[PATCH net v3] tun: bound the NAPI receive queue

[PATCH net v3] tun: bound the NAPI receive queue

[Antonio Quartulli]

With IFF_NAPI, tun_get_user() queues every written packet for NAPI on
an unbounded list. When the poll runs asynchronously (threaded NAPI)
and is slower than the writer, the queue grows until the system runs
out of memory. An unprivileged user can do this from its own user and
network namespaces, and the queued skbs are not charged to its memcg:
in a test VM, a uid 1000 process limited to 128 MB caused a global OOM
in ~6 seconds. The socket send buffer cannot bound this: tun sets it to
INT_MAX, and the build_skb() and XDP batch paths do not check it.

Drop packets once more than netdev_max_backlog of them are queued, like
enqueue_to_backlog() does, and count them as rx_dropped: before
allocating and copying them where possible, and again under the queue
lock before queueing. This covers write(), sendmsg() and the batches of
XDP buffers vhost-net passes to tun_sendmsg(), which share the queue.
Zerocopy buffers of packets dropped early are completed.

Reproducer, as an unprivileged user in a new user and network
namespace, without kernel modifications or fault injection:
  ip tuntap add t0 mode tun; ip addr add 10.11.0.1/24 dev t0
  ip link add d0 type dummy; ip addr add 10.20.0.1/24 dev d0
  ip link set t0 up; ip link set d0 up; sysctl net.ipv4.ip_forward=1
  install ~500 iptables FORWARD rules and a MASQUERADE rule on d0
  open t0 with IFF_TUN | IFF_NO_PI | IFF_NAPI
  echo 1 > /sys/class/net/t0/threaded
  write() 1400-byte IPv4 packets for 10.20.0.2 in a loop

Tested with the reproducer in an x86-64 VM: memory use stays flat
and the forwarding rate is unchanged. The vhost-net paths are only
build-tested, and the kselftests have not been run yet.

Still open: the limit counts packets rather than bytes and applies per
queue, the NAPI poll splices the queue out while it runs so up to about
twice the limit can be in flight, and the queued skbs are still not
charged to the writer's memcg.

Found, fixed and tested with the help of an AI coding assistant
(Claude Code).

Fixes: 943170998b20 ("tun: enable NAPI for TUN/TAP driver")
Signed-off-by: Antonio Quartulli <antonio@mandelbit.com>
---
v3:
- Also bound the sendmsg() paths, which share the queue: zerocopy
  buffers are completed when dropped early, and the batched XDP buffers
  of tun_xdp_one() are covered too (Willem)
- Drop the IFF_NAPI_FRAGS exclusion: tun_get_user() never queues in
  that mode (napi_gro_frags() is synchronous), so the early check only
  fires if tun_xdp_one() filled the same queue, and dropping is fine
  then too (Willem)
- Recheck under the queue lock before queueing (Willem)
- Compare with > like enqueue_to_backlog() (Willem)
- Keep the includes sorted (Willem)
- Add the reproducer and a testing statement to the commit message

v2: https://lore.kernel.org/netdev/20261030152540.1409884-1-antonio@mandelbit.com/
- Cc netdev and the maintainers

Notes:
- Affected since 943170998b20 (v4.15). Reproduced on mainline
  7be4bc52fd9e; the code is unchanged in net/main 94cea342e891, which
  this patch is based on and was build-tested (W=1) against.
- Mitigation: disallow unprivileged user namespaces or restrict
  access to /dev/net/tun.

 drivers/net/tun.c | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 770b8fe085c3..df5f0cbd1b16 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -58,6 +58,7 @@
 #include <linux/nsproxy.h>
 #include <linux/virtio_net.h>
 #include <linux/rcupdate.h>
+#include <net/hotdata.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
@@ -227,6 +228,15 @@ struct veth {
 static void tun_flow_init(struct tun_struct *tun);
 static void tun_flow_uninit(struct tun_struct *tun);
 
+/* In IFF_NAPI mode written packets wait in the tfile's sk_write_queue for the
+ * NAPI poll, which may run later in a kthread or ksoftirqd. Bound that queue
+ * like the per-CPU backlog of netif_rx().
+ */
+static bool tun_napi_queue_full(const struct sk_buff_head *queue)
+{
+	return skb_queue_len_lockless(queue) > READ_ONCE(net_hotdata.max_backlog);
+}
+
 static int tun_napi_receive(struct napi_struct *napi, int budget)
 {
 	struct tun_file *tfile = container_of(napi, struct tun_file, napi);
@@ -1856,6 +1866,20 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			zerocopy = true;
 	}
 
+	/* Drop before allocating and copying when the NAPI queue is full. The
+	 * check is repeated under the queue lock before queueing.
+	 */
+	if (tfile->napi_enabled &&
+	    unlikely(tun_napi_queue_full(&tfile->sk.sk_write_queue))) {
+		if (msg_control) {
+			struct ubuf_info *uarg = msg_control;
+
+			uarg->ops->complete(NULL, uarg, false);
+		}
+		dev_core_stats_rx_dropped_inc(tun->dev);
+		return total_len;
+	}
+
 	if (!frags && tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) {
 		/* For the packet that is not easy to be processed
 		 * (e.g gso or jumbo packet), we will do it at after
@@ -2045,6 +2069,14 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			goto free_skb;
 		}
 
+		if (unlikely(tun_napi_queue_full(queue))) {
+			spin_unlock_bh(&queue->lock);
+			rcu_read_unlock();
+			kfree_skb_reason(skb, SKB_DROP_REASON_FULL_RING);
+			dev_core_stats_rx_dropped_inc(tun->dev);
+			return total_len;
+		}
+
 		__skb_queue_tail(queue, skb);
 		queue_len = skb_queue_len(queue);
 		spin_unlock(&queue->lock);
@@ -2649,6 +2681,13 @@ static int tun_xdp_one(struct tun_struct *tun,
 			return -EBUSY;
 		}
 
+		if (unlikely(tun_napi_queue_full(queue))) {
+			spin_unlock(&queue->lock);
+			kfree_skb_reason(skb, SKB_DROP_REASON_FULL_RING);
+			dev_core_stats_rx_dropped_inc(tun->dev);
+			return 0;
+		}
+
 		__skb_queue_tail(queue, skb);
 		spin_unlock(&queue->lock);
 		ret = 1;
-- 
2.56.0

Re: [PATCH net v3] tun: bound the NAPI receive queue

[Willem de Bruijn]

Antonio Quartulli wrote:
> With IFF_NAPI, tun_get_user() queues every written packet for NAPI on
> an unbounded list. When the poll runs asynchronously (threaded NAPI)
> and is slower than the writer, the queue grows until the system runs
> out of memory. An unprivileged user can do this from its own user and
> network namespaces, and the queued skbs are not charged to its memcg:
> in a test VM, a uid 1000 process limited to 128 MB caused a global OOM
> in ~6 seconds. The socket send buffer cannot bound this: tun sets it to
> INT_MAX, and the build_skb() and XDP batch paths do not check it.
> 
> Drop packets once more than netdev_max_backlog of them are queued, like
> enqueue_to_backlog() does, and count them as rx_dropped: before
> allocating and copying them where possible, and again under the queue
> lock before queueing. This covers write(), sendmsg() and the batches of
> XDP buffers vhost-net passes to tun_sendmsg(), which share the queue.
> Zerocopy buffers of packets dropped early are completed.
> 
> Reproducer, as an unprivileged user in a new user and network
> namespace, without kernel modifications or fault injection:
>   ip tuntap add t0 mode tun; ip addr add 10.11.0.1/24 dev t0
>   ip link add d0 type dummy; ip addr add 10.20.0.1/24 dev d0
>   ip link set t0 up; ip link set d0 up; sysctl net.ipv4.ip_forward=1
>   install ~500 iptables FORWARD rules and a MASQUERADE rule on d0
>   open t0 with IFF_TUN | IFF_NO_PI | IFF_NAPI
>   echo 1 > /sys/class/net/t0/threaded
>   write() 1400-byte IPv4 packets for 10.20.0.2 in a loop
> 
> Tested with the reproducer in an x86-64 VM: memory use stays flat
> and the forwarding rate is unchanged. The vhost-net paths are only
> build-tested, and the kselftests have not been run yet.

Let's make sure the tun selftests pass.
 
> Still open: the limit counts packets rather than bytes and applies per
> queue, the NAPI poll splices the queue out while it runs so up to about
> twice the limit can be in flight, and the queued skbs are still not
> charged to the writer's memcg.
> 
> Found, fixed and tested with the help of an AI coding assistant
> (Claude Code).
> 
> Fixes: 943170998b20 ("tun: enable NAPI for TUN/TAP driver")
> Signed-off-by: Antonio Quartulli <antonio@mandelbit.com>
> ---
> v3:
> - Also bound the sendmsg() paths, which share the queue: zerocopy
>   buffers are completed when dropped early, and the batched XDP buffers
>   of tun_xdp_one() are covered too (Willem)
> - Drop the IFF_NAPI_FRAGS exclusion: tun_get_user() never queues in
>   that mode (napi_gro_frags() is synchronous), so the early check only
>   fires if tun_xdp_one() filled the same queue, and dropping is fine
>   then too (Willem)
> - Recheck under the queue lock before queueing (Willem)
> - Compare with > like enqueue_to_backlog() (Willem)
> - Keep the includes sorted (Willem)
> - Add the reproducer and a testing statement to the commit message
> 
> v2: https://lore.kernel.org/netdev/20261030152540.1409884-1-antonio@mandelbit.com/
> - Cc netdev and the maintainers
> 
> Notes:
> - Affected since 943170998b20 (v4.15). Reproduced on mainline
>   7be4bc52fd9e; the code is unchanged in net/main 94cea342e891, which
>   this patch is based on and was build-tested (W=1) against.
> - Mitigation: disallow unprivileged user namespaces or restrict
>   access to /dev/net/tun.
> 
>  drivers/net/tun.c | 39 +++++++++++++++++++++++++++++++++++++++
>  1 file changed, 39 insertions(+)
> 
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index 770b8fe085c3..df5f0cbd1b16 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -58,6 +58,7 @@
>  #include <linux/nsproxy.h>
>  #include <linux/virtio_net.h>
>  #include <linux/rcupdate.h>
> +#include <net/hotdata.h>
>  #include <net/net_namespace.h>
>  #include <net/netns/generic.h>
>  #include <net/rtnetlink.h>
> @@ -227,6 +228,15 @@ struct veth {
>  static void tun_flow_init(struct tun_struct *tun);
>  static void tun_flow_uninit(struct tun_struct *tun);
>  
> +/* In IFF_NAPI mode written packets wait in the tfile's sk_write_queue for the
> + * NAPI poll, which may run later in a kthread or ksoftirqd. Bound that queue
> + * like the per-CPU backlog of netif_rx().
> + */
> +static bool tun_napi_queue_full(const struct sk_buff_head *queue)
> +{
> +	return skb_queue_len_lockless(queue) > READ_ONCE(net_hotdata.max_backlog);
> +}
> +
>  static int tun_napi_receive(struct napi_struct *napi, int budget)
>  {
>  	struct tun_file *tfile = container_of(napi, struct tun_file, napi);
> @@ -1856,6 +1866,20 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
>  			zerocopy = true;
>  	}
>  
> +	/* Drop before allocating and copying when the NAPI queue is full. The
> +	 * check is repeated under the queue lock before queueing.
> +	 */
> +	if (tfile->napi_enabled &&
> +	    unlikely(tun_napi_queue_full(&tfile->sk.sk_write_queue))) {
> +		if (msg_control) {
> +			struct ubuf_info *uarg = msg_control;
> +
> +			uarg->ops->complete(NULL, uarg, false);
> +		}
> +		dev_core_stats_rx_dropped_inc(tun->dev);
> +		return total_len;
> +	}
> +
>  	if (!frags && tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) {
>  		/* For the packet that is not easy to be processed
>  		 * (e.g gso or jumbo packet), we will do it at after
> @@ -2045,6 +2069,14 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
>  			goto free_skb;
>  		}
>  
> +		if (unlikely(tun_napi_queue_full(queue))) {
> +			spin_unlock_bh(&queue->lock);
> +			rcu_read_unlock();
> +			kfree_skb_reason(skb, SKB_DROP_REASON_FULL_RING);
> +			dev_core_stats_rx_dropped_inc(tun->dev);
> +			return total_len;

consider goto free_skb instead of open coding.
> +		}
> +
>  		__skb_queue_tail(queue, skb);
>  		queue_len = skb_queue_len(queue);
>  		spin_unlock(&queue->lock);
> @@ -2649,6 +2681,13 @@ static int tun_xdp_one(struct tun_struct *tun,
>  			return -EBUSY;
>  		}
>  
> +		if (unlikely(tun_napi_queue_full(queue))) {
> +			spin_unlock(&queue->lock);
> +			kfree_skb_reason(skb, SKB_DROP_REASON_FULL_RING);
> +			dev_core_stats_rx_dropped_inc(tun->dev);
> +			return 0;
> +		}
> +
>  		__skb_queue_tail(queue, skb);
>  		spin_unlock(&queue->lock);
>  		ret = 1;
> -- 
> 2.56.0
>