Merge tag 'pull-work.dcache' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs dcache updates from Al Viro:
 "The main part here is making parallel lookups safe for RT - making
  sure preemption is disabled in start_dir_add()/ end_dir_add() sections
  (on non-RT it's automatic, on RT it needs to to be done explicitly)
  and moving wakeups from __d_lookup_done() inside of such to the end of
  those sections.

  Wakeups can be safely delayed for as long as ->d_lock on in-lookup
  dentry is held; proving that has caught a bug in d_add_ci() that
  allows memory corruption when sufficiently bogus ntfs (or
  case-insensitive xfs) image is mounted. Easily fixed, fortunately"

* tag 'pull-work.dcache' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  fs/dcache: Move wakeup out of i_seq_dir write held region.
  fs/dcache: Move the wakeup from __d_lookup_done() to the caller.
  fs/dcache: Disable preemption on i_dir_seq write side on PREEMPT_RT
  d_add_ci(): make sure we don't miss d_lookup_done()

Author: torvalds

fs/dcache.c

@@ -2240,6 +2240,7 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
 	}
 	res = d_splice_alias(inode, found);
 	if (res) {
+		d_lookup_done(found);
 		dput(found);
 		return res;
 	}
@@ -2563,7 +2564,15 @@ EXPORT_SYMBOL(d_rehash);
 
 static inline unsigned start_dir_add(struct inode *dir)
 {
-
+	/*
+	 * The caller holds a spinlock (dentry::d_lock). On !PREEMPT_RT
+	 * kernels spin_lock() implicitly disables preemption, but not on
+	 * PREEMPT_RT.  So for RT it has to be done explicitly to protect
+	 * the sequence count write side critical section against a reader
+	 * or another writer preempting, which would result in a live lock.
+	 */
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_disable();
 	for (;;) {
 		unsigned n = dir->i_dir_seq;
 		if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
@@ -2572,9 +2581,13 @@ static inline unsigned start_dir_add(struct inode *dir)
 	}
 }
 
-static inline void end_dir_add(struct inode *dir, unsigned n)
+static inline void end_dir_add(struct inode *dir, unsigned int n,
+			       wait_queue_head_t *d_wait)
 {
 	smp_store_release(&dir->i_dir_seq, n + 2);
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_enable();
+	wake_up_all(d_wait);
 }
 
 static void d_wait_lookup(struct dentry *dentry)
@@ -2701,32 +2714,50 @@ struct dentry *d_alloc_parallel(struct dentry *parent,
 }
 EXPORT_SYMBOL(d_alloc_parallel);
 
-void __d_lookup_done(struct dentry *dentry)
+/*
+ * - Unhash the dentry
+ * - Retrieve and clear the waitqueue head in dentry
+ * - Return the waitqueue head
+ */
+static wait_queue_head_t *__d_lookup_unhash(struct dentry *dentry)
 {
-	struct hlist_bl_head *b = in_lookup_hash(dentry->d_parent,
-						 dentry->d_name.hash);
+	wait_queue_head_t *d_wait;
+	struct hlist_bl_head *b;
+
+	lockdep_assert_held(&dentry->d_lock);
+
+	b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash);
 	hlist_bl_lock(b);
 	dentry->d_flags &= ~DCACHE_PAR_LOOKUP;
 	__hlist_bl_del(&dentry->d_u.d_in_lookup_hash);
-	wake_up_all(dentry->d_wait);
+	d_wait = dentry->d_wait;
 	dentry->d_wait = NULL;
 	hlist_bl_unlock(b);
 	INIT_HLIST_NODE(&dentry->d_u.d_alias);
 	INIT_LIST_HEAD(&dentry->d_lru);
+	return d_wait;
+}
+
+void __d_lookup_unhash_wake(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	wake_up_all(__d_lookup_unhash(dentry));
+	spin_unlock(&dentry->d_lock);
 }
-EXPORT_SYMBOL(__d_lookup_done);
+EXPORT_SYMBOL(__d_lookup_unhash_wake);
 
 /* inode->i_lock held if inode is non-NULL */
 
 static inline void __d_add(struct dentry *dentry, struct inode *inode)
 {
+	wait_queue_head_t *d_wait;
 	struct inode *dir = NULL;
 	unsigned n;
 	spin_lock(&dentry->d_lock);
 	if (unlikely(d_in_lookup(dentry))) {
 		dir = dentry->d_parent->d_inode;
 		n = start_dir_add(dir);
-		__d_lookup_done(dentry);
+		d_wait = __d_lookup_unhash(dentry);
 	}
 	if (inode) {
 		unsigned add_flags = d_flags_for_inode(inode);
@@ -2738,7 +2769,7 @@ static inline void __d_add(struct dentry *dentry, struct inode *inode)
 	}
 	__d_rehash(dentry);
 	if (dir)
-		end_dir_add(dir, n);
+		end_dir_add(dir, n, d_wait);
 	spin_unlock(&dentry->d_lock);
 	if (inode)
 		spin_unlock(&inode->i_lock);
@@ -2885,6 +2916,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 		     bool exchange)
 {
 	struct dentry *old_parent, *p;
+	wait_queue_head_t *d_wait;
 	struct inode *dir = NULL;
 	unsigned n;
 
@@ -2915,7 +2947,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	if (unlikely(d_in_lookup(target))) {
 		dir = target->d_parent->d_inode;
 		n = start_dir_add(dir);
-		__d_lookup_done(target);
+		d_wait = __d_lookup_unhash(target);
 	}
 
 	write_seqcount_begin(&dentry->d_seq);
@@ -2951,7 +2983,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	write_seqcount_end(&dentry->d_seq);
 
 	if (dir)
-		end_dir_add(dir, n);
+		end_dir_add(dir, n, d_wait);
 
 	if (dentry->d_parent != old_parent)
 		spin_unlock(&dentry->d_parent->d_lock);

include/linux/dcache.h

@@ -349,7 +349,7 @@ static inline void dont_mount(struct dentry *dentry)
 	spin_unlock(&dentry->d_lock);
 }
 
-extern void __d_lookup_done(struct dentry *);
+extern void __d_lookup_unhash_wake(struct dentry *dentry);
 
 static inline int d_in_lookup(const struct dentry *dentry)
 {
@@ -358,11 +358,8 @@ static inline int d_in_lookup(const struct dentry *dentry)
 
 static inline void d_lookup_done(struct dentry *dentry)
 {
-	if (unlikely(d_in_lookup(dentry))) {
-		spin_lock(&dentry->d_lock);
-		__d_lookup_done(dentry);
-		spin_unlock(&dentry->d_lock);
-	}
+	if (unlikely(d_in_lookup(dentry)))
+		__d_lookup_unhash_wake(dentry);
 }
 
 extern void dput(struct dentry *);