From 88c4c066c6b4db26dc4909ee94e6bf377e8e8e81 Mon Sep 17 00:00:00 2001 From: Zang MingJie Date: Mon, 4 Mar 2013 06:07:34 +0000 Subject: reset nf before xmit vxlan encapsulated packet We should reset nf settings bond to the skb as ipip/ipgre do. If not, the conntrack/nat info bond to the origin packet may continually redirect the packet to vxlan interface causing a routing loop. this is the scenario: VETP VXLAN Gateway /----\ /---------------\ | | | | | vx+--+vx --NAT-> eth0+--> Internet | | | | \----/ \---------------/ when there are any packet coming from internet to the vetp, there will be lots of garbage packets coming out the gateway's vxlan interface, but none actually sent to the physical interface, because they are redirected back to the vxlan interface in the postrouting chain of NAT rule, and dmesg complains: Mar 1 21:52:53 debian kernel: [ 8802.997699] Dead loop on virtual device vxlan0, fix it urgently! Mar 1 21:52:54 debian kernel: [ 8804.004907] Dead loop on virtual device vxlan0, fix it urgently! Mar 1 21:52:55 debian kernel: [ 8805.012189] Dead loop on virtual device vxlan0, fix it urgently! Mar 1 21:52:56 debian kernel: [ 8806.020593] Dead loop on virtual device vxlan0, fix it urgently! the patch should fix the problem Signed-off-by: Zang MingJie Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/vxlan.c') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index f10e58ac9c1..c3e3d2929ee 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -961,6 +961,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) iph->ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); tunnel_ip_select_ident(skb, old_iph, &rt->dst); + nf_reset(skb); + vxlan_set_owner(dev, skb); /* See iptunnel_xmit() */ -- cgit v1.2.3-70-g09d2 From 9cb6cb7ed11cd3b69c47bb414983603a6ff20b1d Mon Sep 17 00:00:00 2001 From: Zang MingJie Date: Wed, 6 Mar 2013 04:37:37 +0000 Subject: vxlan: fix oops when delete netns containing vxlan The following script will produce a kernel oops: sudo ip netns add v sudo ip netns exec v ip ad add 127.0.0.1/8 dev lo sudo ip netns exec v ip link set lo up sudo ip netns exec v ip ro add 224.0.0.0/4 dev lo sudo ip netns exec v ip li add vxlan0 type vxlan id 42 group 239.1.1.1 dev lo sudo ip netns exec v ip link set vxlan0 up sudo ip netns del v where inspect by gdb: Program received signal SIGSEGV, Segmentation fault. [Switching to Thread 107] 0xffffffffa0289e33 in ?? () (gdb) bt #0 vxlan_leave_group (dev=0xffff88001bafa000) at drivers/net/vxlan.c:533 #1 vxlan_stop (dev=0xffff88001bafa000) at drivers/net/vxlan.c:1087 #2 0xffffffff812cc498 in __dev_close_many (head=head@entry=0xffff88001f2e7dc8) at net/core/dev.c:1299 #3 0xffffffff812cd920 in dev_close_many (head=head@entry=0xffff88001f2e7dc8) at net/core/dev.c:1335 #4 0xffffffff812cef31 in rollback_registered_many (head=head@entry=0xffff88001f2e7dc8) at net/core/dev.c:4851 #5 0xffffffff812cf040 in unregister_netdevice_many (head=head@entry=0xffff88001f2e7dc8) at net/core/dev.c:5752 #6 0xffffffff812cf1ba in default_device_exit_batch (net_list=0xffff88001f2e7e18) at net/core/dev.c:6170 #7 0xffffffff812cab27 in cleanup_net (work=) at net/core/net_namespace.c:302 #8 0xffffffff810540ef in process_one_work (worker=0xffff88001ba9ed40, work=0xffffffff8167d020) at kernel/workqueue.c:2157 #9 0xffffffff810549d0 in worker_thread (__worker=__worker@entry=0xffff88001ba9ed40) at kernel/workqueue.c:2276 #10 0xffffffff8105870c in kthread (_create=0xffff88001f2e5d68) at kernel/kthread.c:168 #11 #12 0x0000000000000000 in ?? () #13 0x0000000000000000 in ?? () (gdb) fr 0 #0 vxlan_leave_group (dev=0xffff88001bafa000) at drivers/net/vxlan.c:533 533 struct sock *sk = vn->sock->sk; (gdb) l 528 static int vxlan_leave_group(struct net_device *dev) 529 { 530 struct vxlan_dev *vxlan = netdev_priv(dev); 531 struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); 532 int err = 0; 533 struct sock *sk = vn->sock->sk; 534 struct ip_mreqn mreq = { 535 .imr_multiaddr.s_addr = vxlan->gaddr, 536 .imr_ifindex = vxlan->link, 537 }; (gdb) p vn->sock $4 = (struct socket *) 0x0 The kernel calls `vxlan_exit_net` when deleting the netns before shutting down vxlan interfaces. Later the removal of all vxlan interfaces, where `vn->sock` is already gone causes the oops. so we should manually shutdown all interfaces before deleting `vn->sock` as the patch does. Signed-off-by: Zang MingJie Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'drivers/net/vxlan.c') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index c3e3d2929ee..7cee7a3068e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1506,6 +1506,14 @@ static __net_init int vxlan_init_net(struct net *net) static __net_exit void vxlan_exit_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); + struct vxlan_dev *vxlan; + unsigned h; + + rtnl_lock(); + for (h = 0; h < VNI_HASH_SIZE; ++h) + hlist_for_each_entry(vxlan, &vn->vni_list[h], hlist) + dev_close(vxlan->dev); + rtnl_unlock(); if (vn->sock) { sk_release_kernel(vn->sock->sk); -- cgit v1.2.3-70-g09d2