[PATCH 2/2] drm/i915/gt: Poll aux invalidation register bit on invalidation

[Andi Shyti]

From: Jonathan Cavitt <jonathan.cavitt at intel.com>

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

Signed-off-by: Jonathan Cavitt <jonathan.cavitt at intel.com>
Signed-off-by: Andi Shyti <andi.shyti at linux.intel.com>
---
 drivers/gpu/drm/i915/gt/gen8_engine_cs.c     | 17 +++++++++++++----
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h |  1 +
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 6f830f80eb0f8..d93484211abdb 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -174,6 +174,16 @@ u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv
 	*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;
+	*cs++ = MI_NOOP;
+
 	return cs;
 }
 
@@ -243,10 +253,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 		else if (engine->class == COMPUTE_CLASS)
 			flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;
 
+		count = 8;
 		if (!HAS_FLAT_CCS(rq->engine->i915))
-			count = 8 + 4;
-		else
-			count = 8;
+			count += 10;
 
 		cs = intel_ring_begin(rq, count);
 		if (IS_ERR(cs))
@@ -289,7 +298,7 @@ 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 += 10;
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index e10507fa71ce6..8026b6a891923 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/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)
-- 
2.39.2