From 41063e9dd11956f2d285e12e4342e1d232ba0ea2 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 19 Jun 2012 21:22:05 -0700
Subject: ipv4: Early TCP socket demux.

Input packet processing for local sockets involves two major demuxes.
One for the route and one for the socket.

But we can optimize this down to one demux for certain kinds of local
sockets.

Currently we only do this for established TCP sockets, but it could
at least in theory be expanded to other kinds of connections.

If a TCP socket is established then it's identity is fully specified.

This means that whatever input route was used during the three-way
handshake must work equally well for the rest of the connection since
the keys will not change.

Once we move to established state, we cache the receive packet's input
route to use later.

Like the existing cached route in sk->sk_dst_cache used for output
packets, we have to check for route invalidations using dst->obsolete
and dst->ops->check().

Early demux occurs outside of a socket locked section, so when a route
invalidation occurs we defer the fixup of sk->sk_rx_dst until we are
actually inside of established state packet processing and thus have
the socket locked.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

(limited to 'net/ipv4/tcp_input.c')

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b224eb8bce8..8416f8a68e6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5518,6 +5518,18 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 	struct tcp_sock *tp = tcp_sk(sk);
 	int res;
 
+	if (sk->sk_rx_dst) {
+		struct dst_entry *dst = sk->sk_rx_dst;
+		if (unlikely(dst->obsolete)) {
+			if (dst->ops->check(dst, 0) == NULL) {
+				dst_release(dst);
+				sk->sk_rx_dst = NULL;
+			}
+		}
+	}
+	if (unlikely(sk->sk_rx_dst == NULL))
+		sk->sk_rx_dst = dst_clone(skb_dst(skb));
+
 	/*
 	 *	Header prediction.
 	 *	The code loosely follows the one in the famous
@@ -5729,8 +5741,10 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 
 	tcp_set_state(sk, TCP_ESTABLISHED);
 
-	if (skb != NULL)
+	if (skb != NULL) {
+		sk->sk_rx_dst = dst_clone(skb_dst(skb));
 		security_inet_conn_established(sk, skb);
+	}
 
 	/* Make sure socket is routed, for correct metrics.  */
 	icsk->icsk_af_ops->rebuild_header(sk);
-- 
cgit v1.2.3-70-g09d2


From 5110effee8fde2edfacac9cd12a9960ab2dc39ea Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 2 Jul 2012 02:21:03 -0700
Subject: net: Do delayed neigh confirmation.

When a dst_confirm() happens, mark the confirmation as pending in the
dst.  Then on the next packet out, when we have the neigh in-hand, do
the update.

This removes the dependency in dst_confirm() of dst's having an
attached neigh.

While we're here, remove the explicit 'dst' NULL check, all except 2
or 3 call sites ensure it's not NULL.  So just fix those cases up.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h       | 29 +++++++++++++++++++++--------
 include/net/neighbour.h | 15 ---------------
 net/core/dst.c          |  3 ++-
 net/ipv4/ip_output.c    |  2 +-
 net/ipv4/tcp_input.c    | 19 +++++++++++++------
 net/ipv6/ip6_output.c   |  2 +-
 6 files changed, 38 insertions(+), 32 deletions(-)

(limited to 'net/ipv4/tcp_input.c')

diff --git a/include/net/dst.h b/include/net/dst.h
index f0bf3b8d591..84e7a3ff968 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -51,7 +51,7 @@ struct dst_entry {
 	int			(*input)(struct sk_buff *);
 	int			(*output)(struct sk_buff *);
 
-	int			flags;
+	unsigned short		flags;
 #define DST_HOST		0x0001
 #define DST_NOXFRM		0x0002
 #define DST_NOPOLICY		0x0004
@@ -62,6 +62,8 @@ struct dst_entry {
 #define DST_FAKE_RTABLE		0x0080
 #define DST_XFRM_TUNNEL		0x0100
 
+	unsigned short		pending_confirm;
+
 	short			error;
 	short			obsolete;
 	unsigned short		header_len;	/* more space at head required */
@@ -371,7 +373,8 @@ static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb)
 
 extern int dst_discard(struct sk_buff *skb);
 extern void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
-		       int initial_ref, int initial_obsolete, int flags);
+		       int initial_ref, int initial_obsolete,
+		       unsigned short flags);
 extern void __dst_free(struct dst_entry *dst);
 extern struct dst_entry *dst_destroy(struct dst_entry *dst);
 
@@ -395,14 +398,24 @@ static inline void dst_rcu_free(struct rcu_head *head)
 
 static inline void dst_confirm(struct dst_entry *dst)
 {
-	if (dst) {
-		struct neighbour *n;
+	dst->pending_confirm = 1;
+}
 
-		rcu_read_lock();
-		n = dst_get_neighbour_noref(dst);
-		neigh_confirm(n);
-		rcu_read_unlock();
+static inline int dst_neigh_output(struct dst_entry *dst, struct neighbour *n,
+				   struct sk_buff *skb)
+{
+	struct hh_cache *hh;
+
+	if (unlikely(dst->pending_confirm)) {
+		n->confirmed = jiffies;
+		dst->pending_confirm = 0;
 	}
+
+	hh = &n->hh;
+	if ((n->nud_state & NUD_CONNECTED) && hh->hh_len)
+		return neigh_hh_output(hh, skb);
+	else
+		return n->output(n, skb);
 }
 
 static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, const void *daddr)
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index e1d18bdeebb..344d8988842 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -309,12 +309,6 @@ static inline struct neighbour * neigh_clone(struct neighbour *neigh)
 
 #define neigh_hold(n)	atomic_inc(&(n)->refcnt)
 
-static inline void neigh_confirm(struct neighbour *neigh)
-{
-	if (neigh)
-		neigh->confirmed = jiffies;
-}
-
 static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 {
 	unsigned long now = jiffies;
@@ -358,15 +352,6 @@ static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb)
 	return dev_queue_xmit(skb);
 }
 
-static inline int neigh_output(struct neighbour *n, struct sk_buff *skb)
-{
-	struct hh_cache *hh = &n->hh;
-	if ((n->nud_state & NUD_CONNECTED) && hh->hh_len)
-		return neigh_hh_output(hh, skb);
-	else
-		return n->output(n, skb);
-}
-
 static inline struct neighbour *
 __neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev, int creat)
 {
diff --git a/net/core/dst.c b/net/core/dst.c
index 43d94cedbf7..a6e19a23a74 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -152,7 +152,7 @@ EXPORT_SYMBOL(dst_discard);
 const u32 dst_default_metrics[RTAX_MAX];
 
 void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
-		int initial_ref, int initial_obsolete, int flags)
+		int initial_ref, int initial_obsolete, unsigned short flags)
 {
 	struct dst_entry *dst;
 
@@ -188,6 +188,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
 	dst->__use = 0;
 	dst->lastuse = jiffies;
 	dst->flags = flags;
+	dst->pending_confirm = 0;
 	dst->next = NULL;
 	if (!(flags & DST_NOCOUNT))
 		dst_entries_add(ops, 1);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 6e9a266a053..cc52679790b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -198,7 +198,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	if (unlikely(!neigh))
 		neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
 	if (neigh) {
-		int res = neigh_output(neigh, skb);
+		int res = dst_neigh_output(dst, neigh, skb);
 
 		rcu_read_unlock_bh();
 		return res;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8416f8a68e6..ca0d0e7c977 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -740,13 +740,13 @@ void tcp_update_metrics(struct sock *sk)
 	if (sysctl_tcp_nometrics_save)
 		return;
 
-	dst_confirm(dst);
-
 	if (dst && (dst->flags & DST_HOST)) {
 		const struct inet_connection_sock *icsk = inet_csk(sk);
 		int m;
 		unsigned long rtt;
 
+		dst_confirm(dst);
+
 		if (icsk->icsk_backoff || !tp->srtt) {
 			/* This session failed to estimate rtt. Why?
 			 * Probably, no packets returned in time.
@@ -3869,9 +3869,11 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 			tcp_cong_avoid(sk, ack, prior_in_flight);
 	}
 
-	if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
-		dst_confirm(__sk_dst_get(sk));
-
+	if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) {
+		struct dst_entry *dst = __sk_dst_get(sk);
+		if (dst)
+			dst_confirm(dst);
+	}
 	return 1;
 
 no_queue:
@@ -6140,9 +6142,14 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 
 		case TCP_FIN_WAIT1:
 			if (tp->snd_una == tp->write_seq) {
+				struct dst_entry *dst;
+
 				tcp_set_state(sk, TCP_FIN_WAIT2);
 				sk->sk_shutdown |= SEND_SHUTDOWN;
-				dst_confirm(__sk_dst_get(sk));
+
+				dst = __sk_dst_get(sk);
+				if (dst)
+					dst_confirm(dst);
 
 				if (!sock_flag(sk, SOCK_DEAD))
 					/* Wake up lingering close() */
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a233a7ccbc3..c94e4aabe11 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -125,7 +125,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
 	rcu_read_lock();
 	neigh = dst_get_neighbour_noref(dst);
 	if (neigh) {
-		int res = neigh_output(neigh, skb);
+		int res = dst_neigh_output(dst, neigh, skb);
 
 		rcu_read_unlock();
 		return res;
-- 
cgit v1.2.3-70-g09d2


From 4aabd8ef8c43677cfee3e1e36c5a79edddb41942 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 9 Jul 2012 16:07:30 -0700
Subject: tcp: Move dynamnic metrics handling into seperate file.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h      |   4 ++
 net/ipv4/Makefile      |   2 +-
 net/ipv4/tcp_input.c   | 188 +-----------------------------------------------
 net/ipv4/tcp_metrics.c | 192 +++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 199 insertions(+), 187 deletions(-)
 create mode 100644 net/ipv4/tcp_metrics.c

(limited to 'net/ipv4/tcp_input.c')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 53fb7d81417..98ca797001a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -388,6 +388,8 @@ extern void tcp_enter_frto(struct sock *sk);
 extern void tcp_enter_loss(struct sock *sk, int how);
 extern void tcp_clear_retrans(struct tcp_sock *tp);
 extern void tcp_update_metrics(struct sock *sk);
+extern void tcp_init_metrics(struct sock *sk);
+extern void tcp_disable_fack(struct tcp_sock *tp);
 extern void tcp_close(struct sock *sk, long timeout);
 extern void tcp_init_sock(struct sock *sk);
 extern unsigned int tcp_poll(struct file * file, struct socket *sock,
@@ -556,6 +558,8 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
 	return (tp->srtt >> 3) + tp->rttvar;
 }
 
+extern void tcp_set_rto(struct sock *sk);
+
 static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
 {
 	tp->pred_flags = htonl((tp->tcp_header_len << 26) |
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index ff75d3bbcd6..5a23e8b3710 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -7,7 +7,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     ip_output.o ip_sockglue.o inet_hashtables.o \
 	     inet_timewait_sock.o inet_connection_sock.o \
 	     tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
-	     tcp_minisocks.o tcp_cong.o \
+	     tcp_minisocks.o tcp_cong.o tcp_metrics.o \
 	     datagram.o raw.o udp.o udplite.o \
 	     arp.o icmp.o devinet.o af_inet.o  igmp.o \
 	     fib_frontend.o fib_semantics.o fib_trie.o \
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ca0d0e7c977..055ac49b8b4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -93,7 +93,6 @@ int sysctl_tcp_rfc1337 __read_mostly;
 int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 int sysctl_tcp_frto __read_mostly = 2;
 int sysctl_tcp_frto_response __read_mostly;
-int sysctl_tcp_nometrics_save __read_mostly;
 
 int sysctl_tcp_thin_dupack __read_mostly;
 
@@ -701,7 +700,7 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
 /* Calculate rto without backoff.  This is the second half of Van Jacobson's
  * routine referred to above.
  */
-static inline void tcp_set_rto(struct sock *sk)
+void tcp_set_rto(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	/* Old crap is replaced with new one. 8)
@@ -728,109 +727,6 @@ static inline void tcp_set_rto(struct sock *sk)
 	tcp_bound_rto(sk);
 }
 
-/* Save metrics learned by this TCP session.
-   This function is called only, when TCP finishes successfully
-   i.e. when it enters TIME-WAIT or goes from LAST-ACK to CLOSE.
- */
-void tcp_update_metrics(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct dst_entry *dst = __sk_dst_get(sk);
-
-	if (sysctl_tcp_nometrics_save)
-		return;
-
-	if (dst && (dst->flags & DST_HOST)) {
-		const struct inet_connection_sock *icsk = inet_csk(sk);
-		int m;
-		unsigned long rtt;
-
-		dst_confirm(dst);
-
-		if (icsk->icsk_backoff || !tp->srtt) {
-			/* This session failed to estimate rtt. Why?
-			 * Probably, no packets returned in time.
-			 * Reset our results.
-			 */
-			if (!(dst_metric_locked(dst, RTAX_RTT)))
-				dst_metric_set(dst, RTAX_RTT, 0);
-			return;
-		}
-
-		rtt = dst_metric_rtt(dst, RTAX_RTT);
-		m = rtt - tp->srtt;
-
-		/* If newly calculated rtt larger than stored one,
-		 * store new one. Otherwise, use EWMA. Remember,
-		 * rtt overestimation is always better than underestimation.
-		 */
-		if (!(dst_metric_locked(dst, RTAX_RTT))) {
-			if (m <= 0)
-				set_dst_metric_rtt(dst, RTAX_RTT, tp->srtt);
-			else
-				set_dst_metric_rtt(dst, RTAX_RTT, rtt - (m >> 3));
-		}
-
-		if (!(dst_metric_locked(dst, RTAX_RTTVAR))) {
-			unsigned long var;
-			if (m < 0)
-				m = -m;
-
-			/* Scale deviation to rttvar fixed point */
-			m >>= 1;
-			if (m < tp->mdev)
-				m = tp->mdev;
-
-			var = dst_metric_rtt(dst, RTAX_RTTVAR);
-			if (m >= var)
-				var = m;
-			else
-				var -= (var - m) >> 2;
-
-			set_dst_metric_rtt(dst, RTAX_RTTVAR, var);
-		}
-
-		if (tcp_in_initial_slowstart(tp)) {
-			/* Slow start still did not finish. */
-			if (dst_metric(dst, RTAX_SSTHRESH) &&
-			    !dst_metric_locked(dst, RTAX_SSTHRESH) &&
-			    (tp->snd_cwnd >> 1) > dst_metric(dst, RTAX_SSTHRESH))
-				dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_cwnd >> 1);
-			if (!dst_metric_locked(dst, RTAX_CWND) &&
-			    tp->snd_cwnd > dst_metric(dst, RTAX_CWND))
-				dst_metric_set(dst, RTAX_CWND, tp->snd_cwnd);
-		} else if (tp->snd_cwnd > tp->snd_ssthresh &&
-			   icsk->icsk_ca_state == TCP_CA_Open) {
-			/* Cong. avoidance phase, cwnd is reliable. */
-			if (!dst_metric_locked(dst, RTAX_SSTHRESH))
-				dst_metric_set(dst, RTAX_SSTHRESH,
-					       max(tp->snd_cwnd >> 1, tp->snd_ssthresh));
-			if (!dst_metric_locked(dst, RTAX_CWND))
-				dst_metric_set(dst, RTAX_CWND,
-					       (dst_metric(dst, RTAX_CWND) +
-						tp->snd_cwnd) >> 1);
-		} else {
-			/* Else slow start did not finish, cwnd is non-sense,
-			   ssthresh may be also invalid.
-			 */
-			if (!dst_metric_locked(dst, RTAX_CWND))
-				dst_metric_set(dst, RTAX_CWND,
-					       (dst_metric(dst, RTAX_CWND) +
-						tp->snd_ssthresh) >> 1);
-			if (dst_metric(dst, RTAX_SSTHRESH) &&
-			    !dst_metric_locked(dst, RTAX_SSTHRESH) &&
-			    tp->snd_ssthresh > dst_metric(dst, RTAX_SSTHRESH))
-				dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_ssthresh);
-		}
-
-		if (!dst_metric_locked(dst, RTAX_REORDERING)) {
-			if (dst_metric(dst, RTAX_REORDERING) < tp->reordering &&
-			    tp->reordering != sysctl_tcp_reordering)
-				dst_metric_set(dst, RTAX_REORDERING, tp->reordering);
-		}
-	}
-}
-
 __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst)
 {
 	__u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0);
@@ -867,7 +763,7 @@ void tcp_enter_cwr(struct sock *sk, const int set_ssthresh)
  * Packet counting of FACK is based on in-order assumptions, therefore TCP
  * disables it when reordering is detected
  */
-static void tcp_disable_fack(struct tcp_sock *tp)
+void tcp_disable_fack(struct tcp_sock *tp)
 {
 	/* RFC3517 uses different metric in lost marker => reset on change */
 	if (tcp_is_fack(tp))
@@ -881,86 +777,6 @@ static void tcp_dsack_seen(struct tcp_sock *tp)
 	tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
 }
 
-/* Initialize metrics on socket. */
-
-static void tcp_init_metrics(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct dst_entry *dst = __sk_dst_get(sk);
-
-	if (dst == NULL)
-		goto reset;
-
-	dst_confirm(dst);
-
-	if (dst_metric_locked(dst, RTAX_CWND))
-		tp->snd_cwnd_clamp = dst_metric(dst, RTAX_CWND);
-	if (dst_metric(dst, RTAX_SSTHRESH)) {
-		tp->snd_ssthresh = dst_metric(dst, RTAX_SSTHRESH);
-		if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
-			tp->snd_ssthresh = tp->snd_cwnd_clamp;
-	} else {
-		/* ssthresh may have been reduced unnecessarily during.
-		 * 3WHS. Restore it back to its initial default.
-		 */
-		tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
-	}
-	if (dst_metric(dst, RTAX_REORDERING) &&
-	    tp->reordering != dst_metric(dst, RTAX_REORDERING)) {
-		tcp_disable_fack(tp);
-		tcp_disable_early_retrans(tp);
-		tp->reordering = dst_metric(dst, RTAX_REORDERING);
-	}
-
-	if (dst_metric(dst, RTAX_RTT) == 0 || tp->srtt == 0)
-		goto reset;
-
-	/* Initial rtt is determined from SYN,SYN-ACK.
-	 * The segment is small and rtt may appear much
-	 * less than real one. Use per-dst memory
-	 * to make it more realistic.
-	 *
-	 * A bit of theory. RTT is time passed after "normal" sized packet
-	 * is sent until it is ACKed. In normal circumstances sending small
-	 * packets force peer to delay ACKs and calculation is correct too.
-	 * The algorithm is adaptive and, provided we follow specs, it
-	 * NEVER underestimate RTT. BUT! If peer tries to make some clever
-	 * tricks sort of "quick acks" for time long enough to decrease RTT
-	 * to low value, and then abruptly stops to do it and starts to delay
-	 * ACKs, wait for troubles.
-	 */
-	if (dst_metric_rtt(dst, RTAX_RTT) > tp->srtt) {
-		tp->srtt = dst_metric_rtt(dst, RTAX_RTT);
-		tp->rtt_seq = tp->snd_nxt;
-	}
-	if (dst_metric_rtt(dst, RTAX_RTTVAR) > tp->mdev) {
-		tp->mdev = dst_metric_rtt(dst, RTAX_RTTVAR);
-		tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
-	}
-	tcp_set_rto(sk);
-reset:
-	if (tp->srtt == 0) {
-		/* RFC6298: 5.7 We've failed to get a valid RTT sample from
-		 * 3WHS. This is most likely due to retransmission,
-		 * including spurious one. Reset the RTO back to 3secs
-		 * from the more aggressive 1sec to avoid more spurious
-		 * retransmission.
-		 */
-		tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK;
-		inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK;
-	}
-	/* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been
-	 * retransmitted. In light of RFC6298 more aggressive 1sec
-	 * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK
-	 * retransmission has occurred.
-	 */
-	if (tp->total_retrans > 1)
-		tp->snd_cwnd = 1;
-	else
-		tp->snd_cwnd = tcp_init_cwnd(tp, dst);
-	tp->snd_cwnd_stamp = tcp_time_stamp;
-}
-
 static void tcp_update_reordering(struct sock *sk, const int metric,
 				  const int ts)
 {
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
new file mode 100644
index 00000000000..2793ecf928d
--- /dev/null
+++ b/net/ipv4/tcp_metrics.c
@@ -0,0 +1,192 @@
+#include <linux/cache.h>
+#include <linux/tcp.h>
+
+#include <net/inet_connection_sock.h>
+#include <net/sock.h>
+#include <net/dst.h>
+#include <net/tcp.h>
+
+int sysctl_tcp_nometrics_save __read_mostly;
+
+/* Save metrics learned by this TCP session.  This function is called
+ * only, when TCP finishes successfully i.e. when it enters TIME-WAIT
+ * or goes from LAST-ACK to CLOSE.
+ */
+void tcp_update_metrics(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct dst_entry *dst = __sk_dst_get(sk);
+
+	if (sysctl_tcp_nometrics_save)
+		return;
+
+	if (dst && (dst->flags & DST_HOST)) {
+		const struct inet_connection_sock *icsk = inet_csk(sk);
+		int m;
+		unsigned long rtt;
+
+		dst_confirm(dst);
+
+		if (icsk->icsk_backoff || !tp->srtt) {
+			/* This session failed to estimate rtt. Why?
+			 * Probably, no packets returned in time.
+			 * Reset our results.
+			 */
+			if (!(dst_metric_locked(dst, RTAX_RTT)))
+				dst_metric_set(dst, RTAX_RTT, 0);
+			return;
+		}
+
+		rtt = dst_metric_rtt(dst, RTAX_RTT);
+		m = rtt - tp->srtt;
+
+		/* If newly calculated rtt larger than stored one,
+		 * store new one. Otherwise, use EWMA. Remember,
+		 * rtt overestimation is always better than underestimation.
+		 */
+		if (!(dst_metric_locked(dst, RTAX_RTT))) {
+			if (m <= 0)
+				set_dst_metric_rtt(dst, RTAX_RTT, tp->srtt);
+			else
+				set_dst_metric_rtt(dst, RTAX_RTT, rtt - (m >> 3));
+		}
+
+		if (!(dst_metric_locked(dst, RTAX_RTTVAR))) {
+			unsigned long var;
+			if (m < 0)
+				m = -m;
+
+			/* Scale deviation to rttvar fixed point */
+			m >>= 1;
+			if (m < tp->mdev)
+				m = tp->mdev;
+
+			var = dst_metric_rtt(dst, RTAX_RTTVAR);
+			if (m >= var)
+				var = m;
+			else
+				var -= (var - m) >> 2;
+
+			set_dst_metric_rtt(dst, RTAX_RTTVAR, var);
+		}
+
+		if (tcp_in_initial_slowstart(tp)) {
+			/* Slow start still did not finish. */
+			if (dst_metric(dst, RTAX_SSTHRESH) &&
+			    !dst_metric_locked(dst, RTAX_SSTHRESH) &&
+			    (tp->snd_cwnd >> 1) > dst_metric(dst, RTAX_SSTHRESH))
+				dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_cwnd >> 1);
+			if (!dst_metric_locked(dst, RTAX_CWND) &&
+			    tp->snd_cwnd > dst_metric(dst, RTAX_CWND))
+				dst_metric_set(dst, RTAX_CWND, tp->snd_cwnd);
+		} else if (tp->snd_cwnd > tp->snd_ssthresh &&
+			   icsk->icsk_ca_state == TCP_CA_Open) {
+			/* Cong. avoidance phase, cwnd is reliable. */
+			if (!dst_metric_locked(dst, RTAX_SSTHRESH))
+				dst_metric_set(dst, RTAX_SSTHRESH,
+					       max(tp->snd_cwnd >> 1, tp->snd_ssthresh));
+			if (!dst_metric_locked(dst, RTAX_CWND))
+				dst_metric_set(dst, RTAX_CWND,
+					       (dst_metric(dst, RTAX_CWND) +
+						tp->snd_cwnd) >> 1);
+		} else {
+			/* Else slow start did not finish, cwnd is non-sense,
+			   ssthresh may be also invalid.
+			 */
+			if (!dst_metric_locked(dst, RTAX_CWND))
+				dst_metric_set(dst, RTAX_CWND,
+					       (dst_metric(dst, RTAX_CWND) +
+						tp->snd_ssthresh) >> 1);
+			if (dst_metric(dst, RTAX_SSTHRESH) &&
+			    !dst_metric_locked(dst, RTAX_SSTHRESH) &&
+			    tp->snd_ssthresh > dst_metric(dst, RTAX_SSTHRESH))
+				dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_ssthresh);
+		}
+
+		if (!dst_metric_locked(dst, RTAX_REORDERING)) {
+			if (dst_metric(dst, RTAX_REORDERING) < tp->reordering &&
+			    tp->reordering != sysctl_tcp_reordering)
+				dst_metric_set(dst, RTAX_REORDERING, tp->reordering);
+		}
+	}
+}
+
+/* Initialize metrics on socket. */
+
+void tcp_init_metrics(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct dst_entry *dst = __sk_dst_get(sk);
+
+	if (dst == NULL)
+		goto reset;
+
+	dst_confirm(dst);
+
+	if (dst_metric_locked(dst, RTAX_CWND))
+		tp->snd_cwnd_clamp = dst_metric(dst, RTAX_CWND);
+	if (dst_metric(dst, RTAX_SSTHRESH)) {
+		tp->snd_ssthresh = dst_metric(dst, RTAX_SSTHRESH);
+		if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
+			tp->snd_ssthresh = tp->snd_cwnd_clamp;
+	} else {
+		/* ssthresh may have been reduced unnecessarily during.
+		 * 3WHS. Restore it back to its initial default.
+		 */
+		tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
+	}
+	if (dst_metric(dst, RTAX_REORDERING) &&
+	    tp->reordering != dst_metric(dst, RTAX_REORDERING)) {
+		tcp_disable_fack(tp);
+		tcp_disable_early_retrans(tp);
+		tp->reordering = dst_metric(dst, RTAX_REORDERING);
+	}
+
+	if (dst_metric(dst, RTAX_RTT) == 0 || tp->srtt == 0)
+		goto reset;
+
+	/* Initial rtt is determined from SYN,SYN-ACK.
+	 * The segment is small and rtt may appear much
+	 * less than real one. Use per-dst memory
+	 * to make it more realistic.
+	 *
+	 * A bit of theory. RTT is time passed after "normal" sized packet
+	 * is sent until it is ACKed. In normal circumstances sending small
+	 * packets force peer to delay ACKs and calculation is correct too.
+	 * The algorithm is adaptive and, provided we follow specs, it
+	 * NEVER underestimate RTT. BUT! If peer tries to make some clever
+	 * tricks sort of "quick acks" for time long enough to decrease RTT
+	 * to low value, and then abruptly stops to do it and starts to delay
+	 * ACKs, wait for troubles.
+	 */
+	if (dst_metric_rtt(dst, RTAX_RTT) > tp->srtt) {
+		tp->srtt = dst_metric_rtt(dst, RTAX_RTT);
+		tp->rtt_seq = tp->snd_nxt;
+	}
+	if (dst_metric_rtt(dst, RTAX_RTTVAR) > tp->mdev) {
+		tp->mdev = dst_metric_rtt(dst, RTAX_RTTVAR);
+		tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
+	}
+	tcp_set_rto(sk);
+reset:
+	if (tp->srtt == 0) {
+		/* RFC6298: 5.7 We've failed to get a valid RTT sample from
+		 * 3WHS. This is most likely due to retransmission,
+		 * including spurious one. Reset the RTO back to 3secs
+		 * from the more aggressive 1sec to avoid more spurious
+		 * retransmission.
+		 */
+		tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK;
+		inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK;
+	}
+	/* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been
+	 * retransmitted. In light of RFC6298 more aggressive 1sec
+	 * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK
+	 * retransmission has occurred.
+	 */
+	if (tp->total_retrans > 1)
+		tp->snd_cwnd = 1;
+	else
+		tp->snd_cwnd = tcp_init_cwnd(tp, dst);
+	tp->snd_cwnd_stamp = tcp_time_stamp;
+}
-- 
cgit v1.2.3-70-g09d2


From a6df1ae9383697c4eb1365176002f154982325ad Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 16 Jul 2012 01:41:36 +0000
Subject: tcp: add OFO snmp counters

Add three SNMP TCP counters, to better track TCP behavior
at global stage (netstat -s), when packets are received
Out Of Order (OFO)

TCPOFOQueue : Number of packets queued in OFO queue

TCPOFODrop  : Number of packets meant to be queued in OFO
              but dropped because socket rcvbuf limit hit.

TCPOFOMerge : Number of packets in OFO that were merged with
              other packets.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/snmp.h | 5 ++++-
 net/ipv4/proc.c      | 3 +++
 net/ipv4/tcp_input.c | 7 +++++--
 3 files changed, 12 insertions(+), 3 deletions(-)

(limited to 'net/ipv4/tcp_input.c')

diff --git a/include/linux/snmp.h b/include/linux/snmp.h
index 2e68f5ba038..6e4c5112382 100644
--- a/include/linux/snmp.h
+++ b/include/linux/snmp.h
@@ -233,7 +233,10 @@ enum
 	LINUX_MIB_TCPREQQFULLDOCOOKIES,		/* TCPReqQFullDoCookies */
 	LINUX_MIB_TCPREQQFULLDROP,		/* TCPReqQFullDrop */
 	LINUX_MIB_TCPRETRANSFAIL,		/* TCPRetransFail */
-	LINUX_MIB_TCPRCVCOALESCE,			/* TCPRcvCoalesce */
+	LINUX_MIB_TCPRCVCOALESCE,		/* TCPRcvCoalesce */
+	LINUX_MIB_TCPOFOQUEUE,			/* TCPOFOQueue */
+	LINUX_MIB_TCPOFODROP,			/* TCPOFODrop */
+	LINUX_MIB_TCPOFOMERGE,			/* TCPOFOMerge */
 	__LINUX_MIB_MAX
 };
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 8af0d44e4e2..dae25e7622c 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -258,6 +258,9 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPReqQFullDrop", LINUX_MIB_TCPREQQFULLDROP),
 	SNMP_MIB_ITEM("TCPRetransFail", LINUX_MIB_TCPRETRANSFAIL),
 	SNMP_MIB_ITEM("TCPRcvCoalesce", LINUX_MIB_TCPRCVCOALESCE),
+	SNMP_MIB_ITEM("TCPOFOQueue", LINUX_MIB_TCPOFOQUEUE),
+	SNMP_MIB_ITEM("TCPOFODrop", LINUX_MIB_TCPOFODROP),
+	SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 055ac49b8b4..cc4e12f1f2f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4397,8 +4397,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 
 	TCP_ECN_check_ce(tp, skb);
 
-	if (tcp_try_rmem_schedule(sk, skb->truesize)) {
-		/* TODO: should increment a counter */
+	if (unlikely(tcp_try_rmem_schedule(sk, skb->truesize))) {
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP);
 		__kfree_skb(skb);
 		return;
 	}
@@ -4407,6 +4407,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	tp->pred_flags = 0;
 	inet_csk_schedule_ack(sk);
 
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOQUEUE);
 	SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n",
 		   tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
 
@@ -4460,6 +4461,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) {
 		if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
 			/* All the bits are present. Drop. */
+			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE);
 			__kfree_skb(skb);
 			skb = NULL;
 			tcp_dsack_set(sk, seq, end_seq);
@@ -4498,6 +4500,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		__skb_unlink(skb1, &tp->out_of_order_queue);
 		tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
 				 TCP_SKB_CB(skb1)->end_seq);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE);
 		__kfree_skb(skb1);
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 282f23c6ee343126156dd41218b22ece96d747e3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 17 Jul 2012 10:13:05 +0200
Subject: tcp: implement RFC 5961 3.2

Implement the RFC 5691 mitigation against Blind
Reset attack using RST bit.

Idea is to validate incoming RST sequence,
to match RCV.NXT value, instead of previouly accepted
window : (RCV.NXT <= SEG.SEQ < RCV.NXT+RCV.WND)

If sequence is in window but not an exact match, send
a "challenge ACK", so that the other part can resend an
RST with the appropriate sequence.

Add a new sysctl, tcp_challenge_ack_limit, to limit
number of challenge ACK sent per second.

Add a new SNMP counter to count number of challenge acks sent.
(netstat -s | grep TCPChallengeACK)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kiran Kumar Kella <kkiran@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  5 +++++
 include/linux/snmp.h                   |  1 +
 include/net/tcp.h                      |  1 +
 net/ipv4/proc.c                        |  1 +
 net/ipv4/sysctl_net_ipv4.c             |  7 +++++++
 net/ipv4/tcp_input.c                   | 31 ++++++++++++++++++++++++++++++-
 6 files changed, 45 insertions(+), 1 deletion(-)

(limited to 'net/ipv4/tcp_input.c')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index e20c17a7d34..e1e021594cf 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -565,6 +565,11 @@ tcp_limit_output_bytes - INTEGER
 	reduce the size of individual GSO packet (64KB being the max)
 	Default: 131072
 
+tcp_challenge_ack_limit - INTEGER
+	Limits number of Challenge ACK sent per second, as recommended
+	in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks)
+	Default: 100
+
 UDP variables:
 
 udp_mem - vector of 3 INTEGERs: min, pressure, max
diff --git a/include/linux/snmp.h b/include/linux/snmp.h
index 6e4c5112382..673e0e928b2 100644
--- a/include/linux/snmp.h
+++ b/include/linux/snmp.h
@@ -237,6 +237,7 @@ enum
 	LINUX_MIB_TCPOFOQUEUE,			/* TCPOFOQueue */
 	LINUX_MIB_TCPOFODROP,			/* TCPOFODrop */
 	LINUX_MIB_TCPOFOMERGE,			/* TCPOFOMerge */
+	LINUX_MIB_TCPCHALLENGEACK,		/* TCPChallengeACK */
 	__LINUX_MIB_MAX
 };
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 439984b9af4..85c5090bfe2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -254,6 +254,7 @@ extern int sysctl_tcp_thin_linear_timeouts;
 extern int sysctl_tcp_thin_dupack;
 extern int sysctl_tcp_early_retrans;
 extern int sysctl_tcp_limit_output_bytes;
+extern int sysctl_tcp_challenge_ack_limit;
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index dae25e7622c..3e8e78f12a3 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -261,6 +261,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPOFOQueue", LINUX_MIB_TCPOFOQUEUE),
 	SNMP_MIB_ITEM("TCPOFODrop", LINUX_MIB_TCPOFODROP),
 	SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE),
+	SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 70730f7aeaf..3f6a1e762e9 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -605,6 +605,13 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tcp_challenge_ack_limit",
+		.data		= &sysctl_tcp_challenge_ack_limit,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 #ifdef CONFIG_NET_DMA
 	{
 		.procname	= "tcp_dma_copybreak",
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cc4e12f1f2f..c841a899037 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -88,6 +88,9 @@ int sysctl_tcp_app_win __read_mostly = 31;
 int sysctl_tcp_adv_win_scale __read_mostly = 1;
 EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
 
+/* rfc5961 challenge ack rate limiting */
+int sysctl_tcp_challenge_ack_limit = 100;
+
 int sysctl_tcp_stdurg __read_mostly;
 int sysctl_tcp_rfc1337 __read_mostly;
 int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
@@ -5247,6 +5250,23 @@ out:
 }
 #endif /* CONFIG_NET_DMA */
 
+static void tcp_send_challenge_ack(struct sock *sk)
+{
+	/* unprotected vars, we dont care of overwrites */
+	static u32 challenge_timestamp;
+	static unsigned int challenge_count;
+	u32 now = jiffies / HZ;
+
+	if (now != challenge_timestamp) {
+		challenge_timestamp = now;
+		challenge_count = 0;
+	}
+	if (++challenge_count <= sysctl_tcp_challenge_ack_limit) {
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
+		tcp_send_ack(sk);
+	}
+}
+
 /* Does PAWS and seqno based validation of an incoming segment, flags will
  * play significant role here.
  */
@@ -5283,7 +5303,16 @@ static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 
 	/* Step 2: check RST bit */
 	if (th->rst) {
-		tcp_reset(sk);
+		/* RFC 5961 3.2 :
+		 * If sequence number exactly matches RCV.NXT, then
+		 *     RESET the connection
+		 * else
+		 *     Send a challenge ACK
+		 */
+		if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt)
+			tcp_reset(sk);
+		else
+			tcp_send_challenge_ack(sk);
 		goto discard;
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 0c24604b68fc7810d429d6c3657b6f148270e528 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 17 Jul 2012 01:41:30 +0000
Subject: tcp: implement RFC 5961 4.2

Implement the RFC 5691 mitigation against Blind
Reset attack using SYN bit.

Section 4.2 of RFC 5961 advises to send a Challenge ACK and drop
incoming packet, instead of resetting the session.

Add a new SNMP counter to count number of challenge acks sent
in response to SYN packets.
(netstat -s | grep TCPSYNChallenge)

Remove obsolete TCPAbortOnSyn, since we no longer abort a TCP session
because of a SYN flag.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kiran Kumar Kella <kkiran@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/snmp.h |  2 +-
 net/ipv4/proc.c      |  2 +-
 net/ipv4/tcp_input.c | 32 +++++++++++++++-----------------
 3 files changed, 17 insertions(+), 19 deletions(-)

(limited to 'net/ipv4/tcp_input.c')

diff --git a/include/linux/snmp.h b/include/linux/snmp.h
index 673e0e928b2..e5fcbd079e4 100644
--- a/include/linux/snmp.h
+++ b/include/linux/snmp.h
@@ -208,7 +208,6 @@ enum
 	LINUX_MIB_TCPDSACKOFOSENT,		/* TCPDSACKOfoSent */
 	LINUX_MIB_TCPDSACKRECV,			/* TCPDSACKRecv */
 	LINUX_MIB_TCPDSACKOFORECV,		/* TCPDSACKOfoRecv */
-	LINUX_MIB_TCPABORTONSYN,		/* TCPAbortOnSyn */
 	LINUX_MIB_TCPABORTONDATA,		/* TCPAbortOnData */
 	LINUX_MIB_TCPABORTONCLOSE,		/* TCPAbortOnClose */
 	LINUX_MIB_TCPABORTONMEMORY,		/* TCPAbortOnMemory */
@@ -238,6 +237,7 @@ enum
 	LINUX_MIB_TCPOFODROP,			/* TCPOFODrop */
 	LINUX_MIB_TCPOFOMERGE,			/* TCPOFOMerge */
 	LINUX_MIB_TCPCHALLENGEACK,		/* TCPChallengeACK */
+	LINUX_MIB_TCPSYNCHALLENGE,		/* TCPSYNChallenge */
 	__LINUX_MIB_MAX
 };
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 3e8e78f12a3..2a5240b2ea6 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -232,7 +232,6 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPDSACKOfoSent", LINUX_MIB_TCPDSACKOFOSENT),
 	SNMP_MIB_ITEM("TCPDSACKRecv", LINUX_MIB_TCPDSACKRECV),
 	SNMP_MIB_ITEM("TCPDSACKOfoRecv", LINUX_MIB_TCPDSACKOFORECV),
-	SNMP_MIB_ITEM("TCPAbortOnSyn", LINUX_MIB_TCPABORTONSYN),
 	SNMP_MIB_ITEM("TCPAbortOnData", LINUX_MIB_TCPABORTONDATA),
 	SNMP_MIB_ITEM("TCPAbortOnClose", LINUX_MIB_TCPABORTONCLOSE),
 	SNMP_MIB_ITEM("TCPAbortOnMemory", LINUX_MIB_TCPABORTONMEMORY),
@@ -262,6 +261,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPOFODrop", LINUX_MIB_TCPOFODROP),
 	SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE),
 	SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK),
+	SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c841a899037..8aaec553611 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5270,8 +5270,8 @@ static void tcp_send_challenge_ack(struct sock *sk)
 /* Does PAWS and seqno based validation of an incoming segment, flags will
  * play significant role here.
  */
-static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
-			      const struct tcphdr *th, int syn_inerr)
+static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
+				  const struct tcphdr *th, int syn_inerr)
 {
 	const u8 *hash_location;
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -5323,20 +5323,22 @@ static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 
 	/* step 3: check security and precedence [ignored] */
 
-	/* step 4: Check for a SYN in window. */
-	if (th->syn && !before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
+	/* step 4: Check for a SYN
+	 * RFC 5691 4.2 : Send a challenge ack
+	 */
+	if (th->syn) {
 		if (syn_inerr)
 			TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONSYN);
-		tcp_reset(sk);
-		return -1;
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE);
+		tcp_send_challenge_ack(sk);
+		goto discard;
 	}
 
-	return 1;
+	return true;
 
 discard:
 	__kfree_skb(skb);
-	return 0;
+	return false;
 }
 
 /*
@@ -5366,7 +5368,6 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			const struct tcphdr *th, unsigned int len)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	int res;
 
 	if (sk->sk_rx_dst) {
 		struct dst_entry *dst = sk->sk_rx_dst;
@@ -5555,9 +5556,8 @@ slow_path:
 	 *	Standard slow path.
 	 */
 
-	res = tcp_validate_incoming(sk, skb, th, 1);
-	if (res <= 0)
-		return -res;
+	if (!tcp_validate_incoming(sk, skb, th, 1))
+		return 0;
 
 step5:
 	if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0)
@@ -5877,7 +5877,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int queued = 0;
-	int res;
 
 	tp->rx_opt.saw_tstamp = 0;
 
@@ -5932,9 +5931,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 		return 0;
 	}
 
-	res = tcp_validate_incoming(sk, skb, th, 0);
-	if (res <= 0)
-		return -res;
+	if (!tcp_validate_incoming(sk, skb, th, 0))
+		return 0;
 
 	/* step 5: check the ACK field */
 	if (th->ack) {
-- 
cgit v1.2.3-70-g09d2


From e371589917011efe6ff8c7dfb4e9e81934ac5855 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 17 Jul 2012 12:29:30 +0000
Subject: tcp: refine SYN handling in tcp_validate_incoming

Followup of commit 0c24604b68fc (tcp: implement RFC 5961 4.2)

As reported by Vijay Subramanian, we should send a challenge ACK
instead of a dup ack if a SYN flag is set on a packet received out of
window.

This permits the ratelimiting to work as intended, and to increase
correct SNMP counters.

Suggested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Kiran Kumar Kella <kkiran@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'net/ipv4/tcp_input.c')

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8aaec553611..fdd49f1b7a5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5296,8 +5296,11 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		 * an acknowledgment should be sent in reply (unless the RST
 		 * bit is set, if so drop the segment and return)".
 		 */
-		if (!th->rst)
+		if (!th->rst) {
+			if (th->syn)
+				goto syn_challenge;
 			tcp_send_dupack(sk, skb);
+		}
 		goto discard;
 	}
 
@@ -5327,6 +5330,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 	 * RFC 5691 4.2 : Send a challenge ack
 	 */
 	if (th->syn) {
+syn_challenge:
 		if (syn_inerr)
 			TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE);
-- 
cgit v1.2.3-70-g09d2


From 2100c8d2d9db23c0a09901a782bb4e3b21bee298 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 19 Jul 2012 06:43:05 +0000
Subject: net-tcp: Fast Open base

This patch impelements the common code for both the client and server.

1. TCP Fast Open option processing. Since Fast Open does not have an
   option number assigned by IANA yet, it shares the experiment option
   code 254 by implementing draft-ietf-tcpm-experimental-options
   with a 16 bits magic number 0xF989. This enables global experiments
   without clashing the scarce(2) experimental options available for TCP.

   When the draft status becomes standard (maybe), the client should
   switch to the new option number assigned while the server supports
   both numbers for transistion.

2. The new sysctl tcp_fastopen

3. A place holder init function

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h        | 10 ++++++++++
 include/net/tcp.h          |  9 ++++++++-
 net/ipv4/Makefile          |  2 +-
 net/ipv4/syncookies.c      |  2 +-
 net/ipv4/sysctl_net_ipv4.c |  7 +++++++
 net/ipv4/tcp_fastopen.c    | 11 +++++++++++
 net/ipv4/tcp_input.c       | 26 ++++++++++++++++++++++----
 net/ipv4/tcp_ipv4.c        |  2 +-
 net/ipv4/tcp_minisocks.c   |  4 ++--
 net/ipv4/tcp_output.c      | 25 +++++++++++++++++++++----
 net/ipv6/syncookies.c      |  2 +-
 net/ipv6/tcp_ipv6.c        |  2 +-
 12 files changed, 86 insertions(+), 16 deletions(-)
 create mode 100644 net/ipv4/tcp_fastopen.c

(limited to 'net/ipv4/tcp_input.c')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 1888169e07c..12948f54383 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -243,6 +243,16 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb)
 	return (tcp_hdr(skb)->doff - 5) * 4;
 }
 
+/* TCP Fast Open */
+#define TCP_FASTOPEN_COOKIE_MIN	4	/* Min Fast Open Cookie size in bytes */
+#define TCP_FASTOPEN_COOKIE_MAX	16	/* Max Fast Open Cookie size in bytes */
+
+/* TCP Fast Open Cookie as stored in memory */
+struct tcp_fastopen_cookie {
+	s8	len;
+	u8	val[TCP_FASTOPEN_COOKIE_MAX];
+};
+
 /* This defines a selective acknowledgement block. */
 struct tcp_sack_block_wire {
 	__be32	start_seq;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 85c5090bfe2..5aed3718fde 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -170,6 +170,11 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOPT_TIMESTAMP	8	/* Better RTT estimations/PAWS */
 #define TCPOPT_MD5SIG		19	/* MD5 Signature (RFC2385) */
 #define TCPOPT_COOKIE		253	/* Cookie extension (experimental) */
+#define TCPOPT_EXP		254	/* Experimental */
+/* Magic number to be after the option value for sharing TCP
+ * experimental options. See draft-ietf-tcpm-experimental-options-00.txt
+ */
+#define TCPOPT_FASTOPEN_MAGIC	0xF989
 
 /*
  *     TCP option lengths
@@ -180,6 +185,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOLEN_SACK_PERM      2
 #define TCPOLEN_TIMESTAMP      10
 #define TCPOLEN_MD5SIG         18
+#define TCPOLEN_EXP_FASTOPEN_BASE  4
 #define TCPOLEN_COOKIE_BASE    2	/* Cookie-less header extension */
 #define TCPOLEN_COOKIE_PAIR    3	/* Cookie pair header extension */
 #define TCPOLEN_COOKIE_MIN     (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN)
@@ -222,6 +228,7 @@ extern int sysctl_tcp_retries1;
 extern int sysctl_tcp_retries2;
 extern int sysctl_tcp_orphan_retries;
 extern int sysctl_tcp_syncookies;
+extern int sysctl_tcp_fastopen;
 extern int sysctl_tcp_retrans_collapse;
 extern int sysctl_tcp_stdurg;
 extern int sysctl_tcp_rfc1337;
@@ -418,7 +425,7 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		       size_t len, int nonblock, int flags, int *addr_len);
 extern void tcp_parse_options(const struct sk_buff *skb,
 			      struct tcp_options_received *opt_rx, const u8 **hvpp,
-			      int estab);
+			      int estab, struct tcp_fastopen_cookie *foc);
 extern const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
 
 /*
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index a677d804e53..ae2ccf2890e 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -7,7 +7,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     ip_output.o ip_sockglue.o inet_hashtables.o \
 	     inet_timewait_sock.o inet_connection_sock.o \
 	     tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
-	     tcp_minisocks.o tcp_cong.o tcp_metrics.o \
+	     tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \
 	     datagram.o raw.o udp.o udplite.o \
 	     arp.o icmp.o devinet.o af_inet.o  igmp.o \
 	     fib_frontend.o fib_semantics.o fib_trie.o \
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index eab2a7fb15d..650e1528e1e 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -293,7 +293,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 
 	/* check for timestamp cookie support */
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
-	tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
 
 	if (!cookie_check_timestamp(&tcp_opt, &ecn_ok))
 		goto out;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 3f6a1e762e9..5840c325572 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -366,6 +366,13 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 #endif
+	{
+		.procname	= "tcp_fastopen",
+		.data		= &sysctl_tcp_fastopen,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "tcp_tw_recycle",
 		.data		= &tcp_death_row.sysctl_tw_recycle,
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
new file mode 100644
index 00000000000..a7f729c409d
--- /dev/null
+++ b/net/ipv4/tcp_fastopen.c
@@ -0,0 +1,11 @@
+#include <linux/init.h>
+#include <linux/kernel.h>
+
+int sysctl_tcp_fastopen;
+
+static int __init tcp_fastopen_init(void)
+{
+	return 0;
+}
+
+late_initcall(tcp_fastopen_init);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fdd49f1b7a5..a06bb8959e7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3732,7 +3732,8 @@ old_ack:
  * the fast version below fails.
  */
 void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx,
-		       const u8 **hvpp, int estab)
+		       const u8 **hvpp, int estab,
+		       struct tcp_fastopen_cookie *foc)
 {
 	const unsigned char *ptr;
 	const struct tcphdr *th = tcp_hdr(skb);
@@ -3839,8 +3840,25 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o
 					break;
 				}
 				break;
-			}
 
+			case TCPOPT_EXP:
+				/* Fast Open option shares code 254 using a
+				 * 16 bits magic number. It's valid only in
+				 * SYN or SYN-ACK with an even size.
+				 */
+				if (opsize < TCPOLEN_EXP_FASTOPEN_BASE ||
+				    get_unaligned_be16(ptr) != TCPOPT_FASTOPEN_MAGIC ||
+				    foc == NULL || !th->syn || (opsize & 1))
+					break;
+				foc->len = opsize - TCPOLEN_EXP_FASTOPEN_BASE;
+				if (foc->len >= TCP_FASTOPEN_COOKIE_MIN &&
+				    foc->len <= TCP_FASTOPEN_COOKIE_MAX)
+					memcpy(foc->val, ptr + 2, foc->len);
+				else if (foc->len != 0)
+					foc->len = -1;
+				break;
+
+			}
 			ptr += opsize-2;
 			length -= opsize;
 		}
@@ -3882,7 +3900,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb,
 		if (tcp_parse_aligned_timestamp(tp, th))
 			return true;
 	}
-	tcp_parse_options(skb, &tp->rx_opt, hvpp, 1);
+	tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);
 	return true;
 }
 
@@ -5637,7 +5655,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 	struct tcp_cookie_values *cvp = tp->cookie_values;
 	int saved_clamp = tp->rx_opt.mss_clamp;
 
-	tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, NULL);
 
 	if (th->ack) {
 		/* rfc793:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d7d2fa50f07..01aa77a9702 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1307,7 +1307,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_clear_options(&tmp_opt);
 	tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
 	tmp_opt.user_mss  = tp->rx_opt.user_mss;
-	tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
 
 	if (tmp_opt.cookie_plus > 0 &&
 	    tmp_opt.saw_tstamp &&
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index c66f2ede160..5912ac3fd24 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -97,7 +97,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 
 	tmp_opt.saw_tstamp = 0;
 	if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
-		tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+		tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
 
 		if (tmp_opt.saw_tstamp) {
 			tmp_opt.ts_recent	= tcptw->tw_ts_recent;
@@ -534,7 +534,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	tmp_opt.saw_tstamp = 0;
 	if (th->doff > (sizeof(struct tcphdr)>>2)) {
-		tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+		tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
 
 		if (tmp_opt.saw_tstamp) {
 			tmp_opt.ts_recent = req->ts_recent;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 15a7c7bc3e5..4849be76ccd 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -385,15 +385,17 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_MD5		(1 << 2)
 #define OPTION_WSCALE		(1 << 3)
 #define OPTION_COOKIE_EXTENSION	(1 << 4)
+#define OPTION_FAST_OPEN_COOKIE	(1 << 8)
 
 struct tcp_out_options {
-	u8 options;		/* bit field of OPTION_* */
+	u16 options;		/* bit field of OPTION_* */
+	u16 mss;		/* 0 to disable */
 	u8 ws;			/* window scale, 0 to disable */
 	u8 num_sack_blocks;	/* number of SACK blocks to include */
 	u8 hash_size;		/* bytes in hash_location */
-	u16 mss;		/* 0 to disable */
-	__u32 tsval, tsecr;	/* need to include OPTION_TS */
 	__u8 *hash_location;	/* temporary pointer, overloaded */
+	__u32 tsval, tsecr;	/* need to include OPTION_TS */
+	struct tcp_fastopen_cookie *fastopen_cookie;	/* Fast open cookie */
 };
 
 /* The sysctl int routines are generic, so check consistency here.
@@ -442,7 +444,7 @@ static u8 tcp_cookie_size_check(u8 desired)
 static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 			      struct tcp_out_options *opts)
 {
-	u8 options = opts->options;	/* mungable copy */
+	u16 options = opts->options;	/* mungable copy */
 
 	/* Having both authentication and cookies for security is redundant,
 	 * and there's certainly not enough room.  Instead, the cookie-less
@@ -564,6 +566,21 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 
 		tp->rx_opt.dsack = 0;
 	}
+
+	if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) {
+		struct tcp_fastopen_cookie *foc = opts->fastopen_cookie;
+
+		*ptr++ = htonl((TCPOPT_EXP << 24) |
+			       ((TCPOLEN_EXP_FASTOPEN_BASE + foc->len) << 16) |
+			       TCPOPT_FASTOPEN_MAGIC);
+
+		memcpy(ptr, foc->val, foc->len);
+		if ((foc->len & 3) == 2) {
+			u8 *align = ((u8 *)ptr) + foc->len;
+			align[0] = align[1] = TCPOPT_NOP;
+		}
+		ptr += (foc->len + 3) >> 2;
+	}
 }
 
 /* Compute TCP options for SYN packets. This is not the final
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 7bf3cc427c2..bb46061c813 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -177,7 +177,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 
 	/* check for timestamp cookie support */
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
-	tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
 
 	if (!cookie_check_timestamp(&tcp_opt, &ecn_ok))
 		goto out;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c9dabdd832d..0302ec3fecf 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1033,7 +1033,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_clear_options(&tmp_opt);
 	tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 	tmp_opt.user_mss = tp->rx_opt.user_mss;
-	tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
 
 	if (tmp_opt.cookie_plus > 0 &&
 	    tmp_opt.saw_tstamp &&
-- 
cgit v1.2.3-70-g09d2


From 8e4178c1c7b52f7c99f5fd22ef7af6b2bff409e3 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 19 Jul 2012 06:43:08 +0000
Subject: net-tcp: Fast Open client - receiving SYN-ACK

On receiving the SYN-ACK after SYN-data, the client needs to
a) update the cached MSS and cookie (if included in SYN-ACK)
b) retransmit the data not yet acknowledged by the SYN-ACK in the final ACK of
   the handshake.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 40 +++++++++++++++++++++++++++++++++++-----
 1 file changed, 35 insertions(+), 5 deletions(-)

(limited to 'net/ipv4/tcp_input.c')

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a06bb8959e7..38b6a811edf 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5646,6 +5646,34 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	}
 }
 
+static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
+				    struct tcp_fastopen_cookie *cookie)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct sk_buff *data = tcp_write_queue_head(sk);
+	u16 mss = tp->rx_opt.mss_clamp;
+
+	if (mss == tp->rx_opt.user_mss) {
+		struct tcp_options_received opt;
+		const u8 *hash_location;
+
+		/* Get original SYNACK MSS value if user MSS sets mss_clamp */
+		tcp_clear_options(&opt);
+		opt.user_mss = opt.mss_clamp = 0;
+		tcp_parse_options(synack, &opt, &hash_location, 0, NULL);
+		mss = opt.mss_clamp;
+	}
+
+	tcp_fastopen_cache_set(sk, mss, cookie);
+
+	if (data) { /* Retransmit unacked data in SYN */
+		tcp_retransmit_skb(sk, data);
+		tcp_rearm_rto(sk);
+		return true;
+	}
+	return false;
+}
+
 static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 					 const struct tcphdr *th, unsigned int len)
 {
@@ -5653,9 +5681,10 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_cookie_values *cvp = tp->cookie_values;
+	struct tcp_fastopen_cookie foc = { .len = -1 };
 	int saved_clamp = tp->rx_opt.mss_clamp;
 
-	tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, NULL);
+	tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, &foc);
 
 	if (th->ack) {
 		/* rfc793:
@@ -5665,11 +5694,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		 *	  If SEG.ACK =< ISS, or SEG.ACK > SND.NXT, send
 		 *        a reset (unless the RST bit is set, if so drop
 		 *        the segment and return)"
-		 *
-		 *  We do not send data with SYN, so that RFC-correct
-		 *  test reduces to:
 		 */
-		if (TCP_SKB_CB(skb)->ack_seq != tp->snd_nxt)
+		if (!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_una) ||
+		    after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt))
 			goto reset_and_undo;
 
 		if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
@@ -5781,6 +5808,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 
 		tcp_finish_connect(sk, skb);
 
+		if (tp->syn_fastopen && tcp_rcv_fastopen_synack(sk, skb, &foc))
+			return -1;
+
 		if (sk->sk_write_pending ||
 		    icsk->icsk_accept_queue.rskq_defer_accept ||
 		    icsk->icsk_ack.pingpong) {
-- 
cgit v1.2.3-70-g09d2


From aab4874355679c70f93993cf3b3fd74643b9ac33 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 19 Jul 2012 06:43:10 +0000
Subject: net-tcp: Fast Open client - detecting SYN-data drops

On paths with firewalls dropping SYN with data or experimental TCP options,
Fast Open connections will have experience SYN timeout and bad performance.
The solution is to track such incidents in the cookie cache and disables
Fast Open temporarily.

Since only the original SYN includes data and/or Fast Open option, the
SYN-ACK has some tell-tale sign (tcp_rcv_fastopen_synack()) to detect
such drops. If a path has recurring Fast Open SYN drops, Fast Open is
disabled for 2^(recurring_losses) minutes starting from four minutes up to
roughly one and half day. sendmsg with MSG_FASTOPEN flag will succeed but
it behaves as connect() then write().

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h      |  6 ++++--
 net/ipv4/tcp_input.c   | 10 +++++++++-
 net/ipv4/tcp_metrics.c | 16 +++++++++++++---
 net/ipv4/tcp_output.c  | 13 +++++++++++--
 4 files changed, 37 insertions(+), 8 deletions(-)

(limited to 'net/ipv4/tcp_input.c')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index c0258100d70..e07878d246a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -409,9 +409,11 @@ extern bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
 extern bool tcp_remember_stamp(struct sock *sk);
 extern bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw);
 extern void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
-				   struct tcp_fastopen_cookie *cookie);
+				   struct tcp_fastopen_cookie *cookie,
+				   int *syn_loss, unsigned long *last_syn_loss);
 extern void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
-				   struct tcp_fastopen_cookie *cookie);
+				   struct tcp_fastopen_cookie *cookie,
+				   bool syn_lost);
 extern void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst);
 extern void tcp_disable_fack(struct tcp_sock *tp);
 extern void tcp_close(struct sock *sk, long timeout);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 38b6a811edf..c49a4fc175b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5652,6 +5652,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *data = tcp_write_queue_head(sk);
 	u16 mss = tp->rx_opt.mss_clamp;
+	bool syn_drop;
 
 	if (mss == tp->rx_opt.user_mss) {
 		struct tcp_options_received opt;
@@ -5664,7 +5665,14 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 		mss = opt.mss_clamp;
 	}
 
-	tcp_fastopen_cache_set(sk, mss, cookie);
+	/* The SYN-ACK neither has cookie nor acknowledges the data. Presumably
+	 * the remote receives only the retransmitted (regular) SYNs: either
+	 * the original SYN-data or the corresponding SYN-ACK is lost.
+	 */
+	syn_drop = (cookie->len <= 0 && data &&
+		    inet_csk(sk)->icsk_retransmits);
+
+	tcp_fastopen_cache_set(sk, mss, cookie, syn_drop);
 
 	if (data) { /* Retransmit unacked data in SYN */
 		tcp_retransmit_skb(sk, data);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index d02ff377778..99779ae44f6 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -32,6 +32,8 @@ enum tcp_metric_index {
 
 struct tcp_fastopen_metrics {
 	u16	mss;
+	u16	syn_loss:10;		/* Recurring Fast Open SYN losses */
+	unsigned long	last_syn_loss;	/* Last Fast Open SYN loss */
 	struct	tcp_fastopen_cookie	cookie;
 };
 
@@ -125,6 +127,7 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst)
 	tm->tcpm_ts = 0;
 	tm->tcpm_ts_stamp = 0;
 	tm->tcpm_fastopen.mss = 0;
+	tm->tcpm_fastopen.syn_loss = 0;
 	tm->tcpm_fastopen.cookie.len = 0;
 }
 
@@ -644,7 +647,8 @@ bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw)
 static DEFINE_SEQLOCK(fastopen_seqlock);
 
 void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
-			    struct tcp_fastopen_cookie *cookie)
+			    struct tcp_fastopen_cookie *cookie,
+			    int *syn_loss, unsigned long *last_syn_loss)
 {
 	struct tcp_metrics_block *tm;
 
@@ -659,14 +663,15 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
 			if (tfom->mss)
 				*mss = tfom->mss;
 			*cookie = tfom->cookie;
+			*syn_loss = tfom->syn_loss;
+			*last_syn_loss = *syn_loss ? tfom->last_syn_loss : 0;
 		} while (read_seqretry(&fastopen_seqlock, seq));
 	}
 	rcu_read_unlock();
 }
 
-
 void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
-			    struct tcp_fastopen_cookie *cookie)
+			    struct tcp_fastopen_cookie *cookie, bool syn_lost)
 {
 	struct tcp_metrics_block *tm;
 
@@ -679,6 +684,11 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
 		tfom->mss = mss;
 		if (cookie->len > 0)
 			tfom->cookie = *cookie;
+		if (syn_lost) {
+			++tfom->syn_loss;
+			tfom->last_syn_loss = jiffies;
+		} else
+			tfom->syn_loss = 0;
 		write_sequnlock_bh(&fastopen_seqlock);
 	}
 	rcu_read_unlock();
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 88693281da4..c5cfd5ec318 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2860,10 +2860,19 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
-	int space, i, err = 0, iovlen = fo->data->msg_iovlen;
+	int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen;
 	struct sk_buff *syn_data = NULL, *data;
+	unsigned long last_syn_loss = 0;
+
+	tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie,
+			       &syn_loss, &last_syn_loss);
+	/* Recurring FO SYN losses: revert to regular handshake temporarily */
+	if (syn_loss > 1 &&
+	    time_before(jiffies, last_syn_loss + (60*HZ << syn_loss))) {
+		fo->cookie.len = -1;
+		goto fallback;
+	}
 
-	tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie);
 	if (fo->cookie.len <= 0)
 		goto fallback;
 
-- 
cgit v1.2.3-70-g09d2


From 67da22d23fa6f3324e03bcd0580b914b2e4afbf3 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 19 Jul 2012 06:43:11 +0000
Subject: net-tcp: Fast Open client - cookie-less mode

In trusted networks, e.g., intranet, data-center, the client does not
need to use Fast Open cookie to mitigate DoS attacks. In cookie-less
mode, sendmsg() with MSG_FASTOPEN flag will send SYN-data regardless
of cookie availability.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 2 ++
 include/linux/tcp.h                    | 1 +
 include/net/tcp.h                      | 1 +
 net/ipv4/tcp_input.c                   | 8 ++++++--
 net/ipv4/tcp_output.c                  | 6 +++++-
 5 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'net/ipv4/tcp_input.c')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 03964e08818..5f3ef7f7fce 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -476,6 +476,8 @@ tcp_fastopen - INTEGER
 
 	The values (bitmap) are:
 	1: Enables sending data in the opening SYN on the client
+	5: Enables sending data in the opening SYN on the client regardless
+	   of cookie availability.
 
 	Default: 0
 
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 1edf96afab4..9febfb685c3 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -387,6 +387,7 @@ struct tcp_sock {
 	u8	repair_queue;
 	u8	do_early_retrans:1,/* Enable RFC5827 early-retransmit  */
 		early_retrans_delayed:1, /* Delayed ER timer installed */
+		syn_data:1,	/* SYN includes data */
 		syn_fastopen:1;	/* SYN includes Fast Open option */
 
 /* RTT measurement */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e07878d246a..bc7c134ec05 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -214,6 +214,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 
 /* Bit Flags for sysctl_tcp_fastopen */
 #define	TFO_CLIENT_ENABLE	1
+#define	TFO_CLIENT_NO_COOKIE	4	/* Data in SYN w/o cookie option */
 
 extern struct inet_timewait_death_row tcp_death_row;
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c49a4fc175b..e67d685a6c0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5650,7 +5650,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 				    struct tcp_fastopen_cookie *cookie)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *data = tcp_write_queue_head(sk);
+	struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL;
 	u16 mss = tp->rx_opt.mss_clamp;
 	bool syn_drop;
 
@@ -5665,6 +5665,9 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 		mss = opt.mss_clamp;
 	}
 
+	if (!tp->syn_fastopen)  /* Ignore an unsolicited cookie */
+		cookie->len = -1;
+
 	/* The SYN-ACK neither has cookie nor acknowledges the data. Presumably
 	 * the remote receives only the retransmitted (regular) SYNs: either
 	 * the original SYN-data or the corresponding SYN-ACK is lost.
@@ -5816,7 +5819,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 
 		tcp_finish_connect(sk, skb);
 
-		if (tp->syn_fastopen && tcp_rcv_fastopen_synack(sk, skb, &foc))
+		if ((tp->syn_fastopen || tp->syn_data) &&
+		    tcp_rcv_fastopen_synack(sk, skb, &foc))
 			return -1;
 
 		if (sk->sk_write_pending ||
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c5cfd5ec318..27a32acfdb6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2864,6 +2864,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	struct sk_buff *syn_data = NULL, *data;
 	unsigned long last_syn_loss = 0;
 
+	tp->rx_opt.mss_clamp = tp->advmss;  /* If MSS is not cached */
 	tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie,
 			       &syn_loss, &last_syn_loss);
 	/* Recurring FO SYN losses: revert to regular handshake temporarily */
@@ -2873,7 +2874,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		goto fallback;
 	}
 
-	if (fo->cookie.len <= 0)
+	if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE)
+		fo->cookie.len = -1;
+	else if (fo->cookie.len <= 0)
 		goto fallback;
 
 	/* MSS for SYN-data is based on cached MSS and bounded by PMTU and
@@ -2916,6 +2919,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	fo->copied = data->len;
 
 	if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) {
+		tp->syn_data = (fo->copied > 0);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
 		goto done;
 	}
-- 
cgit v1.2.3-70-g09d2


From 67b95bd78f0de85793bf30835913f6ef784a39b6 Mon Sep 17 00:00:00 2001
From: Vijay Subramanian <subramanian.vijay@gmail.com>
Date: Thu, 19 Jul 2012 21:32:18 +0000
Subject: tcp: Return bool instead of int where appropriate

Applied to a set of static inline functions in tcp_input.c

Signed-off-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'net/ipv4/tcp_input.c')

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e67d685a6c0..21d7f8f3a7a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2521,7 +2521,7 @@ static void tcp_cwnd_down(struct sock *sk, int flag)
 /* Nothing was retransmitted or returned timestamp is less
  * than timestamp of the first retransmission.
  */
-static inline int tcp_packet_delayed(const struct tcp_sock *tp)
+static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
 {
 	return !tp->retrans_stamp ||
 		(tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
@@ -2582,7 +2582,7 @@ static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh)
 	tp->snd_cwnd_stamp = tcp_time_stamp;
 }
 
-static inline int tcp_may_undo(const struct tcp_sock *tp)
+static inline bool tcp_may_undo(const struct tcp_sock *tp)
 {
 	return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp));
 }
@@ -3371,13 +3371,13 @@ static void tcp_ack_probe(struct sock *sk)
 	}
 }
 
-static inline int tcp_ack_is_dubious(const struct sock *sk, const int flag)
+static inline bool tcp_ack_is_dubious(const struct sock *sk, const int flag)
 {
 	return !(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) ||
 		inet_csk(sk)->icsk_ca_state != TCP_CA_Open;
 }
 
-static inline int tcp_may_raise_cwnd(const struct sock *sk, const int flag)
+static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	return (!(flag & FLAG_ECE) || tp->snd_cwnd < tp->snd_ssthresh) &&
@@ -3387,7 +3387,7 @@ static inline int tcp_may_raise_cwnd(const struct sock *sk, const int flag)
 /* Check that window update is acceptable.
  * The function assumes that snd_una<=ack<=snd_next.
  */
-static inline int tcp_may_update_window(const struct tcp_sock *tp,
+static inline bool tcp_may_update_window(const struct tcp_sock *tp,
 					const u32 ack, const u32 ack_seq,
 					const u32 nwin)
 {
@@ -4006,7 +4006,7 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
 		(s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ);
 }
 
-static inline int tcp_paws_discard(const struct sock *sk,
+static inline bool tcp_paws_discard(const struct sock *sk,
 				   const struct sk_buff *skb)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -4028,7 +4028,7 @@ static inline int tcp_paws_discard(const struct sock *sk,
  * (borrowed from freebsd)
  */
 
-static inline int tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq)
+static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq)
 {
 	return	!before(end_seq, tp->rcv_wup) &&
 		!after(seq, tp->rcv_nxt + tcp_receive_window(tp));
@@ -5214,7 +5214,7 @@ static __sum16 __tcp_checksum_complete_user(struct sock *sk,
 	return result;
 }
 
-static inline int tcp_checksum_complete_user(struct sock *sk,
+static inline bool tcp_checksum_complete_user(struct sock *sk,
 					     struct sk_buff *skb)
 {
 	return !skb_csum_unnecessary(skb) &&
-- 
cgit v1.2.3-70-g09d2


From 92101b3b2e3178087127709a556b091dae314e9e Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 23 Jul 2012 16:29:00 -0700
Subject: ipv4: Prepare for change of rt->rt_iif encoding.

Use inet_iif() consistently, and for TCP record the input interface of
cached RX dst in inet sock.

rt->rt_iif is going to be encoded differently, so that we can
legitimately cache input routes in the FIB info more aggressively.

When the input interface is "use SKB device index" the rt->rt_iif will
be set to zero.

This forces us to move the TCP RX dst cache installation into the ipv4
specific code, and as well it should since doing the route caching for
ipv6 is pointless at the moment since it is not inspected in the ipv6
input paths yet.

Also, remove the unlikely on dst->obsolete, all ipv4 dsts have
obsolete set to a non-zero value to force invocation of the check
callback.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h |  1 +
 net/dccp/ipv4.c         |  2 +-
 net/ipv4/icmp.c         |  2 +-
 net/ipv4/ip_sockglue.c  |  5 ++---
 net/ipv4/route.c        |  2 +-
 net/ipv4/tcp_input.c    | 12 ------------
 net/ipv4/tcp_ipv4.c     | 24 ++++++++++++++++++------
 net/sched/cls_route.c   |  2 +-
 net/sched/em_meta.c     |  2 +-
 net/sctp/protocol.c     |  2 +-
 10 files changed, 27 insertions(+), 27 deletions(-)

(limited to 'net/ipv4/tcp_input.c')

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 924d7b98ab6..613cfa40167 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -172,6 +172,7 @@ struct inet_sock {
 	int			uc_index;
 	int			mc_index;
 	__be32			mc_addr;
+	int			rx_dst_ifindex;
 	struct ip_mc_socklist __rcu	*mc_list;
 	struct inet_cork_full	cork;
 };
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 25428d0c50c..176ecdba4a2 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -481,7 +481,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 	struct rtable *rt;
 	const struct iphdr *iph = ip_hdr(skb);
 	struct flowi4 fl4 = {
-		.flowi4_oif = skb_rtable(skb)->rt_iif,
+		.flowi4_oif = inet_iif(skb),
 		.daddr = iph->saddr,
 		.saddr = iph->daddr,
 		.flowi4_tos = RT_CONN_FLAGS(sk),
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index f2a06beffbd..f2eccd53174 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -571,7 +571,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 		rcu_read_lock();
 		if (rt_is_input_route(rt) &&
 		    net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)
-			dev = dev_get_by_index_rcu(net, rt->rt_iif);
+			dev = dev_get_by_index_rcu(net, inet_iif(skb_in));
 
 		if (dev)
 			saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index de29f46f68b..5eea4a81104 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1027,10 +1027,9 @@ e_inval:
 void ipv4_pktinfo_prepare(struct sk_buff *skb)
 {
 	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
-	const struct rtable *rt = skb_rtable(skb);
 
-	if (rt) {
-		pktinfo->ipi_ifindex = rt->rt_iif;
+	if (skb_rtable(skb)) {
+		pktinfo->ipi_ifindex = inet_iif(skb);
 		pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
 	} else {
 		pktinfo->ipi_ifindex = 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 34017be87c8..f6be7811939 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -848,7 +848,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 		if (log_martians &&
 		    peer->rate_tokens == ip_rt_redirect_number)
 			net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
-					     &ip_hdr(skb)->saddr, rt->rt_iif,
+					     &ip_hdr(skb)->saddr, inet_iif(skb),
 					     &ip_hdr(skb)->daddr, &rt->rt_gateway);
 #endif
 	}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 21d7f8f3a7a..3e07a64ca44 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5391,18 +5391,6 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (sk->sk_rx_dst) {
-		struct dst_entry *dst = sk->sk_rx_dst;
-		if (unlikely(dst->obsolete)) {
-			if (dst->ops->check(dst, 0) == NULL) {
-				dst_release(dst);
-				sk->sk_rx_dst = NULL;
-			}
-		}
-	}
-	if (unlikely(sk->sk_rx_dst == NULL))
-		sk->sk_rx_dst = dst_clone(skb_dst(skb));
-
 	/*
 	 *	Header prediction.
 	 *	The code loosely follows the one in the famous
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bc5432e3c77..3e30548ac32 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1618,6 +1618,20 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
 		sock_rps_save_rxhash(sk, skb);
+		if (sk->sk_rx_dst) {
+			struct dst_entry *dst = sk->sk_rx_dst;
+			if (dst->ops->check(dst, 0) == NULL) {
+				dst_release(dst);
+				sk->sk_rx_dst = NULL;
+			}
+		}
+		if (unlikely(sk->sk_rx_dst == NULL)) {
+			struct inet_sock *icsk = inet_sk(sk);
+			struct rtable *rt = skb_rtable(skb);
+
+			sk->sk_rx_dst = dst_clone(&rt->dst);
+			icsk->rx_dst_ifindex = inet_iif(skb);
+		}
 		if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
 			rsk = sk;
 			goto reset;
@@ -1700,14 +1714,12 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 		skb->destructor = sock_edemux;
 		if (sk->sk_state != TCP_TIME_WAIT) {
 			struct dst_entry *dst = sk->sk_rx_dst;
+			struct inet_sock *icsk = inet_sk(sk);
 			if (dst)
 				dst = dst_check(dst, 0);
-			if (dst) {
-				struct rtable *rt = (struct rtable *) dst;
-
-				if (rt->rt_iif == dev->ifindex)
-					skb_dst_set_noref(skb, dst);
-			}
+			if (dst &&
+			    icsk->rx_dst_ifindex == dev->ifindex)
+				skb_dst_set_noref(skb, dst);
 		}
 	}
 }
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 36fec422740..44f405cb9aa 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -143,7 +143,7 @@ static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	if (head == NULL)
 		goto old_method;
 
-	iif = ((struct rtable *)dst)->rt_iif;
+	iif = inet_iif(skb);
 
 	h = route4_fastmap_hash(id, iif);
 	if (id == head->fastmap[h].id &&
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 4790c696cbc..4ab6e332557 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -264,7 +264,7 @@ META_COLLECTOR(int_rtiif)
 	if (unlikely(skb_rtable(skb) == NULL))
 		*err = -1;
 	else
-		dst->value = skb_rtable(skb)->rt_iif;
+		dst->value = inet_iif(skb);
 }
 
 /**************************************************************************
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 9c90811d113..1f89c4e6964 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -568,7 +568,7 @@ static void sctp_v4_get_saddr(struct sctp_sock *sk,
 /* What interface did this skb arrive on? */
 static int sctp_v4_skb_iif(const struct sk_buff *skb)
 {
-	return skb_rtable(skb)->rt_iif;
+	return inet_iif(skb);
 }
 
 /* Was this packet marked by Explicit Congestion Notification? */
-- 
cgit v1.2.3-70-g09d2