drm/amdgpu: Add AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES

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
v3: Bump KMS version
v4: put old fence AFTER acquiring the scheduled fence.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Suggested-by: Christian Koenig <Christian.Koenig@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 12 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 1c49b8266d69..52a5e4fdc95b 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 +1091,15 @@ 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);
+                        struct dma_fence *old = fence;
+
+                        fence = dma_fence_get(&s_fence->scheduled);
+                        dma_fence_put(old);
+                }
+
                 if (IS_ERR(fence)) {
                         r = PTR_ERR(fence);
                         amdgpu_ctx_put(ctx);
@@ -1177,7 +1187,8 @@ 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;