tcp: let tcp_send_syn_data() build headless packets

tcp_send_syn_data() is the last component in TCP transmit
path to put payload in skb->head.

Switch it to use page frags, so that we can remove dead
code later.

This allows to put more payload than previous implementation.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 49611af..f718ed2 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -333,6 +333,7 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
 int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
                        size_t size, int flags);
 int tcp_send_mss(struct sock *sk, int *size_goal, int flags);
+int tcp_wmem_schedule(struct sock *sk, int copy);
 void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle,
              int size_goal);
 void tcp_release_cb(struct sock *sk);

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 09f0322..da7f156 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -957,7 +957,7 @@ static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb)
 }
 
 
-static int tcp_wmem_schedule(struct sock *sk, int copy)
+int tcp_wmem_schedule(struct sock *sk, int copy)
 {
        int left;
 

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f8ce77c..d039663 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3802,8 +3802,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
        struct inet_connection_sock *icsk = inet_csk(sk);
        struct tcp_sock *tp = tcp_sk(sk);
        struct tcp_fastopen_request *fo = tp->fastopen_req;
-       int space, err = 0;
+       struct page_frag *pfrag = sk_page_frag(sk);
        struct sk_buff *syn_data;
+       int space, err = 0;
 
        tp->rx_opt.mss_clamp = tp->advmss;  /* If MSS is not cached */
        if (!tcp_fastopen_cookie_check(sk, &tp->rx_opt.mss_clamp, &fo->cookie))
@@ -3822,25 +3823,31 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 
        space = min_t(size_t, space, fo->size);
 
-       /* limit to order-0 allocations */
-       space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
-
-       syn_data = tcp_stream_alloc_skb(sk, space, sk->sk_allocation, false);
+       if (space &&
+           !skb_page_frag_refill(min_t(size_t, space, PAGE_SIZE),
+                                 pfrag, sk->sk_allocation))
+               goto fallback;
+       syn_data = tcp_stream_alloc_skb(sk, 0, sk->sk_allocation, false);
        if (!syn_data)
                goto fallback;
        memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
        if (space) {
-               int copied = copy_from_iter(skb_put(syn_data, space), space,
-                                           &fo->data->msg_iter);
-               if (unlikely(!copied)) {
+               space = min_t(size_t, space, pfrag->size - pfrag->offset);
+               space = tcp_wmem_schedule(sk, space);
+       }
+       if (space) {
+               space = copy_page_from_iter(pfrag->page, pfrag->offset,
+                                           space, &fo->data->msg_iter);
+               if (unlikely(!space)) {
                        tcp_skb_tsorted_anchor_cleanup(syn_data);
                        kfree_skb(syn_data);
                        goto fallback;
                }
-               if (copied != space) {
-                       skb_trim(syn_data, copied);
-                       space = copied;
-               }
+               skb_fill_page_desc(syn_data, 0, pfrag->page,
+                                  pfrag->offset, space);
+               page_ref_inc(pfrag->page);
+               pfrag->offset += space;
+               skb_len_add(syn_data, space);
                skb_zcopy_set(syn_data, fo->uarg, NULL);
        }
        /* No more data pending in inet_wait_for_connect() */