Merge branch 'for-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

Pull percpu updates from Tejun Heo:

 - Nick improved generic implementations of percpu operations which
   modify the variable and return so that they calculate the physical
   address only once.

 - percpu_ref percpu <-> atomic mode switching improvements. The
   patchset was originally posted about a year ago but fell through the
   crack.

 - misc non-critical fixes.

* 'for-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu:
  mm/percpu.c: fix potential memory leakage for pcpu_embed_first_chunk()
  mm/percpu.c: correct max_distance calculation for pcpu_embed_first_chunk()
  percpu: eliminate two sparse warnings
  percpu: improve generic percpu modify-return implementation
  percpu-refcount: init ->confirm_switch member properly
  percpu_ref: allow operation mode switching operations to be called concurrently
  percpu_ref: restructure operation mode switching
  percpu_ref: unify staggered atomic switching wait behavior
  percpu_ref: reorganize __percpu_ref_switch_to_atomic() and relocate percpu_ref_switch_to_atomic()
  percpu_ref: remove unnecessary RCU grace period for staggered atomic switching confirmation

1 files changed, 95 insertions, 74 deletions

diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 27fe74948882..9ac959ef4cae 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -33,6 +33,7 @@
 
 #define PERCPU_COUNT_BIAS	(1LU << (BITS_PER_LONG - 1))
 
+static DEFINE_SPINLOCK(percpu_ref_switch_lock);
 static DECLARE_WAIT_QUEUE_HEAD(percpu_ref_switch_waitq);
 
 static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref)
@@ -82,6 +83,7 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
 	atomic_long_set(&ref->count, start_count);
 
 	ref->release = release;
+	ref->confirm_switch = NULL;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(percpu_ref_init);
@@ -101,6 +103,8 @@ void percpu_ref_exit(struct percpu_ref *ref)
 	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
 
 	if (percpu_count) {
+		/* non-NULL confirm_switch indicates switching in progress */
+		WARN_ON_ONCE(ref->confirm_switch);
 		free_percpu(percpu_count);
 		ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD;
 	}
@@ -161,66 +165,23 @@ static void percpu_ref_noop_confirm_switch(struct percpu_ref *ref)
 static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 					  percpu_ref_func_t *confirm_switch)
 {
-	if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC)) {
-		/* switching from percpu to atomic */
-		ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
-
-		/*
-		 * Non-NULL ->confirm_switch is used to indicate that
-		 * switching is in progress.  Use noop one if unspecified.
-		 */
-		WARN_ON_ONCE(ref->confirm_switch);
-		ref->confirm_switch =
-			confirm_switch ?: percpu_ref_noop_confirm_switch;
-
-		percpu_ref_get(ref);	/* put after confirmation */
-		call_rcu_sched(&ref->rcu, percpu_ref_switch_to_atomic_rcu);
-	} else if (confirm_switch) {
-		/*
-		 * Somebody already set ATOMIC.  Switching may still be in
-		 * progress.  @confirm_switch must be invoked after the
-		 * switching is complete and a full sched RCU grace period
-		 * has passed.  Wait synchronously for the previous
-		 * switching and schedule @confirm_switch invocation.
-		 */
-		wait_event(percpu_ref_switch_waitq, !ref->confirm_switch);
-		ref->confirm_switch = confirm_switch;
-
-		percpu_ref_get(ref);	/* put after confirmation */
-		call_rcu_sched(&ref->rcu, percpu_ref_call_confirm_rcu);
+	if (ref->percpu_count_ptr & __PERCPU_REF_ATOMIC) {
+		if (confirm_switch)
+			confirm_switch(ref);
+		return;
 	}
-}
 
-/**
- * percpu_ref_switch_to_atomic - switch a percpu_ref to atomic mode
- * @ref: percpu_ref to switch to atomic mode
- * @confirm_switch: optional confirmation callback
- *
- * There's no reason to use this function for the usual reference counting.
- * Use percpu_ref_kill[_and_confirm]().
- *
- * Schedule switching of @ref to atomic mode.  All its percpu counts will
- * be collected to the main atomic counter.  On completion, when all CPUs
- * are guaraneed to be in atomic mode, @confirm_switch, which may not
- * block, is invoked.  This function may be invoked concurrently with all
- * the get/put operations and can safely be mixed with kill and reinit
- * operations.  Note that @ref will stay in atomic mode across kill/reinit
- * cycles until percpu_ref_switch_to_percpu() is called.
- *
- * This function normally doesn't block and can be called from any context
- * but it may block if @confirm_kill is specified and @ref is already in
- * the process of switching to atomic mode.  In such cases, @confirm_switch
- * will be invoked after the switching is complete.
- *
- * Due to the way percpu_ref is implemented, @confirm_switch will be called
- * after at least one full sched RCU grace period has passed but this is an
- * implementation detail and must not be depended upon.
- */
-void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
-				 percpu_ref_func_t *confirm_switch)
-{
-	ref->force_atomic = true;
-	__percpu_ref_switch_to_atomic(ref, confirm_switch);
+	/* switching from percpu to atomic */
+	ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
+
+	/*
+	 * Non-NULL ->confirm_switch is used to indicate that switching is
+	 * in progress.  Use noop one if unspecified.
+	 */
+	ref->confirm_switch = confirm_switch ?: percpu_ref_noop_confirm_switch;
+
+	percpu_ref_get(ref);	/* put after confirmation */
+	call_rcu_sched(&ref->rcu, percpu_ref_switch_to_atomic_rcu);
 }
 
 static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
@@ -233,8 +194,6 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 	if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC))
 		return;
 
-	wait_event(percpu_ref_switch_waitq, !ref->confirm_switch);
-
 	atomic_long_add(PERCPU_COUNT_BIAS, &ref->count);
 
 	/*
@@ -250,6 +209,58 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 			  ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC);
 }
 
+static void __percpu_ref_switch_mode(struct percpu_ref *ref,
+				     percpu_ref_func_t *confirm_switch)
+{
+	lockdep_assert_held(&percpu_ref_switch_lock);
+
+	/*
+	 * If the previous ATOMIC switching hasn't finished yet, wait for
+	 * its completion.  If the caller ensures that ATOMIC switching
+	 * isn't in progress, this function can be called from any context.
+	 */
+	wait_event_lock_irq(percpu_ref_switch_waitq, !ref->confirm_switch,
+			    percpu_ref_switch_lock);
+
+	if (ref->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD))
+		__percpu_ref_switch_to_atomic(ref, confirm_switch);
+	else
+		__percpu_ref_switch_to_percpu(ref);
+}
+
+/**
+ * percpu_ref_switch_to_atomic - switch a percpu_ref to atomic mode
+ * @ref: percpu_ref to switch to atomic mode
+ * @confirm_switch: optional confirmation callback
+ *
+ * There's no reason to use this function for the usual reference counting.
+ * Use percpu_ref_kill[_and_confirm]().
+ *
+ * Schedule switching of @ref to atomic mode.  All its percpu counts will
+ * be collected to the main atomic counter.  On completion, when all CPUs
+ * are guaraneed to be in atomic mode, @confirm_switch, which may not
+ * block, is invoked.  This function may be invoked concurrently with all
+ * the get/put operations and can safely be mixed with kill and reinit
+ * operations.  Note that @ref will stay in atomic mode across kill/reinit
+ * cycles until percpu_ref_switch_to_percpu() is called.
+ *
+ * This function may block if @ref is in the process of switching to atomic
+ * mode.  If the caller ensures that @ref is not in the process of
+ * switching to atomic mode, this function can be called from any context.
+ */
+void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
+				 percpu_ref_func_t *confirm_switch)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+
+	ref->force_atomic = true;
+	__percpu_ref_switch_mode(ref, confirm_switch);
+
+	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+}
+
 /**
  * percpu_ref_switch_to_percpu - switch a percpu_ref to percpu mode
  * @ref: percpu_ref to switch to percpu mode
@@ -264,17 +275,20 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
  * dying or dead, the actual switching takes place on the following
  * percpu_ref_reinit().
  *
- * This function normally doesn't block and can be called from any context
- * but it may block if @ref is in the process of switching to atomic mode
- * by percpu_ref_switch_atomic().
+ * This function may block if @ref is in the process of switching to atomic
+ * mode.  If the caller ensures that @ref is not in the process of
+ * switching to atomic mode, this function can be called from any context.
  */
 void percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+
 	ref->force_atomic = false;
+	__percpu_ref_switch_mode(ref, NULL);
 
-	/* a dying or dead ref can't be switched to percpu mode w/o reinit */
-	if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD))
-		__percpu_ref_switch_to_percpu(ref);
+	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
 }
 
 /**
@@ -290,21 +304,23 @@ void percpu_ref_switch_to_percpu(struct percpu_ref *ref)
  *
  * This function normally doesn't block and can be called from any context
  * but it may block if @confirm_kill is specified and @ref is in the
- * process of switching to atomic mode by percpu_ref_switch_atomic().
- *
- * Due to the way percpu_ref is implemented, @confirm_switch will be called
- * after at least one full sched RCU grace period has passed but this is an
- * implementation detail and must not be depended upon.
+ * process of switching to atomic mode by percpu_ref_switch_to_atomic().
  */
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+
 	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD,
 		  "%s called more than once on %pf!", __func__, ref->release);
 
 	ref->percpu_count_ptr |= __PERCPU_REF_DEAD;
-	__percpu_ref_switch_to_atomic(ref, confirm_kill);
+	__percpu_ref_switch_mode(ref, confirm_kill);
 	percpu_ref_put(ref);
+
+	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
 
@@ -321,11 +337,16 @@ EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
  */
 void percpu_ref_reinit(struct percpu_ref *ref)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+
 	WARN_ON_ONCE(!percpu_ref_is_zero(ref));
 
 	ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD;
 	percpu_ref_get(ref);
-	if (!ref->force_atomic)
-		__percpu_ref_switch_to_percpu(ref);
+	__percpu_ref_switch_mode(ref, NULL);
+
+	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_reinit);