Merge branch 'scftorture.2020.08.24a' into HEAD

scftorture.2020.08.24a: Torture tests for smp_call_function() and friends.

6 files changed, 745 insertions, 168 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 9a20016d4900..c45f551deaaa 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -133,6 +133,8 @@ KASAN_SANITIZE_stackleak.o := n
 KCSAN_SANITIZE_stackleak.o := n
 KCOV_INSTRUMENT_stackleak.o := n
 
+obj-$(CONFIG_SCF_TORTURE_TEST) += scftorture.o
+
 $(obj)/configs.o: $(obj)/config_data.gz
 
 targets += config_data.gz
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 3cf6132a4bb9..5cb175df6ece 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -23,7 +23,7 @@ config TORTURE_TEST
 	tristate
 	default n
 
-config RCU_PERF_TEST
+config RCU_SCALE_TEST
 	tristate "performance tests for RCU"
 	depends on DEBUG_KERNEL
 	select TORTURE_TEST
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 95f5117ef8da..0cfb009a99b9 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -11,7 +11,7 @@ obj-y += update.o sync.o
 obj-$(CONFIG_TREE_SRCU) += srcutree.o
 obj-$(CONFIG_TINY_SRCU) += srcutiny.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
-obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o
+obj-$(CONFIG_RCU_SCALE_TEST) += rcuscale.o
 obj-$(CONFIG_RCU_REF_SCALE_TEST) += refscale.o
 obj-$(CONFIG_TREE_RCU) += tree.o
 obj-$(CONFIG_TINY_RCU) += tiny.o
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuscale.c
index 21448d3374e2..2819b95479af 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuscale.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
- * Read-Copy Update module-based performance-test facility
+ * Read-Copy Update module-based scalability-test facility
  *
  * Copyright (C) IBM Corporation, 2015
  *
@@ -44,13 +44,13 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
 
-#define PERF_FLAG "-perf:"
-#define PERFOUT_STRING(s) \
-	pr_alert("%s" PERF_FLAG " %s\n", perf_type, s)
-#define VERBOSE_PERFOUT_STRING(s) \
-	do { if (verbose) pr_alert("%s" PERF_FLAG " %s\n", perf_type, s); } while (0)
-#define VERBOSE_PERFOUT_ERRSTRING(s) \
-	do { if (verbose) pr_alert("%s" PERF_FLAG "!!! %s\n", perf_type, s); } while (0)
+#define SCALE_FLAG "-scale:"
+#define SCALEOUT_STRING(s) \
+	pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s)
+#define VERBOSE_SCALEOUT_STRING(s) \
+	do { if (verbose) pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s); } while (0)
+#define VERBOSE_SCALEOUT_ERRSTRING(s) \
+	do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! %s\n", scale_type, s); } while (0)
 
 /*
  * The intended use cases for the nreaders and nwriters module parameters
@@ -61,25 +61,25 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
  *	nr_cpus for a mixed reader/writer test.
  *
  * 2.	Specify the nr_cpus kernel boot parameter, but set
- *	rcuperf.nreaders to zero.  This will set nwriters to the
+ *	rcuscale.nreaders to zero.  This will set nwriters to the
  *	value specified by nr_cpus for an update-only test.
  *
  * 3.	Specify the nr_cpus kernel boot parameter, but set
- *	rcuperf.nwriters to zero.  This will set nreaders to the
+ *	rcuscale.nwriters to zero.  This will set nreaders to the
  *	value specified by nr_cpus for a read-only test.
  *
  * Various other use cases may of course be specified.
  *
  * Note that this test's readers are intended only as a test load for
- * the writers.  The reader performance statistics will be overly
+ * the writers.  The reader scalability statistics will be overly
  * pessimistic due to the per-critical-section interrupt disabling,
  * test-end checks, and the pair of calls through pointers.
  */
 
 #ifdef MODULE
-# define RCUPERF_SHUTDOWN 0
+# define RCUSCALE_SHUTDOWN 0
 #else
-# define RCUPERF_SHUTDOWN 1
+# define RCUSCALE_SHUTDOWN 1
 #endif
 
 torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives");
@@ -88,16 +88,16 @@ torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
 torture_param(int, holdoff, 10, "Holdoff time before test start (s)");
 torture_param(int, nreaders, -1, "Number of RCU reader threads");
 torture_param(int, nwriters, -1, "Number of RCU updater threads");
-torture_param(bool, shutdown, RCUPERF_SHUTDOWN,
-	      "Shutdown at end of performance tests.");
+torture_param(bool, shutdown, RCUSCALE_SHUTDOWN,
+	      "Shutdown at end of scalability tests.");
 torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
-torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() perf test?");
+torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() scale test?");
 torture_param(int, kfree_mult, 1, "Multiple of kfree_obj size to allocate.");
 
-static char *perf_type = "rcu";
-module_param(perf_type, charp, 0444);
-MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, srcu, ...)");
+static char *scale_type = "rcu";
+module_param(scale_type, charp, 0444);
+MODULE_PARM_DESC(scale_type, "Type of RCU to scalability-test (rcu, srcu, ...)");
 
 static int nrealreaders;
 static int nrealwriters;
@@ -107,12 +107,12 @@ static struct task_struct *shutdown_task;
 
 static u64 **writer_durations;
 static int *writer_n_durations;
-static atomic_t n_rcu_perf_reader_started;
-static atomic_t n_rcu_perf_writer_started;
-static atomic_t n_rcu_perf_writer_finished;
+static atomic_t n_rcu_scale_reader_started;
+static atomic_t n_rcu_scale_writer_started;
+static atomic_t n_rcu_scale_writer_finished;
 static wait_queue_head_t shutdown_wq;
-static u64 t_rcu_perf_writer_started;
-static u64 t_rcu_perf_writer_finished;
+static u64 t_rcu_scale_writer_started;
+static u64 t_rcu_scale_writer_finished;
 static unsigned long b_rcu_gp_test_started;
 static unsigned long b_rcu_gp_test_finished;
 static DEFINE_PER_CPU(atomic_t, n_async_inflight);
@@ -124,7 +124,7 @@ static DEFINE_PER_CPU(atomic_t, n_async_inflight);
  * Operations vector for selecting different types of tests.
  */
 
-struct rcu_perf_ops {
+struct rcu_scale_ops {
 	int ptype;
 	void (*init)(void);
 	void (*cleanup)(void);
@@ -140,19 +140,19 @@ struct rcu_perf_ops {
 	const char *name;
 };
 
-static struct rcu_perf_ops *cur_ops;
+static struct rcu_scale_ops *cur_ops;
 
 /*
- * Definitions for rcu perf testing.
+ * Definitions for rcu scalability testing.
  */
 
-static int rcu_perf_read_lock(void) __acquires(RCU)
+static int rcu_scale_read_lock(void) __acquires(RCU)
 {
 	rcu_read_lock();
 	return 0;
 }
 
-static void rcu_perf_read_unlock(int idx) __releases(RCU)
+static void rcu_scale_read_unlock(int idx) __releases(RCU)
 {
 	rcu_read_unlock();
 }
@@ -162,15 +162,15 @@ static unsigned long __maybe_unused rcu_no_completed(void)
 	return 0;
 }
 
-static void rcu_sync_perf_init(void)
+static void rcu_sync_scale_init(void)
 {
 }
 
-static struct rcu_perf_ops rcu_ops = {
+static struct rcu_scale_ops rcu_ops = {
 	.ptype		= RCU_FLAVOR,
-	.init		= rcu_sync_perf_init,
-	.readlock	= rcu_perf_read_lock,
-	.readunlock	= rcu_perf_read_unlock,
+	.init		= rcu_sync_scale_init,
+	.readlock	= rcu_scale_read_lock,
+	.readunlock	= rcu_scale_read_unlock,
 	.get_gp_seq	= rcu_get_gp_seq,
 	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= rcu_exp_batches_completed,
@@ -182,23 +182,23 @@ static struct rcu_perf_ops rcu_ops = {
 };
 
 /*
- * Definitions for srcu perf testing.
+ * Definitions for srcu scalability testing.
  */
 
-DEFINE_STATIC_SRCU(srcu_ctl_perf);
-static struct srcu_struct *srcu_ctlp = &srcu_ctl_perf;
+DEFINE_STATIC_SRCU(srcu_ctl_scale);
+static struct srcu_struct *srcu_ctlp = &srcu_ctl_scale;
 
-static int srcu_perf_read_lock(void) __acquires(srcu_ctlp)
+static int srcu_scale_read_lock(void) __acquires(srcu_ctlp)
 {
 	return srcu_read_lock(srcu_ctlp);
 }
 
-static void srcu_perf_read_unlock(int idx) __releases(srcu_ctlp)
+static void srcu_scale_read_unlock(int idx) __releases(srcu_ctlp)
 {
 	srcu_read_unlock(srcu_ctlp, idx);
 }
 
-static unsigned long srcu_perf_completed(void)
+static unsigned long srcu_scale_completed(void)
 {
 	return srcu_batches_completed(srcu_ctlp);
 }
@@ -213,78 +213,78 @@ static void srcu_rcu_barrier(void)
 	srcu_barrier(srcu_ctlp);
 }
 
-static void srcu_perf_synchronize(void)
+static void srcu_scale_synchronize(void)
 {
 	synchronize_srcu(srcu_ctlp);
 }
 
-static void srcu_perf_synchronize_expedited(void)
+static void srcu_scale_synchronize_expedited(void)
 {
 	synchronize_srcu_expedited(srcu_ctlp);
 }
 
-static struct rcu_perf_ops srcu_ops = {
+static struct rcu_scale_ops srcu_ops = {
 	.ptype		= SRCU_FLAVOR,
-	.init		= rcu_sync_perf_init,
-	.readlock	= srcu_perf_read_lock,
-	.readunlock	= srcu_perf_read_unlock,
-	.get_gp_seq	= srcu_perf_completed,
+	.init		= rcu_sync_scale_init,
+	.readlock	= srcu_scale_read_lock,
+	.readunlock	= srcu_scale_read_unlock,
+	.get_gp_seq	= srcu_scale_completed,
 	.gp_diff	= rcu_seq_diff,
-	.exp_completed	= srcu_perf_completed,
+	.exp_completed	= srcu_scale_completed,
 	.async		= srcu_call_rcu,
 	.gp_barrier	= srcu_rcu_barrier,
-	.sync		= srcu_perf_synchronize,
-	.exp_sync	= srcu_perf_synchronize_expedited,
+	.sync		= srcu_scale_synchronize,
+	.exp_sync	= srcu_scale_synchronize_expedited,
 	.name		= "srcu"
 };
 
 static struct srcu_struct srcud;
 
-static void srcu_sync_perf_init(void)
+static void srcu_sync_scale_init(void)
 {
 	srcu_ctlp = &srcud;
 	init_srcu_struct(srcu_ctlp);
 }
 
-static void srcu_sync_perf_cleanup(void)
+static void srcu_sync_scale_cleanup(void)
 {
 	cleanup_srcu_struct(srcu_ctlp);
 }
 
-static struct rcu_perf_ops srcud_ops = {
+static struct rcu_scale_ops srcud_ops = {
 	.ptype		= SRCU_FLAVOR,
-	.init		= srcu_sync_perf_init,
-	.cleanup	= srcu_sync_perf_cleanup,
-	.readlock	= srcu_perf_read_lock,
-	.readunlock	= srcu_perf_read_unlock,
-	.get_gp_seq	= srcu_perf_completed,
+	.init		= srcu_sync_scale_init,
+	.cleanup	= srcu_sync_scale_cleanup,
+	.readlock	= srcu_scale_read_lock,
+	.readunlock	= srcu_scale_read_unlock,
+	.get_gp_seq	= srcu_scale_completed,
 	.gp_diff	= rcu_seq_diff,
-	.exp_completed	= srcu_perf_completed,
+	.exp_completed	= srcu_scale_completed,
 	.async		= srcu_call_rcu,
 	.gp_barrier	= srcu_rcu_barrier,
-	.sync		= srcu_perf_synchronize,
-	.exp_sync	= srcu_perf_synchronize_expedited,
+	.sync		= srcu_scale_synchronize,
+	.exp_sync	= srcu_scale_synchronize_expedited,
 	.name		= "srcud"
 };
 
 /*
- * Definitions for RCU-tasks perf testing.
+ * Definitions for RCU-tasks scalability testing.
  */
 
-static int tasks_perf_read_lock(void)
+static int tasks_scale_read_lock(void)
 {
 	return 0;
 }
 
-static void tasks_perf_read_unlock(int idx)
+static void tasks_scale_read_unlock(int idx)
 {
 }
 
-static struct rcu_perf_ops tasks_ops = {
+static struct rcu_scale_ops tasks_ops = {
 	.ptype		= RCU_TASKS_FLAVOR,
-	.init		= rcu_sync_perf_init,
-	.readlock	= tasks_perf_read_lock,
-	.readunlock	= tasks_perf_read_unlock,
+	.init		= rcu_sync_scale_init,
+	.readlock	= tasks_scale_read_lock,
+	.readunlock	= tasks_scale_read_unlock,
 	.get_gp_seq	= rcu_no_completed,
 	.gp_diff	= rcu_seq_diff,
 	.async		= call_rcu_tasks,
@@ -294,7 +294,7 @@ static struct rcu_perf_ops tasks_ops = {
 	.name		= "tasks"
 };
 
-static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old)
+static unsigned long rcuscale_seq_diff(unsigned long new, unsigned long old)
 {
 	if (!cur_ops->gp_diff)
 		return new - old;
@@ -302,60 +302,60 @@ static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old)
 }
 
 /*
- * If performance tests complete, wait for shutdown to commence.
+ * If scalability tests complete, wait for shutdown to commence.
  */
-static void rcu_perf_wait_shutdown(void)
+static void rcu_scale_wait_shutdown(void)
 {
 	cond_resched_tasks_rcu_qs();
-	if (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters)
+	if (atomic_read(&n_rcu_scale_writer_finished) < nrealwriters)
 		return;
 	while (!torture_must_stop())
 		schedule_timeout_uninterruptible(1);
 }
 
 /*
- * RCU perf reader kthread.  Repeatedly does empty RCU read-side critical
- * section, minimizing update-side interference.  However, the point of
- * this test is not to evaluate reader performance, but instead to serve
- * as a test load for update-side performance testing.
+ * RCU scalability reader kthread.  Repeatedly does empty RCU read-side
+ * critical section, minimizing update-side interference.  However, the
+ * point of this test is not to evaluate reader scalability, but instead
+ * to serve as a test load for update-side scalability testing.
  */
 static int
-rcu_perf_reader(void *arg)
+rcu_scale_reader(void *arg)
 {
 	unsigned long flags;
 	int idx;
 	long me = (long)arg;
 
-	VERBOSE_PERFOUT_STRING("rcu_perf_reader task started");
+	VERBOSE_SCALEOUT_STRING("rcu_scale_reader task started");
 	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
 	set_user_nice(current, MAX_NICE);
-	atomic_inc(&n_rcu_perf_reader_started);
+	atomic_inc(&n_rcu_scale_reader_started);
 
 	do {
 		local_irq_save(flags);
 		idx = cur_ops->readlock();
 		cur_ops->readunlock(idx);
 		local_irq_restore(flags);
-		rcu_perf_wait_shutdown();
+		rcu_scale_wait_shutdown();
 	} while (!torture_must_stop());
-	torture_kthread_stopping("rcu_perf_reader");
+	torture_kthread_stopping("rcu_scale_reader");
 	return 0;
 }
 
 /*
- * Callback function for asynchronous grace periods from rcu_perf_writer().
+ * Callback function for asynchronous grace periods from rcu_scale_writer().
  */
-static void rcu_perf_async_cb(struct rcu_head *rhp)
+static void rcu_scale_async_cb(struct rcu_head *rhp)
 {
 	atomic_dec(this_cpu_ptr(&n_async_inflight));
 	kfree(rhp);
 }
 
 /*
- * RCU perf writer kthread.  Repeatedly does a grace period.
+ * RCU scale writer kthread.  Repeatedly does a grace period.
  */
 static int
-rcu_perf_writer(void *arg)
+rcu_scale_writer(void *arg)
 {
 	int i = 0;
 	int i_max;
@@ -366,7 +366,7 @@ rcu_perf_writer(void *arg)
 	u64 *wdp;
 	u64 *wdpp = writer_durations[me];
 
-	VERBOSE_PERFOUT_STRING("rcu_perf_writer task started");
+	VERBOSE_SCALEOUT_STRING("rcu_scale_writer task started");
 	WARN_ON(!wdpp);
 	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
 	sched_set_fifo_low(current);
@@ -383,8 +383,8 @@ rcu_perf_writer(void *arg)
 		schedule_timeout_uninterruptible(1);
 
 	t = ktime_get_mono_fast_ns();
-	if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) {
-		t_rcu_perf_writer_started = t;
+	if (atomic_inc_return(&n_rcu_scale_writer_started) >= nrealwriters) {
+		t_rcu_scale_writer_started = t;
 		if (gp_exp) {
 			b_rcu_gp_test_started =
 				cur_ops->exp_completed() / 2;
@@ -404,7 +404,7 @@ retry:
 				rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
 			if (rhp && atomic_read(this_cpu_ptr(&n_async_inflight)) < gp_async_max) {
 				atomic_inc(this_cpu_ptr(&n_async_inflight));
-				cur_ops->async(rhp, rcu_perf_async_cb);
+				cur_ops->async(rhp, rcu_scale_async_cb);
 				rhp = NULL;
 			} else if (!kthread_should_stop()) {
 				cur_ops->gp_barrier();
@@ -421,19 +421,19 @@ retry:
 		*wdp = t - *wdp;
 		i_max = i;
 		if (!started &&
-		    atomic_read(&n_rcu_perf_writer_started) >= nrealwriters)
+		    atomic_read(&n_rcu_scale_writer_started) >= nrealwriters)
 			started = true;
 		if (!done && i >= MIN_MEAS) {
 			done = true;
 			sched_set_normal(current, 0);
-			pr_alert("%s%s rcu_perf_writer %ld has %d measurements\n",
-				 perf_type, PERF_FLAG, me, MIN_MEAS);
-			if (atomic_inc_return(&n_rcu_perf_writer_finished) >=
+			pr_alert("%s%s rcu_scale_writer %ld has %d measurements\n",
+				 scale_type, SCALE_FLAG, me, MIN_MEAS);
+			if (atomic_inc_return(&n_rcu_scale_writer_finished) >=
 			    nrealwriters) {
 				schedule_timeout_interruptible(10);
 				rcu_ftrace_dump(DUMP_ALL);
-				PERFOUT_STRING("Test complete");
-				t_rcu_perf_writer_finished = t;
+				SCALEOUT_STRING("Test complete");
+				t_rcu_scale_writer_finished = t;
 				if (gp_exp) {
 					b_rcu_gp_test_finished =
 						cur_ops->exp_completed() / 2;
@@ -448,30 +448,30 @@ retry:
 			}
 		}
 		if (done && !alldone &&
-		    atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters)
+		    atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters)
 			alldone = true;
 		if (started && !alldone && i < MAX_MEAS - 1)
 			i++;
-		rcu_perf_wait_shutdown();
+		rcu_scale_wait_shutdown();
 	} while (!torture_must_stop());
 	if (gp_async) {
 		cur_ops->gp_barrier();
 	}
 	writer_n_durations[me] = i_max;
-	torture_kthread_stopping("rcu_perf_writer");
+	torture_kthread_stopping("rcu_scale_writer");
 	return 0;
 }
 
 static void
-rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag)
+rcu_scale_print_module_parms(struct rcu_scale_ops *cur_ops, const char *tag)
 {
-	pr_alert("%s" PERF_FLAG
+	pr_alert("%s" SCALE_FLAG
 		 "--- %s: nreaders=%d nwriters=%d verbose=%d shutdown=%d\n",
-		 perf_type, tag, nrealreaders, nrealwriters, verbose, shutdown);
+		 scale_type, tag, nrealreaders, nrealwriters, verbose, shutdown);
 }
 
 static void
-rcu_perf_cleanup(void)
+rcu_scale_cleanup(void)
 {
 	int i;
 	int j;
@@ -484,11 +484,11 @@ rcu_perf_cleanup(void)
 	 * during the mid-boot phase, so have to wait till the end.
 	 */
 	if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp)
-		VERBOSE_PERFOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
+		VERBOSE_SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
 	if (rcu_gp_is_normal() && gp_exp)
-		VERBOSE_PERFOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
+		VERBOSE_SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
 	if (gp_exp && gp_async)
-		VERBOSE_PERFOUT_ERRSTRING("No expedited async GPs, so went with async!");
+		VERBOSE_SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!");
 
 	if (torture_cleanup_begin())
 		return;
@@ -499,30 +499,30 @@ rcu_perf_cleanup(void)
 
 	if (reader_tasks) {
 		for (i = 0; i < nrealreaders; i++)
-			torture_stop_kthread(rcu_perf_reader,
+			torture_stop_kthread(rcu_scale_reader,
 					     reader_tasks[i]);
 		kfree(reader_tasks);
 	}
 
 	if (writer_tasks) {
 		for (i = 0; i < nrealwriters; i++) {
-			torture_stop_kthread(rcu_perf_writer,
+			torture_stop_kthread(rcu_scale_writer,
 					     writer_tasks[i]);
 			if (!writer_n_durations)
 				continue;
 			j = writer_n_durations[i];
 			pr_alert("%s%s writer %d gps: %d\n",
-				 perf_type, PERF_FLAG, i, j);
+				 scale_type, SCALE_FLAG, i, j);
 			ngps += j;
 		}
 		pr_alert("%s%s start: %llu end: %llu duration: %llu gps: %d batches: %ld\n",
-			 perf_type, PERF_FLAG,
-			 t_rcu_perf_writer_started, t_rcu_perf_writer_finished,
-			 t_rcu_perf_writer_finished -
-			 t_rcu_perf_writer_started,
+			 scale_type, SCALE_FLAG,
+			 t_rcu_scale_writer_started, t_rcu_scale_writer_finished,
+			 t_rcu_scale_writer_finished -
+			 t_rcu_scale_writer_started,
 			 ngps,
-			 rcuperf_seq_diff(b_rcu_gp_test_finished,
-					  b_rcu_gp_test_started));
+			 rcuscale_seq_diff(b_rcu_gp_test_finished,
+					   b_rcu_gp_test_started));
 		for (i = 0; i < nrealwriters; i++) {
 			if (!writer_durations)
 				break;
@@ -534,7 +534,7 @@ rcu_perf_cleanup(void)
 			for (j = 0; j <= writer_n_durations[i]; j++) {
 				wdp = &wdpp[j];
 				pr_alert("%s%s %4d writer-duration: %5d %llu\n",
-					perf_type, PERF_FLAG,
+					scale_type, SCALE_FLAG,
 					i, j, *wdp);
 				if (j % 100 == 0)
 					schedule_timeout_uninterruptible(1);
@@ -573,22 +573,22 @@ static int compute_real(int n)
 }
 
 /*
- * RCU perf shutdown kthread.  Just waits to be awakened, then shuts
+ * RCU scalability shutdown kthread.  Just waits to be awakened, then shuts
  * down system.
  */
 static int
-rcu_perf_shutdown(void *arg)
+rcu_scale_shutdown(void *arg)
 {
 	wait_event(shutdown_wq,
-		   atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters);
+		   atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters);
 	smp_mb(); /* Wake before output. */
-	rcu_perf_cleanup();
+	rcu_scale_cleanup();
 	kernel_power_off();
 	return -EINVAL;
 }
 
 /*
- * kfree_rcu() performance tests: Start a kfree_rcu() loop on all CPUs for number
+ * kfree_rcu() scalability tests: Start a kfree_rcu() loop on all CPUs for number
  * of iterations and measure total time and number of GP for all iterations to complete.
  */
 
@@ -598,8 +598,8 @@ torture_param(int, kfree_loops, 10, "Number of loops doing kfree_alloc_num alloc
 
 static struct task_struct **kfree_reader_tasks;
 static int kfree_nrealthreads;
-static atomic_t n_kfree_perf_thread_started;
-static atomic_t n_kfree_perf_thread_ended;
+static atomic_t n_kfree_scale_thread_started;
+static atomic_t n_kfree_scale_thread_ended;
 
 struct kfree_obj {
 	char kfree_obj[8];
@@ -607,7 +607,7 @@ struct kfree_obj {
 };
 
 static int
-kfree_perf_thread(void *arg)
+kfree_scale_thread(void *arg)
 {
 	int i, loop = 0;
 	long me = (long)arg;
@@ -615,13 +615,13 @@ kfree_perf_thread(void *arg)
 	u64 start_time, end_time;
 	long long mem_begin, mem_during = 0;
 
-	VERBOSE_PERFOUT_STRING("kfree_perf_thread task started");
+	VERBOSE_SCALEOUT_STRING("kfree_scale_thread task started");
 	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
 	set_user_nice(current, MAX_NICE);
 
 	start_time = ktime_get_mono_fast_ns();
 
-	if (atomic_inc_return(&n_kfree_perf_thread_started) >= kfree_nrealthreads) {
+	if (atomic_inc_return(&n_kfree_scale_thread_started) >= kfree_nrealthreads) {
 		if (gp_exp)
 			b_rcu_gp_test_started = cur_ops->exp_completed() / 2;
 		else
@@ -646,7 +646,7 @@ kfree_perf_thread(void *arg)
 		cond_resched();
 	} while (!torture_must_stop() && ++loop < kfree_loops);
 
-	if (atomic_inc_return(&n_kfree_perf_thread_ended) >= kfree_nrealthreads) {
+	if (atomic_inc_return(&n_kfree_scale_thread_ended) >= kfree_nrealthreads) {
 		end_time = ktime_get_mono_fast_ns();
 
 		if (gp_exp)
@@ -656,7 +656,7 @@ kfree_perf_thread(void *arg)
 
 		pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld, memory footprint: %lldMB\n",
 		       (unsigned long long)(end_time - start_time), kfree_loops,
-		       rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started),
+		       rcuscale_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started),
 		       (mem_begin - mem_during) >> (20 - PAGE_SHIFT));
 
 		if (shutdown) {
@@ -665,12 +665,12 @@ kfree_perf_thread(void *arg)
 		}
 	}
 
-	torture_kthread_stopping("kfree_perf_thread");
+	torture_kthread_stopping("kfree_scale_thread");
 	return 0;
 }
 
 static void
-kfree_perf_cleanup(void)
+kfree_scale_cleanup(void)
 {
 	int i;
 
@@ -679,7 +679,7 @@ kfree_perf_cleanup(void)
 
 	if (kfree_reader_tasks) {
 		for (i = 0; i < kfree_nrealthreads; i++)
-			torture_stop_kthread(kfree_perf_thread,
+			torture_stop_kthread(kfree_scale_thread,
 					     kfree_reader_tasks[i]);
 		kfree(kfree_reader_tasks);
 	}
@@ -691,20 +691,20 @@ kfree_perf_cleanup(void)
  * shutdown kthread.  Just waits to be awakened, then shuts down system.
  */
 static int
-kfree_perf_shutdown(void *arg)
+kfree_scale_shutdown(void *arg)
 {
 	wait_event(shutdown_wq,
-		   atomic_read(&n_kfree_perf_thread_ended) >= kfree_nrealthreads);
+		   atomic_read(&n_kfree_scale_thread_ended) >= kfree_nrealthreads);
 
 	smp_mb(); /* Wake before output. */
 
-	kfree_perf_cleanup();
+	kfree_scale_cleanup();
 	kernel_power_off();
 	return -EINVAL;
 }
 
 static int __init
-kfree_perf_init(void)
+kfree_scale_init(void)
 {
 	long i;
 	int firsterr = 0;
@@ -713,7 +713,7 @@ kfree_perf_init(void)
 	/* Start up the kthreads. */
 	if (shutdown) {
 		init_waitqueue_head(&shutdown_wq);
-		firsterr = torture_create_kthread(kfree_perf_shutdown, NULL,
+		firsterr = torture_create_kthread(kfree_scale_shutdown, NULL,
 						  shutdown_task);
 		if (firsterr)
 			goto unwind;
@@ -730,13 +730,13 @@ kfree_perf_init(void)
 	}
 
 	for (i = 0; i < kfree_nrealthreads; i++) {
-		firsterr = torture_create_kthread(kfree_perf_thread, (void *)i,
+		firsterr = torture_create_kthread(kfree_scale_thread, (void *)i,
 						  kfree_reader_tasks[i]);
 		if (firsterr)
 			goto unwind;
 	}
 
-	while (atomic_read(&n_kfree_perf_thread_started) < kfree_nrealthreads)
+	while (atomic_read(&n_kfree_scale_thread_started) < kfree_nrealthreads)
 		schedule_timeout_uninterruptible(1);
 
 	torture_init_end();
@@ -744,35 +744,35 @@ kfree_perf_init(void)
 
 unwind:
 	torture_init_end();
-	kfree_perf_cleanup();
+	kfree_scale_cleanup();
 	return firsterr;
 }
 
 static int __init
-rcu_perf_init(void)
+rcu_scale_init(void)
 {
 	long i;
 	int firsterr = 0;
-	static struct rcu_perf_ops *perf_ops[] = {
+	static struct rcu_scale_ops *scale_ops[] = {
 		&rcu_ops, &srcu_ops, &srcud_ops, &tasks_ops,
 	};
 
-	if (!torture_init_begin(perf_type, verbose))
+	if (!torture_init_begin(scale_type, verbose))
 		return -EBUSY;
 
-	/* Process args and tell the world that the perf'er is on the job. */
-	for (i = 0; i < ARRAY_SIZE(perf_ops); i++) {
-		cur_ops = perf_ops[i];
-		if (strcmp(perf_type, cur_ops->name) == 0)
+	/* Process args and announce that the scalability'er is on the job. */
+	for (i = 0; i < ARRAY_SIZE(scale_ops); i++) {
+		cur_ops = scale_ops[i];
+		if (strcmp(scale_type, cur_ops->name) == 0)
 			break;
 	}
-	if (i == ARRAY_SIZE(perf_ops)) {
-		pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type);
-		pr_alert("rcu-perf types:");
-		for (i = 0; i < ARRAY_SIZE(perf_ops); i++)
-			pr_cont(" %s", perf_ops[i]->name);
+	if (i == ARRAY_SIZE(scale_ops)) {
+		pr_alert("rcu-scale: invalid scale type: \"%s\"\n", scale_type);
+		pr_alert("rcu-scale types:");
+		for (i = 0; i < ARRAY_SIZE(scale_ops); i++)
+			pr_cont(" %s", scale_ops[i]->name);
 		pr_cont("\n");
-		WARN_ON(!IS_MODULE(CONFIG_RCU_PERF_TEST));
+		WARN_ON(!IS_MODULE(CONFIG_RCU_SCALE_TEST));
 		firsterr = -EINVAL;
 		cur_ops = NULL;
 		goto unwind;
@@ -781,20 +781,20 @@ rcu_perf_init(void)
 		cur_ops->init();
 
 	if (kfree_rcu_test)
-		return kfree_perf_init();
+		return kfree_scale_init();
 
 	nrealwriters = compute_real(nwriters);
 	nrealreaders = compute_real(nreaders);
-	atomic_set(&n_rcu_perf_reader_started, 0);
-	atomic_set(&n_rcu_perf_writer_started, 0);
-	atomic_set(&n_rcu_perf_writer_finished, 0);
-	rcu_perf_print_module_parms(cur_ops, "Start of test");
+	atomic_set(&n_rcu_scale_reader_started, 0);
+	atomic_set(&n_rcu_scale_writer_started, 0);
+	atomic_set(&n_rcu_scale_writer_finished, 0);
+	rcu_scale_print_module_parms(cur_ops, "Start of test");
 
 	/* Start up the kthreads. */
 
 	if (shutdown) {
 		init_waitqueue_head(&shutdown_wq);
-		firsterr = torture_create_kthread(rcu_perf_shutdown, NULL,
+		firsterr = torture_create_kthread(rcu_scale_shutdown, NULL,
 						  shutdown_task);
 		if (firsterr)
 			goto unwind;
@@ -803,17 +803,17 @@ rcu_perf_init(void)
 	reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
 			       GFP_KERNEL);
 	if (reader_tasks == NULL) {
-		VERBOSE_PERFOUT_ERRSTRING("out of memory");
+		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
 	for (i = 0; i < nrealreaders; i++) {
-		firsterr = torture_create_kthread(rcu_perf_reader, (void *)i,
+		firsterr = torture_create_kthread(rcu_scale_reader, (void *)i,
 						  reader_tasks[i]);
 		if (firsterr)
 			goto unwind;
 	}
-	while (atomic_read(&n_rcu_perf_reader_started) < nrealreaders)
+	while (atomic_read(&n_rcu_scale_reader_started) < nrealreaders)
 		schedule_timeout_uninterruptible(1);
 	writer_tasks = kcalloc(nrealwriters, sizeof(reader_tasks[0]),
 			       GFP_KERNEL);
@@ -823,7 +823,7 @@ rcu_perf_init(void)
 		kcalloc(nrealwriters, sizeof(*writer_n_durations),
 			GFP_KERNEL);
 	if (!writer_tasks || !writer_durations || !writer_n_durations) {
-		VERBOSE_PERFOUT_ERRSTRING("out of memory");
+		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
@@ -835,7 +835,7 @@ rcu_perf_init(void)
 			firsterr = -ENOMEM;
 			goto unwind;
 		}
-		firsterr = torture_create_kthread(rcu_perf_writer, (void *)i,
+		firsterr = torture_create_kthread(rcu_scale_writer, (void *)i,
 						  writer_tasks[i]);
 		if (firsterr)
 			goto unwind;
@@ -845,9 +845,9 @@ rcu_perf_init(void)
 
 unwind:
 	torture_init_end();
-	rcu_perf_cleanup();
+	rcu_scale_cleanup();
 	return firsterr;
 }
 
-module_init(rcu_perf_init);
-module_exit(rcu_perf_cleanup);
+module_init(rcu_scale_init);
+module_exit(rcu_scale_cleanup);
diff --git a/kernel/scftorture.c b/kernel/scftorture.c
new file mode 100644
index 000000000000..554a521ee235
--- /dev/null
+++ b/kernel/scftorture.c
@@ -0,0 +1,575 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Torture test for smp_call_function() and friends.
+//
+// Copyright (C) Facebook, 2020.
+//
+// Author: Paul E. McKenney <paulmck@kernel.org>
+
+#define pr_fmt(fmt) fmt
+
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kthread.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/notifier.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/rcupdate_trace.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/stat.h>
+#include <linux/srcu.h>
+#include <linux/slab.h>
+#include <linux/torture.h>
+#include <linux/types.h>
+
+#define SCFTORT_STRING "scftorture"
+#define SCFTORT_FLAG SCFTORT_STRING ": "
+
+#define SCFTORTOUT(s, x...) \
+	pr_alert(SCFTORT_FLAG s, ## x)
+
+#define VERBOSE_SCFTORTOUT(s, x...) \
+	do { if (verbose) pr_alert(SCFTORT_FLAG s, ## x); } while (0)
+
+#define VERBOSE_SCFTORTOUT_ERRSTRING(s, x...) \
+	do { if (verbose) pr_alert(SCFTORT_FLAG "!!! " s, ## x); } while (0)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@kernel.org>");
+
+// Wait until there are multiple CPUs before starting test.
+torture_param(int, holdoff, IS_BUILTIN(CONFIG_SCF_TORTURE_TEST) ? 10 : 0,
+	      "Holdoff time before test start (s)");
+torture_param(int, longwait, 0, "Include ridiculously long waits? (seconds)");
+torture_param(int, nthreads, -1, "# threads, defaults to -1 for all CPUs.");
+torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
+torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (s), 0=disable");
+torture_param(int, shutdown_secs, 0, "Shutdown time (ms), <= zero to disable.");
+torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s.");
+torture_param(int, stutter_cpus, 5, "Number of jiffies to change CPUs under test, 0=disable");
+torture_param(bool, use_cpus_read_lock, 0, "Use cpus_read_lock() to exclude CPU hotplug.");
+torture_param(int, verbose, 0, "Enable verbose debugging printk()s");
+torture_param(int, weight_single, -1, "Testing weight for single-CPU no-wait operations.");
+torture_param(int, weight_single_wait, -1, "Testing weight for single-CPU operations.");
+torture_param(int, weight_many, -1, "Testing weight for multi-CPU no-wait operations.");
+torture_param(int, weight_many_wait, -1, "Testing weight for multi-CPU operations.");
+torture_param(int, weight_all, -1, "Testing weight for all-CPU no-wait operations.");
+torture_param(int, weight_all_wait, -1, "Testing weight for all-CPU operations.");
+
+char *torture_type = "";
+
+#ifdef MODULE
+# define SCFTORT_SHUTDOWN 0
+#else
+# define SCFTORT_SHUTDOWN 1
+#endif
+
+torture_param(bool, shutdown, SCFTORT_SHUTDOWN, "Shutdown at end of torture test.");
+
+struct scf_statistics {
+	struct task_struct *task;
+	int cpu;
+	long long n_single;
+	long long n_single_ofl;
+	long long n_single_wait;
+	long long n_single_wait_ofl;
+	long long n_many;
+	long long n_many_wait;
+	long long n_all;
+	long long n_all_wait;
+};
+
+static struct scf_statistics *scf_stats_p;
+static struct task_struct *scf_torture_stats_task;
+static DEFINE_PER_CPU(long long, scf_invoked_count);
+
+// Data for random primitive selection
+#define SCF_PRIM_SINGLE		0
+#define SCF_PRIM_MANY		1
+#define SCF_PRIM_ALL		2
+#define SCF_NPRIMS		(2 * 3) // Need wait and no-wait versions of each.
+
+static char *scf_prim_name[] = {
+	"smp_call_function_single",
+	"smp_call_function_many",
+	"smp_call_function",
+};
+
+struct scf_selector {
+	unsigned long scfs_weight;
+	int scfs_prim;
+	bool scfs_wait;
+};
+static struct scf_selector scf_sel_array[SCF_NPRIMS];
+static int scf_sel_array_len;
+static unsigned long scf_sel_totweight;
+
+// Communicate between caller and handler.
+struct scf_check {
+	bool scfc_in;
+	bool scfc_out;
+	int scfc_cpu; // -1 for not _single().
+	bool scfc_wait;
+};
+
+// Use to wait for all threads to start.
+static atomic_t n_started;
+static atomic_t n_errs;
+static atomic_t n_mb_in_errs;
+static atomic_t n_mb_out_errs;
+static atomic_t n_alloc_errs;
+static bool scfdone;
+static char *bangstr = "";
+
+static DEFINE_TORTURE_RANDOM_PERCPU(scf_torture_rand);
+
+// Print torture statistics.  Caller must ensure serialization.
+static void scf_torture_stats_print(void)
+{
+	int cpu;
+	int i;
+	long long invoked_count = 0;
+	bool isdone = READ_ONCE(scfdone);
+	struct scf_statistics scfs = {};
+
+	for_each_possible_cpu(cpu)
+		invoked_count += data_race(per_cpu(scf_invoked_count, cpu));
+	for (i = 0; i < nthreads; i++) {
+		scfs.n_single += scf_stats_p[i].n_single;
+		scfs.n_single_ofl += scf_stats_p[i].n_single_ofl;
+		scfs.n_single_wait += scf_stats_p[i].n_single_wait;
+		scfs.n_single_wait_ofl += scf_stats_p[i].n_single_wait_ofl;
+		scfs.n_many += scf_stats_p[i].n_many;
+		scfs.n_many_wait += scf_stats_p[i].n_many_wait;
+		scfs.n_all += scf_stats_p[i].n_all;
+		scfs.n_all_wait += scf_stats_p[i].n_all_wait;
+	}
+	if (atomic_read(&n_errs) || atomic_read(&n_mb_in_errs) ||
+	    atomic_read(&n_mb_out_errs) || atomic_read(&n_alloc_errs))
+		bangstr = "!!! ";
+	pr_alert("%s %sscf_invoked_count %s: %lld single: %lld/%lld single_ofl: %lld/%lld many: %lld/%lld all: %lld/%lld ",
+		 SCFTORT_FLAG, bangstr, isdone ? "VER" : "ver", invoked_count,
+		 scfs.n_single, scfs.n_single_wait, scfs.n_single_ofl, scfs.n_single_wait_ofl,
+		 scfs.n_many, scfs.n_many_wait, scfs.n_all, scfs.n_all_wait);
+	torture_onoff_stats();
+	pr_cont("ste: %d stnmie: %d stnmoe: %d staf: %d\n", atomic_read(&n_errs),
+		atomic_read(&n_mb_in_errs), atomic_read(&n_mb_out_errs),
+		atomic_read(&n_alloc_errs));
+}
+
+// Periodically prints torture statistics, if periodic statistics printing
+// was specified via the stat_interval module parameter.
+static int
+scf_torture_stats(void *arg)
+{
+	VERBOSE_TOROUT_STRING("scf_torture_stats task started");
+	do {
+		schedule_timeout_interruptible(stat_interval * HZ);
+		scf_torture_stats_print();
+		torture_shutdown_absorb("scf_torture_stats");
+	} while (!torture_must_stop());
+	torture_kthread_stopping("scf_torture_stats");
+	return 0;
+}
+
+// Add a primitive to the scf_sel_array[].
+static void scf_sel_add(unsigned long weight, int prim, bool wait)
+{
+	struct scf_selector *scfsp = &scf_sel_array[scf_sel_array_len];
+
+	// If no weight, if array would overflow, if computing three-place
+	// percentages would overflow, or if the scf_prim_name[] array would
+	// overflow, don't bother.  In the last three two cases, complain.
+	if (!weight ||
+	    WARN_ON_ONCE(scf_sel_array_len >= ARRAY_SIZE(scf_sel_array)) ||
+	    WARN_ON_ONCE(0 - 100000 * weight <= 100000 * scf_sel_totweight) ||
+	    WARN_ON_ONCE(prim >= ARRAY_SIZE(scf_prim_name)))
+		return;
+	scf_sel_totweight += weight;
+	scfsp->scfs_weight = scf_sel_totweight;
+	scfsp->scfs_prim = prim;
+	scfsp->scfs_wait = wait;
+	scf_sel_array_len++;
+}
+
+// Dump out weighting percentages for scf_prim_name[] array.
+static void scf_sel_dump(void)
+{
+	int i;
+	unsigned long oldw = 0;
+	struct scf_selector *scfsp;
+	unsigned long w;
+
+	for (i = 0; i < scf_sel_array_len; i++) {
+		scfsp = &scf_sel_array[i];
+		w = (scfsp->scfs_weight - oldw) * 100000 / scf_sel_totweight;
+		pr_info("%s: %3lu.%03lu %s(%s)\n", __func__, w / 1000, w % 1000,
+			scf_prim_name[scfsp->scfs_prim],
+			scfsp->scfs_wait ? "wait" : "nowait");
+		oldw = scfsp->scfs_weight;
+	}
+}
+
+// Randomly pick a primitive and wait/nowait, based on weightings.
+static struct scf_selector *scf_sel_rand(struct torture_random_state *trsp)
+{
+	int i;
+	unsigned long w = torture_random(trsp) % (scf_sel_totweight + 1);
+
+	for (i = 0; i < scf_sel_array_len; i++)
+		if (scf_sel_array[i].scfs_weight >= w)
+			return &scf_sel_array[i];
+	WARN_ON_ONCE(1);
+	return &scf_sel_array[0];
+}
+
+// Update statistics and occasionally burn up mass quantities of CPU time,
+// if told to do so via scftorture.longwait.  Otherwise, occasionally burn
+// a little bit.
+static void scf_handler(void *scfc_in)
+{
+	int i;
+	int j;
+	unsigned long r = torture_random(this_cpu_ptr(&scf_torture_rand));
+	struct scf_check *scfcp = scfc_in;
+
+	if (likely(scfcp)) {
+		WRITE_ONCE(scfcp->scfc_out, false); // For multiple receivers.
+		if (WARN_ON_ONCE(unlikely(!READ_ONCE(scfcp->scfc_in))))
+			atomic_inc(&n_mb_in_errs);
+	}
+	this_cpu_inc(scf_invoked_count);
+	if (longwait <= 0) {
+		if (!(r & 0xffc0))
+			udelay(r & 0x3f);
+		goto out;
+	}
+	if (r & 0xfff)
+		goto out;
+	r = (r >> 12);
+	if (longwait <= 0) {
+		udelay((r & 0xff) + 1);
+		goto out;
+	}
+	r = r % longwait + 1;
+	for (i = 0; i < r; i++) {
+		for (j = 0; j < 1000; j++) {
+			udelay(1000);
+			cpu_relax();
+		}
+	}
+out:
+	if (unlikely(!scfcp))
+		return;
+	if (scfcp->scfc_wait)
+		WRITE_ONCE(scfcp->scfc_out, true);
+	else
+		kfree(scfcp);
+}
+
+// As above, but check for correct CPU.
+static void scf_handler_1(void *scfc_in)
+{
+	struct scf_check *scfcp = scfc_in;
+
+	if (likely(scfcp) && WARN_ONCE(smp_processor_id() != scfcp->scfc_cpu, "%s: Wanted CPU %d got CPU %d\n", __func__, scfcp->scfc_cpu, smp_processor_id())) {
+		atomic_inc(&n_errs);
+	}
+	scf_handler(scfcp);
+}
+
+// Randomly do an smp_call_function*() invocation.
+static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_random_state *trsp)
+{
+	uintptr_t cpu;
+	int ret = 0;
+	struct scf_check *scfcp = NULL;
+	struct scf_selector *scfsp = scf_sel_rand(trsp);
+
+	if (use_cpus_read_lock)
+		cpus_read_lock();
+	else
+		preempt_disable();
+	if (scfsp->scfs_prim == SCF_PRIM_SINGLE || scfsp->scfs_wait) {
+		scfcp = kmalloc(sizeof(*scfcp), GFP_ATOMIC);
+		if (WARN_ON_ONCE(!scfcp)) {
+			atomic_inc(&n_alloc_errs);
+		} else {
+			scfcp->scfc_cpu = -1;
+			scfcp->scfc_wait = scfsp->scfs_wait;
+			scfcp->scfc_out = false;
+		}
+	}
+	switch (scfsp->scfs_prim) {
+	case SCF_PRIM_SINGLE:
+		cpu = torture_random(trsp) % nr_cpu_ids;
+		if (scfsp->scfs_wait)
+			scfp->n_single_wait++;
+		else
+			scfp->n_single++;
+		if (scfcp) {
+			scfcp->scfc_cpu = cpu;
+			barrier(); // Prevent race-reduction compiler optimizations.
+			scfcp->scfc_in = true;
+		}
+		ret = smp_call_function_single(cpu, scf_handler_1, (void *)scfcp, scfsp->scfs_wait);
+		if (ret) {
+			if (scfsp->scfs_wait)
+				scfp->n_single_wait_ofl++;
+			else
+				scfp->n_single_ofl++;
+			kfree(scfcp);
+			scfcp = NULL;
+		}
+		break;
+	case SCF_PRIM_MANY:
+		if (scfsp->scfs_wait)
+			scfp->n_many_wait++;
+		else
+			scfp->n_many++;
+		if (scfcp) {
+			barrier(); // Prevent race-reduction compiler optimizations.
+			scfcp->scfc_in = true;
+		}
+		smp_call_function_many(cpu_online_mask, scf_handler, scfcp, scfsp->scfs_wait);
+		break;
+	case SCF_PRIM_ALL:
+		if (scfsp->scfs_wait)
+			scfp->n_all_wait++;
+		else
+			scfp->n_all++;
+		if (scfcp) {
+			barrier(); // Prevent race-reduction compiler optimizations.
+			scfcp->scfc_in = true;
+		}
+		smp_call_function(scf_handler, scfcp, scfsp->scfs_wait);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		if (scfcp)
+			scfcp->scfc_out = true;
+	}
+	if (scfcp && scfsp->scfs_wait) {
+		if (WARN_ON_ONCE((num_online_cpus() > 1 || scfsp->scfs_prim == SCF_PRIM_SINGLE) &&
+				 !scfcp->scfc_out))
+			atomic_inc(&n_mb_out_errs); // Leak rather than trash!
+		else
+			kfree(scfcp);
+		barrier(); // Prevent race-reduction compiler optimizations.
+	}
+	if (use_cpus_read_lock)
+		cpus_read_unlock();
+	else
+		preempt_enable();
+	if (!(torture_random(trsp) & 0xfff))
+		schedule_timeout_uninterruptible(1);
+}
+
+// SCF test kthread.  Repeatedly does calls to members of the
+// smp_call_function() family of functions.
+static int scftorture_invoker(void *arg)
+{
+	int cpu;
+	DEFINE_TORTURE_RANDOM(rand);
+	struct scf_statistics *scfp = (struct scf_statistics *)arg;
+	bool was_offline = false;
+
+	VERBOSE_SCFTORTOUT("scftorture_invoker %d: task started", scfp->cpu);
+	cpu = scfp->cpu % nr_cpu_ids;
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
+	set_user_nice(current, MAX_NICE);
+	if (holdoff)
+		schedule_timeout_interruptible(holdoff * HZ);
+
+	VERBOSE_SCFTORTOUT("scftorture_invoker %d: Waiting for all SCF torturers from cpu %d", scfp->cpu, smp_processor_id());
+
+	// Make sure that the CPU is affinitized appropriately during testing.
+	WARN_ON_ONCE(smp_processor_id() != scfp->cpu);
+
+	if (!atomic_dec_return(&n_started))
+		while (atomic_read_acquire(&n_started)) {
+			if (torture_must_stop()) {
+				VERBOSE_SCFTORTOUT("scftorture_invoker %d ended before starting", scfp->cpu);
+				goto end;
+			}
+			schedule_timeout_uninterruptible(1);
+		}
+
+	VERBOSE_SCFTORTOUT("scftorture_invoker %d started", scfp->cpu);
+
+	do {
+		scftorture_invoke_one(scfp, &rand);
+		while (cpu_is_offline(cpu) && !torture_must_stop()) {
+			schedule_timeout_interruptible(HZ / 5);
+			was_offline = true;
+		}
+		if (was_offline) {
+			set_cpus_allowed_ptr(current, cpumask_of(cpu));
+			was_offline = false;
+		}
+		cond_resched();
+	} while (!torture_must_stop());
+
+	VERBOSE_SCFTORTOUT("scftorture_invoker %d ended", scfp->cpu);
+end:
+	torture_kthread_stopping("scftorture_invoker");
+	return 0;
+}
+
+static void
+scftorture_print_module_parms(const char *tag)
+{
+	pr_alert(SCFTORT_FLAG
+		 "--- %s:  verbose=%d holdoff=%d longwait=%d nthreads=%d onoff_holdoff=%d onoff_interval=%d shutdown_secs=%d stat_interval=%d stutter_cpus=%d use_cpus_read_lock=%d, weight_single=%d, weight_single_wait=%d, weight_many=%d, weight_many_wait=%d, weight_all=%d, weight_all_wait=%d\n", tag,
+		 verbose, holdoff, longwait, nthreads, onoff_holdoff, onoff_interval, shutdown, stat_interval, stutter_cpus, use_cpus_read_lock, weight_single, weight_single_wait, weight_many, weight_many_wait, weight_all, weight_all_wait);
+}
+
+static void scf_cleanup_handler(void *unused)
+{
+}
+
+static void scf_torture_cleanup(void)
+{
+	int i;
+
+	if (torture_cleanup_begin())
+		return;
+
+	WRITE_ONCE(scfdone, true);
+	if (nthreads)
+		for (i = 0; i < nthreads; i++)
+			torture_stop_kthread("scftorture_invoker", scf_stats_p[i].task);
+	else
+		goto end;
+	smp_call_function(scf_cleanup_handler, NULL, 0);
+	torture_stop_kthread(scf_torture_stats, scf_torture_stats_task);
+	scf_torture_stats_print();  // -After- the stats thread is stopped!
+	kfree(scf_stats_p);  // -After- the last stats print has completed!
+	scf_stats_p = NULL;
+
+	if (atomic_read(&n_errs) || atomic_read(&n_mb_in_errs) || atomic_read(&n_mb_out_errs))
+		scftorture_print_module_parms("End of test: FAILURE");
+	else if (torture_onoff_failures())
+		scftorture_print_module_parms("End of test: LOCK_HOTPLUG");
+	else
+		scftorture_print_module_parms("End of test: SUCCESS");
+
+end:
+	torture_cleanup_end();
+}
+
+static int __init scf_torture_init(void)
+{
+	long i;
+	int firsterr = 0;
+	unsigned long weight_single1 = weight_single;
+	unsigned long weight_single_wait1 = weight_single_wait;
+	unsigned long weight_many1 = weight_many;
+	unsigned long weight_many_wait1 = weight_many_wait;
+	unsigned long weight_all1 = weight_all;
+	unsigned long weight_all_wait1 = weight_all_wait;
+
+	if (!torture_init_begin(SCFTORT_STRING, verbose))
+		return -EBUSY;
+
+	scftorture_print_module_parms("Start of test");
+
+	if (weight_single == -1 && weight_single_wait == -1 &&
+	    weight_many == -1 && weight_many_wait == -1 &&
+	    weight_all == -1 && weight_all_wait == -1) {
+		weight_single1 = 2 * nr_cpu_ids;
+		weight_single_wait1 = 2 * nr_cpu_ids;
+		weight_many1 = 2;
+		weight_many_wait1 = 2;
+		weight_all1 = 1;
+		weight_all_wait1 = 1;
+	} else {
+		if (weight_single == -1)
+			weight_single1 = 0;
+		if (weight_single_wait == -1)
+			weight_single_wait1 = 0;
+		if (weight_many == -1)
+			weight_many1 = 0;
+		if (weight_many_wait == -1)
+			weight_many_wait1 = 0;
+		if (weight_all == -1)
+			weight_all1 = 0;
+		if (weight_all_wait == -1)
+			weight_all_wait1 = 0;
+	}
+	if (weight_single1 == 0 && weight_single_wait1 == 0 &&
+	    weight_many1 == 0 && weight_many_wait1 == 0 &&
+	    weight_all1 == 0 && weight_all_wait1 == 0) {
+		VERBOSE_SCFTORTOUT_ERRSTRING("all zero weights makes no sense");
+		firsterr = -EINVAL;
+		goto unwind;
+	}
+	scf_sel_add(weight_single1, SCF_PRIM_SINGLE, false);
+	scf_sel_add(weight_single_wait1, SCF_PRIM_SINGLE, true);
+	scf_sel_add(weight_many1, SCF_PRIM_MANY, false);
+	scf_sel_add(weight_many_wait1, SCF_PRIM_MANY, true);
+	scf_sel_add(weight_all1, SCF_PRIM_ALL, false);
+	scf_sel_add(weight_all_wait1, SCF_PRIM_ALL, true);
+	scf_sel_dump();
+
+	if (onoff_interval > 0) {
+		firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval, NULL);
+		if (firsterr)
+			goto unwind;
+	}
+	if (shutdown_secs > 0) {
+		firsterr = torture_shutdown_init(shutdown_secs, scf_torture_cleanup);
+		if (firsterr)
+			goto unwind;
+	}
+
+	// Worker tasks invoking smp_call_function().
+	if (nthreads < 0)
+		nthreads = num_online_cpus();
+	scf_stats_p = kcalloc(nthreads, sizeof(scf_stats_p[0]), GFP_KERNEL);
+	if (!scf_stats_p) {
+		VERBOSE_SCFTORTOUT_ERRSTRING("out of memory");
+		firsterr = -ENOMEM;
+		goto unwind;
+	}
+
+	VERBOSE_SCFTORTOUT("Starting %d smp_call_function() threads\n", nthreads);
+
+	atomic_set(&n_started, nthreads);
+	for (i = 0; i < nthreads; i++) {
+		scf_stats_p[i].cpu = i;
+		firsterr = torture_create_kthread(scftorture_invoker, (void *)&scf_stats_p[i],
+						  scf_stats_p[i].task);
+		if (firsterr)
+			goto unwind;
+	}
+	if (stat_interval > 0) {
+		firsterr = torture_create_kthread(scf_torture_stats, NULL, scf_torture_stats_task);
+		if (firsterr)
+			goto unwind;
+	}
+
+	torture_init_end();
+	return 0;
+
+unwind:
+	torture_init_end();
+	scf_torture_cleanup();
+	return firsterr;
+}
+
+module_init(scf_torture_init);
+module_exit(scf_torture_cleanup);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f0199a4ba1ad..81632cd5e3b7 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -927,7 +927,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 
 		if (ratelimit < 10 &&
 		    (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
-			pr_warn("NOHZ: local_softirq_pending %02x\n",
+			pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n",
 				(unsigned int) local_softirq_pending());
 			ratelimit++;
 		}