From: Simon Schippers <simon.schippers@tu-dortmund.de>
To: willemdebruijn.kernel@gmail.com, jasowang@redhat.com,
andrew+netdev@lunn.ch, davem@davemloft.net, edumazet@google.com,
kuba@kernel.org, pabeni@redhat.com, mst@redhat.com,
eperezma@redhat.com, leiyang@redhat.com,
stephen@networkplumber.org, jon@nutanix.com,
tim.gebauer@tu-dortmund.de, simon.schippers@tu-dortmund.de,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
kvm@vger.kernel.org, virtualization@lists.linux.dev
Subject: [PATCH net-next v7 7/9] vhost-net: vhost-net: replace rx_ring with tun/tap ring wrappers
Date: Wed, 7 Jan 2026 22:04:46 +0100 [thread overview]
Message-ID: <20260107210448.37851-8-simon.schippers@tu-dortmund.de> (raw)
In-Reply-To: <20260107210448.37851-1-simon.schippers@tu-dortmund.de>
Replace the direct use of ptr_ring in the vhost-net virtqueue with
tun/tap ring wrapper helpers. Instead of storing an rx_ring pointer,
the virtqueue now stores the interface type (IF_TUN, IF_TAP, or IF_NONE)
and dispatches to the corresponding tun/tap helpers for ring
produce, consume, and unconsume operations.
Routing ring operations through the tun/tap helpers enables netdev
queue wakeups, which are required for upcoming netdev queue flow
control support shared by tun/tap and vhost-net.
No functional change is intended beyond switching to the wrapper
helpers.
Co-developed-by: Tim Gebauer <tim.gebauer@tu-dortmund.de>
Signed-off-by: Tim Gebauer <tim.gebauer@tu-dortmund.de>
Co-developed by: Jon Kohler <jon@nutanix.com>
Signed-off-by: Jon Kohler <jon@nutanix.com>
Signed-off-by: Simon Schippers <simon.schippers@tu-dortmund.de>
---
drivers/vhost/net.c | 92 +++++++++++++++++++++++++++++----------------
1 file changed, 60 insertions(+), 32 deletions(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 7f886d3dba7d..215556f7cd40 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -90,6 +90,12 @@ enum {
VHOST_NET_VQ_MAX = 2,
};
+enum if_type {
+ IF_NONE = 0,
+ IF_TUN = 1,
+ IF_TAP = 2,
+};
+
struct vhost_net_ubuf_ref {
/* refcount follows semantics similar to kref:
* 0: object is released
@@ -127,10 +133,11 @@ struct vhost_net_virtqueue {
/* Reference counting for outstanding ubufs.
* Protected by vq mutex. Writers must also take device mutex. */
struct vhost_net_ubuf_ref *ubufs;
- struct ptr_ring *rx_ring;
struct vhost_net_buf rxq;
/* Batched XDP buffs */
struct xdp_buff *xdp;
+ /* Interface type */
+ enum if_type type;
};
struct vhost_net {
@@ -176,24 +183,50 @@ static void *vhost_net_buf_consume(struct vhost_net_buf *rxq)
return ret;
}
-static int vhost_net_buf_produce(struct vhost_net_virtqueue *nvq)
+static int vhost_net_buf_produce(struct vhost_net_virtqueue *nvq,
+ struct sock *sk)
{
+ struct file *file = sk->sk_socket->file;
struct vhost_net_buf *rxq = &nvq->rxq;
rxq->head = 0;
- rxq->tail = ptr_ring_consume_batched(nvq->rx_ring, rxq->queue,
- VHOST_NET_BATCH);
+ switch (nvq->type) {
+ case IF_TUN:
+ rxq->tail = tun_ring_consume_batched(file, rxq->queue,
+ VHOST_NET_BATCH);
+ break;
+ case IF_TAP:
+ rxq->tail = tap_ring_consume_batched(file, rxq->queue,
+ VHOST_NET_BATCH);
+ break;
+ case IF_NONE:
+ return 0;
+ }
return rxq->tail;
}
-static void vhost_net_buf_unproduce(struct vhost_net_virtqueue *nvq)
+static void vhost_net_buf_unproduce(struct vhost_net_virtqueue *nvq,
+ struct socket *sk)
{
struct vhost_net_buf *rxq = &nvq->rxq;
-
- if (nvq->rx_ring && !vhost_net_buf_is_empty(rxq)) {
- ptr_ring_unconsume(nvq->rx_ring, rxq->queue + rxq->head,
- vhost_net_buf_get_size(rxq),
- tun_ptr_free);
+ struct file *file;
+
+ if (sk && !vhost_net_buf_is_empty(rxq)) {
+ file = sk->file;
+ switch (nvq->type) {
+ case IF_TUN:
+ tun_ring_unconsume(file, rxq->queue + rxq->head,
+ vhost_net_buf_get_size(rxq),
+ tun_ptr_free);
+ break;
+ case IF_TAP:
+ tap_ring_unconsume(file, rxq->queue + rxq->head,
+ vhost_net_buf_get_size(rxq),
+ tun_ptr_free);
+ break;
+ case IF_NONE:
+ return;
+ }
rxq->head = rxq->tail = 0;
}
}
@@ -209,14 +242,15 @@ static int vhost_net_buf_peek_len(void *ptr)
return __skb_array_len_with_tag(ptr);
}
-static int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq)
+static int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq,
+ struct sock *sk)
{
struct vhost_net_buf *rxq = &nvq->rxq;
if (!vhost_net_buf_is_empty(rxq))
goto out;
- if (!vhost_net_buf_produce(nvq))
+ if (!vhost_net_buf_produce(nvq, sk))
return 0;
out:
@@ -996,8 +1030,8 @@ static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk)
int len = 0;
unsigned long flags;
- if (rvq->rx_ring)
- return vhost_net_buf_peek(rvq);
+ if (rvq->type)
+ return vhost_net_buf_peek(rvq, sk);
spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
head = skb_peek(&sk->sk_receive_queue);
@@ -1212,7 +1246,7 @@ static void handle_rx(struct vhost_net *net)
goto out;
}
busyloop_intr = false;
- if (nvq->rx_ring)
+ if (nvq->type)
msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
/* On overrun, truncate and discard */
if (unlikely(headcount > UIO_MAXIOV)) {
@@ -1368,7 +1402,6 @@ static int vhost_net_open(struct inode *inode, struct file *f)
n->vqs[i].batched_xdp = 0;
n->vqs[i].vhost_hlen = 0;
n->vqs[i].sock_hlen = 0;
- n->vqs[i].rx_ring = NULL;
vhost_net_buf_init(&n->vqs[i].rxq);
}
vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX,
@@ -1398,8 +1431,8 @@ static struct socket *vhost_net_stop_vq(struct vhost_net *n,
sock = vhost_vq_get_backend(vq);
vhost_net_disable_vq(n, vq);
vhost_vq_set_backend(vq, NULL);
- vhost_net_buf_unproduce(nvq);
- nvq->rx_ring = NULL;
+ vhost_net_buf_unproduce(nvq, sock);
+ nvq->type = IF_NONE;
mutex_unlock(&vq->mutex);
return sock;
}
@@ -1479,18 +1512,13 @@ static struct socket *get_raw_socket(int fd)
return ERR_PTR(r);
}
-static struct ptr_ring *get_tap_ptr_ring(struct file *file)
+static enum if_type get_if_type(struct file *file)
{
- struct ptr_ring *ring;
- ring = tun_get_tx_ring(file);
- if (!IS_ERR(ring))
- goto out;
- ring = tap_get_ptr_ring(file);
- if (!IS_ERR(ring))
- goto out;
- ring = NULL;
-out:
- return ring;
+ if (tap_is_tap_file(file))
+ return IF_TAP;
+ if (tun_is_tun_file(file))
+ return IF_TUN;
+ return IF_NONE;
}
static struct socket *get_tap_socket(int fd)
@@ -1572,7 +1600,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
vhost_net_disable_vq(n, vq);
vhost_vq_set_backend(vq, sock);
- vhost_net_buf_unproduce(nvq);
+ vhost_net_buf_unproduce(nvq, sock);
r = vhost_vq_init_access(vq);
if (r)
goto err_used;
@@ -1581,9 +1609,9 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
goto err_used;
if (index == VHOST_NET_VQ_RX) {
if (sock)
- nvq->rx_ring = get_tap_ptr_ring(sock->file);
+ nvq->type = get_if_type(sock->file);
else
- nvq->rx_ring = NULL;
+ nvq->type = IF_NONE;
}
oldubufs = nvq->ubufs;
--
2.43.0
next prev parent reply other threads:[~2026-01-07 21:06 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-07 21:04 [PATCH net-next v7 0/9] tun/tap & vhost-net: apply qdisc backpressure on full ptr_ring to reduce TX drops Simon Schippers
2026-01-07 21:04 ` [PATCH net-next v7 1/9] ptr_ring: move free-space check into separate helper Simon Schippers
2026-01-07 21:04 ` [PATCH net-next v7 2/9] ptr_ring: add helper to detect newly freed space on consume Simon Schippers
2026-01-08 3:23 ` Jason Wang
2026-01-08 7:20 ` Simon Schippers
2026-01-09 6:01 ` Jason Wang
2026-01-09 6:47 ` Michael S. Tsirkin
2026-01-09 7:22 ` Michael S. Tsirkin
2026-01-09 7:35 ` Simon Schippers
2026-01-09 8:31 ` Michael S. Tsirkin
2026-01-09 9:06 ` Simon Schippers
2026-01-12 16:29 ` Simon Schippers
2026-01-07 21:04 ` [PATCH net-next v7 3/9] tun/tap: add ptr_ring consume helper with netdev queue wakeup Simon Schippers
2026-01-08 3:38 ` Jason Wang
2026-01-08 7:40 ` Simon Schippers
2026-01-09 6:02 ` Jason Wang
2026-01-09 9:31 ` Simon Schippers
2026-01-21 9:32 ` Simon Schippers
2026-01-22 5:35 ` Jason Wang
2026-01-23 3:05 ` Jason Wang
2026-01-23 9:54 ` Simon Schippers
2026-01-27 16:47 ` Simon Schippers
2026-01-28 7:03 ` Jason Wang
2026-01-28 7:53 ` Simon Schippers
2026-01-29 1:14 ` Jason Wang
2026-01-29 9:24 ` Simon Schippers
2026-01-30 1:51 ` Jason Wang
2026-02-01 20:19 ` Simon Schippers
2026-02-03 3:48 ` Jason Wang
2026-02-04 15:43 ` Simon Schippers
2026-02-05 3:59 ` Jason Wang
2026-02-05 22:28 ` Simon Schippers
2026-02-06 3:21 ` Jason Wang
2026-02-08 18:18 ` Simon Schippers
2026-02-12 0:12 ` Simon Schippers
2026-02-12 7:06 ` Michael S. Tsirkin
2026-02-12 8:03 ` Simon Schippers
2026-02-12 8:14 ` Jason Wang
2026-02-14 17:13 ` Simon Schippers
2026-02-14 18:18 ` Michael S. Tsirkin
2026-02-14 19:51 ` Simon Schippers
2026-02-14 23:49 ` Michael S. Tsirkin
2026-02-15 10:38 ` Michael S. Tsirkin
2026-02-16 13:27 ` Simon Schippers
2026-01-07 21:04 ` [PATCH net-next v7 4/9] tun/tap: add batched ptr_ring consume functions " Simon Schippers
2026-01-07 21:04 ` [PATCH net-next v7 5/9] tun/tap: add unconsume function for returning entries to ptr_ring Simon Schippers
2026-01-08 3:40 ` Jason Wang
2026-01-07 21:04 ` [PATCH net-next v7 6/9] tun/tap: add helper functions to check file type Simon Schippers
2026-01-07 21:04 ` Simon Schippers [this message]
2026-01-08 4:38 ` [PATCH net-next v7 7/9] vhost-net: vhost-net: replace rx_ring with tun/tap ring wrappers Jason Wang
2026-01-08 7:47 ` Simon Schippers
2026-01-09 6:04 ` Jason Wang
2026-01-09 9:57 ` Simon Schippers
2026-01-12 2:54 ` Jason Wang
2026-01-12 4:42 ` Michael S. Tsirkin
2026-01-07 21:04 ` [PATCH net-next v7 8/9] tun/tap: drop get ring exports Simon Schippers
2026-01-07 21:04 ` [PATCH net-next v7 9/9] tun/tap & vhost-net: avoid ptr_ring tail-drop when qdisc is present Simon Schippers
2026-01-08 4:37 ` Jason Wang
2026-01-08 8:01 ` Simon Schippers
2026-01-09 6:09 ` Jason Wang
2026-01-09 10:14 ` Simon Schippers
2026-01-12 2:22 ` Jason Wang
2026-01-12 11:08 ` Simon Schippers
2026-01-12 11:18 ` Michael S. Tsirkin
2026-01-13 6:26 ` Jason Wang
2026-01-12 4:33 ` Michael S. Tsirkin
2026-01-12 11:17 ` Simon Schippers
2026-01-12 11:19 ` Michael S. Tsirkin
2026-01-12 11:28 ` Simon Schippers
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260107210448.37851-8-simon.schippers@tu-dortmund.de \
--to=simon.schippers@tu-dortmund.de \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=eperezma@redhat.com \
--cc=jasowang@redhat.com \
--cc=jon@nutanix.com \
--cc=kuba@kernel.org \
--cc=kvm@vger.kernel.org \
--cc=leiyang@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=stephen@networkplumber.org \
--cc=tim.gebauer@tu-dortmund.de \
--cc=virtualization@lists.linux.dev \
--cc=willemdebruijn.kernel@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox