Virtualization - May 2023 - [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

On Tue, 2 May 2023 20:35:25 -0400, Feng Liu <feliu at nvidia.com>
wrote:
> When initializing XDP in virtnet_open(), some rq xdp initialization
> may hit an error causing net device open failed. However, previous
> rqs have already initialized XDP and enabled NAPI, which is not the
> expected behavior. Need to roll back the previous rq initialization
> to avoid leaks in error unwinding of init code.
>
> Also extract a helper function of disable queue pairs, and use newly
> introduced helper function in error unwinding and virtnet_close;
>
> Issue: 3383038
> Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info")
> Signed-off-by: Feng Liu <feliu at nvidia.com>
> Reviewed-by: William Tu <witu at nvidia.com>
> Reviewed-by: Parav Pandit <parav at nvidia.com>
> Reviewed-by: Simon Horman <simon.horman at corigine.com>
> Acked-by: Michael S. Tsirkin <mst at redhat.com>
> Change-Id: Ib4c6a97cb7b837cfa484c593dd43a435c47ea68f
> ---
>  drivers/net/virtio_net.c | 30 ++++++++++++++++++++----------
>  1 file changed, 20 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 8d8038538fc4..3737cf120cb7 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -1868,6 +1868,13 @@ static int virtnet_poll(struct napi_struct *napi,
int budget)
>  	return received;
>  }
>
> +static void virtnet_disable_qp(struct virtnet_info *vi, int qp_index)
> +{
> +	virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
> +	napi_disable(&vi->rq[qp_index].napi);
> +	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
> +}
> +
>  static int virtnet_open(struct net_device *dev)
>  {
>  	struct virtnet_info *vi = netdev_priv(dev);
> @@ -1883,20 +1890,26 @@ static int virtnet_open(struct net_device *dev)
>
>  		err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i,
vi->rq[i].napi.napi_id);
>  		if (err < 0)
> -			return err;
> +			goto err_xdp_info_reg;
>
>  		err = xdp_rxq_info_reg_mem_model(&vi->rq[i].xdp_rxq,
>  						 MEM_TYPE_PAGE_SHARED, NULL);
> -		if (err < 0) {
> -			xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
> -			return err;
> -		}
> +		if (err < 0)
> +			goto err_xdp_reg_mem_model;
>
>  		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
>  		virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi);
>  	}
>
>  	return 0;
> +
> +err_xdp_reg_mem_model:
> +	xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
> +err_xdp_info_reg:
> +	for (i = i - 1; i >= 0; i--)
> +		virtnet_disable_qp(vi, i);

I would to know should we handle for these:

	disable_delayed_refill(vi);
	cancel_delayed_work_sync(&vi->refill);


Maybe we should call virtnet_close() with "i" directly.

Thanks.

> +
> +	return err;
>  }
>
>  static int virtnet_poll_tx(struct napi_struct *napi, int budget)
> @@ -2305,11 +2318,8 @@ static int virtnet_close(struct net_device *dev)
>  	/* Make sure refill_work doesn't re-enable napi! */
>  	cancel_delayed_work_sync(&vi->refill);
>
> -	for (i = 0; i < vi->max_queue_pairs; i++) {
> -		virtnet_napi_tx_disable(&vi->sq[i].napi);
> -		napi_disable(&vi->rq[i].napi);
> -		xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
> -	}
> +	for (i = 0; i < vi->max_queue_pairs; i++)
> +		virtnet_disable_qp(vi, i);
>
>  	return 0;
>  }
> --
> 2.37.1 (Apple Git-137.1)
>

On 2023-05-05 p.m.10:33, Xuan Zhuo wrote:
> External email: Use caution opening links or attachments
> 
> 
> On Tue, 2 May 2023 20:35:25 -0400, Feng Liu <feliu at nvidia.com>
wrote:
>> When initializing XDP in virtnet_open(), some rq xdp initialization
>> may hit an error causing net device open failed. However, previous
>> rqs have already initialized XDP and enabled NAPI, which is not the
>> expected behavior. Need to roll back the previous rq initialization
>> to avoid leaks in error unwinding of init code.
>>
>> Also extract a helper function of disable queue pairs, and use newly
>> introduced helper function in error unwinding and virtnet_close;
>>
>> Issue: 3383038
>> Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info")
>> Signed-off-by: Feng Liu <feliu at nvidia.com>
>> Reviewed-by: William Tu <witu at nvidia.com>
>> Reviewed-by: Parav Pandit <parav at nvidia.com>
>> Reviewed-by: Simon Horman <simon.horman at corigine.com>
>> Acked-by: Michael S. Tsirkin <mst at redhat.com>
>> Change-Id: Ib4c6a97cb7b837cfa484c593dd43a435c47ea68f
>> ---
>>   drivers/net/virtio_net.c | 30 ++++++++++++++++++++----------
>>   1 file changed, 20 insertions(+), 10 deletions(-)
>>
>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>> index 8d8038538fc4..3737cf120cb7 100644
>> --- a/drivers/net/virtio_net.c
>> +++ b/drivers/net/virtio_net.c
>> @@ -1868,6 +1868,13 @@ static int virtnet_poll(struct napi_struct
*napi, int budget)
>>        return received;
>>   }
>>
>> +static void virtnet_disable_qp(struct virtnet_info *vi, int qp_index)
>> +{
>> +     virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
>> +     napi_disable(&vi->rq[qp_index].napi);
>> +     xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
>> +}
>> +
>>   static int virtnet_open(struct net_device *dev)
>>   {
>>        struct virtnet_info *vi = netdev_priv(dev);
>> @@ -1883,20 +1890,26 @@ static int virtnet_open(struct net_device *dev)
>>
>>                err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev,
i, vi->rq[i].napi.napi_id);
>>                if (err < 0)
>> -                     return err;
>> +                     goto err_xdp_info_reg;
>>
>>                err =
xdp_rxq_info_reg_mem_model(&vi->rq[i].xdp_rxq,
>>                                                 MEM_TYPE_PAGE_SHARED,
NULL);
>> -             if (err < 0) {
>> -                     xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
>> -                     return err;
>> -             }
>> +             if (err < 0)
>> +                     goto err_xdp_reg_mem_model;
>>
>>                virtnet_napi_enable(vi->rq[i].vq,
&vi->rq[i].napi);
>>                virtnet_napi_tx_enable(vi, vi->sq[i].vq,
&vi->sq[i].napi);
>>        }
>>
>>        return 0;
>> +
>> +err_xdp_reg_mem_model:
>> +     xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
>> +err_xdp_info_reg:
>> +     for (i = i - 1; i >= 0; i--)
>> +             virtnet_disable_qp(vi, i);
> 
> 
> I would to know should we handle for these:
> 
>          disable_delayed_refill(vi);
>          cancel_delayed_work_sync(&vi->refill);
> 
> 
> Maybe we should call virtnet_close() with "i" directly.
> 
> Thanks.
> 
> 
Can?t use i directly here, because if xdp_rxq_info_reg fails, napi has 
not been enabled for current qp yet, I should roll back from the queue 
pairs where napi was enabled before(i--), otherwise it will hang at napi 
disable api
>> +
>> +     return err;
>>   }
>>
>>   static int virtnet_poll_tx(struct napi_struct *napi, int budget)
>> @@ -2305,11 +2318,8 @@ static int virtnet_close(struct net_device *dev)
>>        /* Make sure refill_work doesn't re-enable napi! */
>>        cancel_delayed_work_sync(&vi->refill);
>>
>> -     for (i = 0; i < vi->max_queue_pairs; i++) {
>> -             virtnet_napi_tx_disable(&vi->sq[i].napi);
>> -             napi_disable(&vi->rq[i].napi);
>> -             xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
>> -     }
>> +     for (i = 0; i < vi->max_queue_pairs; i++)
>> +             virtnet_disable_qp(vi, i);
>>
>>        return 0;
>>   }
>> --
>> 2.37.1 (Apple Git-137.1)
>>