[PATCH v5 05/16] drm/xe/xelp: Quiesce memory traffic before invalidating auxccs

[Tvrtko Ursulin]

According to i915 before invalidating auxccs we must quiesce the memory
traffic by an extra flush.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at igalia.com>
---
 drivers/gpu/drm/xe/xe_ring_ops.c       | 14 ++++++++++----
 drivers/gpu/drm/xe/xe_ring_ops_types.h |  2 +-
 2 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 61295f93ffb7..3f075dd36c86 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -172,7 +172,8 @@ static int emit_store_imm_ppgtt_posted(u64 addr, u64 value,
 	return i;
 }
 
-static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i)
+static int emit_render_cache_flush(struct xe_sched_job *job, bool flush_l3,
+				   u32 *dw, int i)
 {
 	struct xe_gt *gt = job->q->gt;
 	struct xe_device *xe = gt_to_xe(gt);
@@ -204,7 +205,7 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i)
 	 * deals with Protected Memory which is not needed for
 	 * AUX CCS invalidation and lead to unwanted side effects.
 	 */
-	if (GRAPHICS_VERx100(xe) < 1270)
+	if (flush_l3 && GRAPHICS_VERx100(xe) < 1270)
 		flags |= PIPE_CONTROL_FLUSH_L3;
 
 	if (lacks_render)
@@ -370,10 +371,15 @@ 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;
 
 	i = emit_copy_timestamp(lrc, dw, i);
 
+	/* hsdes: 1809175790 */
+	if (aux_ccs)
+		i = emit_render_cache_flush(job, 0, dw, i);
+
 	dw[i++] = preparser_disable(true);
 	if (lacks_render)
 		mask_flags = PIPE_CONTROL_3D_ARCH_FLAGS;
@@ -384,7 +390,7 @@ 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);
@@ -394,7 +400,7 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
-	i = emit_render_cache_flush(job, dw, i);
+	i = emit_render_cache_flush(job, true, dw, i);
 
 	if (job->user_fence.used)
 		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
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)
 
 /**
-- 
2.48.0