Merge /spare/repo/linux-2.6/

1 files changed, 445 insertions, 139 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f17c6577e337..dd30dd137b74 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -49,7 +49,7 @@ int sysctl_tcp_retrans_collapse = 1;
  * will allow a single TSO frame to consume.  Building TSO frames
  * which are too large can cause TCP streams to be bursty.
  */
-int sysctl_tcp_tso_win_divisor = 8;
+int sysctl_tcp_tso_win_divisor = 3;
 
 static inline void update_send_head(struct sock *sk, struct tcp_sock *tp,
                                     struct sk_buff *skb)
@@ -111,8 +111,7 @@ static void tcp_cwnd_restart(struct tcp_sock *tp, struct dst_entry *dst)
         u32 restart_cwnd = tcp_init_cwnd(tp, dst);
         u32 cwnd = tp->snd_cwnd;
 
-        if (tcp_is_vegas(tp)) 
-                tcp_vegas_enable(tp);
+        tcp_ca_event(tp, CA_EVENT_CWND_RESTART);
 
         tp->snd_ssthresh = tcp_current_ssthresh(tp);
         restart_cwnd = min(restart_cwnd, cwnd);
@@ -141,11 +140,11 @@ static inline void tcp_event_data_sent(struct tcp_sock *tp,
                 tp->ack.pingpong = 1;
 }
 
-static __inline__ void tcp_event_ack_sent(struct sock *sk)
+static __inline__ void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
 {
         struct tcp_sock *tp = tcp_sk(sk);
 
-        tcp_dec_quickack_mode(tp);
+        tcp_dec_quickack_mode(tp, pkts);
         tcp_clear_xmit_timer(sk, TCP_TIME_DACK);
 }
 
@@ -280,6 +279,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 #define SYSCTL_FLAG_WSCALE      0x2
 #define SYSCTL_FLAG_SACK        0x4
 
+                /* If congestion control is doing timestamping */
+                if (tp->ca_ops->rtt_sample)
+                        do_gettimeofday(&skb->stamp);
+
                 sysctl_flags = 0;
                 if (tcb->flags & TCPCB_FLAG_SYN) {
                         tcp_header_size = sizeof(struct tcphdr) + TCPOLEN_MSS;
@@ -304,17 +307,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb)
                                             (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK));
                 }
                 
-                /*
-                 * If the connection is idle and we are restarting,
-                 * then we don't want to do any Vegas calculations
-                 * until we get fresh RTT samples.  So when we
-                 * restart, we reset our Vegas state to a clean
-                 * slate. After we get acks for this flight of
-                 * packets, _then_ we can make Vegas calculations
-                 * again.
-                 */
-                if (tcp_is_vegas(tp) && tcp_packets_in_flight(tp) == 0)
-                        tcp_vegas_enable(tp);
+                if (tcp_packets_in_flight(tp) == 0)
+                        tcp_ca_event(tp, CA_EVENT_TX_START);
 
                 th = (struct tcphdr *) skb_push(skb, tcp_header_size);
                 skb->h.th = th;
@@ -361,7 +355,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb)
                 tp->af_specific->send_check(sk, th, skb->len, skb);
 
                 if (tcb->flags & TCPCB_FLAG_ACK)
-                        tcp_event_ack_sent(sk);
+                        tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
 
                 if (skb->len != tcp_header_size)
                         tcp_event_data_sent(tp, skb, sk);
@@ -409,42 +403,9 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
                 sk->sk_send_head = skb;
 }
 
-static inline void tcp_tso_set_push(struct sk_buff *skb)
-{
-        /* Force push to be on for any TSO frames to workaround
-         * problems with busted implementations like Mac OS-X that
-         * hold off socket receive wakeups until push is seen.
-         */
-        if (tcp_skb_pcount(skb) > 1)
-                TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
-}
-
-/* Send _single_ skb sitting at the send head. This function requires
- * true push pending frames to setup probe timer etc.
- */
-void tcp_push_one(struct sock *sk, unsigned cur_mss)
-{
-        struct tcp_sock *tp = tcp_sk(sk);
-        struct sk_buff *skb = sk->sk_send_head;
-
-        if (tcp_snd_test(sk, skb, cur_mss, TCP_NAGLE_PUSH)) {
-                /* Send it out now. */
-                TCP_SKB_CB(skb)->when = tcp_time_stamp;
-                tcp_tso_set_push(skb);
-                if (!tcp_transmit_skb(sk, skb_clone(skb, sk->sk_allocation))) {
-                        sk->sk_send_head = NULL;
-                        tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
-                        tcp_packets_out_inc(sk, tp, skb);
-                        return;
-                }
-        }
-}
-
-void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb)
+static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
 {
-        struct tcp_sock *tp = tcp_sk(sk);
-
-        if (skb->len <= tp->mss_cache_std ||
+        if (skb->len <= mss_now ||
             !(sk->sk_route_caps & NETIF_F_TSO)) {
                 /* Avoid the costly divide in the normal
                  * non-TSO case.
@@ -454,10 +415,10 @@ void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb)
         } else {
                 unsigned int factor;
 
-                factor = skb->len + (tp->mss_cache_std - 1);
-                factor /= tp->mss_cache_std;
+                factor = skb->len + (mss_now - 1);
+                factor /= mss_now;
                 skb_shinfo(skb)->tso_segs = factor;
-                skb_shinfo(skb)->tso_size = tp->mss_cache_std;
+                skb_shinfo(skb)->tso_size = mss_now;
         }
 }
 
@@ -466,7 +427,7 @@ void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb)
  * packet to the list.  This won't be called frequently, I hope. 
  * Remember, these are still headerless SKBs at this point.
  */
-static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len)
+static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss_now)
 {
         struct tcp_sock *tp = tcp_sk(sk);
         struct sk_buff *buff;
@@ -521,6 +482,7 @@ static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len)
          * skbs, which it never sent before. --ANK
          */
         TCP_SKB_CB(buff)->when = TCP_SKB_CB(skb)->when;
+        buff->stamp = skb->stamp;
 
         if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) {
                 tp->lost_out -= tcp_skb_pcount(skb);
@@ -528,8 +490,8 @@ static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len)
         }
 
         /* Fix up tso_factor for both original and new SKB.  */
-        tcp_set_skb_tso_segs(sk, skb);
-        tcp_set_skb_tso_segs(sk, buff);
+        tcp_set_skb_tso_segs(sk, skb, mss_now);
+        tcp_set_skb_tso_segs(sk, buff, mss_now);
 
         if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) {
                 tp->lost_out += tcp_skb_pcount(skb);
@@ -542,6 +504,7 @@ static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len)
         }
 
         /* Link BUFF into the send queue. */
+        skb_header_release(buff);
         __skb_append(skb, buff);
 
         return 0;
@@ -604,7 +567,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
          * factor and mss.
          */
         if (tcp_skb_pcount(skb) > 1)
-                tcp_set_skb_tso_segs(sk, skb);
+                tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk, 1));
 
         return 0;
 }
@@ -662,7 +625,7 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
 
         /* And store cached results */
         tp->pmtu_cookie = pmtu;
-        tp->mss_cache = tp->mss_cache_std = mss_now;
+        tp->mss_cache = mss_now;
 
         return mss_now;
 }
@@ -674,57 +637,315 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
  * 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)
+unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
 {
         struct tcp_sock *tp = tcp_sk(sk);
         struct dst_entry *dst = __sk_dst_get(sk);
-        unsigned int do_large, mss_now;
+        u32 mss_now;
+        u16 xmit_size_goal;
+        int doing_tso = 0;
+
+        mss_now = tp->mss_cache;
+
+        if (large_allowed &&
+            (sk->sk_route_caps & NETIF_F_TSO) &&
+            !tp->urg_mode)
+                doing_tso = 1;
 
-        mss_now = tp->mss_cache_std;
         if (dst) {
                 u32 mtu = dst_mtu(dst);
                 if (mtu != tp->pmtu_cookie)
                         mss_now = tcp_sync_mss(sk, mtu);
         }
 
-        do_large = (large &&
-                    (sk->sk_route_caps & NETIF_F_TSO) &&
-                    !tp->urg_mode);
+        if (tp->rx_opt.eff_sacks)
+                mss_now -= (TCPOLEN_SACK_BASE_ALIGNED +
+                            (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK));
 
-        if (do_large) {
-                unsigned int large_mss, factor, limit;
+        xmit_size_goal = mss_now;
 
-                large_mss = 65535 - tp->af_specific->net_header_len -
+        if (doing_tso) {
+                xmit_size_goal = 65535 -
+                        tp->af_specific->net_header_len -
                         tp->ext_header_len - tp->tcp_header_len;
 
-                if (tp->max_window && large_mss > (tp->max_window>>1))
-                        large_mss = max((tp->max_window>>1),
-                                        68U - tp->tcp_header_len);
+                if (tp->max_window &&
+                    (xmit_size_goal > (tp->max_window >> 1)))
+                        xmit_size_goal = max((tp->max_window >> 1),
+                                             68U - tp->tcp_header_len);
 
-                factor = large_mss / mss_now;
+                xmit_size_goal -= (xmit_size_goal % mss_now);
+        }
+        tp->xmit_size_goal = xmit_size_goal;
 
-                /* Always keep large mss multiple of real mss, but
-                 * do not exceed 1/tso_win_divisor of the congestion window
-                 * so we can keep the ACK clock ticking and minimize
-                 * bursting.
-                 */
-                limit = tp->snd_cwnd;
-                if (sysctl_tcp_tso_win_divisor)
-                        limit /= sysctl_tcp_tso_win_divisor;
-                limit = max(1U, limit);
-                if (factor > limit)
-                        factor = limit;
+        return mss_now;
+}
+
+/* Congestion window validation. (RFC2861) */
 
-                tp->mss_cache = mss_now * factor;
+static inline void tcp_cwnd_validate(struct sock *sk, struct tcp_sock *tp)
+{
+        __u32 packets_out = tp->packets_out;
+
+        if (packets_out >= tp->snd_cwnd) {
+                /* Network is feed fully. */
+                tp->snd_cwnd_used = 0;
+                tp->snd_cwnd_stamp = tcp_time_stamp;
+        } else {
+                /* Network starves. */
+                if (tp->packets_out > tp->snd_cwnd_used)
+                        tp->snd_cwnd_used = tp->packets_out;
 
-                mss_now = tp->mss_cache;
+                if ((s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= tp->rto)
+                        tcp_cwnd_application_limited(sk);
         }
+}
 
-        if (tp->rx_opt.eff_sacks)
-                mss_now -= (TCPOLEN_SACK_BASE_ALIGNED +
-                            (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK));
-        return mss_now;
+static unsigned int tcp_window_allows(struct tcp_sock *tp, struct sk_buff *skb, unsigned int mss_now, unsigned int cwnd)
+{
+        u32 window, cwnd_len;
+
+        window = (tp->snd_una + tp->snd_wnd - TCP_SKB_CB(skb)->seq);
+        cwnd_len = mss_now * cwnd;
+        return min(window, cwnd_len);
+}
+
+/* Can at least one segment of SKB be sent right now, according to the
+ * congestion window rules?  If so, return how many segments are allowed.
+ */
+static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, struct sk_buff *skb)
+{
+        u32 in_flight, cwnd;
+
+        /* Don't be strict about the congestion window for the final FIN.  */
+        if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)
+                return 1;
+
+        in_flight = tcp_packets_in_flight(tp);
+        cwnd = tp->snd_cwnd;
+        if (in_flight < cwnd)
+                return (cwnd - in_flight);
+
+        return 0;
+}
+
+/* This must be invoked the first time we consider transmitting
+ * SKB onto the wire.
+ */
+static inline int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
+{
+        int tso_segs = tcp_skb_pcount(skb);
+
+        if (!tso_segs ||
+            (tso_segs > 1 &&
+             skb_shinfo(skb)->tso_size != mss_now)) {
+                tcp_set_skb_tso_segs(sk, skb, mss_now);
+                tso_segs = tcp_skb_pcount(skb);
+        }
+        return tso_segs;
+}
+
+static inline int tcp_minshall_check(const struct tcp_sock *tp)
+{
+        return after(tp->snd_sml,tp->snd_una) &&
+                !after(tp->snd_sml, tp->snd_nxt);
+}
+
+/* Return 0, if packet can be sent now without violation Nagle's rules:
+ * 1. It is full sized.
+ * 2. Or it contains FIN. (already checked by caller)
+ * 3. Or TCP_NODELAY was set.
+ * 4. Or TCP_CORK is not set, and all sent packets are ACKed.
+ *    With Minshall's modification: all sent small packets are ACKed.
+ */
+
+static inline int tcp_nagle_check(const struct tcp_sock *tp,
+                                  const struct sk_buff *skb, 
+                                  unsigned mss_now, int nonagle)
+{
+        return (skb->len < mss_now &&
+                ((nonagle&TCP_NAGLE_CORK) ||
+                 (!nonagle &&
+                  tp->packets_out &&
+                  tcp_minshall_check(tp))));
+}
+
+/* Return non-zero if the Nagle test allows this packet to be
+ * sent now.
+ */
+static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb,
+                                 unsigned int cur_mss, int nonagle)
+{
+        /* Nagle rule does not apply to frames, which sit in the middle of the
+         * write_queue (they have no chances to get new data).
+         *
+         * This is implemented in the callers, where they modify the 'nonagle'
+         * argument based upon the location of SKB in the send queue.
+         */
+        if (nonagle & TCP_NAGLE_PUSH)
+                return 1;
+
+        /* Don't use the nagle rule for urgent data (or for the final FIN).  */
+        if (tp->urg_mode ||
+            (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN))
+                return 1;
+
+        if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
+                return 1;
+
+        return 0;
+}
+
+/* Does at least the first segment of SKB fit into the send window? */
+static inline int tcp_snd_wnd_test(struct tcp_sock *tp, struct sk_buff *skb, unsigned int cur_mss)
+{
+        u32 end_seq = TCP_SKB_CB(skb)->end_seq;
+
+        if (skb->len > cur_mss)
+                end_seq = TCP_SKB_CB(skb)->seq + cur_mss;
+
+        return !after(end_seq, tp->snd_una + tp->snd_wnd);
+}
+
+/* This checks if the data bearing packet SKB (usually sk->sk_send_head)
+ * should be put on the wire right now.  If so, it returns the number of
+ * packets allowed by the congestion window.
+ */
+static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb,
+                                 unsigned int cur_mss, int nonagle)
+{
+        struct tcp_sock *tp = tcp_sk(sk);
+        unsigned int cwnd_quota;
+
+        tcp_init_tso_segs(sk, skb, cur_mss);
+
+        if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
+                return 0;
+
+        cwnd_quota = tcp_cwnd_test(tp, skb);
+        if (cwnd_quota &&
+            !tcp_snd_wnd_test(tp, skb, cur_mss))
+                cwnd_quota = 0;
+
+        return cwnd_quota;
+}
+
+static inline int tcp_skb_is_last(const struct sock *sk, 
+                                  const struct sk_buff *skb)
+{
+        return skb->next == (struct sk_buff *)&sk->sk_write_queue;
+}
+
+int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp)
+{
+        struct sk_buff *skb = sk->sk_send_head;
+
+        return (skb &&
+                tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
+                             (tcp_skb_is_last(sk, skb) ?
+                              TCP_NAGLE_PUSH :
+                              tp->nonagle)));
+}
+
+/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
+ * which is put after SKB on the list.  It is very much like
+ * tcp_fragment() except that it may make several kinds of assumptions
+ * in order to speed up the splitting operation.  In particular, we
+ * know that all the data is in scatter-gather pages, and that the
+ * packet has never been sent out before (and thus is not cloned).
+ */
+static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, unsigned int mss_now)
+{
+        struct sk_buff *buff;
+        int nlen = skb->len - len;
+        u16 flags;
+
+        /* All of a TSO frame must be composed of paged data.  */
+        if (skb->len != skb->data_len)
+                return tcp_fragment(sk, skb, len, mss_now);
+
+        buff = sk_stream_alloc_pskb(sk, 0, 0, GFP_ATOMIC);
+        if (unlikely(buff == NULL))
+                return -ENOMEM;
+
+        buff->truesize = nlen;
+        skb->truesize -= nlen;
+
+        /* Correct the sequence numbers. */
+        TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len;
+        TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
+        TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;
+
+        /* PSH and FIN should only be set in the second packet. */
+        flags = TCP_SKB_CB(skb)->flags;
+        TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
+        TCP_SKB_CB(buff)->flags = flags;
+
+        /* This packet was never sent out yet, so no SACK bits. */
+        TCP_SKB_CB(buff)->sacked = 0;
+
+        buff->ip_summed = skb->ip_summed = CHECKSUM_HW;
+        skb_split(skb, buff, len);
+
+        /* Fix up tso_factor for both original and new SKB.  */
+        tcp_set_skb_tso_segs(sk, skb, mss_now);
+        tcp_set_skb_tso_segs(sk, buff, mss_now);
+
+        /* Link BUFF into the send queue. */
+        skb_header_release(buff);
+        __skb_append(skb, buff);
+
+        return 0;
+}
+
+/* Try to defer sending, if possible, in order to minimize the amount
+ * of TSO splitting we do.  View it as a kind of TSO Nagle test.
+ *
+ * This algorithm is from John Heffner.
+ */
+static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb)
+{
+        u32 send_win, cong_win, limit, in_flight;
+
+        if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)
+                return 0;
+
+        if (tp->ca_state != TCP_CA_Open)
+                return 0;
+
+        in_flight = tcp_packets_in_flight(tp);
+
+        BUG_ON(tcp_skb_pcount(skb) <= 1 ||
+               (tp->snd_cwnd <= in_flight));
+
+        send_win = (tp->snd_una + tp->snd_wnd) - TCP_SKB_CB(skb)->seq;
+
+        /* From in_flight test above, we know that cwnd > in_flight.  */
+        cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache;
+
+        limit = min(send_win, cong_win);
+
+        if (sysctl_tcp_tso_win_divisor) {
+                u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
+
+                /* If at least some fraction of a window is available,
+                 * just use it.
+                 */
+                chunk /= sysctl_tcp_tso_win_divisor;
+                if (limit >= chunk)
+                        return 0;
+        } else {
+                /* Different approach, try not to defer past a single
+                 * ACK.  Receiver should ACK every other full sized
+                 * frame, so if we have space for more than 3 frames
+                 * then send now.
+                 */
+                if (limit > tcp_max_burst(tp) * tp->mss_cache)
+                        return 0;
+        }
+
+        /* Ok, it looks like it is advisable to defer.  */
+        return 1;
 }
 
 /* This routine writes packets to the network.  It advances the
@@ -734,57 +955,142 @@ unsigned int tcp_current_mss(struct sock *sk, int large)
  * Returns 1, if no segments are in flight and we have queued segments, but
  * cannot send anything now because of SWS or another problem.
  */
-int tcp_write_xmit(struct sock *sk, int nonagle)
+static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle)
 {
         struct tcp_sock *tp = tcp_sk(sk);
-        unsigned int mss_now;
+        struct sk_buff *skb;
+        unsigned int tso_segs, sent_pkts;
+        int cwnd_quota;
 
         /* If we are closed, the bytes will have to remain here.
          * In time closedown will finish, we empty the write queue and all
          * will be happy.
          */
-        if (sk->sk_state != TCP_CLOSE) {
-                struct sk_buff *skb;
-                int sent_pkts = 0;
+        if (unlikely(sk->sk_state == TCP_CLOSE))
+                return 0;
 
-                /* Account for SACKS, we may need to fragment due to this.
-                 * It is just like the real MSS changing on us midstream.
-                 * We also handle things correctly when the user adds some
-                 * IP options mid-stream.  Silly to do, but cover it.
-                 */
-                mss_now = tcp_current_mss(sk, 1);
-
-                while ((skb = sk->sk_send_head) &&
-                       tcp_snd_test(sk, skb, mss_now,
-                                    tcp_skb_is_last(sk, skb) ? nonagle :
-                                                               TCP_NAGLE_PUSH)) {
-                        if (skb->len > mss_now) {
-                                if (tcp_fragment(sk, skb, mss_now))
-                                        break;
-                        }
+        sent_pkts = 0;
+        while ((skb = sk->sk_send_head)) {
+                unsigned int limit;
 
-                        TCP_SKB_CB(skb)->when = tcp_time_stamp;
-                        tcp_tso_set_push(skb);
-                        if (tcp_transmit_skb(sk, skb_clone(skb, GFP_ATOMIC)))
+                tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
+                BUG_ON(!tso_segs);
+
+                cwnd_quota = tcp_cwnd_test(tp, skb);
+                if (!cwnd_quota)
+                        break;
+
+                if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
+                        break;
+
+                if (tso_segs == 1) {
+                        if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
+                                                     (tcp_skb_is_last(sk, skb) ?
+                                                      nonagle : TCP_NAGLE_PUSH))))
                                 break;
+                } else {
+                        if (tcp_tso_should_defer(sk, tp, skb))
+                                break;
+                }
 
-                        /* Advance the send_head.  This one is sent out.
-                         * This call will increment packets_out.
-                         */
-                        update_send_head(sk, tp, skb);
+                limit = mss_now;
+                if (tso_segs > 1) {
+                        limit = tcp_window_allows(tp, skb,
+                                                  mss_now, cwnd_quota);
+
+                        if (skb->len < limit) {
+                                unsigned int trim = skb->len % mss_now;
 
-                        tcp_minshall_update(tp, mss_now, skb);
-                        sent_pkts = 1;
+                                if (trim)
+                                        limit = skb->len - trim;
+                        }
                 }
 
-                if (sent_pkts) {
-                        tcp_cwnd_validate(sk, tp);
-                        return 0;
+                if (skb->len > limit &&
+                    unlikely(tso_fragment(sk, skb, limit, mss_now)))
+                        break;
+
+                TCP_SKB_CB(skb)->when = tcp_time_stamp;
+
+                if (unlikely(tcp_transmit_skb(sk, skb_clone(skb, GFP_ATOMIC))))
+                        break;
+
+                /* Advance the send_head.  This one is sent out.
+                 * This call will increment packets_out.
+                 */
+                update_send_head(sk, tp, skb);
+
+                tcp_minshall_update(tp, mss_now, skb);
+                sent_pkts++;
+        }
+
+        if (likely(sent_pkts)) {
+                tcp_cwnd_validate(sk, tp);
+                return 0;
+        }
+        return !tp->packets_out && sk->sk_send_head;
+}
+
+/* Push out any pending frames which were held back due to
+ * TCP_CORK or attempt at coalescing tiny packets.
+ * The socket must be locked by the caller.
+ */
+void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp,
+                               unsigned int cur_mss, int nonagle)
+{
+        struct sk_buff *skb = sk->sk_send_head;
+
+        if (skb) {
+                if (tcp_write_xmit(sk, cur_mss, nonagle))
+                        tcp_check_probe_timer(sk, tp);
+        }
+}
+
+/* Send _single_ skb sitting at the send head. This function requires
+ * true push pending frames to setup probe timer etc.
+ */
+void tcp_push_one(struct sock *sk, unsigned int mss_now)
+{
+        struct tcp_sock *tp = tcp_sk(sk);
+        struct sk_buff *skb = sk->sk_send_head;
+        unsigned int tso_segs, cwnd_quota;
+
+        BUG_ON(!skb || skb->len < mss_now);
+
+        tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
+        cwnd_quota = tcp_snd_test(sk, skb, mss_now, TCP_NAGLE_PUSH);
+
+        if (likely(cwnd_quota)) {
+                unsigned int limit;
+
+                BUG_ON(!tso_segs);
+
+                limit = mss_now;
+                if (tso_segs > 1) {
+                        limit = tcp_window_allows(tp, skb,
+                                                  mss_now, cwnd_quota);
+
+                        if (skb->len < limit) {
+                                unsigned int trim = skb->len % mss_now;
+
+                                if (trim)
+                                        limit = skb->len - trim;
+                        }
                 }
 
-                return !tp->packets_out && sk->sk_send_head;
+                if (skb->len > limit &&
+                    unlikely(tso_fragment(sk, skb, limit, mss_now)))
+                        return;
+
+                /* Send it out now. */
+                TCP_SKB_CB(skb)->when = tcp_time_stamp;
+
+                if (likely(!tcp_transmit_skb(sk, skb_clone(skb, sk->sk_allocation)))) {
+                        update_send_head(sk, tp, skb);
+                        tcp_cwnd_validate(sk, tp);
+                        return;
+                }
         }
-        return 0;
 }
 
 /* This function returns the amount that we can raise the
@@ -1044,7 +1350,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
                 if (sk->sk_route_caps & NETIF_F_TSO) {
                         sk->sk_route_caps &= ~NETIF_F_TSO;
                         sock_set_flag(sk, SOCK_NO_LARGESEND);
-                        tp->mss_cache = tp->mss_cache_std;
                 }
 
                 if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
@@ -1062,15 +1367,21 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 
         if (skb->len > cur_mss) {
                 int old_factor = tcp_skb_pcount(skb);
-                int new_factor;
+                int diff;
 
-                if (tcp_fragment(sk, skb, cur_mss))
+                if (tcp_fragment(sk, skb, cur_mss, cur_mss))
                         return -ENOMEM; /* We'll try again later. */
 
                 /* New SKB created, account for it. */
-                new_factor = tcp_skb_pcount(skb);
-                tp->packets_out -= old_factor - new_factor;
-                tp->packets_out += tcp_skb_pcount(skb->next);
+                diff = old_factor - tcp_skb_pcount(skb) -
+                       tcp_skb_pcount(skb->next);
+                tp->packets_out -= diff;
+
+                if (diff > 0) {
+                        tp->fackets_out -= diff;
+                        if ((int)tp->fackets_out < 0)
+                                tp->fackets_out = 0;
+                }
         }
 
         /* Collapse two adjacent packets if worthwhile and we can. */
@@ -1106,7 +1417,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
          * is still in somebody's hands, else make a clone.
          */
         TCP_SKB_CB(skb)->when = tcp_time_stamp;
-        tcp_tso_set_push(skb);
 
         err = tcp_transmit_skb(sk, (skb_cloned(skb) ?
                                     pskb_copy(skb, GFP_ATOMIC):
@@ -1290,7 +1600,7 @@ void tcp_send_fin(struct sock *sk)
  * was unread data in the receive queue.  This behavior is recommended
  * by draft-ietf-tcpimpl-prob-03.txt section 3.10.  -DaveM
  */
-void tcp_send_active_reset(struct sock *sk, int priority)
+void tcp_send_active_reset(struct sock *sk, unsigned int __nocast priority)
 {
         struct tcp_sock *tp = tcp_sk(sk);
         struct sk_buff *skb;
@@ -1449,7 +1759,6 @@ static inline void tcp_connect_init(struct sock *sk)
                 tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
         tp->advmss = dst_metric(dst, RTAX_ADVMSS);
         tcp_initialize_rcv_mss(sk);
-        tcp_ca_init(tp);
 
         tcp_select_initial_window(tcp_full_space(sk),
                                   tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
@@ -1503,7 +1812,6 @@ int tcp_connect(struct sock *sk)
         TCP_SKB_CB(buff)->end_seq = tp->write_seq;
         tp->snd_nxt = tp->write_seq;
         tp->pushed_seq = tp->write_seq;
-        tcp_ca_init(tp);
 
         /* Send it off. */
         TCP_SKB_CB(buff)->when = tcp_time_stamp;
@@ -1670,21 +1978,19 @@ int tcp_write_wakeup(struct sock *sk)
                             skb->len > mss) {
                                 seg_size = min(seg_size, mss);
                                 TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
-                                if (tcp_fragment(sk, skb, seg_size))
+                                if (tcp_fragment(sk, skb, seg_size, mss))
                                         return -1;
                                 /* SWS override triggered forced fragmentation.
                                  * Disable TSO, the connection is too sick. */
                                 if (sk->sk_route_caps & NETIF_F_TSO) {
                                         sock_set_flag(sk, SOCK_NO_LARGESEND);
                                         sk->sk_route_caps &= ~NETIF_F_TSO;
-                                        tp->mss_cache = tp->mss_cache_std;
                                 }
                         } else if (!tcp_skb_pcount(skb))
-                                tcp_set_skb_tso_segs(sk, skb);
+                                tcp_set_skb_tso_segs(sk, skb, mss);
 
                         TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
                         TCP_SKB_CB(skb)->when = tcp_time_stamp;
-                        tcp_tso_set_push(skb);
                         err = tcp_transmit_skb(sk, skb_clone(skb, GFP_ATOMIC));
                         if (!err) {
                                 update_send_head(sk, tp, skb);