ipv6: 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. 128 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>

net/ipv6/ip6_output.c

@@ -1464,6 +1464,7 @@ static int __ip6_append_data(struct sock *sk,
 	int copy;
 	int err;
 	int offset = 0;
+	bool zc = false;
 	u32 tskey = 0;
 	struct rt6_info *rt = (struct rt6_info *)cork->dst;
 	struct ipv6_txoptions *opt = v6_cork->opt;
@@ -1549,6 +1550,7 @@ static int __ip6_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);
@@ -1630,9 +1632,12 @@ static int __ip6_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;