[PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[PATCH net v3] 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 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@nvidia.com>
Reviewed-by: William Tu <witu@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Acked-by: Michael S. Tsirkin <mst@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);
+
+	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)

[PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu via Virtualization]

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@nvidia.com>
Reviewed-by: William Tu <witu@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Acked-by: Michael S. Tsirkin <mst@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);
+
+	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)

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

RE: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Parav Pandit]

> From: Feng Liu <feliu@nvidia.com>
> Sent: Tuesday, May 2, 2023 8:35 PM

> Issue: 3383038
Remove this internal garbage.

> Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info")
> Signed-off-by: Feng Liu <feliu@nvidia.com>
> Reviewed-by: William Tu <witu@nvidia.com>
> Reviewed-by: Parav Pandit <parav@nvidia.com>
> Reviewed-by: Simon Horman <simon.horman@corigine.com>
> Acked-by: Michael S. Tsirkin <mst@redhat.com>

> Change-Id: Ib4c6a97cb7b837cfa484c593dd43a435c47ea68f
Remove this internal garbage.
Please run a local script not to forward the above garbage in upstream patches.

You are missing the changelog from v0->v1->v2->v3.
Please add and resend with above things removed and with changelog.

RE: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Parav Pandit via Virtualization]

> From: Feng Liu <feliu@nvidia.com>
> Sent: Tuesday, May 2, 2023 8:35 PM

> Issue: 3383038
Remove this internal garbage.

> Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info")
> Signed-off-by: Feng Liu <feliu@nvidia.com>
> Reviewed-by: William Tu <witu@nvidia.com>
> Reviewed-by: Parav Pandit <parav@nvidia.com>
> Reviewed-by: Simon Horman <simon.horman@corigine.com>
> Acked-by: Michael S. Tsirkin <mst@redhat.com>

> Change-Id: Ib4c6a97cb7b837cfa484c593dd43a435c47ea68f
Remove this internal garbage.
Please run a local script not to forward the above garbage in upstream patches.

You are missing the changelog from v0->v1->v2->v3.
Please add and resend with above things removed and with changelog.
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu]

On 2023-05-02 p.m.11:14, Parav Pandit wrote:
> 
>> From: Feng Liu <feliu@nvidia.com>
>> Sent: Tuesday, May 2, 2023 8:35 PM
> 
>> Issue: 3383038
> Remove this internal garbage.
> 
>> Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info")
>> Signed-off-by: Feng Liu <feliu@nvidia.com>
>> Reviewed-by: William Tu <witu@nvidia.com>
>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>> Acked-by: Michael S. Tsirkin <mst@redhat.com>
> 
>> Change-Id: Ib4c6a97cb7b837cfa484c593dd43a435c47ea68f
> Remove this internal garbage.
> Please run a local script not to forward the above garbage in upstream patches.
> 
> You are missing the changelog from v0->v1->v2->v3.
> Please add and resend with above things removed and with changelog.
ok

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu via Virtualization]

On 2023-05-02 p.m.11:14, Parav Pandit wrote:
> 
>> From: Feng Liu <feliu@nvidia.com>
>> Sent: Tuesday, May 2, 2023 8:35 PM
> 
>> Issue: 3383038
> Remove this internal garbage.
> 
>> Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info")
>> Signed-off-by: Feng Liu <feliu@nvidia.com>
>> Reviewed-by: William Tu <witu@nvidia.com>
>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>> Acked-by: Michael S. Tsirkin <mst@redhat.com>
> 
>> Change-Id: Ib4c6a97cb7b837cfa484c593dd43a435c47ea68f
> Remove this internal garbage.
> Please run a local script not to forward the above garbage in upstream patches.
> 
> You are missing the changelog from v0->v1->v2->v3.
> Please add and resend with above things removed and with changelog.
ok
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Xuan Zhuo]

On Tue, 2 May 2023 20:35:25 -0400, Feng Liu <feliu@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@nvidia.com>
> Reviewed-by: William Tu <witu@nvidia.com>
> Reviewed-by: Parav Pandit <parav@nvidia.com>
> Reviewed-by: Simon Horman <simon.horman@corigine.com>
> Acked-by: Michael S. Tsirkin <mst@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)
>

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Xuan Zhuo]

On Tue, 2 May 2023 20:35:25 -0400, Feng Liu <feliu@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@nvidia.com>
> Reviewed-by: William Tu <witu@nvidia.com>
> Reviewed-by: Parav Pandit <parav@nvidia.com>
> Reviewed-by: Simon Horman <simon.horman@corigine.com>
> Acked-by: Michael S. Tsirkin <mst@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)
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu]

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@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@nvidia.com>
>> Reviewed-by: William Tu <witu@nvidia.com>
>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>> Acked-by: Michael S. Tsirkin <mst@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)
>>

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu via Virtualization]

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@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@nvidia.com>
>> Reviewed-by: William Tu <witu@nvidia.com>
>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>> Acked-by: Michael S. Tsirkin <mst@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)
>>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Xuan Zhuo]

On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
>
>
> 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@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@nvidia.com>
> >> Reviewed-by: William Tu <witu@nvidia.com>
> >> Reviewed-by: Parav Pandit <parav@nvidia.com>
> >> Reviewed-by: Simon Horman <simon.horman@corigine.com>
> >> Acked-by: Michael S. Tsirkin <mst@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

This is not the point, the key is whether we should handle with:

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

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)
> >>

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Xuan Zhuo]

On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
>
>
> 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@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@nvidia.com>
> >> Reviewed-by: William Tu <witu@nvidia.com>
> >> Reviewed-by: Parav Pandit <parav@nvidia.com>
> >> Reviewed-by: Simon Horman <simon.horman@corigine.com>
> >> Acked-by: Michael S. Tsirkin <mst@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

This is not the point, the key is whether we should handle with:

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

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)
> >>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu]

On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
> External email: Use caution opening links or attachments
> 
> 
> On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>
>>
>> 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@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@nvidia.com>
>>>> Reviewed-by: William Tu <witu@nvidia.com>
>>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>>>> Acked-by: Michael S. Tsirkin <mst@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
> 
> This is not the point, the key is whether we should handle with:
> 
>            disable_delayed_refill(vi);
>            cancel_delayed_work_sync(&vi->refill);
> 
> Thanks.
> 
> 

OK, get the point. Thanks for your careful review. And I check the code 
again.

There are two points that I need to explain:

1. All refill delay work calls(vi->refill, vi->refill_enabled) are based 
on that the virtio interface is successfully opened, such as 
virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there 
is an error in the xdp reg here, it will not trigger these subsequent 
functions. There is no need to call disable_delayed_refill() and 
cancel_delayed_work_sync(). The logic here is different from that of 
virtnet_close. virtnet_close is based on the success of virtnet_open and 
the tx and rx has been carried out normally. For error unwinding, only 
disable qp is needed. Also encapuslated a helper function of disable qp, 
which is used ing error unwinding and virtnet close
2. The current error qp, which has not enabled NAPI, can only call xdp 
unreg, and cannot call the interface of disable NAPI, otherwise the 
kernel will be stuck. So for i-- the reason for calling disable qp on 
the previous queue

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)
>>>>

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu via Virtualization]

On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
> External email: Use caution opening links or attachments
> 
> 
> On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>
>>
>> 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@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@nvidia.com>
>>>> Reviewed-by: William Tu <witu@nvidia.com>
>>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>>>> Acked-by: Michael S. Tsirkin <mst@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
> 
> This is not the point, the key is whether we should handle with:
> 
>            disable_delayed_refill(vi);
>            cancel_delayed_work_sync(&vi->refill);
> 
> Thanks.
> 
> 

OK, get the point. Thanks for your careful review. And I check the code 
again.

There are two points that I need to explain:

1. All refill delay work calls(vi->refill, vi->refill_enabled) are based 
on that the virtio interface is successfully opened, such as 
virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there 
is an error in the xdp reg here, it will not trigger these subsequent 
functions. There is no need to call disable_delayed_refill() and 
cancel_delayed_work_sync(). The logic here is different from that of 
virtnet_close. virtnet_close is based on the success of virtnet_open and 
the tx and rx has been carried out normally. For error unwinding, only 
disable qp is needed. Also encapuslated a helper function of disable qp, 
which is used ing error unwinding and virtnet close
2. The current error qp, which has not enabled NAPI, can only call xdp 
unreg, and cannot call the interface of disable NAPI, otherwise the 
kernel will be stuck. So for i-- the reason for calling disable qp on 
the previous queue

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)
>>>>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Xuan Zhuo]

On Mon, 8 May 2023 11:00:10 -0400, Feng Liu <feliu@nvidia.com> wrote:
>
>
> On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
> > External email: Use caution opening links or attachments
> >
> >
> > On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
> >>
> >>
> >> 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@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@nvidia.com>
> >>>> Reviewed-by: William Tu <witu@nvidia.com>
> >>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
> >>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
> >>>> Acked-by: Michael S. Tsirkin <mst@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
> >
> > This is not the point, the key is whether we should handle with:
> >
> >            disable_delayed_refill(vi);
> >            cancel_delayed_work_sync(&vi->refill);
> >
> > Thanks.
> >
> >
>
> OK, get the point. Thanks for your careful review. And I check the code
> again.
>
> There are two points that I need to explain:
>
> 1. All refill delay work calls(vi->refill, vi->refill_enabled) are based
> on that the virtio interface is successfully opened, such as
> virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there
> is an error in the xdp reg here, it will not trigger these subsequent
> functions. There is no need to call disable_delayed_refill() and
> cancel_delayed_work_sync().

Maybe something is wrong. I think these lines may call delay work.

static int virtnet_open(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);
	int i, err;

	enable_delayed_refill(vi);

	for (i = 0; i < vi->max_queue_pairs; i++) {
		if (i < vi->curr_queue_pairs)
			/* Make sure we have some buffers: if oom use wq. */
-->			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);
		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);
	}

	return 0;
}


And I think, if we virtnet_open() return error, then the status of virtnet
should like the status after virtnet_close().

Or someone has other opinion.

Thanks.

> The logic here is different from that of
> virtnet_close. virtnet_close is based on the success of virtnet_open and
> the tx and rx has been carried out normally. For error unwinding, only
> disable qp is needed. Also encapuslated a helper function of disable qp,
> which is used ing error unwinding and virtnet close
> 2. The current error qp, which has not enabled NAPI, can only call xdp
> unreg, and cannot call the interface of disable NAPI, otherwise the
> kernel will be stuck. So for i-- the reason for calling disable qp on
> the previous queue
>
> 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)
> >>>>

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Xuan Zhuo]

On Mon, 8 May 2023 11:00:10 -0400, Feng Liu <feliu@nvidia.com> wrote:
>
>
> On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
> > External email: Use caution opening links or attachments
> >
> >
> > On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
> >>
> >>
> >> 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@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@nvidia.com>
> >>>> Reviewed-by: William Tu <witu@nvidia.com>
> >>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
> >>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
> >>>> Acked-by: Michael S. Tsirkin <mst@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
> >
> > This is not the point, the key is whether we should handle with:
> >
> >            disable_delayed_refill(vi);
> >            cancel_delayed_work_sync(&vi->refill);
> >
> > Thanks.
> >
> >
>
> OK, get the point. Thanks for your careful review. And I check the code
> again.
>
> There are two points that I need to explain:
>
> 1. All refill delay work calls(vi->refill, vi->refill_enabled) are based
> on that the virtio interface is successfully opened, such as
> virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there
> is an error in the xdp reg here, it will not trigger these subsequent
> functions. There is no need to call disable_delayed_refill() and
> cancel_delayed_work_sync().

Maybe something is wrong. I think these lines may call delay work.

static int virtnet_open(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);
	int i, err;

	enable_delayed_refill(vi);

	for (i = 0; i < vi->max_queue_pairs; i++) {
		if (i < vi->curr_queue_pairs)
			/* Make sure we have some buffers: if oom use wq. */
-->			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);
		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);
	}

	return 0;
}


And I think, if we virtnet_open() return error, then the status of virtnet
should like the status after virtnet_close().

Or someone has other opinion.

Thanks.

> The logic here is different from that of
> virtnet_close. virtnet_close is based on the success of virtnet_open and
> the tx and rx has been carried out normally. For error unwinding, only
> disable qp is needed. Also encapuslated a helper function of disable qp,
> which is used ing error unwinding and virtnet close
> 2. The current error qp, which has not enabled NAPI, can only call xdp
> unreg, and cannot call the interface of disable NAPI, otherwise the
> kernel will be stuck. So for i-- the reason for calling disable qp on
> the previous queue
>
> 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)
> >>>>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Jason Wang]

在 2023/5/9 09:43, Xuan Zhuo 写道:
> On Mon, 8 May 2023 11:00:10 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>
>> On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
>>> External email: Use caution opening links or attachments
>>>
>>>
>>> On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>>>
>>>> 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@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@nvidia.com>
>>>>>> Reviewed-by: William Tu <witu@nvidia.com>
>>>>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>>>>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>>>>>> Acked-by: Michael S. Tsirkin <mst@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
>>> This is not the point, the key is whether we should handle with:
>>>
>>>             disable_delayed_refill(vi);
>>>             cancel_delayed_work_sync(&vi->refill);
>>>
>>> Thanks.
>>>
>>>
>> OK, get the point. Thanks for your careful review. And I check the code
>> again.
>>
>> There are two points that I need to explain:
>>
>> 1. All refill delay work calls(vi->refill, vi->refill_enabled) are based
>> on that the virtio interface is successfully opened, such as
>> virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there
>> is an error in the xdp reg here, it will not trigger these subsequent
>> functions. There is no need to call disable_delayed_refill() and
>> cancel_delayed_work_sync().
> Maybe something is wrong. I think these lines may call delay work.
>
> static int virtnet_open(struct net_device *dev)
> {
> 	struct virtnet_info *vi = netdev_priv(dev);
> 	int i, err;
>
> 	enable_delayed_refill(vi);
>
> 	for (i = 0; i < vi->max_queue_pairs; i++) {
> 		if (i < vi->curr_queue_pairs)
> 			/* Make sure we have some buffers: if oom use wq. */
> -->			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);
> 		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);
> 	}
>
> 	return 0;
> }
>
>
> And I think, if we virtnet_open() return error, then the status of virtnet
> should like the status after virtnet_close().
>
> Or someone has other opinion.


I agree, we need to disable and sync with the refill work.

Thanks


>
> Thanks.
>
>> The logic here is different from that of
>> virtnet_close. virtnet_close is based on the success of virtnet_open and
>> the tx and rx has been carried out normally. For error unwinding, only
>> disable qp is needed. Also encapuslated a helper function of disable qp,
>> which is used ing error unwinding and virtnet close
>> 2. The current error qp, which has not enabled NAPI, can only call xdp
>> unreg, and cannot call the interface of disable NAPI, otherwise the
>> kernel will be stuck. So for i-- the reason for calling disable qp on
>> the previous queue
>>
>> 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)
>>>>>>

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Jason Wang]

在 2023/5/9 09:43, Xuan Zhuo 写道:
> On Mon, 8 May 2023 11:00:10 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>
>> On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
>>> External email: Use caution opening links or attachments
>>>
>>>
>>> On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>>>
>>>> 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@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@nvidia.com>
>>>>>> Reviewed-by: William Tu <witu@nvidia.com>
>>>>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>>>>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>>>>>> Acked-by: Michael S. Tsirkin <mst@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
>>> This is not the point, the key is whether we should handle with:
>>>
>>>             disable_delayed_refill(vi);
>>>             cancel_delayed_work_sync(&vi->refill);
>>>
>>> Thanks.
>>>
>>>
>> OK, get the point. Thanks for your careful review. And I check the code
>> again.
>>
>> There are two points that I need to explain:
>>
>> 1. All refill delay work calls(vi->refill, vi->refill_enabled) are based
>> on that the virtio interface is successfully opened, such as
>> virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there
>> is an error in the xdp reg here, it will not trigger these subsequent
>> functions. There is no need to call disable_delayed_refill() and
>> cancel_delayed_work_sync().
> Maybe something is wrong. I think these lines may call delay work.
>
> static int virtnet_open(struct net_device *dev)
> {
> 	struct virtnet_info *vi = netdev_priv(dev);
> 	int i, err;
>
> 	enable_delayed_refill(vi);
>
> 	for (i = 0; i < vi->max_queue_pairs; i++) {
> 		if (i < vi->curr_queue_pairs)
> 			/* Make sure we have some buffers: if oom use wq. */
> -->			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);
> 		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);
> 	}
>
> 	return 0;
> }
>
>
> And I think, if we virtnet_open() return error, then the status of virtnet
> should like the status after virtnet_close().
>
> Or someone has other opinion.


I agree, we need to disable and sync with the refill work.

Thanks


>
> Thanks.
>
>> The logic here is different from that of
>> virtnet_close. virtnet_close is based on the success of virtnet_open and
>> the tx and rx has been carried out normally. For error unwinding, only
>> disable qp is needed. Also encapuslated a helper function of disable qp,
>> which is used ing error unwinding and virtnet close
>> 2. The current error qp, which has not enabled NAPI, can only call xdp
>> unreg, and cannot call the interface of disable NAPI, otherwise the
>> kernel will be stuck. So for i-- the reason for calling disable qp on
>> the previous queue
>>
>> 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)
>>>>>>

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu]

On 2023-05-10 a.m.1:00, Jason Wang wrote:
> External email: Use caution opening links or attachments
> 
> 
> 在 2023/5/9 09:43, Xuan Zhuo 写道:
>> On Mon, 8 May 2023 11:00:10 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>>
>>> On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
>>>> External email: Use caution opening links or attachments
>>>>
>>>>
>>>> On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>>>>
>>>>> 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@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@nvidia.com>
>>>>>>> Reviewed-by: William Tu <witu@nvidia.com>
>>>>>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>>>>>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>>>>>>> Acked-by: Michael S. Tsirkin <mst@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
>>>> This is not the point, the key is whether we should handle with:
>>>>
>>>>             disable_delayed_refill(vi);
>>>>             cancel_delayed_work_sync(&vi->refill);
>>>>
>>>> Thanks.
>>>>
>>>>
>>> OK, get the point. Thanks for your careful review. And I check the code
>>> again.
>>>
>>> There are two points that I need to explain:
>>>
>>> 1. All refill delay work calls(vi->refill, vi->refill_enabled) are based
>>> on that the virtio interface is successfully opened, such as
>>> virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there
>>> is an error in the xdp reg here, it will not trigger these subsequent
>>> functions. There is no need to call disable_delayed_refill() and
>>> cancel_delayed_work_sync().
>> Maybe something is wrong. I think these lines may call delay work.
>>
>> static int virtnet_open(struct net_device *dev)
>> {
>>       struct virtnet_info *vi = netdev_priv(dev);
>>       int i, err;
>>
>>       enable_delayed_refill(vi);
>>
>>       for (i = 0; i < vi->max_queue_pairs; i++) {
>>               if (i < vi->curr_queue_pairs)
>>                       /* Make sure we have some buffers: if oom use 
>> wq. */
>> -->                   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);
>>               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);
>>       }
>>
>>       return 0;
>> }
>>
>>
>> And I think, if we virtnet_open() return error, then the status of 
>> virtnet
>> should like the status after virtnet_close().
>>
>> Or someone has other opinion.
> 
> 
> I agree, we need to disable and sync with the refill work.
> 
> Thanks
> 
> 
OK，got it.
Thanks Jason & Xuan
>>
>> Thanks.
>>
>>> The logic here is different from that of
>>> virtnet_close. virtnet_close is based on the success of virtnet_open and
>>> the tx and rx has been carried out normally. For error unwinding, only
>>> disable qp is needed. Also encapuslated a helper function of disable qp,
>>> which is used ing error unwinding and virtnet close
>>> 2. The current error qp, which has not enabled NAPI, can only call xdp
>>> unreg, and cannot call the interface of disable NAPI, otherwise the
>>> kernel will be stuck. So for i-- the reason for calling disable qp on
>>> the previous queue
>>>
>>> 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)
>>>>>>>
> 

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu via Virtualization]

On 2023-05-10 a.m.1:00, Jason Wang wrote:
> External email: Use caution opening links or attachments
> 
> 
> 在 2023/5/9 09:43, Xuan Zhuo 写道:
>> On Mon, 8 May 2023 11:00:10 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>>
>>> On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
>>>> External email: Use caution opening links or attachments
>>>>
>>>>
>>>> On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>>>>
>>>>> 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@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@nvidia.com>
>>>>>>> Reviewed-by: William Tu <witu@nvidia.com>
>>>>>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>>>>>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>>>>>>> Acked-by: Michael S. Tsirkin <mst@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
>>>> This is not the point, the key is whether we should handle with:
>>>>
>>>>             disable_delayed_refill(vi);
>>>>             cancel_delayed_work_sync(&vi->refill);
>>>>
>>>> Thanks.
>>>>
>>>>
>>> OK, get the point. Thanks for your careful review. And I check the code
>>> again.
>>>
>>> There are two points that I need to explain:
>>>
>>> 1. All refill delay work calls(vi->refill, vi->refill_enabled) are based
>>> on that the virtio interface is successfully opened, such as
>>> virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there
>>> is an error in the xdp reg here, it will not trigger these subsequent
>>> functions. There is no need to call disable_delayed_refill() and
>>> cancel_delayed_work_sync().
>> Maybe something is wrong. I think these lines may call delay work.
>>
>> static int virtnet_open(struct net_device *dev)
>> {
>>       struct virtnet_info *vi = netdev_priv(dev);
>>       int i, err;
>>
>>       enable_delayed_refill(vi);
>>
>>       for (i = 0; i < vi->max_queue_pairs; i++) {
>>               if (i < vi->curr_queue_pairs)
>>                       /* Make sure we have some buffers: if oom use 
>> wq. */
>> -->                   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);
>>               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);
>>       }
>>
>>       return 0;
>> }
>>
>>
>> And I think, if we virtnet_open() return error, then the status of 
>> virtnet
>> should like the status after virtnet_close().
>>
>> Or someone has other opinion.
> 
> 
> I agree, we need to disable and sync with the refill work.
> 
> Thanks
> 
> 
OK，got it.
Thanks Jason & Xuan
>>
>> Thanks.
>>
>>> The logic here is different from that of
>>> virtnet_close. virtnet_close is based on the success of virtnet_open and
>>> the tx and rx has been carried out normally. For error unwinding, only
>>> disable qp is needed. Also encapuslated a helper function of disable qp,
>>> which is used ing error unwinding and virtnet close
>>> 2. The current error qp, which has not enabled NAPI, can only call xdp
>>> unreg, and cannot call the interface of disable NAPI, otherwise the
>>> kernel will be stuck. So for i-- the reason for calling disable qp on
>>> the previous queue
>>>
>>> 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)
>>>>>>>
> 
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu]

On 2023-05-10 a.m.1:00, Jason Wang wrote:
> External email: Use caution opening links or attachments
> 
> 
> 在 2023/5/9 09:43, Xuan Zhuo 写道:
>> On Mon, 8 May 2023 11:00:10 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>>
>>> On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
>>>> External email: Use caution opening links or attachments
>>>>
>>>>
>>>> On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>>>>
>>>>> 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@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@nvidia.com>
>>>>>>> Reviewed-by: William Tu <witu@nvidia.com>
>>>>>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>>>>>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>>>>>>> Acked-by: Michael S. Tsirkin <mst@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
>>>> This is not the point, the key is whether we should handle with:
>>>>
>>>>             disable_delayed_refill(vi);
>>>>             cancel_delayed_work_sync(&vi->refill);
>>>>
>>>> Thanks.
>>>>
>>>>
>>> OK, get the point. Thanks for your careful review. And I check the code
>>> again.
>>>
>>> There are two points that I need to explain:
>>>
>>> 1. All refill delay work calls(vi->refill, vi->refill_enabled) are based
>>> on that the virtio interface is successfully opened, such as
>>> virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there
>>> is an error in the xdp reg here, it will not trigger these subsequent
>>> functions. There is no need to call disable_delayed_refill() and
>>> cancel_delayed_work_sync().
>> Maybe something is wrong. I think these lines may call delay work.
>>
>> static int virtnet_open(struct net_device *dev)
>> {
>>       struct virtnet_info *vi = netdev_priv(dev);
>>       int i, err;
>>
>>       enable_delayed_refill(vi);
>>
>>       for (i = 0; i < vi->max_queue_pairs; i++) {
>>               if (i < vi->curr_queue_pairs)
>>                       /* Make sure we have some buffers: if oom use 
>> wq. */
>> -->                   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);
>>               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);
>>       }
>>
>>       return 0;
>> }
>>
>>
>> And I think, if we virtnet_open() return error, then the status of 
>> virtnet
>> should like the status after virtnet_close().
>>
>> Or someone has other opinion.
> 
> 
> I agree, we need to disable and sync with the refill work.
> 
> Thanks
> 
> 
Hi, Jason & Xuan

I will modify the patch according to the comments.

But cannot call virtnet_close(), since virtnet_close cannot disable 
queue pairs from the specified error one. so still need to use disable 
helper function. The reason is as mentioned in the previous email, we 
need to roll back from the specified error queue,  otherwise the queue 
pairs which has not been enabled napi will hang up at napi disable api.

According to the comments, I will call disable_delayed_refill() and 
cancel_delayed_work_sync() in error unwinding, then call the disable 
helper function one by one for the queue pairs before the error one.

Do you have any other comments about these?

Thanks

>>
>> Thanks.
>>
>>> The logic here is different from that of
>>> virtnet_close. virtnet_close is based on the success of virtnet_open and
>>> the tx and rx has been carried out normally. For error unwinding, only
>>> disable qp is needed. Also encapuslated a helper function of disable qp,
>>> which is used ing error unwinding and virtnet close
>>> 2. The current error qp, which has not enabled NAPI, can only call xdp
>>> unreg, and cannot call the interface of disable NAPI, otherwise the
>>> kernel will be stuck. So for i-- the reason for calling disable qp on
>>> the previous queue
>>>
>>> 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)
>>>>>>>
> 

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Feng Liu via Virtualization]

On 2023-05-10 a.m.1:00, Jason Wang wrote:
> External email: Use caution opening links or attachments
> 
> 
> 在 2023/5/9 09:43, Xuan Zhuo 写道:
>> On Mon, 8 May 2023 11:00:10 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>>
>>> On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
>>>> External email: Use caution opening links or attachments
>>>>
>>>>
>>>> On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
>>>>>
>>>>> 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@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@nvidia.com>
>>>>>>> Reviewed-by: William Tu <witu@nvidia.com>
>>>>>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
>>>>>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
>>>>>>> Acked-by: Michael S. Tsirkin <mst@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
>>>> This is not the point, the key is whether we should handle with:
>>>>
>>>>             disable_delayed_refill(vi);
>>>>             cancel_delayed_work_sync(&vi->refill);
>>>>
>>>> Thanks.
>>>>
>>>>
>>> OK, get the point. Thanks for your careful review. And I check the code
>>> again.
>>>
>>> There are two points that I need to explain:
>>>
>>> 1. All refill delay work calls(vi->refill, vi->refill_enabled) are based
>>> on that the virtio interface is successfully opened, such as
>>> virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there
>>> is an error in the xdp reg here, it will not trigger these subsequent
>>> functions. There is no need to call disable_delayed_refill() and
>>> cancel_delayed_work_sync().
>> Maybe something is wrong. I think these lines may call delay work.
>>
>> static int virtnet_open(struct net_device *dev)
>> {
>>       struct virtnet_info *vi = netdev_priv(dev);
>>       int i, err;
>>
>>       enable_delayed_refill(vi);
>>
>>       for (i = 0; i < vi->max_queue_pairs; i++) {
>>               if (i < vi->curr_queue_pairs)
>>                       /* Make sure we have some buffers: if oom use 
>> wq. */
>> -->                   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);
>>               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);
>>       }
>>
>>       return 0;
>> }
>>
>>
>> And I think, if we virtnet_open() return error, then the status of 
>> virtnet
>> should like the status after virtnet_close().
>>
>> Or someone has other opinion.
> 
> 
> I agree, we need to disable and sync with the refill work.
> 
> Thanks
> 
> 
Hi, Jason & Xuan

I will modify the patch according to the comments.

But cannot call virtnet_close(), since virtnet_close cannot disable 
queue pairs from the specified error one. so still need to use disable 
helper function. The reason is as mentioned in the previous email, we 
need to roll back from the specified error queue,  otherwise the queue 
pairs which has not been enabled napi will hang up at napi disable api.

According to the comments, I will call disable_delayed_refill() and 
cancel_delayed_work_sync() in error unwinding, then call the disable 
helper function one by one for the queue pairs before the error one.

Do you have any other comments about these?

Thanks

>>
>> Thanks.
>>
>>> The logic here is different from that of
>>> virtnet_close. virtnet_close is based on the success of virtnet_open and
>>> the tx and rx has been carried out normally. For error unwinding, only
>>> disable qp is needed. Also encapuslated a helper function of disable qp,
>>> which is used ing error unwinding and virtnet close
>>> 2. The current error qp, which has not enabled NAPI, can only call xdp
>>> unreg, and cannot call the interface of disable NAPI, otherwise the
>>> kernel will be stuck. So for i-- the reason for calling disable qp on
>>> the previous queue
>>>
>>> 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)
>>>>>>>
> 
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Xuan Zhuo]

On Thu, 11 May 2023 21:54:40 -0400, Feng Liu <feliu@nvidia.com> wrote:
>
>
> On 2023-05-10 a.m.1:00, Jason Wang wrote:
> > External email: Use caution opening links or attachments
> >
> >
> > 在 2023/5/9 09:43, Xuan Zhuo 写道:
> >> On Mon, 8 May 2023 11:00:10 -0400, Feng Liu <feliu@nvidia.com> wrote:
> >>>
> >>> On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
> >>>> External email: Use caution opening links or attachments
> >>>>
> >>>>
> >>>> On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
> >>>>>
> >>>>> 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@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@nvidia.com>
> >>>>>>> Reviewed-by: William Tu <witu@nvidia.com>
> >>>>>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
> >>>>>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
> >>>>>>> Acked-by: Michael S. Tsirkin <mst@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
> >>>> This is not the point, the key is whether we should handle with:
> >>>>
> >>>>             disable_delayed_refill(vi);
> >>>>             cancel_delayed_work_sync(&vi->refill);
> >>>>
> >>>> Thanks.
> >>>>
> >>>>
> >>> OK, get the point. Thanks for your careful review. And I check the code
> >>> again.
> >>>
> >>> There are two points that I need to explain:
> >>>
> >>> 1. All refill delay work calls(vi->refill, vi->refill_enabled) are based
> >>> on that the virtio interface is successfully opened, such as
> >>> virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there
> >>> is an error in the xdp reg here, it will not trigger these subsequent
> >>> functions. There is no need to call disable_delayed_refill() and
> >>> cancel_delayed_work_sync().
> >> Maybe something is wrong. I think these lines may call delay work.
> >>
> >> static int virtnet_open(struct net_device *dev)
> >> {
> >>       struct virtnet_info *vi = netdev_priv(dev);
> >>       int i, err;
> >>
> >>       enable_delayed_refill(vi);
> >>
> >>       for (i = 0; i < vi->max_queue_pairs; i++) {
> >>               if (i < vi->curr_queue_pairs)
> >>                       /* Make sure we have some buffers: if oom use
> >> wq. */
> >> -->                   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);
> >>               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);
> >>       }
> >>
> >>       return 0;
> >> }
> >>
> >>
> >> And I think, if we virtnet_open() return error, then the status of
> >> virtnet
> >> should like the status after virtnet_close().
> >>
> >> Or someone has other opinion.
> >
> >
> > I agree, we need to disable and sync with the refill work.
> >
> > Thanks
> >
> >
> Hi, Jason & Xuan
>
> I will modify the patch according to the comments.
>
> But cannot call virtnet_close(), since virtnet_close cannot disable
> queue pairs from the specified error one. so still need to use disable
> helper function. The reason is as mentioned in the previous email, we
> need to roll back from the specified error queue,  otherwise the queue
> pairs which has not been enabled napi will hang up at napi disable api.
>
> According to the comments, I will call disable_delayed_refill() and
> cancel_delayed_work_sync() in error unwinding, then call the disable
> helper function one by one for the queue pairs before the error one.
>
> Do you have any other comments about these?

LGTM

Thanks.

>
> Thanks
>
> >>
> >> Thanks.
> >>
> >>> The logic here is different from that of
> >>> virtnet_close. virtnet_close is based on the success of virtnet_open and
> >>> the tx and rx has been carried out normally. For error unwinding, only
> >>> disable qp is needed. Also encapuslated a helper function of disable qp,
> >>> which is used ing error unwinding and virtnet close
> >>> 2. The current error qp, which has not enabled NAPI, can only call xdp
> >>> unreg, and cannot call the interface of disable NAPI, otherwise the
> >>> kernel will be stuck. So for i-- the reason for calling disable qp on
> >>> the previous queue
> >>>
> >>> 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)
> >>>>>>>
> >

Re: [PATCH net v3] virtio_net: Fix error unwinding of XDP initialization

[Xuan Zhuo]

On Thu, 11 May 2023 21:54:40 -0400, Feng Liu <feliu@nvidia.com> wrote:
>
>
> On 2023-05-10 a.m.1:00, Jason Wang wrote:
> > External email: Use caution opening links or attachments
> >
> >
> > 在 2023/5/9 09:43, Xuan Zhuo 写道:
> >> On Mon, 8 May 2023 11:00:10 -0400, Feng Liu <feliu@nvidia.com> wrote:
> >>>
> >>> On 2023-05-07 p.m.9:45, Xuan Zhuo wrote:
> >>>> External email: Use caution opening links or attachments
> >>>>
> >>>>
> >>>> On Sat, 6 May 2023 08:08:02 -0400, Feng Liu <feliu@nvidia.com> wrote:
> >>>>>
> >>>>> 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@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@nvidia.com>
> >>>>>>> Reviewed-by: William Tu <witu@nvidia.com>
> >>>>>>> Reviewed-by: Parav Pandit <parav@nvidia.com>
> >>>>>>> Reviewed-by: Simon Horman <simon.horman@corigine.com>
> >>>>>>> Acked-by: Michael S. Tsirkin <mst@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
> >>>> This is not the point, the key is whether we should handle with:
> >>>>
> >>>>             disable_delayed_refill(vi);
> >>>>             cancel_delayed_work_sync(&vi->refill);
> >>>>
> >>>> Thanks.
> >>>>
> >>>>
> >>> OK, get the point. Thanks for your careful review. And I check the code
> >>> again.
> >>>
> >>> There are two points that I need to explain:
> >>>
> >>> 1. All refill delay work calls(vi->refill, vi->refill_enabled) are based
> >>> on that the virtio interface is successfully opened, such as
> >>> virtnet_receive, virtnet_rx_resize, _virtnet_set_queues, etc. If there
> >>> is an error in the xdp reg here, it will not trigger these subsequent
> >>> functions. There is no need to call disable_delayed_refill() and
> >>> cancel_delayed_work_sync().
> >> Maybe something is wrong. I think these lines may call delay work.
> >>
> >> static int virtnet_open(struct net_device *dev)
> >> {
> >>       struct virtnet_info *vi = netdev_priv(dev);
> >>       int i, err;
> >>
> >>       enable_delayed_refill(vi);
> >>
> >>       for (i = 0; i < vi->max_queue_pairs; i++) {
> >>               if (i < vi->curr_queue_pairs)
> >>                       /* Make sure we have some buffers: if oom use
> >> wq. */
> >> -->                   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);
> >>               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);
> >>       }
> >>
> >>       return 0;
> >> }
> >>
> >>
> >> And I think, if we virtnet_open() return error, then the status of
> >> virtnet
> >> should like the status after virtnet_close().
> >>
> >> Or someone has other opinion.
> >
> >
> > I agree, we need to disable and sync with the refill work.
> >
> > Thanks
> >
> >
> Hi, Jason & Xuan
>
> I will modify the patch according to the comments.
>
> But cannot call virtnet_close(), since virtnet_close cannot disable
> queue pairs from the specified error one. so still need to use disable
> helper function. The reason is as mentioned in the previous email, we
> need to roll back from the specified error queue,  otherwise the queue
> pairs which has not been enabled napi will hang up at napi disable api.
>
> According to the comments, I will call disable_delayed_refill() and
> cancel_delayed_work_sync() in error unwinding, then call the disable
> helper function one by one for the queue pairs before the error one.
>
> Do you have any other comments about these?

LGTM

Thanks.

>
> Thanks
>
> >>
> >> Thanks.
> >>
> >>> The logic here is different from that of
> >>> virtnet_close. virtnet_close is based on the success of virtnet_open and
> >>> the tx and rx has been carried out normally. For error unwinding, only
> >>> disable qp is needed. Also encapuslated a helper function of disable qp,
> >>> which is used ing error unwinding and virtnet close
> >>> 2. The current error qp, which has not enabled NAPI, can only call xdp
> >>> unreg, and cannot call the interface of disable NAPI, otherwise the
> >>> kernel will be stuck. So for i-- the reason for calling disable qp on
> >>> the previous queue
> >>>
> >>> 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)
> >>>>>>>
> >
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization