Commit d095c462 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'tcp-add-tos-reflection-feature' 



Wei Wang says:

====================
tcp: add tos reflection feature

This patch series adds a new tcp feature to reflect TOS value received in
SYN, and send it out in SYN-ACK, and eventually set the TOS value of the
established socket with this reflected TOS value. This provides a way to
set the traffic class/QoS level for all traffic in the same connection
to be the same as the incoming SYN. It could be useful for datacenters
to provide equivalent QoS according to the incoming request.
This feature is guarded by /proc/sys/net/ipv4/tcp_reflect_tos, and is by
default turned off.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 3a8c4ad1 ac8f1710

include/linux/tcp.h

+1 −0
Original line number Diff line number Diff line
@@ -134,6 +134,7 @@ struct tcp_request_sock { 
						  * FastOpen it's the seq#

						  * after data-in-SYN.

						  */

	u8				syn_tos;

};



static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)

include/net/ip.h

+1 −1
Original line number Diff line number Diff line
@@ -151,7 +151,7 @@ int igmp_mc_init(void); 


int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,

			  __be32 saddr, __be32 daddr,

			  struct ip_options_rcu *opt);

			  struct ip_options_rcu *opt, u8 tos);

int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,

	   struct net_device *orig_dev);

void ip_list_rcv(struct list_head *head, struct packet_type *pt,

include/net/netns/ipv4.h

+1 −0
Original line number Diff line number Diff line
@@ -183,6 +183,7 @@ struct netns_ipv4 { 
	unsigned int sysctl_tcp_fastopen_blackhole_timeout;

	atomic_t tfo_active_disable_times;

	unsigned long tfo_active_disable_stamp;

	int sysctl_tcp_reflect_tos;



	int sysctl_udp_wmem_min;

	int sysctl_udp_rmem_min;

net/dccp/ipv4.c

+4 −2
Original line number Diff line number Diff line
@@ -495,7 +495,8 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req 
		rcu_read_lock();

		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,

					    ireq->ir_rmt_addr,

					    rcu_dereference(ireq->ireq_opt));

					    rcu_dereference(ireq->ireq_opt),

					    inet_sk(sk)->tos);

		rcu_read_unlock();

		err = net_xmit_eval(err);

	}
@@ -537,7 +538,8 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) 
	local_bh_disable();

	bh_lock_sock(ctl_sk);

	err = ip_build_and_send_pkt(skb, ctl_sk,

				    rxiph->daddr, rxiph->saddr, NULL);

				    rxiph->daddr, rxiph->saddr, NULL,

				    inet_sk(ctl_sk)->tos);

	bh_unlock_sock(ctl_sk);



	if (net_xmit_eval(err) == 0) {

net/ipv4/ip_output.c

+3 −2
Original line number Diff line number Diff line
@@ -142,7 +142,8 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) 
 *

 */

int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,

			  __be32 saddr, __be32 daddr, struct ip_options_rcu *opt)

			  __be32 saddr, __be32 daddr, struct ip_options_rcu *opt,

			  u8 tos)

{

	struct inet_sock *inet = inet_sk(sk);

	struct rtable *rt = skb_rtable(skb);
@@ -155,7 +156,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, 
	iph = ip_hdr(skb);

	iph->version  = 4;

	iph->ihl      = 5;

	iph->tos      = inet->tos;

	iph->tos      = tos;

	iph->ttl      = ip_select_ttl(inet, &rt->dst);

	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);

	iph->saddr    = saddr;

CRA Git | Maintained and supported by SUSTech CRA and CCSE