1 files changed, 41 insertions, 24 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 28e029632493..b55f60f6fcbe 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -62,6 +62,7 @@
  */
 
 #include <linux/mm.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/sysctl.h>
 #include <linux/kernel.h>
@@ -77,10 +78,13 @@ 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;
+EXPORT_SYMBOL(sysctl_tcp_reordering);
 int sysctl_tcp_ecn __read_mostly = 2;
+EXPORT_SYMBOL(sysctl_tcp_ecn);
 int sysctl_tcp_dsack __read_mostly = 1;
 int sysctl_tcp_app_win __read_mostly = 31;
 int sysctl_tcp_adv_win_scale __read_mostly = 2;
+EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
 
 int sysctl_tcp_stdurg __read_mostly;
 int sysctl_tcp_rfc1337 __read_mostly;
@@ -89,6 +93,8 @@ 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;
+
 int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
 int sysctl_tcp_abc __read_mostly;
 
@@ -416,6 +422,7 @@ void tcp_initialize_rcv_mss(struct sock *sk)
 
         inet_csk(sk)->icsk_ack.rcv_mss = hint;
 }
+EXPORT_SYMBOL(tcp_initialize_rcv_mss);
 
 /* Receiver "autotuning" code.
  *
@@ -2447,6 +2454,16 @@ static int tcp_time_to_recover(struct sock *sk)
                 return 1;
         }
 
+        /* If a thin stream is detected, retransmit after first
+         * received dupack. Employ only if SACK is supported in order
+         * to avoid possible corner-case series of spurious retransmissions
+         * Use only if there are no unsent data.
+         */
+        if ((tp->thin_dupack || sysctl_tcp_thin_dupack) &&
+            tcp_stream_is_thin(tp) && tcp_dupack_heuristics(tp) > 1 &&
+            tcp_is_sack(tp) && !tcp_send_head(sk))
+                return 1;
+
         return 0;
 }
 
@@ -2499,6 +2516,9 @@ static void tcp_mark_head_lost(struct sock *sk, int packets)
         int err;
         unsigned int mss;
 
+        if (packets == 0)
+                return;
+
         WARN_ON(packets > tp->packets_out);
         if (tp->lost_skb_hint) {
                 skb = tp->lost_skb_hint;
@@ -2525,7 +2545,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets)
                         cnt += tcp_skb_pcount(skb);
 
                 if (cnt > packets) {
-                        if (tcp_is_sack(tp) || (oldcnt >= packets))
+                        if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
+                            (oldcnt >= packets))
                                 break;
 
                         mss = skb_shinfo(skb)->gso_size;
@@ -2623,7 +2644,7 @@ static void DBGUNDO(struct sock *sk, const char *msg)
         if (sk->sk_family == AF_INET) {
                 printk(KERN_DEBUG "Undo %s %pI4/%u c%u l%u ss%u/%u p%u\n",
                        msg,
-                       &inet->daddr, ntohs(inet->dport),
+                       &inet->inet_daddr, ntohs(inet->inet_dport),
                        tp->snd_cwnd, tcp_left_out(tp),
                        tp->snd_ssthresh, tp->prior_ssthresh,
                        tp->packets_out);
@@ -2633,7 +2654,7 @@ static void DBGUNDO(struct sock *sk, const char *msg)
                 struct ipv6_pinfo *np = inet6_sk(sk);
                 printk(KERN_DEBUG "Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
                        msg,
-                       &np->daddr, ntohs(inet->dport),
+                       &np->daddr, ntohs(inet->inet_dport),
                        tp->snd_cwnd, tcp_left_out(tp),
                        tp->snd_ssthresh, tp->prior_ssthresh,
                        tp->packets_out);
@@ -2922,6 +2943,7 @@ void tcp_simple_retransmit(struct sock *sk)
         }
         tcp_xmit_retransmit_queue(sk);
 }
+EXPORT_SYMBOL(tcp_simple_retransmit);
 
 /* Process an event, which can update packets-in-flight not trivially.
  * Main goal of this function is to calculate new estimate for left_out,
@@ -3270,7 +3292,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
                  * connection startup slow start one packet too
                  * quickly.  This is severely frowned upon behavior.
                  */
-                if (!(scb->flags & TCPCB_FLAG_SYN)) {
+                if (!(scb->flags & TCPHDR_SYN)) {
                         flag |= FLAG_DATA_ACKED;
                 } else {
                         flag |= FLAG_SYN_ACKED;
@@ -3694,7 +3716,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
         }
 
         if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
-                dst_confirm(sk->sk_dst_cache);
+                dst_confirm(__sk_dst_get(sk));
 
         return 1;
 
@@ -3829,18 +3851,20 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
                                         /* 16-bit multiple */
                                         opt_rx->cookie_plus = opsize;
                                         *hvpp = ptr;
+                                        break;
                                 default:
                                         /* ignore option */
                                         break;
-                                };
+                                }
                                 break;
-                        };
+                        }
 
                         ptr += opsize-2;
                         length -= opsize;
                 }
         }
 }
+EXPORT_SYMBOL(tcp_parse_options);
 
 static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th)
 {
@@ -3907,13 +3931,14 @@ u8 *tcp_parse_md5sig_option(struct tcphdr *th)
                         if (opsize < 2 || opsize > length)
                                 return NULL;
                         if (opcode == TCPOPT_MD5SIG)
-                                return ptr;
+                                return opsize == TCPOLEN_MD5SIG ? ptr : NULL;
                 }
                 ptr += opsize - 2;
                 length -= opsize;
         }
         return NULL;
 }
+EXPORT_SYMBOL(tcp_parse_md5sig_option);
 #endif
 
 static inline void tcp_store_ts_recent(struct tcp_sock *tp)
@@ -4024,6 +4049,8 @@ static void tcp_reset(struct sock *sk)
         default:
                 sk->sk_err = ECONNRESET;
         }
+        /* This barrier is coupled with smp_rmb() in tcp_poll() */
+        smp_wmb();
 
         if (!sock_flag(sk, SOCK_DEAD))
                 sk->sk_error_report(sk);
@@ -4303,7 +4330,7 @@ static void tcp_ofo_queue(struct sock *sk)
                 }
 
                 if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
-                        SOCK_DEBUG(sk, "ofo packet was already received \n");
+                        SOCK_DEBUG(sk, "ofo packet was already received\n");
                         __skb_unlink(skb, &tp->out_of_order_queue);
                         __kfree_skb(skb);
                         continue;
@@ -4351,6 +4378,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
         if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)
                 goto drop;
 
+        skb_dst_drop(skb);
         __skb_pull(skb, th->doff * 4);
 
         TCP_ECN_accept_cwr(tp, skb);
@@ -5414,6 +5442,7 @@ discard:
         __kfree_skb(skb);
         return 0;
 }
+EXPORT_SYMBOL(tcp_rcv_established);
 
 static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
                                          struct tcphdr *th, unsigned len)
@@ -5783,11 +5812,9 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 
                                 /* tcp_ack considers this ACK as duplicate
                                  * and does not calculate rtt.
-                                 * Fix it at least with timestamps.
+                                 * Force it here.
                                  */
-                                if (tp->rx_opt.saw_tstamp &&
-                                    tp->rx_opt.rcv_tsecr && !tp->srtt)
-                                        tcp_ack_saw_tstamp(sk, 0);
+                                tcp_ack_update_rtt(sk, 0, 0);
 
                                 if (tp->rx_opt.tstamp_ok)
                                         tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
@@ -5819,7 +5846,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
                         if (tp->snd_una == tp->write_seq) {
                                 tcp_set_state(sk, TCP_FIN_WAIT2);
                                 sk->sk_shutdown |= SEND_SHUTDOWN;
-                                dst_confirm(sk->sk_dst_cache);
+                                dst_confirm(__sk_dst_get(sk));
 
                                 if (!sock_flag(sk, SOCK_DEAD))
                                         /* Wake up lingering close() */
@@ -5915,14 +5942,4 @@ discard:
         }
         return 0;
 }
-
-EXPORT_SYMBOL(sysctl_tcp_ecn);
-EXPORT_SYMBOL(sysctl_tcp_reordering);
-EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
-EXPORT_SYMBOL(tcp_parse_options);
-#ifdef CONFIG_TCP_MD5SIG
-EXPORT_SYMBOL(tcp_parse_md5sig_option);
-#endif
-EXPORT_SYMBOL(tcp_rcv_established);
 EXPORT_SYMBOL(tcp_rcv_state_process);
-EXPORT_SYMBOL(tcp_initialize_rcv_mss);