1 files changed, 40 insertions, 19 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 57ae96a04220..28e029632493 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2717,6 +2717,35 @@ static void tcp_try_undo_dsack(struct sock *sk)
         }
 }
 
+/* We can clear retrans_stamp when there are no retransmissions in the
+ * window. It would seem that it is trivially available for us in
+ * tp->retrans_out, however, that kind of assumptions doesn't consider
+ * what will happen if errors occur when sending retransmission for the
+ * second time. ...It could the that such segment has only
+ * TCPCB_EVER_RETRANS set at the present time. It seems that checking
+ * the head skb is enough except for some reneging corner cases that
+ * are not worth the effort.
+ *
+ * Main reason for all this complexity is the fact that connection dying
+ * time now depends on the validity of the retrans_stamp, in particular,
+ * that successive retransmissions of a segment must not advance
+ * retrans_stamp under any conditions.
+ */
+static int tcp_any_retrans_done(struct sock *sk)
+{
+        struct tcp_sock *tp = tcp_sk(sk);
+        struct sk_buff *skb;
+
+        if (tp->retrans_out)
+                return 1;
+
+        skb = tcp_write_queue_head(sk);
+        if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS))
+                return 1;
+
+        return 0;
+}
+
 /* Undo during fast recovery after partial ACK. */
 
 static int tcp_try_undo_partial(struct sock *sk, int acked)
@@ -2729,7 +2758,7 @@ static int tcp_try_undo_partial(struct sock *sk, int acked)
                 /* Plain luck! Hole if filled with delayed
                  * packet, rather than with a retransmit.
                  */
-                if (tp->retrans_out == 0)
+                if (!tcp_any_retrans_done(sk))
                         tp->retrans_stamp = 0;
 
                 tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
@@ -2788,7 +2817,7 @@ static void tcp_try_keep_open(struct sock *sk)
         struct tcp_sock *tp = tcp_sk(sk);
         int state = TCP_CA_Open;
 
-        if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker)
+        if (tcp_left_out(tp) || tcp_any_retrans_done(sk) || tp->undo_marker)
                 state = TCP_CA_Disorder;
 
         if (inet_csk(sk)->icsk_ca_state != state) {
@@ -2803,7 +2832,7 @@ static void tcp_try_to_open(struct sock *sk, int flag)
 
         tcp_verify_left_out(tp);
 
-        if (!tp->frto_counter && tp->retrans_out == 0)
+        if (!tp->frto_counter && !tcp_any_retrans_done(sk))
                 tp->retrans_stamp = 0;
 
         if (flag & FLAG_ECE)
@@ -3698,7 +3727,7 @@ old_ack:
  * the fast version below fails.
  */
 void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
-                       u8 **hvpp, int estab,  struct dst_entry *dst)
+                       u8 **hvpp, int estab)
 {
         unsigned char *ptr;
         struct tcphdr *th = tcp_hdr(skb);
@@ -3737,8 +3766,7 @@ 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 &&
-                                    !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)) {
+                                    !estab && sysctl_tcp_window_scaling) {
                                         __u8 snd_wscale = *(__u8 *)ptr;
                                         opt_rx->wscale_ok = 1;
                                         if (snd_wscale > 14) {
@@ -3754,8 +3782,7 @@ 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 &&
-                                      !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP)))) {
+                                     (!estab && sysctl_tcp_timestamps))) {
                                         opt_rx->saw_tstamp = 1;
                                         opt_rx->rcv_tsval = get_unaligned_be32(ptr);
                                         opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
@@ -3763,8 +3790,7 @@ 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 &&
-                                    !dst_feature(dst, RTAX_FEATURE_NO_SACK)) {
+                                    !estab && sysctl_tcp_sack) {
                                         opt_rx->sack_ok = 1;
                                         tcp_sack_reset(opt_rx);
                                 }
@@ -3849,7 +3875,7 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
                 if (tcp_parse_aligned_timestamp(tp, th))
                         return 1;
         }
-        tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);
+        tcp_parse_options(skb, &tp->rx_opt, hvpp, 1);
         return 1;
 }
 
@@ -4104,10 +4130,8 @@ 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 &&
-            !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
+        if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
                 int mib_idx;
 
                 if (before(seq, tp->rcv_nxt))
@@ -4136,15 +4160,13 @@ 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 &&
-                    !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
+                if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
                         u32 end_seq = TCP_SKB_CB(skb)->end_seq;
 
                         if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
@@ -5399,11 +5421,10 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
         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, &hash_location, 0, dst);
+        tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0);
 
         if (th->ack) {
                 /* rfc793: