[PATCH v6 7/9] drm/i915/gt: Enable the CCS_FLUSH bit in the pipe control

[Andi Shyti <andi.shyti@xxxxxxxxxxxxxxx>]

Enable the CCS_FLUSH bit 13 in the control pipe for render and
compute engines in platforms starting from Meteor Lake (BSPEC
43904 and 47112). The VE and BCS engines need to add the flush
part in their command streamer.

Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines")
Signed-off-by: Andi Shyti <andi.shyti@xxxxxxxxxxxxxxx>
Cc: Jonathan Cavitt <jonathan.cavitt@xxxxxxxxx>
Cc: Nirmoy Das <nirmoy.das@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> # v5.8+
---
 drivers/gpu/drm/i915/gt/gen8_engine_cs.c     | 31 ++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h |  1 +
 2 files changed, 32 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 3bedab8d61db1..78bbd55262a2d 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -225,6 +225,13 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 
 		bit_group_0 |= PIPE_CONTROL0_HDC_PIPELINE_FLUSH;
 
+		/*
+		 * When required, in MTL+ 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;
+
 		bit_group_1 |= PIPE_CONTROL_TILE_CACHE_FLUSH;
 		bit_group_1 |= PIPE_CONTROL_FLUSH_L3;
 		bit_group_1 |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
@@ -309,6 +316,7 @@ 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_flush = 0;
 	u32 cmd = 4;
 	u32 *cs;
 
@@ -339,6 +347,13 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
 			bit_group_1 |= PIPE_CONTROL_FLUSH_L3;
 			bit_group_1 |= PIPE_CONTROL_CS_STALL;
 
+			/*
+			 * When required, in MTL+ 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;
+
 			intel_emit_pipe_control_cs(rq, bit_group_0, bit_group_1,
 						   LRC_PPHWSP_SCRATCH_ADDR);
 
@@ -346,7 +361,18 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
 
 		case VIDEO_ENHANCEMENT_CLASS:
 		case COMPUTE_CLASS:
+			cmd += 2;
+			cmd_flush = MI_FLUSH_DW;
+
+			break;
+
 		case COPY_ENGINE_CLASS:
+			cmd += 2;
+			/*
+			 * When required, in MTL+ platforms we need to
+			 * set the CCS_FLUSH bit in the pipe control
+			 */
+			cmd_flush = MI_FLUSH_DW | MI_FLUSH_DW_CCS;
 			break;
 		}
 	}
@@ -355,6 +381,11 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
+	if (cmd_flush) {
+		*cs++ = cmd_flush;
+		*cs++ = 0;
+	}
+
 	if (mode & EMIT_INVALIDATE)
 		*cs++ = preparser_disable(true);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 5d143e2a8db03..5df7cce23197c 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -299,6 +299,7 @@
 #define   PIPE_CONTROL_QW_WRITE				(1<<14)
 #define   PIPE_CONTROL_POST_SYNC_OP_MASK                (3<<14)
 #define   PIPE_CONTROL_DEPTH_STALL			(1<<13)
+#define   PIPE_CONTROL_CCS_FLUSH			(1<<13) /* MTL+ */
 #define   PIPE_CONTROL_WRITE_FLUSH			(1<<12)
 #define   PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH	(1<<12) /* gen6+ */
 #define   PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE	(1<<11) /* MBZ on ILK */
-- 
2.40.1