summaryrefslogtreecommitdiff
path: root/mm/zsmalloc.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/zsmalloc.c')
-rw-r--r--mm/zsmalloc.c365
1 files changed, 302 insertions, 63 deletions
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index d03941cace2c..9445bee6b014 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -33,8 +33,7 @@
/*
* lock ordering:
* page_lock
- * pool->migrate_lock
- * class->lock
+ * pool->lock
* zspage->lock
*/
@@ -192,7 +191,6 @@ static const int fullness_threshold_frac = 4;
static size_t huge_class_size;
struct size_class {
- spinlock_t lock;
struct list_head fullness_list[NR_ZS_FULLNESS];
/*
* Size of objects stored in this class. Must be multiple
@@ -241,14 +239,20 @@ struct zs_pool {
/* Compact classes */
struct shrinker shrinker;
+#ifdef CONFIG_ZPOOL
+ /* List tracking the zspages in LRU order by most recently added object */
+ struct list_head lru;
+ struct zpool *zpool;
+ const struct zpool_ops *zpool_ops;
+#endif
+
#ifdef CONFIG_ZSMALLOC_STAT
struct dentry *stat_dentry;
#endif
#ifdef CONFIG_COMPACTION
struct work_struct free_work;
#endif
- /* protect page/zspage migration */
- rwlock_t migrate_lock;
+ spinlock_t lock;
};
struct zspage {
@@ -263,10 +267,17 @@ struct zspage {
unsigned int freeobj;
struct page *first_page;
struct list_head list; /* fullness list */
+
+#ifdef CONFIG_ZPOOL
+ /* 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;
+#endif
+
struct zs_pool *pool;
-#ifdef CONFIG_COMPACTION
rwlock_t lock;
-#endif
};
struct mapping_area {
@@ -287,10 +298,11 @@ 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);
@@ -298,9 +310,6 @@ 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) {}
@@ -355,7 +364,7 @@ static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage)
kmem_cache_free(pool->zspage_cachep, zspage);
}
-/* class->lock(which owns the handle) synchronizes races */
+/* pool->lock(which owns the handle) synchronizes races */
static void record_obj(unsigned long handle, unsigned long obj)
{
*(unsigned long *)handle = obj;
@@ -374,7 +383,14 @@ static void *zs_zpool_create(const char *name, gfp_t gfp,
* different contexts and its caller must provide a valid
* gfp mask.
*/
- return zs_create_pool(name);
+ struct zs_pool *pool = zs_create_pool(name);
+
+ if (pool) {
+ pool->zpool = zpool;
+ pool->zpool_ops = zpool_ops;
+ }
+
+ return pool;
}
static void zs_zpool_destroy(void *pool)
@@ -387,7 +403,7 @@ static int zs_zpool_malloc(void *pool, size_t size, gfp_t gfp,
{
*handle = zs_malloc(pool, size, gfp);
- if (IS_ERR((void *)(*handle)))
+ if (IS_ERR_VALUE(*handle))
return PTR_ERR((void *)*handle);
return 0;
}
@@ -396,6 +412,27 @@ 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)
{
@@ -434,6 +471,7 @@ 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,
@@ -452,7 +490,7 @@ static __maybe_unused int is_first_page(struct page *page)
return PagePrivate(page);
}
-/* Protected by class->lock */
+/* Protected by pool->lock */
static inline int get_zspage_inuse(struct zspage *zspage)
{
return zspage->inuse;
@@ -597,13 +635,13 @@ static int zs_stats_size_show(struct seq_file *s, void *v)
if (class->index != i)
continue;
- spin_lock(&class->lock);
+ spin_lock(&pool->lock);
class_almost_full = zs_stat_get(class, CLASS_ALMOST_FULL);
class_almost_empty = zs_stat_get(class, CLASS_ALMOST_EMPTY);
obj_allocated = zs_stat_get(class, OBJ_ALLOCATED);
obj_used = zs_stat_get(class, OBJ_USED);
freeable = zs_can_compact(class);
- spin_unlock(&class->lock);
+ spin_unlock(&pool->lock);
objs_per_zspage = class->objs_per_zspage;
pages_used = obj_allocated / objs_per_zspage *
@@ -907,6 +945,25 @@ unlock:
return 0;
}
+#ifdef CONFIG_ZPOOL
+/*
+ * 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;
+ }
+}
+#else
+static inline void free_handles(struct zs_pool *pool, struct zspage *zspage) {}
+#endif
+
static void __free_zspage(struct zs_pool *pool, struct size_class *class,
struct zspage *zspage)
{
@@ -916,11 +973,14 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class,
get_zspage_mapping(zspage, &class_idx, &fg);
- assert_spin_locked(&class->lock);
+ assert_spin_locked(&pool->lock);
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);
@@ -956,6 +1016,9 @@ static void free_zspage(struct zs_pool *pool, struct size_class *class,
}
remove_zspage(class, zspage, ZS_EMPTY);
+#ifdef CONFIG_ZPOOL
+ list_del(&zspage->lru);
+#endif
__free_zspage(pool, class, zspage);
}
@@ -1001,6 +1064,12 @@ static void init_zspage(struct size_class *class, struct zspage *zspage)
off %= PAGE_SIZE;
}
+#ifdef CONFIG_ZPOOL
+ INIT_LIST_HEAD(&zspage->lru);
+ zspage->under_reclaim = false;
+ zspage->deferred_handles = NULL;
+#endif
+
set_freeobj(zspage, 0);
}
@@ -1205,6 +1274,27 @@ static bool zspage_full(struct size_class *class, struct zspage *zspage)
return get_zspage_inuse(zspage) == class->objs_per_zspage;
}
+/**
+ * zs_lookup_class_index() - Returns index of the zsmalloc &size_class
+ * that hold objects of the provided size.
+ * @pool: zsmalloc pool to use
+ * @size: object size
+ *
+ * Context: Any context.
+ *
+ * Return: the index of the zsmalloc &size_class that hold objects of the
+ * provided size.
+ */
+unsigned int zs_lookup_class_index(struct zs_pool *pool, unsigned int size)
+{
+ struct size_class *class;
+
+ class = pool->size_class[get_size_class_index(size)];
+
+ return class->index;
+}
+EXPORT_SYMBOL_GPL(zs_lookup_class_index);
+
unsigned long zs_get_total_pages(struct zs_pool *pool)
{
return atomic_long_read(&pool->pages_allocated);
@@ -1247,19 +1337,44 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
BUG_ON(in_interrupt());
/* It guarantees it can get zspage from handle safely */
- read_lock(&pool->migrate_lock);
+ spin_lock(&pool->lock);
obj = handle_to_obj(handle);
obj_to_location(obj, &page, &obj_idx);
zspage = get_zspage(page);
+#ifdef CONFIG_ZPOOL
/*
- * migration cannot move any zpages in this zspage. Here, class->lock
+ * Move the zspage to front of pool's LRU.
+ *
+ * Note that this is swap-specific, so by definition there are no ongoing
+ * accesses to the memory while the page is swapped out that would make
+ * it "hot". A new entry is hot, then ages to the tail until it gets either
+ * written back or swaps back in.
+ *
+ * Furthermore, map is also called during writeback. We must not put an
+ * isolated page on the LRU mid-reclaim.
+ *
+ * As a result, only update the LRU when the page is mapped for write
+ * when it's first instantiated.
+ *
+ * This is a deviation from the other backends, which perform this update
+ * in the allocation function (zbud_alloc, z3fold_alloc).
+ */
+ if (mm == ZS_MM_WO) {
+ if (!list_empty(&zspage->lru))
+ list_del(&zspage->lru);
+ list_add(&zspage->lru, &pool->lru);
+ }
+#endif
+
+ /*
+ * 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);
- read_unlock(&pool->migrate_lock);
+ spin_unlock(&pool->lock);
class = zspage_class(pool, zspage);
off = (class->size * obj_idx) & ~PAGE_MASK;
@@ -1412,8 +1527,8 @@ 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)];
- /* class->lock effectively protects the zpage migration */
- spin_lock(&class->lock);
+ /* pool->lock effectively protects the zpage migration */
+ spin_lock(&pool->lock);
zspage = find_get_zspage(class);
if (likely(zspage)) {
obj = obj_malloc(pool, zspage, handle);
@@ -1421,12 +1536,12 @@ 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);
- spin_unlock(&class->lock);
+ spin_unlock(&pool->lock);
return handle;
}
- spin_unlock(&class->lock);
+ spin_unlock(&pool->lock);
zspage = alloc_zspage(pool, class, gfp);
if (!zspage) {
@@ -1434,7 +1549,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp)
return (unsigned long)ERR_PTR(-ENOMEM);
}
- spin_lock(&class->lock);
+ spin_lock(&pool->lock);
obj = obj_malloc(pool, zspage, handle);
newfg = get_fullness_group(class, zspage);
insert_zspage(class, zspage, newfg);
@@ -1447,7 +1562,7 @@ 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);
- spin_unlock(&class->lock);
+ spin_unlock(&pool->lock);
return handle;
}
@@ -1491,26 +1606,38 @@ void zs_free(struct zs_pool *pool, unsigned long handle)
return;
/*
- * The pool->migrate_lock protects the race with zpage's migration
+ * The pool->lock protects the race with zpage's migration
* so it's safe to get the page from handle.
*/
- read_lock(&pool->migrate_lock);
+ spin_lock(&pool->lock);
obj = handle_to_obj(handle);
obj_to_page(obj, &f_page);
zspage = get_zspage(f_page);
class = zspage_class(pool, zspage);
- spin_lock(&class->lock);
- read_unlock(&pool->migrate_lock);
obj_free(class->size, obj);
class_stat_dec(class, OBJ_USED, 1);
+
+#ifdef CONFIG_ZPOOL
+ 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;
+ }
+#endif
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(&class->lock);
+ spin_unlock(&pool->lock);
cache_free_handle(pool, handle);
}
EXPORT_SYMBOL_GPL(zs_free);
@@ -1709,7 +1836,7 @@ 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.
@@ -1751,6 +1878,24 @@ 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)
{
@@ -1767,6 +1912,7 @@ 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);
@@ -1867,16 +2013,12 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
pool = zspage->pool;
/*
- * The pool migrate_lock protects the race between zpage migration
+ * The pool's lock protects the race between zpage migration
* and zs_free.
*/
- write_lock(&pool->migrate_lock);
+ spin_lock(&pool->lock);
class = zspage_class(pool, zspage);
- /*
- * the class lock protects zpage alloc/free in the zspage.
- */
- spin_lock(&class->lock);
/* the migrate_write_lock protects zpage access via zs_map_object */
migrate_write_lock(zspage);
@@ -1906,10 +2048,9 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
replace_sub_page(class, zspage, newpage, page);
/*
* Since we complete the data copy and set up new zspage structure,
- * it's okay to release migration_lock.
+ * it's okay to release the pool's lock.
*/
- write_unlock(&pool->migrate_lock);
- spin_unlock(&class->lock);
+ spin_unlock(&pool->lock);
dec_zspage_isolation(zspage);
migrate_write_unlock(zspage);
@@ -1964,9 +2105,9 @@ static void async_free_zspage(struct work_struct *work)
if (class->index != i)
continue;
- spin_lock(&class->lock);
+ spin_lock(&pool->lock);
list_splice_init(&class->fullness_list[ZS_EMPTY], &free_pages);
- spin_unlock(&class->lock);
+ spin_unlock(&pool->lock);
}
list_for_each_entry_safe(zspage, tmp, &free_pages, list) {
@@ -1976,9 +2117,12 @@ static void async_free_zspage(struct work_struct *work)
get_zspage_mapping(zspage, &class_idx, &fullness);
VM_BUG_ON(fullness != ZS_EMPTY);
class = pool->size_class[class_idx];
- spin_lock(&class->lock);
+ spin_lock(&pool->lock);
+#ifdef CONFIG_ZPOOL
+ list_del(&zspage->lru);
+#endif
__free_zspage(pool, class, zspage);
- spin_unlock(&class->lock);
+ spin_unlock(&pool->lock);
}
};
@@ -2039,10 +2183,11 @@ static unsigned long __zs_compact(struct zs_pool *pool,
struct zspage *dst_zspage = NULL;
unsigned long pages_freed = 0;
- /* protect the race between zpage migration and zs_free */
- write_lock(&pool->migrate_lock);
- /* protect zpage allocation/free */
- spin_lock(&class->lock);
+ /*
+ * protect the race between zpage migration and zs_free
+ * as well as zpage allocation/free
+ */
+ spin_lock(&pool->lock);
while ((src_zspage = isolate_zspage(class, true))) {
/* protect someone accessing the zspage(i.e., zs_map_object) */
migrate_write_lock(src_zspage);
@@ -2067,7 +2212,7 @@ static unsigned long __zs_compact(struct zs_pool *pool,
putback_zspage(class, dst_zspage);
migrate_write_unlock(dst_zspage);
dst_zspage = NULL;
- if (rwlock_is_contended(&pool->migrate_lock))
+ if (spin_is_contended(&pool->lock))
break;
}
@@ -2084,11 +2229,9 @@ static unsigned long __zs_compact(struct zs_pool *pool,
pages_freed += class->pages_per_zspage;
} else
migrate_write_unlock(src_zspage);
- spin_unlock(&class->lock);
- write_unlock(&pool->migrate_lock);
+ spin_unlock(&pool->lock);
cond_resched();
- write_lock(&pool->migrate_lock);
- spin_lock(&class->lock);
+ spin_lock(&pool->lock);
}
if (src_zspage) {
@@ -2096,8 +2239,7 @@ static unsigned long __zs_compact(struct zs_pool *pool,
migrate_write_unlock(src_zspage);
}
- spin_unlock(&class->lock);
- write_unlock(&pool->migrate_lock);
+ spin_unlock(&pool->lock);
return pages_freed;
}
@@ -2200,7 +2342,7 @@ struct zs_pool *zs_create_pool(const char *name)
return NULL;
init_deferred_free(pool);
- rwlock_init(&pool->migrate_lock);
+ spin_lock_init(&pool->lock);
pool->name = kstrdup(name, GFP_KERNEL);
if (!pool->name)
@@ -2271,7 +2413,6 @@ 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;
for (fullness = ZS_EMPTY; fullness < NR_ZS_FULLNESS;
fullness++)
@@ -2291,6 +2432,10 @@ struct zs_pool *zs_create_pool(const char *name)
*/
zs_register_shrinker(pool);
+#ifdef CONFIG_ZPOOL
+ INIT_LIST_HEAD(&pool->lru);
+#endif
+
return pool;
err:
@@ -2332,6 +2477,100 @@ 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 (list_empty(&pool->lru)) {
+ 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;
+
+ 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);
+ cond_resched();
+
+ /* Lock backing pages into place */
+ lock_zspage(zspage);
+
+ obj_idx = 0;
+ page = get_first_page(zspage);
+ 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->zpool_ops->evict(pool->zpool, 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;