[PATCH v2 2/3] fs: record I_DIRTY_TIME even if inode already has I_DIRTY_INODE

[Lukas Czerner <lczerner@redhat.com>]

Currently the I_DIRTY_TIME will never get set if the inode already has
I_DIRTY_INODE with assumption that it supersedes I_DIRTY_TIME.  That's
true, however ext4 will only update the on-disk inode in
->dirty_inode(), not on actual writeback. As a result if the inode
already has I_DIRTY_INODE state by the time we get to
__mark_inode_dirty() only with I_DIRTY_TIME, the time was already filled
into on-disk inode and will not get updated until the next I_DIRTY_INODE
update, which might never come if we crash or get a power failure.

The problem can be reproduced on ext4 by running xfstest generic/622
with -o iversion mount option.

Fix it by allowing I_DIRTY_TIME to be set even if the inode already has
I_DIRTY_INODE. Also make sure that the case is properly handled in
writeback_single_inode() as well. Additionally changes in
xfs_fs_dirty_inode() was made to accommodate for I_DIRTY_TIME in flag.

Thanks Jan Kara for suggestions on how to make this work properly.

Cc: Dave Chinner <david@fromorbit.com>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Suggested-by: Jan Kara <jack@suse.cz>
---
v2: Reworked according to suggestions from Jan

 fs/fs-writeback.c  | 34 ++++++++++++++++++++++------------
 fs/xfs/xfs_super.c |  3 ++-
 include/linux/fs.h |  6 +++---
 3 files changed, 27 insertions(+), 16 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 05221366a16d..638dbf143727 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1718,9 +1718,14 @@ static int writeback_single_inode(struct inode *inode,
 	 */
 	if (!(inode->i_state & I_DIRTY_ALL))
 		inode_cgwb_move_to_attached(inode, wb);
-	else if (!(inode->i_state & I_SYNC_QUEUED) &&
-		 (inode->i_state & I_DIRTY))
-		redirty_tail_locked(inode, wb);
+	else if (!(inode->i_state & I_SYNC_QUEUED)) {
+		if ((inode->i_state & I_DIRTY))
+			redirty_tail_locked(inode, wb);
+		else if (inode->i_state & I_DIRTY_TIME) {
+			inode->dirtied_when = jiffies;
+			inode_io_list_move_locked(inode, wb, &wb->b_dirty_time);
+		}
+	}
 
 	spin_unlock(&wb->list_lock);
 	inode_sync_complete(inode);
@@ -2369,6 +2374,17 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	trace_writeback_mark_inode_dirty(inode, flags);
 
 	if (flags & I_DIRTY_INODE) {
+
+		/* Inode timestamp update will piggback on this dirtying */
+		if (inode->i_state & I_DIRTY_TIME) {
+			spin_lock(&inode->i_lock);
+			if (inode->i_state & I_DIRTY_TIME) {
+				inode->i_state &= ~I_DIRTY_TIME;
+				flags |= I_DIRTY_TIME;
+			}
+			spin_unlock(&inode->i_lock);
+		}
+
 		/*
 		 * Notify the filesystem about the inode being dirtied, so that
 		 * (if needed) it can update on-disk fields and journal the
@@ -2378,7 +2394,8 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		 */
 		trace_writeback_dirty_inode_start(inode, flags);
 		if (sb->s_op->dirty_inode)
-			sb->s_op->dirty_inode(inode, flags & I_DIRTY_INODE);
+			sb->s_op->dirty_inode(inode,
+				flags & (I_DIRTY_INODE | I_DIRTY_TIME));
 		trace_writeback_dirty_inode(inode, flags);
 
 		/* I_DIRTY_INODE supersedes I_DIRTY_TIME. */
@@ -2399,21 +2416,15 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	 */
 	smp_mb();
 
-	if (((inode->i_state & flags) == flags) ||
-	    (dirtytime && (inode->i_state & I_DIRTY_INODE)))
+	if ((inode->i_state & flags) == flags)
 		return;
 
 	spin_lock(&inode->i_lock);
-	if (dirtytime && (inode->i_state & I_DIRTY_INODE))
-		goto out_unlock_inode;
 	if ((inode->i_state & flags) != flags) {
 		const int was_dirty = inode->i_state & I_DIRTY;
 
 		inode_attach_wb(inode, NULL);
 
-		/* I_DIRTY_INODE supersedes I_DIRTY_TIME. */
-		if (flags & I_DIRTY_INODE)
-			inode->i_state &= ~I_DIRTY_TIME;
 		inode->i_state |= flags;
 
 		/*
@@ -2486,7 +2497,6 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 out_unlock:
 	if (wb)
 		spin_unlock(&wb->list_lock);
-out_unlock_inode:
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index aa977c7ea370..cff05a4771b5 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -658,7 +658,8 @@ xfs_fs_dirty_inode(
 
 	if (!(inode->i_sb->s_flags & SB_LAZYTIME))
 		return;
-	if (flag != I_DIRTY_SYNC || !(inode->i_state & I_DIRTY_TIME))
+	if ((flag & ~I_DIRTY_TIME) != I_DIRTY_SYNC ||
+	    !((inode->i_state | flag) & I_DIRTY_TIME))
 		return;
 
 	if (xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp))
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9ad5e3520fae..2243797badf2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2245,9 +2245,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
  *			lazytime mount option is enabled.  We keep track of this
  *			separately from I_DIRTY_SYNC in order to implement
  *			lazytime.  This gets cleared if I_DIRTY_INODE
- *			(I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set.  I.e.
- *			either I_DIRTY_TIME *or* I_DIRTY_INODE can be set in
- *			i_state, but not both.  I_DIRTY_PAGES may still be set.
+ *			(I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But
+ *			I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already
+ *			in place.
  * I_NEW		Serves as both a mutex and completion notification.
  *			New inodes set I_NEW.  If two processes both create
  *			the same inode, one of them will release its inode and
-- 
2.37.1