Re: [PATCH v13 08/12] drm/xe/xelp: Add AuxCCS invalidation to the indirect context workarounds

["Ville Syrjälä" <ville.syrjala@linux.intel.com>]

On Mon, Oct 20, 2025 at 08:58:26AM +0100, Tvrtko Ursulin wrote:
> Following from the i915 reference implementation, we add the AuxCCS
> invalidation to the indirect context workarounds page.
> 
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
> ---
>  drivers/gpu/drm/xe/xe_lrc.c | 38 +++++++++++++++++++++++++++++++++++++
>  1 file changed, 38 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
> index b5083c99dd50..c77a166a2742 100644
> --- a/drivers/gpu/drm/xe/xe_lrc.c
> +++ b/drivers/gpu/drm/xe/xe_lrc.c
> @@ -27,6 +27,7 @@
>  #include "xe_map.h"
>  #include "xe_memirq.h"
>  #include "xe_mmio.h"
> +#include "xe_ring_ops.h"
>  #include "xe_sriov.h"
>  #include "xe_trace_lrc.h"
>  #include "xe_vm.h"
> @@ -88,6 +89,16 @@ gt_engine_needs_indirect_ctx(struct xe_gt *gt, enum xe_engine_class class)
>  					       class, NULL))
>  		return true;
>  
> +	/* AuxCCS invalidation */
> +	if (GRAPHICS_VERx100(xe) >= 1200 &&
> +	    GRAPHICS_VERx100(xe) <= 1210 &&
> +	    (class == XE_ENGINE_CLASS_RENDER ||
> +	     class == XE_ENGINE_CLASS_COMPUTE ||
> +	     class == XE_ENGINE_CLASS_COPY ||
> +	     class == XE_ENGINE_CLASS_VIDEO_DECODE ||
> +	     class == XE_ENGINE_CLASS_VIDEO_ENHANCE))
> +		return true;
> +
>  	return false;
>  }
>  
> @@ -1188,6 +1199,31 @@ static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc,
>  	return cmd - batch;
>  }
>  
> +static ssize_t setup_invalidate_auxccs_wa(struct xe_lrc *lrc,
> +					  struct xe_hw_engine *hwe,
> +					  u32 *batch, size_t max_len)
> +{
> +	struct xe_gt *gt = lrc->gt;
> +	struct xe_device *xe = gt_to_xe(gt);
> +	const unsigned int class = hwe->class;
> +	u32 *cmd;
> +
> +	if (GRAPHICS_VERx100(xe) < 1200 || GRAPHICS_VERx100(xe) > 1210 ||
> +	    !(class == XE_ENGINE_CLASS_RENDER ||
> +	      class == XE_ENGINE_CLASS_COMPUTE ||
> +	      class == XE_ENGINE_CLASS_COPY ||
> +	      class == XE_ENGINE_CLASS_VIDEO_DECODE ||
> +	      class == XE_ENGINE_CLASS_VIDEO_ENHANCE))
> +		return 0;

I would extract that into a function instead of repeating it twice.

> +
> +	if (xe_gt_WARN_ON(gt, max_len < 8))
> +		return -ENOSPC;
> +
> +	cmd = xe_emit_aux_table_inv(hwe, batch);
> +
> +	return cmd - batch;
> +}
> +
>  struct bo_setup {
>  	ssize_t (*setup)(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
>  			 u32 *batch, size_t max_size);
> @@ -1320,9 +1356,11 @@ setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
>  {
>  	static const struct bo_setup rcs_funcs[] = {
>  		{ .setup = setup_timestamp_wa },
> +		{ .setup = setup_invalidate_auxccs_wa },
>  		{ .setup = setup_configfs_mid_ctx_restore_bb },
>  	};
>  	static const struct bo_setup xcs_funcs[] = {
> +		{ .setup = setup_invalidate_auxccs_wa },
>  		{ .setup = setup_configfs_mid_ctx_restore_bb },
>  	};
>  	struct bo_setup_state state = {
> -- 
> 2.48.0

-- 
Ville Syrjälä
Intel