Re: [PATCH 2/4] drm/xe: add bind time pat index to xe_bo structure

From: Matt Roper <matthew.d.roper@intel.com>
To: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
Cc: intel-gfx@lists.freedesktop.org, intel-xe@lists.freedesktop.org
Subject: Re: [PATCH 2/4] drm/xe: add bind time pat index to xe_bo structure
Date: Wed, 31 Jan 2024 10:56:37 -0800	[thread overview]
Message-ID: <20240131185637.GB5347@mdroper-desk1.amr.corp.intel.com> (raw)
In-Reply-To: <20240130193652.374270-3-juhapekka.heikkila@gmail.com>

On Tue, Jan 30, 2024 at 09:36:50PM +0200, Juha-Pekka Heikkila wrote:
> Add BO bind time pat index member to xe_bo structure and store
> pat index from xe_vma to xe_bo.
> 
> Signed-off-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
> ---
>  drivers/gpu/drm/xe/xe_bo_types.h | 12 ++++++++++++
>  drivers/gpu/drm/xe/xe_pt.c       | 22 ++++++++++++++++++----
>  2 files changed, 30 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
> index 14ef13b7b421..6d599f1e846b 100644
> --- a/drivers/gpu/drm/xe/xe_bo_types.h
> +++ b/drivers/gpu/drm/xe/xe_bo_types.h
> @@ -91,6 +91,18 @@ struct xe_bo {
>  
>  	/** @vram_userfault_link: Link into @mem_access.vram_userfault.list */
>  		struct list_head vram_userfault_link;
> +
> +	/**
> +	 * @pat_index: The pat index requested when bind this BO
> +	 */
> +	u16 pat_index;
> +
> +	/**
> +	 * @has_sealed_pat_index: The pat index is sealed because this BO is
> +	 * pinned as framebuffer. This is to prevent flipping compression
> +	 * on/off from framebuffers while in use.
> +	 */
> +	bool has_sealed_pat_index;
>  };
>  
>  #define intel_bo_to_drm_bo(bo) (&(bo)->ttm.base)
> diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
> index de1030a47588..c72cb75d993c 100644
> --- a/drivers/gpu/drm/xe/xe_pt.c
> +++ b/drivers/gpu/drm/xe/xe_pt.c
> @@ -1208,10 +1208,11 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
>  	struct dma_fence *fence;
>  	struct invalidation_fence *ifence = NULL;
>  	struct xe_range_fence *rfence;
> +	struct xe_bo *bo = xe_vma_bo(vma);
>  	int err;
>  
>  	bind_pt_update.locked = false;
> -	xe_bo_assert_held(xe_vma_bo(vma));
> +	xe_bo_assert_held(bo);
>  	xe_vm_assert_held(vm);
>  
>  	vm_dbg(&xe_vma_vm(vma)->xe->drm,
> @@ -1252,8 +1253,21 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
>  		return ERR_PTR(-ENOMEM);
>  	}
>  
> +	/*
> +	 * On Xe2 BO which was pinned as framebuffer before with different
> +	 * PAT index cannot be bound with different PAT index. This is
> +	 * to prevent switching CCS on/off from framebuffers on the fly
> +	 * with Xe2.
> +	 */

I haven't been following all the discussion here, but why is switching
it on/off a problem?  On Xe2 can't we just always turn on decompression
(assuming they were 4-tile)?

Even if a content producer puts data into the buffer using a
non-compression PAT index, my understanding is that the FlatCCS metadata
for that part of the buffer still gets updated appropriately (to 0000 or
whatever the code is for "uncompressed block").  If the decompression
bit in PLANE_CTL basically translates to "pay attention to FlatCCS" vs
"ignore FlatCCS" it shouldn't matter whether the data is truly
compressed or not, right?  Since the FlatCCS area that corresponds to a
buffer is still correct even when non-compressed PAT is used (I think),
is there a reason to turn off decompression for 4-tile?

Am I overlooking something?

Matt

> +	if (bo) {
> +		if (bo->has_sealed_pat_index && bo->pat_index != vma->pat_index)
> +			return ERR_PTR(-EINVAL);
> +
> +		bo->pat_index = vma->pat_index;
> +	}
> +
>  	fence = xe_migrate_update_pgtables(tile->migrate,
> -					   vm, xe_vma_bo(vma), q,
> +					   vm, bo, q,
>  					   entries, num_entries,
>  					   syncs, num_syncs,
>  					   &bind_pt_update.base);
> @@ -1287,8 +1301,8 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
>  				   DMA_RESV_USAGE_KERNEL :
>  				   DMA_RESV_USAGE_BOOKKEEP);
>  
> -		if (!xe_vma_has_no_bo(vma) && !xe_vma_bo(vma)->vm)
> -			dma_resv_add_fence(xe_vma_bo(vma)->ttm.base.resv, fence,
> +		if (!xe_vma_has_no_bo(vma) && !bo->vm)
> +			dma_resv_add_fence(bo->ttm.base.resv, fence,
>  					   DMA_RESV_USAGE_BOOKKEEP);
>  		xe_pt_commit_bind(vma, entries, num_entries, rebind,
>  				  bind_pt_update.locked ? &deferred : NULL);
> -- 
> 2.25.1
> 

-- 
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation