drm/i915/gen12: Fix HDC pipeline flush

HDC pipeline flush is bit on the first dword of
the PIPE_CONTROL, not the second. Make it so.

v2: function naming (Chris)
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200506144734.29297-2-mika.kuoppala@linux.intel.com

drivers/gpu/drm/i915/gt/intel_engine.h

@@ -241,19 +241,29 @@ void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
 void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine,
 				    struct drm_printer *p);
 
-static inline u32 *gen8_emit_pipe_control(u32 *batch, u32 flags, u32 offset)
+static inline u32 *__gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset)
 {
 	memset(batch, 0, 6 * sizeof(u32));
 
-	batch[0] = GFX_OP_PIPE_CONTROL(6);
-	batch[1] = flags;
+	batch[0] = GFX_OP_PIPE_CONTROL(6) | flags0;
+	batch[1] = flags1;
 	batch[2] = offset;
 
 	return batch + 6;
 }
 
+static inline u32 *gen8_emit_pipe_control(u32 *batch, u32 flags, u32 offset)
+{
+	return __gen8_emit_pipe_control(batch, 0, flags, offset);
+}
+
+static inline u32 *gen12_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset)
+{
+	return __gen8_emit_pipe_control(batch, flags0, flags1, offset);
+}
+
 static inline u32 *
-gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
+__gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
 {
 	/* We're using qword write, offset should be aligned to 8 bytes. */
 	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
@@ -262,8 +272,8 @@ gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 	 * need a prior CS_STALL, which is emitted by the flush
 	 * following the batch.
 	 */
-	*cs++ = GFX_OP_PIPE_CONTROL(6);
-	*cs++ = flags | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB;
+	*cs++ = GFX_OP_PIPE_CONTROL(6) | flags0;
+	*cs++ = flags1 | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB;
 	*cs++ = gtt_offset;
 	*cs++ = 0;
 	*cs++ = value;
@@ -273,6 +283,18 @@ gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 	return cs;
 }
 
+static inline u32*
+gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
+{
+	return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, 0, flags);
+}
+
+static inline u32*
+gen12_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
+{
+	return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, flags0, flags1);
+}
+
 static inline u32 *
 gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 {

drivers/gpu/drm/i915/gt/intel_gpu_commands.h

@@ -237,7 +237,7 @@
 #define   PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE	(1<<11) /* MBZ on ILK */
 #define   PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE		(1<<10) /* GM45+ only */
 #define   PIPE_CONTROL_INDIRECT_STATE_DISABLE		(1<<9)
-#define   PIPE_CONTROL_HDC_PIPELINE_FLUSH		REG_BIT(9)  /* gen12 */
+#define   PIPE_CONTROL0_HDC_PIPELINE_FLUSH		REG_BIT(9)  /* gen12 */
 #define   PIPE_CONTROL_NOTIFY				(1<<8)
 #define   PIPE_CONTROL_FLUSH_ENABLE			(1<<7) /* gen7+ */
 #define   PIPE_CONTROL_DC_FLUSH_ENABLE			(1<<5)

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

@@ -4553,7 +4553,6 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_DEPTH_STALL;
 		flags |= PIPE_CONTROL_DC_FLUSH_ENABLE;
 		flags |= PIPE_CONTROL_FLUSH_ENABLE;
-		flags |= PIPE_CONTROL_HDC_PIPELINE_FLUSH;
 
 		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 		flags |= PIPE_CONTROL_QW_WRITE;
@@ -4564,7 +4563,9 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
-		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
+		cs = gen12_emit_pipe_control(cs,
+					     PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
+					     flags, LRC_PPHWSP_SCRATCH_ADDR);
 		intel_ring_advance(request, cs);
 	}
 
@@ -4751,9 +4752,10 @@ static u32 *gen12_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs)
 static u32 *
 gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 {
-	cs = gen8_emit_ggtt_write_rcs(cs,
+	cs = gen12_emit_ggtt_write_rcs(cs,
 				       request->fence.seqno,
 				       i915_request_active_timeline(request)->hwsp_offset,
+				       PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
 				       PIPE_CONTROL_CS_STALL |
 				       PIPE_CONTROL_TILE_CACHE_FLUSH |
 				       PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
@@ -4761,8 +4763,7 @@ gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 				       /* Wa_1409600907:tgl */
 				       PIPE_CONTROL_DEPTH_STALL |
 				       PIPE_CONTROL_DC_FLUSH_ENABLE |
-				      PIPE_CONTROL_FLUSH_ENABLE |
-				      PIPE_CONTROL_HDC_PIPELINE_FLUSH);
+				       PIPE_CONTROL_FLUSH_ENABLE);
 
 	return gen12_emit_fini_breadcrumb_tail(request, cs);
 }