[PATCH v15 02/10] drm/xe/xelp: Quiesce memory traffic before invalidating AuxCCS

[Tvrtko Ursulin <tursulin@igalia.com>]

From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>

According to i915 commit
ad8ebf12217e ("drm/i915/gt: Ensure memory quiesced before invalidation")
quiescing of the memory traffic is required before invalidating the AuxCCS
tables.

Add an extra pipe control flush to achieve that.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_ring_ops.c       | 10 +++++++++-
 drivers/gpu/drm/xe/xe_ring_ops_types.h |  2 +-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 5336ea626031..bc806cabb5c3 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -358,12 +358,20 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 	struct xe_gt *gt = job->q->gt;
 	struct xe_device *xe = gt_to_xe(gt);
 	bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK);
+	const bool aux_ccs = has_aux_ccs(xe);
 	u32 mask_flags = 0;
 
 	*head = lrc->ring.tail;
 
 	i = emit_copy_timestamp(lrc, dw, i);
 
+	/*
+	 * On AuxCCS platforms the invalidation of the Aux table requires
+	 * quiescing the memory traffic beforehand.
+	 */
+	if (aux_ccs)
+		i = emit_render_cache_flush(job, dw, i);
+
 	dw[i++] = preparser_disable(true);
 	if (lacks_render)
 		mask_flags = PIPE_CONTROL_3D_ARCH_FLAGS;
@@ -374,7 +382,7 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 	i = emit_pipe_invalidate(mask_flags, job->ring_ops_flush_tlb, dw, i);
 
 	/* hsdes: 1809175790 */
-	if (has_aux_ccs(xe))
+	if (aux_ccs)
 		i = emit_aux_table_inv(gt, CCS_AUX_INV, dw, i);
 
 	dw[i++] = preparser_disable(false);
diff --git a/drivers/gpu/drm/xe/xe_ring_ops_types.h b/drivers/gpu/drm/xe/xe_ring_ops_types.h
index d7e3e150a9a5..477dc7defd72 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops_types.h
+++ b/drivers/gpu/drm/xe/xe_ring_ops_types.h
@@ -8,7 +8,7 @@
 
 struct xe_sched_job;
 
-#define MAX_JOB_SIZE_DW 58
+#define MAX_JOB_SIZE_DW 70
 #define MAX_JOB_SIZE_BYTES (MAX_JOB_SIZE_DW * 4)
 
 /**
-- 
2.52.0