[PATCH] ocfs2: fix deadlock when creating quota file

[Heming Zhao]

syzbot detected a circular locking dependency. the scenarios:

        CPU0                    CPU1
        ----                    ----
   lock(&ocfs2_quota_ip_alloc_sem_key);
                                lock(&ocfs2_sysfile_lock_key[USER_QUOTA_SYSTEM_INODE]);
                                lock(&ocfs2_quota_ip_alloc_sem_key);
   lock(&ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE]);

or:
       CPU0                    CPU1
       ----                    ----
  lock(&ocfs2_quota_ip_alloc_sem_key);
                               lock(&dquot->dq_lock);
                               lock(&ocfs2_quota_ip_alloc_sem_key);
  lock(&ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE]);

Following are the code paths for above scenarios:

path_openat
 ocfs2_create
  ocfs2_mknod
  + ocfs2_reserve_new_inode
  |  ocfs2_reserve_suballoc_bits
  |   inode_lock(alloc_inode) //C0: hold INODE_ALLOC_SYSTEM_INODE
  |    //at end of this func, ocfs2_free_alloc_context(inode_ac) calls inode_unlock
  |
  + ocfs2_get_init_inode
     __dquot_initialize
      dqget
       ocfs2_acquire_dquot
       + ocfs2_lock_global_qf
       |  down_write(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem)//A2:grabbing
       + ocfs2_create_local_dquot
          down_write(&OCFS2_I(lqinode)->ip_alloc_sem)//A3:grabbing

evict
 ocfs2_evict_inode
  ocfs2_delete_inode
   ocfs2_wipe_inode
    + inode_lock(orphan_dir_inode) //B0:hold
    + ...
    + ocfs2_remove_inode
       inode_lock(inode_alloc_inode) //INODE_ALLOC_SYSTEM_INODE
        down_write(&inode->i_rwsem) //C1:grabbing

generic_file_direct_write
 ocfs2_direct_IO
  __blockdev_direct_IO
   dio_complete
    ocfs2_dio_end_io
     ocfs2_dio_end_io_write
     + down_write(&oi->ip_alloc_sem) //A0:hold
     + ocfs2_del_inode_from_orphan
        inode_lock(orphan_dir_inode) //B1:grabbing

Root cause for the circular locking:

DIO completion path:
 holds oi->ip_alloc_sem and is trying to acquire the orphan_dir_inode lock.

evict path:
 holds the orphan_dir_inode lock and is trying to acquire the
 inode_alloc_inode lock.

ocfs2_mknod path:
 Holds the inode_alloc_inode lock (to allocate a new quota file) and is
 blocked waiting for oi->ip_alloc_sem in ocfs2_acquire_dquot().

How to fix:

Replace down_write() with down_write_trylock() in ocfs2_acquire_dquot().
If acquiring oi->ip_alloc_sem fails, return -EBUSY to abort the file creation
routine and break the deadlock.

Reported-by: syzbot+78359d5fbb04318c35e9@xxxxxxxxxxxxxxxxxxxxxxxxx
Closes: https://syzkaller.appspot.com/bug?extid=78359d5fbb04318c35e9
Signed-off-by: Heming Zhao <heming.zhao@xxxxxxxx>
---
 fs/ocfs2/quota_global.c | 5 ++++-
 fs/ocfs2/quota_local.c  | 5 ++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index e85b1ccf81be..4321d8f59402 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -311,7 +311,10 @@ int ocfs2_lock_global_qf(struct ocfs2_mem_dqinfo *oinfo, int ex)
 	spin_unlock(&dq_data_lock);
 	if (ex) {
 		inode_lock(oinfo->dqi_gqinode);
-		down_write(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem);
+		if (!down_write_trylock(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem)) {
+			inode_unlock(oinfo->dqi_gqinode);
+			return -EBUSY;
+		}
 	} else {
 		down_read(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem);
 	}
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index c4e0117d8977..e451f3d96037 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -1224,7 +1224,10 @@ int ocfs2_create_local_dquot(struct dquot *dquot)
 	int status;
 	u64 pcount;
 
-	down_write(&OCFS2_I(lqinode)->ip_alloc_sem);
+	if (!down_write_trylock(&OCFS2_I(lqinode)->ip_alloc_sem)) {
+		status = -EBUSY;
+		goto out;
+	}
 	chunk = ocfs2_find_free_entry(sb, type, &offset);
 	if (!chunk) {
 		chunk = ocfs2_extend_local_quota_file(sb, type, &offset);
-- 
2.43.0