/*
* lock ordering:
* page_lock
- * pool->migrate_lock
- * class->lock
+ * pool->lock
* zspage->lock
*/
*/
#define ZS_ALIGN 8
-/*
- * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single)
- * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N.
- */
-#define ZS_MAX_ZSPAGE_ORDER 2
-#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER)
-
#define ZS_HANDLE_SIZE (sizeof(unsigned long))
/*
* have room for two bit at least.
*/
#define OBJ_ALLOCATED_TAG 1
-#define OBJ_TAG_BITS 1
-#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS)
+
+#define OBJ_TAG_BITS 1
+#define OBJ_TAG_MASK OBJ_ALLOCATED_TAG
+
+#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS)
#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
#define HUGE_BITS 1
-#define FULLNESS_BITS 2
+#define FULLNESS_BITS 4
#define CLASS_BITS 8
-#define ISOLATED_BITS 3
#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 */
#define ZS_MIN_ALLOC_SIZE \
MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
#define ZS_SIZE_CLASSES (DIV_ROUND_UP(ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE, \
ZS_SIZE_CLASS_DELTA) + 1)
+/*
+ * Pages are distinguished by the ratio of used memory (that is the ratio
+ * of ->inuse objects to all objects that page can store). For example,
+ * INUSE_RATIO_10 means that the ratio of used objects is > 0% and <= 10%.
+ *
+ * The number of fullness groups is not random. It allows us to keep
+ * difference between the least busy page in the group (minimum permitted
+ * number of ->inuse objects) and the most busy page (maximum permitted
+ * number of ->inuse objects) at a reasonable value.
+ */
enum fullness_group {
- ZS_EMPTY,
- ZS_ALMOST_EMPTY,
- ZS_ALMOST_FULL,
- ZS_FULL,
- NR_ZS_FULLNESS,
+ ZS_INUSE_RATIO_0,
+ ZS_INUSE_RATIO_10,
+ /* NOTE: 8 more fullness groups here */
+ ZS_INUSE_RATIO_99 = 10,
+ ZS_INUSE_RATIO_100,
+ NR_FULLNESS_GROUPS,
};
enum class_stat_type {
- CLASS_EMPTY,
- CLASS_ALMOST_EMPTY,
- CLASS_ALMOST_FULL,
- CLASS_FULL,
- OBJ_ALLOCATED,
- OBJ_USED,
- NR_ZS_STAT_TYPE,
+ /* NOTE: stats for 12 fullness groups here: from inuse 0 to 100 */
+ ZS_OBJS_ALLOCATED = NR_FULLNESS_GROUPS,
+ ZS_OBJS_INUSE,
+ NR_CLASS_STAT_TYPES,
};
struct zs_size_stat {
- unsigned long objs[NR_ZS_STAT_TYPE];
+ unsigned long objs[NR_CLASS_STAT_TYPES];
};
#ifdef CONFIG_ZSMALLOC_STAT
static struct dentry *zs_stat_root;
#endif
-/*
- * We assign a page to ZS_ALMOST_EMPTY fullness group when:
- * n <= N / f, where
- * n = number of allocated objects
- * N = total number of objects zspage can store
- * f = fullness_threshold_frac
- *
- * Similarly, we assign zspage to:
- * ZS_ALMOST_FULL when n > N / f
- * ZS_EMPTY when n == 0
- * ZS_FULL when n == N
- *
- * (see: fix_fullness_group())
- */
-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];
+ struct list_head fullness_list[NR_FULLNESS_GROUPS];
/*
* Size of objects stored in this class. Must be multiple
* of ZS_ALIGN.
struct zs_pool_stats stats;
/* Compact classes */
- struct shrinker shrinker;
+ struct shrinker *shrinker;
#ifdef CONFIG_ZSMALLOC_STAT
struct dentry *stat_dentry;
#ifdef CONFIG_COMPACTION
struct work_struct free_work;
#endif
- /* protect page/zspage migration */
- rwlock_t migrate_lock;
+ spinlock_t lock;
+ atomic_t compaction_in_progress;
};
struct zspage {
unsigned int huge:HUGE_BITS;
unsigned int fullness:FULLNESS_BITS;
unsigned int class:CLASS_BITS + 1;
- unsigned int isolated:ISOLATED_BITS;
unsigned int magic:MAGIC_VAL_BITS;
};
unsigned int inuse;
struct page *first_page;
struct list_head list; /* fullness list */
struct zs_pool *pool;
-#ifdef CONFIG_COMPACTION
rwlock_t lock;
-#endif
};
struct mapping_area {
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);
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);
+
+#ifdef CONFIG_COMPACTION
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) {}
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) {}
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;
#ifdef CONFIG_ZPOOL
-static void *zs_zpool_create(const char *name, gfp_t gfp,
- const struct zpool_ops *zpool_ops,
- struct zpool *zpool)
+static void *zs_zpool_create(const char *name, gfp_t gfp)
{
/*
* Ignore global gfp flags: zs_malloc() may be invoked from
{
*handle = zs_malloc(pool, size, gfp);
- if (IS_ERR((void *)(*handle)))
+ if (IS_ERR_VALUE(*handle))
return PTR_ERR((void *)*handle);
return 0;
}
return PagePrivate(page);
}
-/* Protected by class->lock */
+/* Protected by pool->lock */
static inline int get_zspage_inuse(struct zspage *zspage)
{
return zspage->inuse;
return first_page;
}
-static inline int get_first_obj_offset(struct page *page)
+static inline unsigned int get_first_obj_offset(struct page *page)
{
return page->page_type;
}
-static inline void set_first_obj_offset(struct page *page, int offset)
+static inline void set_first_obj_offset(struct page *page, unsigned int offset)
{
page->page_type = offset;
}
zspage->freeobj = obj;
}
-static void get_zspage_mapping(struct zspage *zspage,
- unsigned int *class_idx,
- enum fullness_group *fullness)
-{
- BUG_ON(zspage->magic != ZSPAGE_MAGIC);
-
- *fullness = zspage->fullness;
- *class_idx = zspage->class;
-}
-
static struct size_class *zspage_class(struct zs_pool *pool,
- struct zspage *zspage)
+ struct zspage *zspage)
{
return pool->size_class[zspage->class];
}
-static void set_zspage_mapping(struct zspage *zspage,
- unsigned int class_idx,
- enum fullness_group fullness)
-{
- zspage->class = class_idx;
- zspage->fullness = fullness;
-}
-
/*
* zsmalloc divides the pool into various size classes where each
* class maintains a list of zspages where each zspage is divided
return min_t(int, ZS_SIZE_CLASSES - 1, idx);
}
-/* type can be of enum type class_stat_type or fullness_group */
static inline void class_stat_inc(struct size_class *class,
int type, unsigned long cnt)
{
class->stats.objs[type] += cnt;
}
-/* type can be of enum type class_stat_type or fullness_group */
static inline void class_stat_dec(struct size_class *class,
int type, unsigned long cnt)
{
class->stats.objs[type] -= cnt;
}
-/* type can be of enum type class_stat_type or fullness_group */
-static inline unsigned long zs_stat_get(struct size_class *class,
- int type)
+static inline unsigned long zs_stat_get(struct size_class *class, int type)
{
return class->stats.objs[type];
}
static int zs_stats_size_show(struct seq_file *s, void *v)
{
- int i;
+ int i, fg;
struct zs_pool *pool = s->private;
struct size_class *class;
int objs_per_zspage;
- unsigned long class_almost_full, class_almost_empty;
unsigned long obj_allocated, obj_used, pages_used, freeable;
- unsigned long total_class_almost_full = 0, total_class_almost_empty = 0;
unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0;
unsigned long total_freeable = 0;
+ unsigned long inuse_totals[NR_FULLNESS_GROUPS] = {0, };
- seq_printf(s, " %5s %5s %11s %12s %13s %10s %10s %16s %8s\n",
- "class", "size", "almost_full", "almost_empty",
+ seq_printf(s, " %5s %5s %9s %9s %9s %9s %9s %9s %9s %9s %9s %9s %9s %13s %10s %10s %16s %8s\n",
+ "class", "size", "10%", "20%", "30%", "40%",
+ "50%", "60%", "70%", "80%", "90%", "99%", "100%",
"obj_allocated", "obj_used", "pages_used",
"pages_per_zspage", "freeable");
for (i = 0; i < ZS_SIZE_CLASSES; i++) {
+
class = pool->size_class[i];
if (class->index != i)
continue;
- spin_lock(&class->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);
+ spin_lock(&pool->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));
+ }
+
+ obj_allocated = zs_stat_get(class, ZS_OBJS_ALLOCATED);
+ obj_used = zs_stat_get(class, ZS_OBJS_INUSE);
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 *
class->pages_per_zspage;
- seq_printf(s, " %5u %5u %11lu %12lu %13lu"
- " %10lu %10lu %16d %8lu\n",
- i, class->size, class_almost_full, class_almost_empty,
- obj_allocated, obj_used, pages_used,
- class->pages_per_zspage, freeable);
+ seq_printf(s, "%13lu %10lu %10lu %16d %8lu\n",
+ obj_allocated, obj_used, pages_used,
+ class->pages_per_zspage, freeable);
- total_class_almost_full += class_almost_full;
- total_class_almost_empty += class_almost_empty;
total_objs += obj_allocated;
total_used_objs += obj_used;
total_pages += pages_used;
}
seq_puts(s, "\n");
- seq_printf(s, " %5s %5s %11lu %12lu %13lu %10lu %10lu %16s %8lu\n",
- "Total", "", total_class_almost_full,
- total_class_almost_empty, total_objs,
- total_used_objs, total_pages, "", total_freeable);
+ seq_printf(s, " %5s %5s ", "Total", "");
+
+ for (fg = ZS_INUSE_RATIO_10; fg < NR_FULLNESS_GROUPS; fg++)
+ seq_printf(s, "%9lu ", inuse_totals[fg]);
+
+ seq_printf(s, "%13lu %10lu %10lu %16s %8lu\n",
+ total_objs, total_used_objs, total_pages, "",
+ total_freeable);
return 0;
}
/*
* For each size class, zspages are divided into different groups
- * depending on how "full" they are. This was done so that we could
- * easily find empty or nearly empty zspages when we try to shrink
- * the pool (not yet implemented). This function returns fullness
+ * depending on their usage ratio. This function returns fullness
* status of the given page.
*/
-static enum fullness_group get_fullness_group(struct size_class *class,
- struct zspage *zspage)
+static int get_fullness_group(struct size_class *class, struct zspage *zspage)
{
- int inuse, objs_per_zspage;
- enum fullness_group fg;
+ int inuse, objs_per_zspage, ratio;
inuse = get_zspage_inuse(zspage);
objs_per_zspage = class->objs_per_zspage;
if (inuse == 0)
- fg = ZS_EMPTY;
- else if (inuse == objs_per_zspage)
- fg = ZS_FULL;
- else if (inuse <= 3 * objs_per_zspage / fullness_threshold_frac)
- fg = ZS_ALMOST_EMPTY;
- else
- fg = ZS_ALMOST_FULL;
+ return ZS_INUSE_RATIO_0;
+ if (inuse == objs_per_zspage)
+ return ZS_INUSE_RATIO_100;
- return fg;
+ ratio = 100 * inuse / objs_per_zspage;
+ /*
+ * Take integer division into consideration: a page with one inuse
+ * object out of 127 possible, will end up having 0 usage ratio,
+ * which is wrong as it belongs in ZS_INUSE_RATIO_10 fullness group.
+ */
+ return ratio / 10 + 1;
}
/*
*/
static void insert_zspage(struct size_class *class,
struct zspage *zspage,
- enum fullness_group fullness)
+ int fullness)
{
- struct zspage *head;
-
class_stat_inc(class, fullness, 1);
- head = list_first_entry_or_null(&class->fullness_list[fullness],
- struct zspage, list);
- /*
- * We want to see more ZS_FULL pages and less almost empty/full.
- * Put pages with higher ->inuse first.
- */
- if (head && get_zspage_inuse(zspage) < get_zspage_inuse(head))
- list_add(&zspage->list, &head->list);
- else
- list_add(&zspage->list, &class->fullness_list[fullness]);
+ list_add(&zspage->list, &class->fullness_list[fullness]);
+ zspage->fullness = fullness;
}
/*
* This function removes the given zspage from the freelist identified
* by <class, fullness_group>.
*/
-static void remove_zspage(struct size_class *class,
- struct zspage *zspage,
- enum fullness_group fullness)
+static void remove_zspage(struct size_class *class, struct zspage *zspage)
{
+ int fullness = zspage->fullness;
+
VM_BUG_ON(list_empty(&class->fullness_list[fullness]));
list_del_init(&zspage->list);
/*
* Each size class maintains zspages in different fullness groups depending
* on the number of live objects they contain. When allocating or freeing
- * objects, the fullness status of the page can change, say, from ALMOST_FULL
- * to ALMOST_EMPTY when freeing an object. This function checks if such
- * a status change has occurred for the given page and accordingly moves the
- * page from the freelist of the old fullness group to that of the new
- * fullness group.
+ * objects, the fullness status of the page can change, for instance, from
+ * INUSE_RATIO_80 to INUSE_RATIO_70 when freeing an object. This function
+ * checks if such a status change has occurred for the given page and
+ * accordingly moves the page from the list of the old fullness group to that
+ * of the new fullness group.
*/
-static enum fullness_group fix_fullness_group(struct size_class *class,
- struct zspage *zspage)
+static int fix_fullness_group(struct size_class *class, struct zspage *zspage)
{
- int class_idx;
- enum fullness_group currfg, newfg;
+ int newfg;
- get_zspage_mapping(zspage, &class_idx, &currfg);
newfg = get_fullness_group(class, zspage);
- if (newfg == currfg)
+ if (newfg == zspage->fullness)
goto out;
- remove_zspage(class, zspage, currfg);
+ remove_zspage(class, zspage);
insert_zspage(class, zspage, newfg);
- set_zspage_mapping(zspage, class_idx, newfg);
out:
return newfg;
}
-/*
- * We have to decide on how many pages to link together
- * to form a zspage for each size class. This is important
- * to reduce wastage due to unusable space left at end of
- * each zspage which is given as:
- * wastage = Zp % class_size
- * usage = Zp - wastage
- * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ...
- *
- * For example, for size class of 3/8 * PAGE_SIZE, we should
- * link together 3 PAGE_SIZE sized pages to form a zspage
- * since then we can perfectly fit in 8 such objects.
- */
-static int get_pages_per_zspage(int class_size)
-{
- int i, max_usedpc = 0;
- /* zspage order which gives maximum used size per KB */
- int max_usedpc_order = 1;
-
- for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
- int zspage_size;
- int waste, usedpc;
-
- zspage_size = i * PAGE_SIZE;
- waste = zspage_size % class_size;
- usedpc = (zspage_size - waste) * 100 / zspage_size;
-
- if (usedpc > max_usedpc) {
- max_usedpc = usedpc;
- max_usedpc_order = i;
- }
- }
-
- return max_usedpc_order;
-}
-
static struct zspage *get_zspage(struct page *page)
{
struct zspage *zspage = (struct zspage *)page_private(page);
static void obj_to_location(unsigned long obj, struct page **page,
unsigned int *obj_idx)
{
- obj >>= OBJ_TAG_BITS;
*page = pfn_to_page(obj >> OBJ_INDEX_BITS);
*obj_idx = (obj & OBJ_INDEX_MASK);
}
static void obj_to_page(unsigned long obj, struct page **page)
{
- obj >>= OBJ_TAG_BITS;
*page = pfn_to_page(obj >> OBJ_INDEX_BITS);
}
obj = page_to_pfn(page) << OBJ_INDEX_BITS;
obj |= obj_idx & OBJ_INDEX_MASK;
- obj <<= OBJ_TAG_BITS;
return obj;
}
return *(unsigned long *)handle;
}
-static bool obj_allocated(struct page *page, void *obj, unsigned long *phandle)
+static inline bool obj_allocated(struct page *page, void *obj,
+ unsigned long *phandle)
{
unsigned long handle;
struct zspage *zspage = get_zspage(page);
if (!(handle & OBJ_ALLOCATED_TAG))
return false;
- *phandle = handle & ~OBJ_ALLOCATED_TAG;
+ /* Clear all tags before returning the handle */
+ *phandle = handle & ~OBJ_TAG_MASK;
return true;
}
struct zspage *zspage)
{
struct page *page, *next;
- enum fullness_group fg;
- unsigned int class_idx;
- 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);
+ VM_BUG_ON(zspage->fullness != ZS_INUSE_RATIO_0);
next = page = get_first_page(zspage);
do {
cache_free_zspage(pool, zspage);
- class_stat_dec(class, OBJ_ALLOCATED, class->objs_per_zspage);
- atomic_long_sub(class->pages_per_zspage,
- &pool->pages_allocated);
+ class_stat_dec(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage);
+ atomic_long_sub(class->pages_per_zspage, &pool->pages_allocated);
}
static void free_zspage(struct zs_pool *pool, struct size_class *class,
return;
}
- remove_zspage(class, zspage, ZS_EMPTY);
+ remove_zspage(class, zspage);
__free_zspage(pool, class, zspage);
}
create_page_chain(class, zspage, pages);
init_zspage(class, zspage);
zspage->pool = pool;
+ zspage->class = class->index;
return zspage;
}
int i;
struct zspage *zspage;
- for (i = ZS_ALMOST_FULL; i >= ZS_EMPTY; i--) {
+ for (i = ZS_INUSE_RATIO_99; i >= ZS_INUSE_RATIO_0; i--) {
zspage = list_first_entry_or_null(&class->fullness_list[i],
- struct zspage, list);
+ struct zspage, list);
if (zspage)
break;
}
return get_zspage_inuse(zspage) == class->objs_per_zspage;
}
+static bool zspage_empty(struct zspage *zspage)
+{
+ return get_zspage_inuse(zspage) == 0;
+}
+
+/**
+ * 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);
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);
/*
- * migration cannot move any zpages in this zspage. Here, class->lock
+ * 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;
+ off = offset_in_page(class->size * obj_idx);
local_lock(&zs_map_area.lock);
area = this_cpu_ptr(&zs_map_area);
obj_to_location(obj, &page, &obj_idx);
zspage = get_zspage(page);
class = zspage_class(pool, zspage);
- off = (class->size * obj_idx) & ~PAGE_MASK;
+ off = offset_in_page(class->size * obj_idx);
area = this_cpu_ptr(&zs_map_area);
if (off + class->size <= PAGE_SIZE)
offset = obj * class->size;
nr_page = offset >> PAGE_SHIFT;
- m_offset = offset & ~PAGE_MASK;
+ m_offset = offset_in_page(offset);
m_page = get_first_page(zspage);
for (i = 0; i < nr_page; i++)
{
unsigned long handle, obj;
struct size_class *class;
- enum fullness_group newfg;
+ int newfg;
struct zspage *zspage;
- if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
+ if (unlikely(!size))
return (unsigned long)ERR_PTR(-EINVAL);
+ if (unlikely(size > ZS_MAX_ALLOC_SIZE))
+ return (unsigned long)ERR_PTR(-ENOSPC);
+
handle = cache_alloc_handle(pool, gfp);
if (!handle)
return (unsigned long)ERR_PTR(-ENOMEM);
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);
/* Now move the zspage to another fullness group, if required */
fix_fullness_group(class, zspage);
record_obj(handle, obj);
- class_stat_inc(class, OBJ_USED, 1);
- spin_unlock(&class->lock);
+ class_stat_inc(class, ZS_OBJS_INUSE, 1);
- return handle;
+ goto out;
}
- spin_unlock(&class->lock);
+ spin_unlock(&pool->lock);
zspage = alloc_zspage(pool, class, gfp);
if (!zspage) {
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);
- set_zspage_mapping(zspage, class->index, newfg);
record_obj(handle, obj);
- atomic_long_add(class->pages_per_zspage,
- &pool->pages_allocated);
- class_stat_inc(class, OBJ_ALLOCATED, class->objs_per_zspage);
- class_stat_inc(class, OBJ_USED, 1);
+ 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);
/* We completely set up zspage so mark them as movable */
SetZsPageMovable(pool, zspage);
- spin_unlock(&class->lock);
+out:
+ spin_unlock(&pool->lock);
return handle;
}
void *vaddr;
obj_to_location(obj, &f_page, &f_objidx);
- f_offset = (class_size * f_objidx) & ~PAGE_MASK;
+ f_offset = offset_in_page(class_size * f_objidx);
zspage = get_zspage(f_page);
vaddr = kmap_atomic(f_page);
+ link = (struct link_free *)(vaddr + f_offset);
/* Insert this object in containing zspage's freelist */
- link = (struct link_free *)(vaddr + f_offset);
if (likely(!ZsHugePage(zspage)))
link->next = get_freeobj(zspage) << OBJ_TAG_BITS;
else
f_page->index = 0;
- kunmap_atomic(vaddr);
set_freeobj(zspage, f_objidx);
+
+ kunmap_atomic(vaddr);
mod_zspage_inuse(zspage, -1);
}
struct page *f_page;
unsigned long obj;
struct size_class *class;
- enum fullness_group fullness;
+ int fullness;
- if (unlikely(!handle))
+ if (IS_ERR_OR_NULL((void *)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);
+ class_stat_dec(class, ZS_OBJS_INUSE, 1);
obj_free(class->size, obj);
- class_stat_dec(class, OBJ_USED, 1);
+
fullness = fix_fullness_group(class, zspage);
- if (fullness != ZS_EMPTY)
- goto out;
+ if (fullness == ZS_INUSE_RATIO_0)
+ 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);
obj_to_location(src, &s_page, &s_objidx);
obj_to_location(dst, &d_page, &d_objidx);
- s_off = (class->size * s_objidx) & ~PAGE_MASK;
- d_off = (class->size * d_objidx) & ~PAGE_MASK;
+ s_off = offset_in_page(class->size * s_objidx);
+ d_off = offset_in_page(class->size * d_objidx);
if (s_off + class->size > PAGE_SIZE)
s_size = PAGE_SIZE - s_off;
d_off += size;
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
+ * Documentation/mm/highmem.rst.
+ */
if (s_off >= PAGE_SIZE) {
kunmap_atomic(d_addr);
kunmap_atomic(s_addr);
* return handle.
*/
static unsigned long find_alloced_obj(struct size_class *class,
- struct page *page, int *obj_idx)
+ struct page *page, int *obj_idx)
{
- int offset = 0;
+ unsigned int offset;
int index = *obj_idx;
unsigned long handle = 0;
void *addr = kmap_atomic(page);
return handle;
}
-struct zs_compact_control {
- /* Source spage for migration which could be a subpage of zspage */
- struct page *s_page;
- /* Destination page for migration which should be a first page
- * of zspage. */
- struct page *d_page;
- /* Starting object index within @s_page which used for live object
- * in the subpage. */
- int obj_idx;
-};
-
-static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
- struct zs_compact_control *cc)
+static void migrate_zspage(struct zs_pool *pool, struct zspage *src_zspage,
+ struct zspage *dst_zspage)
{
unsigned long used_obj, free_obj;
unsigned long handle;
- struct page *s_page = cc->s_page;
- struct page *d_page = cc->d_page;
- int obj_idx = cc->obj_idx;
- int ret = 0;
+ int obj_idx = 0;
+ struct page *s_page = get_first_page(src_zspage);
+ struct size_class *class = pool->size_class[src_zspage->class];
while (1) {
handle = find_alloced_obj(class, s_page, &obj_idx);
continue;
}
- /* Stop if there is no more space */
- if (zspage_full(class, get_zspage(d_page))) {
- ret = -ENOMEM;
- break;
- }
-
used_obj = handle_to_obj(handle);
- free_obj = obj_malloc(pool, get_zspage(d_page), handle);
+ 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);
- }
- /* Remember last position in this iteration */
- cc->s_page = s_page;
- cc->obj_idx = obj_idx;
+ /* Stop if there is no more space */
+ if (zspage_full(class, dst_zspage))
+ break;
- return ret;
+ /* Stop if there are no more objects to migrate */
+ if (zspage_empty(src_zspage))
+ break;
+ }
}
-static struct zspage *isolate_zspage(struct size_class *class, bool source)
+static struct zspage *isolate_src_zspage(struct size_class *class)
{
- int i;
struct zspage *zspage;
- enum fullness_group fg[2] = {ZS_ALMOST_EMPTY, ZS_ALMOST_FULL};
+ int fg;
- if (!source) {
- fg[0] = ZS_ALMOST_FULL;
- fg[1] = ZS_ALMOST_EMPTY;
+ for (fg = ZS_INUSE_RATIO_10; fg <= ZS_INUSE_RATIO_99; fg++) {
+ zspage = list_first_entry_or_null(&class->fullness_list[fg],
+ struct zspage, list);
+ if (zspage) {
+ remove_zspage(class, zspage);
+ return zspage;
+ }
}
- for (i = 0; i < 2; i++) {
- zspage = list_first_entry_or_null(&class->fullness_list[fg[i]],
- struct zspage, list);
+ return zspage;
+}
+
+static struct zspage *isolate_dst_zspage(struct size_class *class)
+{
+ struct zspage *zspage;
+ int fg;
+
+ for (fg = ZS_INUSE_RATIO_99; fg >= ZS_INUSE_RATIO_10; fg--) {
+ zspage = list_first_entry_or_null(&class->fullness_list[fg],
+ struct zspage, list);
if (zspage) {
- remove_zspage(class, zspage, fg[i]);
+ remove_zspage(class, zspage);
return zspage;
}
}
* @class: destination class
* @zspage: target page
*
- * Return @zspage's fullness_group
+ * Return @zspage's fullness status
*/
-static enum fullness_group putback_zspage(struct size_class *class,
- struct zspage *zspage)
+static int putback_zspage(struct size_class *class, struct zspage *zspage)
{
- enum fullness_group fullness;
+ int fullness;
fullness = get_fullness_group(class, zspage);
insert_zspage(class, zspage, fullness);
- set_zspage_mapping(zspage, class->index, fullness);
return fullness;
}
}
migrate_read_unlock(zspage);
}
+#endif /* CONFIG_COMPACTION */
static void migrate_lock_init(struct zspage *zspage)
{
write_lock(&zspage->lock);
}
-static void migrate_write_lock_nested(struct zspage *zspage)
-{
- write_lock_nested(&zspage->lock, SINGLE_DEPTH_NESTING);
-}
-
static void migrate_write_unlock(struct zspage *zspage)
{
write_unlock(&zspage->lock);
}
-/* Number of isolated subpage for *page migration* in this zspage */
-static void inc_zspage_isolation(struct zspage *zspage)
-{
- zspage->isolated++;
-}
-
-static void dec_zspage_isolation(struct zspage *zspage)
-{
- VM_BUG_ON(zspage->isolated == 0);
- zspage->isolated--;
-}
+#ifdef CONFIG_COMPACTION
static const struct movable_operations zsmalloc_mops;
static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
{
- struct zspage *zspage;
-
/*
* Page is locked so zspage couldn't be destroyed. For detail, look at
* lock_zspage in free_zspage.
*/
- VM_BUG_ON_PAGE(!PageMovable(page), page);
VM_BUG_ON_PAGE(PageIsolated(page), page);
- zspage = get_zspage(page);
- migrate_write_lock(zspage);
- inc_zspage_isolation(zspage);
- migrate_write_unlock(zspage);
-
return true;
}
struct zspage *zspage;
struct page *dummy;
void *s_addr, *d_addr, *addr;
- int offset;
+ unsigned int offset;
unsigned long handle;
unsigned long old_obj, new_obj;
unsigned int obj_idx;
if (mode == MIGRATE_SYNC_NO_COPY)
return -EINVAL;
- VM_BUG_ON_PAGE(!PageMovable(page), page);
VM_BUG_ON_PAGE(!PageIsolated(page), page);
/* The page is locked, so this pointer must remain valid */
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);
* Here, any user cannot access all objects in the zspage so let's move.
*/
d_addr = kmap_atomic(newpage);
- memcpy(d_addr, s_addr, PAGE_SIZE);
+ copy_page(d_addr, s_addr);
kunmap_atomic(d_addr);
for (addr = s_addr + offset; addr < s_addr + PAGE_SIZE;
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);
- dec_zspage_isolation(zspage);
+ spin_unlock(&pool->lock);
migrate_write_unlock(zspage);
get_page(newpage);
static void zs_page_putback(struct page *page)
{
- struct zspage *zspage;
-
- VM_BUG_ON_PAGE(!PageMovable(page), page);
VM_BUG_ON_PAGE(!PageIsolated(page), page);
-
- zspage = get_zspage(page);
- migrate_write_lock(zspage);
- dec_zspage_isolation(zspage);
- migrate_write_unlock(zspage);
}
static const struct movable_operations zsmalloc_mops = {
{
int i;
struct size_class *class;
- unsigned int class_idx;
- enum fullness_group fullness;
struct zspage *zspage, *tmp;
LIST_HEAD(free_pages);
struct zs_pool *pool = container_of(work, struct zs_pool,
if (class->index != i)
continue;
- spin_lock(&class->lock);
- list_splice_init(&class->fullness_list[ZS_EMPTY], &free_pages);
- spin_unlock(&class->lock);
+ spin_lock(&pool->lock);
+ list_splice_init(&class->fullness_list[ZS_INUSE_RATIO_0],
+ &free_pages);
+ spin_unlock(&pool->lock);
}
list_for_each_entry_safe(zspage, tmp, &free_pages, list) {
list_del(&zspage->list);
lock_zspage(zspage);
- 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);
+ class = zspage_class(pool, zspage);
__free_zspage(pool, class, zspage);
- spin_unlock(&class->lock);
+ spin_unlock(&pool->lock);
}
};
static unsigned long zs_can_compact(struct size_class *class)
{
unsigned long obj_wasted;
- unsigned long obj_allocated = zs_stat_get(class, OBJ_ALLOCATED);
- unsigned long obj_used = zs_stat_get(class, OBJ_USED);
+ unsigned long obj_allocated = zs_stat_get(class, ZS_OBJS_ALLOCATED);
+ unsigned long obj_used = zs_stat_get(class, ZS_OBJS_INUSE);
if (obj_allocated <= obj_used)
return 0;
static unsigned long __zs_compact(struct zs_pool *pool,
struct size_class *class)
{
- struct zs_compact_control cc;
- struct zspage *src_zspage;
+ struct zspage *src_zspage = NULL;
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);
- while ((src_zspage = isolate_zspage(class, true))) {
- /* protect someone accessing the zspage(i.e., zs_map_object) */
- migrate_write_lock(src_zspage);
-
- if (!zs_can_compact(class))
- break;
-
- cc.obj_idx = 0;
- cc.s_page = get_first_page(src_zspage);
-
- while ((dst_zspage = isolate_zspage(class, false))) {
- migrate_write_lock_nested(dst_zspage);
-
- cc.d_page = get_first_page(dst_zspage);
- /*
- * If there is no more space in dst_page, resched
- * and see if anyone had allocated another zspage.
- */
- if (!migrate_zspage(pool, class, &cc))
- break;
+ /*
+ * protect the race between zpage migration and zs_free
+ * as well as zpage allocation/free
+ */
+ spin_lock(&pool->lock);
+ while (zs_can_compact(class)) {
+ int fg;
- putback_zspage(class, dst_zspage);
- migrate_write_unlock(dst_zspage);
- dst_zspage = NULL;
- if (rwlock_is_contended(&pool->migrate_lock))
+ if (!dst_zspage) {
+ dst_zspage = isolate_dst_zspage(class);
+ if (!dst_zspage)
break;
}
- /* Stop if we couldn't find slot */
- if (dst_zspage == NULL)
+ src_zspage = isolate_src_zspage(class);
+ if (!src_zspage)
break;
- putback_zspage(class, dst_zspage);
- migrate_write_unlock(dst_zspage);
+ migrate_write_lock(src_zspage);
+ migrate_zspage(pool, src_zspage, dst_zspage);
+ migrate_write_unlock(src_zspage);
- if (putback_zspage(class, src_zspage) == ZS_EMPTY) {
- migrate_write_unlock(src_zspage);
+ fg = putback_zspage(class, src_zspage);
+ if (fg == ZS_INUSE_RATIO_0) {
free_zspage(pool, class, src_zspage);
pages_freed += class->pages_per_zspage;
- } else
- migrate_write_unlock(src_zspage);
- spin_unlock(&class->lock);
- write_unlock(&pool->migrate_lock);
- cond_resched();
- write_lock(&pool->migrate_lock);
- spin_lock(&class->lock);
+ }
+ src_zspage = NULL;
+
+ if (get_fullness_group(class, dst_zspage) == ZS_INUSE_RATIO_100
+ || spin_is_contended(&pool->lock)) {
+ putback_zspage(class, dst_zspage);
+ dst_zspage = NULL;
+
+ spin_unlock(&pool->lock);
+ cond_resched();
+ spin_lock(&pool->lock);
+ }
}
- if (src_zspage) {
+ if (src_zspage)
putback_zspage(class, src_zspage);
- migrate_write_unlock(src_zspage);
- }
- spin_unlock(&class->lock);
- write_unlock(&pool->migrate_lock);
+ if (dst_zspage)
+ putback_zspage(class, dst_zspage);
+
+ spin_unlock(&pool->lock);
return pages_freed;
}
struct size_class *class;
unsigned long pages_freed = 0;
+ /*
+ * Pool compaction is performed under pool->lock so it is basically
+ * single-threaded. Having more than one thread in __zs_compact()
+ * will increase pool->lock contention, which will impact other
+ * zsmalloc operations that need pool->lock.
+ */
+ if (atomic_xchg(&pool->compaction_in_progress, 1))
+ return 0;
+
for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
class = pool->size_class[i];
- if (!class)
- continue;
if (class->index != i)
continue;
pages_freed += __zs_compact(pool, class);
}
atomic_long_add(pages_freed, &pool->stats.pages_compacted);
+ atomic_set(&pool->compaction_in_progress, 0);
return pages_freed;
}
struct shrink_control *sc)
{
unsigned long pages_freed;
- struct zs_pool *pool = container_of(shrinker, struct zs_pool,
- shrinker);
+ struct zs_pool *pool = shrinker->private_data;
/*
* Compact classes and calculate compaction delta.
int i;
struct size_class *class;
unsigned long pages_to_free = 0;
- struct zs_pool *pool = container_of(shrinker, struct zs_pool,
- shrinker);
+ struct zs_pool *pool = shrinker->private_data;
for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
class = pool->size_class[i];
- if (!class)
- continue;
if (class->index != i)
continue;
static void zs_unregister_shrinker(struct zs_pool *pool)
{
- unregister_shrinker(&pool->shrinker);
+ shrinker_free(pool->shrinker);
}
static int zs_register_shrinker(struct zs_pool *pool)
{
- pool->shrinker.scan_objects = zs_shrinker_scan;
- pool->shrinker.count_objects = zs_shrinker_count;
- pool->shrinker.batch = 0;
- pool->shrinker.seeks = DEFAULT_SEEKS;
+ pool->shrinker = shrinker_alloc(0, "mm-zspool:%s", pool->name);
+ if (!pool->shrinker)
+ return -ENOMEM;
+
+ pool->shrinker->scan_objects = zs_shrinker_scan;
+ pool->shrinker->count_objects = zs_shrinker_count;
+ pool->shrinker->batch = 0;
+ pool->shrinker->private_data = pool;
- return register_shrinker(&pool->shrinker, "mm-zspool:%s",
- pool->name);
+ shrinker_register(pool->shrinker);
+
+ return 0;
+}
+
+static int calculate_zspage_chain_size(int class_size)
+{
+ int i, min_waste = INT_MAX;
+ int chain_size = 1;
+
+ if (is_power_of_2(class_size))
+ return chain_size;
+
+ for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
+ int waste;
+
+ waste = (i * PAGE_SIZE) % class_size;
+ if (waste < min_waste) {
+ min_waste = waste;
+ chain_size = i;
+ }
+ }
+
+ return chain_size;
}
/**
return NULL;
init_deferred_free(pool);
- rwlock_init(&pool->migrate_lock);
+ spin_lock_init(&pool->lock);
+ atomic_set(&pool->compaction_in_progress, 0);
pool->name = kstrdup(name, GFP_KERNEL);
if (!pool->name)
int pages_per_zspage;
int objs_per_zspage;
struct size_class *class;
- int fullness = 0;
+ int fullness;
size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
if (size > ZS_MAX_ALLOC_SIZE)
size = ZS_MAX_ALLOC_SIZE;
- pages_per_zspage = get_pages_per_zspage(size);
+ pages_per_zspage = calculate_zspage_chain_size(size);
objs_per_zspage = pages_per_zspage * PAGE_SIZE / size;
/*
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++)
+
+ fullness = ZS_INUSE_RATIO_0;
+ while (fullness < NR_FULLNESS_GROUPS) {
INIT_LIST_HEAD(&class->fullness_list[fullness]);
+ fullness++;
+ }
prev_class = class;
}
if (class->index != i)
continue;
- for (fg = ZS_EMPTY; fg < NR_ZS_FULLNESS; fg++) {
- if (!list_empty(&class->fullness_list[fg])) {
- pr_info("Freeing non-empty class with size %db, fullness group %d\n",
- class->size, fg);
- }
+ for (fg = ZS_INUSE_RATIO_0; fg < NR_FULLNESS_GROUPS; fg++) {
+ if (list_empty(&class->fullness_list[fg]))
+ continue;
+
+ pr_err("Class-%d fullness group %d is not empty\n",
+ class->size, fg);
}
kfree(class);
}