Merge branch 'SO_PRIORITY'

Eric Dumazet says:

====================
tcp: provide correct skb->priority

SO_PRIORITY socket option requests TCP egress packets
to contain a user provided value.

TCP manages to send most packets with the requested values,
notably for TCP_ESTABLISHED state, but fails to do so for
few packets.

These packets are control packets sent on behalf
of SYN_RECV or TIME_WAIT states.

Note that to test this with packetdrill, it is a bit
of a hassle, since packetdrill can not verify priority
of egress packets, other than indirect observations,
using for example sch_prio on its tunnel device.

The bad skb priorities cause problems for GCP,
as this field is one of the keys used in routing.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 29 insertions, 17 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/include/net/ipv6.h b/include/net/ipv6.h
index 8dfc65639aa4..009605c56f20 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -981,7 +981,7 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
  *	upper-layer output functions
  */
 int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
-	     __u32 mark, struct ipv6_txoptions *opt, int tclass);
+	     __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority);
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr);
 
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 1b7381ff787b..25aab672fc99 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -230,7 +230,8 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
 		opt = ireq->ipv6_opt;
 		if (!opt)
 			opt = rcu_dereference(np->opt);
-		err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass);
+		err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass,
+			       sk->sk_priority);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -284,7 +285,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
 	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(skb, dst);
-		ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0);
+		ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0, 0);
 		DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
 		DCCP_INC_STATS(DCCP_MIB_OUTRSTS);
 		return;
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/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 4da24aa6c696..0a0945a5b30d 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -133,7 +133,7 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
 	fl6.daddr = sk->sk_v6_daddr;
 
 	res = ip6_xmit(sk, skb, &fl6, sk->sk_mark, rcu_dereference(np->opt),
-		       np->tclass);
+		       np->tclass,  sk->sk_priority);
 	rcu_read_unlock();
 	return res;
 }
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 89a4c7c2e25d..edadee4a7e76 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -193,7 +193,7 @@ bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
  * which are using proper atomic operations or spinlocks.
  */
 int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
-	     __u32 mark, struct ipv6_txoptions *opt, int tclass)
+	     __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority)
 {
 	struct net *net = sock_net(sk);
 	const struct ipv6_pinfo *np = inet6_sk(sk);
@@ -258,7 +258,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	hdr->daddr = *first_hop;
 
 	skb->protocol = htons(ETH_P_IPV6);
-	skb->priority = sk->sk_priority;
+	skb->priority = priority;
 	skb->mark = mark;
 
 	mtu = dst_mtu(dst);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 87f44d3250ee..e3d9f4559c99 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -512,7 +512,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 		opt = ireq->ipv6_opt;
 		if (!opt)
 			opt = rcu_dereference(np->opt);
-		err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass);
+		err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass,
+			       sk->sk_priority);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -803,7 +804,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq,
 				 u32 ack, u32 win, u32 tsval, u32 tsecr,
 				 int oif, struct tcp_md5sig_key *key, int rst,
-				 u8 tclass, __be32 label)
+				 u8 tclass, __be32 label, u32 priority)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 	struct tcphdr *t1;
@@ -907,7 +908,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(buff, dst);
-		ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass);
+		ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass,
+			 priority);
 		TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 		if (rst)
 			TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
@@ -930,6 +932,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 	struct sock *sk1 = NULL;
 #endif
 	__be32 label = 0;
+	u32 priority = 0;
 	struct net *net;
 	int oif = 0;
 
@@ -990,16 +993,19 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 			trace_tcp_send_reset(sk, skb);
 			if (np->repflow)
 				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);
 	}
 
 	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0,
-			     label);
+			     label, priority);
 
 #ifdef CONFIG_TCP_MD5SIG
 out:
@@ -1010,10 +1016,10 @@ out:
 static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq,
 			    u32 ack, u32 win, u32 tsval, u32 tsecr, int oif,
 			    struct tcp_md5sig_key *key, u8 tclass,
-			    __be32 label)
+			    __be32 label, u32 priority)
 {
 	tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
-			     tclass, label);
+			     tclass, label, priority);
 }
 
 static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
@@ -1025,7 +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));
+			tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority);
 
 	inet_twsk_put(tw);
 }
@@ -1048,7 +1054,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
 			req->ts_recent, sk->sk_bound_dev_if,
 			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr),
-			0, 0);
+			0, 0, sk->sk_priority);
 }
 
 
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e5f2fc726a98..dd860fea0148 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -215,7 +215,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 
 	rcu_read_lock();
 	res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt),
-		       tclass);
+		       tclass, sk->sk_priority);
 	rcu_read_unlock();
 	return res;
 }