[Intel-gfx] [PATCH v3 11/14] drm/i915/mtl: Add gsi_offset when emitting aux table invalidation

[Iddamsetty, Aravind]

On 07-09-2022 05:19, Matt Roper wrote:
> The aux table invalidation registers are a bit unique --- they're
> engine-centric registers that reside in the GSI register space rather
> than within the engines' regular MMIO ranges.  That means that when
> issuing invalidation on engines in the standalone media GT, the GSI
> offset must be added to the regular MMIO offset for the invalidation
> registers.
> 
> Cc: Aravind Iddamsetty <aravind.iddamsetty at intel.com>
> Signed-off-by: Matt Roper <matthew.d.roper at intel.com>
> ---
>  drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 15 ++++++++++-----
>  drivers/gpu/drm/i915/gt/gen8_engine_cs.h |  3 ++-
>  drivers/gpu/drm/i915/gt/intel_lrc.c      |  9 ++++++---
>  3 files changed, 18 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> index 98645797962f..e49fa6fa6aee 100644
> --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> @@ -165,10 +165,12 @@ static u32 preparser_disable(bool state)
>  	return MI_ARB_CHECK | 1 << 8 | state;
>  }
>  
> -u32 *gen12_emit_aux_table_inv(u32 *cs, const i915_reg_t inv_reg)
> +u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg)
>  {
> +	u32 gsi_offset = gt->uncore->gsi_offset;
> +
>  	*cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN;
> -	*cs++ = i915_mmio_reg_offset(inv_reg);
> +	*cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset;
>  	*cs++ = AUX_INV;
>  	*cs++ = MI_NOOP;
>  
> @@ -254,7 +256,8 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
>  
>  		if (!HAS_FLAT_CCS(rq->engine->i915)) {
>  			/* hsdes: 1809175790 */
> -			cs = gen12_emit_aux_table_inv(cs, GEN12_GFX_CCS_AUX_NV);
> +			cs = gen12_emit_aux_table_inv(rq->engine->gt,
> +						      cs, GEN12_GFX_CCS_AUX_NV);
>  		}
>  
>  		*cs++ = preparser_disable(false);
> @@ -313,9 +316,11 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
>  
>  	if (aux_inv) { /* hsdes: 1809175790 */
>  		if (rq->engine->class == VIDEO_DECODE_CLASS)
> -			cs = gen12_emit_aux_table_inv(cs, GEN12_VD0_AUX_NV);
> +			cs = gen12_emit_aux_table_inv(rq->engine->gt,
> +						      cs, GEN12_VD0_AUX_NV);
>  		else
> -			cs = gen12_emit_aux_table_inv(cs, GEN12_VE0_AUX_NV);
> +			cs = gen12_emit_aux_table_inv(rq->engine->gt,
> +						      cs, GEN12_VE0_AUX_NV);
>  	}
>  
>  	if (mode & EMIT_INVALIDATE)
> diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h
> index 32e3d2b831bb..e4d24c811dd6 100644
> --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h
> +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h
> @@ -13,6 +13,7 @@
>  #include "intel_gt_regs.h"
>  #include "intel_gpu_commands.h"
>  
> +struct intel_gt;
>  struct i915_request;
>  
>  int gen8_emit_flush_rcs(struct i915_request *rq, u32 mode);
> @@ -45,7 +46,7 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs);
>  u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs);
>  u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs);
>  
> -u32 *gen12_emit_aux_table_inv(u32 *cs, const i915_reg_t inv_reg);
> +u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg);
>  
>  static inline u32 *
>  __gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset)
> diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
> index 070cec4ff8a4..08214683e130 100644
> --- a/drivers/gpu/drm/i915/gt/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
> @@ -1278,7 +1278,8 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
>  
>  	/* hsdes: 1809175790 */
>  	if (!HAS_FLAT_CCS(ce->engine->i915))
> -		cs = gen12_emit_aux_table_inv(cs, GEN12_GFX_CCS_AUX_NV);
> +		cs = gen12_emit_aux_table_inv(ce->engine->gt,
> +					      cs, GEN12_GFX_CCS_AUX_NV);
>  
>  	/* Wa_16014892111 */
>  	if (IS_DG2(ce->engine->i915))
> @@ -1304,9 +1305,11 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs)
>  	/* hsdes: 1809175790 */
>  	if (!HAS_FLAT_CCS(ce->engine->i915)) {
>  		if (ce->engine->class == VIDEO_DECODE_CLASS)
> -			cs = gen12_emit_aux_table_inv(cs, GEN12_VD0_AUX_NV);
> +			cs = gen12_emit_aux_table_inv(ce->engine->gt,
> +						      cs, GEN12_VD0_AUX_NV);
>  		else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS)
> -			cs = gen12_emit_aux_table_inv(cs, GEN12_VE0_AUX_NV);
> +			cs = gen12_emit_aux_table_inv(ce->engine->gt,
> +						      cs, GEN12_VE0_AUX_NV);
>  	}
>  
>  	return cs;

LGTM

Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty at intel.com>

Thanks,
Aravind.