4 files changed, 88 insertions, 6 deletions

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 22cf5e1ac987..ab2791b3189d 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -390,6 +390,7 @@ enum
         NET_TCP_BIC_BETA=108,
         NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR=109,
         NET_TCP_CONG_CONTROL=110,
+        NET_TCP_ABC=111,
 };
 
 enum {
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index ac4ca44c75ca..0e1da6602e05 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -307,6 +307,21 @@ struct tcp_sock {
         struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */
         struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/
 
+        struct tcp_sack_block recv_sack_cache[4];
+
+        /* from STCP, retrans queue hinting */
+        struct sk_buff* lost_skb_hint;
+
+        struct sk_buff *scoreboard_skb_hint;
+        struct sk_buff *retransmit_skb_hint;
+        struct sk_buff *forward_skb_hint;
+        struct sk_buff *fastpath_skb_hint;
+
+        int     fastpath_cnt_hint;
+        int     lost_cnt_hint;
+        int     retransmit_cnt_hint;
+        int     forward_cnt_hint;
+
         __u16   advmss;         /* Advertised MSS                       */
         __u16   prior_ssthresh; /* ssthresh saved at recovery start     */
         __u32   lost_out;       /* Lost packets                 */
@@ -326,6 +341,7 @@ struct tcp_sock {
         __u32   snd_up;         /* Urgent pointer               */
 
         __u32   total_retrans;  /* Total retransmits for entire connection */
+        __u32   bytes_acked;    /* Appropriate Byte Counting - RFC3465 */
 
         unsigned int            keepalive_time;   /* time before keep alive takes place */
         unsigned int            keepalive_intvl;  /* time interval between keep alive probes */
diff --git a/include/net/sock.h b/include/net/sock.h
index ff13c4cc287a..982b4ecd187b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1247,6 +1247,12 @@ static inline struct page *sk_stream_alloc_page(struct sock *sk)
                      (skb != (struct sk_buff *)&(sk)->sk_write_queue);  \
                      skb = skb->next)
 
+/*from STCP for fast SACK Process*/
+#define sk_stream_for_retrans_queue_from(skb, sk)                       \
+                for (; (skb != (sk)->sk_send_head) &&                   \
+                     (skb != (struct sk_buff *)&(sk)->sk_write_queue);  \
+                     skb = skb->next)
+
 /*
  *      Default write policy as shown to user space via poll/select/SIGIO
  */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 96cc3b434e40..0f9848011972 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -89,10 +89,10 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
                                  */
 
 #define TCP_SYN_RETRIES  5      /* number of times to retry active opening a
-                                 * connection: ~180sec is RFC minumum   */
+                                 * connection: ~180sec is RFC minimum   */
 
 #define TCP_SYNACK_RETRIES 5    /* number of times to retry passive opening a
-                                 * connection: ~180sec is RFC minumum   */
+                                 * connection: ~180sec is RFC minimum   */
 
 
 #define TCP_ORPHAN_RETRIES 7    /* number of times to retry on an orphaned
@@ -180,7 +180,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 /* Flags in tp->nonagle */
 #define TCP_NAGLE_OFF           1       /* Nagle's algo is disabled */
 #define TCP_NAGLE_CORK          2       /* Socket is corked         */
-#define TCP_NAGLE_PUSH          4       /* Cork is overriden for already queued data */
+#define TCP_NAGLE_PUSH          4       /* Cork is overridden for already queued data */
 
 extern struct inet_timewait_death_row tcp_death_row;
 
@@ -218,6 +218,7 @@ extern int sysctl_tcp_low_latency;
 extern int sysctl_tcp_nometrics_save;
 extern int sysctl_tcp_moderate_rcvbuf;
 extern int sysctl_tcp_tso_win_divisor;
+extern int sysctl_tcp_abc;
 
 extern atomic_t tcp_memory_allocated;
 extern atomic_t tcp_sockets_allocated;
@@ -551,13 +552,13 @@ extern u32	__tcp_select_window(struct sock *sk);
 
 /* TCP timestamps are only 32-bits, this causes a slight
  * complication on 64-bit systems since we store a snapshot
- * of jiffies in the buffer control blocks below.  We decidely
+ * of jiffies in the buffer control blocks below.  We decidedly
  * only use of the low 32-bits of jiffies and hide the ugly
  * casts with the following macro.
  */
 #define tcp_time_stamp          ((__u32)(jiffies))
 
-/* This is what the send packet queueing engine uses to pass
+/* This is what the send packet queuing engine uses to pass
  * TCP per-packet control information to the transmission
  * code.  We also store the host-order sequence numbers in
  * here too.  This is 36 bytes on 32-bit architectures,
@@ -597,7 +598,7 @@ struct tcp_skb_cb {
 #define TCPCB_EVER_RETRANS      0x80    /* Ever retransmitted frame     */
 #define TCPCB_RETRANS           (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS)
 
-#define TCPCB_URG               0x20    /* Urgent pointer advenced here */
+#define TCPCB_URG               0x20    /* Urgent pointer advanced here */
 
 #define TCPCB_AT_TAIL           (TCPCB_URG)
 
@@ -765,6 +766,33 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk)
                             (tp->snd_cwnd >> 2)));
 }
 
+/*
+ * Linear increase during slow start
+ */
+static inline void tcp_slow_start(struct tcp_sock *tp)
+{
+        if (sysctl_tcp_abc) {
+                /* RFC3465: Slow Start
+                 * TCP sender SHOULD increase cwnd by the number of
+                 * previously unacknowledged bytes ACKed by each incoming
+                 * acknowledgment, provided the increase is not more than L
+                 */
+                if (tp->bytes_acked < tp->mss_cache)
+                        return;
+
+                /* We MAY increase by 2 if discovered delayed ack */
+                if (sysctl_tcp_abc > 1 && tp->bytes_acked > 2*tp->mss_cache) {
+                        if (tp->snd_cwnd < tp->snd_cwnd_clamp)
+                                tp->snd_cwnd++;
+                }
+        }
+        tp->bytes_acked = 0;
+
+        if (tp->snd_cwnd < tp->snd_cwnd_clamp)
+                tp->snd_cwnd++;
+}
+
+
 static inline void tcp_sync_left_out(struct tcp_sock *tp)
 {
         if (tp->rx_opt.sack_ok &&
@@ -794,6 +822,7 @@ static inline void tcp_enter_cwr(struct sock *sk)
         struct tcp_sock *tp = tcp_sk(sk);
 
         tp->prior_ssthresh = 0;
+        tp->bytes_acked = 0;
         if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
                 __tcp_enter_cwr(sk);
                 tcp_set_ca_state(sk, TCP_CA_CWR);
@@ -810,6 +839,27 @@ static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp)
         return 3;
 }
 
+/* RFC2861 Check whether we are limited by application or congestion window
+ * This is the inverse of cwnd check in tcp_tso_should_defer
+ */
+static inline int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
+{
+        const struct tcp_sock *tp = tcp_sk(sk);
+        u32 left;
+
+        if (in_flight >= tp->snd_cwnd)
+                return 1;
+
+        if (!(sk->sk_route_caps & NETIF_F_TSO))
+                return 0;
+
+        left = tp->snd_cwnd - in_flight;
+        if (sysctl_tcp_tso_win_divisor)
+                return left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd;
+        else
+                return left <= tcp_max_burst(tp);
+}
+
 static __inline__ void tcp_minshall_update(struct tcp_sock *tp, int mss, 
                                            const struct sk_buff *skb)
 {
@@ -1157,6 +1207,15 @@ static inline void tcp_mib_init(void)
         TCP_ADD_STATS_USER(TCP_MIB_MAXCONN, -1);
 }
 
+/*from STCP */
+static inline void clear_all_retrans_hints(struct tcp_sock *tp){
+        tp->lost_skb_hint = NULL;
+        tp->scoreboard_skb_hint = NULL;
+        tp->retransmit_skb_hint = NULL;
+        tp->forward_skb_hint = NULL;
+        tp->fastpath_skb_hint = NULL;
+}
+
 /* /proc */
 enum tcp_seq_states {
         TCP_SEQ_STATE_LISTENING,