diff options
Diffstat (limited to 'mm/zsmalloc.c')
| -rw-r--r-- | mm/zsmalloc.c | 1098 |
1 files changed, 543 insertions, 555 deletions
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 7d7cb3eaabe0..f3e2215f95eb 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + /* * zsmalloc memory allocator * @@ -11,57 +13,33 @@ * Released under the terms of GNU General Public License Version 2.0 */ -/* - * Following is how we use various fields and flags of underlying - * struct page(s) to form a zspage. - * - * Usage of struct page fields: - * page->private: points to zspage - * page->index: links together all component pages of a zspage - * For the huge page, this is always 0, so we use this field - * to store handle. - * page->page_type: first object offset in a subpage of zspage - * - * Usage of struct page flags: - * PG_private: identifies the first component page - * PG_owner_priv_1: identifies the huge component page - * - */ - #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt /* * lock ordering: * page_lock * pool->lock + * class->lock * zspage->lock */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched.h> -#include <linux/bitops.h> #include <linux/errno.h> #include <linux/highmem.h> #include <linux/string.h> #include <linux/slab.h> -#include <linux/pgtable.h> -#include <asm/tlbflush.h> -#include <linux/cpumask.h> -#include <linux/cpu.h> -#include <linux/vmalloc.h> -#include <linux/preempt.h> #include <linux/spinlock.h> +#include <linux/sprintf.h> #include <linux/shrinker.h> #include <linux/types.h> #include <linux/debugfs.h> #include <linux/zsmalloc.h> #include <linux/zpool.h> -#include <linux/migrate.h> -#include <linux/wait.h> -#include <linux/pagemap.h> #include <linux/fs.h> -#include <linux/local_lock.h> +#include <linux/workqueue.h> +#include "zpdesc.h" #define ZSPAGE_MAGIC 0x58 @@ -118,8 +96,6 @@ #define CLASS_BITS 8 #define MAGIC_VAL_BITS 8 -#define MAX(a, b) ((a) >= (b) ? (a) : (b)) - #define ZS_MAX_PAGES_PER_ZSPAGE (_AC(CONFIG_ZSMALLOC_CHAIN_SIZE, UL)) /* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */ @@ -182,6 +158,7 @@ static struct dentry *zs_stat_root; static size_t huge_class_size; struct size_class { + spinlock_t lock; struct list_head fullness_list[NR_FULLNESS_GROUPS]; /* * Size of objects stored in this class. Must be multiple @@ -236,10 +213,49 @@ struct zs_pool { #ifdef CONFIG_COMPACTION struct work_struct free_work; #endif - spinlock_t lock; + /* protect zspage migration/compaction */ + rwlock_t lock; atomic_t compaction_in_progress; }; +static inline void zpdesc_set_first(struct zpdesc *zpdesc) +{ + SetPagePrivate(zpdesc_page(zpdesc)); +} + +static inline void zpdesc_inc_zone_page_state(struct zpdesc *zpdesc) +{ + inc_zone_page_state(zpdesc_page(zpdesc), NR_ZSPAGES); +} + +static inline void zpdesc_dec_zone_page_state(struct zpdesc *zpdesc) +{ + dec_zone_page_state(zpdesc_page(zpdesc), NR_ZSPAGES); +} + +static inline struct zpdesc *alloc_zpdesc(gfp_t gfp, const int nid) +{ + struct page *page = alloc_pages_node(nid, gfp, 0); + + return page_zpdesc(page); +} + +static inline void free_zpdesc(struct zpdesc *zpdesc) +{ + struct page *page = zpdesc_page(zpdesc); + + __free_page(page); +} + +#define ZS_PAGE_UNLOCKED 0 +#define ZS_PAGE_WRLOCKED -1 + +struct zspage_lock { + spinlock_t lock; + int cnt; + struct lockdep_map dep_map; +}; + struct zspage { struct { unsigned int huge:HUGE_BITS; @@ -249,18 +265,89 @@ struct zspage { }; unsigned int inuse; unsigned int freeobj; - struct page *first_page; + struct zpdesc *first_zpdesc; struct list_head list; /* fullness list */ struct zs_pool *pool; - rwlock_t lock; + struct zspage_lock zsl; }; -struct mapping_area { - local_lock_t lock; - char *vm_buf; /* copy buffer for objects that span pages */ - char *vm_addr; /* address of kmap_atomic()'ed pages */ - enum zs_mapmode vm_mm; /* mapping mode */ -}; +static void zspage_lock_init(struct zspage *zspage) +{ + static struct lock_class_key __key; + struct zspage_lock *zsl = &zspage->zsl; + + lockdep_init_map(&zsl->dep_map, "zspage->lock", &__key, 0); + spin_lock_init(&zsl->lock); + zsl->cnt = ZS_PAGE_UNLOCKED; +} + +/* + * The zspage lock can be held from atomic contexts, but it needs to remain + * preemptible when held for reading because it remains held outside of those + * atomic contexts, otherwise we unnecessarily lose preemptibility. + * + * To achieve this, the following rules are enforced on readers and writers: + * + * - Writers are blocked by both writers and readers, while readers are only + * blocked by writers (i.e. normal rwlock semantics). + * + * - Writers are always atomic (to allow readers to spin waiting for them). + * + * - Writers always use trylock (as the lock may be held be sleeping readers). + * + * - Readers may spin on the lock (as they can only wait for atomic writers). + * + * - Readers may sleep while holding the lock (as writes only use trylock). + */ +static void zspage_read_lock(struct zspage *zspage) +{ + struct zspage_lock *zsl = &zspage->zsl; + + rwsem_acquire_read(&zsl->dep_map, 0, 0, _RET_IP_); + + spin_lock(&zsl->lock); + zsl->cnt++; + spin_unlock(&zsl->lock); + + lock_acquired(&zsl->dep_map, _RET_IP_); +} + +static void zspage_read_unlock(struct zspage *zspage) +{ + struct zspage_lock *zsl = &zspage->zsl; + + rwsem_release(&zsl->dep_map, _RET_IP_); + + spin_lock(&zsl->lock); + zsl->cnt--; + spin_unlock(&zsl->lock); +} + +static __must_check bool zspage_write_trylock(struct zspage *zspage) +{ + struct zspage_lock *zsl = &zspage->zsl; + + spin_lock(&zsl->lock); + if (zsl->cnt == ZS_PAGE_UNLOCKED) { + zsl->cnt = ZS_PAGE_WRLOCKED; + rwsem_acquire(&zsl->dep_map, 0, 1, _RET_IP_); + lock_acquired(&zsl->dep_map, _RET_IP_); + return true; + } + + spin_unlock(&zsl->lock); + return false; +} + +static void zspage_write_unlock(struct zspage *zspage) +{ + struct zspage_lock *zsl = &zspage->zsl; + + rwsem_release(&zsl->dep_map, _RET_IP_); + + zsl->cnt = ZS_PAGE_UNLOCKED; + spin_unlock(&zsl->lock); +} /* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */ static void SetZsHugePage(struct zspage *zspage) @@ -273,12 +360,6 @@ static bool ZsHugePage(struct zspage *zspage) return zspage->huge; } -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_unlock(struct zspage *zspage); - #ifdef CONFIG_COMPACTION static void kick_deferred_free(struct zs_pool *pool); static void init_deferred_free(struct zs_pool *pool); @@ -291,17 +372,27 @@ static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {} static int create_cache(struct zs_pool *pool) { - pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE, - 0, 0, NULL); + char *name; + + name = kasprintf(GFP_KERNEL, "zs_handle-%s", pool->name); + if (!name) + return -ENOMEM; + pool->handle_cachep = kmem_cache_create(name, ZS_HANDLE_SIZE, + 0, 0, NULL); + kfree(name); if (!pool->handle_cachep) - return 1; + return -EINVAL; - pool->zspage_cachep = kmem_cache_create("zspage", sizeof(struct zspage), - 0, 0, NULL); + name = kasprintf(GFP_KERNEL, "zspage-%s", pool->name); + if (!name) + return -ENOMEM; + pool->zspage_cachep = kmem_cache_create(name, sizeof(struct zspage), + 0, 0, NULL); + kfree(name); if (!pool->zspage_cachep) { kmem_cache_destroy(pool->handle_cachep); pool->handle_cachep = NULL; - return 1; + return -EINVAL; } return 0; @@ -335,7 +426,7 @@ static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage) kmem_cache_free(pool->zspage_cachep, zspage); } -/* pool->lock(which owns the handle) synchronizes races */ +/* class->lock(which owns the handle) synchronizes races */ static void record_obj(unsigned long handle, unsigned long obj) { *(unsigned long *)handle = obj; @@ -361,9 +452,9 @@ static void zs_zpool_destroy(void *pool) } static int zs_zpool_malloc(void *pool, size_t size, gfp_t gfp, - unsigned long *handle) + unsigned long *handle, const int nid) { - *handle = zs_malloc(pool, size, gfp); + *handle = zs_malloc(pool, size, gfp, nid); if (IS_ERR_VALUE(*handle)) return PTR_ERR((void *)*handle); @@ -374,34 +465,27 @@ static void zs_zpool_free(void *pool, unsigned long handle) zs_free(pool, handle); } -static void *zs_zpool_map(void *pool, unsigned long handle, - enum zpool_mapmode mm) +static void *zs_zpool_obj_read_begin(void *pool, unsigned long handle, + void *local_copy) { - enum zs_mapmode zs_mm; - - switch (mm) { - case ZPOOL_MM_RO: - zs_mm = ZS_MM_RO; - break; - case ZPOOL_MM_WO: - zs_mm = ZS_MM_WO; - break; - case ZPOOL_MM_RW: - default: - zs_mm = ZS_MM_RW; - break; - } + return zs_obj_read_begin(pool, handle, local_copy); +} - return zs_map_object(pool, handle, zs_mm); +static void zs_zpool_obj_read_end(void *pool, unsigned long handle, + void *handle_mem) +{ + zs_obj_read_end(pool, handle, handle_mem); } -static void zs_zpool_unmap(void *pool, unsigned long handle) + +static void zs_zpool_obj_write(void *pool, unsigned long handle, + void *handle_mem, size_t mem_len) { - zs_unmap_object(pool, handle); + zs_obj_write(pool, handle, handle_mem, mem_len); } -static u64 zs_zpool_total_size(void *pool) +static u64 zs_zpool_total_pages(void *pool) { - return zs_get_total_pages(pool) << PAGE_SHIFT; + return zs_get_total_pages(pool); } static struct zpool_driver zs_zpool_driver = { @@ -409,55 +493,57 @@ static struct zpool_driver zs_zpool_driver = { .owner = THIS_MODULE, .create = zs_zpool_create, .destroy = zs_zpool_destroy, - .malloc_support_movable = true, .malloc = zs_zpool_malloc, .free = zs_zpool_free, - .map = zs_zpool_map, - .unmap = zs_zpool_unmap, - .total_size = zs_zpool_total_size, + .obj_read_begin = zs_zpool_obj_read_begin, + .obj_read_end = zs_zpool_obj_read_end, + .obj_write = zs_zpool_obj_write, + .total_pages = zs_zpool_total_pages, }; MODULE_ALIAS("zpool-zsmalloc"); #endif /* CONFIG_ZPOOL */ -/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ -static DEFINE_PER_CPU(struct mapping_area, zs_map_area) = { - .lock = INIT_LOCAL_LOCK(lock), -}; - -static __maybe_unused int is_first_page(struct page *page) +static inline bool __maybe_unused is_first_zpdesc(struct zpdesc *zpdesc) { - return PagePrivate(page); + return PagePrivate(zpdesc_page(zpdesc)); } -/* Protected by pool->lock */ +/* Protected by class->lock */ static inline int get_zspage_inuse(struct zspage *zspage) { return zspage->inuse; } - static inline void mod_zspage_inuse(struct zspage *zspage, int val) { zspage->inuse += val; } -static inline struct page *get_first_page(struct zspage *zspage) +static struct zpdesc *get_first_zpdesc(struct zspage *zspage) { - struct page *first_page = zspage->first_page; + struct zpdesc *first_zpdesc = zspage->first_zpdesc; - VM_BUG_ON_PAGE(!is_first_page(first_page), first_page); - return first_page; + VM_BUG_ON_PAGE(!is_first_zpdesc(first_zpdesc), zpdesc_page(first_zpdesc)); + return first_zpdesc; } -static inline unsigned int get_first_obj_offset(struct page *page) +#define FIRST_OBJ_PAGE_TYPE_MASK 0xffffff + +static inline unsigned int get_first_obj_offset(struct zpdesc *zpdesc) { - return page->page_type; + VM_WARN_ON_ONCE(!PageZsmalloc(zpdesc_page(zpdesc))); + return zpdesc->first_obj_offset & FIRST_OBJ_PAGE_TYPE_MASK; } -static inline void set_first_obj_offset(struct page *page, unsigned int offset) +static inline void set_first_obj_offset(struct zpdesc *zpdesc, unsigned int offset) { - page->page_type = offset; + /* With 24 bits available, we can support offsets into 16 MiB pages. */ + BUILD_BUG_ON(PAGE_SIZE > SZ_16M); + VM_WARN_ON_ONCE(!PageZsmalloc(zpdesc_page(zpdesc))); + VM_WARN_ON_ONCE(offset & ~FIRST_OBJ_PAGE_TYPE_MASK); + zpdesc->first_obj_offset &= ~FIRST_OBJ_PAGE_TYPE_MASK; + zpdesc->first_obj_offset |= offset & FIRST_OBJ_PAGE_TYPE_MASK; } static inline unsigned int get_freeobj(struct zspage *zspage) @@ -494,19 +580,19 @@ static int get_size_class_index(int size) return min_t(int, ZS_SIZE_CLASSES - 1, idx); } -static inline void class_stat_inc(struct size_class *class, - int type, unsigned long cnt) +static inline void class_stat_add(struct size_class *class, int type, + unsigned long cnt) { class->stats.objs[type] += cnt; } -static inline void class_stat_dec(struct size_class *class, - int type, unsigned long cnt) +static inline void class_stat_sub(struct size_class *class, int type, + unsigned long cnt) { class->stats.objs[type] -= cnt; } -static inline unsigned long zs_stat_get(struct size_class *class, int type) +static inline unsigned long class_stat_read(struct size_class *class, int type) { return class->stats.objs[type]; } @@ -554,18 +640,18 @@ static int zs_stats_size_show(struct seq_file *s, void *v) if (class->index != i) continue; - spin_lock(&pool->lock); + spin_lock(&class->lock); seq_printf(s, " %5u %5u ", i, class->size); for (fg = ZS_INUSE_RATIO_10; fg < NR_FULLNESS_GROUPS; fg++) { - inuse_totals[fg] += zs_stat_get(class, fg); - seq_printf(s, "%9lu ", zs_stat_get(class, fg)); + inuse_totals[fg] += class_stat_read(class, fg); + seq_printf(s, "%9lu ", class_stat_read(class, fg)); } - obj_allocated = zs_stat_get(class, ZS_OBJS_ALLOCATED); - obj_used = zs_stat_get(class, ZS_OBJS_INUSE); + obj_allocated = class_stat_read(class, ZS_OBJS_ALLOCATED); + obj_used = class_stat_read(class, ZS_OBJS_INUSE); freeable = zs_can_compact(class); - spin_unlock(&pool->lock); + spin_unlock(&class->lock); objs_per_zspage = class->objs_per_zspage; pages_used = obj_allocated / objs_per_zspage * @@ -668,7 +754,7 @@ static void insert_zspage(struct size_class *class, struct zspage *zspage, int fullness) { - class_stat_inc(class, fullness, 1); + class_stat_add(class, fullness, 1); list_add(&zspage->list, &class->fullness_list[fullness]); zspage->fullness = fullness; } @@ -684,7 +770,7 @@ static void remove_zspage(struct size_class *class, struct zspage *zspage) VM_BUG_ON(list_empty(&class->fullness_list[fullness])); list_del_init(&zspage->list); - class_stat_dec(class, fullness, 1); + class_stat_sub(class, fullness, 1); } /* @@ -710,52 +796,52 @@ out: return newfg; } -static struct zspage *get_zspage(struct page *page) +static struct zspage *get_zspage(struct zpdesc *zpdesc) { - struct zspage *zspage = (struct zspage *)page_private(page); + struct zspage *zspage = zpdesc->zspage; BUG_ON(zspage->magic != ZSPAGE_MAGIC); return zspage; } -static struct page *get_next_page(struct page *page) +static struct zpdesc *get_next_zpdesc(struct zpdesc *zpdesc) { - struct zspage *zspage = get_zspage(page); + struct zspage *zspage = get_zspage(zpdesc); if (unlikely(ZsHugePage(zspage))) return NULL; - return (struct page *)page->index; + return zpdesc->next; } /** - * obj_to_location - get (<page>, <obj_idx>) from encoded object value + * obj_to_location - get (<zpdesc>, <obj_idx>) from encoded object value * @obj: the encoded object value - * @page: page object resides in zspage + * @zpdesc: zpdesc object resides in zspage * @obj_idx: object index */ -static void obj_to_location(unsigned long obj, struct page **page, +static void obj_to_location(unsigned long obj, struct zpdesc **zpdesc, unsigned int *obj_idx) { - *page = pfn_to_page(obj >> OBJ_INDEX_BITS); + *zpdesc = pfn_zpdesc(obj >> OBJ_INDEX_BITS); *obj_idx = (obj & OBJ_INDEX_MASK); } -static void obj_to_page(unsigned long obj, struct page **page) +static void obj_to_zpdesc(unsigned long obj, struct zpdesc **zpdesc) { - *page = pfn_to_page(obj >> OBJ_INDEX_BITS); + *zpdesc = pfn_zpdesc(obj >> OBJ_INDEX_BITS); } /** - * location_to_obj - get obj value encoded from (<page>, <obj_idx>) - * @page: page object resides in zspage + * location_to_obj - get obj value encoded from (<zpdesc>, <obj_idx>) + * @zpdesc: zpdesc object resides in zspage * @obj_idx: object index */ -static unsigned long location_to_obj(struct page *page, unsigned int obj_idx) +static unsigned long location_to_obj(struct zpdesc *zpdesc, unsigned int obj_idx) { unsigned long obj; - obj = page_to_pfn(page) << OBJ_INDEX_BITS; + obj = zpdesc_pfn(zpdesc) << OBJ_INDEX_BITS; obj |= obj_idx & OBJ_INDEX_MASK; return obj; @@ -766,15 +852,15 @@ static unsigned long handle_to_obj(unsigned long handle) return *(unsigned long *)handle; } -static inline bool obj_allocated(struct page *page, void *obj, +static inline bool obj_allocated(struct zpdesc *zpdesc, void *obj, unsigned long *phandle) { unsigned long handle; - struct zspage *zspage = get_zspage(page); + struct zspage *zspage = get_zspage(zpdesc); if (unlikely(ZsHugePage(zspage))) { - VM_BUG_ON_PAGE(!is_first_page(page), page); - handle = page->index; + VM_BUG_ON_PAGE(!is_first_zpdesc(zpdesc), zpdesc_page(zpdesc)); + handle = zpdesc->handle; } else handle = *(unsigned long *)obj; @@ -786,22 +872,24 @@ static inline bool obj_allocated(struct page *page, void *obj, return true; } -static void reset_page(struct page *page) +static void reset_zpdesc(struct zpdesc *zpdesc) { + struct page *page = zpdesc_page(zpdesc); + __ClearPageMovable(page); ClearPagePrivate(page); - set_page_private(page, 0); - page_mapcount_reset(page); - page->index = 0; + zpdesc->zspage = NULL; + zpdesc->next = NULL; + __ClearPageZsmalloc(page); } static int trylock_zspage(struct zspage *zspage) { - struct page *cursor, *fail; + struct zpdesc *cursor, *fail; - for (cursor = get_first_page(zspage); cursor != NULL; cursor = - get_next_page(cursor)) { - if (!trylock_page(cursor)) { + for (cursor = get_first_zpdesc(zspage); cursor != NULL; cursor = + get_next_zpdesc(cursor)) { + if (!zpdesc_trylock(cursor)) { fail = cursor; goto unlock; } @@ -809,9 +897,9 @@ static int trylock_zspage(struct zspage *zspage) return 1; unlock: - for (cursor = get_first_page(zspage); cursor != fail; cursor = - get_next_page(cursor)) - unlock_page(cursor); + for (cursor = get_first_zpdesc(zspage); cursor != fail; cursor = + get_next_zpdesc(cursor)) + zpdesc_unlock(cursor); return 0; } @@ -819,27 +907,27 @@ unlock: static void __free_zspage(struct zs_pool *pool, struct size_class *class, struct zspage *zspage) { - struct page *page, *next; + struct zpdesc *zpdesc, *next; - assert_spin_locked(&pool->lock); + assert_spin_locked(&class->lock); VM_BUG_ON(get_zspage_inuse(zspage)); VM_BUG_ON(zspage->fullness != ZS_INUSE_RATIO_0); - next = page = get_first_page(zspage); + next = zpdesc = get_first_zpdesc(zspage); do { - VM_BUG_ON_PAGE(!PageLocked(page), page); - next = get_next_page(page); - reset_page(page); - unlock_page(page); - dec_zone_page_state(page, NR_ZSPAGES); - put_page(page); - page = next; - } while (page != NULL); + VM_BUG_ON_PAGE(!zpdesc_is_locked(zpdesc), zpdesc_page(zpdesc)); + next = get_next_zpdesc(zpdesc); + reset_zpdesc(zpdesc); + zpdesc_unlock(zpdesc); + zpdesc_dec_zone_page_state(zpdesc); + zpdesc_put(zpdesc); + zpdesc = next; + } while (zpdesc != NULL); cache_free_zspage(pool, zspage); - class_stat_dec(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage); + class_stat_sub(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage); atomic_long_sub(class->pages_per_zspage, &pool->pages_allocated); } @@ -868,16 +956,16 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) { unsigned int freeobj = 1; unsigned long off = 0; - struct page *page = get_first_page(zspage); + struct zpdesc *zpdesc = get_first_zpdesc(zspage); - while (page) { - struct page *next_page; + while (zpdesc) { + struct zpdesc *next_zpdesc; struct link_free *link; void *vaddr; - set_first_obj_offset(page, off); + set_first_obj_offset(zpdesc, off); - vaddr = kmap_atomic(page); + vaddr = kmap_local_zpdesc(zpdesc); link = (struct link_free *)vaddr + off / sizeof(*link); while ((off += class->size) < PAGE_SIZE) { @@ -890,8 +978,8 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) * page, which must point to the first object on the next * page (if present) */ - next_page = get_next_page(page); - if (next_page) { + next_zpdesc = get_next_zpdesc(zpdesc); + if (next_zpdesc) { link->next = freeobj++ << OBJ_TAG_BITS; } else { /* @@ -900,8 +988,8 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) */ link->next = -1UL << OBJ_TAG_BITS; } - kunmap_atomic(vaddr); - page = next_page; + kunmap_local(vaddr); + zpdesc = next_zpdesc; off %= PAGE_SIZE; } @@ -909,35 +997,35 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) } static void create_page_chain(struct size_class *class, struct zspage *zspage, - struct page *pages[]) + struct zpdesc *zpdescs[]) { int i; - struct page *page; - struct page *prev_page = NULL; - int nr_pages = class->pages_per_zspage; + struct zpdesc *zpdesc; + struct zpdesc *prev_zpdesc = NULL; + int nr_zpdescs = class->pages_per_zspage; /* * Allocate individual pages and link them together as: - * 1. all pages are linked together using page->index - * 2. each sub-page point to zspage using page->private + * 1. all pages are linked together using zpdesc->next + * 2. each sub-page point to zspage using zpdesc->zspage * - * we set PG_private to identify the first page (i.e. no other sub-page + * we set PG_private to identify the first zpdesc (i.e. no other zpdesc * has this flag set). */ - for (i = 0; i < nr_pages; i++) { - page = pages[i]; - set_page_private(page, (unsigned long)zspage); - page->index = 0; + for (i = 0; i < nr_zpdescs; i++) { + zpdesc = zpdescs[i]; + zpdesc->zspage = zspage; + zpdesc->next = NULL; if (i == 0) { - zspage->first_page = page; - SetPagePrivate(page); + zspage->first_zpdesc = zpdesc; + zpdesc_set_first(zpdesc); if (unlikely(class->objs_per_zspage == 1 && class->pages_per_zspage == 1)) SetZsHugePage(zspage); } else { - prev_page->index = (unsigned long)page; + prev_zpdesc->next = zpdesc; } - prev_page = page; + prev_zpdesc = zpdesc; } } @@ -945,40 +1033,45 @@ static void create_page_chain(struct size_class *class, struct zspage *zspage, * Allocate a zspage for the given size class */ static struct zspage *alloc_zspage(struct zs_pool *pool, - struct size_class *class, - gfp_t gfp) + struct size_class *class, + gfp_t gfp, const int nid) { int i; - struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE]; + struct zpdesc *zpdescs[ZS_MAX_PAGES_PER_ZSPAGE]; struct zspage *zspage = cache_alloc_zspage(pool, gfp); if (!zspage) return NULL; + if (!IS_ENABLED(CONFIG_COMPACTION)) + gfp &= ~__GFP_MOVABLE; + zspage->magic = ZSPAGE_MAGIC; - migrate_lock_init(zspage); + zspage->pool = pool; + zspage->class = class->index; + zspage_lock_init(zspage); for (i = 0; i < class->pages_per_zspage; i++) { - struct page *page; + struct zpdesc *zpdesc; - page = alloc_page(gfp); - if (!page) { + zpdesc = alloc_zpdesc(gfp, nid); + if (!zpdesc) { while (--i >= 0) { - dec_zone_page_state(pages[i], NR_ZSPAGES); - __free_page(pages[i]); + zpdesc_dec_zone_page_state(zpdescs[i]); + __zpdesc_clear_zsmalloc(zpdescs[i]); + free_zpdesc(zpdescs[i]); } cache_free_zspage(pool, zspage); return NULL; } + __zpdesc_set_zsmalloc(zpdesc); - inc_zone_page_state(page, NR_ZSPAGES); - pages[i] = page; + zpdesc_inc_zone_page_state(zpdesc); + zpdescs[i] = zpdesc; } - create_page_chain(class, zspage, pages); + create_page_chain(class, zspage, zpdescs); init_zspage(class, zspage); - zspage->pool = pool; - zspage->class = class->index; return zspage; } @@ -998,103 +1091,6 @@ static struct zspage *find_get_zspage(struct size_class *class) return zspage; } -static inline int __zs_cpu_up(struct mapping_area *area) -{ - /* - * Make sure we don't leak memory if a cpu UP notification - * and zs_init() race and both call zs_cpu_up() on the same cpu - */ - if (area->vm_buf) - return 0; - area->vm_buf = kmalloc(ZS_MAX_ALLOC_SIZE, GFP_KERNEL); - if (!area->vm_buf) - return -ENOMEM; - return 0; -} - -static inline void __zs_cpu_down(struct mapping_area *area) -{ - kfree(area->vm_buf); - area->vm_buf = NULL; -} - -static void *__zs_map_object(struct mapping_area *area, - struct page *pages[2], int off, int size) -{ - int sizes[2]; - void *addr; - char *buf = area->vm_buf; - - /* disable page faults to match kmap_atomic() return conditions */ - pagefault_disable(); - - /* no read fastpath */ - if (area->vm_mm == ZS_MM_WO) - goto out; - - sizes[0] = PAGE_SIZE - off; - sizes[1] = size - sizes[0]; - - /* copy object to per-cpu buffer */ - addr = kmap_atomic(pages[0]); - memcpy(buf, addr + off, sizes[0]); - kunmap_atomic(addr); - addr = kmap_atomic(pages[1]); - memcpy(buf + sizes[0], addr, sizes[1]); - kunmap_atomic(addr); -out: - return area->vm_buf; -} - -static void __zs_unmap_object(struct mapping_area *area, - struct page *pages[2], int off, int size) -{ - int sizes[2]; - void *addr; - char *buf; - - /* no write fastpath */ - if (area->vm_mm == ZS_MM_RO) - goto out; - - buf = area->vm_buf; - buf = buf + ZS_HANDLE_SIZE; - size -= ZS_HANDLE_SIZE; - off += ZS_HANDLE_SIZE; - - sizes[0] = PAGE_SIZE - off; - sizes[1] = size - sizes[0]; - - /* copy per-cpu buffer to object */ - addr = kmap_atomic(pages[0]); - memcpy(addr + off, buf, sizes[0]); - kunmap_atomic(addr); - addr = kmap_atomic(pages[1]); - memcpy(addr, buf + sizes[0], sizes[1]); - kunmap_atomic(addr); - -out: - /* enable page faults to match kunmap_atomic() return conditions */ - pagefault_enable(); -} - -static int zs_cpu_prepare(unsigned int cpu) -{ - struct mapping_area *area; - - area = &per_cpu(zs_map_area, cpu); - return __zs_cpu_up(area); -} - -static int zs_cpu_dead(unsigned int cpu) -{ - struct mapping_area *area; - - area = &per_cpu(zs_map_area, cpu); - __zs_cpu_down(area); - return 0; -} - static bool can_merge(struct size_class *prev, int pages_per_zspage, int objs_per_zspage) { @@ -1142,116 +1138,130 @@ unsigned long zs_get_total_pages(struct zs_pool *pool) } EXPORT_SYMBOL_GPL(zs_get_total_pages); -/** - * zs_map_object - get address of allocated object from handle. - * @pool: pool from which the object was allocated - * @handle: handle returned from zs_malloc - * @mm: mapping mode to use - * - * Before using an object allocated from zs_malloc, it must be mapped using - * this function. When done with the object, it must be unmapped using - * zs_unmap_object. - * - * Only one object can be mapped per cpu at a time. There is no protection - * against nested mappings. - * - * This function returns with preemption and page faults disabled. - */ -void *zs_map_object(struct zs_pool *pool, unsigned long handle, - enum zs_mapmode mm) +void *zs_obj_read_begin(struct zs_pool *pool, unsigned long handle, + void *local_copy) { struct zspage *zspage; - struct page *page; + struct zpdesc *zpdesc; unsigned long obj, off; unsigned int obj_idx; - struct size_class *class; - struct mapping_area *area; - struct page *pages[2]; - void *ret; - - /* - * Because we use per-cpu mapping areas shared among the - * pools/users, we can't allow mapping in interrupt context - * because it can corrupt another users mappings. - */ - BUG_ON(in_interrupt()); + void *addr; - /* It guarantees it can get zspage from handle safely */ - spin_lock(&pool->lock); + /* Guarantee we can get zspage from handle safely */ + read_lock(&pool->lock); obj = handle_to_obj(handle); - obj_to_location(obj, &page, &obj_idx); - zspage = get_zspage(page); + obj_to_location(obj, &zpdesc, &obj_idx); + zspage = get_zspage(zpdesc); - /* - * migration cannot move any zpages in this zspage. Here, pool->lock - * is too heavy since callers would take some time until they calls - * zs_unmap_object API so delegate the locking from class to zspage - * which is smaller granularity. - */ - migrate_read_lock(zspage); - spin_unlock(&pool->lock); + /* Make sure migration doesn't move any pages in this zspage */ + zspage_read_lock(zspage); + read_unlock(&pool->lock); class = zspage_class(pool, zspage); off = offset_in_page(class->size * obj_idx); - local_lock(&zs_map_area.lock); - area = this_cpu_ptr(&zs_map_area); - area->vm_mm = mm; if (off + class->size <= PAGE_SIZE) { /* this object is contained entirely within a page */ - area->vm_addr = kmap_atomic(page); - ret = area->vm_addr + off; - goto out; + addr = kmap_local_zpdesc(zpdesc); + addr += off; + } else { + size_t sizes[2]; + + /* this object spans two pages */ + sizes[0] = PAGE_SIZE - off; + sizes[1] = class->size - sizes[0]; + addr = local_copy; + + memcpy_from_page(addr, zpdesc_page(zpdesc), + off, sizes[0]); + zpdesc = get_next_zpdesc(zpdesc); + memcpy_from_page(addr + sizes[0], + zpdesc_page(zpdesc), + 0, sizes[1]); } - /* this object spans two pages */ - pages[0] = page; - pages[1] = get_next_page(page); - BUG_ON(!pages[1]); - - ret = __zs_map_object(area, pages, off, class->size); -out: - if (likely(!ZsHugePage(zspage))) - ret += ZS_HANDLE_SIZE; + if (!ZsHugePage(zspage)) + addr += ZS_HANDLE_SIZE; - return ret; + return addr; } -EXPORT_SYMBOL_GPL(zs_map_object); +EXPORT_SYMBOL_GPL(zs_obj_read_begin); -void zs_unmap_object(struct zs_pool *pool, unsigned long handle) +void zs_obj_read_end(struct zs_pool *pool, unsigned long handle, + void *handle_mem) { struct zspage *zspage; - struct page *page; + struct zpdesc *zpdesc; unsigned long obj, off; unsigned int obj_idx; - struct size_class *class; - struct mapping_area *area; obj = handle_to_obj(handle); - obj_to_location(obj, &page, &obj_idx); - zspage = get_zspage(page); + obj_to_location(obj, &zpdesc, &obj_idx); + zspage = get_zspage(zpdesc); class = zspage_class(pool, zspage); off = offset_in_page(class->size * obj_idx); - area = this_cpu_ptr(&zs_map_area); - if (off + class->size <= PAGE_SIZE) - kunmap_atomic(area->vm_addr); - else { - struct page *pages[2]; + if (off + class->size <= PAGE_SIZE) { + if (!ZsHugePage(zspage)) + off += ZS_HANDLE_SIZE; + handle_mem -= off; + kunmap_local(handle_mem); + } + + zspage_read_unlock(zspage); +} +EXPORT_SYMBOL_GPL(zs_obj_read_end); + +void zs_obj_write(struct zs_pool *pool, unsigned long handle, + void *handle_mem, size_t mem_len) +{ + struct zspage *zspage; + struct zpdesc *zpdesc; + unsigned long obj, off; + unsigned int obj_idx; + struct size_class *class; + + /* Guarantee we can get zspage from handle safely */ + read_lock(&pool->lock); + obj = handle_to_obj(handle); + obj_to_location(obj, &zpdesc, &obj_idx); + zspage = get_zspage(zpdesc); - pages[0] = page; - pages[1] = get_next_page(page); - BUG_ON(!pages[1]); + /* Make sure migration doesn't move any pages in this zspage */ + zspage_read_lock(zspage); + read_unlock(&pool->lock); - __zs_unmap_object(area, pages, off, class->size); + class = zspage_class(pool, zspage); + off = offset_in_page(class->size * obj_idx); + + if (!ZsHugePage(zspage)) + off += ZS_HANDLE_SIZE; + + if (off + mem_len <= PAGE_SIZE) { + /* this object is contained entirely within a page */ + void *dst = kmap_local_zpdesc(zpdesc); + + memcpy(dst + off, handle_mem, mem_len); + kunmap_local(dst); + } else { + /* this object spans two pages */ + size_t sizes[2]; + + sizes[0] = PAGE_SIZE - off; + sizes[1] = mem_len - sizes[0]; + + memcpy_to_page(zpdesc_page(zpdesc), off, + handle_mem, sizes[0]); + zpdesc = get_next_zpdesc(zpdesc); + memcpy_to_page(zpdesc_page(zpdesc), 0, + handle_mem + sizes[0], sizes[1]); } - local_unlock(&zs_map_area.lock); - migrate_read_unlock(zspage); + zspage_read_unlock(zspage); } -EXPORT_SYMBOL_GPL(zs_unmap_object); +EXPORT_SYMBOL_GPL(zs_obj_write); /** * zs_huge_class_size() - Returns the size (in bytes) of the first huge @@ -1275,41 +1285,40 @@ EXPORT_SYMBOL_GPL(zs_huge_class_size); static unsigned long obj_malloc(struct zs_pool *pool, struct zspage *zspage, unsigned long handle) { - int i, nr_page, offset; + int i, nr_zpdesc, offset; unsigned long obj; struct link_free *link; struct size_class *class; - struct page *m_page; + struct zpdesc *m_zpdesc; unsigned long m_offset; void *vaddr; class = pool->size_class[zspage->class]; - handle |= OBJ_ALLOCATED_TAG; obj = get_freeobj(zspage); offset = obj * class->size; - nr_page = offset >> PAGE_SHIFT; + nr_zpdesc = offset >> PAGE_SHIFT; m_offset = offset_in_page(offset); - m_page = get_first_page(zspage); + m_zpdesc = get_first_zpdesc(zspage); - for (i = 0; i < nr_page; i++) - m_page = get_next_page(m_page); + for (i = 0; i < nr_zpdesc; i++) + m_zpdesc = get_next_zpdesc(m_zpdesc); - vaddr = kmap_atomic(m_page); + vaddr = kmap_local_zpdesc(m_zpdesc); link = (struct link_free *)vaddr + m_offset / sizeof(*link); set_freeobj(zspage, link->next >> OBJ_TAG_BITS); if (likely(!ZsHugePage(zspage))) /* record handle in the header of allocated chunk */ - link->handle = handle; + link->handle = handle | OBJ_ALLOCATED_TAG; else - /* record handle to page->index */ - zspage->first_page->index = handle; + zspage->first_zpdesc->handle = handle | OBJ_ALLOCATED_TAG; - kunmap_atomic(vaddr); + kunmap_local(vaddr); mod_zspage_inuse(zspage, 1); - obj = location_to_obj(m_page, obj); + obj = location_to_obj(m_zpdesc, obj); + record_obj(handle, obj); return obj; } @@ -1320,14 +1329,16 @@ static unsigned long obj_malloc(struct zs_pool *pool, * @pool: pool to allocate from * @size: size of block to allocate * @gfp: gfp flags when allocating object + * @nid: The preferred node id to allocate new zspage (if needed) * * On success, handle to the allocated object is returned, * otherwise an ERR_PTR(). * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail. */ -unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) +unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp, + const int nid) { - unsigned long handle, obj; + unsigned long handle; struct size_class *class; int newfg; struct zspage *zspage; @@ -1346,40 +1357,38 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) size += ZS_HANDLE_SIZE; class = pool->size_class[get_size_class_index(size)]; - /* pool->lock effectively protects the zpage migration */ - spin_lock(&pool->lock); + /* class->lock effectively protects the zpage migration */ + spin_lock(&class->lock); zspage = find_get_zspage(class); if (likely(zspage)) { - obj = obj_malloc(pool, zspage, handle); + obj_malloc(pool, zspage, handle); /* Now move the zspage to another fullness group, if required */ fix_fullness_group(class, zspage); - record_obj(handle, obj); - class_stat_inc(class, ZS_OBJS_INUSE, 1); + class_stat_add(class, ZS_OBJS_INUSE, 1); goto out; } - spin_unlock(&pool->lock); + spin_unlock(&class->lock); - zspage = alloc_zspage(pool, class, gfp); + zspage = alloc_zspage(pool, class, gfp, nid); if (!zspage) { cache_free_handle(pool, handle); return (unsigned long)ERR_PTR(-ENOMEM); } - spin_lock(&pool->lock); - obj = obj_malloc(pool, zspage, handle); + spin_lock(&class->lock); + obj_malloc(pool, zspage, handle); newfg = get_fullness_group(class, zspage); insert_zspage(class, zspage, newfg); - record_obj(handle, obj); atomic_long_add(class->pages_per_zspage, &pool->pages_allocated); - class_stat_inc(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage); - class_stat_inc(class, ZS_OBJS_INUSE, 1); + class_stat_add(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage); + class_stat_add(class, ZS_OBJS_INUSE, 1); /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); out: - spin_unlock(&pool->lock); + spin_unlock(&class->lock); return handle; } @@ -1389,33 +1398,34 @@ static void obj_free(int class_size, unsigned long obj) { struct link_free *link; struct zspage *zspage; - struct page *f_page; + struct zpdesc *f_zpdesc; unsigned long f_offset; unsigned int f_objidx; void *vaddr; - obj_to_location(obj, &f_page, &f_objidx); + + obj_to_location(obj, &f_zpdesc, &f_objidx); f_offset = offset_in_page(class_size * f_objidx); - zspage = get_zspage(f_page); + zspage = get_zspage(f_zpdesc); - vaddr = kmap_atomic(f_page); + vaddr = kmap_local_zpdesc(f_zpdesc); link = (struct link_free *)(vaddr + f_offset); /* Insert this object in containing zspage's freelist */ if (likely(!ZsHugePage(zspage))) link->next = get_freeobj(zspage) << OBJ_TAG_BITS; else - f_page->index = 0; + f_zpdesc->handle = 0; set_freeobj(zspage, f_objidx); - kunmap_atomic(vaddr); + kunmap_local(vaddr); mod_zspage_inuse(zspage, -1); } void zs_free(struct zs_pool *pool, unsigned long handle) { struct zspage *zspage; - struct page *f_page; + struct zpdesc *f_zpdesc; unsigned long obj; struct size_class *class; int fullness; @@ -1427,20 +1437,22 @@ void zs_free(struct zs_pool *pool, unsigned long handle) * The pool->lock protects the race with zpage's migration * so it's safe to get the page from handle. */ - spin_lock(&pool->lock); + read_lock(&pool->lock); obj = handle_to_obj(handle); - obj_to_page(obj, &f_page); - zspage = get_zspage(f_page); + obj_to_zpdesc(obj, &f_zpdesc); + zspage = get_zspage(f_zpdesc); class = zspage_class(pool, zspage); + spin_lock(&class->lock); + read_unlock(&pool->lock); - class_stat_dec(class, ZS_OBJS_INUSE, 1); + class_stat_sub(class, ZS_OBJS_INUSE, 1); obj_free(class->size, obj); fullness = fix_fullness_group(class, zspage); if (fullness == ZS_INUSE_RATIO_0) free_zspage(pool, class, zspage); - spin_unlock(&pool->lock); + spin_unlock(&class->lock); cache_free_handle(pool, handle); } EXPORT_SYMBOL_GPL(zs_free); @@ -1448,7 +1460,7 @@ EXPORT_SYMBOL_GPL(zs_free); static void zs_object_copy(struct size_class *class, unsigned long dst, unsigned long src) { - struct page *s_page, *d_page; + struct zpdesc *s_zpdesc, *d_zpdesc; unsigned int s_objidx, d_objidx; unsigned long s_off, d_off; void *s_addr, *d_addr; @@ -1457,8 +1469,8 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, s_size = d_size = class->size; - obj_to_location(src, &s_page, &s_objidx); - obj_to_location(dst, &d_page, &d_objidx); + obj_to_location(src, &s_zpdesc, &s_objidx); + obj_to_location(dst, &d_zpdesc, &d_objidx); s_off = offset_in_page(class->size * s_objidx); d_off = offset_in_page(class->size * d_objidx); @@ -1469,8 +1481,8 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, if (d_off + class->size > PAGE_SIZE) d_size = PAGE_SIZE - d_off; - s_addr = kmap_atomic(s_page); - d_addr = kmap_atomic(d_page); + s_addr = kmap_local_zpdesc(s_zpdesc); + d_addr = kmap_local_zpdesc(d_zpdesc); while (1) { size = min(s_size, d_size); @@ -1486,33 +1498,33 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, d_size -= size; /* - * Calling kunmap_atomic(d_addr) is necessary. kunmap_atomic() - * calls must occurs in reverse order of calls to kmap_atomic(). - * So, to call kunmap_atomic(s_addr) we should first call - * kunmap_atomic(d_addr). For more details see + * Calling kunmap_local(d_addr) is necessary. kunmap_local() + * calls must occurs in reverse order of calls to kmap_local_page(). + * So, to call kunmap_local(s_addr) we should first call + * kunmap_local(d_addr). For more details see * Documentation/mm/highmem.rst. */ if (s_off >= PAGE_SIZE) { - kunmap_atomic(d_addr); - kunmap_atomic(s_addr); - s_page = get_next_page(s_page); - s_addr = kmap_atomic(s_page); - d_addr = kmap_atomic(d_page); + kunmap_local(d_addr); + kunmap_local(s_addr); + s_zpdesc = get_next_zpdesc(s_zpdesc); + s_addr = kmap_local_zpdesc(s_zpdesc); + d_addr = kmap_local_zpdesc(d_zpdesc); s_size = class->size - written; s_off = 0; } if (d_off >= PAGE_SIZE) { - kunmap_atomic(d_addr); - d_page = get_next_page(d_page); - d_addr = kmap_atomic(d_page); + kunmap_local(d_addr); + d_zpdesc = get_next_zpdesc(d_zpdesc); + d_addr = kmap_local_zpdesc(d_zpdesc); d_size = class->size - written; d_off = 0; } } - kunmap_atomic(d_addr); - kunmap_atomic(s_addr); + kunmap_local(d_addr); + kunmap_local(s_addr); } /* @@ -1520,25 +1532,25 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, * return handle. */ static unsigned long find_alloced_obj(struct size_class *class, - struct page *page, int *obj_idx) + struct zpdesc *zpdesc, int *obj_idx) { unsigned int offset; int index = *obj_idx; unsigned long handle = 0; - void *addr = kmap_atomic(page); + void *addr = kmap_local_zpdesc(zpdesc); - offset = get_first_obj_offset(page); + offset = get_first_obj_offset(zpdesc); offset += class->size * index; while (offset < PAGE_SIZE) { - if (obj_allocated(page, addr + offset, &handle)) + if (obj_allocated(zpdesc, addr + offset, &handle)) break; offset += class->size; index++; } - kunmap_atomic(addr); + kunmap_local(addr); *obj_idx = index; @@ -1551,14 +1563,14 @@ static void migrate_zspage(struct zs_pool *pool, struct zspage *src_zspage, unsigned long used_obj, free_obj; unsigned long handle; int obj_idx = 0; - struct page *s_page = get_first_page(src_zspage); + struct zpdesc *s_zpdesc = get_first_zpdesc(src_zspage); struct size_class *class = pool->size_class[src_zspage->class]; while (1) { - handle = find_alloced_obj(class, s_page, &obj_idx); + handle = find_alloced_obj(class, s_zpdesc, &obj_idx); if (!handle) { - s_page = get_next_page(s_page); - if (!s_page) + s_zpdesc = get_next_zpdesc(s_zpdesc); + if (!s_zpdesc) break; obj_idx = 0; continue; @@ -1568,7 +1580,6 @@ static void migrate_zspage(struct zs_pool *pool, struct zspage *src_zspage, free_obj = obj_malloc(pool, dst_zspage, handle); zs_object_copy(class, free_obj, used_obj); obj_idx++; - record_obj(handle, free_obj); obj_free(class->size, used_obj); /* Stop if there is no more space */ @@ -1639,93 +1650,70 @@ static int putback_zspage(struct size_class *class, struct zspage *zspage) */ static void lock_zspage(struct zspage *zspage) { - struct page *curr_page, *page; + struct zpdesc *curr_zpdesc, *zpdesc; /* * Pages we haven't locked yet can be migrated off the list while we're * trying to lock them, so we need to be careful and only attempt to - * lock each page under migrate_read_lock(). Otherwise, the page we lock + * lock each page under zspage_read_lock(). Otherwise, the page we lock * may no longer belong to the zspage. This means that we may wait for * the wrong page to unlock, so we must take a reference to the page - * prior to waiting for it to unlock outside migrate_read_lock(). + * prior to waiting for it to unlock outside zspage_read_lock(). */ while (1) { - migrate_read_lock(zspage); - page = get_first_page(zspage); - if (trylock_page(page)) + zspage_read_lock(zspage); + zpdesc = get_first_zpdesc(zspage); + if (zpdesc_trylock(zpdesc)) break; - get_page(page); - migrate_read_unlock(zspage); - wait_on_page_locked(page); - put_page(page); + zpdesc_get(zpdesc); + zspage_read_unlock(zspage); + zpdesc_wait_locked(zpdesc); + zpdesc_put(zpdesc); } - curr_page = page; - while ((page = get_next_page(curr_page))) { - if (trylock_page(page)) { - curr_page = page; + curr_zpdesc = zpdesc; + while ((zpdesc = get_next_zpdesc(curr_zpdesc))) { + if (zpdesc_trylock(zpdesc)) { + curr_zpdesc = zpdesc; } else { - get_page(page); - migrate_read_unlock(zspage); - wait_on_page_locked(page); - put_page(page); - migrate_read_lock(zspage); + zpdesc_get(zpdesc); + zspage_read_unlock(zspage); + zpdesc_wait_locked(zpdesc); + zpdesc_put(zpdesc); + zspage_read_lock(zspage); } } - migrate_read_unlock(zspage); + zspage_read_unlock(zspage); } #endif /* CONFIG_COMPACTION */ -static void migrate_lock_init(struct zspage *zspage) -{ - rwlock_init(&zspage->lock); -} - -static void migrate_read_lock(struct zspage *zspage) __acquires(&zspage->lock) -{ - read_lock(&zspage->lock); -} - -static void migrate_read_unlock(struct zspage *zspage) __releases(&zspage->lock) -{ - read_unlock(&zspage->lock); -} - -static void migrate_write_lock(struct zspage *zspage) -{ - write_lock(&zspage->lock); -} - -static void migrate_write_unlock(struct zspage *zspage) -{ - write_unlock(&zspage->lock); -} - #ifdef CONFIG_COMPACTION static const struct movable_operations zsmalloc_mops; static void replace_sub_page(struct size_class *class, struct zspage *zspage, - struct page *newpage, struct page *oldpage) + struct zpdesc *newzpdesc, struct zpdesc *oldzpdesc) { - struct page *page; - struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE] = {NULL, }; + struct zpdesc *zpdesc; + struct zpdesc *zpdescs[ZS_MAX_PAGES_PER_ZSPAGE] = {NULL, }; + unsigned int first_obj_offset; int idx = 0; - page = get_first_page(zspage); + zpdesc = get_first_zpdesc(zspage); do { - if (page == oldpage) - pages[idx] = newpage; + if (zpdesc == oldzpdesc) + zpdescs[idx] = newzpdesc; else - pages[idx] = page; + zpdescs[idx] = zpdesc; idx++; - } while ((page = get_next_page(page)) != NULL); + } while ((zpdesc = get_next_zpdesc(zpdesc)) != NULL); - create_page_chain(class, zspage, pages); - set_first_obj_offset(newpage, get_first_obj_offset(oldpage)); + create_page_chain(class, zspage, zpdescs); + first_obj_offset = get_first_obj_offset(oldzpdesc); + set_first_obj_offset(newzpdesc, first_obj_offset); if (unlikely(ZsHugePage(zspage))) - newpage->index = oldpage->index; - __SetPageMovable(newpage, &zsmalloc_mops); + newzpdesc->handle = oldzpdesc->handle; + __zpdesc_set_movable(newzpdesc, &zsmalloc_mops); } static bool zs_page_isolate(struct page *page, isolate_mode_t mode) @@ -1745,76 +1733,81 @@ static int zs_page_migrate(struct page *newpage, struct page *page, struct zs_pool *pool; struct size_class *class; struct zspage *zspage; - struct page *dummy; + struct zpdesc *dummy; + struct zpdesc *newzpdesc = page_zpdesc(newpage); + struct zpdesc *zpdesc = page_zpdesc(page); void *s_addr, *d_addr, *addr; unsigned int offset; unsigned long handle; unsigned long old_obj, new_obj; unsigned int obj_idx; - /* - * We cannot support the _NO_COPY case here, because copy needs to - * happen under the zs lock, which does not work with - * MIGRATE_SYNC_NO_COPY workflow. - */ - if (mode == MIGRATE_SYNC_NO_COPY) - return -EINVAL; - - VM_BUG_ON_PAGE(!PageIsolated(page), page); + VM_BUG_ON_PAGE(!zpdesc_is_isolated(zpdesc), zpdesc_page(zpdesc)); /* The page is locked, so this pointer must remain valid */ - zspage = get_zspage(page); + zspage = get_zspage(zpdesc); pool = zspage->pool; /* - * The pool's lock protects the race between zpage migration + * The pool migrate_lock protects the race between zpage migration * and zs_free. */ - spin_lock(&pool->lock); + write_lock(&pool->lock); class = zspage_class(pool, zspage); - /* the migrate_write_lock protects zpage access via zs_map_object */ - migrate_write_lock(zspage); + /* + * the class lock protects zpage alloc/free in the zspage. + */ + spin_lock(&class->lock); + /* the zspage write_lock protects zpage access via zs_obj_read/write() */ + if (!zspage_write_trylock(zspage)) { + spin_unlock(&class->lock); + write_unlock(&pool->lock); + return -EINVAL; + } - offset = get_first_obj_offset(page); - s_addr = kmap_atomic(page); + /* We're committed, tell the world that this is a Zsmalloc page. */ + __zpdesc_set_zsmalloc(newzpdesc); + + offset = get_first_obj_offset(zpdesc); + s_addr = kmap_local_zpdesc(zpdesc); /* * Here, any user cannot access all objects in the zspage so let's move. */ - d_addr = kmap_atomic(newpage); + d_addr = kmap_local_zpdesc(newzpdesc); copy_page(d_addr, s_addr); - kunmap_atomic(d_addr); + kunmap_local(d_addr); for (addr = s_addr + offset; addr < s_addr + PAGE_SIZE; addr += class->size) { - if (obj_allocated(page, addr, &handle)) { + if (obj_allocated(zpdesc, addr, &handle)) { old_obj = handle_to_obj(handle); obj_to_location(old_obj, &dummy, &obj_idx); - new_obj = (unsigned long)location_to_obj(newpage, - obj_idx); + new_obj = (unsigned long)location_to_obj(newzpdesc, obj_idx); record_obj(handle, new_obj); } } - kunmap_atomic(s_addr); + kunmap_local(s_addr); - replace_sub_page(class, zspage, newpage, page); + replace_sub_page(class, zspage, newzpdesc, zpdesc); /* * Since we complete the data copy and set up new zspage structure, - * it's okay to release the pool's lock. + * it's okay to release migration_lock. */ - spin_unlock(&pool->lock); - migrate_write_unlock(zspage); - - get_page(newpage); - if (page_zone(newpage) != page_zone(page)) { - dec_zone_page_state(page, NR_ZSPAGES); - inc_zone_page_state(newpage, NR_ZSPAGES); + write_unlock(&pool->lock); + spin_unlock(&class->lock); + zspage_write_unlock(zspage); + + zpdesc_get(newzpdesc); + if (zpdesc_zone(newzpdesc) != zpdesc_zone(zpdesc)) { + zpdesc_dec_zone_page_state(zpdesc); + zpdesc_inc_zone_page_state(newzpdesc); } - reset_page(page); - put_page(page); + reset_zpdesc(zpdesc); + zpdesc_put(zpdesc); return MIGRATEPAGE_SUCCESS; } @@ -1848,20 +1841,21 @@ static void async_free_zspage(struct work_struct *work) if (class->index != i) continue; - spin_lock(&pool->lock); + spin_lock(&class->lock); list_splice_init(&class->fullness_list[ZS_INUSE_RATIO_0], &free_pages); - spin_unlock(&pool->lock); + spin_unlock(&class->lock); } list_for_each_entry_safe(zspage, tmp, &free_pages, list) { list_del(&zspage->list); lock_zspage(zspage); - spin_lock(&pool->lock); class = zspage_class(pool, zspage); + spin_lock(&class->lock); + class_stat_sub(class, ZS_INUSE_RATIO_0, 1); __free_zspage(pool, class, zspage); - spin_unlock(&pool->lock); + spin_unlock(&class->lock); } }; @@ -1882,13 +1876,13 @@ static void init_deferred_free(struct zs_pool *pool) static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) { - struct page *page = get_first_page(zspage); + struct zpdesc *zpdesc = get_first_zpdesc(zspage); do { - WARN_ON(!trylock_page(page)); - __SetPageMovable(page, &zsmalloc_mops); - unlock_page(page); - } while ((page = get_next_page(page)) != NULL); + WARN_ON(!zpdesc_trylock(zpdesc)); + __zpdesc_set_movable(zpdesc, &zsmalloc_mops); + zpdesc_unlock(zpdesc); + } while ((zpdesc = get_next_zpdesc(zpdesc)) != NULL); } #else static inline void zs_flush_migration(struct zs_pool *pool) { } @@ -1902,8 +1896,8 @@ static inline void zs_flush_migration(struct zs_pool *pool) { } static unsigned long zs_can_compact(struct size_class *class) { unsigned long obj_wasted; - unsigned long obj_allocated = zs_stat_get(class, ZS_OBJS_ALLOCATED); - unsigned long obj_used = zs_stat_get(class, ZS_OBJS_INUSE); + unsigned long obj_allocated = class_stat_read(class, ZS_OBJS_ALLOCATED); + unsigned long obj_used = class_stat_read(class, ZS_OBJS_INUSE); if (obj_allocated <= obj_used) return 0; @@ -1925,7 +1919,8 @@ static unsigned long __zs_compact(struct zs_pool *pool, * protect the race between zpage migration and zs_free * as well as zpage allocation/free */ - spin_lock(&pool->lock); + write_lock(&pool->lock); + spin_lock(&class->lock); while (zs_can_compact(class)) { int fg; @@ -1939,9 +1934,11 @@ static unsigned long __zs_compact(struct zs_pool *pool, if (!src_zspage) break; - migrate_write_lock(src_zspage); + if (!zspage_write_trylock(src_zspage)) + break; + migrate_zspage(pool, src_zspage, dst_zspage); - migrate_write_unlock(src_zspage); + zspage_write_unlock(src_zspage); fg = putback_zspage(class, src_zspage); if (fg == ZS_INUSE_RATIO_0) { @@ -1951,13 +1948,15 @@ static unsigned long __zs_compact(struct zs_pool *pool, src_zspage = NULL; if (get_fullness_group(class, dst_zspage) == ZS_INUSE_RATIO_100 - || spin_is_contended(&pool->lock)) { + || rwlock_is_contended(&pool->lock)) { putback_zspage(class, dst_zspage); dst_zspage = NULL; - spin_unlock(&pool->lock); + spin_unlock(&class->lock); + write_unlock(&pool->lock); cond_resched(); - spin_lock(&pool->lock); + write_lock(&pool->lock); + spin_lock(&class->lock); } } @@ -1967,7 +1966,8 @@ static unsigned long __zs_compact(struct zs_pool *pool, if (dst_zspage) putback_zspage(class, dst_zspage); - spin_unlock(&pool->lock); + spin_unlock(&class->lock); + write_unlock(&pool->lock); return pages_freed; } @@ -2104,7 +2104,7 @@ struct zs_pool *zs_create_pool(const char *name) return NULL; init_deferred_free(pool); - spin_lock_init(&pool->lock); + rwlock_init(&pool->lock); atomic_set(&pool->compaction_in_progress, 0); pool->name = kstrdup(name, GFP_KERNEL); @@ -2176,6 +2176,7 @@ struct zs_pool *zs_create_pool(const char *name) class->index = i; class->pages_per_zspage = pages_per_zspage; class->objs_per_zspage = objs_per_zspage; + spin_lock_init(&class->lock); pool->size_class[i] = class; fullness = ZS_INUSE_RATIO_0; @@ -2242,23 +2243,11 @@ EXPORT_SYMBOL_GPL(zs_destroy_pool); static int __init zs_init(void) { - int ret; - - ret = cpuhp_setup_state(CPUHP_MM_ZS_PREPARE, "mm/zsmalloc:prepare", - zs_cpu_prepare, zs_cpu_dead); - if (ret) - goto out; - #ifdef CONFIG_ZPOOL zpool_register_driver(&zs_zpool_driver); #endif - zs_stat_init(); - return 0; - -out: - return ret; } static void __exit zs_exit(void) @@ -2266,8 +2255,6 @@ static void __exit zs_exit(void) #ifdef CONFIG_ZPOOL zpool_unregister_driver(&zs_zpool_driver); #endif - cpuhp_remove_state(CPUHP_MM_ZS_PREPARE); - zs_stat_exit(); } @@ -2276,3 +2263,4 @@ module_exit(zs_exit); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>"); +MODULE_DESCRIPTION("zsmalloc memory allocator"); |