From 576551cb97c6a5efb27d8afc59ad60550dde51ce Mon Sep 17 00:00:00 2001 From: Alexander Boyko Date: Thu, 21 Sep 2017 16:13:27 +0300 Subject: [PATCH 1/1] LU-10015 o2iblnd: fix race at kiblnd_connect_peer cmid will be destroyed at OFED if kiblnd_cm_callback return error. if error happen before the end of kiblnd_connect_peer, it will touch destroyed cmid and fail as (o2iblnd_cb.c:1315:kiblnd_connect_peer()) ASSERTION( cmid->device != ((void *)0) ) failed: Seagate-bug-id: MRP-4592 Signed-off-by: Alexander Boyko Change-Id: I83eb5bceeb567acef0316498b936d25d6c6ccd95 Reviewed-on: https://review.whamcloud.com/29134 Tested-by: Jenkins Tested-by: Maloo Reviewed-by: Alexey Lyashkov Reviewed-by: Doug Oucharek Reviewed-by: Oleg Drokin --- lnet/klnds/o2iblnd/o2iblnd_cb.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/lnet/klnds/o2iblnd/o2iblnd_cb.c b/lnet/klnds/o2iblnd/o2iblnd_cb.c index 9699fa7..35502b6 100644 --- a/lnet/klnds/o2iblnd/o2iblnd_cb.c +++ b/lnet/klnds/o2iblnd/o2iblnd_cb.c @@ -1296,11 +1296,6 @@ kiblnd_connect_peer (kib_peer_ni_t *peer_ni) goto failed2; } - LASSERT (cmid->device != NULL); - CDEBUG(D_NET, "%s: connection bound to %s:%pI4h:%s\n", - libcfs_nid2str(peer_ni->ibp_nid), dev->ibd_ifname, - &dev->ibd_ifip, cmid->device->name); - return; failed2: @@ -2997,8 +2992,19 @@ kiblnd_cm_callback(struct rdma_cm_id *cmid, struct rdma_cm_event *event) } else { rc = rdma_resolve_route( cmid, *kiblnd_tunables.kib_timeout * 1000); - if (rc == 0) - return 0; + if (rc == 0) { + kib_net_t *net = peer_ni->ibp_ni->ni_data; + kib_dev_t *dev = net->ibn_dev; + + CDEBUG(D_NET, "%s: connection bound to "\ + "%s:%pI4h:%s\n", + libcfs_nid2str(peer_ni->ibp_nid), + dev->ibd_ifname, + &dev->ibd_ifip, cmid->device->name); + + return 0; + } + /* Can't initiate route resolution */ CERROR("Can't resolve route for %s: %d\n", libcfs_nid2str(peer_ni->ibp_nid), rc); -- 1.8.3.1