Re: [PATCH v2 2/4] vfio: Move the Intel no-snoop control off of IOMMU_CACHE

[Lu Baolu <baolu.lu@linux.intel.com>]

On 2022/4/13 7:04, Tian, Kevin wrote:
>> From: Jason Gunthorpe<jgg@nvidia.com>
>> Sent: Tuesday, April 12, 2022 9:21 PM
>>
>> On Tue, Apr 12, 2022 at 09:13:27PM +0800, Lu Baolu wrote:
>>
>>>>>> btw as discussed in last version it is not necessarily to recalculate
>>>>>> snoop control globally with this new approach. Will follow up to
>>>>>> clean it up after this series is merged.
>>>>> Agreed. But it also requires the enforce_cache_coherency() to be called
>>>>> only after domain being attached to a device just as VFIO is doing.
>>>> that actually makes sense, right? w/o device attached it's pointless to
>>>> call that interface on a domain...
>>> Agreed. Return -EOPNOTSUPP or -EINVAL to tell the caller that this
>>> operation is invalid before any device attachment.
>> That is backwards. enforce_cache_coherency() succeeds on an empty
>> domain and attach of an incompatible device must fail.
> seems it's just a matter of the default policy on an empty domain. No
> matter we by default allow enforce_cache_coherency succeed or not
> the compatibility check against the default policy must be done anyway
> when attaching a device.
> 
> given most IOMMUs supports force-snooping, allowing it succeed by
> default certainly makes more sense.

Make sense. I will come up with the patches after this series is merged.

Best regards,
baolu