Merge branch 'virtio-net-link-queues-to-napis'

Joe Damato says:

====================
virtio-net: Link queues to NAPIs

Jakub recently commented [1] that I should not hold this series on
virtio-net linking queues to NAPIs behind other important work that is
on-going and suggested I re-spin, so here we are :)

As per the discussion on the v3 [2], now both RX and TX NAPIs use the
API to link queues to NAPIs. Since TX-only NAPIs don't have a NAPI ID,
commit 6597e8d35851 ("netdev-genl: Elide napi_id when not present") now
correctly elides the TX-only NAPIs (instead of printing zero) when the
queues and NAPIs are linked.

As per the discussion on the v4 [3], patch 3 has been refactored to hold
RTNL only in the specific locations which need it as Jason requested.

As per the discussion on the v5 [4], patch 3 now leaves refill_work
as-is and does not use the API to unlink and relink queues and NAPIs. A
comment has been left as suggested by Jakub [5] for future work.

See the commit message of patch 3 for an example of how to get the NAPI
to queue mapping information.

See the commit message of patch 4 for an example of how NAPI IDs are
persistent despite queue count changes.

[1]: https://lore.kernel.org/20250221142650.3c74dcac@kernel.org
[2]: https://lore.kernel.org/20250127142400.24eca319@kernel.org
[3]: https://lore.kernel.org/CACGkMEv=ejJnOWDnAu7eULLvrqXjkMkTL4cbi-uCTUhCpKN_GA@mail.gmail.com
[4]: https://lore.kernel.org/Z8X15hxz8t-vXpPU@LQ3V64L9R2
[5]: https://lore.kernel.org/20250303160355.5f8d82d8@kernel.org

v5: https://lore.kernel.org/20250227185017.206785-1-jdamato@fastly.com
v4: https://lore.kernel.org/20250225020455.212895-1-jdamato@fastly.com
rfcv3: https://lore.kernel.org/20250121191047.269844-1-jdamato@fastly.com
v2: https://lore.kernel.org/20250116055302.14308-1-jdamato@fastly.com
v1: https://lore.kernel.org/20250110202605.429475-1-jdamato@fastly.com
====================

Link: https://patch.msgid.link/20250307011215.266806-1-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 74 insertions, 27 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ac26a6201c44..34cec2b11b74 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2807,7 +2807,8 @@ static void skb_recv_done(struct virtqueue *rvq)
 	virtqueue_napi_schedule(&rq->napi, rvq);
 }
 
-static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi)
+static void virtnet_napi_do_enable(struct virtqueue *vq,
+				   struct napi_struct *napi)
 {
 	napi_enable(napi);
 
@@ -2820,10 +2821,21 @@ static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi)
 	local_bh_enable();
 }
 
-static void virtnet_napi_tx_enable(struct virtnet_info *vi,
-				   struct virtqueue *vq,
-				   struct napi_struct *napi)
+static void virtnet_napi_enable(struct receive_queue *rq)
+{
+	struct virtnet_info *vi = rq->vq->vdev->priv;
+	int qidx = vq2rxq(rq->vq);
+
+	virtnet_napi_do_enable(rq->vq, &rq->napi);
+	netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_RX, &rq->napi);
+}
+
+static void virtnet_napi_tx_enable(struct send_queue *sq)
 {
+	struct virtnet_info *vi = sq->vq->vdev->priv;
+	struct napi_struct *napi = &sq->napi;
+	int qidx = vq2txq(sq->vq);
+
 	if (!napi->weight)
 		return;
 
@@ -2835,13 +2847,30 @@ static void virtnet_napi_tx_enable(struct virtnet_info *vi,
 		return;
 	}
 
-	return virtnet_napi_enable(vq, napi);
+	virtnet_napi_do_enable(sq->vq, napi);
+	netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_TX, napi);
 }
 
-static void virtnet_napi_tx_disable(struct napi_struct *napi)
+static void virtnet_napi_tx_disable(struct send_queue *sq)
 {
-	if (napi->weight)
+	struct virtnet_info *vi = sq->vq->vdev->priv;
+	struct napi_struct *napi = &sq->napi;
+	int qidx = vq2txq(sq->vq);
+
+	if (napi->weight) {
+		netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_TX, NULL);
 		napi_disable(napi);
+	}
+}
+
+static void virtnet_napi_disable(struct receive_queue *rq)
+{
+	struct virtnet_info *vi = rq->vq->vdev->priv;
+	struct napi_struct *napi = &rq->napi;
+	int qidx = vq2rxq(rq->vq);
+
+	netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_RX, NULL);
+	napi_disable(napi);
 }
 
 static void refill_work(struct work_struct *work)
@@ -2854,9 +2883,23 @@ static void refill_work(struct work_struct *work)
 	for (i = 0; i < vi->curr_queue_pairs; i++) {
 		struct receive_queue *rq = &vi->rq[i];
 
+		/*
+		 * When queue API support is added in the future and the call
+		 * below becomes napi_disable_locked, this driver will need to
+		 * be refactored.
+		 *
+		 * One possible solution would be to:
+		 *   - cancel refill_work with cancel_delayed_work (note:
+		 *     non-sync)
+		 *   - cancel refill_work with cancel_delayed_work_sync in
+		 *     virtnet_remove after the netdev is unregistered
+		 *   - wrap all of the work in a lock (perhaps the netdev
+		 *     instance lock)
+		 *   - check netif_running() and return early to avoid a race
+		 */
 		napi_disable(&rq->napi);
 		still_empty = !try_fill_recv(vi, rq, GFP_KERNEL);
-		virtnet_napi_enable(rq->vq, &rq->napi);
+		virtnet_napi_do_enable(rq->vq, &rq->napi);
 
 		/* In theory, this can happen: if we don't get any buffers in
 		 * we will *never* try to fill again.
@@ -3053,8 +3096,8 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 
 static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index)
 {
-	virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
-	napi_disable(&vi->rq[qp_index].napi);
+	virtnet_napi_tx_disable(&vi->sq[qp_index]);
+	virtnet_napi_disable(&vi->rq[qp_index]);
 	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
 }
 
@@ -3073,8 +3116,8 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
 	if (err < 0)
 		goto err_xdp_reg_mem_model;
 
-	virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
-	virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
+	virtnet_napi_enable(&vi->rq[qp_index]);
+	virtnet_napi_tx_enable(&vi->sq[qp_index]);
 
 	return 0;
 
@@ -3326,7 +3369,7 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
 	bool running = netif_running(vi->dev);
 
 	if (running) {
-		napi_disable(&rq->napi);
+		virtnet_napi_disable(rq);
 		virtnet_cancel_dim(vi, &rq->dim);
 	}
 }
@@ -3339,7 +3382,7 @@ static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
 		schedule_delayed_work(&vi->refill, 0);
 
 	if (running)
-		virtnet_napi_enable(rq->vq, &rq->napi);
+		virtnet_napi_enable(rq);
 }
 
 static int virtnet_rx_resize(struct virtnet_info *vi,
@@ -3368,7 +3411,7 @@ static void virtnet_tx_pause(struct virtnet_info *vi, struct send_queue *sq)
 	qindex = sq - vi->sq;
 
 	if (running)
-		virtnet_napi_tx_disable(&sq->napi);
+		virtnet_napi_tx_disable(sq);
 
 	txq = netdev_get_tx_queue(vi->dev, qindex);
 
@@ -3402,7 +3445,7 @@ static void virtnet_tx_resume(struct virtnet_info *vi, struct send_queue *sq)
 	__netif_tx_unlock_bh(txq);
 
 	if (running)
-		virtnet_napi_tx_enable(vi, sq->vq, &sq->napi);
+		virtnet_napi_tx_enable(sq);
 }
 
 static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq,
@@ -5634,8 +5677,11 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 	netif_tx_lock_bh(vi->dev);
 	netif_device_detach(vi->dev);
 	netif_tx_unlock_bh(vi->dev);
-	if (netif_running(vi->dev))
+	if (netif_running(vi->dev)) {
+		rtnl_lock();
 		virtnet_close(vi->dev);
+		rtnl_unlock();
+	}
 }
 
 static int init_vqs(struct virtnet_info *vi);
@@ -5655,7 +5701,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 	enable_rx_mode_work(vi);
 
 	if (netif_running(vi->dev)) {
+		rtnl_lock();
 		err = virtnet_open(vi->dev);
+		rtnl_unlock();
 		if (err)
 			return err;
 	}
@@ -5945,8 +5993,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
 	if (netif_running(dev)) {
 		for (i = 0; i < vi->max_queue_pairs; i++) {
-			napi_disable(&vi->rq[i].napi);
-			virtnet_napi_tx_disable(&vi->sq[i].napi);
+			virtnet_napi_disable(&vi->rq[i]);
+			virtnet_napi_tx_disable(&vi->sq[i]);
 		}
 	}
 
@@ -5983,9 +6031,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		if (old_prog)
 			bpf_prog_put(old_prog);
 		if (netif_running(dev)) {
-			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
-					       &vi->sq[i].napi);
+			virtnet_napi_enable(&vi->rq[i]);
+			virtnet_napi_tx_enable(&vi->sq[i]);
 		}
 	}
 
@@ -6000,9 +6047,8 @@ err:
 
 	if (netif_running(dev)) {
 		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
-					       &vi->sq[i].napi);
+			virtnet_napi_enable(&vi->rq[i]);
+			virtnet_napi_tx_enable(&vi->sq[i]);
 		}
 	}
 	if (prog)
@@ -6409,8 +6455,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 	INIT_DELAYED_WORK(&vi->refill, refill_work);
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		vi->rq[i].pages = NULL;
-		netif_napi_add_weight(vi->dev, &vi->rq[i].napi, virtnet_poll,
-				      napi_weight);
+		netif_napi_add_config(vi->dev, &vi->rq[i].napi, virtnet_poll,
+				      i);
+		vi->rq[i].napi.weight = napi_weight;
 		netif_napi_add_tx_weight(vi->dev, &vi->sq[i].napi,
 					 virtnet_poll_tx,
 					 napi_tx ? napi_weight : 0);