[RFC PATCH net-next 25/33] mptcp: use sk_page_frag() in sendmsg

[Mat Martineau]

From: Paolo Abeni <pab...@redhat.com>

This clean-up a bit the send path, and allows better performances.

Signed-off-by: Paolo Abeni <pab...@redhat.com>
---
 net/mptcp/protocol.c | 41 ++++++++++++++++++++---------------------
 1 file changed, 20 insertions(+), 21 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 0db4099d9c13..98257a70ac2b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -52,10 +52,11 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr 
*msg, size_t len)
        struct mptcp_sock *msk = mptcp_sk(sk);
        int mss_now, size_goal, poffset, ret;
        struct mptcp_ext *mpext = NULL;
-       struct page *page = NULL;
+       struct page_frag *pfrag;
        struct sk_buff *skb;
        struct sock *ssk;
        size_t psize;
+       long timeo;
 
        pr_debug("msk=%p", msk);
        if (msk->subflow) {
@@ -80,33 +81,33 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr 
*msg, size_t len)
                goto put_out;
        }
 
-       /* Initial experiment: new page per send.  Real code will
-        * maintain list of active pages and DSS mappings, append to the
-        * end and honor zerocopy
+       lock_sock(sk);
+       lock_sock(ssk);
+       timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+
+       /* use the mptcp page cache so that we can easily move the data
+        * from one substream to another, but do per subflow memory accounting
         */
-       page = alloc_page(GFP_KERNEL);
-       if (!page) {
-               ret = -ENOMEM;
-               goto put_out;
+       pfrag = sk_page_frag(sk);
+       while (!sk_page_frag_refill(ssk, pfrag)) {
+               ret = sk_stream_wait_memory(ssk, &timeo);
+               if (ret)
+                       goto release_out;
        }
 
        /* Copy to page */
-       poffset = 0;
+       poffset = pfrag->offset;
        pr_debug("left=%zu", msg_data_left(msg));
-       psize = copy_page_from_iter(page, poffset,
+       psize = copy_page_from_iter(pfrag->page, poffset,
                                    min_t(size_t, msg_data_left(msg),
-                                         PAGE_SIZE),
+                                         pfrag->size - poffset),
                                    &msg->msg_iter);
        pr_debug("left=%zu", msg_data_left(msg));
-
        if (!psize) {
                ret = -EINVAL;
-               goto put_out;
+               goto release_out;
        }
 
-       lock_sock(sk);
-       lock_sock(ssk);
-
        /* Mark the end of the previous write so the beginning of the
         * next write (with its own mptcp skb extension data) is not
         * collapsed.
@@ -116,8 +117,8 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr 
*msg, size_t len)
                TCP_SKB_CB(skb)->eor = 1;
 
        mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags);
-
-       ret = do_tcp_sendpages(ssk, page, poffset, min_t(int, size_goal, psize),
+       psize = min_t(int, size_goal, psize);
+       ret = do_tcp_sendpages(ssk, pfrag->page, poffset, psize,
                               msg->msg_flags | MSG_SENDPAGE_NOTLAST);
        if (ret <= 0)
                goto release_out;
@@ -143,6 +144,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr 
*msg, size_t len)
                         mpext->checksum, mpext->dsn64);
        } /* TODO: else fallback */
 
+       pfrag->offset += ret;
        msk->write_seq += ret;
        subflow_ctx(ssk)->rel_write_seq += ret;
 
@@ -153,9 +155,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr 
*msg, size_t len)
        release_sock(sk);
 
 put_out:
-       if (page)
-               put_page(page);
-
        sock_put(ssk);
        return ret;
 }
-- 
2.22.0