[9/9] vhost: only use vDPA config workaround if needed

  Now that we have Virtio device status support, let's
only use the vDPA workaround if it is not supported.

This patch also document why Virtio device status
protocol feature support is strongly advised.

Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
 lib/librte_vhost/vhost_user.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)
  

Hi Maxime

Thanks for the huge work.
Please see a suggestion inline.

From: Maxime Coquelin:
> Sent: Thursday, May 14, 2020 11:02 AM
> To: xiaolong.ye@intel.com; Shahaf Shuler <shahafs@mellanox.com>; Matan
> Azrad <matan@mellanox.com>; amorenoz@redhat.com;
> xiao.w.wang@intel.com; Slava Ovsiienko <viacheslavo@mellanox.com>;
> dev@dpdk.org
> Cc: jasowang@redhat.com; lulu@redhat.com; Maxime Coquelin
> <maxime.coquelin@redhat.com>
> Subject: [PATCH 9/9] vhost: only use vDPA config workaround if needed
> 
> Now that we have Virtio device status support, let's only use the vDPA
> workaround if it is not supported.
> 
> This patch also document why Virtio device status protocol feature support is
> strongly advised.
> 
> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> ---
>  lib/librte_vhost/vhost_user.c | 16 ++++++++++++++--
>  1 file changed, 14 insertions(+), 2 deletions(-)
> 
> diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
> index e5a44be58d..67e96a872a 100644
> --- a/lib/librte_vhost/vhost_user.c
> +++ b/lib/librte_vhost/vhost_user.c
> @@ -2847,8 +2847,20 @@ vhost_user_msg_handler(int vid, int fd)
>  	if (!vdpa_dev)
>  		goto out;
> 
> -	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
> -			request == VHOST_USER_SET_VRING_CALL) {
> +	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
> +		/*
> +		 * Workaround when Virtio device status protocol
> +		 * feature is not supported, wait for SET_VRING_CALL
> +		 * request. This is not ideal as some frontends like
> +		 * Virtio-user may not send this request, so vDPA device
> +		 * may never be configured. Virtio device status support
> +		 * on frontend side is strongly advised.
> +		 */
> +		if (!(dev->protocol_features &
> +				(1ULL <<
> VHOST_USER_PROTOCOL_F_STATUS)) &&
> +				(request !=
> VHOST_USER_SET_VRING_CALL))
> +			goto out;
> +


When status protocol feature is not supported, in the current code, the vDPA configuration triggering depends in:
1. Device is ready - all the queues are configured (datapath addresses, callfd and kickfd) .
2. last command is callfd.


The code doesn't take into account that some queues may stay disabled.
Maybe the correct timing is:
1. Device is ready - all the enabled queues are configured and MEM table is configured.
2. no need callfd to be last.

Queues that will be configured later will be configured to the HW when the virtq becoming enabled.


What do think? 


>  		if (vdpa_dev->ops->dev_conf(dev->vid))
>  			VHOST_LOG_CONFIG(ERR,
>  					"Failed to configure vDPA device\n");
> --
> 2.25.4
  

Hi Matan,

On 6/7/20 12:38 PM, Matan Azrad wrote:
> Hi Maxime
> 
> Thanks for the huge work.
> Please see a suggestion inline.
> 
> From: Maxime Coquelin:
>> Sent: Thursday, May 14, 2020 11:02 AM
>> To: xiaolong.ye@intel.com; Shahaf Shuler <shahafs@mellanox.com>; Matan
>> Azrad <matan@mellanox.com>; amorenoz@redhat.com;
>> xiao.w.wang@intel.com; Slava Ovsiienko <viacheslavo@mellanox.com>;
>> dev@dpdk.org
>> Cc: jasowang@redhat.com; lulu@redhat.com; Maxime Coquelin
>> <maxime.coquelin@redhat.com>
>> Subject: [PATCH 9/9] vhost: only use vDPA config workaround if needed
>>
>> Now that we have Virtio device status support, let's only use the vDPA
>> workaround if it is not supported.
>>
>> This patch also document why Virtio device status protocol feature support is
>> strongly advised.
>>
>> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
>> ---
>>  lib/librte_vhost/vhost_user.c | 16 ++++++++++++++--
>>  1 file changed, 14 insertions(+), 2 deletions(-)
>>
>> diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
>> index e5a44be58d..67e96a872a 100644
>> --- a/lib/librte_vhost/vhost_user.c
>> +++ b/lib/librte_vhost/vhost_user.c
>> @@ -2847,8 +2847,20 @@ vhost_user_msg_handler(int vid, int fd)
>>  	if (!vdpa_dev)
>>  		goto out;
>>
>> -	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
>> -			request == VHOST_USER_SET_VRING_CALL) {
>> +	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
>> +		/*
>> +		 * Workaround when Virtio device status protocol
>> +		 * feature is not supported, wait for SET_VRING_CALL
>> +		 * request. This is not ideal as some frontends like
>> +		 * Virtio-user may not send this request, so vDPA device
>> +		 * may never be configured. Virtio device status support
>> +		 * on frontend side is strongly advised.
>> +		 */
>> +		if (!(dev->protocol_features &
>> +				(1ULL <<
>> VHOST_USER_PROTOCOL_F_STATUS)) &&
>> +				(request !=
>> VHOST_USER_SET_VRING_CALL))
>> +			goto out;
>> +
> 
> 
> When status protocol feature is not supported, in the current code, the vDPA configuration triggering depends in:
> 1. Device is ready - all the queues are configured (datapath addresses, callfd and kickfd) .
> 2. last command is callfd.
> 
> 
> The code doesn't take into account that some queues may stay disabled.
> Maybe the correct timing is:
> 1. Device is ready - all the enabled queues are configured and MEM table is configured.

I think current virtio_is_ready() already assumes the mem table is
configured, otherwise we would not have vq->desc, vq->used and vq->avail
being set as it needs to be translated using the mem table.

> 2. no need callfd to be last.
> 
> Queues that will be configured later will be configured to the HW when the virtq becoming enabled.
> 
> 
> What do think? 

Maybe I did not understood what you mean, so please correct me if
needed.

If I understood correctly, then your suggestion is just to remove the
workaround, but it has been introduced by Intel because the callfd gets
set a second time in some cases.


Thanks,
Maxime
> 
>>  		if (vdpa_dev->ops->dev_conf(dev->vid))
>>  			VHOST_LOG_CONFIG(ERR,
>>  					"Failed to configure vDPA device\n");
>> --
>> 2.25.4
>
  

Hi Maxime

From: Maxime Coquelin:
> Hi Matan,
> 
> On 6/7/20 12:38 PM, Matan Azrad wrote:
> > Hi Maxime
> >
> > Thanks for the huge work.
> > Please see a suggestion inline.
> >
> > From: Maxime Coquelin:
> >> Sent: Thursday, May 14, 2020 11:02 AM
> >> To: xiaolong.ye@intel.com; Shahaf Shuler <shahafs@mellanox.com>;
> >> Matan Azrad <matan@mellanox.com>; amorenoz@redhat.com;
> >> xiao.w.wang@intel.com; Slava Ovsiienko <viacheslavo@mellanox.com>;
> >> dev@dpdk.org
> >> Cc: jasowang@redhat.com; lulu@redhat.com; Maxime Coquelin
> >> <maxime.coquelin@redhat.com>
> >> Subject: [PATCH 9/9] vhost: only use vDPA config workaround if needed
> >>
> >> Now that we have Virtio device status support, let's only use the
> >> vDPA workaround if it is not supported.
> >>
> >> This patch also document why Virtio device status protocol feature
> >> support is strongly advised.
> >>
> >> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> >> ---
> >>  lib/librte_vhost/vhost_user.c | 16 ++++++++++++++--
> >>  1 file changed, 14 insertions(+), 2 deletions(-)
> >>
> >> diff --git a/lib/librte_vhost/vhost_user.c
> >> b/lib/librte_vhost/vhost_user.c index e5a44be58d..67e96a872a 100644
> >> --- a/lib/librte_vhost/vhost_user.c
> >> +++ b/lib/librte_vhost/vhost_user.c
> >> @@ -2847,8 +2847,20 @@ vhost_user_msg_handler(int vid, int fd)
> >>  	if (!vdpa_dev)
> >>  		goto out;
> >>
> >> -	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
> >> -			request == VHOST_USER_SET_VRING_CALL) {
> >> +	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
> >> +		/*
> >> +		 * Workaround when Virtio device status protocol
> >> +		 * feature is not supported, wait for SET_VRING_CALL
> >> +		 * request. This is not ideal as some frontends like
> >> +		 * Virtio-user may not send this request, so vDPA device
> >> +		 * may never be configured. Virtio device status support
> >> +		 * on frontend side is strongly advised.
> >> +		 */
> >> +		if (!(dev->protocol_features &
> >> +				(1ULL <<
> >> VHOST_USER_PROTOCOL_F_STATUS)) &&
> >> +				(request !=
> >> VHOST_USER_SET_VRING_CALL))
> >> +			goto out;
> >> +
> >
> >
> > When status protocol feature is not supported, in the current code, the
> vDPA configuration triggering depends in:
> > 1. Device is ready - all the queues are configured (datapath addresses,
> callfd and kickfd) .
> > 2. last command is callfd.
> >
> >
> > The code doesn't take into account that some queues may stay disabled.
> > Maybe the correct timing is:
> > 1. Device is ready - all the enabled queues are configured and MEM table is
> configured.
> 
> I think current virtio_is_ready() already assumes the mem table is
> configured, otherwise we would not have vq->desc, vq->used and vq->avail
> being set as it needs to be translated using the mem table.
> 

Yes, but if you don't expect to check them for disabled queues you need to check mem table to be sure it was set.


> > 2. no need callfd to be last.
> >
> > Queues that will be configured later will be configured to the HW when the
> virtq becoming enabled.
> >
> >
> > What do think?
> 
> Maybe I did not understood what you mean, so please correct me if needed.
> 
> If I understood correctly, then your suggestion is just to remove the
> workaround, but it has been introduced by Intel because the callfd gets set a
> second time in some cases.

Not to remove the WA, just to improve it😊

I don't sure I understand the issue here, can you add details?


> 
> Thanks,
> Maxime
> >
> >>  		if (vdpa_dev->ops->dev_conf(dev->vid))
> >>  			VHOST_LOG_CONFIG(ERR,
> >>  					"Failed to configure vDPA device\n");
> >> --
> >> 2.25.4
> >
  

Hi Matan,

On 6/8/20 11:19 AM, Matan Azrad wrote:
> Hi Maxime
> 
> From: Maxime Coquelin:
>> Hi Matan,
>>
>> On 6/7/20 12:38 PM, Matan Azrad wrote:
>>> Hi Maxime
>>>
>>> Thanks for the huge work.
>>> Please see a suggestion inline.
>>>
>>> From: Maxime Coquelin:
>>>> Sent: Thursday, May 14, 2020 11:02 AM
>>>> To: xiaolong.ye@intel.com; Shahaf Shuler <shahafs@mellanox.com>;
>>>> Matan Azrad <matan@mellanox.com>; amorenoz@redhat.com;
>>>> xiao.w.wang@intel.com; Slava Ovsiienko <viacheslavo@mellanox.com>;
>>>> dev@dpdk.org
>>>> Cc: jasowang@redhat.com; lulu@redhat.com; Maxime Coquelin
>>>> <maxime.coquelin@redhat.com>
>>>> Subject: [PATCH 9/9] vhost: only use vDPA config workaround if needed
>>>>
>>>> Now that we have Virtio device status support, let's only use the
>>>> vDPA workaround if it is not supported.
>>>>
>>>> This patch also document why Virtio device status protocol feature
>>>> support is strongly advised.
>>>>
>>>> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
>>>> ---
>>>>  lib/librte_vhost/vhost_user.c | 16 ++++++++++++++--
>>>>  1 file changed, 14 insertions(+), 2 deletions(-)
>>>>
>>>> diff --git a/lib/librte_vhost/vhost_user.c
>>>> b/lib/librte_vhost/vhost_user.c index e5a44be58d..67e96a872a 100644
>>>> --- a/lib/librte_vhost/vhost_user.c
>>>> +++ b/lib/librte_vhost/vhost_user.c
>>>> @@ -2847,8 +2847,20 @@ vhost_user_msg_handler(int vid, int fd)
>>>>  	if (!vdpa_dev)
>>>>  		goto out;
>>>>
>>>> -	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
>>>> -			request == VHOST_USER_SET_VRING_CALL) {
>>>> +	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
>>>> +		/*
>>>> +		 * Workaround when Virtio device status protocol
>>>> +		 * feature is not supported, wait for SET_VRING_CALL
>>>> +		 * request. This is not ideal as some frontends like
>>>> +		 * Virtio-user may not send this request, so vDPA device
>>>> +		 * may never be configured. Virtio device status support
>>>> +		 * on frontend side is strongly advised.
>>>> +		 */
>>>> +		if (!(dev->protocol_features &
>>>> +				(1ULL <<
>>>> VHOST_USER_PROTOCOL_F_STATUS)) &&
>>>> +				(request !=
>>>> VHOST_USER_SET_VRING_CALL))
>>>> +			goto out;
>>>> +
>>>
>>>
>>> When status protocol feature is not supported, in the current code, the
>> vDPA configuration triggering depends in:
>>> 1. Device is ready - all the queues are configured (datapath addresses,
>> callfd and kickfd) .
>>> 2. last command is callfd.
>>>
>>>
>>> The code doesn't take into account that some queues may stay disabled.
>>> Maybe the correct timing is:
>>> 1. Device is ready - all the enabled queues are configured and MEM table is
>> configured.
>>
>> I think current virtio_is_ready() already assumes the mem table is
>> configured, otherwise we would not have vq->desc, vq->used and vq->avail
>> being set as it needs to be translated using the mem table.
>>
> 
> Yes, but if you don't expect to check them for disabled queues you need to check mem table to be sure it was set.

Even disabled queues should be allocated/configured by the guest driver.

> 
>>> 2. no need callfd to be last.
>>>
>>> Queues that will be configured later will be configured to the HW when the
>> virtq becoming enabled.
>>>
>>>
>>> What do think?
>>
>> Maybe I did not understood what you mean, so please correct me if needed.
>>
>> If I understood correctly, then your suggestion is just to remove the
>> workaround, but it has been introduced by Intel because the callfd gets set a
>> second time in some cases.
> 
> Not to remove the WA, just to improve it😊
> 
> I don't sure I understand the issue here, can you add details?

My understanding is that callfd is sent early by Qemu but is then
updated after by Qemu and we have no way to distinguish whether the
first one is valid or not... I did a bit of archeology and found this
explanation from Xiao:

https://inbox.dpdk.org/stable/B7F2E978279D1D49A3034B7786DACF407AFAA0C6@SHSMSX106.ccr.corp.intel.com/

I haven't managed to reproduce the issue myself, so that's why I'm a bit
reluctant in trying to improve it. Ideally Xiao could try to reproduce
the issue, so that if we can find something more elegant (and that does
make Virtio-user to work without the SET_STATUS support) we can be
confident in merging it (and maybe even backport it).

Regards,
Maxime

> 
>>
>> Thanks,
>> Maxime
>>>
>>>>  		if (vdpa_dev->ops->dev_conf(dev->vid))
>>>>  			VHOST_LOG_CONFIG(ERR,
>>>>  					"Failed to configure vDPA device\n");
>>>> --
>>>> 2.25.4
>>>
>
  

Hi Maxime

From: Maxime Coquelin
> Hi Matan,
> 
> On 6/8/20 11:19 AM, Matan Azrad wrote:
> > Hi Maxime
> >
> > From: Maxime Coquelin:
> >> Hi Matan,
> >>
> >> On 6/7/20 12:38 PM, Matan Azrad wrote:
> >>> Hi Maxime
> >>>
> >>> Thanks for the huge work.
> >>> Please see a suggestion inline.
> >>>
> >>> From: Maxime Coquelin:
> >>>> Sent: Thursday, May 14, 2020 11:02 AM
> >>>> To: xiaolong.ye@intel.com; Shahaf Shuler <shahafs@mellanox.com>;
> >>>> Matan Azrad <matan@mellanox.com>; amorenoz@redhat.com;
> >>>> xiao.w.wang@intel.com; Slava Ovsiienko
> <viacheslavo@mellanox.com>;
> >>>> dev@dpdk.org
> >>>> Cc: jasowang@redhat.com; lulu@redhat.com; Maxime Coquelin
> >>>> <maxime.coquelin@redhat.com>
> >>>> Subject: [PATCH 9/9] vhost: only use vDPA config workaround if
> >>>> needed
> >>>>
> >>>> Now that we have Virtio device status support, let's only use the
> >>>> vDPA workaround if it is not supported.
> >>>>
> >>>> This patch also document why Virtio device status protocol feature
> >>>> support is strongly advised.
> >>>>
> >>>> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> >>>> ---
> >>>>  lib/librte_vhost/vhost_user.c | 16 ++++++++++++++--
> >>>>  1 file changed, 14 insertions(+), 2 deletions(-)
> >>>>
> >>>> diff --git a/lib/librte_vhost/vhost_user.c
> >>>> b/lib/librte_vhost/vhost_user.c index e5a44be58d..67e96a872a 100644
> >>>> --- a/lib/librte_vhost/vhost_user.c
> >>>> +++ b/lib/librte_vhost/vhost_user.c
> >>>> @@ -2847,8 +2847,20 @@ vhost_user_msg_handler(int vid, int fd)
> >>>>  	if (!vdpa_dev)
> >>>>  		goto out;
> >>>>
> >>>> -	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
> >>>> -			request == VHOST_USER_SET_VRING_CALL) {
> >>>> +	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
> >>>> +		/*
> >>>> +		 * Workaround when Virtio device status protocol
> >>>> +		 * feature is not supported, wait for SET_VRING_CALL
> >>>> +		 * request. This is not ideal as some frontends like
> >>>> +		 * Virtio-user may not send this request, so vDPA device
> >>>> +		 * may never be configured. Virtio device status support
> >>>> +		 * on frontend side is strongly advised.
> >>>> +		 */
> >>>> +		if (!(dev->protocol_features &
> >>>> +				(1ULL <<
> >>>> VHOST_USER_PROTOCOL_F_STATUS)) &&
> >>>> +				(request !=
> >>>> VHOST_USER_SET_VRING_CALL))
> >>>> +			goto out;
> >>>> +
> >>>
> >>>
> >>> When status protocol feature is not supported, in the current code,
> >>> the
> >> vDPA configuration triggering depends in:
> >>> 1. Device is ready - all the queues are configured (datapath
> >>> addresses,
> >> callfd and kickfd) .
> >>> 2. last command is callfd.
> >>>
> >>>
> >>> The code doesn't take into account that some queues may stay disabled.
> >>> Maybe the correct timing is:
> >>> 1. Device is ready - all the enabled queues are configured and MEM
> >>> table is
> >> configured.
> >>
> >> I think current virtio_is_ready() already assumes the mem table is
> >> configured, otherwise we would not have vq->desc, vq->used and
> >> vq->avail being set as it needs to be translated using the mem table.
> >>
> >
> > Yes, but if you don't expect to check them for disabled queues you need to
> check mem table to be sure it was set.
> 
> Even disabled queues should be allocated/configured by the guest driver.

Is it by spec?

We saw that windows virtio guest driver doesn't configure disabled queues.
Is it bug in windows guest?
You probably can take a look here:
https://github.com/virtio-win/kvm-guest-drivers-windows

> >>> 2. no need callfd to be last.
> >>>
> >>> Queues that will be configured later will be configured to the HW
> >>> when the
> >> virtq becoming enabled.
> >>>
> >>>
> >>> What do think?
> >>
> >> Maybe I did not understood what you mean, so please correct me if
> needed.
> >>
> >> If I understood correctly, then your suggestion is just to remove the
> >> workaround, but it has been introduced by Intel because the callfd
> >> gets set a second time in some cases.
> >
> > Not to remove the WA, just to improve it😊
> >
> > I don't sure I understand the issue here, can you add details?
> 
> My understanding is that callfd is sent early by Qemu but is then updated
> after by Qemu and we have no way to distinguish whether the first one is
> valid or not... I did a bit of archeology and found this explanation from Xiao:
> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Finbox
> .dpdk.org%2Fstable%2FB7F2E978279D1D49A3034B7786DACF407AFAA0C6%4
> 0SHSMSX106.ccr.corp.intel.com%2F&amp;data=02%7C01%7Cmatan%40mella
> nox.com%7Cdafcc4fcf4074202227208d80c542b1e%7Ca652971c7d2e4d9ba6a4
> d149256f461b%7C0%7C0%7C637272902927735523&amp;sdata=hvUJq5VdXH
> usbBp1y%2BSr1Yp2AukNQZbRnFS6dR3rgMw%3D&amp;reserved=0
> 
> I haven't managed to reproduce the issue myself, so that's why I'm a bit
> reluctant in trying to improve it. Ideally Xiao could try to reproduce the issue,
> so that if we can find something more elegant (and that does make Virtio-
> user to work without the SET_STATUS support) we can be confident in
> merging it (and maybe even backport it).


It looks like very specific case WA which breaks other cases, for example:
Guest poll mode driver: callfd is configured twice one by one, the first is X=!-1 and the second -1, here vdpa configuration may be triggered in the first one what make the driver think wrongly that the queue is not in poll mode.


I will send RFC patch with my suggestion.

 
> Regards,
> Maxime
> 
> >
> >>
> >> Thanks,
> >> Maxime
> >>>
> >>>>  		if (vdpa_dev->ops->dev_conf(dev->vid))
> >>>>  			VHOST_LOG_CONFIG(ERR,
> >>>>  					"Failed to configure vDPA device\n");
> >>>> --
> >>>> 2.25.4
> >>>
> >
  

On 6/9/20 1:09 PM, Matan Azrad wrote:
> 
> Hi Maxime
> 
> From: Maxime Coquelin
>> Hi Matan,
>>
>> On 6/8/20 11:19 AM, Matan Azrad wrote:
>>> Hi Maxime
>>>
>>> From: Maxime Coquelin:
>>>> Hi Matan,
>>>>
>>>> On 6/7/20 12:38 PM, Matan Azrad wrote:
>>>>> Hi Maxime
>>>>>
>>>>> Thanks for the huge work.
>>>>> Please see a suggestion inline.
>>>>>
>>>>> From: Maxime Coquelin:
>>>>>> Sent: Thursday, May 14, 2020 11:02 AM
>>>>>> To: xiaolong.ye@intel.com; Shahaf Shuler <shahafs@mellanox.com>;
>>>>>> Matan Azrad <matan@mellanox.com>; amorenoz@redhat.com;
>>>>>> xiao.w.wang@intel.com; Slava Ovsiienko
>> <viacheslavo@mellanox.com>;
>>>>>> dev@dpdk.org
>>>>>> Cc: jasowang@redhat.com; lulu@redhat.com; Maxime Coquelin
>>>>>> <maxime.coquelin@redhat.com>
>>>>>> Subject: [PATCH 9/9] vhost: only use vDPA config workaround if
>>>>>> needed
>>>>>>
>>>>>> Now that we have Virtio device status support, let's only use the
>>>>>> vDPA workaround if it is not supported.
>>>>>>
>>>>>> This patch also document why Virtio device status protocol feature
>>>>>> support is strongly advised.
>>>>>>
>>>>>> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
>>>>>> ---
>>>>>>  lib/librte_vhost/vhost_user.c | 16 ++++++++++++++--
>>>>>>  1 file changed, 14 insertions(+), 2 deletions(-)
>>>>>>
>>>>>> diff --git a/lib/librte_vhost/vhost_user.c
>>>>>> b/lib/librte_vhost/vhost_user.c index e5a44be58d..67e96a872a 100644
>>>>>> --- a/lib/librte_vhost/vhost_user.c
>>>>>> +++ b/lib/librte_vhost/vhost_user.c
>>>>>> @@ -2847,8 +2847,20 @@ vhost_user_msg_handler(int vid, int fd)
>>>>>>  	if (!vdpa_dev)
>>>>>>  		goto out;
>>>>>>
>>>>>> -	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
>>>>>> -			request == VHOST_USER_SET_VRING_CALL) {
>>>>>> +	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
>>>>>> +		/*
>>>>>> +		 * Workaround when Virtio device status protocol
>>>>>> +		 * feature is not supported, wait for SET_VRING_CALL
>>>>>> +		 * request. This is not ideal as some frontends like
>>>>>> +		 * Virtio-user may not send this request, so vDPA device
>>>>>> +		 * may never be configured. Virtio device status support
>>>>>> +		 * on frontend side is strongly advised.
>>>>>> +		 */
>>>>>> +		if (!(dev->protocol_features &
>>>>>> +				(1ULL <<
>>>>>> VHOST_USER_PROTOCOL_F_STATUS)) &&
>>>>>> +				(request !=
>>>>>> VHOST_USER_SET_VRING_CALL))
>>>>>> +			goto out;
>>>>>> +
>>>>>
>>>>>
>>>>> When status protocol feature is not supported, in the current code,
>>>>> the
>>>> vDPA configuration triggering depends in:
>>>>> 1. Device is ready - all the queues are configured (datapath
>>>>> addresses,
>>>> callfd and kickfd) .
>>>>> 2. last command is callfd.
>>>>>
>>>>>
>>>>> The code doesn't take into account that some queues may stay disabled.
>>>>> Maybe the correct timing is:
>>>>> 1. Device is ready - all the enabled queues are configured and MEM
>>>>> table is
>>>> configured.
>>>>
>>>> I think current virtio_is_ready() already assumes the mem table is
>>>> configured, otherwise we would not have vq->desc, vq->used and
>>>> vq->avail being set as it needs to be translated using the mem table.
>>>>
>>>
>>> Yes, but if you don't expect to check them for disabled queues you need to
>> check mem table to be sure it was set.
>>
>> Even disabled queues should be allocated/configured by the guest driver.
> 
> Is it by spec?
> 
> We saw that windows virtio guest driver doesn't configure disabled queues.
> Is it bug in windows guest?
> You probably can take a look here:
> https://github.com/virtio-win/kvm-guest-drivers-windows
> 
>>>>> 2. no need callfd to be last.
>>>>>
>>>>> Queues that will be configured later will be configured to the HW
>>>>> when the
>>>> virtq becoming enabled.
>>>>>
>>>>>
>>>>> What do think?
>>>>
>>>> Maybe I did not understood what you mean, so please correct me if
>> needed.
>>>>
>>>> If I understood correctly, then your suggestion is just to remove the
>>>> workaround, but it has been introduced by Intel because the callfd
>>>> gets set a second time in some cases.
>>>
>>> Not to remove the WA, just to improve it😊
>>>
>>> I don't sure I understand the issue here, can you add details?
>>
>> My understanding is that callfd is sent early by Qemu but is then updated
>> after by Qemu and we have no way to distinguish whether the first one is
>> valid or not... I did a bit of archeology and found this explanation from Xiao:
>> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Finbox
>> .dpdk.org%2Fstable%2FB7F2E978279D1D49A3034B7786DACF407AFAA0C6%4
>> 0SHSMSX106.ccr.corp.intel.com%2F&amp;data=02%7C01%7Cmatan%40mella
>> nox.com%7Cdafcc4fcf4074202227208d80c542b1e%7Ca652971c7d2e4d9ba6a4
>> d149256f461b%7C0%7C0%7C637272902927735523&amp;sdata=hvUJq5VdXH
>> usbBp1y%2BSr1Yp2AukNQZbRnFS6dR3rgMw%3D&amp;reserved=0
>>
>> I haven't managed to reproduce the issue myself, so that's why I'm a bit
>> reluctant in trying to improve it. Ideally Xiao could try to reproduce the issue,
>> so that if we can find something more elegant (and that does make Virtio-
>> user to work without the SET_STATUS support) we can be confident in
>> merging it (and maybe even backport it).
> 
> 
> It looks like very specific case WA which breaks other cases, for example:
> Guest poll mode driver: callfd is configured twice one by one, the first is X=!-1 and the second -1, here vdpa configuration may be triggered in the first one what make the driver think wrongly that the queue is not in poll mode.

Yes, I agree that it would be better to avoid having this workaround, as
it may create regressions.

> I will send RFC patch with my suggestion.

Thanks.
Xiao, any chance you try to reproduce the initial issue? This way we can
test Matan's RFC.

Maxime

>  
>> Regards,
>> Maxime
>>
>>>
>>>>
>>>> Thanks,
>>>> Maxime
>>>>>
>>>>>>  		if (vdpa_dev->ops->dev_conf(dev->vid))
>>>>>>  			VHOST_LOG_CONFIG(ERR,
>>>>>>  					"Failed to configure vDPA device\n");
>>>>>> --
>>>>>> 2.25.4
>>>>>
>>>
>
  

On 6/9/20 1:09 PM, Matan Azrad wrote:
> Hi Maxime
> 
> From: Maxime Coquelin
>> Hi Matan,
>>
>> On 6/8/20 11:19 AM, Matan Azrad wrote:
>>> Hi Maxime
>>>
>>> From: Maxime Coquelin:
>>>> Hi Matan,
>>>>
>>>> On 6/7/20 12:38 PM, Matan Azrad wrote:
>>>>> Hi Maxime
>>>>>
>>>>> Thanks for the huge work.
>>>>> Please see a suggestion inline.
>>>>>
>>>>> From: Maxime Coquelin:
>>>>>> Sent: Thursday, May 14, 2020 11:02 AM
>>>>>> To: xiaolong.ye@intel.com; Shahaf Shuler <shahafs@mellanox.com>;
>>>>>> Matan Azrad <matan@mellanox.com>; amorenoz@redhat.com;
>>>>>> xiao.w.wang@intel.com; Slava Ovsiienko
>> <viacheslavo@mellanox.com>;
>>>>>> dev@dpdk.org
>>>>>> Cc: jasowang@redhat.com; lulu@redhat.com; Maxime Coquelin
>>>>>> <maxime.coquelin@redhat.com>
>>>>>> Subject: [PATCH 9/9] vhost: only use vDPA config workaround if
>>>>>> needed
>>>>>>
>>>>>> Now that we have Virtio device status support, let's only use the
>>>>>> vDPA workaround if it is not supported.
>>>>>>
>>>>>> This patch also document why Virtio device status protocol feature
>>>>>> support is strongly advised.
>>>>>>
>>>>>> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
>>>>>> ---
>>>>>>  lib/librte_vhost/vhost_user.c | 16 ++++++++++++++--
>>>>>>  1 file changed, 14 insertions(+), 2 deletions(-)
>>>>>>
>>>>>> diff --git a/lib/librte_vhost/vhost_user.c
>>>>>> b/lib/librte_vhost/vhost_user.c index e5a44be58d..67e96a872a 100644
>>>>>> --- a/lib/librte_vhost/vhost_user.c
>>>>>> +++ b/lib/librte_vhost/vhost_user.c
>>>>>> @@ -2847,8 +2847,20 @@ vhost_user_msg_handler(int vid, int fd)
>>>>>>  	if (!vdpa_dev)
>>>>>>  		goto out;
>>>>>>
>>>>>> -	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
>>>>>> -			request == VHOST_USER_SET_VRING_CALL) {
>>>>>> +	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
>>>>>> +		/*
>>>>>> +		 * Workaround when Virtio device status protocol
>>>>>> +		 * feature is not supported, wait for SET_VRING_CALL
>>>>>> +		 * request. This is not ideal as some frontends like
>>>>>> +		 * Virtio-user may not send this request, so vDPA device
>>>>>> +		 * may never be configured. Virtio device status support
>>>>>> +		 * on frontend side is strongly advised.
>>>>>> +		 */
>>>>>> +		if (!(dev->protocol_features &
>>>>>> +				(1ULL <<
>>>>>> VHOST_USER_PROTOCOL_F_STATUS)) &&
>>>>>> +				(request !=
>>>>>> VHOST_USER_SET_VRING_CALL))
>>>>>> +			goto out;
>>>>>> +
>>>>>
>>>>> When status protocol feature is not supported, in the current code,
>>>>> the
>>>> vDPA configuration triggering depends in:
>>>>> 1. Device is ready - all the queues are configured (datapath
>>>>> addresses,
>>>> callfd and kickfd) .
>>>>> 2. last command is callfd.
>>>>>
>>>>>
>>>>> The code doesn't take into account that some queues may stay disabled.
>>>>> Maybe the correct timing is:
>>>>> 1. Device is ready - all the enabled queues are configured and MEM
>>>>> table is
>>>> configured.
>>>>
>>>> I think current virtio_is_ready() already assumes the mem table is
>>>> configured, otherwise we would not have vq->desc, vq->used and
>>>> vq->avail being set as it needs to be translated using the mem table.
>>>>
>>> Yes, but if you don't expect to check them for disabled queues you need to
>> check mem table to be sure it was set.
>>
>> Even disabled queues should be allocated/configured by the guest driver.
> Is it by spec?

Sorry, that was a misunderstanding from my side.
The number of queues set by the driver using MQ_VQ_PAIRS_SET control
message have to be allocated and configured by the driver:
http://docs.oasis-open.org/virtio/virtio/v1.0/cs04/virtio-v1.0-cs04.html#x1-1940001

> We saw that windows virtio guest driver doesn't configure disabled queues.
> Is it bug in windows guest?
> You probably can take a look here:
> https://github.com/virtio-win/kvm-guest-drivers-windows
> 

Indeed it limits the number of queue pairs to the number of CPUs.
This is done here:
https://github.com/virtio-win/kvm-guest-drivers-windows/blob/edda3f50a17015aab1450ca09e3263c7409e4001/NetKVM/Common/ParaNdis_Common.cpp#L956

Linux does the same by the way:
https://elixir.bootlin.com/linux/latest/source/drivers/net/virtio_net.c#L3092

We rarely face this issue because by default, the management
layers usually set the number of queue pairs to the number of vCPUs if
multiqueue is enabled. But the problem is real.

In my opinion, the problem is more on Vhost-user spec side and/or Vhost-
user backend.

The DPDK backend allocates queue pairs for every time it receives a
Vhost-user message setting a new queue (callfd, kickfd, enable,... see
vhost_user_check_and_alloc_queue_pair()). And then virtio_is_ready()
waits for all the allocated queue pairs to be initialized.

The problem is that QEMU sends some if these messages even for queues
that aren't (or won't be) initialized, as you can see in below log where
I reproduced the issue with Windows 10:
https://pastebin.com/YYCfW9Y3

I don't see how the backend could know the guest driver is done with
currently received information from Qemu as it seems to him some queues
are partially initialized (callfd is set).

With VHOST_USER_SET_STATUS, we will be able to handle this properly, as
the backend can be sure the guest won't initialize more queues as soon
as DRIVER_OK Virtio status bit is set. In my v2, I can add one patch to
handle this case properly, by "destorying" queues metadata as soon as
DRIVER_OK is received.

Note that it was the exact reason why I first tried to add support for
VHOST_USER_SET_STATUS more than two years ago...:
https://lists.gnu.org/archive/html/qemu-devel/2018-02/msg04560.html

What do you think?

Regards,
Maxime
  

Hi Maxime

From: Maxime Coquelin:
> On 6/9/20 1:09 PM, Matan Azrad wrote:
> > Hi Maxime
> >
> > From: Maxime Coquelin
> >> Hi Matan,
> >>
> >> On 6/8/20 11:19 AM, Matan Azrad wrote:
> >>> Hi Maxime
> >>>
> >>> From: Maxime Coquelin:
> >>>> Hi Matan,
> >>>>
> >>>> On 6/7/20 12:38 PM, Matan Azrad wrote:
> >>>>> Hi Maxime
> >>>>>
> >>>>> Thanks for the huge work.
> >>>>> Please see a suggestion inline.
> >>>>>
> >>>>> From: Maxime Coquelin:
> >>>>>> Sent: Thursday, May 14, 2020 11:02 AM
> >>>>>> To: xiaolong.ye@intel.com; Shahaf Shuler
> <shahafs@mellanox.com>;
> >>>>>> Matan Azrad <matan@mellanox.com>; amorenoz@redhat.com;
> >>>>>> xiao.w.wang@intel.com; Slava Ovsiienko
> >> <viacheslavo@mellanox.com>;
> >>>>>> dev@dpdk.org
> >>>>>> Cc: jasowang@redhat.com; lulu@redhat.com; Maxime Coquelin
> >>>>>> <maxime.coquelin@redhat.com>
> >>>>>> Subject: [PATCH 9/9] vhost: only use vDPA config workaround if
> >>>>>> needed
> >>>>>>
> >>>>>> Now that we have Virtio device status support, let's only use the
> >>>>>> vDPA workaround if it is not supported.
> >>>>>>
> >>>>>> This patch also document why Virtio device status protocol
> >>>>>> feature support is strongly advised.
> >>>>>>
> >>>>>> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> >>>>>> ---
> >>>>>>  lib/librte_vhost/vhost_user.c | 16 ++++++++++++++--
> >>>>>>  1 file changed, 14 insertions(+), 2 deletions(-)
> >>>>>>
> >>>>>> diff --git a/lib/librte_vhost/vhost_user.c
> >>>>>> b/lib/librte_vhost/vhost_user.c index e5a44be58d..67e96a872a
> >>>>>> 100644
> >>>>>> --- a/lib/librte_vhost/vhost_user.c
> >>>>>> +++ b/lib/librte_vhost/vhost_user.c
> >>>>>> @@ -2847,8 +2847,20 @@ vhost_user_msg_handler(int vid, int fd)
> >>>>>>  	if (!vdpa_dev)
> >>>>>>  		goto out;
> >>>>>>
> >>>>>> -	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
> >>>>>> -			request == VHOST_USER_SET_VRING_CALL)
> {
> >>>>>> +	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
> >>>>>> +		/*
> >>>>>> +		 * Workaround when Virtio device status protocol
> >>>>>> +		 * feature is not supported, wait for
> SET_VRING_CALL
> >>>>>> +		 * request. This is not ideal as some frontends like
> >>>>>> +		 * Virtio-user may not send this request, so vDPA
> device
> >>>>>> +		 * may never be configured. Virtio device status
> support
> >>>>>> +		 * on frontend side is strongly advised.
> >>>>>> +		 */
> >>>>>> +		if (!(dev->protocol_features &
> >>>>>> +				(1ULL <<
> >>>>>> VHOST_USER_PROTOCOL_F_STATUS)) &&
> >>>>>> +				(request !=
> >>>>>> VHOST_USER_SET_VRING_CALL))
> >>>>>> +			goto out;
> >>>>>> +
> >>>>>
> >>>>> When status protocol feature is not supported, in the current
> >>>>> code, the
> >>>> vDPA configuration triggering depends in:
> >>>>> 1. Device is ready - all the queues are configured (datapath
> >>>>> addresses,
> >>>> callfd and kickfd) .
> >>>>> 2. last command is callfd.
> >>>>>
> >>>>>
> >>>>> The code doesn't take into account that some queues may stay
> disabled.
> >>>>> Maybe the correct timing is:
> >>>>> 1. Device is ready - all the enabled queues are configured and MEM
> >>>>> table is
> >>>> configured.
> >>>>
> >>>> I think current virtio_is_ready() already assumes the mem table is
> >>>> configured, otherwise we would not have vq->desc, vq->used and
> >>>> vq->avail being set as it needs to be translated using the mem table.
> >>>>
> >>> Yes, but if you don't expect to check them for disabled queues you
> >>> need to
> >> check mem table to be sure it was set.
> >>
> >> Even disabled queues should be allocated/configured by the guest driver.
> > Is it by spec?
> 
> Sorry, that was a misunderstanding from my side.
> The number of queues set by the driver using MQ_VQ_PAIRS_SET control
> message have to be allocated and configured by the driver:
> https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fdocs.o
> asis-open.org%2Fvirtio%2Fvirtio%2Fv1.0%2Fcs04%2Fvirtio-v1.0-
> cs04.html%23x1-
> 1940001&amp;data=02%7C01%7Cmatan%40mellanox.com%7Cbed5d361fbff
> 47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0%
> 7C637273201984684513&amp;sdata=zbBLclza39Fi5QenFtRx%2F1T29Dgj4w%2
> FudJ6obp5RxYo%3D&amp;reserved=0
> 

Do you mean to the sentence:
"The driver MUST configure the virtqueues before enabling them with the VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET command." ?

Maybe I miss English understanding here but it looks like this sentence doesn't say if the driver should do configuration for queues that will not be enabled by the virtio driver (stay disabled forever).


> > We saw that windows virtio guest driver doesn't configure disabled
> queues.
> > Is it bug in windows guest?
> > You probably can take a look here:
> > https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgith
> > ub.com%2Fvirtio-win%2Fkvm-guest-drivers-
> windows&amp;data=02%7C01%7Cmat
> >
> an%40mellanox.com%7Cbed5d361fbff47ab766008d80c99cc53%7Ca652971c7d
> 2e4d9
> >
> ba6a4d149256f461b%7C0%7C0%7C637273201984684513&amp;sdata=%2BqPf
> myvTw1T
> > RFif9woeR%2BsndUEunfR5O9EegJfilDI0%3D&amp;reserved=0
> >
> 
> Indeed it limits the number of queue pairs to the number of CPUs.
> This is done here:
> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithu
> b.com%2Fvirtio-win%2Fkvm-guest-drivers-
> windows%2Fblob%2Fedda3f50a17015aab1450ca09e3263c7409e4001%2FNetK
> VM%2FCommon%2FParaNdis_Common.cpp%23L956&amp;data=02%7C01%
> 7Cmatan%40mellanox.com%7Cbed5d361fbff47ab766008d80c99cc53%7Ca652
> 971c7d2e4d9ba6a4d149256f461b%7C0%7C0%7C637273201984684513&amp;s
> data=XXFIkVJWFacUMZLJwsKyoy6%2Bcqkn5f60fEC9rmMpaNI%3D&amp;res
> erved=0
> 
> Linux does the same by the way:
> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Felixir.
> bootlin.com%2Flinux%2Flatest%2Fsource%2Fdrivers%2Fnet%2Fvirtio_net.c
> %23L3092&amp;data=02%7C01%7Cmatan%40mellanox.com%7Cbed5d361fbf
> f47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0
> %7C637273201984684513&amp;sdata=ef6KJLHkkaGf5d6V8%2BI8N1WsI0Q3x
> X31jz2Y8oUSeNE%3D&amp;reserved=0

Yes, I think it makes sense.

> We rarely face this issue because by default, the management layers usually
> set the number of queue pairs to the number of vCPUs if multiqueue is
> enabled. But the problem is real.
> 
> In my opinion, the problem is more on Vhost-user spec side and/or Vhost-
> user backend.
> 
> The DPDK backend allocates queue pairs for every time it receives a Vhost-
> user message setting a new queue (callfd, kickfd, enable,... see
> vhost_user_check_and_alloc_queue_pair()). And then virtio_is_ready()
> waits for all the allocated queue pairs to be initialized.
> 
> The problem is that QEMU sends some if these messages even for queues
> that aren't (or won't be) initialized, as you can see in below log where I
> reproduced the issue with Windows 10:
> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fpaste
> bin.com%2FYYCfW9Y3&amp;data=02%7C01%7Cmatan%40mellanox.com%7C
> bed5d361fbff47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461
> b%7C0%7C0%7C637273201984684513&amp;sdata=MBG09v4BscpX5%2Bf%2Bl
> 7EOwhJcrpvoH7Wo3ISTLOxC6Lk%3D&amp;reserved=0
> 
> I don't see how the backend could know the guest driver is done with
> currently received information from Qemu as it seems to him some queues
> are partially initialized (callfd is set).

Don’t you think that only enabled queues must be fully initialized when their status is changed from disabled to enabled?
So, you can assume that disabled queues can stay "not fully initialized"...


> With VHOST_USER_SET_STATUS, we will be able to handle this properly, as
> the backend can be sure the guest won't initialize more queues as soon as
> DRIVER_OK Virtio status bit is set. In my v2, I can add one patch to handle this
> case properly, by "destorying" queues metadata as soon as DRIVER_OK is
> received.
> 
> Note that it was the exact reason why I first tried to add support for
> VHOST_USER_SET_STATUS more than two years ago...:
> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.g
> nu.org%2Farchive%2Fhtml%2Fqemu-devel%2F2018-
> 02%2Fmsg04560.html&amp;data=02%7C01%7Cmatan%40mellanox.com%7C
> bed5d361fbff47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461
> b%7C0%7C0%7C637273201984684513&amp;sdata=KGJjdEtEN54duNu41rhBIw
> o4tmdWn6QD4yvdR3zeLI8%3D&amp;reserved=0
> 
> What do you think?

Yes, I agree it may be solved by VHOST_USER_SET_STATUS (and probably a lot of other issues),
But I think we need support also legacy QEMU versions if we can... 
Don't you think so?

> Regards,
> Maxime
  

Hi Matan,

On 6/14/20 8:08 AM, Matan Azrad wrote:
> Hi Maxime
> 
> From: Maxime Coquelin:
>> On 6/9/20 1:09 PM, Matan Azrad wrote:
>>> Hi Maxime
>>>
>>> From: Maxime Coquelin
>>>> Hi Matan,
>>>>
>>>> On 6/8/20 11:19 AM, Matan Azrad wrote:
>>>>> Hi Maxime
>>>>>
>>>>> From: Maxime Coquelin:
>>>>>> Hi Matan,
>>>>>>
>>>>>> On 6/7/20 12:38 PM, Matan Azrad wrote:
>>>>>>> Hi Maxime
>>>>>>>
>>>>>>> Thanks for the huge work.
>>>>>>> Please see a suggestion inline.
>>>>>>>
>>>>>>> From: Maxime Coquelin:
>>>>>>>> Sent: Thursday, May 14, 2020 11:02 AM
>>>>>>>> To: xiaolong.ye@intel.com; Shahaf Shuler
>> <shahafs@mellanox.com>;
>>>>>>>> Matan Azrad <matan@mellanox.com>; amorenoz@redhat.com;
>>>>>>>> xiao.w.wang@intel.com; Slava Ovsiienko
>>>> <viacheslavo@mellanox.com>;
>>>>>>>> dev@dpdk.org
>>>>>>>> Cc: jasowang@redhat.com; lulu@redhat.com; Maxime Coquelin
>>>>>>>> <maxime.coquelin@redhat.com>
>>>>>>>> Subject: [PATCH 9/9] vhost: only use vDPA config workaround if
>>>>>>>> needed
>>>>>>>>
>>>>>>>> Now that we have Virtio device status support, let's only use the
>>>>>>>> vDPA workaround if it is not supported.
>>>>>>>>
>>>>>>>> This patch also document why Virtio device status protocol
>>>>>>>> feature support is strongly advised.
>>>>>>>>
>>>>>>>> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
>>>>>>>> ---
>>>>>>>>  lib/librte_vhost/vhost_user.c | 16 ++++++++++++++--
>>>>>>>>  1 file changed, 14 insertions(+), 2 deletions(-)
>>>>>>>>
>>>>>>>> diff --git a/lib/librte_vhost/vhost_user.c
>>>>>>>> b/lib/librte_vhost/vhost_user.c index e5a44be58d..67e96a872a
>>>>>>>> 100644
>>>>>>>> --- a/lib/librte_vhost/vhost_user.c
>>>>>>>> +++ b/lib/librte_vhost/vhost_user.c
>>>>>>>> @@ -2847,8 +2847,20 @@ vhost_user_msg_handler(int vid, int fd)
>>>>>>>>  	if (!vdpa_dev)
>>>>>>>>  		goto out;
>>>>>>>>
>>>>>>>> -	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
>>>>>>>> -			request == VHOST_USER_SET_VRING_CALL)
>> {
>>>>>>>> +	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
>>>>>>>> +		/*
>>>>>>>> +		 * Workaround when Virtio device status protocol
>>>>>>>> +		 * feature is not supported, wait for
>> SET_VRING_CALL
>>>>>>>> +		 * request. This is not ideal as some frontends like
>>>>>>>> +		 * Virtio-user may not send this request, so vDPA
>> device
>>>>>>>> +		 * may never be configured. Virtio device status
>> support
>>>>>>>> +		 * on frontend side is strongly advised.
>>>>>>>> +		 */
>>>>>>>> +		if (!(dev->protocol_features &
>>>>>>>> +				(1ULL <<
>>>>>>>> VHOST_USER_PROTOCOL_F_STATUS)) &&
>>>>>>>> +				(request !=
>>>>>>>> VHOST_USER_SET_VRING_CALL))
>>>>>>>> +			goto out;
>>>>>>>> +
>>>>>>>
>>>>>>> When status protocol feature is not supported, in the current
>>>>>>> code, the
>>>>>> vDPA configuration triggering depends in:
>>>>>>> 1. Device is ready - all the queues are configured (datapath
>>>>>>> addresses,
>>>>>> callfd and kickfd) .
>>>>>>> 2. last command is callfd.
>>>>>>>
>>>>>>>
>>>>>>> The code doesn't take into account that some queues may stay
>> disabled.
>>>>>>> Maybe the correct timing is:
>>>>>>> 1. Device is ready - all the enabled queues are configured and MEM
>>>>>>> table is
>>>>>> configured.
>>>>>>
>>>>>> I think current virtio_is_ready() already assumes the mem table is
>>>>>> configured, otherwise we would not have vq->desc, vq->used and
>>>>>> vq->avail being set as it needs to be translated using the mem table.
>>>>>>
>>>>> Yes, but if you don't expect to check them for disabled queues you
>>>>> need to
>>>> check mem table to be sure it was set.
>>>>
>>>> Even disabled queues should be allocated/configured by the guest driver.
>>> Is it by spec?
>>
>> Sorry, that was a misunderstanding from my side.
>> The number of queues set by the driver using MQ_VQ_PAIRS_SET control
>> message have to be allocated and configured by the driver:
>> https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fdocs.o
>> asis-open.org%2Fvirtio%2Fvirtio%2Fv1.0%2Fcs04%2Fvirtio-v1.0-
>> cs04.html%23x1-
>> 1940001&amp;data=02%7C01%7Cmatan%40mellanox.com%7Cbed5d361fbff
>> 47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0%
>> 7C637273201984684513&amp;sdata=zbBLclza39Fi5QenFtRx%2F1T29Dgj4w%2
>> FudJ6obp5RxYo%3D&amp;reserved=0
>>
> 
> Do you mean to the sentence:
> "The driver MUST configure the virtqueues before enabling them with the VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET command." ?
> 
> Maybe I miss English understanding here but it looks like this sentence doesn't say if the driver should do configuration for queues that will not be enabled by the virtio driver (stay disabled forever).
> 
> 
>>> We saw that windows virtio guest driver doesn't configure disabled
>> queues.
>>> Is it bug in windows guest?
>>> You probably can take a look here:
>>> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgith
>>> ub.com%2Fvirtio-win%2Fkvm-guest-drivers-
>> windows&amp;data=02%7C01%7Cmat
>>>
>> an%40mellanox.com%7Cbed5d361fbff47ab766008d80c99cc53%7Ca652971c7d
>> 2e4d9
>>>
>> ba6a4d149256f461b%7C0%7C0%7C637273201984684513&amp;sdata=%2BqPf
>> myvTw1T
>>> RFif9woeR%2BsndUEunfR5O9EegJfilDI0%3D&amp;reserved=0
>>>
>>
>> Indeed it limits the number of queue pairs to the number of CPUs.
>> This is done here:
>> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithu
>> b.com%2Fvirtio-win%2Fkvm-guest-drivers-
>> windows%2Fblob%2Fedda3f50a17015aab1450ca09e3263c7409e4001%2FNetK
>> VM%2FCommon%2FParaNdis_Common.cpp%23L956&amp;data=02%7C01%
>> 7Cmatan%40mellanox.com%7Cbed5d361fbff47ab766008d80c99cc53%7Ca652
>> 971c7d2e4d9ba6a4d149256f461b%7C0%7C0%7C637273201984684513&amp;s
>> data=XXFIkVJWFacUMZLJwsKyoy6%2Bcqkn5f60fEC9rmMpaNI%3D&amp;res
>> erved=0
>>
>> Linux does the same by the way:
>> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Felixir.
>> bootlin.com%2Flinux%2Flatest%2Fsource%2Fdrivers%2Fnet%2Fvirtio_net.c
>> %23L3092&amp;data=02%7C01%7Cmatan%40mellanox.com%7Cbed5d361fbf
>> f47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0
>> %7C637273201984684513&amp;sdata=ef6KJLHkkaGf5d6V8%2BI8N1WsI0Q3x
>> X31jz2Y8oUSeNE%3D&amp;reserved=0
> 
> Yes, I think it makes sense.
> 
>> We rarely face this issue because by default, the management layers usually
>> set the number of queue pairs to the number of vCPUs if multiqueue is
>> enabled. But the problem is real.
>>
>> In my opinion, the problem is more on Vhost-user spec side and/or Vhost-
>> user backend.
>>
>> The DPDK backend allocates queue pairs for every time it receives a Vhost-
>> user message setting a new queue (callfd, kickfd, enable,... see
>> vhost_user_check_and_alloc_queue_pair()). And then virtio_is_ready()
>> waits for all the allocated queue pairs to be initialized.
>>
>> The problem is that QEMU sends some if these messages even for queues
>> that aren't (or won't be) initialized, as you can see in below log where I
>> reproduced the issue with Windows 10:
>> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fpaste
>> bin.com%2FYYCfW9Y3&amp;data=02%7C01%7Cmatan%40mellanox.com%7C
>> bed5d361fbff47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461
>> b%7C0%7C0%7C637273201984684513&amp;sdata=MBG09v4BscpX5%2Bf%2Bl
>> 7EOwhJcrpvoH7Wo3ISTLOxC6Lk%3D&amp;reserved=0
>>
>> I don't see how the backend could know the guest driver is done with
>> currently received information from Qemu as it seems to him some queues
>> are partially initialized (callfd is set).
> 
> Don’t you think that only enabled queues must be fully initialized when their status is changed from disabled to enabled?
> So, you can assume that disabled queues can stay "not fully initialized"...

That may work but might not be following the Virtio spec as with 1.0 we
shouldn't process the rings before DRIVER_OK is set (but we cannot be
sure we follow it anyway without SET_STATUS support).

I propose to cook a patch doing the following:
1. virtio_is_ready() will only ensure the first queue pair is ready
(i.e. enabled and configured). Meaning that app's new_device callback
and vDPA drivers dev_conf callback will be called with only the first
queue pair configured and enabled.

2. Before handling a new vhost-user request, it saves the ready status
for every queue pair.

3. Same handling of the requests, except that we won't notify the vdpa
driver and the application of vring state changes in the
VHOST_USER_SET_VRING_ENABLE handler.

4. Once the Vhost-user request is handled, it compares the new ready
status foe every queues with the old one and send queue state event
changes accordingly.

It is likely to need changes in the .dev_conf and .set_vring_state
implementations by the drivers.

> 
>> With VHOST_USER_SET_STATUS, we will be able to handle this properly, as
>> the backend can be sure the guest won't initialize more queues as soon as
>> DRIVER_OK Virtio status bit is set. In my v2, I can add one patch to handle this
>> case properly, by "destorying" queues metadata as soon as DRIVER_OK is
>> received.
>>
>> Note that it was the exact reason why I first tried to add support for
>> VHOST_USER_SET_STATUS more than two years ago...:
>> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.g
>> nu.org%2Farchive%2Fhtml%2Fqemu-devel%2F2018-
>> 02%2Fmsg04560.html&amp;data=02%7C01%7Cmatan%40mellanox.com%7C
>> bed5d361fbff47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461
>> b%7C0%7C0%7C637273201984684513&amp;sdata=KGJjdEtEN54duNu41rhBIw
>> o4tmdWn6QD4yvdR3zeLI8%3D&amp;reserved=0
>>
>> What do you think?
> 
> Yes, I agree it may be solved by VHOST_USER_SET_STATUS (and probably a lot of other issues),
> But I think we need support also legacy QEMU versions if we can...

I think the SET_STATUS support is important to be compliant with the
Virtio specifictation.

> Don't you think so?

We can try that.
I will try to cook something this week, but it will require validation
with OVS to be sure we don't break multiqueue. I will send it as RFC,
and count on you to try it with your mlx5 vDPA driver.

Does it work for you? (note I'll be on vacation from July 1st to 17th)

Thanks,
Maxime

>> Regards,
>> Maxime
>
  

Hi Maxime

From: Maxime Coquelin:
> Hi Matan,
> 
> On 6/14/20 8:08 AM, Matan Azrad wrote:
> > Hi Maxime
> >
> > From: Maxime Coquelin:
> >> On 6/9/20 1:09 PM, Matan Azrad wrote:
> >>> Hi Maxime
> >>>
> >>> From: Maxime Coquelin
> >>>> Hi Matan,
> >>>>
> >>>> On 6/8/20 11:19 AM, Matan Azrad wrote:
> >>>>> Hi Maxime
> >>>>>
> >>>>> From: Maxime Coquelin:
> >>>>>> Hi Matan,
> >>>>>>
> >>>>>> On 6/7/20 12:38 PM, Matan Azrad wrote:
> >>>>>>> Hi Maxime
> >>>>>>>
> >>>>>>> Thanks for the huge work.
> >>>>>>> Please see a suggestion inline.
> >>>>>>>
> >>>>>>> From: Maxime Coquelin:
> >>>>>>>> Sent: Thursday, May 14, 2020 11:02 AM
> >>>>>>>> To: xiaolong.ye@intel.com; Shahaf Shuler
> >> <shahafs@mellanox.com>;
> >>>>>>>> Matan Azrad <matan@mellanox.com>; amorenoz@redhat.com;
> >>>>>>>> xiao.w.wang@intel.com; Slava Ovsiienko
> >>>> <viacheslavo@mellanox.com>;
> >>>>>>>> dev@dpdk.org
> >>>>>>>> Cc: jasowang@redhat.com; lulu@redhat.com; Maxime Coquelin
> >>>>>>>> <maxime.coquelin@redhat.com>
> >>>>>>>> Subject: [PATCH 9/9] vhost: only use vDPA config workaround if
> >>>>>>>> needed
> >>>>>>>>
> >>>>>>>> Now that we have Virtio device status support, let's only use
> >>>>>>>> the vDPA workaround if it is not supported.
> >>>>>>>>
> >>>>>>>> This patch also document why Virtio device status protocol
> >>>>>>>> feature support is strongly advised.
> >>>>>>>>
> >>>>>>>> Signed-off-by: Maxime Coquelin
> <maxime.coquelin@redhat.com>
> >>>>>>>> ---
> >>>>>>>>  lib/librte_vhost/vhost_user.c | 16 ++++++++++++++--
> >>>>>>>>  1 file changed, 14 insertions(+), 2 deletions(-)
> >>>>>>>>
> >>>>>>>> diff --git a/lib/librte_vhost/vhost_user.c
> >>>>>>>> b/lib/librte_vhost/vhost_user.c index e5a44be58d..67e96a872a
> >>>>>>>> 100644
> >>>>>>>> --- a/lib/librte_vhost/vhost_user.c
> >>>>>>>> +++ b/lib/librte_vhost/vhost_user.c
> >>>>>>>> @@ -2847,8 +2847,20 @@ vhost_user_msg_handler(int vid, int
> fd)
> >>>>>>>>  	if (!vdpa_dev)
> >>>>>>>>  		goto out;
> >>>>>>>>
> >>>>>>>> -	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
> >>>>>>>> -			request == VHOST_USER_SET_VRING_CALL)
> >> {
> >>>>>>>> +	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
> >>>>>>>> +		/*
> >>>>>>>> +		 * Workaround when Virtio device status protocol
> >>>>>>>> +		 * feature is not supported, wait for
> >> SET_VRING_CALL
> >>>>>>>> +		 * request. This is not ideal as some frontends like
> >>>>>>>> +		 * Virtio-user may not send this request, so vDPA
> >> device
> >>>>>>>> +		 * may never be configured. Virtio device status
> >> support
> >>>>>>>> +		 * on frontend side is strongly advised.
> >>>>>>>> +		 */
> >>>>>>>> +		if (!(dev->protocol_features &
> >>>>>>>> +				(1ULL <<
> >>>>>>>> VHOST_USER_PROTOCOL_F_STATUS)) &&
> >>>>>>>> +				(request !=
> >>>>>>>> VHOST_USER_SET_VRING_CALL))
> >>>>>>>> +			goto out;
> >>>>>>>> +
> >>>>>>>
> >>>>>>> When status protocol feature is not supported, in the current
> >>>>>>> code, the
> >>>>>> vDPA configuration triggering depends in:
> >>>>>>> 1. Device is ready - all the queues are configured (datapath
> >>>>>>> addresses,
> >>>>>> callfd and kickfd) .
> >>>>>>> 2. last command is callfd.
> >>>>>>>
> >>>>>>>
> >>>>>>> The code doesn't take into account that some queues may stay
> >> disabled.
> >>>>>>> Maybe the correct timing is:
> >>>>>>> 1. Device is ready - all the enabled queues are configured and
> >>>>>>> MEM table is
> >>>>>> configured.
> >>>>>>
> >>>>>> I think current virtio_is_ready() already assumes the mem table
> >>>>>> is configured, otherwise we would not have vq->desc, vq->used and
> >>>>>> vq->avail being set as it needs to be translated using the mem table.
> >>>>>>
> >>>>> Yes, but if you don't expect to check them for disabled queues you
> >>>>> need to
> >>>> check mem table to be sure it was set.
> >>>>
> >>>> Even disabled queues should be allocated/configured by the guest
> driver.
> >>> Is it by spec?
> >>
> >> Sorry, that was a misunderstanding from my side.
> >> The number of queues set by the driver using MQ_VQ_PAIRS_SET control
> >> message have to be allocated and configured by the driver:
> >>
> https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fdocs
> >> .o
> >> asis-open.org%2Fvirtio%2Fvirtio%2Fv1.0%2Fcs04%2Fvirtio-v1.0-
> >> cs04.html%23x1-
> >>
> 1940001&amp;data=02%7C01%7Cmatan%40mellanox.com%7Cbed5d361fbff
> >>
> 47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0%
> >>
> 7C637273201984684513&amp;sdata=zbBLclza39Fi5QenFtRx%2F1T29Dgj4w%2
> >> FudJ6obp5RxYo%3D&amp;reserved=0
> >>
> >
> > Do you mean to the sentence:
> > "The driver MUST configure the virtqueues before enabling them with the
> VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET command." ?
> >
> > Maybe I miss English understanding here but it looks like this sentence
> doesn't say if the driver should do configuration for queues that will not be
> enabled by the virtio driver (stay disabled forever).
> >
> >
> >>> We saw that windows virtio guest driver doesn't configure disabled
> >> queues.
> >>> Is it bug in windows guest?
> >>> You probably can take a look here:
> >>>
> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgi
> >>> th
> >>> ub.com%2Fvirtio-win%2Fkvm-guest-drivers-
> >> windows&amp;data=02%7C01%7Cmat
> >>>
> >>
> an%40mellanox.com%7Cbed5d361fbff47ab766008d80c99cc53%7Ca652971c7d
> >> 2e4d9
> >>>
> >>
> ba6a4d149256f461b%7C0%7C0%7C637273201984684513&amp;sdata=%2BqPf
> >> myvTw1T
> >>> RFif9woeR%2BsndUEunfR5O9EegJfilDI0%3D&amp;reserved=0
> >>>
> >>
> >> Indeed it limits the number of queue pairs to the number of CPUs.
> >> This is done here:
> >> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgit
> >> hu
> >> b.com%2Fvirtio-win%2Fkvm-guest-drivers-
> >>
> windows%2Fblob%2Fedda3f50a17015aab1450ca09e3263c7409e4001%2FNetK
> >>
> VM%2FCommon%2FParaNdis_Common.cpp%23L956&amp;data=02%7C01%
> >>
> 7Cmatan%40mellanox.com%7Cbed5d361fbff47ab766008d80c99cc53%7Ca652
> >>
> 971c7d2e4d9ba6a4d149256f461b%7C0%7C0%7C637273201984684513&amp;s
> >>
> data=XXFIkVJWFacUMZLJwsKyoy6%2Bcqkn5f60fEC9rmMpaNI%3D&amp;res
> >> erved=0
> >>
> >> Linux does the same by the way:
> >>
> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Felixir.
> >>
> bootlin.com%2Flinux%2Flatest%2Fsource%2Fdrivers%2Fnet%2Fvirtio_net.c
> >>
> %23L3092&amp;data=02%7C01%7Cmatan%40mellanox.com%7Cbed5d361fbf
> >>
> f47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0
> >>
> %7C637273201984684513&amp;sdata=ef6KJLHkkaGf5d6V8%2BI8N1WsI0Q3x
> >> X31jz2Y8oUSeNE%3D&amp;reserved=0
> >
> > Yes, I think it makes sense.
> >
> >> We rarely face this issue because by default, the management layers
> >> usually set the number of queue pairs to the number of vCPUs if
> >> multiqueue is enabled. But the problem is real.
> >>
> >> In my opinion, the problem is more on Vhost-user spec side and/or
> >> Vhost- user backend.
> >>
> >> The DPDK backend allocates queue pairs for every time it receives a
> >> Vhost- user message setting a new queue (callfd, kickfd, enable,...
> >> see vhost_user_check_and_alloc_queue_pair()). And then
> >> virtio_is_ready() waits for all the allocated queue pairs to be initialized.
> >>
> >> The problem is that QEMU sends some if these messages even for
> queues
> >> that aren't (or won't be) initialized, as you can see in below log
> >> where I reproduced the issue with Windows 10:
> >>
> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fpas
> >> te
> bin.com%2FYYCfW9Y3&amp;data=02%7C01%7Cmatan%40mellanox.com%7C
> >>
> bed5d361fbff47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461
> >>
> b%7C0%7C0%7C637273201984684513&amp;sdata=MBG09v4BscpX5%2Bf%2Bl
> >> 7EOwhJcrpvoH7Wo3ISTLOxC6Lk%3D&amp;reserved=0
> >>
> >> I don't see how the backend could know the guest driver is done with
> >> currently received information from Qemu as it seems to him some
> >> queues are partially initialized (callfd is set).
> >
> > Don’t you think that only enabled queues must be fully initialized when
> their status is changed from disabled to enabled?
> > So, you can assume that disabled queues can stay "not fully initialized"...
> 
> That may work but might not be following the Virtio spec as with 1.0 we
> shouldn't process the rings before DRIVER_OK is set (but we cannot be sure
> we follow it anyway without SET_STATUS support).
> 
> I propose to cook a patch doing the following:
> 1. virtio_is_ready() will only ensure the first queue pair is ready (i.e. enabled
> and configured). Meaning that app's new_device callback and vDPA drivers
> dev_conf callback will be called with only the first queue pair configured and
> enabled.
> 
> 2. Before handling a new vhost-user request, it saves the ready status for
> every queue pair.
> 
> 3. Same handling of the requests, except that we won't notify the vdpa
> driver and the application of vring state changes in the
> VHOST_USER_SET_VRING_ENABLE handler.
> 
> 4. Once the Vhost-user request is handled, it compares the new ready status
> foe every queues with the old one and send queue state event changes
> accordingly.

Looks very nice to me.

More points:
By this method some queues may be configured by the set_vring_state operation so the next calls are expected to be called for each queue by the driver from the set_vring_state callback :
1. rte_vhost_enable_guest_notification
	This one takes datapath lock so we need to be sure that datapath lock is not locked on this queue from the same caller thread (maybe to not takes datapath locks when vdpa is configured at all).
2. rte_vhost_host_notifier_ctrl
	This function API is per device and not per queue, maybe we need to change this function to be per queue (add new for now and deprecate the old one in 20.11).

3. Need to be sure that if ready queue configuration is changed after dev_conf, we should notify it to the driver. (maybe by set_vring_state(disabl) and set_vring_state(enable)).


> It is likely to need changes in the .dev_conf and .set_vring_state
> implementations by the drivers.

Yes, for Mellanox it is very easy change.
Intel?

 
> >
> >> With VHOST_USER_SET_STATUS, we will be able to handle this properly,
> >> as the backend can be sure the guest won't initialize more queues as
> >> soon as DRIVER_OK Virtio status bit is set. In my v2, I can add one
> >> patch to handle this case properly, by "destorying" queues metadata
> >> as soon as DRIVER_OK is received.
> >>
> >> Note that it was the exact reason why I first tried to add support
> >> for VHOST_USER_SET_STATUS more than two years ago...:
> >> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Flis
> >> ts.g
> >> nu.org%2Farchive%2Fhtml%2Fqemu-devel%2F2018-
> >>
> 02%2Fmsg04560.html&amp;data=02%7C01%7Cmatan%40mellanox.com%7C
> >>
> bed5d361fbff47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461
> >>
> b%7C0%7C0%7C637273201984684513&amp;sdata=KGJjdEtEN54duNu41rhBIw
> >> o4tmdWn6QD4yvdR3zeLI8%3D&amp;reserved=0
> >>
> >> What do you think?
> >
> > Yes, I agree it may be solved by VHOST_USER_SET_STATUS (and probably a
> > lot of other issues), But I think we need support also legacy QEMU versions
> if we can...
> 
> I think the SET_STATUS support is important to be compliant with the Virtio
> specifictation.
> 
> > Don't you think so?

Yes, I agree.

> 
> We can try that.
> I will try to cook something this week, but it will require validation with OVS
> to be sure we don't break multiqueue. I will send it as RFC, and count on you
> to try it with your mlx5 vDPA driver.
> 
> Does it work for you? (note I'll be on vacation from July 1st to 17th)

Sure,
Do you have capacity to do it this week?
I can help..... 

Matan


> 
> Thanks,
> Maxime
> 
> >> Regards,
> >> Maxime
> >
  

On 6/17/20 1:04 PM, Matan Azrad wrote:

>>> Don’t you think that only enabled queues must be fully initialized when
>> their status is changed from disabled to enabled?
>>> So, you can assume that disabled queues can stay "not fully initialized"...
>>
>> That may work but might not be following the Virtio spec as with 1.0 we
>> shouldn't process the rings before DRIVER_OK is set (but we cannot be sure
>> we follow it anyway without SET_STATUS support).
>>
>> I propose to cook a patch doing the following:
>> 1. virtio_is_ready() will only ensure the first queue pair is ready (i.e. enabled
>> and configured). Meaning that app's new_device callback and vDPA drivers
>> dev_conf callback will be called with only the first queue pair configured and
>> enabled.
>>
>> 2. Before handling a new vhost-user request, it saves the ready status for
>> every queue pair.
>>
>> 3. Same handling of the requests, except that we won't notify the vdpa
>> driver and the application of vring state changes in the
>> VHOST_USER_SET_VRING_ENABLE handler.
>>
>> 4. Once the Vhost-user request is handled, it compares the new ready status
>> foe every queues with the old one and send queue state event changes
>> accordingly.
> 
> Looks very nice to me.

Cool!

> More points:
> By this method some queues may be configured by the set_vring_state operation so the next calls are expected to be called for each queue by the driver from the set_vring_state callback :
> 1. rte_vhost_enable_guest_notification
> 	This one takes datapath lock so we need to be sure that datapath lock is not locked on this queue from the same caller thread (maybe to not takes datapath locks when vdpa is configured at all).

Good point, I agree we shouldn't need to use the access lock when vdpa
is configured. We may want to document that all the control path is
assumed to be single thread though.


> 2. rte_vhost_host_notifier_ctrl
> 	This function API is per device and not per queue, maybe we need to change this function to be per queue (add new for now and deprecate the old one in 20.11).

This one is still experimental, so no issue in reworking the API to make
it per queue without deprecation notice.

> 3. Need to be sure that if ready queue configuration is changed after dev_conf, we should notify it to the driver. (maybe by set_vring_state(disabl) and set_vring_state(enable)).

Agree, I'm not sure yet if we should just toggle set_vring_state as you
proposes, or if we should have a new callback for this.

>> It is likely to need changes in the .dev_conf and .set_vring_state
>> implementations by the drivers.
> 
> Yes, for Mellanox it is very easy change.
> Intel?
> 
>  
>>>
>>>> With VHOST_USER_SET_STATUS, we will be able to handle this properly,
>>>> as the backend can be sure the guest won't initialize more queues as
>>>> soon as DRIVER_OK Virtio status bit is set. In my v2, I can add one
>>>> patch to handle this case properly, by "destorying" queues metadata
>>>> as soon as DRIVER_OK is received.
>>>>
>>>> Note that it was the exact reason why I first tried to add support
>>>> for VHOST_USER_SET_STATUS more than two years ago...:
>>>> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Flis
>>>> ts.g
>>>> nu.org%2Farchive%2Fhtml%2Fqemu-devel%2F2018-
>>>>
>> 02%2Fmsg04560.html&data=02%7C01%7Cmatan%40mellanox.com%7C
>>>>
>> bed5d361fbff47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461
>>>>
>> b%7C0%7C0%7C637273201984684513&sdata=KGJjdEtEN54duNu41rhBIw
>>>> o4tmdWn6QD4yvdR3zeLI8%3D&reserved=0
>>>>
>>>> What do you think?
>>>
>>> Yes, I agree it may be solved by VHOST_USER_SET_STATUS (and probably a
>>> lot of other issues), But I think we need support also legacy QEMU versions
>> if we can...
>>
>> I think the SET_STATUS support is important to be compliant with the Virtio
>> specifictation.
>>
>>> Don't you think so?
> 
> Yes, I agree.
> 
>>
>> We can try that.
>> I will try to cook something this week, but it will require validation with OVS
>> to be sure we don't break multiqueue. I will send it as RFC, and count on you
>> to try it with your mlx5 vDPA driver.
>>
>> Does it work for you? (note I'll be on vacation from July 1st to 17th)
> 
> Sure,
> Do you have capacity to do it this week?
> I can help..... 

That would be welcome, as I initially planned to spend time on reviewing
& merging patches this week.

Thanks,
Maxime
> Matan
> 
> 
>>
>> Thanks,
>> Maxime
>>
>>>> Regards,
>>>> Maxime
>>>
>
  

HI Maxime

From: Maxime Coquelin:
> On 6/17/20 1:04 PM, Matan Azrad wrote:
> 
> >>> Don’t you think that only enabled queues must be fully initialized
> >>> when
> >> their status is changed from disabled to enabled?
> >>> So, you can assume that disabled queues can stay "not fully initialized"...
> >>
> >> That may work but might not be following the Virtio spec as with 1.0
> >> we shouldn't process the rings before DRIVER_OK is set (but we cannot
> >> be sure we follow it anyway without SET_STATUS support).
> >>
> >> I propose to cook a patch doing the following:
> >> 1. virtio_is_ready() will only ensure the first queue pair is ready
> >> (i.e. enabled and configured). Meaning that app's new_device callback
> >> and vDPA drivers dev_conf callback will be called with only the first
> >> queue pair configured and enabled.
> >>
> >> 2. Before handling a new vhost-user request, it saves the ready
> >> status for every queue pair.
> >>
> >> 3. Same handling of the requests, except that we won't notify the
> >> vdpa driver and the application of vring state changes in the
> >> VHOST_USER_SET_VRING_ENABLE handler.
> >>
> >> 4. Once the Vhost-user request is handled, it compares the new ready
> >> status foe every queues with the old one and send queue state event
> >> changes accordingly.
> >
> > Looks very nice to me.
> 
> Cool!
> 
> > More points:
> > By this method some queues may be configured by the set_vring_state
> operation so the next calls are expected to be called for each queue by the
> driver from the set_vring_state callback :
> > 1. rte_vhost_enable_guest_notification
> > 	This one takes datapath lock so we need to be sure that datapath
> lock is not locked on this queue from the same caller thread (maybe to not
> takes datapath locks when vdpa is configured at all).
> 
> Good point, I agree we shouldn't need to use the access lock when vdpa is
> configured. We may want to document that all the control path is assumed to
> be single thread though.
> 
> 
> > 2. rte_vhost_host_notifier_ctrl
> > 	This function API is per device and not per queue, maybe we need to
> change this function to be per queue (add new for now and deprecate the
> old one in 20.11).
> 
> This one is still experimental, so no issue in reworking the API to make it per
> queue without deprecation notice.
> 
> > 3. Need to be sure that if ready queue configuration is changed after
> dev_conf, we should notify it to the driver. (maybe by
> set_vring_state(disabl) and set_vring_state(enable)).
> 
> Agree, I'm not sure yet if we should just toggle set_vring_state as you
> proposes, or if we should have a new callback for this.

Actually, when the queue configuration is changed, there is one moment that configuration is not valid (in the write time).
So maybe it makes sense to toggle.

But there is one more option:

It doesn't make sense that after configuration change the QEMU will not send VHOST_USER_SET_VRING_ENABLE massage.

So maybe we need to call set_vring_state in the next events:
	1. queue becomes ready (enabled and fully configured) - set_vring_state(enable).
	2. queue becomes not ready - set_vring_state(disable).
	3. queue stay ready and VHOST_USER_SET_VRING_ENABLE massage was handled - set_vring_state(enable).

Then we need to document that every set_vring_state call may point on configuration changes in the queue even if the state was not changed.

What do you think?



> >> It is likely to need changes in the .dev_conf and .set_vring_state
> >> implementations by the drivers.
> >
> > Yes, for Mellanox it is very easy change.
> > Intel?
> >
> >
> >>>
> >>>> With VHOST_USER_SET_STATUS, we will be able to handle this
> >>>> properly, as the backend can be sure the guest won't initialize
> >>>> more queues as soon as DRIVER_OK Virtio status bit is set. In my
> >>>> v2, I can add one patch to handle this case properly, by
> >>>> "destorying" queues metadata as soon as DRIVER_OK is received.
> >>>>
> >>>> Note that it was the exact reason why I first tried to add support
> >>>> for VHOST_USER_SET_STATUS more than two years ago...:
> >>>>
> https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fl
> >>>> is
> >>>> ts.g
> >>>> nu.org%2Farchive%2Fhtml%2Fqemu-devel%2F2018-
> >>>>
> >>
> 02%2Fmsg04560.html&data=02%7C01%7Cmatan%40mellanox.com%7C
> >>>>
> >>
> bed5d361fbff47ab766008d80c99cc53%7Ca652971c7d2e4d9ba6a4d149256f461
> >>>>
> >>
> b%7C0%7C0%7C637273201984684513&sdata=KGJjdEtEN54duNu41rhBIw
> >>>> o4tmdWn6QD4yvdR3zeLI8%3D&reserved=0
> >>>>
> >>>> What do you think?
> >>>
> >>> Yes, I agree it may be solved by VHOST_USER_SET_STATUS (and
> probably
> >>> a lot of other issues), But I think we need support also legacy QEMU
> >>> versions
> >> if we can...
> >>
> >> I think the SET_STATUS support is important to be compliant with the
> >> Virtio specifictation.
> >>
> >>> Don't you think so?
> >
> > Yes, I agree.
> >
> >>
> >> We can try that.
> >> I will try to cook something this week, but it will require
> >> validation with OVS to be sure we don't break multiqueue. I will send
> >> it as RFC, and count on you to try it with your mlx5 vDPA driver.
> >>
> >> Does it work for you? (note I'll be on vacation from July 1st to
> >> 17th)
> >
> > Sure,
> > Do you have capacity to do it this week?
> > I can help.....
> 
> That would be welcome, as I initially planned to spend time on reviewing &
> merging patches this week.
> 
> Thanks,
> Maxime
> > Matan
> >
> >
> >>
> >> Thanks,
> >> Maxime
> >>
> >>>> Regards,
> >>>> Maxime
> >>>
> >
  

On 6/18/20 8:39 AM, Matan Azrad wrote:
> HI Maxime
> 
> From: Maxime Coquelin:
>> On 6/17/20 1:04 PM, Matan Azrad wrote:
>>
>>>>> Don’t you think that only enabled queues must be fully initialized
>>>>> when
>>>> their status is changed from disabled to enabled?
>>>>> So, you can assume that disabled queues can stay "not fully initialized"...
>>>>
>>>> That may work but might not be following the Virtio spec as with 1.0
>>>> we shouldn't process the rings before DRIVER_OK is set (but we cannot
>>>> be sure we follow it anyway without SET_STATUS support).
>>>>
>>>> I propose to cook a patch doing the following:
>>>> 1. virtio_is_ready() will only ensure the first queue pair is ready
>>>> (i.e. enabled and configured). Meaning that app's new_device callback
>>>> and vDPA drivers dev_conf callback will be called with only the first
>>>> queue pair configured and enabled.
>>>>
>>>> 2. Before handling a new vhost-user request, it saves the ready
>>>> status for every queue pair.
>>>>
>>>> 3. Same handling of the requests, except that we won't notify the
>>>> vdpa driver and the application of vring state changes in the
>>>> VHOST_USER_SET_VRING_ENABLE handler.
>>>>
>>>> 4. Once the Vhost-user request is handled, it compares the new ready
>>>> status foe every queues with the old one and send queue state event
>>>> changes accordingly.
>>>
>>> Looks very nice to me.
>>
>> Cool!
>>
>>> More points:
>>> By this method some queues may be configured by the set_vring_state
>> operation so the next calls are expected to be called for each queue by the
>> driver from the set_vring_state callback :
>>> 1. rte_vhost_enable_guest_notification
>>> 	This one takes datapath lock so we need to be sure that datapath
>> lock is not locked on this queue from the same caller thread (maybe to not
>> takes datapath locks when vdpa is configured at all).
>>
>> Good point, I agree we shouldn't need to use the access lock when vdpa is
>> configured. We may want to document that all the control path is assumed to
>> be single thread though.
>>
>>
>>> 2. rte_vhost_host_notifier_ctrl
>>> 	This function API is per device and not per queue, maybe we need to
>> change this function to be per queue (add new for now and deprecate the
>> old one in 20.11).
>>
>> This one is still experimental, so no issue in reworking the API to make it per
>> queue without deprecation notice.
>>
>>> 3. Need to be sure that if ready queue configuration is changed after
>> dev_conf, we should notify it to the driver. (maybe by
>> set_vring_state(disabl) and set_vring_state(enable)).
>>
>> Agree, I'm not sure yet if we should just toggle set_vring_state as you
>> proposes, or if we should have a new callback for this.
> 
> Actually, when the queue configuration is changed, there is one moment that configuration is not valid (in the write time).
> So maybe it makes sense to toggle.
> 
> But there is one more option:
> 
> It doesn't make sense that after configuration change the QEMU will not send VHOST_USER_SET_VRING_ENABLE massage.

Agree.
> So maybe we need to call set_vring_state in the next events:
> 	1. queue becomes ready (enabled and fully configured) - set_vring_state(enable).
> 	2. queue becomes not ready - set_vring_state(disable).
> 	3. queue stay ready and VHOST_USER_SET_VRING_ENABLE massage was handled - set_vring_state(enable).
> 
> Then we need to document that every set_vring_state call may point on configuration changes in the queue even if the state was not changed.
> 
> What do you think?

I think it is worth a try.

Thanks,
Maxime
  

Hi,

The original issue is with legacy QEMU (e.g.QEMUv2.6, with centos7.2 as guest kernel, without set_vring_status as an indicator).
For a normal boot, the last 2 messages are set_vring_kick and set_vring_call, inside the set_vring_kick handling,
virtio_is_ready() will reture true (because of that special very early set_vring_call message). Then
vdpa dev_config is called, and the fake call fd is used. As a result, the virtio kernel driver in VM will not
receive interrupt.

+1 for introducing SET_STATUS to make things clearer.
IFCVF driver hasn't added support for MQ and .set_vring_state ops, so no need to test,

Just curious about MQ live migration case, on the dst side, will this SET_STATUS msg comes to vhost-user? and When?

BRs,
Xiao

> -----Original Message-----
> From: Maxime Coquelin <maxime.coquelin@redhat.com>
> Sent: Thursday, June 18, 2020 3:31 PM
> To: Matan Azrad <matan@mellanox.com>; Ye, Xiaolong
> <xiaolong.ye@intel.com>; Shahaf Shuler <shahafs@mellanox.com>;
> amorenoz@redhat.com; Wang, Xiao W <xiao.w.wang@intel.com>; Slava
> Ovsiienko <viacheslavo@mellanox.com>; dev@dpdk.org
> Cc: jasowang@redhat.com; lulu@redhat.com
> Subject: Re: [PATCH 9/9] vhost: only use vDPA config workaround if needed
> 
> 
> 
> On 6/18/20 8:39 AM, Matan Azrad wrote:
> > HI Maxime
> >
> > From: Maxime Coquelin:
> >> On 6/17/20 1:04 PM, Matan Azrad wrote:
> >>
> >>>>> Don’t you think that only enabled queues must be fully initialized
> >>>>> when
> >>>> their status is changed from disabled to enabled?
> >>>>> So, you can assume that disabled queues can stay "not fully
> initialized"...
> >>>>
> >>>> That may work but might not be following the Virtio spec as with 1.0
> >>>> we shouldn't process the rings before DRIVER_OK is set (but we cannot
> >>>> be sure we follow it anyway without SET_STATUS support).
> >>>>
> >>>> I propose to cook a patch doing the following:
> >>>> 1. virtio_is_ready() will only ensure the first queue pair is ready
> >>>> (i.e. enabled and configured). Meaning that app's new_device callback
> >>>> and vDPA drivers dev_conf callback will be called with only the first
> >>>> queue pair configured and enabled.
> >>>>
> >>>> 2. Before handling a new vhost-user request, it saves the ready
> >>>> status for every queue pair.
> >>>>
> >>>> 3. Same handling of the requests, except that we won't notify the
> >>>> vdpa driver and the application of vring state changes in the
> >>>> VHOST_USER_SET_VRING_ENABLE handler.
> >>>>
> >>>> 4. Once the Vhost-user request is handled, it compares the new ready
> >>>> status foe every queues with the old one and send queue state event
> >>>> changes accordingly.
> >>>
> >>> Looks very nice to me.
> >>
> >> Cool!
> >>
> >>> More points:
> >>> By this method some queues may be configured by the set_vring_state
> >> operation so the next calls are expected to be called for each queue by the
> >> driver from the set_vring_state callback :
> >>> 1. rte_vhost_enable_guest_notification
> >>> 	This one takes datapath lock so we need to be sure that datapath
> >> lock is not locked on this queue from the same caller thread (maybe to not
> >> takes datapath locks when vdpa is configured at all).
> >>
> >> Good point, I agree we shouldn't need to use the access lock when vdpa is
> >> configured. We may want to document that all the control path is
> assumed to
> >> be single thread though.
> >>
> >>
> >>> 2. rte_vhost_host_notifier_ctrl
> >>> 	This function API is per device and not per queue, maybe we need to
> >> change this function to be per queue (add new for now and deprecate the
> >> old one in 20.11).
> >>
> >> This one is still experimental, so no issue in reworking the API to make it
> per
> >> queue without deprecation notice.
> >>
> >>> 3. Need to be sure that if ready queue configuration is changed after
> >> dev_conf, we should notify it to the driver. (maybe by
> >> set_vring_state(disabl) and set_vring_state(enable)).
> >>
> >> Agree, I'm not sure yet if we should just toggle set_vring_state as you
> >> proposes, or if we should have a new callback for this.
> >
> > Actually, when the queue configuration is changed, there is one moment
> that configuration is not valid (in the write time).
> > So maybe it makes sense to toggle.
> >
> > But there is one more option:
> >
> > It doesn't make sense that after configuration change the QEMU will not
> send VHOST_USER_SET_VRING_ENABLE massage.
> 
> Agree.
> > So maybe we need to call set_vring_state in the next events:
> > 	1. queue becomes ready (enabled and fully configured) -
> set_vring_state(enable).
> > 	2. queue becomes not ready - set_vring_state(disable).
> > 	3. queue stay ready and VHOST_USER_SET_VRING_ENABLE massage
> was handled - set_vring_state(enable).
> >
> > Then we need to document that every set_vring_state call may point on
> configuration changes in the queue even if the state was not changed.
> >
> > What do you think?
> 
> I think it is worth a try.
> 
> Thanks,
> Maxime