Merge remote-tracking branch 'ipsec/master'

[karo-tx-linux.git] / net / ipv4 / tcp_output.c

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7c83cb8bf1378022ba3a68c56403ef40801cd3ae..d46f2143305c2632e7703f2677310dd177d67208 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -637,6 +637,8 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
        unsigned int size = 0;
        unsigned int eff_sacks;
 
+       opts->options = 0;
+
 #ifdef CONFIG_TCP_MD5SIG
        *md5 = tp->af_specific->md5_lookup(sk, sk);
        if (unlikely(*md5)) {
@@ -895,8 +897,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
        skb_orphan(skb);
        skb->sk = sk;
-       skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
-                         tcp_wfree : sock_wfree;
+       skb->destructor = tcp_wfree;
        atomic_add(skb->truesize, &sk->sk_wmem_alloc);
 
        /* Build TCP header and checksum it. */
@@ -985,8 +986,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
                                 unsigned int mss_now)
 {
-       if (skb->len <= mss_now || !sk_can_gso(sk) ||
-           skb->ip_summed == CHECKSUM_NONE) {
+       /* Make sure we own this skb before messing gso_size/gso_segs */
+       WARN_ON_ONCE(skb_cloned(skb));
+
+       if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) {
                /* Avoid the costly divide in the normal
                 * non-TSO case.
                 */
@@ -1066,9 +1069,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
        if (nsize < 0)
                nsize = 0;
 
-       if (skb_cloned(skb) &&
-           skb_is_nonlinear(skb) &&
-           pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+       if (skb_unclone(skb, GFP_ATOMIC))
                return -ENOMEM;
 
        /* Get a new skb... force flag on. */
@@ -1840,7 +1841,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
        while ((skb = tcp_send_head(sk))) {
                unsigned int limit;
 
-
                tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
                BUG_ON(!tso_segs);
 
@@ -1869,13 +1869,20 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
                                break;
                }
 
-               /* TSQ : sk_wmem_alloc accounts skb truesize,
-                * including skb overhead. But thats OK.
+               /* TCP Small Queues :
+                * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+                * This allows for :
+                *  - better RTT estimation and ACK scheduling
+                *  - faster recovery
+                *  - high rates
                 */
-               if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+               limit = max(skb->truesize, sk->sk_pacing_rate >> 10);
+
+               if (atomic_read(&sk->sk_wmem_alloc) > limit) {
                        set_bit(TSQ_THROTTLED, &tp->tsq_flags);
                        break;
                }
+
                limit = mss_now;
                if (tso_segs > 1 && !tcp_urg_mode(tp))
                        limit = tcp_mss_split_point(sk, skb, mss_now,
@@ -2337,6 +2344,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
                int oldpcount = tcp_skb_pcount(skb);
 
                if (unlikely(oldpcount > 1)) {
+                       if (skb_unclone(skb, GFP_ATOMIC))
+                               return -ENOMEM;
                        tcp_init_tso_segs(sk, skb, cur_mss);
                        tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
                }