1 files changed, 160 insertions, 63 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2bc8e27a163d..57ae96a04220 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -77,7 +77,7 @@ int sysctl_tcp_window_scaling __read_mostly = 1;
 int sysctl_tcp_sack __read_mostly = 1;
 int sysctl_tcp_fack __read_mostly = 1;
 int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
-int sysctl_tcp_ecn __read_mostly;
+int sysctl_tcp_ecn __read_mostly = 2;
 int sysctl_tcp_dsack __read_mostly = 1;
 int sysctl_tcp_app_win __read_mostly = 31;
 int sysctl_tcp_adv_win_scale __read_mostly = 2;
@@ -140,7 +140,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 		 * "len" is invariant segment length, including TCP header.
 		 */
 		len += skb->data - skb_transport_header(skb);
-		if (len >= TCP_MIN_RCVMSS + sizeof(struct tcphdr) ||
+		if (len >= TCP_MSS_DEFAULT + sizeof(struct tcphdr) ||
 		    /* If PSH is not set, packet should be
 		     * full sized, provided peer TCP is not badly broken.
 		     * This observation (if it is correct 8)) allows
@@ -411,7 +411,7 @@ void tcp_initialize_rcv_mss(struct sock *sk)
 	unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache);
 
 	hint = min(hint, tp->rcv_wnd / 2);
-	hint = min(hint, TCP_MIN_RCVMSS);
+	hint = min(hint, TCP_MSS_DEFAULT);
 	hint = max(hint, TCP_MIN_MSS);
 
 	inet_csk(sk)->icsk_ack.rcv_mss = hint;
@@ -597,16 +597,6 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 		tcp_grow_window(sk, skb);
 }
 
-static u32 tcp_rto_min(struct sock *sk)
-{
-	struct dst_entry *dst = __sk_dst_get(sk);
-	u32 rto_min = TCP_RTO_MIN;
-
-	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
-		rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
-	return rto_min;
-}
-
 /* Called to compute a smoothed rtt estimate. The data fed to this
  * routine either comes from timestamps, or from segments that were
  * known _not_ to have been retransmitted [see Karn/Partridge
@@ -695,7 +685,7 @@ static inline void tcp_set_rto(struct sock *sk)
 	 *    is invisible. Actually, Linux-2.4 also generates erratic
 	 *    ACKs in some circumstances.
 	 */
-	inet_csk(sk)->icsk_rto = (tp->srtt >> 3) + tp->rttvar;
+	inet_csk(sk)->icsk_rto = __tcp_set_rto(tp);
 
 	/* 2. Fixups made earlier cannot be right.
 	 *    If we do not estimate RTO correctly without them,
@@ -706,8 +696,7 @@ static inline void tcp_set_rto(struct sock *sk)
 	/* NOTE: clamping at TCP_RTO_MIN is not required, current algo
 	 * guarantees that rto is higher.
 	 */
-	if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX)
-		inet_csk(sk)->icsk_rto = TCP_RTO_MAX;
+	tcp_bound_rto(sk);
 }
 
 /* Save metrics learned by this TCP session.
@@ -772,7 +761,7 @@ void tcp_update_metrics(struct sock *sk)
 			set_dst_metric_rtt(dst, RTAX_RTTVAR, var);
 		}
 
-		if (tp->snd_ssthresh >= 0xFFFF) {
+		if (tcp_in_initial_slowstart(tp)) {
 			/* Slow start still did not finish. */
 			if (dst_metric(dst, RTAX_SSTHRESH) &&
 			    !dst_metric_locked(dst, RTAX_SSTHRESH) &&
@@ -928,6 +917,8 @@ static void tcp_init_metrics(struct sock *sk)
 	tcp_set_rto(sk);
 	if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp)
 		goto reset;
+
+cwnd:
 	tp->snd_cwnd = tcp_init_cwnd(tp, dst);
 	tp->snd_cwnd_stamp = tcp_time_stamp;
 	return;
@@ -942,6 +933,7 @@ reset:
 		tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT;
 		inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
 	}
+	goto cwnd;
 }
 
 static void tcp_update_reordering(struct sock *sk, const int metric,
@@ -2308,7 +2300,7 @@ static inline int tcp_fackets_out(struct tcp_sock *tp)
  * they differ. Since neither occurs due to loss, TCP should really
  * ignore them.
  */
-static inline int tcp_dupack_heurestics(struct tcp_sock *tp)
+static inline int tcp_dupack_heuristics(struct tcp_sock *tp)
 {
 	return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1;
 }
@@ -2433,7 +2425,7 @@ static int tcp_time_to_recover(struct sock *sk)
 		return 1;
 
 	/* Not-A-Trick#2 : Classic rule... */
-	if (tcp_dupack_heurestics(tp) > tp->reordering)
+	if (tcp_dupack_heuristics(tp) > tp->reordering)
 		return 1;
 
 	/* Trick#3 : when we use RFC2988 timer restart, fast
@@ -3706,7 +3698,7 @@ old_ack:
  * the fast version below fails.
  */
 void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
-		       int estab)
+		       u8 **hvpp, int estab,  struct dst_entry *dst)
 {
 	unsigned char *ptr;
 	struct tcphdr *th = tcp_hdr(skb);
@@ -3745,7 +3737,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
 				break;
 			case TCPOPT_WINDOW:
 				if (opsize == TCPOLEN_WINDOW && th->syn &&
-				    !estab && sysctl_tcp_window_scaling) {
+				    !estab && sysctl_tcp_window_scaling &&
+				    !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)) {
 					__u8 snd_wscale = *(__u8 *)ptr;
 					opt_rx->wscale_ok = 1;
 					if (snd_wscale > 14) {
@@ -3761,7 +3754,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
 			case TCPOPT_TIMESTAMP:
 				if ((opsize == TCPOLEN_TIMESTAMP) &&
 				    ((estab && opt_rx->tstamp_ok) ||
-				     (!estab && sysctl_tcp_timestamps))) {
+				     (!estab && sysctl_tcp_timestamps &&
+				      !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP)))) {
 					opt_rx->saw_tstamp = 1;
 					opt_rx->rcv_tsval = get_unaligned_be32(ptr);
 					opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
@@ -3769,7 +3763,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
 				break;
 			case TCPOPT_SACK_PERM:
 				if (opsize == TCPOLEN_SACK_PERM && th->syn &&
-				    !estab && sysctl_tcp_sack) {
+				    !estab && sysctl_tcp_sack &&
+				    !dst_feature(dst, RTAX_FEATURE_NO_SACK)) {
 					opt_rx->sack_ok = 1;
 					tcp_sack_reset(opt_rx);
 				}
@@ -3790,7 +3785,30 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
 				 */
 				break;
 #endif
-			}
+			case TCPOPT_COOKIE:
+				/* This option is variable length.
+				 */
+				switch (opsize) {
+				case TCPOLEN_COOKIE_BASE:
+					/* not yet implemented */
+					break;
+				case TCPOLEN_COOKIE_PAIR:
+					/* not yet implemented */
+					break;
+				case TCPOLEN_COOKIE_MIN+0:
+				case TCPOLEN_COOKIE_MIN+2:
+				case TCPOLEN_COOKIE_MIN+4:
+				case TCPOLEN_COOKIE_MIN+6:
+				case TCPOLEN_COOKIE_MAX:
+					/* 16-bit multiple */
+					opt_rx->cookie_plus = opsize;
+					*hvpp = ptr;
+				default:
+					/* ignore option */
+					break;
+				};
+				break;
+			};
 
 			ptr += opsize-2;
 			length -= opsize;
@@ -3818,17 +3836,20 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th)
  * If it is wrong it falls back on tcp_parse_options().
  */
 static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
-				  struct tcp_sock *tp)
+				  struct tcp_sock *tp, u8 **hvpp)
 {
-	if (th->doff == sizeof(struct tcphdr) >> 2) {
+	/* In the spirit of fast parsing, compare doff directly to constant
+	 * values.  Because equality is used, short doff can be ignored here.
+	 */
+	if (th->doff == (sizeof(*th) / 4)) {
 		tp->rx_opt.saw_tstamp = 0;
 		return 0;
 	} else if (tp->rx_opt.tstamp_ok &&
-		   th->doff == (sizeof(struct tcphdr)>>2)+(TCPOLEN_TSTAMP_ALIGNED>>2)) {
+		   th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) {
 		if (tcp_parse_aligned_timestamp(tp, th))
 			return 1;
 	}
-	tcp_parse_options(skb, &tp->rx_opt, 1);
+	tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);
 	return 1;
 }
 
@@ -4083,8 +4104,10 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq,
 static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct dst_entry *dst = __sk_dst_get(sk);
 
-	if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+	if (tcp_is_sack(tp) && sysctl_tcp_dsack &&
+	    !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
 		int mib_idx;
 
 		if (before(seq, tp->rcv_nxt))
@@ -4113,13 +4136,15 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq)
 static void tcp_send_dupack(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct dst_entry *dst = __sk_dst_get(sk);
 
 	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
 	    before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
 		tcp_enter_quickack_mode(sk);
 
-		if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+		if (tcp_is_sack(tp) && sysctl_tcp_dsack &&
+		    !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
 			u32 end_seq = TCP_SKB_CB(skb)->end_seq;
 
 			if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
@@ -4433,7 +4458,7 @@ drop:
 		}
 		__skb_queue_head(&tp->out_of_order_queue, skb);
 	} else {
-		struct sk_buff *skb1 = tp->out_of_order_queue.prev;
+		struct sk_buff *skb1 = skb_peek_tail(&tp->out_of_order_queue);
 		u32 seq = TCP_SKB_CB(skb)->seq;
 		u32 end_seq = TCP_SKB_CB(skb)->end_seq;
 
@@ -4450,15 +4475,18 @@ drop:
 		}
 
 		/* Find place to insert this segment. */
-		do {
+		while (1) {
 			if (!after(TCP_SKB_CB(skb1)->seq, seq))
 				break;
-		} while ((skb1 = skb1->prev) !=
-			 (struct sk_buff *)&tp->out_of_order_queue);
+			if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) {
+				skb1 = NULL;
+				break;
+			}
+			skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1);
+		}
 
 		/* Do skb overlap to previous one? */
-		if (skb1 != (struct sk_buff *)&tp->out_of_order_queue &&
-		    before(seq, TCP_SKB_CB(skb1)->end_seq)) {
+		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. */
 				__kfree_skb(skb);
@@ -4470,15 +4498,26 @@ drop:
 				tcp_dsack_set(sk, seq,
 					      TCP_SKB_CB(skb1)->end_seq);
 			} else {
-				skb1 = skb1->prev;
+				if (skb_queue_is_first(&tp->out_of_order_queue,
+						       skb1))
+					skb1 = NULL;
+				else
+					skb1 = skb_queue_prev(
+						&tp->out_of_order_queue,
+						skb1);
 			}
 		}
-		__skb_queue_after(&tp->out_of_order_queue, skb1, skb);
+		if (!skb1)
+			__skb_queue_head(&tp->out_of_order_queue, skb);
+		else
+			__skb_queue_after(&tp->out_of_order_queue, skb1, skb);
 
 		/* And clean segments covered by new one as whole. */
-		while ((skb1 = skb->next) !=
-		       (struct sk_buff *)&tp->out_of_order_queue &&
-		       after(end_seq, TCP_SKB_CB(skb1)->seq)) {
+		while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) {
+			skb1 = skb_queue_next(&tp->out_of_order_queue, skb);
+
+			if (!after(end_seq, TCP_SKB_CB(skb1)->seq))
+				break;
 			if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
 				tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
 						 end_seq);
@@ -4499,7 +4538,10 @@ add_sack:
 static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
 					struct sk_buff_head *list)
 {
-	struct sk_buff *next = skb->next;
+	struct sk_buff *next = NULL;
+
+	if (!skb_queue_is_last(list, skb))
+		next = skb_queue_next(list, skb);
 
 	__skb_unlink(skb, list);
 	__kfree_skb(skb);
@@ -4510,6 +4552,9 @@ static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
 
 /* Collapse contiguous sequence of skbs head..tail with
  * sequence numbers start..end.
+ *
+ * If tail is NULL, this means until the end of the list.
+ *
  * Segments with FIN/SYN are not collapsed (only because this
  * simplifies code)
  */
@@ -4518,15 +4563,23 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list,
 	     struct sk_buff *head, struct sk_buff *tail,
 	     u32 start, u32 end)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb, *n;
+	bool end_of_skbs;
 
 	/* First, check that queue is collapsible and find
 	 * the point where collapsing can be useful. */
-	for (skb = head; skb != tail;) {
+	skb = head;
+restart:
+	end_of_skbs = true;
+	skb_queue_walk_from_safe(list, skb, n) {
+		if (skb == tail)
+			break;
 		/* No new bits? It is possible on ofo queue. */
 		if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
 			skb = tcp_collapse_one(sk, skb, list);
-			continue;
+			if (!skb)
+				break;
+			goto restart;
 		}
 
 		/* The first skb to collapse is:
@@ -4536,16 +4589,24 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list,
 		 */
 		if (!tcp_hdr(skb)->syn && !tcp_hdr(skb)->fin &&
 		    (tcp_win_from_space(skb->truesize) > skb->len ||
-		     before(TCP_SKB_CB(skb)->seq, start) ||
-		     (skb->next != tail &&
-		      TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb->next)->seq)))
+		     before(TCP_SKB_CB(skb)->seq, start))) {
+			end_of_skbs = false;
 			break;
+		}
+
+		if (!skb_queue_is_last(list, skb)) {
+			struct sk_buff *next = skb_queue_next(list, skb);
+			if (next != tail &&
+			    TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(next)->seq) {
+				end_of_skbs = false;
+				break;
+			}
+		}
 
 		/* Decided to skip this, advance start seq. */
 		start = TCP_SKB_CB(skb)->end_seq;
-		skb = skb->next;
 	}
-	if (skb == tail || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin)
+	if (end_of_skbs || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin)
 		return;
 
 	while (before(start, end)) {
@@ -4590,7 +4651,8 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list,
 			}
 			if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
 				skb = tcp_collapse_one(sk, skb, list);
-				if (skb == tail ||
+				if (!skb ||
+				    skb == tail ||
 				    tcp_hdr(skb)->syn ||
 				    tcp_hdr(skb)->fin)
 					return;
@@ -4617,17 +4679,21 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 	head = skb;
 
 	for (;;) {
-		skb = skb->next;
+		struct sk_buff *next = NULL;
+
+		if (!skb_queue_is_last(&tp->out_of_order_queue, skb))
+			next = skb_queue_next(&tp->out_of_order_queue, skb);
+		skb = next;
 
 		/* Segment is terminated when we see gap or when
 		 * we are at the end of all the queue. */
-		if (skb == (struct sk_buff *)&tp->out_of_order_queue ||
+		if (!skb ||
 		    after(TCP_SKB_CB(skb)->seq, end) ||
 		    before(TCP_SKB_CB(skb)->end_seq, start)) {
 			tcp_collapse(sk, &tp->out_of_order_queue,
 				     head, skb, start, end);
 			head = skb;
-			if (skb == (struct sk_buff *)&tp->out_of_order_queue)
+			if (!skb)
 				break;
 			/* Start new segment */
 			start = TCP_SKB_CB(skb)->seq;
@@ -4688,10 +4754,11 @@ static int tcp_prune_queue(struct sock *sk)
 		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
 
 	tcp_collapse_ofo_queue(sk);
-	tcp_collapse(sk, &sk->sk_receive_queue,
-		     sk->sk_receive_queue.next,
-		     (struct sk_buff *)&sk->sk_receive_queue,
-		     tp->copied_seq, tp->rcv_nxt);
+	if (!skb_queue_empty(&sk->sk_receive_queue))
+		tcp_collapse(sk, &sk->sk_receive_queue,
+			     skb_peek(&sk->sk_receive_queue),
+			     NULL,
+			     tp->copied_seq, tp->rcv_nxt);
 	sk_mem_reclaim(sk);
 
 	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
@@ -4811,11 +4878,11 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	    /* More than one full frame received... */
-	if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss
+	if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss &&
 	     /* ... and right edge of window advances far enough.
 	      * (tcp_recvmsg() will send ACK otherwise). Or...
 	      */
-	     && __tcp_select_window(sk) >= tp->rcv_wnd) ||
+	     __tcp_select_window(sk) >= tp->rcv_wnd) ||
 	    /* We ACK each frame or... */
 	    tcp_in_quickack_mode(sk) ||
 	    /* We have out of order data. */
@@ -5036,10 +5103,12 @@ out:
 static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 			      struct tcphdr *th, int syn_inerr)
 {
+	u8 *hash_location;
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	/* RFC1323: H1. Apply PAWS check first. */
-	if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp &&
+	if (tcp_fast_parse_options(skb, th, tp, &hash_location) &&
+	    tp->rx_opt.saw_tstamp &&
 	    tcp_paws_discard(sk, skb)) {
 		if (!th->rst) {
 			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
@@ -5327,11 +5396,14 @@ discard:
 static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 					 struct tcphdr *th, unsigned len)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
+	u8 *hash_location;
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct dst_entry *dst = __sk_dst_get(sk);
+	struct tcp_cookie_values *cvp = tp->cookie_values;
 	int saved_clamp = tp->rx_opt.mss_clamp;
 
-	tcp_parse_options(skb, &tp->rx_opt, 0);
+	tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, dst);
 
 	if (th->ack) {
 		/* rfc793:
@@ -5428,6 +5500,31 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		 * Change state from SYN-SENT only after copied_seq
 		 * is initialized. */
 		tp->copied_seq = tp->rcv_nxt;
+
+		if (cvp != NULL &&
+		    cvp->cookie_pair_size > 0 &&
+		    tp->rx_opt.cookie_plus > 0) {
+			int cookie_size = tp->rx_opt.cookie_plus
+					- TCPOLEN_COOKIE_BASE;
+			int cookie_pair_size = cookie_size
+					     + cvp->cookie_desired;
+
+			/* A cookie extension option was sent and returned.
+			 * Note that each incoming SYNACK replaces the
+			 * Responder cookie.  The initial exchange is most
+			 * fragile, as protection against spoofing relies
+			 * entirely upon the sequence and timestamp (above).
+			 * This replacement strategy allows the correct pair to
+			 * pass through, while any others will be filtered via
+			 * Responder verification later.
+			 */
+			if (sizeof(cvp->cookie_pair) >= cookie_pair_size) {
+				memcpy(&cvp->cookie_pair[cvp->cookie_desired],
+				       hash_location, cookie_size);
+				cvp->cookie_pair_size = cookie_pair_size;
+			}
+		}
+
 		smp_mb();
 		tcp_set_state(sk, TCP_ESTABLISHED);