powerpc/book3s64/pkeys: Store/restore userspace AMR/IAMR correctly on entry and exit from kernel

This prepare kernel to operate with a different value than userspace AMR/IAMR.
For this, AMR/IAMR need to be saved and restored on entry and return from the
kernel.

With KUAP we modify kernel AMR when accessing user address from the kernel
via copy_to/from_user interfaces. We don't need to modify IAMR value in
similar fashion.

If MMU_FTR_PKEY is enabled we need to save AMR/IAMR in pt_regs on entering
kernel from userspace. If not we can assume that AMR/IAMR is not modified
from userspace.

We need to save AMR if we have MMU_FTR_BOOK3S_KUAP feature enabled and we are
interrupted within kernel. This is required so that if we get interrupted
within copy_to/from_user we continue with the right AMR value.

If we hae MMU_FTR_BOOK3S_KUEP enabled we need to restore IAMR on
return to userspace beause kernel will be running with a different
IAMR value.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201127044424.40686-11-aneesh.kumar@linux.ibm.com

arch/powerpc/include/asm/book3s/64/kup.h

@@ -13,17 +13,46 @@
 
 #ifdef __ASSEMBLY__
 
-.macro kuap_restore_amr	gpr1, gpr2
+.macro kuap_user_restore gpr1
-#ifdef CONFIG_PPC_KUAP
+#if defined(CONFIG_PPC_PKEY)
 	BEGIN_MMU_FTR_SECTION_NESTED(67)
-	mfspr	\gpr1, SPRN_AMR
+	/*
+	 * AMR and IAMR are going to be different when
+	 * returning to userspace.
+	 */
+	ld	\gpr1, STACK_REGS_AMR(r1)
+	isync
+	mtspr	SPRN_AMR, \gpr1
+	/*
+	 * Restore IAMR only when returning to userspace
+	 */
+	ld	\gpr1, STACK_REGS_IAMR(r1)
+	mtspr	SPRN_IAMR, \gpr1
+
+	/* No isync required, see kuap_user_restore() */
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_PKEY, 67)
+#endif
+.endm
+
+.macro kuap_kernel_restore	gpr1, gpr2
+#if defined(CONFIG_PPC_PKEY)
+
+	BEGIN_MMU_FTR_SECTION_NESTED(67)
+	/*
+	 * AMR is going to be mostly the same since we are
+	 * returning to the kernel. Compare and do a mtspr.
+	 */
 	ld	\gpr2, STACK_REGS_AMR(r1)
+	mfspr	\gpr1, SPRN_AMR
 	cmpd	\gpr1, \gpr2
-	beq	998f
+	beq	100f
 	isync
 	mtspr	SPRN_AMR, \gpr2
-	/* No isync required, see kuap_restore_amr() */
+	/*
-998:
+	 * No isync required, see kuap_restore_amr()
+	 * No need to restore IAMR when returning to kernel space.
+	 */
+100:
 	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUAP, 67)
 #endif
 .endm
@@ -42,23 +71,98 @@
 .endm
 #endif
 
+/*
+ *	if (pkey) {
+ *
+ *		save AMR -> stack;
+ *		if (kuap) {
+ *			if (AMR != BLOCKED)
+ *				KUAP_BLOCKED -> AMR;
+ *		}
+ *		if (from_user) {
+ *			save IAMR -> stack;
+ *			if (kuep) {
+ *				KUEP_BLOCKED ->IAMR
+ *			}
+ *		}
+ *		return;
+ *	}
+ *
+ *	if (kuap) {
+ *		if (from_kernel) {
+ *			save AMR -> stack;
+ *			if (AMR != BLOCKED)
+ *				KUAP_BLOCKED -> AMR;
+ *		}
+ *
+ *	}
+ */
 .macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr
-#ifdef CONFIG_PPC_KUAP
+#if defined(CONFIG_PPC_PKEY)
+
+	/*
+	 * if both pkey and kuap is disabled, nothing to do
+	 */
+	BEGIN_MMU_FTR_SECTION_NESTED(68)
+	b	100f  // skip_save_amr
+	END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY | MMU_FTR_BOOK3S_KUAP, 68)
+
+	/*
+	 * if pkey is disabled and we are entering from userspace
+	 * don't do anything.
+	 */
 	BEGIN_MMU_FTR_SECTION_NESTED(67)
 	.ifnb \msr_pr_cr
-	bne	\msr_pr_cr, 99f
+	/*
+	 * Without pkey we are not changing AMR outside the kernel
+	 * hence skip this completely.
+	 */
+	bne	\msr_pr_cr, 100f  // from userspace
 	.endif
+        END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY, 67)
+
+	/*
+	 * pkey is enabled or pkey is disabled but entering from kernel
+	 */
 	mfspr	\gpr1, SPRN_AMR
 	std	\gpr1, STACK_REGS_AMR(r1)
-	li	\gpr2, (AMR_KUAP_BLOCKED >> AMR_KUAP_SHIFT)
+
-	sldi	\gpr2, \gpr2, AMR_KUAP_SHIFT
+	/*
+	 * update kernel AMR with AMR_KUAP_BLOCKED only
+	 * if KUAP feature is enabled
+	 */
+	BEGIN_MMU_FTR_SECTION_NESTED(69)
+	LOAD_REG_IMMEDIATE(\gpr2, AMR_KUAP_BLOCKED)
 	cmpd	\use_cr, \gpr1, \gpr2
-	beq	\use_cr, 99f
+	beq	\use_cr, 102f
-	// We don't isync here because we very recently entered via rfid
+	/*
+	 * We don't isync here because we very recently entered via an interrupt
+	 */
 	mtspr	SPRN_AMR, \gpr2
 	isync
-99:
+102:
-	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUAP, 67)
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUAP, 69)
+
+	/*
+	 * if entering from kernel we don't need save IAMR
+	 */
+	.ifnb \msr_pr_cr
+	beq	\msr_pr_cr, 100f // from kernel space
+	mfspr	\gpr1, SPRN_IAMR
+	std	\gpr1, STACK_REGS_IAMR(r1)
+
+	/*
+	 * update kernel IAMR with AMR_KUEP_BLOCKED only
+	 * if KUEP feature is enabled
+	 */
+	BEGIN_MMU_FTR_SECTION_NESTED(70)
+	LOAD_REG_IMMEDIATE(\gpr2, AMR_KUEP_BLOCKED)
+	mtspr	SPRN_IAMR, \gpr2
+	isync
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUEP, 70)
+	.endif
+
+100: // skip_save_amr
 #endif
 .endm
 
@@ -68,22 +172,42 @@
 
 DECLARE_STATIC_KEY_FALSE(uaccess_flush_key);
 
-#ifdef CONFIG_PPC_KUAP
+#ifdef CONFIG_PPC_PKEY
 
 #include <asm/mmu.h>
 #include <asm/ptrace.h>
 
-static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr)
+static inline void kuap_user_restore(struct pt_regs *regs)
 {
-	if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP) && unlikely(regs->kuap != amr)) {
+	if (!mmu_has_feature(MMU_FTR_PKEY))
-		isync();
+		return;
-		mtspr(SPRN_AMR, regs->kuap);
+
-		/*
+	isync();
-		 * No isync required here because we are about to RFI back to
+	mtspr(SPRN_AMR, regs->amr);
-		 * previous context before any user accesses would be made,
+	mtspr(SPRN_IAMR, regs->iamr);
-		 * which is a CSI.
+	/*
-		 */
+	 * No isync required here because we are about to rfi
+	 * back to previous context before any user accesses
+	 * would be made, which is a CSI.
+	 */
+}
+static inline void kuap_kernel_restore(struct pt_regs *regs,
+					   unsigned long amr)
+{
+	if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) {
+		if (unlikely(regs->amr != amr)) {
+			isync();
+			mtspr(SPRN_AMR, regs->amr);
+			/*
+			 * No isync required here because we are about to rfi
+			 * back to previous context before any user accesses
+			 * would be made, which is a CSI.
+			 */
+		}
 	}
+	/*
+	 * No need to restore IAMR when returning to kernel space.
+	 */
 }
 
 static inline unsigned long kuap_get_and_check_amr(void)
@@ -97,6 +221,26 @@ static inline unsigned long kuap_get_and_check_amr(void)
 	return 0;
 }
 
+#else /* CONFIG_PPC_PKEY */
+
+static inline void kuap_user_restore(struct pt_regs *regs)
+{
+}
+
+static inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long amr)
+{
+}
+
+static inline unsigned long kuap_get_and_check_amr(void)
+{
+	return 0;
+}
+
+#endif /* CONFIG_PPC_PKEY */
+
+
+#ifdef CONFIG_PPC_KUAP
+
 static inline void kuap_check_amr(void)
 {
 	if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && mmu_has_feature(MMU_FTR_BOOK3S_KUAP))
@@ -145,21 +289,6 @@ bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 		    (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
 		    "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read");
 }
-#else /* CONFIG_PPC_KUAP */
-static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) { }
-
-static inline unsigned long kuap_get_and_check_amr(void)
-{
-	return 0UL;
-}
-
-static inline unsigned long get_kuap(void)
-{
-	return AMR_KUAP_BLOCKED;
-}
-
-static inline void set_kuap(unsigned long value) { }
-#endif /* !CONFIG_PPC_KUAP */
 
 static __always_inline void allow_user_access(void __user *to, const void __user *from,
 					      unsigned long size, unsigned long dir)
@@ -176,6 +305,21 @@ static __always_inline void allow_user_access(void __user *to, const void __user
 		BUILD_BUG();
 }
 
+#else /* CONFIG_PPC_KUAP */
+
+static inline unsigned long get_kuap(void)
+{
+	return AMR_KUAP_BLOCKED;
+}
+
+static inline void set_kuap(unsigned long value) { }
+
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      unsigned long size, unsigned long dir)
+{ }
+
+#endif /* !CONFIG_PPC_KUAP */
+
 static inline void prevent_user_access(void __user *to, const void __user *from,
 				       unsigned long size, unsigned long dir)
 {

arch/powerpc/include/asm/ptrace.h

@@ -61,8 +61,11 @@ struct pt_regs
 				unsigned long amr;
 #endif
 			};
+#ifdef CONFIG_PPC_PKEY
+			unsigned long iamr;
+#endif
 		};
-		unsigned long __pad[2];	/* Maintain 16 byte interrupt stack alignment */
+		unsigned long __pad[4];	/* Maintain 16 byte interrupt stack alignment */
 	};
 };
 #endif

arch/powerpc/kernel/asm-offsets.c

@@ -358,11 +358,13 @@ int main(void)
 
 #ifdef CONFIG_PPC_PKEY
 	STACK_PT_REGS_OFFSET(STACK_REGS_AMR, amr);
+	STACK_PT_REGS_OFFSET(STACK_REGS_IAMR, iamr);
 #endif
 #ifdef CONFIG_PPC_KUAP
 	STACK_PT_REGS_OFFSET(STACK_REGS_KUAP, kuap);
 #endif
 
+
 #if defined(CONFIG_PPC32)
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
 	DEFINE(EXC_LVL_SIZE, STACK_EXC_LVL_FRAME_SIZE);

arch/powerpc/kernel/entry_64.S

@@ -653,8 +653,8 @@ _ASM_NOKPROBE_SYMBOL(fast_interrupt_return)
 	kuap_check_amr r3, r4
 	ld	r5,_MSR(r1)
 	andi.	r0,r5,MSR_PR
-	bne	.Lfast_user_interrupt_return
+	bne	.Lfast_user_interrupt_return_amr
-	kuap_restore_amr r3, r4
+	kuap_kernel_restore r3, r4
 	andi.	r0,r5,MSR_RI
 	li	r3,0 /* 0 return value, no EMULATE_STACK_STORE */
 	bne+	.Lfast_kernel_interrupt_return
@@ -674,6 +674,8 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
 	cmpdi	r3,0
 	bne-	.Lrestore_nvgprs
 
+.Lfast_user_interrupt_return_amr:
+	kuap_user_restore r3
 .Lfast_user_interrupt_return:
 	ld	r11,_NIP(r1)
 	ld	r12,_MSR(r1)

arch/powerpc/kernel/exceptions-64s.S

@@ -1059,7 +1059,7 @@ EXC_COMMON_BEGIN(system_reset_common)
 	ld	r10,SOFTE(r1)
 	stb	r10,PACAIRQSOFTMASK(r13)
 
-	kuap_restore_amr r9, r10
+	kuap_kernel_restore r9, r10
 	EXCEPTION_RESTORE_REGS
 	RFI_TO_USER_OR_KERNEL
 
@@ -2875,7 +2875,7 @@ EXC_COMMON_BEGIN(soft_nmi_common)
 	ld	r10,SOFTE(r1)
 	stb	r10,PACAIRQSOFTMASK(r13)
 
-	kuap_restore_amr r9, r10
+	kuap_kernel_restore r9, r10
 	EXCEPTION_RESTORE_REGS hsrr=0
 	RFI_TO_KERNEL
 

arch/powerpc/kernel/syscall_64.c

@@ -35,7 +35,25 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	BUG_ON(!FULL_REGS(regs));
 	BUG_ON(regs->softe != IRQS_ENABLED);
 
-	kuap_check_amr();
+#ifdef CONFIG_PPC_PKEY
+	if (mmu_has_feature(MMU_FTR_PKEY)) {
+		unsigned long amr, iamr;
+		/*
+		 * When entering from userspace we mostly have the AMR/IAMR
+		 * different from kernel default values. Hence don't compare.
+		 */
+		amr = mfspr(SPRN_AMR);
+		iamr = mfspr(SPRN_IAMR);
+		regs->amr  = amr;
+		regs->iamr = iamr;
+		if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP))
+			mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
+		if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP))
+			mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED);
+		isync();
+	} else
+#endif
+		kuap_check_amr();
 
 	account_cpu_user_entry();
 
@@ -245,6 +263,12 @@ again:
 
 	account_cpu_user_exit();
 
+#ifdef CONFIG_PPC_BOOK3S /* BOOK3E not yet using this */
+	/*
+	 * We do this at the end so that we do context switch with KERNEL AMR
+	 */
+	kuap_user_restore(regs);
+#endif
 	return ret;
 }
 
@@ -330,6 +354,10 @@ again:
 
 	account_cpu_user_exit();
 
+	/*
+	 * We do this at the end so that we do context switch with KERNEL AMR
+	 */
+	kuap_user_restore(regs);
 	return ret;
 }
 
@@ -400,7 +428,7 @@ again:
 	 * which would cause Read-After-Write stalls. Hence, we take the AMR
 	 * value from the check above.
 	 */
-	kuap_restore_amr(regs, amr);
+	kuap_kernel_restore(regs, amr);
 
 	return ret;
 }