drm/amdgpu: install ctx entities with cmpxchg

Since we removed the context lock we need to make sure that not two threads
are trying to install an entity at the same time.

Signed-off-by: Christian König <christian.koenig@amd.com>
Fixes: 461fa7b0ac565e ("drm/amdgpu: remove ctx->lock")
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 2d2dcea..5981c7d 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -205,9 +205,15 @@ static int amdgpu_ctx_init_entity(struct amdgpu_ctx *ctx, u32 hw_ip,
        if (r)
                goto error_free_entity;
 
-       ctx->entities[hw_ip][ring] = entity;
+       /* It's not an error if we fail to install the new entity */
+       if (cmpxchg(&ctx->entities[hw_ip][ring], NULL, entity))
+               goto cleanup_entity;
+
        return 0;
 
+cleanup_entity:
+       drm_sched_entity_fini(&entity->entity);
+
 error_free_entity:
        kfree(entity);