[Intel-gfx] [PATCH v3] drm/i915: Create dumb buffer from LMEM

[Matthew Auld]

On 06/11/2019 11:42, Ramalingam C wrote:
> On 2019-11-05 at 11:47:16 +0000, Chris Wilson wrote:
>> Quoting Ramalingam C (2019-11-05 11:30:29)
>>> When LMEM is supported, dumb buffer preferred to be created from LMEM.
>>>
>>> v2:
>>>    Parameters are reshuffled. [Chris]
>>> v3:
>>>    s/region_id/mem_type
>>>
>>> Signed-off-by: Ramalingam C <ramalingam.c at intel.com>
>>> cc: Matthew Auld <matthew.auld at intel.com>
>>> ---
>>>   drivers/gpu/drm/i915/i915_gem.c | 17 ++++++++++++++---
>>>   1 file changed, 14 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
>>> index 143a8952b736..db72af98905f 100644
>>> --- a/drivers/gpu/drm/i915/i915_gem.c
>>> +++ b/drivers/gpu/drm/i915/i915_gem.c
>>> @@ -44,6 +44,7 @@
>>>   #include "gem/i915_gem_clflush.h"
>>>   #include "gem/i915_gem_context.h"
>>>   #include "gem/i915_gem_ioctls.h"
>>> +#include "gem/i915_gem_lmem.h"
>>>   #include "gem/i915_gem_pm.h"
>>>   #include "gt/intel_engine_user.h"
>>>   #include "gt/intel_gt.h"
>>> @@ -175,6 +176,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
>>>   static int
>>>   i915_gem_create(struct drm_file *file,
>>>                  struct drm_i915_private *dev_priv,
>>> +               enum intel_memory_type mem_type,
>>>                  u64 *size_p,
>>>                  u32 *handle_p)
>>>   {
>>> @@ -188,7 +190,11 @@ i915_gem_create(struct drm_file *file,
>>>                  return -EINVAL;
>>>   
>>>          /* Allocate the new object */
>>> -       obj = i915_gem_object_create_shmem(dev_priv, size);
>>> +       if (mem_type == INTEL_MEMORY_LOCAL)
>>> +               obj = i915_gem_object_create_lmem(dev_priv, size, 0);
>>> +       else
>>> +               obj = i915_gem_object_create_shmem(dev_priv, size);
>>
>> Have you not talked Matthew into creating a
>> i915_gem_object_create_region(?dev_priv?,
>> 			      intel_memory_region_lookup(dev_priv, mem_type),
>> 			      size, flags)
> Sounds a good idea to skip a wrapper function.
> 
> Matt, Is that ok with you?

Sure.

> 
> -Ram
>> yet?
>> -Chris