diff mbox series

[net-next,v4,01/27] ipv4: avoid partial copy for zc

Message ID 0eb1cb5746e9ac938a7ba7848b33ccf680d30030.1657194434.git.asml.silence@gmail.com (mailing list archive)
State New
Headers show
Series io_uring zerocopy send | expand

Commit Message

Pavel Begunkov July 7, 2022, 11:49 a.m. UTC
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 coies. And as a bonus we can allocate smaller skb.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 net/ipv4/ip_output.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 00b4bf26fd93..581d1e233260 100644
--- 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 @@  static int __ip_append_data(struct sock *sk,
 				 (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;