Re: [PATCH 01/14] drm/amdgpu/gmc: Don't hardcode GART page count before GTT

["Timur Kristóf" <timur.kristof@gmail.com>]

On Wed, 2025-10-29 at 11:00 +0100, Christian König wrote:
> On 10/28/25 23:06, Timur Kristóf wrote:
> > GART contains some pages in its address space that come before
> > the GTT and are used for BO copies.
> > 
> > Instead of hardcoding the size of the GART space before GTT,
> > make it a field in the amdgpu_gmc struct. This allows us to map
> > more things in GART before GTT.
> > 
> > Split this into a separate patch to make it easier to bisect,
> > in case there are any errors in the future.
> 
> Pierre-Eric has been working on something similar.
> 
> On the newer HW generations we need more transfer windows since we
> want to utilize more DMA engines for copies and clears.
> 
> My suggestion is that we just make AMDGPU_GTT_NUM_TRANSFER_WINDOWS
> depend on adev and so the HW generation and then reserve one extra
> transfer window for this workaround on SI.

I think the best would be to leave this patch as-is to avoid conflicts
with Pierre-Eric's work. After that work lands, we can revisit this
workaround.

Does that sound reasonable to you?

> 
> Regards,
> Christian.
> 
> > 
> > Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
> > ---
> >  drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c     | 2 ++
> >  drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h     | 1 +
> >  drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c | 2 +-
> >  3 files changed, 4 insertions(+), 1 deletion(-)
> > 
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> > b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> > index 97b562a79ea8..bf31bd022d6d 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> > @@ -325,6 +325,8 @@ void amdgpu_gmc_gart_location(struct
> > amdgpu_device *adev, struct amdgpu_gmc *mc,
> >  		break;
> >  	}
> >  
> > +	mc->num_gart_pages_before_gtt =
> > +		AMDGPU_GTT_MAX_TRANSFER_SIZE *
> > AMDGPU_GTT_NUM_TRANSFER_WINDOWS;
> >  	mc->gart_start &= ~(four_gb - 1);
> >  	mc->gart_end = mc->gart_start + mc->gart_size - 1;
> >  	dev_info(adev->dev, "GART: %lluM 0x%016llX - 0x%016llX\n",
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> > b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> > index 55097ca10738..568eed3eb557 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> > @@ -266,6 +266,7 @@ struct amdgpu_gmc {
> >  	u64			fb_end;
> >  	unsigned		vram_width;
> >  	u64			real_vram_size;
> > +	u32			num_gart_pages_before_gtt;
> >  	int			vram_mtrr;
> >  	u64                     mc_mask;
> >  	const struct firmware   *fw;	/* MC firmware */
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> > b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> > index 0760e70402ec..4c2563a70c2b 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> > @@ -283,7 +283,7 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device
> > *adev, uint64_t gtt_size)
> >  
> >  	ttm_resource_manager_init(man, &adev->mman.bdev,
> > gtt_size);
> >  
> > -	start = AMDGPU_GTT_MAX_TRANSFER_SIZE *
> > AMDGPU_GTT_NUM_TRANSFER_WINDOWS;
> > +	start = adev->gmc.num_gart_pages_before_gtt;
> >  	size = (adev->gmc.gart_size >> PAGE_SHIFT) - start;
> >  	drm_mm_init(&mgr->mm, start, size);
> >  	spin_lock_init(&mgr->lock);