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 <jasowang@redhat.com>
Link: https://patch.msgid.link/20250701010352.74515-2-jasowang@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 777eb6193985d1cb964fe2e6cc4eb253b0cb4ad1..9dbd88eb9ff45c66caf62eba393d0d6aef6a42b0 100644 (file)
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -690,13 +690,13 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
        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);
@@ -715,15 +715,11 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
                }
        }
 
-       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;