drm/i915/gt: Add workaround 14016712196

For mtl, workaround suggests that, SW insert a
dummy PIPE_CONTROL prior to PIPE_CONTROL which
contains a post sync: Timestamp or Write Immediate.

Bspec: 72197

V5:
  - Remove ret variable - Andi
V4:
  - Update commit message, avoid returing cs - Andi/Matt
V3:
  - Wrap dummy pipe control stuff in API - Andi
V2:
  - Fix  kernel test robot warnings

Closes: https://lore.kernel.org/oe-kbuild-all/202305121525.3EWdGoBY-lkp@intel.com/
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230601110959.1715927-1-tejas.upadhyay@intel.com

Author: tejasup

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

@@ -177,14 +177,40 @@ u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv
 	return cs;
 }
 
+static int mtl_dummy_pipe_control(struct i915_request *rq)
+{
+	/* Wa_14016712196 */
+	if (IS_MTL_GRAPHICS_STEP(rq->engine->i915, M, STEP_A0, STEP_B0) ||
+	    IS_MTL_GRAPHICS_STEP(rq->engine->i915, P, STEP_A0, STEP_B0)) {
+		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;
+		int err;
 		u32 *cs;
 
+		err = mtl_dummy_pipe_control(rq);
+		if (err)
+			return err;
+
 		flags |= PIPE_CONTROL_TILE_CACHE_FLUSH;
 		flags |= PIPE_CONTROL_FLUSH_L3;
 		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
@@ -217,6 +243,11 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 	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;
@@ -733,6 +764,13 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 		     PIPE_CONTROL_DC_FLUSH_ENABLE |
 		     PIPE_CONTROL_FLUSH_ENABLE);
 
+	/* Wa_14016712196 */
+	if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) ||
+	    IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0))
+		/* 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, 50))
 		/* Wa_1409600907 */
 		flags |= PIPE_CONTROL_DEPTH_STALL;