drm/amdgpu: clean up memory/GDS/GWS/OA alignment code

- move all adjustments into one place
- specify GDS/GWS/OA alignment in basic units of the heaps
- it looks like GDS alignment was 1 instead of 4
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -54,10 +54,6 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
 
 	memset(&bp, 0, sizeof(bp));
 	*obj = NULL;
-	/* At least align on page size */
-	if (alignment < PAGE_SIZE) {
-		alignment = PAGE_SIZE;
-	}
 
 	bp.size = size;
 	bp.byte_align = alignment;
@@ -244,9 +240,6 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 			return -EINVAL;
 		}
 		flags |= AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
-		/* GDS allocations must be DW aligned */
-		if (args->in.domains & AMDGPU_GEM_DOMAIN_GDS)
-			size = ALIGN(size, 4);
 	}
 
 	if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) {

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

@@ -426,12 +426,20 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 	size_t acc_size;
 	int r;
 
-	page_align = roundup(bp->byte_align, PAGE_SIZE) >> PAGE_SHIFT;
-	if (bp->domain & (AMDGPU_GEM_DOMAIN_GDS | AMDGPU_GEM_DOMAIN_GWS |
-			  AMDGPU_GEM_DOMAIN_OA))
+	/* Note that GDS/GWS/OA allocates 1 page per byte/resource. */
+	if (bp->domain & (AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) {
+		/* GWS and OA don't need any alignment. */
+		page_align = bp->byte_align;
 		size <<= PAGE_SHIFT;
-	else
+	} else if (bp->domain & AMDGPU_GEM_DOMAIN_GDS) {
+		/* Both size and alignment must be a multiple of 4. */
+		page_align = ALIGN(bp->byte_align, 4);
+		size = ALIGN(size, 4) << PAGE_SHIFT;
+	} else {
+		/* Memory should be aligned at least to a page size. */
+		page_align = ALIGN(bp->byte_align, PAGE_SIZE) >> PAGE_SHIFT;
 		size = ALIGN(size, PAGE_SIZE);
+	}
 
 	if (!amdgpu_bo_validate_size(adev, size, bp->domain))
 		return -ENOMEM;

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

@@ -1756,7 +1756,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	}
 
 	r = amdgpu_bo_create_kernel(adev, adev->gds.mem.gfx_partition_size,
-				    PAGE_SIZE, AMDGPU_GEM_DOMAIN_GDS,
+				    4, AMDGPU_GEM_DOMAIN_GDS,
 				    &adev->gds.gds_gfx_bo, NULL, NULL);
 	if (r)
 		return r;
@@ -1769,7 +1769,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	}
 
 	r = amdgpu_bo_create_kernel(adev, adev->gds.gws.gfx_partition_size,
-				    PAGE_SIZE, AMDGPU_GEM_DOMAIN_GWS,
+				    1, AMDGPU_GEM_DOMAIN_GWS,
 				    &adev->gds.gws_gfx_bo, NULL, NULL);
 	if (r)
 		return r;
@@ -1782,7 +1782,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	}
 
 	r = amdgpu_bo_create_kernel(adev, adev->gds.oa.gfx_partition_size,
-				    PAGE_SIZE, AMDGPU_GEM_DOMAIN_OA,
+				    1, AMDGPU_GEM_DOMAIN_OA,
 				    &adev->gds.oa_gfx_bo, NULL, NULL);
 	if (r)
 		return r;