On Tue, Jun 25, 2024 at 09:27:38AM +0800, Jason Wang wrote:

On Mon, Jun 24, 2024 at 6:07 PM Michael S. Tsirkin [off-list ref] wrote:

quoted

On Mon, Jun 24, 2024 at 10:45:23AM +0800, Jason Wang wrote:

quoted

This patch synchronize operstate with admin state per RFC2863.

This is done by trying to toggle the carrier upon open/close and
synchronize with the config change work. This allows propagate status
correctly to stacked devices like:

ip link add link enp0s3 macvlan0 type macvlan
ip link set link enp0s3 down
ip link show

Before this patch:

3: enp0s3: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000
    link/ether 00:00:05:00:00:09 brd ff:ff:ff:ff:ff:ff
......
5: macvlan0@enp0s3: <BROADCAST,MULTICAST,UP,LOWER_UP,M-DOWN> mtu 1500 qdisc noqueue state UP mode DEFAULT group default qlen 1000
    link/ether b2:a9:c5:04:da:53 brd ff:ff:ff:ff:ff:ff

After this patch:

3: enp0s3: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000
    link/ether 00:00:05:00:00:09 brd ff:ff:ff:ff:ff:ff
...
5: macvlan0@enp0s3: <NO-CARRIER,BROADCAST,MULTICAST,UP,M-DOWN> mtu 1500 qdisc noqueue state LOWERLAYERDOWN mode DEFAULT group default qlen 1000
    link/ether b2:a9:c5:04:da:53 brd ff:ff:ff:ff:ff:ff

Cc: Venkat Venkatsubra <redacted>
Cc: Gia-Khanh Nguyen <redacted>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/net/virtio_net.c | 72 +++++++++++++++++++++++-----------------
 1 file changed, 42 insertions(+), 30 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b1f8b720733e..eff3ad3d6bcc 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c

@@ -2468,6 +2468,25 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
      return err;
 }

+static void virtnet_update_settings(struct virtnet_info *vi)
+{
+     u32 speed;
+     u8 duplex;
+
+     if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX))
+             return;
+
+     virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed);
+
+     if (ethtool_validate_speed(speed))
+             vi->speed = speed;
+
+     virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex);
+
+     if (ethtool_validate_duplex(duplex))
+             vi->duplex = duplex;
+}
+
 static int virtnet_open(struct net_device *dev)
 {
      struct virtnet_info *vi = netdev_priv(dev);

@@ -2486,6 +2505,22 @@ static int virtnet_open(struct net_device *dev)
                      goto err_enable_qp;
      }

+     /* Assume link up if device can't report link status,
+        otherwise get link status from config. */
+     netif_carrier_off(dev);
+     if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
+             virtio_config_enable(vi->vdev);
+             /* We are not sure if config interrupt is disabled by
+              * core or not, so we can't schedule config_work by
+              * ourselves.
+              */

This comment confuses more than it explains.
You seem to be arguing about some alternative design
you had in mind, but readers don't have it in mind.


Please just explain what this does and why.
For what: something like "Trigger re-read of config - same
as we'd do if config changed".

Now, please do what you don't do here: explain the why:


why do we want all these VM
exits on each open/close as opposed to once on probe and later on
config changed interrupt.

Fine, the main reason is that a config interrupt might be pending
during ifdown and core may disable configure interrupt due to several
reasons.

Thanks

If the config changes exactly as command is executing?
Then we'll get an interrupt later and update.
You can't always win this race, even if you read it can
change right after.

quoted

quoted

+             virtio_config_changed(vi->vdev);
+     } else {
+             vi->status = VIRTIO_NET_S_LINK_UP;
+             virtnet_update_settings(vi);
+             netif_carrier_on(dev);
+     }
+
      return 0;

 err_enable_qp:

@@ -2928,12 +2963,19 @@ static int virtnet_close(struct net_device *dev)
      disable_delayed_refill(vi);
      /* Make sure refill_work doesn't re-enable napi! */
      cancel_delayed_work_sync(&vi->refill);
+     /* Make sure config notification doesn't schedule config work */
+     virtio_config_disable(vi->vdev);
+     /* Make sure status updating is cancelled */
+     cancel_work_sync(&vi->config_work);

      for (i = 0; i < vi->max_queue_pairs; i++) {
              virtnet_disable_queue_pair(vi, i);
              cancel_work_sync(&vi->rq[i].dim.work);
      }

+     vi->status &= ~VIRTIO_NET_S_LINK_UP;
+     netif_carrier_off(dev);
+
      return 0;
 }

@@ -4632,25 +4674,6 @@ static void virtnet_init_settings(struct net_device *dev)
      vi->duplex = DUPLEX_UNKNOWN;
 }

-static void virtnet_update_settings(struct virtnet_info *vi)
-{
-     u32 speed;
-     u8 duplex;
-
-     if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX))
-             return;
-
-     virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed);
-
-     if (ethtool_validate_speed(speed))
-             vi->speed = speed;
-
-     virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex);
-
-     if (ethtool_validate_duplex(duplex))
-             vi->duplex = duplex;
-}
-
 static u32 virtnet_get_rxfh_key_size(struct net_device *dev)
 {
      return ((struct virtnet_info *)netdev_priv(dev))->rss_key_size;

@@ -5958,17 +5981,6 @@ static int virtnet_probe(struct virtio_device *vdev)
              goto free_unregister_netdev;
      }

-     /* Assume link up if device can't report link status,
-        otherwise get link status from config. */
-     netif_carrier_off(dev);
-     if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
-             schedule_work(&vi->config_work);
-     } else {
-             vi->status = VIRTIO_NET_S_LINK_UP;
-             virtnet_update_settings(vi);
-             netif_carrier_on(dev);
-     }
-
      for (i = 0; i < ARRAY_SIZE(guest_offloads); i++)
              if (virtio_has_feature(vi->vdev, guest_offloads[i]))
                      set_bit(guest_offloads[i], &vi->guest_offloads);
--

2.31.1