[v2,5/5] zsmalloc: Implement writeback mechanism for zsmalloc

Message ID	20221027182736.513530-1-nphamcs@gmail.com (mailing list archive)
State	New
Headers	show Return-Path: <owner-linux-mm@kvack.org> From: Nhat Pham <nphamcs@gmail.com> To: akpm@linux-foundation.org Cc: hannes@cmpxchg.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, minchan@kernel.org, ngupta@vflare.org, senozhatsky@chromium.org, sjenning@redhat.com, ddstreet@ieee.org, vitaly.wool@konsulko.com Subject: [PATCH v2 5/5] zsmalloc: Implement writeback mechanism for zsmalloc Date: Thu, 27 Oct 2022 11:27:36 -0700 Message-Id: <20221027182736.513530-1-nphamcs@gmail.com> In-Reply-To: <202210272158.7swYwd23-lkp@intel.com> References: <202210272158.7swYwd23-lkp@intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: owner-linux-mm@kvack.org Precedence: bulk
Series	None \| expand [v2,5/5] zsmalloc: Implement writeback mechanism for zsmalloc

diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 76ff2ed839d0..f7fa69360dd9 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -279,10 +279,13 @@ struct zspage { /* links the zspage to the lru list in the pool */ struct list_head lru; + bool under_reclaim; + + /* list of unfreed handles whose objects have been reclaimed */ + unsigned long *deferred_handles; + struct zs_pool *pool; -#ifdef CONFIG_COMPACTION rwlock_t lock; -#endif }; struct mapping_area { @@ -303,10 +306,11 @@ static bool ZsHugePage(struct zspage *zspage) return zspage->huge; } -#ifdef CONFIG_COMPACTION static void migrate_lock_init(struct zspage *zspage); static void migrate_read_lock(struct zspage *zspage); static void migrate_read_unlock(struct zspage *zspage); + +#ifdef CONFIG_COMPACTION static void migrate_write_lock(struct zspage *zspage); static void migrate_write_lock_nested(struct zspage *zspage); static void migrate_write_unlock(struct zspage *zspage); @@ -314,9 +318,6 @@ static void kick_deferred_free(struct zs_pool *pool); static void init_deferred_free(struct zs_pool *pool); static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage); #else -static void migrate_lock_init(struct zspage *zspage) {} -static void migrate_read_lock(struct zspage *zspage) {} -static void migrate_read_unlock(struct zspage *zspage) {} static void migrate_write_lock(struct zspage *zspage) {} static void migrate_write_lock_nested(struct zspage *zspage) {} static void migrate_write_unlock(struct zspage *zspage) {} @@ -444,6 +445,27 @@ static void zs_zpool_free(void *pool, unsigned long handle) zs_free(pool, handle); } +static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries); + +static int zs_zpool_shrink(void *pool, unsigned int pages, + unsigned int *reclaimed) +{ + unsigned int total = 0; + int ret = -EINVAL; + + while (total < pages) { + ret = zs_reclaim_page(pool, 8); + if (ret < 0) + break; + total++; + } + + if (reclaimed) + *reclaimed = total; + + return ret; +} + static void *zs_zpool_map(void *pool, unsigned long handle, enum zpool_mapmode mm) { @@ -482,6 +504,7 @@ static struct zpool_driver zs_zpool_driver = { .malloc_support_movable = true, .malloc = zs_zpool_malloc, .free = zs_zpool_free, + .shrink = zs_zpool_shrink, .map = zs_zpool_map, .unmap = zs_zpool_unmap, .total_size = zs_zpool_total_size, @@ -955,6 +978,21 @@ static int trylock_zspage(struct zspage *zspage) return 0; } +/* + * Free all the deferred handles whose objects are freed in zs_free. + */ +static void free_handles(struct zs_pool *pool, struct zspage *zspage) +{ + unsigned long handle = (unsigned long) zspage->deferred_handles; + + while (handle) { + unsigned long nxt_handle = handle_to_obj(handle); + + cache_free_handle(pool, handle); + handle = nxt_handle; + } +} + static void __free_zspage(struct zs_pool *pool, struct size_class *class, struct zspage *zspage) { @@ -969,6 +1007,9 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class, VM_BUG_ON(get_zspage_inuse(zspage)); VM_BUG_ON(fg != ZS_EMPTY); + /* Free all deferred handles from zs_free */ + free_handles(pool, zspage); + next = page = get_first_page(zspage); do { VM_BUG_ON_PAGE(!PageLocked(page), page); @@ -1051,6 +1092,8 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) } INIT_LIST_HEAD(&zspage->lru); + zspage->under_reclaim = false; + zspage->deferred_handles = NULL; set_freeobj(zspage, 0); } @@ -1472,11 +1515,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, OBJ_USED, 1); - /* Move the zspage to front of pool's LRU */ - move_to_front(pool, zspage); - spin_unlock(&pool->lock); - return handle; + goto out; } spin_unlock(&pool->lock); @@ -1500,6 +1540,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); + +out: /* Move the zspage to front of pool's LRU */ move_to_front(pool, zspage); spin_unlock(&pool->lock); @@ -1557,12 +1599,24 @@ void zs_free(struct zs_pool *pool, unsigned long handle) obj_free(class->size, obj); class_stat_dec(class, OBJ_USED, 1); + + if (zspage->under_reclaim) { + /* + * Reclaim needs the handles during writeback. It'll free + * them along with the zspage when it's done with them. + * + * Record current deferred handle at the memory location + * whose address is given by handle. + */ + record_obj(handle, (unsigned long) zspage->deferred_handles); + zspage->deferred_handles = (unsigned long *) handle; + spin_unlock(&pool->lock); + return; + } fullness = fix_fullness_group(class, zspage); - if (fullness != ZS_EMPTY) - goto out; + if (fullness == ZS_EMPTY) + free_zspage(pool, class, zspage); - free_zspage(pool, class, zspage); -out: spin_unlock(&pool->lock); cache_free_handle(pool, handle); } @@ -1762,7 +1816,7 @@ static enum fullness_group putback_zspage(struct size_class *class, return fullness; } -#ifdef CONFIG_COMPACTION +#if defined(CONFIG_ZPOOL) || defined(CONFIG_COMPACTION) /* * To prevent zspage destroy during migration, zspage freeing should * hold locks of all pages in the zspage. @@ -1804,6 +1858,24 @@ static void lock_zspage(struct zspage *zspage) } migrate_read_unlock(zspage); } +#endif /* defined(CONFIG_ZPOOL) || defined(CONFIG_COMPACTION) */ + +#ifdef CONFIG_ZPOOL +/* + * Unlocks all the pages of the zspage. + * + * pool->lock must be held before this function is called + * to prevent the underlying pages from migrating. + */ +static void unlock_zspage(struct zspage *zspage) +{ + struct page *page = get_first_page(zspage); + + do { + unlock_page(page); + } while ((page = get_next_page(page)) != NULL); +} +#endif /* CONFIG_ZPOOL */ static void migrate_lock_init(struct zspage *zspage) { @@ -1820,6 +1892,7 @@ static void migrate_read_unlock(struct zspage *zspage) __releases(&zspage->lock) read_unlock(&zspage->lock); } +#ifdef CONFIG_COMPACTION static void migrate_write_lock(struct zspage *zspage) { write_lock(&zspage->lock); @@ -2380,6 +2453,101 @@ void zs_destroy_pool(struct zs_pool *pool) } EXPORT_SYMBOL_GPL(zs_destroy_pool); +#ifdef CONFIG_ZPOOL +static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries) +{ + int i, obj_idx, ret = 0; + unsigned long handle; + struct zspage *zspage; + struct page *page; + enum fullness_group fullness; + + /* Lock LRU and fullness list */ + spin_lock(&pool->lock); + if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) || + retries == 0) { + spin_unlock(&pool->lock); + return -EINVAL; + } + + for (i = 0; i < retries; i++) { + struct size_class *class; + + zspage = list_last_entry(&pool->lru, struct zspage, lru); + list_del(&zspage->lru); + + /* zs_free may free objects, but not the zspage and handles */ + zspage->under_reclaim = true; + + /* Lock backing pages into place */ + lock_zspage(zspage); + + class = zspage_class(pool, zspage); + fullness = get_fullness_group(class, zspage); + + /* Lock out object allocations and object compaction */ + remove_zspage(class, zspage, fullness); + + spin_unlock(&pool->lock); + + obj_idx = 0; + page = zspage->first_page; + while (1) { + handle = find_alloced_obj(class, page, &obj_idx); + if (!handle) { + page = get_next_page(page); + if (!page) + break; + obj_idx = 0; + continue; + } + + /* + * This will write the object and call + * zs_free. + * + * zs_free will free the object, but the + * under_reclaim flag prevents it from freeing + * the zspage altogether. This is necessary so + * that we can continue working with the + * zspage potentially after the last object + * has been freed. + */ + ret = pool->ops->evict(pool, handle); + if (ret) + goto next; + + obj_idx++; + } + +next: + /* For freeing the zspage, or putting it back in the pool and LRU list. */ + spin_lock(&pool->lock); + zspage->under_reclaim = false; + + if (!get_zspage_inuse(zspage)) { + /* + * Fullness went stale as zs_free() won't touch it + * while the page is removed from the pool. Fix it + * up for the check in __free_zspage(). + */ + zspage->fullness = ZS_EMPTY; + + __free_zspage(pool, class, zspage); + spin_unlock(&pool->lock); + return 0; + } + + putback_zspage(class, zspage); + list_add(&zspage->lru, &pool->lru); + unlock_zspage(zspage); + } + + spin_unlock(&pool->lock); + return -EAGAIN; +} +#endif /* CONFIG_ZPOOL */ + static int __init zs_init(void) { int ret;

[v2,5/5] zsmalloc: Implement writeback mechanism for zsmalloc

Commit Message

Comments

Patch