dcache: let the dentry count go down to zero without taking d_lock

We can be more aggressive about this, if we are clever and careful. This is subtle.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

3 files changed, 144 insertions, 13 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index 40432e59d72e..a14d00e9839e 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -508,7 +508,7 @@ static void __dentry_kill(struct dentry *dentry)
 	 * dentry_iput drops the locks, at which point nobody (except
 	 * transient RCU lookups) can reach this dentry.
 	 */
-	BUG_ON((int)dentry->d_lockref.count > 0);
+	BUG_ON(dentry->d_lockref.count > 0);
 	this_cpu_dec(nr_dentry);
 	if (dentry->d_op && dentry->d_op->d_release)
 		dentry->d_op->d_release(dentry);
@@ -561,7 +561,7 @@ static inline struct dentry *lock_parent(struct dentry *dentry)
 	struct dentry *parent = dentry->d_parent;
 	if (IS_ROOT(dentry))
 		return NULL;
-	if (unlikely((int)dentry->d_lockref.count < 0))
+	if (unlikely(dentry->d_lockref.count < 0))
 		return NULL;
 	if (likely(spin_trylock(&parent->d_lock)))
 		return parent;
@@ -590,6 +590,110 @@ again:
 	return parent;
 }
 
+/*
+ * Try to do a lockless dput(), and return whether that was successful.
+ *
+ * If unsuccessful, we return false, having already taken the dentry lock.
+ *
+ * The caller needs to hold the RCU read lock, so that the dentry is
+ * guaranteed to stay around even if the refcount goes down to zero!
+ */
+static inline bool fast_dput(struct dentry *dentry)
+{
+	int ret;
+	unsigned int d_flags;
+
+	/*
+	 * If we have a d_op->d_delete() operation, we sould not
+	 * let the dentry count go to zero, so use "put__or_lock".
+	 */
+	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE))
+		return lockref_put_or_lock(&dentry->d_lockref);
+
+	/*
+	 * .. otherwise, we can try to just decrement the
+	 * lockref optimistically.
+	 */
+	ret = lockref_put_return(&dentry->d_lockref);
+
+	/*
+	 * If the lockref_put_return() failed due to the lock being held
+	 * by somebody else, the fast path has failed. We will need to
+	 * get the lock, and then check the count again.
+	 */
+	if (unlikely(ret < 0)) {
+		spin_lock(&dentry->d_lock);
+		if (dentry->d_lockref.count > 1) {
+			dentry->d_lockref.count--;
+			spin_unlock(&dentry->d_lock);
+			return 1;
+		}
+		return 0;
+	}
+
+	/*
+	 * If we weren't the last ref, we're done.
+	 */
+	if (ret)
+		return 1;
+
+	/*
+	 * Careful, careful. The reference count went down
+	 * to zero, but we don't hold the dentry lock, so
+	 * somebody else could get it again, and do another
+	 * dput(), and we need to not race with that.
+	 *
+	 * However, there is a very special and common case
+	 * where we don't care, because there is nothing to
+	 * do: the dentry is still hashed, it does not have
+	 * a 'delete' op, and it's referenced and already on
+	 * the LRU list.
+	 *
+	 * NOTE! Since we aren't locked, these values are
+	 * not "stable". However, it is sufficient that at
+	 * some point after we dropped the reference the
+	 * dentry was hashed and the flags had the proper
+	 * value. Other dentry users may have re-gotten
+	 * a reference to the dentry and change that, but
+	 * our work is done - we can leave the dentry
+	 * around with a zero refcount.
+	 */
+	smp_rmb();
+	d_flags = ACCESS_ONCE(dentry->d_flags);
+	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST;
+
+	/* Nothing to do? Dropping the reference was all we needed? */
+	if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
+		return 1;
+
+	/*
+	 * Not the fast normal case? Get the lock. We've already decremented
+	 * the refcount, but we'll need to re-check the situation after
+	 * getting the lock.
+	 */
+	spin_lock(&dentry->d_lock);
+
+	/*
+	 * Did somebody else grab a reference to it in the meantime, and
+	 * we're no longer the last user after all? Alternatively, somebody
+	 * else could have killed it and marked it dead. Either way, we
+	 * don't need to do anything else.
+	 */
+	if (dentry->d_lockref.count) {
+		spin_unlock(&dentry->d_lock);
+		return 1;
+	}
+
+	/*
+	 * Re-get the reference we optimistically dropped. We hold the
+	 * lock, and we just tested that it was zero, so we can just
+	 * set it to 1.
+	 */
+	dentry->d_lockref.count = 1;
+	return 0;
+}
+
+
 /* 
  * This is dput
  *
@@ -622,8 +726,14 @@ void dput(struct dentry *dentry)
 		return;
 
 repeat:
-	if (lockref_put_or_lock(&dentry->d_lockref))
+	rcu_read_lock();
+	if (likely(fast_dput(dentry))) {
+		rcu_read_unlock();
 		return;
+	}
+
+	/* Slow case: now with the dentry lock held */
+	rcu_read_unlock();
 
 	/* Unreachable? Get rid of it */
 	if (unlikely(d_unhashed(dentry)))
@@ -810,7 +920,7 @@ static void shrink_dentry_list(struct list_head *list)
 		 * We found an inuse dentry which was not removed from
 		 * the LRU because of laziness during lookup. Do not free it.
 		 */
-		if ((int)dentry->d_lockref.count > 0) {
+		if (dentry->d_lockref.count > 0) {
 			spin_unlock(&dentry->d_lock);
 			if (parent)
 				spin_unlock(&parent->d_lock);
diff --git a/include/linux/lockref.h b/include/linux/lockref.h
index 4bfde0e99ed5..b10b122dd099 100644
--- a/include/linux/lockref.h
+++ b/include/linux/lockref.h
@@ -28,12 +28,13 @@ struct lockref {
 #endif
 		struct {
 			spinlock_t lock;
-			unsigned int count;
+			int count;
 		};
 	};
 };
 
 extern void lockref_get(struct lockref *);
+extern int lockref_put_return(struct lockref *);
 extern int lockref_get_not_zero(struct lockref *);
 extern int lockref_get_or_lock(struct lockref *);
 extern int lockref_put_or_lock(struct lockref *);
diff --git a/lib/lockref.c b/lib/lockref.c
index d2233de9a86e..ecb9a665ec19 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -60,7 +60,7 @@ void lockref_get(struct lockref *lockref)
 EXPORT_SYMBOL(lockref_get);
 
 /**
- * lockref_get_not_zero - Increments count unless the count is 0
+ * lockref_get_not_zero - Increments count unless the count is 0 or dead
  * @lockref: pointer to lockref structure
  * Return: 1 if count updated successfully or 0 if count was zero
  */
@@ -70,7 +70,7 @@ int lockref_get_not_zero(struct lockref *lockref)
 
 	CMPXCHG_LOOP(
 		new.count++;
-		if (!old.count)
+		if (old.count <= 0)
 			return 0;
 	,
 		return 1;
@@ -78,7 +78,7 @@ int lockref_get_not_zero(struct lockref *lockref)
 
 	spin_lock(&lockref->lock);
 	retval = 0;
-	if (lockref->count) {
+	if (lockref->count > 0) {
 		lockref->count++;
 		retval = 1;
 	}
@@ -88,7 +88,7 @@ int lockref_get_not_zero(struct lockref *lockref)
 EXPORT_SYMBOL(lockref_get_not_zero);
 
 /**
- * lockref_get_or_lock - Increments count unless the count is 0
+ * lockref_get_or_lock - Increments count unless the count is 0 or dead
  * @lockref: pointer to lockref structure
  * Return: 1 if count updated successfully or 0 if count was zero
  * and we got the lock instead.
@@ -97,14 +97,14 @@ int lockref_get_or_lock(struct lockref *lockref)
 {
 	CMPXCHG_LOOP(
 		new.count++;
-		if (!old.count)
+		if (old.count <= 0)
 			break;
 	,
 		return 1;
 	);
 
 	spin_lock(&lockref->lock);
-	if (!lockref->count)
+	if (lockref->count <= 0)
 		return 0;
 	lockref->count++;
 	spin_unlock(&lockref->lock);
@@ -113,6 +113,26 @@ int lockref_get_or_lock(struct lockref *lockref)
 EXPORT_SYMBOL(lockref_get_or_lock);
 
 /**
+ * lockref_put_return - Decrement reference count if possible
+ * @lockref: pointer to lockref structure
+ *
+ * Decrement the reference count and return the new value.
+ * If the lockref was dead or locked, return an error.
+ */
+int lockref_put_return(struct lockref *lockref)
+{
+	CMPXCHG_LOOP(
+		new.count--;
+		if (old.count <= 0)
+			return -1;
+	,
+		return new.count;
+	);
+	return -1;
+}
+EXPORT_SYMBOL(lockref_put_return);
+
+/**
  * lockref_put_or_lock - decrements count unless count <= 1 before decrement
  * @lockref: pointer to lockref structure
  * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken
@@ -158,7 +178,7 @@ int lockref_get_not_dead(struct lockref *lockref)
 
 	CMPXCHG_LOOP(
 		new.count++;
-		if ((int)old.count < 0)
+		if (old.count < 0)
 			return 0;
 	,
 		return 1;
@@ -166,7 +186,7 @@ int lockref_get_not_dead(struct lockref *lockref)
 
 	spin_lock(&lockref->lock);
 	retval = 0;
-	if ((int) lockref->count >= 0) {
+	if (lockref->count >= 0) {
 		lockref->count++;
 		retval = 1;
 	}