9e33ce453f
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: [<ffffffff817b1ca5>] 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:[<ffffffff817b1ca5>] [<ffffffff817b1ca5>] 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] <IRQ> [ 579.784562] [ 579.784603] [<ffffffff817b26c7>] br_nf_forward_ip+0x275/0x2c8 [ 579.784707] [<ffffffff81704b58>] nf_iterate+0x47/0x7d [ 579.784797] [<ffffffff817ac32e>] ? br_dev_queue_push_xmit+0xae/0xae [ 579.784906] [<ffffffff81704bfb>] nf_hook_slow+0x6d/0x102 [ 579.784995] [<ffffffff817ac32e>] ? br_dev_queue_push_xmit+0xae/0xae [ 579.785175] [<ffffffff8187fa95>] ? _raw_write_unlock_bh+0x19/0x1b [ 579.785179] [<ffffffff817ac417>] __br_forward+0x97/0xa2 [ 579.785179] [<ffffffff817ad366>] br_handle_frame_finish+0x1a6/0x257 [ 579.785179] [<ffffffff817b2386>] br_nf_pre_routing_finish+0x26d/0x2cb [ 579.785179] [<ffffffff817b2cf0>] br_nf_pre_routing+0x55d/0x5c1 [ 579.785179] [<ffffffff81704b58>] nf_iterate+0x47/0x7d [ 579.785179] [<ffffffff817ad1c0>] ? br_handle_local_finish+0x44/0x44 [ 579.785179] [<ffffffff81704bfb>] nf_hook_slow+0x6d/0x102 [ 579.785179] [<ffffffff817ad1c0>] ? br_handle_local_finish+0x44/0x44 [ 579.785179] [<ffffffff81551525>] ? sky2_poll+0xb35/0xb54 [ 579.785179] [<ffffffff817ad62a>] br_handle_frame+0x213/0x229 [ 579.785179] [<ffffffff817ad417>] ? br_handle_frame_finish+0x257/0x257 [ 579.785179] [<ffffffff816e3b47>] __netif_receive_skb+0x2b4/0x3f1 [ 579.785179] [<ffffffff816e69fc>] process_backlog+0x99/0x1e2 [ 579.785179] [<ffffffff816e6800>] net_rx_action+0xdf/0x242 [ 579.785179] [<ffffffff8107e8a8>] __do_softirq+0xc1/0x1e0 [ 579.785179] [<ffffffff8135a5ba>] ? trace_hardirqs_off_thunk+0x3a/0x6c [ 579.785179] [<ffffffff8188812c>] 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 <mlin@ss.pku.edu.cn> Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> |
||
---|---|---|
.. | ||
9p | ||
bluetooth | ||
caif | ||
irda | ||
iucv | ||
netfilter | ||
netns | ||
nfc | ||
phonet | ||
sctp | ||
tc_act | ||
act_api.h | ||
addrconf.h | ||
af_ieee802154.h | ||
af_rxrpc.h | ||
af_unix.h | ||
ah.h | ||
arp.h | ||
atmclip.h | ||
ax25.h | ||
ax88796.h | ||
cfg80211-wext.h | ||
cfg80211.h | ||
checksum.h | ||
cipso_ipv4.h | ||
cls_cgroup.h | ||
codel.h | ||
compat.h | ||
datalink.h | ||
dcbevent.h | ||
dcbnl.h | ||
dn_dev.h | ||
dn_fib.h | ||
dn_neigh.h | ||
dn_nsp.h | ||
dn_route.h | ||
dn.h | ||
dsa.h | ||
dsfield.h | ||
dst_ops.h | ||
dst.h | ||
esp.h | ||
ethoc.h | ||
fib_rules.h | ||
flow_keys.h | ||
flow.h | ||
garp.h | ||
gen_stats.h | ||
genetlink.h | ||
gre.h | ||
icmp.h | ||
ieee80211_radiotap.h | ||
ieee802154_netdev.h | ||
ieee802154.h | ||
if_inet6.h | ||
inet6_connection_sock.h | ||
inet6_hashtables.h | ||
inet_common.h | ||
inet_connection_sock.h | ||
inet_ecn.h | ||
inet_frag.h | ||
inet_hashtables.h | ||
inet_sock.h | ||
inet_timewait_sock.h | ||
inetpeer.h | ||
ip6_checksum.h | ||
ip6_fib.h | ||
ip6_route.h | ||
ip6_tunnel.h | ||
ip_fib.h | ||
ip_vs.h | ||
ip.h | ||
ipcomp.h | ||
ipconfig.h | ||
ipip.h | ||
ipv6.h | ||
ipx.h | ||
iw_handler.h | ||
lapb.h | ||
lib80211.h | ||
llc_c_ac.h | ||
llc_c_ev.h | ||
llc_c_st.h | ||
llc_conn.h | ||
llc_if.h | ||
llc_pdu.h | ||
llc_s_ac.h | ||
llc_s_ev.h | ||
llc_s_st.h | ||
llc_sap.h | ||
llc.h | ||
mac80211.h | ||
mac802154.h | ||
mip6.h | ||
mld.h | ||
ndisc.h | ||
neighbour.h | ||
net_namespace.h | ||
net_ratelimit.h | ||
netdma.h | ||
netevent.h | ||
netlabel.h | ||
netlink.h | ||
netprio_cgroup.h | ||
netrom.h | ||
nexthop.h | ||
nl802154.h | ||
p8022.h | ||
ping.h | ||
pkt_cls.h | ||
pkt_sched.h | ||
protocol.h | ||
psnap.h | ||
raw.h | ||
rawv6.h | ||
red.h | ||
regulatory.h | ||
request_sock.h | ||
rose.h | ||
route.h | ||
rtnetlink.h | ||
sch_generic.h | ||
scm.h | ||
secure_seq.h | ||
slhc_vj.h | ||
snmp.h | ||
sock.h | ||
stp.h | ||
tcp_memcontrol.h | ||
tcp_states.h | ||
tcp.h | ||
timewait_sock.h | ||
transp_v6.h | ||
udp.h | ||
udplite.h | ||
wext.h | ||
wimax.h | ||
wpan-phy.h | ||
x25.h | ||
x25device.h | ||
xfrm.h |