tcp: honour SO_BINDTODEVICE for TW_RST case too

Hannes points out that when we generate tcp reset for timewait sockets we
pretend we found no socket and pass NULL sk to tcp_vX_send_reset().

Make it cope with inet tw sockets and then provide tw sk.

This makes RSTs appear on correct interface when SO_BINDTODEVICE is used.

Packetdrill test case:
// want default route to be used, we rely on BINDTODEVICE
`ip route del 192.0.2.0/24 via 192.168.0.2 dev tun0`

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
// test case still works due to BINDTODEVICE
0.001 setsockopt(3, SOL_SOCKET, SO_BINDTODEVICE, "tun0", 4) = 0
0.100...0.200 connect(3, ..., ...) = 0

0.100 > S 0:0(0) <mss 1460,sackOK,nop,nop>
0.200 < S. 0:0(0) ack 1 win 32792 <mss 1460,sackOK,nop,nop>
0.200 > . 1:1(0) ack 1

0.210 close(3) = 0

0.210 > F. 1:1(0) ack 1 win 29200
0.300 < . 1:1(0) ack 2 win 46

// more data while in FIN_WAIT2, expect RST
1.300 < P. 1:1001(1000) ack 1 win 46

// fails without this change -- default route is used
1.301 > R 1:1(0) win 0

Reported-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index eb29c2f5bcea21b411437773e0a349d430eb5ebc..fc4f7268670504486d7ab2cab0ea20d6d01e68d4 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -627,7 +627,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
        net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
 #ifdef CONFIG_TCP_MD5SIG
        hash_location = tcp_parse_md5sig_option(th);
-       if (sk) {
+       if (sk && sk_fullsock(sk)) {
                key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)
                                        &ip_hdr(skb)->saddr, AF_INET);
        } else if (hash_location) {
@@ -674,7 +674,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
                                      ip_hdr(skb)->saddr, /* XXX */
                                      arg.iov[0].iov_len, IPPROTO_TCP, 0);
        arg.csumoffset = offsetof(struct tcphdr, check) / 2;
-       arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
+       arg.flags = (sk && inet_sk_transparent(sk)) ? IP_REPLY_ARG_NOSRCCHECK : 0;
+
        /* When socket is gone, all binding information is lost.
         * routing might fail in this case. No choice here, if we choose to force
         * input interface, we will misroute in case of asymmetric route.
@@ -682,6 +683,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
        if (sk)
                arg.bound_dev_if = sk->sk_bound_dev_if;
 
+       BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
+                    offsetof(struct inet_timewait_sock, tw_bound_dev_if));
+
        arg.tos = ip_hdr(skb)->tos;
        ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
                              skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -1705,7 +1709,9 @@ do_time_wait:
                tcp_v4_timewait_ack(sk, skb);
                break;
        case TCP_TW_RST:
-               goto no_tcp_socket;
+               tcp_v4_send_reset(sk, skb);
+               inet_twsk_deschedule_put(inet_twsk(sk));
+               goto discard_it;
        case TCP_TW_SUCCESS:;
        }
        goto discard_it;

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ac6b1961ffeb32a40b662300aebee4ba182ce31a..75632a92582425db63f1078c223cbd54a91fa0c3 100644 (file)
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -131,7 +131,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
                        goto kill;
 
                if (th->syn && !before(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt))
-                       goto kill_with_rst;
+                       return TCP_TW_RST;
 
                /* Dup ACK? */
                if (!th->ack ||
@@ -145,11 +145,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
                 * reset.
                 */
                if (!th->fin ||
-                   TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) {
-kill_with_rst:
-                       inet_twsk_deschedule_put(tw);
+                   TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1)
                        return TCP_TW_RST;
-               }
 
                /* FIN arrived, enter true time-wait state. */
                tw->tw_substate   = TCP_TIME_WAIT;

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 32fa0de9982a2d4f469b3e3179d48f2e498bb926..9ecb012291cf13a14ca83fb065444902ff3a590f 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -854,7 +854,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_TCP_MD5SIG
        hash_location = tcp_parse_md5sig_option(th);
-       if (sk) {
+       if (sk && sk_fullsock(sk)) {
                key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr);
        } else if (hash_location) {
                /*
@@ -1516,7 +1516,9 @@ do_time_wait:
                break;
        case TCP_TW_RST:
                tcp_v6_restore_cb(skb);
-               goto no_tcp_socket;
+               tcp_v6_send_reset(sk, skb);
+               inet_twsk_deschedule_put(inet_twsk(sk));
+               goto discard_it;
        case TCP_TW_SUCCESS:
                ;
        }