[PATCH] staging: lustre: o2iblnd: fix race at kiblnd_connect_peer

Doug Oucharek dougso at me.com
Fri Mar 9 23:29:40 UTC 2018


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:

Signed-off-by: Alexander Boyko <alexander.boyko at seagate.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-10015
Reviewed-by: Alexey Lyashkov <c17817 at cray.com>
Reviewed-by: Doug Oucharek <dougso at me.com>
Reviewed-by: John L. Hammond <john.hammond at intel.com>
Signed-off-by: Doug Oucharek <dougso at me.com>
---
drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c | 18 ++++++++++++------
1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
index 6690a6c..080c2a1 100644
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
+++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
@@ -1290,11 +1290,6 @@ static int kiblnd_resolve_addr(struct rdma_cm_id *cmid,
		goto failed2;
	}

-	LASSERT(cmid->device);
-	CDEBUG(D_NET, "%s: connection bound to %s:%pI4h:%s\n",
-	       libcfs_nid2str(peer->ibp_nid), dev->ibd_ifname,
-	       &dev->ibd_ifip, cmid->device->name);
-
	return;

 failed2:
@@ -2996,8 +2991,19 @@ static int kiblnd_resolve_addr(struct rdma_cm_id *cmid,
		} else {
			rc = rdma_resolve_route(
				cmid, *kiblnd_tunables.kib_timeout * 1000);
-			if (!rc)
+			if (!rc) {
+				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->ibp_nid), rc);
-- 
1.8.3.1



More information about the devel mailing list