[PATCH net v4] virtio_net: Fix error unwinding of XDP initialization

[PATCH net v4] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu]

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 helper functions of disable and enable queue pairs.
Use newly introduced disable helper function in error unwinding and
virtnet_close. Use enable helper function in virtnet_open.

Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info")
Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---

v3 -> v4
feedbacks from Jiri Pirko
- Add symmetric helper function virtnet_enable_qp to enable queues.
- Error handle:  cleanup current queue pair in virtnet_enable_qp,
  and complete the reset queue pairs cleanup in virtnet_open.
- Fix coding style.
feedbacks from Parav Pandit
- Remove redundant debug message and white space.

v2 -> v3
feedbacks from Michael S. Tsirkin
- Remove redundant comment.

v1 -> v2
feedbacks from Michael S. Tsirkin
- squash two patches together.

---
 drivers/net/virtio_net.c | 58 ++++++++++++++++++++++++++++------------
 1 file changed, 41 insertions(+), 17 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 8d8038538fc4..df7c08048fa7 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1868,6 +1868,38 @@ 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_enable_qp(struct virtnet_info *vi, int qp_index)
+{
+	struct net_device *dev = vi->dev;
+	int err;
+
+	err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index,
+			       vi->rq[qp_index].napi.napi_id);
+	if (err < 0)
+		return err;
+
+	err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq,
+					 MEM_TYPE_PAGE_SHARED, NULL);
+	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);
+
+	return 0;
+
+err_xdp_reg_mem_model:
+	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
+	return err;
+}
+
 static int virtnet_open(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
@@ -1881,22 +1913,17 @@ static int virtnet_open(struct net_device *dev)
 			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
 				schedule_delayed_work(&vi->refill, 0);
 
-		err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id);
+		err = virtnet_enable_qp(vi, i);
 		if (err < 0)
-			return err;
-
-		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;
-		}
-
-		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-		virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi);
+			goto err_enable_qp;
 	}
 
 	return 0;
+
+err_enable_qp:
+	for (i--; i >= 0; i--)
+		virtnet_disable_qp(vi, i);
+	return err;
 }
 
 static int virtnet_poll_tx(struct napi_struct *napi, int budget)
@@ -2305,11 +2332,8 @@ 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)

Re: [PATCH net v4] virtio_net: Fix error unwinding of XDP initialization

[Michael S. Tsirkin]

On Mon, May 08, 2023 at 06:27:08PM -0400, Feng Liu 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 helper functions of disable and enable queue pairs.
> Use newly introduced disable helper function in error unwinding and
> virtnet_close. Use enable helper function in virtnet_open.
> 
> Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info")
> Signed-off-by: Feng Liu <feliu@nvidia.com>
> Reviewed-by: Jiri Pirko <jiri@nvidia.com>
> ---
> 
> v3 -> v4
> feedbacks from Jiri Pirko
> - Add symmetric helper function virtnet_enable_qp to enable queues.
> - Error handle:  cleanup current queue pair in virtnet_enable_qp,
>   and complete the reset queue pairs cleanup in virtnet_open.
> - Fix coding style.
> feedbacks from Parav Pandit
> - Remove redundant debug message and white space.
> 
> v2 -> v3
> feedbacks from Michael S. Tsirkin
> - Remove redundant comment.
> 
> v1 -> v2
> feedbacks from Michael S. Tsirkin
> - squash two patches together.
> 
> ---
>  drivers/net/virtio_net.c | 58 ++++++++++++++++++++++++++++------------
>  1 file changed, 41 insertions(+), 17 deletions(-)
> 
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 8d8038538fc4..df7c08048fa7 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -1868,6 +1868,38 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
>  	return received;
>  }
>  
> +static void virtnet_disable_qp(struct virtnet_info *vi, int qp_index)


I am guessing _qp stands for queue pair? Let's call it
virtnet_disable_queue_pair please, consistently with max_queue_pairs.

> +{
> +	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_enable_qp(struct virtnet_info *vi, int qp_index)

Similarly, virtnet_enable_queue_pair

> +{
> +	struct net_device *dev = vi->dev;
> +	int err;
> +
> +	err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index,
> +			       vi->rq[qp_index].napi.napi_id);
> +	if (err < 0)
> +		return err;
> +
> +	err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq,
> +					 MEM_TYPE_PAGE_SHARED, NULL);
> +	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);
> +
> +	return 0;
> +
> +err_xdp_reg_mem_model:
> +	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
> +	return err;
> +}
> +
>  static int virtnet_open(struct net_device *dev)
>  {
>  	struct virtnet_info *vi = netdev_priv(dev);
> @@ -1881,22 +1913,17 @@ static int virtnet_open(struct net_device *dev)
>  			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
>  				schedule_delayed_work(&vi->refill, 0);
>  
> -		err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id);
> +		err = virtnet_enable_qp(vi, i);
>  		if (err < 0)
> -			return err;
> -
> -		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;
> -		}
> -
> -		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
> -		virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi);
> +			goto err_enable_qp;
>  	}
>  
>  	return 0;
> +
> +err_enable_qp:
> +	for (i--; i >= 0; i--)
> +		virtnet_disable_qp(vi, i);
> +	return err;
>  }
>  
>  static int virtnet_poll_tx(struct napi_struct *napi, int budget)
> @@ -2305,11 +2332,8 @@ 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)

Re: [PATCH net v4] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu]

On 2023-05-09 a.m.12:42, Michael S. Tsirkin wrote:
> External email: Use caution opening links or attachments
> 
> 
> On Mon, May 08, 2023 at 06:27:08PM -0400, Feng Liu 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 helper functions of disable and enable queue pairs.
>> Use newly introduced disable helper function in error unwinding and
>> virtnet_close. Use enable helper function in virtnet_open.
>>
>> Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info")
>> Signed-off-by: Feng Liu <feliu@nvidia.com>
>> Reviewed-by: Jiri Pirko <jiri@nvidia.com>
>> ---
>>
>> v3 -> v4
>> feedbacks from Jiri Pirko
>> - Add symmetric helper function virtnet_enable_qp to enable queues.
>> - Error handle:  cleanup current queue pair in virtnet_enable_qp,
>>    and complete the reset queue pairs cleanup in virtnet_open.
>> - Fix coding style.
>> feedbacks from Parav Pandit
>> - Remove redundant debug message and white space.
>>
>> v2 -> v3
>> feedbacks from Michael S. Tsirkin
>> - Remove redundant comment.
>>
>> v1 -> v2
>> feedbacks from Michael S. Tsirkin
>> - squash two patches together.
>>
>> ---
>>   drivers/net/virtio_net.c | 58 ++++++++++++++++++++++++++++------------
>>   1 file changed, 41 insertions(+), 17 deletions(-)
>>
>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>> index 8d8038538fc4..df7c08048fa7 100644
>> --- a/drivers/net/virtio_net.c
>> +++ b/drivers/net/virtio_net.c
>> @@ -1868,6 +1868,38 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
>>        return received;
>>   }
>>
>> +static void virtnet_disable_qp(struct virtnet_info *vi, int qp_index)
> 
> 
> I am guessing _qp stands for queue pair? Let's call it
> virtnet_disable_queue_pair please, consistently with max_queue_pairs.
> 
Yes, qp stands for queue pair
will do, thanks

>> +{
>> +     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_enable_qp(struct virtnet_info *vi, int qp_index)
> 
> Similarly, virtnet_enable_queue_pair
> 
will do, thanks

>> +{
>> +     struct net_device *dev = vi->dev;
>> +     int err;
>> +
>> +     err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index,
>> +                            vi->rq[qp_index].napi.napi_id);
>> +     if (err < 0)
>> +             return err;
>> +
>> +     err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq,
>> +                                      MEM_TYPE_PAGE_SHARED, NULL);
>> +     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);
>> +
>> +     return 0;
>> +
>> +err_xdp_reg_mem_model:
>> +     xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
>> +     return err;
>> +}
>> +
>>   static int virtnet_open(struct net_device *dev)
>>   {
>>        struct virtnet_info *vi = netdev_priv(dev);
>> @@ -1881,22 +1913,17 @@ static int virtnet_open(struct net_device *dev)
>>                        if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
>>                                schedule_delayed_work(&vi->refill, 0);
>>
>> -             err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id);
>> +             err = virtnet_enable_qp(vi, i);
>>                if (err < 0)
>> -                     return err;
>> -
>> -             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;
>> -             }
>> -
>> -             virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
>> -             virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi);
>> +                     goto err_enable_qp;
>>        }
>>
>>        return 0;
>> +
>> +err_enable_qp:
>> +     for (i--; i >= 0; i--)
>> +             virtnet_disable_qp(vi, i);
>> +     return err;
>>   }
>>
>>   static int virtnet_poll_tx(struct napi_struct *napi, int budget)
>> @@ -2305,11 +2332,8 @@ 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)
> 

Re: [PATCH net v4] virtio_net: Fix error unwinding of XDP initialization

[Michal Kubiak]

On Mon, May 08, 2023 at 06:27:08PM -0400, Feng Liu 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 helper functions of disable and enable queue pairs.
> Use newly introduced disable helper function in error unwinding and
> virtnet_close. Use enable helper function in virtnet_open.
> 
> Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info")
> Signed-off-by: Feng Liu <feliu@nvidia.com>
> Reviewed-by: Jiri Pirko <jiri@nvidia.com>
> ---
> 
> v3 -> v4
> feedbacks from Jiri Pirko
> - Add symmetric helper function virtnet_enable_qp to enable queues.
> - Error handle:  cleanup current queue pair in virtnet_enable_qp,
>   and complete the reset queue pairs cleanup in virtnet_open.
> - Fix coding style.
> feedbacks from Parav Pandit
> - Remove redundant debug message and white space.
> 
> v2 -> v3
> feedbacks from Michael S. Tsirkin
> - Remove redundant comment.
> 
> v1 -> v2
> feedbacks from Michael S. Tsirkin
> - squash two patches together.
> 
> ---
>  drivers/net/virtio_net.c | 58 ++++++++++++++++++++++++++++------------
>  1 file changed, 41 insertions(+), 17 deletions(-)
> 
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 8d8038538fc4..df7c08048fa7 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -1868,6 +1868,38 @@ 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_enable_qp(struct virtnet_info *vi, int qp_index)
> +{
> +	struct net_device *dev = vi->dev;
> +	int err;
> +
> +	err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index,
> +			       vi->rq[qp_index].napi.napi_id);
> +	if (err < 0)
> +		return err;
> +
> +	err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq,
> +					 MEM_TYPE_PAGE_SHARED, NULL);
> +	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);
> +
> +	return 0;
> +
> +err_xdp_reg_mem_model:
> +	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);

Is it really necessary to call 'xdp_rxq_info_unreg()' from here?
It seems there is a risk of calling that function twice if 'xdp_rxq_info_reg_mem_model()" fails.

For example in the following scenario:
	1. We call 'virtnet_enable_qp()' from 'virtnet_open()'
	2. 'xdp_rxq_info_reg()' succeeds.
	3. 'xdp_rxq_info_reg_mem_model()' fails, so we go to the label "err_xdp_info_reg_mem_model".
	4. 'xdp_rxq_info_unreg()' is called.
	5. Register state of 'xdp_rxq' changes to 'REG_STATE_UNREGISTERED'.
	6. 'virtnet_enable_qp()' returns an error.
	7. In 'virtnet_open()' we go to the "err_enable_qp" label.
	8. 'virtnet_disable_qp()' is called.
	9. 'xdp_rxq_info_unreg()' is called for the second time on the xdp_rxq which is already
	   in state 'REG_STATE_UNREGISTERED'.
	10. The following warning from 'xdp_rxq_info_unreg_mem_model' can be displayed:

		if (xdp_rxq->reg_state != REG_STATE_REGISTERED)
		{
			WARN(1, "Missing register, driver bug");
			return;
		}

I think the 'xdp_rxq_info_unreg()' can be called only once for the same 'xdp_rxq'.
I believe we should either:
	- remove that call from 'virtnet_enable_qp()',
	- or use the following API in 'virtnet_disable_qp()':
		'xdp_rxq_info_is_reg()'
	     to check if the xdp_rxq is actually registered.

Thanks,
Michal

> +	return err;
> +}
> +
>  static int virtnet_open(struct net_device *dev)
>  {
>  	struct virtnet_info *vi = netdev_priv(dev);
> @@ -1881,22 +1913,17 @@ static int virtnet_open(struct net_device *dev)
>  			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
>  				schedule_delayed_work(&vi->refill, 0);
>  
> -		err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id);
> +		err = virtnet_enable_qp(vi, i);
>  		if (err < 0)
> -			return err;
> -
> -		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;
> -		}
> -
> -		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
> -		virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi);
> +			goto err_enable_qp;
>  	}
>  
>  	return 0;
> +
> +err_enable_qp:
> +	for (i--; i >= 0; i--)
> +		virtnet_disable_qp(vi, i);
> +	return err;
>  }
>  
>  static int virtnet_poll_tx(struct napi_struct *napi, int budget)
> @@ -2305,11 +2332,8 @@ 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)
> 
>