c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2024-12-25 18:59:33 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix deadlock between zpool export and zfs list

Browse Source 
Pool reference count is NOT checked in spa_export_common()
if the pool has been imported readonly=on, i.e. spa->spa_sync_on
is FALSE. Then zpool export and zfs list may deadlock:

1. Pool A is imported readonly.
2. zpool export A and zfs list are run concurrently.
3. zfs command gets reference on the spa, which holds a dbuf on
   on the MOS meta dnode.
4. zpool command grabs spa_namespace_lock, and tries to evict dbufs
   of the MOS meta dnode. The dbuf held by zfs command can't be
   evicted as its reference count is not 0.
5. zpool command blocks in dnode_special_close() waiting for the
   MOS meta dnode reference count to drop to 0, with
   spa_namespace_lock held.
6. zfs command tries to get the spa_namespace_lock with a reference
   on the spa held, which holds a dbuf on the MOS meta dnode.
7. Now zpool command and zfs command deadlock each other.

Also any further zfs/zpool command will block on spa_namespace_lock
forever.

The fix is to always check pool reference count in spa_export_common(),
no matter whether the pool was imported readonly or not.

Signed-off-by: Isaac Huang <he.huang@intel.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #2034
This commit is contained in:
Isaac Huang 2015-02-26 22:46:45 -07:00 committed by Brian Behlendorf
parent 87a63dd702
commit d14cfd83da
1 changed files with 20 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
module/zfs/spa.c
View File

@ -4262,30 +4262,30 @@ spa_export_common(char *pool, int new_state, nvlist_t **oldconfig,
mutex_enter(&spa_namespace_lock); mutex_enter(&spa_namespace_lock);
spa_close(spa, FTAG); spa_close(spa, FTAG);
if (spa->spa_state == POOL_STATE_UNINITIALIZED)
goto export_spa;
/* /*
* The pool will be in core if it's openable, * The pool will be in core if it's openable, in which case we can
* in which case we can modify its state. * modify its state. Objsets may be open only because they're dirty,
* so we have to force it to sync before checking spa_refcnt.
*/ */
if (spa->spa_state != POOL_STATE_UNINITIALIZED && spa->spa_sync_on) { if (spa->spa_sync_on)
/*
* Objsets may be open only because they're dirty, so we
* have to force it to sync before checking spa_refcnt.
*/
txg_wait_synced(spa->spa_dsl_pool, 0); txg_wait_synced(spa->spa_dsl_pool, 0);
/* /*
* A pool cannot be exported or destroyed if there are active * A pool cannot be exported or destroyed if there are active
* references. If we are resetting a pool, allow references by * references. If we are resetting a pool, allow references by
* fault injection handlers. * fault injection handlers.
*/ */
if (!spa_refcount_zero(spa) || if (!spa_refcount_zero(spa) ||
(spa->spa_inject_ref != 0 && (spa->spa_inject_ref != 0 &&
new_state != POOL_STATE_UNINITIALIZED)) { new_state != POOL_STATE_UNINITIALIZED)) {
spa_async_resume(spa); spa_async_resume(spa);
mutex_exit(&spa_namespace_lock); mutex_exit(&spa_namespace_lock);
return (SET_ERROR(EBUSY)); return (SET_ERROR(EBUSY));
} }
if (spa->spa_sync_on) {
/* /*
* A pool cannot be exported if it has an active shared spare. * A pool cannot be exported if it has an active shared spare.
* This is to prevent other pools stealing the active spare * This is to prevent other pools stealing the active spare
@ -4314,6 +4314,7 @@ spa_export_common(char *pool, int new_state, nvlist_t **oldconfig,
} }
} }
export_spa:
spa_event_notify(spa, NULL, FM_EREPORT_ZFS_POOL_DESTROY); spa_event_notify(spa, NULL, FM_EREPORT_ZFS_POOL_DESTROY);
if (spa->spa_state != POOL_STATE_UNINITIALIZED) { if (spa->spa_state != POOL_STATE_UNINITIALIZED) {