drm/i915/gt: Poll aux invalidation register bit on invalidation

For platforms that use Aux CCS, wait for aux invalidation to
complete by checking the aux invalidation register bit is
cleared.

Fixes: 972282c4 ("drm/i915/gen12: Add aux table invalidate for all engines")
Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.8+
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230725001950.1014671-7-andi.shyti@linux.intel.com

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

@@ -184,7 +184,15 @@ u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv
 	*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;
 }
@@ -292,10 +300,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 		else if (engine->class == COMPUTE_CLASS)
 			flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;
 
-		if (gen12_needs_ccs_aux_inv(rq->engine))
-			count = 8 + 4;
-		else
 		count = 8;
+		if (gen12_needs_ccs_aux_inv(rq->engine))
+			count += 8;
 
 		cs = intel_ring_begin(rq, count);
 		if (IS_ERR(cs))
@@ -338,7 +345,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
 			aux_inv = rq->engine->mask &
 				~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0);
 			if (aux_inv)
-				cmd += 4;
+				cmd += 8;
 		}
 	}
 

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

@@ -121,6 +121,7 @@
 #define   MI_SEMAPHORE_TARGET(engine)	((engine)<<15)
 #define MI_SEMAPHORE_WAIT	MI_INSTR(0x1c, 2) /* GEN8+ */
 #define MI_SEMAPHORE_WAIT_TOKEN	MI_INSTR(0x1c, 3) /* GEN12+ */
+#define   MI_SEMAPHORE_REGISTER_POLL	(1 << 16)
 #define   MI_SEMAPHORE_POLL		(1 << 15)
 #define   MI_SEMAPHORE_SAD_GT_SDD	(0 << 12)
 #define   MI_SEMAPHORE_SAD_GTE_SDD	(1 << 12)