tcp: preserve ACK clocking in TSO

[pandora-kernel.git] / net / ipv4 / tcp_output.c

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 63170e2..5c1807c 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1093,6 +1093,13 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 {
        int i, k, eat;
 
+       eat = min_t(int, len, skb_headlen(skb));
+       if (eat) {
+               __skb_pull(skb, eat);
+               len -= eat;
+               if (!len)
+                       return;
+       }
        eat = len;
        k = 0;
        for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
@@ -1124,11 +1131,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
        if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
                return -ENOMEM;
 
-       /* If len == headlen, we avoid __skb_pull to preserve alignment. */
-       if (unlikely(len < skb_headlen(skb)))
-               __skb_pull(skb, len);
-       else
-               __pskb_trim_head(skb, len - skb_headlen(skb));
+       __pskb_trim_head(skb, len);
 
        TCP_SKB_CB(skb)->seq += len;
        skb->ip_summed = CHECKSUM_PARTIAL;
@@ -1138,11 +1141,9 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
        sk_mem_uncharge(sk, len);
        sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 
-       /* Any change of skb->len requires recalculation of tso
-        * factor and mss.
-        */
+       /* Any change of skb->len requires recalculation of tso factor. */
        if (tcp_skb_pcount(skb) > 1)
-               tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk));
+               tcp_set_skb_tso_segs(sk, skb, tcp_skb_mss(skb));
 
        return 0;
 }
@@ -1316,21 +1317,21 @@ static void tcp_cwnd_validate(struct sock *sk)
  * when we would be allowed to send the split-due-to-Nagle skb fully.
  */
 static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb,
-                                       unsigned int mss_now, unsigned int cwnd)
+                                       unsigned int mss_now, unsigned int max_segs)
 {
        const struct tcp_sock *tp = tcp_sk(sk);
-       u32 needed, window, cwnd_len;
+       u32 needed, window, max_len;
 
        window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
-       cwnd_len = mss_now * cwnd;
+       max_len = mss_now * max_segs;
 
-       if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk)))
-               return cwnd_len;
+       if (likely(max_len <= window && skb != tcp_write_queue_tail(sk)))
+               return max_len;
 
        needed = min(skb->len, window);
 
-       if (cwnd_len <= needed)
-               return cwnd_len;
+       if (max_len <= needed)
+               return max_len;
 
        return needed - needed % mss_now;
 }
@@ -1558,7 +1559,8 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
        limit = min(send_win, cong_win);
 
        /* If a full-sized TSO skb can be sent, do it. */
-       if (limit >= sk->sk_gso_max_size)
+       if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
+                          sk->sk_gso_max_segs * tp->mss_cache))
                goto send_now;
 
        /* Middle in queue won't get any more data, full sendable already? */
@@ -1585,8 +1587,11 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
                        goto send_now;
        }
 
-       /* Ok, it looks like it is advisable to defer.  */
-       tp->tso_deferred = 1 | (jiffies << 1);
+       /* Ok, it looks like it is advisable to defer.
+        * Do not rearm the timer if already set to not break TCP ACK clocking.
+        */
+       if (!tp->tso_deferred)
+               tp->tso_deferred = 1 | (jiffies << 1);
 
        return 1;
 
@@ -1784,7 +1789,9 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
                limit = mss_now;
                if (tso_segs > 1 && !tcp_urg_mode(tp))
                        limit = tcp_mss_split_point(sk, skb, mss_now,
-                                                   cwnd_quota);
+                                                   min_t(unsigned int,
+                                                         cwnd_quota,
+                                                         sk->sk_gso_max_segs));
 
                if (skb->len > limit &&
                    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
@@ -2059,7 +2066,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
                /* Punt if not enough space exists in the first SKB for
                 * the data in the second
                 */
-               if (skb->len > skb_tailroom(to))
+               if (skb->len > skb_availroom(to))
                        break;
 
                if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp)))