[TCP]: Simplify SKB data portion allocation with NETIF_F_SG.

The ideal and most optimal layout for an SKB when doing
scatter-gather is to put all the headers at skb->data, and
all the user data in the page array.

This makes SKB splitting and combining extremely simple,
especially before a packet goes onto the wire the first
time.

So, when sk_stream_alloc_pskb() is given a zero size, make
sure there is no skb_tailroom().  This is achieved by applying
SKB_DATA_ALIGN() to the header length used here.

Next, make select_size() in TCP output segmentation use a
length of zero when NETIF_F_SG is true on the outgoing
interface.

Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/sock.h b/include/net/sock.h
index e593af5b1ecce5db772ae22a17521be6833dd699..7b76f891ae2d4b9cdba1954dd02823c4eb3353a0 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1134,13 +1134,16 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk)
 static inline struct sk_buff *sk_stream_alloc_pskb(struct sock *sk,
                                                   int size, int mem, int gfp)
 {
-       struct sk_buff *skb = alloc_skb(size + sk->sk_prot->max_header, gfp);
+       struct sk_buff *skb;
+       int hdr_len;
 
+       hdr_len = SKB_DATA_ALIGN(sk->sk_prot->max_header);
+       skb = alloc_skb(size + hdr_len, gfp);
        if (skb) {
                skb->truesize += mem;
                if (sk->sk_forward_alloc >= (int)skb->truesize ||
                    sk_stream_mem_schedule(sk, skb->truesize, 0)) {
-                       skb_reserve(skb, sk->sk_prot->max_header);
+                       skb_reserve(skb, hdr_len);
                        return skb;
                }
                __kfree_skb(skb);

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 882436da9a3a74da59e22def22723fb208928a6b..be354155b2f93331ac0071bfcb1af879fd2d46ff 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -756,13 +756,9 @@ static inline int select_size(struct sock *sk, struct tcp_sock *tp)
 {
        int tmp = tp->mss_cache_std;
 
-       if (sk->sk_route_caps & NETIF_F_SG) {
-               int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);
+       if (sk->sk_route_caps & NETIF_F_SG)
+               tmp = 0;
 
-               if (tmp >= pgbreak &&
-                   tmp <= pgbreak + (MAX_SKB_FRAGS - 1) * PAGE_SIZE)
-                       tmp = pgbreak;
-       }
        return tmp;
 }
 
@@ -872,11 +868,6 @@ new_segment:
                                        tcp_mark_push(tp, skb);
                                        goto new_segment;
                                } else if (page) {
-                                       /* If page is cached, align
-                                        * offset to L1 cache boundary
-                                        */
-                                       off = (off + L1_CACHE_BYTES - 1) &
-                                             ~(L1_CACHE_BYTES - 1);
                                        if (off == PAGE_SIZE) {
                                                put_page(page);
                                                TCP_PAGE(sk) = page = NULL;