3.16.7-ckt19 -stable review patch. If anyone has any objections, please let me know.
------------------ From: Joseph Qi <[email protected]> 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 <[email protected]> Cc: Joel Becker <[email protected]> Cc: Mark Fasheh <[email protected]> Cc: "Junxiao Bi" <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]> [ luis: backported to 3.16: adjusted context ] Signed-off-by: Luis Henriques <[email protected]> --- fs/ocfs2/dlm/dlmmaster.c | 9 ++++++--- fs/ocfs2/dlm/dlmrecovery.c | 8 ++++++-- 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 7b9f96899812..189e7e1b7144 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1450,6 +1450,7 @@ 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; @@ -1656,14 +1657,17 @@ send_response: mlog(ML_ERROR, "failed to dispatch assert master work\n"); response = DLM_MASTER_RESP_ERROR; dlm_lockres_put(res); - } else + } else { + dispatched = 1; dlm_lockres_grab_inflight_worker(dlm, res); + } } else { if (res) dlm_lockres_put(res); } - dlm_put(dlm); + if (!dispatched) + dlm_put(dlm); return response; } @@ -2083,7 +2087,6 @@ 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 45067faf5695..5084ce856879 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1687,6 +1687,7 @@ 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 @@ -1708,15 +1709,18 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, mlog_errno(-ENOMEM); /* retry!? */ BUG(); - } else + } else { + dispatched = 1; __dlm_lockres_grab_inflight_worker(dlm, res); + } } else /* put.. incase we are not the master */ dlm_lockres_put(res); spin_unlock(&res->spinlock); } spin_unlock(&dlm->spinlock); - dlm_put(dlm); + if (!dispatched) + dlm_put(dlm); return master; } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
