Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull filesystem fixes from Jan Kara:
 "Notification, writeback, udf, quota fixes

  The notification patches are (with one exception) a fallout of my
  fsnotify rework which went into -rc1 (I've extented LTP to cover these
  cornercases to avoid similar breakage in future).

  The UDF patch is a nasty data corruption Al has recently reported,
  the revert of the writeback patch is due to possibility of violating
  sync(2) guarantees, and a quota bug can lead to corruption of quota
  files in ocfs2"

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  fsnotify: Allocate overflow events with proper type
  fanotify: Handle overflow in case of permission events
  fsnotify: Fix detection whether overflow event is queued
  Revert "writeback: do not sync data dirtied after sync start"
  quota: Fix race between dqput() and dquot_scan_active()
  udf: Fix data corruption on file type conversion
  inotify: Fix reporting of cookies for inotify events

fs/fs-writeback.c

@@ -40,18 +40,13 @@
 struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
-	/*
-	 * Write only inodes dirtied before this time. Don't forget to set
-	 * older_than_this_is_set when you set this.
-	 */
-	unsigned long older_than_this;
+	unsigned long *older_than_this;
 	enum writeback_sync_modes sync_mode;
 	unsigned int tagged_writepages:1;
 	unsigned int for_kupdate:1;
 	unsigned int range_cyclic:1;
 	unsigned int for_background:1;
 	unsigned int for_sync:1;	/* sync(2) WB_SYNC_ALL writeback */
-	unsigned int older_than_this_is_set:1;
 	enum wb_reason reason;		/* why was writeback initiated? */
 
 	struct list_head list;		/* pending work list */
@@ -252,10 +247,10 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 	int moved = 0;
 
-	WARN_ON_ONCE(!work->older_than_this_is_set);
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (inode_dirtied_after(inode, work->older_than_this))
+		if (work->older_than_this &&
+		    inode_dirtied_after(inode, *work->older_than_this))
 			break;
 		list_move(&inode->i_wb_list, &tmp);
 		moved++;
@@ -742,8 +737,6 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 		.sync_mode	= WB_SYNC_NONE,
 		.range_cyclic	= 1,
 		.reason		= reason,
-		.older_than_this = jiffies,
-		.older_than_this_is_set = 1,
 	};
 
 	spin_lock(&wb->list_lock);
@@ -802,13 +795,12 @@ static long wb_writeback(struct bdi_writeback *wb,
 {
 	unsigned long wb_start = jiffies;
 	long nr_pages = work->nr_pages;
+	unsigned long oldest_jif;
 	struct inode *inode;
 	long progress;
 
-	if (!work->older_than_this_is_set) {
-		work->older_than_this = jiffies;
-		work->older_than_this_is_set = 1;
-	}
+	oldest_jif = jiffies;
+	work->older_than_this = &oldest_jif;
 
 	spin_lock(&wb->list_lock);
 	for (;;) {
@@ -842,10 +834,10 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * safe.
 		 */
 		if (work->for_kupdate) {
-			work->older_than_this = jiffies -
+			oldest_jif = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
 		} else if (work->for_background)
-			work->older_than_this = jiffies;
+			oldest_jif = jiffies;
 
 		trace_writeback_start(wb->bdi, work);
 		if (list_empty(&wb->b_io))
@@ -1357,21 +1349,18 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb);
 
 /**
  * sync_inodes_sb	-	sync sb inode pages
- * @sb:			the superblock
- * @older_than_this:	timestamp
+ * @sb: the superblock
  *
  * This function writes and waits on any dirty inode belonging to this
- * superblock that has been dirtied before given timestamp.
+ * super_block.
  */
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this)
+void sync_inodes_sb(struct super_block *sb)
 {
 	DECLARE_COMPLETION_ONSTACK(done);
 	struct wb_writeback_work work = {
 		.sb		= sb,
 		.sync_mode	= WB_SYNC_ALL,
 		.nr_pages	= LONG_MAX,
-		.older_than_this = older_than_this,
-		.older_than_this_is_set = 1,
 		.range_cyclic	= 0,
 		.done		= &done,
 		.reason		= WB_REASON_SYNC,

fs/notify/dnotify/dnotify.c

@@ -86,7 +86,7 @@ static int dnotify_handle_event(struct fsnotify_group *group,
 				struct fsnotify_mark *inode_mark,
 				struct fsnotify_mark *vfsmount_mark,
 				u32 mask, void *data, int data_type,
-				const unsigned char *file_name)
+				const unsigned char *file_name, u32 cookie)
 {
 	struct dnotify_mark *dn_mark;
 	struct dnotify_struct *dn;

fs/notify/fanotify/fanotify.c

@@ -147,7 +147,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 				 struct fsnotify_mark *inode_mark,
 				 struct fsnotify_mark *fanotify_mark,
 				 u32 mask, void *data, int data_type,
-				 const unsigned char *file_name)
+				 const unsigned char *file_name, u32 cookie)
 {
 	int ret = 0;
 	struct fanotify_event_info *event;
@@ -192,10 +192,12 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 
 	ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge);
 	if (ret) {
-		BUG_ON(mask & FAN_ALL_PERM_EVENTS);
+		/* Permission events shouldn't be merged */
+		BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS);
 		/* Our event wasn't used in the end. Free it. */
 		fsnotify_destroy_event(group, fsn_event);
-		ret = 0;
+
+		return 0;
 	}
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS

fs/notify/fanotify/fanotify_user.c

@@ -698,6 +698,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	struct fsnotify_group *group;
 	int f_flags, fd;
 	struct user_struct *user;
+	struct fanotify_event_info *oevent;
 
 	pr_debug("%s: flags=%d event_f_flags=%d\n",
 		__func__, flags, event_f_flags);
@@ -730,8 +731,20 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	group->fanotify_data.user = user;
 	atomic_inc(&user->fanotify_listeners);
 
+	oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+	if (unlikely(!oevent)) {
+		fd = -ENOMEM;
+		goto out_destroy_group;
+	}
+	group->overflow_event = &oevent->fse;
+	fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+	oevent->tgid = get_pid(task_tgid(current));
+	oevent->path.mnt = NULL;
+	oevent->path.dentry = NULL;
+
 	group->fanotify_data.f_flags = event_f_flags;
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	oevent->response = 0;
 	mutex_init(&group->fanotify_data.access_mutex);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);

fs/notify/fsnotify.c

@@ -179,7 +179,7 @@ static int send_to_group(struct inode *to_tell,
 
 	return group->ops->handle_event(group, to_tell, inode_mark,
 					vfsmount_mark, mask, data, data_is,
-					file_name);
+					file_name, cookie);
 }
 
 /*

fs/notify/group.c

@@ -55,6 +55,13 @@ void fsnotify_destroy_group(struct fsnotify_group *group)
 	/* clear the notification queue of all events */
 	fsnotify_flush_notify(group);
 
+	/*
+	 * Destroy overflow event (we cannot use fsnotify_destroy_event() as
+	 * that deliberately ignores overflow events.
+	 */
+	if (group->overflow_event)
+		group->ops->free_event(group->overflow_event);
+
 	fsnotify_put_group(group);
 }
 
@@ -99,7 +106,6 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
 	INIT_LIST_HEAD(&group->marks_list);
 
 	group->ops = ops;
-	fsnotify_init_event(&group->overflow_event, NULL, FS_Q_OVERFLOW);
 
 	return group;
 }

fs/notify/inotify/inotify.h

@@ -27,6 +27,6 @@ extern int inotify_handle_event(struct fsnotify_group *group,
 				struct fsnotify_mark *inode_mark,
 				struct fsnotify_mark *vfsmount_mark,
 				u32 mask, void *data, int data_type,
-				const unsigned char *file_name);
+				const unsigned char *file_name, u32 cookie);
 
 extern const struct fsnotify_ops inotify_fsnotify_ops;

fs/notify/inotify/inotify_fsnotify.c

@@ -67,7 +67,7 @@ int inotify_handle_event(struct fsnotify_group *group,
 			 struct fsnotify_mark *inode_mark,
 			 struct fsnotify_mark *vfsmount_mark,
 			 u32 mask, void *data, int data_type,
-			 const unsigned char *file_name)
+			 const unsigned char *file_name, u32 cookie)
 {
 	struct inotify_inode_mark *i_mark;
 	struct inotify_event_info *event;
@@ -103,6 +103,7 @@ int inotify_handle_event(struct fsnotify_group *group,
 	fsn_event = &event->fse;
 	fsnotify_init_event(fsn_event, inode, mask);
 	event->wd = i_mark->wd;
+	event->sync_cookie = cookie;
 	event->name_len = len;
 	if (len)
 		strcpy(event->name, file_name);

fs/notify/inotify/inotify_user.c

@@ -495,7 +495,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
 
 	/* Queue ignore event for the watch */
 	inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
-			     NULL, FSNOTIFY_EVENT_NONE, NULL);
+			     NULL, FSNOTIFY_EVENT_NONE, NULL, 0);
 
 	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
 	/* remove this mark from the idr */
@@ -633,11 +633,23 @@ static int inotify_update_watch(struct fsnotify_group *group, struct inode *inod
 static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 {
 	struct fsnotify_group *group;
+	struct inotify_event_info *oevent;
 
 	group = fsnotify_alloc_group(&inotify_fsnotify_ops);
 	if (IS_ERR(group))
 		return group;
 
+	oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL);
+	if (unlikely(!oevent)) {
+		fsnotify_destroy_group(group);
+		return ERR_PTR(-ENOMEM);
+	}
+	group->overflow_event = &oevent->fse;
+	fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+	oevent->wd = -1;
+	oevent->sync_cookie = 0;
+	oevent->name_len = 0;
+
 	group->max_events = max_events;
 
 	spin_lock_init(&group->inotify_data.idr_lock);

fs/notify/notification.c

@@ -80,7 +80,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
 /*
  * Add an event to the group notification queue.  The group can later pull this
  * event off the queue to deal with.  The function returns 0 if the event was
- * added to the queue, 1 if the event was merged with some other queued event.
+ * added to the queue, 1 if the event was merged with some other queued event,
+ * 2 if the queue of events has overflown.
  */
 int fsnotify_add_notify_event(struct fsnotify_group *group,
 			      struct fsnotify_event *event,
@@ -95,10 +96,14 @@ int fsnotify_add_notify_event(struct fsnotify_group *group,
 	mutex_lock(&group->notification_mutex);
 
 	if (group->q_len >= group->max_events) {
+		ret = 2;
 		/* Queue overflow event only if it isn't already queued */
-		if (list_empty(&group->overflow_event.list))
-			event = &group->overflow_event;
-		ret = 1;
+		if (!list_empty(&group->overflow_event->list)) {
+			mutex_unlock(&group->notification_mutex);
+			return ret;
+		}
+		event = group->overflow_event;
+		goto queue;
 	}
 
 	if (!list_empty(list) && merge) {
@@ -109,6 +114,7 @@ int fsnotify_add_notify_event(struct fsnotify_group *group,
 		}
 	}
 
+queue:
 	group->q_len++;
 	list_add_tail(&event->list, list);
 	mutex_unlock(&group->notification_mutex);
@@ -132,7 +138,11 @@ struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group
 
 	event = list_first_entry(&group->notification_list,
 				 struct fsnotify_event, list);
-	list_del(&event->list);
+	/*
+	 * We need to init list head for the case of overflow event so that
+	 * check in fsnotify_add_notify_events() works
+	 */
+	list_del_init(&event->list);
 	group->q_len--;
 
 	return event;

fs/quota/dquot.c

@@ -581,9 +581,17 @@ int dquot_scan_active(struct super_block *sb,
 		dqstats_inc(DQST_LOOKUPS);
 		dqput(old_dquot);
 		old_dquot = dquot;
-		ret = fn(dquot, priv);
-		if (ret < 0)
-			goto out;
+		/*
+		 * ->release_dquot() can be racing with us. Our reference
+		 * protects us from new calls to it so just wait for any
+		 * outstanding call and recheck the DQ_ACTIVE_B after that.
+		 */
+		wait_on_dquot(dquot);
+		if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+			ret = fn(dquot, priv);
+			if (ret < 0)
+				goto out;
+		}
 		spin_lock(&dq_list_lock);
 		/* We are safe to continue now because our dquot could not
 		 * be moved out of the inuse list while we hold the reference */

fs/sync.c

@@ -27,11 +27,10 @@
  * wait == 1 case since in that case write_inode() functions do
  * sync_dirty_buffer() and thus effectively write one block at a time.
  */
-static int __sync_filesystem(struct super_block *sb, int wait,
-			     unsigned long start)
+static int __sync_filesystem(struct super_block *sb, int wait)
 {
 	if (wait)
-		sync_inodes_sb(sb, start);
+		sync_inodes_sb(sb);
 	else
 		writeback_inodes_sb(sb, WB_REASON_SYNC);
 
@@ -48,7 +47,6 @@ static int __sync_filesystem(struct super_block *sb, int wait,
 int sync_filesystem(struct super_block *sb)
 {
 	int ret;
-	unsigned long start = jiffies;
 
 	/*
 	 * We need to be protected against the filesystem going from
@@ -62,17 +60,17 @@ int sync_filesystem(struct super_block *sb)
 	if (sb->s_flags & MS_RDONLY)
 		return 0;
 
-	ret = __sync_filesystem(sb, 0, start);
+	ret = __sync_filesystem(sb, 0);
 	if (ret < 0)
 		return ret;
-	return __sync_filesystem(sb, 1, start);
+	return __sync_filesystem(sb, 1);
 }
 EXPORT_SYMBOL_GPL(sync_filesystem);
 
 static void sync_inodes_one_sb(struct super_block *sb, void *arg)
 {
 	if (!(sb->s_flags & MS_RDONLY))
-		sync_inodes_sb(sb, *((unsigned long *)arg));
+		sync_inodes_sb(sb);
 }
 
 static void sync_fs_one_sb(struct super_block *sb, void *arg)
@@ -104,10 +102,9 @@ static void fdatawait_one_bdev(struct block_device *bdev, void *arg)
 SYSCALL_DEFINE0(sync)
 {
 	int nowait = 0, wait = 1;
-	unsigned long start = jiffies;
 
 	wakeup_flusher_threads(0, WB_REASON_SYNC);
-	iterate_supers(sync_inodes_one_sb, &start);
+	iterate_supers(sync_inodes_one_sb, NULL);
 	iterate_supers(sync_fs_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &wait);
 	iterate_bdevs(fdatawrite_one_bdev, NULL);

fs/udf/file.c

@@ -144,6 +144,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	size_t count = iocb->ki_nbytes;
 	struct udf_inode_info *iinfo = UDF_I(inode);
 
+	mutex_lock(&inode->i_mutex);
 	down_write(&iinfo->i_data_sem);
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
 		if (file->f_flags & O_APPEND)
@@ -156,6 +157,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 						pos + count)) {
 			err = udf_expand_file_adinicb(inode);
 			if (err) {
+				mutex_unlock(&inode->i_mutex);
 				udf_debug("udf_expand_adinicb: err=%d\n", err);
 				return err;
 			}
@@ -169,9 +171,17 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	} else
 		up_write(&iinfo->i_data_sem);
 
-	retval = generic_file_aio_write(iocb, iov, nr_segs, ppos);
-	if (retval > 0)
+	retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	mutex_unlock(&inode->i_mutex);
+
+	if (retval > 0) {
+		ssize_t err;
+
 		mark_inode_dirty(inode);
+		err = generic_write_sync(file, iocb->ki_pos - retval, retval);
+		if (err < 0)
+			retval = err;
+	}
 
 	return retval;
 }

fs/udf/inode.c

@@ -265,6 +265,7 @@ int udf_expand_file_adinicb(struct inode *inode)
 		.nr_to_write = 1,
 	};
 
+	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
 	if (!iinfo->i_lenAlloc) {
 		if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD))
 			iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT;

fs/xfs/xfs_super.c

@@ -913,7 +913,7 @@ xfs_flush_inodes(
 	struct super_block	*sb = mp->m_super;
 
 	if (down_read_trylock(&sb->s_umount)) {
-		sync_inodes_sb(sb, jiffies);
+		sync_inodes_sb(sb);
 		up_read(&sb->s_umount);
 	}
 }

include/linux/fsnotify_backend.h

@@ -99,7 +99,7 @@ struct fsnotify_ops {
 			    struct fsnotify_mark *inode_mark,
 			    struct fsnotify_mark *vfsmount_mark,
 			    u32 mask, void *data, int data_type,
-			    const unsigned char *file_name);
+			    const unsigned char *file_name, u32 cookie);
 	void (*free_group_priv)(struct fsnotify_group *group);
 	void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
 	void (*free_event)(struct fsnotify_event *event);
@@ -160,7 +160,7 @@ struct fsnotify_group {
 
 	struct fasync_struct *fsn_fa;    /* async notification */
 
-	struct fsnotify_event overflow_event;	/* Event we queue when the
+	struct fsnotify_event *overflow_event;	/* Event we queue when the
 						 * notification list is too
 						 * full */
 

include/linux/writeback.h

@@ -97,7 +97,7 @@ void writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
 int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason);
 int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
 				  enum wb_reason reason);
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this);
+void sync_inodes_sb(struct super_block *);
 void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
 void inode_wait_for_writeback(struct inode *inode);
 

include/trace/events/writeback.h

@@ -287,11 +287,11 @@ TRACE_EVENT(writeback_queue_io,
 		__field(int,		reason)
 	),
 	TP_fast_assign(
-		unsigned long older_than_this = work->older_than_this;
+		unsigned long *older_than_this = work->older_than_this;
 		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
-		__entry->older	= older_than_this;
+		__entry->older	= older_than_this ?  *older_than_this : 0;
 		__entry->age	= older_than_this ?
-				  (jiffies - older_than_this) * 1000 / HZ : -1;
+				  (jiffies - *older_than_this) * 1000 / HZ : -1;
 		__entry->moved	= moved;
 		__entry->reason	= work->reason;
 	),

kernel/audit_tree.c

@@ -916,7 +916,7 @@ static int audit_tree_handle_event(struct fsnotify_group *group,
 				   struct fsnotify_mark *inode_mark,
 				   struct fsnotify_mark *vfsmount_mark,
 				   u32 mask, void *data, int data_type,
-				   const unsigned char *file_name)
+				   const unsigned char *file_name, u32 cookie)
 {
 	return 0;
 }

kernel/audit_watch.c

@@ -471,7 +471,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
 				    struct fsnotify_mark *inode_mark,
 				    struct fsnotify_mark *vfsmount_mark,
 				    u32 mask, void *data, int data_type,
-				    const unsigned char *dname)
+				    const unsigned char *dname, u32 cookie)
 {
 	struct inode *inode;
 	struct audit_parent *parent;