1 files changed, 162 insertions, 63 deletions

diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index e1c76e5bfa82..071c1cc45257 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -3,10 +3,12 @@
  * Copyright © 2014 Intel Corporation
  */
 
+#include <drm/drm_print.h>
+
 #include "gen8_engine_cs.h"
-#include "i915_drv.h"
 #include "intel_engine_regs.h"
 #include "intel_gpu_commands.h"
+#include "intel_gt.h"
 #include "intel_lrc.h"
 #include "intel_ring.h"
 
@@ -39,11 +41,11 @@ int gen8_emit_flush_rcs(struct i915_request *rq, u32 mode)
 		 * On GEN9: before VF_CACHE_INVALIDATE we need to emit a NULL
 		 * pipe control.
 		 */
-		if (GRAPHICS_VER(rq->engine->i915) == 9)
+		if (GRAPHICS_VER(rq->i915) == 9)
 			vf_flush_wa = true;
 
 		/* WaForGAMHang:kbl */
-		if (IS_KBL_GRAPHICS_STEP(rq->engine->i915, 0, STEP_C0))
+		if (IS_KABYLAKE(rq->i915) && IS_GRAPHICS_STEP(rq->i915, 0, STEP_C0))
 			dc_flush_wa = true;
 	}
 
@@ -165,58 +167,155 @@ static u32 preparser_disable(bool state)
 	return MI_ARB_CHECK | 1 << 8 | state;
 }
 
-u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg)
+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)
 {
-	u32 gsi_offset = gt->uncore->gsi_offset;
+	i915_reg_t reg = gen12_get_aux_inv_reg(engine);
+
+	/*
+	 * So far platforms supported by i915 having flat ccs do not require
+	 * AUX invalidation. Check also whether the engine requires it.
+	 */
+	return i915_mmio_reg_valid(reg) && !HAS_FLAT_CCS(engine->i915);
+}
+
+u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs)
+{
+	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;
 	*cs++ = AUX_INV;
-	*cs++ = MI_NOOP;
+
+	*cs++ = MI_SEMAPHORE_WAIT_TOKEN |
+		MI_SEMAPHORE_REGISTER_POLL |
+		MI_SEMAPHORE_POLL |
+		MI_SEMAPHORE_SAD_EQ_SDD;
+	*cs++ = 0;
+	*cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset;
+	*cs++ = 0;
+	*cs++ = 0;
 
 	return cs;
 }
 
+static int mtl_dummy_pipe_control(struct i915_request *rq)
+{
+	/* Wa_14016712196 */
+	if (IS_GFX_GT_IP_RANGE(rq->engine->gt, IP_VER(12, 70), IP_VER(12, 74)) ||
+	    IS_DG2(rq->i915)) {
+		u32 *cs;
+
+		/* dummy PIPE_CONTROL + depth flush */
+		cs = intel_ring_begin(rq, 6);
+		if (IS_ERR(cs))
+			return PTR_ERR(cs);
+		cs = gen12_emit_pipe_control(cs,
+					     0,
+					     PIPE_CONTROL_DEPTH_CACHE_FLUSH,
+					     LRC_PPHWSP_SCRATCH_ADDR);
+		intel_ring_advance(rq, cs);
+	}
+
+	return 0;
+}
+
 int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 {
 	struct intel_engine_cs *engine = rq->engine;
 
-	if (mode & EMIT_FLUSH) {
-		u32 flags = 0;
+	/*
+	 * On Aux CCS platforms the invalidation of the Aux
+	 * table requires quiescing memory traffic beforehand
+	 */
+	if (mode & EMIT_FLUSH || gen12_needs_ccs_aux_inv(engine)) {
+		u32 bit_group_0 = 0;
+		u32 bit_group_1 = 0;
+		int err;
 		u32 *cs;
 
-		flags |= PIPE_CONTROL_TILE_CACHE_FLUSH;
-		flags |= PIPE_CONTROL_FLUSH_L3;
-		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
-		flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
+		err = mtl_dummy_pipe_control(rq);
+		if (err)
+			return err;
+
+		bit_group_0 |= PIPE_CONTROL0_HDC_PIPELINE_FLUSH;
+
+		/*
+		 * When required, in MTL and beyond platforms we
+		 * need to set the CCS_FLUSH bit in the pipe control
+		 */
+		if (GRAPHICS_VER_FULL(rq->i915) >= IP_VER(12, 70))
+			bit_group_0 |= PIPE_CONTROL_CCS_FLUSH;
+
+		/*
+		 * L3 fabric flush is needed for AUX CCS invalidation
+		 * which happens as part of pipe-control so we can
+		 * ignore PIPE_CONTROL_FLUSH_L3. Also PIPE_CONTROL_FLUSH_L3
+		 * deals with Protected Memory which is not needed for
+		 * AUX CCS invalidation and lead to unwanted side effects.
+		 */
+		if ((mode & EMIT_FLUSH) &&
+		    GRAPHICS_VER_FULL(rq->i915) < IP_VER(12, 70))
+			bit_group_1 |= PIPE_CONTROL_FLUSH_L3;
+
+		bit_group_1 |= PIPE_CONTROL_TILE_CACHE_FLUSH;
+		bit_group_1 |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
+		bit_group_1 |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
 		/* Wa_1409600907:tgl,adl-p */
-		flags |= PIPE_CONTROL_DEPTH_STALL;
-		flags |= PIPE_CONTROL_DC_FLUSH_ENABLE;
-		flags |= PIPE_CONTROL_FLUSH_ENABLE;
+		bit_group_1 |= PIPE_CONTROL_DEPTH_STALL;
+		bit_group_1 |= PIPE_CONTROL_DC_FLUSH_ENABLE;
+		bit_group_1 |= PIPE_CONTROL_FLUSH_ENABLE;
 
-		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
-		flags |= PIPE_CONTROL_QW_WRITE;
+		bit_group_1 |= PIPE_CONTROL_STORE_DATA_INDEX;
+		bit_group_1 |= PIPE_CONTROL_QW_WRITE;
 
-		flags |= PIPE_CONTROL_CS_STALL;
+		bit_group_1 |= PIPE_CONTROL_CS_STALL;
 
 		if (!HAS_3D_PIPELINE(engine->i915))
-			flags &= ~PIPE_CONTROL_3D_ARCH_FLAGS;
+			bit_group_1 &= ~PIPE_CONTROL_3D_ARCH_FLAGS;
 		else if (engine->class == COMPUTE_CLASS)
-			flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;
+			bit_group_1 &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;
 
 		cs = intel_ring_begin(rq, 6);
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
-		cs = gen12_emit_pipe_control(cs,
-					     PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
-					     flags, LRC_PPHWSP_SCRATCH_ADDR);
+		cs = gen12_emit_pipe_control(cs, bit_group_0, bit_group_1,
+					     LRC_PPHWSP_SCRATCH_ADDR);
 		intel_ring_advance(rq, cs);
 	}
 
 	if (mode & EMIT_INVALIDATE) {
 		u32 flags = 0;
 		u32 *cs, count;
+		int err;
+
+		err = mtl_dummy_pipe_control(rq);
+		if (err)
+			return err;
 
 		flags |= PIPE_CONTROL_COMMAND_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_TLB_INVALIDATE;
@@ -236,10 +335,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 		else if (engine->class == COMPUTE_CLASS)
 			flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;
 
-		if (!HAS_FLAT_CCS(rq->engine->i915))
-			count = 8 + 4;
-		else
-			count = 8;
+		count = 8;
+		if (gen12_needs_ccs_aux_inv(rq->engine))
+			count += 8;
 
 		cs = intel_ring_begin(rq, count);
 		if (IS_ERR(cs))
@@ -254,11 +352,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 
 		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 
-		if (!HAS_FLAT_CCS(rq->engine->i915)) {
-			/* hsdes: 1809175790 */
-			cs = gen12_emit_aux_table_inv(rq->engine->gt,
-						      cs, GEN12_GFX_CCS_AUX_NV);
-		}
+		cs = gen12_emit_aux_table_inv(engine, cs);
 
 		*cs++ = preparser_disable(false);
 		intel_ring_advance(rq, cs);
@@ -269,21 +363,14 @@ 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 (!HAS_FLAT_CCS(rq->engine->i915) &&
-		    (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 += 4;
-		}
+		if (gen12_needs_ccs_aux_inv(rq->engine))
+			cmd += 8;
 	}
 
 	cs = intel_ring_begin(rq, cmd);
@@ -307,6 +394,10 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
 		cmd |= MI_INVALIDATE_TLB;
 		if (rq->engine->class == VIDEO_DECODE_CLASS)
 			cmd |= MI_INVALIDATE_BSD;
+
+		if (gen12_needs_ccs_aux_inv(rq->engine) &&
+		    rq->engine->class == COPY_ENGINE_CLASS)
+			cmd |= MI_FLUSH_DW_CCS;
 	}
 
 	*cs++ = cmd;
@@ -314,14 +405,7 @@ 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_NV);
-		else
-			cs = gen12_emit_aux_table_inv(rq->engine->gt,
-						      cs, GEN12_VE0_AUX_NV);
-	}
+	cs = gen12_emit_aux_table_inv(rq->engine, cs);
 
 	if (mode & EMIT_INVALIDATE)
 		*cs++ = preparser_disable(false);
@@ -658,21 +742,25 @@ static u32 *gen12_emit_preempt_busywait(struct i915_request *rq, u32 *cs)
 }
 
 /* Wa_14014475959:dg2 */
-#define CCS_SEMAPHORE_PPHWSP_OFFSET	0x540
-static u32 ccs_semaphore_offset(struct i915_request *rq)
+/* Wa_16019325821 */
+/* Wa_14019159160 */
+#define HOLD_SWITCHOUT_SEMAPHORE_PPHWSP_OFFSET	0x540
+static u32 hold_switchout_semaphore_offset(struct i915_request *rq)
 {
 	return i915_ggtt_offset(rq->context->state) +
-		(LRC_PPHWSP_PN * PAGE_SIZE) + CCS_SEMAPHORE_PPHWSP_OFFSET;
+		(LRC_PPHWSP_PN * PAGE_SIZE) + HOLD_SWITCHOUT_SEMAPHORE_PPHWSP_OFFSET;
 }
 
 /* Wa_14014475959:dg2 */
-static u32 *ccs_emit_wa_busywait(struct i915_request *rq, u32 *cs)
+/* Wa_16019325821 */
+/* Wa_14019159160 */
+static u32 *hold_switchout_emit_wa_busywait(struct i915_request *rq, u32 *cs)
 {
 	int i;
 
 	*cs++ = MI_ATOMIC_INLINE | MI_ATOMIC_GLOBAL_GTT | MI_ATOMIC_CS_STALL |
 		MI_ATOMIC_MOVE;
-	*cs++ = ccs_semaphore_offset(rq);
+	*cs++ = hold_switchout_semaphore_offset(rq);
 	*cs++ = 0;
 	*cs++ = 1;
 
@@ -688,7 +776,7 @@ static u32 *ccs_emit_wa_busywait(struct i915_request *rq, u32 *cs)
 		MI_SEMAPHORE_POLL |
 		MI_SEMAPHORE_SAD_EQ_SDD;
 	*cs++ = 0;
-	*cs++ = ccs_semaphore_offset(rq);
+	*cs++ = hold_switchout_semaphore_offset(rq);
 	*cs++ = 0;
 
 	return cs;
@@ -705,8 +793,10 @@ gen12_emit_fini_breadcrumb_tail(struct i915_request *rq, u32 *cs)
 		cs = gen12_emit_preempt_busywait(rq, cs);
 
 	/* Wa_14014475959:dg2 */
-	if (intel_engine_uses_wa_hold_ccs_switchout(rq->engine))
-		cs = ccs_emit_wa_busywait(rq, cs);
+	/* Wa_16019325821 */
+	/* Wa_14019159160 */
+	if (intel_engine_uses_wa_hold_switchout(rq->engine))
+		cs = hold_switchout_emit_wa_busywait(rq, cs);
 
 	rq->tail = intel_ring_offset(rq, cs);
 	assert_ring_tail_valid(rq->ring, rq->tail);
@@ -723,21 +813,30 @@ u32 *gen12_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
 
 u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
-	struct drm_i915_private *i915 = rq->engine->i915;
+	struct drm_i915_private *i915 = rq->i915;
+	struct intel_gt *gt = rq->engine->gt;
 	u32 flags = (PIPE_CONTROL_CS_STALL |
 		     PIPE_CONTROL_TLB_INVALIDATE |
 		     PIPE_CONTROL_TILE_CACHE_FLUSH |
-		     PIPE_CONTROL_FLUSH_L3 |
 		     PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
 		     PIPE_CONTROL_DEPTH_CACHE_FLUSH |
 		     PIPE_CONTROL_DC_FLUSH_ENABLE |
 		     PIPE_CONTROL_FLUSH_ENABLE);
 
-	if (GRAPHICS_VER(i915) == 12 && GRAPHICS_VER_FULL(i915) < IP_VER(12, 50))
+	if (GRAPHICS_VER_FULL(rq->i915) < IP_VER(12, 70))
+		flags |= PIPE_CONTROL_FLUSH_L3;
+
+	/* Wa_14016712196 */
+	if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)) || IS_DG2(i915))
+		/* dummy PIPE_CONTROL + depth flush */
+		cs = gen12_emit_pipe_control(cs, 0,
+					     PIPE_CONTROL_DEPTH_CACHE_FLUSH, 0);
+
+	if (GRAPHICS_VER(i915) == 12 && GRAPHICS_VER_FULL(i915) < IP_VER(12, 55))
 		/* Wa_1409600907 */
 		flags |= PIPE_CONTROL_DEPTH_STALL;
 
-	if (!HAS_3D_PIPELINE(rq->engine->i915))
+	if (!HAS_3D_PIPELINE(rq->i915))
 		flags &= ~PIPE_CONTROL_3D_ARCH_FLAGS;
 	else if (rq->engine->class == COMPUTE_CLASS)
 		flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;