Re: [Intel-gfx] [PATCH v5 1/5] drm/i915: add needs_compact_pt flag

["Thomas Hellström" <thomas.hellstrom@linux.intel.com>]

On 1/31/22 15:19, Robert Beckett wrote:
>
>
> On 27/01/2022 09:37, Thomas Hellström (Intel) wrote:
>>
>> On 1/26/22 18:11, Robert Beckett wrote:
>>>
>>>
>>> On 26/01/2022 13:49, Thomas Hellström (Intel) wrote:
>>>>
>>>> On 1/25/22 20:35, Robert Beckett wrote:
>>>>> From: Ramalingam C <ramalingam.c@intel.com>
>>>>>
>>>>> Add a new platform flag, needs_compact_pt, to mark the requirement of
>>>>> compact pt layout support for the ppGTT when using 64K GTT pages.
>>>>>
>>>>> With this flag has_64k_pages will only indicate requirement of 64K
>>>>> GTT page sizes or larger for device local memory access.
>>>>>
>>>>> Suggested-by: Matthew Auld <matthew.auld@intel.com>
>>>>> Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
>>>>> Signed-off-by: Robert Beckett <bob.beckett@collabora.com>
>>>>> ---
>>>>>   drivers/gpu/drm/i915/i915_drv.h          | 10 +++++++---
>>>>>   drivers/gpu/drm/i915/i915_pci.c          |  2 ++
>>>>>   drivers/gpu/drm/i915/intel_device_info.h |  1 +
>>>>>   3 files changed, 10 insertions(+), 3 deletions(-)
>>>>>
>>>>> diff --git a/drivers/gpu/drm/i915/i915_drv.h 
>>>>> b/drivers/gpu/drm/i915/i915_drv.h
>>>>> index 44c1f98144b4..1258b7779705 100644
>>>>> --- a/drivers/gpu/drm/i915/i915_drv.h
>>>>> +++ b/drivers/gpu/drm/i915/i915_drv.h
>>>>> @@ -1512,12 +1512,16 @@ IS_SUBPLATFORM(const struct 
>>>>> drm_i915_private *i915,
>>>>>   /*
>>>>>    * Set this flag, when platform requires 64K GTT page sizes or 
>>>>> larger for
>>>>> - * device local memory access. Also this flag implies that we 
>>>>> require or
>>>>> - * at least support the compact PT layout for the ppGTT when 
>>>>> using the 64K
>>>>> - * GTT pages.
>>>>
>>>> Why do we remove these comment lines?
>>> Because HAS_64K_PAGES now means just 64K page, it no longer means 
>>> also requires compact pt.
>>> This is to support other products that will have 64K but not have 
>>> the PDE non-sharing restriction in future.
>>>
>>> Those lines moved to the next change NEEDS_COMPACT_PT, which is now 
>>> separate.
>>
>> Yes, NEEDS_COMPACT_PT indicates that compact is *required* but does 
>> "HAS_64K_PAGES" still mean compact is supported? That information is 
>> lost.
> Not any more.
> I discussed the ambiguity of the original wording with mauld on irc.
> We came to the conclusion that HAS_64K_PAGES should mean just that, 
> that the hw has support for 64K pages, and says nothing about 
> compact-pt at all.
>
> NEEDS_COMPACT_PT means that the hw has compact-pt support and the 
> driver is required to use it as it is a hw limitation.
>
> There will be other devices that can support compact-pt but do not 
> mandate its use. In this case, the current code would not use them, 
> but there is potential for some future opportunistic use of that in 
> the driver if desired (currently expected to include accelerated 
> move/clear). If any opportunistic use is added to the driver, a new 
> flag can be added along with the code that uses it to indicate 
> compact-pt availability that is not mandatory (HAS_COMPACT_PT most 
> likely), but as there is no code requiring it currently it should not 
> be added yet, and the comments left as this patch does.
>
Ok, Thanks for the clarification.

Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>



>>
>> /Thomas
>>
>>