ipv4: avoid partial copy for zc

Even when zerocopy transmission is requested and possible,
__ip_append_data() will still copy a small chunk of data just because it
allocated some extra linear space (e.g. 148 bytes). It wastes CPU cycles
on copy and iter manipulations and also misalignes potentially aligned
data. Avoid such copies. And as a bonus we can allocate smaller skb.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 00b4bf26fd932b5043b23ca3bbc32823dd5c74c7..581d1e2332603e670e942e014d559d4921e38f61 100644 (file)
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -969,7 +969,6 @@ static int __ip_append_data(struct sock *sk,
        struct inet_sock *inet = inet_sk(sk);
        struct ubuf_info *uarg = NULL;
        struct sk_buff *skb;
-
        struct ip_options *opt = cork->opt;
        int hh_len;
        int exthdrlen;
@@ -977,6 +976,7 @@ static int __ip_append_data(struct sock *sk,
        int copy;
        int err;
        int offset = 0;
+       bool zc = false;
        unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
        int csummode = CHECKSUM_NONE;
        struct rtable *rt = (struct rtable *)cork->dst;
@@ -1025,6 +1025,7 @@ static int __ip_append_data(struct sock *sk,
                if (rt->dst.dev->features & NETIF_F_SG &&
                    csummode == CHECKSUM_PARTIAL) {
                        paged = true;
+                       zc = true;
                } else {
                        uarg->zerocopy = 0;
                        skb_zcopy_set(skb, uarg, &extra_uref);
@@ -1091,9 +1092,12 @@ alloc_new_skb:
                                 (fraglen + alloc_extra < SKB_MAX_ALLOC ||
                                  !(rt->dst.dev->features & NETIF_F_SG)))
                                alloclen = fraglen;
-                       else {
+                       else if (!zc) {
                                alloclen = min_t(int, fraglen, MAX_HEADER);
                                pagedlen = fraglen - alloclen;
+                       } else {
+                               alloclen = fragheaderlen + transhdrlen;
+                               pagedlen = datalen - transhdrlen;
                        }
 
                        alloclen += alloc_extra;