From: Amir Shehata <ashehata@whamcloud.com>
Date: Sun, 17 Mar 2019 15:16:40 +0000 (-0700)
Subject: LU-12080 lnet: recovery event handling broken
X-Git-Tag: 2.12.55~25^2~42
X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=commitdiff_plain;h=5409e620e0256dc9b657f1c457541d7411b543cd

LU-12080 lnet: recovery event handling broken

Don't increment health on unlink event.
If a SEND fails an unlink will follow so no need to do any
special processing on SEND event. If SEND succeeds then we
wait for the reply.
When queuing a message on the NI recovery queue only do so
if the MT thread is still running.

Test-Parameters: forbuildonly
Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: I4877caebcac5cdfc35a59a18a3e3451b1f23cb0d
Reviewed-on: https://review.whamcloud.com/34445
Reviewed-by: Olaf Weber <olaf.weber@hpe.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Chris Horn <hornc@cray.com>
Tested-by: Jenkins
---

diff --git a/lnet/lnet/lib-move.c b/lnet/lnet/lib-move.c
index 41ab43a..ac16237 100644
--- a/lnet/lnet/lib-move.c
+++ b/lnet/lnet/lib-move.c
@@ -3453,7 +3453,7 @@ fail_error:
 
 static void
 lnet_handle_recovery_reply(struct lnet_mt_event_info *ev_info,
-			   int status)
+			   int status, bool unlink_event)
 {
 	lnet_nid_t nid = ev_info->mt_nid;
 
@@ -3485,7 +3485,8 @@ lnet_handle_recovery_reply(struct lnet_mt_event_info *ev_info,
 		 * carry forward too much information.
 		 * In the peer case, it'll naturally be incremented
 		 */
-		lnet_inc_healthv(&ni->ni_healthv);
+		if (!unlink_event)
+			lnet_inc_healthv(&ni->ni_healthv);
 	} else {
 		struct lnet_peer_ni *lpni;
 		int cpt;
@@ -3529,14 +3530,14 @@ lnet_mt_event_handler(struct lnet_event *event)
 		CDEBUG(D_NET, "%s recovery ping unlinked\n",
 		       libcfs_nid2str(ev_info->mt_nid));
 	case LNET_EVENT_REPLY:
-		lnet_handle_recovery_reply(ev_info, event->status);
+		lnet_handle_recovery_reply(ev_info, event->status,
+					   event->type == LNET_EVENT_UNLINK);
 		break;
 	case LNET_EVENT_SEND:
 		CDEBUG(D_NET, "%s recovery message sent %s:%d\n",
 			       libcfs_nid2str(ev_info->mt_nid),
 			       (event->status) ? "unsuccessfully" :
 			       "successfully", event->status);
-		lnet_handle_recovery_reply(ev_info, event->status);
 		break;
 	default:
 		CERROR("Unexpected event: %d\n", event->type);
diff --git a/lnet/lnet/lib-msg.c b/lnet/lnet/lib-msg.c
index 3497157..be2f94a 100644
--- a/lnet/lnet/lib-msg.c
+++ b/lnet/lnet/lib-msg.c
@@ -516,6 +516,11 @@ lnet_handle_remote_failure(struct lnet_peer_ni *lpni)
 		return;
 
 	lnet_net_lock(0);
+	/* the mt could've shutdown and cleaned up the queues */
+	if (the_lnet.ln_mt_state != LNET_MT_STATE_RUNNING) {
+		lnet_net_unlock(0);
+		return;
+	}
 	lnet_handle_remote_failure_locked(lpni);
 	lnet_net_unlock(0);
 }