net: tcp6: fix double call of tcp_v6_fill_cb()

tcp_v6_fill_cb() will be called twice if socket's state changes from
TCP_TIME_WAIT to TCP_LISTEN. That can result in control buffer data
corruption because in the second tcp_v6_fill_cb() call it's not copying
IP6CB(skb) anymore, but 'seq', 'end_seq', etc., so we can get weird and
unpredictable results. Performance loss of up to 1200% has been observed
in LTP/vxlan03 test.

This can be fixed by copying inet6_skb_parm to the beginning of 'cb'
only if xfrm6_policy_check() and tcp_v6_fill_cb() are going to be
called again.

Fixes: 2dc49d1680b53 ("tcp6: don't move IP6CB before xfrm6_policy_check()")

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/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b283a498f7a4d095f91e2442d5b1f8e78970680b..1f5e62229aaa8b4d5822f82c3af3a6c8b1382ba6 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1411,6 +1411,15 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
        TCP_SKB_CB(skb)->sacked = 0;
 }
 
+static void tcp_v6_restore_cb(struct sk_buff *skb)
+{
+       /* We need to move header back to the beginning if xfrm6_policy_check()
+        * and tcp_v6_fill_cb() are going to be called again.
+        */
+       memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
+               sizeof(struct inet6_skb_parm));
+}
+
 static int tcp_v6_rcv(struct sk_buff *skb)
 {
        const struct tcphdr *th;
@@ -1543,6 +1552,7 @@ do_time_wait:
                        inet_twsk_deschedule(tw, &tcp_death_row);
                        inet_twsk_put(tw);
                        sk = sk2;
+                       tcp_v6_restore_cb(skb);
                        goto process;
                }
                /* Fall through to ACK */
@@ -1551,6 +1561,7 @@ do_time_wait:
                tcp_v6_timewait_ack(sk, skb);
                break;
        case TCP_TW_RST:
+               tcp_v6_restore_cb(skb);
                goto no_tcp_socket;
        case TCP_TW_SUCCESS:
                ;