Merge branch 'for-next' of git://git.infradead.org/users/eparis/notify

Pull filesystem notification updates from Eric Paris:
 "This pull mostly is about locking changes in the fsnotify system.  By
  switching the group lock from a spin_lock() to a mutex() we can now
  hold the lock across things like iput().  This fixes a problem
  involving unmounting a fs and having inodes be busy, first pointed out
  by FAT, but reproducible with tmpfs.

  This also restores signal driven I/O for inotify, which has been
  broken since about 2.6.32."

Ugh.  I *hate* the timing of this.  It was rebased after the merge
window opened, and then left to sit with the pull request coming the day
before the merge window closes.  That's just crap.  But apparently the
patches themselves have been around for over a year, just gathering
dust, so now it's suddenly critical.

Fixed up semantic conflict in fs/notify/fdinfo.c as per Stephen
Rothwell's fixes from -next.

* 'for-next' of git://git.infradead.org/users/eparis/notify:
  inotify: automatically restart syscalls
  inotify: dont skip removal of watch descriptor if creation of ignored event failed
  fanotify: dont merge permission events
  fsnotify: make fasync generic for both inotify and fanotify
  fsnotify: change locking order
  fsnotify: dont put marks on temporary list when clearing marks by group
  fsnotify: introduce locked versions of fsnotify_add_mark() and fsnotify_remove_mark()
  fsnotify: pass group to fsnotify_destroy_mark()
  fsnotify: use a mutex instead of a spinlock to protect a groups mark list
  fanotify: add an extra flag to mark_remove_from_mask that indicates wheather a mark should be destroyed
  fsnotify: take groups mark_lock before mark lock
  fsnotify: use reference counting for groups
  fsnotify: introduce fsnotify_get_group()
  inotify, fanotify: replace fsnotify_put_group() with fsnotify_destroy_group()

2 files changed, 31 insertions, 12 deletions

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index a506360..0c2f912 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -18,6 +18,12 @@ static bool should_merge(struct fsnotify_event *old, struct fsnotify_event *new)
 	    old->tgid == new->tgid) {
 		switch (old->data_type) {
 		case (FSNOTIFY_EVENT_PATH):
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+			/* dont merge two permission events */
+			if ((old->mask & FAN_ALL_PERM_EVENTS) &&
+			    (new->mask & FAN_ALL_PERM_EVENTS))
+				return false;
+#endif
 			if ((old->path.mnt == new->path.mnt) &&
 			    (old->path.dentry == new->path.dentry))
 				return true;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index a5cd9bb..9ff4a5e 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -397,8 +397,12 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 
 	wake_up(&group->fanotify_data.access_waitq);
 #endif
+
+	if (file->f_flags & FASYNC)
+		fsnotify_fasync(-1, file, 0);
+
 	/* matches the fanotify_init->fsnotify_alloc_group */
-	fsnotify_put_group(group);
+	fsnotify_destroy_group(group);
 
 	return 0;
 }
@@ -493,7 +497,8 @@ out:
 
 static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
 					    __u32 mask,
-					    unsigned int flags)
+					    unsigned int flags,
+					    int *destroy)
 {
 	__u32 oldmask;
 
@@ -507,8 +512,7 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
 	}
 	spin_unlock(&fsn_mark->lock);
 
-	if (!(oldmask & ~mask))
-		fsnotify_destroy_mark(fsn_mark);
+	*destroy = !(oldmask & ~mask);
 
 	return mask & oldmask;
 }
@@ -519,12 +523,17 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
 {
 	struct fsnotify_mark *fsn_mark = NULL;
 	__u32 removed;
+	int destroy_mark;
 
 	fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
 	if (!fsn_mark)
 		return -ENOENT;
 
-	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags);
+	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
+						 &destroy_mark);
+	if (destroy_mark)
+		fsnotify_destroy_mark(fsn_mark, group);
+
 	fsnotify_put_mark(fsn_mark);
 	if (removed & real_mount(mnt)->mnt_fsnotify_mask)
 		fsnotify_recalc_vfsmount_mask(mnt);
@@ -538,12 +547,16 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group,
 {
 	struct fsnotify_mark *fsn_mark = NULL;
 	__u32 removed;
+	int destroy_mark;
 
 	fsn_mark = fsnotify_find_inode_mark(group, inode);
 	if (!fsn_mark)
 		return -ENOENT;
 
-	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags);
+	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
+						 &destroy_mark);
+	if (destroy_mark)
+		fsnotify_destroy_mark(fsn_mark, group);
 	/* matches the fsnotify_find_inode_mark() */
 	fsnotify_put_mark(fsn_mark);
 	if (removed & inode->i_fsnotify_mask)
@@ -710,13 +723,13 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 		break;
 	default:
 		fd = -EINVAL;
-		goto out_put_group;
+		goto out_destroy_group;
 	}
 
 	if (flags & FAN_UNLIMITED_QUEUE) {
 		fd = -EPERM;
 		if (!capable(CAP_SYS_ADMIN))
-			goto out_put_group;
+			goto out_destroy_group;
 		group->max_events = UINT_MAX;
 	} else {
 		group->max_events = FANOTIFY_DEFAULT_MAX_EVENTS;
@@ -725,7 +738,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	if (flags & FAN_UNLIMITED_MARKS) {
 		fd = -EPERM;
 		if (!capable(CAP_SYS_ADMIN))
-			goto out_put_group;
+			goto out_destroy_group;
 		group->fanotify_data.max_marks = UINT_MAX;
 	} else {
 		group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS;
@@ -733,12 +746,12 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 
 	fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
 	if (fd < 0)
-		goto out_put_group;
+		goto out_destroy_group;
 
 	return fd;
 
-out_put_group:
-	fsnotify_put_group(group);
+out_destroy_group:
+	fsnotify_destroy_group(group);
 	return fd;
 }