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 biggest RCU changes in this cycle were:

   - Convert RCU's BUG_ON() and similar calls to WARN_ON() and similar.

   - Replace calls of RCU-bh and RCU-sched update-side functions to
     their vanilla RCU counterparts. This series is a step towards
     complete removal of the RCU-bh and RCU-sched update-side functions.

     ( Note that some of these conversions are going upstream via their
       respective maintainers. )

   - Documentation updates, including a number of flavor-consolidation
     updates from Joel Fernandes.

   - Miscellaneous fixes.

   - Automate generation of the initrd filesystem used for rcutorture
     testing.

   - Convert spin_is_locked() assertions to instead use lockdep.

     ( Note that some of these conversions are going upstream via their
       respective maintainers. )

   - SRCU updates, especially including a fix from Dennis Krein for a
     bag-on-head-class bug.

   - RCU torture-test updates"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (112 commits)
  rcutorture: Don't do busted forward-progress testing
  rcutorture: Use 100ms buckets for forward-progress callback histograms
  rcutorture: Recover from OOM during forward-progress tests
  rcutorture: Print forward-progress test age upon failure
  rcutorture: Print time since GP end upon forward-progress failure
  rcutorture: Print histogram of CB invocation at OOM time
  rcutorture: Print GP age upon forward-progress failure
  rcu: Print per-CPU callback counts for forward-progress failures
  rcu: Account for nocb-CPU callback counts in RCU CPU stall warnings
  rcutorture: Dump grace-period diagnostics upon forward-progress OOM
  rcutorture: Prepare for asynchronous access to rcu_fwd_startat
  torture: Remove unnecessary "ret" variables
  rcutorture: Affinity forward-progress test to avoid housekeeping CPUs
  rcutorture: Break up too-long rcu_torture_fwd_prog() function
  rcutorture: Remove cbflood facility
  torture: Bring any extra CPUs online during kernel startup
  rcutorture: Add call_rcu() flooding forward-progress tests
  rcutorture/formal: Replace synchronize_sched() with synchronize_rcu()
  tools/kernel.h: Replace synchronize_sched() with synchronize_rcu()
  net/decnet: Replace rcu_barrier_bh() with rcu_barrier()
  ...

28 files changed, 824 insertions, 583 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 6aaf5dd5383b..7a8429f8e280 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5343,7 +5343,7 @@ int __init cgroup_init(void)
 	cgroup_rstat_boot();
 
 	/*
-	 * The latency of the synchronize_sched() is too high for cgroups,
+	 * The latency of the synchronize_rcu() is too high for cgroups,
 	 * avoid it at the cost of forcing all readers into the slow path.
 	 */
 	rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 84530ab358c3..c4b90cf7734a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9918,7 +9918,7 @@ static void account_event(struct perf_event *event)
 			 * call the perf scheduling hooks before proceeding to
 			 * install events that need them.
 			 */
-			synchronize_sched();
+			synchronize_rcu();
 		}
 		/*
 		 * Now that we have waited for the sync_sched(), allow further
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 90e98e233647..08e31d863191 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -229,7 +229,7 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c)
 	struct kprobe_insn_page *kip, *next;
 
 	/* Ensure no-one is interrupted on the garbages */
-	synchronize_sched();
+	synchronize_rcu();
 
 	list_for_each_entry_safe(kip, next, &c->pages, list) {
 		int i;
@@ -1382,7 +1382,7 @@ out:
 			if (ret) {
 				ap->flags |= KPROBE_FLAG_DISABLED;
 				list_del_rcu(&p->list);
-				synchronize_sched();
+				synchronize_rcu();
 			}
 		}
 	}
@@ -1597,7 +1597,7 @@ int register_kprobe(struct kprobe *p)
 		ret = arm_kprobe(p);
 		if (ret) {
 			hlist_del_rcu(&p->hlist);
-			synchronize_sched();
+			synchronize_rcu();
 			goto out;
 		}
 	}
@@ -1776,7 +1776,7 @@ void unregister_kprobes(struct kprobe **kps, int num)
 			kps[i]->addr = NULL;
 	mutex_unlock(&kprobe_mutex);
 
-	synchronize_sched();
+	synchronize_rcu();
 	for (i = 0; i < num; i++)
 		if (kps[i]->addr)
 			__unregister_kprobe_bottom(kps[i]);
@@ -1966,7 +1966,7 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
 			rps[i]->kp.addr = NULL;
 	mutex_unlock(&kprobe_mutex);
 
-	synchronize_sched();
+	synchronize_rcu();
 	for (i = 0; i < num; i++) {
 		if (rps[i]->kp.addr) {
 			__unregister_kprobe_bottom(&rps[i]->kp);
diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c
index 82d584225dc6..7702cb4064fc 100644
--- a/kernel/livepatch/patch.c
+++ b/kernel/livepatch/patch.c
@@ -61,7 +61,7 @@ static void notrace klp_ftrace_handler(unsigned long ip,
 	ops = container_of(fops, struct klp_ops, fops);
 
 	/*
-	 * A variant of synchronize_sched() is used to allow patching functions
+	 * A variant of synchronize_rcu() is used to allow patching functions
 	 * where RCU is not watching, see klp_synchronize_transition().
 	 */
 	preempt_disable_notrace();
@@ -72,7 +72,7 @@ static void notrace klp_ftrace_handler(unsigned long ip,
 	/*
 	 * func should never be NULL because preemption should be disabled here
 	 * and unregister_ftrace_function() does the equivalent of a
-	 * synchronize_sched() before the func_stack removal.
+	 * synchronize_rcu() before the func_stack removal.
 	 */
 	if (WARN_ON_ONCE(!func))
 		goto unlock;
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 5bc349805e03..304d5eb8a98c 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -52,7 +52,7 @@ static DECLARE_DELAYED_WORK(klp_transition_work, klp_transition_work_fn);
 
 /*
  * This function is just a stub to implement a hard force
- * of synchronize_sched(). This requires synchronizing
+ * of synchronize_rcu(). This requires synchronizing
  * tasks even in userspace and idle.
  */
 static void klp_sync(struct work_struct *work)
@@ -175,7 +175,7 @@ void klp_cancel_transition(void)
 void klp_update_patch_state(struct task_struct *task)
 {
 	/*
-	 * A variant of synchronize_sched() is used to allow patching functions
+	 * A variant of synchronize_rcu() is used to allow patching functions
 	 * where RCU is not watching, see klp_synchronize_transition().
 	 */
 	preempt_disable_notrace();
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 1efada2dd9dd..ef27f98714c0 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4195,7 +4195,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
 	 *
 	 * sync_sched() is sufficient because the read-side is IRQ disable.
 	 */
-	synchronize_sched();
+	synchronize_rcu();
 
 	/*
 	 * XXX at this point we could return the resources to the pool;
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 9aa713629387..771d4ca96dda 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -36,7 +36,7 @@ void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter)
 
 void debug_mutex_wake_waiter(struct mutex *lock, struct mutex_waiter *waiter)
 {
-	SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
+	lockdep_assert_held(&lock->wait_lock);
 	DEBUG_LOCKS_WARN_ON(list_empty(&lock->wait_list));
 	DEBUG_LOCKS_WARN_ON(waiter->magic != waiter);
 	DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
@@ -51,7 +51,7 @@ void debug_mutex_free_waiter(struct mutex_waiter *waiter)
 void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 			    struct task_struct *task)
 {
-	SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
+	lockdep_assert_held(&lock->wait_lock);
 
 	/* Mark the current thread as blocked on the lock: */
 	task->blocked_on = waiter;
diff --git a/kernel/module.c b/kernel/module.c
index 49a405891587..99b46c32d579 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2159,7 +2159,7 @@ static void free_module(struct module *mod)
 	/* Remove this module from bug list, this uses list_del_rcu */
 	module_bug_cleanup(mod);
 	/* Wait for RCU-sched synchronizing before releasing mod->list and buglist. */
-	synchronize_sched();
+	synchronize_rcu();
 	mutex_unlock(&module_mutex);
 
 	/* This may be empty, but that's OK */
@@ -3507,15 +3507,15 @@ static noinline int do_init_module(struct module *mod)
 	/*
 	 * We want to free module_init, but be aware that kallsyms may be
 	 * walking this with preempt disabled.  In all the failure paths, we
-	 * call synchronize_sched(), but we don't want to slow down the success
+	 * call synchronize_rcu(), but we don't want to slow down the success
 	 * path, so use actual RCU here.
 	 * Note that module_alloc() on most architectures creates W+X page
 	 * mappings which won't be cleaned up until do_free_init() runs.  Any
 	 * code such as mark_rodata_ro() which depends on those mappings to
 	 * be cleaned up needs to sync with the queued work - ie
-	 * rcu_barrier_sched()
+	 * rcu_barrier()
 	 */
-	call_rcu_sched(&freeinit->rcu, do_free_init);
+	call_rcu(&freeinit->rcu, do_free_init);
 	mutex_unlock(&module_mutex);
 	wake_up_all(&module_wq);
 
@@ -3526,7 +3526,7 @@ fail_free_freeinit:
 fail:
 	/* Try to protect us from buggy refcounters. */
 	mod->state = MODULE_STATE_GOING;
-	synchronize_sched();
+	synchronize_rcu();
 	module_put(mod);
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_GOING, mod);
@@ -3819,7 +3819,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
  ddebug_cleanup:
 	ftrace_release_mod(mod);
 	dynamic_debug_remove(mod, info->debug);
-	synchronize_sched();
+	synchronize_rcu();
 	kfree(mod->args);
  free_arch_cleanup:
 	module_arch_cleanup(mod);
@@ -3834,7 +3834,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	mod_tree_remove(mod);
 	wake_up_all(&module_wq);
 	/* Wait for RCU-sched synchronizing before releasing mod->list. */
-	synchronize_sched();
+	synchronize_rcu();
 	mutex_unlock(&module_mutex);
  free_module:
 	/* Free lock-classes; relies on the preceding sync_rcu() */
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 2866166863f0..a393e24a9195 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -526,12 +526,14 @@ srcu_batches_completed(struct srcu_struct *sp) { return 0; }
 static inline void rcu_force_quiescent_state(void) { }
 static inline void show_rcu_gp_kthreads(void) { }
 static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
+static inline void rcu_fwd_progress_check(unsigned long j) { }
 #else /* #ifdef CONFIG_TINY_RCU */
 unsigned long rcu_get_gp_seq(void);
 unsigned long rcu_exp_batches_completed(void);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
 void show_rcu_gp_kthreads(void);
 int rcu_get_gp_kthreads_prio(void);
+void rcu_fwd_progress_check(unsigned long j);
 void rcu_force_quiescent_state(void);
 extern struct workqueue_struct *rcu_gp_wq;
 extern struct workqueue_struct *rcu_par_gp_wq;
@@ -539,8 +541,10 @@ extern struct workqueue_struct *rcu_par_gp_wq;
 
 #ifdef CONFIG_RCU_NOCB_CPU
 bool rcu_is_nocb_cpu(int cpu);
+void rcu_bind_current_to_nocb(void);
 #else
 static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
+static inline void rcu_bind_current_to_nocb(void) { }
 #endif
 
 #endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 210c77460365..f6e85faa4ff4 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -56,6 +56,7 @@
 #include <linux/vmalloc.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/sysctl.h>
+#include <linux/oom.h>
 
 #include "rcu.h"
 
@@ -80,13 +81,6 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@jos
 					/* Must be power of two minus one. */
 #define RCUTORTURE_RDR_MAX_SEGS (RCUTORTURE_RDR_MAX_LOOPS + 3)
 
-torture_param(int, cbflood_inter_holdoff, HZ,
-	      "Holdoff between floods (jiffies)");
-torture_param(int, cbflood_intra_holdoff, 1,
-	      "Holdoff between bursts (jiffies)");
-torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable");
-torture_param(int, cbflood_n_per_burst, 20000,
-	      "# callbacks per burst in flood");
 torture_param(int, extendables, RCUTORTURE_MAX_EXTEND,
 	      "Extend readers by disabling bh (1), irqs (2), or preempt (4)");
 torture_param(int, fqs_duration, 0,
@@ -138,12 +132,10 @@ module_param(torture_type, charp, 0444);
 MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, srcu, ...)");
 
 static int nrealreaders;
-static int ncbflooders;
 static struct task_struct *writer_task;
 static struct task_struct **fakewriter_tasks;
 static struct task_struct **reader_tasks;
 static struct task_struct *stats_task;
-static struct task_struct **cbflood_task;
 static struct task_struct *fqs_task;
 static struct task_struct *boost_tasks[NR_CPUS];
 static struct task_struct *stall_task;
@@ -181,7 +173,6 @@ 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 atomic_long_t n_cbfloods;
 static struct list_head rcu_torture_removed;
 
 static int rcu_torture_writer_state;
@@ -259,6 +250,8 @@ static atomic_t barrier_cbs_invoked;	/* Barrier callbacks invoked. */
 static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
 static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
 
+static bool rcu_fwd_cb_nodelay;		/* Short rcu_torture_delay() delays. */
+
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -348,7 +341,8 @@ rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp)
 	 * period, and we want a long delay occasionally to trigger
 	 * force_quiescent_state. */
 
-	if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
+	if (!rcu_fwd_cb_nodelay &&
+	    !(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
 		started = cur_ops->get_gp_seq();
 		ts = rcu_trace_clock_local();
 		if (preempt_count() & (SOFTIRQ_MASK | HARDIRQ_MASK))
@@ -870,59 +864,6 @@ checkwait:	stutter_wait("rcu_torture_boost");
 	return 0;
 }
 
-static void rcu_torture_cbflood_cb(struct rcu_head *rhp)
-{
-}
-
-/*
- * RCU torture callback-flood kthread.  Repeatedly induces bursts of calls
- * to call_rcu() or analogous, increasing the probability of occurrence
- * of callback-overflow corner cases.
- */
-static int
-rcu_torture_cbflood(void *arg)
-{
-	int err = 1;
-	int i;
-	int j;
-	struct rcu_head *rhp;
-
-	if (cbflood_n_per_burst > 0 &&
-	    cbflood_inter_holdoff > 0 &&
-	    cbflood_intra_holdoff > 0 &&
-	    cur_ops->call &&
-	    cur_ops->cb_barrier) {
-		rhp = vmalloc(array3_size(cbflood_n_burst,
-					  cbflood_n_per_burst,
-					  sizeof(*rhp)));
-		err = !rhp;
-	}
-	if (err) {
-		VERBOSE_TOROUT_STRING("rcu_torture_cbflood disabled: Bad args or OOM");
-		goto wait_for_stop;
-	}
-	VERBOSE_TOROUT_STRING("rcu_torture_cbflood task started");
-	do {
-		schedule_timeout_interruptible(cbflood_inter_holdoff);
-		atomic_long_inc(&n_cbfloods);
-		WARN_ON(signal_pending(current));
-		for (i = 0; i < cbflood_n_burst; i++) {
-			for (j = 0; j < cbflood_n_per_burst; j++) {
-				cur_ops->call(&rhp[i * cbflood_n_per_burst + j],
-					      rcu_torture_cbflood_cb);
-			}
-			schedule_timeout_interruptible(cbflood_intra_holdoff);
-			WARN_ON(signal_pending(current));
-		}
-		cur_ops->cb_barrier();
-		stutter_wait("rcu_torture_cbflood");
-	} while (!torture_must_stop());
-	vfree(rhp);
-wait_for_stop:
-	torture_kthread_stopping("rcu_torture_cbflood");
-	return 0;
-}
-
 /*
  * RCU torture force-quiescent-state kthread.  Repeatedly induces
  * bursts of calls to force_quiescent_state(), increasing the probability
@@ -1457,11 +1398,10 @@ 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 ",
+	pr_cont("barrier: %ld/%ld:%ld\n",
 		n_barrier_successes,
 		n_barrier_attempts,
 		n_rcu_torture_barrier_error);
-	pr_cont("cbflood: %ld\n", atomic_long_read(&n_cbfloods));
 
 	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
@@ -1674,8 +1614,90 @@ static void rcu_torture_fwd_prog_cb(struct rcu_head *rhp)
 	cur_ops->call(&fcsp->rh, rcu_torture_fwd_prog_cb);
 }
 
-/* Carry out grace-period forward-progress testing. */
-static int rcu_torture_fwd_prog(void *args)
+/* State for continuous-flood RCU callbacks. */
+struct rcu_fwd_cb {
+	struct rcu_head rh;
+	struct rcu_fwd_cb *rfc_next;
+	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. */
+static long n_launders_hist[2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV)];
+
+static void rcu_torture_fwd_cb_hist(void)
+{
+	int i;
+	int j;
+
+	for (i = ARRAY_SIZE(n_launders_hist) - 1; i > 0; i--)
+		if (n_launders_hist[i] > 0)
+			break;
+	pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):",
+		 __func__, jiffies - rcu_fwd_startat);
+	for (j = 0; j <= i; j++)
+		pr_cont(" %ds/%d: %ld",
+			j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j]);
+	pr_cont("\n");
+}
+
+/* Callback function for continuous-flood RCU callbacks. */
+static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
+{
+	unsigned long flags;
+	int i;
+	struct rcu_fwd_cb *rfcp = container_of(rhp, struct rcu_fwd_cb, rh);
+	struct rcu_fwd_cb **rfcpp;
+
+	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;
+	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]++;
+	spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+}
+
+/*
+ * 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)
+{
+	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;
+		if (!rfcp)
+			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);
+		kfree(rfcp);
+		freed++;
+	}
+	spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+	return freed;
+}
+
+/* Carry out need_resched()/cond_resched() forward-progress testing. */
+static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
 {
 	unsigned long cver;
 	unsigned long dur;
@@ -1686,56 +1708,186 @@ static int rcu_torture_fwd_prog(void *args)
 	int sd4;
 	bool selfpropcb = false;
 	unsigned long stopat;
-	int tested = 0;
-	int tested_tries = 0;
 	static DEFINE_TORTURE_RANDOM(trs);
 
-	VERBOSE_TOROUT_STRING("rcu_torture_fwd_progress task started");
-	if (!IS_ENABLED(CONFIG_SMP) || !IS_ENABLED(CONFIG_RCU_BOOST))
-		set_user_nice(current, MAX_NICE);
 	if  (cur_ops->call && cur_ops->sync && cur_ops->cb_barrier) {
 		init_rcu_head_on_stack(&fcs.rh);
 		selfpropcb = true;
 	}
+
+	/* Tight loop containing cond_resched(). */
+	if  (selfpropcb) {
+		WRITE_ONCE(fcs.stop, 0);
+		cur_ops->call(&fcs.rh, rcu_torture_fwd_prog_cb);
+	}
+	cver = READ_ONCE(rcu_torture_current_version);
+	gps = cur_ops->get_gp_seq();
+	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;
+	while (time_before(jiffies, stopat) &&
+	       !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
+		idx = cur_ops->readlock();
+		udelay(10);
+		cur_ops->readunlock(idx);
+		if (!fwd_progress_need_resched || need_resched())
+			cond_resched();
+	}
+	(*tested_tries)++;
+	if (!time_before(jiffies, stopat) &&
+	    !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
+		(*tested)++;
+		cver = READ_ONCE(rcu_torture_current_version) - cver;
+		gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
+		WARN_ON(!cver && gps < 2);
+		pr_alert("%s: Duration %ld cver %ld gps %ld\n", __func__, dur, cver, gps);
+	}
+	if (selfpropcb) {
+		WRITE_ONCE(fcs.stop, 1);
+		cur_ops->sync(); /* Wait for running CB to complete. */
+		cur_ops->cb_barrier(); /* Wait for queued callbacks. */
+	}
+
+	if (selfpropcb) {
+		WARN_ON(READ_ONCE(fcs.stop) != 2);
+		destroy_rcu_head_on_stack(&fcs.rh);
+	}
+}
+
+/* Carry out call_rcu() forward-progress testing. */
+static void rcu_torture_fwd_prog_cr(void)
+{
+	unsigned long cver;
+	unsigned long gps;
+	int i;
+	long n_launders;
+	long n_launders_cb_snap;
+	long n_launders_sa;
+	long n_max_cbs;
+	long n_max_gps;
+	struct rcu_fwd_cb *rfcp;
+	struct rcu_fwd_cb *rfcpn;
+	unsigned long stopat;
+	unsigned long stoppedat;
+
+	if (READ_ONCE(rcu_fwd_emergency_stop))
+		return; /* Get out of the way quickly, no GP wait! */
+
+	/* 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;
+	n_launders = 0;
+	n_launders_cb = 0;
+	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] = 0;
+	cver = READ_ONCE(rcu_torture_current_version);
+	gps = cur_ops->get_gp_seq();
+	while (time_before(jiffies, stopat) &&
+	       !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
+		rfcp = READ_ONCE(rcu_fwd_cb_head);
+		rfcpn = NULL;
+		if (rfcp)
+			rfcpn = READ_ONCE(rfcp->rfc_next);
+		if (rfcpn) {
+			if (rfcp->rfc_gps >= MIN_FWD_CB_LAUNDERS &&
+			    ++n_max_gps >= MIN_FWD_CBS_LAUNDERED)
+				break;
+			rcu_fwd_cb_head = rfcpn;
+			n_launders++;
+			n_launders_sa++;
+		} else {
+			rfcp = kmalloc(sizeof(*rfcp), GFP_KERNEL);
+			if (WARN_ON_ONCE(!rfcp)) {
+				schedule_timeout_interruptible(1);
+				continue;
+			}
+			n_max_cbs++;
+			n_launders_sa = 0;
+			rfcp->rfc_gps = 0;
+		}
+		cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr);
+		cond_resched();
+	}
+	stoppedat = jiffies;
+	n_launders_cb_snap = READ_ONCE(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();
+
+	WRITE_ONCE(rcu_fwd_cb_nodelay, false);
+	if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop)) {
+		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,
+			 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();
+	}
+}
+
+
+/*
+ * OOM notifier, but this only prints diagnostic information for the
+ * current forward-progress test.
+ */
+static int rcutorture_oom_notify(struct notifier_block *self,
+				 unsigned long notused, void *nfreed)
+{
+	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));
+	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());
+	rcu_barrier();
+	pr_info("%s: Freed %lu RCU callbacks.\n",
+		__func__, rcu_torture_fwd_prog_cbfree());
+	rcu_barrier();
+	pr_info("%s: Freed %lu RCU callbacks.\n",
+		__func__, rcu_torture_fwd_prog_cbfree());
+	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__);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block rcutorture_oom_nb = {
+	.notifier_call = rcutorture_oom_notify
+};
+
+/* Carry out grace-period forward-progress testing. */
+static int rcu_torture_fwd_prog(void *args)
+{
+	int tested = 0;
+	int tested_tries = 0;
+
+	VERBOSE_TOROUT_STRING("rcu_torture_fwd_progress task started");
+	rcu_bind_current_to_nocb();
+	if (!IS_ENABLED(CONFIG_SMP) || !IS_ENABLED(CONFIG_RCU_BOOST))
+		set_user_nice(current, MAX_NICE);
 	do {
 		schedule_timeout_interruptible(fwd_progress_holdoff * HZ);
-		if  (selfpropcb) {
-			WRITE_ONCE(fcs.stop, 0);
-			cur_ops->call(&fcs.rh, rcu_torture_fwd_prog_cb);
-		}
-		cver = READ_ONCE(rcu_torture_current_version);
-		gps = cur_ops->get_gp_seq();
-		sd = cur_ops->stall_dur() + 1;
-		sd4 = (sd + fwd_progress_div - 1) / fwd_progress_div;
-		dur = sd4 + torture_random(&trs) % (sd - sd4);
-		stopat = jiffies + dur;
-		while (time_before(jiffies, stopat) && !torture_must_stop()) {
-			idx = cur_ops->readlock();
-			udelay(10);
-			cur_ops->readunlock(idx);
-			if (!fwd_progress_need_resched || need_resched())
-				cond_resched();
-		}
-		tested_tries++;
-		if (!time_before(jiffies, stopat) && !torture_must_stop()) {
-			tested++;
-			cver = READ_ONCE(rcu_torture_current_version) - cver;
-			gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
-			WARN_ON(!cver && gps < 2);
-			pr_alert("%s: Duration %ld cver %ld gps %ld\n", __func__, dur, cver, gps);
-		}
-		if (selfpropcb) {
-			WRITE_ONCE(fcs.stop, 1);
-			cur_ops->sync(); /* Wait for running CB to complete. */
-			cur_ops->cb_barrier(); /* Wait for queued callbacks. */
-		}
+		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();
+		unregister_oom_notifier(&rcutorture_oom_nb);
+
 		/* Avoid slow periods, better to test when busy. */
 		stutter_wait("rcu_torture_fwd_prog");
 	} while (!torture_must_stop());
-	if (selfpropcb) {
-		WARN_ON(READ_ONCE(fcs.stop) != 2);
-		destroy_rcu_head_on_stack(&fcs.rh);
-	}
 	/* Short runs might not contain a valid forward-progress attempt. */
 	WARN_ON(!tested && tested_tries >= 5);
 	pr_alert("%s: tested %d tested_tries %d\n", __func__, tested, tested_tries);
@@ -1748,7 +1900,8 @@ static int __init rcu_torture_fwd_prog_init(void)
 {
 	if (!fwd_progress)
 		return 0; /* Not requested, so don't do it. */
-	if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0) {
+	if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0 ||
+	    cur_ops == &rcu_busted_ops) {
 		VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, unsupported by RCU flavor under test");
 		return 0;
 	}
@@ -1968,8 +2121,6 @@ rcu_torture_cleanup(void)
 		 cur_ops->name, gp_seq, flags);
 	torture_stop_kthread(rcu_torture_stats, stats_task);
 	torture_stop_kthread(rcu_torture_fqs, fqs_task);
-	for (i = 0; i < ncbflooders; i++)
-		torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]);
 	if (rcu_torture_can_boost())
 		cpuhp_remove_state(rcutor_hp);
 
@@ -2252,24 +2403,6 @@ rcu_torture_init(void)
 		goto unwind;
 	if (object_debug)
 		rcu_test_debug_objects();
-	if (cbflood_n_burst > 0) {
-		/* Create the cbflood threads */
-		ncbflooders = (num_online_cpus() + 3) / 4;
-		cbflood_task = kcalloc(ncbflooders, sizeof(*cbflood_task),
-				       GFP_KERNEL);
-		if (!cbflood_task) {
-			VERBOSE_TOROUT_ERRSTRING("out of memory");
-			firsterr = -ENOMEM;
-			goto unwind;
-		}
-		for (i = 0; i < ncbflooders; i++) {
-			firsterr = torture_create_kthread(rcu_torture_cbflood,
-							  NULL,
-							  cbflood_task[i]);
-			if (firsterr)
-				goto unwind;
-		}
-	}
 	torture_init_end();
 	return 0;
 
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index b46e6683f8c9..32dfd6522548 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -37,30 +37,30 @@ int rcu_scheduler_active __read_mostly;
 static LIST_HEAD(srcu_boot_list);
 static bool srcu_init_done;
 
-static int init_srcu_struct_fields(struct srcu_struct *sp)
+static int init_srcu_struct_fields(struct srcu_struct *ssp)
 {
-	sp->srcu_lock_nesting[0] = 0;
-	sp->srcu_lock_nesting[1] = 0;
-	init_swait_queue_head(&sp->srcu_wq);
-	sp->srcu_cb_head = NULL;
-	sp->srcu_cb_tail = &sp->srcu_cb_head;
-	sp->srcu_gp_running = false;
-	sp->srcu_gp_waiting = false;
-	sp->srcu_idx = 0;
-	INIT_WORK(&sp->srcu_work, srcu_drive_gp);
-	INIT_LIST_HEAD(&sp->srcu_work.entry);
+	ssp->srcu_lock_nesting[0] = 0;
+	ssp->srcu_lock_nesting[1] = 0;
+	init_swait_queue_head(&ssp->srcu_wq);
+	ssp->srcu_cb_head = NULL;
+	ssp->srcu_cb_tail = &ssp->srcu_cb_head;
+	ssp->srcu_gp_running = false;
+	ssp->srcu_gp_waiting = false;
+	ssp->srcu_idx = 0;
+	INIT_WORK(&ssp->srcu_work, srcu_drive_gp);
+	INIT_LIST_HEAD(&ssp->srcu_work.entry);
 	return 0;
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
-int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+int __init_srcu_struct(struct srcu_struct *ssp, const char *name,
 		       struct lock_class_key *key)
 {
 	/* Don't re-initialize a lock while it is held. */
-	debug_check_no_locks_freed((void *)sp, sizeof(*sp));
-	lockdep_init_map(&sp->dep_map, name, key, 0);
-	return init_srcu_struct_fields(sp);
+	debug_check_no_locks_freed((void *)ssp, sizeof(*ssp));
+	lockdep_init_map(&ssp->dep_map, name, key, 0);
+	return init_srcu_struct_fields(ssp);
 }
 EXPORT_SYMBOL_GPL(__init_srcu_struct);
 
@@ -68,15 +68,15 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct);
 
 /*
  * init_srcu_struct - initialize a sleep-RCU structure
- * @sp: structure to initialize.
+ * @ssp: structure to initialize.
  *
  * Must invoke this on a given srcu_struct before passing that srcu_struct
  * to any other function.  Each srcu_struct represents a separate domain
  * of SRCU protection.
  */
-int init_srcu_struct(struct srcu_struct *sp)
+int init_srcu_struct(struct srcu_struct *ssp)
 {
-	return init_srcu_struct_fields(sp);
+	return init_srcu_struct_fields(ssp);
 }
 EXPORT_SYMBOL_GPL(init_srcu_struct);
 
@@ -84,22 +84,22 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
 
 /*
  * cleanup_srcu_struct - deconstruct a sleep-RCU structure
- * @sp: structure to clean up.
+ * @ssp: structure to clean up.
  *
  * Must invoke this after you are finished using a given srcu_struct that
  * was initialized via init_srcu_struct(), else you leak memory.
  */
-void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
+void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
 {
-	WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]);
+	WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]);
 	if (quiesced)
-		WARN_ON(work_pending(&sp->srcu_work));
+		WARN_ON(work_pending(&ssp->srcu_work));
 	else
-		flush_work(&sp->srcu_work);
-	WARN_ON(sp->srcu_gp_running);
-	WARN_ON(sp->srcu_gp_waiting);
-	WARN_ON(sp->srcu_cb_head);
-	WARN_ON(&sp->srcu_cb_head != sp->srcu_cb_tail);
+		flush_work(&ssp->srcu_work);
+	WARN_ON(ssp->srcu_gp_running);
+	WARN_ON(ssp->srcu_gp_waiting);
+	WARN_ON(ssp->srcu_cb_head);
+	WARN_ON(&ssp->srcu_cb_head != ssp->srcu_cb_tail);
 }
 EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
 
@@ -107,13 +107,13 @@ EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
  * Removes the count for the old reader from the appropriate element of
  * the srcu_struct.
  */
-void __srcu_read_unlock(struct srcu_struct *sp, int idx)
+void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
 {
-	int newval = sp->srcu_lock_nesting[idx] - 1;
+	int newval = ssp->srcu_lock_nesting[idx] - 1;
 
-	WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
-	if (!newval && READ_ONCE(sp->srcu_gp_waiting))
-		swake_up_one(&sp->srcu_wq);
+	WRITE_ONCE(ssp->srcu_lock_nesting[idx], newval);
+	if (!newval && READ_ONCE(ssp->srcu_gp_waiting))
+		swake_up_one(&ssp->srcu_wq);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
@@ -127,24 +127,24 @@ void srcu_drive_gp(struct work_struct *wp)
 	int idx;
 	struct rcu_head *lh;
 	struct rcu_head *rhp;
-	struct srcu_struct *sp;
+	struct srcu_struct *ssp;
 
-	sp = container_of(wp, struct srcu_struct, srcu_work);
-	if (sp->srcu_gp_running || !READ_ONCE(sp->srcu_cb_head))
+	ssp = container_of(wp, struct srcu_struct, srcu_work);
+	if (ssp->srcu_gp_running || !READ_ONCE(ssp->srcu_cb_head))
 		return; /* Already running or nothing to do. */
 
 	/* Remove recently arrived callbacks and wait for readers. */
-	WRITE_ONCE(sp->srcu_gp_running, true);
+	WRITE_ONCE(ssp->srcu_gp_running, true);
 	local_irq_disable();
-	lh = sp->srcu_cb_head;
-	sp->srcu_cb_head = NULL;
-	sp->srcu_cb_tail = &sp->srcu_cb_head;
+	lh = ssp->srcu_cb_head;
+	ssp->srcu_cb_head = NULL;
+	ssp->srcu_cb_tail = &ssp->srcu_cb_head;
 	local_irq_enable();
-	idx = sp->srcu_idx;
-	WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
-	WRITE_ONCE(sp->srcu_gp_waiting, true);  /* srcu_read_unlock() wakes! */
-	swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
-	WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
+	idx = ssp->srcu_idx;
+	WRITE_ONCE(ssp->srcu_idx, !ssp->srcu_idx);
+	WRITE_ONCE(ssp->srcu_gp_waiting, true);  /* srcu_read_unlock() wakes! */
+	swait_event_exclusive(ssp->srcu_wq, !READ_ONCE(ssp->srcu_lock_nesting[idx]));
+	WRITE_ONCE(ssp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
 
 	/* Invoke the callbacks we removed above. */
 	while (lh) {
@@ -161,9 +161,9 @@ void srcu_drive_gp(struct work_struct *wp)
 	 * at interrupt level, but the ->srcu_gp_running checks will
 	 * straighten that out.
 	 */
-	WRITE_ONCE(sp->srcu_gp_running, false);
-	if (READ_ONCE(sp->srcu_cb_head))
-		schedule_work(&sp->srcu_work);
+	WRITE_ONCE(ssp->srcu_gp_running, false);
+	if (READ_ONCE(ssp->srcu_cb_head))
+		schedule_work(&ssp->srcu_work);
 }
 EXPORT_SYMBOL_GPL(srcu_drive_gp);
 
@@ -171,7 +171,7 @@ EXPORT_SYMBOL_GPL(srcu_drive_gp);
  * Enqueue an SRCU callback on the specified srcu_struct structure,
  * initiating grace-period processing if it is not already running.
  */
-void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
+void call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 	       rcu_callback_t func)
 {
 	unsigned long flags;
@@ -179,14 +179,14 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
 	rhp->func = func;
 	rhp->next = NULL;
 	local_irq_save(flags);
-	*sp->srcu_cb_tail = rhp;
-	sp->srcu_cb_tail = &rhp->next;
+	*ssp->srcu_cb_tail = rhp;
+	ssp->srcu_cb_tail = &rhp->next;
 	local_irq_restore(flags);
-	if (!READ_ONCE(sp->srcu_gp_running)) {
+	if (!READ_ONCE(ssp->srcu_gp_running)) {
 		if (likely(srcu_init_done))
-			schedule_work(&sp->srcu_work);
-		else if (list_empty(&sp->srcu_work.entry))
-			list_add(&sp->srcu_work.entry, &srcu_boot_list);
+			schedule_work(&ssp->srcu_work);
+		else if (list_empty(&ssp->srcu_work.entry))
+			list_add(&ssp->srcu_work.entry, &srcu_boot_list);
 	}
 }
 EXPORT_SYMBOL_GPL(call_srcu);
@@ -194,13 +194,13 @@ EXPORT_SYMBOL_GPL(call_srcu);
 /*
  * synchronize_srcu - wait for prior SRCU read-side critical-section completion
  */
-void synchronize_srcu(struct srcu_struct *sp)
+void synchronize_srcu(struct srcu_struct *ssp)
 {
 	struct rcu_synchronize rs;
 
 	init_rcu_head_on_stack(&rs.head);
 	init_completion(&rs.completion);
-	call_srcu(sp, &rs.head, wakeme_after_rcu);
+	call_srcu(ssp, &rs.head, wakeme_after_rcu);
 	wait_for_completion(&rs.completion);
 	destroy_rcu_head_on_stack(&rs.head);
 }
@@ -219,13 +219,13 @@ void __init rcu_scheduler_starting(void)
  */
 void __init srcu_init(void)
 {
-	struct srcu_struct *sp;
+	struct srcu_struct *ssp;
 
 	srcu_init_done = true;
 	while (!list_empty(&srcu_boot_list)) {
-		sp = list_first_entry(&srcu_boot_list,
+		ssp = list_first_entry(&srcu_boot_list,
 				      struct srcu_struct, srcu_work.entry);
-		list_del_init(&sp->srcu_work.entry);
-		schedule_work(&sp->srcu_work);
+		list_del_init(&ssp->srcu_work.entry);
+		schedule_work(&ssp->srcu_work);
 	}
 }
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index a8846ed7f352..3600d88d8956 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -56,7 +56,7 @@ static LIST_HEAD(srcu_boot_list);
 static bool __read_mostly srcu_init_done;
 
 static void srcu_invoke_callbacks(struct work_struct *work);
-static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);
+static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay);
 static void process_srcu(struct work_struct *work);
 
 /* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
@@ -92,7 +92,7 @@ do {									\
  * srcu_read_unlock() running against them.  So if the is_static parameter
  * is set, don't initialize ->srcu_lock_count[] and ->srcu_unlock_count[].
  */
-static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
+static void init_srcu_struct_nodes(struct srcu_struct *ssp, bool is_static)
 {
 	int cpu;
 	int i;
@@ -103,13 +103,13 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
 	struct srcu_node *snp_first;
 
 	/* Work out the overall tree geometry. */
-	sp->level[0] = &sp->node[0];
+	ssp->level[0] = &ssp->node[0];
 	for (i = 1; i < rcu_num_lvls; i++)
-		sp->level[i] = sp->level[i - 1] + num_rcu_lvl[i - 1];
+		ssp->level[i] = ssp->level[i - 1] + num_rcu_lvl[i - 1];
 	rcu_init_levelspread(levelspread, num_rcu_lvl);
 
 	/* Each pass through this loop initializes one srcu_node structure. */
-	srcu_for_each_node_breadth_first(sp, snp) {
+	srcu_for_each_node_breadth_first(ssp, snp) {
 		spin_lock_init(&ACCESS_PRIVATE(snp, lock));
 		WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
 			     ARRAY_SIZE(snp->srcu_data_have_cbs));
@@ -120,17 +120,17 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
 		snp->srcu_gp_seq_needed_exp = 0;
 		snp->grplo = -1;
 		snp->grphi = -1;
-		if (snp == &sp->node[0]) {
+		if (snp == &ssp->node[0]) {
 			/* Root node, special case. */
 			snp->srcu_parent = NULL;
 			continue;
 		}
 
 		/* Non-root node. */
-		if (snp == sp->level[level + 1])
+		if (snp == ssp->level[level + 1])
 			level++;
-		snp->srcu_parent = sp->level[level - 1] +
-				   (snp - sp->level[level]) /
+		snp->srcu_parent = ssp->level[level - 1] +
+				   (snp - ssp->level[level]) /
 				   levelspread[level - 1];
 	}
 
@@ -141,14 +141,14 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
 	WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
 		     ARRAY_SIZE(sdp->srcu_unlock_count));
 	level = rcu_num_lvls - 1;
-	snp_first = sp->level[level];
+	snp_first = ssp->level[level];
 	for_each_possible_cpu(cpu) {
-		sdp = per_cpu_ptr(sp->sda, cpu);
+		sdp = per_cpu_ptr(ssp->sda, cpu);
 		spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
 		rcu_segcblist_init(&sdp->srcu_cblist);
 		sdp->srcu_cblist_invoking = false;
-		sdp->srcu_gp_seq_needed = sp->srcu_gp_seq;
-		sdp->srcu_gp_seq_needed_exp = sp->srcu_gp_seq;
+		sdp->srcu_gp_seq_needed = ssp->srcu_gp_seq;
+		sdp->srcu_gp_seq_needed_exp = ssp->srcu_gp_seq;
 		sdp->mynode = &snp_first[cpu / levelspread[level]];
 		for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) {
 			if (snp->grplo < 0)
@@ -157,7 +157,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
 		}
 		sdp->cpu = cpu;
 		INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks);
-		sdp->sp = sp;
+		sdp->ssp = ssp;
 		sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
 		if (is_static)
 			continue;
@@ -176,35 +176,35 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
  * parameter is passed through to init_srcu_struct_nodes(), and
  * also tells us that ->sda has already been wired up to srcu_data.
  */
-static int init_srcu_struct_fields(struct srcu_struct *sp, bool is_static)
+static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 {
-	mutex_init(&sp->srcu_cb_mutex);
-	mutex_init(&sp->srcu_gp_mutex);
-	sp->srcu_idx = 0;
-	sp->srcu_gp_seq = 0;
-	sp->srcu_barrier_seq = 0;
-	mutex_init(&sp->srcu_barrier_mutex);
-	atomic_set(&sp->srcu_barrier_cpu_cnt, 0);
-	INIT_DELAYED_WORK(&sp->work, process_srcu);
+	mutex_init(&ssp->srcu_cb_mutex);
+	mutex_init(&ssp->srcu_gp_mutex);
+	ssp->srcu_idx = 0;
+	ssp->srcu_gp_seq = 0;
+	ssp->srcu_barrier_seq = 0;
+	mutex_init(&ssp->srcu_barrier_mutex);
+	atomic_set(&ssp->srcu_barrier_cpu_cnt, 0);
+	INIT_DELAYED_WORK(&ssp->work, process_srcu);
 	if (!is_static)
-		sp->sda = alloc_percpu(struct srcu_data);
-	init_srcu_struct_nodes(sp, is_static);
-	sp->srcu_gp_seq_needed_exp = 0;
-	sp->srcu_last_gp_end = ktime_get_mono_fast_ns();
-	smp_store_release(&sp->srcu_gp_seq_needed, 0); /* Init done. */
-	return sp->sda ? 0 : -ENOMEM;
+		ssp->sda = alloc_percpu(struct srcu_data);
+	init_srcu_struct_nodes(ssp, is_static);
+	ssp->srcu_gp_seq_needed_exp = 0;
+	ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
+	smp_store_release(&ssp->srcu_gp_seq_needed, 0); /* Init done. */
+	return ssp->sda ? 0 : -ENOMEM;
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
-int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+int __init_srcu_struct(struct srcu_struct *ssp, const char *name,
 		       struct lock_class_key *key)
 {
 	/* Don't re-initialize a lock while it is held. */
-	debug_check_no_locks_freed((void *)sp, sizeof(*sp));
-	lockdep_init_map(&sp->dep_map, name, key, 0);
-	spin_lock_init(&ACCESS_PRIVATE(sp, lock));
-	return init_srcu_struct_fields(sp, false);
+	debug_check_no_locks_freed((void *)ssp, sizeof(*ssp));
+	lockdep_init_map(&ssp->dep_map, name, key, 0);
+	spin_lock_init(&ACCESS_PRIVATE(ssp, lock));
+	return init_srcu_struct_fields(ssp, false);
 }
 EXPORT_SYMBOL_GPL(__init_srcu_struct);
 
@@ -212,16 +212,16 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct);
 
 /**
  * init_srcu_struct - initialize a sleep-RCU structure
- * @sp: structure to initialize.
+ * @ssp: structure to initialize.
  *
  * Must invoke this on a given srcu_struct before passing that srcu_struct
  * to any other function.  Each srcu_struct represents a separate domain
  * of SRCU protection.
  */
-int init_srcu_struct(struct srcu_struct *sp)
+int init_srcu_struct(struct srcu_struct *ssp)
 {
-	spin_lock_init(&ACCESS_PRIVATE(sp, lock));
-	return init_srcu_struct_fields(sp, false);
+	spin_lock_init(&ACCESS_PRIVATE(ssp, lock));
+	return init_srcu_struct_fields(ssp, false);
 }
 EXPORT_SYMBOL_GPL(init_srcu_struct);
 
@@ -231,37 +231,37 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
  * First-use initialization of statically allocated srcu_struct
  * structure.  Wiring up the combining tree is more than can be
  * done with compile-time initialization, so this check is added
- * to each update-side SRCU primitive.  Use sp->lock, which -is-
+ * to each update-side SRCU primitive.  Use ssp->lock, which -is-
  * compile-time initialized, to resolve races involving multiple
  * CPUs trying to garner first-use privileges.
  */
-static void check_init_srcu_struct(struct srcu_struct *sp)
+static void check_init_srcu_struct(struct srcu_struct *ssp)
 {
 	unsigned long flags;
 
 	/* The smp_load_acquire() pairs with the smp_store_release(). */
-	if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/
+	if (!rcu_seq_state(smp_load_acquire(&ssp->srcu_gp_seq_needed))) /*^^^*/
 		return; /* Already initialized. */
-	spin_lock_irqsave_rcu_node(sp, flags);
-	if (!rcu_seq_state(sp->srcu_gp_seq_needed)) {
-		spin_unlock_irqrestore_rcu_node(sp, flags);
+	spin_lock_irqsave_rcu_node(ssp, flags);
+	if (!rcu_seq_state(ssp->srcu_gp_seq_needed)) {
+		spin_unlock_irqrestore_rcu_node(ssp, flags);
 		return;
 	}
-	init_srcu_struct_fields(sp, true);
-	spin_unlock_irqrestore_rcu_node(sp, flags);
+	init_srcu_struct_fields(ssp, true);
+	spin_unlock_irqrestore_rcu_node(ssp, flags);
 }
 
 /*
  * Returns approximate total of the readers' ->srcu_lock_count[] values
  * for the rank of per-CPU counters specified by idx.
  */
-static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
+static unsigned long srcu_readers_lock_idx(struct srcu_struct *ssp, int idx)
 {
 	int cpu;
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
 
 		sum += READ_ONCE(cpuc->srcu_lock_count[idx]);
 	}
@@ -272,13 +272,13 @@ static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
  * Returns approximate total of the readers' ->srcu_unlock_count[] values
  * for the rank of per-CPU counters specified by idx.
  */
-static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
 {
 	int cpu;
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
 
 		sum += READ_ONCE(cpuc->srcu_unlock_count[idx]);
 	}
@@ -289,11 +289,11 @@ static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
  * Return true if the number of pre-existing readers is determined to
  * be zero.
  */
-static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
+static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
 {
 	unsigned long unlocks;
 
-	unlocks = srcu_readers_unlock_idx(sp, idx);
+	unlocks = srcu_readers_unlock_idx(ssp, idx);
 
 	/*
 	 * Make sure that a lock is always counted if the corresponding
@@ -329,25 +329,25 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
 	 * of floor(ULONG_MAX/NR_CPUS/2), which should be sufficient,
 	 * especially on 64-bit systems.
 	 */
-	return srcu_readers_lock_idx(sp, idx) == unlocks;
+	return srcu_readers_lock_idx(ssp, idx) == unlocks;
 }
 
 /**
  * srcu_readers_active - returns true if there are readers. and false
  *                       otherwise
- * @sp: which srcu_struct to count active readers (holding srcu_read_lock).
+ * @ssp: which srcu_struct to count active readers (holding srcu_read_lock).
  *
  * Note that this is not an atomic primitive, and can therefore suffer
  * severe errors when invoked on an active srcu_struct.  That said, it
  * can be useful as an error check at cleanup time.
  */
-static bool srcu_readers_active(struct srcu_struct *sp)
+static bool srcu_readers_active(struct srcu_struct *ssp)
 {
 	int cpu;
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
 
 		sum += READ_ONCE(cpuc->srcu_lock_count[0]);
 		sum += READ_ONCE(cpuc->srcu_lock_count[1]);
@@ -363,44 +363,44 @@ static bool srcu_readers_active(struct srcu_struct *sp)
  * Return grace-period delay, zero if there are expedited grace
  * periods pending, SRCU_INTERVAL otherwise.
  */
-static unsigned long srcu_get_delay(struct srcu_struct *sp)
+static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 {
-	if (ULONG_CMP_LT(READ_ONCE(sp->srcu_gp_seq),
-			 READ_ONCE(sp->srcu_gp_seq_needed_exp)))
+	if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq),
+			 READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
 		return 0;
 	return SRCU_INTERVAL;
 }
 
 /* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */
-void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
+void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
 {
 	int cpu;
 
-	if (WARN_ON(!srcu_get_delay(sp)))
+	if (WARN_ON(!srcu_get_delay(ssp)))
 		return; /* Just leak it! */
-	if (WARN_ON(srcu_readers_active(sp)))
+	if (WARN_ON(srcu_readers_active(ssp)))
 		return; /* Just leak it! */
 	if (quiesced) {
-		if (WARN_ON(delayed_work_pending(&sp->work)))
+		if (WARN_ON(delayed_work_pending(&ssp->work)))
 			return; /* Just leak it! */
 	} else {
-		flush_delayed_work(&sp->work);
+		flush_delayed_work(&ssp->work);
 	}
 	for_each_possible_cpu(cpu)
 		if (quiesced) {
-			if (WARN_ON(delayed_work_pending(&per_cpu_ptr(sp->sda, cpu)->work)))
+			if (WARN_ON(delayed_work_pending(&per_cpu_ptr(ssp->sda, cpu)->work)))
 				return; /* Just leak it! */
 		} else {
-			flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+			flush_delayed_work(&per_cpu_ptr(ssp->sda, cpu)->work);
 		}
-	if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
-	    WARN_ON(srcu_readers_active(sp))) {
+	if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
+	    WARN_ON(srcu_readers_active(ssp))) {
 		pr_info("%s: Active srcu_struct %p state: %d\n",
-			__func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+			__func__, ssp, rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)));
 		return; /* Caller forgot to stop doing call_srcu()? */
 	}
-	free_percpu(sp->sda);
-	sp->sda = NULL;
+	free_percpu(ssp->sda);
+	ssp->sda = NULL;
 }
 EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
 
@@ -409,12 +409,12 @@ EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
  * srcu_struct.
  * Returns an index that must be passed to the matching srcu_read_unlock().
  */
-int __srcu_read_lock(struct srcu_struct *sp)
+int __srcu_read_lock(struct srcu_struct *ssp)
 {
 	int idx;
 
-	idx = READ_ONCE(sp->srcu_idx) & 0x1;
-	this_cpu_inc(sp->sda->srcu_lock_count[idx]);
+	idx = READ_ONCE(ssp->srcu_idx) & 0x1;
+	this_cpu_inc(ssp->sda->srcu_lock_count[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
 	return idx;
 }
@@ -425,10 +425,10 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
  * element of the srcu_struct.  Note that this may well be a different
  * CPU than that which was incremented by the corresponding srcu_read_lock().
  */
-void __srcu_read_unlock(struct srcu_struct *sp, int idx)
+void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
 {
 	smp_mb(); /* C */  /* Avoid leaking the critical section. */
-	this_cpu_inc(sp->sda->srcu_unlock_count[idx]);
+	this_cpu_inc(ssp->sda->srcu_unlock_count[idx]);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
@@ -444,20 +444,22 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 /*
  * Start an SRCU grace period.
  */
-static void srcu_gp_start(struct srcu_struct *sp)
+static void srcu_gp_start(struct srcu_struct *ssp)
 {
-	struct srcu_data *sdp = this_cpu_ptr(sp->sda);
+	struct srcu_data *sdp = this_cpu_ptr(ssp->sda);
 	int state;
 
-	lockdep_assert_held(&ACCESS_PRIVATE(sp, lock));
-	WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
+	lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock));
+	WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed));
+	spin_lock_rcu_node(sdp);  /* Interrupts already disabled. */
 	rcu_segcblist_advance(&sdp->srcu_cblist,
-			      rcu_seq_current(&sp->srcu_gp_seq));
+			      rcu_seq_current(&ssp->srcu_gp_seq));
 	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
-				       rcu_seq_snap(&sp->srcu_gp_seq));
+				       rcu_seq_snap(&ssp->srcu_gp_seq));
+	spin_unlock_rcu_node(sdp);  /* Interrupts remain disabled. */
 	smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
-	rcu_seq_start(&sp->srcu_gp_seq);
-	state = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
+	rcu_seq_start(&ssp->srcu_gp_seq);
+	state = rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq));
 	WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
 }
 
@@ -511,7 +513,7 @@ static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
  * just-completed grace period, the one corresponding to idx.  If possible,
  * schedule this invocation on the corresponding CPUs.
  */
-static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp,
+static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp,
 				  unsigned long mask, unsigned long delay)
 {
 	int cpu;
@@ -519,7 +521,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp,
 	for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
 		if (!(mask & (1 << (cpu - snp->grplo))))
 			continue;
-		srcu_schedule_cbs_sdp(per_cpu_ptr(sp->sda, cpu), delay);
+		srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay);
 	}
 }
 
@@ -532,7 +534,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp,
  * are initiating callback invocation.  This allows the ->srcu_have_cbs[]
  * array to have a finite number of elements.
  */
-static void srcu_gp_end(struct srcu_struct *sp)
+static void srcu_gp_end(struct srcu_struct *ssp)
 {
 	unsigned long cbdelay;
 	bool cbs;
@@ -546,28 +548,28 @@ static void srcu_gp_end(struct srcu_struct *sp)
 	struct srcu_node *snp;
 
 	/* Prevent more than one additional grace period. */
-	mutex_lock(&sp->srcu_cb_mutex);
+	mutex_lock(&ssp->srcu_cb_mutex);
 
 	/* End the current grace period. */
-	spin_lock_irq_rcu_node(sp);
-	idx = rcu_seq_state(sp->srcu_gp_seq);
+	spin_lock_irq_rcu_node(ssp);
+	idx = rcu_seq_state(ssp->srcu_gp_seq);
 	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
-	cbdelay = srcu_get_delay(sp);
-	sp->srcu_last_gp_end = ktime_get_mono_fast_ns();
-	rcu_seq_end(&sp->srcu_gp_seq);
-	gpseq = rcu_seq_current(&sp->srcu_gp_seq);
-	if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, gpseq))
-		sp->srcu_gp_seq_needed_exp = gpseq;
-	spin_unlock_irq_rcu_node(sp);
-	mutex_unlock(&sp->srcu_gp_mutex);
+	cbdelay = srcu_get_delay(ssp);
+	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))
+		ssp->srcu_gp_seq_needed_exp = gpseq;
+	spin_unlock_irq_rcu_node(ssp);
+	mutex_unlock(&ssp->srcu_gp_mutex);
 	/* A new grace period can start at this point.  But only one. */
 
 	/* Initiate callback invocation as needed. */
 	idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
-	srcu_for_each_node_breadth_first(sp, snp) {
+	srcu_for_each_node_breadth_first(ssp, snp) {
 		spin_lock_irq_rcu_node(snp);
 		cbs = false;
-		last_lvl = snp >= sp->level[rcu_num_lvls - 1];
+		last_lvl = snp >= ssp->level[rcu_num_lvls - 1];
 		if (last_lvl)
 			cbs = snp->srcu_have_cbs[idx] == gpseq;
 		snp->srcu_have_cbs[idx] = gpseq;
@@ -578,12 +580,12 @@ static void srcu_gp_end(struct srcu_struct *sp)
 		snp->srcu_data_have_cbs[idx] = 0;
 		spin_unlock_irq_rcu_node(snp);
 		if (cbs)
-			srcu_schedule_cbs_snp(sp, snp, mask, cbdelay);
+			srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay);
 
 		/* Occasionally prevent srcu_data counter wrap. */
 		if (!(gpseq & counter_wrap_check) && last_lvl)
 			for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
-				sdp = per_cpu_ptr(sp->sda, cpu);
+				sdp = per_cpu_ptr(ssp->sda, cpu);
 				spin_lock_irqsave_rcu_node(sdp, flags);
 				if (ULONG_CMP_GE(gpseq,
 						 sdp->srcu_gp_seq_needed + 100))
@@ -596,18 +598,18 @@ static void srcu_gp_end(struct srcu_struct *sp)
 	}
 
 	/* Callback initiation done, allow grace periods after next. */
-	mutex_unlock(&sp->srcu_cb_mutex);
+	mutex_unlock(&ssp->srcu_cb_mutex);
 
 	/* Start a new grace period if needed. */
-	spin_lock_irq_rcu_node(sp);
-	gpseq = rcu_seq_current(&sp->srcu_gp_seq);
+	spin_lock_irq_rcu_node(ssp);
+	gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
 	if (!rcu_seq_state(gpseq) &&
-	    ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) {
-		srcu_gp_start(sp);
-		spin_unlock_irq_rcu_node(sp);
-		srcu_reschedule(sp, 0);
+	    ULONG_CMP_LT(gpseq, ssp->srcu_gp_seq_needed)) {
+		srcu_gp_start(ssp);
+		spin_unlock_irq_rcu_node(ssp);
+		srcu_reschedule(ssp, 0);
 	} else {
-		spin_unlock_irq_rcu_node(sp);
+		spin_unlock_irq_rcu_node(ssp);
 	}
 }
 
@@ -618,13 +620,13 @@ static void srcu_gp_end(struct srcu_struct *sp)
  * but without expediting.  To start a completely new grace period,
  * whether expedited or not, use srcu_funnel_gp_start() instead.
  */
-static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
+static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp,
 				  unsigned long s)
 {
 	unsigned long flags;
 
 	for (; snp != NULL; snp = snp->srcu_parent) {
-		if (rcu_seq_done(&sp->srcu_gp_seq, s) ||
+		if (rcu_seq_done(&ssp->srcu_gp_seq, s) ||
 		    ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s))
 			return;
 		spin_lock_irqsave_rcu_node(snp, flags);
@@ -635,10 +637,10 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
 		WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
 		spin_unlock_irqrestore_rcu_node(snp, flags);
 	}
-	spin_lock_irqsave_rcu_node(sp, flags);
-	if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
-		sp->srcu_gp_seq_needed_exp = s;
-	spin_unlock_irqrestore_rcu_node(sp, flags);
+	spin_lock_irqsave_rcu_node(ssp, flags);
+	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
+		ssp->srcu_gp_seq_needed_exp = s;
+	spin_unlock_irqrestore_rcu_node(ssp, flags);
 }
 
 /*
@@ -651,7 +653,7 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
  * Note that this function also does the work of srcu_funnel_exp_start(),
  * in some cases by directly invoking it.
  */
-static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
+static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 				 unsigned long s, bool do_norm)
 {
 	unsigned long flags;
@@ -661,7 +663,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
 
 	/* Each pass through the loop does one level of the srcu_node tree. */
 	for (; snp != NULL; snp = snp->srcu_parent) {
-		if (rcu_seq_done(&sp->srcu_gp_seq, s) && snp != sdp->mynode)
+		if (rcu_seq_done(&ssp->srcu_gp_seq, s) && snp != sdp->mynode)
 			return; /* GP already done and CBs recorded. */
 		spin_lock_irqsave_rcu_node(snp, flags);
 		if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
@@ -676,7 +678,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
 				return;
 			}
 			if (!do_norm)
-				srcu_funnel_exp_start(sp, snp, s);
+				srcu_funnel_exp_start(ssp, snp, s);
 			return;
 		}
 		snp->srcu_have_cbs[idx] = s;
@@ -688,29 +690,29 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
 	}
 
 	/* Top of tree, must ensure the grace period will be started. */
-	spin_lock_irqsave_rcu_node(sp, flags);
-	if (ULONG_CMP_LT(sp->srcu_gp_seq_needed, s)) {
+	spin_lock_irqsave_rcu_node(ssp, flags);
+	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed, s)) {
 		/*
 		 * Record need for grace period s.  Pair with load
 		 * acquire setting up for initialization.
 		 */
-		smp_store_release(&sp->srcu_gp_seq_needed, s); /*^^^*/
+		smp_store_release(&ssp->srcu_gp_seq_needed, s); /*^^^*/
 	}
-	if (!do_norm && ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
-		sp->srcu_gp_seq_needed_exp = s;
+	if (!do_norm && ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
+		ssp->srcu_gp_seq_needed_exp = s;
 
 	/* If grace period not already done and none in progress, start it. */
-	if (!rcu_seq_done(&sp->srcu_gp_seq, s) &&
-	    rcu_seq_state(sp->srcu_gp_seq) == SRCU_STATE_IDLE) {
-		WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
-		srcu_gp_start(sp);
+	if (!rcu_seq_done(&ssp->srcu_gp_seq, s) &&
+	    rcu_seq_state(ssp->srcu_gp_seq) == SRCU_STATE_IDLE) {
+		WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed));
+		srcu_gp_start(ssp);
 		if (likely(srcu_init_done))
-			queue_delayed_work(rcu_gp_wq, &sp->work,
-					   srcu_get_delay(sp));
-		else if (list_empty(&sp->work.work.entry))
-			list_add(&sp->work.work.entry, &srcu_boot_list);
+			queue_delayed_work(rcu_gp_wq, &ssp->work,
+					   srcu_get_delay(ssp));
+		else if (list_empty(&ssp->work.work.entry))
+			list_add(&ssp->work.work.entry, &srcu_boot_list);
 	}
-	spin_unlock_irqrestore_rcu_node(sp, flags);
+	spin_unlock_irqrestore_rcu_node(ssp, flags);
 }
 
 /*
@@ -718,12 +720,12 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
  * loop an additional time if there is an expedited grace period pending.
  * The caller must ensure that ->srcu_idx is not changed while checking.
  */
-static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
+static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount)
 {
 	for (;;) {
-		if (srcu_readers_active_idx_check(sp, idx))
+		if (srcu_readers_active_idx_check(ssp, idx))
 			return true;
-		if (--trycount + !srcu_get_delay(sp) <= 0)
+		if (--trycount + !srcu_get_delay(ssp) <= 0)
 			return false;
 		udelay(SRCU_RETRY_CHECK_DELAY);
 	}
@@ -734,7 +736,7 @@ static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
  * use the other rank of the ->srcu_(un)lock_count[] arrays.  This allows
  * us to wait for pre-existing readers in a starvation-free manner.
  */
-static void srcu_flip(struct srcu_struct *sp)
+static void srcu_flip(struct srcu_struct *ssp)
 {
 	/*
 	 * Ensure that if this updater saw a given reader's increment
@@ -746,7 +748,7 @@ static void srcu_flip(struct srcu_struct *sp)
 	 */
 	smp_mb(); /* E */  /* Pairs with B and C. */
 
-	WRITE_ONCE(sp->srcu_idx, sp->srcu_idx + 1);
+	WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1);
 
 	/*
 	 * Ensure that if the updater misses an __srcu_read_unlock()
@@ -779,7 +781,7 @@ static void srcu_flip(struct srcu_struct *sp)
  * negligible when amoritized 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 *sp)
+static bool srcu_might_be_idle(struct srcu_struct *ssp)
 {
 	unsigned long curseq;
 	unsigned long flags;
@@ -788,7 +790,7 @@ static bool srcu_might_be_idle(struct srcu_struct *sp)
 
 	/* If the local srcu_data structure has callbacks, not idle.  */
 	local_irq_save(flags);
-	sdp = this_cpu_ptr(sp->sda);
+	sdp = this_cpu_ptr(ssp->sda);
 	if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
 		local_irq_restore(flags);
 		return false; /* Callbacks already present, so not idle. */
@@ -804,17 +806,17 @@ static bool srcu_might_be_idle(struct srcu_struct *sp)
 	/* First, see if enough time has passed since the last GP. */
 	t = ktime_get_mono_fast_ns();
 	if (exp_holdoff == 0 ||
-	    time_in_range_open(t, sp->srcu_last_gp_end,
-			       sp->srcu_last_gp_end + exp_holdoff))
+	    time_in_range_open(t, ssp->srcu_last_gp_end,
+			       ssp->srcu_last_gp_end + exp_holdoff))
 		return false; /* Too soon after last GP. */
 
 	/* Next, check for probable idleness. */
-	curseq = rcu_seq_current(&sp->srcu_gp_seq);
+	curseq = rcu_seq_current(&ssp->srcu_gp_seq);
 	smp_mb(); /* Order ->srcu_gp_seq with ->srcu_gp_seq_needed. */
-	if (ULONG_CMP_LT(curseq, READ_ONCE(sp->srcu_gp_seq_needed)))
+	if (ULONG_CMP_LT(curseq, READ_ONCE(ssp->srcu_gp_seq_needed)))
 		return false; /* Grace period in progress, so not idle. */
 	smp_mb(); /* Order ->srcu_gp_seq with prior access. */
-	if (curseq != rcu_seq_current(&sp->srcu_gp_seq))
+	if (curseq != rcu_seq_current(&ssp->srcu_gp_seq))
 		return false; /* GP # changed, so not idle. */
 	return true; /* With reasonable probability, idle! */
 }
@@ -854,16 +856,17 @@ static void srcu_leak_callback(struct rcu_head *rhp)
  * srcu_read_lock(), and srcu_read_unlock() that are all passed the same
  * srcu_struct structure.
  */
-void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
+void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 		 rcu_callback_t func, bool do_norm)
 {
 	unsigned long flags;
+	int idx;
 	bool needexp = false;
 	bool needgp = false;
 	unsigned long s;
 	struct srcu_data *sdp;
 
-	check_init_srcu_struct(sp);
+	check_init_srcu_struct(ssp);
 	if (debug_rcu_head_queue(rhp)) {
 		/* Probable double call_srcu(), so leak the callback. */
 		WRITE_ONCE(rhp->func, srcu_leak_callback);
@@ -871,13 +874,14 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
 		return;
 	}
 	rhp->func = func;
+	idx = srcu_read_lock(ssp);
 	local_irq_save(flags);
-	sdp = this_cpu_ptr(sp->sda);
+	sdp = this_cpu_ptr(ssp->sda);
 	spin_lock_rcu_node(sdp);
 	rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false);
 	rcu_segcblist_advance(&sdp->srcu_cblist,
-			      rcu_seq_current(&sp->srcu_gp_seq));
-	s = rcu_seq_snap(&sp->srcu_gp_seq);
+			      rcu_seq_current(&ssp->srcu_gp_seq));
+	s = rcu_seq_snap(&ssp->srcu_gp_seq);
 	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
 	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
 		sdp->srcu_gp_seq_needed = s;
@@ -889,14 +893,15 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
 	}
 	spin_unlock_irqrestore_rcu_node(sdp, flags);
 	if (needgp)
-		srcu_funnel_gp_start(sp, sdp, s, do_norm);
+		srcu_funnel_gp_start(ssp, sdp, s, do_norm);
 	else if (needexp)
-		srcu_funnel_exp_start(sp, sdp->mynode, s);
+		srcu_funnel_exp_start(ssp, sdp->mynode, s);
+	srcu_read_unlock(ssp, idx);
 }
 
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
- * @sp: srcu_struct in queue the callback
+ * @ssp: srcu_struct in queue the callback
  * @rhp: structure to be used for queueing the SRCU callback.
  * @func: function to be invoked after the SRCU grace period
  *
@@ -911,21 +916,21 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
  * The callback will be invoked from process context, but must nevertheless
  * be fast and must not block.
  */
-void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
+void call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 	       rcu_callback_t func)
 {
-	__call_srcu(sp, rhp, func, true);
+	__call_srcu(ssp, rhp, func, true);
 }
 EXPORT_SYMBOL_GPL(call_srcu);
 
 /*
  * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
  */
-static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
+static void __synchronize_srcu(struct srcu_struct *ssp, bool do_norm)
 {
 	struct rcu_synchronize rcu;
 
-	RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) ||
+	RCU_LOCKDEP_WARN(lock_is_held(&ssp->dep_map) ||
 			 lock_is_held(&rcu_bh_lock_map) ||
 			 lock_is_held(&rcu_lock_map) ||
 			 lock_is_held(&rcu_sched_lock_map),
@@ -934,10 +939,10 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
 	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
 		return;
 	might_sleep();
-	check_init_srcu_struct(sp);
+	check_init_srcu_struct(ssp);
 	init_completion(&rcu.completion);
 	init_rcu_head_on_stack(&rcu.head);
-	__call_srcu(sp, &rcu.head, wakeme_after_rcu, do_norm);
+	__call_srcu(ssp, &rcu.head, wakeme_after_rcu, do_norm);
 	wait_for_completion(&rcu.completion);
 	destroy_rcu_head_on_stack(&rcu.head);
 
@@ -953,7 +958,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
 
 /**
  * synchronize_srcu_expedited - Brute-force SRCU grace period
- * @sp: srcu_struct with which to synchronize.
+ * @ssp: srcu_struct with which to synchronize.
  *
  * Wait for an SRCU grace period to elapse, but be more aggressive about
  * spinning rather than blocking when waiting.
@@ -961,15 +966,15 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
  * Note that synchronize_srcu_expedited() has the same deadlock and
  * memory-ordering properties as does synchronize_srcu().
  */
-void synchronize_srcu_expedited(struct srcu_struct *sp)
+void synchronize_srcu_expedited(struct srcu_struct *ssp)
 {
-	__synchronize_srcu(sp, rcu_gp_is_normal());
+	__synchronize_srcu(ssp, rcu_gp_is_normal());
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
 
 /**
  * synchronize_srcu - wait for prior SRCU read-side critical-section completion
- * @sp: srcu_struct with which to synchronize.
+ * @ssp: srcu_struct with which to synchronize.
  *
  * Wait for the count to drain to zero of both indexes. To avoid the
  * possible starvation of synchronize_srcu(), it waits for the count of
@@ -1011,12 +1016,12 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
  * SRCU must also provide it.  Note that detecting idleness is heuristic
  * and subject to both false positives and negatives.
  */
-void synchronize_srcu(struct srcu_struct *sp)
+void synchronize_srcu(struct srcu_struct *ssp)
 {
-	if (srcu_might_be_idle(sp) || rcu_gp_is_expedited())
-		synchronize_srcu_expedited(sp);
+	if (srcu_might_be_idle(ssp) || rcu_gp_is_expedited())
+		synchronize_srcu_expedited(ssp);
 	else
-		__synchronize_srcu(sp, true);
+		__synchronize_srcu(ssp, true);
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu);
 
@@ -1026,36 +1031,36 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
 static void srcu_barrier_cb(struct rcu_head *rhp)
 {
 	struct srcu_data *sdp;
-	struct srcu_struct *sp;
+	struct srcu_struct *ssp;
 
 	sdp = container_of(rhp, struct srcu_data, srcu_barrier_head);
-	sp = sdp->sp;
-	if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
-		complete(&sp->srcu_barrier_completion);
+	ssp = sdp->ssp;
+	if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt))
+		complete(&ssp->srcu_barrier_completion);
 }
 
 /**
  * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
- * @sp: srcu_struct on which to wait for in-flight callbacks.
+ * @ssp: srcu_struct on which to wait for in-flight callbacks.
  */
-void srcu_barrier(struct srcu_struct *sp)
+void srcu_barrier(struct srcu_struct *ssp)
 {
 	int cpu;
 	struct srcu_data *sdp;
-	unsigned long s = rcu_seq_snap(&sp->srcu_barrier_seq);
+	unsigned long s = rcu_seq_snap(&ssp->srcu_barrier_seq);
 
-	check_init_srcu_struct(sp);
-	mutex_lock(&sp->srcu_barrier_mutex);
-	if (rcu_seq_done(&sp->srcu_barrier_seq, s)) {
+	check_init_srcu_struct(ssp);
+	mutex_lock(&ssp->srcu_barrier_mutex);
+	if (rcu_seq_done(&ssp->srcu_barrier_seq, s)) {
 		smp_mb(); /* Force ordering following return. */
-		mutex_unlock(&sp->srcu_barrier_mutex);
+		mutex_unlock(&ssp->srcu_barrier_mutex);
 		return; /* Someone else did our work for us. */
 	}
-	rcu_seq_start(&sp->srcu_barrier_seq);
-	init_completion(&sp->srcu_barrier_completion);
+	rcu_seq_start(&ssp->srcu_barrier_seq);
+	init_completion(&ssp->srcu_barrier_completion);
 
 	/* Initial count prevents reaching zero until all CBs are posted. */
-	atomic_set(&sp->srcu_barrier_cpu_cnt, 1);
+	atomic_set(&ssp->srcu_barrier_cpu_cnt, 1);
 
 	/*
 	 * Each pass through this loop enqueues a callback, but only
@@ -1066,39 +1071,39 @@ void srcu_barrier(struct srcu_struct *sp)
 	 * grace period as the last callback already in the queue.
 	 */
 	for_each_possible_cpu(cpu) {
-		sdp = per_cpu_ptr(sp->sda, cpu);
+		sdp = per_cpu_ptr(ssp->sda, cpu);
 		spin_lock_irq_rcu_node(sdp);
-		atomic_inc(&sp->srcu_barrier_cpu_cnt);
+		atomic_inc(&ssp->srcu_barrier_cpu_cnt);
 		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)) {
 			debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
-			atomic_dec(&sp->srcu_barrier_cpu_cnt);
+			atomic_dec(&ssp->srcu_barrier_cpu_cnt);
 		}
 		spin_unlock_irq_rcu_node(sdp);
 	}
 
 	/* Remove the initial count, at which point reaching zero can happen. */
-	if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
-		complete(&sp->srcu_barrier_completion);
-	wait_for_completion(&sp->srcu_barrier_completion);
+	if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt))
+		complete(&ssp->srcu_barrier_completion);
+	wait_for_completion(&ssp->srcu_barrier_completion);
 
-	rcu_seq_end(&sp->srcu_barrier_seq);
-	mutex_unlock(&sp->srcu_barrier_mutex);
+	rcu_seq_end(&ssp->srcu_barrier_seq);
+	mutex_unlock(&ssp->srcu_barrier_mutex);
 }
 EXPORT_SYMBOL_GPL(srcu_barrier);
 
 /**
  * srcu_batches_completed - return batches completed.
- * @sp: srcu_struct on which to report batch completion.
+ * @ssp: srcu_struct on which to report batch completion.
  *
  * Report the number of batches, correlated with, but not necessarily
  * precisely the same as, the number of grace periods that have elapsed.
  */
-unsigned long srcu_batches_completed(struct srcu_struct *sp)
+unsigned long srcu_batches_completed(struct srcu_struct *ssp)
 {
-	return sp->srcu_idx;
+	return ssp->srcu_idx;
 }
 EXPORT_SYMBOL_GPL(srcu_batches_completed);
 
@@ -1107,11 +1112,11 @@ EXPORT_SYMBOL_GPL(srcu_batches_completed);
  * to SRCU_STATE_SCAN2, and invoke srcu_gp_end() when scan has
  * completed in that state.
  */
-static void srcu_advance_state(struct srcu_struct *sp)
+static void srcu_advance_state(struct srcu_struct *ssp)
 {
 	int idx;
 
-	mutex_lock(&sp->srcu_gp_mutex);
+	mutex_lock(&ssp->srcu_gp_mutex);
 
 	/*
 	 * Because readers might be delayed for an extended period after
@@ -1123,47 +1128,47 @@ static void srcu_advance_state(struct srcu_struct *sp)
 	 * The load-acquire ensures that we see the accesses performed
 	 * by the prior grace period.
 	 */
-	idx = rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq)); /* ^^^ */
+	idx = rcu_seq_state(smp_load_acquire(&ssp->srcu_gp_seq)); /* ^^^ */
 	if (idx == SRCU_STATE_IDLE) {
-		spin_lock_irq_rcu_node(sp);
-		if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
-			WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq));
-			spin_unlock_irq_rcu_node(sp);
-			mutex_unlock(&sp->srcu_gp_mutex);
+		spin_lock_irq_rcu_node(ssp);
+		if (ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)) {
+			WARN_ON_ONCE(rcu_seq_state(ssp->srcu_gp_seq));
+			spin_unlock_irq_rcu_node(ssp);
+			mutex_unlock(&ssp->srcu_gp_mutex);
 			return;
 		}
-		idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
+		idx = rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq));
 		if (idx == SRCU_STATE_IDLE)
-			srcu_gp_start(sp);
-		spin_unlock_irq_rcu_node(sp);
+			srcu_gp_start(ssp);
+		spin_unlock_irq_rcu_node(ssp);
 		if (idx != SRCU_STATE_IDLE) {
-			mutex_unlock(&sp->srcu_gp_mutex);
+			mutex_unlock(&ssp->srcu_gp_mutex);
 			return; /* Someone else started the grace period. */
 		}
 	}
 
-	if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
-		idx = 1 ^ (sp->srcu_idx & 1);
-		if (!try_check_zero(sp, idx, 1)) {
-			mutex_unlock(&sp->srcu_gp_mutex);
+	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
+		idx = 1 ^ (ssp->srcu_idx & 1);
+		if (!try_check_zero(ssp, idx, 1)) {
+			mutex_unlock(&ssp->srcu_gp_mutex);
 			return; /* readers present, retry later. */
 		}
-		srcu_flip(sp);
-		rcu_seq_set_state(&sp->srcu_gp_seq, SRCU_STATE_SCAN2);
+		srcu_flip(ssp);
+		rcu_seq_set_state(&ssp->srcu_gp_seq, SRCU_STATE_SCAN2);
 	}
 
-	if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
+	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
 
 		/*
 		 * SRCU read-side critical sections are normally short,
 		 * so check at least twice in quick succession after a flip.
 		 */
-		idx = 1 ^ (sp->srcu_idx & 1);
-		if (!try_check_zero(sp, idx, 2)) {
-			mutex_unlock(&sp->srcu_gp_mutex);
+		idx = 1 ^ (ssp->srcu_idx & 1);
+		if (!try_check_zero(ssp, idx, 2)) {
+			mutex_unlock(&ssp->srcu_gp_mutex);
 			return; /* readers present, retry later. */
 		}
-		srcu_gp_end(sp);  /* Releases ->srcu_gp_mutex. */
+		srcu_gp_end(ssp);  /* Releases ->srcu_gp_mutex. */
 	}
 }
 
@@ -1179,14 +1184,14 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	struct rcu_cblist ready_cbs;
 	struct rcu_head *rhp;
 	struct srcu_data *sdp;
-	struct srcu_struct *sp;
+	struct srcu_struct *ssp;
 
 	sdp = container_of(work, struct srcu_data, work.work);
-	sp = sdp->sp;
+	ssp = sdp->ssp;
 	rcu_cblist_init(&ready_cbs);
 	spin_lock_irq_rcu_node(sdp);
 	rcu_segcblist_advance(&sdp->srcu_cblist,
-			      rcu_seq_current(&sp->srcu_gp_seq));
+			      rcu_seq_current(&ssp->srcu_gp_seq));
 	if (sdp->srcu_cblist_invoking ||
 	    !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
 		spin_unlock_irq_rcu_node(sdp);
@@ -1212,7 +1217,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	spin_lock_irq_rcu_node(sdp);
 	rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs);
 	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
-				       rcu_seq_snap(&sp->srcu_gp_seq));
+				       rcu_seq_snap(&ssp->srcu_gp_seq));
 	sdp->srcu_cblist_invoking = false;
 	more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
 	spin_unlock_irq_rcu_node(sdp);
@@ -1224,24 +1229,24 @@ static void srcu_invoke_callbacks(struct work_struct *work)
  * Finished one round of SRCU grace period.  Start another if there are
  * more SRCU callbacks queued, otherwise put SRCU into not-running state.
  */
-static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
+static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay)
 {
 	bool pushgp = true;
 
-	spin_lock_irq_rcu_node(sp);
-	if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
-		if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) {
+	spin_lock_irq_rcu_node(ssp);
+	if (ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)) {
+		if (!WARN_ON_ONCE(rcu_seq_state(ssp->srcu_gp_seq))) {
 			/* All requests fulfilled, time to go idle. */
 			pushgp = false;
 		}
-	} else if (!rcu_seq_state(sp->srcu_gp_seq)) {
+	} else if (!rcu_seq_state(ssp->srcu_gp_seq)) {
 		/* Outstanding request and no GP.  Start one. */
-		srcu_gp_start(sp);
+		srcu_gp_start(ssp);
 	}
-	spin_unlock_irq_rcu_node(sp);
+	spin_unlock_irq_rcu_node(ssp);
 
 	if (pushgp)
-		queue_delayed_work(rcu_gp_wq, &sp->work, delay);
+		queue_delayed_work(rcu_gp_wq, &ssp->work, delay);
 }
 
 /*
@@ -1249,41 +1254,41 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
  */
 static void process_srcu(struct work_struct *work)
 {
-	struct srcu_struct *sp;
+	struct srcu_struct *ssp;
 
-	sp = container_of(work, struct srcu_struct, work.work);
+	ssp = container_of(work, struct srcu_struct, work.work);
 
-	srcu_advance_state(sp);
-	srcu_reschedule(sp, srcu_get_delay(sp));
+	srcu_advance_state(ssp);
+	srcu_reschedule(ssp, srcu_get_delay(ssp));
 }
 
 void srcutorture_get_gp_data(enum rcutorture_type test_type,
-			     struct srcu_struct *sp, int *flags,
+			     struct srcu_struct *ssp, int *flags,
 			     unsigned long *gp_seq)
 {
 	if (test_type != SRCU_FLAVOR)
 		return;
 	*flags = 0;
-	*gp_seq = rcu_seq_current(&sp->srcu_gp_seq);
+	*gp_seq = rcu_seq_current(&ssp->srcu_gp_seq);
 }
 EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
 
-void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
+void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
 {
 	int cpu;
 	int idx;
 	unsigned long s0 = 0, s1 = 0;
 
-	idx = sp->srcu_idx & 0x1;
+	idx = ssp->srcu_idx & 0x1;
 	pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):",
-		 tt, tf, rcu_seq_current(&sp->srcu_gp_seq), idx);
+		 tt, tf, rcu_seq_current(&ssp->srcu_gp_seq), idx);
 	for_each_possible_cpu(cpu) {
 		unsigned long l0, l1;
 		unsigned long u0, u1;
 		long c0, c1;
 		struct srcu_data *sdp;
 
-		sdp = per_cpu_ptr(sp->sda, cpu);
+		sdp = per_cpu_ptr(ssp->sda, cpu);
 		u0 = sdp->srcu_unlock_count[!idx];
 		u1 = sdp->srcu_unlock_count[idx];
 
@@ -1318,14 +1323,14 @@ early_initcall(srcu_bootup_announce);
 
 void __init srcu_init(void)
 {
-	struct srcu_struct *sp;
+	struct srcu_struct *ssp;
 
 	srcu_init_done = true;
 	while (!list_empty(&srcu_boot_list)) {
-		sp = list_first_entry(&srcu_boot_list, struct srcu_struct,
+		ssp = list_first_entry(&srcu_boot_list, struct srcu_struct,
 				      work.work.entry);
-		check_init_srcu_struct(sp);
-		list_del_init(&sp->work.work.entry);
-		queue_work(rcu_gp_wq, &sp->work.work);
+		check_init_srcu_struct(ssp);
+		list_del_init(&ssp->work.work.entry);
+		queue_work(rcu_gp_wq, &ssp->work.work);
 	}
 }
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index 3f943efcf61c..be10036fa621 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -44,15 +44,15 @@ static const struct {
 		__INIT_HELD(rcu_read_lock_held)
 	},
 	[RCU_SCHED_SYNC] = {
-		.sync = synchronize_sched,
-		.call = call_rcu_sched,
-		.wait = rcu_barrier_sched,
+		.sync = synchronize_rcu,
+		.call = call_rcu,
+		.wait = rcu_barrier,
 		__INIT_HELD(rcu_read_lock_sched_held)
 	},
 	[RCU_BH_SYNC] = {
-		.sync = synchronize_rcu_bh,
-		.call = call_rcu_bh,
-		.wait = rcu_barrier_bh,
+		.sync = synchronize_rcu,
+		.call = call_rcu,
+		.wait = rcu_barrier,
 		__INIT_HELD(rcu_read_lock_bh_held)
 	},
 };
@@ -125,8 +125,7 @@ void rcu_sync_enter(struct rcu_sync *rsp)
 		rsp->gp_state = GP_PENDING;
 	spin_unlock_irq(&rsp->rss_lock);
 
-	BUG_ON(need_wait && need_sync);
-
+	WARN_ON_ONCE(need_wait && need_sync);
 	if (need_sync) {
 		gp_ops[rsp->gp_type].sync();
 		rsp->gp_state = GP_PASSED;
@@ -139,7 +138,7 @@ void rcu_sync_enter(struct rcu_sync *rsp)
 		 * Nobody has yet been allowed the 'fast' path and thus we can
 		 * avoid doing any sync(). The callback will get 'dropped'.
 		 */
-		BUG_ON(rsp->gp_state != GP_PASSED);
+		WARN_ON_ONCE(rsp->gp_state != GP_PASSED);
 	}
 }
 
@@ -166,8 +165,8 @@ static void rcu_sync_func(struct rcu_head *rhp)
 	struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head);
 	unsigned long flags;
 
-	BUG_ON(rsp->gp_state != GP_PASSED);
-	BUG_ON(rsp->cb_state == CB_IDLE);
+	WARN_ON_ONCE(rsp->gp_state != GP_PASSED);
+	WARN_ON_ONCE(rsp->cb_state == CB_IDLE);
 
 	spin_lock_irqsave(&rsp->rss_lock, flags);
 	if (rsp->gp_count) {
@@ -225,7 +224,7 @@ void rcu_sync_dtor(struct rcu_sync *rsp)
 {
 	int cb_state;
 
-	BUG_ON(rsp->gp_count);
+	WARN_ON_ONCE(rsp->gp_count);
 
 	spin_lock_irq(&rsp->rss_lock);
 	if (rsp->cb_state == CB_REPLAY)
@@ -235,6 +234,6 @@ void rcu_sync_dtor(struct rcu_sync *rsp)
 
 	if (cb_state != CB_IDLE) {
 		gp_ops[rsp->gp_type].wait();
-		BUG_ON(rsp->cb_state != CB_IDLE);
+		WARN_ON_ONCE(rsp->cb_state != CB_IDLE);
 	}
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 121f833acd04..9180158756d2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -207,6 +207,19 @@ static int rcu_gp_in_progress(void)
 	return rcu_seq_state(rcu_seq_current(&rcu_state.gp_seq));
 }
 
+/*
+ * Return the number of callbacks queued on the specified CPU.
+ * Handles both the nocbs and normal cases.
+ */
+static long rcu_get_n_cbs_cpu(int cpu)
+{
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
+	if (rcu_segcblist_is_enabled(&rdp->cblist)) /* Online normal CPU? */
+		return rcu_segcblist_n_cbs(&rdp->cblist);
+	return rcu_get_n_cbs_nocb_cpu(rdp); /* Works for offline, too. */
+}
+
 void rcu_softirq_qs(void)
 {
 	rcu_qs();
@@ -500,16 +513,29 @@ void rcu_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /*
+ * 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];
+}
+
+/*
  * Show the state of the grace-period kthreads.
  */
 void show_rcu_gp_kthreads(void)
 {
 	int cpu;
+	unsigned long j;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
-	pr_info("%s: wait state: %d ->state: %#lx\n", rcu_state.name,
-		rcu_state.gp_state, rcu_state.gp_kthread->state);
+	j = jiffies - READ_ONCE(rcu_state.gp_activity);
+	pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %ld\n",
+		rcu_state.name, gp_state_getname(rcu_state.gp_state),
+		rcu_state.gp_state, rcu_state.gp_kthread->state, j);
 	rcu_for_each_node_breadth_first(rnp) {
 		if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
 			continue;
@@ -891,12 +917,12 @@ void rcu_irq_enter_irqson(void)
 }
 
 /**
- * rcu_is_watching - see if RCU thinks that the current CPU is idle
+ * rcu_is_watching - see if RCU thinks that the current CPU is not idle
  *
  * Return true if RCU is watching the running CPU, which means that this
  * CPU can safely enter RCU read-side critical sections.  In other words,
- * if the current CPU is in its idle loop and is neither in an interrupt
- * or NMI handler, return true.
+ * if the current CPU is not in its idle loop or is in an interrupt or
+ * NMI handler, return true.
  */
 bool notrace rcu_is_watching(void)
 {
@@ -1143,16 +1169,6 @@ static void record_gp_stall_check_time(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];
-}
-
-/*
  * Complain about starvation of grace-period kthread.
  */
 static void rcu_check_gp_kthread_starvation(void)
@@ -1262,8 +1278,7 @@ static void print_other_cpu_stall(unsigned long gp_seq)
 
 	print_cpu_stall_info_end();
 	for_each_possible_cpu(cpu)
-		totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(&rcu_data,
-							    cpu)->cblist);
+		totqlen += rcu_get_n_cbs_cpu(cpu);
 	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
 	       smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
 	       (long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
@@ -1323,8 +1338,7 @@ static void print_cpu_stall(void)
 	raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
 	print_cpu_stall_info_end();
 	for_each_possible_cpu(cpu)
-		totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(&rcu_data,
-							    cpu)->cblist);
+		totqlen += rcu_get_n_cbs_cpu(cpu);
 	pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
 		jiffies - rcu_state.gp_start,
 		(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
@@ -1986,7 +2000,8 @@ static void rcu_gp_cleanup(void)
 
 	WRITE_ONCE(rcu_state.gp_activity, jiffies);
 	raw_spin_lock_irq_rcu_node(rnp);
-	gp_duration = jiffies - rcu_state.gp_start;
+	rcu_state.gp_end = jiffies;
+	gp_duration = rcu_state.gp_end - rcu_state.gp_start;
 	if (gp_duration > rcu_state.gp_max)
 		rcu_state.gp_max = gp_duration;
 
@@ -2032,9 +2047,9 @@ static void rcu_gp_cleanup(void)
 	rnp = rcu_get_root();
 	raw_spin_lock_irq_rcu_node(rnp); /* GP before ->gp_seq update. */
 
-	/* Declare grace period done. */
-	rcu_seq_end(&rcu_state.gp_seq);
+	/* Declare grace period done, trace first to use old GP number. */
 	trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end"));
+	rcu_seq_end(&rcu_state.gp_seq);
 	rcu_state.gp_state = RCU_GP_IDLE;
 	/* Check for GP requests since above loop. */
 	rdp = this_cpu_ptr(&rcu_data);
@@ -2600,10 +2615,10 @@ static void force_quiescent_state(void)
  * This function checks for grace-period requests that fail to motivate
  * RCU to come out of its idle mode.
  */
-static void
-rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp)
+void
+rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
+			 const unsigned long gpssdelay)
 {
-	const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ;
 	unsigned long flags;
 	unsigned long j;
 	struct rcu_node *rnp_root = rcu_get_root();
@@ -2655,6 +2670,48 @@ rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp)
 }
 
 /*
+ * Do a forward-progress check for rcutorture.  This is normally invoked
+ * due to an OOM event.  The argument "j" gives the time period during
+ * which rcutorture would like progress to have been made.
+ */
+void rcu_fwd_progress_check(unsigned long j)
+{
+	unsigned long cbs;
+	int cpu;
+	unsigned long max_cbs = 0;
+	int max_cpu = -1;
+	struct rcu_data *rdp;
+
+	if (rcu_gp_in_progress()) {
+		pr_info("%s: GP age %lu jiffies\n",
+			__func__, jiffies - rcu_state.gp_start);
+		show_rcu_gp_kthreads();
+	} else {
+		pr_info("%s: Last GP end %lu jiffies ago\n",
+			__func__, jiffies - rcu_state.gp_end);
+		preempt_disable();
+		rdp = this_cpu_ptr(&rcu_data);
+		rcu_check_gp_start_stall(rdp->mynode, rdp, j);
+		preempt_enable();
+	}
+	for_each_possible_cpu(cpu) {
+		cbs = rcu_get_n_cbs_cpu(cpu);
+		if (!cbs)
+			continue;
+		if (max_cpu < 0)
+			pr_info("%s: callbacks", __func__);
+		pr_cont(" %d: %lu", cpu, cbs);
+		if (cbs <= max_cbs)
+			continue;
+		max_cbs = cbs;
+		max_cpu = cpu;
+	}
+	if (max_cpu >= 0)
+		pr_cont("\n");
+}
+EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
+
+/*
  * This does the RCU core processing work for the specified rcu_data
  * structures.  This may be called only from the CPU to whom the rdp
  * belongs.
@@ -2690,7 +2747,7 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused
 		local_irq_restore(flags);
 	}
 
-	rcu_check_gp_start_stall(rnp, rdp);
+	rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check());
 
 	/* If there are callbacks ready, invoke them. */
 	if (rcu_segcblist_ready_cbs(&rdp->cblist))
@@ -2826,7 +2883,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy)
 		 * Very early boot, before rcu_init().  Initialize if needed
 		 * and then drop through to queue the callback.
 		 */
-		BUG_ON(cpu != -1);
+		WARN_ON_ONCE(cpu != -1);
 		WARN_ON_ONCE(!rcu_is_watching());
 		if (rcu_segcblist_empty(&rdp->cblist))
 			rcu_segcblist_init(&rdp->cblist);
@@ -3485,7 +3542,8 @@ static int __init rcu_spawn_gp_kthread(void)
 
 	rcu_scheduler_fully_active = 1;
 	t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name);
-	BUG_ON(IS_ERR(t));
+	if (WARN_ONCE(IS_ERR(t), "%s: Could not start grace-period kthread, OOM is now expected behavior\n", __func__))
+		return 0;
 	rnp = rcu_get_root();
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rcu_state.gp_kthread = t;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 703e19ff532d..d90b02b53c0e 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -57,7 +57,7 @@ struct rcu_node {
 					/*  some rcu_state fields as well as */
 					/*  following. */
 	unsigned long gp_seq;	/* Track rsp->rcu_gp_seq. */
-	unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */
+	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 */
 				/*  order for current grace period to proceed.*/
@@ -163,7 +163,7 @@ union rcu_noqs {
 struct rcu_data {
 	/* 1) quiescent-state and grace-period handling : */
 	unsigned long	gp_seq;		/* Track rsp->rcu_gp_seq counter. */
-	unsigned long	gp_seq_needed;	/* Track rsp->rcu_gp_seq_needed ctr. */
+	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. */
 	bool		beenonline;	/* CPU online at least once. */
@@ -328,6 +328,8 @@ struct rcu_state {
 						/*  force_quiescent_state(). */
 	unsigned long gp_start;			/* Time at which GP started, */
 						/*  but in jiffies. */
+	unsigned long gp_end;			/* Time last GP ended, again */
+						/*  in jiffies. */
 	unsigned long gp_activity;		/* Time of last GP kthread */
 						/*  activity in jiffies. */
 	unsigned long gp_req_activity;		/* Time of last GP request */
@@ -398,17 +400,6 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
 #define RCU_NAME rcu_name
 #endif /* #else #ifdef CONFIG_TRACING */
 
-/*
- * RCU implementation internal declarations:
- */
-extern struct rcu_state rcu_sched_state;
-
-extern struct rcu_state rcu_bh_state;
-
-#ifdef CONFIG_PREEMPT_RCU
-extern struct rcu_state rcu_preempt_state;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-
 int rcu_dynticks_snap(struct rcu_data *rdp);
 
 #ifdef CONFIG_RCU_BOOST
@@ -466,6 +457,7 @@ static void __init rcu_spawn_nocb_kthreads(void);
 static void __init rcu_organize_nocb_kthreads(void);
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 static bool init_nocb_callback_list(struct rcu_data *rdp);
+static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp);
 static void rcu_bind_gp_kthread(void);
 static bool rcu_nohz_full_cpu(void);
 static void rcu_dynticks_task_enter(void);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 8d18c1014e2b..928fe5893a57 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -450,10 +450,12 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
 		}
 		INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
 		preempt_disable();
-		cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask);
+		cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1);
 		/* If all offline, queue the work on an unbound CPU. */
-		if (unlikely(cpu > rnp->grphi))
+		if (unlikely(cpu > rnp->grphi - rnp->grplo))
 			cpu = WORK_CPU_UNBOUND;
+		else
+			cpu += rnp->grplo;
 		queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
 		preempt_enable();
 		rnp->exp_need_flush = true;
@@ -690,8 +692,10 @@ static void sync_rcu_exp_handler(void *unused)
 	 */
 	if (t->rcu_read_lock_nesting > 0) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		if (rnp->expmask & rdp->grpmask)
+		if (rnp->expmask & rdp->grpmask) {
 			rdp->deferred_qs = true;
+			WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true);
+		}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 05915e536336..1b3dd2fc0cd6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -397,6 +397,11 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 	return rnp->gp_tasks != NULL;
 }
 
+/* Bias and limit values for ->rcu_read_lock_nesting. */
+#define RCU_NEST_BIAS INT_MAX
+#define RCU_NEST_NMAX (-INT_MAX / 2)
+#define RCU_NEST_PMAX (INT_MAX / 2)
+
 /*
  * Preemptible RCU implementation for rcu_read_lock().
  * Just increment ->rcu_read_lock_nesting, shared state will be updated
@@ -405,6 +410,8 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 void __rcu_read_lock(void)
 {
 	current->rcu_read_lock_nesting++;
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING))
+		WARN_ON_ONCE(current->rcu_read_lock_nesting > RCU_NEST_PMAX);
 	barrier();  /* critical section after entry code. */
 }
 EXPORT_SYMBOL_GPL(__rcu_read_lock);
@@ -424,20 +431,18 @@ void __rcu_read_unlock(void)
 		--t->rcu_read_lock_nesting;
 	} else {
 		barrier();  /* critical section before exit code. */
-		t->rcu_read_lock_nesting = INT_MIN;
+		t->rcu_read_lock_nesting = -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;
 	}
-#ifdef CONFIG_PROVE_LOCKING
-	{
-		int rrln = READ_ONCE(t->rcu_read_lock_nesting);
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+		int rrln = t->rcu_read_lock_nesting;
 
-		WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
+		WARN_ON_ONCE(rrln < 0 && rrln > RCU_NEST_NMAX);
 	}
-#endif /* #ifdef CONFIG_PROVE_LOCKING */
 }
 EXPORT_SYMBOL_GPL(__rcu_read_unlock);
 
@@ -597,7 +602,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
  */
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
-	return (this_cpu_ptr(&rcu_data)->deferred_qs ||
+	return (__this_cpu_read(rcu_data.deferred_qs) ||
 		READ_ONCE(t->rcu_read_unlock_special.s)) &&
 	       t->rcu_read_lock_nesting <= 0;
 }
@@ -617,11 +622,11 @@ static void rcu_preempt_deferred_qs(struct task_struct *t)
 	if (!rcu_preempt_need_deferred_qs(t))
 		return;
 	if (couldrecurse)
-		t->rcu_read_lock_nesting -= INT_MIN;
+		t->rcu_read_lock_nesting -= RCU_NEST_BIAS;
 	local_irq_save(flags);
 	rcu_preempt_deferred_qs_irqrestore(t, flags);
 	if (couldrecurse)
-		t->rcu_read_lock_nesting += INT_MIN;
+		t->rcu_read_lock_nesting += RCU_NEST_BIAS;
 }
 
 /*
@@ -642,13 +647,21 @@ static void rcu_read_unlock_special(struct task_struct *t)
 
 	local_irq_save(flags);
 	irqs_were_disabled = irqs_disabled_flags(flags);
-	if ((preempt_bh_were_disabled || irqs_were_disabled) &&
-	    t->rcu_read_unlock_special.b.blocked) {
+	if (preempt_bh_were_disabled || irqs_were_disabled) {
+		WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false);
 		/* Need to defer quiescent state until everything is enabled. */
-		raise_softirq_irqoff(RCU_SOFTIRQ);
+		if (irqs_were_disabled) {
+			/* Enabling irqs does not reschedule, so... */
+			raise_softirq_irqoff(RCU_SOFTIRQ);
+		} else {
+			/* Enabling BH or preempt does reschedule, so... */
+			set_tsk_need_resched(current);
+			set_preempt_need_resched();
+		}
 		local_irq_restore(flags);
 		return;
 	}
+	WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false);
 	rcu_preempt_deferred_qs_irqrestore(t, flags);
 }
 
@@ -1464,7 +1477,8 @@ static void __init rcu_spawn_boost_kthreads(void)
 
 	for_each_possible_cpu(cpu)
 		per_cpu(rcu_cpu_has_work, cpu) = 0;
-	BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
+	if (WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec), "%s: Could not start rcub kthread, OOM is now expected behavior\n", __func__))
+		return;
 	rcu_for_each_leaf_node(rnp)
 		(void)rcu_spawn_one_boost_kthread(rnp);
 }
@@ -1997,7 +2011,7 @@ static bool rcu_nocb_cpu_needs_barrier(int cpu)
 	 * (if a callback is in fact needed).  This is associated with an
 	 * atomic_inc() in the caller.
 	 */
-	ret = atomic_long_read(&rdp->nocb_q_count);
+	ret = rcu_get_n_cbs_nocb_cpu(rdp);
 
 #ifdef CONFIG_PROVE_RCU
 	rhp = READ_ONCE(rdp->nocb_head);
@@ -2052,7 +2066,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 				    TPS("WakeNotPoll"));
 		return;
 	}
-	len = atomic_long_read(&rdp->nocb_q_count);
+	len = rcu_get_n_cbs_nocb_cpu(rdp);
 	if (old_rhpp == &rdp->nocb_head) {
 		if (!irqs_disabled_flags(flags)) {
 			/* ... if queue was empty ... */
@@ -2101,11 +2115,11 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 		trace_rcu_kfree_callback(rcu_state.name, rhp,
 					 (unsigned long)rhp->func,
 					 -atomic_long_read(&rdp->nocb_q_count_lazy),
-					 -atomic_long_read(&rdp->nocb_q_count));
+					 -rcu_get_n_cbs_nocb_cpu(rdp));
 	else
 		trace_rcu_callback(rcu_state.name, rhp,
 				   -atomic_long_read(&rdp->nocb_q_count_lazy),
-				   -atomic_long_read(&rdp->nocb_q_count));
+				   -rcu_get_n_cbs_nocb_cpu(rdp));
 
 	/*
 	 * If called from an extended quiescent state with interrupts
@@ -2322,13 +2336,14 @@ static int rcu_nocb_kthread(void *arg)
 		tail = rdp->nocb_follower_tail;
 		rdp->nocb_follower_tail = &rdp->nocb_follower_head;
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
-		BUG_ON(!list);
+		if (WARN_ON_ONCE(!list))
+			continue;
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeNonEmpty"));
 
 		/* Each pass through the following loop invokes a callback. */
 		trace_rcu_batch_start(rcu_state.name,
 				      atomic_long_read(&rdp->nocb_q_count_lazy),
-				      atomic_long_read(&rdp->nocb_q_count), -1);
+				      rcu_get_n_cbs_nocb_cpu(rdp), -1);
 		c = cl = 0;
 		while (list) {
 			next = list->next;
@@ -2495,7 +2510,8 @@ static void rcu_spawn_one_nocb_kthread(int cpu)
 	/* Spawn the kthread for this CPU. */
 	t = kthread_run(rcu_nocb_kthread, rdp_spawn,
 			"rcuo%c/%d", rcu_state.abbr, cpu);
-	BUG_ON(IS_ERR(t));
+	if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo kthread, OOM is now expected behavior\n", __func__))
+		return;
 	WRITE_ONCE(rdp_spawn->nocb_kthread, t);
 }
 
@@ -2587,6 +2603,26 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 	return true;
 }
 
+/*
+ * Bind the current task to the offloaded CPUs.  If there are no offloaded
+ * CPUs, leave the task unbound.  Splat if the bind attempt fails.
+ */
+void rcu_bind_current_to_nocb(void)
+{
+	if (cpumask_available(rcu_nocb_mask) && cpumask_weight(rcu_nocb_mask))
+		WARN_ON(sched_setaffinity(current->pid, rcu_nocb_mask));
+}
+EXPORT_SYMBOL_GPL(rcu_bind_current_to_nocb);
+
+/*
+ * Return the number of RCU callbacks still queued from the specified
+ * CPU, which must be a nocbs CPU.
+ */
+static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp)
+{
+	return atomic_long_read(&rdp->nocb_q_count);
+}
+
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 static bool rcu_nocb_cpu_needs_barrier(int cpu)
@@ -2647,6 +2683,11 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 	return false;
 }
 
+static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp)
+{
+	return 0;
+}
+
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 
 /*
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index f203b94f6b5b..1971869c4072 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -335,8 +335,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
 	/* Initialize and register callbacks for each crcu_array element. */
 	for (i = 0; i < n; i++) {
 		if (checktiny &&
-		    (crcu_array[i] == call_rcu ||
-		     crcu_array[i] == call_rcu_bh)) {
+		    (crcu_array[i] == call_rcu)) {
 			might_sleep();
 			continue;
 		}
@@ -352,8 +351,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
 	/* Wait for all callbacks to be invoked. */
 	for (i = 0; i < n; i++) {
 		if (checktiny &&
-		    (crcu_array[i] == call_rcu ||
-		     crcu_array[i] == call_rcu_bh))
+		    (crcu_array[i] == call_rcu))
 			continue;
 		for (j = 0; j < i; j++)
 			if (crcu_array[j] == crcu_array[i])
@@ -822,7 +820,8 @@ static int __init rcu_spawn_tasks_kthread(void)
 	struct task_struct *t;
 
 	t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
-	BUG_ON(IS_ERR(t));
+	if (WARN_ONCE(IS_ERR(t), "%s: Could not start Tasks-RCU grace-period kthread, OOM is now expected behavior\n", __func__))
+		return 0;
 	smp_mb(); /* Ensure others see full kthread. */
 	WRITE_ONCE(rcu_tasks_kthread_ptr, t);
 	return 0;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6fedf3a98581..a5b7f1c9f24f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5783,7 +5783,7 @@ int sched_cpu_deactivate(unsigned int cpu)
 	 *
 	 * Do sync before park smpboot threads to take care the rcu boost case.
 	 */
-	synchronize_rcu_mult(call_rcu, call_rcu_sched);
+	synchronize_rcu();
 
 #ifdef CONFIG_SCHED_SMT
 	/*
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 76e0eaf4654e..3cd8a3a795d2 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -210,7 +210,7 @@ static int membarrier_register_global_expedited(void)
 		 * future scheduler executions will observe the new
 		 * thread flag state for this mm.
 		 */
-		synchronize_sched();
+		synchronize_rcu();
 	}
 	atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY,
 		  &mm->membarrier_state);
@@ -246,7 +246,7 @@ static int membarrier_register_private_expedited(int flags)
 		 * Ensure all future scheduler executions will observe the
 		 * new thread flag state for this process.
 		 */
-		synchronize_sched();
+		synchronize_rcu();
 	}
 	atomic_or(state, &mm->membarrier_state);
 
@@ -298,7 +298,7 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
 		if (tick_nohz_full_enabled())
 			return -EINVAL;
 		if (num_online_cpus() > 1)
-			synchronize_sched();
+			synchronize_rcu();
 		return 0;
 	case MEMBARRIER_CMD_GLOBAL_EXPEDITED:
 		return membarrier_global_expedited();
diff --git a/kernel/torture.c b/kernel/torture.c
index 17d91f5fba2a..bbf6d473e50c 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -194,11 +194,23 @@ torture_onoff(void *arg)
 	int cpu;
 	int maxcpu = -1;
 	DEFINE_TORTURE_RANDOM(rand);
+	int ret;
 
 	VERBOSE_TOROUT_STRING("torture_onoff task started");
 	for_each_online_cpu(cpu)
 		maxcpu = cpu;
 	WARN_ON(maxcpu < 0);
+	if (!IS_MODULE(CONFIG_TORTURE_TEST))
+		for_each_possible_cpu(cpu) {
+			if (cpu_online(cpu))
+				continue;
+			ret = cpu_up(cpu);
+			if (ret && verbose) {
+				pr_alert("%s" TORTURE_FLAG
+					 "%s: Initial online %d: errno %d\n",
+					 __func__, torture_type, cpu, ret);
+			}
+		}
 
 	if (maxcpu == 0) {
 		VERBOSE_TOROUT_STRING("Only one CPU, so CPU-hotplug testing is disabled");
@@ -233,16 +245,15 @@ stop:
  */
 int torture_onoff_init(long ooholdoff, long oointerval)
 {
-	int ret = 0;
-
 #ifdef CONFIG_HOTPLUG_CPU
 	onoff_holdoff = ooholdoff;
 	onoff_interval = oointerval;
 	if (onoff_interval <= 0)
 		return 0;
-	ret = torture_create_kthread(torture_onoff, NULL, onoff_task);
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-	return ret;
+	return torture_create_kthread(torture_onoff, NULL, onoff_task);
+#else /* #ifdef CONFIG_HOTPLUG_CPU */
+	return 0;
+#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
 }
 EXPORT_SYMBOL_GPL(torture_onoff_init);
 
@@ -513,15 +524,13 @@ static int torture_shutdown(void *arg)
  */
 int torture_shutdown_init(int ssecs, void (*cleanup)(void))
 {
-	int ret = 0;
-
 	torture_shutdown_hook = cleanup;
 	if (ssecs > 0) {
 		shutdown_time = ktime_add(ktime_get(), ktime_set(ssecs, 0));
-		ret = torture_create_kthread(torture_shutdown, NULL,
+		return torture_create_kthread(torture_shutdown, NULL,
 					     shutdown_task);
 	}
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(torture_shutdown_init);
 
@@ -620,13 +629,10 @@ static int torture_stutter(void *arg)
 /*
  * Initialize and kick off the torture_stutter kthread.
  */
-int torture_stutter_init(int s)
+int torture_stutter_init(const int s)
 {
-	int ret;
-
 	stutter = s;
-	ret = torture_create_kthread(torture_stutter, NULL, stutter_task);
-	return ret;
+	return torture_create_kthread(torture_stutter, NULL, stutter_task);
 }
 EXPORT_SYMBOL_GPL(torture_stutter_init);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index e23eb9fc77aa..f0ff24173a0b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -173,7 +173,7 @@ static void ftrace_sync(struct work_struct *work)
 {
 	/*
 	 * This function is just a stub to implement a hard force
-	 * of synchronize_sched(). This requires synchronizing
+	 * of synchronize_rcu(). This requires synchronizing
 	 * tasks even in userspace and idle.
 	 *
 	 * Yes, function tracing is rude.
@@ -934,7 +934,7 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
 			ftrace_profile_enabled = 0;
 			/*
 			 * unregister_ftrace_profiler calls stop_machine
-			 * so this acts like an synchronize_sched.
+			 * so this acts like an synchronize_rcu.
 			 */
 			unregister_ftrace_profiler();
 		}
@@ -1086,7 +1086,7 @@ struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr)
 
 	/*
 	 * Some of the ops may be dynamically allocated,
-	 * they are freed after a synchronize_sched().
+	 * they are freed after a synchronize_rcu().
 	 */
 	preempt_disable_notrace();
 
@@ -1286,7 +1286,7 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
 {
 	if (!hash || hash == EMPTY_HASH)
 		return;
-	call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu);
+	call_rcu(&hash->rcu, __free_ftrace_hash_rcu);
 }
 
 void ftrace_free_filter(struct ftrace_ops *ops)
@@ -1501,7 +1501,7 @@ static bool hash_contains_ip(unsigned long ip,
  * the ip is not in the ops->notrace_hash.
  *
  * This needs to be called with preemption disabled as
- * the hashes are freed with call_rcu_sched().
+ * the hashes are freed with call_rcu().
  */
 static int
 ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
@@ -4496,7 +4496,7 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
 	if (ftrace_enabled && !ftrace_hash_empty(hash))
 		ftrace_run_modify_code(&probe->ops, FTRACE_UPDATE_CALLS,
 				       &old_hash_ops);
-	synchronize_sched();
+	synchronize_rcu();
 
 	hlist_for_each_entry_safe(entry, tmp, &hhd, hlist) {
 		hlist_del(&entry->hlist);
@@ -5314,7 +5314,7 @@ ftrace_graph_release(struct inode *inode, struct file *file)
 		mutex_unlock(&graph_lock);
 
 		/* Wait till all users are no longer using the old hash */
-		synchronize_sched();
+		synchronize_rcu();
 
 		free_ftrace_hash(old_hash);
 	}
@@ -5708,7 +5708,7 @@ void ftrace_release_mod(struct module *mod)
 	list_for_each_entry_safe(mod_map, n, &ftrace_mod_maps, list) {
 		if (mod_map->mod == mod) {
 			list_del_rcu(&mod_map->list);
-			call_rcu_sched(&mod_map->rcu, ftrace_free_mod_map);
+			call_rcu(&mod_map->rcu, ftrace_free_mod_map);
 			break;
 		}
 	}
@@ -5928,7 +5928,7 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 	struct ftrace_mod_map *mod_map;
 	const char *ret = NULL;
 
-	/* mod_map is freed via call_rcu_sched() */
+	/* mod_map is freed via call_rcu() */
 	preempt_disable();
 	list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) {
 		ret = ftrace_func_address_lookup(mod_map, addr, size, off, sym);
@@ -6263,7 +6263,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 
 	/*
 	 * Some of the ops may be dynamically allocated,
-	 * they must be freed after a synchronize_sched().
+	 * they must be freed after a synchronize_rcu().
 	 */
 	preempt_disable_notrace();
 
@@ -6434,7 +6434,7 @@ static void clear_ftrace_pids(struct trace_array *tr)
 	rcu_assign_pointer(tr->function_pids, NULL);
 
 	/* Wait till all users are no longer using pid filtering */
-	synchronize_sched();
+	synchronize_rcu();
 
 	trace_free_pid_list(pid_list);
 }
@@ -6581,7 +6581,7 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf,
 	rcu_assign_pointer(tr->function_pids, pid_list);
 
 	if (filtered_pids) {
-		synchronize_sched();
+		synchronize_rcu();
 		trace_free_pid_list(filtered_pids);
 	} else if (pid_list) {
 		/* Register a probe to set whether to ignore the tracing of a task */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 65bd4616220d..4f3247a53259 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1834,7 +1834,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 		 * There could have been a race between checking
 		 * record_disable and incrementing it.
 		 */
-		synchronize_sched();
+		synchronize_rcu();
 		for_each_buffer_cpu(buffer, cpu) {
 			cpu_buffer = buffer->buffers[cpu];
 			rb_check_pages(cpu_buffer);
@@ -3151,7 +3151,7 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
  * This prevents all writes to the buffer. Any attempt to write
  * to the buffer after this will fail and return NULL.
  *
- * The caller should call synchronize_sched() after this.
+ * The caller should call synchronize_rcu() after this.
  */
 void ring_buffer_record_disable(struct ring_buffer *buffer)
 {
@@ -3253,7 +3253,7 @@ bool ring_buffer_record_is_set_on(struct ring_buffer *buffer)
  * This prevents all writes to the buffer. Any attempt to write
  * to the buffer after this will fail and return NULL.
  *
- * The caller should call synchronize_sched() after this.
+ * The caller should call synchronize_rcu() after this.
  */
 void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu)
 {
@@ -4191,7 +4191,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_prepare);
 void
 ring_buffer_read_prepare_sync(void)
 {
-	synchronize_sched();
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync);
 
@@ -4363,7 +4363,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	atomic_inc(&cpu_buffer->record_disabled);
 
 	/* Make sure all commits have finished */
-	synchronize_sched();
+	synchronize_rcu();
 
 	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
@@ -4496,7 +4496,7 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 		goto out;
 
 	/*
-	 * We can't do a synchronize_sched here because this
+	 * We can't do a synchronize_rcu here because this
 	 * function can be called in atomic context.
 	 * Normally this will be called from the same CPU as cpu.
 	 * If not it's up to the caller to protect this.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ff1c4b20cd0a..51612b4a603f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1681,7 +1681,7 @@ void tracing_reset(struct trace_buffer *buf, int cpu)
 	ring_buffer_record_disable(buffer);
 
 	/* Make sure all commits have finished */
-	synchronize_sched();
+	synchronize_rcu();
 	ring_buffer_reset_cpu(buffer, cpu);
 
 	ring_buffer_record_enable(buffer);
@@ -1698,7 +1698,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf)
 	ring_buffer_record_disable(buffer);
 
 	/* Make sure all commits have finished */
-	synchronize_sched();
+	synchronize_rcu();
 
 	buf->time_start = buffer_ftrace_now(buf, buf->cpu);
 
@@ -2250,7 +2250,7 @@ void trace_buffered_event_disable(void)
 	preempt_enable();
 
 	/* Wait for all current users to finish */
-	synchronize_sched();
+	synchronize_rcu();
 
 	for_each_tracing_cpu(cpu) {
 		free_page((unsigned long)per_cpu(trace_buffered_event, cpu));
@@ -5398,7 +5398,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
 	if (tr->current_trace->reset)
 		tr->current_trace->reset(tr);
 
-	/* Current trace needs to be nop_trace before synchronize_sched */
+	/* Current trace needs to be nop_trace before synchronize_rcu */
 	tr->current_trace = &nop_trace;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -5412,7 +5412,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
 		 * The update_max_tr is called from interrupts disabled
 		 * so a synchronized_sched() is sufficient.
 		 */
-		synchronize_sched();
+		synchronize_rcu();
 		free_snapshot(tr);
 	}
 #endif
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 5574e862de8d..27821480105e 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1616,7 +1616,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
 
 	/*
 	 * The calls can still be using the old filters.
-	 * Do a synchronize_sched() and to ensure all calls are
+	 * Do a synchronize_rcu() and to ensure all calls are
 	 * done with them before we free them.
 	 */
 	tracepoint_synchronize_unregister();
@@ -1848,7 +1848,7 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir,
 	if (filter) {
 		/*
 		 * No event actually uses the system filter
-		 * we can free it without synchronize_sched().
+		 * we can free it without synchronize_rcu().
 		 */
 		__free_filter(system->filter);
 		system->filter = filter;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index fec67188c4d2..adc153ab51c0 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -333,7 +333,7 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
 		 * event_call related objects, which will be accessed in
 		 * the kprobe_trace_func/kretprobe_trace_func.
 		 */
-		synchronize_sched();
+		synchronize_rcu();
 		kfree(link);	/* Ignored if link == NULL */
 	}
 
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index a3be42304485..46f2ab1e08a9 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -92,7 +92,7 @@ static __init int release_early_probes(void)
 	while (early_probes) {
 		tmp = early_probes;
 		early_probes = tmp->next;
-		call_rcu_sched(tmp, rcu_free_old_probes);
+		call_rcu(tmp, rcu_free_old_probes);
 	}
 
 	return 0;
@@ -123,7 +123,7 @@ static inline void release_probes(struct tracepoint_func *old)
 		 * cover both cases. So let us chain the SRCU and sched RCU
 		 * callbacks to wait for both grace periods.
 		 */
-		call_rcu_sched(&tp_probes->rcu, rcu_free_old_probes);
+		call_rcu(&tp_probes->rcu, rcu_free_old_probes);
 	}
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0280deac392e..392be4b252f6 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3396,7 +3396,7 @@ static void put_unbound_pool(struct worker_pool *pool)
 	del_timer_sync(&pool->mayday_timer);
 
 	/* sched-RCU protected to allow dereferences from get_work_pool() */
-	call_rcu_sched(&pool->rcu, rcu_free_pool);
+	call_rcu(&pool->rcu, rcu_free_pool);
 }
 
 /**
@@ -3503,14 +3503,14 @@ static void pwq_unbound_release_workfn(struct work_struct *work)
 	put_unbound_pool(pool);
 	mutex_unlock(&wq_pool_mutex);
 
-	call_rcu_sched(&pwq->rcu, rcu_free_pwq);
+	call_rcu(&pwq->rcu, rcu_free_pwq);
 
 	/*
 	 * If we're the last pwq going away, @wq is already dead and no one
 	 * is gonna access it anymore.  Schedule RCU free.
 	 */
 	if (is_last)
-		call_rcu_sched(&wq->rcu, rcu_free_wq);
+		call_rcu(&wq->rcu, rcu_free_wq);
 }
 
 /**
@@ -4195,7 +4195,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
 		 * The base ref is never dropped on per-cpu pwqs.  Directly
 		 * schedule RCU free.
 		 */
-		call_rcu_sched(&wq->rcu, rcu_free_wq);
+		call_rcu(&wq->rcu, rcu_free_wq);
 	} else {
 		/*
 		 * We're the sole accessor of @wq at this point.  Directly