A few MIPS fixes for 4.18:

- A GPIO device name fix for a regression in v4.15-rc1.
 
   - An errata workaround for the BCM5300X platform.
 
   - A fix to ftrace function graph tracing, broken for a long time with
     the fix applying cleanly back as far as v3.17.
 
   - Addition of read barriers to in{b,w,l,q}() functions, matching
     behavior of other architectures & mirroring the equivalent addition
     to read{b,w,l,q} in v4.17-rc2.
 
 Plus changes to wire up new syscalls introduced in the 4.18 cycle:
 
   - Restartable sequences support is added, including MIPS support in
     the selftests.
 
   - io_pgetevents is wired up.
 -----BEGIN PGP SIGNATURE-----
 
 iIsEABYIADMWIQRgLjeFAZEXQzy86/s+p5+stXUA3QUCWy7dhBUccGF1bC5idXJ0
 b25AbWlwcy5jb20ACgkQPqefrLV1AN3jzAEA9QsaC/W2hsC/P4A49aNem1/LL2i+
 L6ZGhrquwdpGZHoBAIolXlc23LaMkeAVZGkHvgcJkxSnPGs3k1JuUMjP14EE
 =3P+z
 -----END PGP SIGNATURE-----

Merge tag 'mips_fixes_4.18_1' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux

Pull MIPS fixes from Paul Burton:
 "A few MIPS fixes for 4.18:

   - a GPIO device name fix for a regression in v4.15-rc1.

   - an errata workaround for the BCM5300X platform.

   - a fix to ftrace function graph tracing, broken for a long time with
     the fix applying cleanly back as far as v3.17.

   - addition of read barriers to in{b,w,l,q}() functions, matching
     behavior of other architectures & mirroring the equivalent addition
     to read{b,w,l,q} in v4.17-rc2.

  Plus changes to wire up new syscalls introduced in the 4.18 cycle:

   - Restartable sequences support is added, including MIPS support in
     the selftests.

   - io_pgetevents is wired up"

* tag 'mips_fixes_4.18_1' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux:
  MIPS: Wire up io_pgetevents syscall
  rseq/selftests: Implement MIPS support
  MIPS: Wire up the restartable sequences (rseq) syscall
  MIPS: Add syscall detection for restartable sequences
  MIPS: Add support for restartable sequences
  MIPS: io: Add barrier after register read in inX()
  mips: ftrace: fix static function graph tracing
  MIPS: BCM47XX: Enable 74K Core ExternalSync for PCIe erratum
  MIPS: pb44: Fix i2c-gpio GPIO descriptor table

arch/mips/Kconfig

@@ -65,6 +65,7 @@ config MIPS
 	select HAVE_OPROFILE
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN if 64BIT || !SMP

arch/mips/ath79/mach-pb44.c

@@ -34,7 +34,7 @@
 #define PB44_KEYS_DEBOUNCE_INTERVAL	(3 * PB44_KEYS_POLL_INTERVAL)
 
 static struct gpiod_lookup_table pb44_i2c_gpiod_table = {
-	.dev_id = "i2c-gpio",
+	.dev_id = "i2c-gpio.0",
 	.table = {
 		GPIO_LOOKUP_IDX("ath79-gpio", PB44_GPIO_I2C_SDA,
 				NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),

arch/mips/bcm47xx/setup.c

@@ -212,6 +212,12 @@ static int __init bcm47xx_cpu_fixes(void)
 		 */
 		if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706)
 			cpu_wait = NULL;
+
+		/*
+		 * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail"
+		 * Enable ExternalSync for sync instruction to take effect
+		 */
+		set_c0_config7(MIPS_CONF7_ES);
 		break;
 #endif
 	}

arch/mips/include/asm/io.h

@@ -414,6 +414,8 @@ static inline type pfx##in##bwlq##p(unsigned long port)			\
 	__val = *__addr;						\
 	slow;								\
 									\
+	/* prevent prefetching of coherent DMA data prematurely */	\
+	rmb();								\
 	return pfx##ioswab##bwlq(__addr, __val);			\
 }
 

arch/mips/include/asm/mipsregs.h

@@ -681,6 +681,8 @@
 #define MIPS_CONF7_WII		(_ULCAST_(1) << 31)
 
 #define MIPS_CONF7_RPS		(_ULCAST_(1) << 2)
+/* ExternalSync */
+#define MIPS_CONF7_ES		(_ULCAST_(1) << 8)
 
 #define MIPS_CONF7_IAR		(_ULCAST_(1) << 10)
 #define MIPS_CONF7_AR		(_ULCAST_(1) << 16)
@@ -2765,6 +2767,7 @@ __BUILD_SET_C0(status)
 __BUILD_SET_C0(cause)
 __BUILD_SET_C0(config)
 __BUILD_SET_C0(config5)
+__BUILD_SET_C0(config7)
 __BUILD_SET_C0(intcontrol)
 __BUILD_SET_C0(intctl)
 __BUILD_SET_C0(srsmap)

arch/mips/include/uapi/asm/unistd.h

@@ -388,17 +388,19 @@
 #define __NR_pkey_alloc			(__NR_Linux + 364)
 #define __NR_pkey_free			(__NR_Linux + 365)
 #define __NR_statx			(__NR_Linux + 366)
+#define __NR_rseq			(__NR_Linux + 367)
+#define __NR_io_pgetevents		(__NR_Linux + 368)
 
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		366
+#define __NR_Linux_syscalls		368
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		366
+#define __NR_O32_Linux_syscalls		368
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -733,16 +735,18 @@
 #define __NR_pkey_alloc			(__NR_Linux + 324)
 #define __NR_pkey_free			(__NR_Linux + 325)
 #define __NR_statx			(__NR_Linux + 326)
+#define __NR_rseq			(__NR_Linux + 327)
+#define __NR_io_pgetevents		(__NR_Linux + 328)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		326
+#define __NR_Linux_syscalls		328
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		326
+#define __NR_64_Linux_syscalls		328
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1081,15 +1085,17 @@
 #define __NR_pkey_alloc			(__NR_Linux + 328)
 #define __NR_pkey_free			(__NR_Linux + 329)
 #define __NR_statx			(__NR_Linux + 330)
+#define __NR_rseq			(__NR_Linux + 331)
+#define __NR_io_pgetevents		(__NR_Linux + 332)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		330
+#define __NR_Linux_syscalls		332
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		330
+#define __NR_N32_Linux_syscalls		332
 
 #endif /* _UAPI_ASM_UNISTD_H */

arch/mips/kernel/entry.S

@@ -79,6 +79,10 @@ FEXPORT(ret_from_fork)
 	jal	schedule_tail		# a0 = struct task_struct *prev
 
 FEXPORT(syscall_exit)
+#ifdef CONFIG_DEBUG_RSEQ
+	move	a0, sp
+	jal	rseq_syscall
+#endif
 	local_irq_disable		# make sure need_resched and
 					# signals dont change between
 					# sampling and return
@@ -141,6 +145,10 @@ work_notifysig:				# deal with pending signals and
 	j	resume_userspace_check
 
 FEXPORT(syscall_exit_partial)
+#ifdef CONFIG_DEBUG_RSEQ
+	move	a0, sp
+	jal	rseq_syscall
+#endif
 	local_irq_disable		# make sure need_resched doesn't
 					# change between and return
 	LONG_L	a2, TI_FLAGS($28)	# current->work

arch/mips/kernel/mcount.S

@@ -119,10 +119,20 @@ NESTED(_mcount, PT_SIZE, ra)
 EXPORT_SYMBOL(_mcount)
 	PTR_LA	t1, ftrace_stub
 	PTR_L	t2, ftrace_trace_function /* Prepare t2 for (1) */
-	bne	t1, t2, static_trace
+	beq	t1, t2, fgraph_trace
 	 nop
 
+	MCOUNT_SAVE_REGS
+
+	move	a0, ra		/* arg1: self return address */
+	jalr	t2		/* (1) call *ftrace_trace_function */
+	 move	a1, AT		/* arg2: parent's return address */
+
+	MCOUNT_RESTORE_REGS
+
+fgraph_trace:
 #ifdef	CONFIG_FUNCTION_GRAPH_TRACER
+	PTR_LA	t1, ftrace_stub
 	PTR_L	t3, ftrace_graph_return
 	bne	t1, t3, ftrace_graph_caller
 	 nop
@@ -131,24 +141,11 @@ EXPORT_SYMBOL(_mcount)
 	bne	t1, t3, ftrace_graph_caller
 	 nop
 #endif
-	b	ftrace_stub
-#ifdef CONFIG_32BIT
-	 addiu sp, sp, 8
-#else
-	 nop
-#endif
 
-static_trace:
-	MCOUNT_SAVE_REGS
-
-	move	a0, ra		/* arg1: self return address */
-	jalr	t2		/* (1) call *ftrace_trace_function */
-	 move	a1, AT		/* arg2: parent's return address */
-
-	MCOUNT_RESTORE_REGS
 #ifdef CONFIG_32BIT
 	addiu sp, sp, 8
 #endif
+
 	.globl ftrace_stub
 ftrace_stub:
 	RETURN_BACK

arch/mips/kernel/scall32-o32.S

@@ -590,3 +590,5 @@ EXPORT(sys_call_table)
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 4365 */
 	PTR	sys_statx
+	PTR	sys_rseq
+	PTR	sys_io_pgetevents

arch/mips/kernel/scall64-64.S

@@ -439,4 +439,6 @@ EXPORT(sys_call_table)
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 5325 */
 	PTR	sys_statx
+	PTR	sys_rseq
+	PTR	sys_io_pgetevents
 	.size	sys_call_table,.-sys_call_table

arch/mips/kernel/scall64-n32.S

@@ -434,4 +434,6 @@ EXPORT(sysn32_call_table)
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free
 	PTR	sys_statx			/* 6330 */
+	PTR	sys_rseq
+	PTR	compat_sys_io_pgetevents
 	.size	sysn32_call_table,.-sysn32_call_table

arch/mips/kernel/scall64-o32.S

@@ -583,4 +583,6 @@ EXPORT(sys32_call_table)
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 4365 */
 	PTR	sys_statx
+	PTR	sys_rseq
+	PTR	compat_sys_io_pgetevents
 	.size	sys32_call_table,.-sys32_call_table

arch/mips/kernel/signal.c

@@ -801,6 +801,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		regs->regs[0] = 0;		/* Don't deal with this again.	*/
 	}
 
+	rseq_signal_deliver(regs);
+
 	if (sig_uses_siginfo(&ksig->ka, abi))
 		ret = abi->setup_rt_frame(vdso + abi->vdso->off_rt_sigreturn,
 					  ksig, regs, oldset);
@@ -868,6 +870,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
+		rseq_handle_notify_resume(regs);
 	}
 
 	user_enter();

tools/testing/selftests/rseq/param_test.c

@@ -137,6 +137,30 @@ unsigned int yield_mod_cnt, nr_abort;
 	"subic. %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG ", 1\n\t" \
 	"bne 222b\n\t" \
 	"333:\n\t"
+
+#elif defined(__mips__)
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1]"m"(loop_cnt[1]) \
+	, [loop_cnt_2]"m"(loop_cnt[2]) \
+	, [loop_cnt_3]"m"(loop_cnt[3]) \
+	, [loop_cnt_4]"m"(loop_cnt[4]) \
+	, [loop_cnt_5]"m"(loop_cnt[5]) \
+	, [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG	"$5"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"lw " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"beqz " INJECT_ASM_REG ", 333f\n\t" \
+	"222:\n\t" \
+	"addiu " INJECT_ASM_REG ", -1\n\t" \
+	"bnez " INJECT_ASM_REG ", 222b\n\t" \
+	"333:\n\t"
+
 #else
 #error unsupported target
 #endif

tools/testing/selftests/rseq/rseq-mips.h

@@ -0,0 +1,725 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Author: Paul Burton <paul.burton@mips.com>
+ * (C) Copyright 2018 MIPS Tech LLC
+ *
+ * Based on rseq-arm.h:
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#define RSEQ_SIG	0x53053053
+
+#define rseq_smp_mb()	__asm__ __volatile__ ("sync" ::: "memory")
+#define rseq_smp_rmb()	rseq_smp_mb()
+#define rseq_smp_wmb()	rseq_smp_mb()
+
+#define rseq_smp_load_acquire(p)					\
+__extension__ ({							\
+	__typeof(*p) ____p1 = RSEQ_READ_ONCE(*p);			\
+	rseq_smp_mb();							\
+	____p1;								\
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()	rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)					\
+do {									\
+	rseq_smp_mb();							\
+	RSEQ_WRITE_ONCE(*p, v);						\
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#if _MIPS_SZLONG == 64
+# define LONG			".dword"
+# define LONG_LA		"dla"
+# define LONG_L			"ld"
+# define LONG_S			"sd"
+# define LONG_ADDI		"daddiu"
+# define U32_U64_PAD(x)		x
+#elif _MIPS_SZLONG == 32
+# define LONG			".word"
+# define LONG_LA		"la"
+# define LONG_L			"lw"
+# define LONG_S			"sw"
+# define LONG_ADDI		"addiu"
+# ifdef __BIG_ENDIAN
+#  define U32_U64_PAD(x)	"0x0, " x
+# else
+#  define U32_U64_PAD(x)	x ", 0x0"
+# endif
+#else
+# error unsupported _MIPS_SZLONG
+#endif
+
+#define __RSEQ_ASM_DEFINE_TABLE(version, flags,	start_ip, \
+				post_commit_offset, abort_ip) \
+		".pushsection __rseq_table, \"aw\"\n\t" \
+		".balign 32\n\t" \
+		".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(start_ip)) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(post_commit_offset)) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(abort_ip)) "\n\t" \
+		".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_TABLE(start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_TABLE(0x0, 0x0, start_ip, \
+				(post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \
+		RSEQ_INJECT_ASM(1) \
+		LONG_LA " $4, " __rseq_str(cs_label) "\n\t" \
+		LONG_S  " $4, %[" __rseq_str(rseq_cs) "]\n\t" \
+		__rseq_str(label) ":\n\t"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \
+		RSEQ_INJECT_ASM(2) \
+		"lw  $4, %[" __rseq_str(current_cpu_id) "]\n\t" \
+		"bne $4, %[" __rseq_str(cpu_id) "], " __rseq_str(label) "\n\t"
+
+#define __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \
+				abort_label, version, flags, \
+				start_ip, post_commit_offset, abort_ip) \
+		".balign 32\n\t" \
+		__rseq_str(table_label) ":\n\t" \
+		".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(start_ip)) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(post_commit_offset)) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(abort_ip)) "\n\t" \
+		".word " __rseq_str(RSEQ_SIG) "\n\t" \
+		__rseq_str(label) ":\n\t" \
+		teardown \
+		"b %l[" __rseq_str(abort_label) "]\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, abort_label, \
+			      start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \
+				abort_label, 0x0, 0x0, start_ip, \
+				(post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label) \
+		__rseq_str(label) ":\n\t" \
+		teardown \
+		"b %l[" __rseq_str(cmpfail_label) "]\n\t"
+
+#define rseq_workaround_gcc_asm_size_guess()	__asm__ __volatile__("")
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[error2]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       off_t voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"beq $4, %[expectnot], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " $4, %[v]\n\t"
+		"beq $4, %[expectnot], %l[error2]\n\t"
+#endif
+		LONG_S " $4, %[load]\n\t"
+		LONG_ADDI " $4, %[voffp]\n\t"
+		LONG_L " $4, 0($4)\n\t"
+		/* final store */
+		LONG_S " $4, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [voffp]		"Ir" (voffp),
+		  [load]		"m" (*load)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+		LONG_L " $4, %[v]\n\t"
+		LONG_ADDI " $4, %[count]\n\t"
+		/* final store */
+		LONG_S " $4, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(4)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"m" (*v),
+		  [count]		"Ir" (count)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+				 intptr_t *v2, intptr_t newv2,
+				 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[error2]\n\t"
+#endif
+		/* try store */
+		LONG_S " %[newv2], %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+					 intptr_t *v2, intptr_t newv2,
+					 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[error2]\n\t"
+#endif
+		/* try store */
+		LONG_S " %[newv2], %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		"sync\n\t"	/* full sync provides store-release */
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+			      intptr_t *v2, intptr_t expect2,
+			      intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+		LONG_L " $4, %[v2]\n\t"
+		"bne $4, %[expect2], %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], %l[error2]\n\t"
+		LONG_L " $4, %[v2]\n\t"
+		"bne $4, %[expect2], %l[error3]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		"b 5f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+		"5:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* cmp2 input */
+		  [v2]			"m" (*v2),
+		  [expect2]		"r" (expect2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("1st expected value comparison failed");
+error3:
+	rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+				 void *dst, void *src, size_t len,
+				 intptr_t newv, int cpu)
+{
+	uintptr_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		LONG_S " %[src], %[rseq_scratch0]\n\t"
+		LONG_S "  %[dst], %[rseq_scratch1]\n\t"
+		LONG_S " %[len], %[rseq_scratch2]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], 7f\n\t"
+#endif
+		/* try memcpy */
+		"beqz %[len], 333f\n\t" \
+		"222:\n\t" \
+		"lb   $4, 0(%[src])\n\t" \
+		"sb   $4, 0(%[dst])\n\t" \
+		LONG_ADDI " %[src], 1\n\t" \
+		LONG_ADDI " %[dst], 1\n\t" \
+		LONG_ADDI " %[len], -1\n\t" \
+		"bnez %[len], 222b\n\t" \
+		"333:\n\t" \
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		LONG_L " %[len], %[rseq_scratch2]\n\t"
+		LONG_L " %[dst], %[rseq_scratch1]\n\t"
+		LONG_L " %[src], %[rseq_scratch0]\n\t"
+		"b 8f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4,
+				      /* teardown */
+				      LONG_L " %[len], %[rseq_scratch2]\n\t"
+				      LONG_L " %[dst], %[rseq_scratch1]\n\t"
+				      LONG_L " %[src], %[rseq_scratch0]\n\t",
+				      abort, 1b, 2b, 4f)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					error2)
+#endif
+		"8:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv),
+		  /* try memcpy input */
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len),
+		  [rseq_scratch0]	"m" (rseq_scratch[0]),
+		  [rseq_scratch1]	"m" (rseq_scratch[1]),
+		  [rseq_scratch2]	"m" (rseq_scratch[2])
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_workaround_gcc_asm_size_guess();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_workaround_gcc_asm_size_guess();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+					 void *dst, void *src, size_t len,
+					 intptr_t newv, int cpu)
+{
+	uintptr_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	rseq_workaround_gcc_asm_size_guess();
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+		LONG_S " %[src], %[rseq_scratch0]\n\t"
+		LONG_S " %[dst], %[rseq_scratch1]\n\t"
+		LONG_S " %[len], %[rseq_scratch2]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+		LONG_L " $4, %[v]\n\t"
+		"bne $4, %[expect], 7f\n\t"
+#endif
+		/* try memcpy */
+		"beqz %[len], 333f\n\t" \
+		"222:\n\t" \
+		"lb   $4, 0(%[src])\n\t" \
+		"sb   $4, 0(%[dst])\n\t" \
+		LONG_ADDI " %[src], 1\n\t" \
+		LONG_ADDI " %[dst], 1\n\t" \
+		LONG_ADDI " %[len], -1\n\t" \
+		"bnez %[len], 222b\n\t" \
+		"333:\n\t" \
+		RSEQ_INJECT_ASM(5)
+		"sync\n\t"	/* full sync provides store-release */
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		LONG_L " %[len], %[rseq_scratch2]\n\t"
+		LONG_L " %[dst], %[rseq_scratch1]\n\t"
+		LONG_L " %[src], %[rseq_scratch0]\n\t"
+		"b 8f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4,
+				      /* teardown */
+				      LONG_L " %[len], %[rseq_scratch2]\n\t"
+				      LONG_L " %[dst], %[rseq_scratch1]\n\t"
+				      LONG_L " %[src], %[rseq_scratch0]\n\t",
+				      abort, 1b, 2b, 4f)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+					/* teardown */
+					LONG_L " %[len], %[rseq_scratch2]\n\t"
+					LONG_L " %[dst], %[rseq_scratch1]\n\t"
+					LONG_L " %[src], %[rseq_scratch0]\n\t",
+					error2)
+#endif
+		"8:\n\t"
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv),
+		  /* try memcpy input */
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len),
+		  [rseq_scratch0]	"m" (rseq_scratch[0]),
+		  [rseq_scratch1]	"m" (rseq_scratch[1]),
+		  [rseq_scratch2]	"m" (rseq_scratch[2])
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_workaround_gcc_asm_size_guess();
+	return 0;
+abort:
+	rseq_workaround_gcc_asm_size_guess();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_workaround_gcc_asm_size_guess();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_workaround_gcc_asm_size_guess();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_workaround_gcc_asm_size_guess();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */

tools/testing/selftests/rseq/rseq.h

@@ -73,6 +73,8 @@ extern __thread volatile struct rseq __rseq_abi;
 #include <rseq-arm.h>
 #elif defined(__PPC__)
 #include <rseq-ppc.h>
+#elif defined(__mips__)
+#include <rseq-mips.h>
 #else
 #error unsupported target
 #endif