[PATCH net v2] tun/tap & vhost-net: make qdisc backpressure opt-in via IFF_BACKPRESSURE
From: Simon Schippers
Date: Mon Jul 06 2026 - 06:54:09 EST
Commit 1d6e569b7d0c ("tun/tap & vhost-net: avoid ptr_ring tail-drop
when a qdisc is present") did not show a relevant performance regression
in my testing but on Brett Sheffield's librecast testbed it shows a
significant performance drop in a IPv6 multicast testcase. The regression
can be pinpointed when multiple iperf3 UDP threads are sending. For 8
threads the performance dropped from 13.5 Gbit/s to 9.13 Gbit/s. This is
the reason why this patch makes the qdisc backpressure behavior opt-in.
One option to accomplish the opt-in would be to set the default qdisc to
noqueue at init. However this may also break userspace as users might
have chosen a custom qdisc even though most of the qdiscs did nothing
for tun/tap in the past due to missing backpressure...
This is the reason why in this patch, the flag IFF_BACKPRESSURE is
introduced instead which is required to enable the backpressure logic.
This means the stopping logic in tun_net_xmit() and the waking logic in
__tun_wake_queue() are skipped if the flag is disabled.
To avoid a possible stall due to disabling IFF_BACKPRESSURE, the new
helper tun_force_wake_queue() is implemented. The helper safely wakes the
respective netdev queue and resets cons_cnt while the consumer_lock and
the producer_lock of the ring are held. The helper is run in tun_attach()
when a queue (re)attaches, in tun_set_iff() for attached tfiles, and
in tun_queue_resize().
The documentation in tuntap.rst is updated accordingly.
Fixes: 1d6e569b7d0c ("tun/tap & vhost-net: avoid ptr_ring tail-drop when a qdisc is present")
Reported-by: Brett Sheffield <brett@xxxxxxxxxxxxx>
Closes: https://lore.kernel.org/netdev/akVnoOYQOrt8k-Gu@xxxxxxxxxxxxxxxxxxxx/T/#u
Signed-off-by: Simon Schippers <simon.schippers@xxxxxxxxxxxxxx>
---
V1 -> V2:
- Sashiko: Ensure detached queues are woken on re-attach by calling the
new tun_force_wake_queue() helper from tun_attach(), and reuse it
across the existing wake paths.
- Specify the failing test case in the commit message.
---
Documentation/networking/tuntap.rst | 17 ++++++++++
drivers/net/tun.c | 49 ++++++++++++++++++-----------
include/uapi/linux/if_tun.h | 1 +
tools/include/uapi/linux/if_tun.h | 1 +
4 files changed, 50 insertions(+), 18 deletions(-)
diff --git a/Documentation/networking/tuntap.rst b/Documentation/networking/tuntap.rst
index 4d7087f727be..599264825dd2 100644
--- a/Documentation/networking/tuntap.rst
+++ b/Documentation/networking/tuntap.rst
@@ -206,6 +206,23 @@ enable is true we enable it, otherwise we disable it::
return ioctl(fd, TUNSETQUEUE, (void *)&ifr);
}
+3.4 qdisc backpressure
+----------------------
+
+Starting with Linux 7.2, IFF_BACKPRESSURE can be set to enable qdisc
+backpressure. Without it, TX drops occur when the internal ring buffer is
+full. With it, the kernel stops the TX queue instead, letting the qdisc
+hold packets. Drops only occur as a rare race. This can benefit protocols
+like TCP that react to drops. Backpressure requires a qdisc to be
+attached and has no effect with noqueue.
+
+The TUN/TAP ring buffer size can be reduced alongside this flag to
+further shift buffering into the qdisc and reduce bufferbloat, but comes
+at possible performance cost.
+
+When running multiple network streams in parallel, the flag may reduce
+performance due to the extra overhead of the backpressure mechanism.
+
Universal TUN/TAP device driver Frequently Asked Question
=========================================================
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ffbe6f13fb1f..62e5eab4e345 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -98,7 +98,8 @@ static void tun_default_link_ksettings(struct net_device *dev,
#define TUN_FASYNC IFF_ATTACH_QUEUE
#define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
- IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS)
+ IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS | \
+ IFF_BACKPRESSURE)
#define GOODCOPY_LEN 128
@@ -694,6 +695,20 @@ static void tun_detach_all(struct net_device *dev)
module_put(THIS_MODULE);
}
+static void tun_force_wake_queue(struct tun_struct *tun,
+ struct tun_file *tfile)
+{
+ /* Ensure that the producer can not stop the
+ * queue concurrently by taking locks.
+ */
+ spin_lock_bh(&tfile->tx_ring.consumer_lock);
+ spin_lock(&tfile->tx_ring.producer_lock);
+ netif_wake_subqueue(tun->dev, tfile->queue_index);
+ tfile->cons_cnt = 0;
+ spin_unlock(&tfile->tx_ring.producer_lock);
+ spin_unlock_bh(&tfile->tx_ring.consumer_lock);
+}
+
static int tun_attach(struct tun_struct *tun, struct file *file,
bool skip_filter, bool napi, bool napi_frags,
bool publish_tun)
@@ -737,11 +752,9 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
goto out;
}
- spin_lock(&tfile->tx_ring.consumer_lock);
- tfile->cons_cnt = 0;
- spin_unlock(&tfile->tx_ring.consumer_lock);
tfile->queue_index = tun->numqueues;
tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN;
+ tun_force_wake_queue(tun, tfile);
if (tfile->detached) {
/* Re-attach detached tfile, updating XDP queue_index */
@@ -1077,7 +1090,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
spin_lock(&tfile->tx_ring.producer_lock);
ret = __ptr_ring_produce(&tfile->tx_ring, skb);
- if (!qdisc_txq_has_no_queue(queue) &&
+ if ((tun->flags & IFF_BACKPRESSURE) &&
+ !qdisc_txq_has_no_queue(queue) &&
__ptr_ring_check_produce(&tfile->tx_ring) == -ENOSPC) {
netif_tx_stop_queue(queue);
/* Paired with smp_mb() in __tun_wake_queue() */
@@ -2151,8 +2165,12 @@ static ssize_t tun_put_user(struct tun_struct *tun,
static void __tun_wake_queue(struct tun_struct *tun,
struct tun_file *tfile, int consumed)
{
- struct netdev_queue *txq = netdev_get_tx_queue(tun->dev,
- tfile->queue_index);
+ struct netdev_queue *txq;
+
+ if (!(tun->flags & IFF_BACKPRESSURE))
+ return;
+
+ txq = netdev_get_tx_queue(tun->dev, tfile->queue_index);
/* Paired with smp_mb__after_atomic() in tun_net_xmit() */
smp_mb();
@@ -2764,7 +2782,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
struct tun_struct *tun;
struct tun_file *tfile = file->private_data;
struct net_device *dev;
- int err;
+ int err, i;
if (tfile->detached)
return -EINVAL;
@@ -2894,7 +2912,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
* xoff state.
*/
if (netif_running(tun->dev))
- netif_tx_wake_all_queues(tun->dev);
+ for (i = 0; i < tun->numqueues; i++)
+ tun_force_wake_queue(tun, rtnl_dereference(tun->tfiles[i]));
strscpy(ifr->ifr_name, tun->dev->name);
return 0;
@@ -3690,15 +3709,9 @@ static int tun_queue_resize(struct tun_struct *tun)
dev->tx_queue_len, GFP_KERNEL,
tun_ptr_free);
- if (!ret) {
- for (i = 0; i < tun->numqueues; i++) {
- tfile = rtnl_dereference(tun->tfiles[i]);
- spin_lock(&tfile->tx_ring.consumer_lock);
- netif_wake_subqueue(tun->dev, tfile->queue_index);
- tfile->cons_cnt = 0;
- spin_unlock(&tfile->tx_ring.consumer_lock);
- }
- }
+ if (!ret)
+ for (i = 0; i < tun->numqueues; i++)
+ tun_force_wake_queue(tun, rtnl_dereference(tun->tfiles[i]));
kfree(rings);
return ret;
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 79d53c7a1ebd..73a77141315c 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -69,6 +69,7 @@
#define IFF_NAPI_FRAGS 0x0020
/* Used in TUNSETIFF to bring up tun/tap without carrier */
#define IFF_NO_CARRIER 0x0040
+#define IFF_BACKPRESSURE 0x0080
#define IFF_NO_PI 0x1000
/* This flag has no real effect */
#define IFF_ONE_QUEUE 0x2000
diff --git a/tools/include/uapi/linux/if_tun.h b/tools/include/uapi/linux/if_tun.h
index 2ec07de1d73b..97b670f5bc0a 100644
--- a/tools/include/uapi/linux/if_tun.h
+++ b/tools/include/uapi/linux/if_tun.h
@@ -67,6 +67,7 @@
#define IFF_TAP 0x0002
#define IFF_NAPI 0x0010
#define IFF_NAPI_FRAGS 0x0020
+#define IFF_BACKPRESSURE 0x0080
#define IFF_NO_PI 0x1000
/* This flag has no real effect */
#define IFF_ONE_QUEUE 0x2000
--
2.43.0