RE: [PATCH net-next v2 2/3] vhost_net: Call peek_len when using xdp
> -Original Message-
> From: Paolo Abeni [mailto:pab...@redhat.com]
> Sent: Thursday, February 29, 2024 6:49 PM
> To: wangyunjian ; m...@redhat.com;
> willemdebruijn.ker...@gmail.com; jasow...@redhat.com; k...@kernel.org;
> bj...@kernel.org; magnus.karls...@intel.com; maciej.fijalkow...@intel.com;
> jonathan.le...@gmail.com; da...@davemloft.net
> Cc: b...@vger.kernel.org; net...@vger.kernel.org;
> linux-kernel@vger.kernel.org; k...@vger.kernel.org;
> virtualizat...@lists.linux.dev; xudingke ; liwei (DT)
>
> Subject: Re: [PATCH net-next v2 2/3] vhost_net: Call peek_len when using xdp
>
> On Wed, 2024-02-28 at 19:05 +0800, Yunjian Wang wrote:
> > If TUN supports AF_XDP TX zero-copy, the XDP program will enqueue
> > packets to the XDP ring and wake up the vhost worker. This requires
> > the vhost worker to call peek_len(), which can be used to consume XDP
> > descriptors.
> >
> > Signed-off-by: Yunjian Wang
> > ---
> > drivers/vhost/net.c | 17 -
> > 1 file changed, 12 insertions(+), 5 deletions(-)
> >
> > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index
> > f2ed7167c848..077e74421558 100644
> > --- a/drivers/vhost/net.c
> > +++ b/drivers/vhost/net.c
> > @@ -207,6 +207,11 @@ static int vhost_net_buf_peek_len(void *ptr)
> > return __skb_array_len_with_tag(ptr); }
> >
> > +static bool vhost_sock_xdp(struct socket *sock) {
> > + return sock_flag(sock->sk, SOCK_XDP); }
> > +
> > static int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq) {
> > struct vhost_net_buf *rxq = >rxq; @@ -214,6 +219,13 @@ static
> > int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq)
> > if (!vhost_net_buf_is_empty(rxq))
> > goto out;
> >
> > + if (ptr_ring_empty(nvq->rx_ring)) {
> > + struct socket *sock = vhost_vq_get_backend(>vq);
> > + /* Call peek_len to consume XSK descriptors, when using xdp */
> > + if (vhost_sock_xdp(sock) && sock->ops->peek_len)
> > + sock->ops->peek_len(sock);
>
> This really looks like a socket API misuse. Why can't you use ptr-ring
> primitives
> to consume XSK descriptors? peek_len could be constified some day, this code
> will prevent such (good) thing.
Thank you for your suggestion. I will consider that with Patch 3/3.
>
> Cheers,
>
> Paolo
Re: [PATCH net-next v2 2/3] vhost_net: Call peek_len when using xdp
On Wed, 2024-02-28 at 19:05 +0800, Yunjian Wang wrote:
> If TUN supports AF_XDP TX zero-copy, the XDP program will enqueue
> packets to the XDP ring and wake up the vhost worker. This requires
> the vhost worker to call peek_len(), which can be used to consume
> XDP descriptors.
>
> Signed-off-by: Yunjian Wang
> ---
> drivers/vhost/net.c | 17 -
> 1 file changed, 12 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index f2ed7167c848..077e74421558 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -207,6 +207,11 @@ static int vhost_net_buf_peek_len(void *ptr)
> return __skb_array_len_with_tag(ptr);
> }
>
> +static bool vhost_sock_xdp(struct socket *sock)
> +{
> + return sock_flag(sock->sk, SOCK_XDP);
> +}
> +
> static int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq)
> {
> struct vhost_net_buf *rxq = >rxq;
> @@ -214,6 +219,13 @@ static int vhost_net_buf_peek(struct vhost_net_virtqueue
> *nvq)
> if (!vhost_net_buf_is_empty(rxq))
> goto out;
>
> + if (ptr_ring_empty(nvq->rx_ring)) {
> + struct socket *sock = vhost_vq_get_backend(>vq);
> + /* Call peek_len to consume XSK descriptors, when using xdp */
> + if (vhost_sock_xdp(sock) && sock->ops->peek_len)
> + sock->ops->peek_len(sock);
This really looks like a socket API misuse. Why can't you use ptr-ring
primitives to consume XSK descriptors? peek_len could be constified
some day, this code will prevent such (good) thing.
Cheers,
Paolo
[PATCH net-next v2 2/3] vhost_net: Call peek_len when using xdp
If TUN supports AF_XDP TX zero-copy, the XDP program will enqueue
packets to the XDP ring and wake up the vhost worker. This requires
the vhost worker to call peek_len(), which can be used to consume
XDP descriptors.
Signed-off-by: Yunjian Wang
---
drivers/vhost/net.c | 17 -
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f2ed7167c848..077e74421558 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -207,6 +207,11 @@ static int vhost_net_buf_peek_len(void *ptr)
return __skb_array_len_with_tag(ptr);
}
+static bool vhost_sock_xdp(struct socket *sock)
+{
+ return sock_flag(sock->sk, SOCK_XDP);
+}
+
static int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq)
{
struct vhost_net_buf *rxq = >rxq;
@@ -214,6 +219,13 @@ static int vhost_net_buf_peek(struct vhost_net_virtqueue
*nvq)
if (!vhost_net_buf_is_empty(rxq))
goto out;
+ if (ptr_ring_empty(nvq->rx_ring)) {
+ struct socket *sock = vhost_vq_get_backend(>vq);
+ /* Call peek_len to consume XSK descriptors, when using xdp */
+ if (vhost_sock_xdp(sock) && sock->ops->peek_len)
+ sock->ops->peek_len(sock);
+ }
+
if (!vhost_net_buf_produce(nvq))
return 0;
@@ -346,11 +358,6 @@ static bool vhost_sock_zcopy(struct socket *sock)
sock_flag(sock->sk, SOCK_ZEROCOPY);
}
-static bool vhost_sock_xdp(struct socket *sock)
-{
- return sock_flag(sock->sk, SOCK_XDP);
-}
-
/* In case of DMA done not in order in lower device driver for some reason.
* upend_idx is used to track end of used idx, done_idx is used to track head
* of used idx. Once lower device DMA done contiguously, we will signal KVM
--
2.41.0
