tcp: setup timestamp offset when write_seq already set

Found that when randomized tcp offsets are enabled (by default)
TCP client can still start new connections without them. Later,
if server does active close and re-uses sockets in TIME-WAIT
state, new SYN from client can be rejected on PAWS check inside
tcp_timewait_state_process(), because either tw_ts_recent or
rcv_tsval doesn't really have an offset set.

Here is how to reproduce it with LTP netstress tool:
    netstress -R 1 &
    netstress -H 127.0.0.1 -lr 1000000 -a1

    [...]
    < S  seq 1956977072 win 43690 TS val 295618 ecr 459956970
    > .  ack 1956911535 win 342 TS val 459967184 ecr 1547117608
    < R  seq 1956911535 win 0 length 0
+1. < S  seq 1956977072 win 43690 TS val 296640 ecr 459956970
    > S. seq 657450664 ack 1956977073 win 43690 TS val 459968205 ecr 296640

Fixes: 95a22caee396 ("tcp: randomize tcp timestamp offsets for each connection")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8c124d4..9a89b8d 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -145,6 +145,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
        struct flowi4 *fl4;
        struct rtable *rt;
        int err;
+       u32 seq;
        struct ip_options_rcu *inet_opt;
        struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
@@ -234,12 +235,15 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
        sk_setup_caps(sk, &rt->dst);
        rt = NULL;
 
-       if (!tp->write_seq && likely(!tp->repair))
-               tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr,
-                                                          inet->inet_daddr,
-                                                          inet->inet_sport,
-                                                          usin->sin_port,
-                                                          &tp->tsoffset);
+       if (likely(!tp->repair)) {
+               seq = secure_tcp_sequence_number(inet->inet_saddr,
+                                                inet->inet_daddr,
+                                                inet->inet_sport,
+                                                usin->sin_port,
+                                                &tp->tsoffset);
+               if (!tp->write_seq)
+                       tp->write_seq = seq;
+       }
 
        inet->inet_id = tp->write_seq ^ jiffies;
 

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 21c7199..60a5295 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -122,6 +122,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
        struct flowi6 fl6;
        struct dst_entry *dst;
        int addr_type;
+       u32 seq;
        int err;
        struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
@@ -285,12 +286,15 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
        sk_set_txhash(sk);
 
-       if (!tp->write_seq && likely(!tp->repair))
-               tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
-                                                            sk->sk_v6_daddr.s6_addr32,
-                                                            inet->inet_sport,
-                                                            inet->inet_dport,
-                                                            &tp->tsoffset);
+       if (likely(!tp->repair)) {
+               seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
+                                                  sk->sk_v6_daddr.s6_addr32,
+                                                  inet->inet_sport,
+                                                  inet->inet_dport,
+                                                  &tp->tsoffset);
+               if (!tp->write_seq)
+                       tp->write_seq = seq;
+       }
 
        if (tcp_fastopen_defer_connect(sk, &err))
                return err;