf8554bdcd2c212669a0868ab68df5c0 Mon Sep 17 00:00:00 2001
From: Lijun Pan <lijunp213@gmail.com>
Date: Wed, 14 Apr 2021 02:46:14 -0500
Subject: [PATCH 1768/1820] ibmvnic: avoid calling napi_disable() twice

__ibmvnic_open calls napi_disable without checking whether NAPI polling
has already been disabled or not. This could cause napi_disable
being called twice, which could generate deadlock. For example,
the first napi_disable will spin until NAPI_STATE_SCHED is cleared
by napi_complete_done, then set it again.
When napi_disable is called the second time, it will loop infinitely
because no dev->poll will be running to clear NAPI_STATE_SCHED.

To prevent above scenario from happening, call ibmvnic_napi_disable()
which checks if napi is disabled or not before calling napi_disable.

Fixes: bfc32f297337 ("ibmvnic: Move resource initialization to its own routine")
Suggested-by: Thomas Falcon <tlfalcon@linux.ibm.com>
Signed-off-by: Lijun Pan <lijunp213@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 110a0d0eaabb..2d27f8aa0d4b 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1149,8 +1149,7 @@ static int __ibmvnic_open(struct net_device *netdev)
 
 	rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP);
 	if (rc) {
-		for (i = 0; i < adapter->req_rx_queues; i++)
-			napi_disable(&adapter->napi[i]);
+		ibmvnic_napi_disable(adapter);
 		release_resources(adapter);
 		return rc;
 	}

From d3a6abccbd272aea7dc2c6f984bb5a2c11278e44 Mon Sep 17 00:00:00 2001
From: Lijun Pan <lijunp213@gmail.com>
Date: Wed, 14 Apr 2021 02:46:15 -0500
Subject: [PATCH 1769/1820] ibmvnic: remove duplicate napi_schedule call in
 do_reset function

During adapter reset, do_reset/do_hard_reset calls ibmvnic_open(),
which will calls napi_schedule if previous state is VNIC_CLOSED
(i.e, the reset case, and "ifconfig down" case). So there is no need
for do_reset to call napi_schedule again at the end of the function
though napi_schedule will neglect the request if napi is already
scheduled.

Fixes: ed651a10875f ("ibmvnic: Updated reset handling")
Signed-off-by: Lijun Pan <lijunp213@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 2d27f8aa0d4b..f4bd63216672 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1921,7 +1921,7 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 	u64 old_num_rx_queues, old_num_tx_queues;
 	u64 old_num_rx_slots, old_num_tx_slots;
 	struct net_device *netdev = adapter->netdev;
-	int i, rc;
+	int rc;
 
 	netdev_dbg(adapter->netdev,
 		   "[S:%d FOP:%d] Reset reason %d, reset_state %d\n",
@@ -2110,10 +2110,6 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 	/* refresh device's multicast list */
 	ibmvnic_set_multi(netdev);
 
-	/* kick napi */
-	for (i = 0; i < adapter->req_rx_queues; i++)
-		napi_schedule(&adapter->napi[i]);
-
 	if (adapter->reset_reason == VNIC_RESET_FAILOVER ||
 	    adapter->reset_reason == VNIC_RESET_MOBILITY)
 		__netdev_notify_peers(netdev);

From 7c451f3ef676c805a4b77a743a01a5c21a250a73 Mon Sep 17 00:00:00 2001
From: Lijun Pan <lijunp213@gmail.com>
Date: Wed, 14 Apr 2021 02:46:16 -0500
Subject: [PATCH 1770/1820] ibmvnic: remove duplicate napi_schedule call in
 open function

Remove the unnecessary napi_schedule() call in __ibmvnic_open() since
interrupt_rx() calls napi_schedule_prep/__napi_schedule during every
receive interrupt.

Fixes: ed651a10875f ("ibmvnic: Updated reset handling")
Signed-off-by: Lijun Pan <lijunp213@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index f4bd63216672..ffb2a91750c7 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1156,11 +1156,6 @@ static int __ibmvnic_open(struct net_device *netdev)
 
 	netif_tx_start_all_queues(netdev);
 
-	if (prev_state == VNIC_CLOSED) {
-		for (i = 0; i < adapter->req_rx_queues; i++)
-			napi_schedule(&adapter->napi[i]);
-	}
-
 	adapter->state = VNIC_OPEN;
 	return rc;
 }

From 292ecd9f5a94dd29d09fe03b5b669cb20b44f19e Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 14 Apr 2021 12:00:27 +0200
Subject: [PATCH 1771/1820] doc: move seg6_flowlabel to seg6-sysctl.rst

Let's have all seg6 sysctl at the same place.

Fixes: a6dc6670cd7e ("ipv6: sr: Add documentation for seg_flowlabel sysctl")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.rst   | 15 ---------------
 Documentation/networking/seg6-sysctl.rst | 13 +++++++++++++
 2 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index c7952ac5bd2f..3feb5e565b1a 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -1849,21 +1849,6 @@ ip6frag_low_thresh - INTEGER
 ip6frag_time - INTEGER
 	Time in seconds to keep an IPv6 fragment in memory.
 
-IPv6 Segment Routing:
-
-seg6_flowlabel - INTEGER
-	Controls the behaviour of computing the flowlabel of outer
-	IPv6 header in case of SR T.encaps
-
-	 == =======================================================
-	 -1  set flowlabel to zero.
-	  0  copy flowlabel from Inner packet in case of Inner IPv6
-	     (Set flowlabel to 0 in case IPv4/L2)
-	  1  Compute the flowlabel using seg6_make_flowlabel()
-	 == =======================================================
-
-	Default is 0.
-
 ``conf/default/*``:
 	Change the interface-specific default settings.
 
diff --git a/Documentation/networking/seg6-sysctl.rst b/Documentation/networking/seg6-sysctl.rst
index ec73e1445030..07c20e470baf 100644
--- a/Documentation/networking/seg6-sysctl.rst
+++ b/Documentation/networking/seg6-sysctl.rst
@@ -24,3 +24,16 @@ seg6_require_hmac - INTEGER
 	* 1 - Drop SR packets without HMAC, validate SR packets with HMAC
 
 	Default is 0.
+
+seg6_flowlabel - INTEGER
+	Controls the behaviour of computing the flowlabel of outer
+	IPv6 header in case of SR T.encaps
+
+	 == =======================================================
+	 -1  set flowlabel to zero.
+	  0  copy flowlabel from Inner packet in case of Inner IPv6
+	     (Set flowlabel to 0 in case IPv4/L2)
+	  1  Compute the flowlabel using seg6_make_flowlabel()
+	 == =======================================================
+
+	Default is 0.

From 2e1534f395e73152e2051332034bff61a56a8368 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 14 Apr 2021 12:03:25 +0200
Subject: [PATCH 1772/1820] vrf: fix a comment about loopback device

This is a leftover of the below commit.

Fixes: 4f04256c983a ("net: vrf: Drop local rtable and rt6_info")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 6d9130859c55..503e2fd7ce51 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -471,9 +471,8 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 
 	skb_dst_drop(skb);
 
-	/* if dst.dev is loopback or the VRF device again this is locally
-	 * originated traffic destined to a local address. Short circuit
-	 * to Rx path
+	/* if dst.dev is the VRF device again this is locally originated traffic
+	 * destined to a local address. Short circuit to Rx path.
 	 */
 	if (dst->dev == dev)
 		return vrf_local_xmit(skb, dev, dst);
@@ -547,9 +546,8 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 
 	skb_dst_drop(skb);
 
-	/* if dst.dev is loopback or the VRF device again this is locally
-	 * originated traffic destined to a local address. Short circuit
-	 * to Rx path
+	/* if dst.dev is the VRF device again this is locally originated traffic
+	 * destined to a local address. Short circuit to Rx path.
 	 */
 	if (rt->dst.dev == vrf_dev)
 		return vrf_local_xmit(skb, vrf_dev, &rt->dst);

From ab4d9913632b1e5ffcf3365783e98718b3c83c7f Mon Sep 17 00:00:00 2001
From: Zack Rusin <zackr@vmware.com>
Date: Thu, 14 Jan 2021 18:38:16 -0500
Subject: [PATCH 1773/1820] drm/vmwgfx: Make sure we unpin no longer needed
 buffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We were not correctly unpinning no longer needed buffers. In particular
vmw_buffer_object, which is internally often pinned on creation wasn't
unpinned on destruction and none of the internal MOB buffers were
unpinned before being put back. Technically this existed for a
long time but commit 57fcd550eb15 ("drm/ttm: Warn on pinning without
holding a reference") introduced a WARN_ON which was filling up the
kernel logs rather quickly.

Quite frankly internal usage of vmw_buffer_object and in general
pinning needs to be refactored in vmwgfx but for now this makes
it work.

Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Martin Krastev <krastevm@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Fixes: 57fcd550eb15 ("drm/ttm: Warn on pinning without holding a reference")
Link: https://patchwork.freedesktop.org/patch/414984/?series=86052&rev=1
Cc: Huang Rui <ray.huang@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: dri-devel@lists.freedesktop.org
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 2 ++
 drivers/gpu/drm/vmwgfx/vmwgfx_mob.c | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 5fa5bcd20cc5..336f5086ca26 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1525,6 +1525,8 @@ static inline void vmw_bo_unreference(struct vmw_buffer_object **buf)
 
 	*buf = NULL;
 	if (tmp_buf != NULL) {
+		if (tmp_buf->base.pin_count > 0)
+			ttm_bo_unpin(&tmp_buf->base);
 		ttm_bo_put(&tmp_buf->base);
 	}
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
index a372980fe6a5..a0b53141dded 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
@@ -277,6 +277,7 @@ out_no_setup:
 						 &batch->otables[i]);
 	}
 
+	ttm_bo_unpin(batch->otable_bo);
 	ttm_bo_put(batch->otable_bo);
 	batch->otable_bo = NULL;
 	return ret;
@@ -342,6 +343,7 @@ static void vmw_otable_batch_takedown(struct vmw_private *dev_priv,
 	vmw_bo_fence_single(bo, NULL);
 	ttm_bo_unreserve(bo);
 
+	ttm_bo_unpin(batch->otable_bo);
 	ttm_bo_put(batch->otable_bo);
 	batch->otable_bo = NULL;
 }
@@ -528,6 +530,7 @@ static void vmw_mob_pt_setup(struct vmw_mob *mob,
 void vmw_mob_destroy(struct vmw_mob *mob)
 {
 	if (mob->pt_bo) {
+		ttm_bo_unpin(mob->pt_bo);
 		ttm_bo_put(mob->pt_bo);
 		mob->pt_bo = NULL;
 	}
@@ -643,6 +646,7 @@ int vmw_mob_bind(struct vmw_private *dev_priv,
 out_no_cmd_space:
 	vmw_fifo_resource_dec(dev_priv);
 	if (pt_set_up) {
+		ttm_bo_unpin(mob->pt_bo);
 		ttm_bo_put(mob->pt_bo);
 		mob->pt_bo = NULL;
 	}

From 68ce556bd1643498080af310d4544f46f3c4f3df Mon Sep 17 00:00:00 2001
From: Zack Rusin <zackr@vmware.com>
Date: Mon, 22 Mar 2021 12:54:57 -0400
Subject: [PATCH 1774/1820] drm/vmwgfx: Fix the lockdep breakage

Thomas has noticed that the lockdep was broken in vmwgfx. It
was broken during the pci initialization rework. This fixes
the breakage by making sure we initialize the locking code
before doing anything else. This was independently spotted
and fixed by Tetsuo Handa as well.

Reviewed-by: Martin Krastev <krastevm@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Zack Rusin <zackr@vmware.com>
Fixes: 8772c0bb58bbf98a ("drm/vmwgfx: Cleanup pci resource allocation")
Link: https://patchwork.freedesktop.org/patch/msgid/20210408172245.673785-1-zackr@vmware.com
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 19 +++++++++----------
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h |  2 --
 2 files changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index dd69b51c40e4..6fa24645fbbf 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -712,6 +712,15 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 	dev_priv->last_read_seqno = (uint32_t) -100;
 	dev_priv->drm.dev_private = dev_priv;
 
+	mutex_init(&dev_priv->cmdbuf_mutex);
+	mutex_init(&dev_priv->binding_mutex);
+	ttm_lock_init(&dev_priv->reservation_sem);
+	spin_lock_init(&dev_priv->resource_lock);
+	spin_lock_init(&dev_priv->hw_lock);
+	spin_lock_init(&dev_priv->waiter_lock);
+	spin_lock_init(&dev_priv->cap_lock);
+	spin_lock_init(&dev_priv->cursor_lock);
+
 	ret = vmw_setup_pci_resources(dev_priv, pci_id);
 	if (ret)
 		return ret;
@@ -719,16 +728,6 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 	if (ret)
 		goto out_no_pci_or_version;
 
-	mutex_init(&dev_priv->cmdbuf_mutex);
-	mutex_init(&dev_priv->release_mutex);
-	mutex_init(&dev_priv->binding_mutex);
-	mutex_init(&dev_priv->global_kms_state_mutex);
-	ttm_lock_init(&dev_priv->reservation_sem);
-	spin_lock_init(&dev_priv->resource_lock);
-	spin_lock_init(&dev_priv->hw_lock);
-	spin_lock_init(&dev_priv->waiter_lock);
-	spin_lock_init(&dev_priv->cap_lock);
-	spin_lock_init(&dev_priv->cursor_lock);
 
 	for (i = vmw_res_context; i < vmw_res_max; ++i) {
 		idr_init(&dev_priv->res_idr[i]);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 336f5086ca26..8087a9013455 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -529,7 +529,6 @@ struct vmw_private {
 	struct vmw_overlay *overlay_priv;
 	struct drm_property *hotplug_mode_update_property;
 	struct drm_property *implicit_placement_property;
-	struct mutex global_kms_state_mutex;
 	spinlock_t cursor_lock;
 	struct drm_atomic_state *suspend_state;
 
@@ -592,7 +591,6 @@ struct vmw_private {
 	bool refuse_hibernation;
 	bool suspend_locked;
 
-	struct mutex release_mutex;
 	atomic_t num_fifo_resources;
 
 	/*

From 2ef4fb92363c44e8a6f93fd0877b6a7dee6f874d Mon Sep 17 00:00:00 2001
From: Zack Rusin <zackr@vmware.com>
Date: Mon, 22 Mar 2021 13:04:11 -0400
Subject: [PATCH 1775/1820] drm/vmwgfx: Make sure bo's are unpinned before
 putting them back
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During cotable resize we pin the backup buffer to make sure the
trylock doesn't fail. We were never unpinning the backup buffer
resulting in every subsequent cotable resize trying to release a
pinned bo. After we copy the old backup to the new we can release
the pin.
Mob's are always pinned so we just have to make sure we unpin
them before releasing them.

Reviewed-by: Thomas Hellström (Intel) <thomas_os@shipmail.org>
Fixes: d1a73c641afd ("drm/vmwgfx: Make sure we unpin no longer needed buffers")
Link: https://patchwork.freedesktop.org/patch/msgid/20210413205938.788366-1-zackr@vmware.com
Signed-off-by: Zack Rusin <zackr@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c |  4 ++++
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h     |  5 +----
 drivers/gpu/drm/vmwgfx/vmwgfx_mob.c     | 18 ++++++++++++++----
 3 files changed, 19 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
index ba658fa9cf6c..183571c387b7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
@@ -481,11 +481,15 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 	vmw_bo_unreference(&old_buf);
 	res->id = vcotbl->type;
 
+	/* Release the pin acquired in vmw_bo_init */
+	ttm_bo_unpin(bo);
+
 	return 0;
 
 out_map_new:
 	ttm_bo_kunmap(&old_map);
 out_wait:
+	ttm_bo_unpin(bo);
 	ttm_bo_unreserve(bo);
 	vmw_bo_unreference(&buf);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 8087a9013455..eb76a6b9ebca 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1522,11 +1522,8 @@ static inline void vmw_bo_unreference(struct vmw_buffer_object **buf)
 	struct vmw_buffer_object *tmp_buf = *buf;
 
 	*buf = NULL;
-	if (tmp_buf != NULL) {
-		if (tmp_buf->base.pin_count > 0)
-			ttm_bo_unpin(&tmp_buf->base);
+	if (tmp_buf != NULL)
 		ttm_bo_put(&tmp_buf->base);
-	}
 }
 
 static inline struct vmw_buffer_object *
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
index a0b53141dded..f2d625415458 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
@@ -94,6 +94,16 @@ static void vmw_mob_pt_setup(struct vmw_mob *mob,
 			     struct vmw_piter data_iter,
 			     unsigned long num_data_pages);
 
+
+static inline void vmw_bo_unpin_unlocked(struct ttm_buffer_object *bo)
+{
+	int ret = ttm_bo_reserve(bo, false, true, NULL);
+	BUG_ON(ret != 0);
+	ttm_bo_unpin(bo);
+	ttm_bo_unreserve(bo);
+}
+
+
 /*
  * vmw_setup_otable_base - Issue an object table base setup command to
  * the device
@@ -277,7 +287,7 @@ out_no_setup:
 						 &batch->otables[i]);
 	}
 
-	ttm_bo_unpin(batch->otable_bo);
+	vmw_bo_unpin_unlocked(batch->otable_bo);
 	ttm_bo_put(batch->otable_bo);
 	batch->otable_bo = NULL;
 	return ret;
@@ -341,9 +351,9 @@ static void vmw_otable_batch_takedown(struct vmw_private *dev_priv,
 	BUG_ON(ret != 0);
 
 	vmw_bo_fence_single(bo, NULL);
+	ttm_bo_unpin(bo);
 	ttm_bo_unreserve(bo);
 
-	ttm_bo_unpin(batch->otable_bo);
 	ttm_bo_put(batch->otable_bo);
 	batch->otable_bo = NULL;
 }
@@ -530,7 +540,7 @@ static void vmw_mob_pt_setup(struct vmw_mob *mob,
 void vmw_mob_destroy(struct vmw_mob *mob)
 {
 	if (mob->pt_bo) {
-		ttm_bo_unpin(mob->pt_bo);
+		vmw_bo_unpin_unlocked(mob->pt_bo);
 		ttm_bo_put(mob->pt_bo);
 		mob->pt_bo = NULL;
 	}
@@ -646,7 +656,7 @@ int vmw_mob_bind(struct vmw_private *dev_priv,
 out_no_cmd_space:
 	vmw_fifo_resource_dec(dev_priv);
 	if (pt_set_up) {
-		ttm_bo_unpin(mob->pt_bo);
+		vmw_bo_unpin_unlocked(mob->pt_bo);
 		ttm_bo_put(mob->pt_bo);
 		mob->pt_bo = NULL;
 	}

From a714e27ea8bdee2b238748029d31472d0a65b611 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 14 Apr 2021 14:20:29 +0300
Subject: [PATCH 1776/1820] net: macb: fix the restore of cmp registers

Commit a14d273ba159 ("net: macb: restore cmp registers on resume path")
introduces the restore of CMP registers on resume path. In case the IP
doesn't support type 2 screeners (zero on DCFG8 register) the
struct macb::rx_fs_list::list is not initialized and thus the
list_for_each_entry(item, &bp->rx_fs_list.list, list) loop introduced in
commit a14d273ba159 ("net: macb: restore cmp registers on resume path")
will access an uninitialized list leading to crash. Thus, initialize
the struct macb::rx_fs_list::list without taking into account if the
IP supports type 2 screeners or not.

Fixes: a14d273ba159 ("net: macb: restore cmp registers on resume path")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 6e5cf490c01d..0f6a6cb7e98d 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3918,6 +3918,7 @@ static int macb_init(struct platform_device *pdev)
 	reg = gem_readl(bp, DCFG8);
 	bp->max_tuples = min((GEM_BFEXT(SCR2CMP, reg) / 3),
 			GEM_BFEXT(T2SCR, reg));
+	INIT_LIST_HEAD(&bp->rx_fs_list.list);
 	if (bp->max_tuples > 0) {
 		/* also needs one ethtype match to check IPv4 */
 		if (GEM_BFEXT(SCR2ETH, reg) > 0) {
@@ -3928,7 +3929,6 @@ static int macb_init(struct platform_device *pdev)
 			/* Filtering is supported in hw but don't enable it in kernel now */
 			dev->hw_features |= NETIF_F_NTUPLE;
 			/* init Rx flow definitions */
-			INIT_LIST_HEAD(&bp->rx_fs_list.list);
 			bp->rx_fs_list.count = 0;
 			spin_lock_init(&bp->rx_fs_lock);
 		} else

From 416dcc5ce9d2a810477171c62ffa061a98f87367 Mon Sep 17 00:00:00 2001
From: Wan Jiabing <wanjiabing@vivo.com>
Date: Wed, 14 Apr 2021 19:31:48 +0800
Subject: [PATCH 1777/1820] cavium/liquidio: Fix duplicate argument

Fix the following coccicheck warning:

./drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h:413:6-28:
duplicated argument to & or |

The CN6XXX_INTR_M1UPB0_ERR here is duplicate.
Here should be CN6XXX_INTR_M1UNB0_ERR.

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h b/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h
index b248966837b4..7aad40b2aa73 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h
@@ -412,7 +412,7 @@
 	   | CN6XXX_INTR_M0UNWI_ERR             \
 	   | CN6XXX_INTR_M1UPB0_ERR             \
 	   | CN6XXX_INTR_M1UPWI_ERR             \
-	   | CN6XXX_INTR_M1UPB0_ERR             \
+	   | CN6XXX_INTR_M1UNB0_ERR             \
 	   | CN6XXX_INTR_M1UNWI_ERR             \
 	   | CN6XXX_INTR_INSTR_DB_OF_ERR        \
 	   | CN6XXX_INTR_SLIST_DB_OF_ERR        \

From 00423969d806d7169d16fa6314c570a472ca26c9 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Wed, 14 Apr 2021 17:10:07 +0200
Subject: [PATCH 1778/1820] Revert "net: stmmac: re-init rx buffers when mac
 resume back"

This reverts commit 9c63faaa931e443e7abbbee9de0169f1d4710546, which
introduces a suspend/resume regression on Jetson TX2 boards that can be
reproduced every time. Given that the issue that this was supposed to
fix only occurs very sporadically the safest course of action is to
revert before v5.12 and then we can have another go at fixing the more
rare issue in the next release (and perhaps backport it if necessary).

The root cause of the observed problem seems to be that when the system
is suspended, some packets are still in transit. When the descriptors
for these buffers are cleared on resume, the descriptors become invalid
and cause a fatal bus error.

Link: https://lore.kernel.org/r/708edb92-a5df-ecc4-3126-5ab36707e275@nvidia.com/
Reported-by: Jonathan Hunter <jonathanh@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 84 +------------------
 1 file changed, 1 insertion(+), 83 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 208cae344ffa..4749bd0af160 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1379,88 +1379,6 @@ static void stmmac_free_tx_buffer(struct stmmac_priv *priv, u32 queue, int i)
 	}
 }
 
-/**
- * stmmac_reinit_rx_buffers - reinit the RX descriptor buffer.
- * @priv: driver private structure
- * Description: this function is called to re-allocate a receive buffer, perform
- * the DMA mapping and init the descriptor.
- */
-static void stmmac_reinit_rx_buffers(struct stmmac_priv *priv)
-{
-	u32 rx_count = priv->plat->rx_queues_to_use;
-	u32 queue;
-	int i;
-
-	for (queue = 0; queue < rx_count; queue++) {
-		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
-
-		for (i = 0; i < priv->dma_rx_size; i++) {
-			struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
-
-			if (buf->page) {
-				page_pool_recycle_direct(rx_q->page_pool, buf->page);
-				buf->page = NULL;
-			}
-
-			if (priv->sph && buf->sec_page) {
-				page_pool_recycle_direct(rx_q->page_pool, buf->sec_page);
-				buf->sec_page = NULL;
-			}
-		}
-	}
-
-	for (queue = 0; queue < rx_count; queue++) {
-		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
-
-		for (i = 0; i < priv->dma_rx_size; i++) {
-			struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
-			struct dma_desc *p;
-
-			if (priv->extend_desc)
-				p = &((rx_q->dma_erx + i)->basic);
-			else
-				p = rx_q->dma_rx + i;
-
-			if (!buf->page) {
-				buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
-				if (!buf->page)
-					goto err_reinit_rx_buffers;
-
-				buf->addr = page_pool_get_dma_addr(buf->page);
-			}
-
-			if (priv->sph && !buf->sec_page) {
-				buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool);
-				if (!buf->sec_page)
-					goto err_reinit_rx_buffers;
-
-				buf->sec_addr = page_pool_get_dma_addr(buf->sec_page);
-			}
-
-			stmmac_set_desc_addr(priv, p, buf->addr);
-			if (priv->sph)
-				stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, true);
-			else
-				stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, false);
-			if (priv->dma_buf_sz == BUF_SIZE_16KiB)
-				stmmac_init_desc3(priv, p);
-		}
-	}
-
-	return;
-
-err_reinit_rx_buffers:
-	do {
-		while (--i >= 0)
-			stmmac_free_rx_buffer(priv, queue, i);
-
-		if (queue == 0)
-			break;
-
-		i = priv->dma_rx_size;
-	} while (queue-- > 0);
-}
-
 /**
  * init_dma_rx_desc_rings - init the RX descriptor rings
  * @dev: net device structure
@@ -5428,7 +5346,7 @@ int stmmac_resume(struct device *dev)
 	mutex_lock(&priv->lock);
 
 	stmmac_reset_queues_param(priv);
-	stmmac_reinit_rx_buffers(priv);
+
 	stmmac_free_tx_skbufs(priv);
 	stmmac_clear_descriptors(priv);
 

From 41bafb31dcd58d834bdffa5db703f94fd2cec727 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Mon, 12 Apr 2021 17:50:08 +0300
Subject: [PATCH 1779/1820] net/mlx5: Fix setting of devlink traps in switchdev
 mode

Prevent setting of devlink traps on the uplink while in switchdev mode.
In this mode, it is the SW switch responsibility to handle both packets
with a mismatch in destination MAC or VLAN ID. Therefore, there are no
flow steering tables to trap undesirable packets and driver crashes upon
setting a trap.

Fixes: 241dc159391f ("net/mlx5: Notify on trap action by blocking event")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index d7d8a68ef23d..d0f9d3cee97d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -246,6 +246,11 @@ static int mlx5_devlink_trap_action_set(struct devlink *devlink,
 	struct mlx5_devlink_trap *dl_trap;
 	int err = 0;
 
+	if (is_mdev_switchdev_mode(dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Devlink traps can't be set in switchdev mode");
+		return -EOPNOTSUPP;
+	}
+
 	dl_trap = mlx5_find_trap_by_id(dev, trap->id);
 	if (!dl_trap) {
 		mlx5_core_err(dev, "Devlink trap: Set action on invalid trap id 0x%x", trap->id);

From 7a320c9db3e73fb6c4f9a331087df9df18767221 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Sun, 11 Apr 2021 09:33:12 +0300
Subject: [PATCH 1780/1820] net/mlx5e: Fix setting of RS FEC mode

Change register setting from bit number to bit mask.

Fixes: b5ede32d3329 ("net/mlx5e: Add support for FEC modes based on 50G per lane links")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Eran Ben Elisha <eranbe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/port.c | 23 ++++---------------
 1 file changed, 4 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 308fd279669e..89510cac46c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -387,21 +387,6 @@ enum mlx5e_fec_supported_link_mode {
 			*_policy = MLX5_GET(pplm_reg, _buf, fec_override_admin_##link);	\
 	} while (0)
 
-#define MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(buf, policy, write, link)			\
-	do {										\
-		unsigned long policy_long;						\
-		u16 *__policy = &(policy);						\
-		bool _write = (write);							\
-											\
-		policy_long = *__policy;						\
-		if (_write && *__policy)						\
-			*__policy = find_first_bit(&policy_long,			\
-						   sizeof(policy_long) * BITS_PER_BYTE);\
-		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, *__policy, _write, link);		\
-		if (!_write && *__policy)						\
-			*__policy = 1 << *__policy;					\
-	} while (0)
-
 /* get/set FEC admin field for a given speed */
 static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write,
 				 enum mlx5e_fec_supported_link_mode link_mode)
@@ -423,16 +408,16 @@ static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write,
 		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 100g);
 		break;
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X:
-		MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 50g_1x);
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 50g_1x);
 		break;
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_100G_2X:
-		MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 100g_2x);
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 100g_2x);
 		break;
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_4X:
-		MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 200g_4x);
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 200g_4x);
 		break;
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_8X:
-		MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 400g_8x);
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 400g_8x);
 		break;
 	default:
 		return -EINVAL;

From e3e0f9b279705154b951d579dc3d8b7041710e24 Mon Sep 17 00:00:00 2001
From: wenxu <wenxu@ucloud.cn>
Date: Fri, 9 Apr 2021 13:33:48 +0800
Subject: [PATCH 1781/1820] net/mlx5e: fix ingress_ifindex check in
 mlx5e_flower_parse_meta

In the nft_offload there is the mate flow_dissector with no
ingress_ifindex but with ingress_iftype that only be used
in the software. So if the mask of ingress_ifindex in meta is
0, this meta check should be bypass.

Fixes: 6d65bc64e232 ("net/mlx5e: Add mlx5e_flower_parse_meta support")
Signed-off-by: wenxu <wenxu@ucloud.cn>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index df2a0af854bb..d675107d9eca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1895,6 +1895,9 @@ static int mlx5e_flower_parse_meta(struct net_device *filter_dev,
 		return 0;
 
 	flow_rule_match_meta(rule, &match);
+	if (!match.mask->ingress_ifindex)
+		return 0;
+
 	if (match.mask->ingress_ifindex != 0xFFFFFFFF) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported ingress ifindex mask");
 		return -EOPNOTSUPP;

From 22315a2296f4c251fa92aec45fbbae37e9301b6c Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 13 Apr 2021 17:08:04 -0700
Subject: [PATCH 1782/1820] arm64: alternatives: Move length validation in
 alternative_{insn, endif}

After commit 2decad92f473 ("arm64: mte: Ensure TIF_MTE_ASYNC_FAULT is
set atomically"), LLVM's integrated assembler fails to build entry.S:

<instantiation>:5:7: error: expected assembly-time absolute expression
 .org . - (664b-663b) + (662b-661b)
      ^
<instantiation>:6:7: error: expected assembly-time absolute expression
 .org . - (662b-661b) + (664b-663b)
      ^

The root cause is LLVM's assembler has a one-pass design, meaning it
cannot figure out these instruction lengths when the .org directive is
outside of the subsection that they are in, which was changed by the
.arch_extension directive added in the above commit.

Apply the same fix from commit 966a0acce2fc ("arm64/alternatives: move
length validation inside the subsection") to the alternative_endif
macro, shuffling the .org directives so that the length validation
happen will always happen in the same subsections. alternative_insn has
not shown any issue yet but it appears that it could have the same issue
in the future so just preemptively change it.

Fixes: f7b93d42945c ("arm64/alternatives: use subsections for replacement sequences")
Cc: <stable@vger.kernel.org> # 5.8.x
Link: https://github.com/ClangBuiltLinux/linux/issues/1347
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lore.kernel.org/r/20210414000803.662534-1-nathan@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/alternative-macros.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
index 5df500dcc627..8a078fc662ac 100644
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -97,9 +97,9 @@
 	.popsection
 	.subsection 1
 663:	\insn2
-664:	.previous
-	.org	. - (664b-663b) + (662b-661b)
+664:	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
+	.previous
 	.endif
 .endm
 
@@ -169,11 +169,11 @@
  */
 .macro alternative_endif
 664:
+	.org	. - (664b-663b) + (662b-661b)
+	.org	. - (662b-661b) + (664b-663b)
 	.if .Lasm_alt_mode==0
 	.previous
 	.endif
-	.org	. - (664b-663b) + (662b-661b)
-	.org	. - (662b-661b) + (664b-663b)
 .endm
 
 /*

From 39930213e7779b9c4257499972b8afb8858f1a2d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Thu, 8 Apr 2021 04:00:00 +0200
Subject: [PATCH 1783/1820] i2c: mv64xxx: Fix random system lock caused by
 runtime PM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I noticed a weird bug with this driver on Marvell CN9130 Customer
Reference Board.

Sometime after boot, the system locks with the following message:
 [104.071363] i2c i2c-0: mv64xxx: I2C bus locked, block: 1, time_left: 0

The system does not respond afterwards, only warns about RCU stalls.

This first appeared with commit e5c02cf54154 ("i2c: mv64xxx: Add runtime
PM support").

With further experimentation I discovered that adding a delay into
mv64xxx_i2c_hw_init() fixes this issue. This function is called before
every xfer, due to how runtime PM works in this driver. It seems that in
order to work correctly, a delay is needed after the bus is reset in
this function.

Since there already is a known erratum with this controller needing a
delay, I assume that this is just another place this needs to be
applied. Therefore I apply the delay only if errata_delay is true.

Signed-off-by: Marek Behún <kabel@kernel.org>
Acked-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Reviewed-by: Samuel Holland <samuel@sholland.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/busses/i2c-mv64xxx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c
index c590d36b5fd1..5c8e94b6cdb5 100644
--- a/drivers/i2c/busses/i2c-mv64xxx.c
+++ b/drivers/i2c/busses/i2c-mv64xxx.c
@@ -221,6 +221,10 @@ mv64xxx_i2c_hw_init(struct mv64xxx_i2c_data *drv_data)
 	writel(0, drv_data->reg_base + drv_data->reg_offsets.ext_addr);
 	writel(MV64XXX_I2C_REG_CONTROL_TWSIEN | MV64XXX_I2C_REG_CONTROL_STOP,
 		drv_data->reg_base + drv_data->reg_offsets.control);
+
+	if (drv_data->errata_delay)
+		udelay(5);
+
 	drv_data->state = MV64XXX_I2C_STATE_IDLE;
 }
 

From 4e39a072a6a0fc422ba7da5e4336bdc295d70211 Mon Sep 17 00:00:00 2001
From: Jason Xing <xingwanli@kuaishou.com>
Date: Wed, 14 Apr 2021 10:34:28 +0800
Subject: [PATCH 1784/1820] i40e: fix the panic when running bpf in xdpdrv mode

Fix this panic by adding more rules to calculate the value of @rss_size_max
which could be used in allocating the queues when bpf is loaded, which,
however, could cause the failure and then trigger the NULL pointer of
vsi->rx_rings. Prio to this fix, the machine doesn't care about how many
cpus are online and then allocates 256 queues on the machine with 32 cpus
online actually.

Once the load of bpf begins, the log will go like this "failed to get
tracking for 256 queues for VSI 0 err -12" and this "setup of MAIN VSI
failed".

Thus, I attach the key information of the crash-log here.

BUG: unable to handle kernel NULL pointer dereference at
0000000000000000
RIP: 0010:i40e_xdp+0xdd/0x1b0 [i40e]
Call Trace:
[2160294.717292]  ? i40e_reconfig_rss_queues+0x170/0x170 [i40e]
[2160294.717666]  dev_xdp_install+0x4f/0x70
[2160294.718036]  dev_change_xdp_fd+0x11f/0x230
[2160294.718380]  ? dev_disable_lro+0xe0/0xe0
[2160294.718705]  do_setlink+0xac7/0xe70
[2160294.719035]  ? __nla_parse+0xed/0x120
[2160294.719365]  rtnl_newlink+0x73b/0x860

Fixes: 41c445ff0f48 ("i40e: main driver core")
Co-developed-by: Shujin Li <lishujin@kuaishou.com>
Signed-off-by: Shujin Li <lishujin@kuaishou.com>
Signed-off-by: Jason Xing <xingwanli@kuaishou.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 30ad7c08d0fb..527023ee4c07 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -12357,6 +12357,7 @@ static int i40e_sw_init(struct i40e_pf *pf)
 {
 	int err = 0;
 	int size;
+	u16 pow;
 
 	/* Set default capability flags */
 	pf->flags = I40E_FLAG_RX_CSUM_ENABLED |
@@ -12375,6 +12376,11 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	pf->rss_table_size = pf->hw.func_caps.rss_table_size;
 	pf->rss_size_max = min_t(int, pf->rss_size_max,
 				 pf->hw.func_caps.num_tx_qp);
+
+	/* find the next higher power-of-2 of num cpus */
+	pow = roundup_pow_of_two(num_online_cpus());
+	pf->rss_size_max = min_t(int, pf->rss_size_max, pow);
+
 	if (pf->hw.func_caps.rss) {
 		pf->flags |= I40E_FLAG_RSS_ENABLED;
 		pf->alloc_rss_size = min_t(int, pf->rss_size_max,

From 1a73e427b824133940c2dd95ebe26b6dce1cbf10 Mon Sep 17 00:00:00 2001
From: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Date: Thu, 15 Apr 2021 13:17:45 +0530
Subject: [PATCH 1785/1820] ch_ktls: Fix kernel panic

Taking page refcount is not ideal and causes kernel panic
sometimes. It's better to take tx_ctx lock for the complete
skb transmit, to avoid page cleanup if ACK received in middle.

Fixes: 5a4b9fe7fece ("cxgb4/chcr: complete record tx handling")
Signed-off-by: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Signed-off-by: Rohit Maheshwari <rohitm@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../chelsio/inline_crypto/ch_ktls/chcr_ktls.c | 24 ++++---------------
 1 file changed, 5 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index 1115b8f9ea4e..e39fa0940367 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -2010,12 +2010,11 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * we will send the complete record again.
 	 */
 
+	spin_lock_irqsave(&tx_ctx->base.lock, flags);
+
 	do {
-		int i;
 
 		cxgb4_reclaim_completed_tx(adap, &q->q, true);
-		/* lock taken */
-		spin_lock_irqsave(&tx_ctx->base.lock, flags);
 		/* fetch the tls record */
 		record = tls_get_record(&tx_ctx->base, tcp_seq,
 					&tx_info->record_no);
@@ -2074,11 +2073,11 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 						    tls_end_offset, skb_offset,
 						    0);
 
-			spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
 			if (ret) {
 				/* free the refcount taken earlier */
 				if (tls_end_offset < data_len)
 					dev_kfree_skb_any(skb);
+				spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
 				goto out;
 			}
 
@@ -2088,16 +2087,6 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 			continue;
 		}
 
-		/* increase page reference count of the record, so that there
-		 * won't be any chance of page free in middle if in case stack
-		 * receives ACK and try to delete the record.
-		 */
-		for (i = 0; i < record->num_frags; i++)
-			__skb_frag_ref(&record->frags[i]);
-		/* lock cleared */
-		spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
-
-
 		/* if a tls record is finishing in this SKB */
 		if (tls_end_offset <= data_len) {
 			ret = chcr_end_part_handler(tx_info, skb, record,
@@ -2122,13 +2111,9 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 			data_len = 0;
 		}
 
-		/* clear the frag ref count which increased locally before */
-		for (i = 0; i < record->num_frags; i++) {
-			/* clear the frag ref count */
-			__skb_frag_unref(&record->frags[i]);
-		}
 		/* if any failure, come out from the loop. */
 		if (ret) {
+			spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
 			if (th->fin)
 				dev_kfree_skb_any(skb);
 
@@ -2143,6 +2128,7 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	} while (data_len > 0);
 
+	spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
 	atomic64_inc(&port_stats->ktls_tx_encrypted_packets);
 	atomic64_add(skb_data_len, &port_stats->ktls_tx_encrypted_bytes);
 

From bc16efd2430652f894ae34b1de5eccc3bf0d2810 Mon Sep 17 00:00:00 2001
From: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Date: Thu, 15 Apr 2021 13:17:46 +0530
Subject: [PATCH 1786/1820] ch_ktls: fix device connection close

When sge queue is full and chcr_ktls_xmit_wr_complete()
returns failure, skb is not freed if it is not the last tls record in
this skb, causes refcount never gets freed and tls_dev_del()
never gets called on this connection.

Fixes: 5a4b9fe7fece ("cxgb4/chcr: complete record tx handling")
Signed-off-by: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Signed-off-by: Rohit Maheshwari <rohitm@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c  | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index e39fa0940367..a626560f8365 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -1735,7 +1735,9 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info,
 				 struct sge_eth_txq *q, u32 skb_offset,
 				 u32 tls_end_offset, bool last_wr)
 {
+	bool free_skb_if_tx_fails = false;
 	struct sk_buff *nskb = NULL;
+
 	/* check if it is a complete record */
 	if (tls_end_offset == record->len) {
 		nskb = skb;
@@ -1758,6 +1760,8 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info,
 
 		if (last_wr)
 			dev_kfree_skb_any(skb);
+		else
+			free_skb_if_tx_fails = true;
 
 		last_wr = true;
 
@@ -1769,6 +1773,8 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info,
 				       record->num_frags,
 				       (last_wr && tcp_push_no_fin),
 				       mss)) {
+		if (free_skb_if_tx_fails)
+			dev_kfree_skb_any(skb);
 		goto out;
 	}
 	tx_info->prev_seq = record->end_seq;

From 21d8c25e3f4b9052a471ced8f47b531956eb9963 Mon Sep 17 00:00:00 2001
From: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Date: Thu, 15 Apr 2021 13:17:47 +0530
Subject: [PATCH 1787/1820] ch_ktls: tcb close causes tls connection failure

HW doesn't need marking TCB closed. This TCB state change
sometimes causes problem to the new connection which gets
the same tid.

Fixes: 34aba2c45024 ("cxgb4/chcr : Register to tls add and del callback")
Signed-off-by: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Signed-off-by: Rohit Maheshwari <rohitm@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../chelsio/inline_crypto/ch_ktls/chcr_ktls.c | 19 -------------------
 1 file changed, 19 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index a626560f8365..8559eec161f0 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -349,18 +349,6 @@ static int chcr_set_tcb_field(struct chcr_ktls_info *tx_info, u16 word,
 	return cxgb4_ofld_send(tx_info->netdev, skb);
 }
 
-/*
- * chcr_ktls_mark_tcb_close: mark tcb state to CLOSE
- * @tx_info - driver specific tls info.
- * return: NET_TX_OK/NET_XMIT_DROP.
- */
-static int chcr_ktls_mark_tcb_close(struct chcr_ktls_info *tx_info)
-{
-	return chcr_set_tcb_field(tx_info, TCB_T_STATE_W,
-				  TCB_T_STATE_V(TCB_T_STATE_M),
-				  CHCR_TCB_STATE_CLOSED, 1);
-}
-
 /*
  * chcr_ktls_dev_del:  call back for tls_dev_del.
  * Remove the tid and l2t entry and close the connection.
@@ -395,8 +383,6 @@ static void chcr_ktls_dev_del(struct net_device *netdev,
 
 	/* clear tid */
 	if (tx_info->tid != -1) {
-		/* clear tcb state and then release tid */
-		chcr_ktls_mark_tcb_close(tx_info);
 		cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan,
 				 tx_info->tid, tx_info->ip_family);
 	}
@@ -574,7 +560,6 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
 	return 0;
 
 free_tid:
-	chcr_ktls_mark_tcb_close(tx_info);
 #if IS_ENABLED(CONFIG_IPV6)
 	/* clear clip entry */
 	if (tx_info->ip_family == AF_INET6)
@@ -672,10 +657,6 @@ static int chcr_ktls_cpl_act_open_rpl(struct adapter *adap,
 	if (tx_info->pending_close) {
 		spin_unlock(&tx_info->lock);
 		if (!status) {
-			/* it's a late success, tcb status is established,
-			 * mark it close.
-			 */
-			chcr_ktls_mark_tcb_close(tx_info);
 			cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan,
 					 tid, tx_info->ip_family);
 		}

From e8a4155567b3c903f49cbf89b8017e9cc22c4fe4 Mon Sep 17 00:00:00 2001
From: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Date: Thu, 15 Apr 2021 13:17:48 +0530
Subject: [PATCH 1788/1820] ch_ktls: do not send snd_una update to TCB in
 middle

snd_una update should not be done when the same skb is being
sent out.chcr_short_record_handler() sends it again even
though SND_UNA update is already sent for the skb in
chcr_ktls_xmit(), which causes mismatch in un-acked
TCP seq number, later causes problem in sending out
complete record.

Fixes: 429765a149f1 ("chcr: handle partial end part of a record")
Signed-off-by: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Signed-off-by: Rohit Maheshwari <rohitm@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../chelsio/inline_crypto/ch_ktls/chcr_ktls.c | 53 -------------------
 1 file changed, 53 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index 8559eec161f0..a3f5b80888e5 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -1644,54 +1644,6 @@ static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb,
 	refcount_add(nskb->truesize, &nskb->sk->sk_wmem_alloc);
 }
 
-/*
- * chcr_ktls_update_snd_una:  Reset the SEND_UNA. It will be done to avoid
- * sending the same segment again. It will discard the segment which is before
- * the current tx max.
- * @tx_info - driver specific tls info.
- * @q - TX queue.
- * return: NET_TX_OK/NET_XMIT_DROP.
- */
-static int chcr_ktls_update_snd_una(struct chcr_ktls_info *tx_info,
-				    struct sge_eth_txq *q)
-{
-	struct fw_ulptx_wr *wr;
-	unsigned int ndesc;
-	int credits;
-	void *pos;
-	u32 len;
-
-	len = sizeof(*wr) + roundup(CHCR_SET_TCB_FIELD_LEN, 16);
-	ndesc = DIV_ROUND_UP(len, 64);
-
-	credits = chcr_txq_avail(&q->q) - ndesc;
-	if (unlikely(credits < 0)) {
-		chcr_eth_txq_stop(q);
-		return NETDEV_TX_BUSY;
-	}
-
-	pos = &q->q.desc[q->q.pidx];
-
-	wr = pos;
-	/* ULPTX wr */
-	wr->op_to_compl = htonl(FW_WR_OP_V(FW_ULPTX_WR));
-	wr->cookie = 0;
-	/* fill len in wr field */
-	wr->flowid_len16 = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(len, 16)));
-
-	pos += sizeof(*wr);
-
-	pos = chcr_write_cpl_set_tcb_ulp(tx_info, q, tx_info->tid, pos,
-					 TCB_SND_UNA_RAW_W,
-					 TCB_SND_UNA_RAW_V(TCB_SND_UNA_RAW_M),
-					 TCB_SND_UNA_RAW_V(0), 0);
-
-	chcr_txq_advance(&q->q, ndesc);
-	cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc);
-
-	return 0;
-}
-
 /*
  * chcr_end_part_handler: This handler will handle the record which
  * is complete or if record's end part is received. T6 adapter has a issue that
@@ -1892,11 +1844,6 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info,
 			/* reset tcp_seq as per the prior_data_required len */
 			tcp_seq -= prior_data_len;
 		}
-		/* reset snd una, so the middle record won't send the already
-		 * sent part.
-		 */
-		if (chcr_ktls_update_snd_una(tx_info, q))
-			goto out;
 		atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_middle_pkts);
 	} else {
 		atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_start_pkts);

From b21bb4cd1102dd9e24a169d09cf4e6f3c8a46bcf Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben.widawsky@intel.com>
Date: Thu, 15 Apr 2021 16:26:08 -0700
Subject: [PATCH 1789/1820] cxl/mem: Fix register block offset calculation

The "Register Offset Low" register of a "DVSEC Register Locator"
contains the 64K aligned offset for the registers along with the BAR
indicator and an id. The implementation was treating the "Register Block
Offset Low" field a value rather than as a pre-aligned component of the
64-bit offset. So, just mask, don't mask and shift (FIELD_GET).

The user visible result of this bug is that the driver fails to bind to
the device after none of the required blocks are found.

This was missed earlier because the primary development done in the QEMU
environment only uses 0 offsets, i.e. 0 shifted is still 0.

Fixes: 8adaf747c9f0 ("cxl/mem: Find device capabilities")
Reported-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
Link: https://lore.kernel.org/r/20210415232610.603273-1-ben.widawsky@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/mem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index e3003f49b329..1b5078311f7d 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -998,7 +998,7 @@ static struct cxl_mem *cxl_mem_create(struct pci_dev *pdev, u32 reg_lo,
 		return NULL;
 	}
 
-	offset = ((u64)reg_hi << 32) | FIELD_GET(CXL_REGLOC_ADDR_MASK, reg_lo);
+	offset = ((u64)reg_hi << 32) | (reg_lo & CXL_REGLOC_ADDR_MASK);
 	bar = FIELD_GET(CXL_REGLOC_BIR_MASK, reg_lo);
 
 	/* Basic sanity check that BAR is big enough */

From 199fc6b8dee7d6d50467a57e0dc7e3e1b7d59966 Mon Sep 17 00:00:00 2001
From: Kefeng Wang <wangkefeng.wang@huawei.com>
Date: Mon, 29 Mar 2021 11:13:07 +0800
Subject: [PATCH 1790/1820] riscv: Fix spelling mistake "SPARSEMEM" to
 "SPARSMEM"

There is a spelling mistake when SPARSEMEM Kconfig copy.

Fixes: a5406a7ff56e ("riscv: Correct SPARSEMEM configuration")
Cc: stable@vger.kernel.org
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 0d0cf67359cb..4515a10c5d22 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -153,7 +153,7 @@ config ARCH_FLATMEM_ENABLE
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
 	depends on MMU
-	select SPARSEMEM_STATIC if 32BIT && SPARSMEM
+	select SPARSEMEM_STATIC if 32BIT && SPARSEMEM
 	select SPARSEMEM_VMEMMAP_ENABLE if 64BIT
 
 config ARCH_SELECT_MEMORY_MODEL

From 2349a3b26e29b8d860466bafda2e02b4b87a9e40 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Tue, 30 Mar 2021 02:12:26 +0800
Subject: [PATCH 1791/1820] riscv: add do_page_fault and do_trap_break into the
 kprobes blacklist

These two functions are used to implement the kprobes feature so they
can't be kprobed.

Fixes: c22b0bcb1dd0 ("riscv: Add kprobes supported")
Cc: stable@vger.kernel.org
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/kernel/traps.c | 1 +
 arch/riscv/mm/fault.c     | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 0879b5df11b9..1357abf79570 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -178,6 +178,7 @@ asmlinkage __visible void do_trap_break(struct pt_regs *regs)
 	else
 		die(regs, "Kernel BUG");
 }
+NOKPROBE_SYMBOL(do_trap_break);
 
 #ifdef CONFIG_GENERIC_BUG
 int is_valid_bugaddr(unsigned long pc)
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 8f17519208c7..c5dbd55cbf7c 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -328,3 +328,4 @@ good_area:
 	}
 	return;
 }
+NOKPROBE_SYMBOL(do_page_fault);

From e31be8d343e64e7ab17aef55c1d1b36dc504da67 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Tue, 30 Mar 2021 02:14:40 +0800
Subject: [PATCH 1792/1820] riscv: kprobes/ftrace: Add recursion protection to
 the ftrace callback

Currently, the riscv's kprobes(powerred by ftrace) handler is
preemptible. Futher check indicates we miss something similar as the
commit c536aa1c5b17 ("kprobes/ftrace: Add recursion protection to the
ftrace callback"), so do similar modifications as the commit does.

Fixes: 829adda597fe ("riscv: Add KPROBES_ON_FTRACE supported")
Cc: stable@vger.kernel.org
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/kernel/probes/ftrace.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c
index 17ca5e923bb0..aab85a82f419 100644
--- a/arch/riscv/kernel/probes/ftrace.c
+++ b/arch/riscv/kernel/probes/ftrace.c
@@ -9,10 +9,16 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	struct kprobe *p;
 	struct pt_regs *regs;
 	struct kprobe_ctlblk *kcb;
+	int bit;
 
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
+	if (bit < 0)
+		return;
+
+	preempt_disable_notrace();
 	p = get_kprobe((kprobe_opcode_t *)ip);
 	if (unlikely(!p) || kprobe_disabled(p))
-		return;
+		goto out;
 
 	regs = ftrace_get_regs(fregs);
 	kcb = get_kprobe_ctlblk();
@@ -45,6 +51,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 		 */
 		__this_cpu_write(current_kprobe, NULL);
 	}
+out:
+	preempt_enable_notrace();
+	ftrace_test_recursion_unlock(bit);
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
 

From 7ae11635ec90072083503c6b6485cdffe46203b3 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Tue, 30 Mar 2021 02:16:24 +0800
Subject: [PATCH 1793/1820] riscv: keep interrupts disabled for BREAKPOINT
 exception

Current riscv's kprobe handlers are run with both preemption and
interrupt enabled, this violates kprobe requirements. Fix this issue
by keeping interrupts disabled for BREAKPOINT exception.

Fixes: c22b0bcb1dd0 ("riscv: Add kprobes supported")
Cc: stable@vger.kernel.org
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
[Palmer: add a comment]
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 arch/riscv/kernel/entry.S | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 76274a4a1d8e..83095faa680e 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -130,6 +130,9 @@ skip_context_tracking:
 	 */
 	andi t0, s1, SR_PIE
 	beqz t0, 1f
+	/* kprobes, entered via ebreak, must have interrupts disabled. */
+	li t0, EXC_BREAKPOINT
+	beq s4, t0, 1f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	call trace_hardirqs_on
 #endif

From 9601148392520e2e134936e76788fc2a6371e7be Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 23 Mar 2021 08:32:59 +0100
Subject: [PATCH 1794/1820] bpf: Use correct permission flag for mixed signed
 bounds arithmetic

We forbid adding unknown scalars with mixed signed bounds due to the
spectre v1 masking mitigation. Hence this also needs bypass_spec_v1
flag instead of allow_ptr_leaks.

Fixes: 2c78ee898d8f ("bpf: Implement CAP_BPF")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3a738724a380..2ede4b850230 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6085,7 +6085,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 			dst, reg_type_str[ptr_reg->type]);
 		return -EACCES;
 	case PTR_TO_MAP_VALUE:
-		if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) {
+		if (!env->env->bypass_spec_v1 && !known && (smin_val < 0) != (smax_val < 0)) {
 			verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n",
 				off_reg == dst_reg ? dst : src);
 			return -EACCES;

From 6f55b2f2a1178856c19bbce2f71449926e731914 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 22 Mar 2021 15:45:52 +0100
Subject: [PATCH 1795/1820] bpf: Move off_reg into sanitize_ptr_alu

Small refactor to drag off_reg into sanitize_ptr_alu(), so we later on can
use off_reg for generalizing some of the checks for all pointer types.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2ede4b850230..4ee014dadac7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5929,11 +5929,12 @@ static int sanitize_val_alu(struct bpf_verifier_env *env,
 static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 			    struct bpf_insn *insn,
 			    const struct bpf_reg_state *ptr_reg,
-			    struct bpf_reg_state *dst_reg,
-			    bool off_is_neg)
+			    const struct bpf_reg_state *off_reg,
+			    struct bpf_reg_state *dst_reg)
 {
 	struct bpf_verifier_state *vstate = env->cur_state;
 	struct bpf_insn_aux_data *aux = cur_aux(env);
+	bool off_is_neg = off_reg->smin_value < 0;
 	bool ptr_is_dst_reg = ptr_reg == dst_reg;
 	u8 opcode = BPF_OP(insn->code);
 	u32 alu_state, alu_limit;
@@ -6110,7 +6111,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 
 	switch (opcode) {
 	case BPF_ADD:
-		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
+		ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg);
 		if (ret < 0) {
 			verbose(env, "R%d tried to add from different maps, paths, or prohibited types\n", dst);
 			return ret;
@@ -6165,7 +6166,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		}
 		break;
 	case BPF_SUB:
-		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
+		ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg);
 		if (ret < 0) {
 			verbose(env, "R%d tried to sub from different maps, paths, or prohibited types\n", dst);
 			return ret;

From 24c109bb1537c12c02aeed2d51a347b4d6a9b76e Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 23 Mar 2021 08:51:02 +0100
Subject: [PATCH 1796/1820] bpf: Ensure off_reg has no mixed signed bounds for
 all types

The mixed signed bounds check really belongs into retrieve_ptr_limit()
instead of outside of it in adjust_ptr_min_max_vals(). The reason is
that this check is not tied to PTR_TO_MAP_VALUE only, but to all pointer
types that we handle in retrieve_ptr_limit() and given errors from the latter
propagate back to adjust_ptr_min_max_vals() and lead to rejection of the
program, it's a better place to reside to avoid anything slipping through
for future types. The reason why we must reject such off_reg is that we
otherwise would not be able to derive a mask, see details in 9d7eceede769
("bpf: restrict unknown scalars of mixed signed bounds for unprivileged").

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4ee014dadac7..a21d7f1a0ba8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5857,12 +5857,18 @@ static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
 }
 
 static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
-			      u32 *ptr_limit, u8 opcode, bool off_is_neg)
+			      const struct bpf_reg_state *off_reg,
+			      u32 *ptr_limit, u8 opcode)
 {
+	bool off_is_neg = off_reg->smin_value < 0;
 	bool mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
 			    (opcode == BPF_SUB && !off_is_neg);
 	u32 off, max;
 
+	if (!tnum_is_const(off_reg->var_off) &&
+	    (off_reg->smin_value < 0) != (off_reg->smax_value < 0))
+		return -EACCES;
+
 	switch (ptr_reg->type) {
 	case PTR_TO_STACK:
 		/* Offset 0 is out-of-bounds, but acceptable start for the
@@ -5956,7 +5962,7 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 	alu_state |= ptr_is_dst_reg ?
 		     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
 
-	err = retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg);
+	err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode);
 	if (err < 0)
 		return err;
 
@@ -6036,8 +6042,8 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	    smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
 	u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
 	    umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
-	u32 dst = insn->dst_reg, src = insn->src_reg;
 	u8 opcode = BPF_OP(insn->code);
+	u32 dst = insn->dst_reg;
 	int ret;
 
 	dst_reg = &regs[dst];
@@ -6085,13 +6091,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		verbose(env, "R%d pointer arithmetic on %s prohibited\n",
 			dst, reg_type_str[ptr_reg->type]);
 		return -EACCES;
-	case PTR_TO_MAP_VALUE:
-		if (!env->env->bypass_spec_v1 && !known && (smin_val < 0) != (smax_val < 0)) {
-			verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n",
-				off_reg == dst_reg ? dst : src);
-			return -EACCES;
-		}
-		fallthrough;
 	default:
 		break;
 	}

From b658bbb844e28f1862867f37e8ca11a8e2aa94a3 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 23 Mar 2021 09:04:10 +0100
Subject: [PATCH 1797/1820] bpf: Rework ptr_limit into alu_limit and add common
 error path

Small refactor with no semantic changes in order to consolidate the max
ptr_limit boundary check.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a21d7f1a0ba8..b8e0171d9591 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5858,12 +5858,12 @@ static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
 
 static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 			      const struct bpf_reg_state *off_reg,
-			      u32 *ptr_limit, u8 opcode)
+			      u32 *alu_limit, u8 opcode)
 {
 	bool off_is_neg = off_reg->smin_value < 0;
 	bool mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
 			    (opcode == BPF_SUB && !off_is_neg);
-	u32 off, max;
+	u32 off, max = 0, ptr_limit = 0;
 
 	if (!tnum_is_const(off_reg->var_off) &&
 	    (off_reg->smin_value < 0) != (off_reg->smax_value < 0))
@@ -5880,22 +5880,27 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 		 */
 		off = ptr_reg->off + ptr_reg->var_off.value;
 		if (mask_to_left)
-			*ptr_limit = MAX_BPF_STACK + off;
+			ptr_limit = MAX_BPF_STACK + off;
 		else
-			*ptr_limit = -off - 1;
-		return *ptr_limit >= max ? -ERANGE : 0;
+			ptr_limit = -off - 1;
+		break;
 	case PTR_TO_MAP_VALUE:
 		max = ptr_reg->map_ptr->value_size;
 		if (mask_to_left) {
-			*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
+			ptr_limit = ptr_reg->umax_value + ptr_reg->off;
 		} else {
 			off = ptr_reg->smin_value + ptr_reg->off;
-			*ptr_limit = ptr_reg->map_ptr->value_size - off - 1;
+			ptr_limit = ptr_reg->map_ptr->value_size - off - 1;
 		}
-		return *ptr_limit >= max ? -ERANGE : 0;
+		break;
 	default:
 		return -EINVAL;
 	}
+
+	if (ptr_limit >= max)
+		return -ERANGE;
+	*alu_limit = ptr_limit;
+	return 0;
 }
 
 static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,

From a6aaece00a57fa6f22575364b3903dfbccf5345d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 23 Mar 2021 09:30:01 +0100
Subject: [PATCH 1798/1820] bpf: Improve verifier error messages for users

Consolidate all error handling and provide more user-friendly error messages
from sanitize_ptr_alu() and sanitize_val_alu().

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 86 +++++++++++++++++++++++++++++++------------
 1 file changed, 63 insertions(+), 23 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b8e0171d9591..f378d4ae405f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5856,6 +5856,14 @@ static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
 	return &env->insn_aux_data[env->insn_idx];
 }
 
+enum {
+	REASON_BOUNDS	= -1,
+	REASON_TYPE	= -2,
+	REASON_PATHS	= -3,
+	REASON_LIMIT	= -4,
+	REASON_STACK	= -5,
+};
+
 static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 			      const struct bpf_reg_state *off_reg,
 			      u32 *alu_limit, u8 opcode)
@@ -5867,7 +5875,7 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 
 	if (!tnum_is_const(off_reg->var_off) &&
 	    (off_reg->smin_value < 0) != (off_reg->smax_value < 0))
-		return -EACCES;
+		return REASON_BOUNDS;
 
 	switch (ptr_reg->type) {
 	case PTR_TO_STACK:
@@ -5894,11 +5902,11 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 		}
 		break;
 	default:
-		return -EINVAL;
+		return REASON_TYPE;
 	}
 
 	if (ptr_limit >= max)
-		return -ERANGE;
+		return REASON_LIMIT;
 	*alu_limit = ptr_limit;
 	return 0;
 }
@@ -5918,7 +5926,7 @@ static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
 	if (aux->alu_state &&
 	    (aux->alu_state != alu_state ||
 	     aux->alu_limit != alu_limit))
-		return -EACCES;
+		return REASON_PATHS;
 
 	/* Corresponding fixup done in fixup_bpf_calls(). */
 	aux->alu_state = alu_state;
@@ -5991,7 +5999,46 @@ do_sim:
 	ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
 	if (!ptr_is_dst_reg && ret)
 		*dst_reg = tmp;
-	return !ret ? -EFAULT : 0;
+	return !ret ? REASON_STACK : 0;
+}
+
+static int sanitize_err(struct bpf_verifier_env *env,
+			const struct bpf_insn *insn, int reason,
+			const struct bpf_reg_state *off_reg,
+			const struct bpf_reg_state *dst_reg)
+{
+	static const char *err = "pointer arithmetic with it prohibited for !root";
+	const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub";
+	u32 dst = insn->dst_reg, src = insn->src_reg;
+
+	switch (reason) {
+	case REASON_BOUNDS:
+		verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n",
+			off_reg == dst_reg ? dst : src, err);
+		break;
+	case REASON_TYPE:
+		verbose(env, "R%d has pointer with unsupported alu operation, %s\n",
+			off_reg == dst_reg ? src : dst, err);
+		break;
+	case REASON_PATHS:
+		verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n",
+			dst, op, err);
+		break;
+	case REASON_LIMIT:
+		verbose(env, "R%d tried to %s beyond pointer bounds, %s\n",
+			dst, op, err);
+		break;
+	case REASON_STACK:
+		verbose(env, "R%d could not be pushed for speculative verification, %s\n",
+			dst, err);
+		break;
+	default:
+		verbose(env, "verifier internal error: unknown reason (%d)\n",
+			reason);
+		break;
+	}
+
+	return -EACCES;
 }
 
 /* check that stack access falls within stack limits and that 'reg' doesn't
@@ -6116,10 +6163,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	switch (opcode) {
 	case BPF_ADD:
 		ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg);
-		if (ret < 0) {
-			verbose(env, "R%d tried to add from different maps, paths, or prohibited types\n", dst);
-			return ret;
-		}
+		if (ret < 0)
+			return sanitize_err(env, insn, ret, off_reg, dst_reg);
+
 		/* We can take a fixed offset as long as it doesn't overflow
 		 * the s32 'off' field
 		 */
@@ -6171,10 +6217,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		break;
 	case BPF_SUB:
 		ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg);
-		if (ret < 0) {
-			verbose(env, "R%d tried to sub from different maps, paths, or prohibited types\n", dst);
-			return ret;
-		}
+		if (ret < 0)
+			return sanitize_err(env, insn, ret, off_reg, dst_reg);
+
 		if (dst_reg == off_reg) {
 			/* scalar -= pointer.  Creates an unknown scalar */
 			verbose(env, "R%d tried to subtract pointer from scalar\n",
@@ -6863,9 +6908,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 	s32 s32_min_val, s32_max_val;
 	u32 u32_min_val, u32_max_val;
 	u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
-	u32 dst = insn->dst_reg;
-	int ret;
 	bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
+	int ret;
 
 	smin_val = src_reg.smin_value;
 	smax_val = src_reg.smax_value;
@@ -6924,20 +6968,16 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 	switch (opcode) {
 	case BPF_ADD:
 		ret = sanitize_val_alu(env, insn);
-		if (ret < 0) {
-			verbose(env, "R%d tried to add from different pointers or scalars\n", dst);
-			return ret;
-		}
+		if (ret < 0)
+			return sanitize_err(env, insn, ret, NULL, NULL);
 		scalar32_min_max_add(dst_reg, &src_reg);
 		scalar_min_max_add(dst_reg, &src_reg);
 		dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
 		break;
 	case BPF_SUB:
 		ret = sanitize_val_alu(env, insn);
-		if (ret < 0) {
-			verbose(env, "R%d tried to sub from different pointers or scalars\n", dst);
-			return ret;
-		}
+		if (ret < 0)
+			return sanitize_err(env, insn, ret, NULL, NULL);
 		scalar32_min_max_sub(dst_reg, &src_reg);
 		scalar_min_max_sub(dst_reg, &src_reg);
 		dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);

From 073815b756c51ba9d8384d924c5d1c03ca3d1ae4 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 23 Mar 2021 15:05:48 +0100
Subject: [PATCH 1799/1820] bpf: Refactor and streamline bounds check into
 helper

Move the bounds check in adjust_ptr_min_max_vals() into a small helper named
sanitize_check_bounds() in order to simplify the former a bit.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 49 +++++++++++++++++++++++++++++--------------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f378d4ae405f..db77e2c670b9 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6075,6 +6075,37 @@ static int check_stack_access_for_ptr_arithmetic(
 	return 0;
 }
 
+static int sanitize_check_bounds(struct bpf_verifier_env *env,
+				 const struct bpf_insn *insn,
+				 const struct bpf_reg_state *dst_reg)
+{
+	u32 dst = insn->dst_reg;
+
+	/* For unprivileged we require that resulting offset must be in bounds
+	 * in order to be able to sanitize access later on.
+	 */
+	if (env->bypass_spec_v1)
+		return 0;
+
+	switch (dst_reg->type) {
+	case PTR_TO_STACK:
+		if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg,
+					dst_reg->off + dst_reg->var_off.value))
+			return -EACCES;
+		break;
+	case PTR_TO_MAP_VALUE:
+		if (check_map_access(env, dst, dst_reg->off, 1, false)) {
+			verbose(env, "R%d pointer arithmetic of map value goes out of range, "
+				"prohibited for !root\n", dst);
+			return -EACCES;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
 
 /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
  * Caller should also handle BPF_MOV case separately.
@@ -6300,22 +6331,8 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	__reg_deduce_bounds(dst_reg);
 	__reg_bound_offset(dst_reg);
 
-	/* For unprivileged we require that resulting offset must be in bounds
-	 * in order to be able to sanitize access later on.
-	 */
-	if (!env->bypass_spec_v1) {
-		if (dst_reg->type == PTR_TO_MAP_VALUE &&
-		    check_map_access(env, dst, dst_reg->off, 1, false)) {
-			verbose(env, "R%d pointer arithmetic of map value goes out of range, "
-				"prohibited for !root\n", dst);
-			return -EACCES;
-		} else if (dst_reg->type == PTR_TO_STACK &&
-			   check_stack_access_for_ptr_arithmetic(
-				   env, dst, dst_reg, dst_reg->off +
-				   dst_reg->var_off.value)) {
-			return -EACCES;
-		}
-	}
+	if (sanitize_check_bounds(env, insn, dst_reg) < 0)
+		return -EACCES;
 
 	return 0;
 }

From f528819334881fd622fdadeddb3f7edaed8b7c9b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 24 Mar 2021 11:25:39 +0100
Subject: [PATCH 1800/1820] bpf: Move sanitize_val_alu out of op switch

Add a small sanitize_needed() helper function and move sanitize_val_alu()
out of the main opcode switch. In upcoming work, we'll move sanitize_ptr_alu()
as well out of its opcode switch so this helps to streamline both.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index db77e2c670b9..e41b6326e3e6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5945,6 +5945,11 @@ static int sanitize_val_alu(struct bpf_verifier_env *env,
 	return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0);
 }
 
+static bool sanitize_needed(u8 opcode)
+{
+	return opcode == BPF_ADD || opcode == BPF_SUB;
+}
+
 static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 			    struct bpf_insn *insn,
 			    const struct bpf_reg_state *ptr_reg,
@@ -6968,6 +6973,12 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		return 0;
 	}
 
+	if (sanitize_needed(opcode)) {
+		ret = sanitize_val_alu(env, insn);
+		if (ret < 0)
+			return sanitize_err(env, insn, ret, NULL, NULL);
+	}
+
 	/* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops.
 	 * There are two classes of instructions: The first class we track both
 	 * alu32 and alu64 sign/unsigned bounds independently this provides the
@@ -6984,17 +6995,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 	 */
 	switch (opcode) {
 	case BPF_ADD:
-		ret = sanitize_val_alu(env, insn);
-		if (ret < 0)
-			return sanitize_err(env, insn, ret, NULL, NULL);
 		scalar32_min_max_add(dst_reg, &src_reg);
 		scalar_min_max_add(dst_reg, &src_reg);
 		dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
 		break;
 	case BPF_SUB:
-		ret = sanitize_val_alu(env, insn);
-		if (ret < 0)
-			return sanitize_err(env, insn, ret, NULL, NULL);
 		scalar32_min_max_sub(dst_reg, &src_reg);
 		scalar_min_max_sub(dst_reg, &src_reg);
 		dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);

From 7fedb63a8307dda0ec3b8969a3b233a1dd7ea8e0 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 24 Mar 2021 10:38:26 +0100
Subject: [PATCH 1801/1820] bpf: Tighten speculative pointer arithmetic mask

This work tightens the offset mask we use for unprivileged pointer arithmetic
in order to mitigate a corner case reported by Piotr and Benedict where in
the speculative domain it is possible to advance, for example, the map value
pointer by up to value_size-1 out-of-bounds in order to leak kernel memory
via side-channel to user space.

Before this change, the computed ptr_limit for retrieve_ptr_limit() helper
represents largest valid distance when moving pointer to the right or left
which is then fed as aux->alu_limit to generate masking instructions against
the offset register. After the change, the derived aux->alu_limit represents
the largest potential value of the offset register which we mask against which
is just a narrower subset of the former limit.

For minimal complexity, we call sanitize_ptr_alu() from 2 observation points
in adjust_ptr_min_max_vals(), that is, before and after the simulated alu
operation. In the first step, we retieve the alu_state and alu_limit before
the operation as well as we branch-off a verifier path and push it to the
verification stack as we did before which checks the dst_reg under truncation,
in other words, when the speculative domain would attempt to move the pointer
out-of-bounds.

In the second step, we retrieve the new alu_limit and calculate the absolute
distance between both. Moreover, we commit the alu_state and final alu_limit
via update_alu_sanitation_state() to the env's instruction aux data, and bail
out from there if there is a mismatch due to coming from different verification
paths with different states.

Reported-by: Piotr Krysiuk <piotras@gmail.com>
Reported-by: Benedict Schlueter <benedict.schlueter@rub.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Benedict Schlueter <benedict.schlueter@rub.de>
---
 kernel/bpf/verifier.c | 73 ++++++++++++++++++++++++++-----------------
 1 file changed, 44 insertions(+), 29 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e41b6326e3e6..0399ac092b36 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5871,7 +5871,7 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 	bool off_is_neg = off_reg->smin_value < 0;
 	bool mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
 			    (opcode == BPF_SUB && !off_is_neg);
-	u32 off, max = 0, ptr_limit = 0;
+	u32 max = 0, ptr_limit = 0;
 
 	if (!tnum_is_const(off_reg->var_off) &&
 	    (off_reg->smin_value < 0) != (off_reg->smax_value < 0))
@@ -5880,26 +5880,18 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 	switch (ptr_reg->type) {
 	case PTR_TO_STACK:
 		/* Offset 0 is out-of-bounds, but acceptable start for the
-		 * left direction, see BPF_REG_FP.
+		 * left direction, see BPF_REG_FP. Also, unknown scalar
+		 * offset where we would need to deal with min/max bounds is
+		 * currently prohibited for unprivileged.
 		 */
 		max = MAX_BPF_STACK + mask_to_left;
-		/* Indirect variable offset stack access is prohibited in
-		 * unprivileged mode so it's not handled here.
-		 */
-		off = ptr_reg->off + ptr_reg->var_off.value;
-		if (mask_to_left)
-			ptr_limit = MAX_BPF_STACK + off;
-		else
-			ptr_limit = -off - 1;
+		ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off);
 		break;
 	case PTR_TO_MAP_VALUE:
 		max = ptr_reg->map_ptr->value_size;
-		if (mask_to_left) {
-			ptr_limit = ptr_reg->umax_value + ptr_reg->off;
-		} else {
-			off = ptr_reg->smin_value + ptr_reg->off;
-			ptr_limit = ptr_reg->map_ptr->value_size - off - 1;
-		}
+		ptr_limit = (mask_to_left ?
+			     ptr_reg->smin_value :
+			     ptr_reg->umax_value) + ptr_reg->off;
 		break;
 	default:
 		return REASON_TYPE;
@@ -5954,10 +5946,12 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 			    struct bpf_insn *insn,
 			    const struct bpf_reg_state *ptr_reg,
 			    const struct bpf_reg_state *off_reg,
-			    struct bpf_reg_state *dst_reg)
+			    struct bpf_reg_state *dst_reg,
+			    struct bpf_insn_aux_data *tmp_aux,
+			    const bool commit_window)
 {
+	struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux;
 	struct bpf_verifier_state *vstate = env->cur_state;
-	struct bpf_insn_aux_data *aux = cur_aux(env);
 	bool off_is_neg = off_reg->smin_value < 0;
 	bool ptr_is_dst_reg = ptr_reg == dst_reg;
 	u8 opcode = BPF_OP(insn->code);
@@ -5976,18 +5970,33 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 	if (vstate->speculative)
 		goto do_sim;
 
-	alu_state  = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
-	alu_state |= ptr_is_dst_reg ?
-		     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
-
 	err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode);
 	if (err < 0)
 		return err;
 
+	if (commit_window) {
+		/* In commit phase we narrow the masking window based on
+		 * the observed pointer move after the simulated operation.
+		 */
+		alu_state = tmp_aux->alu_state;
+		alu_limit = abs(tmp_aux->alu_limit - alu_limit);
+	} else {
+		alu_state  = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
+		alu_state |= ptr_is_dst_reg ?
+			     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+	}
+
 	err = update_alu_sanitation_state(aux, alu_state, alu_limit);
 	if (err < 0)
 		return err;
 do_sim:
+	/* If we're in commit phase, we're done here given we already
+	 * pushed the truncated dst_reg into the speculative verification
+	 * stack.
+	 */
+	if (commit_window)
+		return 0;
+
 	/* Simulate and find potential out-of-bounds access under
 	 * speculative execution from truncation as a result of
 	 * masking when off was not within expected range. If off
@@ -6130,6 +6139,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	    smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
 	u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
 	    umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
+	struct bpf_insn_aux_data tmp_aux = {};
 	u8 opcode = BPF_OP(insn->code);
 	u32 dst = insn->dst_reg;
 	int ret;
@@ -6196,12 +6206,15 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	/* pointer types do not carry 32-bit bounds at the moment. */
 	__mark_reg32_unbounded(dst_reg);
 
-	switch (opcode) {
-	case BPF_ADD:
-		ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg);
+	if (sanitize_needed(opcode)) {
+		ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg,
+				       &tmp_aux, false);
 		if (ret < 0)
 			return sanitize_err(env, insn, ret, off_reg, dst_reg);
+	}
 
+	switch (opcode) {
+	case BPF_ADD:
 		/* We can take a fixed offset as long as it doesn't overflow
 		 * the s32 'off' field
 		 */
@@ -6252,10 +6265,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		}
 		break;
 	case BPF_SUB:
-		ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg);
-		if (ret < 0)
-			return sanitize_err(env, insn, ret, off_reg, dst_reg);
-
 		if (dst_reg == off_reg) {
 			/* scalar -= pointer.  Creates an unknown scalar */
 			verbose(env, "R%d tried to subtract pointer from scalar\n",
@@ -6338,6 +6347,12 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 
 	if (sanitize_check_bounds(env, insn, dst_reg) < 0)
 		return -EACCES;
+	if (sanitize_needed(opcode)) {
+		ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg,
+				       &tmp_aux, true);
+		if (ret < 0)
+			return sanitize_err(env, insn, ret, off_reg, dst_reg);
+	}
 
 	return 0;
 }

From d7a5091351756d0ae8e63134313c455624e36a13 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 24 Mar 2021 14:52:31 +0100
Subject: [PATCH 1802/1820] bpf: Update selftests to reflect new error states

Update various selftest error messages:

 * The 'Rx tried to sub from different maps, paths, or prohibited types'
   is reworked into more specific/differentiated error messages for better
   guidance.

 * The change into 'value -4294967168 makes map_value pointer be out of
   bounds' is due to moving the mixed bounds check into the speculation
   handling and thus occuring slightly later than above mentioned sanity
   check.

 * The change into 'math between map_value pointer and register with
   unbounded min value' is similarly due to register sanity check coming
   before the mixed bounds check.

 * The case of 'map access: known scalar += value_ptr from different maps'
   now loads fine given masks are the same from the different paths (despite
   max map value size being different).

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/verifier/bounds.c |  5 -----
 .../selftests/bpf/verifier/bounds_deduction.c | 21 ++++++++++---------
 .../bpf/verifier/bounds_mix_sign_unsign.c     | 13 ------------
 .../testing/selftests/bpf/verifier/map_ptr.c  |  4 ++--
 tools/testing/selftests/bpf/verifier/unpriv.c |  2 +-
 .../selftests/bpf/verifier/value_ptr_arith.c  |  6 ++----
 6 files changed, 16 insertions(+), 35 deletions(-)

diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index 57ed67b86074..8a1caf46ffbc 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -261,8 +261,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	/* not actually fully unbounded, but the bound is very high */
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
-	.result_unpriv = REJECT,
 	.errstr = "value -4294967168 makes map_value pointer be out of bounds",
 	.result = REJECT,
 },
@@ -298,9 +296,6 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_8b = { 3 },
-	/* not actually fully unbounded, but the bound is very high */
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
-	.result_unpriv = REJECT,
 	.errstr = "value -4294967168 makes map_value pointer be out of bounds",
 	.result = REJECT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/bounds_deduction.c b/tools/testing/selftests/bpf/verifier/bounds_deduction.c
index c162498a64fc..91869aea6d64 100644
--- a/tools/testing/selftests/bpf/verifier/bounds_deduction.c
+++ b/tools/testing/selftests/bpf/verifier/bounds_deduction.c
@@ -6,7 +6,7 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "R0 tried to subtract pointer from scalar",
 	.result = REJECT,
 },
@@ -21,7 +21,7 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
 		BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R1 tried to sub from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 1,
@@ -34,22 +34,23 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "R0 tried to subtract pointer from scalar",
 	.result = REJECT,
 },
 {
 	"check deducing bounds from const, 4",
 	.insns = {
+		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
 		BPF_MOV64_IMM(BPF_REG_0, 0),
 		BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 0, 1),
 		BPF_EXIT_INSN(),
 		BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1),
 		BPF_EXIT_INSN(),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+		BPF_ALU64_REG(BPF_SUB, BPF_REG_6, BPF_REG_0),
 		BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R1 tried to sub from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R6 has pointer with unsupported alu operation",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
@@ -61,7 +62,7 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "R0 tried to subtract pointer from scalar",
 	.result = REJECT,
 },
@@ -74,7 +75,7 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "R0 tried to subtract pointer from scalar",
 	.result = REJECT,
 },
@@ -88,7 +89,7 @@
 			    offsetof(struct __sk_buff, mark)),
 		BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R1 tried to sub from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "dereference of modified ctx ptr",
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -103,7 +104,7 @@
 			    offsetof(struct __sk_buff, mark)),
 		BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "dereference of modified ctx ptr",
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -116,7 +117,7 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 tried to sub from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "R0 tried to subtract pointer from scalar",
 	.result = REJECT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c
index 9baca7a75c42..c2aa6f26738b 100644
--- a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c
+++ b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c
@@ -19,7 +19,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -43,7 +42,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -69,7 +67,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R8 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -94,7 +91,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R8 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -141,7 +137,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -210,7 +205,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -260,7 +254,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -287,7 +280,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -313,7 +305,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -342,7 +333,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R7 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -372,7 +362,6 @@
 	},
 	.fixup_map_hash_8b = { 4 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -400,7 +389,5 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
-	.result_unpriv = REJECT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c
index 6f610cfddae5..1f82021429bf 100644
--- a/tools/testing/selftests/bpf/verifier/map_ptr.c
+++ b/tools/testing/selftests/bpf/verifier/map_ptr.c
@@ -76,7 +76,7 @@
 	},
 	.fixup_map_hash_16b = { 4 },
 	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.result = ACCEPT,
 },
 {
@@ -94,6 +94,6 @@
 	},
 	.fixup_map_hash_16b = { 4 },
 	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R0 has pointer with unsupported alu operation",
 	.result = ACCEPT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c
index 3e32400c4b44..bd436df5cc32 100644
--- a/tools/testing/selftests/bpf/verifier/unpriv.c
+++ b/tools/testing/selftests/bpf/verifier/unpriv.c
@@ -505,7 +505,7 @@
 	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R1 tried to add from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index feb91266db39..e5913fd3b903 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -21,8 +21,6 @@
 	.fixup_map_hash_16b = { 5 },
 	.fixup_map_array_48b = { 8 },
 	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 tried to add from different maps",
 	.retval = 1,
 },
 {
@@ -122,7 +120,7 @@
 	.fixup_map_array_48b = { 1 },
 	.result = ACCEPT,
 	.result_unpriv = REJECT,
-	.errstr_unpriv = "R2 tried to add from different pointers or scalars",
+	.errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
 	.retval = 0,
 },
 {
@@ -169,7 +167,7 @@
 	.fixup_map_array_48b = { 1 },
 	.result = ACCEPT,
 	.result_unpriv = REJECT,
-	.errstr_unpriv = "R2 tried to add from different maps, paths, or prohibited types",
+	.errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
 	.retval = 0,
 },
 {

From 6b389c16378a03fe71f3b1365b593ba41d2dd8ec Mon Sep 17 00:00:00 2001
From: Lijun Pan <lijunp213@gmail.com>
Date: Thu, 15 Apr 2021 23:18:13 -0500
Subject: [PATCH 1803/1820] MAINTAINERS: update my email

Update my email and change myself to Reviewer.

Signed-off-by: Lijun Pan <lijunp213@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 163264c282eb..a31f76c41aec 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8517,9 +8517,9 @@ F:	drivers/pci/hotplug/rpaphp*
 
 IBM Power SRIOV Virtual NIC Device Driver
 M:	Dany Madden <drt@linux.ibm.com>
-M:	Lijun Pan <ljp@linux.ibm.com>
 M:	Sukadev Bhattiprolu <sukadev@linux.ibm.com>
 R:	Thomas Falcon <tlfalcon@linux.ibm.com>
+R:	Lijun Pan <lijunp213@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/ibm/ibmvnic.*

From 845be1cd34464620861b457b808e5fb2115d06b0 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 16 Apr 2021 15:45:54 -0700
Subject: [PATCH 1804/1820] mm: eliminate "expecting prototype" kernel-doc
 warnings

Fix stray kernel-doc warnings in mm/ due to mis-typed or missing function
names.

Quietens these kernel-doc warnings:

  mm/mmu_gather.c:264: warning: expecting prototype for tlb_gather_mmu(). Prototype was for __tlb_gather_mmu() instead
  mm/oom_kill.c:180: warning: expecting prototype for Check whether unreclaimable slab amount is greater than(). Prototype was for should_dump_unreclaim_slab() instead
  mm/shuffle.c:155: warning: expecting prototype for shuffle_free_memory(). Prototype was for __shuffle_free_memory() instead

Link: https://lkml.kernel.org/r/20210411210642.11362-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/mmu_gather.c | 29 +++++++++++++++++++----------
 mm/oom_kill.c   |  2 +-
 mm/shuffle.c    |  4 ++--
 3 files changed, 22 insertions(+), 13 deletions(-)

diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 0dc7149b0c61..1b9837419bf9 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -249,16 +249,6 @@ void tlb_flush_mmu(struct mmu_gather *tlb)
 	tlb_flush_mmu_free(tlb);
 }
 
-/**
- * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
- * @tlb: the mmu_gather structure to initialize
- * @mm: the mm_struct of the target address space
- * @fullmm: @mm is without users and we're going to destroy the full address
- *	    space (exit/execve)
- *
- * Called to initialize an (on-stack) mmu_gather structure for page-table
- * tear-down from @mm.
- */
 static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 			     bool fullmm)
 {
@@ -283,11 +273,30 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 	inc_tlb_flush_pending(tlb->mm);
 }
 
+/**
+ * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
+ * @tlb: the mmu_gather structure to initialize
+ * @mm: the mm_struct of the target address space
+ *
+ * Called to initialize an (on-stack) mmu_gather structure for page-table
+ * tear-down from @mm.
+ */
 void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm)
 {
 	__tlb_gather_mmu(tlb, mm, false);
 }
 
+/**
+ * tlb_gather_mmu_fullmm - initialize an mmu_gather structure for page-table tear-down
+ * @tlb: the mmu_gather structure to initialize
+ * @mm: the mm_struct of the target address space
+ *
+ * In this case, @mm is without users and we're going to destroy the
+ * full address space (exit/execve).
+ *
+ * Called to initialize an (on-stack) mmu_gather structure for page-table
+ * tear-down from @mm.
+ */
 void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm)
 {
 	__tlb_gather_mmu(tlb, mm, true);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 9efaf430cfd3..fa1cf18bac97 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -170,7 +170,7 @@ static bool oom_unkillable_task(struct task_struct *p)
 	return false;
 }
 
-/**
+/*
  * Check whether unreclaimable slab amount is greater than
  * all user memory(LRU pages).
  * dump_unreclaimable_slab() could help in the case that
diff --git a/mm/shuffle.c b/mm/shuffle.c
index 9c2e145a747a..c13c33b247e8 100644
--- a/mm/shuffle.c
+++ b/mm/shuffle.c
@@ -147,8 +147,8 @@ void __meminit __shuffle_zone(struct zone *z)
 	spin_unlock_irqrestore(&z->lock, flags);
 }
 
-/**
- * shuffle_free_memory - reduce the predictability of the page allocator
+/*
+ * __shuffle_free_memory - reduce the predictability of the page allocator
  * @pgdat: node page data
  */
 void __meminit __shuffle_free_memory(pg_data_t *pgdat)

From 5c595ac4c776c44b5c59de22ab43b3fe256d9fbb Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 16 Apr 2021 15:45:57 -0700
Subject: [PATCH 1805/1820] kasan: fix hwasan build for gcc

gcc-11 adds support for -fsanitize=kernel-hwaddress, so it becomes
possible to enable CONFIG_KASAN_SW_TAGS.

Unfortunately this fails to build at the moment, because the
corresponding command line arguments use llvm specific syntax.

Change it to use the cc-param macro instead, which works on both clang
and gcc.

[elver@google.com: fixup for "kasan: fix hwasan build for gcc"]
  Link: https://lkml.kernel.org/r/YHQZVfVVLE/LDK2v@elver.google.com

Link: https://lkml.kernel.org/r/20210323124112.1229772-1-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Marco Elver <elver@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Acked-by: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 scripts/Makefile.kasan | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan
index 1e000cc2e7b4..127012f45166 100644
--- a/scripts/Makefile.kasan
+++ b/scripts/Makefile.kasan
@@ -2,6 +2,8 @@
 CFLAGS_KASAN_NOSANITIZE := -fno-builtin
 KASAN_SHADOW_OFFSET ?= $(CONFIG_KASAN_SHADOW_OFFSET)
 
+cc-param = $(call cc-option, -mllvm -$(1), $(call cc-option, --param $(1)))
+
 ifdef CONFIG_KASAN_GENERIC
 
 ifdef CONFIG_KASAN_INLINE
@@ -12,8 +14,6 @@ endif
 
 CFLAGS_KASAN_MINIMAL := -fsanitize=kernel-address
 
-cc-param = $(call cc-option, -mllvm -$(1), $(call cc-option, --param $(1)))
-
 # -fasan-shadow-offset fails without -fsanitize
 CFLAGS_KASAN_SHADOW := $(call cc-option, -fsanitize=kernel-address \
 			-fasan-shadow-offset=$(KASAN_SHADOW_OFFSET), \
@@ -36,14 +36,14 @@ endif # CONFIG_KASAN_GENERIC
 ifdef CONFIG_KASAN_SW_TAGS
 
 ifdef CONFIG_KASAN_INLINE
-    instrumentation_flags := -mllvm -hwasan-mapping-offset=$(KASAN_SHADOW_OFFSET)
+    instrumentation_flags := $(call cc-param,hwasan-mapping-offset=$(KASAN_SHADOW_OFFSET))
 else
-    instrumentation_flags := -mllvm -hwasan-instrument-with-calls=1
+    instrumentation_flags := $(call cc-param,hwasan-instrument-with-calls=1)
 endif
 
 CFLAGS_KASAN := -fsanitize=kernel-hwaddress \
-		-mllvm -hwasan-instrument-stack=$(CONFIG_KASAN_STACK) \
-		-mllvm -hwasan-use-short-granules=0 \
+		$(call cc-param,hwasan-instrument-stack=$(CONFIG_KASAN_STACK)) \
+		$(call cc-param,hwasan-use-short-granules=0) \
 		$(instrumentation_flags)
 
 endif # CONFIG_KASAN_SW_TAGS

From 02c587733c8161355a43e6e110c2e29bd0acff72 Mon Sep 17 00:00:00 2001
From: Walter Wu <walter-zh.wu@mediatek.com>
Date: Fri, 16 Apr 2021 15:46:00 -0700
Subject: [PATCH 1806/1820] kasan: remove redundant config option

CONFIG_KASAN_STACK and CONFIG_KASAN_STACK_ENABLE both enable KASAN stack
instrumentation, but we should only need one config, so that we remove
CONFIG_KASAN_STACK_ENABLE and make CONFIG_KASAN_STACK workable.  see [1].

When enable KASAN stack instrumentation, then for gcc we could do no
prompt and default value y, and for clang prompt and default value n.

This patch fixes the following compilation warning:

  include/linux/kasan.h:333:30: warning: 'CONFIG_KASAN_STACK' is not defined, evaluates to 0 [-Wundef]

[akpm@linux-foundation.org: fix merge snafu]

Link: https://bugzilla.kernel.org/show_bug.cgi?id=210221 [1]
Link: https://lkml.kernel.org/r/20210226012531.29231-1-walter-zh.wu@mediatek.com
Fixes: d9b571c885a8 ("kasan: fix KASAN_STACK dependency for HW_TAGS")
Signed-off-by: Walter Wu <walter-zh.wu@mediatek.com>
Suggested-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/kernel/sleep.S        |  2 +-
 arch/x86/kernel/acpi/wakeup_64.S |  2 +-
 include/linux/kasan.h            |  2 +-
 lib/Kconfig.kasan                |  9 ++-------
 mm/kasan/common.c                |  2 +-
 mm/kasan/kasan.h                 |  2 +-
 mm/kasan/report_generic.c        |  2 +-
 scripts/Makefile.kasan           | 10 ++++++++--
 security/Kconfig.hardening       |  4 ++--
 9 files changed, 18 insertions(+), 17 deletions(-)

diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 5bfd9b87f85d..4ea9392f86e0 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -134,7 +134,7 @@ SYM_FUNC_START(_cpu_resume)
 	 */
 	bl	cpu_do_resume
 
-#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
+#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
 	mov	x0, sp
 	bl	kasan_unpoison_task_stack_below
 #endif
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 56b6865afb2a..d5d8a352eafa 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -115,7 +115,7 @@ SYM_FUNC_START(do_suspend_lowlevel)
 	movq	pt_regs_r14(%rax), %r14
 	movq	pt_regs_r15(%rax), %r15
 
-#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
+#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
 	/*
 	 * The suspend path may have poisoned some areas deeper in the stack,
 	 * which we now need to unpoison.
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index b91732bd05d7..14f72ec96492 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -330,7 +330,7 @@ static inline bool kasan_check_byte(const void *address)
 
 #endif /* CONFIG_KASAN */
 
-#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
+#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
 void kasan_unpoison_task_stack(struct task_struct *task);
 #else
 static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index fba9909e31b7..cffc2ebbf185 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -138,9 +138,10 @@ config KASAN_INLINE
 
 endchoice
 
-config KASAN_STACK_ENABLE
+config KASAN_STACK
 	bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST
 	depends on KASAN_GENERIC || KASAN_SW_TAGS
+	default y if CC_IS_GCC
 	help
 	  The LLVM stack address sanitizer has a know problem that
 	  causes excessive stack usage in a lot of functions, see
@@ -154,12 +155,6 @@ config KASAN_STACK_ENABLE
 	  CONFIG_COMPILE_TEST.	On gcc it is assumed to always be safe
 	  to use and enabled by default.
 
-config KASAN_STACK
-	int
-	depends on KASAN_GENERIC || KASAN_SW_TAGS
-	default 1 if KASAN_STACK_ENABLE || CC_IS_GCC
-	default 0
-
 config KASAN_SW_TAGS_IDENTIFY
 	bool "Enable memory corruption identification"
 	depends on KASAN_SW_TAGS
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index b5e08d4cefec..7b53291dafa1 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -63,7 +63,7 @@ void __kasan_unpoison_range(const void *address, size_t size)
 	kasan_unpoison(address, size);
 }
 
-#if CONFIG_KASAN_STACK
+#ifdef CONFIG_KASAN_STACK
 /* Unpoison the entire stack for a task. */
 void kasan_unpoison_task_stack(struct task_struct *task)
 {
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 8c55634d6edd..3436c6bf7c0c 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -231,7 +231,7 @@ void *kasan_find_first_bad_addr(void *addr, size_t size);
 const char *kasan_get_bug_type(struct kasan_access_info *info);
 void kasan_metadata_fetch_row(char *buffer, void *row);
 
-#if defined(CONFIG_KASAN_GENERIC) && CONFIG_KASAN_STACK
+#if defined(CONFIG_KASAN_GENERIC) && defined(CONFIG_KASAN_STACK)
 void kasan_print_address_stack_frame(const void *addr);
 #else
 static inline void kasan_print_address_stack_frame(const void *addr) { }
diff --git a/mm/kasan/report_generic.c b/mm/kasan/report_generic.c
index 41f374585144..de732bc341c5 100644
--- a/mm/kasan/report_generic.c
+++ b/mm/kasan/report_generic.c
@@ -128,7 +128,7 @@ void kasan_metadata_fetch_row(char *buffer, void *row)
 	memcpy(buffer, kasan_mem_to_shadow(row), META_BYTES_PER_ROW);
 }
 
-#if CONFIG_KASAN_STACK
+#ifdef CONFIG_KASAN_STACK
 static bool __must_check tokenize_frame_descr(const char **frame_descr,
 					      char *token, size_t max_tok_len,
 					      unsigned long *value)
diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan
index 127012f45166..3d791908ed36 100644
--- a/scripts/Makefile.kasan
+++ b/scripts/Makefile.kasan
@@ -4,6 +4,12 @@ KASAN_SHADOW_OFFSET ?= $(CONFIG_KASAN_SHADOW_OFFSET)
 
 cc-param = $(call cc-option, -mllvm -$(1), $(call cc-option, --param $(1)))
 
+ifdef CONFIG_KASAN_STACK
+	stack_enable := 1
+else
+	stack_enable := 0
+endif
+
 ifdef CONFIG_KASAN_GENERIC
 
 ifdef CONFIG_KASAN_INLINE
@@ -27,7 +33,7 @@ else
 	CFLAGS_KASAN := $(CFLAGS_KASAN_SHADOW) \
 	 $(call cc-param,asan-globals=1) \
 	 $(call cc-param,asan-instrumentation-with-call-threshold=$(call_threshold)) \
-	 $(call cc-param,asan-stack=$(CONFIG_KASAN_STACK)) \
+	 $(call cc-param,asan-stack=$(stack_enable)) \
 	 $(call cc-param,asan-instrument-allocas=1)
 endif
 
@@ -42,7 +48,7 @@ else
 endif
 
 CFLAGS_KASAN := -fsanitize=kernel-hwaddress \
-		$(call cc-param,hwasan-instrument-stack=$(CONFIG_KASAN_STACK)) \
+		$(call cc-param,hwasan-instrument-stack=$(stack_enable)) \
 		$(call cc-param,hwasan-use-short-granules=0) \
 		$(instrumentation_flags)
 
diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening
index 269967c4fc1b..a56c36470cb1 100644
--- a/security/Kconfig.hardening
+++ b/security/Kconfig.hardening
@@ -64,7 +64,7 @@ choice
 	config GCC_PLUGIN_STRUCTLEAK_BYREF
 		bool "zero-init structs passed by reference (strong)"
 		depends on GCC_PLUGINS
-		depends on !(KASAN && KASAN_STACK=1)
+		depends on !(KASAN && KASAN_STACK)
 		select GCC_PLUGIN_STRUCTLEAK
 		help
 		  Zero-initialize any structures on the stack that may
@@ -82,7 +82,7 @@ choice
 	config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL
 		bool "zero-init anything passed by reference (very strong)"
 		depends on GCC_PLUGINS
-		depends on !(KASAN && KASAN_STACK=1)
+		depends on !(KASAN && KASAN_STACK)
 		select GCC_PLUGIN_STRUCTLEAK
 		help
 		  Zero-initialize any stack variables that may be passed

From d199161653d612b8fb96ac51bfd5b2d2782ecef3 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 16 Apr 2021 15:46:03 -0700
Subject: [PATCH 1807/1820] csky: change a Kconfig symbol name to fix e1000
 build error

e1000's #define of CONFIG_RAM_BASE conflicts with a Kconfig symbol in
arch/csky/Kconfig.

The symbol in e1000 has been around longer, so change arch/csky/ to use
DRAM_BASE instead of RAM_BASE to remove the conflict.  (although e1000
is also a 2-line change)

Link: https://lkml.kernel.org/r/20210411055335.7111-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Acked-by: Guo Ren <guoren@kernel.org>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/csky/Kconfig            | 2 +-
 arch/csky/include/asm/page.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 34e91224adc3..8de5b987edb9 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -314,7 +314,7 @@ config FORCE_MAX_ZONEORDER
 	int "Maximum zone order"
 	default "11"
 
-config RAM_BASE
+config DRAM_BASE
 	hex "DRAM start addr (the same with memory-section in dts)"
 	default 0x0
 
diff --git a/arch/csky/include/asm/page.h b/arch/csky/include/asm/page.h
index 3b91fc3cf36f..ed7451478b1b 100644
--- a/arch/csky/include/asm/page.h
+++ b/arch/csky/include/asm/page.h
@@ -28,7 +28,7 @@
 #define SSEG_SIZE	0x20000000
 #define LOWMEM_LIMIT	(SSEG_SIZE * 2)
 
-#define PHYS_OFFSET_OFFSET (CONFIG_RAM_BASE & (SSEG_SIZE - 1))
+#define PHYS_OFFSET_OFFSET (CONFIG_DRAM_BASE & (SSEG_SIZE - 1))
 
 #ifndef __ASSEMBLY__
 

From 19d000d93303e05bd7b1326e3de9df05a41b25b5 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 16 Apr 2021 15:46:06 -0700
Subject: [PATCH 1808/1820] ia64: remove duplicate entries in generic_defconfig

Fix ia64 generic_defconfig duplicate entries, as warned by:

  arch/ia64/configs/generic_defconfig: warning: override: reassigning to symbol ATA:  => 58
  arch/ia64/configs/generic_defconfig: warning: override: reassigning to symbol ATA_PIIX:  => 59

These 2 symbols still have the same value as in the removed lines.

Link: https://lkml.kernel.org/r/20210411020255.18052-1-rdunlap@infradead.org
Fixes: c331649e6371 ("ia64: Use libata instead of the legacy ide driver in defconfigs")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/configs/generic_defconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig
index ca0d596c800d..8916a2850c48 100644
--- a/arch/ia64/configs/generic_defconfig
+++ b/arch/ia64/configs/generic_defconfig
@@ -55,8 +55,6 @@ CONFIG_CHR_DEV_SG=m
 CONFIG_SCSI_FC_ATTRS=y
 CONFIG_SCSI_SYM53C8XX_2=y
 CONFIG_SCSI_QLOGIC_1280=y
-CONFIG_ATA=y
-CONFIG_ATA_PIIX=y
 CONFIG_SATA_VITESSE=y
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=m

From e2af9da4f867a1a54f1252bf3abc1a5c63951778 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 16 Apr 2021 15:46:09 -0700
Subject: [PATCH 1809/1820] ia64: fix discontig.c section mismatches

Fix IA64 discontig.c Section mismatch warnings.

When CONFIG_SPARSEMEM=y and CONFIG_MEMORY_HOTPLUG=y, the functions
computer_pernodesize() and scatter_node_data() should not be marked as
__meminit because they are needed after init, on any memory hotplug
event.  Also, early_nr_cpus_node() is called by compute_pernodesize(),
so early_nr_cpus_node() cannot be __meminit either.

  WARNING: modpost: vmlinux.o(.text.unlikely+0x1612): Section mismatch in reference from the function arch_alloc_nodedata() to the function .meminit.text:compute_pernodesize()
  The function arch_alloc_nodedata() references the function __meminit compute_pernodesize().
  This is often because arch_alloc_nodedata lacks a __meminit annotation or the annotation of compute_pernodesize is wrong.

  WARNING: modpost: vmlinux.o(.text.unlikely+0x1692): Section mismatch in reference from the function arch_refresh_nodedata() to the function .meminit.text:scatter_node_data()
  The function arch_refresh_nodedata() references the function __meminit scatter_node_data().
  This is often because arch_refresh_nodedata lacks a __meminit annotation or the annotation of scatter_node_data is wrong.

  WARNING: modpost: vmlinux.o(.text.unlikely+0x1502): Section mismatch in reference from the function compute_pernodesize() to the function .meminit.text:early_nr_cpus_node()
  The function compute_pernodesize() references the function __meminit early_nr_cpus_node().
  This is often because compute_pernodesize lacks a __meminit annotation or the annotation of early_nr_cpus_node is wrong.

Link: https://lkml.kernel.org/r/20210411001201.3069-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/mm/discontig.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 03b3a02375ff..c310b4c99fb3 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -95,7 +95,7 @@ static int __init build_node_maps(unsigned long start, unsigned long len,
  * acpi_boot_init() (which builds the node_to_cpu_mask array) hasn't been
  * called yet.  Note that node 0 will also count all non-existent cpus.
  */
-static int __meminit early_nr_cpus_node(int node)
+static int early_nr_cpus_node(int node)
 {
 	int cpu, n = 0;
 
@@ -110,7 +110,7 @@ static int __meminit early_nr_cpus_node(int node)
  * compute_pernodesize - compute size of pernode data
  * @node: the node id.
  */
-static unsigned long __meminit compute_pernodesize(int node)
+static unsigned long compute_pernodesize(int node)
 {
 	unsigned long pernodesize = 0, cpus;
 
@@ -367,7 +367,7 @@ static void __init reserve_pernode_space(void)
 	}
 }
 
-static void __meminit scatter_node_data(void)
+static void scatter_node_data(void)
 {
 	pg_data_t **dst;
 	int node;

From 17786fea414393813b56e33a1a01b2dfa03c0915 Mon Sep 17 00:00:00 2001
From: John Paul Adrian Glaubitz <glaubitz () physik ! fu-berlin ! de>
Date: Fri, 16 Apr 2021 15:46:12 -0700
Subject: [PATCH 1810/1820] ia64: tools: remove inclusion of ia64-specific
 version of errno.h header

There is no longer an ia64-specific version of the errno.h header below
arch/ia64/include/uapi/asm/, so trying to build tools/bpf fails with:

    CC       /usr/src/linux/tools/bpf/bpftool/btf_dumper.o
  In file included from /usr/src/linux/tools/include/linux/err.h:8,
                   from btf_dumper.c:11:
  /usr/src/linux/tools/include/uapi/asm/errno.h:13:10: fatal error: ../../../arch/ia64/include/uapi/asm/errno.h: No such file or directory
     13 | #include "../../../arch/ia64/include/uapi/asm/errno.h"
        |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  compilation terminated.

Thus, just remove the inclusion of the ia64-specific errno.h so that the
build will use the generic errno.h header on this target which was used
there anyway as the ia64-specific errno.h was just a wrapper for the
generic header.

Fixes: c25f867ddd00 ("ia64: remove unneeded uapi asm-generic wrappers")
Signed-off-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/include/uapi/asm/errno.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h
index 637189ec1ab9..d30439b4b8ab 100644
--- a/tools/include/uapi/asm/errno.h
+++ b/tools/include/uapi/asm/errno.h
@@ -9,8 +9,6 @@
 #include "../../../arch/alpha/include/uapi/asm/errno.h"
 #elif defined(__mips__)
 #include "../../../arch/mips/include/uapi/asm/errno.h"
-#elif defined(__ia64__)
-#include "../../../arch/ia64/include/uapi/asm/errno.h"
 #elif defined(__xtensa__)
 #include "../../../arch/xtensa/include/uapi/asm/errno.h"
 #else

From f4bf09dc3aaa4b07cd15630f2023f68cb2668809 Mon Sep 17 00:00:00 2001
From: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Date: Fri, 16 Apr 2021 15:46:15 -0700
Subject: [PATCH 1811/1820] ia64: tools: remove duplicate definition of
 ia64_mf() on ia64

The ia64_mf() macro defined in tools/arch/ia64/include/asm/barrier.h is
already defined in <asm/gcc_intrin.h> on ia64 which causes libbpf
failing to build:

    CC       /usr/src/linux/tools/bpf/bpftool//libbpf/staticobjs/libbpf.o
  In file included from /usr/src/linux/tools/include/asm/barrier.h:24,
                   from /usr/src/linux/tools/include/linux/ring_buffer.h:4,
                   from libbpf.c:37:
  /usr/src/linux/tools/include/asm/../../arch/ia64/include/asm/barrier.h:43: error: "ia64_mf" redefined [-Werror]
     43 | #define ia64_mf()       asm volatile ("mf" ::: "memory")
        |
  In file included from /usr/include/ia64-linux-gnu/asm/intrinsics.h:20,
                   from /usr/include/ia64-linux-gnu/asm/swab.h:11,
                   from /usr/include/linux/swab.h:8,
                   from /usr/include/linux/byteorder/little_endian.h:13,
                   from /usr/include/ia64-linux-gnu/asm/byteorder.h:5,
                   from /usr/src/linux/tools/include/uapi/linux/perf_event.h:20,
                   from libbpf.c:36:
  /usr/include/ia64-linux-gnu/asm/gcc_intrin.h:382: note: this is the location of the previous definition
    382 | #define ia64_mf() __asm__ volatile ("mf" ::: "memory")
        |
  cc1: all warnings being treated as errors

Thus, remove the definition from tools/arch/ia64/include/asm/barrier.h.

Signed-off-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/arch/ia64/include/asm/barrier.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/tools/arch/ia64/include/asm/barrier.h b/tools/arch/ia64/include/asm/barrier.h
index 4d471d9511a5..6fffe5682713 100644
--- a/tools/arch/ia64/include/asm/barrier.h
+++ b/tools/arch/ia64/include/asm/barrier.h
@@ -39,9 +39,6 @@
  * sequential memory pages only.
  */
 
-/* XXX From arch/ia64/include/uapi/asm/gcc_intrin.h */
-#define ia64_mf()       asm volatile ("mf" ::: "memory")
-
 #define mb()		ia64_mf()
 #define rmb()		mb()
 #define wmb()		mb()

From 94036f4c884377bdf2da1ba7666c9599d6df0191 Mon Sep 17 00:00:00 2001
From: Zack Rusin <zackr@vmware.com>
Date: Fri, 16 Apr 2021 15:46:18 -0700
Subject: [PATCH 1812/1820] mm/mapping_dirty_helpers: guard hugepage pud's
 usage

Mapping dirty helpers have, so far, been only used on X86, but a port of
vmwgfx to ARM64 exposed a problem which results in a compilation error
on ARM64 systems:

  mm/mapping_dirty_helpers.c: In function `wp_clean_pud_entry':
  mm/mapping_dirty_helpers.c:172:32: error: implicit declaration of function `pud_dirty'; did you mean `pmd_dirty'? [-Werror=implicit-function-declaration]

This is due to the fact that mapping_dirty_helpers code assumes that
pud_dirty is always defined, which is not the case for architectures
that don't define CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD.

ARM64 arch is a little inconsistent when it comes to PUD hugepage
helpers, e.g. it defines pud_young but not pud_dirty but regardless of
that the core kernel code shouldn't assume that any of the PUD hugepage
helpers are available unless CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
is defined.  This prevents compilation errors whenever one of the
drivers is ported to new architectures.

Link: https://lkml.kernel.org/r/20210409165151.694574-1-zackr@vmware.com
Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Thomas Hellstrm (Intel) <thomas_os@shipmail.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/mapping_dirty_helpers.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c
index b59054ef2e10..b890854ec761 100644
--- a/mm/mapping_dirty_helpers.c
+++ b/mm/mapping_dirty_helpers.c
@@ -165,10 +165,12 @@ static int wp_clean_pud_entry(pud_t *pud, unsigned long addr, unsigned long end,
 		return 0;
 	}
 
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 	/* Huge pud */
 	walk->action = ACTION_CONTINUE;
 	if (pud_trans_huge(pudval) || pud_devmap(pudval))
 		WARN_ON(pud_write(pudval) || pud_dirty(pudval));
+#endif
 
 	return 0;
 }

From 458376913d86bed2fb781b4952eb6861675ef3be Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Fri, 16 Apr 2021 15:46:20 -0700
Subject: [PATCH 1813/1820] mm: ptdump: fix build failure

READ_ONCE() cannot be used for reading PTEs.  Use ptep_get() instead, to
avoid the following errors:

    CC      mm/ptdump.o
  In file included from <command-line>:
  mm/ptdump.c: In function 'ptdump_pte_entry':
  include/linux/compiler_types.h:320:38: error: call to '__compiletime_assert_207' declared with attribute error: Unsupported access size for {READ,WRITE}_ONCE().
    320 |  _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
        |                                      ^
  include/linux/compiler_types.h:301:4: note: in definition of macro '__compiletime_assert'
    301 |    prefix ## suffix();    \
        |    ^~~~~~
  include/linux/compiler_types.h:320:2: note: in expansion of macro '_compiletime_assert'
    320 |  _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
        |  ^~~~~~~~~~~~~~~~~~~
  include/asm-generic/rwonce.h:36:2: note: in expansion of macro 'compiletime_assert'
     36 |  compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \
        |  ^~~~~~~~~~~~~~~~~~
  include/asm-generic/rwonce.h:49:2: note: in expansion of macro 'compiletime_assert_rwonce_type'
     49 |  compiletime_assert_rwonce_type(x);    \
        |  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  mm/ptdump.c:114:14: note: in expansion of macro 'READ_ONCE'
    114 |  pte_t val = READ_ONCE(*pte);
        |              ^~~~~~~~~
  make[2]: *** [mm/ptdump.o] Error 1

See commit 481e980a7c19 ("mm: Allow arches to provide ptep_get()") and
commit c0e1c8c22beb ("powerpc/8xx: Provide ptep_get() with 16k pages")
for details.

Link: https://lkml.kernel.org/r/912b349e2bcaa88939904815ca0af945740c6bd4.1618478922.git.christophe.leroy@csgroup.eu
Fixes: 30d621f6723b ("mm: add generic ptdump")
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Steven Price <steven.price@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/ptdump.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/ptdump.c b/mm/ptdump.c
index 4354c1422d57..da751448d0e4 100644
--- a/mm/ptdump.c
+++ b/mm/ptdump.c
@@ -111,7 +111,7 @@ static int ptdump_pte_entry(pte_t *pte, unsigned long addr,
 			    unsigned long next, struct mm_walk *walk)
 {
 	struct ptdump_state *st = walk->private;
-	pte_t val = READ_ONCE(*pte);
+	pte_t val = ptep_get(pte);
 
 	if (st->effective_prot)
 		st->effective_prot(st, 4, pte_val(val));

From 04c53de57cb6435738961dace8b1b71d3ecd3c39 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 16 Apr 2021 15:46:23 -0700
Subject: [PATCH 1814/1820] gcov: clang: fix clang-11+ build

With clang-11+, the code is broken due to my kvmalloc() conversion
(which predated the clang-11 support code) leaving one vmalloc() in
place.  Fix that.

Link: https://lkml.kernel.org/r/20210412214210.6e1ecca9cdc5.I24459763acf0591d5e6b31c7e3a59890d802f79c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/gcov/clang.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c
index c466c7fbdece..b81f2823630d 100644
--- a/kernel/gcov/clang.c
+++ b/kernel/gcov/clang.c
@@ -369,7 +369,7 @@ static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn)
 	INIT_LIST_HEAD(&fn_dup->head);
 
 	cv_size = fn->num_counters * sizeof(fn->counters[0]);
-	fn_dup->counters = vmalloc(cv_size);
+	fn_dup->counters = kvmalloc(cv_size, GFP_KERNEL);
 	if (!fn_dup->counters) {
 		kfree(fn_dup);
 		return NULL;

From c95c2d328cd051484bea161e66dfa715c02a7d7e Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 16 Apr 2021 15:46:26 -0700
Subject: [PATCH 1815/1820] lib: remove "expecting prototype" kernel-doc
 warnings

Fix various kernel-doc warnings in lib/ due to missing or erroneous
function names.

Add kernel-doc for some function parameters that was missing.  Use
kernel-doc "Return:" notation in earlycpio.c.

Quietens the following warnings:

  lib/earlycpio.c:61: warning: expecting prototype for cpio_data find_cpio_data(). Prototype was for find_cpio_data() instead

  lib/lru_cache.c:640: warning: expecting prototype for lc_dump(). Prototype was for lc_seq_dump_details() instead
  lru_cache.c:90: warning: Function parameter or member 'cache' not described in 'lc_create'

  lib/parman.c:368: warning: expecting prototype for parman_item_del(). Prototype was for parman_item_remove() instead
  parman.c:309: warning: Excess function parameter 'prority' description in 'parman_prio_init'

  lib/radix-tree.c:703: warning: expecting prototype for __radix_tree_insert(). Prototype was for radix_tree_insert() instead
  radix-tree.c:180: warning: Excess function parameter 'addr' description in 'radix_tree_find_next_bit'
  radix-tree.c:180: warning: Excess function parameter 'size' description in 'radix_tree_find_next_bit'
  radix-tree.c:931: warning: Function parameter or member 'iter' not described in 'radix_tree_iter_replace'

Link: https://lkml.kernel.org/r/20210411221756.15461-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Lars Ellenberg <lars.ellenberg@linbit.com>
Cc: Jiri Pirko <jiri@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/earlycpio.c  |  4 ++--
 lib/lru_cache.c  |  3 ++-
 lib/parman.c     |  4 ++--
 lib/radix-tree.c | 11 ++++++-----
 4 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/lib/earlycpio.c b/lib/earlycpio.c
index e83628882001..7921193f0424 100644
--- a/lib/earlycpio.c
+++ b/lib/earlycpio.c
@@ -40,7 +40,7 @@ enum cpio_fields {
 };
 
 /**
- * cpio_data find_cpio_data - Search for files in an uncompressed cpio
+ * find_cpio_data - Search for files in an uncompressed cpio
  * @path:       The directory to search for, including a slash at the end
  * @data:       Pointer to the cpio archive or a header inside
  * @len:        Remaining length of the cpio based on data pointer
@@ -49,7 +49,7 @@ enum cpio_fields {
  *              matching file itself. It can be used to iterate through the cpio
  *              to find all files inside of a directory path.
  *
- * @return:     struct cpio_data containing the address, length and
+ * Return:      &struct cpio_data containing the address, length and
  *              filename (with the directory path cut off) of the found file.
  *              If you search for a filename and not for files in a directory,
  *              pass the absolute path of the filename in the cpio and make sure
diff --git a/lib/lru_cache.c b/lib/lru_cache.c
index c69ee53d8dde..52313acbfa62 100644
--- a/lib/lru_cache.c
+++ b/lib/lru_cache.c
@@ -76,6 +76,7 @@ int lc_try_lock(struct lru_cache *lc)
 /**
  * lc_create - prepares to track objects in an active set
  * @name: descriptive name only used in lc_seq_printf_stats and lc_seq_dump_details
+ * @cache: cache root pointer
  * @max_pending_changes: maximum changes to accumulate until a transaction is required
  * @e_count: number of elements allowed to be active simultaneously
  * @e_size: size of the tracked objects
@@ -627,7 +628,7 @@ void lc_set(struct lru_cache *lc, unsigned int enr, int index)
 }
 
 /**
- * lc_dump - Dump a complete LRU cache to seq in textual form.
+ * lc_seq_dump_details - Dump a complete LRU cache to seq in textual form.
  * @lc: the lru cache to operate on
  * @seq: the &struct seq_file pointer to seq_printf into
  * @utext: user supplied additional "heading" or other info
diff --git a/lib/parman.c b/lib/parman.c
index a11f2f667639..3f8f8d422e62 100644
--- a/lib/parman.c
+++ b/lib/parman.c
@@ -297,7 +297,7 @@ EXPORT_SYMBOL(parman_destroy);
  * parman_prio_init - initializes a parman priority chunk
  * @parman:	parman instance
  * @prio:	parman prio structure to be initialized
- * @prority:	desired priority of the chunk
+ * @priority:	desired priority of the chunk
  *
  * Note: all locking must be provided by the caller.
  *
@@ -356,7 +356,7 @@ int parman_item_add(struct parman *parman, struct parman_prio *prio,
 EXPORT_SYMBOL(parman_item_add);
 
 /**
- * parman_item_del - deletes parman item
+ * parman_item_remove - deletes parman item
  * @parman:	parman instance
  * @prio:	parman prio instance to delete the item from
  * @item:	parman item instance
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 3a4da11b804d..b3afafe46fff 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -166,9 +166,9 @@ static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag)
 /**
  * radix_tree_find_next_bit - find the next set bit in a memory region
  *
- * @addr: The address to base the search on
- * @size: The bitmap size in bits
- * @offset: The bitnumber to start searching at
+ * @node: where to begin the search
+ * @tag: the tag index
+ * @offset: the bitnumber to start searching at
  *
  * Unrollable variant of find_next_bit() for constant size arrays.
  * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero.
@@ -461,7 +461,7 @@ out:
 
 /**
  *	radix_tree_shrink    -    shrink radix tree to minimum height
- *	@root		radix tree root
+ *	@root:		radix tree root
  */
 static inline bool radix_tree_shrink(struct radix_tree_root *root)
 {
@@ -691,7 +691,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 }
 
 /**
- *	__radix_tree_insert    -    insert into a radix tree
+ *	radix_tree_insert    -    insert into a radix tree
  *	@root:		radix tree root
  *	@index:		index key
  *	@item:		item to insert
@@ -919,6 +919,7 @@ EXPORT_SYMBOL(radix_tree_replace_slot);
 /**
  * radix_tree_iter_replace - replace item in a slot
  * @root:	radix tree root
+ * @iter:	iterator state
  * @slot:	pointer to slot
  * @item:	new item to store in the slot.
  *

From f2764bd4f6a8dffaec3e220728385d9756b3c2cb Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 16 Apr 2021 21:29:13 +0200
Subject: [PATCH 1816/1820] netlink: don't call ->netlink_bind with table lock
 held

When I added support to allow generic netlink multicast groups to be
restricted to subscribers with CAP_NET_ADMIN I was unaware that a
genl_bind implementation already existed in the past.

It was reverted due to ABBA deadlock:

1. ->netlink_bind gets called with the table lock held.
2. genetlink bind callback is invoked, it grabs the genl lock.

But when a new genl subsystem is (un)registered, these two locks are
taken in reverse order.

One solution would be to revert again and add a comment in genl
referring 1e82a62fec613, "genetlink: remove genl_bind").

This would need a second change in mptcp to not expose the raw token
value anymore, e.g.  by hashing the token with a secret key so userspace
can still associate subflow events with the correct mptcp connection.

However, Paolo Abeni reminded me to double-check why the netlink table is
locked in the first place.

I can't find one.  netlink_bind() is already called without this lock
when userspace joins a group via NETLINK_ADD_MEMBERSHIP setsockopt.
Same holds for the netlink_unbind operation.

Digging through the history, commit f773608026ee1
("netlink: access nlk groups safely in netlink bind and getname")
expanded the lock scope.

commit 3a20773beeeeade ("net: netlink: cap max groups which will be considered in netlink_bind()")
... removed the nlk->ngroups access that the lock scope
extension was all about.

Reduce the lock scope again and always call ->netlink_bind without
the table lock.

The Fixes tag should be vs. the patch mentioned in the link below,
but that one got squash-merged into the patch that came earlier in the
series.

Fixes: 4d54cc32112d8d ("mptcp: avoid lock_fast usage in accept path")
Link: https://lore.kernel.org/mptcp/20210213000001.379332-8-mathew.j.martineau@linux.intel.com/T/#u
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Xin Long <lucien.xin@gmail.com>
Cc: Johannes Berg <johannes.berg@intel.com>
Cc: Sean Tranchetti <stranche@codeaurora.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index dd488938447f..3a62f97acf39 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1019,7 +1019,6 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			return -EINVAL;
 	}
 
-	netlink_lock_table();
 	if (nlk->netlink_bind && groups) {
 		int group;
 
@@ -1031,13 +1030,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			if (!err)
 				continue;
 			netlink_undo_bind(group, groups, sk);
-			goto unlock;
+			return err;
 		}
 	}
 
 	/* No need for barriers here as we return to user-space without
 	 * using any of the bound attributes.
 	 */
+	netlink_lock_table();
 	if (!bound) {
 		err = nladdr->nl_pid ?
 			netlink_insert(sk, nladdr->nl_pid) :

From fae8817ae804a682c6823ad1672438f39fc46c28 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 16 Apr 2021 17:43:30 -0700
Subject: [PATCH 1817/1820] cxl/mem: Fix memory device capacity probing

The CXL Identify Memory Device output payload emits capacity in 256MB
units. The driver is treating the capacity field as bytes. This was
missed because QEMU reports bytes when it should report bytes / 256MB.

Fixes: 8adaf747c9f0 ("cxl/mem: Find device capabilities")
Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Cc: Ben Widawsky <ben.widawsky@intel.com>
Link: https://lore.kernel.org/r/161862021044.3259705.7008520073059739760.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/mem.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 1b5078311f7d..2acc6173da36 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -4,6 +4,7 @@
 #include <linux/security.h>
 #include <linux/debugfs.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <linux/mutex.h>
 #include <linux/cdev.h>
 #include <linux/idr.h>
@@ -1419,6 +1420,7 @@ out:
  */
 static int cxl_mem_identify(struct cxl_mem *cxlm)
 {
+	/* See CXL 2.0 Table 175 Identify Memory Device Output Payload */
 	struct cxl_mbox_identify {
 		char fw_revision[0x10];
 		__le64 total_capacity;
@@ -1447,10 +1449,11 @@ static int cxl_mem_identify(struct cxl_mem *cxlm)
 	 * For now, only the capacity is exported in sysfs
 	 */
 	cxlm->ram_range.start = 0;
-	cxlm->ram_range.end = le64_to_cpu(id.volatile_capacity) - 1;
+	cxlm->ram_range.end = le64_to_cpu(id.volatile_capacity) * SZ_256M - 1;
 
 	cxlm->pmem_range.start = 0;
-	cxlm->pmem_range.end = le64_to_cpu(id.persistent_capacity) - 1;
+	cxlm->pmem_range.end =
+		le64_to_cpu(id.persistent_capacity) * SZ_256M - 1;
 
 	memcpy(cxlm->firmware_version, id.fw_revision, sizeof(id.fw_revision));
 

From 0c93ac69407d63a85be0129aa55ffaec27ffebd3 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sat, 17 Apr 2021 09:27:04 -0700
Subject: [PATCH 1818/1820] readdir: make sure to verify directory entry for
 legacy interfaces too

This does the directory entry name verification for the legacy
"fillonedir" (and compat) interface that goes all the way back to the
dark ages before we had a proper dirent, and the readdir() system call
returned just a single entry at a time.

Nobody should use this interface unless you still have binaries from
1991, but let's do it right.

This came up during discussions about unsafe_copy_to_user() and proper
checking of all the inputs to it, as the networking layer is looking to
use it in a few new places.  So let's make sure the _old_ users do it
all right and proper, before we add new ones.

See also commit 8a23eb804ca4 ("Make filldir[64]() verify the directory
entry filename is valid") which did the proper modern interfaces that
people actually use. It had a note:

    Note that I didn't bother adding the checks to any legacy interfaces
    that nobody uses.

which this now corrects.  Note that we really don't care about POSIX and
the presense of '/' in a directory entry, but verify_dirent_name() also
ends up doing the proper name length verification which is what the
input checking discussion was about.

[ Another option would be to remove the support for this particular very
  old interface: any binaries that use it are likely a.out binaries, and
  they will no longer run anyway since we removed a.out binftm support
  in commit eac616557050 ("x86: Deprecate a.out support").

  But I'm not sure which came first: getdents() or ELF support, so let's
  pretend somebody might still have a working binary that uses the
  legacy readdir() case.. ]

Link: https://lore.kernel.org/lkml/CAHk-=wjbvzCAhAtvG0d81W5o0-KT5PPTHhfJ5ieDFq+bGtgOYg@mail.gmail.com/
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/readdir.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/readdir.c b/fs/readdir.c
index 19434b3c982c..09e8ed7d4161 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -150,6 +150,9 @@ static int fillonedir(struct dir_context *ctx, const char *name, int namlen,
 
 	if (buf->result)
 		return -EINVAL;
+	buf->result = verify_dirent_name(name, namlen);
+	if (buf->result < 0)
+		return buf->result;
 	d_ino = ino;
 	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
 		buf->result = -EOVERFLOW;
@@ -405,6 +408,9 @@ static int compat_fillonedir(struct dir_context *ctx, const char *name,
 
 	if (buf->result)
 		return -EINVAL;
+	buf->result = verify_dirent_name(name, namlen);
+	if (buf->result < 0)
+		return buf->result;
 	d_ino = ino;
 	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
 		buf->result = -EOVERFLOW;

From d2f7eca60b29006285d57c7035539e33300e89e5 Mon Sep 17 00:00:00 2001
From: Fredrik Strupe <fredrik@strupe.net>
Date: Mon, 5 Apr 2021 21:52:05 +0100
Subject: [PATCH 1819/1820] ARM: 9071/1: uprobes: Don't hook on thumb
 instructions

Since uprobes is not supported for thumb, check that the thumb bit is
not set when matching the uprobes instruction hooks.

The Arm UDF instructions used for uprobes triggering
(UPROBE_SWBP_ARM_INSN and UPROBE_SS_ARM_INSN) coincidentally share the
same encoding as a pair of unallocated 32-bit thumb instructions (not
UDF) when the condition code is 0b1111 (0xf). This in effect makes it
possible to trigger the uprobes functionality from thumb, and at that
using two unallocated instructions which are not permanently undefined.

Signed-off-by: Fredrik Strupe <fredrik@strupe.net>
Cc: stable@vger.kernel.org
Fixes: c7edc9e326d5 ("ARM: add uprobes support")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/probes/uprobes/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/probes/uprobes/core.c b/arch/arm/probes/uprobes/core.c
index c4b49b322e8a..f5f790c6e5f8 100644
--- a/arch/arm/probes/uprobes/core.c
+++ b/arch/arm/probes/uprobes/core.c
@@ -204,7 +204,7 @@ unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
 static struct undef_hook uprobes_arm_break_hook = {
 	.instr_mask	= 0x0fffffff,
 	.instr_val	= (UPROBE_SWBP_ARM_INSN & 0x0fffffff),
-	.cpsr_mask	= MODE_MASK,
+	.cpsr_mask	= (PSR_T_BIT | MODE_MASK),
 	.cpsr_val	= USR_MODE,
 	.fn		= uprobe_trap_handler,
 };
@@ -212,7 +212,7 @@ static struct undef_hook uprobes_arm_break_hook = {
 static struct undef_hook uprobes_arm_ss_hook = {
 	.instr_mask	= 0x0fffffff,
 	.instr_val	= (UPROBE_SS_ARM_INSN & 0x0fffffff),
-	.cpsr_mask	= MODE_MASK,
+	.cpsr_mask	= (PSR_T_BIT | MODE_MASK),
 	.cpsr_val	= USR_MODE,
 	.fn		= uprobe_trap_handler,
 };

From bf05bf16c76bb44ab5156223e1e58e26dfe30a88 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 18 Apr 2021 14:45:32 -0700
Subject: [PATCH 1820/1820] Linux 5.12-rc8

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 4730cf156f6b..bc19584fee59 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc7
+EXTRAVERSION = -rc8
 NAME = Frozen Wasteland
 
 # *DOCUMENTATION*