From 1946e672c173559155a3e210fe95dbf8b7b8ddf7 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 28 Dec 2016 17:52:32 +0800
Subject: ipv4: Namespaceify tcp_tw_recycle and tcp_max_tw_buckets knob

Different namespace application might require fast recycling
TIME-WAIT sockets independently of the host.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 73bc8fc68acd..a4cdf6a34c30 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -123,6 +123,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct dst_entry *dst;
 	int addr_type;
 	int err;
+	struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
 	if (addr_len < SIN6_LEN_RFC2133)
 		return -EINVAL;
@@ -258,7 +259,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	sk->sk_gso_type = SKB_GSO_TCPV6;
 	ip6_dst_store(sk, dst, NULL, NULL);
 
-	if (tcp_death_row.sysctl_tw_recycle &&
+	if (tcp_death_row->sysctl_tw_recycle &&
 	    !tp->rx_opt.ts_recent_stamp &&
 	    ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr))
 		tcp_fetch_timewait_stamp(sk, dst);
@@ -273,7 +274,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	inet->inet_dport = usin->sin6_port;
 
 	tcp_set_state(sk, TCP_SYN_SENT);
-	err = inet6_hash_connect(&tcp_death_row, sk);
+	err = inet6_hash_connect(tcp_death_row, sk);
 	if (err)
 		goto late_failure;
 
@@ -1948,7 +1949,7 @@ static void __net_exit tcpv6_net_exit(struct net *net)
 
 static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list)
 {
-	inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET6);
+	inet_twsk_purge(&tcp_hashinfo, AF_INET6);
 }
 
 static struct pernet_operations tcpv6_net_ops = {
-- 
cgit 


From 4b9d07a44015a0e940448fa3885b894349e8b162 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Mon, 9 Jan 2017 16:55:12 +0100
Subject: net: introduce keepalive function in struct proto

Direct call of tcp_set_keepalive() function from protocol-agnostic
sock_setsockopt() function in net/core/sock.c violates network
layering. And newly introduced protocol (SMC-R) will need its own
keepalive function. Therefore, add "keepalive" function pointer
to "struct proto", and call it from sock_setsockopt() via this pointer.

Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Reviewed-by: Utz Bacher <utz.bacher@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h   | 1 +
 net/core/sock.c      | 7 ++-----
 net/ipv4/tcp_ipv4.c  | 1 +
 net/ipv4/tcp_timer.c | 1 +
 net/ipv6/tcp_ipv6.c  | 1 +
 5 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/include/net/sock.h b/include/net/sock.h
index f0e867f58722..99deda67eba0 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1024,6 +1024,7 @@ struct proto {
 	int			(*getsockopt)(struct sock *sk, int level,
 					int optname, char __user *optval,
 					int __user *option);
+	void			(*keepalive)(struct sock *sk, int valbool);
 #ifdef CONFIG_COMPAT
 	int			(*compat_setsockopt)(struct sock *sk,
 					int level,
diff --git a/net/core/sock.c b/net/core/sock.c
index f560e0826009..5018703ee2c2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -762,11 +762,8 @@ set_rcvbuf:
 		goto set_rcvbuf;
 
 	case SO_KEEPALIVE:
-#ifdef CONFIG_INET
-		if (sk->sk_protocol == IPPROTO_TCP &&
-		    sk->sk_type == SOCK_STREAM)
-			tcp_set_keepalive(sk, valbool);
-#endif
+		if (sk->sk_prot->keepalive)
+			sk->sk_prot->keepalive(sk, valbool);
 		sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
 		break;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7e4be4f361f3..56d756ecfb59 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2376,6 +2376,7 @@ struct proto tcp_prot = {
 	.shutdown		= tcp_shutdown,
 	.setsockopt		= tcp_setsockopt,
 	.getsockopt		= tcp_getsockopt,
+	.keepalive		= tcp_set_keepalive,
 	.recvmsg		= tcp_recvmsg,
 	.sendmsg		= tcp_sendmsg,
 	.sendpage		= tcp_sendpage,
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 3705075f42c3..29a9bd5f1225 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -617,6 +617,7 @@ void tcp_set_keepalive(struct sock *sk, int val)
 	else if (!val)
 		inet_csk_delete_keepalive_timer(sk);
 }
+EXPORT_SYMBOL_GPL(tcp_set_keepalive);
 
 
 static void tcp_keepalive_timer (unsigned long data)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a4cdf6a34c30..228965dca3c5 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1889,6 +1889,7 @@ struct proto tcpv6_prot = {
 	.shutdown		= tcp_shutdown,
 	.setsockopt		= tcp_setsockopt,
 	.getsockopt		= tcp_getsockopt,
+	.keepalive		= tcp_set_keepalive,
 	.recvmsg		= tcp_recvmsg,
 	.sendmsg		= tcp_sendmsg,
 	.sendpage		= tcp_sendpage,
-- 
cgit 


From 57dde7f70de34d4251f291c9eac7ad920aaf56b2 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 12 Jan 2017 22:11:33 -0800
Subject: tcp: add reordering timer in RACK loss detection

This patch makes RACK install a reordering timer when it suspects
some packets might be lost, but wants to delay the decision
a little bit to accomodate reordering.

It does not create a new timer but instead repurposes the existing
RTO timer, because both are meant to retransmit packets.
Specifically it arms a timer ICSK_TIME_REO_TIMEOUT when
the RACK timing check fails. The wait time is set to

  RACK.RTT + RACK.reo_wnd - (NOW - Packet.xmit_time) + fudge

This translates to expecting a packet (Packet) should take
(RACK.RTT + RACK.reo_wnd + fudge) to deliver after it was sent.

When there are multiple packets that need a timer, we use one timer
with the maximum timeout. Therefore the timer conservatively uses
the maximum window to expire N packets by one timeout, instead of
N timeouts to expire N packets sent at different times.

The fudge factor is 2 jiffies to ensure when the timer fires, all
the suspected packets would exceed the deadline and be marked lost
by tcp_rack_detect_loss(). It has to be at least 1 jiffy because the
clock may tick between calling icsk_reset_xmit_timer(timeout) and
actually hang the timer. The next jiffy is to lower-bound the timeout
to 2 jiffies when reo_wnd is < 1ms.

When the reordering timer fires (tcp_rack_reo_timeout): If we aren't
in Recovery we'll enter fast recovery and force fast retransmit.
This is very similar to the early retransmit (RFC5827) except RACK
is not constrained to only enter recovery for small outstanding
flights.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h |  4 ++-
 include/net/tcp.h                  |  4 +++
 net/ipv4/inet_diag.c               |  1 +
 net/ipv4/tcp_input.c               |  6 ++--
 net/ipv4/tcp_ipv4.c                |  1 +
 net/ipv4/tcp_output.c              |  3 +-
 net/ipv4/tcp_recovery.c            | 57 +++++++++++++++++++++++++++++++++-----
 net/ipv4/tcp_timer.c               |  3 ++
 net/ipv6/tcp_ipv6.c                |  1 +
 9 files changed, 68 insertions(+), 12 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 85ee3879499e..84b2edde09b1 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -144,6 +144,7 @@ struct inet_connection_sock {
 #define ICSK_TIME_PROBE0	3	/* Zero window probe timer */
 #define ICSK_TIME_EARLY_RETRANS 4	/* Early retransmit timer */
 #define ICSK_TIME_LOSS_PROBE	5	/* Tail loss probe timer */
+#define ICSK_TIME_REO_TIMEOUT	6	/* Reordering timer */
 
 static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
 {
@@ -234,7 +235,8 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
 	}
 
 	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 ||
-	    what == ICSK_TIME_EARLY_RETRANS || what ==  ICSK_TIME_LOSS_PROBE) {
+	    what == ICSK_TIME_EARLY_RETRANS || what == ICSK_TIME_LOSS_PROBE ||
+	    what == ICSK_TIME_REO_TIMEOUT) {
 		icsk->icsk_pending = what;
 		icsk->icsk_timeout = jiffies + when;
 		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 1439107658c2..64fcdeb3358b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -143,6 +143,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes
 					                 * for local resources.
 					                 */
+#define TCP_REO_TIMEOUT_MIN	(2000) /* Min RACK reordering timeout in usec */
 
 #define TCP_KEEPALIVE_TIME	(120*60*HZ)	/* two hours */
 #define TCP_KEEPALIVE_PROBES	9		/* Max of 9 keepalive probes	*/
@@ -397,6 +398,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 int tcp_child_process(struct sock *parent, struct sock *child,
 		      struct sk_buff *skb);
 void tcp_enter_loss(struct sock *sk);
+void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag);
 void tcp_clear_retrans(struct tcp_sock *tp);
 void tcp_update_metrics(struct sock *sk);
 void tcp_init_metrics(struct sock *sk);
@@ -541,6 +543,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
 void tcp_retransmit_timer(struct sock *sk);
 void tcp_xmit_retransmit_queue(struct sock *);
 void tcp_simple_retransmit(struct sock *);
+void tcp_enter_recovery(struct sock *sk, bool ece_ack);
 int tcp_trim_head(struct sock *, struct sk_buff *, u32);
 int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t);
 
@@ -1867,6 +1870,7 @@ extern void tcp_rack_mark_lost(struct sock *sk, const struct skb_mstamp *now);
 extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked,
 			     const struct skb_mstamp *xmit_time,
 			     const struct skb_mstamp *ack_time);
+extern void tcp_rack_reo_timeout(struct sock *sk);
 
 /*
  * Save and compile IPv4 options, return a pointer to it
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 4dea33e5f295..d216e40623d3 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -216,6 +216,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
 	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		r->idiag_timer = 1;
 		r->idiag_retrans = icsk->icsk_retransmits;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8ccd171999bf..be1191829963 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2522,8 +2522,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk)
 	tcp_ecn_queue_cwr(tp);
 }
 
-static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked,
-			       int flag)
+void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int sndcnt = 0;
@@ -2691,7 +2690,7 @@ void tcp_simple_retransmit(struct sock *sk)
 }
 EXPORT_SYMBOL(tcp_simple_retransmit);
 
-static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
+void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int mib_idx;
@@ -3031,6 +3030,7 @@ void tcp_rearm_rto(struct sock *sk)
 		u32 rto = inet_csk(sk)->icsk_rto;
 		/* Offset the time elapsed after installing regular RTO */
 		if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+		    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 		    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 			struct sk_buff *skb = tcp_write_queue_head(sk);
 			const u32 rto_time_stamp =
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 56d756ecfb59..ebf3e0c4967a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2230,6 +2230,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
 	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1d5331a1b1dc..0ba9026cb70d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2960,7 +2960,8 @@ begin_fwd:
 		if (tcp_in_cwnd_reduction(sk))
 			tp->prr_out += tcp_skb_pcount(skb);
 
-		if (skb == tcp_write_queue_head(sk))
+		if (skb == tcp_write_queue_head(sk) &&
+		    icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT)
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 						  inet_csk(sk)->icsk_rto,
 						  TCP_RTO_MAX);
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 557363cde58a..eb39b1b6d1dc 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -32,19 +32,18 @@ static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
  * The current version is only used after recovery starts but can be
  * easily extended to detect the first loss.
  */
-static void tcp_rack_detect_loss(struct sock *sk, const struct skb_mstamp *now)
+static void tcp_rack_detect_loss(struct sock *sk, const struct skb_mstamp *now,
+				 u32 *reo_timeout)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	u32 reo_wnd;
 
+	*reo_timeout = 0;
 	/* To be more reordering resilient, allow min_rtt/4 settling delay
 	 * (lower-bounded to 1000uS). We use min_rtt instead of the smoothed
 	 * RTT because reordering is often a path property and less related
 	 * to queuing or delayed ACKs.
-	 *
-	 * TODO: measure and adapt to the observed reordering delay, and
-	 * use a timer to retransmit like the delayed early retransmit.
 	 */
 	reo_wnd = 1000;
 	if (tp->rack.reord && tcp_min_rtt(tp) != ~0U)
@@ -66,10 +65,23 @@ static void tcp_rack_detect_loss(struct sock *sk, const struct skb_mstamp *now)
 			 * A packet is lost if its elapsed time is beyond
 			 * the recent RTT plus the reordering window.
 			 */
-			if (skb_mstamp_us_delta(now, &skb->skb_mstamp) >
-			    tp->rack.rtt_us + reo_wnd) {
+			u32 elapsed = skb_mstamp_us_delta(now,
+							  &skb->skb_mstamp);
+			s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed;
+
+			if (remaining < 0) {
 				tcp_rack_mark_skb_lost(sk, skb);
+				continue;
 			}
+
+			/* Skip ones marked lost but not yet retransmitted */
+			if ((scb->sacked & TCPCB_LOST) &&
+			    !(scb->sacked & TCPCB_SACKED_RETRANS))
+				continue;
+
+			/* Record maximum wait time (+1 to avoid 0) */
+			*reo_timeout = max_t(u32, *reo_timeout, 1 + remaining);
+
 		} else if (!(scb->sacked & TCPCB_RETRANS)) {
 			/* Original data are sent sequentially so stop early
 			 * b/c the rest are all sent after rack_sent
@@ -82,12 +94,19 @@ static void tcp_rack_detect_loss(struct sock *sk, const struct skb_mstamp *now)
 void tcp_rack_mark_lost(struct sock *sk, const struct skb_mstamp *now)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	u32 timeout;
 
 	if (inet_csk(sk)->icsk_ca_state < TCP_CA_Recovery || !tp->rack.advanced)
 		return;
+
 	/* Reset the advanced flag to avoid unnecessary queue scanning */
 	tp->rack.advanced = 0;
-	tcp_rack_detect_loss(sk, now);
+	tcp_rack_detect_loss(sk, now, &timeout);
+	if (timeout) {
+		timeout = usecs_to_jiffies(timeout + TCP_REO_TIMEOUT_MIN);
+		inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
+					  timeout, inet_csk(sk)->icsk_rto);
+	}
 }
 
 /* Record the most recently (re)sent time among the (s)acked packets
@@ -123,3 +142,27 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked,
 	tp->rack.mstamp = *xmit_time;
 	tp->rack.advanced = 1;
 }
+
+/* We have waited long enough to accommodate reordering. Mark the expired
+ * packets lost and retransmit them.
+ */
+void tcp_rack_reo_timeout(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct skb_mstamp now;
+	u32 timeout, prior_inflight;
+
+	skb_mstamp_get(&now);
+	prior_inflight = tcp_packets_in_flight(tp);
+	tcp_rack_detect_loss(sk, &now, &timeout);
+	if (prior_inflight != tcp_packets_in_flight(tp)) {
+		if (inet_csk(sk)->icsk_ca_state != TCP_CA_Recovery) {
+			tcp_enter_recovery(sk, false);
+			if (!inet_csk(sk)->icsk_ca_ops->cong_control)
+				tcp_cwnd_reduction(sk, 1, 0);
+		}
+		tcp_xmit_retransmit_queue(sk);
+	}
+	if (inet_csk(sk)->icsk_pending != ICSK_TIME_RETRANS)
+		tcp_rearm_rto(sk);
+}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 29a9bd5f1225..953c02a8566e 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -563,6 +563,9 @@ void tcp_write_timer_handler(struct sock *sk)
 	event = icsk->icsk_pending;
 
 	switch (event) {
+	case ICSK_TIME_REO_TIMEOUT:
+		tcp_rack_reo_timeout(sk);
+		break;
 	case ICSK_TIME_EARLY_RETRANS:
 		tcp_resume_early_retransmit(sk);
 		break;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 228965dca3c5..f52c3742b404 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1746,6 +1746,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
 	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
-- 
cgit 


From bec41a11dd3dc8c54f766b4f494140ca92ba7c10 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 12 Jan 2017 22:11:39 -0800
Subject: tcp: remove early retransmit

This patch removes the support of RFC5827 early retransmit (i.e.,
fast recovery on small inflight with <3 dupacks) because it is
subsumed by the new RACK loss detection. More specifically when
RACK receives DUPACKs, it'll arm a reordering timer to start fast
recovery after a quarter of (min)RTT, hence it covers the early
retransmit except RACK does not limit itself to specific inflight
or dupack numbers.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 19 +++--------
 include/linux/tcp.h                    |  3 +-
 include/net/tcp.h                      | 19 -----------
 net/ipv4/inet_diag.c                   |  1 -
 net/ipv4/tcp.c                         |  3 --
 net/ipv4/tcp_input.c                   | 60 ++--------------------------------
 net/ipv4/tcp_ipv4.c                    |  1 -
 net/ipv4/tcp_metrics.c                 |  1 -
 net/ipv4/tcp_minisocks.c               |  1 -
 net/ipv4/tcp_output.c                  | 11 +++----
 net/ipv4/tcp_timer.c                   |  3 --
 net/ipv6/tcp_ipv6.c                    |  1 -
 12 files changed, 12 insertions(+), 111 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 7dd65c9cf707..7de2cf79e16f 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -246,21 +246,12 @@ tcp_dsack - BOOLEAN
 	Allows TCP to send "duplicate" SACKs.
 
 tcp_early_retrans - INTEGER
-	Enable Early Retransmit (ER), per RFC 5827. ER lowers the threshold
-	for triggering fast retransmit when the amount of outstanding data is
-	small and when no previously unsent data can be transmitted (such
-	that limited transmit could be used). Also controls the use of
-	Tail loss probe (TLP) that converts RTOs occurring due to tail
-	losses into fast recovery (draft-dukkipati-tcpm-tcp-loss-probe-01).
+	Tail loss probe (TLP) converts RTOs occurring due to tail
+	losses into fast recovery (draft-ietf-tcpm-rack). Note that
+	TLP requires RACK to function properly (see tcp_recovery below)
 	Possible values:
-		0 disables ER
-		1 enables ER
-		2 enables ER but delays fast recovery and fast retransmit
-		  by a fourth of RTT. This mitigates connection falsely
-		  recovers when network has a small degree of reordering
-		  (less than 3 packets).
-		3 enables delayed ER and TLP.
-		4 enables TLP only.
+		0 disables TLP
+		3 or 4 enables TLP
 	Default: 3
 
 tcp_ecn - INTEGER
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 8e5f4c15d0e5..4733368f953a 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -224,8 +224,7 @@ struct tcp_sock {
 		repair      : 1,
 		frto        : 1;/* F-RTO (RFC5682) activated in CA_Loss */
 	u8	repair_queue;
-	u8	do_early_retrans:1,/* Enable RFC5827 early-retransmit  */
-		syn_data:1,	/* SYN includes data */
+	u8	syn_data:1,	/* SYN includes data */
 		syn_fastopen:1,	/* SYN includes Fast Open option */
 		syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
 		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 423438dd6fe9..c55d65f74f7f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -565,7 +565,6 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb,
 			     const struct sk_buff *next_skb);
 
 /* tcp_input.c */
-void tcp_resume_early_retransmit(struct sock *sk);
 void tcp_rearm_rto(struct sock *sk);
 void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);
 void tcp_reset(struct sock *sk);
@@ -1037,24 +1036,6 @@ static inline void tcp_enable_fack(struct tcp_sock *tp)
 	tp->rx_opt.sack_ok |= TCP_FACK_ENABLED;
 }
 
-/* TCP early-retransmit (ER) is similar to but more conservative than
- * the thin-dupack feature.  Enable ER only if thin-dupack is disabled.
- */
-static inline void tcp_enable_early_retrans(struct tcp_sock *tp)
-{
-	struct net *net = sock_net((struct sock *)tp);
-
-	tp->do_early_retrans = sysctl_tcp_early_retrans &&
-		sysctl_tcp_early_retrans < 4 && !sysctl_tcp_thin_dupack &&
-		!(sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) &&
-		net->ipv4.sysctl_tcp_reordering == 3;
-}
-
-static inline void tcp_disable_early_retrans(struct tcp_sock *tp)
-{
-	tp->do_early_retrans = 0;
-}
-
 static inline unsigned int tcp_left_out(const struct tcp_sock *tp)
 {
 	return tp->sacked_out + tp->lost_out;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index d216e40623d3..3828b3a805cd 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -215,7 +215,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 	}
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
-	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
 	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		r->idiag_timer = 1;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c8d46c140b4a..d9023e8ed53e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -406,7 +406,6 @@ void tcp_init_sock(struct sock *sk)
 	tp->mss_cache = TCP_MSS_DEFAULT;
 
 	tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
-	tcp_enable_early_retrans(tp);
 	tcp_assign_congestion_control(sk);
 
 	tp->tsoffset = 0;
@@ -2477,8 +2476,6 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 			err = -EINVAL;
 		else {
 			tp->thin_dupack = val;
-			if (tp->thin_dupack)
-				tcp_disable_early_retrans(tp);
 		}
 		break;
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a041a92348ee..79c819077a59 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -904,8 +904,6 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
 		tcp_disable_fack(tp);
 	}
 
-	if (metric > 0)
-		tcp_disable_early_retrans(tp);
 	tp->rack.reord = 1;
 }
 
@@ -2054,30 +2052,6 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp)
 	return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1;
 }
 
-static bool tcp_pause_early_retransmit(struct sock *sk, int flag)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	unsigned long delay;
-
-	/* Delay early retransmit and entering fast recovery for
-	 * max(RTT/4, 2msec) unless ack has ECE mark, no RTT samples
-	 * available, or RTO is scheduled to fire first.
-	 */
-	if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 ||
-	    (flag & FLAG_ECE) || !tp->srtt_us)
-		return false;
-
-	delay = max(usecs_to_jiffies(tp->srtt_us >> 5),
-		    msecs_to_jiffies(2));
-
-	if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay)))
-		return false;
-
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_EARLY_RETRANS, delay,
-				  TCP_RTO_MAX);
-	return true;
-}
-
 /* Linux NewReno/SACK/FACK/ECN state machine.
  * --------------------------------------
  *
@@ -2221,16 +2195,6 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
 	    tcp_is_sack(tp) && !tcp_send_head(sk))
 		return true;
 
-	/* Trick#6: TCP early retransmit, per RFC5827.  To avoid spurious
-	 * retransmissions due to small network reorderings, we implement
-	 * Mitigation A.3 in the RFC and delay the retransmission for a short
-	 * interval if appropriate.
-	 */
-	if (tp->do_early_retrans && !tp->retrans_out && tp->sacked_out &&
-	    (tp->packets_out >= (tp->sacked_out + 1) && tp->packets_out < 4) &&
-	    !tcp_may_send_now(sk))
-		return !tcp_pause_early_retransmit(sk, flag);
-
 	return false;
 }
 
@@ -3050,8 +3014,7 @@ void tcp_rearm_rto(struct sock *sk)
 	} else {
 		u32 rto = inet_csk(sk)->icsk_rto;
 		/* Offset the time elapsed after installing regular RTO */
-		if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
-		    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
+		if (icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 		    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 			struct sk_buff *skb = tcp_write_queue_head(sk);
 			const u32 rto_time_stamp =
@@ -3068,24 +3031,6 @@ void tcp_rearm_rto(struct sock *sk)
 	}
 }
 
-/* This function is called when the delayed ER timer fires. TCP enters
- * fast recovery and performs fast-retransmit.
- */
-void tcp_resume_early_retransmit(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	tcp_rearm_rto(sk);
-
-	/* Stop if ER is disabled after the delayed ER timer is scheduled */
-	if (!tp->do_early_retrans)
-		return;
-
-	tcp_enter_recovery(sk, false);
-	tcp_update_scoreboard(sk, 1);
-	tcp_xmit_retransmit_queue(sk);
-}
-
 /* If we get here, the whole TSO packet has not been acked. */
 static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb)
 {
@@ -3651,8 +3596,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	skb_mstamp_get(&sack_state.ack_time);
 
-	if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
-	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
+	if (icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
 
 	if (after(ack, prior_snd_una)) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ebf3e0c4967a..63214136cf1c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2229,7 +2229,6 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 	int state;
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
-	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
 	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index ba8f02d0f283..b9ed0d50aead 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -522,7 +522,6 @@ void tcp_init_metrics(struct sock *sk)
 	val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
 	if (val && tp->reordering != val) {
 		tcp_disable_fack(tp);
-		tcp_disable_early_retrans(tp);
 		tp->reordering = val;
 	}
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 06fde26a82b7..bdb443471c39 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -468,7 +468,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->sacked_out = 0;
 		newtp->fackets_out = 0;
 		newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
-		tcp_enable_early_retrans(newtp);
 		newtp->tlp_high_seq = 0;
 		newtp->lsndtime = treq->snt_synack.stamp_jiffies;
 		newsk->sk_txhash = treq->txhash;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 6327e4d368a4..9a1a1494b9dd 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -76,10 +76,8 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb)
 	tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
 
 	tp->packets_out += tcp_skb_pcount(skb);
-	if (!prior_packets || icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
-	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
+	if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
-	}
 
 	NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT,
 		      tcp_skb_pcount(skb));
@@ -2289,8 +2287,6 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	u32 timeout, tlp_time_stamp, rto_time_stamp;
 	u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3);
 
-	if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS))
-		return false;
 	/* No consecutive loss probes. */
 	if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) {
 		tcp_rearm_rto(sk);
@@ -2309,8 +2305,9 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	/* Schedule a loss probe in 2*RTT for SACK capable connections
 	 * in Open state, that are either limited by cwnd or application.
 	 */
-	if (sysctl_tcp_early_retrans < 3 || !tp->packets_out ||
-	    !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
+	if ((sysctl_tcp_early_retrans != 3 && sysctl_tcp_early_retrans != 4) ||
+	    !tp->packets_out || !tcp_is_sack(tp) ||
+	    icsk->icsk_ca_state != TCP_CA_Open)
 		return false;
 
 	if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) &&
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 953c02a8566e..40d893556e67 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -566,9 +566,6 @@ void tcp_write_timer_handler(struct sock *sk)
 	case ICSK_TIME_REO_TIMEOUT:
 		tcp_rack_reo_timeout(sk);
 		break;
-	case ICSK_TIME_EARLY_RETRANS:
-		tcp_resume_early_retransmit(sk);
-		break;
 	case ICSK_TIME_LOSS_PROBE:
 		tcp_send_loss_probe(sk);
 		break;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f52c3742b404..fc14e04028bf 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1745,7 +1745,6 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	srcp  = ntohs(inet->inet_sport);
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
-	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
 	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
-- 
cgit 


From aa078842b702b4a45111f028a604a6c8f69cb27d Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 17 Jan 2017 07:51:02 -0800
Subject: inet: drop ->bind_conflict

The only difference between inet6_csk_bind_conflict and inet_csk_bind_conflict
is how they check the rcv_saddr, so delete this call back and simply
change inet_csk_bind_conflict to call inet_rcv_saddr_equal.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet6_connection_sock.h |  5 -----
 include/net/inet_connection_sock.h  |  6 ------
 net/dccp/ipv4.c                     |  1 -
 net/dccp/ipv6.c                     |  2 --
 net/ipv4/inet_connection_sock.c     | 22 +++++++-------------
 net/ipv4/tcp_ipv4.c                 |  1 -
 net/ipv6/inet6_connection_sock.c    | 40 -------------------------------------
 net/ipv6/tcp_ipv6.c                 |  2 --
 8 files changed, 7 insertions(+), 72 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h
index 3212b39b5bfc..8ec87b62257b 100644
--- a/include/net/inet6_connection_sock.h
+++ b/include/net/inet6_connection_sock.h
@@ -15,16 +15,11 @@
 
 #include <linux/types.h>
 
-struct inet_bind_bucket;
 struct request_sock;
 struct sk_buff;
 struct sock;
 struct sockaddr;
 
-int inet6_csk_bind_conflict(const struct sock *sk,
-			    const struct inet_bind_bucket *tb, bool relax,
-			    bool soreuseport_ok);
-
 struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6,
 				      const struct request_sock *req, u8 proto);
 
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 84b2edde09b1..826f198374f8 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -62,9 +62,6 @@ struct inet_connection_sock_af_ops {
 				char __user *optval, int __user *optlen);
 #endif
 	void	    (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
-	int	    (*bind_conflict)(const struct sock *sk,
-				     const struct inet_bind_bucket *tb,
-				     bool relax, bool soreuseport_ok);
 	void	    (*mtu_reduced)(struct sock *sk);
 };
 
@@ -263,9 +260,6 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk,
 
 struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);
 
-int inet_csk_bind_conflict(const struct sock *sk,
-			   const struct inet_bind_bucket *tb, bool relax,
-			   bool soreuseport_ok);
 int inet_csk_get_port(struct sock *sk, unsigned short snum);
 
 struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4,
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index d859a5c36e70..b043ec833785 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -904,7 +904,6 @@ static const struct inet_connection_sock_af_ops dccp_ipv4_af_ops = {
 	.getsockopt	   = ip_getsockopt,
 	.addr2sockaddr	   = inet_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in),
-	.bind_conflict	   = inet_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ip_setsockopt,
 	.compat_getsockopt = compat_ip_getsockopt,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index adfc790f7193..08bcdc3d1717 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -937,7 +937,6 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops = {
 	.getsockopt	   = ipv6_getsockopt,
 	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in6),
-	.bind_conflict	   = inet6_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,
@@ -958,7 +957,6 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = {
 	.getsockopt	   = ipv6_getsockopt,
 	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in6),
-	.bind_conflict	   = inet6_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index ba597cb504ff..a1c9055769fc 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -116,9 +116,9 @@ void inet_get_local_port_range(struct net *net, int *low, int *high)
 }
 EXPORT_SYMBOL(inet_get_local_port_range);
 
-int inet_csk_bind_conflict(const struct sock *sk,
-			   const struct inet_bind_bucket *tb, bool relax,
-			   bool reuseport_ok)
+static int inet_csk_bind_conflict(const struct sock *sk,
+				  const struct inet_bind_bucket *tb,
+				  bool relax, bool reuseport_ok)
 {
 	struct sock *sk2;
 	bool reuse = sk->sk_reuse;
@@ -134,7 +134,6 @@ int inet_csk_bind_conflict(const struct sock *sk,
 
 	sk_for_each_bound(sk2, &tb->owners) {
 		if (sk != sk2 &&
-		    !inet_v6_ipv6only(sk2) &&
 		    (!sk->sk_bound_dev_if ||
 		     !sk2->sk_bound_dev_if ||
 		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
@@ -144,23 +143,18 @@ int inet_csk_bind_conflict(const struct sock *sk,
 			     rcu_access_pointer(sk->sk_reuseport_cb) ||
 			     (sk2->sk_state != TCP_TIME_WAIT &&
 			     !uid_eq(uid, sock_i_uid(sk2))))) {
-
-				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
-				    sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
+				if (inet_rcv_saddr_equal(sk, sk2, true))
 					break;
 			}
 			if (!relax && reuse && sk2->sk_reuse &&
 			    sk2->sk_state != TCP_LISTEN) {
-
-				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
-				    sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
+				if (inet_rcv_saddr_equal(sk, sk2, true))
 					break;
 			}
 		}
 	}
 	return sk2 != NULL;
 }
-EXPORT_SYMBOL_GPL(inet_csk_bind_conflict);
 
 /* Obtain a reference to a local port for the given sock,
  * if snum is zero it means select any available local port.
@@ -239,8 +233,7 @@ other_parity_scan:
 					smallest_size = tb->num_owners;
 					smallest_port = port;
 				}
-				if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false,
-									      reuseport_ok))
+				if (!inet_csk_bind_conflict(sk, tb, false, reuseport_ok))
 					goto tb_found;
 				goto next_port;
 			}
@@ -281,8 +274,7 @@ tb_found:
 		      sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
 		    smallest_size == -1)
 			goto success;
-		if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true,
-							     reuseport_ok)) {
+		if (inet_csk_bind_conflict(sk, tb, true, reuseport_ok)) {
 			if ((reuse ||
 			     (tb->fastreuseport > 0 &&
 			      sk->sk_reuseport &&
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 63214136cf1c..3644fc117691 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1817,7 +1817,6 @@ const struct inet_connection_sock_af_ops ipv4_specific = {
 	.getsockopt	   = ip_getsockopt,
 	.addr2sockaddr	   = inet_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in),
-	.bind_conflict	   = inet_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ip_setsockopt,
 	.compat_getsockopt = compat_ip_getsockopt,
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 55ee2ea2aee0..97074c459fe6 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -28,46 +28,6 @@
 #include <net/inet6_connection_sock.h>
 #include <net/sock_reuseport.h>
 
-int inet6_csk_bind_conflict(const struct sock *sk,
-			    const struct inet_bind_bucket *tb, bool relax,
-			    bool reuseport_ok)
-{
-	const struct sock *sk2;
-	bool reuse = !!sk->sk_reuse;
-	bool reuseport = !!sk->sk_reuseport && reuseport_ok;
-	kuid_t uid = sock_i_uid((struct sock *)sk);
-
-	/* We must walk the whole port owner list in this case. -DaveM */
-	/*
-	 * See comment in inet_csk_bind_conflict about sock lookup
-	 * vs net namespaces issues.
-	 */
-	sk_for_each_bound(sk2, &tb->owners) {
-		if (sk != sk2 &&
-		    (!sk->sk_bound_dev_if ||
-		     !sk2->sk_bound_dev_if ||
-		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
-			if ((!reuse || !sk2->sk_reuse ||
-			     sk2->sk_state == TCP_LISTEN) &&
-			    (!reuseport || !sk2->sk_reuseport ||
-			     rcu_access_pointer(sk->sk_reuseport_cb) ||
-			     (sk2->sk_state != TCP_TIME_WAIT &&
-			      !uid_eq(uid,
-				      sock_i_uid((struct sock *)sk2))))) {
-				if (inet_rcv_saddr_equal(sk, sk2, true))
-					break;
-			}
-			if (!relax && reuse && sk2->sk_reuse &&
-			    sk2->sk_state != TCP_LISTEN &&
-			    inet_rcv_saddr_equal(sk, sk2, true))
-				break;
-		}
-	}
-
-	return sk2 != NULL;
-}
-EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict);
-
 struct dst_entry *inet6_csk_route_req(const struct sock *sk,
 				      struct flowi6 *fl6,
 				      const struct request_sock *req,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index fc14e04028bf..f72100eedd5d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1621,7 +1621,6 @@ static const struct inet_connection_sock_af_ops ipv6_specific = {
 	.getsockopt	   = ipv6_getsockopt,
 	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in6),
-	.bind_conflict	   = inet6_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,
@@ -1652,7 +1651,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
 	.getsockopt	   = ipv6_getsockopt,
 	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in6),
-	.bind_conflict	   = inet6_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,
-- 
cgit 


From 25776aa943401662617437841b3d3ea4693ee98a Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Mon, 23 Jan 2017 10:59:21 -0800
Subject: net: Remove __sk_dst_reset() in tcp_v6_connect()

Remove __sk_dst_reset() in the failure handling because __sk_dst_reset()
will eventually get called when sk is released. No need to handle it in
the protocol specific connect call.
This is also to make the code path consistent with ipv4.

Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f72100eedd5d..0b7cd3d009b6 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -295,7 +295,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 late_failure:
 	tcp_set_state(sk, TCP_CLOSE);
-	__sk_dst_reset(sk);
 failure:
 	inet->inet_dport = 0;
 	sk->sk_route_caps = 0;
-- 
cgit 


From 19f6d3f3c8422d65b5e3d2162e30ef07c6e21ea2 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Mon, 23 Jan 2017 10:59:22 -0800
Subject: net/tcp-fastopen: Add new API support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds a new socket option, TCP_FASTOPEN_CONNECT, as an
alternative way to perform Fast Open on the active side (client). Prior
to this patch, a client needs to replace the connect() call with
sendto(MSG_FASTOPEN). This can be cumbersome for applications who want
to use Fast Open: these socket operations are often done in lower layer
libraries used by many other applications. Changing these libraries
and/or the socket call sequences are not trivial. A more convenient
approach is to perform Fast Open by simply enabling a socket option when
the socket is created w/o changing other socket calls sequence:
  s = socket()
    create a new socket
  setsockopt(s, IPPROTO_TCP, TCP_FASTOPEN_CONNECT …);
    newly introduced sockopt
    If set, new functionality described below will be used.
    Return ENOTSUPP if TFO is not supported or not enabled in the
    kernel.

  connect()
    With cookie present, return 0 immediately.
    With no cookie, initiate 3WHS with TFO cookie-request option and
    return -1 with errno = EINPROGRESS.

  write()/sendmsg()
    With cookie present, send out SYN with data and return the number of
    bytes buffered.
    With no cookie, and 3WHS not yet completed, return -1 with errno =
    EINPROGRESS.
    No MSG_FASTOPEN flag is needed.

  read()
    Return -1 with errno = EWOULDBLOCK/EAGAIN if connect() is called but
    write() is not called yet.
    Return -1 with errno = EWOULDBLOCK/EAGAIN if connection is
    established but no msg is received yet.
    Return number of bytes read if socket is established and there is
    msg received.

The new API simplifies life for applications that always perform a write()
immediately after a successful connect(). Such applications can now take
advantage of Fast Open by merely making one new setsockopt() call at the time
of creating the socket. Nothing else about the application's socket call
sequence needs to change.

Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      |  3 ++-
 include/net/inet_sock.h  |  6 +++++-
 include/net/tcp.h        |  1 +
 include/uapi/linux/tcp.h |  1 +
 net/ipv4/af_inet.c       | 31 ++++++++++++++++++++++++-------
 net/ipv4/tcp.c           | 35 ++++++++++++++++++++++++++++++++++-
 net/ipv4/tcp_fastopen.c  | 33 +++++++++++++++++++++++++++++++++
 net/ipv4/tcp_ipv4.c      |  7 ++++++-
 net/ipv6/tcp_ipv6.c      |  5 +++++
 9 files changed, 111 insertions(+), 11 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 5371b3d70cfe..f88f4649ba6f 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -222,7 +222,8 @@ struct tcp_sock {
 	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
 	u8	chrono_type:2,	/* current chronograph type */
 		rate_app_limited:1,  /* rate_{delivered,interval_us} limited? */
-		unused:5;
+		fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
+		unused:4;
 	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
 		thin_lto    : 1,/* Use linear timeouts for thin streams */
 		unused1	    : 1,
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index c9cff977a7fb..aa95053dfc78 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -206,7 +206,11 @@ struct inet_sock {
 				transparent:1,
 				mc_all:1,
 				nodefrag:1;
-	__u8			bind_address_no_port:1;
+	__u8			bind_address_no_port:1,
+				defer_connect:1; /* Indicates that fastopen_connect is set
+						  * and cookie exists so we defer connect
+						  * until first data frame is written
+						  */
 	__u8			rcv_tos;
 	__u8			convert_csum;
 	int			uc_index;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index de67541d7adf..6ec4ea652f3f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1495,6 +1495,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 void tcp_fastopen_init_key_once(bool publish);
 bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 			     struct tcp_fastopen_cookie *cookie);
+bool tcp_fastopen_defer_connect(struct sock *sk, int *err);
 #define TCP_FASTOPEN_KEY_LENGTH 16
 
 /* Fastopen key context */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index c53de2691cec..6ff35eb48d10 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -116,6 +116,7 @@ enum {
 #define TCP_SAVE_SYN		27	/* Record SYN headers for new connections */
 #define TCP_SAVED_SYN		28	/* Get SYN headers recorded for connection */
 #define TCP_REPAIR_WINDOW	29	/* Get/set window parameters */
+#define TCP_FASTOPEN_CONNECT	30	/* Attempt FastOpen with connect */
 
 struct tcp_repair_opt {
 	__u32	opt_code;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 28fe8da4e1ac..92e7f3e957fa 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -576,13 +576,24 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	int err;
 	long timeo;
 
-	if (addr_len < sizeof(uaddr->sa_family))
-		return -EINVAL;
+	/*
+	 * uaddr can be NULL and addr_len can be 0 if:
+	 * sk is a TCP fastopen active socket and
+	 * TCP_FASTOPEN_CONNECT sockopt is set and
+	 * we already have a valid cookie for this socket.
+	 * In this case, user can call write() after connect().
+	 * write() will invoke tcp_sendmsg_fastopen() which calls
+	 * __inet_stream_connect().
+	 */
+	if (uaddr) {
+		if (addr_len < sizeof(uaddr->sa_family))
+			return -EINVAL;
 
-	if (uaddr->sa_family == AF_UNSPEC) {
-		err = sk->sk_prot->disconnect(sk, flags);
-		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
-		goto out;
+		if (uaddr->sa_family == AF_UNSPEC) {
+			err = sk->sk_prot->disconnect(sk, flags);
+			sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
+			goto out;
+		}
 	}
 
 	switch (sock->state) {
@@ -593,7 +604,10 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		err = -EISCONN;
 		goto out;
 	case SS_CONNECTING:
-		err = -EALREADY;
+		if (inet_sk(sk)->defer_connect)
+			err = -EINPROGRESS;
+		else
+			err = -EALREADY;
 		/* Fall out of switch with err, set for this state */
 		break;
 	case SS_UNCONNECTED:
@@ -607,6 +621,9 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 
 		sock->state = SS_CONNECTING;
 
+		if (!err && inet_sk(sk)->defer_connect)
+			goto out;
+
 		/* Just entered SS_CONNECTING state; the only
 		 * difference is that return value in non-blocking
 		 * case is EINPROGRESS, rather than EALREADY.
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c43eb1a831d7..d9735b76d073 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -533,6 +533,12 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 		if (tp->urg_data & TCP_URG_VALID)
 			mask |= POLLPRI;
+	} else if (sk->sk_state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
+		/* Active TCP fastopen socket with defer_connect
+		 * Return POLLOUT so application can call write()
+		 * in order for kernel to generate SYN+data
+		 */
+		mask |= POLLOUT | POLLWRNORM;
 	}
 	/* This barrier is coupled with smp_wmb() in tcp_reset() */
 	smp_rmb();
@@ -1071,6 +1077,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 				int *copied, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_sock *inet = inet_sk(sk);
 	int err, flags;
 
 	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
@@ -1085,9 +1092,19 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	tp->fastopen_req->data = msg;
 	tp->fastopen_req->size = size;
 
+	if (inet->defer_connect) {
+		err = tcp_connect(sk);
+		/* Same failure procedure as in tcp_v4/6_connect */
+		if (err) {
+			tcp_set_state(sk, TCP_CLOSE);
+			inet->inet_dport = 0;
+			sk->sk_route_caps = 0;
+		}
+	}
 	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
 	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
 				    msg->msg_namelen, flags);
+	inet->defer_connect = 0;
 	*copied = tp->fastopen_req->copied;
 	tcp_free_fastopen_req(tp);
 	return err;
@@ -1107,7 +1124,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	lock_sock(sk);
 
 	flags = msg->msg_flags;
-	if (flags & MSG_FASTOPEN) {
+	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) {
 		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
 			goto out;
@@ -2656,6 +2673,18 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 			err = -EINVAL;
 		}
 		break;
+	case TCP_FASTOPEN_CONNECT:
+		if (val > 1 || val < 0) {
+			err = -EINVAL;
+		} else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+			if (sk->sk_state == TCP_CLOSE)
+				tp->fastopen_connect = val;
+			else
+				err = -EINVAL;
+		} else {
+			err = -EOPNOTSUPP;
+		}
+		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
 			err = -EPERM;
@@ -3016,6 +3045,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = icsk->icsk_accept_queue.fastopenq.max_qlen;
 		break;
 
+	case TCP_FASTOPEN_CONNECT:
+		val = tp->fastopen_connect;
+		break;
+
 	case TCP_TIMESTAMP:
 		val = tcp_time_stamp + tp->tsoffset;
 		break;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index f90e09e1ff4c..9674bec4a0f8 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -346,3 +346,36 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 	}
 	return cookie->len > 0;
 }
+
+/* This function checks if we want to defer sending SYN until the first
+ * write().  We defer under the following conditions:
+ * 1. fastopen_connect sockopt is set
+ * 2. we have a valid cookie
+ * Return value: return true if we want to defer until application writes data
+ *               return false if we want to send out SYN immediately
+ */
+bool tcp_fastopen_defer_connect(struct sock *sk, int *err)
+{
+	struct tcp_fastopen_cookie cookie = { .len = 0 };
+	struct tcp_sock *tp = tcp_sk(sk);
+	u16 mss;
+
+	if (tp->fastopen_connect && !tp->fastopen_req) {
+		if (tcp_fastopen_cookie_check(sk, &mss, &cookie)) {
+			inet_sk(sk)->defer_connect = 1;
+			return true;
+		}
+
+		/* Alloc fastopen_req in order for FO option to be included
+		 * in SYN
+		 */
+		tp->fastopen_req = kzalloc(sizeof(*tp->fastopen_req),
+					   sk->sk_allocation);
+		if (tp->fastopen_req)
+			tp->fastopen_req->cookie = cookie;
+		else
+			*err = -ENOBUFS;
+	}
+	return false;
+}
+EXPORT_SYMBOL(tcp_fastopen_defer_connect);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a90b4540c11e..8c9e9aa17d66 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -232,6 +232,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	/* OK, now commit destination to socket.  */
 	sk->sk_gso_type = SKB_GSO_TCPV4;
 	sk_setup_caps(sk, &rt->dst);
+	rt = NULL;
 
 	if (!tp->write_seq && likely(!tp->repair))
 		tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr,
@@ -242,9 +243,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	inet->inet_id = tp->write_seq ^ jiffies;
 
+	if (tcp_fastopen_defer_connect(sk, &err))
+		return err;
+	if (err)
+		goto failure;
+
 	err = tcp_connect(sk);
 
-	rt = NULL;
 	if (err)
 		goto failure;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 0b7cd3d009b6..95c05e5293b1 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -287,6 +287,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 							     inet->inet_dport,
 							     &tp->tsoffset);
 
+	if (tcp_fastopen_defer_connect(sk, &err))
+		return err;
+	if (err)
+		goto late_failure;
+
 	err = tcp_connect(sk);
 	if (err)
 		goto late_failure;
-- 
cgit 


From 3541f9e8bdebce02458882b66b638d7302c1f616 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 2 Feb 2017 08:04:56 -0800
Subject: tcp: add tcp_mss_clamp() helper

Small cleanup factorizing code doing the TCP_MAXSEG clamping.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      |  9 +++++++++
 net/ipv4/tcp_ipv4.c      |  5 +----
 net/ipv4/tcp_minisocks.c |  7 ++-----
 net/ipv4/tcp_output.c    | 14 ++++----------
 net/ipv6/tcp_ipv6.c      |  5 +----
 5 files changed, 17 insertions(+), 23 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index f88f4649ba6f..cfc2d9506ce8 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -445,4 +445,13 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp)
 
 struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk);
 
+static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss)
+{
+	/* We use READ_ONCE() here because socket might not be locked.
+	 * This happens for listeners.
+	 */
+	u16 user_mss = READ_ONCE(tp->rx_opt.user_mss);
+
+	return (user_mss && user_mss < mss) ? user_mss : mss;
+}
 #endif	/* _LINUX_TCP_H */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8c9e9aa17d66..8c124d4ef4b7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1324,10 +1324,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst_mtu(dst));
-	newtp->advmss = dst_metric_advmss(dst);
-	if (tcp_sk(sk)->rx_opt.user_mss &&
-	    tcp_sk(sk)->rx_opt.user_mss < newtp->advmss)
-		newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index bdb443471c39..dff7d2aaf861 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -360,15 +360,12 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	const struct tcp_sock *tp = tcp_sk(sk_listener);
-	u16 user_mss = READ_ONCE(tp->rx_opt.user_mss);
 	int full_space = tcp_full_space(sk_listener);
-	int mss = dst_metric_advmss(dst);
 	u32 window_clamp;
 	__u8 rcv_wscale;
+	int mss;
 
-	if (user_mss && user_mss < mss)
-		mss = user_mss;
-
+	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
 	window_clamp = READ_ONCE(tp->window_clamp);
 	/* Set this up on the first call only */
 	req->rsk_window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 6d5bab8a3ea6..956bea9a5394 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3062,7 +3062,6 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	struct sk_buff *skb;
 	int tcp_header_size;
 	struct tcphdr *th;
-	u16 user_mss;
 	int mss;
 
 	skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
@@ -3092,10 +3091,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	}
 	skb_dst_set(skb, dst);
 
-	mss = dst_metric_advmss(dst);
-	user_mss = READ_ONCE(tp->rx_opt.user_mss);
-	if (user_mss && user_mss < mss)
-		mss = user_mss;
+	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
 
 	memset(&opts, 0, sizeof(opts));
 #ifdef CONFIG_SYN_COOKIES
@@ -3201,9 +3197,7 @@ static void tcp_connect_init(struct sock *sk)
 
 	if (!tp->window_clamp)
 		tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
-	tp->advmss = dst_metric_advmss(dst);
-	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->advmss)
-		tp->advmss = tp->rx_opt.user_mss;
+	tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
 
 	tcp_initialize_rcv_mss(sk);
 
@@ -3280,8 +3274,8 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	 * user-MSS. Reserve maximum option space for middleboxes that add
 	 * private TCP options. The cost is reduced data space in SYN :(
 	 */
-	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp)
-		tp->rx_opt.mss_clamp = tp->rx_opt.user_mss;
+	tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp);
+
 	space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
 		MAX_TCP_OPTION_SPACE;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 64834ec5ab73..6b9fc63fd4d2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1147,10 +1147,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst_mtu(dst));
-	newtp->advmss = dst_metric_advmss(dst);
-	if (tcp_sk(sk)->rx_opt.user_mss &&
-	    tcp_sk(sk)->rx_opt.user_mss < newtp->advmss)
-		newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
 
-- 
cgit 


From 00355fa5bb89840c48eb11eb6d84c6c3b128a839 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Wed, 22 Feb 2017 13:23:55 +0300
Subject: tcp: setup timestamp offset when write_seq already set

Found that when randomized tcp offsets are enabled (by default)
TCP client can still start new connections without them. Later,
if server does active close and re-uses sockets in TIME-WAIT
state, new SYN from client can be rejected on PAWS check inside
tcp_timewait_state_process(), because either tw_ts_recent or
rcv_tsval doesn't really have an offset set.

Here is how to reproduce it with LTP netstress tool:
    netstress -R 1 &
    netstress -H 127.0.0.1 -lr 1000000 -a1

    [...]
    < S  seq 1956977072 win 43690 TS val 295618 ecr 459956970
    > .  ack 1956911535 win 342 TS val 459967184 ecr 1547117608
    < R  seq 1956911535 win 0 length 0
+1. < S  seq 1956977072 win 43690 TS val 296640 ecr 459956970
    > S. seq 657450664 ack 1956977073 win 43690 TS val 459968205 ecr 296640

Fixes: 95a22caee396 ("tcp: randomize tcp timestamp offsets for each connection")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 16 ++++++++++------
 net/ipv6/tcp_ipv6.c | 16 ++++++++++------
 2 files changed, 20 insertions(+), 12 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8c124d4ef4b7..9a89b8deafae 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -145,6 +145,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct flowi4 *fl4;
 	struct rtable *rt;
 	int err;
+	u32 seq;
 	struct ip_options_rcu *inet_opt;
 	struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
@@ -234,12 +235,15 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	sk_setup_caps(sk, &rt->dst);
 	rt = NULL;
 
-	if (!tp->write_seq && likely(!tp->repair))
-		tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr,
-							   inet->inet_daddr,
-							   inet->inet_sport,
-							   usin->sin_port,
-							   &tp->tsoffset);
+	if (likely(!tp->repair)) {
+		seq = secure_tcp_sequence_number(inet->inet_saddr,
+						 inet->inet_daddr,
+						 inet->inet_sport,
+						 usin->sin_port,
+						 &tp->tsoffset);
+		if (!tp->write_seq)
+			tp->write_seq = seq;
+	}
 
 	inet->inet_id = tp->write_seq ^ jiffies;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 21c719965b6b..60a5295a7de6 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -122,6 +122,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
+	u32 seq;
 	int err;
 	struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
@@ -285,12 +286,15 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	sk_set_txhash(sk);
 
-	if (!tp->write_seq && likely(!tp->repair))
-		tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
-							     sk->sk_v6_daddr.s6_addr32,
-							     inet->inet_sport,
-							     inet->inet_dport,
-							     &tp->tsoffset);
+	if (likely(!tp->repair)) {
+		seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
+						   sk->sk_v6_daddr.s6_addr32,
+						   inet->inet_sport,
+						   inet->inet_dport,
+						   &tp->tsoffset);
+		if (!tp->write_seq)
+			tp->write_seq = seq;
+	}
 
 	if (tcp_fastopen_defer_connect(sk, &err))
 		return err;
-- 
cgit 


From 45caeaa5ac0b4b11784ac6f932c0ad4c6b67cda0 Mon Sep 17 00:00:00 2001
From: Jon Maxwell <jmaxwell37@gmail.com>
Date: Fri, 10 Mar 2017 16:40:33 +1100
Subject: dccp/tcp: fix routing redirect race
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As Eric Dumazet pointed out this also needs to be fixed in IPv6.
v2: Contains the IPv6 tcp/Ipv6 dccp patches as well.

We have seen a few incidents lately where a dst_enty has been freed
with a dangling TCP socket reference (sk->sk_dst_cache) pointing to that
dst_entry. If the conditions/timings are right a crash then ensues when the
freed dst_entry is referenced later on. A Common crashing back trace is:

 #8 [] page_fault at ffffffff8163e648
    [exception RIP: __tcp_ack_snd_check+74]
.
.
 #9 [] tcp_rcv_established at ffffffff81580b64
#10 [] tcp_v4_do_rcv at ffffffff8158b54a
#11 [] tcp_v4_rcv at ffffffff8158cd02
#12 [] ip_local_deliver_finish at ffffffff815668f4
#13 [] ip_local_deliver at ffffffff81566bd9
#14 [] ip_rcv_finish at ffffffff8156656d
#15 [] ip_rcv at ffffffff81566f06
#16 [] __netif_receive_skb_core at ffffffff8152b3a2
#17 [] __netif_receive_skb at ffffffff8152b608
#18 [] netif_receive_skb at ffffffff8152b690
#19 [] vmxnet3_rq_rx_complete at ffffffffa015eeaf [vmxnet3]
#20 [] vmxnet3_poll_rx_only at ffffffffa015f32a [vmxnet3]
#21 [] net_rx_action at ffffffff8152bac2
#22 [] __do_softirq at ffffffff81084b4f
#23 [] call_softirq at ffffffff8164845c
#24 [] do_softirq at ffffffff81016fc5
#25 [] irq_exit at ffffffff81084ee5
#26 [] do_IRQ at ffffffff81648ff8

Of course it may happen with other NIC drivers as well.

It's found the freed dst_entry here:

 224 static bool tcp_in_quickack_mode(struct sock *sk)↩
 225 {↩
 226 ▹       const struct inet_connection_sock *icsk = inet_csk(sk);↩
 227 ▹       const struct dst_entry *dst = __sk_dst_get(sk);↩
 228 ↩
 229 ▹       return (dst && dst_metric(dst, RTAX_QUICKACK)) ||↩
 230 ▹       ▹       (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong);↩
 231 }↩

But there are other backtraces attributed to the same freed dst_entry in
netfilter code as well.

All the vmcores showed 2 significant clues:

- Remote hosts behind the default gateway had always been redirected to a
different gateway. A rtable/dst_entry will be added for that host. Making
more dst_entrys with lower reference counts. Making this more probable.

- All vmcores showed a postitive LockDroppedIcmps value, e.g:

LockDroppedIcmps                  267

A closer look at the tcp_v4_err() handler revealed that do_redirect() will run
regardless of whether user space has the socket locked. This can result in a
race condition where the same dst_entry cached in sk->sk_dst_entry can be
decremented twice for the same socket via:

do_redirect()->__sk_dst_check()-> dst_release().

Which leads to the dst_entry being prematurely freed with another socket
pointing to it via sk->sk_dst_cache and a subsequent crash.

To fix this skip do_redirect() if usespace has the socket locked. Instead let
the redirect take place later when user space does not have the socket
locked.

The dccp/IPv6 code is very similar in this respect, so fixing it there too.

As Eric Garver pointed out the following commit now invalidates routes. Which
can set the dst->obsolete flag so that ipv4_dst_check() returns null and
triggers the dst_release().

Fixes: ceb3320610d6 ("ipv4: Kill routes during PMTU/redirect updates.")
Cc: Eric Garver <egarver@redhat.com>
Cc: Hannes Sowa <hsowa@redhat.com>
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c     | 3 ++-
 net/dccp/ipv6.c     | 8 +++++---
 net/ipv4/tcp_ipv4.c | 3 ++-
 net/ipv6/tcp_ipv6.c | 8 +++++---
 4 files changed, 14 insertions(+), 8 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 409d0cfd3447..b99168b0fabf 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		dccp_do_redirect(skb, sk);
+		if (!sock_owned_by_user(sk))
+			dccp_do_redirect(skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 233b57367758..d9b6a4e403e7 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8f3ec1365497..575e19dcc017 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -431,7 +431,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		do_redirect(icmp_skb, sk);
+		if (!sock_owned_by_user(sk))
+			do_redirect(icmp_skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 60a5295a7de6..49fa2e8c3fa9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -391,10 +391,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
-- 
cgit