summaryrefslogtreecommitdiffstats
path: root/fs/ocfs2
diff options
context:
space:
mode:
authorxuejiufei <xuejiufei@huawei.com>2016-01-14 15:17:38 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2016-01-14 16:00:49 -0800
commitbef5502de074b6f6fa647b94b73155d675694420 (patch)
tree3c6c516e6cd7923dfc079e3cbaa27f83b2dc554c /fs/ocfs2
parent1cce4df04f37d3f7b969e85528fa54f918a06f03 (diff)
downloadlinux-bef5502de074b6f6fa647b94b73155d675694420.tar.gz
linux-bef5502de074b6f6fa647b94b73155d675694420.tar.bz2
linux-bef5502de074b6f6fa647b94b73155d675694420.zip
ocfs2/dlm: ignore cleaning the migration mle that is inuse
We have found that migration source will trigger a BUG that the refcount of mle is already zero before put when the target is down during migration. The situation is as follows: dlm_migrate_lockres dlm_add_migration_mle dlm_mark_lockres_migrating dlm_get_mle_inuse <<<<<< Now the refcount of the mle is 2. dlm_send_one_lockres and wait for the target to become the new master. <<<<<< o2hb detect the target down and clean the migration mle. Now the refcount is 1. dlm_migrate_lockres woken, and put the mle twice when found the target goes down which trigger the BUG with the following message: "ERROR: bad mle: ". Signed-off-by: Jiufei Xue <xuejiufei@huawei.com> Reviewed-by: Joseph Qi <joseph.qi@huawei.com> Cc: Mark Fasheh <mfasheh@suse.de> Cc: Joel Becker <jlbec@evilplan.org> Cc: Junxiao Bi <junxiao.bi@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/ocfs2')
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c26
1 files changed, 15 insertions, 11 deletions
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 6f0748122117..8b9d483e94a6 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2519,6 +2519,11 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
spin_lock(&dlm->master_lock);
ret = dlm_add_migration_mle(dlm, res, mle, &oldmle, name,
namelen, target, dlm->node_num);
+ /* get an extra reference on the mle.
+ * otherwise the assert_master from the new
+ * master will destroy this.
+ */
+ dlm_get_mle_inuse(mle);
spin_unlock(&dlm->master_lock);
spin_unlock(&dlm->spinlock);
@@ -2554,6 +2559,7 @@ fail:
if (mle_added) {
dlm_mle_detach_hb_events(dlm, mle);
dlm_put_mle(mle);
+ dlm_put_mle_inuse(mle);
} else if (mle) {
kmem_cache_free(dlm_mle_cache, mle);
mle = NULL;
@@ -2571,17 +2577,6 @@ fail:
* ensure that all assert_master work is flushed. */
flush_workqueue(dlm->dlm_worker);
- /* get an extra reference on the mle.
- * otherwise the assert_master from the new
- * master will destroy this.
- * also, make sure that all callers of dlm_get_mle
- * take both dlm->spinlock and dlm->master_lock */
- spin_lock(&dlm->spinlock);
- spin_lock(&dlm->master_lock);
- dlm_get_mle_inuse(mle);
- spin_unlock(&dlm->master_lock);
- spin_unlock(&dlm->spinlock);
-
/* notify new node and send all lock state */
/* call send_one_lockres with migration flag.
* this serves as notice to the target node that a
@@ -3312,6 +3307,15 @@ top:
mle->new_master != dead_node)
continue;
+ if (mle->new_master == dead_node && mle->inuse) {
+ mlog(ML_NOTICE, "%s: target %u died during "
+ "migration from %u, the MLE is "
+ "still keep used, ignore it!\n",
+ dlm->name, dead_node,
+ mle->master);
+ continue;
+ }
+
/* If we have reached this point, this mle needs to be
* removed from the list and freed. */
dlm_clean_migration_mle(dlm, mle);