diff options
| author | Joseph Qi <joseph.qi@huawei.com> | 2015-09-22 14:59:20 -0700 |
|---|---|---|
| committer | Ben Hutchings <ben@decadent.org.uk> | 2015-10-13 03:46:11 +0100 |
| commit | 307c6c27d5de3b44965cdba2a69e1d5f922a01c1 (patch) | |
| tree | bdbd2602f6bb845b22ea0393cd0b02817c823b1c | |
| parent | 81fbc9a5dd000126ef727dcdaea3ef5714d1e898 (diff) | |
| download | kernel_samsung_smdk4412-307c6c27d5de3b44965cdba2a69e1d5f922a01c1.zip kernel_samsung_smdk4412-307c6c27d5de3b44965cdba2a69e1d5f922a01c1.tar.gz kernel_samsung_smdk4412-307c6c27d5de3b44965cdba2a69e1d5f922a01c1.tar.bz2 | |
ocfs2/dlm: fix deadlock when dispatch assert master
commit 012572d4fc2e4ddd5c8ec8614d51414ec6cae02a upstream.
The order of the following three spinlocks should be:
dlm_domain_lock < dlm_ctxt->spinlock < dlm_lock_resource->spinlock
But dlm_dispatch_assert_master() is called while holding
dlm_ctxt->spinlock and dlm_lock_resource->spinlock, and then it calls
dlm_grab() which will take dlm_domain_lock.
Once another thread (for example, dlm_query_join_handler) has already
taken dlm_domain_lock, and tries to take dlm_ctxt->spinlock deadlock
happens.
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Mark Fasheh <mfasheh@suse.com>
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>
[bwh: Backported to 3.2: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
| -rw-r--r-- | fs/ocfs2/dlm/dlmmaster.c | 7 | ||||
| -rw-r--r-- | fs/ocfs2/dlm/dlmrecovery.c | 6 |
2 files changed, 10 insertions, 3 deletions
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 7ba6ac1..8e48ba5 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1411,6 +1411,7 @@ int dlm_master_request_handler(struct o2net_msg *msg, u32 len, void *data, int found, ret; int set_maybe; int dispatch_assert = 0; + int dispatched = 0; if (!dlm_grab(dlm)) return DLM_MASTER_RESP_NO; @@ -1617,13 +1618,16 @@ send_response: mlog(ML_ERROR, "failed to dispatch assert master work\n"); response = DLM_MASTER_RESP_ERROR; dlm_lockres_put(res); + } else { + dispatched = 1; } } else { if (res) dlm_lockres_put(res); } - dlm_put(dlm); + if (!dispatched) + dlm_put(dlm); return response; } @@ -2041,7 +2045,6 @@ int dlm_dispatch_assert_master(struct dlm_ctxt *dlm, /* queue up work for dlm_assert_master_worker */ - dlm_grab(dlm); /* get an extra ref for the work item */ dlm_init_work_item(dlm, item, dlm_assert_master_worker, NULL); item->u.am.lockres = res; /* already have a ref */ /* can optionally ignore node numbers higher than this node */ diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index d15b071..0e5013e 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1689,6 +1689,7 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, unsigned int hash; int master = DLM_LOCK_RES_OWNER_UNKNOWN; u32 flags = DLM_ASSERT_MASTER_REQUERY; + int dispatched = 0; if (!dlm_grab(dlm)) { /* since the domain has gone away on this @@ -1710,6 +1711,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, mlog_errno(-ENOMEM); /* retry!? */ BUG(); + } else { + dispatched = 1; } } else /* put.. incase we are not the master */ dlm_lockres_put(res); @@ -1717,7 +1720,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, } spin_unlock(&dlm->spinlock); - dlm_put(dlm); + if (!dispatched) + dlm_put(dlm); return master; } |