[PATCH net-next v14 3/5] vhost-net: wake queue of tun/tap after ptr_ring consume

Add tun_wake_queue() to tun.c and export it for use by vhost-net. The
function validates that the file belongs to a device implemented by
drivers/net/tun.c, in IFF_TUN as well as in IFF_TAP mode, and that the
tfile exists, 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.
The point is to allow the queue to be stopped when it gets full, which is
required for traffic shaping, implemented by the following
"stop tail-drop when IFF_BACKPRESSURE is set".
As __tun_wake_queue() returns early unless IFF_BACKPRESSURE is set, a
tun/tap device that does not opt in only pays for the added check.

macvtap and ipvtap rings, which get_tap_ptr_ring() accepts too, are
unaffected: their producer is the tap_handle_frame() rx_handler and not
ndo_start_xmit, so stopping a netdev TX queue would not hold it back.
drivers/net/tap.c has no netdev_ops of its own either. No
tap_wake_queue() is needed.

cons_cnt and the wake decision are best-effort and are not reverted by
ptr_ring_unconsume(), so vhost_net_buf_unproduce() can leave the subqueue
woken over a full ring. The producer re-stops it on the next packet, and
that path only runs from vhost_net_stop_vq() and vhost_net_set_backend(),
when the consumer is going away, so a stopped queue is the correct end
state rather than a stall.

Co-developed-by: Tim Gebauer <[email protected]>
Signed-off-by: Tim Gebauer <[email protected]>
Signed-off-by: Simon Schippers <[email protected]>
---
 drivers/net/tun.c      | 25 +++++++++++++++++++++++++
 drivers/vhost/net.c    | 21 +++++++++++++++------
 include/linux/if_tun.h |  4 ++++
 3 files changed, 44 insertions(+), 6 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index d49b6bfd104d..dc32566588d1 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -3848,6 +3848,31 @@ struct ptr_ring *tun_get_tx_ring(struct file *file)
 }
 EXPORT_SYMBOL_GPL(tun_get_tx_ring);
 
+/* Callers must hold ring.consumer_lock */
+void tun_wake_queue(struct file *file, int consumed)
+{
+	struct tun_file *tfile;
+	struct tun_struct *tun;
+
+	if (file->f_op != &tun_fops)
+		return;
+
+	tfile = file->private_data;
+	if (!tfile)
+		return;
+
+	lockdep_assert_held(&tfile->tx_ring.consumer_lock);
+
+	rcu_read_lock();
+
+	tun = rcu_dereference(tfile->tun);
+	if (tun)
+		__tun_wake_queue(tun, tfile, consumed);
+
+	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 6949b704166d..3e72b9c6af0c 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -176,13 +176,21 @@ 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);
+	spin_lock(&nvq->rx_ring->consumer_lock);
+	rxq->tail = __ptr_ring_consume_batched(nvq->rx_ring, rxq->queue,
+					       VHOST_NET_BATCH);
+
+	if (rxq->tail)
+		tun_wake_queue(file, rxq->tail);
+
+	spin_unlock(&nvq->rx_ring->consumer_lock);
 	return rxq->tail;
 }
 
@@ -209,14 +217,15 @@ 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:
@@ -1004,7 +1013,7 @@ 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..eeb9ed3c5a23 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -22,6 +22,8 @@ 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);
+/* Callers must hold the consumer_lock of the ring of file */
+void tun_wake_queue(struct file *file, int consumed);
 
 static inline bool tun_is_xdp_frame(void *ptr)
 {
@@ -55,6 +57,8 @@ 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, int consumed) {}
+
 static inline bool tun_is_xdp_frame(void *ptr)
 {
 	return false;
-- 
2.43.0