Add back our standalone i915_buddy allocator and integrate it into a ttm_resource_manager. This will plug into our ttm backend for managing device local-memory in the next couple of patches. Signed-off-by: Matthew Auld <matthew.auld@xxxxxxxxx> Cc: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx> --- drivers/gpu/drm/i915/Makefile | 2 + drivers/gpu/drm/i915/i915_buddy.c | 412 +++++++++ drivers/gpu/drm/i915/i915_buddy.h | 133 +++ drivers/gpu/drm/i915/i915_ttm_buddy_manager.c | 246 ++++++ drivers/gpu/drm/i915/i915_ttm_buddy_manager.h | 56 ++ drivers/gpu/drm/i915/selftests/i915_buddy.c | 789 ++++++++++++++++++ 6 files changed, 1638 insertions(+) create mode 100644 drivers/gpu/drm/i915/i915_buddy.c create mode 100644 drivers/gpu/drm/i915/i915_buddy.h create mode 100644 drivers/gpu/drm/i915/i915_ttm_buddy_manager.c create mode 100644 drivers/gpu/drm/i915/i915_ttm_buddy_manager.h create mode 100644 drivers/gpu/drm/i915/selftests/i915_buddy.c diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index f57dfc74d6ce..6c84e96ab26a 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -162,6 +162,7 @@ gem-y += \ i915-y += \ $(gem-y) \ i915_active.o \ + i915_buddy.o \ i915_cmd_parser.o \ i915_gem_evict.o \ i915_gem_gtt.o \ @@ -171,6 +172,7 @@ i915-y += \ i915_request.o \ i915_scheduler.o \ i915_trace_points.o \ + i915_ttm_buddy_manager.o \ i915_vma.o \ intel_wopcm.o diff --git a/drivers/gpu/drm/i915/i915_buddy.c b/drivers/gpu/drm/i915/i915_buddy.c new file mode 100644 index 000000000000..29dd7d0310c1 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_buddy.c @@ -0,0 +1,412 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include <linux/kmemleak.h> + +#include "i915_buddy.h" + +#include "i915_gem.h" +#include "i915_utils.h" + +static struct i915_buddy_block *i915_block_alloc(struct i915_buddy_mm *mm, + struct i915_buddy_block *parent, + unsigned int order, + u64 offset) +{ + struct i915_buddy_block *block; + + GEM_BUG_ON(order > I915_BUDDY_MAX_ORDER); + + block = kmem_cache_zalloc(mm->slab_blocks, GFP_KERNEL); + if (!block) + return NULL; + + block->header = offset; + block->header |= order; + block->parent = parent; + + GEM_BUG_ON(block->header & I915_BUDDY_HEADER_UNUSED); + return block; +} + +static void i915_block_free(struct i915_buddy_mm *mm, + struct i915_buddy_block *block) +{ + kmem_cache_free(mm->slab_blocks, block); +} + +static void mark_allocated(struct i915_buddy_block *block) +{ + block->header &= ~I915_BUDDY_HEADER_STATE; + block->header |= I915_BUDDY_ALLOCATED; + + list_del(&block->link); +} + +static void mark_free(struct i915_buddy_mm *mm, + struct i915_buddy_block *block) +{ + block->header &= ~I915_BUDDY_HEADER_STATE; + block->header |= I915_BUDDY_FREE; + + list_add(&block->link, + &mm->free_list[i915_buddy_block_order(block)]); +} + +static void mark_split(struct i915_buddy_block *block) +{ + block->header &= ~I915_BUDDY_HEADER_STATE; + block->header |= I915_BUDDY_SPLIT; + + list_del(&block->link); +} + +int i915_buddy_init(struct i915_buddy_mm *mm, u64 size, u64 chunk_size) +{ + unsigned int i; + u64 offset; + + if (size < chunk_size) + return -EINVAL; + + if (chunk_size < PAGE_SIZE) + return -EINVAL; + + if (!is_power_of_2(chunk_size)) + return -EINVAL; + + size = round_down(size, chunk_size); + + mm->size = size; + mm->chunk_size = chunk_size; + mm->max_order = ilog2(size) - ilog2(chunk_size); + + GEM_BUG_ON(mm->max_order > I915_BUDDY_MAX_ORDER); + + mm->slab_blocks = KMEM_CACHE(i915_buddy_block, SLAB_HWCACHE_ALIGN); + if (!mm->slab_blocks) + return -ENOMEM; + + mm->free_list = kmalloc_array(mm->max_order + 1, + sizeof(struct list_head), + GFP_KERNEL); + if (!mm->free_list) + goto out_destroy_slab; + + for (i = 0; i <= mm->max_order; ++i) + INIT_LIST_HEAD(&mm->free_list[i]); + + mm->n_roots = hweight64(size); + + mm->roots = kmalloc_array(mm->n_roots, + sizeof(struct i915_buddy_block *), + GFP_KERNEL); + if (!mm->roots) + goto out_free_list; + + offset = 0; + i = 0; + + /* + * Split into power-of-two blocks, in case we are given a size that is + * not itself a power-of-two. + */ + do { + struct i915_buddy_block *root; + unsigned int order; + u64 root_size; + + root_size = rounddown_pow_of_two(size); + order = ilog2(root_size) - ilog2(chunk_size); + + root = i915_block_alloc(mm, NULL, order, offset); + if (!root) + goto out_free_roots; + + mark_free(mm, root); + + GEM_BUG_ON(i > mm->max_order); + GEM_BUG_ON(i915_buddy_block_size(mm, root) < chunk_size); + + mm->roots[i] = root; + + offset += root_size; + size -= root_size; + i++; + } while (size); + + return 0; + +out_free_roots: + while (i--) + i915_block_free(mm, mm->roots[i]); + kfree(mm->roots); +out_free_list: + kfree(mm->free_list); +out_destroy_slab: + kmem_cache_destroy(mm->slab_blocks); + return -ENOMEM; +} + +void i915_buddy_fini(struct i915_buddy_mm *mm) +{ + int i; + + for (i = 0; i < mm->n_roots; ++i) { + GEM_WARN_ON(!i915_buddy_block_is_free(mm->roots[i])); + i915_block_free(mm, mm->roots[i]); + } + + kfree(mm->roots); + kfree(mm->free_list); + kmem_cache_destroy(mm->slab_blocks); +} + +static int split_block(struct i915_buddy_mm *mm, + struct i915_buddy_block *block) +{ + unsigned int block_order = i915_buddy_block_order(block) - 1; + u64 offset = i915_buddy_block_offset(block); + + GEM_BUG_ON(!i915_buddy_block_is_free(block)); + GEM_BUG_ON(!i915_buddy_block_order(block)); + + block->left = i915_block_alloc(mm, block, block_order, offset); + if (!block->left) + return -ENOMEM; + + block->right = i915_block_alloc(mm, block, block_order, + offset + (mm->chunk_size << block_order)); + if (!block->right) { + i915_block_free(mm, block->left); + return -ENOMEM; + } + + mark_free(mm, block->left); + mark_free(mm, block->right); + + mark_split(block); + + return 0; +} + +static struct i915_buddy_block * +get_buddy(struct i915_buddy_block *block) +{ + struct i915_buddy_block *parent; + + parent = block->parent; + if (!parent) + return NULL; + + if (parent->left == block) + return parent->right; + + return parent->left; +} + +static void __i915_buddy_free(struct i915_buddy_mm *mm, + struct i915_buddy_block *block) +{ + struct i915_buddy_block *parent; + + while ((parent = block->parent)) { + struct i915_buddy_block *buddy; + + buddy = get_buddy(block); + + if (!i915_buddy_block_is_free(buddy)) + break; + + list_del(&buddy->link); + + i915_block_free(mm, block); + i915_block_free(mm, buddy); + + block = parent; + } + + mark_free(mm, block); +} + +void i915_buddy_free(struct i915_buddy_mm *mm, + struct i915_buddy_block *block) +{ + GEM_BUG_ON(!i915_buddy_block_is_allocated(block)); + __i915_buddy_free(mm, block); +} + +void i915_buddy_free_list(struct i915_buddy_mm *mm, struct list_head *objects) +{ + struct i915_buddy_block *block, *on; + + list_for_each_entry_safe(block, on, objects, link) { + i915_buddy_free(mm, block); + cond_resched(); + } + INIT_LIST_HEAD(objects); +} + +/* + * Allocate power-of-two block. The order value here translates to: + * + * 0 = 2^0 * mm->chunk_size + * 1 = 2^1 * mm->chunk_size + * 2 = 2^2 * mm->chunk_size + * ... + */ +struct i915_buddy_block * +i915_buddy_alloc(struct i915_buddy_mm *mm, unsigned int order) +{ + struct i915_buddy_block *block = NULL; + unsigned int i; + int err; + + for (i = order; i <= mm->max_order; ++i) { + block = list_first_entry_or_null(&mm->free_list[i], + struct i915_buddy_block, + link); + if (block) + break; + } + + if (!block) + return ERR_PTR(-ENOSPC); + + GEM_BUG_ON(!i915_buddy_block_is_free(block)); + + while (i != order) { + err = split_block(mm, block); + if (unlikely(err)) + goto out_free; + + /* Go low */ + block = block->left; + i--; + } + + mark_allocated(block); + kmemleak_update_trace(block); + return block; + +out_free: + if (i != order) + __i915_buddy_free(mm, block); + return ERR_PTR(err); +} + +static inline bool overlaps(u64 s1, u64 e1, u64 s2, u64 e2) +{ + return s1 <= e2 && e1 >= s2; +} + +static inline bool contains(u64 s1, u64 e1, u64 s2, u64 e2) +{ + return s1 <= s2 && e1 >= e2; +} + +/* + * Allocate range. Note that it's safe to chain together multiple alloc_ranges + * with the same blocks list. + * + * Intended for pre-allocating portions of the address space, for example to + * reserve a block for the initial framebuffer or similar, hence the expectation + * here is that i915_buddy_alloc() is still the main vehicle for + * allocations, so if that's not the case then the drm_mm range allocator is + * probably a much better fit, and so you should probably go use that instead. + */ +int i915_buddy_alloc_range(struct i915_buddy_mm *mm, + struct list_head *blocks, + u64 start, u64 size) +{ + struct i915_buddy_block *block; + struct i915_buddy_block *buddy; + LIST_HEAD(allocated); + LIST_HEAD(dfs); + u64 end; + int err; + int i; + + if (size < mm->chunk_size) + return -EINVAL; + + if (!IS_ALIGNED(size | start, mm->chunk_size)) + return -EINVAL; + + if (range_overflows(start, size, mm->size)) + return -EINVAL; + + for (i = 0; i < mm->n_roots; ++i) + list_add_tail(&mm->roots[i]->tmp_link, &dfs); + + end = start + size - 1; + + do { + u64 block_start; + u64 block_end; + + block = list_first_entry_or_null(&dfs, + struct i915_buddy_block, + tmp_link); + if (!block) + break; + + list_del(&block->tmp_link); + + block_start = i915_buddy_block_offset(block); + block_end = block_start + i915_buddy_block_size(mm, block) - 1; + + if (!overlaps(start, end, block_start, block_end)) + continue; + + if (i915_buddy_block_is_allocated(block)) { + err = -ENOSPC; + goto err_free; + } + + if (contains(start, end, block_start, block_end)) { + if (!i915_buddy_block_is_free(block)) { + err = -ENOSPC; + goto err_free; + } + + mark_allocated(block); + list_add_tail(&block->link, &allocated); + continue; + } + + if (!i915_buddy_block_is_split(block)) { + err = split_block(mm, block); + if (unlikely(err)) + goto err_undo; + } + + list_add(&block->right->tmp_link, &dfs); + list_add(&block->left->tmp_link, &dfs); + } while (1); + + list_splice_tail(&allocated, blocks); + return 0; + +err_undo: + /* + * We really don't want to leave around a bunch of split blocks, since + * bigger is better, so make sure we merge everything back before we + * free the allocated blocks. + */ + buddy = get_buddy(block); + if (buddy && + (i915_buddy_block_is_free(block) && + i915_buddy_block_is_free(buddy))) + __i915_buddy_free(mm, block); + +err_free: + i915_buddy_free_list(mm, &allocated); + return err; +} + +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +#include "selftests/i915_buddy.c" +#endif diff --git a/drivers/gpu/drm/i915/i915_buddy.h b/drivers/gpu/drm/i915/i915_buddy.h new file mode 100644 index 000000000000..37f8c42071d1 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_buddy.h @@ -0,0 +1,133 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __I915_BUDDY_H__ +#define __I915_BUDDY_H__ + +#include <linux/bitops.h> +#include <linux/list.h> +#include <linux/slab.h> + +struct i915_buddy_block { +#define I915_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12) +#define I915_BUDDY_HEADER_STATE GENMASK_ULL(11, 10) +#define I915_BUDDY_ALLOCATED (1 << 10) +#define I915_BUDDY_FREE (2 << 10) +#define I915_BUDDY_SPLIT (3 << 10) +/* Free to be used, if needed in the future */ +#define I915_BUDDY_HEADER_UNUSED GENMASK_ULL(9, 6) +#define I915_BUDDY_HEADER_ORDER GENMASK_ULL(5, 0) + u64 header; + + struct i915_buddy_block *left; + struct i915_buddy_block *right; + struct i915_buddy_block *parent; + + void *private; /* owned by creator */ + + /* + * While the block is allocated by the user through i915_buddy_alloc*, + * the user has ownership of the link, for example to maintain within + * a list, if so desired. As soon as the block is freed with + * i915_buddy_free* ownership is given back to the mm. + */ + struct list_head link; + struct list_head tmp_link; +}; + +/* Order-zero must be at least PAGE_SIZE */ +#define I915_BUDDY_MAX_ORDER (63 - PAGE_SHIFT) + +/* + * Binary Buddy System. + * + * Locking should be handled by the user, a simple mutex around + * i915_buddy_alloc* and i915_buddy_free* should suffice. + */ +struct i915_buddy_mm { + struct kmem_cache *slab_blocks; + /* Maintain a free list for each order. */ + struct list_head *free_list; + + /* + * Maintain explicit binary tree(s) to track the allocation of the + * address space. This gives us a simple way of finding a buddy block + * and performing the potentially recursive merge step when freeing a + * block. Nodes are either allocated or free, in which case they will + * also exist on the respective free list. + */ + struct i915_buddy_block **roots; + + /* + * Anything from here is public, and remains static for the lifetime of + * the mm. Everything above is considered do-not-touch. + */ + unsigned int n_roots; + unsigned int max_order; + + /* Must be at least PAGE_SIZE */ + u64 chunk_size; + u64 size; +}; + +static inline u64 +i915_buddy_block_offset(struct i915_buddy_block *block) +{ + return block->header & I915_BUDDY_HEADER_OFFSET; +} + +static inline unsigned int +i915_buddy_block_order(struct i915_buddy_block *block) +{ + return block->header & I915_BUDDY_HEADER_ORDER; +} + +static inline unsigned int +i915_buddy_block_state(struct i915_buddy_block *block) +{ + return block->header & I915_BUDDY_HEADER_STATE; +} + +static inline bool +i915_buddy_block_is_allocated(struct i915_buddy_block *block) +{ + return i915_buddy_block_state(block) == I915_BUDDY_ALLOCATED; +} + +static inline bool +i915_buddy_block_is_free(struct i915_buddy_block *block) +{ + return i915_buddy_block_state(block) == I915_BUDDY_FREE; +} + +static inline bool +i915_buddy_block_is_split(struct i915_buddy_block *block) +{ + return i915_buddy_block_state(block) == I915_BUDDY_SPLIT; +} + +static inline u64 +i915_buddy_block_size(struct i915_buddy_mm *mm, + struct i915_buddy_block *block) +{ + return mm->chunk_size << i915_buddy_block_order(block); +} + +int i915_buddy_init(struct i915_buddy_mm *mm, u64 size, u64 chunk_size); + +void i915_buddy_fini(struct i915_buddy_mm *mm); + +struct i915_buddy_block * +i915_buddy_alloc(struct i915_buddy_mm *mm, unsigned int order); + +int i915_buddy_alloc_range(struct i915_buddy_mm *mm, + struct list_head *blocks, + u64 start, u64 size); + +void i915_buddy_free(struct i915_buddy_mm *mm, struct i915_buddy_block *block); + +void i915_buddy_free_list(struct i915_buddy_mm *mm, struct list_head *objects); + +#endif diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c new file mode 100644 index 000000000000..d7bf37be1932 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include <linux/slab.h> + +#include <drm/ttm/ttm_bo_driver.h> +#include <drm/ttm/ttm_placement.h> + +#include "i915_ttm_buddy_manager.h" + +#include "i915_buddy.h" +#include "i915_gem.h" + +struct i915_ttm_buddy_manager { + struct ttm_resource_manager manager; + struct i915_buddy_mm mm; + struct list_head reserved; + struct mutex lock; +}; + +static inline struct i915_ttm_buddy_manager * +to_buddy_manager(struct ttm_resource_manager *man) +{ + return container_of(man, struct i915_ttm_buddy_manager, manager); +} + +static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man, + struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource **res) +{ + struct i915_ttm_buddy_manager *bman = to_buddy_manager(man); + struct i915_ttm_buddy_resource *bman_res; + struct i915_buddy_mm *mm = &bman->mm; + unsigned long n_pages; + unsigned int min_order; + u64 size; + int err; + + GEM_BUG_ON(place->fpfn || place->lpfn); + GEM_BUG_ON(bo->page_alignment < mm->chunk_size); + + bman_res = kzalloc(sizeof(*bman_res), GFP_KERNEL); + if (!bman_res) + return -ENOMEM; + + ttm_resource_init(bo, place, &bman_res->base); + INIT_LIST_HEAD(&bman_res->blocks); + bman_res->mm = mm; + + GEM_BUG_ON(!bman_res->base.num_pages); + size = bman_res->base.num_pages << PAGE_SHIFT; + + min_order = ilog2(bo->page_alignment) - ilog2(mm->chunk_size); + if (place->flags & TTM_PL_FLAG_CONTIGUOUS) { + size = roundup_pow_of_two(size); + min_order = ilog2(size) - ilog2(mm->chunk_size); + } + + if (size > mm->size) { + err = -E2BIG; + goto err_free_res; + } + + n_pages = size >> ilog2(mm->chunk_size); + + do { + struct i915_buddy_block *block; + unsigned int order; + + order = fls(n_pages) - 1; + GEM_BUG_ON(order > mm->max_order); + GEM_BUG_ON(order < min_order); + + do { + mutex_lock(&bman->lock); + block = i915_buddy_alloc(mm, order); + mutex_unlock(&bman->lock); + if (!IS_ERR(block)) + break; + + if (order-- == min_order) { + err = -ENXIO; + goto err_free_blocks; + } + } while (1); + + n_pages -= BIT(order); + + list_add_tail(&block->link, &bman_res->blocks); + + if (!n_pages) + break; + } while (1); + + *res = &bman_res->base; + return 0; + +err_free_blocks: + mutex_lock(&bman->lock); + i915_buddy_free_list(mm, &bman_res->blocks); + mutex_unlock(&bman->lock); +err_free_res: + kfree(bman_res); + return err; +} + +static void i915_ttm_buddy_man_free(struct ttm_resource_manager *man, + struct ttm_resource *res) +{ + struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res); + struct i915_ttm_buddy_manager *bman = to_buddy_manager(man); + + mutex_lock(&bman->lock); + i915_buddy_free_list(&bman->mm, &bman_res->blocks); + mutex_unlock(&bman->lock); + + kfree(bman_res); +} + +static const struct ttm_resource_manager_func i915_ttm_buddy_manager_func = { + .alloc = i915_ttm_buddy_man_alloc, + .free = i915_ttm_buddy_man_free, +}; + + +/** + * i915_ttm_buddy_man_init - Setup buddy allocator based ttm manager + * @bdev: The ttm device + * @type: Memory type we want to manage + * @use_tt: Set use_tt for the manager + * @size: The size in bytes to manage + * @chunk_size: The minimum page size in bytes for our allocations i.e + * order-zero + * + * Note that the starting address is assumed to be zero here, since this + * simplifies keeping the property where allocated blocks having natural + * power-of-two alignment. So long as the real starting address is some large + * power-of-two, or naturally start from zero, then this should be fine. Also + * the &i915_ttm_buddy_man_reserve interface can be used to preserve alignment + * if say there is some unusable range from the start of the region. We can + * revisit this in the future and make the interface accept an actual starting + * offset and let it take care of the rest. + * + * Note that if the @size is not aligned to the @chunk_size then we perform the + * required rounding to get the usable size. The final size in pages can be + * taken from &ttm_resource_manager.size. + * + * Return: 0 on success, negative error code on failure. + */ +int i915_ttm_buddy_man_init(struct ttm_device *bdev, + unsigned int type, bool use_tt, + u64 size, u64 chunk_size) +{ + struct ttm_resource_manager *man; + struct i915_ttm_buddy_manager *bman; + int err; + + bman = kzalloc(sizeof(*bman), GFP_KERNEL); + if (!bman) + return -ENOMEM; + + err = i915_buddy_init(&bman->mm, size, chunk_size); + if (err) + goto err_free_bman; + + mutex_init(&bman->lock); + INIT_LIST_HEAD(&bman->reserved); + + man = &bman->manager; + man->use_tt = use_tt; + man->func = &i915_ttm_buddy_manager_func; + ttm_resource_manager_init(man, bman->mm.size >> PAGE_SHIFT); + + ttm_resource_manager_set_used(man, true); + ttm_set_driver_manager(bdev, type, man); + + return 0; + +err_free_bman: + kfree(bman); + return err; +} + +/** + * i915_ttm_buddy_man_fini - Destroy the buddy allocator ttm manager + * @bdev: The ttm device + * @type: Memory type we want to manage + * + * Note that if we reserved anything with &i915_ttm_buddy_man_reserve, this will + * also be freed for us here. + * + * Return: 0 on success, negative error code on failure. + */ +int i915_ttm_buddy_man_fini(struct ttm_device *bdev, unsigned int type) +{ + struct ttm_resource_manager *man = ttm_manager_type(bdev, type); + struct i915_ttm_buddy_manager *bman = to_buddy_manager(man); + struct i915_buddy_mm *mm = &bman->mm; + int ret; + + ttm_resource_manager_set_used(man, false); + + ret = ttm_resource_manager_evict_all(bdev, man); + if (ret) + return ret; + + ttm_set_driver_manager(bdev, type, NULL); + + mutex_lock(&bman->lock); + i915_buddy_free_list(mm, &bman->reserved); + i915_buddy_fini(mm); + mutex_unlock(&bman->lock); + + ttm_resource_manager_cleanup(man); + kfree(bman); + + return 0; +} + +/** + * i915_ttm_buddy_man_reserve - Reserve address range + * @man: The buddy allocator ttm manager + * @start: The offset in bytes, where the region start is assumed to be zero + * @size: The size in bytes + * + * Note that the starting address for the region is always assumed to be zero. + * + * Return: 0 on success, negative error code on failure. + */ +int i915_ttm_buddy_man_reserve(struct ttm_resource_manager *man, + u64 start, u64 size) +{ + struct i915_ttm_buddy_manager *bman = to_buddy_manager(man); + struct i915_buddy_mm *mm = &bman->mm; + int ret; + + mutex_lock(&bman->lock); + ret = i915_buddy_alloc_range(mm, &bman->reserved, start, size); + mutex_unlock(&bman->lock); + + return ret; +} + diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h new file mode 100644 index 000000000000..1d58e90548c9 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __I915_TTM_BUDDY_MANAGER_H__ +#define __I915_TTM_BUDDY_MANAGER_H__ + +#include <linux/list.h> +#include <linux/types.h> + +#include <drm/ttm/ttm_resource.h> + +struct ttm_device; +struct ttm_resource_manager; +struct i915_buddy_mm; + +/** + * struct i915_ttm_buddy_resource + * + * @base: struct ttm_resource base class we extend + * @blocks: the list of struct i915_buddy_block for this resource/allocation + * @mm: the struct i915_buddy_mm for this resource + * + * Extends the struct ttm_resource to manage an address space allocation with + * one or more struct i915_buddy_block. + */ +struct i915_ttm_buddy_resource { + struct ttm_resource base; + struct list_head blocks; + struct i915_buddy_mm *mm; +}; + +/** + * to_ttm_buddy_resource + * + * @res: the resource to upcast + * + * Upcast the ttm_resource object into a i915_ttm_buddy_resource. + */ +static inline struct i915_ttm_buddy_resource * +to_ttm_buddy_resource(struct ttm_resource *res) +{ + return container_of(res, struct i915_ttm_buddy_resource, base); +} + +int i915_ttm_buddy_man_init(struct ttm_device *bdev, + unsigned type, bool use_tt, + u64 size, u64 chunk_size); +int i915_ttm_buddy_man_fini(struct ttm_device *bdev, + unsigned int type); + +int i915_ttm_buddy_man_reserve(struct ttm_resource_manager *man, + u64 start, u64 size); + +#endif diff --git a/drivers/gpu/drm/i915/selftests/i915_buddy.c b/drivers/gpu/drm/i915/selftests/i915_buddy.c new file mode 100644 index 000000000000..f0f5c4df8dbc --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/i915_buddy.c @@ -0,0 +1,789 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2019 Intel Corporation + */ + +#include <linux/prime_numbers.h> + +#include "../i915_selftest.h" +#include "i915_random.h" + +static void __igt_dump_block(struct i915_buddy_mm *mm, + struct i915_buddy_block *block, + bool buddy) +{ + pr_err("block info: header=%llx, state=%u, order=%d, offset=%llx size=%llx root=%s buddy=%s\n", + block->header, + i915_buddy_block_state(block), + i915_buddy_block_order(block), + i915_buddy_block_offset(block), + i915_buddy_block_size(mm, block), + yesno(!block->parent), + yesno(buddy)); +} + +static void igt_dump_block(struct i915_buddy_mm *mm, + struct i915_buddy_block *block) +{ + struct i915_buddy_block *buddy; + + __igt_dump_block(mm, block, false); + + buddy = get_buddy(block); + if (buddy) + __igt_dump_block(mm, buddy, true); +} + +static int igt_check_block(struct i915_buddy_mm *mm, + struct i915_buddy_block *block) +{ + struct i915_buddy_block *buddy; + unsigned int block_state; + u64 block_size; + u64 offset; + int err = 0; + + block_state = i915_buddy_block_state(block); + + if (block_state != I915_BUDDY_ALLOCATED && + block_state != I915_BUDDY_FREE && + block_state != I915_BUDDY_SPLIT) { + pr_err("block state mismatch\n"); + err = -EINVAL; + } + + block_size = i915_buddy_block_size(mm, block); + offset = i915_buddy_block_offset(block); + + if (block_size < mm->chunk_size) { + pr_err("block size smaller than min size\n"); + err = -EINVAL; + } + + if (!is_power_of_2(block_size)) { + pr_err("block size not power of two\n"); + err = -EINVAL; + } + + if (!IS_ALIGNED(block_size, mm->chunk_size)) { + pr_err("block size not aligned to min size\n"); + err = -EINVAL; + } + + if (!IS_ALIGNED(offset, mm->chunk_size)) { + pr_err("block offset not aligned to min size\n"); + err = -EINVAL; + } + + if (!IS_ALIGNED(offset, block_size)) { + pr_err("block offset not aligned to block size\n"); + err = -EINVAL; + } + + buddy = get_buddy(block); + + if (!buddy && block->parent) { + pr_err("buddy has gone fishing\n"); + err = -EINVAL; + } + + if (buddy) { + if (i915_buddy_block_offset(buddy) != (offset ^ block_size)) { + pr_err("buddy has wrong offset\n"); + err = -EINVAL; + } + + if (i915_buddy_block_size(mm, buddy) != block_size) { + pr_err("buddy size mismatch\n"); + err = -EINVAL; + } + + if (i915_buddy_block_state(buddy) == block_state && + block_state == I915_BUDDY_FREE) { + pr_err("block and its buddy are free\n"); + err = -EINVAL; + } + } + + return err; +} + +static int igt_check_blocks(struct i915_buddy_mm *mm, + struct list_head *blocks, + u64 expected_size, + bool is_contiguous) +{ + struct i915_buddy_block *block; + struct i915_buddy_block *prev; + u64 total; + int err = 0; + + block = NULL; + prev = NULL; + total = 0; + + list_for_each_entry(block, blocks, link) { + err = igt_check_block(mm, block); + + if (!i915_buddy_block_is_allocated(block)) { + pr_err("block not allocated\n"), + err = -EINVAL; + } + + if (is_contiguous && prev) { + u64 prev_block_size; + u64 prev_offset; + u64 offset; + + prev_offset = i915_buddy_block_offset(prev); + prev_block_size = i915_buddy_block_size(mm, prev); + offset = i915_buddy_block_offset(block); + + if (offset != (prev_offset + prev_block_size)) { + pr_err("block offset mismatch\n"); + err = -EINVAL; + } + } + + if (err) + break; + + total += i915_buddy_block_size(mm, block); + prev = block; + } + + if (!err) { + if (total != expected_size) { + pr_err("size mismatch, expected=%llx, found=%llx\n", + expected_size, total); + err = -EINVAL; + } + return err; + } + + if (prev) { + pr_err("prev block, dump:\n"); + igt_dump_block(mm, prev); + } + + if (block) { + pr_err("bad block, dump:\n"); + igt_dump_block(mm, block); + } + + return err; +} + +static int igt_check_mm(struct i915_buddy_mm *mm) +{ + struct i915_buddy_block *root; + struct i915_buddy_block *prev; + unsigned int i; + u64 total; + int err = 0; + + if (!mm->n_roots) { + pr_err("n_roots is zero\n"); + return -EINVAL; + } + + if (mm->n_roots != hweight64(mm->size)) { + pr_err("n_roots mismatch, n_roots=%u, expected=%lu\n", + mm->n_roots, hweight64(mm->size)); + return -EINVAL; + } + + root = NULL; + prev = NULL; + total = 0; + + for (i = 0; i < mm->n_roots; ++i) { + struct i915_buddy_block *block; + unsigned int order; + + root = mm->roots[i]; + if (!root) { + pr_err("root(%u) is NULL\n", i); + err = -EINVAL; + break; + } + + err = igt_check_block(mm, root); + + if (!i915_buddy_block_is_free(root)) { + pr_err("root not free\n"); + err = -EINVAL; + } + + order = i915_buddy_block_order(root); + + if (!i) { + if (order != mm->max_order) { + pr_err("max order root missing\n"); + err = -EINVAL; + } + } + + if (prev) { + u64 prev_block_size; + u64 prev_offset; + u64 offset; + + prev_offset = i915_buddy_block_offset(prev); + prev_block_size = i915_buddy_block_size(mm, prev); + offset = i915_buddy_block_offset(root); + + if (offset != (prev_offset + prev_block_size)) { + pr_err("root offset mismatch\n"); + err = -EINVAL; + } + } + + block = list_first_entry_or_null(&mm->free_list[order], + struct i915_buddy_block, + link); + if (block != root) { + pr_err("root mismatch at order=%u\n", order); + err = -EINVAL; + } + + if (err) + break; + + prev = root; + total += i915_buddy_block_size(mm, root); + } + + if (!err) { + if (total != mm->size) { + pr_err("expected mm size=%llx, found=%llx\n", mm->size, + total); + err = -EINVAL; + } + return err; + } + + if (prev) { + pr_err("prev root(%u), dump:\n", i - 1); + igt_dump_block(mm, prev); + } + + if (root) { + pr_err("bad root(%u), dump:\n", i); + igt_dump_block(mm, root); + } + + return err; +} + +static void igt_mm_config(u64 *size, u64 *chunk_size) +{ + I915_RND_STATE(prng); + u32 s, ms; + + /* Nothing fancy, just try to get an interesting bit pattern */ + + prandom_seed_state(&prng, i915_selftest.random_seed); + + /* Let size be a random number of pages up to 8 GB (2M pages) */ + s = 1 + i915_prandom_u32_max_state((BIT(33 - 12)) - 1, &prng); + /* Let the chunk size be a random power of 2 less than size */ + ms = BIT(i915_prandom_u32_max_state(ilog2(s), &prng)); + /* Round size down to the chunk size */ + s &= -ms; + + /* Convert from pages to bytes */ + *chunk_size = (u64)ms << 12; + *size = (u64)s << 12; +} + +static int igt_buddy_alloc_smoke(void *arg) +{ + struct i915_buddy_mm mm; + IGT_TIMEOUT(end_time); + I915_RND_STATE(prng); + u64 chunk_size; + u64 mm_size; + int *order; + int err, i; + + igt_mm_config(&mm_size, &chunk_size); + + pr_info("buddy_init with size=%llx, chunk_size=%llx\n", mm_size, chunk_size); + + err = i915_buddy_init(&mm, mm_size, chunk_size); + if (err) { + pr_err("buddy_init failed(%d)\n", err); + return err; + } + + order = i915_random_order(mm.max_order + 1, &prng); + if (!order) + goto out_fini; + + for (i = 0; i <= mm.max_order; ++i) { + struct i915_buddy_block *block; + int max_order = order[i]; + bool timeout = false; + LIST_HEAD(blocks); + int order; + u64 total; + + err = igt_check_mm(&mm); + if (err) { + pr_err("pre-mm check failed, abort\n"); + break; + } + + pr_info("filling from max_order=%u\n", max_order); + + order = max_order; + total = 0; + + do { +retry: + block = i915_buddy_alloc(&mm, order); + if (IS_ERR(block)) { + err = PTR_ERR(block); + if (err == -ENOMEM) { + pr_info("buddy_alloc hit -ENOMEM with order=%d\n", + order); + } else { + if (order--) { + err = 0; + goto retry; + } + + pr_err("buddy_alloc with order=%d failed(%d)\n", + order, err); + } + + break; + } + + list_add_tail(&block->link, &blocks); + + if (i915_buddy_block_order(block) != order) { + pr_err("buddy_alloc order mismatch\n"); + err = -EINVAL; + break; + } + + total += i915_buddy_block_size(&mm, block); + + if (__igt_timeout(end_time, NULL)) { + timeout = true; + break; + } + } while (total < mm.size); + + if (!err) + err = igt_check_blocks(&mm, &blocks, total, false); + + i915_buddy_free_list(&mm, &blocks); + + if (!err) { + err = igt_check_mm(&mm); + if (err) + pr_err("post-mm check failed\n"); + } + + if (err || timeout) + break; + + cond_resched(); + } + + if (err == -ENOMEM) + err = 0; + + kfree(order); +out_fini: + i915_buddy_fini(&mm); + + return err; +} + +static int igt_buddy_alloc_pessimistic(void *arg) +{ + const unsigned int max_order = 16; + struct i915_buddy_block *block, *bn; + struct i915_buddy_mm mm; + unsigned int order; + LIST_HEAD(blocks); + int err; + + /* + * Create a pot-sized mm, then allocate one of each possible + * order within. This should leave the mm with exactly one + * page left. + */ + + err = i915_buddy_init(&mm, PAGE_SIZE << max_order, PAGE_SIZE); + if (err) { + pr_err("buddy_init failed(%d)\n", err); + return err; + } + GEM_BUG_ON(mm.max_order != max_order); + + for (order = 0; order < max_order; order++) { + block = i915_buddy_alloc(&mm, order); + if (IS_ERR(block)) { + pr_info("buddy_alloc hit -ENOMEM with order=%d\n", + order); + err = PTR_ERR(block); + goto err; + } + + list_add_tail(&block->link, &blocks); + } + + /* And now the last remaining block available */ + block = i915_buddy_alloc(&mm, 0); + if (IS_ERR(block)) { + pr_info("buddy_alloc hit -ENOMEM on final alloc\n"); + err = PTR_ERR(block); + goto err; + } + list_add_tail(&block->link, &blocks); + + /* Should be completely full! */ + for (order = max_order; order--; ) { + block = i915_buddy_alloc(&mm, order); + if (!IS_ERR(block)) { + pr_info("buddy_alloc unexpectedly succeeded at order %d, it should be full!", + order); + list_add_tail(&block->link, &blocks); + err = -EINVAL; + goto err; + } + } + + block = list_last_entry(&blocks, typeof(*block), link); + list_del(&block->link); + i915_buddy_free(&mm, block); + + /* As we free in increasing size, we make available larger blocks */ + order = 1; + list_for_each_entry_safe(block, bn, &blocks, link) { + list_del(&block->link); + i915_buddy_free(&mm, block); + + block = i915_buddy_alloc(&mm, order); + if (IS_ERR(block)) { + pr_info("buddy_alloc (realloc) hit -ENOMEM with order=%d\n", + order); + err = PTR_ERR(block); + goto err; + } + i915_buddy_free(&mm, block); + order++; + } + + /* To confirm, now the whole mm should be available */ + block = i915_buddy_alloc(&mm, max_order); + if (IS_ERR(block)) { + pr_info("buddy_alloc (realloc) hit -ENOMEM with order=%d\n", + max_order); + err = PTR_ERR(block); + goto err; + } + i915_buddy_free(&mm, block); + +err: + i915_buddy_free_list(&mm, &blocks); + i915_buddy_fini(&mm); + return err; +} + +static int igt_buddy_alloc_optimistic(void *arg) +{ + const int max_order = 16; + struct i915_buddy_block *block; + struct i915_buddy_mm mm; + LIST_HEAD(blocks); + int order; + int err; + + /* + * Create a mm with one block of each order available, and + * try to allocate them all. + */ + + err = i915_buddy_init(&mm, + PAGE_SIZE * ((1 << (max_order + 1)) - 1), + PAGE_SIZE); + if (err) { + pr_err("buddy_init failed(%d)\n", err); + return err; + } + GEM_BUG_ON(mm.max_order != max_order); + + for (order = 0; order <= max_order; order++) { + block = i915_buddy_alloc(&mm, order); + if (IS_ERR(block)) { + pr_info("buddy_alloc hit -ENOMEM with order=%d\n", + order); + err = PTR_ERR(block); + goto err; + } + + list_add_tail(&block->link, &blocks); + } + + /* Should be completely full! */ + block = i915_buddy_alloc(&mm, 0); + if (!IS_ERR(block)) { + pr_info("buddy_alloc unexpectedly succeeded, it should be full!"); + list_add_tail(&block->link, &blocks); + err = -EINVAL; + goto err; + } + +err: + i915_buddy_free_list(&mm, &blocks); + i915_buddy_fini(&mm); + return err; +} + +static int igt_buddy_alloc_pathological(void *arg) +{ + const int max_order = 16; + struct i915_buddy_block *block; + struct i915_buddy_mm mm; + LIST_HEAD(blocks); + LIST_HEAD(holes); + int order, top; + int err; + + /* + * Create a pot-sized mm, then allocate one of each possible + * order within. This should leave the mm with exactly one + * page left. Free the largest block, then whittle down again. + * Eventually we will have a fully 50% fragmented mm. + */ + + err = i915_buddy_init(&mm, PAGE_SIZE << max_order, PAGE_SIZE); + if (err) { + pr_err("buddy_init failed(%d)\n", err); + return err; + } + GEM_BUG_ON(mm.max_order != max_order); + + for (top = max_order; top; top--) { + /* Make room by freeing the largest allocated block */ + block = list_first_entry_or_null(&blocks, typeof(*block), link); + if (block) { + list_del(&block->link); + i915_buddy_free(&mm, block); + } + + for (order = top; order--; ) { + block = i915_buddy_alloc(&mm, order); + if (IS_ERR(block)) { + pr_info("buddy_alloc hit -ENOMEM with order=%d, top=%d\n", + order, top); + err = PTR_ERR(block); + goto err; + } + list_add_tail(&block->link, &blocks); + } + + /* There should be one final page for this sub-allocation */ + block = i915_buddy_alloc(&mm, 0); + if (IS_ERR(block)) { + pr_info("buddy_alloc hit -ENOMEM for hole\n"); + err = PTR_ERR(block); + goto err; + } + list_add_tail(&block->link, &holes); + + block = i915_buddy_alloc(&mm, top); + if (!IS_ERR(block)) { + pr_info("buddy_alloc unexpectedly succeeded at top-order %d/%d, it should be full!", + top, max_order); + list_add_tail(&block->link, &blocks); + err = -EINVAL; + goto err; + } + } + + i915_buddy_free_list(&mm, &holes); + + /* Nothing larger than blocks of chunk_size now available */ + for (order = 1; order <= max_order; order++) { + block = i915_buddy_alloc(&mm, order); + if (!IS_ERR(block)) { + pr_info("buddy_alloc unexpectedly succeeded at order %d, it should be full!", + order); + list_add_tail(&block->link, &blocks); + err = -EINVAL; + goto err; + } + } + +err: + list_splice_tail(&holes, &blocks); + i915_buddy_free_list(&mm, &blocks); + i915_buddy_fini(&mm); + return err; +} + +static int igt_buddy_alloc_range(void *arg) +{ + struct i915_buddy_mm mm; + unsigned long page_num; + LIST_HEAD(blocks); + u64 chunk_size; + u64 offset; + u64 size; + u64 rem; + int err; + + igt_mm_config(&size, &chunk_size); + + pr_info("buddy_init with size=%llx, chunk_size=%llx\n", size, chunk_size); + + err = i915_buddy_init(&mm, size, chunk_size); + if (err) { + pr_err("buddy_init failed(%d)\n", err); + return err; + } + + err = igt_check_mm(&mm); + if (err) { + pr_err("pre-mm check failed, abort, abort, abort!\n"); + goto err_fini; + } + + rem = mm.size; + offset = 0; + + for_each_prime_number_from(page_num, 1, ULONG_MAX - 1) { + struct i915_buddy_block *block; + LIST_HEAD(tmp); + + size = min(page_num * mm.chunk_size, rem); + + err = i915_buddy_alloc_range(&mm, &tmp, offset, size); + if (err) { + if (err == -ENOMEM) { + pr_info("alloc_range hit -ENOMEM with size=%llx\n", + size); + } else { + pr_err("alloc_range with offset=%llx, size=%llx failed(%d)\n", + offset, size, err); + } + + break; + } + + block = list_first_entry_or_null(&tmp, + struct i915_buddy_block, + link); + if (!block) { + pr_err("alloc_range has no blocks\n"); + err = -EINVAL; + break; + } + + if (i915_buddy_block_offset(block) != offset) { + pr_err("alloc_range start offset mismatch, found=%llx, expected=%llx\n", + i915_buddy_block_offset(block), offset); + err = -EINVAL; + } + + if (!err) + err = igt_check_blocks(&mm, &tmp, size, true); + + list_splice_tail(&tmp, &blocks); + + if (err) + break; + + offset += size; + + rem -= size; + if (!rem) + break; + + cond_resched(); + } + + if (err == -ENOMEM) + err = 0; + + i915_buddy_free_list(&mm, &blocks); + + if (!err) { + err = igt_check_mm(&mm); + if (err) + pr_err("post-mm check failed\n"); + } + +err_fini: + i915_buddy_fini(&mm); + + return err; +} + +static int igt_buddy_alloc_limit(void *arg) +{ + struct i915_buddy_block *block; + struct i915_buddy_mm mm; + const u64 size = U64_MAX; + int err; + + err = i915_buddy_init(&mm, size, PAGE_SIZE); + if (err) + return err; + + if (mm.max_order != I915_BUDDY_MAX_ORDER) { + pr_err("mm.max_order(%d) != %d\n", + mm.max_order, I915_BUDDY_MAX_ORDER); + err = -EINVAL; + goto out_fini; + } + + block = i915_buddy_alloc(&mm, mm.max_order); + if (IS_ERR(block)) { + err = PTR_ERR(block); + goto out_fini; + } + + if (i915_buddy_block_order(block) != mm.max_order) { + pr_err("block order(%d) != %d\n", + i915_buddy_block_order(block), mm.max_order); + err = -EINVAL; + goto out_free; + } + + if (i915_buddy_block_size(&mm, block) != + BIT_ULL(mm.max_order) * PAGE_SIZE) { + pr_err("block size(%llu) != %llu\n", + i915_buddy_block_size(&mm, block), + BIT_ULL(mm.max_order) * PAGE_SIZE); + err = -EINVAL; + goto out_free; + } + +out_free: + i915_buddy_free(&mm, block); +out_fini: + i915_buddy_fini(&mm); + return err; +} + +int i915_buddy_mock_selftests(void) +{ + static const struct i915_subtest tests[] = { + SUBTEST(igt_buddy_alloc_pessimistic), + SUBTEST(igt_buddy_alloc_optimistic), + SUBTEST(igt_buddy_alloc_pathological), + SUBTEST(igt_buddy_alloc_smoke), + SUBTEST(igt_buddy_alloc_range), + SUBTEST(igt_buddy_alloc_limit), + }; + + return i915_subtests(tests, NULL); +} -- 2.26.3