Commit 0d938863 authored by Thomas Hellström's avatar Thomas Hellström
Browse files

drm/i915/ttm: Implement a function to copy the contents of two TTM-based objects



When backing up or restoring contents of pinned objects at suspend /
resume time we need to allocate a new object as the backup. Add a function
to facilitate copies between the two. Some data needs to be copied before
the migration context is ready for operation, so make sure we can
disable accelerated copies.

v2:
- Fix a missing return value check (Matthew Auld)

Signed-off-by: default avatarThomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: default avatarMatthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210922062527.865433-2-thomas.hellstrom@linux.intel.com
parent 2dfa597d
Loading
Loading
Loading
Loading
+60 −9
Original line number Diff line number Diff line
@@ -429,6 +429,7 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
			       bool clear,
			       struct ttm_resource *dst_mem,
			       struct ttm_tt *dst_ttm,
			       struct sg_table *dst_st)
{
	struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915),
@@ -438,14 +439,14 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
	struct sg_table *src_st;
	struct i915_request *rq;
	struct ttm_tt *ttm = bo->ttm;
	struct ttm_tt *src_ttm = bo->ttm;
	enum i915_cache_level src_level, dst_level;
	int ret;

	if (!i915->gt.migrate.context)
		return -EINVAL;

	dst_level = i915_ttm_cache_level(i915, dst_mem, ttm);
	dst_level = i915_ttm_cache_level(i915, dst_mem, dst_ttm);
	if (clear) {
		if (bo->type == ttm_bo_type_kernel)
			return -EINVAL;
@@ -462,10 +463,10 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
		}
		intel_engine_pm_put(i915->gt.migrate.context->engine);
	} else {
		src_st = src_man->use_tt ? i915_ttm_tt_get_st(ttm) :
		src_st = src_man->use_tt ? i915_ttm_tt_get_st(src_ttm) :
			obj->ttm.cached_io_st;

		src_level = i915_ttm_cache_level(i915, bo->resource, ttm);
		src_level = i915_ttm_cache_level(i915, bo->resource, src_ttm);
		intel_engine_pm_get(i915->gt.migrate.context->engine);
		ret = intel_context_migrate_copy(i915->gt.migrate.context,
						 NULL, src_st->sgl, src_level,
@@ -485,11 +486,14 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo,

static void __i915_ttm_move(struct ttm_buffer_object *bo, bool clear,
			    struct ttm_resource *dst_mem,
			    struct sg_table *dst_st)
			    struct ttm_tt *dst_ttm,
			    struct sg_table *dst_st,
			    bool allow_accel)
{
	int ret;
	int ret = -EINVAL;

	ret = i915_ttm_accel_move(bo, clear, dst_mem, dst_st);
	if (allow_accel)
		ret = i915_ttm_accel_move(bo, clear, dst_mem, dst_ttm, dst_st);
	if (ret) {
		struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
		struct intel_memory_region *dst_reg, *src_reg;
@@ -504,7 +508,7 @@ static void __i915_ttm_move(struct ttm_buffer_object *bo, bool clear,
		GEM_BUG_ON(!dst_reg || !src_reg);

		dst_iter = !cpu_maps_iomem(dst_mem) ?
			ttm_kmap_iter_tt_init(&_dst_iter.tt, bo->ttm) :
			ttm_kmap_iter_tt_init(&_dst_iter.tt, dst_ttm) :
			ttm_kmap_iter_iomap_init(&_dst_iter.io, &dst_reg->iomap,
						 dst_st, dst_reg->region.start);

@@ -559,7 +563,7 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,

	clear = !cpu_maps_iomem(bo->resource) && (!ttm || !ttm_tt_is_populated(ttm));
	if (!(clear && ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)))
		__i915_ttm_move(bo, clear, dst_mem, dst_st);
		__i915_ttm_move(bo, clear, dst_mem, bo->ttm, dst_st, true);

	ttm_bo_move_sync_cleanup(bo, dst_mem);
	i915_ttm_adjust_domains_after_move(obj);
@@ -974,3 +978,50 @@ i915_gem_ttm_system_setup(struct drm_i915_private *i915,
	intel_memory_region_set_name(mr, "system-ttm");
	return mr;
}

/**
 * i915_gem_obj_copy_ttm - Copy the contents of one ttm-based gem object to
 * another
 * @dst: The destination object
 * @src: The source object
 * @allow_accel: Allow using the blitter. Otherwise TTM memcpy is used.
 * @intr: Whether to perform waits interruptible:
 *
 * Note: The caller is responsible for assuring that the underlying
 * TTM objects are populated if needed and locked.
 *
 * Return: Zero on success. Negative error code on error. If @intr == true,
 * then it may return -ERESTARTSYS or -EINTR.
 */
int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
			  struct drm_i915_gem_object *src,
			  bool allow_accel, bool intr)
{
	struct ttm_buffer_object *dst_bo = i915_gem_to_ttm(dst);
	struct ttm_buffer_object *src_bo = i915_gem_to_ttm(src);
	struct ttm_operation_ctx ctx = {
		.interruptible = intr,
	};
	struct sg_table *dst_st;
	int ret;

	assert_object_held(dst);
	assert_object_held(src);

	/*
	 * Sync for now. This will change with async moves.
	 */
	ret = ttm_bo_wait_ctx(dst_bo, &ctx);
	if (!ret)
		ret = ttm_bo_wait_ctx(src_bo, &ctx);
	if (ret)
		return ret;

	dst_st = gpu_binds_iomem(dst_bo->resource) ?
		dst->ttm.cached_io_st : i915_ttm_tt_get_st(dst_bo->ttm);

	__i915_ttm_move(src_bo, false, dst_bo->resource, dst_bo->ttm,
			dst_st, allow_accel);

	return 0;
}
+4 −0
Original line number Diff line number Diff line
@@ -46,4 +46,8 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
			       resource_size_t size,
			       resource_size_t page_size,
			       unsigned int flags);

int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
			  struct drm_i915_gem_object *src,
			  bool allow_accel, bool intr);
#endif