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 v9 1/4] tun/tap: add ptr_ring consume helper with netdev queue wakeup
Date: Tue, 28 Apr 2026 14:38:56 +0200 [thread overview]
Message-ID: <20260428123859.19578-2-simon.schippers@tu-dortmund.de> (raw)
In-Reply-To: <20260428123859.19578-1-simon.schippers@tu-dortmund.de>
Introduce tun_ring_consume() that wraps ptr_ring_consume() and calls
__tun_wake_queue(). The latter wakes the stopped netdev subqueue once
half of the ring capacity has been consumed, tracked via the new
cons_cnt field in tun_file. When the ring is empty the queue is also
woken to handle potential races. The point is to allow the queue to
be stopped when it gets full, which is required for traffic shaping -
implemented by the following "avoid ptr_ring tail-drop when a qdisc
is present".
Without the corresponding queue stopping, this patch alone causes no
regression for a tap setup sending to a qemu VM: 1.136 Mpps
to 1.141 Mpps.
Details: AMD Ryzen 5 5600X at 4.3 GHz, 3200 MHz RAM, isolated QEMU
threads, pktgen sender; Avg over 50 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 | 43 +++++++++++++++++++++++++++++++++++++++----
1 file changed, 39 insertions(+), 4 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index b183189f1853..e6ee2271732f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -145,6 +145,7 @@ struct tun_file {
struct list_head next;
struct tun_struct *detached;
struct ptr_ring tx_ring;
+ int cons_cnt;
struct xdp_rxq_info xdp_rxq;
};
@@ -564,6 +565,7 @@ static void tun_queue_purge(struct tun_file *tfile)
while ((ptr = ptr_ring_consume(&tfile->tx_ring)) != NULL)
tun_ptr_free(ptr);
+ tfile->cons_cnt = 0;
skb_queue_purge(&tfile->sk.sk_write_queue);
skb_queue_purge(&tfile->sk.sk_error_queue);
}
@@ -730,6 +732,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
goto out;
}
+ tfile->cons_cnt = 0;
tfile->queue_index = tun->numqueues;
tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN;
@@ -2115,13 +2118,42 @@ static ssize_t tun_put_user(struct tun_struct *tun,
return total;
}
-static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err)
+/* Callers must hold ring.consumer_lock */
+static void __tun_wake_queue(struct tun_struct *tun, struct tun_file *tfile)
+{
+ if (__ptr_ring_empty(&tfile->tx_ring))
+ goto wake;
+
+ if (!__netif_subqueue_stopped(tun->dev, tfile->queue_index) ||
+ ++tfile->cons_cnt < tfile->tx_ring.size / 2)
+ return;
+
+wake:
+ netif_wake_subqueue(tun->dev, tfile->queue_index);
+ tfile->cons_cnt = 0;
+}
+
+static void *tun_ring_consume(struct tun_struct *tun, struct tun_file *tfile)
+{
+ void *ptr;
+
+ spin_lock(&tfile->tx_ring.consumer_lock);
+ ptr = __ptr_ring_consume(&tfile->tx_ring);
+ if (ptr)
+ __tun_wake_queue(tun, tfile);
+
+ spin_unlock(&tfile->tx_ring.consumer_lock);
+ return ptr;
+}
+
+static void *tun_ring_recv(struct tun_struct *tun, struct tun_file *tfile,
+ int noblock, int *err)
{
DECLARE_WAITQUEUE(wait, current);
void *ptr = NULL;
int error = 0;
- ptr = ptr_ring_consume(&tfile->tx_ring);
+ ptr = tun_ring_consume(tun, tfile);
if (ptr)
goto out;
if (noblock) {
@@ -2133,7 +2165,7 @@ static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err)
while (1) {
set_current_state(TASK_INTERRUPTIBLE);
- ptr = ptr_ring_consume(&tfile->tx_ring);
+ ptr = tun_ring_consume(tun, tfile);
if (ptr)
break;
if (signal_pending(current)) {
@@ -2170,7 +2202,7 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
if (!ptr) {
/* Read frames from ring */
- ptr = tun_ring_recv(tfile, noblock, &err);
+ ptr = tun_ring_recv(tun, tfile, noblock, &err);
if (!ptr)
return err;
}
@@ -3406,6 +3438,8 @@ static int tun_chr_open(struct inode *inode, struct file * file)
return -ENOMEM;
}
+ tfile->cons_cnt = 0;
+
mutex_init(&tfile->napi_mutex);
RCU_INIT_POINTER(tfile->tun, NULL);
tfile->flags = 0;
@@ -3614,6 +3648,7 @@ static int tun_queue_resize(struct tun_struct *tun)
for (i = 0; i < tun->numqueues; i++) {
tfile = rtnl_dereference(tun->tfiles[i]);
rings[i] = &tfile->tx_ring;
+ tfile->cons_cnt = 0;
}
list_for_each_entry(tfile, &tun->disabled, next)
rings[i++] = &tfile->tx_ring;
--
2.43.0
next prev parent reply other threads:[~2026-04-28 12:41 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-28 12:38 [PATCH net-next v9 0/4] tun/tap & vhost-net: apply qdisc backpressure on full ptr_ring to reduce TX drops Simon Schippers
2026-04-28 12:38 ` Simon Schippers [this message]
2026-04-28 12:38 ` [PATCH net-next v9 2/4] vhost-net: wake queue of tun/tap after ptr_ring consume Simon Schippers
2026-04-28 12:38 ` [PATCH net-next v9 3/4] ptr_ring: move free-space check into separate helper Simon Schippers
2026-04-28 12:38 ` [PATCH net-next v9 4/4] tun/tap & vhost-net: avoid ptr_ring tail-drop when a qdisc is present Simon Schippers
2026-04-28 12:50 ` Michael S. Tsirkin
2026-04-28 13:10 ` Simon Schippers
2026-04-28 13:22 ` Michael S. Tsirkin
2026-04-28 13:41 ` Simon Schippers
2026-04-28 14:10 ` Michael S. Tsirkin
2026-04-28 14:18 ` Simon Schippers
2026-04-28 14:32 ` Michael S. Tsirkin
2026-04-28 14:55 ` Simon Schippers
2026-04-29 21:04 ` [PATCH net-next v9 0/4] tun/tap & vhost-net: apply qdisc backpressure on full ptr_ring to reduce TX drops 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=20260428123859.19578-2-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