netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v2] tcp: split tcp_ecn sysctl knob to distinguish between IPv4 and IPv6
@ 2013-01-03  0:00 Hannes Frederic Sowa
  2013-01-03 12:28 ` Hannes Frederic Sowa
  2013-01-03 12:47 ` Eric Dumazet
  0 siblings, 2 replies; 10+ messages in thread
From: Hannes Frederic Sowa @ 2013-01-03  0:00 UTC (permalink / raw)
  To: netdev

ECN could be more reliable when used with IPv6 (I don't have proofs). For
people who want to try ECN with IPv6 but still have problems connecting
to destinations because of broken IPv4 routers this switch allows one
to enable ECN just for IPv6.

Perhaps ECN could be enabled by default in future.

No code changes since initial submission, just added documentation.

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
 Documentation/networking/ip-sysctl.txt | 28 +++++++++++++++++++++-------
 include/net/sock.h                     |  1 +
 include/net/tcp.h                      |  8 +++++---
 net/ipv4/syncookies.c                  |  6 ++++--
 net/ipv4/sysctl_net_ipv4.c             |  2 +-
 net/ipv4/tcp_input.c                   |  2 --
 net/ipv4/tcp_ipv4.c                    |  3 ++-
 net/ipv4/tcp_output.c                  |  2 +-
 net/ipv6/syncookies.c                  |  3 ++-
 net/ipv6/sysctl_net_ipv6.c             |  8 ++++++++
 net/ipv6/tcp_ipv6.c                    |  4 +++-
 11 files changed, 48 insertions(+), 19 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ac1710e..974fc2b 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -207,11 +207,11 @@ tcp_early_retrans - INTEGER
 	Default: 2
 
 tcp_ecn - INTEGER
-	Control use of Explicit Congestion Notification (ECN) by TCP.
-	ECN is used only when both ends of the TCP connection indicate
-	support for it.  This feature is useful in avoiding losses due
-	to congestion by allowing supporting routers to signal
-	congestion before having to drop packets.
+	Control use of Explicit Congestion Notification (ECN) by TCP
+	over IPv4.  ECN is used only when both ends of the TCP
+	connection indicate support for it.  This feature is useful in
+	avoiding losses due to congestion by allowing supporting
+	routers to signal congestion before having to drop packets.
 	Possible values are:
 		0 Disable ECN.  Neither initiate nor accept ECN.
 		1 Always request ECN on outgoing connection attempts.
@@ -1065,8 +1065,9 @@ delon.nicolas@wanadoo.fr
 
 /proc/sys/net/ipv6/* Variables:
 
-IPv6 has no global variables such as tcp_*.  tcp_* settings under ipv4/ also
-apply to IPv6 [XXX?].
+IPv6 has no global variables such as tcp_*.  Most tcp_* settings under
+ipv4/ also apply to IPv6 (currently the only exception is tcp_ecn)
+[XXX?].
 
 bindv6only - BOOLEAN
 	Default value for IPV6_V6ONLY socket option,
@@ -1077,6 +1078,19 @@ bindv6only - BOOLEAN
 
 	Default: FALSE (as specified in RFC3493)
 
+tcp_ecn - INTEGER
+	Control use of Explicit Congestion Notification (ECN) by TCP
+	over IPv6.  ECN is used only when both ends of the TCP
+	connection indicate support for it.  This feature is useful in
+	avoiding losses due to congestion by allowing supporting
+	routers to signal congestion before having to drop packets.
+	Possible values are:
+		0 Disable ECN.  Neither initiate nor accept ECN.
+		1 Always request ECN on outgoing connection attempts.
+		2 Enable ECN when requested by incomming connections
+		  but do not request ECN on outgoing connections.
+	Default: 2
+
 IPv6 Fragmentation:
 
 ip6frag_high_thresh - INTEGER
diff --git a/include/net/sock.h b/include/net/sock.h
index 182ca99..aa3c30e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -944,6 +944,7 @@ struct proto {
 	int			*sysctl_rmem;
 	int			max_header;
 	bool			no_autobind;
+	int			ecn;
 
 	struct kmem_cache	*slab;
 	unsigned int		obj_size;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index aed42c7..1202a6d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -266,7 +266,6 @@ extern int sysctl_tcp_abort_on_overflow;
 extern int sysctl_tcp_max_orphans;
 extern int sysctl_tcp_fack;
 extern int sysctl_tcp_reordering;
-extern int sysctl_tcp_ecn;
 extern int sysctl_tcp_dsack;
 extern int sysctl_tcp_wmem[3];
 extern int sysctl_tcp_rmem[3];
@@ -351,6 +350,7 @@ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
 }
 
 extern struct proto tcp_prot;
+extern struct proto tcpv6_prot;
 
 #define TCP_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.tcp_statistics, field)
 #define TCP_INC_STATS_BH(net, field)	SNMP_INC_STATS_BH((net)->mib.tcp_statistics, field)
@@ -504,7 +504,8 @@ static inline __u32 cookie_v4_init_sequence(struct sock *sk,
 #endif
 
 extern __u32 cookie_init_timestamp(struct request_sock *req);
-extern bool cookie_check_timestamp(struct tcp_options_received *opt, bool *);
+extern bool cookie_check_timestamp(struct tcp_options_received *opt,
+				int sysctl_tcp_ecn, bool *ecn_ok);
 
 /* From net/ipv6/syncookies.c */
 extern struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
@@ -728,7 +729,8 @@ struct tcp_skb_cb {
  * notifications, we disable TCP ECN negociation.
  */
 static inline void
-TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb)
+TCP_ECN_create_request(struct request_sock *req,
+		const struct sk_buff *skb, int sysctl_tcp_ecn)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index b236ef0..64dbfc5 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -232,7 +232,8 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
  *
  * return false if we decode an option that should not be.
  */
-bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, bool *ecn_ok)
+bool cookie_check_timestamp(struct tcp_options_received *tcp_opt,
+			int sysctl_tcp_ecn, bool *ecn_ok)
 {
 	/* echoed timestamp, lowest bits contain options */
 	u32 options = tcp_opt->rcv_tsecr & TSMASK;
@@ -278,6 +279,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	struct rtable *rt;
 	__u8 rcv_wscale;
 	bool ecn_ok = false;
+	int sysctl_tcp_ecn = sk->sk_prot->ecn;
 	struct flowi4 fl4;
 
 	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
@@ -295,7 +297,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
 	tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
 
-	if (!cookie_check_timestamp(&tcp_opt, &ecn_ok))
+	if (!cookie_check_timestamp(&tcp_opt, sysctl_tcp_ecn, &ecn_ok))
 		goto out;
 
 	ret = NULL;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d84400b..f7aac98 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -539,7 +539,7 @@ static struct ctl_table ipv4_table[] = {
 	},
 	{
 		.procname	= "tcp_ecn",
-		.data		= &sysctl_tcp_ecn,
+		.data		= &tcp_prot.ecn,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a28e4db..38e1184 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -81,8 +81,6 @@ int sysctl_tcp_sack __read_mostly = 1;
 int sysctl_tcp_fack __read_mostly = 1;
 int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
 EXPORT_SYMBOL(sysctl_tcp_reordering);
-int sysctl_tcp_ecn __read_mostly = 2;
-EXPORT_SYMBOL(sysctl_tcp_ecn);
 int sysctl_tcp_dsack __read_mostly = 1;
 int sysctl_tcp_app_win __read_mostly = 31;
 int sysctl_tcp_adv_win_scale __read_mostly = 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 54139fa..32e012a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1568,7 +1568,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	if (!want_cookie || tmp_opt.tstamp_ok)
-		TCP_ECN_create_request(req, skb);
+		TCP_ECN_create_request(req, skb, tcp_prot.ecn);
 
 	if (want_cookie) {
 		isn = cookie_v4_init_sequence(sk, skb, &req->mss);
@@ -2874,6 +2874,7 @@ struct proto tcp_prot = {
 	.rsk_prot		= &tcp_request_sock_ops,
 	.h.hashinfo		= &tcp_hashinfo,
 	.no_autobind		= true,
+	.ecn			= 2,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt	= compat_tcp_setsockopt,
 	.compat_getsockopt	= compat_tcp_getsockopt,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5d45159..0c75961 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -314,7 +314,7 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	tp->ecn_flags = 0;
-	if (sysctl_tcp_ecn == 1) {
+	if (sk->sk_prot->ecn == 1) {
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
 		tp->ecn_flags = TCP_ECN_OK;
 	}
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 4016197..ce19227 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -163,6 +163,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	struct dst_entry *dst;
 	__u8 rcv_wscale;
 	bool ecn_ok = false;
+	int sysctl_tcp_ecn = sk->sk_prot->ecn;
 
 	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
@@ -179,7 +180,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
 	tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
 
-	if (!cookie_check_timestamp(&tcp_opt, &ecn_ok))
+	if (!cookie_check_timestamp(&tcp_opt, sysctl_tcp_ecn, &ecn_ok))
 		goto out;
 
 	ret = NULL;
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index e85c48b..a2e764f 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -15,6 +15,7 @@
 #include <net/ipv6.h>
 #include <net/addrconf.h>
 #include <net/inet_frag.h>
+#include <net/tcp.h>
 
 static ctl_table ipv6_table_template[] = {
 	{
@@ -24,6 +25,13 @@ static ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tcp_ecn",
+		.data		= &tcpv6_prot.ecn,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 	{ }
 };
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 93825dd..98bd8a3 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1027,7 +1027,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	treq->rmt_addr = ipv6_hdr(skb)->saddr;
 	treq->loc_addr = ipv6_hdr(skb)->daddr;
 	if (!want_cookie || tmp_opt.tstamp_ok)
-		TCP_ECN_create_request(req, skb);
+		TCP_ECN_create_request(req, skb, tcpv6_prot.ecn);
 
 	treq->iif = sk->sk_bound_dev_if;
 
@@ -1955,6 +1955,7 @@ struct proto tcpv6_prot = {
 	.rsk_prot		= &tcp6_request_sock_ops,
 	.h.hashinfo		= &tcp_hashinfo,
 	.no_autobind		= true,
+	.ecn			= 2,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt	= compat_tcp_setsockopt,
 	.compat_getsockopt	= compat_tcp_getsockopt,
@@ -1963,6 +1964,7 @@ struct proto tcpv6_prot = {
 	.proto_cgroup		= tcp_proto_cgroup,
 #endif
 };
+EXPORT_SYMBOL(tcpv6_prot);
 
 static const struct inet6_protocol tcpv6_protocol = {
 	.early_demux	=	tcp_v6_early_demux,
-- 
1.7.11.7

^ permalink raw reply related	[flat|nested] 10+ messages in thread
end of thread, other threads:[~2013-01-06  1:31 UTC | newest]

Thread overview: 10+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2013-01-03  0:00 [PATCH v2] tcp: split tcp_ecn sysctl knob to distinguish between IPv4 and IPv6 Hannes Frederic Sowa
2013-01-03 12:28 ` Hannes Frederic Sowa
2013-01-03 12:53   ` David Miller
2013-01-03 12:58     ` Hannes Frederic Sowa
2013-01-03 16:22       ` Stephen Hemminger
2013-01-03 16:58         ` Hannes Frederic Sowa
2013-01-06  1:31     ` Hannes Frederic Sowa
2013-01-03 12:47 ` Eric Dumazet
2013-01-03 12:57   ` Hannes Frederic Sowa
2013-01-03 13:13     ` Eric Dumazet

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).