Re: [Intel-gfx] [PATCH v2 3/3] drm/i915/dgfx: Make failure to setup stolen non-fatal

[Wayne Boyer <wayne.boyer@xxxxxxxxx>]

On 9/16/22 10:36 AM, Lucas De Marchi wrote:
> There is no reason to consider the setup of Data Stolen Memory fatal on
> dgfx and non-fatal on integrated. Move the debug and error propagation
> around so both have the same behavior: non-fatal. Before this change,
> loading i915 on a system with TGL + DG2 would result in just TGL
> succeeding the initialization (without stolen).
>
> Now loading i915 on the same system with an injected failure in
> i915_gem_init_stolen():
>
> 	$ dmesg | grep stolen
> 	i915 0000:00:02.0: [drm] Injected failure, disabling use of stolen memory
> 	i915 0000:00:02.0: [drm:init_stolen_smem [i915]] Skip stolen region: failed to setup
> 	i915 0000:03:00.0: [drm] Injected failure, disabling use of stolen memory
> 	i915 0000:03:00.0: [drm:init_stolen_lmem [i915]] Skip stolen region: failed to setup
>
> Both GPUs are still available:
>
> 	$ sudo build/tools/lsgpu
> 	card1                    Intel Dg2 (Gen12)                 drm:/dev/dri/card1
> 	└─renderD129                                               drm:/dev/dri/renderD129
> 	card0                    Intel Tigerlake (Gen12)           drm:/dev/dri/card0
> 	└─renderD128                                               drm:/dev/dri/renderD128
>
> Signed-off-by: Lucas De Marchi <lucas.demarchi@xxxxxxxxx>

Reviewed-by: Wayne Boyer <wayne.boyer@xxxxxxxxx>

> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
> index 6edf4e374f54..c5a4035c99cd 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
> @@ -494,26 +494,26 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem)
>   		drm_notice(&i915->drm,
>   			   "%s, disabling use of stolen memory\n",
>   			   "iGVT-g active");
> -		return 0;
> +		return -ENOSPC;
>   	}
>   
>   	if (i915_vtd_active(i915) && GRAPHICS_VER(i915) < 8) {
>   		drm_notice(&i915->drm,
>   			   "%s, disabling use of stolen memory\n",
>   			   "DMAR active");
> -		return 0;
> +		return -ENOSPC;
>   	}
>   
>   	if (adjust_stolen(i915, &mem->region))
> -		return 0;
> +		return -ENOSPC;
>   
>   	if (request_smem_stolen(i915, &mem->region))
> -		return 0;
> +		return -ENOSPC;
>   
>   	i915->dsm = mem->region;
>   
>   	if (init_reserved_stolen(i915))
> -		return 0;
> +		return -ENOSPC;
>   
>   	/* Exclude the reserved region from driver use */
>   	mem->region.end = i915->dsm_reserved.start - 1;
> @@ -527,7 +527,7 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem)
>   		(u64)i915->stolen_usable_size >> 10);
>   
>   	if (i915->stolen_usable_size == 0)
> -		return 0;
> +		return -ENOSPC;
>   
>   	/* Basic memrange allocator for stolen space. */
>   	drm_mm_init(&i915->mm.stolen, 0, i915->stolen_usable_size);
> @@ -765,11 +765,17 @@ i915_gem_object_create_stolen(struct drm_i915_private *i915,
>   
>   static int init_stolen_smem(struct intel_memory_region *mem)
>   {
> +	int err;
> +
>   	/*
>   	 * Initialise stolen early so that we may reserve preallocated
>   	 * objects for the BIOS to KMS transition.
>   	 */
> -	return i915_gem_init_stolen(mem);
> +	err = i915_gem_init_stolen(mem);
> +	if (err)
> +		drm_dbg(&mem->i915->drm, "Skip stolen region: failed to setup\n");
> +
> +	return 0;
>   }
>   
>   static int release_stolen_smem(struct intel_memory_region *mem)
> @@ -786,21 +792,25 @@ static const struct intel_memory_region_ops i915_region_stolen_smem_ops = {
>   
>   static int init_stolen_lmem(struct intel_memory_region *mem)
>   {
> +	struct drm_i915_private *i915 = mem->i915;
>   	int err;
>   
>   	if (GEM_WARN_ON(resource_size(&mem->region) == 0))
> -		return -ENODEV;
> +		return 0;
>   
>   	err = i915_gem_init_stolen(mem);
> -	if (err)
> -		return err;
> +	if (err) {
> +		drm_dbg(&mem->i915->drm, "Skip stolen region: failed to setup\n");
> +		return 0;
> +	}
>   
> -	if (mem->io_size && !io_mapping_init_wc(&mem->iomap,
> -						mem->io_start,
> -						mem->io_size)) {
> -		err = -EIO;
> +	if (mem->io_size &&
> +	    !io_mapping_init_wc(&mem->iomap, mem->io_start, mem->io_size))
>   		goto err_cleanup;
> -	}
> +
> +	drm_dbg(&i915->drm, "Stolen Local memory IO start: %pa\n",
> +		&mem->io_start);
> +	drm_dbg(&i915->drm, "Stolen Local DSM base: %pa\n", &mem->region.start);
>   
>   	return 0;
>   
> @@ -874,16 +884,6 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
>   	if (IS_ERR(mem))
>   		return mem;
>   
> -	/*
> -	 * TODO: consider creating common helper to just print all the
> -	 * interesting stuff from intel_memory_region, which we can use for all
> -	 * our probed regions.
> -	 */
> -
> -	drm_dbg(&i915->drm, "Stolen Local memory IO start: %pa\n",
> -		&mem->io_start);
> -	drm_dbg(&i915->drm, "Stolen Local DSM base: %pa\n", &dsm_base);
> -
>   	intel_memory_region_set_name(mem, "stolen-local");
>   
>   	mem->private = true;
> @@ -908,6 +908,7 @@ i915_gem_stolen_smem_setup(struct drm_i915_private *i915, u16 type,
>   	intel_memory_region_set_name(mem, "stolen-system");
>   
>   	mem->private = true;
> +
>   	return mem;
>   }
>   

--
--
Wayne Boyer
Graphics Software Engineer
VTT-OSGC Platform Enablement