[Intel-gfx] [PATCH v2 11/11] drm/i915/xehpsdv: Initialize multi-tiles

[Andi Shyti]

Hi Tvrtko and Matt,

[...]

> -#define I915_MAX_TILES 4
> -	struct intel_gt *gts[I915_MAX_TILES];
> +#define I915_MAX_GTS 4
> +	struct intel_gt *gts[I915_MAX_GTS];

let's call it MAX_GTS already in patch 5 so that we can avoid a
rename.

BTW, out of the scope of this patch but if we can read the number
of tiles, why don't we make this dynamic? We already have a
"dynamic" version for_each_gt() in probe_gts().

[...]

>  
>  	struct {
>  		struct i915_gem_contexts {
> @@ -1724,6 +1726,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
>  
>  #define HAS_REGION(i915, i) (INTEL_INFO(i915)->memory_regions & (i))
>  #define HAS_LMEM(i915) HAS_REGION(i915, REGION_LMEM)
> +#define HAS_REMOTE_TILES(dev_priv)   (INTEL_INFO(dev_priv)->has_remote_tiles)

s/dev_priv/i915

[...]

> +static const struct intel_gt_definition xehp_sdv_gts[] = {
> +	{
> +		.type = GT_TILE,
> +		.name = "Remote Tile GT",
> +		.mapping_base = SZ_16M,
> +		.engine_mask = XE_HP_SDV_ENGINES,
> +
> +	},
> +	{
> +		.type = GT_TILE,
> +		.name = "Remote Tile GT",
> +		.mapping_base = SZ_16M * 2,
> +		.engine_mask = XE_HP_SDV_ENGINES,
> +
> +	},
> +	{
> +		.type = GT_TILE,
> +		.name = "Remote Tile GT",

why don't we call it "Remote Tile GT <N>" or similar?

[...]

Andi