ocfs2: Fix deadlock on umount

In commit ea455f8ab68338ba69f5d3362b342c115bea8e13, we moved the dentry lock
put process into ocfs2_wq. This causes problems during umount because ocfs2_wq
can drop references to inodes while they are being invalidated by
invalidate_inodes() causing all sorts of nasty things (invalidate_inodes()
ending in an infinite loop, "Busy inodes after umount" messages etc.).

We fix the problem by stopping ocfs2_wq from doing any further releasing of
inode references on the superblock being unmounted, wait until it finishes
the current round of releasing and finally cleaning up all the references in
dentry_lock_list from ocfs2_put_super().

The issue was tracked down by Tao Ma <tao.ma@oracle.com>.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Joel Becker <joel.becker@oracle.com>

1 files changed, 22 insertions, 3 deletions

diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 63af2e36d834a8..f2893878f8ad41 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1213,14 +1213,27 @@ static int ocfs2_get_sb(struct file_system_type *fs_type,
 			   mnt);
 }
 
+static void ocfs2_kill_sb(struct super_block *sb)
+{
+	struct ocfs2_super *osb = OCFS2_SB(sb);
+
+	/* Prevent further queueing of inode drop events */
+	spin_lock(&dentry_list_lock);
+	ocfs2_set_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED);
+	spin_unlock(&dentry_list_lock);
+	/* Wait for work to finish and/or remove it */
+	cancel_work_sync(&osb->dentry_lock_work);
+
+	kill_block_super(sb);
+}
+
 static struct file_system_type ocfs2_fs_type = {
 	.owner          = THIS_MODULE,
 	.name           = "ocfs2",
 	.get_sb         = ocfs2_get_sb, /* is this called when we mount
 					* the fs? */
-	.kill_sb        = kill_block_super, /* set to the generic one
-					     * right now, but do we
-					     * need to change that? */
+	.kill_sb        = ocfs2_kill_sb,
+
 	.fs_flags       = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE,
 	.next           = NULL
 };
@@ -1819,6 +1832,12 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
 	debugfs_remove(osb->osb_ctxt);
 
+	/*
+	 * Flush inode dropping work queue so that deletes are
+	 * performed while the filesystem is still working
+	 */
+	ocfs2_drop_all_dl_inodes(osb);
+
 	/* Orphan scan should be stopped as early as possible */
 	ocfs2_orphan_scan_stop(osb);