X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lnet%2Flnet%2Flib-move.c;h=75a0650d34a97d4e671d68b33bcfd27e0f19ac6e;hp=e3bad23b05f698a0a511edefc4c6f3e864c1eeb3;hb=1a7720934dfb3105afd2f025c953bea2167d4e5d;hpb=f843facff59226d3788d855d1d6948523ab8d944

diff --git a/lnet/lnet/lib-move.c b/lnet/lnet/lib-move.c
index e3bad23..75a0650 100644
--- a/lnet/lnet/lib-move.c
+++ b/lnet/lnet/lib-move.c
@@ -42,8 +42,6 @@
 #include <linux/nsproxy.h>
 #include <net/net_namespace.h>
 
-extern unsigned int lnet_current_net_count;
-
 static int local_nid_dist_zero = 1;
 module_param(local_nid_dist_zero, int, 0444);
 MODULE_PARM_DESC(local_nid_dist_zero, "Reserved");
@@ -1910,8 +1908,11 @@ lnet_handle_spec_local_nmr_dst(struct lnet_send_data *sd)
  * Local Destination
  * MR Peer
  *
- * Run the selection algorithm on the peer NIs unless we're sending
- * a response, in this case just send to the destination
+ * Don't run the selection algorithm on the peer NIs. By specifying the
+ * local NID, we're also saying that we should always use the destination NID
+ * provided. This handles the case where we should be using the same
+ * destination NID for the all the messages which belong to the same RPC
+ * request.
  */
 static int
 lnet_handle_spec_local_mr_dst(struct lnet_send_data *sd)
@@ -1924,17 +1925,6 @@ lnet_handle_spec_local_mr_dst(struct lnet_send_data *sd)
 		return -EINVAL;
 	}
 
-	/*
-	 * only run the selection algorithm to pick the peer_ni if we're
-	 * sending a GET or a PUT. Responses are sent to the same
-	 * destination NID provided.
-	 */
-	if (!(sd->sd_send_case & SND_RESP)) {
-		sd->sd_best_lpni =
-		  lnet_find_best_lpni_on_net(sd, sd->sd_peer,
-					     sd->sd_best_ni->ni_net->net_id);
-	}
-
 	if (sd->sd_best_lpni &&
 	    sd->sd_best_lpni->lpni_nid == the_lnet.ln_loni->ni_nid)
 		return lnet_handle_lo_send(sd);
@@ -2009,15 +1999,21 @@ lnet_initiate_peer_discovery(struct lnet_peer_ni *lpni,
 	}
 	/* The peer may have changed. */
 	peer = lpni->lpni_peer_net->lpn_peer;
+	spin_lock(&peer->lp_lock);
+	if (lnet_peer_is_uptodate_locked(peer)) {
+		spin_unlock(&peer->lp_lock);
+		lnet_peer_ni_decref_locked(lpni);
+		return 0;
+	}
 	/* queue message and return */
 	msg->msg_rtr_nid_param = rtr_nid;
 	msg->msg_sending = 0;
 	msg->msg_txpeer = NULL;
-	spin_lock(&peer->lp_lock);
 	list_add_tail(&msg->msg_list, &peer->lp_dc_pendq);
+	primary_nid = peer->lp_primary_nid;
 	spin_unlock(&peer->lp_lock);
+
 	lnet_peer_ni_decref_locked(lpni);
-	primary_nid = peer->lp_primary_nid;
 
 	CDEBUG(D_NET, "msg %p delayed. %s pending discovery\n",
 		msg, libcfs_nid2str(primary_nid));
@@ -2671,11 +2667,10 @@ again:
 	msg->msg_src_nid_param = src_nid;
 
 	/*
-	 * Now that we have a peer_ni, check if we want to discover
-	 * the peer. Traffic to the LNET_RESERVED_PORTAL should not
-	 * trigger discovery.
+	 * If necessary, perform discovery on the peer that owns this peer_ni.
+	 * Note, this can result in the ownership of this peer_ni changing
+	 * to another peer object.
 	 */
-	peer = lpni->lpni_peer_net->lpn_peer;
 	rc = lnet_initiate_peer_discovery(lpni, msg, rtr_nid, cpt);
 	if (rc) {
 		lnet_peer_ni_decref_locked(lpni);
@@ -2684,6 +2679,8 @@ again:
 	}
 	lnet_peer_ni_decref_locked(lpni);
 
+	peer = lpni->lpni_peer_net->lpn_peer;
+
 	/*
 	 * Identify the different send cases
 	 */
@@ -3542,9 +3539,13 @@ lnet_monitor_thread(void *arg)
 			       min((unsigned int) alive_router_check_interval /
 					lnet_current_net_count,
 				   lnet_transaction_timeout / 2));
-		wait_event_interruptible_timeout(the_lnet.ln_mt_waitq,
-						false,
-						cfs_time_seconds(interval));
+		wait_for_completion_interruptible_timeout(
+			&the_lnet.ln_mt_wait_complete,
+			cfs_time_seconds(interval));
+		/* Must re-init the completion before testing anything,
+		 * including ln_mt_state.
+		 */
+		reinit_completion(&the_lnet.ln_mt_wait_complete);
 	}
 
 	/* Shutting down */
@@ -3809,7 +3810,7 @@ void lnet_monitor_thr_stop(void)
 	lnet_net_unlock(LNET_LOCK_EX);
 
 	/* tell the monitor thread that we're shutting down */
-	wake_up(&the_lnet.ln_mt_waitq);
+	complete(&the_lnet.ln_mt_wait_complete);
 
 	/* block until monitor thread signals that it's done */
 	down(&the_lnet.ln_mt_signal);
@@ -3820,8 +3821,6 @@ void lnet_monitor_thr_stop(void)
 	lnet_clean_local_ni_recoveryq();
 	lnet_clean_peer_ni_recoveryq();
 	lnet_clean_resendqs();
-
-	return;
 }
 
 void
@@ -5094,9 +5093,9 @@ LNetDist(lnet_nid_t dstnid, lnet_nid_t *srcnidp, __u32 *orderp)
 			 * current net namespace.
 			 * If not, assign order above 0xffff0000,
 			 * to make this ni not a priority. */
-			if (!net_eq(ni->ni_net_ns, current->nsproxy->net_ns))
-				order += 0xffff0000;
-
+			if (current->nsproxy &&
+			    !net_eq(ni->ni_net_ns, current->nsproxy->net_ns))
+					order += 0xffff0000;
 			if (srcnidp != NULL)
 				*srcnidp = ni->ni_nid;
 			if (orderp != NULL)