vhost-net: reduce one userspace copy when building XDP buff

We used to do twice copy_from_iter() to copy virtio-net and packet
separately. This introduce overheads for userspace access hardening as
well as SMAP (for x86 it's stac/clac). So this patch tries to use one
copy_from_iter() to copy them once and move the virtio-net header
afterwards to reduce overheads.

Testpmd + vhost_net shows 10% improvement from 5.45Mpps to 6.0Mpps.

Signed-off-by: Jason Wang <[e-mail]>
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

drivers/vhost/net.c

···
 	if (unlikely(!buf))
 		return -ENOMEM;
 
-	copied = copy_from_iter(buf, sock_hlen, from);
-	if (copied != sock_hlen) {
+	copied = copy_from_iter(buf + pad - sock_hlen, len, from);
+	if (copied != len) {
 		ret = -EFAULT;
 		goto err;
 	}
 
-	gso = buf;
+	gso = buf + pad - sock_hlen;
 
 	if (!sock_hlen)
 		memset(buf, 0, pad);
···
 		}
 	}
 
-	len -= sock_hlen;
-	copied = copy_from_iter(buf + pad, len, from);
-	if (copied != len) {
-		ret = -EFAULT;
-		goto err;
-	}
+	/* pad contains sock_hlen */
+	memcpy(buf, buf + pad - sock_hlen, sock_hlen);
 
 	xdp_init_buff(xdp, buflen, NULL);
-	xdp_prepare_buff(xdp, buf, pad, len, true);
+	xdp_prepare_buff(xdp, buf, pad, len - sock_hlen, true);
 
 	++nvq->batched_xdp;