[Intel-gfx] [PATCH 11/23] drm/i915/gem: Remove the call for no-evict i915_vma_pin

[Tvrtko Ursulin]

On 03/07/2020 10:23, Chris Wilson wrote:
> Quoting Tvrtko Ursulin (2020-07-03 09:59:01)
>>
>> On 02/07/2020 09:32, Chris Wilson wrote:
>>> Remove the stub i915_vma_pin() used for incrementally pining objects for
>>> execbuf (under the severe restriction that they must not wait on a
>>> resource as we may have already pinned it) and replace it with a
>>> i915_vma_pin_inplace() that is only allowed to reclaim the currently
>>> bound location for the vma (and will never wait for a pinned resource).
>>
>> Hm I thought the point of the previous patch ("drm/i915/gem: Break apart
>> the early i915_vma_pin from execbuf object lookup") was to move the
>> pinning into a phase under the ww lock, where it will be allowed. I
>> misunderstood something?
> 
> Still different locks, and the vm->mutex is still being used for managing
> the iova assignments.

Right, think I get it. For the record I've asked for a cover letter with 
a high level design description. Emphasis on flow of stages through 
execbuf by the end of the series and separation of lookup and 
reservation, and/or vm->mutex (ppgtt space) and obj->wwlock (backing store).

Regards,

Tvrtko