From 716362d00bff2312c0afffacbb9d4c9deb3faa96 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 29 Aug 2012 16:25:49 +0000 Subject: netfilter: nf_conntrack: fix racy timer handling with reliable events commit 5b423f6a40a0327f9d40bc8b97ce9be266f74368 upstream. Existing code assumes that del_timer returns true for alive conntrack entries. However, this is not true if reliable events are enabled. In that case, del_timer may return true for entries that were just inserted in the dying list. Note that packets / ctnetlink may hold references to conntrack entries that were just inserted to such list. This patch fixes the issue by adding an independent timer for event delivery. This increases the size of the ecache extension. Still we can revisit this later and use variable size extensions to allocate this area on demand. Tested-by: Oliver Smith Signed-off-by: Pablo Neira Ayuso Acked-by: David Miller Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_conntrack_ecache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 4283508..3a0feb1 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -18,6 +18,7 @@ struct nf_conntrack_ecache { u16 ctmask; /* bitmask of ct events to be delivered */ u16 expmask; /* bitmask of expect events to be delivered */ u32 pid; /* netlink pid of destroyer */ + struct timer_list timeout; }; static inline struct nf_conntrack_ecache * -- cgit v1.1 From 4b552154cccd5407bb02a7f17ed5a37939fd821e Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Sat, 7 Jul 2012 18:26:10 +0800 Subject: ipvs: fix oops on NAT reply in br_nf context commit 9e33ce453f8ac8452649802bee1f410319408f4b upstream. IPVS should not reset skb->nf_bridge in FORWARD hook by calling nf_reset for NAT replies. It triggers oops in br_nf_forward_finish. [ 579.781508] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004 [ 579.781669] IP: [] br_nf_forward_finish+0x58/0x112 [ 579.781792] PGD 218f9067 PUD 0 [ 579.781865] Oops: 0000 [#1] SMP [ 579.781945] CPU 0 [ 579.781983] Modules linked in: [ 579.782047] [ 579.782080] [ 579.782114] Pid: 4644, comm: qemu Tainted: G W 3.5.0-rc5-00006-g95e69f9 #282 Hewlett-Packard /30E8 [ 579.782300] RIP: 0010:[] [] br_nf_forward_finish+0x58/0x112 [ 579.782455] RSP: 0018:ffff88007b003a98 EFLAGS: 00010287 [ 579.782541] RAX: 0000000000000008 RBX: ffff8800762ead00 RCX: 000000000001670a [ 579.782653] RDX: 0000000000000000 RSI: 000000000000000a RDI: ffff8800762ead00 [ 579.782845] RBP: ffff88007b003ac8 R08: 0000000000016630 R09: ffff88007b003a90 [ 579.782957] R10: ffff88007b0038e8 R11: ffff88002da37540 R12: ffff88002da01a02 [ 579.783066] R13: ffff88002da01a80 R14: ffff88002d83c000 R15: ffff88002d82a000 [ 579.783177] FS: 0000000000000000(0000) GS:ffff88007b000000(0063) knlGS:00000000f62d1b70 [ 579.783306] CS: 0010 DS: 002b ES: 002b CR0: 000000008005003b [ 579.783395] CR2: 0000000000000004 CR3: 00000000218fe000 CR4: 00000000000027f0 [ 579.783505] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 579.783684] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 579.783795] Process qemu (pid: 4644, threadinfo ffff880021b20000, task ffff880021aba760) [ 579.783919] Stack: [ 579.783959] ffff88007693cedc ffff8800762ead00 ffff88002da01a02 ffff8800762ead00 [ 579.784110] ffff88002da01a02 ffff88002da01a80 ffff88007b003b18 ffffffff817b26c7 [ 579.784260] ffff880080000000 ffffffff81ef59f0 ffff8800762ead00 ffffffff81ef58b0 [ 579.784477] Call Trace: [ 579.784523] [ 579.784562] [ 579.784603] [] br_nf_forward_ip+0x275/0x2c8 [ 579.784707] [] nf_iterate+0x47/0x7d [ 579.784797] [] ? br_dev_queue_push_xmit+0xae/0xae [ 579.784906] [] nf_hook_slow+0x6d/0x102 [ 579.784995] [] ? br_dev_queue_push_xmit+0xae/0xae [ 579.785175] [] ? _raw_write_unlock_bh+0x19/0x1b [ 579.785179] [] __br_forward+0x97/0xa2 [ 579.785179] [] br_handle_frame_finish+0x1a6/0x257 [ 579.785179] [] br_nf_pre_routing_finish+0x26d/0x2cb [ 579.785179] [] br_nf_pre_routing+0x55d/0x5c1 [ 579.785179] [] nf_iterate+0x47/0x7d [ 579.785179] [] ? br_handle_local_finish+0x44/0x44 [ 579.785179] [] nf_hook_slow+0x6d/0x102 [ 579.785179] [] ? br_handle_local_finish+0x44/0x44 [ 579.785179] [] ? sky2_poll+0xb35/0xb54 [ 579.785179] [] br_handle_frame+0x213/0x229 [ 579.785179] [] ? br_handle_frame_finish+0x257/0x257 [ 579.785179] [] __netif_receive_skb+0x2b4/0x3f1 [ 579.785179] [] process_backlog+0x99/0x1e2 [ 579.785179] [] net_rx_action+0xdf/0x242 [ 579.785179] [] __do_softirq+0xc1/0x1e0 [ 579.785179] [] ? trace_hardirqs_off_thunk+0x3a/0x6c [ 579.785179] [] call_softirq+0x1c/0x30 The steps to reproduce as follow, 1. On Host1, setup brige br0(192.168.1.106) 2. Boot a kvm guest(192.168.1.105) on Host1 and start httpd 3. Start IPVS service on Host1 ipvsadm -A -t 192.168.1.106:80 -s rr ipvsadm -a -t 192.168.1.106:80 -r 192.168.1.105:80 -m 4. Run apache benchmark on Host2(192.168.1.101) ab -n 1000 http://192.168.1.106/ ip_vs_reply4 ip_vs_out handle_response ip_vs_notrack nf_reset() { skb->nf_bridge = NULL; } Actually, IPVS wants in this case just to replace nfct with untracked version. So replace the nf_reset(skb) call in ip_vs_notrack() with a nf_conntrack_put(skb->nfct) call. Signed-off-by: Lin Ming Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso Acked-by: David Miller Signed-off-by: Greg Kroah-Hartman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 481f856..15b62bb 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1361,7 +1361,7 @@ static inline void ip_vs_notrack(struct sk_buff *skb) struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (!ct || !nf_ct_is_untracked(ct)) { - nf_reset(skb); + nf_conntrack_put(skb->nfct); skb->nfct = &nf_ct_untracked_get()->ct_general; skb->nfctinfo = IP_CT_NEW; nf_conntrack_get(skb->nfct); -- cgit v1.1