srcu: Parallelize callback handling

Peter Zijlstra proposed using SRCU to reduce mmap_sem contention [1,2],
however, there are workloads that could result in a high volume of
concurrent invocations of call_srcu(), which with current SRCU would
result in excessive lock contention on the srcu_struct structure's
->queue_lock, which protects SRCU's callback lists.  This commit therefore
moves SRCU to per-CPU callback lists, thus greatly reducing contention.

Because a given SRCU instance no longer has a single centralized callback
list, starting grace periods and invoking callbacks are both more complex
than in the single-list Classic SRCU implementation.  Starting grace
periods and handling callbacks are now handled using an srcu_node tree
that is in some ways similar to the rcu_node trees used by RCU-bh,
RCU-preempt, and RCU-sched (for example, the srcu_node tree shape is
controlled by exactly the same Kconfig options and boot parameters that
control the shape of the rcu_node tree).

In addition, the old per-CPU srcu_array structure is now named srcu_data
and contains an rcu_segcblist structure named ->srcu_cblist for its
callbacks (and a spinlock to protect this).  The srcu_struct gets
an srcu_gp_seq that is used to associate callback segments with the
corresponding completion-time grace-period number.  These completion-time
grace-period numbers are propagated up the srcu_node tree so that the
grace-period workqueue handler can determine whether additional grace
periods are needed on the one hand and where to look for callbacks that
are ready to be invoked.

The srcu_barrier() function must now wait on all instances of the per-CPU
->srcu_cblist.  Because each ->srcu_cblist is protected by ->lock,
srcu_barrier() can remotely add the needed callbacks.  In theory,
it could also remotely start grace periods, but in practice doing so
is complex and racy.  And interestingly enough, it is never necessary
for srcu_barrier() to start a grace period because srcu_barrier() only
enqueues a callback when a callback is already present--and it turns out
that a grace period has to have already been started for this pre-existing
callback.  Furthermore, it is only the callback that srcu_barrier()
needs to wait on, not any particular grace period.  Therefore, a new
rcu_segcblist_entrain() function enqueues the srcu_barrier() function's
callback into the same segment occupied by the last pre-existing callback
in the list.  The special case where all the pre-existing callbacks are
on a different list (because they are in the process of being invoked)
is handled by enqueuing srcu_barrier()'s callback into the RCU_DONE_TAIL
segment, relying on the done-callbacks check that takes place after all
callbacks are inovked.

Note that the readers use the same algorithm as before.  Note that there
is a separate srcu_idx that tells the readers what counter to increment.
This unfortunately cannot be combined with srcu_gp_seq because they
need to be incremented at different times.

This commit introduces some ugly #ifdefs in rcutorture.  These will go
away when I feel good enough about Tree SRCU to ditch Classic SRCU.

Some crude performance comparisons, courtesy of a quickly hacked rcuperf
asynchronous-grace-period capability:

			Callback Queuing Overhead
			-------------------------
	# CPUS		Classic SRCU	Tree SRCU
	------          ------------    ---------
	     2              0.349 us     0.342 us
	    16             31.66  us     0.4   us
	    41             ---------     0.417 us

The times are the 90th percentiles, a statistic that was chosen to reject
the overheads of the occasional srcu_barrier() call needed to avoid OOMing
the test machine.  The rcuperf test hangs when running Classic SRCU at 41
CPUs, hence the line of dashes.  Despite the hacks to both the rcuperf code
and that statistics, this is a convincing demonstration of Tree SRCU's
performance and scalability advantages.

[1] https://lwn.net/Articles/309030/
[2] https://patchwork.kernel.org/patch/5108281/

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Fix initialization if synchronize_srcu_expedited() called first. ]

include/linux/rcu_segcblist.h

@@ -401,6 +401,37 @@ static inline void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
 	rsclp->tails[RCU_NEXT_TAIL] = &rhp->next;
 }
 
+/*
+ * Entrain the specified callback onto the specified rcu_segcblist at
+ * the end of the last non-empty segment.  If the entire rcu_segcblist
+ * is empty, make no change, but return false.
+ *
+ * This is intended for use by rcu_barrier()-like primitives, -not-
+ * for normal grace-period use.  IMPORTANT:  The callback you enqueue
+ * will wait for all prior callbacks, NOT necessarily for a grace
+ * period.  You have been warned.
+ */
+static inline bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
+					 struct rcu_head *rhp, bool lazy)
+{
+	int i;
+
+	if (rcu_segcblist_n_cbs(rsclp) == 0)
+		return false;
+	WRITE_ONCE(rsclp->len, rsclp->len + 1);
+	if (lazy)
+		rsclp->len_lazy++;
+	smp_mb(); /* Ensure counts are updated before callback is entrained. */
+	rhp->next = NULL;
+	for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--)
+		if (rsclp->tails[i] != rsclp->tails[i - 1])
+			break;
+	*rsclp->tails[i] = rhp;
+	for (; i <= RCU_NEXT_TAIL; i++)
+		rsclp->tails[i] = &rhp->next;
+	return true;
+}
+
 /*
  * Extract only the counts from the specified rcu_segcblist structure,
  * and place them in the specified rcu_cblist structure.  This function
@@ -537,7 +568,8 @@ static inline void rcu_segcblist_advance(struct rcu_segcblist *rsclp,
 	int i, j;
 
 	WARN_ON_ONCE(!rcu_segcblist_is_enabled(rsclp));
-	WARN_ON_ONCE(rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL));
+	if (rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL))
+		return;
 
 	/*
 	 * Find all callbacks whose ->gp_seq numbers indicate that they
@@ -582,8 +614,9 @@ static inline void rcu_segcblist_advance(struct rcu_segcblist *rsclp,
  * them to complete at the end of the earlier grace period.
  *
  * This function operates on an rcu_segcblist structure, and also the
- * grace-period sequence number at which new callbacks would become
- * ready to invoke.
+ * grace-period sequence number seq at which new callbacks would become
+ * ready to invoke.  Returns true if there are callbacks that won't be
+ * ready to invoke until seq, false otherwise.
  */
 static inline bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp,
 					    unsigned long seq)
@@ -591,7 +624,8 @@ static inline bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp,
 	int i;
 
 	WARN_ON_ONCE(!rcu_segcblist_is_enabled(rsclp));
-	WARN_ON_ONCE(rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL));
+	if (rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL))
+		return false;
 
 	/*
 	 * Find the segment preceding the oldest segment of callbacks

include/linux/srcutree.h

@@ -24,25 +24,75 @@
 #ifndef _LINUX_SRCU_TREE_H
 #define _LINUX_SRCU_TREE_H
 
-struct srcu_array {
-	unsigned long lock_count[2];
-	unsigned long unlock_count[2];
+#include <linux/rcu_node_tree.h>
+#include <linux/completion.h>
+
+struct srcu_node;
+struct srcu_struct;
+
+/*
+ * Per-CPU structure feeding into leaf srcu_node, similar in function
+ * to rcu_node.
+ */
+struct srcu_data {
+	/* Read-side state. */
+	unsigned long srcu_lock_count[2];	/* Locks per CPU. */
+	unsigned long srcu_unlock_count[2];	/* Unlocks per CPU. */
+
+	/* Update-side state. */
+	spinlock_t lock ____cacheline_internodealigned_in_smp;
+	struct rcu_segcblist srcu_cblist;	/* List of callbacks.*/
+	unsigned long srcu_gp_seq_needed;	/* Furthest future GP needed. */
+	bool srcu_cblist_invoking;		/* Invoking these CBs? */
+	struct delayed_work work;		/* Context for CB invoking. */
+	struct rcu_head srcu_barrier_head;	/* For srcu_barrier() use. */
+	struct srcu_node *mynode;		/* Leaf srcu_node. */
+	int cpu;
+	struct srcu_struct *sp;
 };
 
+/*
+ * Node in SRCU combining tree, similar in function to rcu_data.
+ */
+struct srcu_node {
+	spinlock_t lock;
+	unsigned long srcu_have_cbs[4];		/* GP seq for children */
+						/*  having CBs, but only */
+						/*  is > ->srcu_gq_seq. */
+	struct srcu_node *srcu_parent;		/* Next up in tree. */
+	int grplo;				/* Least CPU for node. */
+	int grphi;				/* Biggest CPU for node. */
+};
+
+/*
+ * Per-SRCU-domain structure, similar in function to rcu_state.
+ */
 struct srcu_struct {
-	unsigned long completed;
-	unsigned long srcu_gp_seq;
-	atomic_t srcu_exp_cnt;
-	struct srcu_array __percpu *per_cpu_ref;
-	spinlock_t queue_lock; /* protect ->srcu_cblist */
-	struct rcu_segcblist srcu_cblist;
+	struct srcu_node node[NUM_RCU_NODES];	/* Combining tree. */
+	struct srcu_node *level[RCU_NUM_LVLS + 1];
+						/* First node at each level. */
+	struct mutex srcu_cb_mutex;		/* Serialize CB preparation. */
+	spinlock_t gp_lock;			/* protect ->srcu_cblist */
+	struct mutex srcu_gp_mutex;		/* Serialize GP work. */
+	unsigned int srcu_idx;			/* Current rdr array element. */
+	unsigned long srcu_gp_seq;		/* Grace-period seq #. */
+	unsigned long srcu_gp_seq_needed;	/* Latest gp_seq needed. */
+	atomic_t srcu_exp_cnt;			/* # ongoing expedited GPs. */
+	struct srcu_data __percpu *sda;		/* Per-CPU srcu_data array. */
+	unsigned long srcu_barrier_seq;		/* srcu_barrier seq #. */
+	struct mutex srcu_barrier_mutex;	/* Serialize barrier ops. */
+	struct completion srcu_barrier_completion;
+						/* Awaken barrier rq at end. */
+	atomic_t srcu_barrier_cpu_cnt;		/* # CPUs not yet posting a */
+						/*  callback for the barrier */
+						/*  operation. */
 	struct delayed_work work;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 };
 
-/* Values for -> state variable. */
+/* Values for state variable (bottom bits of ->srcu_gp_seq). */
 #define SRCU_STATE_IDLE		0
 #define SRCU_STATE_SCAN1	1
 #define SRCU_STATE_SCAN2	2
@@ -51,11 +101,9 @@ void process_srcu(struct work_struct *work);
 
 #define __SRCU_STRUCT_INIT(name)					\
 	{								\
-		.completed = -300,					\
-		.per_cpu_ref = &name##_srcu_array,			\
-		.queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock),	\
-		.srcu_cblist = RCU_SEGCBLIST_INITIALIZER(name.srcu_cblist),\
-		.work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\
+		.sda = &name##_srcu_data,				\
+		.gp_lock = __SPIN_LOCK_UNLOCKED(name.gp_lock),		\
+		.srcu_gp_seq_needed = 0 - 1,				\
 		__SRCU_DEP_MAP_INIT(name)				\
 	}
 
@@ -79,7 +127,7 @@ void process_srcu(struct work_struct *work);
  * See include/linux/percpu-defs.h for the rules on per-CPU variables.
  */
 #define __DEFINE_SRCU(name, is_static)					\
-	static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
+	static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data);\
 	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
 #define DEFINE_SRCU(name)		__DEFINE_SRCU(name, /* not static */)
 #define DEFINE_STATIC_SRCU(name)	__DEFINE_SRCU(name, static)

kernel/rcu/rcutorture.c

@@ -563,17 +563,30 @@ static void srcu_torture_stats(void)
 	int idx;
 
 #if defined(CONFIG_TREE_SRCU) || defined(CONFIG_CLASSIC_SRCU)
+#ifdef CONFIG_TREE_SRCU
+	idx = srcu_ctlp->srcu_idx & 0x1;
+#else /* #ifdef CONFIG_TREE_SRCU */
 	idx = srcu_ctlp->completed & 0x1;
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
 	pr_alert("%s%s Tree SRCU per-CPU(idx=%d):",
 		 torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
 		unsigned long l0, l1;
 		unsigned long u0, u1;
 		long c0, c1;
-		struct srcu_array *counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
+#ifdef CONFIG_TREE_SRCU
+		struct srcu_data *counts;
 
+		counts = per_cpu_ptr(srcu_ctlp->sda, cpu);
+		u0 = counts->srcu_unlock_count[!idx];
+		u1 = counts->srcu_unlock_count[idx];
+#else /* #ifdef CONFIG_TREE_SRCU */
+		struct srcu_array *counts;
+
+		counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
 		u0 = counts->unlock_count[!idx];
 		u1 = counts->unlock_count[idx];
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
 
 		/*
 		 * Make sure that a lock is always counted if the corresponding
@@ -581,8 +594,13 @@ static void srcu_torture_stats(void)
 		 */
 		smp_rmb();
 
+#ifdef CONFIG_TREE_SRCU
+		l0 = counts->srcu_lock_count[!idx];
+		l1 = counts->srcu_lock_count[idx];
+#else /* #ifdef CONFIG_TREE_SRCU */
 		l0 = counts->lock_count[!idx];
 		l1 = counts->lock_count[idx];
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
 
 		c0 = l0 - u0;
 		c1 = l1 - u1;

kernel/rcu/srcutree.c

@@ -36,19 +36,110 @@
 #include <linux/delay.h>
 #include <linux/srcu.h>
 
-#include <linux/rcu_node_tree.h>
 #include "rcu.h"
 
-static int init_srcu_struct_fields(struct srcu_struct *sp)
+static void srcu_invoke_callbacks(struct work_struct *work);
+static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);
+
+/*
+ * Initialize SRCU combining tree.  Note that statically allocated
+ * srcu_struct structures might already have srcu_read_lock() and
+ * 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)
 {
-	sp->completed = 0;
+	int cpu;
+	int i;
+	int level = 0;
+	int levelspread[RCU_NUM_LVLS];
+	struct srcu_data *sdp;
+	struct srcu_node *snp;
+	struct srcu_node *snp_first;
+
+	/* Work out the overall tree geometry. */
+	sp->level[0] = &sp->node[0];
+	for (i = 1; i < rcu_num_lvls; i++)
+		sp->level[i] = sp->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. */
+	rcu_for_each_node_breadth_first(sp, snp) {
+		spin_lock_init(&snp->lock);
+		for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++)
+			snp->srcu_have_cbs[i] = 0;
+		snp->grplo = -1;
+		snp->grphi = -1;
+		if (snp == &sp->node[0]) {
+			/* Root node, special case. */
+			snp->srcu_parent = NULL;
+			continue;
+		}
+
+		/* Non-root node. */
+		if (snp == sp->level[level + 1])
+			level++;
+		snp->srcu_parent = sp->level[level - 1] +
+				   (snp - sp->level[level]) /
+				   levelspread[level - 1];
+	}
+
+	/*
+	 * Initialize the per-CPU srcu_data array, which feeds into the
+	 * leaves of the srcu_node tree.
+	 */
+	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];
+	for_each_possible_cpu(cpu) {
+		sdp = per_cpu_ptr(sp->sda, cpu);
+		spin_lock_init(&sdp->lock);
+		rcu_segcblist_init(&sdp->srcu_cblist);
+		sdp->srcu_cblist_invoking = false;
+		sdp->srcu_gp_seq_needed = sp->srcu_gp_seq;
+		sdp->mynode = &snp_first[cpu / levelspread[level]];
+		for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) {
+			if (snp->grplo < 0)
+				snp->grplo = cpu;
+			snp->grphi = cpu;
+		}
+		sdp->cpu = cpu;
+		INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks);
+		sdp->sp = sp;
+		if (is_static)
+			continue;
+
+		/* Dynamically allocated, better be no srcu_read_locks()! */
+		for (i = 0; i < ARRAY_SIZE(sdp->srcu_lock_count); i++) {
+			sdp->srcu_lock_count[i] = 0;
+			sdp->srcu_unlock_count[i] = 0;
+		}
+	}
+}
+
+/*
+ * Initialize non-compile-time initialized fields, including the
+ * associated srcu_node and srcu_data structures.  The 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)
+{
+	mutex_init(&sp->srcu_cb_mutex);
+	mutex_init(&sp->srcu_gp_mutex);
+	sp->srcu_idx = 0;
 	sp->srcu_gp_seq = 0;
 	atomic_set(&sp->srcu_exp_cnt, 0);
-	spin_lock_init(&sp->queue_lock);
-	rcu_segcblist_init(&sp->srcu_cblist);
+	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);
-	sp->per_cpu_ref = alloc_percpu(struct srcu_array);
-	return sp->per_cpu_ref ? 0 : -ENOMEM;
+	if (!is_static)
+		sp->sda = alloc_percpu(struct srcu_data);
+	init_srcu_struct_nodes(sp, is_static);
+	smp_store_release(&sp->srcu_gp_seq_needed, 0); /* Init done. */
+	return sp->sda ? 0 : -ENOMEM;
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -59,7 +150,8 @@ int __init_srcu_struct(struct srcu_struct *sp, const char *name,
 	/* 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);
+	spin_lock_init(&sp->gp_lock);
+	return init_srcu_struct_fields(sp, false);
 }
 EXPORT_SYMBOL_GPL(__init_srcu_struct);
 
@@ -75,15 +167,41 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct);
  */
 int init_srcu_struct(struct srcu_struct *sp)
 {
-	return init_srcu_struct_fields(sp);
+	spin_lock_init(&sp->gp_lock);
+	return init_srcu_struct_fields(sp, false);
 }
 EXPORT_SYMBOL_GPL(init_srcu_struct);
 
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /*
- * Returns approximate total of the readers' ->lock_count[] values for the
- * rank of per-CPU counters specified by idx.
+ * 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 ->gp_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)
+{
+	unsigned long flags;
+
+	WARN_ON_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INIT);
+	/* The smp_load_acquire() pairs with the smp_store_release(). */
+	if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/
+		return; /* Already initialized. */
+	spin_lock_irqsave(&sp->gp_lock, flags);
+	if (!rcu_seq_state(sp->srcu_gp_seq_needed)) {
+		spin_unlock_irqrestore(&sp->gp_lock, flags);
+		return;
+	}
+	init_srcu_struct_fields(sp, true);
+	spin_unlock_irqrestore(&sp->gp_lock, 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)
 {
@@ -91,16 +209,16 @@ static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+		struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
 
-		sum += READ_ONCE(cpuc->lock_count[idx]);
+		sum += READ_ONCE(cpuc->srcu_lock_count[idx]);
 	}
 	return sum;
 }
 
 /*
- * Returns approximate total of the readers' ->unlock_count[] values for the
- * rank of per-CPU counters specified by 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)
 {
@@ -108,9 +226,9 @@ static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+		struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
 
-		sum += READ_ONCE(cpuc->unlock_count[idx]);
+		sum += READ_ONCE(cpuc->srcu_unlock_count[idx]);
 	}
 	return sum;
 }
@@ -145,14 +263,14 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
 	 * the current index but not have incremented the lock counter yet.
 	 *
 	 * Possible bug: There is no guarantee that there haven't been
-	 * ULONG_MAX increments of ->lock_count[] since the unlocks were
+	 * ULONG_MAX increments of ->srcu_lock_count[] since the unlocks were
 	 * counted, meaning that this could return true even if there are
 	 * still active readers.  Since there are no memory barriers around
-	 * srcu_flip(), the CPU is not required to increment ->completed
+	 * srcu_flip(), the CPU is not required to increment ->srcu_idx
 	 * before running srcu_readers_unlock_idx(), which means that there
 	 * could be an arbitrarily large number of critical sections that
 	 * execute after srcu_readers_unlock_idx() but use the old value
-	 * of ->completed.
+	 * of ->srcu_idx.
 	 */
 	return srcu_readers_lock_idx(sp, idx) == unlocks;
 }
@@ -172,12 +290,12 @@ static bool srcu_readers_active(struct srcu_struct *sp)
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+		struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
 
-		sum += READ_ONCE(cpuc->lock_count[0]);
-		sum += READ_ONCE(cpuc->lock_count[1]);
-		sum -= READ_ONCE(cpuc->unlock_count[0]);
-		sum -= READ_ONCE(cpuc->unlock_count[1]);
+		sum += READ_ONCE(cpuc->srcu_lock_count[0]);
+		sum += READ_ONCE(cpuc->srcu_lock_count[1]);
+		sum -= READ_ONCE(cpuc->srcu_unlock_count[0]);
+		sum -= READ_ONCE(cpuc->srcu_unlock_count[1]);
 	}
 	return sum;
 }
@@ -193,18 +311,21 @@ static bool srcu_readers_active(struct srcu_struct *sp)
  */
 void cleanup_srcu_struct(struct srcu_struct *sp)
 {
+	int cpu;
+
 	WARN_ON_ONCE(atomic_read(&sp->srcu_exp_cnt));
 	if (WARN_ON(srcu_readers_active(sp)))
 		return; /* Leakage unless caller handles error. */
-	if (WARN_ON(!rcu_segcblist_empty(&sp->srcu_cblist)))
-		return; /* Leakage unless caller handles error. */
 	flush_delayed_work(&sp->work);
-	if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE)) {
-		pr_info("cleanup_srcu_struct: Active srcu_struct %lu CBs %c state: %d\n", rcu_segcblist_n_cbs(&sp->srcu_cblist), ".E"[rcu_segcblist_empty(&sp->srcu_cblist)], rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+	for_each_possible_cpu(cpu)
+		flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+	if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
+	    WARN_ON(srcu_readers_active(sp))) {
+		pr_info("cleanup_srcu_struct: Active srcu_struct %p state: %d\n", sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
 		return; /* Caller forgot to stop doing call_srcu()? */
 	}
-	free_percpu(sp->per_cpu_ref);
-	sp->per_cpu_ref = NULL;
+	free_percpu(sp->sda);
+	sp->sda = NULL;
 }
 EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
@@ -217,8 +338,8 @@ int __srcu_read_lock(struct srcu_struct *sp)
 {
 	int idx;
 
-	idx = READ_ONCE(sp->completed) & 0x1;
-	__this_cpu_inc(sp->per_cpu_ref->lock_count[idx]);
+	idx = READ_ONCE(sp->srcu_idx) & 0x1;
+	__this_cpu_inc(sp->sda->srcu_lock_count[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
 	return idx;
 }
@@ -233,7 +354,7 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
 	smp_mb(); /* C */  /* Avoid leaking the critical section. */
-	this_cpu_inc(sp->per_cpu_ref->unlock_count[idx]);
+	this_cpu_inc(sp->sda->srcu_unlock_count[idx]);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
@@ -251,19 +372,207 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock);
  */
 static void srcu_gp_start(struct srcu_struct *sp)
 {
+	struct srcu_data *sdp = this_cpu_ptr(sp->sda);
 	int state;
 
-	rcu_segcblist_accelerate(&sp->srcu_cblist,
-				 rcu_seq_snap(&sp->srcu_gp_seq));
+	RCU_LOCKDEP_WARN(!lockdep_is_held(&sp->gp_lock),
+			 "Invoked srcu_gp_start() without ->gp_lock!");
+	WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
+	rcu_segcblist_advance(&sdp->srcu_cblist,
+			      rcu_seq_current(&sp->srcu_gp_seq));
+	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
+				       rcu_seq_snap(&sp->srcu_gp_seq));
 	rcu_seq_start(&sp->srcu_gp_seq);
 	state = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
 	WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
 }
 
+/*
+ * Track online CPUs to guide callback workqueue placement.
+ */
+DEFINE_PER_CPU(bool, srcu_online);
+
+void srcu_online_cpu(unsigned int cpu)
+{
+	WRITE_ONCE(per_cpu(srcu_online, cpu), true);
+}
+
+void srcu_offline_cpu(unsigned int cpu)
+{
+	WRITE_ONCE(per_cpu(srcu_online, cpu), false);
+}
+
+/*
+ * Place the workqueue handler on the specified CPU if online, otherwise
+ * just run it whereever.  This is useful for placing workqueue handlers
+ * that are to invoke the specified CPU's callbacks.
+ */
+static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
+				       struct delayed_work *dwork,
+				       unsigned long delay)
+{
+	bool ret;
+
+	preempt_disable();
+	if (READ_ONCE(per_cpu(srcu_online, cpu)))
+		ret = queue_delayed_work_on(cpu, wq, dwork, delay);
+	else
+		ret = queue_delayed_work(wq, dwork, delay);
+	preempt_enable();
+	return ret;
+}
+
+/*
+ * Schedule callback invocation for the specified srcu_data structure,
+ * if possible, on the corresponding CPU.
+ */
+static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
+{
+	srcu_queue_delayed_work_on(sdp->cpu, system_power_efficient_wq,
+				   &sdp->work, delay);
+}
+
+/*
+ * Schedule callback invocation for all srcu_data structures associated
+ * with the specified srcu_node structure, if possible, on the corresponding
+ * CPUs.
+ */
+static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp)
+{
+	int cpu;
+
+	for (cpu = snp->grplo; cpu <= snp->grphi; cpu++)
+		srcu_schedule_cbs_sdp(per_cpu_ptr(sp->sda, cpu), SRCU_INTERVAL);
+}
+
+/*
+ * Note the end of an SRCU grace period.  Initiates callback invocation
+ * and starts a new grace period if needed.
+ *
+ * The ->srcu_cb_mutex acquisition does not protect any data, but
+ * instead prevents more than one grace period from starting while we
+ * 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)
+{
+	bool cbs;
+	unsigned long gpseq;
+	int idx;
+	int idxnext;
+	struct srcu_node *snp;
+
+	/* Prevent more than one additional grace period. */
+	mutex_lock(&sp->srcu_cb_mutex);
+
+	/* End the current grace period. */
+	spin_lock_irq(&sp->gp_lock);
+	idx = rcu_seq_state(sp->srcu_gp_seq);
+	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
+	rcu_seq_end(&sp->srcu_gp_seq);
+	gpseq = rcu_seq_current(&sp->srcu_gp_seq);
+	spin_unlock_irq(&sp->gp_lock);
+	mutex_unlock(&sp->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);
+	idxnext = (idx + 1) % ARRAY_SIZE(snp->srcu_have_cbs);
+	rcu_for_each_node_breadth_first(sp, snp) {
+		spin_lock_irq(&snp->lock);
+		cbs = false;
+		if (snp >= sp->level[rcu_num_lvls - 1])
+			cbs = snp->srcu_have_cbs[idx] == gpseq;
+		snp->srcu_have_cbs[idx] = gpseq;
+		rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
+		spin_unlock_irq(&snp->lock);
+		if (cbs) {
+			smp_mb(); /* GP end before CB invocation. */
+			srcu_schedule_cbs_snp(sp, snp);
+		}
+	}
+
+	/* Callback initiation done, allow grace periods after next. */
+	mutex_unlock(&sp->srcu_cb_mutex);
+
+	/* Start a new grace period if needed. */
+	spin_lock_irq(&sp->gp_lock);
+	gpseq = rcu_seq_current(&sp->srcu_gp_seq);
+	if (!rcu_seq_state(gpseq) &&
+	    ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) {
+		srcu_gp_start(sp);
+		spin_unlock_irq(&sp->gp_lock);
+		/* Throttle expedited grace periods: Should be rare! */
+		srcu_reschedule(sp, atomic_read(&sp->srcu_exp_cnt) &&
+				    rcu_seq_ctr(gpseq) & 0xf
+				    ? 0
+				    : SRCU_INTERVAL);
+	} else {
+		spin_unlock_irq(&sp->gp_lock);
+	}
+}
+
+/*
+ * Funnel-locking scheme to scalably mediate many concurrent grace-period
+ * requests.  The winner has to do the work of actually starting grace
+ * period s.  Losers must either ensure that their desired grace-period
+ * number is recorded on at least their leaf srcu_node structure, or they
+ * must take steps to invoke their own callbacks.
+ */
+static void srcu_funnel_gp_start(struct srcu_struct *sp,
+				 struct srcu_data *sdp,
+				 unsigned long s)
+{
+	unsigned long flags;
+	int idx = rcu_seq_ctr(s) % ARRAY_SIZE(sdp->mynode->srcu_have_cbs);
+	struct srcu_node *snp = sdp->mynode;
+	unsigned long snp_seq;
+
+	/* 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)
+			return; /* GP already done and CBs recorded. */
+		spin_lock_irqsave(&snp->lock, flags);
+		if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
+			snp_seq = snp->srcu_have_cbs[idx];
+			spin_unlock_irqrestore(&snp->lock, flags);
+			if (snp == sdp->mynode && snp_seq != s) {
+				smp_mb(); /* CBs after GP! */
+				srcu_schedule_cbs_sdp(sdp, 0);
+			}
+			return;
+		}
+		snp->srcu_have_cbs[idx] = s;
+		spin_unlock_irqrestore(&snp->lock, flags);
+	}
+
+	/* Top of tree, must ensure the grace period will be started. */
+	spin_lock_irqsave(&sp->gp_lock, flags);
+	if (ULONG_CMP_LT(sp->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); /*^^^*/
+	}
+
+	/* 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);
+		queue_delayed_work(system_power_efficient_wq, &sp->work,
+				   atomic_read(&sp->srcu_exp_cnt)
+				   ? 0
+				   : SRCU_INTERVAL);
+	}
+	spin_unlock_irqrestore(&sp->gp_lock, flags);
+}
+
 /*
  * Wait until all readers counted by array index idx complete, but
  * loop an additional time if there is an expedited grace period pending.
- * The caller must ensure that ->completed is not changed while checking.
+ * 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)
 {
@@ -277,13 +586,13 @@ static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
 }
 
 /*
- * Increment the ->completed counter so that future SRCU readers will
- * use the other rank of the ->(un)lock_count[] arrays.  This allows
+ * Increment the ->srcu_idx counter so that future SRCU readers will
+ * 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)
 {
-	WRITE_ONCE(sp->completed, sp->completed + 1);
+	WRITE_ONCE(sp->srcu_idx, sp->srcu_idx + 1);
 
 	/*
 	 * Ensure that if the updater misses an __srcu_read_unlock()
@@ -296,21 +605,9 @@ static void srcu_flip(struct srcu_struct *sp)
 }
 
 /*
- * End an SRCU grace period.
- */
-static void srcu_gp_end(struct srcu_struct *sp)
-{
-	rcu_seq_end(&sp->srcu_gp_seq);
-
-	spin_lock_irq(&sp->queue_lock);
-	rcu_segcblist_advance(&sp->srcu_cblist,
-			      rcu_seq_current(&sp->srcu_gp_seq));
-	spin_unlock_irq(&sp->queue_lock);
-}
-
-/*
- * Enqueue an SRCU callback on the specified srcu_struct structure,
- * initiating grace-period processing if it is not already running.
+ * Enqueue an SRCU callback on the srcu_data structure associated with
+ * the current CPU and the specified srcu_struct structure, initiating
+ * grace-period processing if it is not already running.
  *
  * Note that all CPUs must agree that the grace period extended beyond
  * all pre-existing SRCU read-side critical section.  On systems with
@@ -335,33 +632,40 @@ static void srcu_gp_end(struct srcu_struct *sp)
  * 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 *head,
+void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
 	       rcu_callback_t func)
 {
 	unsigned long flags;
+	bool needgp = false;
+	unsigned long s;
+	struct srcu_data *sdp;
 
-	head->next = NULL;
-	head->func = func;
-	spin_lock_irqsave(&sp->queue_lock, flags);
-	smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */
-	rcu_segcblist_enqueue(&sp->srcu_cblist, head, false);
-	if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_IDLE) {
-		srcu_gp_start(sp);
-		queue_delayed_work(system_power_efficient_wq, &sp->work, 0);
+	check_init_srcu_struct(sp);
+	rhp->func = func;
+	local_irq_save(flags);
+	sdp = this_cpu_ptr(sp->sda);
+	spin_lock(&sdp->lock);
+	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);
+	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
+	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
+		sdp->srcu_gp_seq_needed = s;
+		needgp = true;
 	}
-	spin_unlock_irqrestore(&sp->queue_lock, flags);
+	spin_unlock_irqrestore(&sdp->lock, flags);
+	if (needgp)
+		srcu_funnel_gp_start(sp, sdp, s);
 }
 EXPORT_SYMBOL_GPL(call_srcu);
 
-static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);
-
 /*
  * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
  */
 static void __synchronize_srcu(struct srcu_struct *sp)
 {
 	struct rcu_synchronize rcu;
-	struct rcu_head *head = &rcu.head;
 
 	RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) ||
 			 lock_is_held(&rcu_bh_lock_map) ||
@@ -372,26 +676,12 @@ static void __synchronize_srcu(struct srcu_struct *sp)
 	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
 		return;
 	might_sleep();
+	check_init_srcu_struct(sp);
 	init_completion(&rcu.completion);
-
-	head->next = NULL;
-	head->func = wakeme_after_rcu;
-	spin_lock_irq(&sp->queue_lock);
-	smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */
-	if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_IDLE) {
-		/* steal the processing owner */
-		rcu_segcblist_enqueue(&sp->srcu_cblist, head, false);
-		srcu_gp_start(sp);
-		spin_unlock_irq(&sp->queue_lock);
-		/* give the processing owner to work_struct */
-		srcu_reschedule(sp, 0);
-	} else {
-		rcu_segcblist_enqueue(&sp->srcu_cblist, head, false);
-		spin_unlock_irq(&sp->queue_lock);
-	}
-
+	init_rcu_head_on_stack(&rcu.head);
+	call_srcu(sp, &rcu.head, wakeme_after_rcu);
 	wait_for_completion(&rcu.completion);
-	smp_mb(); /* Caller's later accesses after GP. */
+	destroy_rcu_head_on_stack(&rcu.head);
 }
 
 /**
@@ -408,6 +698,7 @@ void synchronize_srcu_expedited(struct srcu_struct *sp)
 {
 	bool do_norm = rcu_gp_is_normal();
 
+	check_init_srcu_struct(sp);
 	if (!do_norm) {
 		atomic_inc(&sp->srcu_exp_cnt);
 		smp_mb__after_atomic(); /* increment before GP. */
@@ -415,7 +706,7 @@ void synchronize_srcu_expedited(struct srcu_struct *sp)
 	__synchronize_srcu(sp);
 	if (!do_norm) {
 		smp_mb__before_atomic(); /* GP before decrement. */
-		atomic_dec(&sp->srcu_exp_cnt);
+		WARN_ON_ONCE(atomic_dec_return(&sp->srcu_exp_cnt) < 0);
 	}
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
@@ -426,8 +717,8 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
  *
  * 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
- * the index=((->completed & 1) ^ 1) to drain to zero at first,
- * and then flip the completed and wait for the count of the other index.
+ * the index=((->srcu_idx & 1) ^ 1) to drain to zero at first,
+ * and then flip the srcu_idx and wait for the count of the other index.
  *
  * Can block; must be called from process context.
  *
@@ -468,13 +759,69 @@ void synchronize_srcu(struct srcu_struct *sp)
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu);
 
+/*
+ * Callback function for srcu_barrier() use.
+ */
+static void srcu_barrier_cb(struct rcu_head *rhp)
+{
+	struct srcu_data *sdp;
+	struct srcu_struct *sp;
+
+	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);
+}
+
 /**
  * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
  * @sp: srcu_struct on which to wait for in-flight callbacks.
  */
 void srcu_barrier(struct srcu_struct *sp)
 {
-	synchronize_srcu(sp);
+	int cpu;
+	struct srcu_data *sdp;
+	unsigned long s = rcu_seq_snap(&sp->srcu_barrier_seq);
+
+	check_init_srcu_struct(sp);
+	mutex_lock(&sp->srcu_barrier_mutex);
+	if (rcu_seq_done(&sp->srcu_barrier_seq, s)) {
+		smp_mb(); /* Force ordering following return. */
+		mutex_unlock(&sp->srcu_barrier_mutex);
+		return; /* Someone else did our work for us. */
+	}
+	rcu_seq_start(&sp->srcu_barrier_seq);
+	init_completion(&sp->srcu_barrier_completion);
+
+	/* Initial count prevents reaching zero until all CBs are posted. */
+	atomic_set(&sp->srcu_barrier_cpu_cnt, 1);
+
+	/*
+	 * Each pass through this loop enqueues a callback, but only
+	 * on CPUs already having callbacks enqueued.  Note that if
+	 * a CPU already has callbacks enqueue, it must have already
+	 * registered the need for a future grace period, so all we
+	 * need do is enqueue a callback that will use the same
+	 * grace period as the last callback already in the queue.
+	 */
+	for_each_possible_cpu(cpu) {
+		sdp = per_cpu_ptr(sp->sda, cpu);
+		spin_lock_irq(&sdp->lock);
+		atomic_inc(&sp->srcu_barrier_cpu_cnt);
+		sdp->srcu_barrier_head.func = srcu_barrier_cb;
+		if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
+					   &sdp->srcu_barrier_head, 0))
+			atomic_dec(&sp->srcu_barrier_cpu_cnt);
+		spin_unlock_irq(&sdp->lock);
+	}
+
+	/* 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);
+
+	rcu_seq_end(&sp->srcu_barrier_seq);
+	mutex_unlock(&sp->srcu_barrier_mutex);
 }
 EXPORT_SYMBOL_GPL(srcu_barrier);
 
@@ -487,21 +834,24 @@ EXPORT_SYMBOL_GPL(srcu_barrier);
  */
 unsigned long srcu_batches_completed(struct srcu_struct *sp)
 {
-	return sp->completed;
+	return sp->srcu_idx;
 }
 EXPORT_SYMBOL_GPL(srcu_batches_completed);
 
 /*
- * Core SRCU state machine.  Advance callbacks from ->batch_check0 to
- * ->batch_check1 and then to ->batch_done as readers drain.
+ * Core SRCU state machine.  Push state bits of ->srcu_gp_seq
+ * to SRCU_STATE_SCAN2, and invoke srcu_gp_end() when scan has
+ * completed in that state.
  */
-static void srcu_advance_batches(struct srcu_struct *sp)
+static void srcu_advance_state(struct srcu_struct *sp)
 {
 	int idx;
 
+	mutex_lock(&sp->srcu_gp_mutex);
+
 	/*
 	 * Because readers might be delayed for an extended period after
-	 * fetching ->completed for their index, at any point in time there
+	 * fetching ->srcu_idx for their index, at any point in time there
 	 * might well be readers using both idx=0 and idx=1.  We therefore
 	 * need to wait for readers to clear from both index values before
 	 * invoking a callback.
@@ -511,23 +861,29 @@ static void srcu_advance_batches(struct srcu_struct *sp)
 	 */
 	idx = rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq)); /* ^^^ */
 	if (idx == SRCU_STATE_IDLE) {
-		spin_lock_irq(&sp->queue_lock);
-		if (rcu_segcblist_empty(&sp->srcu_cblist)) {
-			spin_unlock_irq(&sp->queue_lock);
+		spin_lock_irq(&sp->gp_lock);
+		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(&sp->gp_lock);
+			mutex_unlock(&sp->srcu_gp_mutex);
 			return;
 		}
 		idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
 		if (idx == SRCU_STATE_IDLE)
 			srcu_gp_start(sp);
-		spin_unlock_irq(&sp->queue_lock);
-		if (idx != SRCU_STATE_IDLE)
+		spin_unlock_irq(&sp->gp_lock);
+		if (idx != SRCU_STATE_IDLE) {
+			mutex_unlock(&sp->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->completed & 1);
-		if (!try_check_zero(sp, idx, 1))
+		idx = 1 ^ (sp->srcu_idx & 1);
+		if (!try_check_zero(sp, idx, 1)) {
+			mutex_unlock(&sp->srcu_gp_mutex);
 			return; /* readers present, retry later. */
+		}
 		srcu_flip(sp);
 		rcu_seq_set_state(&sp->srcu_gp_seq, SRCU_STATE_SCAN2);
 	}
@@ -538,10 +894,12 @@ static void srcu_advance_batches(struct srcu_struct *sp)
 		 * SRCU read-side critical sections are normally short,
 		 * so check at least twice in quick succession after a flip.
 		 */
-		idx = 1 ^ (sp->completed & 1);
-		if (!try_check_zero(sp, idx, 2))
-			return; /* readers present, retry after later. */
-		srcu_gp_end(sp);
+		idx = 1 ^ (sp->srcu_idx & 1);
+		if (!try_check_zero(sp, idx, 2)) {
+			mutex_unlock(&sp->srcu_gp_mutex);
+			return; /* readers present, retry later. */
+		}
+		srcu_gp_end(sp);  /* Releases ->srcu_gp_mutex. */
 	}
 }
 
@@ -551,28 +909,51 @@ static void srcu_advance_batches(struct srcu_struct *sp)
  * the workqueue.  Note that needed memory barriers have been executed
  * in this task's context by srcu_readers_active_idx_check().
  */
-static void srcu_invoke_callbacks(struct srcu_struct *sp)
+static void srcu_invoke_callbacks(struct work_struct *work)
 {
+	bool more;
 	struct rcu_cblist ready_cbs;
 	struct rcu_head *rhp;
+	struct srcu_data *sdp;
+	struct srcu_struct *sp;
 
-	spin_lock_irq(&sp->queue_lock);
-	if (!rcu_segcblist_ready_cbs(&sp->srcu_cblist)) {
-		spin_unlock_irq(&sp->queue_lock);
-		return;
-	}
+	sdp = container_of(work, struct srcu_data, work.work);
+	sp = sdp->sp;
 	rcu_cblist_init(&ready_cbs);
-	rcu_segcblist_extract_done_cbs(&sp->srcu_cblist, &ready_cbs);
-	spin_unlock_irq(&sp->queue_lock);
+	spin_lock_irq(&sdp->lock);
+	smp_mb(); /* Old grace periods before callback invocation! */
+	rcu_segcblist_advance(&sdp->srcu_cblist,
+			      rcu_seq_current(&sp->srcu_gp_seq));
+	if (sdp->srcu_cblist_invoking ||
+	    !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
+		spin_unlock_irq(&sdp->lock);
+		return;  /* Someone else on the job or nothing to do. */
+	}
+
+	/* We are on the job!  Extract and invoke ready callbacks. */
+	sdp->srcu_cblist_invoking = true;
+	rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs);
+	spin_unlock_irq(&sdp->lock);
 	rhp = rcu_cblist_dequeue(&ready_cbs);
 	for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
 		local_bh_disable();
 		rhp->func(rhp);
 		local_bh_enable();
 	}
-	spin_lock_irq(&sp->queue_lock);
-	rcu_segcblist_insert_count(&sp->srcu_cblist, &ready_cbs);
-	spin_unlock_irq(&sp->queue_lock);
+
+	/*
+	 * Update counts, accelerate new callbacks, and if needed,
+	 * schedule another round of callback invocation.
+	 */
+	spin_lock_irq(&sdp->lock);
+	rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs);
+	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
+				       rcu_seq_snap(&sp->srcu_gp_seq));
+	sdp->srcu_cblist_invoking = false;
+	more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
+	spin_unlock_irq(&sdp->lock);
+	if (more)
+		srcu_schedule_cbs_sdp(sdp, 0);
 }
 
 /*
@@ -581,19 +962,21 @@ static void srcu_invoke_callbacks(struct srcu_struct *sp)
  */
 static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
 {
-	bool pending = true;
-	int state;
+	bool pushgp = true;
 
-	if (rcu_segcblist_empty(&sp->srcu_cblist)) {
-		spin_lock_irq(&sp->queue_lock);
-		state = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
-		if (rcu_segcblist_empty(&sp->srcu_cblist) &&
-		    state == SRCU_STATE_IDLE)
-			pending = false;
-		spin_unlock_irq(&sp->queue_lock);
+	spin_lock_irq(&sp->gp_lock);
+	if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
+		if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) {
+			/* All requests fulfilled, time to go idle. */
+			pushgp = false;
+		}
+	} else if (!rcu_seq_state(sp->srcu_gp_seq)) {
+		/* Outstanding request and no GP.  Start one. */
+		srcu_gp_start(sp);
 	}
+	spin_unlock_irq(&sp->gp_lock);
 
-	if (pending)
+	if (pushgp)
 		queue_delayed_work(system_power_efficient_wq, &sp->work, delay);
 }
 
@@ -606,8 +989,7 @@ void process_srcu(struct work_struct *work)
 
 	sp = container_of(work, struct srcu_struct, work.work);
 
-	srcu_advance_batches(sp);
-	srcu_invoke_callbacks(sp);
+	srcu_advance_state(sp);
 	srcu_reschedule(sp, atomic_read(&sp->srcu_exp_cnt) ? 0 : SRCU_INTERVAL);
 }
 EXPORT_SYMBOL_GPL(process_srcu);

kernel/rcu/tree.c

@@ -3776,12 +3776,16 @@ int rcutree_online_cpu(unsigned int cpu)
 {
 	sync_sched_exp_online_cleanup(cpu);
 	rcutree_affinity_setting(cpu, -1);
+	if (IS_ENABLED(CONFIG_TREE_SRCU))
+		srcu_online_cpu(cpu);
 	return 0;
 }
 
 int rcutree_offline_cpu(unsigned int cpu)
 {
 	rcutree_affinity_setting(cpu, cpu);
+	if (IS_ENABLED(CONFIG_TREE_SRCU))
+		srcu_offline_cpu(cpu);
 	return 0;
 }
 
@@ -4157,6 +4161,8 @@ void __init rcu_init(void)
 	for_each_online_cpu(cpu) {
 		rcutree_prepare_cpu(cpu);
 		rcu_cpu_starting(cpu);
+		if (IS_ENABLED(CONFIG_TREE_SRCU))
+			srcu_online_cpu(cpu);
 	}
 }
 

kernel/rcu/tree.h

@@ -541,6 +541,14 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
 static void rcu_dynticks_task_enter(void);
 static void rcu_dynticks_task_exit(void);
 
+#ifdef CONFIG_SRCU
+void srcu_online_cpu(unsigned int cpu);
+void srcu_offline_cpu(unsigned int cpu);
+#else /* #ifdef CONFIG_SRCU */
+void srcu_online_cpu(unsigned int cpu) { }
+void srcu_offline_cpu(unsigned int cpu) { }
+#endif /* #else #ifdef CONFIG_SRCU */
+
 #endif /* #ifndef RCU_TREE_NONCORE */
 
 #ifdef CONFIG_RCU_TRACE