Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:
 "The RCU changes in this cycle were:
   - Expedited grace-period updates
   - kfree_rcu() updates
   - RCU list updates
   - Preemptible RCU updates
   - Torture-test updates
   - Miscellaneous fixes
   - Documentation updates"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (69 commits)
  rcu: Remove unused stop-machine #include
  powerpc: Remove comment about read_barrier_depends()
  .mailmap: Add entries for old paulmck@kernel.org addresses
  srcu: Apply *_ONCE() to ->srcu_last_gp_end
  rcu: Switch force_qs_rnp() to for_each_leaf_node_cpu_mask()
  rcu: Move rcu_{expedited,normal} definitions into rcupdate.h
  rcu: Move gp_state_names[] and gp_state_getname() to tree_stall.h
  rcu: Remove the declaration of call_rcu() in tree.h
  rcu: Fix tracepoint tracking RCU CPU kthread utilization
  rcu: Fix harmless omission of "CONFIG_" from #if condition
  rcu: Avoid tick_dep_set_cpu() misordering
  rcu: Provide wrappers for uses of ->rcu_read_lock_nesting
  rcu: Use READ_ONCE() for ->expmask in rcu_read_unlock_special()
  rcu: Clear ->rcu_read_unlock_special only once
  rcu: Clear .exp_hint only when deferred quiescent state has been reported
  rcu: Rename some instance of CONFIG_PREEMPTION to CONFIG_PREEMPT_RCU
  rcu: Remove kfree_call_rcu_nobatch()
  rcu: Remove kfree_rcu() special casing and lazy-callback handling
  rcu: Add support for debug_objects debugging for kfree_rcu()
  rcu: Add multiple in-flight batches of kfree_rcu() work
  ...

17 files changed, 778 insertions, 385 deletions

diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 7644eda17d62..1cc940fef17c 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -7,7 +7,7 @@ menu "RCU Subsystem"
 
 config TREE_RCU
 	bool
-	default y if !PREEMPTION && SMP
+	default y if SMP
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP system with hundreds or
@@ -17,6 +17,7 @@ config TREE_RCU
 config PREEMPT_RCU
 	bool
 	default y if PREEMPTION
+	select TREE_RCU
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or
@@ -78,7 +79,7 @@ config TASKS_RCU
 	  user-mode execution as quiescent states.
 
 config RCU_STALL_COMMON
-	def_bool ( TREE_RCU || PREEMPT_RCU )
+	def_bool TREE_RCU
 	help
 	  This option enables RCU CPU stall code that is common between
 	  the TINY and TREE variants of RCU.  The purpose is to allow
@@ -86,13 +87,13 @@ config RCU_STALL_COMMON
 	  making these warnings mandatory for the tree variants.
 
 config RCU_NEED_SEGCBLIST
-	def_bool ( TREE_RCU || PREEMPT_RCU || TREE_SRCU )
+	def_bool ( TREE_RCU || TREE_SRCU )
 
 config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
 	range 2 64 if 64BIT
 	range 2 32 if !64BIT
-	depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
+	depends on TREE_RCU && RCU_EXPERT
 	default 64 if 64BIT
 	default 32 if !64BIT
 	help
@@ -112,7 +113,7 @@ config RCU_FANOUT_LEAF
 	int "Tree-based hierarchical RCU leaf-level fanout value"
 	range 2 64 if 64BIT
 	range 2 32 if !64BIT
-	depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
+	depends on TREE_RCU && RCU_EXPERT
 	default 16
 	help
 	  This option controls the leaf-level fanout of hierarchical
@@ -187,7 +188,7 @@ config RCU_BOOST_DELAY
 
 config RCU_NOCB_CPU
 	bool "Offload RCU callback processing from boot-selected CPUs"
-	depends on TREE_RCU || PREEMPT_RCU
+	depends on TREE_RCU
 	depends on RCU_EXPERT || NO_HZ_FULL
 	default n
 	help
@@ -200,8 +201,8 @@ config RCU_NOCB_CPU
 	  specified at boot time by the rcu_nocbs parameter.  For each
 	  such CPU, a kthread ("rcuox/N") will be created to invoke
 	  callbacks, where the "N" is the CPU being offloaded, and where
-	  the "p" for RCU-preempt (PREEMPT kernels) and "s" for RCU-sched
-	  (!PREEMPT kernels).  Nothing prevents this kthread from running
+	  the "p" for RCU-preempt (PREEMPTION kernels) and "s" for RCU-sched
+	  (!PREEMPTION kernels).  Nothing prevents this kthread from running
 	  on the specified CPUs, but (1) the kthreads may be preempted
 	  between each callback, and (2) affinity or cgroups can be used
 	  to force the kthreads to run on whatever set of CPUs is desired.
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 020e8b6a644b..82d5fba48b2f 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -9,6 +9,5 @@ obj-$(CONFIG_TINY_SRCU) += srcutiny.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o
 obj-$(CONFIG_TREE_RCU) += tree.o
-obj-$(CONFIG_PREEMPT_RCU) += tree.o
 obj-$(CONFIG_TINY_RCU) += tiny.o
 obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index ab504fbc76ca..05f936ed167a 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -198,33 +198,6 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
-void kfree(const void *);
-
-/*
- * Reclaim the specified callback, either by invoking it (non-lazy case)
- * or freeing it directly (lazy case).  Return true if lazy, false otherwise.
- */
-static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
-{
-	rcu_callback_t f;
-	unsigned long offset = (unsigned long)head->func;
-
-	rcu_lock_acquire(&rcu_callback_map);
-	if (__is_kfree_rcu_offset(offset)) {
-		trace_rcu_invoke_kfree_callback(rn, head, offset);
-		kfree((void *)head - offset);
-		rcu_lock_release(&rcu_callback_map);
-		return true;
-	} else {
-		trace_rcu_invoke_callback(rn, head);
-		f = head->func;
-		WRITE_ONCE(head->func, (rcu_callback_t)0L);
-		f(head);
-		rcu_lock_release(&rcu_callback_map);
-		return false;
-	}
-}
-
 #ifdef CONFIG_RCU_STALL_COMMON
 
 extern int rcu_cpu_stall_ftrace_dump;
@@ -281,7 +254,7 @@ void rcu_test_sync_prims(void);
  */
 extern void resched_cpu(int cpu);
 
-#if defined(SRCU) || !defined(TINY_RCU)
+#if defined(CONFIG_SRCU) || !defined(CONFIG_TINY_RCU)
 
 #include <linux/rcu_node_tree.h>
 
@@ -418,7 +391,7 @@ do {									\
 #define raw_lockdep_assert_held_rcu_node(p)				\
 	lockdep_assert_held(&ACCESS_PRIVATE(p, lock))
 
-#endif /* #if defined(SRCU) || !defined(TINY_RCU) */
+#endif /* #if defined(CONFIG_SRCU) || !defined(CONFIG_TINY_RCU) */
 
 #ifdef CONFIG_SRCU
 void srcu_init(void);
@@ -454,7 +427,7 @@ enum rcutorture_type {
 	INVALID_RCU_FLAVOR
 };
 
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
+#if defined(CONFIG_TREE_RCU)
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 			    unsigned long *gp_seq);
 void do_trace_rcu_torture_read(const char *rcutorturename,
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index cbc87b804db9..5f4fd3b8777c 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -20,14 +20,10 @@ void rcu_cblist_init(struct rcu_cblist *rclp)
 	rclp->head = NULL;
 	rclp->tail = &rclp->head;
 	rclp->len = 0;
-	rclp->len_lazy = 0;
 }
 
 /*
  * Enqueue an rcu_head structure onto the specified callback list.
- * This function assumes that the callback is non-lazy because it
- * is intended for use by no-CBs CPUs, which do not distinguish
- * between lazy and non-lazy RCU callbacks.
  */
 void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp)
 {
@@ -54,7 +50,6 @@ void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp,
 	else
 		drclp->tail = &drclp->head;
 	drclp->len = srclp->len;
-	drclp->len_lazy = srclp->len_lazy;
 	if (!rhp) {
 		rcu_cblist_init(srclp);
 	} else {
@@ -62,16 +57,12 @@ void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp,
 		srclp->head = rhp;
 		srclp->tail = &rhp->next;
 		WRITE_ONCE(srclp->len, 1);
-		srclp->len_lazy = 0;
 	}
 }
 
 /*
  * Dequeue the oldest rcu_head structure from the specified callback
- * list.  This function assumes that the callback is non-lazy, but
- * the caller can later invoke rcu_cblist_dequeued_lazy() if it
- * finds otherwise (and if it cares about laziness).  This allows
- * different users to have different ways of determining laziness.
+ * list.
  */
 struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp)
 {
@@ -161,7 +152,6 @@ void rcu_segcblist_init(struct rcu_segcblist *rsclp)
 	for (i = 0; i < RCU_CBLIST_NSEGS; i++)
 		rsclp->tails[i] = &rsclp->head;
 	rcu_segcblist_set_len(rsclp, 0);
-	rsclp->len_lazy = 0;
 	rsclp->enabled = 1;
 }
 
@@ -173,7 +163,6 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
 {
 	WARN_ON_ONCE(!rcu_segcblist_empty(rsclp));
 	WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp));
-	WARN_ON_ONCE(rcu_segcblist_n_lazy_cbs(rsclp));
 	rsclp->enabled = 0;
 }
 
@@ -253,11 +242,9 @@ bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp)
  * absolutely not OK for it to ever miss posting a callback.
  */
 void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
-			   struct rcu_head *rhp, bool lazy)
+			   struct rcu_head *rhp)
 {
 	rcu_segcblist_inc_len(rsclp);
-	if (lazy)
-		rsclp->len_lazy++;
 	smp_mb(); /* Ensure counts are updated before callback is enqueued. */
 	rhp->next = NULL;
 	WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rhp);
@@ -275,15 +262,13 @@ void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
  * period.  You have been warned.
  */
 bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
-			   struct rcu_head *rhp, bool lazy)
+			   struct rcu_head *rhp)
 {
 	int i;
 
 	if (rcu_segcblist_n_cbs(rsclp) == 0)
 		return false;
 	rcu_segcblist_inc_len(rsclp);
-	if (lazy)
-		rsclp->len_lazy++;
 	smp_mb(); /* Ensure counts are updated before callback is entrained. */
 	rhp->next = NULL;
 	for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--)
@@ -307,8 +292,6 @@ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
 void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
 					       struct rcu_cblist *rclp)
 {
-	rclp->len_lazy += rsclp->len_lazy;
-	rsclp->len_lazy = 0;
 	rclp->len = rcu_segcblist_xchg_len(rsclp, 0);
 }
 
@@ -361,9 +344,7 @@ void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp,
 void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
 				struct rcu_cblist *rclp)
 {
-	rsclp->len_lazy += rclp->len_lazy;
 	rcu_segcblist_add_len(rsclp, rclp->len);
-	rclp->len_lazy = 0;
 	rclp->len = 0;
 }
 
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 815c2fdd3fcc..5c293afc07b8 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -15,15 +15,6 @@ static inline long rcu_cblist_n_cbs(struct rcu_cblist *rclp)
 	return READ_ONCE(rclp->len);
 }
 
-/*
- * Account for the fact that a previously dequeued callback turned out
- * to be marked as lazy.
- */
-static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp)
-{
-	rclp->len_lazy--;
-}
-
 void rcu_cblist_init(struct rcu_cblist *rclp);
 void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp);
 void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp,
@@ -59,18 +50,6 @@ static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp)
 #endif
 }
 
-/* Return number of lazy callbacks in segmented callback list. */
-static inline long rcu_segcblist_n_lazy_cbs(struct rcu_segcblist *rsclp)
-{
-	return rsclp->len_lazy;
-}
-
-/* Return number of lazy callbacks in segmented callback list. */
-static inline long rcu_segcblist_n_nonlazy_cbs(struct rcu_segcblist *rsclp)
-{
-	return rcu_segcblist_n_cbs(rsclp) - rsclp->len_lazy;
-}
-
 /*
  * Is the specified rcu_segcblist enabled, for example, not corresponding
  * to an offline CPU?
@@ -106,9 +85,9 @@ struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);
 struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp);
 bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp);
 void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
-			   struct rcu_head *rhp, bool lazy);
+			   struct rcu_head *rhp);
 bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
-			   struct rcu_head *rhp, bool lazy);
+			   struct rcu_head *rhp);
 void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
 				 struct rcu_cblist *rclp);
 void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 5f884d560384..da94b89cd531 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -86,6 +86,7 @@ torture_param(bool, shutdown, RCUPERF_SHUTDOWN,
 	      "Shutdown at end of performance 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?");
 
 static char *perf_type = "rcu";
 module_param(perf_type, charp, 0444);
@@ -105,8 +106,8 @@ static atomic_t n_rcu_perf_writer_finished;
 static wait_queue_head_t shutdown_wq;
 static u64 t_rcu_perf_writer_started;
 static u64 t_rcu_perf_writer_finished;
-static unsigned long b_rcu_perf_writer_started;
-static unsigned long b_rcu_perf_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);
 
 #define MAX_MEAS 10000
@@ -378,10 +379,10 @@ rcu_perf_writer(void *arg)
 	if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) {
 		t_rcu_perf_writer_started = t;
 		if (gp_exp) {
-			b_rcu_perf_writer_started =
+			b_rcu_gp_test_started =
 				cur_ops->exp_completed() / 2;
 		} else {
-			b_rcu_perf_writer_started = cur_ops->get_gp_seq();
+			b_rcu_gp_test_started = cur_ops->get_gp_seq();
 		}
 	}
 
@@ -429,10 +430,10 @@ retry:
 				PERFOUT_STRING("Test complete");
 				t_rcu_perf_writer_finished = t;
 				if (gp_exp) {
-					b_rcu_perf_writer_finished =
+					b_rcu_gp_test_finished =
 						cur_ops->exp_completed() / 2;
 				} else {
-					b_rcu_perf_writer_finished =
+					b_rcu_gp_test_finished =
 						cur_ops->get_gp_seq();
 				}
 				if (shutdown) {
@@ -515,8 +516,8 @@ rcu_perf_cleanup(void)
 			 t_rcu_perf_writer_finished -
 			 t_rcu_perf_writer_started,
 			 ngps,
-			 rcuperf_seq_diff(b_rcu_perf_writer_finished,
-					  b_rcu_perf_writer_started));
+			 rcuperf_seq_diff(b_rcu_gp_test_finished,
+					  b_rcu_gp_test_started));
 		for (i = 0; i < nrealwriters; i++) {
 			if (!writer_durations)
 				break;
@@ -584,6 +585,159 @@ rcu_perf_shutdown(void *arg)
 	return -EINVAL;
 }
 
+/*
+ * kfree_rcu() performance 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.
+ */
+
+torture_param(int, kfree_nthreads, -1, "Number of threads running loops of kfree_rcu().");
+torture_param(int, kfree_alloc_num, 8000, "Number of allocations and frees done in an iteration.");
+torture_param(int, kfree_loops, 10, "Number of loops doing kfree_alloc_num allocations and frees.");
+
+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;
+
+struct kfree_obj {
+	char kfree_obj[8];
+	struct rcu_head rh;
+};
+
+static int
+kfree_perf_thread(void *arg)
+{
+	int i, loop = 0;
+	long me = (long)arg;
+	struct kfree_obj *alloc_ptr;
+	u64 start_time, end_time;
+
+	VERBOSE_PERFOUT_STRING("kfree_perf_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 (gp_exp)
+			b_rcu_gp_test_started = cur_ops->exp_completed() / 2;
+		else
+			b_rcu_gp_test_started = cur_ops->get_gp_seq();
+	}
+
+	do {
+		for (i = 0; i < kfree_alloc_num; i++) {
+			alloc_ptr = kmalloc(sizeof(struct kfree_obj), GFP_KERNEL);
+			if (!alloc_ptr)
+				return -ENOMEM;
+
+			kfree_rcu(alloc_ptr, rh);
+		}
+
+		cond_resched();
+	} while (!torture_must_stop() && ++loop < kfree_loops);
+
+	if (atomic_inc_return(&n_kfree_perf_thread_ended) >= kfree_nrealthreads) {
+		end_time = ktime_get_mono_fast_ns();
+
+		if (gp_exp)
+			b_rcu_gp_test_finished = cur_ops->exp_completed() / 2;
+		else
+			b_rcu_gp_test_finished = cur_ops->get_gp_seq();
+
+		pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld\n",
+		       (unsigned long long)(end_time - start_time), kfree_loops,
+		       rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started));
+		if (shutdown) {
+			smp_mb(); /* Assign before wake. */
+			wake_up(&shutdown_wq);
+		}
+	}
+
+	torture_kthread_stopping("kfree_perf_thread");
+	return 0;
+}
+
+static void
+kfree_perf_cleanup(void)
+{
+	int i;
+
+	if (torture_cleanup_begin())
+		return;
+
+	if (kfree_reader_tasks) {
+		for (i = 0; i < kfree_nrealthreads; i++)
+			torture_stop_kthread(kfree_perf_thread,
+					     kfree_reader_tasks[i]);
+		kfree(kfree_reader_tasks);
+	}
+
+	torture_cleanup_end();
+}
+
+/*
+ * shutdown kthread.  Just waits to be awakened, then shuts down system.
+ */
+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);
+
+	smp_mb(); /* Wake before output. */
+
+	kfree_perf_cleanup();
+	kernel_power_off();
+	return -EINVAL;
+}
+
+static int __init
+kfree_perf_init(void)
+{
+	long i;
+	int firsterr = 0;
+
+	kfree_nrealthreads = compute_real(kfree_nthreads);
+	/* Start up the kthreads. */
+	if (shutdown) {
+		init_waitqueue_head(&shutdown_wq);
+		firsterr = torture_create_kthread(kfree_perf_shutdown, NULL,
+						  shutdown_task);
+		if (firsterr)
+			goto unwind;
+		schedule_timeout_uninterruptible(1);
+	}
+
+	kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]),
+			       GFP_KERNEL);
+	if (kfree_reader_tasks == NULL) {
+		firsterr = -ENOMEM;
+		goto unwind;
+	}
+
+	for (i = 0; i < kfree_nrealthreads; i++) {
+		firsterr = torture_create_kthread(kfree_perf_thread, (void *)i,
+						  kfree_reader_tasks[i]);
+		if (firsterr)
+			goto unwind;
+	}
+
+	while (atomic_read(&n_kfree_perf_thread_started) < kfree_nrealthreads)
+		schedule_timeout_uninterruptible(1);
+
+	torture_init_end();
+	return 0;
+
+unwind:
+	torture_init_end();
+	kfree_perf_cleanup();
+	return firsterr;
+}
+
 static int __init
 rcu_perf_init(void)
 {
@@ -616,6 +770,9 @@ rcu_perf_init(void)
 	if (cur_ops->init)
 		cur_ops->init();
 
+	if (kfree_rcu_test)
+		return kfree_perf_init();
+
 	nrealwriters = compute_real(nwriters);
 	nrealreaders = compute_real(nreaders);
 	atomic_set(&n_rcu_perf_reader_started, 0);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index dee043feb71f..1aeecc165b21 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1661,43 +1661,52 @@ static void rcu_torture_fwd_prog_cb(struct rcu_head *rhp)
 struct rcu_fwd_cb {
 	struct rcu_head rh;
 	struct rcu_fwd_cb *rfc_next;
+	struct rcu_fwd *rfc_rfp;
 	int rfc_gps;
 };
-static DEFINE_SPINLOCK(rcu_fwd_lock);
-static struct rcu_fwd_cb *rcu_fwd_cb_head;
-static struct rcu_fwd_cb **rcu_fwd_cb_tail = &rcu_fwd_cb_head;
-static long n_launders_cb;
-static unsigned long rcu_fwd_startat;
-static bool rcu_fwd_emergency_stop;
+
 #define MAX_FWD_CB_JIFFIES	(8 * HZ) /* Maximum CB test duration. */
 #define MIN_FWD_CB_LAUNDERS	3	/* This many CB invocations to count. */
 #define MIN_FWD_CBS_LAUNDERED	100	/* Number of counted CBs. */
 #define FWD_CBS_HIST_DIV	10	/* Histogram buckets/second. */
+#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV))
+
 struct rcu_launder_hist {
 	long n_launders;
 	unsigned long launder_gp_seq;
 };
-#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV))
-static struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST];
-static unsigned long rcu_launder_gp_seq_start;
 
-static void rcu_torture_fwd_cb_hist(void)
+struct rcu_fwd {
+	spinlock_t rcu_fwd_lock;
+	struct rcu_fwd_cb *rcu_fwd_cb_head;
+	struct rcu_fwd_cb **rcu_fwd_cb_tail;
+	long n_launders_cb;
+	unsigned long rcu_fwd_startat;
+	struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST];
+	unsigned long rcu_launder_gp_seq_start;
+};
+
+struct rcu_fwd *rcu_fwds;
+bool rcu_fwd_emergency_stop;
+
+static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
 {
 	unsigned long gps;
 	unsigned long gps_old;
 	int i;
 	int j;
 
-	for (i = ARRAY_SIZE(n_launders_hist) - 1; i > 0; i--)
-		if (n_launders_hist[i].n_launders > 0)
+	for (i = ARRAY_SIZE(rfp->n_launders_hist) - 1; i > 0; i--)
+		if (rfp->n_launders_hist[i].n_launders > 0)
 			break;
 	pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):",
-		 __func__, jiffies - rcu_fwd_startat);
-	gps_old = rcu_launder_gp_seq_start;
+		 __func__, jiffies - rfp->rcu_fwd_startat);
+	gps_old = rfp->rcu_launder_gp_seq_start;
 	for (j = 0; j <= i; j++) {
-		gps = n_launders_hist[j].launder_gp_seq;
+		gps = rfp->n_launders_hist[j].launder_gp_seq;
 		pr_cont(" %ds/%d: %ld:%ld",
-			j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j].n_launders,
+			j + 1, FWD_CBS_HIST_DIV,
+			rfp->n_launders_hist[j].n_launders,
 			rcutorture_seq_diff(gps, gps_old));
 		gps_old = gps;
 	}
@@ -1711,26 +1720,27 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
 	int i;
 	struct rcu_fwd_cb *rfcp = container_of(rhp, struct rcu_fwd_cb, rh);
 	struct rcu_fwd_cb **rfcpp;
+	struct rcu_fwd *rfp = rfcp->rfc_rfp;
 
 	rfcp->rfc_next = NULL;
 	rfcp->rfc_gps++;
-	spin_lock_irqsave(&rcu_fwd_lock, flags);
-	rfcpp = rcu_fwd_cb_tail;
-	rcu_fwd_cb_tail = &rfcp->rfc_next;
+	spin_lock_irqsave(&rfp->rcu_fwd_lock, flags);
+	rfcpp = rfp->rcu_fwd_cb_tail;
+	rfp->rcu_fwd_cb_tail = &rfcp->rfc_next;
 	WRITE_ONCE(*rfcpp, rfcp);
-	WRITE_ONCE(n_launders_cb, n_launders_cb + 1);
-	i = ((jiffies - rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
-	if (i >= ARRAY_SIZE(n_launders_hist))
-		i = ARRAY_SIZE(n_launders_hist) - 1;
-	n_launders_hist[i].n_launders++;
-	n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq();
-	spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+	WRITE_ONCE(rfp->n_launders_cb, rfp->n_launders_cb + 1);
+	i = ((jiffies - rfp->rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
+	if (i >= ARRAY_SIZE(rfp->n_launders_hist))
+		i = ARRAY_SIZE(rfp->n_launders_hist) - 1;
+	rfp->n_launders_hist[i].n_launders++;
+	rfp->n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq();
+	spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags);
 }
 
 // Give the scheduler a chance, even on nohz_full CPUs.
 static void rcu_torture_fwd_prog_cond_resched(unsigned long iter)
 {
-	if (IS_ENABLED(CONFIG_PREEMPT) && IS_ENABLED(CONFIG_NO_HZ_FULL)) {
+	if (IS_ENABLED(CONFIG_PREEMPTION) && IS_ENABLED(CONFIG_NO_HZ_FULL)) {
 		// Real call_rcu() floods hit userspace, so emulate that.
 		if (need_resched() || (iter & 0xfff))
 			schedule();
@@ -1744,23 +1754,23 @@ static void rcu_torture_fwd_prog_cond_resched(unsigned long iter)
  * Free all callbacks on the rcu_fwd_cb_head list, either because the
  * test is over or because we hit an OOM event.
  */
-static unsigned long rcu_torture_fwd_prog_cbfree(void)
+static unsigned long rcu_torture_fwd_prog_cbfree(struct rcu_fwd *rfp)
 {
 	unsigned long flags;
 	unsigned long freed = 0;
 	struct rcu_fwd_cb *rfcp;
 
 	for (;;) {
-		spin_lock_irqsave(&rcu_fwd_lock, flags);
-		rfcp = rcu_fwd_cb_head;
+		spin_lock_irqsave(&rfp->rcu_fwd_lock, flags);
+		rfcp = rfp->rcu_fwd_cb_head;
 		if (!rfcp) {
-			spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+			spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags);
 			break;
 		}
-		rcu_fwd_cb_head = rfcp->rfc_next;
-		if (!rcu_fwd_cb_head)
-			rcu_fwd_cb_tail = &rcu_fwd_cb_head;
-		spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+		rfp->rcu_fwd_cb_head = rfcp->rfc_next;
+		if (!rfp->rcu_fwd_cb_head)
+			rfp->rcu_fwd_cb_tail = &rfp->rcu_fwd_cb_head;
+		spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags);
 		kfree(rfcp);
 		freed++;
 		rcu_torture_fwd_prog_cond_resched(freed);
@@ -1774,7 +1784,8 @@ static unsigned long rcu_torture_fwd_prog_cbfree(void)
 }
 
 /* Carry out need_resched()/cond_resched() forward-progress testing. */
-static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
+static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
+				    int *tested, int *tested_tries)
 {
 	unsigned long cver;
 	unsigned long dur;
@@ -1804,8 +1815,8 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
 	sd = cur_ops->stall_dur() + 1;
 	sd4 = (sd + fwd_progress_div - 1) / fwd_progress_div;
 	dur = sd4 + torture_random(&trs) % (sd - sd4);
-	WRITE_ONCE(rcu_fwd_startat, jiffies);
-	stopat = rcu_fwd_startat + dur;
+	WRITE_ONCE(rfp->rcu_fwd_startat, jiffies);
+	stopat = rfp->rcu_fwd_startat + dur;
 	while (time_before(jiffies, stopat) &&
 	       !shutdown_time_arrived() &&
 	       !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
@@ -1840,7 +1851,7 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
 }
 
 /* Carry out call_rcu() forward-progress testing. */
-static void rcu_torture_fwd_prog_cr(void)
+static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 {
 	unsigned long cver;
 	unsigned long flags;
@@ -1864,23 +1875,23 @@ static void rcu_torture_fwd_prog_cr(void)
 	/* Loop continuously posting RCU callbacks. */
 	WRITE_ONCE(rcu_fwd_cb_nodelay, true);
 	cur_ops->sync(); /* Later readers see above write. */
-	WRITE_ONCE(rcu_fwd_startat, jiffies);
-	stopat = rcu_fwd_startat + MAX_FWD_CB_JIFFIES;
+	WRITE_ONCE(rfp->rcu_fwd_startat, jiffies);
+	stopat = rfp->rcu_fwd_startat + MAX_FWD_CB_JIFFIES;
 	n_launders = 0;
-	n_launders_cb = 0;
+	rfp->n_launders_cb = 0; // Hoist initialization for multi-kthread
 	n_launders_sa = 0;
 	n_max_cbs = 0;
 	n_max_gps = 0;
-	for (i = 0; i < ARRAY_SIZE(n_launders_hist); i++)
-		n_launders_hist[i].n_launders = 0;
+	for (i = 0; i < ARRAY_SIZE(rfp->n_launders_hist); i++)
+		rfp->n_launders_hist[i].n_launders = 0;
 	cver = READ_ONCE(rcu_torture_current_version);
 	gps = cur_ops->get_gp_seq();
-	rcu_launder_gp_seq_start = gps;
+	rfp->rcu_launder_gp_seq_start = gps;
 	tick_dep_set_task(current, TICK_DEP_BIT_RCU);
 	while (time_before(jiffies, stopat) &&
 	       !shutdown_time_arrived() &&
 	       !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
-		rfcp = READ_ONCE(rcu_fwd_cb_head);
+		rfcp = READ_ONCE(rfp->rcu_fwd_cb_head);
 		rfcpn = NULL;
 		if (rfcp)
 			rfcpn = READ_ONCE(rfcp->rfc_next);
@@ -1888,7 +1899,7 @@ static void rcu_torture_fwd_prog_cr(void)
 			if (rfcp->rfc_gps >= MIN_FWD_CB_LAUNDERS &&
 			    ++n_max_gps >= MIN_FWD_CBS_LAUNDERED)
 				break;
-			rcu_fwd_cb_head = rfcpn;
+			rfp->rcu_fwd_cb_head = rfcpn;
 			n_launders++;
 			n_launders_sa++;
 		} else {
@@ -1900,6 +1911,7 @@ static void rcu_torture_fwd_prog_cr(void)
 			n_max_cbs++;
 			n_launders_sa = 0;
 			rfcp->rfc_gps = 0;
+			rfcp->rfc_rfp = rfp;
 		}
 		cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr);
 		rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs);
@@ -1910,22 +1922,22 @@ static void rcu_torture_fwd_prog_cr(void)
 		}
 	}
 	stoppedat = jiffies;
-	n_launders_cb_snap = READ_ONCE(n_launders_cb);
+	n_launders_cb_snap = READ_ONCE(rfp->n_launders_cb);
 	cver = READ_ONCE(rcu_torture_current_version) - cver;
 	gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
 	cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */
-	(void)rcu_torture_fwd_prog_cbfree();
+	(void)rcu_torture_fwd_prog_cbfree(rfp);
 
 	if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop) &&
 	    !shutdown_time_arrived()) {
 		WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED);
 		pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld\n",
 			 __func__,
-			 stoppedat - rcu_fwd_startat, jiffies - stoppedat,
+			 stoppedat - rfp->rcu_fwd_startat, jiffies - stoppedat,
 			 n_launders + n_max_cbs - n_launders_cb_snap,
 			 n_launders, n_launders_sa,
 			 n_max_gps, n_max_cbs, cver, gps);
-		rcu_torture_fwd_cb_hist();
+		rcu_torture_fwd_cb_hist(rfp);
 	}
 	schedule_timeout_uninterruptible(HZ); /* Let CBs drain. */
 	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
@@ -1940,20 +1952,22 @@ static void rcu_torture_fwd_prog_cr(void)
 static int rcutorture_oom_notify(struct notifier_block *self,
 				 unsigned long notused, void *nfreed)
 {
+	struct rcu_fwd *rfp = rcu_fwds;
+
 	WARN(1, "%s invoked upon OOM during forward-progress testing.\n",
 	     __func__);
-	rcu_torture_fwd_cb_hist();
-	rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat)) / 2);
+	rcu_torture_fwd_cb_hist(rfp);
+	rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rfp->rcu_fwd_startat)) / 2);
 	WRITE_ONCE(rcu_fwd_emergency_stop, true);
 	smp_mb(); /* Emergency stop before free and wait to avoid hangs. */
 	pr_info("%s: Freed %lu RCU callbacks.\n",
-		__func__, rcu_torture_fwd_prog_cbfree());
+		__func__, rcu_torture_fwd_prog_cbfree(rfp));
 	rcu_barrier();
 	pr_info("%s: Freed %lu RCU callbacks.\n",
-		__func__, rcu_torture_fwd_prog_cbfree());
+		__func__, rcu_torture_fwd_prog_cbfree(rfp));
 	rcu_barrier();
 	pr_info("%s: Freed %lu RCU callbacks.\n",
-		__func__, rcu_torture_fwd_prog_cbfree());
+		__func__, rcu_torture_fwd_prog_cbfree(rfp));
 	smp_mb(); /* Frees before return to avoid redoing OOM. */
 	(*(unsigned long *)nfreed)++; /* Forward progress CBs freed! */
 	pr_info("%s returning after OOM processing.\n", __func__);
@@ -1967,6 +1981,7 @@ static struct notifier_block rcutorture_oom_nb = {
 /* Carry out grace-period forward-progress testing. */
 static int rcu_torture_fwd_prog(void *args)
 {
+	struct rcu_fwd *rfp = args;
 	int tested = 0;
 	int tested_tries = 0;
 
@@ -1978,8 +1993,8 @@ static int rcu_torture_fwd_prog(void *args)
 		schedule_timeout_interruptible(fwd_progress_holdoff * HZ);
 		WRITE_ONCE(rcu_fwd_emergency_stop, false);
 		register_oom_notifier(&rcutorture_oom_nb);
-		rcu_torture_fwd_prog_nr(&tested, &tested_tries);
-		rcu_torture_fwd_prog_cr();
+		rcu_torture_fwd_prog_nr(rfp, &tested, &tested_tries);
+		rcu_torture_fwd_prog_cr(rfp);
 		unregister_oom_notifier(&rcutorture_oom_nb);
 
 		/* Avoid slow periods, better to test when busy. */
@@ -1995,6 +2010,8 @@ static int rcu_torture_fwd_prog(void *args)
 /* If forward-progress checking is requested and feasible, spawn the thread. */
 static int __init rcu_torture_fwd_prog_init(void)
 {
+	struct rcu_fwd *rfp;
+
 	if (!fwd_progress)
 		return 0; /* Not requested, so don't do it. */
 	if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0 ||
@@ -2013,8 +2030,12 @@ static int __init rcu_torture_fwd_prog_init(void)
 		fwd_progress_holdoff = 1;
 	if (fwd_progress_div <= 0)
 		fwd_progress_div = 4;
-	return torture_create_kthread(rcu_torture_fwd_prog,
-				      NULL, fwd_prog_task);
+	rfp = kzalloc(sizeof(*rfp), GFP_KERNEL);
+	if (!rfp)
+		return -ENOMEM;
+	spin_lock_init(&rfp->rcu_fwd_lock);
+	rfp->rcu_fwd_cb_tail = &rfp->rcu_fwd_cb_head;
+	return torture_create_kthread(rcu_torture_fwd_prog, rfp, fwd_prog_task);
 }
 
 /* Callback function for RCU barrier testing. */
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 44d6606b8325..6208c1dae5c9 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -103,7 +103,7 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
 /*
  * Workqueue handler to drive one grace period and invoke any callbacks
- * that become ready as a result.  Single-CPU and !PREEMPT operation
+ * that become ready as a result.  Single-CPU and !PREEMPTION operation
  * means that we get away with murder on synchronization.  ;-)
  */
 void srcu_drive_gp(struct work_struct *wp)
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 5dffade2d7cd..657e6a7d1c03 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -530,7 +530,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	idx = rcu_seq_state(ssp->srcu_gp_seq);
 	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
 	cbdelay = srcu_get_delay(ssp);
-	ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
+	WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns());
 	rcu_seq_end(&ssp->srcu_gp_seq);
 	gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
 	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, gpseq))
@@ -762,6 +762,7 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp)
 	unsigned long flags;
 	struct srcu_data *sdp;
 	unsigned long t;
+	unsigned long tlast;
 
 	/* If the local srcu_data structure has callbacks, not idle.  */
 	local_irq_save(flags);
@@ -780,9 +781,9 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp)
 
 	/* First, see if enough time has passed since the last GP. */
 	t = ktime_get_mono_fast_ns();
+	tlast = READ_ONCE(ssp->srcu_last_gp_end);
 	if (exp_holdoff == 0 ||
-	    time_in_range_open(t, ssp->srcu_last_gp_end,
-			       ssp->srcu_last_gp_end + exp_holdoff))
+	    time_in_range_open(t, tlast, tlast + exp_holdoff))
 		return false; /* Too soon after last GP. */
 
 	/* Next, check for probable idleness. */
@@ -853,7 +854,7 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 	local_irq_save(flags);
 	sdp = this_cpu_ptr(ssp->sda);
 	spin_lock_rcu_node(sdp);
-	rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false);
+	rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&ssp->srcu_gp_seq));
 	s = rcu_seq_snap(&ssp->srcu_gp_seq);
@@ -1052,7 +1053,7 @@ void srcu_barrier(struct srcu_struct *ssp)
 		sdp->srcu_barrier_head.func = srcu_barrier_cb;
 		debug_rcu_head_queue(&sdp->srcu_barrier_head);
 		if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
-					   &sdp->srcu_barrier_head, 0)) {
+					   &sdp->srcu_barrier_head)) {
 			debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
 			atomic_dec(&ssp->srcu_barrier_cpu_cnt);
 		}
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 477b4eb44af5..dd572ce7c747 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -22,6 +22,7 @@
 #include <linux/time.h>
 #include <linux/cpu.h>
 #include <linux/prefetch.h>
+#include <linux/slab.h>
 
 #include "rcu.h"
 
@@ -73,6 +74,31 @@ void rcu_sched_clock_irq(int user)
 	}
 }
 
+/*
+ * Reclaim the specified callback, either by invoking it for non-kfree cases or
+ * freeing it directly (for kfree). Return true if kfreeing, false otherwise.
+ */
+static inline bool rcu_reclaim_tiny(struct rcu_head *head)
+{
+	rcu_callback_t f;
+	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);
+		rcu_lock_release(&rcu_callback_map);
+		return true;
+	}
+
+	trace_rcu_invoke_callback("", head);
+	f = head->func;
+	WRITE_ONCE(head->func, (rcu_callback_t)0L);
+	f(head);
+	rcu_lock_release(&rcu_callback_map);
+	return false;
+}
+
 /* Invoke the RCU callbacks whose grace period has elapsed.  */
 static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
 {
@@ -100,7 +126,7 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused
 		prefetch(next);
 		debug_rcu_head_unqueue(list);
 		local_bh_disable();
-		__rcu_reclaim("", list);
+		rcu_reclaim_tiny(list);
 		local_bh_enable();
 		list = next;
 	}
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1694a6b57ad8..d91c9156fab2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -43,7 +43,6 @@
 #include <uapi/linux/sched/types.h>
 #include <linux/prefetch.h>
 #include <linux/delay.h>
-#include <linux/stop_machine.h>
 #include <linux/random.h>
 #include <linux/trace_events.h>
 #include <linux/suspend.h>
@@ -55,6 +54,7 @@
 #include <linux/oom.h>
 #include <linux/smpboot.h>
 #include <linux/jiffies.h>
+#include <linux/slab.h>
 #include <linux/sched/isolation.h>
 #include <linux/sched/clock.h>
 #include "../time/tick-internal.h"
@@ -84,7 +84,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
 	.dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
 	.dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR),
 };
-struct rcu_state rcu_state = {
+static struct rcu_state rcu_state = {
 	.level = { &rcu_state.node[0] },
 	.gp_state = RCU_GP_IDLE,
 	.gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT,
@@ -188,7 +188,7 @@ EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio);
  * held, but the bit corresponding to the current CPU will be stable
  * in most contexts.
  */
-unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
+static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
 {
 	return READ_ONCE(rnp->qsmaskinitnext);
 }
@@ -294,7 +294,7 @@ static void rcu_dynticks_eqs_online(void)
  *
  * No ordering, as we are sampling CPU-local information.
  */
-bool rcu_dynticks_curr_cpu_in_eqs(void)
+static bool rcu_dynticks_curr_cpu_in_eqs(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
@@ -305,7 +305,7 @@ bool rcu_dynticks_curr_cpu_in_eqs(void)
  * Snapshot the ->dynticks counter with full ordering so as to allow
  * stable comparison of this counter with past and future snapshots.
  */
-int rcu_dynticks_snap(struct rcu_data *rdp)
+static int rcu_dynticks_snap(struct rcu_data *rdp)
 {
 	int snap = atomic_add_return(0, &rdp->dynticks);
 
@@ -529,16 +529,6 @@ static struct rcu_node *rcu_get_root(void)
 }
 
 /*
- * Convert a ->gp_state value to a character string.
- */
-static const char *gp_state_getname(short gs)
-{
-	if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
-		return "???";
-	return gp_state_names[gs];
-}
-
-/*
  * Send along grace-period-related data for rcutorture diagnostics.
  */
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
@@ -577,7 +567,7 @@ static void rcu_eqs_enter(bool user)
 	}
 
 	lockdep_assert_irqs_disabled();
-	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, rdp->dynticks);
+	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	rdp = this_cpu_ptr(&rcu_data);
 	do_nocb_deferred_wakeup(rdp);
@@ -650,14 +640,15 @@ static __always_inline void rcu_nmi_exit_common(bool irq)
 	 * leave it in non-RCU-idle state.
 	 */
 	if (rdp->dynticks_nmi_nesting != 1) {
-		trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, rdp->dynticks);
+		trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2,
+				  atomic_read(&rdp->dynticks));
 		WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
 			   rdp->dynticks_nmi_nesting - 2);
 		return;
 	}
 
 	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
-	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, rdp->dynticks);
+	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
 
 	if (irq)
@@ -744,7 +735,7 @@ static void rcu_eqs_exit(bool user)
 	rcu_dynticks_task_exit();
 	rcu_dynticks_eqs_exit();
 	rcu_cleanup_after_idle();
-	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, rdp->dynticks);
+	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	WRITE_ONCE(rdp->dynticks_nesting, 1);
 	WARN_ON_ONCE(rdp->dynticks_nmi_nesting);
@@ -800,8 +791,8 @@ void rcu_user_exit(void)
  */
 static __always_inline void rcu_nmi_enter_common(bool irq)
 {
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	long incby = 2;
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
 	/* Complain about underflow. */
 	WARN_ON_ONCE(rdp->dynticks_nmi_nesting < 0);
@@ -828,12 +819,17 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
 	} else if (tick_nohz_full_cpu(rdp->cpu) &&
 		   rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE &&
 		   READ_ONCE(rdp->rcu_urgent_qs) && !rdp->rcu_forced_tick) {
-		rdp->rcu_forced_tick = true;
-		tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
+		raw_spin_lock_rcu_node(rdp->mynode);
+		// Recheck under lock.
+		if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
+			rdp->rcu_forced_tick = true;
+			tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
+		}
+		raw_spin_unlock_rcu_node(rdp->mynode);
 	}
 	trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
 			  rdp->dynticks_nmi_nesting,
-			  rdp->dynticks_nmi_nesting + incby, rdp->dynticks);
+			  rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */
 		   rdp->dynticks_nmi_nesting + incby);
 	barrier();
@@ -898,6 +894,7 @@ void rcu_irq_enter_irqson(void)
  */
 static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
 {
+	raw_lockdep_assert_held_rcu_node(rdp->mynode);
 	WRITE_ONCE(rdp->rcu_urgent_qs, false);
 	WRITE_ONCE(rdp->rcu_need_heavy_qs, false);
 	if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) {
@@ -1934,7 +1931,7 @@ rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 	struct rcu_node *rnp_p;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
-	if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPTION)) ||
+	if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_RCU)) ||
 	    WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) ||
 	    rnp->qsmask != 0) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -2146,7 +2143,6 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	/* If no callbacks are ready, just return. */
 	if (!rcu_segcblist_ready_cbs(&rdp->cblist)) {
 		trace_rcu_batch_start(rcu_state.name,
-				      rcu_segcblist_n_lazy_cbs(&rdp->cblist),
 				      rcu_segcblist_n_cbs(&rdp->cblist), 0);
 		trace_rcu_batch_end(rcu_state.name, 0,
 				    !rcu_segcblist_empty(&rdp->cblist),
@@ -2168,7 +2164,6 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	if (unlikely(bl > 100))
 		tlimit = local_clock() + rcu_resched_ns;
 	trace_rcu_batch_start(rcu_state.name,
-			      rcu_segcblist_n_lazy_cbs(&rdp->cblist),
 			      rcu_segcblist_n_cbs(&rdp->cblist), bl);
 	rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
 	if (offloaded)
@@ -2179,9 +2174,19 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	tick_dep_set_task(current, TICK_DEP_BIT_RCU);
 	rhp = rcu_cblist_dequeue(&rcl);
 	for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+		rcu_callback_t f;
+
 		debug_rcu_head_unqueue(rhp);
-		if (__rcu_reclaim(rcu_state.name, rhp))
-			rcu_cblist_dequeued_lazy(&rcl);
+
+		rcu_lock_acquire(&rcu_callback_map);
+		trace_rcu_invoke_callback(rcu_state.name, rhp);
+
+		f = rhp->func;
+		WRITE_ONCE(rhp->func, (rcu_callback_t)0L);
+		f(rhp);
+
+		rcu_lock_release(&rcu_callback_map);
+
 		/*
 		 * Stop only if limit reached and CPU has something to do.
 		 * Note: The rcl structure counts down from zero.
@@ -2294,7 +2299,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 		mask = 0;
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->qsmask == 0) {
-			if (!IS_ENABLED(CONFIG_PREEMPTION) ||
+			if (!IS_ENABLED(CONFIG_PREEMPT_RCU) ||
 			    rcu_preempt_blocked_readers_cgp(rnp)) {
 				/*
 				 * No point in scanning bits because they
@@ -2308,14 +2313,11 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			continue;
 		}
-		for_each_leaf_node_possible_cpu(rnp, cpu) {
-			unsigned long bit = leaf_node_cpu_bit(rnp, cpu);
-			if ((rnp->qsmask & bit) != 0) {
-				rdp = per_cpu_ptr(&rcu_data, cpu);
-				if (f(rdp)) {
-					mask |= bit;
-					rcu_disable_urgency_upon_qs(rdp);
-				}
+		for_each_leaf_node_cpu_mask(rnp, cpu, rnp->qsmask) {
+			rdp = per_cpu_ptr(&rcu_data, cpu);
+			if (f(rdp)) {
+				mask |= rdp->grpmask;
+				rcu_disable_urgency_upon_qs(rdp);
 			}
 		}
 		if (mask != 0) {
@@ -2474,8 +2476,8 @@ static void rcu_cpu_kthread(unsigned int cpu)
 	char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work);
 	int spincnt;
 
+	trace_rcu_utilization(TPS("Start CPU kthread@rcu_run"));
 	for (spincnt = 0; spincnt < 10; spincnt++) {
-		trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
 		local_bh_disable();
 		*statusp = RCU_KTHREAD_RUNNING;
 		local_irq_disable();
@@ -2583,7 +2585,7 @@ static void rcu_leak_callback(struct rcu_head *rhp)
  * is expected to specify a CPU.
  */
 static void
-__call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy)
+__call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
 	unsigned long flags;
 	struct rcu_data *rdp;
@@ -2618,18 +2620,17 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy)
 		if (rcu_segcblist_empty(&rdp->cblist))
 			rcu_segcblist_init(&rdp->cblist);
 	}
+
 	if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags))
 		return; // Enqueued onto ->nocb_bypass, so just leave.
 	/* If we get here, rcu_nocb_try_bypass() acquired ->nocb_lock. */
-	rcu_segcblist_enqueue(&rdp->cblist, head, lazy);
+	rcu_segcblist_enqueue(&rdp->cblist, head);
 	if (__is_kfree_rcu_offset((unsigned long)func))
 		trace_rcu_kfree_callback(rcu_state.name, head,
 					 (unsigned long)func,
-					 rcu_segcblist_n_lazy_cbs(&rdp->cblist),
 					 rcu_segcblist_n_cbs(&rdp->cblist));
 	else
 		trace_rcu_callback(rcu_state.name, head,
-				   rcu_segcblist_n_lazy_cbs(&rdp->cblist),
 				   rcu_segcblist_n_cbs(&rdp->cblist));
 
 	/* Go handle any RCU core processing required. */
@@ -2679,28 +2680,230 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy)
  */
 void call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
-	__call_rcu(head, func, 0);
+	__call_rcu(head, func);
 }
 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
+
+/**
+ * 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
+ * @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_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
+ * @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
+ *
+ * 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
+ * the RCU files.  Such extraction could allow further optimization of
+ * the interactions with the slab allocators.
+ */
+struct kfree_rcu_cpu {
+	struct rcu_head *head;
+	struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
+	spinlock_t lock;
+	struct delayed_work monitor_work;
+	bool monitor_todo;
+	bool initialized;
+};
+
+static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc);
+
+/*
+ * This function is invoked in workqueue context after a grace period.
+ * It frees all the objects queued on ->head_free.
+ */
+static void kfree_rcu_work(struct work_struct *work)
+{
+	unsigned long flags;
+	struct rcu_head *head, *next;
+	struct kfree_rcu_cpu *krcp;
+	struct kfree_rcu_cpu_work *krwp;
+
+	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;
+	spin_unlock_irqrestore(&krcp->lock, flags);
+
+	// List "head" is now private, so traverse locklessly.
+	for (; head; head = next) {
+		unsigned long offset = (unsigned long)head->func;
+
+		next = head->next;
+		// Potentially optimize with kfree_bulk in future.
+		debug_rcu_head_unqueue(head);
+		rcu_lock_acquire(&rcu_callback_map);
+		trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset);
+
+		if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset))) {
+			/* Could be optimized with kfree_bulk() in future. */
+			kfree((void *)head - offset);
+		}
+
+		rcu_lock_release(&rcu_callback_map);
+		cond_resched_tasks_rcu_qs();
+	}
+}
+
 /*
- * Queue an RCU callback for lazy invocation after a grace period.
- * This will likely be later named something like "call_rcu_lazy()",
- * but this change will require some way of tagging the lazy RCU
- * callbacks in the list of pending callbacks. Until then, this
- * function may only be called from __kfree_rcu().
+ * Schedule the kfree batch RCU work to run in workqueue context after a GP.
+ *
+ * This function is invoked by kfree_rcu_monitor() when the KFREE_DRAIN_JIFFIES
+ * timeout has been reached.
+ */
+static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
+{
+	int i;
+	struct kfree_rcu_cpu_work *krwp = NULL;
+
+	lockdep_assert_held(&krcp->lock);
+	for (i = 0; i < KFREE_N_BATCHES; i++)
+		if (!krcp->krw_arr[i].head_free) {
+			krwp = &(krcp->krw_arr[i]);
+			break;
+		}
+
+	// If a previous RCU batch is in progress, we cannot immediately
+	// queue another one, so return false to tell caller to retry.
+	if (!krwp)
+		return false;
+
+	krwp->head_free = krcp->head;
+	krcp->head = NULL;
+	INIT_RCU_WORK(&krwp->rcu_work, kfree_rcu_work);
+	queue_rcu_work(system_wq, &krwp->rcu_work);
+	return true;
+}
+
+static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp,
+					  unsigned long flags)
+{
+	// Attempt to start a new batch.
+	krcp->monitor_todo = false;
+	if (queue_kfree_rcu_work(krcp)) {
+		// Success! Our job is done here.
+		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);
+}
+
+/*
+ * This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
+ * It invokes kfree_rcu_drain_unlock() to attempt to start another batch.
+ */
+static void kfree_rcu_monitor(struct work_struct *work)
+{
+	unsigned long flags;
+	struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu,
+						 monitor_work.work);
+
+	spin_lock_irqsave(&krcp->lock, flags);
+	if (krcp->monitor_todo)
+		kfree_rcu_drain_unlock(krcp, flags);
+	else
+		spin_unlock_irqrestore(&krcp->lock, flags);
+}
+
+/*
+ * Queue a request for lazy invocation of kfree() after a grace period.
+ *
+ * Each kfree_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 kfree'd in workqueue context. This allows us to:
+ *
+ * 1.	Batch requests together to reduce the number of grace periods during
+ *	heavy kfree_rcu() load.
+ *
+ * 2.	It makes it possible to use kfree_bulk() on a large number of
+ *	kfree_rcu() requests thus reducing cache misses and the per-object
+ *	overhead of kfree().
  */
 void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
-	__call_rcu(head, func, 1);
+	unsigned long flags;
+	struct kfree_rcu_cpu *krcp;
+
+	local_irq_save(flags);	// For safely calling this_cpu_ptr().
+	krcp = this_cpu_ptr(&krc);
+	if (krcp->initialized)
+		spin_lock(&krcp->lock);
+
+	// Queue the object but don't yet schedule the batch.
+	if (debug_rcu_head_queue(head)) {
+		// Probable double kfree_rcu(), just leak.
+		WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n",
+			  __func__, head);
+		goto unlock_return;
+	}
+	head->func = func;
+	head->next = krcp->head;
+	krcp->head = head;
+
+	// Set timer to drain after KFREE_DRAIN_JIFFIES.
+	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
+	    !krcp->monitor_todo) {
+		krcp->monitor_todo = true;
+		schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+	}
+
+unlock_return:
+	if (krcp->initialized)
+		spin_unlock(&krcp->lock);
+	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(kfree_call_rcu);
 
+void __init kfree_rcu_scheduler_running(void)
+{
+	int cpu;
+	unsigned long flags;
+
+	for_each_online_cpu(cpu) {
+		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+		spin_lock_irqsave(&krcp->lock, flags);
+		if (!krcp->head || krcp->monitor_todo) {
+			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);
+	}
+}
+
 /*
  * During early boot, any blocking grace-period wait automatically
- * implies a grace period.  Later on, this is never the case for PREEMPT.
+ * implies a grace period.  Later on, this is never the case for PREEMPTION.
  *
- * Howevr, because a context switch is a grace period for !PREEMPT, any
+ * Howevr, because a context switch is a grace period for !PREEMPTION, any
  * blocking grace-period wait automatically implies a grace period if
  * there is only one CPU online at any point time during execution of
  * either synchronize_rcu() or synchronize_rcu_expedited().  It is OK to
@@ -2896,7 +3099,7 @@ static void rcu_barrier_func(void *unused)
 	debug_rcu_head_queue(&rdp->barrier_head);
 	rcu_nocb_lock(rdp);
 	WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
-	if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) {
+	if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) {
 		atomic_inc(&rcu_state.barrier_cpu_count);
 	} else {
 		debug_rcu_head_unqueue(&rdp->barrier_head);
@@ -3557,12 +3760,29 @@ static void __init rcu_dump_rcu_node_tree(void)
 struct workqueue_struct *rcu_gp_wq;
 struct workqueue_struct *rcu_par_gp_wq;
 
+static void __init kfree_rcu_batch_init(void)
+{
+	int cpu;
+	int i;
+
+	for_each_possible_cpu(cpu) {
+		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+		spin_lock_init(&krcp->lock);
+		for (i = 0; i < KFREE_N_BATCHES; i++)
+			krcp->krw_arr[i].krcp = krcp;
+		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
+		krcp->initialized = true;
+	}
+}
+
 void __init rcu_init(void)
 {
 	int cpu;
 
 	rcu_early_boot_tests();
 
+	kfree_rcu_batch_init();
 	rcu_bootup_announce();
 	rcu_init_geometry();
 	rcu_init_one();
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 055c31781d3a..0c87e4c161c2 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -16,7 +16,6 @@
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
 #include <linux/swait.h>
-#include <linux/stop_machine.h>
 #include <linux/rcu_node_tree.h>
 
 #include "rcu_segcblist.h"
@@ -182,8 +181,8 @@ struct rcu_data {
 	bool rcu_need_heavy_qs;		/* GP old, so heavy quiescent state! */
 	bool rcu_urgent_qs;		/* GP old need light quiescent state. */
 	bool rcu_forced_tick;		/* Forced tick to provide QS. */
+	bool rcu_forced_tick_exp;	/*   ... provide QS to expedited GP. */
 #ifdef CONFIG_RCU_FAST_NO_HZ
-	bool all_lazy;			/* All CPU's CBs lazy at idle start? */
 	unsigned long last_accelerate;	/* Last jiffy CBs were accelerated. */
 	unsigned long last_advance_all;	/* Last jiffy CBs were all advanced. */
 	int tick_nohz_enabled_snap;	/* Previously seen value from sysfs. */
@@ -368,18 +367,6 @@ struct rcu_state {
 #define RCU_GP_CLEANUP   7	/* Grace-period cleanup started. */
 #define RCU_GP_CLEANED   8	/* Grace-period cleanup complete. */
 
-static const char * const gp_state_names[] = {
-	"RCU_GP_IDLE",
-	"RCU_GP_WAIT_GPS",
-	"RCU_GP_DONE_GPS",
-	"RCU_GP_ONOFF",
-	"RCU_GP_INIT",
-	"RCU_GP_WAIT_FQS",
-	"RCU_GP_DOING_FQS",
-	"RCU_GP_CLEANUP",
-	"RCU_GP_CLEANED",
-};
-
 /*
  * In order to export the rcu_state name to the tracing tools, it
  * needs to be added in the __tracepoint_string section.
@@ -403,8 +390,6 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
 #define RCU_NAME rcu_name
 #endif /* #else #ifdef CONFIG_TRACING */
 
-int rcu_dynticks_snap(struct rcu_data *rdp);
-
 /* Forward declarations for tree_plugin.h */
 static void rcu_bootup_announce(void);
 static void rcu_qs(void);
@@ -415,7 +400,6 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static int rcu_print_task_exp_stall(struct rcu_node *rnp);
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 static void rcu_flavor_sched_clock_irq(int user);
-void call_rcu(struct rcu_head *head, rcu_callback_t func);
 static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index d632cd019597..6935a9e2b094 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -21,7 +21,7 @@ static void rcu_exp_gp_seq_start(void)
 }
 
 /*
- * Return then value that expedited-grace-period counter will have
+ * Return the value that the expedited-grace-period counter will have
  * at the end of the current grace period.
  */
 static __maybe_unused unsigned long rcu_exp_gp_seq_endval(void)
@@ -39,7 +39,9 @@ static void rcu_exp_gp_seq_end(void)
 }
 
 /*
- * Take a snapshot of the expedited-grace-period counter.
+ * Take a snapshot of the expedited-grace-period counter, which is the
+ * earliest value that will indicate that a full grace period has
+ * elapsed since the current time.
  */
 static unsigned long rcu_exp_gp_seq_snap(void)
 {
@@ -134,7 +136,7 @@ static void __maybe_unused sync_exp_reset_tree(void)
 	rcu_for_each_node_breadth_first(rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		WARN_ON_ONCE(rnp->expmask);
-		rnp->expmask = rnp->expmaskinit;
+		WRITE_ONCE(rnp->expmask, rnp->expmaskinit);
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 }
@@ -143,31 +145,26 @@ static void __maybe_unused sync_exp_reset_tree(void)
  * Return non-zero if there is no RCU expedited grace period in progress
  * for the specified rcu_node structure, in other words, if all CPUs and
  * tasks covered by the specified rcu_node structure have done their bit
- * for the current expedited grace period.  Works only for preemptible
- * RCU -- other RCU implementation use other means.
- *
- * Caller must hold the specificed rcu_node structure's ->lock
+ * for the current expedited grace period.
  */
-static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp)
+static bool sync_rcu_exp_done(struct rcu_node *rnp)
 {
 	raw_lockdep_assert_held_rcu_node(rnp);
-
 	return rnp->exp_tasks == NULL &&
 	       READ_ONCE(rnp->expmask) == 0;
 }
 
 /*
- * Like sync_rcu_preempt_exp_done(), but this function assumes the caller
- * doesn't hold the rcu_node's ->lock, and will acquire and release the lock
- * itself
+ * Like sync_rcu_exp_done(), but where the caller does not hold the
+ * rcu_node's ->lock.
  */
-static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp)
+static bool sync_rcu_exp_done_unlocked(struct rcu_node *rnp)
 {
 	unsigned long flags;
 	bool ret;
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	ret = sync_rcu_preempt_exp_done(rnp);
+	ret = sync_rcu_exp_done(rnp);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 	return ret;
@@ -181,8 +178,6 @@ static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp)
  * which the task was queued or to one of that rcu_node structure's ancestors,
  * recursively up the tree.  (Calm down, calm down, we do the recursion
  * iteratively!)
- *
- * Caller must hold the specified rcu_node structure's ->lock.
  */
 static void __rcu_report_exp_rnp(struct rcu_node *rnp,
 				 bool wake, unsigned long flags)
@@ -190,8 +185,9 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp,
 {
 	unsigned long mask;
 
+	raw_lockdep_assert_held_rcu_node(rnp);
 	for (;;) {
-		if (!sync_rcu_preempt_exp_done(rnp)) {
+		if (!sync_rcu_exp_done(rnp)) {
 			if (!rnp->expmask)
 				rcu_initiate_boost(rnp, flags);
 			else
@@ -211,7 +207,7 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp,
 		rnp = rnp->parent;
 		raw_spin_lock_rcu_node(rnp); /* irqs already disabled */
 		WARN_ON_ONCE(!(rnp->expmask & mask));
-		rnp->expmask &= ~mask;
+		WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask);
 	}
 }
 
@@ -234,14 +230,23 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_node *rnp, bool wake)
 static void rcu_report_exp_cpu_mult(struct rcu_node *rnp,
 				    unsigned long mask, bool wake)
 {
+	int cpu;
 	unsigned long flags;
+	struct rcu_data *rdp;
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if (!(rnp->expmask & mask)) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
 	}
-	rnp->expmask &= ~mask;
+	WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask);
+	for_each_leaf_node_cpu_mask(rnp, cpu, mask) {
+		rdp = per_cpu_ptr(&rcu_data, cpu);
+		if (!IS_ENABLED(CONFIG_NO_HZ_FULL) || !rdp->rcu_forced_tick_exp)
+			continue;
+		rdp->rcu_forced_tick_exp = false;
+		tick_dep_clear_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+	}
 	__rcu_report_exp_rnp(rnp, wake, flags); /* Releases rnp->lock. */
 }
 
@@ -345,8 +350,8 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 	/* Each pass checks a CPU for identity, offline, and idle. */
 	mask_ofl_test = 0;
 	for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
-		unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
 		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+		unsigned long mask = rdp->grpmask;
 		int snap;
 
 		if (raw_smp_processor_id() == cpu ||
@@ -372,12 +377,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 	/* IPI the remaining CPUs for expedited quiescent state. */
-	for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
-		unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
+	for_each_leaf_node_cpu_mask(rnp, cpu, mask_ofl_ipi) {
 		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+		unsigned long mask = rdp->grpmask;
 
-		if (!(mask_ofl_ipi & mask))
-			continue;
 retry_ipi:
 		if (rcu_dynticks_in_eqs_since(rdp, rdp->exp_dynticks_snap)) {
 			mask_ofl_test |= mask;
@@ -389,10 +392,10 @@ retry_ipi:
 		}
 		ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
 		put_cpu();
-		if (!ret) {
-			mask_ofl_ipi &= ~mask;
+		/* The CPU will report the QS in response to the IPI. */
+		if (!ret)
 			continue;
-		}
+
 		/* Failed, raced with CPU hotplug operation. */
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if ((rnp->qsmaskinitnext & mask) &&
@@ -403,13 +406,12 @@ retry_ipi:
 			schedule_timeout_uninterruptible(1);
 			goto retry_ipi;
 		}
-		/* CPU really is offline, so we can ignore it. */
-		if (!(rnp->expmask & mask))
-			mask_ofl_ipi &= ~mask;
+		/* CPU really is offline, so we must report its QS. */
+		if (rnp->expmask & mask)
+			mask_ofl_test |= mask;
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 	/* Report quiescent states for those that went offline. */
-	mask_ofl_test |= mask_ofl_ipi;
 	if (mask_ofl_test)
 		rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
 }
@@ -456,29 +458,62 @@ static void sync_rcu_exp_select_cpus(void)
 			flush_work(&rnp->rew.rew_work);
 }
 
-static void synchronize_sched_expedited_wait(void)
+/*
+ * Wait for the expedited grace period to elapse, within time limit.
+ * If the time limit is exceeded without the grace period elapsing,
+ * return false, otherwise return true.
+ */
+static bool synchronize_rcu_expedited_wait_once(long tlimit)
+{
+	int t;
+	struct rcu_node *rnp_root = rcu_get_root();
+
+	t = swait_event_timeout_exclusive(rcu_state.expedited_wq,
+					  sync_rcu_exp_done_unlocked(rnp_root),
+					  tlimit);
+	// Workqueues should not be signaled.
+	if (t > 0 || sync_rcu_exp_done_unlocked(rnp_root))
+		return true;
+	WARN_ON(t < 0);  /* workqueues should not be signaled. */
+	return false;
+}
+
+/*
+ * Wait for the expedited grace period to elapse, issuing any needed
+ * RCU CPU stall warnings along the way.
+ */
+static void synchronize_rcu_expedited_wait(void)
 {
 	int cpu;
 	unsigned long jiffies_stall;
 	unsigned long jiffies_start;
 	unsigned long mask;
 	int ndetected;
+	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 	struct rcu_node *rnp_root = rcu_get_root();
-	int ret;
 
 	trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait"));
 	jiffies_stall = rcu_jiffies_till_stall_check();
 	jiffies_start = jiffies;
+	if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
+		if (synchronize_rcu_expedited_wait_once(1))
+			return;
+		rcu_for_each_leaf_node(rnp) {
+			for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+				rdp = per_cpu_ptr(&rcu_data, cpu);
+				if (rdp->rcu_forced_tick_exp)
+					continue;
+				rdp->rcu_forced_tick_exp = true;
+				tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+			}
+		}
+		WARN_ON_ONCE(1);
+	}
 
 	for (;;) {
-		ret = swait_event_timeout_exclusive(
-				rcu_state.expedited_wq,
-				sync_rcu_preempt_exp_done_unlocked(rnp_root),
-				jiffies_stall);
-		if (ret > 0 || sync_rcu_preempt_exp_done_unlocked(rnp_root))
+		if (synchronize_rcu_expedited_wait_once(jiffies_stall))
 			return;
-		WARN_ON(ret < 0);  /* workqueues should not be signaled. */
 		if (rcu_cpu_stall_suppress)
 			continue;
 		panic_on_rcu_stall();
@@ -491,7 +526,7 @@ static void synchronize_sched_expedited_wait(void)
 				struct rcu_data *rdp;
 
 				mask = leaf_node_cpu_bit(rnp, cpu);
-				if (!(rnp->expmask & mask))
+				if (!(READ_ONCE(rnp->expmask) & mask))
 					continue;
 				ndetected++;
 				rdp = per_cpu_ptr(&rcu_data, cpu);
@@ -503,17 +538,18 @@ static void synchronize_sched_expedited_wait(void)
 		}
 		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
 			jiffies - jiffies_start, rcu_state.expedited_sequence,
-			rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]);
+			READ_ONCE(rnp_root->expmask),
+			".T"[!!rnp_root->exp_tasks]);
 		if (ndetected) {
 			pr_err("blocking rcu_node structures:");
 			rcu_for_each_node_breadth_first(rnp) {
 				if (rnp == rnp_root)
 					continue; /* printed unconditionally */
-				if (sync_rcu_preempt_exp_done_unlocked(rnp))
+				if (sync_rcu_exp_done_unlocked(rnp))
 					continue;
 				pr_cont(" l=%u:%d-%d:%#lx/%c",
 					rnp->level, rnp->grplo, rnp->grphi,
-					rnp->expmask,
+					READ_ONCE(rnp->expmask),
 					".T"[!!rnp->exp_tasks]);
 			}
 			pr_cont("\n");
@@ -521,7 +557,7 @@ static void synchronize_sched_expedited_wait(void)
 		rcu_for_each_leaf_node(rnp) {
 			for_each_leaf_node_possible_cpu(rnp, cpu) {
 				mask = leaf_node_cpu_bit(rnp, cpu);
-				if (!(rnp->expmask & mask))
+				if (!(READ_ONCE(rnp->expmask) & mask))
 					continue;
 				dump_cpu_task(cpu);
 			}
@@ -540,15 +576,14 @@ static void rcu_exp_wait_wake(unsigned long s)
 {
 	struct rcu_node *rnp;
 
-	synchronize_sched_expedited_wait();
-	rcu_exp_gp_seq_end();
-	trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end"));
+	synchronize_rcu_expedited_wait();
 
-	/*
-	 * Switch over to wakeup mode, allowing the next GP, but -only- the
-	 * next GP, to proceed.
-	 */
+	// Switch over to wakeup mode, allowing the next GP to proceed.
+	// End the previous grace period only after acquiring the mutex
+	// to ensure that only one GP runs concurrently with wakeups.
 	mutex_lock(&rcu_state.exp_wake_mutex);
+	rcu_exp_gp_seq_end();
+	trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end"));
 
 	rcu_for_each_node_breadth_first(rnp) {
 		if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) {
@@ -559,7 +594,7 @@ static void rcu_exp_wait_wake(unsigned long s)
 			spin_unlock(&rnp->exp_lock);
 		}
 		smp_mb(); /* All above changes before wakeup. */
-		wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rcu_state.expedited_sequence) & 0x3]);
+		wake_up_all(&rnp->exp_wq[rcu_seq_ctr(s) & 0x3]);
 	}
 	trace_rcu_exp_grace_period(rcu_state.name, s, TPS("endwake"));
 	mutex_unlock(&rcu_state.exp_wake_mutex);
@@ -610,7 +645,7 @@ static void rcu_exp_handler(void *unused)
 	 * critical section.  If also enabled or idle, immediately
 	 * report the quiescent state, otherwise defer.
 	 */
-	if (!t->rcu_read_lock_nesting) {
+	if (!rcu_preempt_depth()) {
 		if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
 		    rcu_dynticks_curr_cpu_in_eqs()) {
 			rcu_report_exp_rdp(rdp);
@@ -634,7 +669,7 @@ static void rcu_exp_handler(void *unused)
 	 * can have caused this quiescent state to already have been
 	 * reported, so we really do need to check ->expmask.
 	 */
-	if (t->rcu_read_lock_nesting > 0) {
+	if (rcu_preempt_depth() > 0) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmask & rdp->grpmask) {
 			rdp->exp_deferred_qs = true;
@@ -670,7 +705,7 @@ static void rcu_exp_handler(void *unused)
 	}
 }
 
-/* PREEMPT=y, so no PREEMPT=n expedited grace period to clean up after. */
+/* PREEMPTION=y, so no PREEMPTION=n expedited grace period to clean up after. */
 static void sync_sched_exp_online_cleanup(int cpu)
 {
 }
@@ -785,7 +820,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  * implementations, it is still unfriendly to real-time workloads, so is
  * thus not recommended for any sort of common-case code.  In fact, if
  * you are using synchronize_rcu_expedited() in a loop, please restructure
- * your code to batch your updates, and then Use a single synchronize_rcu()
+ * your code to batch your updates, and then use a single synchronize_rcu()
  * instead.
  *
  * This has the same semantics as (but is more brutal than) synchronize_rcu().
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index fa08d55f7040..c6ea81cd4189 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -220,7 +220,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * blocked tasks.
 	 */
 	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) {
-		rnp->gp_tasks = &t->rcu_node_entry;
+		WRITE_ONCE(rnp->gp_tasks, &t->rcu_node_entry);
 		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq);
 	}
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
@@ -290,8 +290,8 @@ void rcu_note_context_switch(bool preempt)
 
 	trace_rcu_utilization(TPS("Start context switch"));
 	lockdep_assert_irqs_disabled();
-	WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0);
-	if (t->rcu_read_lock_nesting > 0 &&
+	WARN_ON_ONCE(!preempt && rcu_preempt_depth() > 0);
+	if (rcu_preempt_depth() > 0 &&
 	    !t->rcu_read_unlock_special.b.blocked) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
@@ -340,7 +340,7 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
  */
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 {
-	return rnp->gp_tasks != NULL;
+	return READ_ONCE(rnp->gp_tasks) != NULL;
 }
 
 /* Bias and limit values for ->rcu_read_lock_nesting. */
@@ -348,6 +348,21 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 #define RCU_NEST_NMAX (-INT_MAX / 2)
 #define RCU_NEST_PMAX (INT_MAX / 2)
 
+static void rcu_preempt_read_enter(void)
+{
+	current->rcu_read_lock_nesting++;
+}
+
+static void rcu_preempt_read_exit(void)
+{
+	current->rcu_read_lock_nesting--;
+}
+
+static void rcu_preempt_depth_set(int val)
+{
+	current->rcu_read_lock_nesting = val;
+}
+
 /*
  * Preemptible RCU implementation for rcu_read_lock().
  * Just increment ->rcu_read_lock_nesting, shared state will be updated
@@ -355,9 +370,9 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
  */
 void __rcu_read_lock(void)
 {
-	current->rcu_read_lock_nesting++;
+	rcu_preempt_read_enter();
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING))
-		WARN_ON_ONCE(current->rcu_read_lock_nesting > RCU_NEST_PMAX);
+		WARN_ON_ONCE(rcu_preempt_depth() > RCU_NEST_PMAX);
 	barrier();  /* critical section after entry code. */
 }
 EXPORT_SYMBOL_GPL(__rcu_read_lock);
@@ -373,19 +388,19 @@ void __rcu_read_unlock(void)
 {
 	struct task_struct *t = current;
 
-	if (t->rcu_read_lock_nesting != 1) {
-		--t->rcu_read_lock_nesting;
+	if (rcu_preempt_depth() != 1) {
+		rcu_preempt_read_exit();
 	} else {
 		barrier();  /* critical section before exit code. */
-		t->rcu_read_lock_nesting = -RCU_NEST_BIAS;
+		rcu_preempt_depth_set(-RCU_NEST_BIAS);
 		barrier();  /* assign before ->rcu_read_unlock_special load */
 		if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
 			rcu_read_unlock_special(t);
 		barrier();  /* ->rcu_read_unlock_special load before assign */
-		t->rcu_read_lock_nesting = 0;
+		rcu_preempt_depth_set(0);
 	}
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
-		int rrln = t->rcu_read_lock_nesting;
+		int rrln = rcu_preempt_depth();
 
 		WARN_ON_ONCE(rrln < 0 && rrln > RCU_NEST_NMAX);
 	}
@@ -444,15 +459,9 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 		local_irq_restore(flags);
 		return;
 	}
-	t->rcu_read_unlock_special.b.deferred_qs = false;
-	if (special.b.need_qs) {
+	t->rcu_read_unlock_special.s = 0;
+	if (special.b.need_qs)
 		rcu_qs();
-		t->rcu_read_unlock_special.b.need_qs = false;
-		if (!t->rcu_read_unlock_special.s && !rdp->exp_deferred_qs) {
-			local_irq_restore(flags);
-			return;
-		}
-	}
 
 	/*
 	 * Respond to a request by an expedited grace period for a
@@ -460,17 +469,11 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 	 * tasks are handled when removing the task from the
 	 * blocked-tasks list below.
 	 */
-	if (rdp->exp_deferred_qs) {
+	if (rdp->exp_deferred_qs)
 		rcu_report_exp_rdp(rdp);
-		if (!t->rcu_read_unlock_special.s) {
-			local_irq_restore(flags);
-			return;
-		}
-	}
 
 	/* Clean up if blocked during RCU read-side critical section. */
 	if (special.b.blocked) {
-		t->rcu_read_unlock_special.b.blocked = false;
 
 		/*
 		 * Remove this task from the list it blocked on.  The task
@@ -485,7 +488,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
 		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq &&
 			     (!empty_norm || rnp->qsmask));
-		empty_exp = sync_rcu_preempt_exp_done(rnp);
+		empty_exp = sync_rcu_exp_done(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
 		np = rcu_next_node_entry(t, rnp);
 		list_del_init(&t->rcu_node_entry);
@@ -493,7 +496,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 		trace_rcu_unlock_preempted_task(TPS("rcu_preempt"),
 						rnp->gp_seq, t->pid);
 		if (&t->rcu_node_entry == rnp->gp_tasks)
-			rnp->gp_tasks = np;
+			WRITE_ONCE(rnp->gp_tasks, np);
 		if (&t->rcu_node_entry == rnp->exp_tasks)
 			rnp->exp_tasks = np;
 		if (IS_ENABLED(CONFIG_RCU_BOOST)) {
@@ -509,7 +512,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 		 * Note that rcu_report_unblock_qs_rnp() releases rnp->lock,
 		 * so we must take a snapshot of the expedited state.
 		 */
-		empty_exp_now = sync_rcu_preempt_exp_done(rnp);
+		empty_exp_now = sync_rcu_exp_done(rnp);
 		if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) {
 			trace_rcu_quiescent_state_report(TPS("preempt_rcu"),
 							 rnp->gp_seq,
@@ -551,7 +554,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
 	return (__this_cpu_read(rcu_data.exp_deferred_qs) ||
 		READ_ONCE(t->rcu_read_unlock_special.s)) &&
-	       t->rcu_read_lock_nesting <= 0;
+	       rcu_preempt_depth() <= 0;
 }
 
 /*
@@ -564,16 +567,16 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 static void rcu_preempt_deferred_qs(struct task_struct *t)
 {
 	unsigned long flags;
-	bool couldrecurse = t->rcu_read_lock_nesting >= 0;
+	bool couldrecurse = rcu_preempt_depth() >= 0;
 
 	if (!rcu_preempt_need_deferred_qs(t))
 		return;
 	if (couldrecurse)
-		t->rcu_read_lock_nesting -= RCU_NEST_BIAS;
+		rcu_preempt_depth_set(rcu_preempt_depth() - RCU_NEST_BIAS);
 	local_irq_save(flags);
 	rcu_preempt_deferred_qs_irqrestore(t, flags);
 	if (couldrecurse)
-		t->rcu_read_lock_nesting += RCU_NEST_BIAS;
+		rcu_preempt_depth_set(rcu_preempt_depth() + RCU_NEST_BIAS);
 }
 
 /*
@@ -610,9 +613,8 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 		struct rcu_node *rnp = rdp->mynode;
 
-		t->rcu_read_unlock_special.b.exp_hint = false;
 		exp = (t->rcu_blocked_node && t->rcu_blocked_node->exp_tasks) ||
-		      (rdp->grpmask & rnp->expmask) ||
+		      (rdp->grpmask & READ_ONCE(rnp->expmask)) ||
 		      tick_nohz_full_cpu(rdp->cpu);
 		// Need to defer quiescent state until everything is enabled.
 		if (irqs_were_disabled && use_softirq &&
@@ -640,7 +642,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		local_irq_restore(flags);
 		return;
 	}
-	WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false);
 	rcu_preempt_deferred_qs_irqrestore(t, flags);
 }
 
@@ -648,8 +649,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
  * Check that the list of blocked tasks for the newly completed grace
  * period is in fact empty.  It is a serious bug to complete a grace
  * period that still has RCU readers blocked!  This function must be
- * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock
- * must be held by the caller.
+ * invoked -before- updating this rnp's ->gp_seq.
  *
  * Also, if there are blocked tasks on the list, they automatically
  * block the newly created grace period, so set up ->gp_tasks accordingly.
@@ -659,11 +659,12 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 	struct task_struct *t;
 
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
+	raw_lockdep_assert_held_rcu_node(rnp);
 	if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
 		dump_blkd_tasks(rnp, 10);
 	if (rcu_preempt_has_tasks(rnp) &&
 	    (rnp->qsmaskinit || rnp->wait_blkd_tasks)) {
-		rnp->gp_tasks = rnp->blkd_tasks.next;
+		WRITE_ONCE(rnp->gp_tasks, rnp->blkd_tasks.next);
 		t = container_of(rnp->gp_tasks, struct task_struct,
 				 rcu_node_entry);
 		trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"),
@@ -686,7 +687,7 @@ static void rcu_flavor_sched_clock_irq(int user)
 	if (user || rcu_is_cpu_rrupt_from_idle()) {
 		rcu_note_voluntary_context_switch(current);
 	}
-	if (t->rcu_read_lock_nesting > 0 ||
+	if (rcu_preempt_depth() > 0 ||
 	    (preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) {
 		/* No QS, force context switch if deferred. */
 		if (rcu_preempt_need_deferred_qs(t)) {
@@ -696,13 +697,13 @@ static void rcu_flavor_sched_clock_irq(int user)
 	} else if (rcu_preempt_need_deferred_qs(t)) {
 		rcu_preempt_deferred_qs(t); /* Report deferred QS. */
 		return;
-	} else if (!t->rcu_read_lock_nesting) {
+	} else if (!rcu_preempt_depth()) {
 		rcu_qs(); /* Report immediate QS. */
 		return;
 	}
 
 	/* If GP is oldish, ask for help from rcu_read_unlock_special(). */
-	if (t->rcu_read_lock_nesting > 0 &&
+	if (rcu_preempt_depth() > 0 &&
 	    __this_cpu_read(rcu_data.core_needs_qs) &&
 	    __this_cpu_read(rcu_data.cpu_no_qs.b.norm) &&
 	    !t->rcu_read_unlock_special.b.need_qs &&
@@ -723,11 +724,11 @@ void exit_rcu(void)
 	struct task_struct *t = current;
 
 	if (unlikely(!list_empty(&current->rcu_node_entry))) {
-		t->rcu_read_lock_nesting = 1;
+		rcu_preempt_depth_set(1);
 		barrier();
 		WRITE_ONCE(t->rcu_read_unlock_special.b.blocked, true);
-	} else if (unlikely(t->rcu_read_lock_nesting)) {
-		t->rcu_read_lock_nesting = 1;
+	} else if (unlikely(rcu_preempt_depth())) {
+		rcu_preempt_depth_set(1);
 	} else {
 		return;
 	}
@@ -757,7 +758,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 		pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
 			__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext);
 	pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n",
-		__func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks);
+		__func__, READ_ONCE(rnp->gp_tasks), rnp->boost_tasks,
+		rnp->exp_tasks);
 	pr_info("%s: ->blkd_tasks", __func__);
 	i = 0;
 	list_for_each(lhp, &rnp->blkd_tasks) {
@@ -788,7 +790,7 @@ static void __init rcu_bootup_announce(void)
 }
 
 /*
- * Note a quiescent state for PREEMPT=n.  Because we do not need to know
+ * Note a quiescent state for PREEMPTION=n.  Because we do not need to know
  * how many quiescent states passed, just if there was at least one since
  * the start of the grace period, this just sets a flag.  The caller must
  * have disabled preemption.
@@ -838,7 +840,7 @@ void rcu_all_qs(void)
 EXPORT_SYMBOL_GPL(rcu_all_qs);
 
 /*
- * Note a PREEMPT=n context switch.  The caller must have disabled interrupts.
+ * Note a PREEMPTION=n context switch. The caller must have disabled interrupts.
  */
 void rcu_note_context_switch(bool preempt)
 {
@@ -1262,10 +1264,9 @@ static void rcu_prepare_for_idle(void)
 /*
  * This code is invoked when a CPU goes idle, at which point we want
  * to have the CPU do everything required for RCU so that it can enter
- * the energy-efficient dyntick-idle mode.  This is handled by a
- * state machine implemented by rcu_prepare_for_idle() below.
+ * the energy-efficient dyntick-idle mode.
  *
- * The following three proprocessor symbols control this state machine:
+ * The following preprocessor symbol controls this:
  *
  * RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted
  *	to sleep in dyntick-idle mode with RCU callbacks pending.  This
@@ -1274,21 +1275,15 @@ static void rcu_prepare_for_idle(void)
  *	number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your
  *	system.  And if you are -that- concerned about energy efficiency,
  *	just power the system down and be done with it!
- * RCU_IDLE_LAZY_GP_DELAY gives the number of jiffies that a CPU is
- *	permitted to sleep in dyntick-idle mode with only lazy RCU
- *	callbacks pending.  Setting this too high can OOM your system.
  *
- * The values below work well in practice.  If future workloads require
+ * The value below works well in practice.  If future workloads require
  * adjustment, they can be converted into kernel config parameters, though
  * making the state machine smarter might be a better option.
  */
 #define RCU_IDLE_GP_DELAY 4		/* Roughly one grace period. */
-#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ)	/* Roughly six seconds. */
 
 static int rcu_idle_gp_delay = RCU_IDLE_GP_DELAY;
 module_param(rcu_idle_gp_delay, int, 0644);
-static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY;
-module_param(rcu_idle_lazy_gp_delay, int, 0644);
 
 /*
  * Try to advance callbacks on the current CPU, but only if it has been
@@ -1327,8 +1322,7 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
 /*
  * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready
  * to invoke.  If the CPU has callbacks, try to advance them.  Tell the
- * caller to set the timeout based on whether or not there are non-lazy
- * callbacks.
+ * caller about what to set the timeout.
  *
  * The caller must have disabled interrupts.
  */
@@ -1354,25 +1348,18 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 	}
 	rdp->last_accelerate = jiffies;
 
-	/* Request timer delay depending on laziness, and round. */
-	rdp->all_lazy = !rcu_segcblist_n_nonlazy_cbs(&rdp->cblist);
-	if (rdp->all_lazy) {
-		dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
-	} else {
-		dj = round_up(rcu_idle_gp_delay + jiffies,
-			       rcu_idle_gp_delay) - jiffies;
-	}
+	/* Request timer and round. */
+	dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies;
+
 	*nextevt = basemono + dj * TICK_NSEC;
 	return 0;
 }
 
 /*
- * Prepare a CPU for idle from an RCU perspective.  The first major task
- * is to sense whether nohz mode has been enabled or disabled via sysfs.
- * The second major task is to check to see if a non-lazy callback has
- * arrived at a CPU that previously had only lazy callbacks.  The third
- * major task is to accelerate (that is, assign grace-period numbers to)
- * any recently arrived callbacks.
+ * Prepare a CPU for idle from an RCU perspective.  The first major task is to
+ * sense whether nohz mode has been enabled or disabled via sysfs.  The second
+ * major task is to accelerate (that is, assign grace-period numbers to) any
+ * recently arrived callbacks.
  *
  * The caller must have disabled interrupts.
  */
@@ -1399,17 +1386,6 @@ static void rcu_prepare_for_idle(void)
 		return;
 
 	/*
-	 * If a non-lazy callback arrived at a CPU having only lazy
-	 * callbacks, invoke RCU core for the side-effect of recalculating
-	 * idle duration on re-entry to idle.
-	 */
-	if (rdp->all_lazy && rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)) {
-		rdp->all_lazy = false;
-		invoke_rcu_core();
-		return;
-	}
-
-	/*
 	 * If we have not yet accelerated this jiffy, accelerate all
 	 * callbacks on this CPU.
 	 */
@@ -2321,6 +2297,8 @@ static void __init rcu_organize_nocb_kthreads(void)
 {
 	int cpu;
 	bool firsttime = true;
+	bool gotnocbs = false;
+	bool gotnocbscbs = true;
 	int ls = rcu_nocb_gp_stride;
 	int nl = 0;  /* Next GP kthread. */
 	struct rcu_data *rdp;
@@ -2343,21 +2321,31 @@ static void __init rcu_organize_nocb_kthreads(void)
 		rdp = per_cpu_ptr(&rcu_data, cpu);
 		if (rdp->cpu >= nl) {
 			/* New GP kthread, set up for CBs & next GP. */
+			gotnocbs = true;
 			nl = DIV_ROUND_UP(rdp->cpu + 1, ls) * ls;
 			rdp->nocb_gp_rdp = rdp;
 			rdp_gp = rdp;
-			if (!firsttime && dump_tree)
-				pr_cont("\n");
-			firsttime = false;
-			pr_alert("%s: No-CB GP kthread CPU %d:", __func__, cpu);
+			if (dump_tree) {
+				if (!firsttime)
+					pr_cont("%s\n", gotnocbscbs
+							? "" : " (self only)");
+				gotnocbscbs = false;
+				firsttime = false;
+				pr_alert("%s: No-CB GP kthread CPU %d:",
+					 __func__, cpu);
+			}
 		} else {
 			/* Another CB kthread, link to previous GP kthread. */
+			gotnocbscbs = true;
 			rdp->nocb_gp_rdp = rdp_gp;
 			rdp_prev->nocb_next_cb_rdp = rdp;
-			pr_alert(" %d", cpu);
+			if (dump_tree)
+				pr_cont(" %d", cpu);
 		}
 		rdp_prev = rdp;
 	}
+	if (gotnocbs && dump_tree)
+		pr_cont("%s\n", gotnocbscbs ? "" : " (self only)");
 }
 
 /*
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index c0b8c458d8a6..55f9b84790d3 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -163,7 +163,7 @@ static void rcu_iw_handler(struct irq_work *iwp)
 //
 // Printing RCU CPU stall warnings
 
-#ifdef CONFIG_PREEMPTION
+#ifdef CONFIG_PREEMPT_RCU
 
 /*
  * Dump detailed information for all tasks blocking the current RCU
@@ -215,7 +215,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 	return ndetected;
 }
 
-#else /* #ifdef CONFIG_PREEMPTION */
+#else /* #ifdef CONFIG_PREEMPT_RCU */
 
 /*
  * Because preemptible RCU does not exist, we never have to check for
@@ -233,7 +233,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 {
 	return 0;
 }
-#endif /* #else #ifdef CONFIG_PREEMPTION */
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 /*
  * Dump stacks of all tasks running on stalled CPUs.  First try using
@@ -263,11 +263,9 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
 {
 	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
 
-	sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
+	sprintf(cp, "last_accelerate: %04lx/%04lx dyntick_enabled: %d",
 		rdp->last_accelerate & 0xffff, jiffies & 0xffff,
-		".l"[rdp->all_lazy],
-		".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
-		".D"[!!rdp->tick_nohz_enabled_snap]);
+		!!rdp->tick_nohz_enabled_snap);
 }
 
 #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
@@ -279,6 +277,28 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
 
 #endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
 
+static const char * const gp_state_names[] = {
+	[RCU_GP_IDLE] = "RCU_GP_IDLE",
+	[RCU_GP_WAIT_GPS] = "RCU_GP_WAIT_GPS",
+	[RCU_GP_DONE_GPS] = "RCU_GP_DONE_GPS",
+	[RCU_GP_ONOFF] = "RCU_GP_ONOFF",
+	[RCU_GP_INIT] = "RCU_GP_INIT",
+	[RCU_GP_WAIT_FQS] = "RCU_GP_WAIT_FQS",
+	[RCU_GP_DOING_FQS] = "RCU_GP_DOING_FQS",
+	[RCU_GP_CLEANUP] = "RCU_GP_CLEANUP",
+	[RCU_GP_CLEANED] = "RCU_GP_CLEANED",
+};
+
+/*
+ * Convert a ->gp_state value to a character string.
+ */
+static const char *gp_state_getname(short gs)
+{
+	if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
+		return "???";
+	return gp_state_names[gs];
+}
+
 /*
  * Print out diagnostic information for the specified stalled CPU.
  *
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 1861103662db..6c4b862f57d6 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -40,6 +40,7 @@
 #include <linux/rcupdate_wait.h>
 #include <linux/sched/isolation.h>
 #include <linux/kprobes.h>
+#include <linux/slab.h>
 
 #define CREATE_TRACE_POINTS
 
@@ -51,9 +52,7 @@
 #define MODULE_PARAM_PREFIX "rcupdate."
 
 #ifndef CONFIG_TINY_RCU
-extern int rcu_expedited; /* from sysctl */
 module_param(rcu_expedited, int, 0);
-extern int rcu_normal; /* from sysctl */
 module_param(rcu_normal, int, 0);
 static int rcu_normal_after_boot;
 module_param(rcu_normal_after_boot, int, 0);
@@ -218,6 +217,7 @@ static int __init rcu_set_runtime_mode(void)
 {
 	rcu_test_sync_prims();
 	rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
+	kfree_rcu_scheduler_running();
 	rcu_test_sync_prims();
 	return 0;
 }
@@ -435,7 +435,7 @@ struct debug_obj_descr rcuhead_debug_descr = {
 EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
 #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_RCU_TRACE)
 void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp,
 			       unsigned long secs,
 			       unsigned long c_old, unsigned long c)
@@ -853,14 +853,22 @@ static void test_callback(struct rcu_head *r)
 
 DEFINE_STATIC_SRCU(early_srcu);
 
+struct early_boot_kfree_rcu {
+	struct rcu_head rh;
+};
+
 static void early_boot_test_call_rcu(void)
 {
 	static struct rcu_head head;
 	static struct rcu_head shead;
+	struct early_boot_kfree_rcu *rhp;
 
 	call_rcu(&head, test_callback);
 	if (IS_ENABLED(CONFIG_SRCU))
 		call_srcu(&early_srcu, &shead, test_callback);
+	rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
+	if (!WARN_ON_ONCE(!rhp))
+		kfree_rcu(rhp, rh);
 }
 
 void rcu_early_boot_tests(void)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 70665934d53e..d396aaaf19a3 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1268,7 +1268,7 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_do_static_key,
 	},
 #endif
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
+#if defined(CONFIG_TREE_RCU)
 	{
 		.procname	= "panic_on_rcu_stall",
 		.data		= &sysctl_panic_on_rcu_stall,