drm/amdgpu: generally allow over-commit during BO allocation

We already fallback to a dummy BO with no backing store when we
allocate GDS,GWS and OA resources and to GTT when we allocate VRAM.

Drop all those workarounds and generalize this for GTT as well. This
fixes ENOMEM issues with runaway applications which try to allocate/free
GTT in a loop and are otherwise only limited by the CPU speed.

The CS will wait for the cleanup of freed up BOs to satisfy the
various domain specific limits and so effectively throttle those
buggy applications down to a sane allocation behavior again.

Signed-off-by: Christian König <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Arunpravin Paneer Selvam <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

Author: ChristianKoenigAMD

drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c

@@ -113,7 +113,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
 	bp.resv = resv;
 	bp.preferred_domain = initial_domain;
 	bp.flags = flags;
-	bp.domain = initial_domain;
+	bp.domain = initial_domain | AMDGPU_GEM_DOMAIN_CPU;
 	bp.bo_ptr_size = sizeof(struct amdgpu_bo);
 
 	r = amdgpu_bo_create_user(adev, &bp, &ubo);
@@ -332,20 +332,10 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 	}
 
 	initial_domain = (u32)(0xffffffff & args->in.domains);
-retry:
 	r = amdgpu_gem_object_create(adev, size, args->in.alignment,
-				     initial_domain,
-				     flags, ttm_bo_type_device, resv, &gobj);
+				     initial_domain, flags, ttm_bo_type_device,
+				     resv, &gobj);
 	if (r && r != -ERESTARTSYS) {
-		if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) {
-			flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-			goto retry;
-		}
-
-		if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) {
-			initial_domain |= AMDGPU_GEM_DOMAIN_GTT;
-			goto retry;
-		}
 		DRM_DEBUG("Failed to allocate GEM object (%llu, %d, %llu, %d)\n",
 				size, initial_domain, args->in.alignment, r);
 	}

drivers/gpu/drm/amd/amdgpu/amdgpu_object.c

@@ -581,11 +581,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 		bo->flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
 
 	bo->tbo.bdev = &adev->mman.bdev;
-	if (bp->domain & (AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA |
-			  AMDGPU_GEM_DOMAIN_GDS))
-		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
-	else
-		amdgpu_bo_placement_from_domain(bo, bp->domain);
+	amdgpu_bo_placement_from_domain(bo, bp->domain);
 	if (bp->type == ttm_bo_type_kernel)
 		bo->tbo.priority = 1;