From: Shaohua Li <s...@fb.com>
Please see below tcpdump output:
21:00:48.109122 IP6 (flowlabel 0x43304, hlim 64, next-header TCP (6) payload
length: 40) fec0::5054:ff:fe12:3456.55804 > fec0::5054:ff:fe12:3456.5555: Flags
[S], cksum 0x0529 (incorrect -> 0xf56c), seq 3282214508, win 43690, options
[mss 65476,sackOK,TS val 2500903437 ecr 0,nop,wscale 7], length 0
21:00:48.109381 IP6 (flowlabel 0xd827f, hlim 64, next-header TCP (6) payload
length: 40) fec0::5054:ff:fe12:3456.5555 > fec0::5054:ff:fe12:3456.55804: Flags
[S.], cksum 0x0529 (incorrect -> 0x49ad), seq 1923801573, ack 3282214509, win
43690, options [mss 65476,sackOK,TS val 2500903437 ecr 2500903437,nop,wscale
7], length 0
21:00:48.109548 IP6 (flowlabel 0x43304, hlim 64, next-header TCP (6) payload
length: 32) fec0::5054:ff:fe12:3456.55804 > fec0::5054:ff:fe12:3456.5555: Flags
[.], cksum 0x0521 (incorrect -> 0x1bdf), seq 1, ack 1, win 342, options
[nop,nop,TS val 2500903437 ecr 2500903437], length 0
21:00:48.109823 IP6 (flowlabel 0x43304, hlim 64, next-header TCP (6) payload
length: 62) fec0::5054:ff:fe12:3456.55804 > fec0::5054:ff:fe12:3456.5555: Flags
[P.], cksum 0x053f (incorrect -> 0xb8b1), seq 1:31, ack 1, win 342, options
[nop,nop,TS val 2500903437 ecr 2500903437], length 30
21:00:48.109910 IP6 (flowlabel 0xd827f, hlim 64, next-header TCP (6) payload
length: 32) fec0::5054:ff:fe12:3456.5555 > fec0::5054:ff:fe12:3456.55804: Flags
[.], cksum 0x0521 (incorrect -> 0x1bc1), seq 1, ack 31, win 342, options
[nop,nop,TS val 2500903437 ecr 2500903437], length 0
21:00:48.110043 IP6 (flowlabel 0xd827f, hlim 64, next-header TCP (6) payload
length: 56) fec0::5054:ff:fe12:3456.5555 > fec0::5054:ff:fe12:3456.55804: Flags
[P.], cksum 0x0539 (incorrect -> 0xb726), seq 1:25, ack 31, win 342, options
[nop,nop,TS val 2500903438 ecr 2500903437], length 24
21:00:48.110173 IP6 (flowlabel 0x43304, hlim 64, next-header TCP (6) payload
length: 32) fec0::5054:ff:fe12:3456.55804 > fec0::5054:ff:fe12:3456.5555: Flags
[.], cksum 0x0521 (incorrect -> 0x1ba7), seq 31, ack 25, win 342, options
[nop,nop,TS val 2500903438 ecr 2500903438], length 0
21:00:48.110211 IP6 (flowlabel 0xd827f, hlim 64, next-header TCP (6) payload
length: 32) fec0::5054:ff:fe12:3456.5555 > fec0::5054:ff:fe12:3456.55804: Flags
[F.], cksum 0x0521 (incorrect -> 0x1ba7), seq 25, ack 31, win 342, options
[nop,nop,TS val 2500903438 ecr 2500903437], length 0
21:00:48.151099 IP6 (flowlabel 0x43304, hlim 64, next-header TCP (6) payload
length: 32) fec0::5054:ff:fe12:3456.55804 > fec0::5054:ff:fe12:3456.5555: Flags
[.], cksum 0x0521 (incorrect -> 0x1ba6), seq 31, ack 26, win 342, options
[nop,nop,TS val 2500903438 ecr 2500903438], length 0
21:00:49.110524 IP6 (flowlabel 0x43304, hlim 64, next-header TCP (6) payload
length: 56) fec0::5054:ff:fe12:3456.55804 > fec0::5054:ff:fe12:3456.5555: Flags
[P.], cksum 0x0539 (incorrect -> 0xb324), seq 31:55, ack 26, win 342, options
[nop,nop,TS val 2500904438 ecr 2500903438], length 24
21:00:49.110637 IP6 (flowlabel 0xb34d5, hlim 64, next-header TCP (6) payload
length: 20) fec0::5054:ff:fe12:3456.5555 > fec0::5054:ff:fe12:3456.55804: Flags
[R], cksum 0x0515 (incorrect -> 0x668c), seq 1923801599, win 0, length 0
The tcp reset packet has a different flowlabel, which causes our router
doesn't correctly close tcp connection. The reason is the normal packet
gets the skb->hash from sk->sk_txhash, which is generated randomly.
ip6_make_flowlabel then uses the hash to create a flowlabel. The reset
packet doesn't get assigned a hash, so the flowlabel is calculated with
flowi6.
The solution is to save the hash value for timeout sock and use it for
reset packet.
Signed-off-by: Shaohua Li <s...@fb.com>
---
include/net/inet_timewait_sock.h | 10 ++++++++++
net/ipv4/inet_timewait_sock.c | 1 +
net/ipv6/tcp_ipv6.c | 7 +++++++
3 files changed, 18 insertions(+)
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 6a75d67..b568224 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -77,6 +77,7 @@ struct inet_timewait_sock {
tw_pad : 2, /* 2 bits hole */
tw_tos : 8;
kmemcheck_bitfield_end(flags);
+ __u32 tw_txhash;
struct timer_list tw_timer;
struct inet_bind_bucket *tw_tb;
};
@@ -87,6 +88,15 @@ static inline struct inet_timewait_sock *inet_twsk(const
struct sock *sk)
return (struct inet_timewait_sock *)sk;
}
+static inline void skb_set_hash_from_twsk(struct sk_buff *skb,
+ struct inet_timewait_sock *twsk)
+{
+ if (twsk->tw_txhash) {
+ skb->l4_hash = 1;
+ skb->hash = twsk->tw_txhash;
+ }
+}
+
void inet_twsk_free(struct inet_timewait_sock *tw);
void inet_twsk_put(struct inet_timewait_sock *tw);
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 5b03915..6f460e7 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -190,6 +190,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct
sock *sk,
twsk_net_set(tw, sock_net(sk));
setup_pinned_timer(&tw->tw_timer, tw_timer_handler,
(unsigned long)tw);
+ tw->tw_txhash = sk->sk_txhash;
/*
* Because we use RCU lookups, we should not set tw_refcnt
* to a non null value before everything is setup for this
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 2521690..2e656d2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -805,6 +805,13 @@ static void tcp_v6_send_response(const struct sock *sk,
struct sk_buff *skb, u32
t1 = skb_push(buff, tot_len);
skb_reset_transport_header(buff);
+ if (sk) {
+ if (sk_fullsock(sk))
+ skb_set_hash_from_sk(buff, (struct sock *)sk);
+ else
+ skb_set_hash_from_twsk(buff, inet_twsk(sk));
+ }
+
/* Swap the send and the receive. */
memset(t1, 0, sizeof(*t1));
t1->dest = th->source;
--
2.9.3
