From 94d9f1c5906b20053efe375b6d66610bca4b8b64 Mon Sep 17 00:00:00 2001 From: David Forster Date: Wed, 3 Aug 2016 15:13:01 +0100 Subject: ipv4: panic in leaf_walk_rcu due to stale node pointer Panic occurs when issuing "cat /proc/net/route" whilst populating FIB with > 1M routes. Use of cached node pointer in fib_route_get_idx is unsafe. BUG: unable to handle kernel paging request at ffffc90001630024 IP: [] leaf_walk_rcu+0x10/0xe0 PGD 11b08d067 PUD 11b08e067 PMD dac4b067 PTE 0 Oops: 0000 [#1] SMP Modules linked in: nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscac snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep virti acpi_cpufreq button parport_pc ppdev lp parport autofs4 ext4 crc16 mbcache jbd tio_ring virtio floppy uhci_hcd ehci_hcd usbcore usb_common libata scsi_mod CPU: 1 PID: 785 Comm: cat Not tainted 4.2.0-rc8+ #4 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007 task: ffff8800da1c0bc0 ti: ffff88011a05c000 task.ti: ffff88011a05c000 RIP: 0010:[] [] leaf_walk_rcu+0x10/0xe0 RSP: 0018:ffff88011a05fda0 EFLAGS: 00010202 RAX: ffff8800d8a40c00 RBX: ffff8800da4af940 RCX: ffff88011a05ff20 RDX: ffffc90001630020 RSI: 0000000001013531 RDI: ffff8800da4af950 RBP: 0000000000000000 R08: ffff8800da1f9a00 R09: 0000000000000000 R10: ffff8800db45b7e4 R11: 0000000000000246 R12: ffff8800da4af950 R13: ffff8800d97a74c0 R14: 0000000000000000 R15: ffff8800d97a7480 FS: 00007fd3970e0700(0000) GS:ffff88011fd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffffc90001630024 CR3: 000000011a7e4000 CR4: 00000000000006e0 Stack: ffffffff814d00d3 0000000000000000 ffff88011a05ff20 ffff8800da1f9a00 ffffffff811dd8b9 0000000000000800 0000000000020000 00007fd396f35000 ffffffff811f8714 0000000000003431 ffffffff8138dce0 0000000000000f80 Call Trace: [] ? fib_route_seq_start+0x93/0xc0 [] ? seq_read+0x149/0x380 [] ? fsnotify+0x3b4/0x500 [] ? process_echoes+0x70/0x70 [] ? proc_reg_read+0x47/0x70 [] ? __vfs_read+0x23/0xd0 [] ? rw_verify_area+0x52/0xf0 [] ? vfs_read+0x81/0x120 [] ? SyS_read+0x42/0xa0 [] ? entry_SYSCALL_64_fastpath+0x16/0x75 Code: 48 85 c0 75 d8 f3 c3 31 c0 c3 f3 c3 66 66 66 66 66 66 2e 0f 1f 84 00 00 a 04 89 f0 33 02 44 89 c9 48 d3 e8 0f b6 4a 05 49 89 RIP [] leaf_walk_rcu+0x10/0xe0 RSP CR2: ffffc90001630024 Signed-off-by: Dave Forster Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- net/ipv4/fib_trie.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index d07fc076bea0..febca0f1008c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2452,9 +2452,7 @@ struct fib_route_iter { static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos) { - struct fib_table *tb = iter->main_tb; struct key_vector *l, **tp = &iter->tnode; - struct trie *t; t_key key; /* use cache location of next-to-find key */ @@ -2462,8 +2460,6 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, pos -= iter->pos; key = iter->key; } else { - t = (struct trie *)tb->tb_data; - iter->tnode = t->kv; iter->pos = 0; key = 0; } @@ -2504,12 +2500,12 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) return NULL; iter->main_tb = tb; + t = (struct trie *)tb->tb_data; + iter->tnode = t->kv; if (*pos != 0) return fib_route_get_idx(iter, *pos); - t = (struct trie *)tb->tb_data; - iter->tnode = t->kv; iter->pos = 0; iter->key = 0; -- cgit v1.2.3 From a5d0dc810abf3d6b241777467ee1d6efb02575fc Mon Sep 17 00:00:00 2001 From: Lance Richardson Date: Tue, 9 Aug 2016 15:29:42 -0400 Subject: vti: flush x-netns xfrm cache when vti interface is removed When executing the script included below, the netns delete operation hangs with the following message (repeated at 10 second intervals): kernel:unregister_netdevice: waiting for lo to become free. Usage count = 1 This occurs because a reference to the lo interface in the "secure" netns is still held by a dst entry in the xfrm bundle cache in the init netns. Address this problem by garbage collecting the tunnel netns flow cache when a cross-namespace vti interface receives a NETDEV_DOWN notification. A more detailed description of the problem scenario (referencing commands in the script below): (1) ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1 The vti_test interface is created in the init namespace. vti_tunnel_init() attaches a struct ip_tunnel to the vti interface's netdev_priv(dev), setting the tunnel net to &init_net. (2) ip link set vti_test netns secure The vti_test interface is moved to the "secure" netns. Note that the associated struct ip_tunnel still has tunnel->net set to &init_net. (3) ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1 The first packet sent using the vti device causes xfrm_lookup() to be called as follows: dst = xfrm_lookup(tunnel->net, skb_dst(skb), fl, NULL, 0); Note that tunnel->net is the init namespace, while skb_dst(skb) references the vti_test interface in the "secure" namespace. The returned dst references an interface in the init namespace. Also note that the first parameter to xfrm_lookup() determines which flow cache is used to store the computed xfrm bundle, so after xfrm_lookup() returns there will be a cached bundle in the init namespace flow cache with a dst referencing a device in the "secure" namespace. (4) ip netns del secure Kernel begins to delete the "secure" namespace. At some point the vti_test interface is deleted, at which point dst_ifdown() changes the dst->dev in the cached xfrm bundle flow from vti_test to lo (still in the "secure" namespace however). Since nothing has happened to cause the init namespace's flow cache to be garbage collected, this dst remains attached to the flow cache, so the kernel loops waiting for the last reference to lo to go away. ip link add br1 type bridge ip link set dev br1 up ip addr add dev br1 1.1.1.1/8 ip netns add secure ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1 ip link set vti_test netns secure ip netns exec secure ip link set vti_test up ip netns exec secure ip link s lo up ip netns exec secure ip addr add dev lo 192.168.100.1/24 ip netns exec secure ip route add 192.168.200.0/24 dev vti_test ip xfrm policy flush ip xfrm state flush ip xfrm policy add dir out tmpl src 1.1.1.1 dst 1.1.1.2 \ proto esp mode tunnel mark 1 ip xfrm policy add dir in tmpl src 1.1.1.2 dst 1.1.1.1 \ proto esp mode tunnel mark 1 ip xfrm state add src 1.1.1.1 dst 1.1.1.2 proto esp spi 1 \ mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788 ip xfrm state add src 1.1.1.2 dst 1.1.1.1 proto esp spi 1 \ mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788 ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1 ip netns del secure Reported-by: Hangbin Liu Reported-by: Jan Tluka Signed-off-by: Lance Richardson Signed-off-by: David S. Miller --- net/ipv4/ip_vti.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index a917903d5e97..cc701fa70b12 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -557,6 +557,33 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = { .get_link_net = ip_tunnel_get_link_net, }; +static bool is_vti_tunnel(const struct net_device *dev) +{ + return dev->netdev_ops == &vti_netdev_ops; +} + +static int vti_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct ip_tunnel *tunnel = netdev_priv(dev); + + if (!is_vti_tunnel(dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_DOWN: + if (!net_eq(tunnel->net, dev_net(dev))) + xfrm_garbage_collect(tunnel->net); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block vti_notifier_block __read_mostly = { + .notifier_call = vti_device_event, +}; + static int __init vti_init(void) { const char *msg; @@ -564,6 +591,8 @@ static int __init vti_init(void) pr_info("IPv4 over IPsec tunneling driver\n"); + register_netdevice_notifier(&vti_notifier_block); + msg = "tunnel device"; err = register_pernet_device(&vti_net_ops); if (err < 0) @@ -596,6 +625,7 @@ xfrm_proto_ah_failed: xfrm_proto_esp_failed: unregister_pernet_device(&vti_net_ops); pernet_dev_failed: + unregister_netdevice_notifier(&vti_notifier_block); pr_err("vti init: failed to register %s\n", msg); return err; } @@ -607,6 +637,7 @@ static void __exit vti_fini(void) xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); + unregister_netdevice_notifier(&vti_notifier_block); } module_init(vti_init); -- cgit v1.2.3 From 3d7b33209201cbfa090d614db993571ca3c6b090 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 15 Aug 2016 13:06:24 +0200 Subject: gre: set inner_protocol on xmit Ensure that the inner_protocol is set on transmit so that GSO segmentation, which relies on that field, works correctly. This is achieved by setting the inner_protocol in gre_build_header rather than each caller of that function. It ensures that the inner_protocol is set when gre_fb_xmit() is used to transmit GRE which was not previously the case. I have observed this is not the case when OvS transmits GRE using lwtunnel metadata (which it always does). Fixes: 38720352412a ("gre: Use inner_proto to obtain inner header protocol") Cc: Pravin Shelar Acked-by: Alexander Duyck Signed-off-by: Simon Horman Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/net/gre.h | 1 + net/ipv4/ip_gre.c | 1 - net/ipv6/ip6_gre.c | 2 -- 3 files changed, 1 insertion(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/gre.h b/include/net/gre.h index 7a54a31d1d4c..73ea256eb7d7 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -104,6 +104,7 @@ static inline void gre_build_header(struct sk_buff *skb, int hdr_len, skb_push(skb, hdr_len); + skb_set_inner_protocol(skb, proto); skb_reset_transport_header(skb); greh = (struct gre_base_hdr *)skb->data; greh->flags = gre_tnl_flags_to_gre_flags(flags); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5b1481be0282..113cc43df789 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -370,7 +370,6 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->parms.o_flags, proto, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - skb_set_inner_protocol(skb, proto); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 776d145113e1..704274cbd495 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -519,8 +519,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - skb_set_inner_protocol(skb, protocol); - return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, NEXTHDR_GRE); } -- cgit v1.2.3