ocfs2: fix occurring deadlock by changing ocfs2_wq from global to local

This patch fixes a deadlock, as follows:

  Node 1                Node 2                  Node 3
1)volume a and b are    only mount vol a        only mount vol b
  mounted

2)                      start to mount b        start to mount a

3)                      check hb of Node 3      check hb of Node 2
                        in vol a, qs_holds++    in vol b, qs_holds++

4) -------------------- all nodes' network down --------------------

5)                      progress of mount b     the same situation as
                        failed, and then call   Node 2
                        ocfs2_dismount_volume.
                        but the process is hung,
                        since there is a work
                        in ocfs2_wq cannot beo
                        completed. This work is
                        about vol a, because
                        ocfs2_wq is global wq.
                        BTW, this work which is
                        scheduled in ocfs2_wq is
                        ocfs2_orphan_scan_work,
                        and the context in this work
                        needs to take inode lock
                        of orphan_dir, because
                        lockres owner are Node 1 and
                        all nodes' nework has been down
                        at the same time, so it can't
                        get the inode lock.

6)                      Why can't this node be fenced
                        when network disconnected?
                        Because the process of
                        mount is hung what caused qs_holds
                        is not equal 0.

Because all works in the ocfs2_wq are relative to the super block.

The solution is to change the ocfs2_wq from global to local.  In other
words, move it into struct ocfs2_super.

Signed-off-by: Yiwen Jiang <jiangyiwen@huawei.com>
Reviewed-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Xue jiufei <xuejiufei@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Cc: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 15 insertions, 22 deletions

diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index e2c4e3839d7b..7db631e1c8b0 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -80,12 +80,6 @@ static struct kmem_cache *ocfs2_inode_cachep;
 struct kmem_cache *ocfs2_dquot_cachep;
 struct kmem_cache *ocfs2_qf_chunk_cachep;
 
-/* OCFS2 needs to schedule several different types of work which
- * require cluster locking, disk I/O, recovery waits, etc. Since these
- * types of work tend to be heavy we avoid using the kernel events
- * workqueue and schedule on our own. */
-struct workqueue_struct *ocfs2_wq = NULL;
-
 static struct dentry *ocfs2_debugfs_root;
 
 MODULE_AUTHOR("Oracle");
@@ -1613,33 +1607,25 @@ static int __init ocfs2_init(void)
 	if (status < 0)
 		goto out2;
 
-	ocfs2_wq = create_singlethread_workqueue("ocfs2_wq");
-	if (!ocfs2_wq) {
-		status = -ENOMEM;
-		goto out3;
-	}
-
 	ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
 	if (!ocfs2_debugfs_root) {
 		status = -ENOMEM;
 		mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n");
-		goto out4;
+		goto out3;
 	}
 
 	ocfs2_set_locking_protocol();
 
 	status = register_quota_format(&ocfs2_quota_format);
 	if (status < 0)
-		goto out4;
+		goto out3;
 	status = register_filesystem(&ocfs2_fs_type);
 	if (!status)
 		return 0;
 
 	unregister_quota_format(&ocfs2_quota_format);
-out4:
-	destroy_workqueue(ocfs2_wq);
-	debugfs_remove(ocfs2_debugfs_root);
 out3:
+	debugfs_remove(ocfs2_debugfs_root);
 	ocfs2_free_mem_caches();
 out2:
 	exit_ocfs2_uptodate_cache();
@@ -1650,11 +1636,6 @@ out1:
 
 static void __exit ocfs2_exit(void)
 {
-	if (ocfs2_wq) {
-		flush_workqueue(ocfs2_wq);
-		destroy_workqueue(ocfs2_wq);
-	}
-
 	unregister_quota_format(&ocfs2_quota_format);
 
 	debugfs_remove(ocfs2_debugfs_root);
@@ -2349,6 +2330,12 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	}
 	cleancache_init_shared_fs(sb);
 
+	osb->ocfs2_wq = create_singlethread_workqueue("ocfs2_wq");
+	if (!osb->ocfs2_wq) {
+		status = -ENOMEM;
+		mlog_errno(status);
+	}
+
 bail:
 	return status;
 }
@@ -2536,6 +2523,12 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
 {
 	/* This function assumes that the caller has the main osb resource */
 
+	/* ocfs2_initializer_super have already created this workqueue */
+	if (osb->ocfs2_wq) {
+		flush_workqueue(osb->ocfs2_wq);
+		destroy_workqueue(osb->ocfs2_wq);
+	}
+
 	ocfs2_free_slot_info(osb);
 
 	kfree(osb->osb_orphan_wipes);