Adding upstream version 5.10.209.upstream/5.10.209upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

22 files changed, 7859 insertions, 0 deletions

diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore
new file mode 100644
index 000000000..5910888eb
--- /dev/null
+++ b/tools/testing/selftests/rseq/.gitignore
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+basic_percpu_ops_test
+basic_test
+basic_rseq_op_test
+param_test
+param_test_benchmark
+param_test_compare_twice
diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
new file mode 100644
index 000000000..82ceca6aa
--- /dev/null
+++ b/tools/testing/selftests/rseq/Makefile
@@ -0,0 +1,40 @@
+# SPDX-License-Identifier: GPL-2.0+ OR MIT
+
+ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),)
+CLANG_FLAGS += -no-integrated-as
+endif
+
+top_srcdir = ../../../..
+
+CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \
+	  $(CLANG_FLAGS) -I$(top_srcdir)/tools/include
+LDLIBS += -lpthread -ldl
+
+# Own dependencies because we only want to build against 1st prerequisite, but
+# still track changes to header files and depend on shared object.
+OVERRIDE_TARGETS = 1
+
+TEST_GEN_PROGS = basic_test basic_percpu_ops_test param_test \
+		param_test_benchmark param_test_compare_twice
+
+TEST_GEN_PROGS_EXTENDED = librseq.so
+
+TEST_PROGS = run_param_test.sh
+
+TEST_FILES := settings
+
+include ../lib.mk
+
+$(OUTPUT)/librseq.so: rseq.c rseq.h rseq-*.h
+	$(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@
+
+$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h
+	$(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@
+
+$(OUTPUT)/param_test_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					rseq.h rseq-*.h
+	$(CC) $(CFLAGS) -DBENCHMARK $< $(LDLIBS) -lrseq -o $@
+
+$(OUTPUT)/param_test_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					rseq.h rseq-*.h
+	$(CC) $(CFLAGS) -DRSEQ_COMPARE_TWICE $< $(LDLIBS) -lrseq -o $@
diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
new file mode 100644
index 000000000..517756afc
--- /dev/null
+++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
@@ -0,0 +1,311 @@
+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stddef.h>
+
+#include "../kselftest.h"
+#include "rseq.h"
+
+struct percpu_lock_entry {
+	intptr_t v;
+} __attribute__((aligned(128)));
+
+struct percpu_lock {
+	struct percpu_lock_entry c[CPU_SETSIZE];
+};
+
+struct test_data_entry {
+	intptr_t count;
+} __attribute__((aligned(128)));
+
+struct spinlock_test_data {
+	struct percpu_lock lock;
+	struct test_data_entry c[CPU_SETSIZE];
+	int reps;
+};
+
+struct percpu_list_node {
+	intptr_t data;
+	struct percpu_list_node *next;
+};
+
+struct percpu_list_entry {
+	struct percpu_list_node *head;
+} __attribute__((aligned(128)));
+
+struct percpu_list {
+	struct percpu_list_entry c[CPU_SETSIZE];
+};
+
+/* A simple percpu spinlock.  Returns the cpu lock was acquired on. */
+int rseq_this_cpu_lock(struct percpu_lock *lock)
+{
+	int cpu;
+
+	for (;;) {
+		int ret;
+
+		cpu = rseq_cpu_start();
+		ret = rseq_cmpeqv_storev(&lock->c[cpu].v,
+					 0, 1, cpu);
+		if (rseq_likely(!ret))
+			break;
+		/* Retry if comparison fails or rseq aborts. */
+	}
+	/*
+	 * Acquire semantic when taking lock after control dependency.
+	 * Matches rseq_smp_store_release().
+	 */
+	rseq_smp_acquire__after_ctrl_dep();
+	return cpu;
+}
+
+void rseq_percpu_unlock(struct percpu_lock *lock, int cpu)
+{
+	assert(lock->c[cpu].v == 1);
+	/*
+	 * Release lock, with release semantic. Matches
+	 * rseq_smp_acquire__after_ctrl_dep().
+	 */
+	rseq_smp_store_release(&lock->c[cpu].v, 0);
+}
+
+void *test_percpu_spinlock_thread(void *arg)
+{
+	struct spinlock_test_data *data = arg;
+	int i, cpu;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+	for (i = 0; i < data->reps; i++) {
+		cpu = rseq_this_cpu_lock(&data->lock);
+		data->c[cpu].count++;
+		rseq_percpu_unlock(&data->lock, cpu);
+	}
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	return NULL;
+}
+
+/*
+ * A simple test which implements a sharded counter using a per-cpu
+ * lock.  Obviously real applications might prefer to simply use a
+ * per-cpu increment; however, this is reasonable for a test and the
+ * lock can be extended to synchronize more complicated operations.
+ */
+void test_percpu_spinlock(void)
+{
+	const int num_threads = 200;
+	int i;
+	uint64_t sum;
+	pthread_t test_threads[num_threads];
+	struct spinlock_test_data data;
+
+	memset(&data, 0, sizeof(data));
+	data.reps = 5000;
+
+	for (i = 0; i < num_threads; i++)
+		pthread_create(&test_threads[i], NULL,
+			       test_percpu_spinlock_thread, &data);
+
+	for (i = 0; i < num_threads; i++)
+		pthread_join(test_threads[i], NULL);
+
+	sum = 0;
+	for (i = 0; i < CPU_SETSIZE; i++)
+		sum += data.c[i].count;
+
+	assert(sum == (uint64_t)data.reps * num_threads);
+}
+
+void this_cpu_list_push(struct percpu_list *list,
+			struct percpu_list_node *node,
+			int *_cpu)
+{
+	int cpu;
+
+	for (;;) {
+		intptr_t *targetptr, newval, expect;
+		int ret;
+
+		cpu = rseq_cpu_start();
+		/* Load list->c[cpu].head with single-copy atomicity. */
+		expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head);
+		newval = (intptr_t)node;
+		targetptr = (intptr_t *)&list->c[cpu].head;
+		node->next = (struct percpu_list_node *)expect;
+		ret = rseq_cmpeqv_storev(targetptr, expect, newval, cpu);
+		if (rseq_likely(!ret))
+			break;
+		/* Retry if comparison fails or rseq aborts. */
+	}
+	if (_cpu)
+		*_cpu = cpu;
+}
+
+/*
+ * Unlike a traditional lock-less linked list; the availability of a
+ * rseq primitive allows us to implement pop without concerns over
+ * ABA-type races.
+ */
+struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
+					   int *_cpu)
+{
+	for (;;) {
+		struct percpu_list_node *head;
+		intptr_t *targetptr, expectnot, *load;
+		long offset;
+		int ret, cpu;
+
+		cpu = rseq_cpu_start();
+		targetptr = (intptr_t *)&list->c[cpu].head;
+		expectnot = (intptr_t)NULL;
+		offset = offsetof(struct percpu_list_node, next);
+		load = (intptr_t *)&head;
+		ret = rseq_cmpnev_storeoffp_load(targetptr, expectnot,
+						 offset, load, cpu);
+		if (rseq_likely(!ret)) {
+			if (_cpu)
+				*_cpu = cpu;
+			return head;
+		}
+		if (ret > 0)
+			return NULL;
+		/* Retry if rseq aborts. */
+	}
+}
+
+/*
+ * __percpu_list_pop is not safe against concurrent accesses. Should
+ * only be used on lists that are not concurrently modified.
+ */
+struct percpu_list_node *__percpu_list_pop(struct percpu_list *list, int cpu)
+{
+	struct percpu_list_node *node;
+
+	node = list->c[cpu].head;
+	if (!node)
+		return NULL;
+	list->c[cpu].head = node->next;
+	return node;
+}
+
+void *test_percpu_list_thread(void *arg)
+{
+	int i;
+	struct percpu_list *list = (struct percpu_list *)arg;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	for (i = 0; i < 100000; i++) {
+		struct percpu_list_node *node;
+
+		node = this_cpu_list_pop(list, NULL);
+		sched_yield();  /* encourage shuffling */
+		if (node)
+			this_cpu_list_push(list, node, NULL);
+	}
+
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu linked list from many threads.  */
+void test_percpu_list(void)
+{
+	int i, j;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_list list;
+	pthread_t test_threads[200];
+	cpu_set_t allowed_cpus;
+
+	memset(&list, 0, sizeof(list));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		for (j = 1; j <= 100; j++) {
+			struct percpu_list_node *node;
+
+			expected_sum += j;
+
+			node = malloc(sizeof(*node));
+			assert(node);
+			node->data = j;
+			node->next = list.c[i].head;
+			list.c[i].head = node;
+		}
+	}
+
+	for (i = 0; i < 200; i++)
+		pthread_create(&test_threads[i], NULL,
+		       test_percpu_list_thread, &list);
+
+	for (i = 0; i < 200; i++)
+		pthread_join(test_threads[i], NULL);
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_list_node *node;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while ((node = __percpu_list_pop(&list, i))) {
+			sum += node->data;
+			free(node);
+		}
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+int main(int argc, char **argv)
+{
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		goto error;
+	}
+	printf("spinlock\n");
+	test_percpu_spinlock();
+	printf("percpu_list\n");
+	test_percpu_list();
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		goto error;
+	}
+	return 0;
+
+error:
+	return -1;
+}
diff --git a/tools/testing/selftests/rseq/basic_test.c b/tools/testing/selftests/rseq/basic_test.c
new file mode 100644
index 000000000..d8efbfb89
--- /dev/null
+++ b/tools/testing/selftests/rseq/basic_test.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Basic test coverage for critical regions and rseq_current_cpu().
+ */
+
+#define _GNU_SOURCE
+#include <assert.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/time.h>
+
+#include "rseq.h"
+
+void test_cpu_pointer(void)
+{
+	cpu_set_t affinity, test_affinity;
+	int i;
+
+	sched_getaffinity(0, sizeof(affinity), &affinity);
+	CPU_ZERO(&test_affinity);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (CPU_ISSET(i, &affinity)) {
+			CPU_SET(i, &test_affinity);
+			sched_setaffinity(0, sizeof(test_affinity),
+					&test_affinity);
+			assert(sched_getcpu() == i);
+			assert(rseq_current_cpu() == i);
+			assert(rseq_current_cpu_raw() == i);
+			assert(rseq_cpu_start() == i);
+			CPU_CLR(i, &test_affinity);
+		}
+	}
+	sched_setaffinity(0, sizeof(affinity), &affinity);
+}
+
+int main(int argc, char **argv)
+{
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		goto init_thread_error;
+	}
+	printf("testing current cpu\n");
+	test_cpu_pointer();
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		goto init_thread_error;
+	}
+	return 0;
+
+init_thread_error:
+	return -1;
+}
diff --git a/tools/testing/selftests/rseq/compiler.h b/tools/testing/selftests/rseq/compiler.h
new file mode 100644
index 000000000..876eb6a7f
--- /dev/null
+++ b/tools/testing/selftests/rseq/compiler.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq/compiler.h
+ *
+ * Work-around asm goto compiler bugs.
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef RSEQ_COMPILER_H
+#define RSEQ_COMPILER_H
+
+/*
+ * gcc prior to 4.8.2 miscompiles asm goto.
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * gcc prior to 8.1.0 miscompiles asm goto at O1.
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103908
+ *
+ * clang prior to version 13.0.1 miscompiles asm goto at O2.
+ * https://github.com/llvm/llvm-project/issues/52735
+ *
+ * Work around these issues by adding a volatile inline asm with
+ * memory clobber in the fallthrough after the asm goto and at each
+ * label target.  Emit this for all compilers in case other similar
+ * issues are found in the future.
+ */
+#define rseq_after_asm_goto()	asm volatile ("" : : : "memory")
+
+#endif  /* RSEQ_COMPILER_H_ */
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
new file mode 100644
index 000000000..e29ecc715
--- /dev/null
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -0,0 +1,1550 @@
+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <linux/membarrier.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdatomic.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <poll.h>
+#include <sys/types.h>
+#include <signal.h>
+#include <errno.h>
+#include <stddef.h>
+
+static inline pid_t rseq_gettid(void)
+{
+	return syscall(__NR_gettid);
+}
+
+#define NR_INJECT	9
+static int loop_cnt[NR_INJECT + 1];
+
+static int loop_cnt_1 asm("asm_loop_cnt_1") __attribute__((used));
+static int loop_cnt_2 asm("asm_loop_cnt_2") __attribute__((used));
+static int loop_cnt_3 asm("asm_loop_cnt_3") __attribute__((used));
+static int loop_cnt_4 asm("asm_loop_cnt_4") __attribute__((used));
+static int loop_cnt_5 asm("asm_loop_cnt_5") __attribute__((used));
+static int loop_cnt_6 asm("asm_loop_cnt_6") __attribute__((used));
+
+static int opt_modulo, verbose;
+
+static int opt_yield, opt_signal, opt_sleep,
+		opt_disable_rseq, opt_threads = 200,
+		opt_disable_mod = 0, opt_test = 's', opt_mb = 0;
+
+#ifndef RSEQ_SKIP_FASTPATH
+static long long opt_reps = 5000;
+#else
+static long long opt_reps = 100;
+#endif
+
+static __thread __attribute__((tls_model("initial-exec")))
+unsigned int signals_delivered;
+
+#ifndef BENCHMARK
+
+static __thread __attribute__((tls_model("initial-exec"), unused))
+unsigned int yield_mod_cnt, nr_abort;
+
+#define printf_verbose(fmt, ...)			\
+	do {						\
+		if (verbose)				\
+			printf(fmt, ## __VA_ARGS__);	\
+	} while (0)
+
+#ifdef __i386__
+
+#define INJECT_ASM_REG	"eax"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"mov asm_loop_cnt_" #n ", %%" INJECT_ASM_REG "\n\t" \
+	"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
+	"jz 333f\n\t" \
+	"222:\n\t" \
+	"dec %%" INJECT_ASM_REG "\n\t" \
+	"jnz 222b\n\t" \
+	"333:\n\t"
+
+#elif defined(__x86_64__)
+
+#define INJECT_ASM_REG_P	"rax"
+#define INJECT_ASM_REG		"eax"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG_P \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG_P "\n\t" \
+	"mov (%%" INJECT_ASM_REG_P "), %%" INJECT_ASM_REG "\n\t" \
+	"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
+	"jz 333f\n\t" \
+	"222:\n\t" \
+	"dec %%" INJECT_ASM_REG "\n\t" \
+	"jnz 222b\n\t" \
+	"333:\n\t"
+
+#elif defined(__s390__)
+
+#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	"r12"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"l %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"ltr %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG "\n\t" \
+	"je 333f\n\t" \
+	"222:\n\t" \
+	"ahi %%" INJECT_ASM_REG ", -1\n\t" \
+	"jnz 222b\n\t" \
+	"333:\n\t"
+
+#elif defined(__ARMEL__)
+
+#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	"r4"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"ldr " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"cmp " INJECT_ASM_REG ", #0\n\t" \
+	"beq 333f\n\t" \
+	"222:\n\t" \
+	"subs " INJECT_ASM_REG ", #1\n\t" \
+	"bne 222b\n\t" \
+	"333:\n\t"
+
+#elif defined(__AARCH64EL__)
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1] "Qo" (loop_cnt[1]) \
+	, [loop_cnt_2] "Qo" (loop_cnt[2]) \
+	, [loop_cnt_3] "Qo" (loop_cnt[3]) \
+	, [loop_cnt_4] "Qo" (loop_cnt[4]) \
+	, [loop_cnt_5] "Qo" (loop_cnt[5]) \
+	, [loop_cnt_6] "Qo" (loop_cnt[6])
+
+#define INJECT_ASM_REG	RSEQ_ASM_TMP_REG32
+
+#define RSEQ_INJECT_ASM(n) \
+	"	ldr	" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n"	\
+	"	cbz	" INJECT_ASM_REG ", 333f\n"			\
+	"222:\n"							\
+	"	sub	" INJECT_ASM_REG ", " INJECT_ASM_REG ", #1\n"	\
+	"	cbnz	" INJECT_ASM_REG ", 222b\n"			\
+	"333:\n"
+
+#elif defined(__PPC__)
+
+#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	"r18"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"lwz %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"cmpwi %%" INJECT_ASM_REG ", 0\n\t" \
+	"beq 333f\n\t" \
+	"222:\n\t" \
+	"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
+
+#define RSEQ_INJECT_FAILED \
+	nr_abort++;
+
+#define RSEQ_INJECT_C(n) \
+{ \
+	int loc_i, loc_nr_loops = loop_cnt[n]; \
+	\
+	for (loc_i = 0; loc_i < loc_nr_loops; loc_i++) { \
+		rseq_barrier(); \
+	} \
+	if (loc_nr_loops == -1 && opt_modulo) { \
+		if (yield_mod_cnt == opt_modulo - 1) { \
+			if (opt_sleep > 0) \
+				poll(NULL, 0, opt_sleep); \
+			if (opt_yield) \
+				sched_yield(); \
+			if (opt_signal) \
+				raise(SIGUSR1); \
+			yield_mod_cnt = 0; \
+		} else { \
+			yield_mod_cnt++; \
+		} \
+	} \
+}
+
+#else
+
+#define printf_verbose(fmt, ...)
+
+#endif /* BENCHMARK */
+
+#include "rseq.h"
+
+struct percpu_lock_entry {
+	intptr_t v;
+} __attribute__((aligned(128)));
+
+struct percpu_lock {
+	struct percpu_lock_entry c[CPU_SETSIZE];
+};
+
+struct test_data_entry {
+	intptr_t count;
+} __attribute__((aligned(128)));
+
+struct spinlock_test_data {
+	struct percpu_lock lock;
+	struct test_data_entry c[CPU_SETSIZE];
+};
+
+struct spinlock_thread_test_data {
+	struct spinlock_test_data *data;
+	long long reps;
+	int reg;
+};
+
+struct inc_test_data {
+	struct test_data_entry c[CPU_SETSIZE];
+};
+
+struct inc_thread_test_data {
+	struct inc_test_data *data;
+	long long reps;
+	int reg;
+};
+
+struct percpu_list_node {
+	intptr_t data;
+	struct percpu_list_node *next;
+};
+
+struct percpu_list_entry {
+	struct percpu_list_node *head;
+} __attribute__((aligned(128)));
+
+struct percpu_list {
+	struct percpu_list_entry c[CPU_SETSIZE];
+};
+
+#define BUFFER_ITEM_PER_CPU	100
+
+struct percpu_buffer_node {
+	intptr_t data;
+};
+
+struct percpu_buffer_entry {
+	intptr_t offset;
+	intptr_t buflen;
+	struct percpu_buffer_node **array;
+} __attribute__((aligned(128)));
+
+struct percpu_buffer {
+	struct percpu_buffer_entry c[CPU_SETSIZE];
+};
+
+#define MEMCPY_BUFFER_ITEM_PER_CPU	100
+
+struct percpu_memcpy_buffer_node {
+	intptr_t data1;
+	uint64_t data2;
+};
+
+struct percpu_memcpy_buffer_entry {
+	intptr_t offset;
+	intptr_t buflen;
+	struct percpu_memcpy_buffer_node *array;
+} __attribute__((aligned(128)));
+
+struct percpu_memcpy_buffer {
+	struct percpu_memcpy_buffer_entry c[CPU_SETSIZE];
+};
+
+/* A simple percpu spinlock. Grabs lock on current cpu. */
+static int rseq_this_cpu_lock(struct percpu_lock *lock)
+{
+	int cpu;
+
+	for (;;) {
+		int ret;
+
+		cpu = rseq_cpu_start();
+		ret = rseq_cmpeqv_storev(&lock->c[cpu].v,
+					 0, 1, cpu);
+		if (rseq_likely(!ret))
+			break;
+		/* Retry if comparison fails or rseq aborts. */
+	}
+	/*
+	 * Acquire semantic when taking lock after control dependency.
+	 * Matches rseq_smp_store_release().
+	 */
+	rseq_smp_acquire__after_ctrl_dep();
+	return cpu;
+}
+
+static void rseq_percpu_unlock(struct percpu_lock *lock, int cpu)
+{
+	assert(lock->c[cpu].v == 1);
+	/*
+	 * Release lock, with release semantic. Matches
+	 * rseq_smp_acquire__after_ctrl_dep().
+	 */
+	rseq_smp_store_release(&lock->c[cpu].v, 0);
+}
+
+void *test_percpu_spinlock_thread(void *arg)
+{
+	struct spinlock_thread_test_data *thread_data = arg;
+	struct spinlock_test_data *data = thread_data->data;
+	long long i, reps;
+
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_register_current_thread())
+		abort();
+	reps = thread_data->reps;
+	for (i = 0; i < reps; i++) {
+		int cpu = rseq_this_cpu_lock(&data->lock);
+		data->c[cpu].count++;
+		rseq_percpu_unlock(&data->lock, cpu);
+#ifndef BENCHMARK
+		if (i != 0 && !(i % (reps / 10)))
+			printf_verbose("tid %d: count %lld\n",
+				       (int) rseq_gettid(), i);
+#endif
+	}
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) rseq_gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_unregister_current_thread())
+		abort();
+	return NULL;
+}
+
+/*
+ * A simple test which implements a sharded counter using a per-cpu
+ * lock.  Obviously real applications might prefer to simply use a
+ * per-cpu increment; however, this is reasonable for a test and the
+ * lock can be extended to synchronize more complicated operations.
+ */
+void test_percpu_spinlock(void)
+{
+	const int num_threads = opt_threads;
+	int i, ret;
+	uint64_t sum;
+	pthread_t test_threads[num_threads];
+	struct spinlock_test_data data;
+	struct spinlock_thread_test_data thread_data[num_threads];
+
+	memset(&data, 0, sizeof(data));
+	for (i = 0; i < num_threads; i++) {
+		thread_data[i].reps = opt_reps;
+		if (opt_disable_mod <= 0 || (i % opt_disable_mod))
+			thread_data[i].reg = 1;
+		else
+			thread_data[i].reg = 0;
+		thread_data[i].data = &data;
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_spinlock_thread,
+				     &thread_data[i]);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	sum = 0;
+	for (i = 0; i < CPU_SETSIZE; i++)
+		sum += data.c[i].count;
+
+	assert(sum == (uint64_t)opt_reps * num_threads);
+}
+
+void *test_percpu_inc_thread(void *arg)
+{
+	struct inc_thread_test_data *thread_data = arg;
+	struct inc_test_data *data = thread_data->data;
+	long long i, reps;
+
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_register_current_thread())
+		abort();
+	reps = thread_data->reps;
+	for (i = 0; i < reps; i++) {
+		int ret;
+
+		do {
+			int cpu;
+
+			cpu = rseq_cpu_start();
+			ret = rseq_addv(&data->c[cpu].count, 1, cpu);
+		} while (rseq_unlikely(ret));
+#ifndef BENCHMARK
+		if (i != 0 && !(i % (reps / 10)))
+			printf_verbose("tid %d: count %lld\n",
+				       (int) rseq_gettid(), i);
+#endif
+	}
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) rseq_gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_unregister_current_thread())
+		abort();
+	return NULL;
+}
+
+void test_percpu_inc(void)
+{
+	const int num_threads = opt_threads;
+	int i, ret;
+	uint64_t sum;
+	pthread_t test_threads[num_threads];
+	struct inc_test_data data;
+	struct inc_thread_test_data thread_data[num_threads];
+
+	memset(&data, 0, sizeof(data));
+	for (i = 0; i < num_threads; i++) {
+		thread_data[i].reps = opt_reps;
+		if (opt_disable_mod <= 0 || (i % opt_disable_mod))
+			thread_data[i].reg = 1;
+		else
+			thread_data[i].reg = 0;
+		thread_data[i].data = &data;
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_inc_thread,
+				     &thread_data[i]);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	sum = 0;
+	for (i = 0; i < CPU_SETSIZE; i++)
+		sum += data.c[i].count;
+
+	assert(sum == (uint64_t)opt_reps * num_threads);
+}
+
+void this_cpu_list_push(struct percpu_list *list,
+			struct percpu_list_node *node,
+			int *_cpu)
+{
+	int cpu;
+
+	for (;;) {
+		intptr_t *targetptr, newval, expect;
+		int ret;
+
+		cpu = rseq_cpu_start();
+		/* Load list->c[cpu].head with single-copy atomicity. */
+		expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head);
+		newval = (intptr_t)node;
+		targetptr = (intptr_t *)&list->c[cpu].head;
+		node->next = (struct percpu_list_node *)expect;
+		ret = rseq_cmpeqv_storev(targetptr, expect, newval, cpu);
+		if (rseq_likely(!ret))
+			break;
+		/* Retry if comparison fails or rseq aborts. */
+	}
+	if (_cpu)
+		*_cpu = cpu;
+}
+
+/*
+ * Unlike a traditional lock-less linked list; the availability of a
+ * rseq primitive allows us to implement pop without concerns over
+ * ABA-type races.
+ */
+struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
+					   int *_cpu)
+{
+	struct percpu_list_node *node = NULL;
+	int cpu;
+
+	for (;;) {
+		struct percpu_list_node *head;
+		intptr_t *targetptr, expectnot, *load;
+		long offset;
+		int ret;
+
+		cpu = rseq_cpu_start();
+		targetptr = (intptr_t *)&list->c[cpu].head;
+		expectnot = (intptr_t)NULL;
+		offset = offsetof(struct percpu_list_node, next);
+		load = (intptr_t *)&head;
+		ret = rseq_cmpnev_storeoffp_load(targetptr, expectnot,
+						   offset, load, cpu);
+		if (rseq_likely(!ret)) {
+			node = head;
+			break;
+		}
+		if (ret > 0)
+			break;
+		/* Retry if rseq aborts. */
+	}
+	if (_cpu)
+		*_cpu = cpu;
+	return node;
+}
+
+/*
+ * __percpu_list_pop is not safe against concurrent accesses. Should
+ * only be used on lists that are not concurrently modified.
+ */
+struct percpu_list_node *__percpu_list_pop(struct percpu_list *list, int cpu)
+{
+	struct percpu_list_node *node;
+
+	node = list->c[cpu].head;
+	if (!node)
+		return NULL;
+	list->c[cpu].head = node->next;
+	return node;
+}
+
+void *test_percpu_list_thread(void *arg)
+{
+	long long i, reps;
+	struct percpu_list *list = (struct percpu_list *)arg;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		abort();
+
+	reps = opt_reps;
+	for (i = 0; i < reps; i++) {
+		struct percpu_list_node *node;
+
+		node = this_cpu_list_pop(list, NULL);
+		if (opt_yield)
+			sched_yield();  /* encourage shuffling */
+		if (node)
+			this_cpu_list_push(list, node, NULL);
+	}
+
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) rseq_gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu linked list from many threads.  */
+void test_percpu_list(void)
+{
+	const int num_threads = opt_threads;
+	int i, j, ret;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_list list;
+	pthread_t test_threads[num_threads];
+	cpu_set_t allowed_cpus;
+
+	memset(&list, 0, sizeof(list));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		for (j = 1; j <= 100; j++) {
+			struct percpu_list_node *node;
+
+			expected_sum += j;
+
+			node = malloc(sizeof(*node));
+			assert(node);
+			node->data = j;
+			node->next = list.c[i].head;
+			list.c[i].head = node;
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_list_thread, &list);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_list_node *node;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while ((node = __percpu_list_pop(&list, i))) {
+			sum += node->data;
+			free(node);
+		}
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+bool this_cpu_buffer_push(struct percpu_buffer *buffer,
+			  struct percpu_buffer_node *node,
+			  int *_cpu)
+{
+	bool result = false;
+	int cpu;
+
+	for (;;) {
+		intptr_t *targetptr_spec, newval_spec;
+		intptr_t *targetptr_final, newval_final;
+		intptr_t offset;
+		int ret;
+
+		cpu = rseq_cpu_start();
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == buffer->c[cpu].buflen)
+			break;
+		newval_spec = (intptr_t)node;
+		targetptr_spec = (intptr_t *)&buffer->c[cpu].array[offset];
+		newval_final = offset + 1;
+		targetptr_final = &buffer->c[cpu].offset;
+		if (opt_mb)
+			ret = rseq_cmpeqv_trystorev_storev_release(
+				targetptr_final, offset, targetptr_spec,
+				newval_spec, newval_final, cpu);
+		else
+			ret = rseq_cmpeqv_trystorev_storev(targetptr_final,
+				offset, targetptr_spec, newval_spec,
+				newval_final, cpu);
+		if (rseq_likely(!ret)) {
+			result = true;
+			break;
+		}
+		/* Retry if comparison fails or rseq aborts. */
+	}
+	if (_cpu)
+		*_cpu = cpu;
+	return result;
+}
+
+struct percpu_buffer_node *this_cpu_buffer_pop(struct percpu_buffer *buffer,
+					       int *_cpu)
+{
+	struct percpu_buffer_node *head;
+	int cpu;
+
+	for (;;) {
+		intptr_t *targetptr, newval;
+		intptr_t offset;
+		int ret;
+
+		cpu = rseq_cpu_start();
+		/* Load offset with single-copy atomicity. */
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == 0) {
+			head = NULL;
+			break;
+		}
+		head = RSEQ_READ_ONCE(buffer->c[cpu].array[offset - 1]);
+		newval = offset - 1;
+		targetptr = (intptr_t *)&buffer->c[cpu].offset;
+		ret = rseq_cmpeqv_cmpeqv_storev(targetptr, offset,
+			(intptr_t *)&buffer->c[cpu].array[offset - 1],
+			(intptr_t)head, newval, cpu);
+		if (rseq_likely(!ret))
+			break;
+		/* Retry if comparison fails or rseq aborts. */
+	}
+	if (_cpu)
+		*_cpu = cpu;
+	return head;
+}
+
+/*
+ * __percpu_buffer_pop is not safe against concurrent accesses. Should
+ * only be used on buffers that are not concurrently modified.
+ */
+struct percpu_buffer_node *__percpu_buffer_pop(struct percpu_buffer *buffer,
+					       int cpu)
+{
+	struct percpu_buffer_node *head;
+	intptr_t offset;
+
+	offset = buffer->c[cpu].offset;
+	if (offset == 0)
+		return NULL;
+	head = buffer->c[cpu].array[offset - 1];
+	buffer->c[cpu].offset = offset - 1;
+	return head;
+}
+
+void *test_percpu_buffer_thread(void *arg)
+{
+	long long i, reps;
+	struct percpu_buffer *buffer = (struct percpu_buffer *)arg;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		abort();
+
+	reps = opt_reps;
+	for (i = 0; i < reps; i++) {
+		struct percpu_buffer_node *node;
+
+		node = this_cpu_buffer_pop(buffer, NULL);
+		if (opt_yield)
+			sched_yield();  /* encourage shuffling */
+		if (node) {
+			if (!this_cpu_buffer_push(buffer, node, NULL)) {
+				/* Should increase buffer size. */
+				abort();
+			}
+		}
+	}
+
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) rseq_gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu buffer from many threads.  */
+void test_percpu_buffer(void)
+{
+	const int num_threads = opt_threads;
+	int i, j, ret;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_buffer buffer;
+	pthread_t test_threads[num_threads];
+	cpu_set_t allowed_cpus;
+
+	memset(&buffer, 0, sizeof(buffer));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		/* Worse-case is every item in same CPU. */
+		buffer.c[i].array =
+			malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE *
+			       BUFFER_ITEM_PER_CPU);
+		assert(buffer.c[i].array);
+		buffer.c[i].buflen = CPU_SETSIZE * BUFFER_ITEM_PER_CPU;
+		for (j = 1; j <= BUFFER_ITEM_PER_CPU; j++) {
+			struct percpu_buffer_node *node;
+
+			expected_sum += j;
+
+			/*
+			 * We could theoretically put the word-sized
+			 * "data" directly in the buffer. However, we
+			 * want to model objects that would not fit
+			 * within a single word, so allocate an object
+			 * for each node.
+			 */
+			node = malloc(sizeof(*node));
+			assert(node);
+			node->data = j;
+			buffer.c[i].array[j - 1] = node;
+			buffer.c[i].offset++;
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_buffer_thread, &buffer);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_buffer_node *node;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while ((node = __percpu_buffer_pop(&buffer, i))) {
+			sum += node->data;
+			free(node);
+		}
+		free(buffer.c[i].array);
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+bool this_cpu_memcpy_buffer_push(struct percpu_memcpy_buffer *buffer,
+				 struct percpu_memcpy_buffer_node item,
+				 int *_cpu)
+{
+	bool result = false;
+	int cpu;
+
+	for (;;) {
+		intptr_t *targetptr_final, newval_final, offset;
+		char *destptr, *srcptr;
+		size_t copylen;
+		int ret;
+
+		cpu = rseq_cpu_start();
+		/* Load offset with single-copy atomicity. */
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == buffer->c[cpu].buflen)
+			break;
+		destptr = (char *)&buffer->c[cpu].array[offset];
+		srcptr = (char *)&item;
+		/* copylen must be <= 4kB. */
+		copylen = sizeof(item);
+		newval_final = offset + 1;
+		targetptr_final = &buffer->c[cpu].offset;
+		if (opt_mb)
+			ret = rseq_cmpeqv_trymemcpy_storev_release(
+				targetptr_final, offset,
+				destptr, srcptr, copylen,
+				newval_final, cpu);
+		else
+			ret = rseq_cmpeqv_trymemcpy_storev(targetptr_final,
+				offset, destptr, srcptr, copylen,
+				newval_final, cpu);
+		if (rseq_likely(!ret)) {
+			result = true;
+			break;
+		}
+		/* Retry if comparison fails or rseq aborts. */
+	}
+	if (_cpu)
+		*_cpu = cpu;
+	return result;
+}
+
+bool this_cpu_memcpy_buffer_pop(struct percpu_memcpy_buffer *buffer,
+				struct percpu_memcpy_buffer_node *item,
+				int *_cpu)
+{
+	bool result = false;
+	int cpu;
+
+	for (;;) {
+		intptr_t *targetptr_final, newval_final, offset;
+		char *destptr, *srcptr;
+		size_t copylen;
+		int ret;
+
+		cpu = rseq_cpu_start();
+		/* Load offset with single-copy atomicity. */
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == 0)
+			break;
+		destptr = (char *)item;
+		srcptr = (char *)&buffer->c[cpu].array[offset - 1];
+		/* copylen must be <= 4kB. */
+		copylen = sizeof(*item);
+		newval_final = offset - 1;
+		targetptr_final = &buffer->c[cpu].offset;
+		ret = rseq_cmpeqv_trymemcpy_storev(targetptr_final,
+			offset, destptr, srcptr, copylen,
+			newval_final, cpu);
+		if (rseq_likely(!ret)) {
+			result = true;
+			break;
+		}
+		/* Retry if comparison fails or rseq aborts. */
+	}
+	if (_cpu)
+		*_cpu = cpu;
+	return result;
+}
+
+/*
+ * __percpu_memcpy_buffer_pop is not safe against concurrent accesses. Should
+ * only be used on buffers that are not concurrently modified.
+ */
+bool __percpu_memcpy_buffer_pop(struct percpu_memcpy_buffer *buffer,
+				struct percpu_memcpy_buffer_node *item,
+				int cpu)
+{
+	intptr_t offset;
+
+	offset = buffer->c[cpu].offset;
+	if (offset == 0)
+		return false;
+	memcpy(item, &buffer->c[cpu].array[offset - 1], sizeof(*item));
+	buffer->c[cpu].offset = offset - 1;
+	return true;
+}
+
+void *test_percpu_memcpy_buffer_thread(void *arg)
+{
+	long long i, reps;
+	struct percpu_memcpy_buffer *buffer = (struct percpu_memcpy_buffer *)arg;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		abort();
+
+	reps = opt_reps;
+	for (i = 0; i < reps; i++) {
+		struct percpu_memcpy_buffer_node item;
+		bool result;
+
+		result = this_cpu_memcpy_buffer_pop(buffer, &item, NULL);
+		if (opt_yield)
+			sched_yield();  /* encourage shuffling */
+		if (result) {
+			if (!this_cpu_memcpy_buffer_push(buffer, item, NULL)) {
+				/* Should increase buffer size. */
+				abort();
+			}
+		}
+	}
+
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) rseq_gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu buffer from many threads.  */
+void test_percpu_memcpy_buffer(void)
+{
+	const int num_threads = opt_threads;
+	int i, j, ret;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_memcpy_buffer buffer;
+	pthread_t test_threads[num_threads];
+	cpu_set_t allowed_cpus;
+
+	memset(&buffer, 0, sizeof(buffer));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		/* Worse-case is every item in same CPU. */
+		buffer.c[i].array =
+			malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE *
+			       MEMCPY_BUFFER_ITEM_PER_CPU);
+		assert(buffer.c[i].array);
+		buffer.c[i].buflen = CPU_SETSIZE * MEMCPY_BUFFER_ITEM_PER_CPU;
+		for (j = 1; j <= MEMCPY_BUFFER_ITEM_PER_CPU; j++) {
+			expected_sum += 2 * j + 1;
+
+			/*
+			 * We could theoretically put the word-sized
+			 * "data" directly in the buffer. However, we
+			 * want to model objects that would not fit
+			 * within a single word, so allocate an object
+			 * for each node.
+			 */
+			buffer.c[i].array[j - 1].data1 = j;
+			buffer.c[i].array[j - 1].data2 = j + 1;
+			buffer.c[i].offset++;
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_memcpy_buffer_thread,
+				     &buffer);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_memcpy_buffer_node item;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while (__percpu_memcpy_buffer_pop(&buffer, &item, i)) {
+			sum += item.data1;
+			sum += item.data2;
+		}
+		free(buffer.c[i].array);
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+static void test_signal_interrupt_handler(int signo)
+{
+	signals_delivered++;
+}
+
+static int set_signal_handler(void)
+{
+	int ret = 0;
+	struct sigaction sa;
+	sigset_t sigset;
+
+	ret = sigemptyset(&sigset);
+	if (ret < 0) {
+		perror("sigemptyset");
+		return ret;
+	}
+
+	sa.sa_handler = test_signal_interrupt_handler;
+	sa.sa_mask = sigset;
+	sa.sa_flags = 0;
+	ret = sigaction(SIGUSR1, &sa, NULL);
+	if (ret < 0) {
+		perror("sigaction");
+		return ret;
+	}
+
+	printf_verbose("Signal handler set for SIGUSR1\n");
+
+	return ret;
+}
+
+struct test_membarrier_thread_args {
+	int stop;
+	intptr_t percpu_list_ptr;
+};
+
+/* Worker threads modify data in their "active" percpu lists. */
+void *test_membarrier_worker_thread(void *arg)
+{
+	struct test_membarrier_thread_args *args =
+		(struct test_membarrier_thread_args *)arg;
+	const int iters = opt_reps;
+	int i;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	/* Wait for initialization. */
+	while (!atomic_load(&args->percpu_list_ptr)) {}
+
+	for (i = 0; i < iters; ++i) {
+		int ret;
+
+		do {
+			int cpu = rseq_cpu_start();
+
+			ret = rseq_offset_deref_addv(&args->percpu_list_ptr,
+				sizeof(struct percpu_list_entry) * cpu, 1, cpu);
+		} while (rseq_unlikely(ret));
+	}
+
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+	return NULL;
+}
+
+void test_membarrier_init_percpu_list(struct percpu_list *list)
+{
+	int i;
+
+	memset(list, 0, sizeof(*list));
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_list_node *node;
+
+		node = malloc(sizeof(*node));
+		assert(node);
+		node->data = 0;
+		node->next = NULL;
+		list->c[i].head = node;
+	}
+}
+
+void test_membarrier_free_percpu_list(struct percpu_list *list)
+{
+	int i;
+
+	for (i = 0; i < CPU_SETSIZE; i++)
+		free(list->c[i].head);
+}
+
+static int sys_membarrier(int cmd, int flags, int cpu_id)
+{
+	return syscall(__NR_membarrier, cmd, flags, cpu_id);
+}
+
+/*
+ * The manager thread swaps per-cpu lists that worker threads see,
+ * and validates that there are no unexpected modifications.
+ */
+void *test_membarrier_manager_thread(void *arg)
+{
+	struct test_membarrier_thread_args *args =
+		(struct test_membarrier_thread_args *)arg;
+	struct percpu_list list_a, list_b;
+	intptr_t expect_a = 0, expect_b = 0;
+	int cpu_a = 0, cpu_b = 0;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	/* Init lists. */
+	test_membarrier_init_percpu_list(&list_a);
+	test_membarrier_init_percpu_list(&list_b);
+
+	atomic_store(&args->percpu_list_ptr, (intptr_t)&list_a);
+
+	while (!atomic_load(&args->stop)) {
+		/* list_a is "active". */
+		cpu_a = rand() % CPU_SETSIZE;
+		/*
+		 * As list_b is "inactive", we should never see changes
+		 * to list_b.
+		 */
+		if (expect_b != atomic_load(&list_b.c[cpu_b].head->data)) {
+			fprintf(stderr, "Membarrier test failed\n");
+			abort();
+		}
+
+		/* Make list_b "active". */
+		atomic_store(&args->percpu_list_ptr, (intptr_t)&list_b);
+		if (sys_membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ,
+					MEMBARRIER_CMD_FLAG_CPU, cpu_a) &&
+				errno != ENXIO /* missing CPU */) {
+			perror("sys_membarrier");
+			abort();
+		}
+		/*
+		 * Cpu A should now only modify list_b, so the values
+		 * in list_a should be stable.
+		 */
+		expect_a = atomic_load(&list_a.c[cpu_a].head->data);
+
+		cpu_b = rand() % CPU_SETSIZE;
+		/*
+		 * As list_a is "inactive", we should never see changes
+		 * to list_a.
+		 */
+		if (expect_a != atomic_load(&list_a.c[cpu_a].head->data)) {
+			fprintf(stderr, "Membarrier test failed\n");
+			abort();
+		}
+
+		/* Make list_a "active". */
+		atomic_store(&args->percpu_list_ptr, (intptr_t)&list_a);
+		if (sys_membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ,
+					MEMBARRIER_CMD_FLAG_CPU, cpu_b) &&
+				errno != ENXIO /* missing CPU*/) {
+			perror("sys_membarrier");
+			abort();
+		}
+		/* Remember a value from list_b. */
+		expect_b = atomic_load(&list_b.c[cpu_b].head->data);
+	}
+
+	test_membarrier_free_percpu_list(&list_a);
+	test_membarrier_free_percpu_list(&list_b);
+
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+	return NULL;
+}
+
+/* Test MEMBARRIER_CMD_PRIVATE_RESTART_RSEQ_ON_CPU membarrier command. */
+#ifdef RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+void test_membarrier(void)
+{
+	const int num_threads = opt_threads;
+	struct test_membarrier_thread_args thread_args;
+	pthread_t worker_threads[num_threads];
+	pthread_t manager_thread;
+	int i, ret;
+
+	if (sys_membarrier(MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ, 0, 0)) {
+		perror("sys_membarrier");
+		abort();
+	}
+
+	thread_args.stop = 0;
+	thread_args.percpu_list_ptr = 0;
+	ret = pthread_create(&manager_thread, NULL,
+			test_membarrier_manager_thread, &thread_args);
+	if (ret) {
+		errno = ret;
+		perror("pthread_create");
+		abort();
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&worker_threads[i], NULL,
+				test_membarrier_worker_thread, &thread_args);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(worker_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	atomic_store(&thread_args.stop, 1);
+	ret = pthread_join(manager_thread, NULL);
+	if (ret) {
+		errno = ret;
+		perror("pthread_join");
+		abort();
+	}
+}
+#else /* RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV */
+void test_membarrier(void)
+{
+	fprintf(stderr, "rseq_offset_deref_addv is not implemented on this architecture. "
+			"Skipping membarrier test.\n");
+}
+#endif
+
+static void show_usage(int argc, char **argv)
+{
+	printf("Usage : %s <OPTIONS>\n",
+		argv[0]);
+	printf("OPTIONS:\n");
+	printf("	[-1 loops] Number of loops for delay injection 1\n");
+	printf("	[-2 loops] Number of loops for delay injection 2\n");
+	printf("	[-3 loops] Number of loops for delay injection 3\n");
+	printf("	[-4 loops] Number of loops for delay injection 4\n");
+	printf("	[-5 loops] Number of loops for delay injection 5\n");
+	printf("	[-6 loops] Number of loops for delay injection 6\n");
+	printf("	[-7 loops] Number of loops for delay injection 7 (-1 to enable -m)\n");
+	printf("	[-8 loops] Number of loops for delay injection 8 (-1 to enable -m)\n");
+	printf("	[-9 loops] Number of loops for delay injection 9 (-1 to enable -m)\n");
+	printf("	[-m N] Yield/sleep/kill every modulo N (default 0: disabled) (>= 0)\n");
+	printf("	[-y] Yield\n");
+	printf("	[-k] Kill thread with signal\n");
+	printf("	[-s S] S: =0: disabled (default), >0: sleep time (ms)\n");
+	printf("	[-t N] Number of threads (default 200)\n");
+	printf("	[-r N] Number of repetitions per thread (default 5000)\n");
+	printf("	[-d] Disable rseq system call (no initialization)\n");
+	printf("	[-D M] Disable rseq for each M threads\n");
+	printf("	[-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement, membarrie(r)\n");
+	printf("	[-M] Push into buffer and memcpy buffer with memory barriers.\n");
+	printf("	[-v] Verbose output.\n");
+	printf("	[-h] Show this help.\n");
+	printf("\n");
+}
+
+int main(int argc, char **argv)
+{
+	int i;
+
+	for (i = 1; i < argc; i++) {
+		if (argv[i][0] != '-')
+			continue;
+		switch (argv[i][1]) {
+		case '1':
+		case '2':
+		case '3':
+		case '4':
+		case '5':
+		case '6':
+		case '7':
+		case '8':
+		case '9':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			loop_cnt[argv[i][1] - '0'] = atol(argv[i + 1]);
+			i++;
+			break;
+		case 'm':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_modulo = atol(argv[i + 1]);
+			if (opt_modulo < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 's':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_sleep = atol(argv[i + 1]);
+			if (opt_sleep < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'y':
+			opt_yield = 1;
+			break;
+		case 'k':
+			opt_signal = 1;
+			break;
+		case 'd':
+			opt_disable_rseq = 1;
+			break;
+		case 'D':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_disable_mod = atol(argv[i + 1]);
+			if (opt_disable_mod < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 't':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_threads = atol(argv[i + 1]);
+			if (opt_threads < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'r':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_reps = atoll(argv[i + 1]);
+			if (opt_reps < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'h':
+			show_usage(argc, argv);
+			goto end;
+		case 'T':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_test = *argv[i + 1];
+			switch (opt_test) {
+			case 's':
+			case 'l':
+			case 'i':
+			case 'b':
+			case 'm':
+			case 'r':
+				break;
+			default:
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'v':
+			verbose = 1;
+			break;
+		case 'M':
+			opt_mb = 1;
+			break;
+		default:
+			show_usage(argc, argv);
+			goto error;
+		}
+	}
+
+	loop_cnt_1 = loop_cnt[1];
+	loop_cnt_2 = loop_cnt[2];
+	loop_cnt_3 = loop_cnt[3];
+	loop_cnt_4 = loop_cnt[4];
+	loop_cnt_5 = loop_cnt[5];
+	loop_cnt_6 = loop_cnt[6];
+
+	if (set_signal_handler())
+		goto error;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		goto error;
+	switch (opt_test) {
+	case 's':
+		printf_verbose("spinlock\n");
+		test_percpu_spinlock();
+		break;
+	case 'l':
+		printf_verbose("linked list\n");
+		test_percpu_list();
+		break;
+	case 'b':
+		printf_verbose("buffer\n");
+		test_percpu_buffer();
+		break;
+	case 'm':
+		printf_verbose("memcpy buffer\n");
+		test_percpu_memcpy_buffer();
+		break;
+	case 'i':
+		printf_verbose("counter increment\n");
+		test_percpu_inc();
+		break;
+	case 'r':
+		printf_verbose("membarrier\n");
+		test_membarrier();
+		break;
+	}
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+end:
+	return 0;
+
+error:
+	return -1;
+}
diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h
new file mode 100644
index 000000000..a8c44d9af
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-abi.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _RSEQ_ABI_H
+#define _RSEQ_ABI_H
+
+/*
+ * rseq-abi.h
+ *
+ * Restartable sequences system call API
+ *
+ * Copyright (c) 2015-2022 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+enum rseq_abi_cpu_id_state {
+	RSEQ_ABI_CPU_ID_UNINITIALIZED			= -1,
+	RSEQ_ABI_CPU_ID_REGISTRATION_FAILED		= -2,
+};
+
+enum rseq_abi_flags {
+	RSEQ_ABI_FLAG_UNREGISTER = (1 << 0),
+};
+
+enum rseq_abi_cs_flags_bit {
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT	= 0,
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT	= 1,
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT	= 2,
+};
+
+enum rseq_abi_cs_flags {
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT	=
+		(1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT),
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL	=
+		(1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT),
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE	=
+		(1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT),
+};
+
+/*
+ * struct rseq_abi_cs is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line. It is usually declared as
+ * link-time constant data.
+ */
+struct rseq_abi_cs {
+	/* Version of this structure. */
+	__u32 version;
+	/* enum rseq_abi_cs_flags */
+	__u32 flags;
+	__u64 start_ip;
+	/* Offset from start_ip. */
+	__u64 post_commit_offset;
+	__u64 abort_ip;
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+/*
+ * struct rseq_abi is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line.
+ *
+ * A single struct rseq_abi per thread is allowed.
+ */
+struct rseq_abi {
+	/*
+	 * Restartable sequences cpu_id_start field. Updated by the
+	 * kernel. Read by user-space with single-copy atomicity
+	 * semantics. This field should only be read by the thread which
+	 * registered this data structure. Aligned on 32-bit. Always
+	 * contains a value in the range of possible CPUs, although the
+	 * value may not be the actual current CPU (e.g. if rseq is not
+	 * initialized). This CPU number value should always be compared
+	 * against the value of the cpu_id field before performing a rseq
+	 * commit or returning a value read from a data structure indexed
+	 * using the cpu_id_start value.
+	 */
+	__u32 cpu_id_start;
+	/*
+	 * Restartable sequences cpu_id field. Updated by the kernel.
+	 * Read by user-space with single-copy atomicity semantics. This
+	 * field should only be read by the thread which registered this
+	 * data structure. Aligned on 32-bit. Values
+	 * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED
+	 * have a special semantic: the former means "rseq uninitialized",
+	 * and latter means "rseq initialization failed". This value is
+	 * meant to be read within rseq critical sections and compared
+	 * with the cpu_id_start value previously read, before performing
+	 * the commit instruction, or read and compared with the
+	 * cpu_id_start value before returning a value loaded from a data
+	 * structure indexed using the cpu_id_start value.
+	 */
+	__u32 cpu_id;
+	/*
+	 * Restartable sequences rseq_cs field.
+	 *
+	 * Contains NULL when no critical section is active for the current
+	 * thread, or holds a pointer to the currently active struct rseq_cs.
+	 *
+	 * Updated by user-space, which sets the address of the currently
+	 * active rseq_cs at the beginning of assembly instruction sequence
+	 * block, and set to NULL by the kernel when it restarts an assembly
+	 * instruction sequence block, as well as when the kernel detects that
+	 * it is preempting or delivering a signal outside of the range
+	 * targeted by the rseq_cs. Also needs to be set to NULL by user-space
+	 * before reclaiming memory that contains the targeted struct rseq_cs.
+	 *
+	 * Read and set by the kernel. Set by user-space with single-copy
+	 * atomicity semantics. This field should only be updated by the
+	 * thread which registered this data structure. Aligned on 64-bit.
+	 */
+	union {
+		__u64 ptr64;
+
+		/*
+		 * The "arch" field provides architecture accessor for
+		 * the ptr field based on architecture pointer size and
+		 * endianness.
+		 */
+		struct {
+#ifdef __LP64__
+			__u64 ptr;
+#elif defined(__BYTE_ORDER) ? (__BYTE_ORDER == __BIG_ENDIAN) : defined(__BIG_ENDIAN)
+			__u32 padding;		/* Initialized to zero. */
+			__u32 ptr;
+#else
+			__u32 ptr;
+			__u32 padding;		/* Initialized to zero. */
+#endif
+		} arch;
+	} rseq_cs;
+
+	/*
+	 * Restartable sequences flags field.
+	 *
+	 * This field should only be updated by the thread which
+	 * registered this data structure. Read by the kernel.
+	 * Mainly used for single-stepping through rseq critical sections
+	 * with debuggers.
+	 *
+	 * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT
+	 *     Inhibit instruction sequence block restart on preemption
+	 *     for this thread.
+	 * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL
+	 *     Inhibit instruction sequence block restart on signal
+	 *     delivery for this thread.
+	 * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE
+	 *     Inhibit instruction sequence block restart on migration for
+	 *     this thread.
+	 */
+	__u32 flags;
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+#endif /* _RSEQ_ABI_H */
diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h
new file mode 100644
index 000000000..893a11eca
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-arm.h
@@ -0,0 +1,827 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-arm.h
+ *
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+/*
+ * - ARM little endian
+ *
+ * RSEQ_SIG uses the udf A32 instruction with an uncommon immediate operand
+ * value 0x5de3. This traps if user-space reaches this instruction by mistake,
+ * and the uncommon operand ensures the kernel does not move the instruction
+ * pointer to attacker-controlled code on rseq abort.
+ *
+ * The instruction pattern in the A32 instruction set is:
+ *
+ * e7f5def3    udf    #24035    ; 0x5de3
+ *
+ * This translates to the following instruction pattern in the T16 instruction
+ * set:
+ *
+ * little endian:
+ * def3        udf    #243      ; 0xf3
+ * e7f5        b.n    <7f5>
+ *
+ * - ARMv6+ big endian (BE8):
+ *
+ * ARMv6+ -mbig-endian generates mixed endianness code vs data: little-endian
+ * code and big-endian data. The data value of the signature needs to have its
+ * byte order reversed to generate the trap instruction:
+ *
+ * Data: 0xf3def5e7
+ *
+ * Translates to this A32 instruction pattern:
+ *
+ * e7f5def3    udf    #24035    ; 0x5de3
+ *
+ * Translates to this T16 instruction pattern:
+ *
+ * def3        udf    #243      ; 0xf3
+ * e7f5        b.n    <7f5>
+ *
+ * - Prior to ARMv6 big endian (BE32):
+ *
+ * Prior to ARMv6, -mbig-endian generates big-endian code and data
+ * (which match), so the endianness of the data representation of the
+ * signature should not be reversed. However, the choice between BE32
+ * and BE8 is done by the linker, so we cannot know whether code and
+ * data endianness will be mixed before the linker is invoked. So rather
+ * than try to play tricks with the linker, the rseq signature is simply
+ * data (not a trap instruction) prior to ARMv6 on big endian. This is
+ * why the signature is expressed as data (.word) rather than as
+ * instruction (.inst) in assembler.
+ */
+
+#ifdef __ARMEB__
+#define RSEQ_SIG    0xf3def5e7      /* udf    #24035    ; 0x5de3 (ARMv6+) */
+#else
+#define RSEQ_SIG    0xe7f5def3      /* udf    #24035    ; 0x5de3 */
+#endif
+
+#define rseq_smp_mb()	__asm__ __volatile__ ("dmb" ::: "memory", "cc")
+#define rseq_smp_rmb()	__asm__ __volatile__ ("dmb" ::: "memory", "cc")
+#define rseq_smp_wmb()	__asm__ __volatile__ ("dmb" ::: "memory", "cc")
+
+#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 */
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, start_ip,	\
+				post_commit_offset, abort_ip)		\
+		".pushsection __rseq_cs, \"aw\"\n\t"			\
+		".balign 32\n\t"					\
+		__rseq_str(label) ":\n\t"					\
+		".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		".word " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) ", 0x0\n\t" \
+		".popsection\n\t"					\
+		".pushsection __rseq_cs_ptr_array, \"aw\"\n\t"		\
+		".word " __rseq_str(label) "b, 0x0\n\t"			\
+		".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,		\
+				(post_commit_ip - start_ip), abort_ip)
+
+/*
+ * Exit points of a rseq critical section consist of all instructions outside
+ * of the critical section where a critical section can either branch to or
+ * reach through the normal course of its execution. The abort IP and the
+ * post-commit IP are already part of the __rseq_cs section and should not be
+ * explicitly defined as additional exit points. Knowing all exit points is
+ * useful to assist debuggers stepping over the critical section.
+ */
+#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip)			\
+		".pushsection __rseq_exit_point_array, \"aw\"\n\t"	\
+		".word " __rseq_str(start_ip) ", 0x0, " __rseq_str(exit_ip) ", 0x0\n\t" \
+		".popsection\n\t"
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)		\
+		RSEQ_INJECT_ASM(1)					\
+		"adr r0, " __rseq_str(cs_label) "\n\t"			\
+		"str r0, %[" __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)					\
+		"ldr r0, %[" __rseq_str(current_cpu_id) "]\n\t"	\
+		"cmp %[" __rseq_str(cpu_id) "], r0\n\t"		\
+		"bne " __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" \
+		".word " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) ", 0x0\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"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* 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)
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne %l[error2]\n\t"
+#endif
+		/* final store */
+		"str %[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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "r0", "memory", "cc"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       long voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* 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)
+		"ldr r0, %[v]\n\t"
+		"cmp %[expectnot], r0\n\t"
+		"beq %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		"ldr r0, %[v]\n\t"
+		"cmp %[expectnot], r0\n\t"
+		"beq %l[error2]\n\t"
+#endif
+		"str r0, %[load]\n\t"
+		"add r0, %[voffp]\n\t"
+		"ldr r0, [r0]\n\t"
+		/* final store */
+		"str r0, %[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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [voffp]		"Ir" (voffp),
+		  [load]		"m" (*load)
+		  RSEQ_INJECT_INPUT
+		: "r0", "memory", "cc"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+#endif
+		/* 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
+		"ldr r0, %[v]\n\t"
+		"add r0, %[count]\n\t"
+		/* final store */
+		"str r0, %[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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [v]			"m" (*v),
+		  [count]		"Ir" (count)
+		  RSEQ_INJECT_INPUT
+		: "r0", "memory", "cc"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* 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)
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne %l[error2]\n\t"
+#endif
+		/* try store */
+		"str %[newv2], %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		"str %[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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "r0", "memory", "cc"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* 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)
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne %l[error2]\n\t"
+#endif
+		/* try store */
+		"str %[newv2], %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		"dmb\n\t"	/* full mb provides store-release */
+		/* final store */
+		"str %[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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "r0", "memory", "cc"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
+#endif
+		/* 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)
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+		"ldr r0, %[v2]\n\t"
+		"cmp %[expect2], r0\n\t"
+		"bne %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne %l[error2]\n\t"
+		"ldr r0, %[v2]\n\t"
+		"cmp %[expect2], r0\n\t"
+		"bne %l[error3]\n\t"
+#endif
+		/* final store */
+		"str %[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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* cmp2 input */
+		  [v2]			"m" (*v2),
+		  [expect2]		"r" (expect2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "r0", "memory", "cc"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("1st expected value comparison failed");
+error3:
+	rseq_after_asm_goto();
+	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)
+{
+	uint32_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		"str %[src], %[rseq_scratch0]\n\t"
+		"str %[dst], %[rseq_scratch1]\n\t"
+		"str %[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)
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne 7f\n\t"
+#endif
+		/* try memcpy */
+		"cmp %[len], #0\n\t" \
+		"beq 333f\n\t" \
+		"222:\n\t" \
+		"ldrb %%r0, [%[src]]\n\t" \
+		"strb %%r0, [%[dst]]\n\t" \
+		"adds %[src], #1\n\t" \
+		"adds %[dst], #1\n\t" \
+		"subs %[len], #1\n\t" \
+		"bne 222b\n\t" \
+		"333:\n\t" \
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		"str %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		"ldr %[len], %[rseq_scratch2]\n\t"
+		"ldr %[dst], %[rseq_scratch1]\n\t"
+		"ldr %[src], %[rseq_scratch0]\n\t"
+		"b 8f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4,
+				      /* teardown */
+				      "ldr %[len], %[rseq_scratch2]\n\t"
+				      "ldr %[dst], %[rseq_scratch1]\n\t"
+				      "ldr %[src], %[rseq_scratch0]\n\t",
+				      abort, 1b, 2b, 4f)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+					/* teardown */
+					"ldr %[len], %[rseq_scratch2]\n\t"
+					"ldr %[dst], %[rseq_scratch1]\n\t"
+					"ldr %[src], %[rseq_scratch0]\n\t",
+					cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+					/* teardown */
+					"ldr %[len], %[rseq_scratch2]\n\t"
+					"ldr %[dst], %[rseq_scratch1]\n\t"
+					"ldr %[src], %[rseq_scratch0]\n\t",
+					error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+					/* teardown */
+					"ldr %[len], %[rseq_scratch2]\n\t"
+					"ldr %[dst], %[rseq_scratch1]\n\t"
+					"ldr %[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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* 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
+		: "r0", "memory", "cc"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+{
+	uint32_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		"str %[src], %[rseq_scratch0]\n\t"
+		"str %[dst], %[rseq_scratch1]\n\t"
+		"str %[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)
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+		"ldr r0, %[v]\n\t"
+		"cmp %[expect], r0\n\t"
+		"bne 7f\n\t"
+#endif
+		/* try memcpy */
+		"cmp %[len], #0\n\t" \
+		"beq 333f\n\t" \
+		"222:\n\t" \
+		"ldrb %%r0, [%[src]]\n\t" \
+		"strb %%r0, [%[dst]]\n\t" \
+		"adds %[src], #1\n\t" \
+		"adds %[dst], #1\n\t" \
+		"subs %[len], #1\n\t" \
+		"bne 222b\n\t" \
+		"333:\n\t" \
+		RSEQ_INJECT_ASM(5)
+		"dmb\n\t"	/* full mb provides store-release */
+		/* final store */
+		"str %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		"ldr %[len], %[rseq_scratch2]\n\t"
+		"ldr %[dst], %[rseq_scratch1]\n\t"
+		"ldr %[src], %[rseq_scratch0]\n\t"
+		"b 8f\n\t"
+		RSEQ_ASM_DEFINE_ABORT(3, 4,
+				      /* teardown */
+				      "ldr %[len], %[rseq_scratch2]\n\t"
+				      "ldr %[dst], %[rseq_scratch1]\n\t"
+				      "ldr %[src], %[rseq_scratch0]\n\t",
+				      abort, 1b, 2b, 4f)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+					/* teardown */
+					"ldr %[len], %[rseq_scratch2]\n\t"
+					"ldr %[dst], %[rseq_scratch1]\n\t"
+					"ldr %[src], %[rseq_scratch0]\n\t",
+					cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+					/* teardown */
+					"ldr %[len], %[rseq_scratch2]\n\t"
+					"ldr %[dst], %[rseq_scratch1]\n\t"
+					"ldr %[src], %[rseq_scratch0]\n\t",
+					error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+					/* teardown */
+					"ldr %[len], %[rseq_scratch2]\n\t"
+					"ldr %[dst], %[rseq_scratch1]\n\t"
+					"ldr %[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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* 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
+		: "r0", "memory", "cc"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h
new file mode 100644
index 000000000..cbe190a4d
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-arm64.h
@@ -0,0 +1,695 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-arm64.h
+ *
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ * (C) Copyright 2018 - Will Deacon <will.deacon@arm.com>
+ */
+
+/*
+ * aarch64 -mbig-endian generates mixed endianness code vs data:
+ * little-endian code and big-endian data. Ensure the RSEQ_SIG signature
+ * matches code endianness.
+ */
+#define RSEQ_SIG_CODE	0xd428bc00	/* BRK #0x45E0.  */
+
+#ifdef __AARCH64EB__
+#define RSEQ_SIG_DATA	0x00bc28d4	/* BRK #0x45E0.  */
+#else
+#define RSEQ_SIG_DATA	RSEQ_SIG_CODE
+#endif
+
+#define RSEQ_SIG	RSEQ_SIG_DATA
+
+#define rseq_smp_mb()	__asm__ __volatile__ ("dmb ish" ::: "memory")
+#define rseq_smp_rmb()	__asm__ __volatile__ ("dmb ishld" ::: "memory")
+#define rseq_smp_wmb()	__asm__ __volatile__ ("dmb ishst" ::: "memory")
+
+#define rseq_smp_load_acquire(p)						\
+__extension__ ({								\
+	__typeof(*p) ____p1;							\
+	switch (sizeof(*p)) {							\
+	case 1:									\
+		asm volatile ("ldarb %w0, %1"					\
+			: "=r" (*(__u8 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	case 2:									\
+		asm volatile ("ldarh %w0, %1"					\
+			: "=r" (*(__u16 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	case 4:									\
+		asm volatile ("ldar %w0, %1"					\
+			: "=r" (*(__u32 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	case 8:									\
+		asm volatile ("ldar %0, %1"					\
+			: "=r" (*(__u64 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	}									\
+	____p1;									\
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()	rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)						\
+do {										\
+	switch (sizeof(*p)) {							\
+	case 1:									\
+		asm volatile ("stlrb %w1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u8)v)					\
+				: "memory");					\
+		break;								\
+	case 2:									\
+		asm volatile ("stlrh %w1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u16)v)				\
+				: "memory");					\
+		break;								\
+	case 4:									\
+		asm volatile ("stlr %w1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u32)v)				\
+				: "memory");					\
+		break;								\
+	case 8:									\
+		asm volatile ("stlr %1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u64)v)				\
+				: "memory");					\
+		break;								\
+	}									\
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#define RSEQ_ASM_TMP_REG32	"w15"
+#define RSEQ_ASM_TMP_REG	"x15"
+#define RSEQ_ASM_TMP_REG_2	"x14"
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, start_ip,		\
+				post_commit_offset, abort_ip)			\
+	"	.pushsection	__rseq_cs, \"aw\"\n"				\
+	"	.balign	32\n"							\
+	__rseq_str(label) ":\n"							\
+	"	.long	" __rseq_str(version) ", " __rseq_str(flags) "\n"	\
+	"	.quad	" __rseq_str(start_ip) ", "				\
+			  __rseq_str(post_commit_offset) ", "			\
+			  __rseq_str(abort_ip) "\n"				\
+	"	.popsection\n\t"						\
+	"	.pushsection __rseq_cs_ptr_array, \"aw\"\n"				\
+	"	.quad " __rseq_str(label) "b\n"					\
+	"	.popsection\n"
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip)	\
+	__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,			\
+				(post_commit_ip - start_ip), abort_ip)
+
+/*
+ * Exit points of a rseq critical section consist of all instructions outside
+ * of the critical section where a critical section can either branch to or
+ * reach through the normal course of its execution. The abort IP and the
+ * post-commit IP are already part of the __rseq_cs section and should not be
+ * explicitly defined as additional exit points. Knowing all exit points is
+ * useful to assist debuggers stepping over the critical section.
+ */
+#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip)				\
+	"	.pushsection __rseq_exit_point_array, \"aw\"\n"			\
+	"	.quad " __rseq_str(start_ip) ", " __rseq_str(exit_ip) "\n"	\
+	"	.popsection\n"
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)			\
+	RSEQ_INJECT_ASM(1)							\
+	"	adrp	" RSEQ_ASM_TMP_REG ", " __rseq_str(cs_label) "\n"	\
+	"	add	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", :lo12:" __rseq_str(cs_label) "\n"			\
+	"	str	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(rseq_cs) "]\n"	\
+	__rseq_str(label) ":\n"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, abort_label)				\
+	"	b	222f\n"							\
+	"	.inst 	"	__rseq_str(RSEQ_SIG_CODE) "\n"			\
+	__rseq_str(label) ":\n"							\
+	"	b	%l[" __rseq_str(abort_label) "]\n"			\
+	"222:\n"
+
+#define RSEQ_ASM_OP_STORE(value, var)						\
+	"	str	%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_STORE_RELEASE(value, var)					\
+	"	stlr	%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label)			\
+	RSEQ_ASM_OP_STORE(value, var)						\
+	__rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_FINAL_STORE_RELEASE(value, var, post_commit_label)		\
+	RSEQ_ASM_OP_STORE_RELEASE(value, var)					\
+	__rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_CMPEQ(var, expect, label)					\
+	"	ldr	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"		\
+	"	sub	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(expect) "]\n"				\
+	"	cbnz	" RSEQ_ASM_TMP_REG ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_OP_CMPEQ32(var, expect, label)					\
+	"	ldr	" RSEQ_ASM_TMP_REG32 ", %[" __rseq_str(var) "]\n"	\
+	"	sub	" RSEQ_ASM_TMP_REG32 ", " RSEQ_ASM_TMP_REG32		\
+			", %w[" __rseq_str(expect) "]\n"			\
+	"	cbnz	" RSEQ_ASM_TMP_REG32 ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_OP_CMPNE(var, expect, label)					\
+	"	ldr	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"		\
+	"	sub	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(expect) "]\n"				\
+	"	cbz	" RSEQ_ASM_TMP_REG ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label)			\
+	RSEQ_INJECT_ASM(2)							\
+	RSEQ_ASM_OP_CMPEQ32(current_cpu_id, cpu_id, label)
+
+#define RSEQ_ASM_OP_R_LOAD(var)							\
+	"	ldr	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_R_STORE(var)						\
+	"	str	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_R_LOAD_OFF(offset)						\
+	"	ldr	" RSEQ_ASM_TMP_REG ", [" RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(offset) "]]\n"
+
+#define RSEQ_ASM_OP_R_ADD(count)						\
+	"	add	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(count) "]\n"
+
+#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label)			\
+	"	str	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"		\
+	__rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)					\
+	"	cbz	%[" __rseq_str(len) "], 333f\n"				\
+	"	mov	" RSEQ_ASM_TMP_REG_2 ", %[" __rseq_str(len) "]\n"	\
+	"222:	sub	" RSEQ_ASM_TMP_REG_2 ", " RSEQ_ASM_TMP_REG_2 ", #1\n"	\
+	"	ldrb	" RSEQ_ASM_TMP_REG32 ", [%[" __rseq_str(src) "]"	\
+			", " RSEQ_ASM_TMP_REG_2 "]\n"				\
+	"	strb	" RSEQ_ASM_TMP_REG32 ", [%[" __rseq_str(dst) "]"	\
+			", " RSEQ_ASM_TMP_REG_2 "]\n"				\
+	"	cbnz	" RSEQ_ASM_TMP_REG_2 ", 222b\n"				\
+	"333:\n"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error2])
+#endif
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [v]			"Qo" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       long voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error2])
+#endif
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPNE(v, expectnot, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPNE(v, expectnot, %l[error2])
+#endif
+		RSEQ_ASM_OP_R_LOAD(v)
+		RSEQ_ASM_OP_R_STORE(load)
+		RSEQ_ASM_OP_R_LOAD_OFF(voffp)
+		RSEQ_ASM_OP_R_FINAL_STORE(v, 3)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [v]			"Qo" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [load]		"Qo" (*load),
+		  [voffp]		"r" (voffp)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error1])
+#endif
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, 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
+		RSEQ_ASM_OP_R_LOAD(v)
+		RSEQ_ASM_OP_R_ADD(count)
+		RSEQ_ASM_OP_R_FINAL_STORE(v, 3)
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [v]			"Qo" (*v),
+		  [count]		"r" (count)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error2])
+#endif
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_STORE(newv2, v2)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [v2]			"Qo" (*v2),
+		  [newv2]		"r" (newv2)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error2])
+#endif
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_STORE(newv2, v2)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [v2]			"Qo" (*v2),
+		  [newv2]		"r" (newv2)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error2])
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error3])
+#endif
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[cmpfail])
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+		RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[error3])
+#endif
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [v]			"Qo" (*v),
+		  [expect]		"r" (expect),
+		  [v2]			"Qo" (*v2),
+		  [expect2]		"r" (expect2),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+error3:
+	rseq_after_asm_goto();
+	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)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error2])
+#endif
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG, RSEQ_ASM_TMP_REG_2
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(2f, %l[error2])
+#endif
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG, RSEQ_ASM_TMP_REG_2
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h
new file mode 100644
index 000000000..38c584661
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-generic-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_GENERIC_THREAD_POINTER
+#define _RSEQ_GENERIC_THREAD_POINTER
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Use gcc builtin thread pointer. */
+static inline void *rseq_thread_pointer(void)
+{
+	return __builtin_thread_pointer();
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-mips.h b/tools/testing/selftests/rseq/rseq-mips.h
new file mode 100644
index 000000000..878739fae
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-mips.h
@@ -0,0 +1,777 @@
+/* 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>
+ */
+
+/*
+ * RSEQ_SIG uses the break instruction. The instruction pattern is:
+ *
+ * On MIPS:
+ *	0350000d        break     0x350
+ *
+ * On nanoMIPS:
+ *      00100350        break     0x350
+ *
+ * On microMIPS:
+ *      0000d407        break     0x350
+ *
+ * For nanoMIPS32 and microMIPS, the instruction stream is encoded as 16-bit
+ * halfwords, so the signature halfwords need to be swapped accordingly for
+ * little-endian.
+ */
+#if defined(__nanomips__)
+# ifdef __MIPSEL__
+#  define RSEQ_SIG	0x03500010
+# else
+#  define RSEQ_SIG	0x00100350
+# endif
+#elif defined(__mips_micromips)
+# ifdef __MIPSEL__
+#  define RSEQ_SIG	0xd4070000
+# else
+#  define RSEQ_SIG	0x0000d407
+# endif
+#elif defined(__mips__)
+# define RSEQ_SIG	0x0350000d
+#else
+/* Unknown MIPS architecture. */
+#endif
+
+#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(label, version, flags, start_ip, \
+				post_commit_offset, abort_ip) \
+		".pushsection __rseq_cs, \"aw\"\n\t" \
+		".balign 32\n\t" \
+		__rseq_str(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" \
+		".popsection\n\t" \
+		".pushsection __rseq_cs_ptr_array, \"aw\"\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(label) "b") "\n\t" \
+		".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip, \
+				(post_commit_ip - start_ip), abort_ip)
+
+/*
+ * Exit points of a rseq critical section consist of all instructions outside
+ * of the critical section where a critical section can either branch to or
+ * reach through the normal course of its execution. The abort IP and the
+ * post-commit IP are already part of the __rseq_cs section and should not be
+ * explicitly defined as additional exit points. Knowing all exit points is
+ * useful to assist debuggers stepping over the critical section.
+ */
+#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip) \
+		".pushsection __rseq_exit_point_array, \"aw\"\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(start_ip)) "\n\t" \
+		LONG " " U32_U64_PAD(__rseq_str(exit_ip)) "\n\t" \
+		".popsection\n\t"
+
+#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"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* 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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [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
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	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,
+			       long voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* 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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* 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
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+#endif
+		/* 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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [v]			"m" (*v),
+		  [count]		"Ir" (count)
+		  RSEQ_INJECT_INPUT
+		: "$4", "memory"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	return 0;
+abort:
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* 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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* 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
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* 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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* 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
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
+#endif
+		/* 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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* 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
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* 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
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	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_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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		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_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* 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
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h
new file mode 100644
index 000000000..263eee84f
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-ppc-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_PPC_THREAD_POINTER
+#define _RSEQ_PPC_THREAD_POINTER
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+static inline void *rseq_thread_pointer(void)
+{
+#ifdef __powerpc64__
+	register void *__result asm ("r13");
+#else
+	register void *__result asm ("r2");
+#endif
+	asm ("" : "=r" (__result));
+	return __result;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-ppc.h b/tools/testing/selftests/rseq/rseq-ppc.h
new file mode 100644
index 000000000..bab8e0b9f
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-ppc.h
@@ -0,0 +1,791 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-ppc.h
+ *
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ * (C) Copyright 2016-2018 - Boqun Feng <boqun.feng@gmail.com>
+ */
+
+/*
+ * RSEQ_SIG is used with the following trap instruction:
+ *
+ * powerpc-be:    0f e5 00 0b           twui   r5,11
+ * powerpc64-le:  0b 00 e5 0f           twui   r5,11
+ * powerpc64-be:  0f e5 00 0b           twui   r5,11
+ */
+
+#define RSEQ_SIG	0x0fe5000b
+
+#define rseq_smp_mb()		__asm__ __volatile__ ("sync"	::: "memory", "cc")
+#define rseq_smp_lwsync()	__asm__ __volatile__ ("lwsync"	::: "memory", "cc")
+#define rseq_smp_rmb()		rseq_smp_lwsync()
+#define rseq_smp_wmb()		rseq_smp_lwsync()
+
+#define rseq_smp_load_acquire(p)					\
+__extension__ ({							\
+	__typeof(*p) ____p1 = RSEQ_READ_ONCE(*p);			\
+	rseq_smp_lwsync();						\
+	____p1;								\
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()	rseq_smp_lwsync()
+
+#define rseq_smp_store_release(p, v)					\
+do {									\
+	rseq_smp_lwsync();						\
+	RSEQ_WRITE_ONCE(*p, v);						\
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+/*
+ * The __rseq_cs_ptr_array and __rseq_cs sections can be used by debuggers to
+ * better handle single-stepping through the restartable critical sections.
+ */
+
+#ifdef __PPC64__
+
+#define RSEQ_STORE_LONG(arg)	"std%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* To memory ("m" constraint) */
+#define RSEQ_STORE_INT(arg)	"stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* To memory ("m" constraint) */
+#define RSEQ_LOAD_LONG(arg)	"ld%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* From memory ("m" constraint) */
+#define RSEQ_LOAD_INT(arg)	"lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* From memory ("m" constraint) */
+#define RSEQ_LOADX_LONG		"ldx "							/* From base register ("b" constraint) */
+#define RSEQ_CMP_LONG		"cmpd "
+#define RSEQ_CMP_LONG_INT	"cmpdi "
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,				\
+			start_ip, post_commit_offset, abort_ip)			\
+		".pushsection __rseq_cs, \"aw\"\n\t"				\
+		".balign 32\n\t"						\
+		__rseq_str(label) ":\n\t"					\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t"	\
+		".quad " __rseq_str(start_ip) ", " __rseq_str(post_commit_offset) ", " __rseq_str(abort_ip) "\n\t" \
+		".popsection\n\t"						\
+		".pushsection __rseq_cs_ptr_array, \"aw\"\n\t"			\
+		".quad " __rseq_str(label) "b\n\t"				\
+		".popsection\n\t"
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)			\
+		RSEQ_INJECT_ASM(1)						\
+		"lis %%r17, (" __rseq_str(cs_label) ")@highest\n\t"		\
+		"ori %%r17, %%r17, (" __rseq_str(cs_label) ")@higher\n\t"	\
+		"rldicr %%r17, %%r17, 32, 31\n\t"				\
+		"oris %%r17, %%r17, (" __rseq_str(cs_label) ")@high\n\t"	\
+		"ori %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t"		\
+		"std %%r17, %[" __rseq_str(rseq_cs) "]\n\t"			\
+		__rseq_str(label) ":\n\t"
+
+/*
+ * Exit points of a rseq critical section consist of all instructions outside
+ * of the critical section where a critical section can either branch to or
+ * reach through the normal course of its execution. The abort IP and the
+ * post-commit IP are already part of the __rseq_cs section and should not be
+ * explicitly defined as additional exit points. Knowing all exit points is
+ * useful to assist debuggers stepping over the critical section.
+ */
+#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip)			\
+		".pushsection __rseq_exit_point_array, \"aw\"\n\t"	\
+		".quad " __rseq_str(start_ip) ", " __rseq_str(exit_ip) "\n\t" \
+		".popsection\n\t"
+
+#else /* #ifdef __PPC64__ */
+
+#define RSEQ_STORE_LONG(arg)	"stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* To memory ("m" constraint) */
+#define RSEQ_STORE_INT(arg)	RSEQ_STORE_LONG(arg)					/* To memory ("m" constraint) */
+#define RSEQ_LOAD_LONG(arg)	"lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* From memory ("m" constraint) */
+#define RSEQ_LOAD_INT(arg)	RSEQ_LOAD_LONG(arg)					/* From memory ("m" constraint) */
+#define RSEQ_LOADX_LONG		"lwzx "							/* From base register ("b" constraint) */
+#define RSEQ_CMP_LONG		"cmpw "
+#define RSEQ_CMP_LONG_INT	"cmpwi "
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,				\
+			start_ip, post_commit_offset, abort_ip)			\
+		".pushsection __rseq_cs, \"aw\"\n\t"				\
+		".balign 32\n\t"						\
+		__rseq_str(label) ":\n\t"					\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t"	\
+		/* 32-bit only supported on BE */				\
+		".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) "\n\t" \
+		".popsection\n\t"					\
+		".pushsection __rseq_cs_ptr_array, \"aw\"\n\t"		\
+		".long 0x0, " __rseq_str(label) "b\n\t"			\
+		".popsection\n\t"
+
+/*
+ * Exit points of a rseq critical section consist of all instructions outside
+ * of the critical section where a critical section can either branch to or
+ * reach through the normal course of its execution. The abort IP and the
+ * post-commit IP are already part of the __rseq_cs section and should not be
+ * explicitly defined as additional exit points. Knowing all exit points is
+ * useful to assist debuggers stepping over the critical section.
+ */
+#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip)				\
+		".pushsection __rseq_exit_point_array, \"aw\"\n\t"		\
+		/* 32-bit only supported on BE */				\
+		".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(exit_ip) "\n\t"	\
+		".popsection\n\t"
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)			\
+		RSEQ_INJECT_ASM(1)						\
+		"lis %%r17, (" __rseq_str(cs_label) ")@ha\n\t"			\
+		"addi %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t"		\
+		RSEQ_STORE_INT(rseq_cs) "%%r17, %[" __rseq_str(rseq_cs) "]\n\t"	\
+		__rseq_str(label) ":\n\t"
+
+#endif /* #ifdef __PPC64__ */
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip)	\
+		__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,		\
+					(post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label)			\
+		RSEQ_INJECT_ASM(2)						\
+		RSEQ_LOAD_INT(current_cpu_id) "%%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \
+		"cmpw cr7, %[" __rseq_str(cpu_id) "], %%r17\n\t"		\
+		"bne- cr7, " __rseq_str(label) "\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, abort_label)				\
+		".pushsection __rseq_failure, \"ax\"\n\t"			\
+		".long " __rseq_str(RSEQ_SIG) "\n\t"				\
+		__rseq_str(label) ":\n\t"					\
+		"b %l[" __rseq_str(abort_label) "]\n\t"				\
+		".popsection\n\t"
+
+/*
+ * RSEQ_ASM_OPs: asm operations for rseq
+ * 	RSEQ_ASM_OP_R_*: has hard-code registers in it
+ * 	RSEQ_ASM_OP_* (else): doesn't have hard-code registers(unless cr7)
+ */
+#define RSEQ_ASM_OP_CMPEQ(var, expect, label)					\
+		RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"		\
+		RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expect) "]\n\t"		\
+		"bne- cr7, " __rseq_str(label) "\n\t"
+
+#define RSEQ_ASM_OP_CMPNE(var, expectnot, label)				\
+		RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"		\
+		RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t"		\
+		"beq- cr7, " __rseq_str(label) "\n\t"
+
+#define RSEQ_ASM_OP_STORE(value, var)						\
+		RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t"
+
+/* Load @var to r17 */
+#define RSEQ_ASM_OP_R_LOAD(var)							\
+		RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"
+
+/* Store r17 to @var */
+#define RSEQ_ASM_OP_R_STORE(var)						\
+		RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"
+
+/* Add @count to r17 */
+#define RSEQ_ASM_OP_R_ADD(count)						\
+		"add %%r17, %[" __rseq_str(count) "], %%r17\n\t"
+
+/* Load (r17 + voffp) to r17 */
+#define RSEQ_ASM_OP_R_LOADX(voffp)						\
+		RSEQ_LOADX_LONG "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t"
+
+/* TODO: implement a faster memcpy. */
+#define RSEQ_ASM_OP_R_MEMCPY() \
+		RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \
+		"beq 333f\n\t" \
+		"addi %%r20, %%r20, -1\n\t" \
+		"addi %%r21, %%r21, -1\n\t" \
+		"222:\n\t" \
+		"lbzu %%r18, 1(%%r20)\n\t" \
+		"stbu %%r18, 1(%%r21)\n\t" \
+		"addi %%r19, %%r19, -1\n\t" \
+		RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \
+		"bne 222b\n\t" \
+		"333:\n\t" \
+
+#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label)			\
+		RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"			\
+		__rseq_str(post_commit_label) ":\n\t"
+
+#define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label)			\
+		RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \
+		__rseq_str(post_commit_label) ":\n\t"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		/* final store */
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 2)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r17"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       long voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		/* cmp @v not equal to @expectnot */
+		RSEQ_ASM_OP_CMPNE(v, expectnot, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		/* cmp @v not equal to @expectnot */
+		RSEQ_ASM_OP_CMPNE(v, expectnot, %l[error2])
+#endif
+		/* load the value of @v */
+		RSEQ_ASM_OP_R_LOAD(v)
+		/* store it in @load */
+		RSEQ_ASM_OP_R_STORE(load)
+		/* dereference voffp(v) */
+		RSEQ_ASM_OP_R_LOADX(voffp)
+		/* final store the value at voffp(v) */
+		RSEQ_ASM_OP_R_FINAL_STORE(v, 2)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [voffp]		"b" (voffp),
+		  [load]		"m" (*load)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r17"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+		/* load the value of @v */
+		RSEQ_ASM_OP_R_LOAD(v)
+		/* add @count to it */
+		RSEQ_ASM_OP_R_ADD(count)
+		/* final store */
+		RSEQ_ASM_OP_R_FINAL_STORE(v, 2)
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [count]		"r" (count)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r17"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		/* try store */
+		RSEQ_ASM_OP_STORE(newv2, v2)
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 2)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r17"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		/* try store */
+		RSEQ_ASM_OP_STORE(newv2, v2)
+		RSEQ_INJECT_ASM(5)
+		/* for 'release' */
+		"lwsync\n\t"
+		/* final store */
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 2)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r17"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+		/* cmp @v2 equal to @expct2 */
+		RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[cmpfail])
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+		/* cmp @v2 equal to @expct2 */
+		RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[error3])
+#endif
+		/* final store */
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 2)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* cmp2 input */
+		  [v2]			"m" (*v2),
+		  [expect2]		"r" (expect2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r17"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("1st expected value comparison failed");
+error3:
+	rseq_after_asm_goto();
+	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)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* setup for mempcy */
+		"mr %%r19, %[len]\n\t"
+		"mr %%r20, %[src]\n\t"
+		"mr %%r21, %[dst]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		/* try memcpy */
+		RSEQ_ASM_OP_R_MEMCPY()
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 2)
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* 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_INJECT_INPUT
+		: "memory", "cc", "r17", "r18", "r19", "r20", "r21"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* setup for mempcy */
+		"mr %%r19, %[len]\n\t"
+		"mr %%r20, %[src]\n\t"
+		"mr %%r21, %[dst]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		/* cmp cpuid */
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		/* cmp @v equal to @expect */
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		/* try memcpy */
+		RSEQ_ASM_OP_R_MEMCPY()
+		RSEQ_INJECT_ASM(5)
+		/* for 'release' */
+		"lwsync\n\t"
+		/* final store */
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 2)
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* 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_INJECT_INPUT
+		: "memory", "cc", "r17", "r18", "r19", "r20", "r21"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
new file mode 100644
index 000000000..4e6dc5f0c
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -0,0 +1,610 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+
+/*
+ * RSEQ_SIG uses the trap4 instruction. As Linux does not make use of the
+ * access-register mode nor the linkage stack this instruction will always
+ * cause a special-operation exception (the trap-enabled bit in the DUCT
+ * is and will stay 0). The instruction pattern is
+ *	b2 ff 0f ff	trap4	4095(%r0)
+ */
+#define RSEQ_SIG	0xB2FF0FFF
+
+#define rseq_smp_mb()	__asm__ __volatile__ ("bcr 15,0" ::: "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_barrier();							\
+	____p1;								\
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()	rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)					\
+do {									\
+	rseq_barrier();							\
+	RSEQ_WRITE_ONCE(*p, v);						\
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#ifdef __s390x__
+
+#define LONG_L			"lg"
+#define LONG_S			"stg"
+#define LONG_LT_R		"ltgr"
+#define LONG_CMP		"cg"
+#define LONG_CMP_R		"cgr"
+#define LONG_ADDI		"aghi"
+#define LONG_ADD_R		"agr"
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,			\
+				start_ip, post_commit_offset, abort_ip)	\
+		".pushsection __rseq_cs, \"aw\"\n\t"			\
+		".balign 32\n\t"					\
+		__rseq_str(label) ":\n\t"				\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		".quad " __rseq_str(start_ip) ", " __rseq_str(post_commit_offset) ", " __rseq_str(abort_ip) "\n\t" \
+		".popsection\n\t"					\
+		".pushsection __rseq_cs_ptr_array, \"aw\"\n\t"		\
+		".quad " __rseq_str(label) "b\n\t"			\
+		".popsection\n\t"
+
+/*
+ * Exit points of a rseq critical section consist of all instructions outside
+ * of the critical section where a critical section can either branch to or
+ * reach through the normal course of its execution. The abort IP and the
+ * post-commit IP are already part of the __rseq_cs section and should not be
+ * explicitly defined as additional exit points. Knowing all exit points is
+ * useful to assist debuggers stepping over the critical section.
+ */
+#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip)			\
+		".pushsection __rseq_exit_point_array, \"aw\"\n\t"	\
+		".quad " __rseq_str(start_ip) ", " __rseq_str(exit_ip) "\n\t" \
+		".popsection\n\t"
+
+#elif __s390__
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,			\
+				start_ip, post_commit_offset, abort_ip)	\
+		".pushsection __rseq_cs, \"aw\"\n\t"			\
+		".balign 32\n\t"					\
+		__rseq_str(label) ":\n\t"				\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) "\n\t" \
+		".popsection\n\t"					\
+		".pushsection __rseq_cs_ptr_array, \"aw\"\n\t"		\
+		".long 0x0, " __rseq_str(label) "b\n\t"			\
+		".popsection\n\t"
+
+/*
+ * Exit points of a rseq critical section consist of all instructions outside
+ * of the critical section where a critical section can either branch to or
+ * reach through the normal course of its execution. The abort IP and the
+ * post-commit IP are already part of the __rseq_cs section and should not be
+ * explicitly defined as additional exit points. Knowing all exit points is
+ * useful to assist debuggers stepping over the critical section.
+ */
+#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip)			\
+		".pushsection __rseq_exit_point_array, \"aw\"\n\t"	\
+		".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(exit_ip) "\n\t" \
+		".popsection\n\t"
+
+#define LONG_L			"l"
+#define LONG_S			"st"
+#define LONG_LT_R		"ltr"
+#define LONG_CMP		"c"
+#define LONG_CMP_R		"cr"
+#define LONG_ADDI		"ahi"
+#define LONG_ADD_R		"ar"
+
+#endif
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_TABLE(label, 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)					\
+		"larl %%r0, " __rseq_str(cs_label) "\n\t"		\
+		LONG_S " %%r0, %[" __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)					\
+		"c %[" __rseq_str(cpu_id) "], %[" __rseq_str(current_cpu_id) "]\n\t" \
+		"jnz " __rseq_str(label) "\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, teardown, abort_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		".long " __rseq_str(RSEQ_SIG) "\n\t"			\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"jg %l[" __rseq_str(abort_label) "]\n\t"		\
+		".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"jg %l[" __rseq_str(cmpfail_label) "]\n\t"		\
+		".popsection\n\t"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %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_CMP " %[expect], %[v]\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/*
+ * Compare @v against @expectnot. When it does _not_ match, load @v
+ * into @load, and store the content of *@v + voffp into @v.
+ */
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       long voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " %%r1, %[v]\n\t"
+		LONG_CMP_R " %%r1, %[expectnot]\n\t"
+		"je %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 " %%r1, %[v]\n\t"
+		LONG_CMP_R " %%r1, %[expectnot]\n\t"
+		"je %l[error2]\n\t"
+#endif
+		LONG_S " %%r1, %[load]\n\t"
+		LONG_ADD_R " %%r1, %[voffp]\n\t"
+		LONG_L " %%r1, 0(%%r1)\n\t"
+		/* final store */
+		LONG_S " %%r1, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [voffp]		"r" (voffp),
+		  [load]		"m" (*load)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0", "r1"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, 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 " %%r0, %[v]\n\t"
+		LONG_ADD_R " %%r0, %[count]\n\t"
+		/* final store */
+		LONG_S " %%r0, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [count]		"r" (count)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %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_CMP " %[expect], %[v]\n\t"
+		"jnz %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)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+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)
+{
+	return rseq_cmpeqv_trystorev_storev(v, expect, v2, newv2, newv, cpu);
+}
+
+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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+		LONG_CMP " %[expect2], %[v2]\n\t"
+		"jnz %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_CMP " %[expect], %[v]\n\t"
+		"jnz %l[error2]\n\t"
+		LONG_CMP " %[expect2], %[v2]\n\t"
+		"jnz %l[error3]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* cmp2 input */
+		  [v2]			"m" (*v2),
+		  [expect2]		"r" (expect2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("1st expected value comparison failed");
+error3:
+	rseq_after_asm_goto();
+	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)
+{
+	uint64_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		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, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz 7f\n\t"
+#endif
+		/* try memcpy */
+		LONG_LT_R " %[len], %[len]\n\t"
+		"jz 333f\n\t"
+		"222:\n\t"
+		"ic %%r0,0(%[src])\n\t"
+		"stc %%r0,0(%[dst])\n\t"
+		LONG_ADDI " %[src], 1\n\t"
+		LONG_ADDI " %[dst], 1\n\t"
+		LONG_ADDI " %[len], -1\n\t"
+		"jnz 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"
+		RSEQ_ASM_DEFINE_ABORT(4,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			abort)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+			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,
+			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,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			error2)
+#endif
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+		  /* 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
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+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)
+{
+	return rseq_cmpeqv_trymemcpy_storev(v, expect, dst, src, len,
+					    newv, cpu);
+}
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq-skip.h b/tools/testing/selftests/rseq/rseq-skip.h
new file mode 100644
index 000000000..7b53dac1f
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-skip.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-skip.h
+ *
+ * (C) Copyright 2017-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	return -1;
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       long voffp, intptr_t *load, int cpu)
+{
+	return -1;
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+	return -1;
+}
+
+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)
+{
+	return -1;
+}
+
+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)
+{
+	return -1;
+}
+
+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)
+{
+	return -1;
+}
+
+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)
+{
+	return -1;
+}
+
+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)
+{
+	return -1;
+}
diff --git a/tools/testing/selftests/rseq/rseq-thread-pointer.h b/tools/testing/selftests/rseq/rseq-thread-pointer.h
new file mode 100644
index 000000000..977c25d75
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-thread-pointer.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_THREAD_POINTER
+#define _RSEQ_THREAD_POINTER
+
+#if defined(__x86_64__) || defined(__i386__)
+#include "rseq-x86-thread-pointer.h"
+#elif defined(__PPC__)
+#include "rseq-ppc-thread-pointer.h"
+#else
+#include "rseq-generic-thread-pointer.h"
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h
new file mode 100644
index 000000000..d3133587d
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-x86-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_X86_THREAD_POINTER
+#define _RSEQ_X86_THREAD_POINTER
+
+#include <features.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#if __GNUC_PREREQ (11, 1)
+static inline void *rseq_thread_pointer(void)
+{
+	return __builtin_thread_pointer();
+}
+#else
+static inline void *rseq_thread_pointer(void)
+{
+	void *__result;
+
+# ifdef __x86_64__
+	__asm__ ("mov %%fs:0, %0" : "=r" (__result));
+# else
+	__asm__ ("mov %%gs:0, %0" : "=r" (__result));
+# endif
+	return __result;
+}
+#endif /* !GCC 11 */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h
new file mode 100644
index 000000000..bd01dc41c
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-x86.h
@@ -0,0 +1,1365 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-x86.h
+ *
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#include <stdint.h>
+
+/*
+ * RSEQ_SIG is used with the following reserved undefined instructions, which
+ * trap in user-space:
+ *
+ * x86-32:    0f b9 3d 53 30 05 53      ud1    0x53053053,%edi
+ * x86-64:    0f b9 3d 53 30 05 53      ud1    0x53053053(%rip),%edi
+ */
+#define RSEQ_SIG	0x53053053
+
+/*
+ * Due to a compiler optimization bug in gcc-8 with asm goto and TLS asm input
+ * operands, we cannot use "m" input operands, and rather pass the __rseq_abi
+ * address through a "r" input operand.
+ */
+
+/* Offset of cpu_id and rseq_cs fields in struct rseq. */
+#define RSEQ_CPU_ID_OFFSET	4
+#define RSEQ_CS_OFFSET		8
+
+#ifdef __x86_64__
+
+#define RSEQ_ASM_TP_SEGMENT	%%fs
+
+#define rseq_smp_mb()	\
+	__asm__ __volatile__ ("lock; addl $0,-128(%%rsp)" ::: "memory", "cc")
+#define rseq_smp_rmb()	rseq_barrier()
+#define rseq_smp_wmb()	rseq_barrier()
+
+#define rseq_smp_load_acquire(p)					\
+__extension__ ({							\
+	__typeof(*p) ____p1 = RSEQ_READ_ONCE(*p);			\
+	rseq_barrier();							\
+	____p1;								\
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()	rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)					\
+do {									\
+	rseq_barrier();							\
+	RSEQ_WRITE_ONCE(*p, v);						\
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,			\
+				start_ip, post_commit_offset, abort_ip)	\
+		".pushsection __rseq_cs, \"aw\"\n\t"			\
+		".balign 32\n\t"					\
+		__rseq_str(label) ":\n\t"				\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		".quad " __rseq_str(start_ip) ", " __rseq_str(post_commit_offset) ", " __rseq_str(abort_ip) "\n\t" \
+		".popsection\n\t"					\
+		".pushsection __rseq_cs_ptr_array, \"aw\"\n\t"		\
+		".quad " __rseq_str(label) "b\n\t"			\
+		".popsection\n\t"
+
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,		\
+				(post_commit_ip - start_ip), abort_ip)
+
+/*
+ * Exit points of a rseq critical section consist of all instructions outside
+ * of the critical section where a critical section can either branch to or
+ * reach through the normal course of its execution. The abort IP and the
+ * post-commit IP are already part of the __rseq_cs section and should not be
+ * explicitly defined as additional exit points. Knowing all exit points is
+ * useful to assist debuggers stepping over the critical section.
+ */
+#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip)			\
+		".pushsection __rseq_exit_point_array, \"aw\"\n\t"	\
+		".quad " __rseq_str(start_ip) ", " __rseq_str(exit_ip) "\n\t" \
+		".popsection\n\t"
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)		\
+		RSEQ_INJECT_ASM(1)					\
+		"leaq " __rseq_str(cs_label) "(%%rip), %%rax\n\t"	\
+		"movq %%rax, " __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)					\
+		"cmpl %[" __rseq_str(cpu_id) "], " __rseq_str(current_cpu_id) "\n\t" \
+		"jnz " __rseq_str(label) "\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, teardown, abort_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		/* Disassembler-friendly signature: ud1 <sig>(%rip),%edi. */ \
+		".byte 0x0f, 0xb9, 0x3d\n\t"				\
+		".long " __rseq_str(RSEQ_SIG) "\n\t"			\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"jmp %l[" __rseq_str(abort_label) "]\n\t"		\
+		".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"jmp %l[" __rseq_str(cmpfail_label) "]\n\t"		\
+		".popsection\n\t"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"cmpq %[v], %[expect]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+		"cmpq %[v], %[expect]\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* final store */
+		"movq %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		: "memory", "cc", "rax"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/*
+ * Compare @v against @expectnot. When it does _not_ match, load @v
+ * into @load, and store the content of *@v + voffp into @v.
+ */
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       long voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"movq %[v], %%rbx\n\t"
+		"cmpq %%rbx, %[expectnot]\n\t"
+		"je %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+		"movq %[v], %%rbx\n\t"
+		"cmpq %%rbx, %[expectnot]\n\t"
+		"je %l[error2]\n\t"
+#endif
+		"movq %%rbx, %[load]\n\t"
+		"addq %[voffp], %%rbx\n\t"
+		"movq (%%rbx), %%rbx\n\t"
+		/* final store */
+		"movq %%rbx, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [voffp]		"er" (voffp),
+		  [load]		"m" (*load)
+		: "memory", "cc", "rax", "rbx"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+#endif
+		/* final store */
+		"addq %[count], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [count]		"er" (count)
+		: "memory", "cc", "rax"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+#define RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+
+/*
+ *   pval = *(ptr+off)
+ *  *pval += inc;
+ */
+static inline __attribute__((always_inline))
+int rseq_offset_deref_addv(intptr_t *ptr, long off, intptr_t inc, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+#endif
+		/* get p+v */
+		"movq %[ptr], %%rbx\n\t"
+		"addq %[off], %%rbx\n\t"
+		/* get pv */
+		"movq (%%rbx), %%rcx\n\t"
+		/* *pv += inc */
+		"addq %[inc], (%%rcx)\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* final store input */
+		  [ptr]			"m" (*ptr),
+		  [off]			"er" (off),
+		  [inc]			"er" (inc)
+		: "memory", "cc", "rax", "rbx", "rcx"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	return 0;
+abort:
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"cmpq %[v], %[expect]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+		"cmpq %[v], %[expect]\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* try store */
+		"movq %[newv2], %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		"movq %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		: "memory", "cc", "rax"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* x86-64 is TSO. */
+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)
+{
+	return rseq_cmpeqv_trystorev_storev(v, expect, v2, newv2, newv, cpu);
+}
+
+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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"cmpq %[v], %[expect]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+		"cmpq %[v2], %[expect2]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+		"cmpq %[v], %[expect]\n\t"
+		"jnz %l[error2]\n\t"
+		"cmpq %[v2], %[expect2]\n\t"
+		"jnz %l[error3]\n\t"
+#endif
+		/* final store */
+		"movq %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* cmp2 input */
+		  [v2]			"m" (*v2),
+		  [expect2]		"r" (expect2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		: "memory", "cc", "rax"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("1st expected value comparison failed");
+error3:
+	rseq_after_asm_goto();
+	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)
+{
+	uint64_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		"movq %[src], %[rseq_scratch0]\n\t"
+		"movq %[dst], %[rseq_scratch1]\n\t"
+		"movq %[len], %[rseq_scratch2]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"cmpq %[v], %[expect]\n\t"
+		"jnz 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
+		"cmpq %[v], %[expect]\n\t"
+		"jnz 7f\n\t"
+#endif
+		/* try memcpy */
+		"test %[len], %[len]\n\t" \
+		"jz 333f\n\t" \
+		"222:\n\t" \
+		"movb (%[src]), %%al\n\t" \
+		"movb %%al, (%[dst])\n\t" \
+		"inc %[src]\n\t" \
+		"inc %[dst]\n\t" \
+		"dec %[len]\n\t" \
+		"jnz 222b\n\t" \
+		"333:\n\t" \
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		"movq %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		"movq %[rseq_scratch2], %[len]\n\t"
+		"movq %[rseq_scratch1], %[dst]\n\t"
+		"movq %[rseq_scratch0], %[src]\n\t"
+		RSEQ_ASM_DEFINE_ABORT(4,
+			"movq %[rseq_scratch2], %[len]\n\t"
+			"movq %[rseq_scratch1], %[dst]\n\t"
+			"movq %[rseq_scratch0], %[src]\n\t",
+			abort)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+			"movq %[rseq_scratch2], %[len]\n\t"
+			"movq %[rseq_scratch1], %[dst]\n\t"
+			"movq %[rseq_scratch0], %[src]\n\t",
+			cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+			"movq %[rseq_scratch2], %[len]\n\t"
+			"movq %[rseq_scratch1], %[dst]\n\t"
+			"movq %[rseq_scratch0], %[src]\n\t",
+			error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+			"movq %[rseq_scratch2], %[len]\n\t"
+			"movq %[rseq_scratch1], %[dst]\n\t"
+			"movq %[rseq_scratch0], %[src]\n\t",
+			error2)
+#endif
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* 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])
+		: "memory", "cc", "rax"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* x86-64 is TSO. */
+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)
+{
+	return rseq_cmpeqv_trymemcpy_storev(v, expect, dst, src, len,
+					    newv, cpu);
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
+
+#elif defined(__i386__)
+
+#define RSEQ_ASM_TP_SEGMENT	%%gs
+
+#define rseq_smp_mb()	\
+	__asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc")
+#define rseq_smp_rmb()	\
+	__asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc")
+#define rseq_smp_wmb()	\
+	__asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc")
+
+#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 */
+
+/*
+ * Use eax as scratch register and take memory operands as input to
+ * lessen register pressure. Especially needed when compiling in O0.
+ */
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,			\
+				start_ip, post_commit_offset, abort_ip)	\
+		".pushsection __rseq_cs, \"aw\"\n\t"			\
+		".balign 32\n\t"					\
+		__rseq_str(label) ":\n\t"				\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		".long " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) ", 0x0\n\t" \
+		".popsection\n\t"					\
+		".pushsection __rseq_cs_ptr_array, \"aw\"\n\t"		\
+		".long " __rseq_str(label) "b, 0x0\n\t"			\
+		".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,		\
+				(post_commit_ip - start_ip), abort_ip)
+
+/*
+ * Exit points of a rseq critical section consist of all instructions outside
+ * of the critical section where a critical section can either branch to or
+ * reach through the normal course of its execution. The abort IP and the
+ * post-commit IP are already part of the __rseq_cs section and should not be
+ * explicitly defined as additional exit points. Knowing all exit points is
+ * useful to assist debuggers stepping over the critical section.
+ */
+#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip)			\
+		".pushsection __rseq_exit_point_array, \"aw\"\n\t"	\
+		".long " __rseq_str(start_ip) ", 0x0, " __rseq_str(exit_ip) ", 0x0\n\t" \
+		".popsection\n\t"
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)		\
+		RSEQ_INJECT_ASM(1)					\
+		"movl $" __rseq_str(cs_label) ", " __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)					\
+		"cmpl %[" __rseq_str(cpu_id) "], " __rseq_str(current_cpu_id) "\n\t" \
+		"jnz " __rseq_str(label) "\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, teardown, abort_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		/* Disassembler-friendly signature: ud1 <sig>,%edi. */	\
+		".byte 0x0f, 0xb9, 0x3d\n\t"				\
+		".long " __rseq_str(RSEQ_SIG) "\n\t"			\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"jmp %l[" __rseq_str(abort_label) "]\n\t"		\
+		".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"jmp %l[" __rseq_str(cmpfail_label) "]\n\t"		\
+		".popsection\n\t"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"cmpl %[v], %[expect]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+		"cmpl %[v], %[expect]\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* final store */
+		"movl %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		: "memory", "cc", "eax"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/*
+ * Compare @v against @expectnot. When it does _not_ match, load @v
+ * into @load, and store the content of *@v + voffp into @v.
+ */
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       long voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"movl %[v], %%ebx\n\t"
+		"cmpl %%ebx, %[expectnot]\n\t"
+		"je %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+		"movl %[v], %%ebx\n\t"
+		"cmpl %%ebx, %[expectnot]\n\t"
+		"je %l[error2]\n\t"
+#endif
+		"movl %%ebx, %[load]\n\t"
+		"addl %[voffp], %%ebx\n\t"
+		"movl (%%ebx), %%ebx\n\t"
+		/* final store */
+		"movl %%ebx, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [voffp]		"ir" (voffp),
+		  [load]		"m" (*load)
+		: "memory", "cc", "eax", "ebx"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+#endif
+		/* final store */
+		"addl %[count], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [count]		"ir" (count)
+		: "memory", "cc", "eax"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"cmpl %[v], %[expect]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+		"cmpl %[v], %[expect]\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* try store */
+		"movl %[newv2], %%eax\n\t"
+		"movl %%eax, %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		"movl %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"m" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		: "memory", "cc", "eax"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"movl %[expect], %%eax\n\t"
+		"cmpl %[v], %%eax\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+		"movl %[expect], %%eax\n\t"
+		"cmpl %[v], %%eax\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* try store */
+		"movl %[newv2], %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		"lock; addl $0,-128(%%esp)\n\t"
+		/* final store */
+		"movl %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"m" (expect),
+		  [newv]		"r" (newv)
+		: "memory", "cc", "eax"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	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)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"cmpl %[v], %[expect]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+		"cmpl %[expect2], %[v2]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
+		"cmpl %[v], %[expect]\n\t"
+		"jnz %l[error2]\n\t"
+		"cmpl %[expect2], %[v2]\n\t"
+		"jnz %l[error3]\n\t"
+#endif
+		"movl %[newv], %%eax\n\t"
+		/* final store */
+		"movl %%eax, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* cmp2 input */
+		  [v2]			"m" (*v2),
+		  [expect2]		"r" (expect2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"m" (newv)
+		: "memory", "cc", "eax"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("1st expected value comparison failed");
+error3:
+	rseq_after_asm_goto();
+	rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+/* TODO: implement a faster memcpy. */
+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)
+{
+	uint32_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		"movl %[src], %[rseq_scratch0]\n\t"
+		"movl %[dst], %[rseq_scratch1]\n\t"
+		"movl %[len], %[rseq_scratch2]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"movl %[expect], %%eax\n\t"
+		"cmpl %%eax, %[v]\n\t"
+		"jnz 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
+		"movl %[expect], %%eax\n\t"
+		"cmpl %%eax, %[v]\n\t"
+		"jnz 7f\n\t"
+#endif
+		/* try memcpy */
+		"test %[len], %[len]\n\t" \
+		"jz 333f\n\t" \
+		"222:\n\t" \
+		"movb (%[src]), %%al\n\t" \
+		"movb %%al, (%[dst])\n\t" \
+		"inc %[src]\n\t" \
+		"inc %[dst]\n\t" \
+		"dec %[len]\n\t" \
+		"jnz 222b\n\t" \
+		"333:\n\t" \
+		RSEQ_INJECT_ASM(5)
+		"movl %[newv], %%eax\n\t"
+		/* final store */
+		"movl %%eax, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		"movl %[rseq_scratch2], %[len]\n\t"
+		"movl %[rseq_scratch1], %[dst]\n\t"
+		"movl %[rseq_scratch0], %[src]\n\t"
+		RSEQ_ASM_DEFINE_ABORT(4,
+			"movl %[rseq_scratch2], %[len]\n\t"
+			"movl %[rseq_scratch1], %[dst]\n\t"
+			"movl %[rseq_scratch0], %[src]\n\t",
+			abort)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+			"movl %[rseq_scratch2], %[len]\n\t"
+			"movl %[rseq_scratch1], %[dst]\n\t"
+			"movl %[rseq_scratch0], %[src]\n\t",
+			cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+			"movl %[rseq_scratch2], %[len]\n\t"
+			"movl %[rseq_scratch1], %[dst]\n\t"
+			"movl %[rseq_scratch0], %[src]\n\t",
+			error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+			"movl %[rseq_scratch2], %[len]\n\t"
+			"movl %[rseq_scratch1], %[dst]\n\t"
+			"movl %[rseq_scratch0], %[src]\n\t",
+			error2)
+#endif
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"m" (expect),
+		  [newv]		"m" (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])
+		: "memory", "cc", "eax"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* TODO: implement a faster memcpy. */
+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)
+{
+	uint32_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
+#endif
+		"movl %[src], %[rseq_scratch0]\n\t"
+		"movl %[dst], %[rseq_scratch1]\n\t"
+		"movl %[len], %[rseq_scratch2]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
+		RSEQ_INJECT_ASM(3)
+		"movl %[expect], %%eax\n\t"
+		"cmpl %%eax, %[v]\n\t"
+		"jnz 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
+		"movl %[expect], %%eax\n\t"
+		"cmpl %%eax, %[v]\n\t"
+		"jnz 7f\n\t"
+#endif
+		/* try memcpy */
+		"test %[len], %[len]\n\t" \
+		"jz 333f\n\t" \
+		"222:\n\t" \
+		"movb (%[src]), %%al\n\t" \
+		"movb %%al, (%[dst])\n\t" \
+		"inc %[src]\n\t" \
+		"inc %[dst]\n\t" \
+		"dec %[len]\n\t" \
+		"jnz 222b\n\t" \
+		"333:\n\t" \
+		RSEQ_INJECT_ASM(5)
+		"lock; addl $0,-128(%%esp)\n\t"
+		"movl %[newv], %%eax\n\t"
+		/* final store */
+		"movl %%eax, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		"movl %[rseq_scratch2], %[len]\n\t"
+		"movl %[rseq_scratch1], %[dst]\n\t"
+		"movl %[rseq_scratch0], %[src]\n\t"
+		RSEQ_ASM_DEFINE_ABORT(4,
+			"movl %[rseq_scratch2], %[len]\n\t"
+			"movl %[rseq_scratch1], %[dst]\n\t"
+			"movl %[rseq_scratch0], %[src]\n\t",
+			abort)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+			"movl %[rseq_scratch2], %[len]\n\t"
+			"movl %[rseq_scratch1], %[dst]\n\t"
+			"movl %[rseq_scratch0], %[src]\n\t",
+			cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+			"movl %[rseq_scratch2], %[len]\n\t"
+			"movl %[rseq_scratch1], %[dst]\n\t"
+			"movl %[rseq_scratch0], %[src]\n\t",
+			error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+			"movl %[rseq_scratch2], %[len]\n\t"
+			"movl %[rseq_scratch1], %[dst]\n\t"
+			"movl %[rseq_scratch0], %[src]\n\t",
+			error2)
+#endif
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_offset]		"r" (rseq_offset),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"m" (expect),
+		  [newv]		"m" (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])
+		: "memory", "cc", "eax"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	rseq_after_asm_goto();
+	return 0;
+abort:
+	rseq_after_asm_goto();
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	rseq_after_asm_goto();
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_after_asm_goto();
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_after_asm_goto();
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
new file mode 100644
index 000000000..e20191fb4
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * rseq.c
+ *
+ * Copyright (C) 2016 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; only
+ * version 2.1 of the License.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Lesser General Public License for more details.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <syscall.h>
+#include <assert.h>
+#include <signal.h>
+#include <limits.h>
+#include <dlfcn.h>
+#include <stddef.h>
+
+#include <linux/compiler.h>
+
+#include "../kselftest.h"
+#include "rseq.h"
+
+/*
+ * Define weak versions to play nice with binaries that are statically linked
+ * against a libc that doesn't support registering its own rseq.
+ */
+__weak ptrdiff_t __rseq_offset;
+__weak unsigned int __rseq_size;
+__weak unsigned int __rseq_flags;
+
+static const ptrdiff_t *libc_rseq_offset_p = &__rseq_offset;
+static const unsigned int *libc_rseq_size_p = &__rseq_size;
+static const unsigned int *libc_rseq_flags_p = &__rseq_flags;
+
+/* Offset from the thread pointer to the rseq area.  */
+ptrdiff_t rseq_offset;
+
+/* Size of the registered rseq area.  0 if the registration was
+   unsuccessful.  */
+unsigned int rseq_size = -1U;
+
+/* Flags used during rseq registration.  */
+unsigned int rseq_flags;
+
+static int rseq_ownership;
+
+static
+__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = {
+	.cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
+};
+
+static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len,
+		    int flags, uint32_t sig)
+{
+	return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
+}
+
+int rseq_available(void)
+{
+	int rc;
+
+	rc = sys_rseq(NULL, 0, 0, 0);
+	if (rc != -1)
+		abort();
+	switch (errno) {
+	case ENOSYS:
+		return 0;
+	case EINVAL:
+		return 1;
+	default:
+		abort();
+	}
+}
+
+int rseq_register_current_thread(void)
+{
+	int rc;
+
+	if (!rseq_ownership) {
+		/* Treat libc's ownership as a successful registration. */
+		return 0;
+	}
+	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), 0, RSEQ_SIG);
+	if (rc)
+		return -1;
+	assert(rseq_current_cpu_raw() >= 0);
+	return 0;
+}
+
+int rseq_unregister_current_thread(void)
+{
+	int rc;
+
+	if (!rseq_ownership) {
+		/* Treat libc's ownership as a successful unregistration. */
+		return 0;
+	}
+	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+	if (rc)
+		return -1;
+	return 0;
+}
+
+static __attribute__((constructor))
+void rseq_init(void)
+{
+	/*
+	 * If the libc's registered rseq size isn't already valid, it may be
+	 * because the binary is dynamically linked and not necessarily due to
+	 * libc not having registered a restartable sequence.  Try to find the
+	 * symbols if that's the case.
+	 */
+	if (!*libc_rseq_size_p) {
+		libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset");
+		libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size");
+		libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags");
+	}
+	if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p &&
+			*libc_rseq_size_p != 0) {
+		/* rseq registration owned by glibc */
+		rseq_offset = *libc_rseq_offset_p;
+		rseq_size = *libc_rseq_size_p;
+		rseq_flags = *libc_rseq_flags_p;
+		return;
+	}
+	if (!rseq_available())
+		return;
+	rseq_ownership = 1;
+	rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer();
+	rseq_size = sizeof(struct rseq_abi);
+	rseq_flags = 0;
+}
+
+static __attribute__((destructor))
+void rseq_exit(void)
+{
+	if (!rseq_ownership)
+		return;
+	rseq_offset = 0;
+	rseq_size = -1U;
+	rseq_ownership = 0;
+}
+
+int32_t rseq_fallback_current_cpu(void)
+{
+	int32_t cpu;
+
+	cpu = sched_getcpu();
+	if (cpu < 0) {
+		perror("sched_getcpu()");
+		abort();
+	}
+	return cpu;
+}
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
new file mode 100644
index 000000000..9d850b290
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -0,0 +1,175 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq.h
+ *
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef RSEQ_H
+#define RSEQ_H
+
+#include <stdint.h>
+#include <stdbool.h>
+#include <pthread.h>
+#include <signal.h>
+#include <sched.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stddef.h>
+#include "rseq-abi.h"
+#include "compiler.h"
+
+/*
+ * Empty code injection macros, override when testing.
+ * It is important to consider that the ASM injection macros need to be
+ * fully reentrant (e.g. do not modify the stack).
+ */
+#ifndef RSEQ_INJECT_ASM
+#define RSEQ_INJECT_ASM(n)
+#endif
+
+#ifndef RSEQ_INJECT_C
+#define RSEQ_INJECT_C(n)
+#endif
+
+#ifndef RSEQ_INJECT_INPUT
+#define RSEQ_INJECT_INPUT
+#endif
+
+#ifndef RSEQ_INJECT_CLOBBER
+#define RSEQ_INJECT_CLOBBER
+#endif
+
+#ifndef RSEQ_INJECT_FAILED
+#define RSEQ_INJECT_FAILED
+#endif
+
+#include "rseq-thread-pointer.h"
+
+/* Offset from the thread pointer to the rseq area.  */
+extern ptrdiff_t rseq_offset;
+/* Size of the registered rseq area.  0 if the registration was
+   unsuccessful.  */
+extern unsigned int rseq_size;
+/* Flags used during rseq registration.  */
+extern unsigned int rseq_flags;
+
+static inline struct rseq_abi *rseq_get_abi(void)
+{
+	return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset);
+}
+
+#define rseq_likely(x)		__builtin_expect(!!(x), 1)
+#define rseq_unlikely(x)	__builtin_expect(!!(x), 0)
+#define rseq_barrier()		__asm__ __volatile__("" : : : "memory")
+
+#define RSEQ_ACCESS_ONCE(x)	(*(__volatile__  __typeof__(x) *)&(x))
+#define RSEQ_WRITE_ONCE(x, v)	__extension__ ({ RSEQ_ACCESS_ONCE(x) = (v); })
+#define RSEQ_READ_ONCE(x)	RSEQ_ACCESS_ONCE(x)
+
+#define __rseq_str_1(x)	#x
+#define __rseq_str(x)		__rseq_str_1(x)
+
+#define rseq_log(fmt, args...)						       \
+	fprintf(stderr, fmt "(in %s() at " __FILE__ ":" __rseq_str(__LINE__)"\n", \
+		## args, __func__)
+
+#define rseq_bug(fmt, args...)		\
+	do {				\
+		rseq_log(fmt, ##args);	\
+		abort();		\
+	} while (0)
+
+#if defined(__x86_64__) || defined(__i386__)
+#include <rseq-x86.h>
+#elif defined(__ARMEL__)
+#include <rseq-arm.h>
+#elif defined (__AARCH64EL__)
+#include <rseq-arm64.h>
+#elif defined(__PPC__)
+#include <rseq-ppc.h>
+#elif defined(__mips__)
+#include <rseq-mips.h>
+#elif defined(__s390__)
+#include <rseq-s390.h>
+#else
+#error unsupported target
+#endif
+
+/*
+ * Register rseq for the current thread. This needs to be called once
+ * by any thread which uses restartable sequences, before they start
+ * using restartable sequences, to ensure restartable sequences
+ * succeed. A restartable sequence executed from a non-registered
+ * thread will always fail.
+ */
+int rseq_register_current_thread(void);
+
+/*
+ * Unregister rseq for current thread.
+ */
+int rseq_unregister_current_thread(void);
+
+/*
+ * Restartable sequence fallback for reading the current CPU number.
+ */
+int32_t rseq_fallback_current_cpu(void);
+
+/*
+ * Values returned can be either the current CPU number, -1 (rseq is
+ * uninitialized), or -2 (rseq initialization has failed).
+ */
+static inline int32_t rseq_current_cpu_raw(void)
+{
+	return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id);
+}
+
+/*
+ * Returns a possible CPU number, which is typically the current CPU.
+ * The returned CPU number can be used to prepare for an rseq critical
+ * section, which will confirm whether the cpu number is indeed the
+ * current one, and whether rseq is initialized.
+ *
+ * The CPU number returned by rseq_cpu_start should always be validated
+ * by passing it to a rseq asm sequence, or by comparing it to the
+ * return value of rseq_current_cpu_raw() if the rseq asm sequence
+ * does not need to be invoked.
+ */
+static inline uint32_t rseq_cpu_start(void)
+{
+	return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id_start);
+}
+
+static inline uint32_t rseq_current_cpu(void)
+{
+	int32_t cpu;
+
+	cpu = rseq_current_cpu_raw();
+	if (rseq_unlikely(cpu < 0))
+		cpu = rseq_fallback_current_cpu();
+	return cpu;
+}
+
+static inline void rseq_clear_rseq_cs(void)
+{
+	RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0);
+}
+
+/*
+ * rseq_prepare_unload() should be invoked by each thread executing a rseq
+ * critical section at least once between their last critical section and
+ * library unload of the library defining the rseq critical section (struct
+ * rseq_cs) or the code referred to by the struct rseq_cs start_ip and
+ * post_commit_offset fields. This also applies to use of rseq in code
+ * generated by JIT: rseq_prepare_unload() should be invoked at least once by
+ * each thread executing a rseq critical section before reclaim of the memory
+ * holding the struct rseq_cs or reclaim of the code pointed to by struct
+ * rseq_cs start_ip and post_commit_offset fields.
+ */
+static inline void rseq_prepare_unload(void)
+{
+	rseq_clear_rseq_cs();
+}
+
+#endif  /* RSEQ_H_ */
diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh
new file mode 100755
index 000000000..f51bc83c9
--- /dev/null
+++ b/tools/testing/selftests/rseq/run_param_test.sh
@@ -0,0 +1,126 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+ or MIT
+
+NR_CPUS=`grep '^processor' /proc/cpuinfo | wc -l`
+
+EXTRA_ARGS=${@}
+
+OLDIFS="$IFS"
+IFS=$'\n'
+TEST_LIST=(
+	"-T s"
+	"-T l"
+	"-T b"
+	"-T b -M"
+	"-T m"
+	"-T m -M"
+	"-T i"
+	"-T r"
+)
+
+TEST_NAME=(
+	"spinlock"
+	"list"
+	"buffer"
+	"buffer with barrier"
+	"memcpy"
+	"memcpy with barrier"
+	"increment"
+	"membarrier"
+)
+IFS="$OLDIFS"
+
+REPS=1000
+SLOW_REPS=100
+NR_THREADS=$((6*${NR_CPUS}))
+
+function do_tests()
+{
+	local i=0
+	while [ "$i" -lt "${#TEST_LIST[@]}" ]; do
+		echo "Running test ${TEST_NAME[$i]}"
+		./param_test ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+		echo "Running compare-twice test ${TEST_NAME[$i]}"
+		./param_test_compare_twice ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+		let "i++"
+	done
+}
+
+echo "Default parameters"
+do_tests
+
+echo "Loop injection: 10000 loops"
+
+OLDIFS="$IFS"
+IFS=$'\n'
+INJECT_LIST=(
+	"1"
+	"2"
+	"3"
+	"4"
+	"5"
+	"6"
+	"7"
+	"8"
+	"9"
+)
+IFS="$OLDIFS"
+
+NR_LOOPS=10000
+
+i=0
+while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do
+	echo "Injecting at <${INJECT_LIST[$i]}>"
+	do_tests -${INJECT_LIST[i]} ${NR_LOOPS}
+	let "i++"
+done
+NR_LOOPS=
+
+function inject_blocking()
+{
+	OLDIFS="$IFS"
+	IFS=$'\n'
+	INJECT_LIST=(
+		"7"
+		"8"
+		"9"
+	)
+	IFS="$OLDIFS"
+
+	NR_LOOPS=-1
+
+	i=0
+	while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do
+		echo "Injecting at <${INJECT_LIST[$i]}>"
+		do_tests -${INJECT_LIST[i]} -1 ${@}
+		let "i++"
+	done
+	NR_LOOPS=
+}
+
+echo "Yield injection (25%)"
+inject_blocking -m 4 -y
+
+echo "Yield injection (50%)"
+inject_blocking -m 2 -y
+
+echo "Yield injection (100%)"
+inject_blocking -m 1 -y
+
+echo "Kill injection (25%)"
+inject_blocking -m 4 -k
+
+echo "Kill injection (50%)"
+inject_blocking -m 2 -k
+
+echo "Kill injection (100%)"
+inject_blocking -m 1 -k
+
+echo "Sleep injection (1ms, 25%)"
+inject_blocking -m 4 -s 1
+
+echo "Sleep injection (1ms, 50%)"
+inject_blocking -m 2 -s 1
+
+echo "Sleep injection (1ms, 100%)"
+inject_blocking -m 1 -s 1
diff --git a/tools/testing/selftests/rseq/settings b/tools/testing/selftests/rseq/settings
new file mode 100644
index 000000000..e7b941753
--- /dev/null
+++ b/tools/testing/selftests/rseq/settings
@@ -0,0 +1 @@
+timeout=0