mptcp: let MPTCP create max size skbs

Currently the xmit path of the MPTCP protocol creates smaller-
than-max-size skbs, which is suboptimal for the performances.

There are a few things to improve:
- when coalescing to an existing skb, must clear the PUSH flag
- tcp_build_frag() expect the available space as an argument.
  When coalescing is enable MPTCP already subtracted the
  to-be-coalesced skb len. We must increment said argument
  accordingly.

Before:
./use_mptcp.sh netperf -H 127.0.0.1 -t TCP_STREAM
[...]
131072  16384  16384    30.00    24414.86

After:
./use_mptcp.sh netperf -H 127.0.0.1 -t TCP_STREAM
[...]
131072  16384  16384    30.05    28357.69

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index cb8b7ad..b812aaa 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1256,6 +1256,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
        struct mptcp_ext *mpext = NULL;
        struct sk_buff *skb, *tail;
        bool can_collapse = false;
+       int size_bias = 0;
        int avail_size;
        size_t ret = 0;
 
@@ -1277,10 +1278,12 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
                mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
                can_collapse = (info->size_goal - skb->len > 0) &&
                         mptcp_skb_can_collapse_to(data_seq, skb, mpext);
-               if (!can_collapse)
+               if (!can_collapse) {
                        TCP_SKB_CB(skb)->eor = 1;
-               else
+               } else {
+                       size_bias = skb->len;
                        avail_size = info->size_goal - skb->len;
+               }
        }
 
        /* Zero window and all data acked? Probe. */
@@ -1300,8 +1303,8 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
                return 0;
 
        ret = info->limit - info->sent;
-       tail = tcp_build_frag(ssk, avail_size, info->flags, dfrag->page,
-                             dfrag->offset + info->sent, &ret);
+       tail = tcp_build_frag(ssk, avail_size + size_bias, info->flags,
+                             dfrag->page, dfrag->offset + info->sent, &ret);
        if (!tail) {
                tcp_remove_empty_skb(sk, tcp_write_queue_tail(ssk));
                return -ENOMEM;
@@ -1310,8 +1313,9 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
        /* if the tail skb is still the cached one, collapsing really happened.
         */
        if (skb == tail) {
-               WARN_ON_ONCE(!can_collapse);
+               TCP_SKB_CB(tail)->tcp_flags &= ~TCPHDR_PSH;
                mpext->data_len += ret;
+               WARN_ON_ONCE(!can_collapse);
                WARN_ON_ONCE(zero_window_probe);
                goto out;
        }