drm/i915/gt: Support aux invalidation on all engines

Perform some refactoring with the purpose of keeping in one
single place all the operations around the aux table
invalidation.

With this refactoring add more engines where the invalidation
should be performed.

Fixes: 972282c4 ("drm/i915/gen12: Add aux table invalidate for all engines")
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: <stable@vger.kernel.org> # v5.8+
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230725001950.1014671-8-andi.shyti@linux.intel.com
(cherry picked from commit 76ff7789)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

drivers/gpu/drm/i915/gt/gen8_engine_cs.c

@@ -165,21 +165,47 @@ static u32 preparser_disable(bool state)
 	return MI_ARB_CHECK | 1 << 8 | state;
 }
 
+static i915_reg_t gen12_get_aux_inv_reg(struct intel_engine_cs *engine)
+{
+	switch (engine->id) {
+	case RCS0:
+		return GEN12_CCS_AUX_INV;
+	case BCS0:
+		return GEN12_BCS0_AUX_INV;
+	case VCS0:
+		return GEN12_VD0_AUX_INV;
+	case VCS2:
+		return GEN12_VD2_AUX_INV;
+	case VECS0:
+		return GEN12_VE0_AUX_INV;
+	case CCS0:
+		return GEN12_CCS0_AUX_INV;
+	default:
+		return INVALID_MMIO_REG;
+	}
+}
+
 static bool gen12_needs_ccs_aux_inv(struct intel_engine_cs *engine)
 {
+	i915_reg_t reg = gen12_get_aux_inv_reg(engine);
+
 	if (IS_PONTEVECCHIO(engine->i915))
 		return false;
 
 	/*
-	 * so far platforms supported by i915 having
-	 * flat ccs do not require AUX invalidation
+	 * So far platforms supported by i915 having flat ccs do not require
+	 * AUX invalidation. Check also whether the engine requires it.
 	 */
-	return !HAS_FLAT_CCS(engine->i915);
+	return i915_mmio_reg_valid(reg) && !HAS_FLAT_CCS(engine->i915);
 }
 
-u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg)
+u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs)
 {
-	u32 gsi_offset = gt->uncore->gsi_offset;
+	i915_reg_t inv_reg = gen12_get_aux_inv_reg(engine);
+	u32 gsi_offset = engine->gt->uncore->gsi_offset;
+
+	if (!gen12_needs_ccs_aux_inv(engine))
+		return cs;
 
 	*cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN;
 	*cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset;
@@ -317,11 +343,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 
 		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 
-		if (gen12_needs_ccs_aux_inv(rq->engine)) {
-			/* hsdes: 1809175790 */
-			cs = gen12_emit_aux_table_inv(rq->engine->gt, cs,
-						      GEN12_CCS_AUX_INV);
-		}
+		cs = gen12_emit_aux_table_inv(engine, cs);
 
 		*cs++ = preparser_disable(false);
 		intel_ring_advance(rq, cs);
@@ -332,21 +354,14 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 
 int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
 {
-	intel_engine_mask_t aux_inv = 0;
-	u32 cmd, *cs;
+	u32 cmd = 4;
+	u32 *cs;
 
-	cmd = 4;
 	if (mode & EMIT_INVALIDATE) {
 		cmd += 2;
 
-		if (gen12_needs_ccs_aux_inv(rq->engine) &&
-		    (rq->engine->class == VIDEO_DECODE_CLASS ||
-		     rq->engine->class == VIDEO_ENHANCEMENT_CLASS)) {
-			aux_inv = rq->engine->mask &
-				~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0);
-			if (aux_inv)
-				cmd += 8;
-		}
+		if (gen12_needs_ccs_aux_inv(rq->engine))
+			cmd += 8;
 	}
 
 	cs = intel_ring_begin(rq, cmd);
@@ -381,14 +396,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
 	*cs++ = 0; /* upper addr */
 	*cs++ = 0; /* value */
 
-	if (aux_inv) { /* hsdes: 1809175790 */
-		if (rq->engine->class == VIDEO_DECODE_CLASS)
-			cs = gen12_emit_aux_table_inv(rq->engine->gt,
-						      cs, GEN12_VD0_AUX_INV);
-		else
-			cs = gen12_emit_aux_table_inv(rq->engine->gt,
-						      cs, GEN12_VE0_AUX_INV);
-	}
+	cs = gen12_emit_aux_table_inv(rq->engine, cs);
 
 	if (mode & EMIT_INVALIDATE)
 		*cs++ = preparser_disable(false);

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_engine_cs;
 struct intel_gt;
 struct i915_request;
 
@@ -46,7 +47,7 @@ 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(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg);
+u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs);
 
 static inline u32 *
 __gen8_emit_pipe_control(u32 *batch, u32 bit_group_0,

drivers/gpu/drm/i915/gt/intel_lrc.c

@@ -1364,10 +1364,7 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
 	    IS_DG2_G11(ce->engine->i915))
 		cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0);
 
-	/* hsdes: 1809175790 */
-	if (!HAS_FLAT_CCS(ce->engine->i915))
-		cs = gen12_emit_aux_table_inv(ce->engine->gt,
-					      cs, GEN12_CCS_AUX_INV);
+	cs = gen12_emit_aux_table_inv(ce->engine, cs);
 
 	/* Wa_16014892111 */
 	if (IS_MTL_GRAPHICS_STEP(ce->engine->i915, M, STEP_A0, STEP_B0) ||
@@ -1392,17 +1389,7 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs)
 						    PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE,
 						    0);
 
-	/* hsdes: 1809175790 */
-	if (!HAS_FLAT_CCS(ce->engine->i915)) {
-		if (ce->engine->class == VIDEO_DECODE_CLASS)
-			cs = gen12_emit_aux_table_inv(ce->engine->gt,
-						      cs, GEN12_VD0_AUX_INV);
-		else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS)
-			cs = gen12_emit_aux_table_inv(ce->engine->gt,
-						      cs, GEN12_VE0_AUX_INV);
-	}
-
-	return cs;
+	return gen12_emit_aux_table_inv(ce->engine, cs);
 }
 
 static void