1 files changed, 31 insertions, 19 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 990a5849323..fe3b4bdfd25 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -362,6 +362,17 @@ struct tcp_out_options {
         __u32 tsval, tsecr;     /* need to include OPTION_TS */
 };
 
+/* Beware: Something in the Internet is very sensitive to the ordering of
+ * TCP options, we learned this through the hard way, so be careful here.
+ * Luckily we can at least blame others for their non-compliance but from
+ * inter-operatibility perspective it seems that we're somewhat stuck with
+ * the ordering which we have been using if we want to keep working with
+ * those broken things (not that it currently hurts anybody as there isn't
+ * particular reason why the ordering would need to be changed).
+ *
+ * At least SACK_PERM as the first option is known to lead to a disaster
+ * (but it may well be that other scenarios fail similarly).
+ */
 static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
                               const struct tcp_out_options *opts,
                               __u8 **md5_hash) {
@@ -376,6 +387,12 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
                 *md5_hash = NULL;
         }
 
+        if (unlikely(opts->mss)) {
+                *ptr++ = htonl((TCPOPT_MSS << 24) |
+                               (TCPOLEN_MSS << 16) |
+                               opts->mss);
+        }
+
         if (likely(OPTION_TS & opts->options)) {
                 if (unlikely(OPTION_SACK_ADVERTISE & opts->options)) {
                         *ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
@@ -392,12 +409,6 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
                 *ptr++ = htonl(opts->tsecr);
         }
 
-        if (unlikely(opts->mss)) {
-                *ptr++ = htonl((TCPOPT_MSS << 24) |
-                               (TCPOLEN_MSS << 16) |
-                               opts->mss);
-        }
-
         if (unlikely(OPTION_SACK_ADVERTISE & opts->options &&
                      !(OPTION_TS & opts->options))) {
                 *ptr++ = htonl((TCPOPT_NOP << 24) |
@@ -432,7 +443,7 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 
                 if (tp->rx_opt.dsack) {
                         tp->rx_opt.dsack = 0;
-                        tp->rx_opt.eff_sacks--;
+                        tp->rx_opt.eff_sacks = tp->rx_opt.num_sacks;
                 }
         }
 }
@@ -1017,10 +1028,6 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
 
 /* Compute the current effective MSS, taking SACKs and IP options,
  * and even PMTU discovery events into account.
- *
- * LARGESEND note: !tcp_urg_mode is overkill, only frames up to snd_up
- * cannot be large. However, taking into account rare use of URG, this
- * is not a big flaw.
  */
 unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
 {
@@ -1035,7 +1042,7 @@ unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
 
         mss_now = tp->mss_cache;
 
-        if (large_allowed && sk_can_gso(sk) && !tcp_urg_mode(tp))
+        if (large_allowed && sk_can_gso(sk))
                 doing_tso = 1;
 
         if (dst) {
@@ -1505,6 +1512,10 @@ static int tcp_mtu_probe(struct sock *sk)
  * send_head.  This happens as incoming acks open up the remote
  * window for us.
  *
+ * LARGESEND note: !tcp_urg_mode is overkill, only frames between
+ * snd_up-64k-mss .. snd_up cannot be large. However, taking into
+ * account rare use of URG, this is not a big flaw.
+ *
  * Returns 1, if no segments are in flight and we have queued segments, but
  * cannot send anything now because of SWS or another problem.
  */
@@ -1556,7 +1567,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle)
                 }
 
                 limit = mss_now;
-                if (tso_segs > 1)
+                if (tso_segs > 1 && !tcp_urg_mode(tp))
                         limit = tcp_mss_split_point(sk, skb, mss_now,
                                                     cwnd_quota);
 
@@ -1605,6 +1616,7 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
  */
 void tcp_push_one(struct sock *sk, unsigned int mss_now)
 {
+        struct tcp_sock *tp = tcp_sk(sk);
         struct sk_buff *skb = tcp_send_head(sk);
         unsigned int tso_segs, cwnd_quota;
 
@@ -1619,7 +1631,7 @@ void tcp_push_one(struct sock *sk, unsigned int mss_now)
                 BUG_ON(!tso_segs);
 
                 limit = mss_now;
-                if (tso_segs > 1)
+                if (tso_segs > 1 && !tcp_urg_mode(tp))
                         limit = tcp_mss_split_point(sk, skb, mss_now,
                                                     cwnd_quota);
 
@@ -2268,6 +2280,11 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
         }
 
         memset(&opts, 0, sizeof(opts));
+#ifdef CONFIG_SYN_COOKIES
+        if (unlikely(req->cookie_ts))
+                TCP_SKB_CB(skb)->when = cookie_init_timestamp(req);
+        else
+#endif
         TCP_SKB_CB(skb)->when = tcp_time_stamp;
         tcp_header_size = tcp_synack_options(sk, req, mss,
                                              skb, &opts, &md5) +
@@ -2293,11 +2310,6 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 
         /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
         th->window = htons(min(req->rcv_wnd, 65535U));
-#ifdef CONFIG_SYN_COOKIES
-        if (unlikely(req->cookie_ts))
-                TCP_SKB_CB(skb)->when = cookie_init_timestamp(req);
-        else
-#endif
         tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
         th->doff = (tcp_header_size >> 2);
         TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);