LU-14627 lnet: Ensure ref taken when queueing for discovery

[fs/lustre-release.git] / lnet / lnet / peer.c

diff --git a/lnet/lnet/peer.c b/lnet/lnet/peer.c
index 155419d..709fe24 100644 (file)
--- a/lnet/lnet/peer.c
+++ b/lnet/lnet/peer.c
@@ -2565,20 +2565,41 @@ lnet_discovery_event_reply(struct lnet_peer *lp, struct lnet_event *ev)
                goto out;
        }
 
-
        /*
         * The peer may have discovery disabled at its end. Set
         * NO_DISCOVERY as appropriate.
         */
-       if ((pbuf->pb_info.pi_features & LNET_PING_FEAT_DISCOVERY) &&
-           !lnet_peer_discovery_disabled) {
-               CDEBUG(D_NET, "Peer %s has discovery enabled\n",
-                      libcfs_nid2str(lp->lp_primary_nid));
-               lp->lp_state &= ~LNET_PEER_NO_DISCOVERY;
-       } else {
+       if (!(pbuf->pb_info.pi_features & LNET_PING_FEAT_DISCOVERY) ||
+           lnet_peer_discovery_disabled) {
                CDEBUG(D_NET, "Peer %s has discovery disabled\n",
                       libcfs_nid2str(lp->lp_primary_nid));
+
+               /* Detect whether this peer has toggled discovery from on to
+                * off and whether we can delete and re-create the peer. Peers
+                * that were manually configured cannot be deleted by discovery.
+                * We need to delete this peer and re-create it if the peer was
+                * not configured manually, is currently considered DD capable,
+                * and either:
+                * 1. We've already discovered the peer (the peer has toggled
+                *    the discovery feature from on to off), or
+                * 2. The peer is considered MR, but it was not user configured
+                *    (this was a "temporary" peer created via the kernel APIs
+                *     that we're discovering for the first time)
+                */
+               if (!(lp->lp_state & (LNET_PEER_CONFIGURED |
+                                     LNET_PEER_NO_DISCOVERY)) &&
+                   (lp->lp_state & (LNET_PEER_DISCOVERED |
+                                    LNET_PEER_MULTI_RAIL))) {
+                       CDEBUG(D_NET, "Marking %s:0x%x for deletion\n",
+                              libcfs_nid2str(lp->lp_primary_nid),
+                              lp->lp_state);
+                       lp->lp_state |= LNET_PEER_MARK_DELETION;
+               }
                lp->lp_state |= LNET_PEER_NO_DISCOVERY;
+       } else {
+               CDEBUG(D_NET, "Peer %s has discovery enabled\n",
+                      libcfs_nid2str(lp->lp_primary_nid));
+               lp->lp_state &= ~LNET_PEER_NO_DISCOVERY;
        }
 
        /*
@@ -2786,7 +2807,8 @@ static void lnet_discovery_event_handler(struct lnet_event *event)
 
        /* put peer back at end of request queue, if discovery not already
         * done */
-       if (rc == LNET_REDISCOVER_PEER && !lnet_peer_is_uptodate(lp)) {
+       if (rc == LNET_REDISCOVER_PEER && !lnet_peer_is_uptodate(lp) &&
+           lnet_peer_queue_for_discovery(lp)) {
                list_move_tail(&lp->lp_dc_list, &the_lnet.ln_dc_request);
                wake_up(&the_lnet.ln_dc_waitq);
        }
@@ -3099,7 +3121,7 @@ __must_hold(&lp->lp_lock)
         * of deleting it.
         */
        if (!list_empty(&lp->lp_dc_list))
-               list_del(&lp->lp_dc_list);
+               list_del_init(&lp->lp_dc_list);
        list_for_each_entry_safe(route, tmp,
                                 &lp->lp_routes,
                                 lr_gwlist)
@@ -3997,6 +4019,8 @@ int lnet_get_peer_info(struct lnet_ioctl_peer_cfg *cfg, void __user *bulk)
                  atomic_read(&lpni->lpni_hstats.hlt_remote_error);
                lpni_hstats->hlpni_health_value =
                  atomic_read(&lpni->lpni_healthv);
+               lpni_hstats->hlpni_ping_count = lpni->lpni_ping_count;
+               lpni_hstats->hlpni_next_ping = lpni->lpni_next_ping;
                if (copy_to_user(bulk, lpni_hstats, sizeof(*lpni_hstats)))
                        goto out_free_hstats;
                bulk += sizeof(*lpni_hstats);
@@ -4091,7 +4115,7 @@ lnet_peer_ni_set_healthv(lnet_nid_t nid, int value, bool all)
                        lnet_net_unlock(LNET_LOCK_EX);
                        return;
                }
-               atomic_set(&lpni->lpni_healthv, value);
+               lnet_set_lpni_healthv_locked(lpni, value);
                lnet_peer_ni_add_to_recoveryq_locked(lpni,
                                             &the_lnet.ln_mt_peerNIRecovq, now);
                lnet_peer_ni_decref_locked(lpni);
@@ -4112,7 +4136,8 @@ lnet_peer_ni_set_healthv(lnet_nid_t nid, int value, bool all)
                        list_for_each_entry(lpn, &lp->lp_peer_nets, lpn_peer_nets) {
                                list_for_each_entry(lpni, &lpn->lpn_peer_nis,
                                                    lpni_peer_nis) {
-                                       atomic_set(&lpni->lpni_healthv, value);
+                                       lnet_set_lpni_healthv_locked(lpni,
+                                                                    value);
                                        lnet_peer_ni_add_to_recoveryq_locked(lpni,
                                             &the_lnet.ln_mt_peerNIRecovq, now);
                                }