[PATCH v2 4/4] drm/amdgpu: Add a UAPI flag for user to call mem_sync

[Andrey Grodzovsky]

This flag used to avoid calling mem_sync without need.

v2:
Move new flag to drm_amdgpu_cs_chunk_ib.flags
Bump up UAPI version
Remove condition on job != null to emit mem_sync

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c  | 3 +++
 include/uapi/drm/amdgpu_drm.h           | 4 ++++
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 28bb840..f18d974 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -85,9 +85,10 @@
  * - 3.34.0 - Non-DC can flip correctly between buffers with different pitches
  * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask
  * - 3.36.0 - Allow reading more status registers on si/cik
+ * - 3.37.0 - Add AMDGPU_IB_FLAG_EMIT_MEM_SYNC
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	36
+#define KMS_DRIVER_MINOR	37
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index bece01f..a8aa787 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -182,6 +182,9 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		dma_fence_put(tmp);
 	}
 
+	if ((ib->flags & AMDGPU_IB_FLAG_EMIT_MEM_SYNC) && ring->funcs->emit_mem_sync)
+		ring->funcs->emit_mem_sync(ring);
+
 	if (ring->funcs->insert_start)
 		ring->funcs->insert_start(ring);
 
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index cfbec27..5f7a4f5 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -601,6 +601,10 @@ union drm_amdgpu_cs {
  */
 #define AMDGPU_IB_FLAGS_SECURE  (1 << 5)
 
+/* Tell KMD to flush and invalidate caches
+ */
+#define AMDGPU_IB_FLAG_EMIT_MEM_SYNC  (1 << 6)
+
 struct drm_amdgpu_cs_chunk_ib {
 	__u32 _pad;
 	/** AMDGPU_IB_FLAG_* */
-- 
2.7.4