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

Pull RCU changes from Ingo Molnar:
 "This is the v3.5 RCU tree from Paul E.  McKenney:

 1) A set of improvements and fixes to the RCU_FAST_NO_HZ feature (with
    more on the way for 3.6).  Posted to LKML:
       https://lkml.org/lkml/2012/4/23/324 (commits 1-3 and 5),
       https://lkml.org/lkml/2012/4/16/611 (commit 4),
       https://lkml.org/lkml/2012/4/30/390 (commit 6), and
       https://lkml.org/lkml/2012/5/4/410 (commit 7, combined with
       the other commits for the convenience of the tester).

 2) Changes to make rcu_barrier() avoid disrupting execution of CPUs
    that have no RCU callbacks.  Posted to LKML:
       https://lkml.org/lkml/2012/4/23/322.

 3) A couple of commits that improve the efficiency of the interaction
    between preemptible RCU and the scheduler, these two being all that
    survived an abortive attempt to allow preemptible RCU's
    __rcu_read_lock() to be inlined.  The full set was posted to LKML at
    https://lkml.org/lkml/2012/4/14/143, and the first and third patches
    of that set remain.

 4) Lai Jiangshan's algorithmic implementation of SRCU, which includes
    call_srcu() and srcu_barrier().  A major feature of this new
    implementation is that synchronize_srcu() no longer disturbs the
    execution of other CPUs.  This work is based on earlier
    implementations by Peter Zijlstra and Paul E.  McKenney.  Posted to
    LKML: https://lkml.org/lkml/2012/2/22/82.

 5) A number of miscellaneous bug fixes and improvements which were
    posted to LKML at: https://lkml.org/lkml/2012/4/23/353 with
    subsequent updates posted to LKML."

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  rcu: Make rcu_barrier() less disruptive
  rcu: Explicitly initialize RCU_FAST_NO_HZ per-CPU variables
  rcu: Make RCU_FAST_NO_HZ handle timer migration
  rcu: Update RCU maintainership
  rcu: Make exit_rcu() more precise and consolidate
  rcu: Move PREEMPT_RCU preemption to switch_to() invocation
  rcu: Ensure that RCU_FAST_NO_HZ timers expire on correct CPU
  rcu: Add rcutorture test for call_srcu()
  rcu: Implement per-domain single-threaded call_srcu() state machine
  rcu: Use single value to handle expedited SRCU grace periods
  rcu: Improve srcu_readers_active_idx()'s cache locality
  rcu: Remove unused srcu_barrier()
  rcu: Implement a variant of Peter's SRCU algorithm
  rcu: Improve SRCU's wait_idx() comments
  rcu: Flip ->completed only once per SRCU grace period
  rcu: Increment upper bit only for srcu_read_lock()
  rcu: Remove fast check path from __synchronize_srcu()
  rcu: Direct algorithmic SRCU implementation
  rcu: Introduce rcutorture testing for rcu_barrier()
  timer: Fix mod_timer_pinned() header comment
  ...

1 files changed, 435 insertions, 113 deletions

diff --git a/kernel/srcu.c b/kernel/srcu.c
index ba35f3a4a1f4..2095be3318d5 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -34,10 +34,77 @@
 #include <linux/delay.h>
 #include <linux/srcu.h>
 
+/*
+ * Initialize an rcu_batch structure to empty.
+ */
+static inline void rcu_batch_init(struct rcu_batch *b)
+{
+	b->head = NULL;
+	b->tail = &b->head;
+}
+
+/*
+ * Enqueue a callback onto the tail of the specified rcu_batch structure.
+ */
+static inline void rcu_batch_queue(struct rcu_batch *b, struct rcu_head *head)
+{
+	*b->tail = head;
+	b->tail = &head->next;
+}
+
+/*
+ * Is the specified rcu_batch structure empty?
+ */
+static inline bool rcu_batch_empty(struct rcu_batch *b)
+{
+	return b->tail == &b->head;
+}
+
+/*
+ * Remove the callback at the head of the specified rcu_batch structure
+ * and return a pointer to it, or return NULL if the structure is empty.
+ */
+static inline struct rcu_head *rcu_batch_dequeue(struct rcu_batch *b)
+{
+	struct rcu_head *head;
+
+	if (rcu_batch_empty(b))
+		return NULL;
+
+	head = b->head;
+	b->head = head->next;
+	if (b->tail == &head->next)
+		rcu_batch_init(b);
+
+	return head;
+}
+
+/*
+ * Move all callbacks from the rcu_batch structure specified by "from" to
+ * the structure specified by "to".
+ */
+static inline void rcu_batch_move(struct rcu_batch *to, struct rcu_batch *from)
+{
+	if (!rcu_batch_empty(from)) {
+		*to->tail = from->head;
+		to->tail = from->tail;
+		rcu_batch_init(from);
+	}
+}
+
+/* single-thread state-machine */
+static void process_srcu(struct work_struct *work);
+
 static int init_srcu_struct_fields(struct srcu_struct *sp)
 {
 	sp->completed = 0;
-	mutex_init(&sp->mutex);
+	spin_lock_init(&sp->queue_lock);
+	sp->running = false;
+	rcu_batch_init(&sp->batch_queue);
+	rcu_batch_init(&sp->batch_check0);
+	rcu_batch_init(&sp->batch_check1);
+	rcu_batch_init(&sp->batch_done);
+	INIT_DELAYED_WORK(&sp->work, process_srcu);
 	sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array);
 	return sp->per_cpu_ref ? 0 : -ENOMEM;
 }
@@ -73,21 +140,116 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /*
- * srcu_readers_active_idx -- returns approximate number of readers
- *	active on the specified rank of per-CPU counters.
+ * Returns approximate total of the readers' ->seq[] values for the
+ * rank of per-CPU counters specified by idx.
  */
+static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx)
+{
+	int cpu;
+	unsigned long sum = 0;
+	unsigned long t;
 
-static int srcu_readers_active_idx(struct srcu_struct *sp, int idx)
+	for_each_possible_cpu(cpu) {
+		t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
+		sum += t;
+	}
+	return sum;
+}
+
+/*
+ * Returns approximate number of readers active on the specified rank
+ * of the per-CPU ->c[] counters.
+ */
+static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx)
 {
 	int cpu;
-	int sum;
+	unsigned long sum = 0;
+	unsigned long t;
 
-	sum = 0;
-	for_each_possible_cpu(cpu)
-		sum += per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx];
+	for_each_possible_cpu(cpu) {
+		t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
+		sum += t;
+	}
 	return sum;
 }
 
+/*
+ * Return true if the number of pre-existing readers is determined to
+ * be stably zero.  An example unstable zero can occur if the call
+ * to srcu_readers_active_idx() misses an __srcu_read_lock() increment,
+ * but due to task migration, sees the corresponding __srcu_read_unlock()
+ * decrement.  This can happen because srcu_readers_active_idx() takes
+ * time to sum the array, and might in fact be interrupted or preempted
+ * partway through the summation.
+ */
+static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
+{
+	unsigned long seq;
+
+	seq = srcu_readers_seq_idx(sp, idx);
+
+	/*
+	 * The following smp_mb() A pairs with the smp_mb() B located in
+	 * __srcu_read_lock().  This pairing ensures that if an
+	 * __srcu_read_lock() increments its counter after the summation
+	 * in srcu_readers_active_idx(), then the corresponding SRCU read-side
+	 * critical section will see any changes made prior to the start
+	 * of the current SRCU grace period.
+	 *
+	 * Also, if the above call to srcu_readers_seq_idx() saw the
+	 * increment of ->seq[], then the call to srcu_readers_active_idx()
+	 * must see the increment of ->c[].
+	 */
+	smp_mb(); /* A */
+
+	/*
+	 * Note that srcu_readers_active_idx() can incorrectly return
+	 * zero even though there is a pre-existing reader throughout.
+	 * To see this, suppose that task A is in a very long SRCU
+	 * read-side critical section that started on CPU 0, and that
+	 * no other reader exists, so that the sum of the counters
+	 * is equal to one.  Then suppose that task B starts executing
+	 * srcu_readers_active_idx(), summing up to CPU 1, and then that
+	 * task C starts reading on CPU 0, so that its increment is not
+	 * summed, but finishes reading on CPU 2, so that its decrement
+	 * -is- summed.  Then when task B completes its sum, it will
+	 * incorrectly get zero, despite the fact that task A has been
+	 * in its SRCU read-side critical section the whole time.
+	 *
+	 * We therefore do a validation step should srcu_readers_active_idx()
+	 * return zero.
+	 */
+	if (srcu_readers_active_idx(sp, idx) != 0)
+		return false;
+
+	/*
+	 * The remainder of this function is the validation step.
+	 * The following smp_mb() D pairs with the smp_mb() C in
+	 * __srcu_read_unlock().  If the __srcu_read_unlock() was seen
+	 * by srcu_readers_active_idx() above, then any destructive
+	 * operation performed after the grace period will happen after
+	 * the corresponding SRCU read-side critical section.
+	 *
+	 * Note that there can be at most NR_CPUS worth of readers using
+	 * the old index, which is not enough to overflow even a 32-bit
+	 * integer.  (Yes, this does mean that systems having more than
+	 * a billion or so CPUs need to be 64-bit systems.)  Therefore,
+	 * the sum of the ->seq[] counters cannot possibly overflow.
+	 * Therefore, the only way that the return values of the two
+	 * calls to srcu_readers_seq_idx() can be equal is if there were
+	 * no increments of the corresponding rank of ->seq[] counts
+	 * in the interim.  But the missed-increment scenario laid out
+	 * above includes an increment of the ->seq[] counter by
+	 * the corresponding __srcu_read_lock().  Therefore, if this
+	 * scenario occurs, the return values from the two calls to
+	 * srcu_readers_seq_idx() will differ, and thus the validation
+	 * step below suffices.
+	 */
+	smp_mb(); /* D */
+
+	return srcu_readers_seq_idx(sp, idx) == seq;
+}
+
 /**
  * srcu_readers_active - returns approximate number of readers.
  * @sp: which srcu_struct to count active readers (holding srcu_read_lock).
@@ -98,7 +260,14 @@ static int srcu_readers_active_idx(struct srcu_struct *sp, int idx)
  */
 static int srcu_readers_active(struct srcu_struct *sp)
 {
-	return srcu_readers_active_idx(sp, 0) + srcu_readers_active_idx(sp, 1);
+	int cpu;
+	unsigned long sum = 0;
+
+	for_each_possible_cpu(cpu) {
+		sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
+		sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
+	}
+	return sum;
 }
 
 /**
@@ -131,10 +300,11 @@ int __srcu_read_lock(struct srcu_struct *sp)
 	int idx;
 
 	preempt_disable();
-	idx = sp->completed & 0x1;
-	barrier();  /* ensure compiler looks -once- at sp->completed. */
-	per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]++;
-	srcu_barrier();  /* ensure compiler won't misorder critical section. */
+	idx = rcu_dereference_index_check(sp->completed,
+					  rcu_read_lock_sched_held()) & 0x1;
+	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) += 1;
+	smp_mb(); /* B */  /* Avoid leaking the critical section. */
+	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->seq[idx]) += 1;
 	preempt_enable();
 	return idx;
 }
@@ -149,8 +319,8 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
 	preempt_disable();
-	srcu_barrier();  /* ensure compiler won't misorder critical section. */
-	per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--;
+	smp_mb(); /* C */  /* Avoid leaking the critical section. */
+	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) -= 1;
 	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
@@ -163,106 +333,119 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock);
  * we repeatedly block for 1-millisecond time periods.  This approach
  * has done well in testing, so there is no need for a config parameter.
  */
-#define SYNCHRONIZE_SRCU_READER_DELAY 10
+#define SRCU_RETRY_CHECK_DELAY		5
+#define SYNCHRONIZE_SRCU_TRYCOUNT	2
+#define SYNCHRONIZE_SRCU_EXP_TRYCOUNT	12
 
 /*
- * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
+ * @@@ Wait until all pre-existing readers complete.  Such readers
+ * will have used the index specified by "idx".
+ * the caller should ensures the ->completed is not changed while checking
+ * and idx = (->completed & 1) ^ 1
  */
-static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
+static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
 {
-	int idx;
-
-	rcu_lockdep_assert(!lock_is_held(&sp->dep_map) &&
-			   !lock_is_held(&rcu_bh_lock_map) &&
-			   !lock_is_held(&rcu_lock_map) &&
-			   !lock_is_held(&rcu_sched_lock_map),
-			   "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section");
-
-	idx = sp->completed;
-	mutex_lock(&sp->mutex);
+	for (;;) {
+		if (srcu_readers_active_idx_check(sp, idx))
+			return true;
+		if (--trycount <= 0)
+			return false;
+		udelay(SRCU_RETRY_CHECK_DELAY);
+	}
+}
 
-	/*
-	 * Check to see if someone else did the work for us while we were
-	 * waiting to acquire the lock.  We need -two- advances of
-	 * the counter, not just one.  If there was but one, we might have
-	 * shown up -after- our helper's first synchronize_sched(), thus
-	 * having failed to prevent CPU-reordering races with concurrent
-	 * srcu_read_unlock()s on other CPUs (see comment below).  So we
-	 * either (1) wait for two or (2) supply the second ourselves.
-	 */
+/*
+ * Increment the ->completed counter so that future SRCU readers will
+ * use the other rank of the ->c[] and ->seq[] arrays.  This allows
+ * us to wait for pre-existing readers in a starvation-free manner.
+ */
+static void srcu_flip(struct srcu_struct *sp)
+{
+	sp->completed++;
+}
 
-	if ((sp->completed - idx) >= 2) {
-		mutex_unlock(&sp->mutex);
-		return;
+/*
+ * 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 *head,
+		void (*func)(struct rcu_head *head))
+{
+	unsigned long flags;
+
+	head->next = NULL;
+	head->func = func;
+	spin_lock_irqsave(&sp->queue_lock, flags);
+	rcu_batch_queue(&sp->batch_queue, head);
+	if (!sp->running) {
+		sp->running = true;
+		queue_delayed_work(system_nrt_wq, &sp->work, 0);
 	}
+	spin_unlock_irqrestore(&sp->queue_lock, flags);
+}
+EXPORT_SYMBOL_GPL(call_srcu);
 
-	sync_func();  /* Force memory barrier on all CPUs. */
+struct rcu_synchronize {
+	struct rcu_head head;
+	struct completion completion;
+};
 
-	/*
-	 * The preceding synchronize_sched() ensures that any CPU that
-	 * sees the new value of sp->completed will also see any preceding
-	 * changes to data structures made by this CPU.  This prevents
-	 * some other CPU from reordering the accesses in its SRCU
-	 * read-side critical section to precede the corresponding
-	 * srcu_read_lock() -- ensuring that such references will in
-	 * fact be protected.
-	 *
-	 * So it is now safe to do the flip.
-	 */
+/*
+ * Awaken the corresponding synchronize_srcu() instance now that a
+ * grace period has elapsed.
+ */
+static void wakeme_after_rcu(struct rcu_head *head)
+{
+	struct rcu_synchronize *rcu;
 
-	idx = sp->completed & 0x1;
-	sp->completed++;
+	rcu = container_of(head, struct rcu_synchronize, head);
+	complete(&rcu->completion);
+}
 
-	sync_func();  /* Force memory barrier on all CPUs. */
+static void srcu_advance_batches(struct srcu_struct *sp, int trycount);
+static void srcu_reschedule(struct srcu_struct *sp);
 
-	/*
-	 * At this point, because of the preceding synchronize_sched(),
-	 * all srcu_read_lock() calls using the old counters have completed.
-	 * Their corresponding critical sections might well be still
-	 * executing, but the srcu_read_lock() primitives themselves
-	 * will have finished executing.  We initially give readers
-	 * an arbitrarily chosen 10 microseconds to get out of their
-	 * SRCU read-side critical sections, then loop waiting 1/HZ
-	 * seconds per iteration.  The 10-microsecond value has done
-	 * very well in testing.
-	 */
-
-	if (srcu_readers_active_idx(sp, idx))
-		udelay(SYNCHRONIZE_SRCU_READER_DELAY);
-	while (srcu_readers_active_idx(sp, idx))
-		schedule_timeout_interruptible(1);
+/*
+ * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
+ */
+static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
+{
+	struct rcu_synchronize rcu;
+	struct rcu_head *head = &rcu.head;
+	bool done = false;
 
-	sync_func();  /* Force memory barrier on all CPUs. */
+	rcu_lockdep_assert(!lock_is_held(&sp->dep_map) &&
+			   !lock_is_held(&rcu_bh_lock_map) &&
+			   !lock_is_held(&rcu_lock_map) &&
+			   !lock_is_held(&rcu_sched_lock_map),
+			   "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section");
 
-	/*
-	 * The preceding synchronize_sched() forces all srcu_read_unlock()
-	 * primitives that were executing concurrently with the preceding
-	 * for_each_possible_cpu() loop to have completed by this point.
-	 * More importantly, it also forces the corresponding SRCU read-side
-	 * critical sections to have also completed, and the corresponding
-	 * references to SRCU-protected data items to be dropped.
-	 *
-	 * Note:
-	 *
-	 *	Despite what you might think at first glance, the
-	 *	preceding synchronize_sched() -must- be within the
-	 *	critical section ended by the following mutex_unlock().
-	 *	Otherwise, a task taking the early exit can race
-	 *	with a srcu_read_unlock(), which might have executed
-	 *	just before the preceding srcu_readers_active() check,
-	 *	and whose CPU might have reordered the srcu_read_unlock()
-	 *	with the preceding critical section.  In this case, there
-	 *	is nothing preventing the synchronize_sched() task that is
-	 *	taking the early exit from freeing a data structure that
-	 *	is still being referenced (out of order) by the task
-	 *	doing the srcu_read_unlock().
-	 *
-	 *	Alternatively, the comparison with "2" on the early exit
-	 *	could be changed to "3", but this increases synchronize_srcu()
-	 *	latency for bulk loads.  So the current code is preferred.
-	 */
+	init_completion(&rcu.completion);
+
+	head->next = NULL;
+	head->func = wakeme_after_rcu;
+	spin_lock_irq(&sp->queue_lock);
+	if (!sp->running) {
+		/* steal the processing owner */
+		sp->running = true;
+		rcu_batch_queue(&sp->batch_check0, head);
+		spin_unlock_irq(&sp->queue_lock);
+
+		srcu_advance_batches(sp, trycount);
+		if (!rcu_batch_empty(&sp->batch_done)) {
+			BUG_ON(sp->batch_done.head != head);
+			rcu_batch_dequeue(&sp->batch_done);
+			done = true;
+		}
+		/* give the processing owner to work_struct */
+		srcu_reschedule(sp);
+	} else {
+		rcu_batch_queue(&sp->batch_queue, head);
+		spin_unlock_irq(&sp->queue_lock);
+	}
 
-	mutex_unlock(&sp->mutex);
+	if (!done)
+		wait_for_completion(&rcu.completion);
 }
 
 /**
@@ -281,7 +464,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
  */
 void synchronize_srcu(struct srcu_struct *sp)
 {
-	__synchronize_srcu(sp, synchronize_sched);
+	__synchronize_srcu(sp, SYNCHRONIZE_SRCU_TRYCOUNT);
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu);
 
@@ -289,18 +472,11 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
  * synchronize_srcu_expedited - Brute-force SRCU grace period
  * @sp: srcu_struct with which to synchronize.
  *
- * Wait for an SRCU grace period to elapse, but use a "big hammer"
- * approach to force the grace period to end quickly.  This consumes
- * significant time on all CPUs and is unfriendly to real-time workloads,
- * so is thus not recommended for any sort of common-case code.  In fact,
- * if you are using synchronize_srcu_expedited() in a loop, please
- * restructure your code to batch your updates, and then use a single
- * synchronize_srcu() instead.
+ * Wait for an SRCU grace period to elapse, but be more aggressive about
+ * spinning rather than blocking when waiting.
  *
  * Note that it is illegal to call this function while holding any lock
- * that is acquired by a CPU-hotplug notifier.  And yes, it is also illegal
- * to call this function from a CPU-hotplug notifier.  Failing to observe
- * these restriction will result in deadlock.  It is also illegal to call
+ * that is acquired by a CPU-hotplug notifier.  It is also illegal to call
  * synchronize_srcu_expedited() from the corresponding SRCU read-side
  * critical section; doing so will result in deadlock.  However, it is
  * perfectly legal to call synchronize_srcu_expedited() on one srcu_struct
@@ -309,20 +485,166 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
  */
 void synchronize_srcu_expedited(struct srcu_struct *sp)
 {
-	__synchronize_srcu(sp, synchronize_sched_expedited);
+	__synchronize_srcu(sp, SYNCHRONIZE_SRCU_EXP_TRYCOUNT);
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
 
 /**
+ * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
+ */
+void srcu_barrier(struct srcu_struct *sp)
+{
+	synchronize_srcu(sp);
+}
+EXPORT_SYMBOL_GPL(srcu_barrier);
+
+/**
  * srcu_batches_completed - return batches completed.
  * @sp: 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.
  */
-
 long srcu_batches_completed(struct srcu_struct *sp)
 {
 	return sp->completed;
 }
 EXPORT_SYMBOL_GPL(srcu_batches_completed);
+
+#define SRCU_CALLBACK_BATCH	10
+#define SRCU_INTERVAL		1
+
+/*
+ * Move any new SRCU callbacks to the first stage of the SRCU grace
+ * period pipeline.
+ */
+static void srcu_collect_new(struct srcu_struct *sp)
+{
+	if (!rcu_batch_empty(&sp->batch_queue)) {
+		spin_lock_irq(&sp->queue_lock);
+		rcu_batch_move(&sp->batch_check0, &sp->batch_queue);
+		spin_unlock_irq(&sp->queue_lock);
+	}
+}
+
+/*
+ * Core SRCU state machine.  Advance callbacks from ->batch_check0 to
+ * ->batch_check1 and then to ->batch_done as readers drain.
+ */
+static void srcu_advance_batches(struct srcu_struct *sp, int trycount)
+{
+	int idx = 1 ^ (sp->completed & 1);
+
+	/*
+	 * Because readers might be delayed for an extended period after
+	 * fetching ->completed 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.
+	 */
+
+	if (rcu_batch_empty(&sp->batch_check0) &&
+	    rcu_batch_empty(&sp->batch_check1))
+		return; /* no callbacks need to be advanced */
+
+	if (!try_check_zero(sp, idx, trycount))
+		return; /* failed to advance, will try after SRCU_INTERVAL */
+
+	/*
+	 * The callbacks in ->batch_check1 have already done with their
+	 * first zero check and flip back when they were enqueued on
+	 * ->batch_check0 in a previous invocation of srcu_advance_batches().
+	 * (Presumably try_check_zero() returned false during that
+	 * invocation, leaving the callbacks stranded on ->batch_check1.)
+	 * They are therefore ready to invoke, so move them to ->batch_done.
+	 */
+	rcu_batch_move(&sp->batch_done, &sp->batch_check1);
+
+	if (rcu_batch_empty(&sp->batch_check0))
+		return; /* no callbacks need to be advanced */
+	srcu_flip(sp);
+
+	/*
+	 * The callbacks in ->batch_check0 just finished their
+	 * first check zero and flip, so move them to ->batch_check1
+	 * for future checking on the other idx.
+	 */
+	rcu_batch_move(&sp->batch_check1, &sp->batch_check0);
+
+	/*
+	 * SRCU read-side critical sections are normally short, so check
+	 * at least twice in quick succession after a flip.
+	 */
+	trycount = trycount < 2 ? 2 : trycount;
+	if (!try_check_zero(sp, idx^1, trycount))
+		return; /* failed to advance, will try after SRCU_INTERVAL */
+
+	/*
+	 * The callbacks in ->batch_check1 have now waited for all
+	 * pre-existing readers using both idx values.  They are therefore
+	 * ready to invoke, so move them to ->batch_done.
+	 */
+	rcu_batch_move(&sp->batch_done, &sp->batch_check1);
+}
+
+/*
+ * Invoke a limited number of SRCU callbacks that have passed through
+ * their grace period.  If there are more to do, SRCU will reschedule
+ * the workqueue.
+ */
+static void srcu_invoke_callbacks(struct srcu_struct *sp)
+{
+	int i;
+	struct rcu_head *head;
+
+	for (i = 0; i < SRCU_CALLBACK_BATCH; i++) {
+		head = rcu_batch_dequeue(&sp->batch_done);
+		if (!head)
+			break;
+		local_bh_disable();
+		head->func(head);
+		local_bh_enable();
+	}
+}
+
+/*
+ * 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)
+{
+	bool pending = true;
+
+	if (rcu_batch_empty(&sp->batch_done) &&
+	    rcu_batch_empty(&sp->batch_check1) &&
+	    rcu_batch_empty(&sp->batch_check0) &&
+	    rcu_batch_empty(&sp->batch_queue)) {
+		spin_lock_irq(&sp->queue_lock);
+		if (rcu_batch_empty(&sp->batch_done) &&
+		    rcu_batch_empty(&sp->batch_check1) &&
+		    rcu_batch_empty(&sp->batch_check0) &&
+		    rcu_batch_empty(&sp->batch_queue)) {
+			sp->running = false;
+			pending = false;
+		}
+		spin_unlock_irq(&sp->queue_lock);
+	}
+
+	if (pending)
+		queue_delayed_work(system_nrt_wq, &sp->work, SRCU_INTERVAL);
+}
+
+/*
+ * This is the work-queue function that handles SRCU grace periods.
+ */
+static void process_srcu(struct work_struct *work)
+{
+	struct srcu_struct *sp;
+
+	sp = container_of(work, struct srcu_struct, work.work);
+
+	srcu_collect_new(sp);
+	srcu_advance_batches(sp, 1);
+	srcu_invoke_callbacks(sp);
+	srcu_reschedule(sp);
+}