[PATCH 09/10] ovl: handle lazytime on the upper filesystem

[Josef Bacik]

With lazytime the timestamps of the upper inode stay in memory.  A pass of
the flusher writes the data and leaves them alone, for up to 12 hours, so
the overlay inode can't be clean after it: a syncfs() which only looks at
dirty overlay inodes would miss the timestamps.

Keeping it dirty for that long isn't an option either.  The flusher would
walk it every time, and a dirty inode can't be reclaimed.  The upper inode
doesn't have that problem.  It sits on a list of its own, and its
timestamps are written when its last reference goes away, which is what
happens under memory pressure.  But the overlay inode holds a reference to
it.

Do the same one level up.  When the timestamps are all that is left, give
the overlay inode I_DIRTY_TIME.  That takes it off the list which the
flusher walks, while syncfs() still gets to it.  Implement
->sync_lazytime() to pass on to the upper inode what the VFS tells the
overlay inode: on syncfs() and fsync(), when the 12 hours are over, and
when the last reference to the overlay inode goes away.

A change through the overlay to an inode which is parked like this also
writes the timestamps, because marking it dirty ends in ->sync_lazytime().

Signed-off-by: Josef Bacik <josef@xxxxxxxxxxxxxx>
---
 fs/overlayfs/dir.c       |  1 +
 fs/overlayfs/inode.c     | 17 +++++++++++++++++
 fs/overlayfs/overlayfs.h |  1 +
 fs/overlayfs/super.c     | 24 ++++++++++++++++++++++++
 4 files changed, 43 insertions(+)

diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 1194ccf981c3..fc47beffa67e 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -1489,6 +1489,7 @@ const struct inode_operations ovl_dir_inode_operations = {
 	.get_acl	= ovl_get_acl,
 	.set_acl	= ovl_set_acl,
 	.update_time	= ovl_update_time,
+	.sync_lazytime	= ovl_sync_lazytime,
 	.fileattr_get	= ovl_fileattr_get,
 	.fileattr_set	= ovl_fileattr_set,
 	.tmpfile	= ovl_tmpfile,
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 9a4bf7c2502b..858802969017 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -743,6 +743,20 @@ int ovl_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 	return err;
 }
 
+/*
+ * The overlay inode has I_DIRTY_TIME because the upper inode has, see
+ * ovl_park_inode().  Pass it on, and keep track of the upper inode until that
+ * has been written.
+ */
+void ovl_sync_lazytime(struct inode *inode)
+{
+	struct inode *upper = ovl_inode_upper(inode);
+
+	if (upper && (inode_state_read_once(upper) & I_DIRTY_TIME))
+		mark_inode_dirty_sync(upper);
+	ovl_mark_inode_dirty(inode);
+}
+
 static const struct inode_operations ovl_file_inode_operations = {
 	.setattr	= ovl_setattr,
 	.permission	= ovl_permission,
@@ -752,6 +766,7 @@ static const struct inode_operations ovl_file_inode_operations = {
 	.get_acl	= ovl_get_acl,
 	.set_acl	= ovl_set_acl,
 	.update_time	= ovl_update_time,
+	.sync_lazytime	= ovl_sync_lazytime,
 	.fiemap		= ovl_fiemap,
 	.fileattr_get	= ovl_fileattr_get,
 	.fileattr_set	= ovl_fileattr_set,
@@ -763,6 +778,7 @@ static const struct inode_operations ovl_symlink_inode_operations = {
 	.getattr	= ovl_getattr,
 	.listxattr	= ovl_listxattr,
 	.update_time	= ovl_update_time,
+	.sync_lazytime	= ovl_sync_lazytime,
 };
 
 static const struct inode_operations ovl_special_inode_operations = {
@@ -774,6 +790,7 @@ static const struct inode_operations ovl_special_inode_operations = {
 	.get_acl	= ovl_get_acl,
 	.set_acl	= ovl_set_acl,
 	.update_time	= ovl_update_time,
+	.sync_lazytime	= ovl_sync_lazytime,
 };
 
 static const struct address_space_operations ovl_aops = {
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index f5a17bc258b6..ad1084be6191 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -867,6 +867,7 @@ static inline struct posix_acl *ovl_get_acl_path(const struct path *path,
 
 int ovl_update_time(struct inode *inode, enum fs_update_time type,
 		unsigned int flags);
+void ovl_sync_lazytime(struct inode *inode);
 bool ovl_is_private_xattr(struct super_block *sb, const char *name);
 
 struct ovl_inode_params {
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 954648d41700..631f68a97980 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -344,6 +344,28 @@ static bool ovl_upper_unfinished(struct inode *upper)
 	       (inode_state_read_once(upper) & I_SYNC);
 }
 
+/*
+ * All that is left of @inode are timestamps which lazytime holds back on the
+ * upper filesystem.  A pass which does not wait leaves them alone, for up to 12
+ * hours.  Do to the overlay inode what was done to the upper inode: with
+ * I_DIRTY_TIME it is off the list which the flusher walks, syncfs() still gets
+ * to it, and ovl_sync_lazytime() is told when the time has come.
+ *
+ * One such time is when the last reference goes away, which it never does for
+ * the upper inode as long as the overlay inode is there.  It may have gone away
+ * already.  iput() looks for I_DIRTY_TIME under i_lock before it drops the last
+ * reference, so either it sees the flag or the count is zero here.
+ */
+static void ovl_park_inode(struct inode *inode)
+{
+	if (!ovl_tracks_dirty(OVL_FS(inode->i_sb)))
+		return;
+
+	__mark_inode_dirty(inode, I_DIRTY_TIME);
+	if (!icount_read_once(inode))
+		mark_inode_dirty_sync(inode);
+}
+
 static int ovl_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
 	struct inode *upper = ovl_inode_upper(inode);
@@ -360,6 +382,8 @@ static int ovl_write_inode(struct inode *inode, struct writeback_control *wbc)
 
 	if (ovl_upper_unfinished(upper))
 		ovl_mark_inode_dirty(inode);
+	else if (inode_state_read_once(upper) & I_DIRTY_TIME)
+		ovl_park_inode(inode);
 
 	return ret;
 }

-- 
2.55.0