As per the recommendation, A7x and newer GPUs should flush the LRZ cache
before switching the pagetable. Update a6xx_set_pagetable() to do this.
While we are at it, sync both BV and BR before issuing  a
CP_RESET_CONTEXT_STATE command, to match the downstream sequence.

Fixes: af66706accdf ("drm/msm/a6xx: Add skeleton A7xx support")
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Signed-off-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 779c1da7c46d..e6393ef0fd78 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -224,7 +224,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 		OUT_RING(ring, submit->seqno - 1);
 
 		OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
-		OUT_RING(ring, CP_SET_THREAD_BOTH);
+		OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BOTH);
 
 		/* Reset state used to synchronize BR and BV */
 		OUT_PKT7(ring, CP_RESET_CONTEXT_STATE, 1);
@@ -235,7 +235,13 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 			 CP_RESET_CONTEXT_STATE_0_RESET_GLOBAL_LOCAL_TS);
 
 		OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
-		OUT_RING(ring, CP_SET_THREAD_BR);
+		OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BOTH);
+
+		OUT_PKT7(ring, CP_EVENT_WRITE, 1);
+		OUT_RING(ring, LRZ_FLUSH);
+
+		OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+		OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BR);
 	}
 
 	if (!sysprof) {

-- 
2.51.0