LU-13989 ldlm: BL AST vs failed lock enqueue race

failed_lock_cleanup() marks the lock with LDLM_FL_LOCAL_ONLY,
so cancel request isn't sent.

Mark failed lock with LDLM_FL_LOCAL_ONLY only
if BL AST wasn't received.
Add server's lock handle to BL AST RPC.
So client will be able to cancel the lock
even if enqueue fails.

Change-Id: I3201bc29abd877cddc334ca27a9d208cb55c5d8f
HPE-bug-id: LUS-8493, LUS-8830
Signed-off-by: Andriy Skulysh <c17819@cray.com>
Reviewed-by: Vladimir Saveliev <c17830@cray.com>
Reviewed-by: Alexander Boyko <c17825@cray.com>
Reviewed-by: Vitaly Fertman <c17818@cray.com>
Reviewed-on: https://review.whamcloud.com/40046
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Alexander Boyko <alexander.boyko@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

diff --git a/lustre/ldlm/ldlm_lockd.c b/lustre/ldlm/ldlm_lockd.c
index de10643..0315364 100644 (file)
--- a/lustre/ldlm/ldlm_lockd.c
+++ b/lustre/ldlm/ldlm_lockd.c
@@ -944,6 +944,7 @@ int ldlm_server_blocking_ast(struct ldlm_lock *lock,
 
        body = req_capsule_client_get(&req->rq_pill, &RMF_DLM_REQ);
        body->lock_handle[0] = lock->l_remote_handle;
+       body->lock_handle[1].cookie = lock->l_handle.h_cookie;
        body->lock_desc = *desc;
        body->lock_flags |= ldlm_flags_to_wire(lock->l_flags & LDLM_FL_AST_MASK);
 
@@ -1039,6 +1040,7 @@ int ldlm_server_completion_ast(struct ldlm_lock *lock, __u64 flags, void *data)
        body = req_capsule_client_get(&req->rq_pill, &RMF_DLM_REQ);
 
        body->lock_handle[0] = lock->l_remote_handle;
+       body->lock_handle[1].cookie = lock->l_handle.h_cookie;
        body->lock_flags = ldlm_flags_to_wire(flags);
        ldlm_lock2desc(lock, &body->lock_desc);
        if (lvb_len > 0) {
@@ -2413,6 +2415,8 @@ static int ldlm_callback_handler(struct ptlrpc_request *req)
                ldlm_lock_remove_from_lru(lock);
                ldlm_set_bl_ast(lock);
        }
+       if (lock->l_remote_handle.cookie == 0)
+               lock->l_remote_handle = dlm_req->lock_handle[1];
        unlock_res_and_lock(lock);
 
        /*

diff --git a/lustre/ldlm/ldlm_request.c b/lustre/ldlm/ldlm_request.c
index b53a858..23abc07 100644 (file)
--- a/lustre/ldlm/ldlm_request.c
+++ b/lustre/ldlm/ldlm_request.c
@@ -552,8 +552,11 @@ static void failed_lock_cleanup(struct ldlm_namespace *ns,
                 * bl_ast and -EINVAL reply is sent to server anyways.
                 * b=17645
                 */
-               lock->l_flags |= LDLM_FL_LOCAL_ONLY | LDLM_FL_FAILED |
+               lock->l_flags |= LDLM_FL_FAILED |
                                 LDLM_FL_ATOMIC_CB | LDLM_FL_CBPENDING;
+               if (!(ldlm_is_bl_ast(lock) &&
+                     lock->l_remote_handle.cookie != 0))
+                       lock->l_flags |= LDLM_FL_LOCAL_ONLY;
                need_cancel = 1;
        }
        unlock_res_and_lock(lock);