ipv4: tcp: fix TOS value in ACK messages sent from TIME_WAIT

There is a long standing bug in linux tcp stack, about ACK messages sent
on behalf of TIME_WAIT sockets.

In the IP header of the ACK message, we choose to reflect TOS field of
incoming message, and this might break some setups.

Example of things that were broken :
  - Routing using TOS as a selector
  - Firewalls
  - Trafic classification / shaping

We now remember in timewait structure the inet tos field and use it in
ACK generation, and route lookup.

Notes :
 - We still reflect incoming TOS in RST messages.
 - We could extend MuraliRaja Muniraju patch to report TOS value in
netlink messages for TIME_WAIT sockets.
 - A patch is needed for IPv6

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 7 insertions, 4 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1dad7e92f005..0ea10eefa60f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -652,6 +652,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
         arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
 
         net = dev_net(skb_dst(skb)->dev);
+        arg.tos = ip_hdr(skb)->tos;
         ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
                       &arg, arg.iov[0].iov_len);
 
@@ -666,7 +667,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
                             u32 win, u32 ts, int oif,
                             struct tcp_md5sig_key *key,
-                            int reply_flags)
+                            int reply_flags, u8 tos)
 {
         const struct tcphdr *th = tcp_hdr(skb);
         struct {
@@ -726,7 +727,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
         arg.csumoffset = offsetof(struct tcphdr, check) / 2;
         if (oif)
                 arg.bound_dev_if = oif;
-
+        arg.tos = tos;
         ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
                       &arg, arg.iov[0].iov_len);
 
@@ -743,7 +744,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
                         tcptw->tw_ts_recent,
                         tw->tw_bound_dev_if,
                         tcp_twsk_md5_key(tcptw),
-                        tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0
+                        tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0,
+                        tw->tw_tos
                         );
 
         inet_twsk_put(tw);
@@ -757,7 +759,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
                         req->ts_recent,
                         0,
                         tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr),
-                        inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0);
+                        inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
+                        ip_hdr(skb)->tos);
 }
 
 /*