Merge branch 'for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Pull the v5.9 RCU bits from Paul E. McKenney:

 - Documentation updates
 - Miscellaneous fixes
 - kfree_rcu updates
 - RCU tasks updates
 - Read-side scalability tests
 - SRCU updates
 - Torture-test updates

Signed-off-by: Ingo Molnar <mingo@kernel.org>

14 files changed, 1206 insertions, 188 deletions

diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 452feae8de20..3cf6132a4bb9 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -61,6 +61,25 @@ config RCU_TORTURE_TEST
 	  Say M if you want the RCU torture tests to build as a module.
 	  Say N if you are unsure.
 
+config RCU_REF_SCALE_TEST
+	tristate "Scalability tests for read-side synchronization (RCU and others)"
+	depends on DEBUG_KERNEL
+	select TORTURE_TEST
+	select SRCU
+	select TASKS_RCU
+	select TASKS_RUDE_RCU
+	select TASKS_TRACE_RCU
+	default n
+	help
+	  This option provides a kernel module that runs performance tests
+	  useful comparing RCU with various read-side synchronization mechanisms.
+	  The kernel module may be built after the fact on the running kernel to be
+	  tested, if desired.
+
+	  Say Y here if you want these performance tests built into the kernel.
+	  Say M if you want to build it as a module instead.
+	  Say N if you are unsure.
+
 config RCU_CPU_STALL_TIMEOUT
 	int "RCU CPU stall timeout in seconds"
 	depends on RCU_STALL_COMMON
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index f91f2c2cf138..95f5117ef8da 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -12,6 +12,7 @@ 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-$(CONFIG_RCU_REF_SCALE_TEST) += refscale.o
 obj-$(CONFIG_TREE_RCU) += tree.o
 obj-$(CONFIG_TINY_RCU) += tiny.o
 obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 9eb39c20082c..ec903d781778 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -69,6 +69,11 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
  *	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
+ * pessimistic due to the per-critical-section interrupt disabling,
+ * test-end checks, and the pair of calls through pointers.
  */
 
 #ifdef MODULE
@@ -309,8 +314,10 @@ static void rcu_perf_wait_shutdown(void)
 }
 
 /*
- * RCU perf reader kthread.  Repeatedly does empty RCU read-side
- * critical section, minimizing update-side interference.
+ * 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.
  */
 static int
 rcu_perf_reader(void *arg)
@@ -576,11 +583,8 @@ static int compute_real(int n)
 static int
 rcu_perf_shutdown(void *arg)
 {
-	do {
-		wait_event(shutdown_wq,
-			   atomic_read(&n_rcu_perf_writer_finished) >=
-			   nrealwriters);
-	} while (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters);
+	wait_event(shutdown_wq,
+		   atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters);
 	smp_mb(); /* Wake before output. */
 	rcu_perf_cleanup();
 	kernel_power_off();
@@ -693,11 +697,8 @@ kfree_perf_cleanup(void)
 static int
 kfree_perf_shutdown(void *arg)
 {
-	do {
-		wait_event(shutdown_wq,
-			   atomic_read(&n_kfree_perf_thread_ended) >=
-			   kfree_nrealthreads);
-	} while (atomic_read(&n_kfree_perf_thread_ended) < kfree_nrealthreads);
+	wait_event(shutdown_wq,
+		   atomic_read(&n_kfree_perf_thread_ended) >= kfree_nrealthreads);
 
 	smp_mb(); /* Wake before output. */
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index efb792e13fca..d0d265304d14 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -7,7 +7,7 @@
  * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
  *	  Josh Triplett <josh@joshtriplett.org>
  *
- * See also:  Documentation/RCU/torture.txt
+ * See also:  Documentation/RCU/torture.rst
  */
 
 #define pr_fmt(fmt) fmt
@@ -109,6 +109,10 @@ torture_param(int, object_debug, 0,
 torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
 torture_param(int, onoff_interval, 0,
 	     "Time between CPU hotplugs (jiffies), 0=disable");
+torture_param(int, read_exit_delay, 13,
+	      "Delay between read-then-exit episodes (s)");
+torture_param(int, read_exit_burst, 16,
+	      "# of read-then-exit bursts per episode, zero to disable");
 torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
 torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
 torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
@@ -146,6 +150,7 @@ static struct task_struct *stall_task;
 static struct task_struct *fwd_prog_task;
 static struct task_struct **barrier_cbs_tasks;
 static struct task_struct *barrier_task;
+static struct task_struct *read_exit_task;
 
 #define RCU_TORTURE_PIPE_LEN 10
 
@@ -177,6 +182,7 @@ static long n_rcu_torture_boosts;
 static atomic_long_t n_rcu_torture_timers;
 static long n_barrier_attempts;
 static long n_barrier_successes; /* did rcu_barrier test succeed? */
+static unsigned long n_read_exits;
 static struct list_head rcu_torture_removed;
 static unsigned long shutdown_jiffies;
 
@@ -1166,6 +1172,7 @@ rcu_torture_writer(void *arg)
 					WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count);
 				}
 	} while (!torture_must_stop());
+	rcu_torture_current = NULL;  // Let stats task know that we are done.
 	/* Reset expediting back to unexpedited. */
 	if (expediting > 0)
 		expediting = -expediting;
@@ -1370,6 +1377,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 	struct rt_read_seg *rtrsp1;
 	unsigned long long ts;
 
+	WARN_ON_ONCE(!rcu_is_watching());
 	newstate = rcutorture_extend_mask(readstate, trsp);
 	rcutorture_one_extend(&readstate, newstate, trsp, rtrsp++);
 	started = cur_ops->get_gp_seq();
@@ -1539,10 +1547,11 @@ rcu_torture_stats_print(void)
 		n_rcu_torture_boosts,
 		atomic_long_read(&n_rcu_torture_timers));
 	torture_onoff_stats();
-	pr_cont("barrier: %ld/%ld:%ld\n",
+	pr_cont("barrier: %ld/%ld:%ld ",
 		data_race(n_barrier_successes),
 		data_race(n_barrier_attempts),
 		data_race(n_rcu_torture_barrier_error));
+	pr_cont("read-exits: %ld\n", data_race(n_read_exits));
 
 	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) ||
@@ -1634,7 +1643,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 "stall_cpu=%d stall_cpu_holdoff=%d stall_cpu_irqsoff=%d "
 		 "stall_cpu_block=%d "
 		 "n_barrier_cbs=%d "
-		 "onoff_interval=%d onoff_holdoff=%d\n",
+		 "onoff_interval=%d onoff_holdoff=%d "
+		 "read_exit_delay=%d read_exit_burst=%d\n",
 		 torture_type, tag, nrealreaders, nfakewriters,
 		 stat_interval, verbose, test_no_idle_hz, shuffle_interval,
 		 stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
@@ -1643,7 +1653,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 stall_cpu, stall_cpu_holdoff, stall_cpu_irqsoff,
 		 stall_cpu_block,
 		 n_barrier_cbs,
-		 onoff_interval, onoff_holdoff);
+		 onoff_interval, onoff_holdoff,
+		 read_exit_delay, read_exit_burst);
 }
 
 static int rcutorture_booster_cleanup(unsigned int cpu)
@@ -2175,7 +2186,7 @@ static void rcu_torture_barrier1cb(void *rcu_void)
 static int rcu_torture_barrier_cbs(void *arg)
 {
 	long myid = (long)arg;
-	bool lastphase = 0;
+	bool lastphase = false;
 	bool newphase;
 	struct rcu_head rcu;
 
@@ -2338,6 +2349,99 @@ static bool rcu_torture_can_boost(void)
 	return true;
 }
 
+static bool read_exit_child_stop;
+static bool read_exit_child_stopped;
+static wait_queue_head_t read_exit_wq;
+
+// Child kthread which just does an rcutorture reader and exits.
+static int rcu_torture_read_exit_child(void *trsp_in)
+{
+	struct torture_random_state *trsp = trsp_in;
+
+	set_user_nice(current, MAX_NICE);
+	// Minimize time between reading and exiting.
+	while (!kthread_should_stop())
+		schedule_timeout_uninterruptible(1);
+	(void)rcu_torture_one_read(trsp);
+	return 0;
+}
+
+// Parent kthread which creates and destroys read-exit child kthreads.
+static int rcu_torture_read_exit(void *unused)
+{
+	int count = 0;
+	bool errexit = false;
+	int i;
+	struct task_struct *tsp;
+	DEFINE_TORTURE_RANDOM(trs);
+
+	// Allocate and initialize.
+	set_user_nice(current, MAX_NICE);
+	VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of test");
+
+	// Each pass through this loop does one read-exit episode.
+	do {
+		if (++count > read_exit_burst) {
+			VERBOSE_TOROUT_STRING("rcu_torture_read_exit: End of episode");
+			rcu_barrier(); // Wait for task_struct free, avoid OOM.
+			for (i = 0; i < read_exit_delay; i++) {
+				schedule_timeout_uninterruptible(HZ);
+				if (READ_ONCE(read_exit_child_stop))
+					break;
+			}
+			if (!READ_ONCE(read_exit_child_stop))
+				VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of episode");
+			count = 0;
+		}
+		if (READ_ONCE(read_exit_child_stop))
+			break;
+		// Spawn child.
+		tsp = kthread_run(rcu_torture_read_exit_child,
+				     &trs, "%s",
+				     "rcu_torture_read_exit_child");
+		if (IS_ERR(tsp)) {
+			VERBOSE_TOROUT_ERRSTRING("out of memory");
+			errexit = true;
+			tsp = NULL;
+			break;
+		}
+		cond_resched();
+		kthread_stop(tsp);
+		n_read_exits ++;
+		stutter_wait("rcu_torture_read_exit");
+	} while (!errexit && !READ_ONCE(read_exit_child_stop));
+
+	// Clean up and exit.
+	smp_store_release(&read_exit_child_stopped, true); // After reaping.
+	smp_mb(); // Store before wakeup.
+	wake_up(&read_exit_wq);
+	while (!torture_must_stop())
+		schedule_timeout_uninterruptible(1);
+	torture_kthread_stopping("rcu_torture_read_exit");
+	return 0;
+}
+
+static int rcu_torture_read_exit_init(void)
+{
+	if (read_exit_burst <= 0)
+		return -EINVAL;
+	init_waitqueue_head(&read_exit_wq);
+	read_exit_child_stop = false;
+	read_exit_child_stopped = false;
+	return torture_create_kthread(rcu_torture_read_exit, NULL,
+				      read_exit_task);
+}
+
+static void rcu_torture_read_exit_cleanup(void)
+{
+	if (!read_exit_task)
+		return;
+	WRITE_ONCE(read_exit_child_stop, true);
+	smp_mb(); // Above write before wait.
+	wait_event(read_exit_wq, smp_load_acquire(&read_exit_child_stopped));
+	torture_stop_kthread(rcutorture_read_exit, read_exit_task);
+}
+
 static enum cpuhp_state rcutor_hp;
 
 static void
@@ -2359,6 +2463,7 @@ rcu_torture_cleanup(void)
 	}
 
 	show_rcu_gp_kthreads();
+	rcu_torture_read_exit_cleanup();
 	rcu_torture_barrier_cleanup();
 	torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task);
 	torture_stop_kthread(rcu_torture_stall, stall_task);
@@ -2370,7 +2475,6 @@ rcu_torture_cleanup(void)
 					     reader_tasks[i]);
 		kfree(reader_tasks);
 	}
-	rcu_torture_current = NULL;
 
 	if (fakewriter_tasks) {
 		for (i = 0; i < nfakewriters; i++) {
@@ -2682,6 +2786,9 @@ rcu_torture_init(void)
 	firsterr = rcu_torture_barrier_init();
 	if (firsterr)
 		goto unwind;
+	firsterr = rcu_torture_read_exit_init();
+	if (firsterr)
+		goto unwind;
 	if (object_debug)
 		rcu_test_debug_objects();
 	torture_init_end();
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
new file mode 100644
index 000000000000..d9291f883b54
--- /dev/null
+++ b/kernel/rcu/refscale.c
@@ -0,0 +1,717 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Scalability test comparing RCU vs other mechanisms
+// for acquiring references on objects.
+//
+// Copyright (C) Google, 2020.
+//
+// Author: Joel Fernandes <joel@joelfernandes.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>
+
+#include "rcu.h"
+
+#define SCALE_FLAG "-ref-scale: "
+
+#define SCALEOUT(s, x...) \
+	pr_alert("%s" SCALE_FLAG s, scale_type, ## x)
+
+#define VERBOSE_SCALEOUT(s, x...) \
+	do { if (verbose) pr_alert("%s" SCALE_FLAG s, scale_type, ## x); } while (0)
+
+#define VERBOSE_SCALEOUT_ERRSTRING(s, x...) \
+	do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! " s, scale_type, ## x); } while (0)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Joel Fernandes (Google) <joel@joelfernandes.org>");
+
+static char *scale_type = "rcu";
+module_param(scale_type, charp, 0444);
+MODULE_PARM_DESC(scale_type, "Type of test (rcu, srcu, refcnt, rwsem, rwlock.");
+
+torture_param(int, verbose, 0, "Enable verbose debugging printk()s");
+
+// Wait until there are multiple CPUs before starting test.
+torture_param(int, holdoff, IS_BUILTIN(CONFIG_RCU_REF_SCALE_TEST) ? 10 : 0,
+	      "Holdoff time before test start (s)");
+// Number of loops per experiment, all readers execute operations concurrently.
+torture_param(long, loops, 10000, "Number of loops per experiment.");
+// Number of readers, with -1 defaulting to about 75% of the CPUs.
+torture_param(int, nreaders, -1, "Number of readers, -1 for 75% of CPUs.");
+// Number of runs.
+torture_param(int, nruns, 30, "Number of experiments to run.");
+// Reader delay in nanoseconds, 0 for no delay.
+torture_param(int, readdelay, 0, "Read-side delay in nanoseconds.");
+
+#ifdef MODULE
+# define REFSCALE_SHUTDOWN 0
+#else
+# define REFSCALE_SHUTDOWN 1
+#endif
+
+torture_param(bool, shutdown, REFSCALE_SHUTDOWN,
+	      "Shutdown at end of scalability tests.");
+
+struct reader_task {
+	struct task_struct *task;
+	int start_reader;
+	wait_queue_head_t wq;
+	u64 last_duration_ns;
+};
+
+static struct task_struct *shutdown_task;
+static wait_queue_head_t shutdown_wq;
+
+static struct task_struct *main_task;
+static wait_queue_head_t main_wq;
+static int shutdown_start;
+
+static struct reader_task *reader_tasks;
+
+// Number of readers that are part of the current experiment.
+static atomic_t nreaders_exp;
+
+// Use to wait for all threads to start.
+static atomic_t n_init;
+static atomic_t n_started;
+static atomic_t n_warmedup;
+static atomic_t n_cooleddown;
+
+// Track which experiment is currently running.
+static int exp_idx;
+
+// Operations vector for selecting different types of tests.
+struct ref_scale_ops {
+	void (*init)(void);
+	void (*cleanup)(void);
+	void (*readsection)(const int nloops);
+	void (*delaysection)(const int nloops, const int udl, const int ndl);
+	const char *name;
+};
+
+static struct ref_scale_ops *cur_ops;
+
+static void un_delay(const int udl, const int ndl)
+{
+	if (udl)
+		udelay(udl);
+	if (ndl)
+		ndelay(ndl);
+}
+
+static void ref_rcu_read_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		rcu_read_lock();
+		rcu_read_unlock();
+	}
+}
+
+static void ref_rcu_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		rcu_read_lock();
+		un_delay(udl, ndl);
+		rcu_read_unlock();
+	}
+}
+
+static void rcu_sync_scale_init(void)
+{
+}
+
+static struct ref_scale_ops rcu_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= ref_rcu_read_section,
+	.delaysection	= ref_rcu_delay_section,
+	.name		= "rcu"
+};
+
+// Definitions for SRCU ref scale testing.
+DEFINE_STATIC_SRCU(srcu_refctl_scale);
+static struct srcu_struct *srcu_ctlp = &srcu_refctl_scale;
+
+static void srcu_ref_scale_read_section(const int nloops)
+{
+	int i;
+	int idx;
+
+	for (i = nloops; i >= 0; i--) {
+		idx = srcu_read_lock(srcu_ctlp);
+		srcu_read_unlock(srcu_ctlp, idx);
+	}
+}
+
+static void srcu_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+	int idx;
+
+	for (i = nloops; i >= 0; i--) {
+		idx = srcu_read_lock(srcu_ctlp);
+		un_delay(udl, ndl);
+		srcu_read_unlock(srcu_ctlp, idx);
+	}
+}
+
+static struct ref_scale_ops srcu_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= srcu_ref_scale_read_section,
+	.delaysection	= srcu_ref_scale_delay_section,
+	.name		= "srcu"
+};
+
+// Definitions for RCU Tasks ref scale testing: Empty read markers.
+// These definitions also work for RCU Rude readers.
+static void rcu_tasks_ref_scale_read_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--)
+		continue;
+}
+
+static void rcu_tasks_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--)
+		un_delay(udl, ndl);
+}
+
+static struct ref_scale_ops rcu_tasks_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= rcu_tasks_ref_scale_read_section,
+	.delaysection	= rcu_tasks_ref_scale_delay_section,
+	.name		= "rcu-tasks"
+};
+
+// Definitions for RCU Tasks Trace ref scale testing.
+static void rcu_trace_ref_scale_read_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		rcu_read_lock_trace();
+		rcu_read_unlock_trace();
+	}
+}
+
+static void rcu_trace_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		rcu_read_lock_trace();
+		un_delay(udl, ndl);
+		rcu_read_unlock_trace();
+	}
+}
+
+static struct ref_scale_ops rcu_trace_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= rcu_trace_ref_scale_read_section,
+	.delaysection	= rcu_trace_ref_scale_delay_section,
+	.name		= "rcu-trace"
+};
+
+// Definitions for reference count
+static atomic_t refcnt;
+
+static void ref_refcnt_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		atomic_inc(&refcnt);
+		atomic_dec(&refcnt);
+	}
+}
+
+static void ref_refcnt_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		atomic_inc(&refcnt);
+		un_delay(udl, ndl);
+		atomic_dec(&refcnt);
+	}
+}
+
+static struct ref_scale_ops refcnt_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= ref_refcnt_section,
+	.delaysection	= ref_refcnt_delay_section,
+	.name		= "refcnt"
+};
+
+// Definitions for rwlock
+static rwlock_t test_rwlock;
+
+static void ref_rwlock_init(void)
+{
+	rwlock_init(&test_rwlock);
+}
+
+static void ref_rwlock_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		read_lock(&test_rwlock);
+		read_unlock(&test_rwlock);
+	}
+}
+
+static void ref_rwlock_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		read_lock(&test_rwlock);
+		un_delay(udl, ndl);
+		read_unlock(&test_rwlock);
+	}
+}
+
+static struct ref_scale_ops rwlock_ops = {
+	.init		= ref_rwlock_init,
+	.readsection	= ref_rwlock_section,
+	.delaysection	= ref_rwlock_delay_section,
+	.name		= "rwlock"
+};
+
+// Definitions for rwsem
+static struct rw_semaphore test_rwsem;
+
+static void ref_rwsem_init(void)
+{
+	init_rwsem(&test_rwsem);
+}
+
+static void ref_rwsem_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		down_read(&test_rwsem);
+		up_read(&test_rwsem);
+	}
+}
+
+static void ref_rwsem_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		down_read(&test_rwsem);
+		un_delay(udl, ndl);
+		up_read(&test_rwsem);
+	}
+}
+
+static struct ref_scale_ops rwsem_ops = {
+	.init		= ref_rwsem_init,
+	.readsection	= ref_rwsem_section,
+	.delaysection	= ref_rwsem_delay_section,
+	.name		= "rwsem"
+};
+
+static void rcu_scale_one_reader(void)
+{
+	if (readdelay <= 0)
+		cur_ops->readsection(loops);
+	else
+		cur_ops->delaysection(loops, readdelay / 1000, readdelay % 1000);
+}
+
+// Reader kthread.  Repeatedly does empty RCU read-side
+// critical section, minimizing update-side interference.
+static int
+ref_scale_reader(void *arg)
+{
+	unsigned long flags;
+	long me = (long)arg;
+	struct reader_task *rt = &(reader_tasks[me]);
+	u64 start;
+	s64 duration;
+
+	VERBOSE_SCALEOUT("ref_scale_reader %ld: task started", me);
+	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+	set_user_nice(current, MAX_NICE);
+	atomic_inc(&n_init);
+	if (holdoff)
+		schedule_timeout_interruptible(holdoff * HZ);
+repeat:
+	VERBOSE_SCALEOUT("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, smp_processor_id());
+
+	// Wait for signal that this reader can start.
+	wait_event(rt->wq, (atomic_read(&nreaders_exp) && smp_load_acquire(&rt->start_reader)) ||
+			   torture_must_stop());
+
+	if (torture_must_stop())
+		goto end;
+
+	// Make sure that the CPU is affinitized appropriately during testing.
+	WARN_ON_ONCE(smp_processor_id() != me);
+
+	WRITE_ONCE(rt->start_reader, 0);
+	if (!atomic_dec_return(&n_started))
+		while (atomic_read_acquire(&n_started))
+			cpu_relax();
+
+	VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d started", me, exp_idx);
+
+
+	// To reduce noise, do an initial cache-warming invocation, check
+	// in, and then keep warming until everyone has checked in.
+	rcu_scale_one_reader();
+	if (!atomic_dec_return(&n_warmedup))
+		while (atomic_read_acquire(&n_warmedup))
+			rcu_scale_one_reader();
+	// Also keep interrupts disabled.  This also has the effect
+	// of preventing entries into slow path for rcu_read_unlock().
+	local_irq_save(flags);
+	start = ktime_get_mono_fast_ns();
+
+	rcu_scale_one_reader();
+
+	duration = ktime_get_mono_fast_ns() - start;
+	local_irq_restore(flags);
+
+	rt->last_duration_ns = WARN_ON_ONCE(duration < 0) ? 0 : duration;
+	// To reduce runtime-skew noise, do maintain-load invocations until
+	// everyone is done.
+	if (!atomic_dec_return(&n_cooleddown))
+		while (atomic_read_acquire(&n_cooleddown))
+			rcu_scale_one_reader();
+
+	if (atomic_dec_and_test(&nreaders_exp))
+		wake_up(&main_wq);
+
+	VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d ended, (readers remaining=%d)",
+			me, exp_idx, atomic_read(&nreaders_exp));
+
+	if (!torture_must_stop())
+		goto repeat;
+end:
+	torture_kthread_stopping("ref_scale_reader");
+	return 0;
+}
+
+static void reset_readers(void)
+{
+	int i;
+	struct reader_task *rt;
+
+	for (i = 0; i < nreaders; i++) {
+		rt = &(reader_tasks[i]);
+
+		rt->last_duration_ns = 0;
+	}
+}
+
+// Print the results of each reader and return the sum of all their durations.
+static u64 process_durations(int n)
+{
+	int i;
+	struct reader_task *rt;
+	char buf1[64];
+	char *buf;
+	u64 sum = 0;
+
+	buf = kmalloc(128 + nreaders * 32, GFP_KERNEL);
+	if (!buf)
+		return 0;
+	buf[0] = 0;
+	sprintf(buf, "Experiment #%d (Format: <THREAD-NUM>:<Total loop time in ns>)",
+		exp_idx);
+
+	for (i = 0; i < n && !torture_must_stop(); i++) {
+		rt = &(reader_tasks[i]);
+		sprintf(buf1, "%d: %llu\t", i, rt->last_duration_ns);
+
+		if (i % 5 == 0)
+			strcat(buf, "\n");
+		strcat(buf, buf1);
+
+		sum += rt->last_duration_ns;
+	}
+	strcat(buf, "\n");
+
+	SCALEOUT("%s\n", buf);
+
+	kfree(buf);
+	return sum;
+}
+
+// The main_func is the main orchestrator, it performs a bunch of
+// experiments.  For every experiment, it orders all the readers
+// involved to start and waits for them to finish the experiment. It
+// then reads their timestamps and starts the next experiment. Each
+// experiment progresses from 1 concurrent reader to N of them at which
+// point all the timestamps are printed.
+static int main_func(void *arg)
+{
+	bool errexit = false;
+	int exp, r;
+	char buf1[64];
+	char *buf;
+	u64 *result_avg;
+
+	set_cpus_allowed_ptr(current, cpumask_of(nreaders % nr_cpu_ids));
+	set_user_nice(current, MAX_NICE);
+
+	VERBOSE_SCALEOUT("main_func task started");
+	result_avg = kzalloc(nruns * sizeof(*result_avg), GFP_KERNEL);
+	buf = kzalloc(64 + nruns * 32, GFP_KERNEL);
+	if (!result_avg || !buf) {
+		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+		errexit = true;
+	}
+	if (holdoff)
+		schedule_timeout_interruptible(holdoff * HZ);
+
+	// Wait for all threads to start.
+	atomic_inc(&n_init);
+	while (atomic_read(&n_init) < nreaders + 1)
+		schedule_timeout_uninterruptible(1);
+
+	// Start exp readers up per experiment
+	for (exp = 0; exp < nruns && !torture_must_stop(); exp++) {
+		if (errexit)
+			break;
+		if (torture_must_stop())
+			goto end;
+
+		reset_readers();
+		atomic_set(&nreaders_exp, nreaders);
+		atomic_set(&n_started, nreaders);
+		atomic_set(&n_warmedup, nreaders);
+		atomic_set(&n_cooleddown, nreaders);
+
+		exp_idx = exp;
+
+		for (r = 0; r < nreaders; r++) {
+			smp_store_release(&reader_tasks[r].start_reader, 1);
+			wake_up(&reader_tasks[r].wq);
+		}
+
+		VERBOSE_SCALEOUT("main_func: experiment started, waiting for %d readers",
+				nreaders);
+
+		wait_event(main_wq,
+			   !atomic_read(&nreaders_exp) || torture_must_stop());
+
+		VERBOSE_SCALEOUT("main_func: experiment ended");
+
+		if (torture_must_stop())
+			goto end;
+
+		result_avg[exp] = div_u64(1000 * process_durations(nreaders), nreaders * loops);
+	}
+
+	// Print the average of all experiments
+	SCALEOUT("END OF TEST. Calculating average duration per loop (nanoseconds)...\n");
+
+	buf[0] = 0;
+	strcat(buf, "\n");
+	strcat(buf, "Runs\tTime(ns)\n");
+
+	for (exp = 0; exp < nruns; exp++) {
+		u64 avg;
+		u32 rem;
+
+		if (errexit)
+			break;
+		avg = div_u64_rem(result_avg[exp], 1000, &rem);
+		sprintf(buf1, "%d\t%llu.%03u\n", exp + 1, avg, rem);
+		strcat(buf, buf1);
+	}
+
+	if (!errexit)
+		SCALEOUT("%s", buf);
+
+	// This will shutdown everything including us.
+	if (shutdown) {
+		shutdown_start = 1;
+		wake_up(&shutdown_wq);
+	}
+
+	// Wait for torture to stop us
+	while (!torture_must_stop())
+		schedule_timeout_uninterruptible(1);
+
+end:
+	torture_kthread_stopping("main_func");
+	kfree(result_avg);
+	kfree(buf);
+	return 0;
+}
+
+static void
+ref_scale_print_module_parms(struct ref_scale_ops *cur_ops, const char *tag)
+{
+	pr_alert("%s" SCALE_FLAG
+		 "--- %s:  verbose=%d shutdown=%d holdoff=%d loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag,
+		 verbose, shutdown, holdoff, loops, nreaders, nruns, readdelay);
+}
+
+static void
+ref_scale_cleanup(void)
+{
+	int i;
+
+	if (torture_cleanup_begin())
+		return;
+
+	if (!cur_ops) {
+		torture_cleanup_end();
+		return;
+	}
+
+	if (reader_tasks) {
+		for (i = 0; i < nreaders; i++)
+			torture_stop_kthread("ref_scale_reader",
+					     reader_tasks[i].task);
+	}
+	kfree(reader_tasks);
+
+	torture_stop_kthread("main_task", main_task);
+	kfree(main_task);
+
+	// Do scale-type-specific cleanup operations.
+	if (cur_ops->cleanup != NULL)
+		cur_ops->cleanup();
+
+	torture_cleanup_end();
+}
+
+// Shutdown kthread.  Just waits to be awakened, then shuts down system.
+static int
+ref_scale_shutdown(void *arg)
+{
+	wait_event(shutdown_wq, shutdown_start);
+
+	smp_mb(); // Wake before output.
+	ref_scale_cleanup();
+	kernel_power_off();
+
+	return -EINVAL;
+}
+
+static int __init
+ref_scale_init(void)
+{
+	long i;
+	int firsterr = 0;
+	static struct ref_scale_ops *scale_ops[] = {
+		&rcu_ops, &srcu_ops, &rcu_trace_ops, &rcu_tasks_ops,
+		&refcnt_ops, &rwlock_ops, &rwsem_ops,
+	};
+
+	if (!torture_init_begin(scale_type, verbose))
+		return -EBUSY;
+
+	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(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_REF_SCALE_TEST));
+		firsterr = -EINVAL;
+		cur_ops = NULL;
+		goto unwind;
+	}
+	if (cur_ops->init)
+		cur_ops->init();
+
+	ref_scale_print_module_parms(cur_ops, "Start of test");
+
+	// Shutdown task
+	if (shutdown) {
+		init_waitqueue_head(&shutdown_wq);
+		firsterr = torture_create_kthread(ref_scale_shutdown, NULL,
+						  shutdown_task);
+		if (firsterr)
+			goto unwind;
+		schedule_timeout_uninterruptible(1);
+	}
+
+	// Reader tasks (default to ~75% of online CPUs).
+	if (nreaders < 0)
+		nreaders = (num_online_cpus() >> 1) + (num_online_cpus() >> 2);
+	reader_tasks = kcalloc(nreaders, sizeof(reader_tasks[0]),
+			       GFP_KERNEL);
+	if (!reader_tasks) {
+		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+		firsterr = -ENOMEM;
+		goto unwind;
+	}
+
+	VERBOSE_SCALEOUT("Starting %d reader threads\n", nreaders);
+
+	for (i = 0; i < nreaders; i++) {
+		firsterr = torture_create_kthread(ref_scale_reader, (void *)i,
+						  reader_tasks[i].task);
+		if (firsterr)
+			goto unwind;
+
+		init_waitqueue_head(&(reader_tasks[i].wq));
+	}
+
+	// Main Task
+	init_waitqueue_head(&main_wq);
+	firsterr = torture_create_kthread(main_func, NULL, main_task);
+	if (firsterr)
+		goto unwind;
+
+	torture_init_end();
+	return 0;
+
+unwind:
+	torture_init_end();
+	ref_scale_cleanup();
+	return firsterr;
+}
+
+module_init(ref_scale_init);
+module_exit(ref_scale_cleanup);
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 6d3ef700fb0e..c100acf332ed 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -766,7 +766,7 @@ static void srcu_flip(struct srcu_struct *ssp)
  * it, if this function was preempted for enough time for the counters
  * to wrap, it really doesn't matter whether or not we expedite the grace
  * period.  The extra overhead of a needlessly expedited grace period is
- * negligible when amoritized over that time period, and the extra latency
+ * negligible when amortized over that time period, and the extra latency
  * of a needlessly non-expedited grace period is similarly negligible.
  */
 static bool srcu_might_be_idle(struct srcu_struct *ssp)
@@ -777,14 +777,15 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp)
 	unsigned long t;
 	unsigned long tlast;
 
+	check_init_srcu_struct(ssp);
 	/* If the local srcu_data structure has callbacks, not idle.  */
-	local_irq_save(flags);
-	sdp = this_cpu_ptr(ssp->sda);
+	sdp = raw_cpu_ptr(ssp->sda);
+	spin_lock_irqsave_rcu_node(sdp, flags);
 	if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
-		local_irq_restore(flags);
+		spin_unlock_irqrestore_rcu_node(sdp, flags);
 		return false; /* Callbacks already present, so not idle. */
 	}
-	local_irq_restore(flags);
+	spin_unlock_irqrestore_rcu_node(sdp, flags);
 
 	/*
 	 * No local callbacks, so probabalistically probe global state.
@@ -864,9 +865,8 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 	}
 	rhp->func = func;
 	idx = srcu_read_lock(ssp);
-	local_irq_save(flags);
-	sdp = this_cpu_ptr(ssp->sda);
-	spin_lock_rcu_node(sdp);
+	sdp = raw_cpu_ptr(ssp->sda);
+	spin_lock_irqsave_rcu_node(sdp, flags);
 	rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&ssp->srcu_gp_seq));
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index ce23f6cc5043..835e2df8590a 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -103,6 +103,7 @@ module_param(rcu_task_stall_timeout, int, 0644);
 #define RTGS_WAIT_READERS	 9
 #define RTGS_INVOKE_CBS		10
 #define RTGS_WAIT_CBS		11
+#ifndef CONFIG_TINY_RCU
 static const char * const rcu_tasks_gp_state_names[] = {
 	"RTGS_INIT",
 	"RTGS_WAIT_WAIT_CBS",
@@ -117,6 +118,7 @@ static const char * const rcu_tasks_gp_state_names[] = {
 	"RTGS_INVOKE_CBS",
 	"RTGS_WAIT_CBS",
 };
+#endif /* #ifndef CONFIG_TINY_RCU */
 
 ////////////////////////////////////////////////////////////////////////
 //
@@ -129,6 +131,7 @@ static void set_tasks_gp_state(struct rcu_tasks *rtp, int newstate)
 	rtp->gp_jiffies = jiffies;
 }
 
+#ifndef CONFIG_TINY_RCU
 /* Return state name. */
 static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
 {
@@ -139,6 +142,7 @@ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
 		return "???";
 	return rcu_tasks_gp_state_names[j];
 }
+#endif /* #ifndef CONFIG_TINY_RCU */
 
 // Enqueue a callback for the specified flavor of Tasks RCU.
 static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
@@ -205,7 +209,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 			if (!rtp->cbs_head) {
 				WARN_ON(signal_pending(current));
 				set_tasks_gp_state(rtp, RTGS_WAIT_WAIT_CBS);
-				schedule_timeout_interruptible(HZ/10);
+				schedule_timeout_idle(HZ/10);
 			}
 			continue;
 		}
@@ -227,7 +231,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 			cond_resched();
 		}
 		/* Paranoid sleep to keep this from entering a tight loop */
-		schedule_timeout_uninterruptible(HZ/10);
+		schedule_timeout_idle(HZ/10);
 
 		set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
 	}
@@ -268,6 +272,7 @@ static void __init rcu_tasks_bootup_oddness(void)
 
 #endif /* #ifndef CONFIG_TINY_RCU */
 
+#ifndef CONFIG_TINY_RCU
 /* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */
 static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
 {
@@ -281,6 +286,7 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
 		".C"[!!data_race(rtp->cbs_head)],
 		s);
 }
+#endif /* #ifndef CONFIG_TINY_RCU */
 
 static void exit_tasks_rcu_finish_trace(struct task_struct *t);
 
@@ -336,7 +342,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 
 		/* Slowly back off waiting for holdouts */
 		set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS);
-		schedule_timeout_interruptible(HZ/fract);
+		schedule_timeout_idle(HZ/fract);
 
 		if (fract > 1)
 			fract--;
@@ -402,7 +408,7 @@ static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop)
 }
 
 /* Processing between scanning taskslist and draining the holdout list. */
-void rcu_tasks_postscan(struct list_head *hop)
+static void rcu_tasks_postscan(struct list_head *hop)
 {
 	/*
 	 * Wait for tasks that are in the process of exiting.  This
@@ -557,10 +563,12 @@ static int __init rcu_spawn_tasks_kthread(void)
 }
 core_initcall(rcu_spawn_tasks_kthread);
 
+#ifndef CONFIG_TINY_RCU
 static void show_rcu_tasks_classic_gp_kthread(void)
 {
 	show_rcu_tasks_generic_gp_kthread(&rcu_tasks, "");
 }
+#endif /* #ifndef CONFIG_TINY_RCU */
 
 /* Do the srcu_read_lock() for the above synchronize_srcu().  */
 void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
@@ -682,10 +690,12 @@ static int __init rcu_spawn_tasks_rude_kthread(void)
 }
 core_initcall(rcu_spawn_tasks_rude_kthread);
 
+#ifndef CONFIG_TINY_RCU
 static void show_rcu_tasks_rude_gp_kthread(void)
 {
 	show_rcu_tasks_generic_gp_kthread(&rcu_tasks_rude, "");
 }
+#endif /* #ifndef CONFIG_TINY_RCU */
 
 #else /* #ifdef CONFIG_TASKS_RUDE_RCU */
 static void show_rcu_tasks_rude_gp_kthread(void) {}
@@ -727,8 +737,8 @@ EXPORT_SYMBOL_GPL(rcu_trace_lock_map);
 
 #ifdef CONFIG_TASKS_TRACE_RCU
 
-atomic_t trc_n_readers_need_end;	// Number of waited-for readers.
-DECLARE_WAIT_QUEUE_HEAD(trc_wait);	// List of holdout tasks.
+static atomic_t trc_n_readers_need_end;		// Number of waited-for readers.
+static DECLARE_WAIT_QUEUE_HEAD(trc_wait);	// List of holdout tasks.
 
 // Record outstanding IPIs to each CPU.  No point in sending two...
 static DEFINE_PER_CPU(bool, trc_ipi_to_cpu);
@@ -835,7 +845,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg)
 	bool ofl = cpu_is_offline(cpu);
 
 	if (task_curr(t)) {
-		WARN_ON_ONCE(ofl & !is_idle_task(t));
+		WARN_ON_ONCE(ofl && !is_idle_task(t));
 
 		// If no chance of heavyweight readers, do it the hard way.
 		if (!ofl && !IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
@@ -1118,11 +1128,10 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks_trace);
  * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period
  *
  * Control will return to the caller some time after a trace rcu-tasks
- * grace period has elapsed, in other words after all currently
- * executing rcu-tasks read-side critical sections have elapsed.  These
- * read-side critical sections are delimited by calls to schedule(),
- * cond_resched_tasks_rcu_qs(), userspace execution, and (in theory,
- * anyway) cond_resched().
+ * grace period has elapsed, in other words after all currently executing
+ * rcu-tasks read-side critical sections have elapsed.  These read-side
+ * critical sections are delimited by calls to rcu_read_lock_trace()
+ * and rcu_read_unlock_trace().
  *
  * This is a very specialized primitive, intended only for a few uses in
  * tracing and other situations requiring manipulation of function preambles
@@ -1164,6 +1173,7 @@ static int __init rcu_spawn_tasks_trace_kthread(void)
 }
 core_initcall(rcu_spawn_tasks_trace_kthread);
 
+#ifndef CONFIG_TINY_RCU
 static void show_rcu_tasks_trace_gp_kthread(void)
 {
 	char buf[64];
@@ -1174,18 +1184,21 @@ static void show_rcu_tasks_trace_gp_kthread(void)
 		data_race(n_heavy_reader_attempts));
 	show_rcu_tasks_generic_gp_kthread(&rcu_tasks_trace, buf);
 }
+#endif /* #ifndef CONFIG_TINY_RCU */
 
 #else /* #ifdef CONFIG_TASKS_TRACE_RCU */
 static void exit_tasks_rcu_finish_trace(struct task_struct *t) { }
 static inline void show_rcu_tasks_trace_gp_kthread(void) {}
 #endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */
 
+#ifndef CONFIG_TINY_RCU
 void show_rcu_tasks_gp_kthreads(void)
 {
 	show_rcu_tasks_classic_gp_kthread();
 	show_rcu_tasks_rude_gp_kthread();
 	show_rcu_tasks_trace_gp_kthread();
 }
+#endif /* #ifndef CONFIG_TINY_RCU */
 
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
 static inline void rcu_tasks_bootup_oddness(void) {}
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index dd572ce7c747..aa897c3f2e92 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -23,6 +23,7 @@
 #include <linux/cpu.h>
 #include <linux/prefetch.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 
 #include "rcu.h"
 
@@ -84,9 +85,9 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head)
 	unsigned long offset = (unsigned long)head->func;
 
 	rcu_lock_acquire(&rcu_callback_map);
-	if (__is_kfree_rcu_offset(offset)) {
-		trace_rcu_invoke_kfree_callback("", head, offset);
-		kfree((void *)head - offset);
+	if (__is_kvfree_rcu_offset(offset)) {
+		trace_rcu_invoke_kvfree_callback("", head, offset);
+		kvfree((void *)head - offset);
 		rcu_lock_release(&rcu_callback_map);
 		return true;
 	}
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 6c6569e0586c..ac7198ed3197 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -57,6 +57,8 @@
 #include <linux/slab.h>
 #include <linux/sched/isolation.h>
 #include <linux/sched/clock.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include "../time/tick-internal.h"
 
 #include "tree.h"
@@ -175,6 +177,15 @@ module_param(gp_init_delay, int, 0444);
 static int gp_cleanup_delay;
 module_param(gp_cleanup_delay, int, 0444);
 
+/*
+ * This rcu parameter is runtime-read-only. It reflects
+ * a minimum allowed number of objects which can be cached
+ * per-CPU. Object size is equal to one page. This value
+ * can be changed at boot time.
+ */
+static int rcu_min_cached_objs = 2;
+module_param(rcu_min_cached_objs, int, 0444);
+
 /* Retrieve RCU kthreads priority for rcutorture */
 int rcu_get_gp_kthreads_prio(void)
 {
@@ -954,7 +965,6 @@ void __rcu_irq_enter_check_tick(void)
 
 /**
  * rcu_nmi_enter - inform RCU of entry to NMI context
- * @irq: Is this call from rcu_irq_enter?
  *
  * If the CPU was idle from RCU's viewpoint, update rdp->dynticks and
  * rdp->dynticks_nmi_nesting to let the RCU grace-period handling know
@@ -990,8 +1000,11 @@ noinstr void rcu_nmi_enter(void)
 		rcu_dynticks_eqs_exit();
 		// ... but is watching here.
 
-		if (!in_nmi())
+		if (!in_nmi()) {
+			instrumentation_begin();
 			rcu_cleanup_after_idle();
+			instrumentation_end();
+		}
 
 		instrumentation_begin();
 		// instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
@@ -1638,7 +1651,7 @@ static void rcu_gp_slow(int delay)
 	if (delay > 0 &&
 	    !(rcu_seq_ctr(rcu_state.gp_seq) %
 	      (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
-		schedule_timeout_uninterruptible(delay);
+		schedule_timeout_idle(delay);
 }
 
 static unsigned long sleep_duration;
@@ -1661,7 +1674,7 @@ static void rcu_gp_torture_wait(void)
 	duration = xchg(&sleep_duration, 0UL);
 	if (duration > 0) {
 		pr_alert("%s: Waiting %lu jiffies\n", __func__, duration);
-		schedule_timeout_uninterruptible(duration);
+		schedule_timeout_idle(duration);
 		pr_alert("%s: Wait complete\n", __func__);
 	}
 }
@@ -2443,6 +2456,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	local_irq_save(flags);
 	rcu_nocb_lock(rdp);
 	count = -rcl.len;
+	rdp->n_cbs_invoked += count;
 	trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
 			    is_idle_task(current), rcu_is_callbacks_kthread());
 
@@ -2726,7 +2740,7 @@ static void rcu_cpu_kthread(unsigned int cpu)
 	}
 	*statusp = RCU_KTHREAD_YIELDING;
 	trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
-	schedule_timeout_interruptible(2);
+	schedule_timeout_idle(2);
 	trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
 	*statusp = RCU_KTHREAD_WAITING;
 }
@@ -2894,8 +2908,8 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 		return; // Enqueued onto ->nocb_bypass, so just leave.
 	// If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
 	rcu_segcblist_enqueue(&rdp->cblist, head);
-	if (__is_kfree_rcu_offset((unsigned long)func))
-		trace_rcu_kfree_callback(rcu_state.name, head,
+	if (__is_kvfree_rcu_offset((unsigned long)func))
+		trace_rcu_kvfree_callback(rcu_state.name, head,
 					 (unsigned long)func,
 					 rcu_segcblist_n_cbs(&rdp->cblist));
 	else
@@ -2957,53 +2971,53 @@ EXPORT_SYMBOL_GPL(call_rcu);
 /* Maximum number of jiffies to wait before draining a batch. */
 #define KFREE_DRAIN_JIFFIES (HZ / 50)
 #define KFREE_N_BATCHES 2
-
-/*
- * This macro defines how many entries the "records" array
- * will contain. It is based on the fact that the size of
- * kfree_rcu_bulk_data structure becomes exactly one page.
- */
-#define KFREE_BULK_MAX_ENTR ((PAGE_SIZE / sizeof(void *)) - 3)
+#define FREE_N_CHANNELS 2
 
 /**
- * struct kfree_rcu_bulk_data - single block to store kfree_rcu() pointers
+ * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers
  * @nr_records: Number of active pointers in the array
- * @records: Array of the kfree_rcu() pointers
  * @next: Next bulk object in the block chain
- * @head_free_debug: For debug, when CONFIG_DEBUG_OBJECTS_RCU_HEAD is set
+ * @records: Array of the kvfree_rcu() pointers
  */
-struct kfree_rcu_bulk_data {
+struct kvfree_rcu_bulk_data {
 	unsigned long nr_records;
-	void *records[KFREE_BULK_MAX_ENTR];
-	struct kfree_rcu_bulk_data *next;
-	struct rcu_head *head_free_debug;
+	struct kvfree_rcu_bulk_data *next;
+	void *records[];
 };
 
+/*
+ * This macro defines how many entries the "records" array
+ * will contain. It is based on the fact that the size of
+ * kvfree_rcu_bulk_data structure becomes exactly one page.
+ */
+#define KVFREE_BULK_MAX_ENTR \
+	((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *))
+
 /**
  * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests
  * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period
  * @head_free: List of kfree_rcu() objects waiting for a grace period
- * @bhead_free: Bulk-List of kfree_rcu() objects waiting for a grace period
+ * @bkvhead_free: Bulk-List of kvfree_rcu() objects waiting for a grace period
  * @krcp: Pointer to @kfree_rcu_cpu structure
  */
 
 struct kfree_rcu_cpu_work {
 	struct rcu_work rcu_work;
 	struct rcu_head *head_free;
-	struct kfree_rcu_bulk_data *bhead_free;
+	struct kvfree_rcu_bulk_data *bkvhead_free[FREE_N_CHANNELS];
 	struct kfree_rcu_cpu *krcp;
 };
 
 /**
  * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period
  * @head: List of kfree_rcu() objects not yet waiting for a grace period
- * @bhead: Bulk-List of kfree_rcu() objects not yet waiting for a grace period
- * @bcached: Keeps at most one object for later reuse when build chain blocks
+ * @bkvhead: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period
  * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period
  * @lock: Synchronize access to this structure
  * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES
  * @monitor_todo: Tracks whether a @monitor_work delayed work is pending
- * @initialized: The @lock and @rcu_work fields have been initialized
+ * @initialized: The @rcu_work fields have been initialized
+ * @count: Number of objects for which GP not started
  *
  * This is a per-CPU structure.  The reason that it is not included in
  * the rcu_data structure is to permit this code to be extracted from
@@ -3012,28 +3026,84 @@ struct kfree_rcu_cpu_work {
  */
 struct kfree_rcu_cpu {
 	struct rcu_head *head;
-	struct kfree_rcu_bulk_data *bhead;
-	struct kfree_rcu_bulk_data *bcached;
+	struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS];
 	struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct delayed_work monitor_work;
 	bool monitor_todo;
 	bool initialized;
-	// Number of objects for which GP not started
 	int count;
+
+	/*
+	 * A simple cache list that contains objects for
+	 * reuse purpose. In order to save some per-cpu
+	 * space the list is singular. Even though it is
+	 * lockless an access has to be protected by the
+	 * per-cpu lock.
+	 */
+	struct llist_head bkvcache;
+	int nr_bkv_objs;
 };
 
-static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc);
+static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = {
+	.lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock),
+};
 
 static __always_inline void
-debug_rcu_head_unqueue_bulk(struct rcu_head *head)
+debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead)
 {
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-	for (; head; head = head->next)
-		debug_rcu_head_unqueue(head);
+	int i;
+
+	for (i = 0; i < bhead->nr_records; i++)
+		debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i]));
 #endif
 }
 
+static inline struct kfree_rcu_cpu *
+krc_this_cpu_lock(unsigned long *flags)
+{
+	struct kfree_rcu_cpu *krcp;
+
+	local_irq_save(*flags);	// For safely calling this_cpu_ptr().
+	krcp = this_cpu_ptr(&krc);
+	raw_spin_lock(&krcp->lock);
+
+	return krcp;
+}
+
+static inline void
+krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
+{
+	raw_spin_unlock(&krcp->lock);
+	local_irq_restore(flags);
+}
+
+static inline struct kvfree_rcu_bulk_data *
+get_cached_bnode(struct kfree_rcu_cpu *krcp)
+{
+	if (!krcp->nr_bkv_objs)
+		return NULL;
+
+	krcp->nr_bkv_objs--;
+	return (struct kvfree_rcu_bulk_data *)
+		llist_del_first(&krcp->bkvcache);
+}
+
+static inline bool
+put_cached_bnode(struct kfree_rcu_cpu *krcp,
+	struct kvfree_rcu_bulk_data *bnode)
+{
+	// Check the limit.
+	if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
+		return false;
+
+	llist_add((struct llist_node *) bnode, &krcp->bkvcache);
+	krcp->nr_bkv_objs++;
+	return true;
+
+}
+
 /*
  * This function is invoked in workqueue context after a grace period.
  * It frees all the objects queued on ->bhead_free or ->head_free.
@@ -3041,38 +3111,63 @@ debug_rcu_head_unqueue_bulk(struct rcu_head *head)
 static void kfree_rcu_work(struct work_struct *work)
 {
 	unsigned long flags;
+	struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS], *bnext;
 	struct rcu_head *head, *next;
-	struct kfree_rcu_bulk_data *bhead, *bnext;
 	struct kfree_rcu_cpu *krcp;
 	struct kfree_rcu_cpu_work *krwp;
+	int i, j;
 
 	krwp = container_of(to_rcu_work(work),
 			    struct kfree_rcu_cpu_work, rcu_work);
 	krcp = krwp->krcp;
-	spin_lock_irqsave(&krcp->lock, flags);
-	head = krwp->head_free;
-	krwp->head_free = NULL;
-	bhead = krwp->bhead_free;
-	krwp->bhead_free = NULL;
-	spin_unlock_irqrestore(&krcp->lock, flags);
-
-	/* "bhead" is now private, so traverse locklessly. */
-	for (; bhead; bhead = bnext) {
-		bnext = bhead->next;
 
-		debug_rcu_head_unqueue_bulk(bhead->head_free_debug);
+	raw_spin_lock_irqsave(&krcp->lock, flags);
+	// Channels 1 and 2.
+	for (i = 0; i < FREE_N_CHANNELS; i++) {
+		bkvhead[i] = krwp->bkvhead_free[i];
+		krwp->bkvhead_free[i] = NULL;
+	}
 
-		rcu_lock_acquire(&rcu_callback_map);
-		trace_rcu_invoke_kfree_bulk_callback(rcu_state.name,
-			bhead->nr_records, bhead->records);
+	// Channel 3.
+	head = krwp->head_free;
+	krwp->head_free = NULL;
+	raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+	// Handle two first channels.
+	for (i = 0; i < FREE_N_CHANNELS; i++) {
+		for (; bkvhead[i]; bkvhead[i] = bnext) {
+			bnext = bkvhead[i]->next;
+			debug_rcu_bhead_unqueue(bkvhead[i]);
+
+			rcu_lock_acquire(&rcu_callback_map);
+			if (i == 0) { // kmalloc() / kfree().
+				trace_rcu_invoke_kfree_bulk_callback(
+					rcu_state.name, bkvhead[i]->nr_records,
+					bkvhead[i]->records);
+
+				kfree_bulk(bkvhead[i]->nr_records,
+					bkvhead[i]->records);
+			} else { // vmalloc() / vfree().
+				for (j = 0; j < bkvhead[i]->nr_records; j++) {
+					trace_rcu_invoke_kvfree_callback(
+						rcu_state.name,
+						bkvhead[i]->records[j], 0);
+
+					vfree(bkvhead[i]->records[j]);
+				}
+			}
+			rcu_lock_release(&rcu_callback_map);
 
-		kfree_bulk(bhead->nr_records, bhead->records);
-		rcu_lock_release(&rcu_callback_map);
+			krcp = krc_this_cpu_lock(&flags);
+			if (put_cached_bnode(krcp, bkvhead[i]))
+				bkvhead[i] = NULL;
+			krc_this_cpu_unlock(krcp, flags);
 
-		if (cmpxchg(&krcp->bcached, NULL, bhead))
-			free_page((unsigned long) bhead);
+			if (bkvhead[i])
+				free_page((unsigned long) bkvhead[i]);
 
-		cond_resched_tasks_rcu_qs();
+			cond_resched_tasks_rcu_qs();
+		}
 	}
 
 	/*
@@ -3082,14 +3177,15 @@ static void kfree_rcu_work(struct work_struct *work)
 	 */
 	for (; head; head = next) {
 		unsigned long offset = (unsigned long)head->func;
+		void *ptr = (void *)head - offset;
 
 		next = head->next;
-		debug_rcu_head_unqueue(head);
+		debug_rcu_head_unqueue((struct rcu_head *)ptr);
 		rcu_lock_acquire(&rcu_callback_map);
-		trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset);
+		trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset);
 
-		if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset)))
-			kfree((void *)head - offset);
+		if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset)))
+			kvfree(ptr);
 
 		rcu_lock_release(&rcu_callback_map);
 		cond_resched_tasks_rcu_qs();
@@ -3105,8 +3201,8 @@ static void kfree_rcu_work(struct work_struct *work)
 static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 {
 	struct kfree_rcu_cpu_work *krwp;
-	bool queued = false;
-	int i;
+	bool repeat = false;
+	int i, j;
 
 	lockdep_assert_held(&krcp->lock);
 
@@ -3114,21 +3210,25 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 		krwp = &(krcp->krw_arr[i]);
 
 		/*
-		 * Try to detach bhead or head and attach it over any
+		 * Try to detach bkvhead or head and attach it over any
 		 * available corresponding free channel. It can be that
 		 * a previous RCU batch is in progress, it means that
 		 * immediately to queue another one is not possible so
 		 * return false to tell caller to retry.
 		 */
-		if ((krcp->bhead && !krwp->bhead_free) ||
+		if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) ||
+			(krcp->bkvhead[1] && !krwp->bkvhead_free[1]) ||
 				(krcp->head && !krwp->head_free)) {
-			/* Channel 1. */
-			if (!krwp->bhead_free) {
-				krwp->bhead_free = krcp->bhead;
-				krcp->bhead = NULL;
+			// Channel 1 corresponds to SLAB ptrs.
+			// Channel 2 corresponds to vmalloc ptrs.
+			for (j = 0; j < FREE_N_CHANNELS; j++) {
+				if (!krwp->bkvhead_free[j]) {
+					krwp->bkvhead_free[j] = krcp->bkvhead[j];
+					krcp->bkvhead[j] = NULL;
+				}
 			}
 
-			/* Channel 2. */
+			// Channel 3 corresponds to emergency path.
 			if (!krwp->head_free) {
 				krwp->head_free = krcp->head;
 				krcp->head = NULL;
@@ -3137,17 +3237,21 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 			WRITE_ONCE(krcp->count, 0);
 
 			/*
-			 * One work is per one batch, so there are two "free channels",
-			 * "bhead_free" and "head_free" the batch can handle. It can be
-			 * that the work is in the pending state when two channels have
-			 * been detached following each other, one by one.
+			 * One work is per one batch, so there are three
+			 * "free channels", the batch can handle. It can
+			 * be that the work is in the pending state when
+			 * channels have been detached following by each
+			 * other.
 			 */
 			queue_rcu_work(system_wq, &krwp->rcu_work);
-			queued = true;
 		}
+
+		// Repeat if any "free" corresponding channel is still busy.
+		if (krcp->bkvhead[0] || krcp->bkvhead[1] || krcp->head)
+			repeat = true;
 	}
 
-	return queued;
+	return !repeat;
 }
 
 static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp,
@@ -3157,14 +3261,14 @@ static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp,
 	krcp->monitor_todo = false;
 	if (queue_kfree_rcu_work(krcp)) {
 		// Success! Our job is done here.
-		spin_unlock_irqrestore(&krcp->lock, flags);
+		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 		return;
 	}
 
 	// Previous RCU batch still in progress, try again later.
 	krcp->monitor_todo = true;
 	schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
-	spin_unlock_irqrestore(&krcp->lock, flags);
+	raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
 
 /*
@@ -3177,32 +3281,50 @@ static void kfree_rcu_monitor(struct work_struct *work)
 	struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu,
 						 monitor_work.work);
 
-	spin_lock_irqsave(&krcp->lock, flags);
+	raw_spin_lock_irqsave(&krcp->lock, flags);
 	if (krcp->monitor_todo)
 		kfree_rcu_drain_unlock(krcp, flags);
 	else
-		spin_unlock_irqrestore(&krcp->lock, flags);
+		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
 
 static inline bool
-kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp,
-	struct rcu_head *head, rcu_callback_t func)
+kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
 {
-	struct kfree_rcu_bulk_data *bnode;
+	struct kvfree_rcu_bulk_data *bnode;
+	int idx;
 
 	if (unlikely(!krcp->initialized))
 		return false;
 
 	lockdep_assert_held(&krcp->lock);
+	idx = !!is_vmalloc_addr(ptr);
 
 	/* Check if a new block is required. */
-	if (!krcp->bhead ||
-			krcp->bhead->nr_records == KFREE_BULK_MAX_ENTR) {
-		bnode = xchg(&krcp->bcached, NULL);
+	if (!krcp->bkvhead[idx] ||
+			krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
+		bnode = get_cached_bnode(krcp);
 		if (!bnode) {
-			WARN_ON_ONCE(sizeof(struct kfree_rcu_bulk_data) > PAGE_SIZE);
+			/*
+			 * To keep this path working on raw non-preemptible
+			 * sections, prevent the optional entry into the
+			 * allocator as it uses sleeping locks. In fact, even
+			 * if the caller of kfree_rcu() is preemptible, this
+			 * path still is not, as krcp->lock is a raw spinlock.
+			 * With additional page pre-allocation in the works,
+			 * hitting this return is going to be much less likely.
+			 */
+			if (IS_ENABLED(CONFIG_PREEMPT_RT))
+				return false;
 
-			bnode = (struct kfree_rcu_bulk_data *)
+			/*
+			 * NOTE: For one argument of kvfree_rcu() we can
+			 * drop the lock and get the page in sleepable
+			 * context. That would allow to maintain an array
+			 * for the CONFIG_PREEMPT_RT as well if no cached
+			 * pages are available.
+			 */
+			bnode = (struct kvfree_rcu_bulk_data *)
 				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
 		}
 
@@ -3212,53 +3334,62 @@ kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp,
 
 		/* Initialize the new block. */
 		bnode->nr_records = 0;
-		bnode->next = krcp->bhead;
-		bnode->head_free_debug = NULL;
+		bnode->next = krcp->bkvhead[idx];
 
 		/* Attach it to the head. */
-		krcp->bhead = bnode;
+		krcp->bkvhead[idx] = bnode;
 	}
 
-#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-	head->func = func;
-	head->next = krcp->bhead->head_free_debug;
-	krcp->bhead->head_free_debug = head;
-#endif
-
 	/* Finally insert. */
-	krcp->bhead->records[krcp->bhead->nr_records++] =
-		(void *) head - (unsigned long) func;
+	krcp->bkvhead[idx]->records
+		[krcp->bkvhead[idx]->nr_records++] = ptr;
 
 	return true;
 }
 
 /*
- * Queue a request for lazy invocation of kfree_bulk()/kfree() after a grace
- * period. Please note there are two paths are maintained, one is the main one
- * that uses kfree_bulk() interface and second one is emergency one, that is
- * used only when the main path can not be maintained temporary, due to memory
- * pressure.
+ * Queue a request for lazy invocation of appropriate free routine after a
+ * grace period. Please note there are three paths are maintained, two are the
+ * main ones that use array of pointers interface and third one is emergency
+ * one, that is used only when the main path can not be maintained temporary,
+ * due to memory pressure.
  *
- * Each kfree_call_rcu() request is added to a batch. The batch will be drained
+ * Each kvfree_call_rcu() request is added to a batch. The batch will be drained
  * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will
  * be free'd in workqueue context. This allows us to: batch requests together to
- * reduce the number of grace periods during heavy kfree_rcu() load.
+ * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load.
  */
-void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
 	unsigned long flags;
 	struct kfree_rcu_cpu *krcp;
+	bool success;
+	void *ptr;
 
-	local_irq_save(flags);	// For safely calling this_cpu_ptr().
-	krcp = this_cpu_ptr(&krc);
-	if (krcp->initialized)
-		spin_lock(&krcp->lock);
+	if (head) {
+		ptr = (void *) head - (unsigned long) func;
+	} else {
+		/*
+		 * Please note there is a limitation for the head-less
+		 * variant, that is why there is a clear rule for such
+		 * objects: it can be used from might_sleep() context
+		 * only. For other places please embed an rcu_head to
+		 * your data.
+		 */
+		might_sleep();
+		ptr = (unsigned long *) func;
+	}
+
+	krcp = krc_this_cpu_lock(&flags);
 
 	// Queue the object but don't yet schedule the batch.
-	if (debug_rcu_head_queue(head)) {
+	if (debug_rcu_head_queue(ptr)) {
 		// Probable double kfree_rcu(), just leak.
 		WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n",
 			  __func__, head);
+
+		// Mark as success and leave.
+		success = true;
 		goto unlock_return;
 	}
 
@@ -3266,10 +3397,16 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 	 * Under high memory pressure GFP_NOWAIT can fail,
 	 * in that case the emergency path is maintained.
 	 */
-	if (unlikely(!kfree_call_rcu_add_ptr_to_bulk(krcp, head, func))) {
+	success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
+	if (!success) {
+		if (head == NULL)
+			// Inline if kvfree_rcu(one_arg) call.
+			goto unlock_return;
+
 		head->func = func;
 		head->next = krcp->head;
 		krcp->head = head;
+		success = true;
 	}
 
 	WRITE_ONCE(krcp->count, krcp->count + 1);
@@ -3282,11 +3419,20 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 	}
 
 unlock_return:
-	if (krcp->initialized)
-		spin_unlock(&krcp->lock);
-	local_irq_restore(flags);
+	krc_this_cpu_unlock(krcp, flags);
+
+	/*
+	 * Inline kvfree() after synchronize_rcu(). We can do
+	 * it from might_sleep() context only, so the current
+	 * CPU can pass the QS state.
+	 */
+	if (!success) {
+		debug_rcu_head_unqueue((struct rcu_head *) ptr);
+		synchronize_rcu();
+		kvfree(ptr);
+	}
 }
-EXPORT_SYMBOL_GPL(kfree_call_rcu);
+EXPORT_SYMBOL_GPL(kvfree_call_rcu);
 
 static unsigned long
 kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
@@ -3315,11 +3461,11 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
 		count = krcp->count;
-		spin_lock_irqsave(&krcp->lock, flags);
+		raw_spin_lock_irqsave(&krcp->lock, flags);
 		if (krcp->monitor_todo)
 			kfree_rcu_drain_unlock(krcp, flags);
 		else
-			spin_unlock_irqrestore(&krcp->lock, flags);
+			raw_spin_unlock_irqrestore(&krcp->lock, flags);
 
 		sc->nr_to_scan -= count;
 		freed += count;
@@ -3328,7 +3474,7 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 			break;
 	}
 
-	return freed;
+	return freed == 0 ? SHRINK_STOP : freed;
 }
 
 static struct shrinker kfree_rcu_shrinker = {
@@ -3346,15 +3492,15 @@ void __init kfree_rcu_scheduler_running(void)
 	for_each_online_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
-		spin_lock_irqsave(&krcp->lock, flags);
+		raw_spin_lock_irqsave(&krcp->lock, flags);
 		if (!krcp->head || krcp->monitor_todo) {
-			spin_unlock_irqrestore(&krcp->lock, flags);
+			raw_spin_unlock_irqrestore(&krcp->lock, flags);
 			continue;
 		}
 		krcp->monitor_todo = true;
 		schedule_delayed_work_on(cpu, &krcp->monitor_work,
 					 KFREE_DRAIN_JIFFIES);
-		spin_unlock_irqrestore(&krcp->lock, flags);
+		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 	}
 }
 
@@ -3842,10 +3988,9 @@ void rcu_cpu_starting(unsigned int cpu)
 {
 	unsigned long flags;
 	unsigned long mask;
-	int nbits;
-	unsigned long oldmask;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
+	bool newcpu;
 
 	if (per_cpu(rcu_cpu_started, cpu))
 		return;
@@ -3857,12 +4002,10 @@ void rcu_cpu_starting(unsigned int cpu)
 	mask = rdp->grpmask;
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask);
-	oldmask = rnp->expmaskinitnext;
+	newcpu = !(rnp->expmaskinitnext & mask);
 	rnp->expmaskinitnext |= mask;
-	oldmask ^= rnp->expmaskinitnext;
-	nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
 	/* Allow lockless access for expedited grace periods. */
-	smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + nbits); /* ^^^ */
+	smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + newcpu); /* ^^^ */
 	ASSERT_EXCLUSIVE_WRITER(rcu_state.ncpus);
 	rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
 	rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq);
@@ -4249,13 +4392,23 @@ static void __init kfree_rcu_batch_init(void)
 
 	for_each_possible_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+		struct kvfree_rcu_bulk_data *bnode;
 
-		spin_lock_init(&krcp->lock);
 		for (i = 0; i < KFREE_N_BATCHES; i++) {
 			INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
 			krcp->krw_arr[i].krcp = krcp;
 		}
 
+		for (i = 0; i < rcu_min_cached_objs; i++) {
+			bnode = (struct kvfree_rcu_bulk_data *)
+				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+
+			if (bnode)
+				put_cached_bnode(krcp, bnode);
+			else
+				pr_err("Failed to preallocate for %d CPU!\n", cpu);
+		}
+
 		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
 		krcp->initialized = true;
 	}
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 43991a40b084..c96ae351688b 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -41,7 +41,7 @@ struct rcu_node {
 	raw_spinlock_t __private lock;	/* Root rcu_node's lock protects */
 					/*  some rcu_state fields as well as */
 					/*  following. */
-	unsigned long gp_seq;	/* Track rsp->rcu_gp_seq. */
+	unsigned long gp_seq;	/* Track rsp->gp_seq. */
 	unsigned long gp_seq_needed; /* Track furthest future GP request. */
 	unsigned long completedqs; /* All QSes done for this node. */
 	unsigned long qsmask;	/* CPUs or groups that need to switch in */
@@ -73,9 +73,9 @@ struct rcu_node {
 	unsigned long ffmask;	/* Fully functional CPUs. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
 				/*  Only one bit will be set in this mask. */
-	int	grplo;		/* lowest-numbered CPU or group here. */
-	int	grphi;		/* highest-numbered CPU or group here. */
-	u8	grpnum;		/* CPU/group number for next level up. */
+	int	grplo;		/* lowest-numbered CPU here. */
+	int	grphi;		/* highest-numbered CPU here. */
+	u8	grpnum;		/* group number for next level up. */
 	u8	level;		/* root is at level 0. */
 	bool	wait_blkd_tasks;/* Necessary to wait for blocked tasks to */
 				/*  exit RCU read-side critical sections */
@@ -149,7 +149,7 @@ union rcu_noqs {
 /* Per-CPU data for read-copy update. */
 struct rcu_data {
 	/* 1) quiescent-state and grace-period handling : */
-	unsigned long	gp_seq;		/* Track rsp->rcu_gp_seq counter. */
+	unsigned long	gp_seq;		/* Track rsp->gp_seq counter. */
 	unsigned long	gp_seq_needed;	/* Track furthest future GP request. */
 	union rcu_noqs	cpu_no_qs;	/* No QSes yet for this CPU. */
 	bool		core_needs_qs;	/* Core waits for quiesc state. */
@@ -171,6 +171,7 @@ struct rcu_data {
 					/* different grace periods. */
 	long		qlen_last_fqs_check;
 					/* qlen at last check for QS forcing */
+	unsigned long	n_cbs_invoked;	/* # callbacks invoked since boot. */
 	unsigned long	n_force_qs_snap;
 					/* did other CPU force QS recently? */
 	long		blimit;		/* Upper limit on a processed batch */
@@ -301,6 +302,8 @@ struct rcu_state {
 	u8	boost ____cacheline_internodealigned_in_smp;
 						/* Subject to priority boost. */
 	unsigned long gp_seq;			/* Grace-period sequence #. */
+	unsigned long gp_max;			/* Maximum GP duration in */
+						/*  jiffies. */
 	struct task_struct *gp_kthread;		/* Task for grace periods. */
 	struct swait_queue_head gp_wq;		/* Where GP task waits. */
 	short gp_flags;				/* Commands for GP task. */
@@ -346,8 +349,6 @@ struct rcu_state {
 						/*  a reluctant CPU. */
 	unsigned long n_force_qs_gpstart;	/* Snapshot of n_force_qs at */
 						/*  GP start. */
-	unsigned long gp_max;			/* Maximum GP duration in */
-						/*  jiffies. */
 	const char *name;			/* Name of structure. */
 	char abbr;				/* Abbreviated name. */
 
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 72952edad1e4..1888c0eb1216 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -403,7 +403,7 @@ retry_ipi:
 			/* Online, so delay for a bit and try again. */
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("selectofl"));
-			schedule_timeout_uninterruptible(1);
+			schedule_timeout_idle(1);
 			goto retry_ipi;
 		}
 		/* CPU really is offline, so we must report its QS. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 352223664ebd..982fc5be5269 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1033,7 +1033,7 @@ static int rcu_boost_kthread(void *arg)
 		if (spincnt > 10) {
 			WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_YIELDING);
 			trace_rcu_utilization(TPS("End boost kthread@rcu_yield"));
-			schedule_timeout_interruptible(2);
+			schedule_timeout_idle(2);
 			trace_rcu_utilization(TPS("Start boost kthread@rcu_yield"));
 			spincnt = 0;
 		}
@@ -2005,7 +2005,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 		/* Polling, so trace if first poll in the series. */
 		if (gotcbs)
 			trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Poll"));
-		schedule_timeout_interruptible(1);
+		schedule_timeout_idle(1);
 	} else if (!needwait_gp) {
 		/* Wait for callbacks to appear. */
 		trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep"));
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 54a6dba0280d..b5d3b4794db4 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -237,14 +237,12 @@ struct rcu_stall_chk_rdr {
  */
 static bool check_slow_task(struct task_struct *t, void *arg)
 {
-	struct rcu_node *rnp;
 	struct rcu_stall_chk_rdr *rscrp = arg;
 
 	if (task_curr(t))
 		return false; // It is running, so decline to inspect it.
 	rscrp->nesting = t->rcu_read_lock_nesting;
 	rscrp->rs = t->rcu_read_unlock_special;
-	rnp = t->rcu_blocked_node;
 	rscrp->on_blkd_list = !list_empty(&t->rcu_node_entry);
 	return true;
 }
@@ -468,7 +466,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 
 	/*
 	 * OK, time to rat on our buddy...
-	 * See Documentation/RCU/stallwarn.txt for info on how to debug
+	 * See Documentation/RCU/stallwarn.rst for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
 	pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
@@ -535,7 +533,7 @@ static void print_cpu_stall(unsigned long gps)
 
 	/*
 	 * OK, time to rat on ourselves...
-	 * See Documentation/RCU/stallwarn.txt for info on how to debug
+	 * See Documentation/RCU/stallwarn.rst for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
 	pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name);
@@ -649,6 +647,7 @@ static void check_cpu_stall(struct rcu_data *rdp)
  */
 void show_rcu_gp_kthreads(void)
 {
+	unsigned long cbs = 0;
 	int cpu;
 	unsigned long j;
 	unsigned long ja;
@@ -690,9 +689,11 @@ void show_rcu_gp_kthreads(void)
 	}
 	for_each_possible_cpu(cpu) {
 		rdp = per_cpu_ptr(&rcu_data, cpu);
+		cbs += data_race(rdp->n_cbs_invoked);
 		if (rcu_segcblist_is_offloaded(&rdp->cblist))
 			show_rcu_nocb_state(rdp);
 	}
+	pr_info("RCU callbacks invoked since boot: %lu\n", cbs);
 	show_rcu_tasks_gp_kthreads();
 }
 EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 84843adfd939..2de49b5d8dd2 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -42,6 +42,7 @@
 #include <linux/kprobes.h>
 #include <linux/slab.h>
 #include <linux/irq_work.h>
+#include <linux/rcupdate_trace.h>
 
 #define CREATE_TRACE_POINTS
 
@@ -207,7 +208,7 @@ void rcu_end_inkernel_boot(void)
 	rcu_unexpedite_gp();
 	if (rcu_normal_after_boot)
 		WRITE_ONCE(rcu_normal, 1);
-	rcu_boot_ended = 1;
+	rcu_boot_ended = true;
 }
 
 /*
@@ -279,6 +280,7 @@ struct lockdep_map rcu_sched_lock_map = {
 };
 EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 
+// Tell lockdep when RCU callbacks are being invoked.
 static struct lock_class_key rcu_callback_key;
 struct lockdep_map rcu_callback_map =
 	STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
@@ -390,13 +392,14 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
 			might_sleep();
 			continue;
 		}
-		init_rcu_head_on_stack(&rs_array[i].head);
-		init_completion(&rs_array[i].completion);
 		for (j = 0; j < i; j++)
 			if (crcu_array[j] == crcu_array[i])
 				break;
-		if (j == i)
+		if (j == i) {
+			init_rcu_head_on_stack(&rs_array[i].head);
+			init_completion(&rs_array[i].completion);
 			(crcu_array[i])(&rs_array[i].head, wakeme_after_rcu);
+		}
 	}
 
 	/* Wait for all callbacks to be invoked. */
@@ -407,9 +410,10 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
 		for (j = 0; j < i; j++)
 			if (crcu_array[j] == crcu_array[i])
 				break;
-		if (j == i)
+		if (j == i) {
 			wait_for_completion(&rs_array[i].completion);
-		destroy_rcu_head_on_stack(&rs_array[i].head);
+			destroy_rcu_head_on_stack(&rs_array[i].head);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(__wait_rcu_gp);