tcp: honor SO_PRIORITY in TIME_WAIT state

ctl packets sent on behalf of TIME_WAIT sockets currently
have a zero skb->priority, which can cause various problems.

In this patch we :

- add a tw_priority field in struct inet_timewait_sock.

- populate it from sk->sk_priority when a TIME_WAIT is created.

- For IPv4, change ip_send_unicast_reply() and its two
  callers to propagate tw_priority correctly.
  ip_send_unicast_reply() no longer changes sk->sk_priority.

- For IPv6, make sure TIME_WAIT sockets pass their tw_priority
  field to tcp_v6_send_response() and tcp_v6_send_ack().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 10 insertions, 3 deletions

diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index aef38c140014..dfd919b3119e 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -71,6 +71,7 @@ struct inet_timewait_sock {
 				tw_pad		: 2,	/* 2 bits hole */
 				tw_tos		: 8;
 	u32			tw_txhash;
+	u32			tw_priority;
 	struct timer_list	tw_timer;
 	struct inet_bind_bucket	*tw_tb;
 };
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a77c3a4c24de..28fca408812c 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1694,7 +1694,6 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 
 	inet_sk(sk)->tos = arg->tos;
 
-	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
 	sk->sk_sndbuf = sysctl_wmem_default;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fd394ad179a0..2ee45e3755e9 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -771,6 +771,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	if (sk) {
 		ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 				   inet_twsk(sk)->tw_mark : sk->sk_mark;
+		ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
+				   inet_twsk(sk)->tw_priority : sk->sk_priority;
 		transmit_time = tcp_transmit_time(sk);
 	}
 	ip_send_unicast_reply(ctl_sk,
@@ -866,6 +868,8 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	ctl_sk = this_cpu_read(*net->ipv4.tcp_sk);
 	ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 			   inet_twsk(sk)->tw_mark : sk->sk_mark;
+	ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
+			   inet_twsk(sk)->tw_priority : sk->sk_priority;
 	transmit_time = tcp_transmit_time(sk);
 	ip_send_unicast_reply(ctl_sk,
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 8bcaf2586b68..bb140a5db8c0 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -266,6 +266,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 
 		tw->tw_transparent	= inet->transparent;
 		tw->tw_mark		= sk->sk_mark;
+		tw->tw_priority		= sk->sk_priority;
 		tw->tw_rcv_wscale	= tp->rx_opt.rcv_wscale;
 		tcptw->tw_rcv_nxt	= tp->rcv_nxt;
 		tcptw->tw_snd_nxt	= tp->snd_nxt;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5f557bf27da2..e3d9f4559c99 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -995,8 +995,10 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 				label = ip6_flowlabel(ipv6h);
 			priority = sk->sk_priority;
 		}
-		if (sk->sk_state == TCP_TIME_WAIT)
+		if (sk->sk_state == TCP_TIME_WAIT) {
 			label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel);
+			priority = inet_twsk(sk)->tw_priority;
+		}
 	} else {
 		if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_TCP_RESET)
 			label = ip6_flowlabel(ipv6h);
@@ -1029,7 +1031,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp_raw() + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
-			tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), 0);
+			tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority);
 
 	inet_twsk_put(tw);
 }