[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <1562673026-31996-1-git-send-email-dag.moxnes@oracle.com>
Date: Tue, 9 Jul 2019 13:50:26 +0200
From: Dag Moxnes <dag.moxnes@...cle.com>
To: dledford@...hat.com, jgg@...pe.ca, leon@...nel.org,
parav@...lanox.com
Cc: linux-rdma@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH v4] RDMA/core: Fix race when resolving IP address
Use the neighbour lock when copying the MAC address from the neighbour
data struct in dst_fetch_ha.
When not using the lock, it is possible for the function to race with
neigh_update(), causing it to copy an torn MAC address:
rdma_resolve_addr()
rdma_resolve_ip()
addr_resolve()
addr_resolve_neigh()
fetch_ha()
dst_fetch_ha()
memcpy(dev_addr->dst_dev_addr, n->ha, MAX_ADDR_LEN)
and
net_ioctl()
arp_ioctl()
arp_rec_delete()
arp_invalidate()
neigh_update()
__neigh_update()
memcpy(&neigh->ha, lladdr, dev->addr_len)
It is possible to provoke this error by calling rdma_resolve_addr() in a
tight loop, while deleting the corresponding ARP entry in another tight
loop.
Fixes: 51d45974515c ("infiniband: addr: Consolidate code to fetch neighbour hardware address from dst.")
Signed-off-by: Dag Moxnes <dag.moxnes@...cle.com>
Signed-off-by: HÃ¥kon Bugge <haakon.bugge@...cle.com>
Reviewed-by: Parav Pandit <parav@...lanox.com>
Signed-off-by: Jason Gunthorpe <jgg@...lanox.com>
---
drivers/infiniband/core/addr.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 2f7d141598..9b76a8fcdd 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -337,7 +337,7 @@ static int dst_fetch_ha(const struct dst_entry *dst,
neigh_event_send(n, NULL);
ret = -ENODATA;
} else {
- memcpy(dev_addr->dst_dev_addr, n->ha, MAX_ADDR_LEN);
+ neigh_ha_snapshot(dev_addr->dst_dev_addr, n, dst->dev);
}
neigh_release(n);
--
2.20.1
Powered by blists - more mailing lists