Commit 4e1e83be authored by David S. Miller's avatar David S. Miller
Browse files

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: default avatarDavid S. Miller <davem@davemloft.net>
parents 2b6fd3ea f6c0f5d2

include/net/inet_timewait_sock.h

+1 −0
Original line number Diff line number Diff line
@@ -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;

};

include/net/ipv6.h

+1 −1
Original line number Diff line number Diff line
@@ -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);

net/dccp/ipv6.c

+3 −2
Original line number Diff line number Diff line
@@ -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;

net/ipv4/ip_output.c

+0 −1
Original line number Diff line number Diff line
@@ -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;

net/ipv4/tcp_ipv4.c

+4 −0
Original line number Diff line number Diff line
@@ -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,

CRA Git | Maintained and supported by SUSTech CRA and CCSE