[PATCH v2] drm/amdgpu: Add AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES

[Andrey Grodzovsky]

New chunk for dependency on start of job's execution instead on
the end. This is used for GPU deadlock prevention when
userspace uses mid-IB fences to wait for mid-IB work on other rings.

v2: Fix typo in AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky at amd.com>
Suggested-by: Christian Koenig <Christian.Koenig at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 12 +++++++++++-
 include/uapi/drm/amdgpu_drm.h          |  1 +
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 1c49b82..3f21eca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -214,6 +214,7 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
 		case AMDGPU_CHUNK_ID_DEPENDENCIES:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
+		case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES:
 			break;
 
 		default:
@@ -1090,6 +1091,14 @@ static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
 
 		fence = amdgpu_ctx_get_fence(ctx, entity,
 					     deps[i].handle);
+
+		if (chunk->chunk_id == AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES) {
+			struct drm_sched_fence *s_fence = to_drm_sched_fence(fence);
+
+			dma_fence_put(fence);
+			fence = dma_fence_get(&s_fence->scheduled);
+		}
+
 		if (IS_ERR(fence)) {
 			r = PTR_ERR(fence);
 			amdgpu_ctx_put(ctx);
@@ -1177,7 +1186,8 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 
 		chunk = &p->chunks[i];
 
-		if (chunk->chunk_id == AMDGPU_CHUNK_ID_DEPENDENCIES) {
+		if (chunk->chunk_id == AMDGPU_CHUNK_ID_DEPENDENCIES ||
+		    chunk->chunk_id == AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES) {
 			r = amdgpu_cs_process_fence_dep(p, chunk);
 			if (r)
 				return r;
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index faaad04..43d03a2 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -526,6 +526,7 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_CHUNK_ID_SYNCOBJ_IN      0x04
 #define AMDGPU_CHUNK_ID_SYNCOBJ_OUT     0x05
 #define AMDGPU_CHUNK_ID_BO_HANDLES      0x06
+#define AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES	0x07
 
 struct drm_amdgpu_cs_chunk {
 	__u32		chunk_id;
-- 
2.7.4