From: Chris Horn <chris.horn@hpe.com>
Date: Thu, 6 Aug 2020 21:39:27 +0000 (-0500)
Subject: LU-13894 lnet: Transfer disc src NID when merging peers
X-Git-Tag: 2.14.51~67
X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=commitdiff_plain;h=e65d8ba583858ae10f2d53fd270b19d13e423634

LU-13894 lnet: Transfer disc src NID when merging peers

If we're merging two peers in lnet_peer_data_present() then we need
to transfer the src NID stored in the peer whose ping buffer we are
processing to the peer that actually owns the NIDs in the ping
buffer. Otherwise it is possible that the subsequent push to the peer
that is being discovered will go out over an interface that the peer
does not know about and it will be dropped.

Test-Parameters: trivial
HPE-bug-id: LUS-9193
Signed-off-by: Chris Horn <chris.horn@hpe.com>
Change-Id: I050c7c1c2c0eddb8d5ff12f40342a8a02efacb9c
Reviewed-on: https://review.whamcloud.com/39607
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
---

diff --git a/lnet/lnet/peer.c b/lnet/lnet/peer.c
index e3eb262..9a6780c 100644
--- a/lnet/lnet/peer.c
+++ b/lnet/lnet/peer.c
@@ -3132,7 +3132,7 @@ __must_hold(&lp->lp_lock)
 		rc = lnet_peer_merge_data(lp, pbuf);
 	} else {
 		lpni = lnet_find_peer_ni_locked(nid);
-		if (!lpni) {
+		if (!lpni || lp == lpni->lpni_peer_net->lpn_peer) {
 			rc = lnet_peer_set_primary_nid(lp, nid, flags);
 			if (rc) {
 				CERROR("Primary NID error %s versus %s: %d\n",
@@ -3141,6 +3141,8 @@ __must_hold(&lp->lp_lock)
 			} else {
 				rc = lnet_peer_merge_data(lp, pbuf);
 			}
+			if (lpni)
+				lnet_peer_ni_decref_locked(lpni);
 		} else {
 			struct lnet_peer *new_lp;
 			new_lp = lpni->lpni_peer_net->lpn_peer;
@@ -3149,10 +3151,22 @@ __must_hold(&lp->lp_lock)
 			 * should have discovery/MR enabled as well, since
 			 * it's the same peer, which we're about to merge
 			 */
+			spin_lock(&lp->lp_lock);
+			spin_lock(&new_lp->lp_lock);
 			if (!(lp->lp_state & LNET_PEER_NO_DISCOVERY))
 				new_lp->lp_state &= ~LNET_PEER_NO_DISCOVERY;
 			if (lp->lp_state & LNET_PEER_MULTI_RAIL)
 				new_lp->lp_state |= LNET_PEER_MULTI_RAIL;
+			/* If we're processing a ping reply then we may be
+			 * about to send a push to the peer that we ping'd.
+			 * Since the ping reply that we're processing was
+			 * received by lp, we need to set the discovery source
+			 * NID for new_lp to the NID stored in lp.
+			 */
+			if (lp->lp_disc_src_nid != LNET_NID_ANY)
+				new_lp->lp_disc_src_nid = lp->lp_disc_src_nid;
+			spin_unlock(&new_lp->lp_lock);
+			spin_unlock(&lp->lp_lock);
 
 			rc = lnet_peer_set_primary_data(new_lp, pbuf);
 			lnet_consolidate_routes_locked(lp, new_lp);