Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

[cascardo/linux.git] / net / ipv4 / tcp_output.c

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 65caf8b..4fcc9a7 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -948,7 +948,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
        skb_orphan(skb);
        skb->sk = sk;
-       skb->destructor = tcp_wfree;
+       skb->destructor = skb_is_tcp_pure_ack(skb) ? sock_wfree : tcp_wfree;
        skb_set_hash_from_sk(skb, sk);
        atomic_add(skb->truesize, &sk->sk_wmem_alloc);
 
@@ -2939,6 +2939,25 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 }
 EXPORT_SYMBOL(tcp_make_synack);
 
+static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst)
+{
+       struct inet_connection_sock *icsk = inet_csk(sk);
+       const struct tcp_congestion_ops *ca;
+       u32 ca_key = dst_metric(dst, RTAX_CC_ALGO);
+
+       if (ca_key == TCP_CA_UNSPEC)
+               return;
+
+       rcu_read_lock();
+       ca = tcp_ca_find_key(ca_key);
+       if (likely(ca && try_module_get(ca->owner))) {
+               module_put(icsk->icsk_ca_ops->owner);
+               icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
+               icsk->icsk_ca_ops = ca;
+       }
+       rcu_read_unlock();
+}
+
 /* Do all connect socket setups that can be done AF independent. */
 static void tcp_connect_init(struct sock *sk)
 {
@@ -2964,6 +2983,8 @@ static void tcp_connect_init(struct sock *sk)
        tcp_mtup_init(sk);
        tcp_sync_mss(sk, dst_mtu(dst));
 
+       tcp_ca_dst_init(sk, dst);
+
        if (!tp->window_clamp)
                tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
        tp->advmss = dst_metric_advmss(dst);
@@ -3034,7 +3055,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
        struct tcp_sock *tp = tcp_sk(sk);
        struct tcp_fastopen_request *fo = tp->fastopen_req;
-       int syn_loss = 0, space, err = 0;
+       int syn_loss = 0, space, err = 0, copied;
        unsigned long last_syn_loss = 0;
        struct sk_buff *syn_data;
 
@@ -3072,11 +3093,16 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
                goto fallback;
        syn_data->ip_summed = CHECKSUM_PARTIAL;
        memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
-       if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space),
-                                        fo->data->msg_iter.iov, 0, space))) {
+       copied = copy_from_iter(skb_put(syn_data, space), space,
+                               &fo->data->msg_iter);
+       if (unlikely(!copied)) {
                kfree_skb(syn_data);
                goto fallback;
        }
+       if (copied != space) {
+               skb_trim(syn_data, copied);
+               space = copied;
+       }
 
        /* No more data pending in inet_wait_for_connect() */
        if (space == fo->size)
@@ -3244,6 +3270,14 @@ void tcp_send_ack(struct sock *sk)
        skb_reserve(buff, MAX_TCP_HEADER);
        tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK);
 
+       /* We do not want pure acks influencing TCP Small Queues or fq/pacing
+        * too much.
+        * SKB_TRUESIZE(max(1 .. 66, MAX_TCP_HEADER)) is unfortunately ~784
+        * We also avoid tcp_wfree() overhead (cache line miss accessing
+        * tp->tsq_flags) by using regular sock_wfree()
+        */
+       skb_set_tcp_pure_ack(buff);
+
        /* Send it off, this clears delayed acks for us. */
        skb_mstamp_get(&buff->skb_mstamp);
        tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));