Merge tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Improve the scalability of the CFS bandwidth unthrottling logic with
   large number of CPUs.

 - Fix & rework various cpuidle routines, simplify interaction with the
   generic scheduler code. Add __cpuidle methods as noinstr to objtool's
   noinstr detection and fix boatloads of cpuidle bugs & quirks.

 - Add new ABI: introduce MEMBARRIER_CMD_GET_REGISTRATIONS, to query
   previously issued registrations.

 - Limit scheduler slice duration to the sysctl_sched_latency period, to
   improve scheduling granularity with a large number of SCHED_IDLE
   tasks.

 - Debuggability enhancement on sys_exit(): warn about disabled IRQs,
   but also enable them to prevent a cascade of followup problems and
   repeat warnings.

 - Fix the rescheduling logic in prio_changed_dl().

 - Micro-optimize cpufreq and sched-util methods.

 - Micro-optimize ttwu_runnable()

 - Micro-optimize the idle-scanning in update_numa_stats(),
   select_idle_capacity() and steal_cookie_task().

 - Update the RSEQ code & self-tests

 - Constify various scheduler methods

 - Remove unused methods

 - Refine __init tags

 - Documentation updates

 - Misc other cleanups, fixes

* tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (110 commits)
  sched/rt: pick_next_rt_entity(): check list_entry
  sched/deadline: Add more reschedule cases to prio_changed_dl()
  sched/fair: sanitize vruntime of entity being placed
  sched/fair: Remove capacity inversion detection
  sched/fair: unlink misfit task from cpu overutilized
  objtool: mem*() are not uaccess safe
  cpuidle: Fix poll_idle() noinstr annotation
  sched/clock: Make local_clock() noinstr
  sched/clock/x86: Mark sched_clock() noinstr
  x86/pvclock: Improve atomic update of last_value in pvclock_clocksource_read()
  x86/atomics: Always inline arch_atomic64*()
  cpuidle: tracing, preempt: Squash _rcuidle tracing
  cpuidle: tracing: Warn about !rcu_is_watching()
  cpuidle: lib/bug: Disable rcu_is_watching() during WARN/BUG
  cpuidle: drivers: firmware: psci: Dont instrument suspend code
  KVM: selftests: Fix build of rseq test
  exit: Detect and fix irq disabled state in oops
  cpuidle, arm64: Fix the ARM64 cpuidle logic
  cpuidle: mvebu: Fix duplicate flags assignment
  sched/fair: Limit sched slice duration
  ...

31 files changed, 4470 insertions, 4665 deletions

diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
index 3045fdf9bdf5..f74e76d03b7e 100644
--- a/tools/testing/selftests/kvm/rseq_test.c
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -41,18 +41,6 @@ static void guest_code(void)
 		GUEST_SYNC(0);
 }
 
-/*
- * We have to perform direct system call for getcpu() because it's
- * not available until glic 2.29.
- */
-static void sys_getcpu(unsigned *cpu)
-{
-	int r;
-
-	r = syscall(__NR_getcpu, cpu, NULL, NULL);
-	TEST_ASSERT(!r, "getcpu failed, errno = %d (%s)", errno, strerror(errno));
-}
-
 static int next_cpu(int cpu)
 {
 	/*
@@ -249,7 +237,9 @@ int main(int argc, char *argv[])
 			 * across the seq_cnt reads.
 			 */
 			smp_rmb();
-			sys_getcpu(&cpu);
+			r = sys_getcpu(&cpu, NULL);
+			TEST_ASSERT(!r, "getcpu failed, errno = %d (%s)",
+				    errno, strerror(errno));
 			rseq_cpu = rseq_current_cpu_raw();
 			smp_rmb();
 		} while (snapshot != atomic_read(&seq_cnt));
diff --git a/tools/testing/selftests/membarrier/membarrier_test_impl.h b/tools/testing/selftests/membarrier/membarrier_test_impl.h
index 186be69f0a59..af89855adb7b 100644
--- a/tools/testing/selftests/membarrier/membarrier_test_impl.h
+++ b/tools/testing/selftests/membarrier/membarrier_test_impl.h
@@ -9,11 +9,38 @@
 
 #include "../kselftest.h"
 
+static int registrations;
+
 static int sys_membarrier(int cmd, int flags)
 {
 	return syscall(__NR_membarrier, cmd, flags);
 }
 
+static int test_membarrier_get_registrations(int cmd)
+{
+	int ret, flags = 0;
+	const char *test_name =
+		"sys membarrier MEMBARRIER_CMD_GET_REGISTRATIONS";
+
+	registrations |= cmd;
+
+	ret = sys_membarrier(MEMBARRIER_CMD_GET_REGISTRATIONS, 0);
+	if (ret < 0) {
+		ksft_exit_fail_msg(
+			"%s test: flags = %d, errno = %d\n",
+			test_name, flags, errno);
+	} else if (ret != registrations) {
+		ksft_exit_fail_msg(
+			"%s test: flags = %d, ret = %d, registrations = %d\n",
+			test_name, flags, ret, registrations);
+	}
+	ksft_test_result_pass(
+		"%s test: flags = %d, ret = %d, registrations = %d\n",
+		test_name, flags, ret, registrations);
+
+	return 0;
+}
+
 static int test_membarrier_cmd_fail(void)
 {
 	int cmd = -1, flags = 0;
@@ -113,6 +140,8 @@ static int test_membarrier_register_private_expedited_success(void)
 	ksft_test_result_pass(
 		"%s test: flags = %d\n",
 		test_name, flags);
+
+	test_membarrier_get_registrations(cmd);
 	return 0;
 }
 
@@ -170,6 +199,8 @@ static int test_membarrier_register_private_expedited_sync_core_success(void)
 	ksft_test_result_pass(
 		"%s test: flags = %d\n",
 		test_name, flags);
+
+	test_membarrier_get_registrations(cmd);
 	return 0;
 }
 
@@ -204,6 +235,8 @@ static int test_membarrier_register_global_expedited_success(void)
 	ksft_test_result_pass(
 		"%s test: flags = %d\n",
 		test_name, flags);
+
+	test_membarrier_get_registrations(cmd);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/membarrier/membarrier_test_multi_thread.c b/tools/testing/selftests/membarrier/membarrier_test_multi_thread.c
index ac5613e5b0eb..a9cc17facfb3 100644
--- a/tools/testing/selftests/membarrier/membarrier_test_multi_thread.c
+++ b/tools/testing/selftests/membarrier/membarrier_test_multi_thread.c
@@ -62,7 +62,7 @@ static int test_mt_membarrier(void)
 int main(int argc, char **argv)
 {
 	ksft_print_header();
-	ksft_set_plan(13);
+	ksft_set_plan(16);
 
 	test_membarrier_query();
 
diff --git a/tools/testing/selftests/membarrier/membarrier_test_single_thread.c b/tools/testing/selftests/membarrier/membarrier_test_single_thread.c
index c1c963902854..4cdc8b1d124c 100644
--- a/tools/testing/selftests/membarrier/membarrier_test_single_thread.c
+++ b/tools/testing/selftests/membarrier/membarrier_test_single_thread.c
@@ -12,7 +12,9 @@
 int main(int argc, char **argv)
 {
 	ksft_print_header();
-	ksft_set_plan(13);
+	ksft_set_plan(18);
+
+	test_membarrier_get_registrations(/*cmd=*/0);
 
 	test_membarrier_query();
 
@@ -20,5 +22,7 @@ int main(int argc, char **argv)
 
 	test_membarrier_success();
 
+	test_membarrier_get_registrations(/*cmd=*/0);
+
 	return ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore
index 5910888ebfe1..16496de5f6ce 100644
--- a/tools/testing/selftests/rseq/.gitignore
+++ b/tools/testing/selftests/rseq/.gitignore
@@ -1,7 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0-only
 basic_percpu_ops_test
+basic_percpu_ops_mm_cid_test
 basic_test
 basic_rseq_op_test
 param_test
 param_test_benchmark
 param_test_compare_twice
+param_test_mm_cid
+param_test_mm_cid_benchmark
+param_test_mm_cid_compare_twice
diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index 215e1067f037..82a52810a649 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -12,8 +12,9 @@ LDLIBS += -lpthread -ldl
 # 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 = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \
+		param_test_benchmark param_test_compare_twice param_test_mm_cid \
+		param_test_mm_cid_benchmark param_test_mm_cid_compare_twice
 
 TEST_GEN_PROGS_EXTENDED = librseq.so
 
@@ -29,6 +30,9 @@ $(OUTPUT)/librseq.so: rseq.c rseq.h rseq-*.h
 $(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h
 	$(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@
 
+$(OUTPUT)/basic_percpu_ops_mm_cid_test: basic_percpu_ops_test.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h
+	$(CC) $(CFLAGS) -DBUILDOPT_RSEQ_PERCPU_MM_CID_ID $< $(LDLIBS) -lrseq -o $@
+
 $(OUTPUT)/param_test_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
 					rseq.h rseq-*.h
 	$(CC) $(CFLAGS) -DBENCHMARK $< $(LDLIBS) -lrseq -o $@
@@ -36,3 +40,15 @@ $(OUTPUT)/param_test_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
 $(OUTPUT)/param_test_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
 					rseq.h rseq-*.h
 	$(CC) $(CFLAGS) -DRSEQ_COMPARE_TWICE $< $(LDLIBS) -lrseq -o $@
+
+$(OUTPUT)/param_test_mm_cid: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					rseq.h rseq-*.h
+	$(CC) $(CFLAGS) -DBUILDOPT_RSEQ_PERCPU_MM_CID $< $(LDLIBS) -lrseq -o $@
+
+$(OUTPUT)/param_test_mm_cid_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					rseq.h rseq-*.h
+	$(CC) $(CFLAGS) -DBUILDOPT_RSEQ_PERCPU_MM_CID -DBENCHMARK $< $(LDLIBS) -lrseq -o $@
+
+$(OUTPUT)/param_test_mm_cid_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					rseq.h rseq-*.h
+	$(CC) $(CFLAGS) -DBUILDOPT_RSEQ_PERCPU_MM_CID -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
index 517756afc2a4..887542961968 100644
--- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c
+++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
@@ -12,6 +12,32 @@
 #include "../kselftest.h"
 #include "rseq.h"
 
+#ifdef BUILDOPT_RSEQ_PERCPU_MM_CID
+# define RSEQ_PERCPU	RSEQ_PERCPU_MM_CID
+static
+int get_current_cpu_id(void)
+{
+	return rseq_current_mm_cid();
+}
+static
+bool rseq_validate_cpu_id(void)
+{
+	return rseq_mm_cid_available();
+}
+#else
+# define RSEQ_PERCPU	RSEQ_PERCPU_CPU_ID
+static
+int get_current_cpu_id(void)
+{
+	return rseq_cpu_start();
+}
+static
+bool rseq_validate_cpu_id(void)
+{
+	return rseq_current_cpu_raw() >= 0;
+}
+#endif
+
 struct percpu_lock_entry {
 	intptr_t v;
 } __attribute__((aligned(128)));
@@ -51,9 +77,9 @@ int rseq_this_cpu_lock(struct percpu_lock *lock)
 	for (;;) {
 		int ret;
 
-		cpu = rseq_cpu_start();
-		ret = rseq_cmpeqv_storev(&lock->c[cpu].v,
-					 0, 1, cpu);
+		cpu = get_current_cpu_id();
+		ret = rseq_cmpeqv_storev(RSEQ_MO_RELAXED, RSEQ_PERCPU,
+					 &lock->c[cpu].v, 0, 1, cpu);
 		if (rseq_likely(!ret))
 			break;
 		/* Retry if comparison fails or rseq aborts. */
@@ -141,13 +167,14 @@ void this_cpu_list_push(struct percpu_list *list,
 		intptr_t *targetptr, newval, expect;
 		int ret;
 
-		cpu = rseq_cpu_start();
+		cpu = get_current_cpu_id();
 		/* 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);
+		ret = rseq_cmpeqv_storev(RSEQ_MO_RELAXED, RSEQ_PERCPU,
+					 targetptr, expect, newval, cpu);
 		if (rseq_likely(!ret))
 			break;
 		/* Retry if comparison fails or rseq aborts. */
@@ -170,12 +197,13 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
 		long offset;
 		int ret, cpu;
 
-		cpu = rseq_cpu_start();
+		cpu = get_current_cpu_id();
 		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,
+		ret = rseq_cmpnev_storeoffp_load(RSEQ_MO_RELAXED, RSEQ_PERCPU,
+						 targetptr, expectnot,
 						 offset, load, cpu);
 		if (rseq_likely(!ret)) {
 			if (_cpu)
@@ -295,6 +323,10 @@ int main(int argc, char **argv)
 			errno, strerror(errno));
 		goto error;
 	}
+	if (!rseq_validate_cpu_id()) {
+		fprintf(stderr, "Error: cpu id getter unavailable\n");
+		goto error;
+	}
 	printf("spinlock\n");
 	test_percpu_spinlock();
 	printf("percpu_list\n");
diff --git a/tools/testing/selftests/rseq/basic_test.c b/tools/testing/selftests/rseq/basic_test.c
index d8efbfb89193..295eea16466f 100644
--- a/tools/testing/selftests/rseq/basic_test.c
+++ b/tools/testing/selftests/rseq/basic_test.c
@@ -22,6 +22,8 @@ void test_cpu_pointer(void)
 	CPU_ZERO(&test_affinity);
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		if (CPU_ISSET(i, &affinity)) {
+			int node;
+
 			CPU_SET(i, &test_affinity);
 			sched_setaffinity(0, sizeof(test_affinity),
 					&test_affinity);
@@ -29,6 +31,8 @@ void test_cpu_pointer(void)
 			assert(rseq_current_cpu() == i);
 			assert(rseq_current_cpu_raw() == i);
 			assert(rseq_cpu_start() == i);
+			node = rseq_fallback_current_node();
+			assert(rseq_current_node_id() == node);
 			CPU_CLR(i, &test_affinity);
 		}
 	}
diff --git a/tools/testing/selftests/rseq/compiler.h b/tools/testing/selftests/rseq/compiler.h
index 876eb6a7f75b..f47092bddeba 100644
--- a/tools/testing/selftests/rseq/compiler.h
+++ b/tools/testing/selftests/rseq/compiler.h
@@ -27,4 +27,10 @@
  */
 #define rseq_after_asm_goto()	asm volatile ("" : : : "memory")
 
+/* Combine two tokens. */
+#define RSEQ__COMBINE_TOKENS(_tokena, _tokenb)	\
+	_tokena##_tokenb
+#define RSEQ_COMBINE_TOKENS(_tokena, _tokenb)	\
+	RSEQ__COMBINE_TOKENS(_tokena, _tokenb)
+
 #endif  /* RSEQ_COMPILER_H_ */
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index ef29bc16f358..bf951a490bb4 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -16,6 +16,7 @@
 #include <signal.h>
 #include <errno.h>
 #include <stddef.h>
+#include <stdbool.h>
 
 static inline pid_t rseq_gettid(void)
 {
@@ -36,13 +37,9 @@ 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;
+		opt_disable_mod = 0, opt_test = 's';
 
-#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;
@@ -268,6 +265,63 @@ unsigned int yield_mod_cnt, nr_abort;
 
 #include "rseq.h"
 
+static enum rseq_mo opt_mo = RSEQ_MO_RELAXED;
+
+#ifdef RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+#define TEST_MEMBARRIER
+
+static int sys_membarrier(int cmd, int flags, int cpu_id)
+{
+	return syscall(__NR_membarrier, cmd, flags, cpu_id);
+}
+#endif
+
+#ifdef BUILDOPT_RSEQ_PERCPU_MM_CID
+# define RSEQ_PERCPU	RSEQ_PERCPU_MM_CID
+static
+int get_current_cpu_id(void)
+{
+	return rseq_current_mm_cid();
+}
+static
+bool rseq_validate_cpu_id(void)
+{
+	return rseq_mm_cid_available();
+}
+# ifdef TEST_MEMBARRIER
+/*
+ * Membarrier does not currently support targeting a mm_cid, so
+ * issue the barrier on all cpus.
+ */
+static
+int rseq_membarrier_expedited(int cpu)
+{
+	return sys_membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ,
+			      0, 0);
+}
+# endif /* TEST_MEMBARRIER */
+#else
+# define RSEQ_PERCPU	RSEQ_PERCPU_CPU_ID
+static
+int get_current_cpu_id(void)
+{
+	return rseq_cpu_start();
+}
+static
+bool rseq_validate_cpu_id(void)
+{
+	return rseq_current_cpu_raw() >= 0;
+}
+# ifdef TEST_MEMBARRIER
+static
+int rseq_membarrier_expedited(int cpu)
+{
+	return sys_membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ,
+			      MEMBARRIER_CMD_FLAG_CPU, cpu);
+}
+# endif /* TEST_MEMBARRIER */
+#endif
+
 struct percpu_lock_entry {
 	intptr_t v;
 } __attribute__((aligned(128)));
@@ -355,8 +409,14 @@ static int rseq_this_cpu_lock(struct percpu_lock *lock)
 	for (;;) {
 		int ret;
 
-		cpu = rseq_cpu_start();
-		ret = rseq_cmpeqv_storev(&lock->c[cpu].v,
+		cpu = get_current_cpu_id();
+		if (cpu < 0) {
+			fprintf(stderr, "pid: %d: tid: %d, cpu: %d: cid: %d\n",
+					getpid(), (int) rseq_gettid(), rseq_current_cpu_raw(), cpu);
+			abort();
+		}
+		ret = rseq_cmpeqv_storev(RSEQ_MO_RELAXED, RSEQ_PERCPU,
+					 &lock->c[cpu].v,
 					 0, 1, cpu);
 		if (rseq_likely(!ret))
 			break;
@@ -473,8 +533,9 @@ void *test_percpu_inc_thread(void *arg)
 		do {
 			int cpu;
 
-			cpu = rseq_cpu_start();
-			ret = rseq_addv(&data->c[cpu].count, 1, cpu);
+			cpu = get_current_cpu_id();
+			ret = rseq_addv(RSEQ_MO_RELAXED, RSEQ_PERCPU,
+					&data->c[cpu].count, 1, cpu);
 		} while (rseq_unlikely(ret));
 #ifndef BENCHMARK
 		if (i != 0 && !(i % (reps / 10)))
@@ -543,13 +604,14 @@ void this_cpu_list_push(struct percpu_list *list,
 		intptr_t *targetptr, newval, expect;
 		int ret;
 
-		cpu = rseq_cpu_start();
+		cpu = get_current_cpu_id();
 		/* 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);
+		ret = rseq_cmpeqv_storev(RSEQ_MO_RELAXED, RSEQ_PERCPU,
+					 targetptr, expect, newval, cpu);
 		if (rseq_likely(!ret))
 			break;
 		/* Retry if comparison fails or rseq aborts. */
@@ -575,13 +637,14 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
 		long offset;
 		int ret;
 
-		cpu = rseq_cpu_start();
+		cpu = get_current_cpu_id();
 		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);
+		ret = rseq_cmpnev_storeoffp_load(RSEQ_MO_RELAXED, RSEQ_PERCPU,
+						 targetptr, expectnot,
+						 offset, load, cpu);
 		if (rseq_likely(!ret)) {
 			node = head;
 			break;
@@ -719,7 +782,7 @@ bool this_cpu_buffer_push(struct percpu_buffer *buffer,
 		intptr_t offset;
 		int ret;
 
-		cpu = rseq_cpu_start();
+		cpu = get_current_cpu_id();
 		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
 		if (offset == buffer->c[cpu].buflen)
 			break;
@@ -727,14 +790,9 @@ bool this_cpu_buffer_push(struct percpu_buffer *buffer,
 		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);
+		ret = rseq_cmpeqv_trystorev_storev(opt_mo, RSEQ_PERCPU,
+			targetptr_final, offset, targetptr_spec,
+			newval_spec, newval_final, cpu);
 		if (rseq_likely(!ret)) {
 			result = true;
 			break;
@@ -757,7 +815,7 @@ struct percpu_buffer_node *this_cpu_buffer_pop(struct percpu_buffer *buffer,
 		intptr_t offset;
 		int ret;
 
-		cpu = rseq_cpu_start();
+		cpu = get_current_cpu_id();
 		/* Load offset with single-copy atomicity. */
 		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
 		if (offset == 0) {
@@ -767,7 +825,8 @@ struct percpu_buffer_node *this_cpu_buffer_pop(struct percpu_buffer *buffer,
 		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,
+		ret = rseq_cmpeqv_cmpeqv_storev(RSEQ_MO_RELAXED, RSEQ_PERCPU,
+			targetptr, offset,
 			(intptr_t *)&buffer->c[cpu].array[offset - 1],
 			(intptr_t)head, newval, cpu);
 		if (rseq_likely(!ret))
@@ -924,7 +983,7 @@ bool this_cpu_memcpy_buffer_push(struct percpu_memcpy_buffer *buffer,
 		size_t copylen;
 		int ret;
 
-		cpu = rseq_cpu_start();
+		cpu = get_current_cpu_id();
 		/* Load offset with single-copy atomicity. */
 		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
 		if (offset == buffer->c[cpu].buflen)
@@ -935,15 +994,11 @@ bool this_cpu_memcpy_buffer_push(struct percpu_memcpy_buffer *buffer,
 		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);
+		ret = rseq_cmpeqv_trymemcpy_storev(
+			opt_mo, RSEQ_PERCPU,
+			targetptr_final, offset,
+			destptr, srcptr, copylen,
+			newval_final, cpu);
 		if (rseq_likely(!ret)) {
 			result = true;
 			break;
@@ -968,7 +1023,7 @@ bool this_cpu_memcpy_buffer_pop(struct percpu_memcpy_buffer *buffer,
 		size_t copylen;
 		int ret;
 
-		cpu = rseq_cpu_start();
+		cpu = get_current_cpu_id();
 		/* Load offset with single-copy atomicity. */
 		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
 		if (offset == 0)
@@ -979,8 +1034,8 @@ bool this_cpu_memcpy_buffer_pop(struct percpu_memcpy_buffer *buffer,
 		copylen = sizeof(*item);
 		newval_final = offset - 1;
 		targetptr_final = &buffer->c[cpu].offset;
-		ret = rseq_cmpeqv_trymemcpy_storev(targetptr_final,
-			offset, destptr, srcptr, copylen,
+		ret = rseq_cmpeqv_trymemcpy_storev(RSEQ_MO_RELAXED, RSEQ_PERCPU,
+			targetptr_final, offset, destptr, srcptr, copylen,
 			newval_final, cpu);
 		if (rseq_likely(!ret)) {
 			result = true;
@@ -1155,7 +1210,7 @@ static int set_signal_handler(void)
 }
 
 /* Test MEMBARRIER_CMD_PRIVATE_RESTART_RSEQ_ON_CPU membarrier command. */
-#ifdef RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+#ifdef TEST_MEMBARRIER
 struct test_membarrier_thread_args {
 	int stop;
 	intptr_t percpu_list_ptr;
@@ -1182,9 +1237,10 @@ void *test_membarrier_worker_thread(void *arg)
 		int ret;
 
 		do {
-			int cpu = rseq_cpu_start();
+			int cpu = get_current_cpu_id();
 
-			ret = rseq_offset_deref_addv(&args->percpu_list_ptr,
+			ret = rseq_offset_deref_addv(RSEQ_MO_RELAXED, RSEQ_PERCPU,
+				&args->percpu_list_ptr,
 				sizeof(struct percpu_list_entry) * cpu, 1, cpu);
 		} while (rseq_unlikely(ret));
 	}
@@ -1221,11 +1277,6 @@ void test_membarrier_free_percpu_list(struct percpu_list *list)
 		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.
@@ -1264,8 +1315,7 @@ void *test_membarrier_manager_thread(void *arg)
 
 		/* 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) &&
+		if (rseq_membarrier_expedited(cpu_a) &&
 				errno != ENXIO /* missing CPU */) {
 			perror("sys_membarrier");
 			abort();
@@ -1288,8 +1338,7 @@ void *test_membarrier_manager_thread(void *arg)
 
 		/* 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) &&
+		if (rseq_membarrier_expedited(cpu_b) &&
 				errno != ENXIO /* missing CPU*/) {
 			perror("sys_membarrier");
 			abort();
@@ -1360,7 +1409,7 @@ void test_membarrier(void)
 		abort();
 	}
 }
-#else /* RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV */
+#else /* TEST_MEMBARRIER */
 void test_membarrier(void)
 {
 	fprintf(stderr, "rseq_offset_deref_addv is not implemented on this architecture. "
@@ -1517,7 +1566,7 @@ int main(int argc, char **argv)
 			verbose = 1;
 			break;
 		case 'M':
-			opt_mb = 1;
+			opt_mo = RSEQ_MO_RELEASE;
 			break;
 		default:
 			show_usage(argc, argv);
@@ -1537,6 +1586,10 @@ int main(int argc, char **argv)
 
 	if (!opt_disable_rseq && rseq_register_current_thread())
 		goto error;
+	if (!opt_disable_rseq && !rseq_validate_cpu_id()) {
+		fprintf(stderr, "Error: cpu id getter unavailable\n");
+		goto error;
+	}
 	switch (opt_test) {
 	case 's':
 		printf_verbose("spinlock\n");
diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h
index a8c44d9af71f..fb4ec8a75dd4 100644
--- a/tools/testing/selftests/rseq/rseq-abi.h
+++ b/tools/testing/selftests/rseq/rseq-abi.h
@@ -146,6 +146,28 @@ struct rseq_abi {
 	 *     this thread.
 	 */
 	__u32 flags;
+
+	/*
+	 * Restartable sequences node_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. Contains the current NUMA node ID.
+	 */
+	__u32 node_id;
+
+	/*
+	 * Restartable sequences mm_cid 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. Contains the current thread's concurrency ID
+	 * (allocated uniquely within a memory map).
+	 */
+	__u32 mm_cid;
+
+	/*
+	 * Flexible array member at end of structure, after last feature field.
+	 */
+	char end[];
 } __attribute__((aligned(4 * sizeof(__u64))));
 
 #endif /* _RSEQ_ABI_H */
diff --git a/tools/testing/selftests/rseq/rseq-arm-bits.h b/tools/testing/selftests/rseq/rseq-arm-bits.h
new file mode 100644
index 000000000000..4f03cb395462
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-arm-bits.h
@@ -0,0 +1,505 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-arm-bits.h
+ *
+ * (C) Copyright 2016-2022 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#include "rseq-bits-template.h"
+
+#if defined(RSEQ_TEMPLATE_MO_RELAXED) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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
+}
+
+#endif /* #if defined(RSEQ_TEMPLATE_MO_RELAXED) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+		"dmb\n\t"	/* full mb provides store-release */
+#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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+		"dmb\n\t"	/* full mb provides store-release */
+#endif
+		/* 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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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 /* #if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#include "rseq-bits-reset.h"
diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h
index 893a11eca9d5..8414fc3eac15 100644
--- a/tools/testing/selftests/rseq/rseq-arm.h
+++ b/tools/testing/selftests/rseq/rseq-arm.h
@@ -2,7 +2,7 @@
 /*
  * rseq-arm.h
  *
- * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ * (C) Copyright 2016-2022 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
  */
 
 /*
@@ -79,10 +79,6 @@ do {									\
 	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"			\
@@ -147,681 +143,34 @@ do {									\
 		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)
+/* Per-cpu-id indexing. */
 
-	__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
-}
+#define RSEQ_TEMPLATE_CPU_ID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-arm-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
 
-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)
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-arm-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_CPU_ID
 
-	__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
-}
+/* Per-mm-cid indexing. */
 
-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];
+#define RSEQ_TEMPLATE_MM_CID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-arm-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
 
-	RSEQ_INJECT_C(9)
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-arm-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_MM_CID
 
-	__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
-}
+/* APIs which are not based on cpu ids. */
 
-#endif /* !RSEQ_SKIP_FASTPATH */
+#define RSEQ_TEMPLATE_CPU_ID_NONE
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-arm-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
+#undef RSEQ_TEMPLATE_CPU_ID_NONE
diff --git a/tools/testing/selftests/rseq/rseq-arm64-bits.h b/tools/testing/selftests/rseq/rseq-arm64-bits.h
new file mode 100644
index 000000000000..cc7226b1efe1
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-arm64-bits.h
@@ -0,0 +1,392 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-arm64-bits.h
+ *
+ * (C) Copyright 2016-2022 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ * (C) Copyright 2018 - Will Deacon <will.deacon@arm.com>
+ */
+
+#include "rseq-bits-template.h"
+
+#if defined(RSEQ_TEMPLATE_MO_RELAXED) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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
+}
+
+#endif /* #if defined(RSEQ_TEMPLATE_MO_RELAXED) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+		RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+#else
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+#endif
+		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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+		RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+#else
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+#endif
+		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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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 /* #if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#include "rseq-bits-reset.h"
diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h
index cbe190a4d005..85b90977e7e6 100644
--- a/tools/testing/selftests/rseq/rseq-arm64.h
+++ b/tools/testing/selftests/rseq/rseq-arm64.h
@@ -2,7 +2,7 @@
 /*
  * rseq-arm64.h
  *
- * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ * (C) Copyright 2016-2022 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
  * (C) Copyright 2018 - Will Deacon <will.deacon@arm.com>
  */
 
@@ -85,10 +85,6 @@ do {										\
 	}									\
 } 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"
@@ -204,492 +200,34 @@ do {										\
 	"	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
-}
+/* Per-cpu-id indexing. */
 
-static inline __attribute__((always_inline))
-int rseq_addv(intptr_t *v, intptr_t count, int cpu)
-{
-	RSEQ_INJECT_C(9)
+#define RSEQ_TEMPLATE_CPU_ID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-arm64-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
 
-	__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
-}
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-arm64-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_CPU_ID
+
+/* Per-mm-cid indexing. */
+
+#define RSEQ_TEMPLATE_MM_CID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-arm64-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
+
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-arm64-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_MM_CID
+
+/* APIs which are not based on cpu ids. */
 
-#endif /* !RSEQ_SKIP_FASTPATH */
+#define RSEQ_TEMPLATE_CPU_ID_NONE
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-arm64-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
+#undef RSEQ_TEMPLATE_CPU_ID_NONE
diff --git a/tools/testing/selftests/rseq/rseq-bits-reset.h b/tools/testing/selftests/rseq/rseq-bits-reset.h
new file mode 100644
index 000000000000..e8655089f9cb
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-bits-reset.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-bits-reset.h
+ *
+ * (C) Copyright 2016-2022 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#undef RSEQ_TEMPLATE_IDENTIFIER
+#undef RSEQ_TEMPLATE_CPU_ID_FIELD
+#undef RSEQ_TEMPLATE_CPU_ID_OFFSET
+#undef RSEQ_TEMPLATE_SUFFIX
diff --git a/tools/testing/selftests/rseq/rseq-bits-template.h b/tools/testing/selftests/rseq/rseq-bits-template.h
new file mode 100644
index 000000000000..65698d6a6cf9
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-bits-template.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-bits-template.h
+ *
+ * (C) Copyright 2016-2022 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifdef RSEQ_TEMPLATE_CPU_ID
+# define RSEQ_TEMPLATE_CPU_ID_OFFSET	RSEQ_CPU_ID_OFFSET
+# define RSEQ_TEMPLATE_CPU_ID_FIELD	cpu_id
+# ifdef RSEQ_TEMPLATE_MO_RELEASE
+#  define RSEQ_TEMPLATE_SUFFIX		_release_cpu_id
+# elif defined (RSEQ_TEMPLATE_MO_RELAXED)
+#  define RSEQ_TEMPLATE_SUFFIX		_relaxed_cpu_id
+# else
+#  error "Never use <rseq-bits-template.h> directly; include <rseq.h> instead."
+# endif
+#elif defined(RSEQ_TEMPLATE_MM_CID)
+# define RSEQ_TEMPLATE_CPU_ID_OFFSET	RSEQ_MM_CID_OFFSET
+# define RSEQ_TEMPLATE_CPU_ID_FIELD	mm_cid
+# ifdef RSEQ_TEMPLATE_MO_RELEASE
+#  define RSEQ_TEMPLATE_SUFFIX		_release_mm_cid
+# elif defined (RSEQ_TEMPLATE_MO_RELAXED)
+#  define RSEQ_TEMPLATE_SUFFIX		_relaxed_mm_cid
+# else
+#  error "Never use <rseq-bits-template.h> directly; include <rseq.h> instead."
+# endif
+#elif defined (RSEQ_TEMPLATE_CPU_ID_NONE)
+# ifdef RSEQ_TEMPLATE_MO_RELEASE
+#  define RSEQ_TEMPLATE_SUFFIX		_release
+# elif defined (RSEQ_TEMPLATE_MO_RELAXED)
+#  define RSEQ_TEMPLATE_SUFFIX		_relaxed
+# else
+#  error "Never use <rseq-bits-template.h> directly; include <rseq.h> instead."
+# endif
+#else
+# error "Never use <rseq-bits-template.h> directly; include <rseq.h> instead."
+#endif
+
+#define RSEQ_TEMPLATE_IDENTIFIER(x)	RSEQ_COMBINE_TOKENS(x, RSEQ_TEMPLATE_SUFFIX)
+
diff --git a/tools/testing/selftests/rseq/rseq-mips-bits.h b/tools/testing/selftests/rseq/rseq-mips-bits.h
new file mode 100644
index 000000000000..6c48af4d0944
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-mips-bits.h
@@ -0,0 +1,462 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Author: Paul Burton <paul.burton@mips.com>
+ * (C) Copyright 2018 MIPS Tech LLC
+ * (C) Copyright 2016-2022 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#include "rseq-bits-template.h"
+
+#if defined(RSEQ_TEMPLATE_MO_RELAXED) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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
+}
+
+#endif /* #if defined(RSEQ_TEMPLATE_MO_RELAXED) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+		"sync\n\t"	/* full sync provides store-release */
+#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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+		"sync\n\t"	/* full sync provides store-release */
+#endif
+		/* 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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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 /* #if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#include "rseq-bits-reset.h"
diff --git a/tools/testing/selftests/rseq/rseq-mips.h b/tools/testing/selftests/rseq/rseq-mips.h
index 878739fae2fd..50b950cf9585 100644
--- a/tools/testing/selftests/rseq/rseq-mips.h
+++ b/tools/testing/selftests/rseq/rseq-mips.h
@@ -2,9 +2,7 @@
 /*
  * 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>
+ * (C) Copyright 2016-2022 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
  */
 
 /*
@@ -60,10 +58,6 @@ do {									\
 	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"
@@ -154,624 +148,34 @@ do {									\
 		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
-}
+/* Per-cpu-id indexing. */
 
-static inline __attribute__((always_inline))
-int rseq_addv(intptr_t *v, intptr_t count, int cpu)
-{
-	RSEQ_INJECT_C(9)
+#define RSEQ_TEMPLATE_CPU_ID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-mips-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
 
-	__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
-}
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-mips-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_CPU_ID
 
-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)
+/* Per-mm-cid indexing. */
 
-	__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
-}
+#define RSEQ_TEMPLATE_MM_CID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-mips-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
 
-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)
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-mips-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_MM_CID
 
-	__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
-}
+/* APIs which are not based on cpu ids. */
 
-#endif /* !RSEQ_SKIP_FASTPATH */
+#define RSEQ_TEMPLATE_CPU_ID_NONE
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-mips-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
+#undef RSEQ_TEMPLATE_CPU_ID_NONE
diff --git a/tools/testing/selftests/rseq/rseq-ppc-bits.h b/tools/testing/selftests/rseq/rseq-ppc-bits.h
new file mode 100644
index 000000000000..98e69eae1e62
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-ppc-bits.h
@@ -0,0 +1,454 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-ppc-bits.h
+ *
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ * (C) Copyright 2016-2018 - Boqun Feng <boqun.feng@gmail.com>
+ */
+
+#include "rseq-bits-template.h"
+
+#if defined(RSEQ_TEMPLATE_MO_RELAXED) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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
+}
+
+#endif /* #if defined(RSEQ_TEMPLATE_MO_RELAXED) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+		/* for 'release' */
+		"lwsync\n\t"
+#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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+		/* for 'release' */
+		"lwsync\n\t"
+#endif
+		/* 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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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 /* #if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#include "rseq-bits-reset.h"
diff --git a/tools/testing/selftests/rseq/rseq-ppc.h b/tools/testing/selftests/rseq/rseq-ppc.h
index bab8e0b9fb11..dc9190facee9 100644
--- a/tools/testing/selftests/rseq/rseq-ppc.h
+++ b/tools/testing/selftests/rseq/rseq-ppc.h
@@ -2,7 +2,7 @@
 /*
  * rseq-ppc.h
  *
- * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ * (C) Copyright 2016-2022 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
  * (C) Copyright 2016-2018 - Boqun Feng <boqun.feng@gmail.com>
  */
 
@@ -36,10 +36,6 @@ do {									\
 	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.
@@ -209,583 +205,34 @@ do {									\
 		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 */
+/* Per-cpu-id indexing. */
+
+#define RSEQ_TEMPLATE_CPU_ID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-ppc-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
+
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-ppc-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_CPU_ID
+
+/* Per-mm-cid indexing. */
+
+#define RSEQ_TEMPLATE_MM_CID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-ppc-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
+
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-ppc-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_MM_CID
+
+/* APIs which are not based on cpu ids. */
+
+#define RSEQ_TEMPLATE_CPU_ID_NONE
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-ppc-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
+#undef RSEQ_TEMPLATE_CPU_ID_NONE
diff --git a/tools/testing/selftests/rseq/rseq-riscv-bits.h b/tools/testing/selftests/rseq/rseq-riscv-bits.h
new file mode 100644
index 000000000000..de31a0143139
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-riscv-bits.h
@@ -0,0 +1,410 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+
+#include "rseq-bits-template.h"
+
+#if defined(RSEQ_TEMPLATE_MO_RELAXED) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __always_inline
+int RSEQ_TEMPLATE_IDENTIFIER(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]	"m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+				    [v]			"m" (*v),
+				    [expect]		"r" (expect),
+				    [newv]		"r" (newv)
+				    RSEQ_INJECT_INPUT
+				  : "memory", RSEQ_ASM_TMP_REG_1
+				    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 __always_inline
+int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpnev_storeoffp_load)(intptr_t *v, intptr_t expectnot,
+			       off_t 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]	"m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+				    [v]			"m" (*v),
+				    [expectnot]		"r" (expectnot),
+				    [load]		"m" (*load),
+				    [voffp]		"r" (voffp)
+				    RSEQ_INJECT_INPUT
+				  : "memory", RSEQ_ASM_TMP_REG_1
+				    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 __always_inline
+int RSEQ_TEMPLATE_IDENTIFIER(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]	"m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+				    [v]			"m" (*v),
+				    [count]		"r" (count)
+				    RSEQ_INJECT_INPUT
+				  : "memory", RSEQ_ASM_TMP_REG_1
+				    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 __always_inline
+int RSEQ_TEMPLATE_IDENTIFIER(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]	"m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+				    [v]			"m" (*v),
+				    [expect]		"r" (expect),
+				    [v2]			"m" (*v2),
+				    [expect2]		"r" (expect2),
+				    [newv]		"r" (newv)
+				    RSEQ_INJECT_INPUT
+				  : "memory", RSEQ_ASM_TMP_REG_1
+				    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("expected value comparison failed");
+error3:
+	rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+#define RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+
+/*
+ *   pval = *(ptr+off)
+ *  *pval += inc;
+ */
+static inline __always_inline
+int RSEQ_TEMPLATE_IDENTIFIER(rseq_offset_deref_addv)(intptr_t *ptr, off_t off, intptr_t inc, 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_DEREF_ADDV(ptr, off, 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]		"m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+				    [rseq_cs]			"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+				    [ptr]			"r" (ptr),
+				    [off]			"er" (off),
+				    [inc]			"er" (inc)
+				    RSEQ_INJECT_INPUT
+				  : "memory", RSEQ_ASM_TMP_REG_1
+				    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
+}
+
+#endif /* #if defined(RSEQ_TEMPLATE_MO_RELAXED) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __always_inline
+int RSEQ_TEMPLATE_IDENTIFIER(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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+				  RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+#else
+				  RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+#endif
+				  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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+				    [rseq_cs]			"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+				    [expect]			"r" (expect),
+				    [v]				"m" (*v),
+				    [newv]			"r" (newv),
+				    [v2]			"m" (*v2),
+				    [newv2]			"r" (newv2)
+				    RSEQ_INJECT_INPUT
+				  : "memory", RSEQ_ASM_TMP_REG_1
+				    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 __always_inline
+int RSEQ_TEMPLATE_IDENTIFIER(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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+				  RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+#else
+				  RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+#endif
+				  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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+				    [rseq_cs]			"m" (rseq_get_abi()->rseq_cs.arch.ptr),
+				    [expect]			"r" (expect),
+				    [v]				"m" (*v),
+				    [newv]			"r" (newv),
+				    [dst]			"r" (dst),
+				    [src]			"r" (src),
+				    [len]			"r" (len)
+				    RSEQ_INJECT_INPUT
+				  : "memory", RSEQ_ASM_TMP_REG_1, RSEQ_ASM_TMP_REG_2,
+				    RSEQ_ASM_TMP_REG_3, RSEQ_ASM_TMP_REG_4
+				    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 /* #if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#include "rseq-bits-reset.h"
diff --git a/tools/testing/selftests/rseq/rseq-riscv.h b/tools/testing/selftests/rseq/rseq-riscv.h
index 3a391c9bf468..17932a79e066 100644
--- a/tools/testing/selftests/rseq/rseq-riscv.h
+++ b/tools/testing/selftests/rseq/rseq-riscv.h
@@ -49,10 +49,6 @@ do {									\
 	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"				\
@@ -169,509 +165,34 @@ do {									\
 	RSEQ_ASM_OP_R_ADD(inc)						\
 	__rseq_str(post_commit_label) ":\n"
 
-static inline __always_inline
-int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
-{
-	RSEQ_INJECT_C(9)
+/* Per-cpu-id indexing. */
 
-	__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]	"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", RSEQ_ASM_TMP_REG_1
-				    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 __always_inline
-int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
-{
-	RSEQ_INJECT_C(9)
-
-	__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]	"m" (rseq_get_abi()->cpu_id),
-				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
-				    [v]			"m" (*v),
-				    [expectnot]		"r" (expectnot),
-				    [load]		"m" (*load),
-				    [voffp]		"r" (voffp)
-				    RSEQ_INJECT_INPUT
-				  : "memory", RSEQ_ASM_TMP_REG_1
-				    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
-}
+#define RSEQ_TEMPLATE_CPU_ID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-riscv-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
 
-static inline __always_inline
-int rseq_addv(intptr_t *v, intptr_t count, int cpu)
-{
-	RSEQ_INJECT_C(9)
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-riscv-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_CPU_ID
 
-	__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]	"m" (rseq_get_abi()->cpu_id),
-				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
-				    [v]			"m" (*v),
-				    [count]		"r" (count)
-				    RSEQ_INJECT_INPUT
-				  : "memory", RSEQ_ASM_TMP_REG_1
-				    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 __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]	"m" (rseq_get_abi()->cpu_id),
-				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
-				    [expect]		"r" (expect),
-				    [v]			"m" (*v),
-				    [newv]		"r" (newv),
-				    [v2]			"m" (*v2),
-				    [newv2]		"r" (newv2)
-				    RSEQ_INJECT_INPUT
-				  : "memory", RSEQ_ASM_TMP_REG_1
-				    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 __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]	"m" (rseq_get_abi()->cpu_id),
-				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
-				    [expect]		"r" (expect),
-				    [v]			"m" (*v),
-				    [newv]		"r" (newv),
-				    [v2]			"m" (*v2),
-				    [newv2]		"r" (newv2)
-				    RSEQ_INJECT_INPUT
-				  : "memory", RSEQ_ASM_TMP_REG_1
-				    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 __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]	"m" (rseq_get_abi()->cpu_id),
-				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
-				    [v]			"m" (*v),
-				    [expect]		"r" (expect),
-				    [v2]			"m" (*v2),
-				    [expect2]		"r" (expect2),
-				    [newv]		"r" (newv)
-				    RSEQ_INJECT_INPUT
-				  : "memory", RSEQ_ASM_TMP_REG_1
-				    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("expected value comparison failed");
-error3:
-	rseq_bug("2nd expected value comparison failed");
-#endif
-}
-
-static inline __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]	"m" (rseq_get_abi()->cpu_id),
-				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
-				    [expect]		"r" (expect),
-				    [v]			"m" (*v),
-				    [newv]		"r" (newv),
-				    [dst]			"r" (dst),
-				    [src]			"r" (src),
-				    [len]			"r" (len)
-				    RSEQ_INJECT_INPUT
-				  : "memory", RSEQ_ASM_TMP_REG_1, RSEQ_ASM_TMP_REG_2,
-				    RSEQ_ASM_TMP_REG_3, RSEQ_ASM_TMP_REG_4
-				    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 __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]	"m" (rseq_get_abi()->cpu_id),
-				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
-				    [expect]		"r" (expect),
-				    [v]			"m" (*v),
-				    [newv]		"r" (newv),
-				    [dst]			"r" (dst),
-				    [src]			"r" (src),
-				    [len]			"r" (len)
-				    RSEQ_INJECT_INPUT
-				  : "memory", RSEQ_ASM_TMP_REG_1, RSEQ_ASM_TMP_REG_2,
-				    RSEQ_ASM_TMP_REG_3, RSEQ_ASM_TMP_REG_4
-				    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
-}
+/* Per-mm-cid indexing. */
 
-#define RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+#define RSEQ_TEMPLATE_MM_CID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-riscv-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
 
-/*
- *   pval = *(ptr+off)
- *  *pval += inc;
- */
-static inline __always_inline
-int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, 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_DEREF_ADDV(ptr, off, 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]      "m" (rseq_get_abi()->cpu_id),
-				    [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
-				    [ptr]			"r" (ptr),
-				    [off]			"er" (off),
-				    [inc]			"er" (inc)
-				    RSEQ_INJECT_INPUT
-				  : "memory", RSEQ_ASM_TMP_REG_1
-				    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
-}
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-riscv-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_MM_CID
+
+/* APIs which are not based on cpu ids. */
 
-#endif /* !RSEQ_SKIP_FASTPATH */
+#define RSEQ_TEMPLATE_CPU_ID_NONE
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-riscv-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
+#undef RSEQ_TEMPLATE_CPU_ID_NONE
diff --git a/tools/testing/selftests/rseq/rseq-s390-bits.h b/tools/testing/selftests/rseq/rseq-s390-bits.h
new file mode 100644
index 000000000000..0cf17d9f170a
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-s390-bits.h
@@ -0,0 +1,474 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+
+#include "rseq-bits-template.h"
+
+#if defined(RSEQ_TEMPLATE_MO_RELAXED) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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
+}
+
+#endif /* #if defined(RSEQ_TEMPLATE_MO_RELAXED) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+/* s390 is TSO. */
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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_TEMPLATE_IDENTIFIER(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()->RSEQ_TEMPLATE_CPU_ID_FIELD),
+		  [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
+}
+
+#endif /* #if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#include "rseq-bits-reset.h"
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
index 4e6dc5f0cb42..46c92598acc7 100644
--- a/tools/testing/selftests/rseq/rseq-s390.h
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -28,10 +28,6 @@ do {									\
 	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"
@@ -134,477 +130,34 @@ do {									\
 		"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)
+/* Per-cpu-id indexing. */
 
-	__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
-}
+#define RSEQ_TEMPLATE_CPU_ID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-s390-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
 
-/*
- * 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
-}
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-s390-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_CPU_ID
 
-static inline __attribute__((always_inline))
-int rseq_addv(intptr_t *v, intptr_t count, int cpu)
-{
-	RSEQ_INJECT_C(9)
+/* Per-mm-cid indexing. */
 
-	__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
-}
+#define RSEQ_TEMPLATE_MM_CID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-s390-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
 
-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)
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-s390-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_MM_CID
 
-	__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
-}
+/* APIs which are not based on cpu ids. */
 
-/* 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 */
+#define RSEQ_TEMPLATE_CPU_ID_NONE
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-s390-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
+#undef RSEQ_TEMPLATE_CPU_ID_NONE
diff --git a/tools/testing/selftests/rseq/rseq-skip.h b/tools/testing/selftests/rseq/rseq-skip.h
deleted file mode 100644
index 7b53dac1fcdd..000000000000
--- a/tools/testing/selftests/rseq/rseq-skip.h
+++ /dev/null
@@ -1,65 +0,0 @@
-/* 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-x86-bits.h b/tools/testing/selftests/rseq/rseq-x86-bits.h
new file mode 100644
index 000000000000..8a9431eec467
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-x86-bits.h
@@ -0,0 +1,993 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-x86-bits.h
+ *
+ * (C) Copyright 2016-2022 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#include "rseq-bits-template.h"
+
+#ifdef __x86_64__
+
+#if defined(RSEQ_TEMPLATE_MO_RELAXED) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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
+}
+
+#endif /* #if defined(RSEQ_TEMPLATE_MO_RELAXED) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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
+}
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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
+}
+
+#endif /* #if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#elif defined(__i386__)
+
+#if defined(RSEQ_TEMPLATE_MO_RELAXED) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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
+}
+
+#endif /* #if defined(RSEQ_TEMPLATE_MO_RELAXED) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && \
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID))
+
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+		"lock; addl $0,-128(%%esp)\n\t"
+#endif
+		/* 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
+
+}
+
+/* TODO: implement a faster memcpy. */
+static inline __attribute__((always_inline))
+int RSEQ_TEMPLATE_IDENTIFIER(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_TEMPLATE_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_TEMPLATE_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)
+#ifdef RSEQ_TEMPLATE_MO_RELEASE
+		"lock; addl $0,-128(%%esp)\n\t"
+#endif
+		"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 /* #if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) &&
+	(defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */
+
+#endif
+
+#include "rseq-bits-reset.h"
diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h
index bd01dc41ca13..fb65ef54b0fb 100644
--- a/tools/testing/selftests/rseq/rseq-x86.h
+++ b/tools/testing/selftests/rseq/rseq-x86.h
@@ -2,9 +2,13 @@
 /*
  * rseq-x86.h
  *
- * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ * (C) Copyright 2016-2022 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
  */
 
+#ifndef RSEQ_H
+#error "Never use <rseq-x86.h> directly; include <rseq.h> instead."
+#endif
+
 #include <stdint.h>
 
 /*
@@ -22,9 +26,10 @@
  * address through a "r" input operand.
  */
 
-/* Offset of cpu_id and rseq_cs fields in struct rseq. */
+/* Offset of cpu_id, rseq_cs, and mm_cid fields in struct rseq. */
 #define RSEQ_CPU_ID_OFFSET	4
 #define RSEQ_CS_OFFSET		8
+#define RSEQ_MM_CID_OFFSET	24
 
 #ifdef __x86_64__
 
@@ -50,10 +55,6 @@ do {									\
 	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"			\
@@ -112,525 +113,6 @@ do {									\
 		"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
@@ -657,10 +139,6 @@ do {									\
 	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.
@@ -721,645 +199,36 @@ do {									\
 		"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];
+/* Per-cpu-id indexing. */
 
-	RSEQ_INJECT_C(9)
+#define RSEQ_TEMPLATE_CPU_ID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-x86-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
 
-	__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
-}
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-x86-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_CPU_ID
 
-/* 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];
+/* Per-mm-cid indexing. */
 
-	RSEQ_INJECT_C(9)
+#define RSEQ_TEMPLATE_MM_CID
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-x86-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
 
-	__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
-}
+#define RSEQ_TEMPLATE_MO_RELEASE
+#include "rseq-x86-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELEASE
+#undef RSEQ_TEMPLATE_MM_CID
 
-#endif /* !RSEQ_SKIP_FASTPATH */
+/* APIs which are not based on cpu ids. */
 
-#endif
+#define RSEQ_TEMPLATE_CPU_ID_NONE
+#define RSEQ_TEMPLATE_MO_RELAXED
+#include "rseq-x86-bits.h"
+#undef RSEQ_TEMPLATE_MO_RELAXED
+#undef RSEQ_TEMPLATE_CPU_ID_NONE
diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index 4177f9507bbe..4e4aa006004c 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -28,6 +28,8 @@
 #include <limits.h>
 #include <dlfcn.h>
 #include <stddef.h>
+#include <sys/auxv.h>
+#include <linux/auxvec.h>
 
 #include "../kselftest.h"
 #include "rseq.h"
@@ -36,20 +38,38 @@ static const ptrdiff_t *libc_rseq_offset_p;
 static const unsigned int *libc_rseq_size_p;
 static const unsigned int *libc_rseq_flags_p;
 
-/* Offset from the thread pointer to the rseq area.  */
+/* 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.  */
+/*
+ * 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;
 
+/*
+ * rseq feature size supported by the kernel. 0 if the registration was
+ * unsuccessful.
+ */
+unsigned int rseq_feature_size = -1U;
+
 static int rseq_ownership;
+static int rseq_reg_success;	/* At least one rseq registration has succeded. */
+
+/* Allocate a large area for the TLS. */
+#define RSEQ_THREAD_AREA_ALLOC_SIZE	1024
+
+/* Original struct rseq feature size is 20 bytes. */
+#define ORIG_RSEQ_FEATURE_SIZE		20
+
+/* Original struct rseq allocation size is 32 bytes. */
+#define ORIG_RSEQ_ALLOC_SIZE		32
 
 static
-__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = {
+__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"), aligned(RSEQ_THREAD_AREA_ALLOC_SIZE))) = {
 	.cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
 };
 
@@ -59,6 +79,11 @@ static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len,
 	return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
 }
 
+static int sys_getcpu(unsigned *cpu, unsigned *node)
+{
+	return syscall(__NR_getcpu, cpu, node, NULL);
+}
+
 int rseq_available(void)
 {
 	int rc;
@@ -84,10 +109,16 @@ int rseq_register_current_thread(void)
 		/* Treat libc's ownership as a successful registration. */
 		return 0;
 	}
-	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), 0, RSEQ_SIG);
-	if (rc)
+	rc = sys_rseq(&__rseq_abi, rseq_size, 0, RSEQ_SIG);
+	if (rc) {
+		if (RSEQ_READ_ONCE(rseq_reg_success)) {
+			/* Incoherent success/failure within process. */
+			abort();
+		}
 		return -1;
+	}
 	assert(rseq_current_cpu_raw() >= 0);
+	RSEQ_WRITE_ONCE(rseq_reg_success, 1);
 	return 0;
 }
 
@@ -99,12 +130,28 @@ int rseq_unregister_current_thread(void)
 		/* 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);
+	rc = sys_rseq(&__rseq_abi, rseq_size, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
 	if (rc)
 		return -1;
 	return 0;
 }
 
+static
+unsigned int get_rseq_feature_size(void)
+{
+	unsigned long auxv_rseq_feature_size, auxv_rseq_align;
+
+	auxv_rseq_align = getauxval(AT_RSEQ_ALIGN);
+	assert(!auxv_rseq_align || auxv_rseq_align <= RSEQ_THREAD_AREA_ALLOC_SIZE);
+
+	auxv_rseq_feature_size = getauxval(AT_RSEQ_FEATURE_SIZE);
+	assert(!auxv_rseq_feature_size || auxv_rseq_feature_size <= RSEQ_THREAD_AREA_ALLOC_SIZE);
+	if (auxv_rseq_feature_size)
+		return auxv_rseq_feature_size;
+	else
+		return ORIG_RSEQ_FEATURE_SIZE;
+}
+
 static __attribute__((constructor))
 void rseq_init(void)
 {
@@ -117,14 +164,24 @@ void rseq_init(void)
 		rseq_offset = *libc_rseq_offset_p;
 		rseq_size = *libc_rseq_size_p;
 		rseq_flags = *libc_rseq_flags_p;
+		rseq_feature_size = get_rseq_feature_size();
+		if (rseq_feature_size > rseq_size)
+			rseq_feature_size = rseq_size;
 		return;
 	}
-	if (!rseq_available())
-		return;
 	rseq_ownership = 1;
+	if (!rseq_available()) {
+		rseq_size = 0;
+		rseq_feature_size = 0;
+		return;
+	}
 	rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer();
-	rseq_size = sizeof(struct rseq_abi);
 	rseq_flags = 0;
+	rseq_feature_size = get_rseq_feature_size();
+	if (rseq_feature_size == ORIG_RSEQ_FEATURE_SIZE)
+		rseq_size = ORIG_RSEQ_ALLOC_SIZE;
+	else
+		rseq_size = RSEQ_THREAD_AREA_ALLOC_SIZE;
 }
 
 static __attribute__((destructor))
@@ -134,6 +191,7 @@ void rseq_exit(void)
 		return;
 	rseq_offset = 0;
 	rseq_size = -1U;
+	rseq_feature_size = -1U;
 	rseq_ownership = 0;
 }
 
@@ -148,3 +206,16 @@ int32_t rseq_fallback_current_cpu(void)
 	}
 	return cpu;
 }
+
+int32_t rseq_fallback_current_node(void)
+{
+	uint32_t cpu_id, node_id;
+	int ret;
+
+	ret = sys_getcpu(&cpu_id, &node_id);
+	if (ret) {
+		perror("sys_getcpu()");
+		return ret;
+	}
+	return (int32_t) node_id;
+}
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index 6f7513384bf5..d7364ea4d201 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -20,6 +20,15 @@
 #include "rseq-abi.h"
 #include "compiler.h"
 
+#ifndef rseq_sizeof_field
+#define rseq_sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER))
+#endif
+
+#ifndef rseq_offsetofend
+#define rseq_offsetofend(TYPE, MEMBER) \
+	(offsetof(TYPE, MEMBER)	+ rseq_sizeof_field(TYPE, MEMBER))
+#endif
+
 /*
  * Empty code injection macros, override when testing.
  * It is important to consider that the ASM injection macros need to be
@@ -47,14 +56,38 @@
 
 #include "rseq-thread-pointer.h"
 
-/* Offset from the thread pointer to the rseq area.  */
+/* 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.  */
+
+/*
+ * Size of the registered rseq area. 0 if the registration was
+ * unsuccessful.
+ */
 extern unsigned int rseq_size;
-/* Flags used during rseq registration.  */
+
+/* Flags used during rseq registration. */
 extern unsigned int rseq_flags;
 
+/*
+ * rseq feature size supported by the kernel. 0 if the registration was
+ * unsuccessful.
+ */
+extern unsigned int rseq_feature_size;
+
+enum rseq_mo {
+	RSEQ_MO_RELAXED = 0,
+	RSEQ_MO_CONSUME = 1,	/* Unused */
+	RSEQ_MO_ACQUIRE = 2,	/* Unused */
+	RSEQ_MO_RELEASE = 3,
+	RSEQ_MO_ACQ_REL = 4,	/* Unused */
+	RSEQ_MO_SEQ_CST = 5,	/* Unused */
+};
+
+enum rseq_percpu_mode {
+	RSEQ_PERCPU_CPU_ID = 0,
+	RSEQ_PERCPU_MM_CID = 1,
+};
+
 static inline struct rseq_abi *rseq_get_abi(void)
 {
 	return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset);
@@ -119,6 +152,11 @@ int rseq_unregister_current_thread(void);
 int32_t rseq_fallback_current_cpu(void);
 
 /*
+ * Restartable sequence fallback for reading the current node number.
+ */
+int32_t rseq_fallback_current_node(void);
+
+/*
  * Values returned can be either the current CPU number, -1 (rseq is
  * uninitialized), or -2 (rseq initialization has failed).
  */
@@ -153,6 +191,30 @@ static inline uint32_t rseq_current_cpu(void)
 	return cpu;
 }
 
+static inline bool rseq_node_id_available(void)
+{
+	return (int) rseq_feature_size >= rseq_offsetofend(struct rseq_abi, node_id);
+}
+
+/*
+ * Current NUMA node number.
+ */
+static inline uint32_t rseq_current_node_id(void)
+{
+	assert(rseq_node_id_available());
+	return RSEQ_ACCESS_ONCE(rseq_get_abi()->node_id);
+}
+
+static inline bool rseq_mm_cid_available(void)
+{
+	return (int) rseq_feature_size >= rseq_offsetofend(struct rseq_abi, mm_cid);
+}
+
+static inline uint32_t rseq_current_mm_cid(void)
+{
+	return RSEQ_ACCESS_ONCE(rseq_get_abi()->mm_cid);
+}
+
 static inline void rseq_clear_rseq_cs(void)
 {
 	RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0);
@@ -174,4 +236,149 @@ static inline void rseq_prepare_unload(void)
 	rseq_clear_rseq_cs();
 }
 
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode,
+		       intptr_t *v, intptr_t expect,
+		       intptr_t newv, int cpu)
+{
+	if (rseq_mo != RSEQ_MO_RELAXED)
+		return -1;
+	switch (percpu_mode) {
+	case RSEQ_PERCPU_CPU_ID:
+		return rseq_cmpeqv_storev_relaxed_cpu_id(v, expect, newv, cpu);
+	case RSEQ_PERCPU_MM_CID:
+		return rseq_cmpeqv_storev_relaxed_mm_cid(v, expect, newv, cpu);
+	}
+	return -1;
+}
+
+/*
+ * 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(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode,
+			       intptr_t *v, intptr_t expectnot, long voffp, intptr_t *load,
+			       int cpu)
+{
+	if (rseq_mo != RSEQ_MO_RELAXED)
+		return -1;
+	switch (percpu_mode) {
+	case RSEQ_PERCPU_CPU_ID:
+		return rseq_cmpnev_storeoffp_load_relaxed_cpu_id(v, expectnot, voffp, load, cpu);
+	case RSEQ_PERCPU_MM_CID:
+		return rseq_cmpnev_storeoffp_load_relaxed_mm_cid(v, expectnot, voffp, load, cpu);
+	}
+	return -1;
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode,
+	      intptr_t *v, intptr_t count, int cpu)
+{
+	if (rseq_mo != RSEQ_MO_RELAXED)
+		return -1;
+	switch (percpu_mode) {
+	case RSEQ_PERCPU_CPU_ID:
+		return rseq_addv_relaxed_cpu_id(v, count, cpu);
+	case RSEQ_PERCPU_MM_CID:
+		return rseq_addv_relaxed_mm_cid(v, count, cpu);
+	}
+	return -1;
+}
+
+#ifdef RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+/*
+ *   pval = *(ptr+off)
+ *  *pval += inc;
+ */
+static inline __attribute__((always_inline))
+int rseq_offset_deref_addv(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode,
+			   intptr_t *ptr, long off, intptr_t inc, int cpu)
+{
+	if (rseq_mo != RSEQ_MO_RELAXED)
+		return -1;
+	switch (percpu_mode) {
+	case RSEQ_PERCPU_CPU_ID:
+		return rseq_offset_deref_addv_relaxed_cpu_id(ptr, off, inc, cpu);
+	case RSEQ_PERCPU_MM_CID:
+		return rseq_offset_deref_addv_relaxed_mm_cid(ptr, off, inc, cpu);
+	}
+	return -1;
+}
+#endif
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode,
+				 intptr_t *v, intptr_t expect,
+				 intptr_t *v2, intptr_t newv2,
+				 intptr_t newv, int cpu)
+{
+	switch (rseq_mo) {
+	case RSEQ_MO_RELAXED:
+		switch (percpu_mode) {
+		case RSEQ_PERCPU_CPU_ID:
+			return rseq_cmpeqv_trystorev_storev_relaxed_cpu_id(v, expect, v2, newv2, newv, cpu);
+		case RSEQ_PERCPU_MM_CID:
+			return rseq_cmpeqv_trystorev_storev_relaxed_mm_cid(v, expect, v2, newv2, newv, cpu);
+		}
+		return -1;
+	case RSEQ_MO_RELEASE:
+		switch (percpu_mode) {
+		case RSEQ_PERCPU_CPU_ID:
+			return rseq_cmpeqv_trystorev_storev_release_cpu_id(v, expect, v2, newv2, newv, cpu);
+		case RSEQ_PERCPU_MM_CID:
+			return rseq_cmpeqv_trystorev_storev_release_mm_cid(v, expect, v2, newv2, newv, cpu);
+		}
+		return -1;
+	default:
+		return -1;
+	}
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode,
+			      intptr_t *v, intptr_t expect,
+			      intptr_t *v2, intptr_t expect2,
+			      intptr_t newv, int cpu)
+{
+	if (rseq_mo != RSEQ_MO_RELAXED)
+		return -1;
+	switch (percpu_mode) {
+	case RSEQ_PERCPU_CPU_ID:
+		return rseq_cmpeqv_cmpeqv_storev_relaxed_cpu_id(v, expect, v2, expect2, newv, cpu);
+	case RSEQ_PERCPU_MM_CID:
+		return rseq_cmpeqv_cmpeqv_storev_relaxed_mm_cid(v, expect, v2, expect2, newv, cpu);
+	}
+	return -1;
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode,
+				 intptr_t *v, intptr_t expect,
+				 void *dst, void *src, size_t len,
+				 intptr_t newv, int cpu)
+{
+	switch (rseq_mo) {
+	case RSEQ_MO_RELAXED:
+		switch (percpu_mode) {
+		case RSEQ_PERCPU_CPU_ID:
+			return rseq_cmpeqv_trymemcpy_storev_relaxed_cpu_id(v, expect, dst, src, len, newv, cpu);
+		case RSEQ_PERCPU_MM_CID:
+			return rseq_cmpeqv_trymemcpy_storev_relaxed_mm_cid(v, expect, dst, src, len, newv, cpu);
+		}
+		return -1;
+	case RSEQ_MO_RELEASE:
+		switch (percpu_mode) {
+		case RSEQ_PERCPU_CPU_ID:
+			return rseq_cmpeqv_trymemcpy_storev_release_cpu_id(v, expect, dst, src, len, newv, cpu);
+		case RSEQ_PERCPU_MM_CID:
+			return rseq_cmpeqv_trymemcpy_storev_release_mm_cid(v, expect, dst, src, len, newv, cpu);
+		}
+		return -1;
+	default:
+		return -1;
+	}
+}
+
 #endif  /* RSEQ_H_ */
diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh
index f51bc83c9e41..8d31426ab41f 100755
--- a/tools/testing/selftests/rseq/run_param_test.sh
+++ b/tools/testing/selftests/rseq/run_param_test.sh
@@ -42,6 +42,11 @@ function do_tests()
 		./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
+
+		echo "Running mm_cid test ${TEST_NAME[$i]}"
+		./param_test_mm_cid ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+		echo "Running mm_cid compare-twice test ${TEST_NAME[$i]}"
+		./param_test_mm_cid_compare_twice ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
 		let "i++"
 	done
 }