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 v8 2/4] vhost-net: wake queue of tun/tap after ptr_ring consume
Date: Thu, 12 Mar 2026 14:06:37 +0100 [thread overview]
Message-ID: <20260312130639.138988-3-simon.schippers@tu-dortmund.de> (raw)
In-Reply-To: <20260312130639.138988-1-simon.schippers@tu-dortmund.de>
Add tun_wake_queue() to tun.c and export it for use by vhost-net. The
function validates that the file belongs to a tun/tap device,
dereferences the tun_struct under RCU, and delegates to
__tun_wake_queue().
vhost_net_buf_produce() now calls tun_wake_queue() after a successful
batched consume of the ring to allow the netdev subqueue to be woken up.
Without the corresponding queue stopping (introduced in a subsequent
commit), this patch alone causes a slight throughput regression for a
tap+vhost-net setup sending to a qemu VM:
3.948 Mpps to 3.888 Mpps (-1.5%).
Details: AMD Ryzen 5 5600X at 4.3 GHz, 3200 MHz RAM, isolated QEMU
threads, XDP drop program active in VM, pktgen sender; Avg over
20 runs @ 100,000,000 packets. SRSO and spectre v2 mitigations disabled.
Co-developed-by: Tim Gebauer <tim.gebauer@tu-dortmund.de>
Signed-off-by: Tim Gebauer <tim.gebauer@tu-dortmund.de>
Signed-off-by: Simon Schippers <simon.schippers@tu-dortmund.de>
---
drivers/net/tun.c | 21 +++++++++++++++++++++
drivers/vhost/net.c | 15 +++++++++++----
include/linux/if_tun.h | 3 +++
3 files changed, 35 insertions(+), 4 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a82d665dab5f..b86582cc6cb6 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -3760,6 +3760,27 @@ struct ptr_ring *tun_get_tx_ring(struct file *file)
}
EXPORT_SYMBOL_GPL(tun_get_tx_ring);
+void tun_wake_queue(struct file *file)
+{
+ struct tun_file *tfile;
+ struct tun_struct *tun;
+
+ if (file->f_op != &tun_fops)
+ return;
+ tfile = file->private_data;
+ if (!tfile)
+ return;
+
+ rcu_read_lock();
+
+ tun = rcu_dereference(tfile->tun);
+ if (tun)
+ __tun_wake_queue(tun, tfile);
+
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(tun_wake_queue);
+
module_init(tun_init);
module_exit(tun_cleanup);
MODULE_DESCRIPTION(DRV_DESCRIPTION);
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 80965181920c..c8ef804ef28c 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -176,13 +176,19 @@ 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 sock *sk,
+ struct vhost_net_virtqueue *nvq)
{
+ 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);
+
+ if (rxq->tail)
+ tun_wake_queue(file);
+
return rxq->tail;
}
@@ -209,14 +215,15 @@ 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 sock *sk,
+ struct vhost_net_virtqueue *nvq)
{
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(sk, nvq))
return 0;
out:
@@ -995,7 +1002,7 @@ static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk)
unsigned long flags;
if (rvq->rx_ring)
- return vhost_net_buf_peek(rvq);
+ return vhost_net_buf_peek(sk, rvq);
spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
head = skb_peek(&sk->sk_receive_queue);
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 80166eb62f41..ab3b4ebca059 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -22,6 +22,7 @@ struct tun_msg_ctl {
#if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE)
struct socket *tun_get_socket(struct file *);
struct ptr_ring *tun_get_tx_ring(struct file *file);
+void tun_wake_queue(struct file *file);
static inline bool tun_is_xdp_frame(void *ptr)
{
@@ -55,6 +56,8 @@ static inline struct ptr_ring *tun_get_tx_ring(struct file *f)
return ERR_PTR(-EINVAL);
}
+static inline void tun_wake_queue(struct file *f) {}
+
static inline bool tun_is_xdp_frame(void *ptr)
{
return false;
--
2.43.0
next prev parent reply other threads:[~2026-03-12 13:07 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-12 13:06 [PATCH net-next v8 0/4] tun/tap & vhost-net: apply qdisc backpressure on full ptr_ring to reduce TX drops Simon Schippers
2026-03-12 13:06 ` [PATCH net-next v8 1/4] tun/tap: add ptr_ring consume helper with netdev queue wakeup Simon Schippers
2026-03-24 1:47 ` Jason Wang
2026-03-12 13:06 ` Simon Schippers [this message]
2026-03-12 13:54 ` [PATCH net-next v8 2/4] vhost-net: wake queue of tun/tap after ptr_ring consume Michael S. Tsirkin
2026-03-24 1:47 ` Jason Wang
2026-03-12 13:06 ` [PATCH net-next v8 3/4] ptr_ring: move free-space check into separate helper Simon Schippers
2026-03-12 13:17 ` Eric Dumazet
2026-03-12 13:48 ` Michael S. Tsirkin
2026-03-12 14:21 ` Eric Dumazet
2026-03-25 11:07 ` Michael S. Tsirkin
2026-03-12 13:06 ` [PATCH net-next v8 4/4] tun/tap & vhost-net: avoid ptr_ring tail-drop when a qdisc is present Simon Schippers
2026-03-24 1:47 ` Jason Wang
2026-03-24 10:14 ` Simon Schippers
2026-03-25 14:47 ` Simon Schippers
2026-03-26 2:41 ` Jason Wang
2026-03-26 15:30 ` Simon Schippers
2026-03-12 13:55 ` [PATCH net-next v8 0/4] tun/tap & vhost-net: apply qdisc backpressure on full ptr_ring to reduce TX drops Michael S. Tsirkin
2026-03-13 9:49 ` Simon Schippers
2026-03-13 10:35 ` Michael S. Tsirkin
2026-03-23 21:49 ` 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=20260312130639.138988-3-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