Re: [PATCH net-next V2 1/2] virtio-net: convert rx mode setting to use workqueue

[Jason Wang <jasowang@redhat.com>]

在 2023/4/17 11:40, Jason Wang 写道:
> On Fri, Apr 14, 2023 at 3:21 PM Michael S. Tsirkin <mst@redhat.com> wrote:
>> On Fri, Apr 14, 2023 at 01:04:15PM +0800, Jason Wang wrote:
>>> Forget to cc netdev, adding.
>>>
>>> On Fri, Apr 14, 2023 at 12:25 AM Michael S. Tsirkin <mst@redhat.com> wrote:
>>>> On Thu, Apr 13, 2023 at 02:40:26PM +0800, Jason Wang wrote:
>>>>> This patch convert rx mode setting to be done in a workqueue, this is
>>>>> a must for allow to sleep when waiting for the cvq command to
>>>>> response since current code is executed under addr spin lock.
>>>>>
>>>>> Signed-off-by: Jason Wang <jasowang@redhat.com>
>>>> I don't like this frankly. This means that setting RX mode which would
>>>> previously be reliable, now becomes unreliable.
>>> It is "unreliable" by design:
>>>
>>>        void                    (*ndo_set_rx_mode)(struct net_device *dev);
>>>
>>>> - first of all configuration is no longer immediate
>>> Is immediate a hard requirement? I can see a workqueue is used at least:
>>>
>>> mlx5e, ipoib, efx, ...
>>>
>>>>    and there is no way for driver to find out when
>>>>    it actually took effect
>>> But we know rx mode is best effort e.g it doesn't support vhost and we
>>> survive from this for years.
>>>
>>>> - second, if device fails command, this is also not
>>>>    propagated to driver, again no way for driver to find out
>>>>
>>>> VDUSE needs to be fixed to do tricks to fix this
>>>> without breaking normal drivers.
>>> It's not specific to VDUSE. For example, when using virtio-net in the
>>> UP environment with any software cvq (like mlx5 via vDPA or cma
>>> transport).
>>>
>>> Thanks
>> Hmm. Can we differentiate between these use-cases?
> It doesn't look easy since we are drivers for virtio bus. Underlayer
> details were hidden from virtio-net.
>
> Or do you have any ideas on this?


Michael, any thought on this?

Thanks


>
> Thanks
>
>>>>
>>>>> ---
>>>>> Changes since V1:
>>>>> - use RTNL to synchronize rx mode worker
>>>>> ---
>>>>>   drivers/net/virtio_net.c | 55 +++++++++++++++++++++++++++++++++++++---
>>>>>   1 file changed, 52 insertions(+), 3 deletions(-)
>>>>>
>>>>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>>>>> index e2560b6f7980..2e56bbf86894 100644
>>>>> --- a/drivers/net/virtio_net.c
>>>>> +++ b/drivers/net/virtio_net.c
>>>>> @@ -265,6 +265,12 @@ struct virtnet_info {
>>>>>        /* Work struct for config space updates */
>>>>>        struct work_struct config_work;
>>>>>
>>>>> +     /* Work struct for config rx mode */
>>>>> +     struct work_struct rx_mode_work;
>>>>> +
>>>>> +     /* Is rx mode work enabled? */
>>>>> +     bool rx_mode_work_enabled;
>>>>> +
>>>>>        /* Does the affinity hint is set for virtqueues? */
>>>>>        bool affinity_hint_set;
>>>>>
>>>>> @@ -388,6 +394,20 @@ static void disable_delayed_refill(struct virtnet_info *vi)
>>>>>        spin_unlock_bh(&vi->refill_lock);
>>>>>   }
>>>>>
>>>>> +static void enable_rx_mode_work(struct virtnet_info *vi)
>>>>> +{
>>>>> +     rtnl_lock();
>>>>> +     vi->rx_mode_work_enabled = true;
>>>>> +     rtnl_unlock();
>>>>> +}
>>>>> +
>>>>> +static void disable_rx_mode_work(struct virtnet_info *vi)
>>>>> +{
>>>>> +     rtnl_lock();
>>>>> +     vi->rx_mode_work_enabled = false;
>>>>> +     rtnl_unlock();
>>>>> +}
>>>>> +
>>>>>   static void virtqueue_napi_schedule(struct napi_struct *napi,
>>>>>                                    struct virtqueue *vq)
>>>>>   {
>>>>> @@ -2310,9 +2330,11 @@ static int virtnet_close(struct net_device *dev)
>>>>>        return 0;
>>>>>   }
>>>>>
>>>>> -static void virtnet_set_rx_mode(struct net_device *dev)
>>>>> +static void virtnet_rx_mode_work(struct work_struct *work)
>>>>>   {
>>>>> -     struct virtnet_info *vi = netdev_priv(dev);
>>>>> +     struct virtnet_info *vi =
>>>>> +             container_of(work, struct virtnet_info, rx_mode_work);
>>>>> +     struct net_device *dev = vi->dev;
>>>>>        struct scatterlist sg[2];
>>>>>        struct virtio_net_ctrl_mac *mac_data;
>>>>>        struct netdev_hw_addr *ha;
>>>>> @@ -2325,6 +2347,8 @@ static void virtnet_set_rx_mode(struct net_device *dev)
>>>>>        if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
>>>>>                return;
>>>>>
>>>>> +     rtnl_lock();
>>>>> +
>>>>>        vi->ctrl->promisc = ((dev->flags & IFF_PROMISC) != 0);
>>>>>        vi->ctrl->allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
>>>>>
>>>>> @@ -2342,14 +2366,19 @@ static void virtnet_set_rx_mode(struct net_device *dev)
>>>>>                dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
>>>>>                         vi->ctrl->allmulti ? "en" : "dis");
>>>>>
>>>>> +     netif_addr_lock_bh(dev);
>>>>> +
>>>>>        uc_count = netdev_uc_count(dev);
>>>>>        mc_count = netdev_mc_count(dev);
>>>>>        /* MAC filter - use one buffer for both lists */
>>>>>        buf = kzalloc(((uc_count + mc_count) * ETH_ALEN) +
>>>>>                      (2 * sizeof(mac_data->entries)), GFP_ATOMIC);
>>>>>        mac_data = buf;
>>>>> -     if (!buf)
>>>>> +     if (!buf) {
>>>>> +             netif_addr_unlock_bh(dev);
>>>>> +             rtnl_unlock();
>>>>>                return;
>>>>> +     }
>>>>>
>>>>>        sg_init_table(sg, 2);
>>>>>
>>>>> @@ -2370,6 +2399,8 @@ static void virtnet_set_rx_mode(struct net_device *dev)
>>>>>        netdev_for_each_mc_addr(ha, dev)
>>>>>                memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);
>>>>>
>>>>> +     netif_addr_unlock_bh(dev);
>>>>> +
>>>>>        sg_set_buf(&sg[1], mac_data,
>>>>>                   sizeof(mac_data->entries) + (mc_count * ETH_ALEN));
>>>>>
>>>>> @@ -2377,9 +2408,19 @@ static void virtnet_set_rx_mode(struct net_device *dev)
>>>>>                                  VIRTIO_NET_CTRL_MAC_TABLE_SET, sg))
>>>>>                dev_warn(&dev->dev, "Failed to set MAC filter table.\n");
>>>>>
>>>>> +     rtnl_unlock();
>>>>> +
>>>>>        kfree(buf);
>>>>>   }
>>>>>
>>>>> +static void virtnet_set_rx_mode(struct net_device *dev)
>>>>> +{
>>>>> +     struct virtnet_info *vi = netdev_priv(dev);
>>>>> +
>>>>> +     if (vi->rx_mode_work_enabled)
>>>>> +             schedule_work(&vi->rx_mode_work);
>>>>> +}
>>>>> +
>>>>>   static int virtnet_vlan_rx_add_vid(struct net_device *dev,
>>>>>                                   __be16 proto, u16 vid)
>>>>>   {
>>>>> @@ -3150,6 +3191,8 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
>>>>>
>>>>>        /* Make sure no work handler is accessing the device */
>>>>>        flush_work(&vi->config_work);
>>>>> +     disable_rx_mode_work(vi);
>>>>> +     flush_work(&vi->rx_mode_work);
>>>>>
>>>>>        netif_tx_lock_bh(vi->dev);
>>>>>        netif_device_detach(vi->dev);
>>>> So now configuration is not propagated to device.
>>>> Won't device later wake up in wrong state?
>>>>
>>>>
>>>>> @@ -3172,6 +3215,7 @@ static int virtnet_restore_up(struct virtio_device *vdev)
>>>>>        virtio_device_ready(vdev);
>>>>>
>>>>>        enable_delayed_refill(vi);
>>>>> +     enable_rx_mode_work(vi);
>>>>>
>>>>>        if (netif_running(vi->dev)) {
>>>>>                err = virtnet_open(vi->dev);
>>>>> @@ -3969,6 +4013,7 @@ static int virtnet_probe(struct virtio_device *vdev)
>>>>>        vdev->priv = vi;
>>>>>
>>>>>        INIT_WORK(&vi->config_work, virtnet_config_changed_work);
>>>>> +     INIT_WORK(&vi->rx_mode_work, virtnet_rx_mode_work);
>>>>>        spin_lock_init(&vi->refill_lock);
>>>>>
>>>>>        if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) {
>>>>> @@ -4077,6 +4122,8 @@ static int virtnet_probe(struct virtio_device *vdev)
>>>>>        if (vi->has_rss || vi->has_rss_hash_report)
>>>>>                virtnet_init_default_rss(vi);
>>>>>
>>>>> +     enable_rx_mode_work(vi);
>>>>> +
>>>>>        /* serialize netdev register + virtio_device_ready() with ndo_open() */
>>>>>        rtnl_lock();
>>>>>
>>>>> @@ -4174,6 +4221,8 @@ static void virtnet_remove(struct virtio_device *vdev)
>>>>>
>>>>>        /* Make sure no work handler is accessing the device. */
>>>>>        flush_work(&vi->config_work);
>>>>> +     disable_rx_mode_work(vi);
>>>>> +     flush_work(&vi->rx_mode_work);
>>>>>
>>>>>        unregister_netdev(vi->dev);
>>>>>
>>>>> --
>>>>> 2.25.1