*
* Usage of struct page fields:
* page->private: points to zspage
- * page->index: offset of the first object starting in this page.
- * For the first page, this is always 0, so we use this field
- * to store handle for huge object.
- * page->next: links together all component pages of a zspage
+ * page->freelist(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->units: first object offset in a subpage of zspage
*
* Usage of struct page flags:
* PG_private: identifies the first component page
* PG_private2: identifies the last component page
+ * PG_owner_priv_1: indentifies the huge component page
*
*/
#include <linux/debugfs.h>
#include <linux/zsmalloc.h>
#include <linux/zpool.h>
+#include <linux/mount.h>
+#include <linux/migrate.h>
+#include <linux/pagemap.h>
+
+#define ZSPAGE_MAGIC 0x58
/*
* This must be power of 2 and greater than of equal to sizeof(link_free).
*/
#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> CLASS_BITS)
-/*
- * We do not maintain any list for completely empty or full pages
- */
enum fullness_group {
- ZS_ALMOST_FULL,
- ZS_ALMOST_EMPTY,
ZS_EMPTY,
- ZS_FULL
+ ZS_ALMOST_EMPTY,
+ ZS_ALMOST_FULL,
+ ZS_FULL,
+ NR_ZS_FULLNESS,
};
enum zs_stat_type {
+ CLASS_EMPTY,
+ CLASS_ALMOST_EMPTY,
+ CLASS_ALMOST_FULL,
+ CLASS_FULL,
OBJ_ALLOCATED,
OBJ_USED,
- CLASS_ALMOST_FULL,
- CLASS_ALMOST_EMPTY,
+ NR_ZS_STAT_TYPE,
};
-#ifdef CONFIG_ZSMALLOC_STAT
-#define NR_ZS_STAT_TYPE (CLASS_ALMOST_EMPTY + 1)
-#else
-#define NR_ZS_STAT_TYPE (OBJ_USED + 1)
-#endif
-
struct zs_size_stat {
unsigned long objs[NR_ZS_STAT_TYPE];
};
static struct dentry *zs_stat_root;
#endif
+#ifdef CONFIG_COMPACTION
+static struct vfsmount *zsmalloc_mnt;
+#endif
+
/*
* number of size_classes
*/
struct size_class {
spinlock_t lock;
- struct list_head fullness_list[2];
+ struct list_head fullness_list[NR_ZS_FULLNESS];
/*
* Size of objects stored in this class. Must be multiple
* of ZS_ALIGN.
*/
int size;
int objs_per_zspage;
- unsigned int index;
-
- struct zs_size_stat stats;
-
/* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
int pages_per_zspage;
- /* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */
- bool huge;
+
+ unsigned int index;
+ struct zs_size_stat stats;
};
+/* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */
+static void SetPageHugeObject(struct page *page)
+{
+ SetPageOwnerPriv1(page);
+}
+
+static void ClearPageHugeObject(struct page *page)
+{
+ ClearPageOwnerPriv1(page);
+}
+
+static int PageHugeObject(struct page *page)
+{
+ return PageOwnerPriv1(page);
+}
+
/*
* Placed within free objects to form a singly linked list.
* For every zspage, zspage->freeobj gives head of this list.
#ifdef CONFIG_ZSMALLOC_STAT
struct dentry *stat_dentry;
#endif
+#ifdef CONFIG_COMPACTION
+ struct inode *inode;
+ struct work_struct free_work;
+#endif
};
/*
*/
#define FULLNESS_BITS 2
#define CLASS_BITS 8
+#define ISOLATED_BITS 3
+#define MAGIC_VAL_BITS 8
struct zspage {
struct {
unsigned int fullness:FULLNESS_BITS;
unsigned int class:CLASS_BITS;
+ unsigned int isolated:ISOLATED_BITS;
+ unsigned int magic:MAGIC_VAL_BITS;
};
unsigned int inuse;
unsigned int freeobj;
struct page *first_page;
struct list_head list; /* fullness list */
+#ifdef CONFIG_COMPACTION
+ rwlock_t lock;
+#endif
};
struct mapping_area {
enum zs_mapmode vm_mm; /* mapping mode */
};
+#ifdef CONFIG_COMPACTION
+static int zs_register_migration(struct zs_pool *pool);
+static void zs_unregister_migration(struct zs_pool *pool);
+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 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 int zsmalloc_mount(void) { return 0; }
+static void zsmalloc_unmount(void) {}
+static int zs_register_migration(struct zs_pool *pool) { return 0; }
+static void zs_unregister_migration(struct zs_pool *pool) {}
+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 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) {}
+#endif
+
static int create_cache(struct zs_pool *pool)
{
pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE,
static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp)
{
return (unsigned long)kmem_cache_alloc(pool->handle_cachep,
- gfp & ~__GFP_HIGHMEM);
+ gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
}
static void cache_free_handle(struct zs_pool *pool, unsigned long handle)
static struct zspage *cache_alloc_zspage(struct zs_pool *pool, gfp_t flags)
{
- return kmem_cache_alloc(pool->zspage_cachep, flags & ~__GFP_HIGHMEM);
+ return kmem_cache_alloc(pool->zspage_cachep,
+ flags & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
};
static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage)
MODULE_ALIAS("zpool-zsmalloc");
#endif /* CONFIG_ZPOOL */
-static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage)
-{
- return pages_per_zspage * PAGE_SIZE / size;
-}
-
/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
+static bool is_zspage_isolated(struct zspage *zspage)
+{
+ return zspage->isolated;
+}
+
static int is_first_page(struct page *page)
{
return PagePrivate(page);
}
+/* Protected by class->lock */
static inline int get_zspage_inuse(struct zspage *zspage)
{
return zspage->inuse;
zspage->inuse += val;
}
-static inline int get_first_obj_offset(struct page *page)
+static inline struct page *get_first_page(struct zspage *zspage)
{
- if (is_first_page(page))
- return 0;
+ struct page *first_page = zspage->first_page;
- return page->index;
+ VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
+ return first_page;
}
-static inline void set_first_obj_offset(struct page *page, int offset)
+static inline int get_first_obj_offset(struct page *page)
{
- if (is_first_page(page))
- return;
+ return page->units;
+}
- page->index = offset;
+static inline void set_first_obj_offset(struct page *page, int offset)
+{
+ page->units = offset;
}
static inline unsigned int get_freeobj(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 inline void zs_stat_inc(struct size_class *class,
enum zs_stat_type type, unsigned long cnt)
{
- if (type < NR_ZS_STAT_TYPE)
- class->stats.objs[type] += cnt;
+ class->stats.objs[type] += cnt;
}
static inline void zs_stat_dec(struct size_class *class,
enum zs_stat_type type, unsigned long cnt)
{
- if (type < NR_ZS_STAT_TYPE)
- class->stats.objs[type] -= cnt;
+ class->stats.objs[type] -= cnt;
}
static inline unsigned long zs_stat_get(struct size_class *class,
enum zs_stat_type type)
{
- if (type < NR_ZS_STAT_TYPE)
- return class->stats.objs[type];
- return 0;
+ return class->stats.objs[type];
}
#ifdef CONFIG_ZSMALLOC_STAT
freeable = zs_can_compact(class);
spin_unlock(&class->lock);
- objs_per_zspage = get_maxobj_per_zspage(class->size,
- class->pages_per_zspage);
+ objs_per_zspage = class->objs_per_zspage;
pages_used = obj_allocated / objs_per_zspage *
class->pages_per_zspage;
}
#endif
+
/*
* For each size class, zspages are divided into different groups
* depending on how "full" they are. This was done so that we could
{
struct zspage *head;
- if (fullness >= ZS_EMPTY)
- return;
-
+ zs_stat_inc(class, fullness, 1);
head = list_first_entry_or_null(&class->fullness_list[fullness],
struct zspage, list);
-
- zs_stat_inc(class, fullness == ZS_ALMOST_EMPTY ?
- CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1);
-
/*
* We want to see more ZS_FULL pages and less almost empty/full.
* Put pages with higher ->inuse first.
struct zspage *zspage,
enum fullness_group fullness)
{
- if (fullness >= ZS_EMPTY)
- return;
-
VM_BUG_ON(list_empty(&class->fullness_list[fullness]));
+ VM_BUG_ON(is_zspage_isolated(zspage));
list_del_init(&zspage->list);
- zs_stat_dec(class, fullness == ZS_ALMOST_EMPTY ?
- CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1);
+ zs_stat_dec(class, fullness, 1);
}
/*
if (newfg == currfg)
goto out;
- remove_zspage(class, zspage, currfg);
- insert_zspage(class, zspage, newfg);
+ if (!is_zspage_isolated(zspage)) {
+ remove_zspage(class, zspage, currfg);
+ insert_zspage(class, zspage, newfg);
+ }
+
set_zspage_mapping(zspage, class_idx, newfg);
out:
return max_usedpc_order;
}
-static struct page *get_first_page(struct zspage *zspage)
-{
- return zspage->first_page;
-}
-
static struct zspage *get_zspage(struct page *page)
{
- return (struct zspage *)page->private;
+ struct zspage *zspage = (struct zspage *)page->private;
+
+ BUG_ON(zspage->magic != ZSPAGE_MAGIC);
+ return zspage;
}
static struct page *get_next_page(struct page *page)
{
- return page->next;
+ if (unlikely(PageHugeObject(page)))
+ return NULL;
+
+ return page->freelist;
}
/**
return *(unsigned long *)handle;
}
-static unsigned long obj_to_head(struct size_class *class, struct page *page,
- void *obj)
+static unsigned long obj_to_head(struct page *page, void *obj)
{
- if (class->huge) {
+ if (unlikely(PageHugeObject(page))) {
VM_BUG_ON_PAGE(!is_first_page(page), page);
return page->index;
} else
return *(unsigned long *)obj;
}
+static inline int testpin_tag(unsigned long handle)
+{
+ return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle);
+}
+
static inline int trypin_tag(unsigned long handle)
{
return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle);
static void reset_page(struct page *page)
{
- clear_bit(PG_private, &page->flags);
- clear_bit(PG_private_2, &page->flags);
+ __ClearPageMovable(page);
+ ClearPagePrivate(page);
+ ClearPagePrivate2(page);
set_page_private(page, 0);
- page->index = 0;
+ page_mapcount_reset(page);
+ ClearPageHugeObject(page);
+ page->freelist = NULL;
}
-static void free_zspage(struct zs_pool *pool, struct zspage *zspage)
+/*
+ * To prevent zspage destroy during migration, zspage freeing should
+ * hold locks of all pages in the zspage.
+ */
+void lock_zspage(struct zspage *zspage)
+{
+ struct page *page = get_first_page(zspage);
+
+ do {
+ lock_page(page);
+ } while ((page = get_next_page(page)) != NULL);
+}
+
+int trylock_zspage(struct zspage *zspage)
+{
+ struct page *cursor, *fail;
+
+ for (cursor = get_first_page(zspage); cursor != NULL; cursor =
+ get_next_page(cursor)) {
+ if (!trylock_page(cursor)) {
+ fail = cursor;
+ goto unlock;
+ }
+ }
+
+ return 1;
+unlock:
+ for (cursor = get_first_page(zspage); cursor != fail; cursor =
+ get_next_page(cursor))
+ unlock_page(cursor);
+
+ return 0;
+}
+
+static void __free_zspage(struct zs_pool *pool, struct size_class *class,
+ 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);
VM_BUG_ON(get_zspage_inuse(zspage));
+ VM_BUG_ON(fg != ZS_EMPTY);
- next = page = zspage->first_page;
+ next = page = get_first_page(zspage);
do {
- next = page->next;
+ 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);
cache_free_zspage(pool, zspage);
+
+ zs_stat_dec(class, OBJ_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,
+ struct zspage *zspage)
+{
+ VM_BUG_ON(get_zspage_inuse(zspage));
+ VM_BUG_ON(list_empty(&zspage->list));
+
+ if (!trylock_zspage(zspage)) {
+ kick_deferred_free(pool);
+ return;
+ }
+
+ remove_zspage(class, zspage, ZS_EMPTY);
+ __free_zspage(pool, class, zspage);
}
/* Initialize a newly allocated zspage */
{
unsigned int freeobj = 1;
unsigned long off = 0;
- struct page *page = zspage->first_page;
+ struct page *page = get_first_page(zspage);
while (page) {
struct page *next_page;
link = (struct link_free *)vaddr + off / sizeof(*link);
while ((off += class->size) < PAGE_SIZE) {
- link->next = freeobj++ << OBJ_ALLOCATED_TAG;
+ link->next = freeobj++ << OBJ_TAG_BITS;
link += class->size / sizeof(*link);
}
*/
next_page = get_next_page(page);
if (next_page) {
- link->next = freeobj++ << OBJ_ALLOCATED_TAG;
+ link->next = freeobj++ << OBJ_TAG_BITS;
} else {
/*
- * Reset OBJ_ALLOCATED_TAG bit to last link to tell
+ * Reset OBJ_TAG_BITS bit to last link to tell
* whether it's allocated object or not.
*/
- link->next = -1 << OBJ_ALLOCATED_TAG;
+ link->next = -1 << OBJ_TAG_BITS;
}
kunmap_atomic(vaddr);
page = next_page;
set_freeobj(zspage, 0);
}
-static void create_page_chain(struct zspage *zspage, struct page *pages[],
- int nr_pages)
+static void create_page_chain(struct size_class *class, struct zspage *zspage,
+ struct page *pages[])
{
int i;
struct page *page;
struct page *prev_page = NULL;
+ int nr_pages = class->pages_per_zspage;
/*
* Allocate individual pages and link them together as:
- * 1. all pages are linked together using page->next
+ * 1. all pages are linked together using page->freelist
* 2. each sub-page point to zspage using page->private
*
* we set PG_private to identify the first page (i.e. no other sub-page
for (i = 0; i < nr_pages; i++) {
page = pages[i];
set_page_private(page, (unsigned long)zspage);
+ page->freelist = NULL;
if (i == 0) {
zspage->first_page = page;
SetPagePrivate(page);
+ if (unlikely(class->objs_per_zspage == 1 &&
+ class->pages_per_zspage == 1))
+ SetPageHugeObject(page);
} else {
- prev_page->next = page;
+ prev_page->freelist = page;
}
- if (i == nr_pages - 1) {
+ if (i == nr_pages - 1)
SetPagePrivate2(page);
- page->next = NULL;
- }
prev_page = page;
}
}
return NULL;
memset(zspage, 0, sizeof(struct zspage));
+ zspage->magic = ZSPAGE_MAGIC;
+ migrate_lock_init(zspage);
for (i = 0; i < class->pages_per_zspage; i++) {
struct page *page;
page = alloc_page(gfp);
if (!page) {
- while (--i >= 0)
+ while (--i >= 0) {
+ dec_zone_page_state(pages[i], NR_ZSPAGES);
__free_page(pages[i]);
+ }
cache_free_zspage(pool, zspage);
return NULL;
}
+
+ inc_zone_page_state(page, NR_ZSPAGES);
pages[i] = page;
}
- create_page_chain(zspage, pages, class->pages_per_zspage);
+ create_page_chain(class, zspage, pages);
init_zspage(class, zspage);
return zspage;
int i;
struct zspage *zspage;
- for (i = ZS_ALMOST_FULL; i <= ZS_ALMOST_EMPTY; i++) {
+ for (i = ZS_ALMOST_FULL; i >= ZS_EMPTY; i--) {
zspage = list_first_entry_or_null(&class->fullness_list[i],
struct zspage, list);
if (zspage)
cpu_notifier_register_done();
}
-static void init_zs_size_classes(void)
+static void __init init_zs_size_classes(void)
{
int nr;
zs_size_classes = nr;
}
-static bool can_merge(struct size_class *prev, int size, int pages_per_zspage)
+static bool can_merge(struct size_class *prev, int pages_per_zspage,
+ int objs_per_zspage)
{
- if (prev->pages_per_zspage != pages_per_zspage)
- return false;
+ if (prev->pages_per_zspage == pages_per_zspage &&
+ prev->objs_per_zspage == objs_per_zspage)
+ return true;
- if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage)
- != get_maxobj_per_zspage(size, pages_per_zspage))
- return false;
-
- return true;
+ return false;
}
static bool zspage_full(struct size_class *class, struct zspage *zspage)
obj = handle_to_obj(handle);
obj_to_location(obj, &page, &obj_idx);
zspage = get_zspage(page);
+
+ /* migration cannot move any subpage in this zspage */
+ migrate_read_lock(zspage);
+
get_zspage_mapping(zspage, &class_idx, &fg);
class = pool->size_class[class_idx];
off = (class->size * obj_idx) & ~PAGE_MASK;
ret = __zs_map_object(area, pages, off, class->size);
out:
- if (!class->huge)
+ if (likely(!PageHugeObject(page)))
ret += ZS_HANDLE_SIZE;
return ret;
__zs_unmap_object(area, pages, off, class->size);
}
put_cpu_var(zs_map_area);
+
+ migrate_read_unlock(zspage);
unpin_tag(handle);
}
EXPORT_SYMBOL_GPL(zs_unmap_object);
vaddr = kmap_atomic(m_page);
link = (struct link_free *)vaddr + m_offset / sizeof(*link);
- set_freeobj(zspage, link->next >> OBJ_ALLOCATED_TAG);
- if (!class->huge)
+ set_freeobj(zspage, link->next >> OBJ_TAG_BITS);
+ if (likely(!PageHugeObject(m_page)))
/* record handle in the header of allocated chunk */
link->handle = handle;
else
* zs_malloc - Allocate block of given size from pool.
* @pool: pool to allocate from
* @size: size of block to allocate
+ * @gfp: gfp flags when allocating object
*
* On success, handle to the allocated object is returned,
* otherwise 0.
{
unsigned long handle, obj;
struct size_class *class;
+ enum fullness_group newfg;
struct zspage *zspage;
if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
spin_lock(&class->lock);
zspage = find_get_zspage(class);
-
- if (!zspage) {
+ if (likely(zspage)) {
+ obj = obj_malloc(class, zspage, handle);
+ /* Now move the zspage to another fullness group, if required */
+ fix_fullness_group(class, zspage);
+ record_obj(handle, obj);
spin_unlock(&class->lock);
- zspage = alloc_zspage(pool, class, gfp);
- if (unlikely(!zspage)) {
- cache_free_handle(pool, handle);
- return 0;
- }
- set_zspage_mapping(zspage, class->index, ZS_EMPTY);
- atomic_long_add(class->pages_per_zspage,
- &pool->pages_allocated);
+ return handle;
+ }
- spin_lock(&class->lock);
- zs_stat_inc(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
- class->size, class->pages_per_zspage));
+ spin_unlock(&class->lock);
+
+ zspage = alloc_zspage(pool, class, gfp);
+ if (!zspage) {
+ cache_free_handle(pool, handle);
+ return 0;
}
+ spin_lock(&class->lock);
obj = obj_malloc(class, zspage, handle);
- /* Now move the zspage to another fullness group, if required */
- fix_fullness_group(class, zspage);
+ 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);
+ zs_stat_inc(class, OBJ_ALLOCATED, class->objs_per_zspage);
+
+ /* We completely set up zspage so mark them as movable */
+ SetZsPageMovable(pool, zspage);
spin_unlock(&class->lock);
return handle;
/* Insert this object in containing zspage's freelist */
link = (struct link_free *)(vaddr + f_offset);
- link->next = get_freeobj(zspage) << OBJ_ALLOCATED_TAG;
+ link->next = get_freeobj(zspage) << OBJ_TAG_BITS;
kunmap_atomic(vaddr);
set_freeobj(zspage, f_objidx);
mod_zspage_inuse(zspage, -1);
int class_idx;
struct size_class *class;
enum fullness_group fullness;
+ bool isolated;
if (unlikely(!handle))
return;
obj_to_location(obj, &f_page, &f_objidx);
zspage = get_zspage(f_page);
+ migrate_read_lock(zspage);
+
get_zspage_mapping(zspage, &class_idx, &fullness);
class = pool->size_class[class_idx];
spin_lock(&class->lock);
obj_free(class, obj);
fullness = fix_fullness_group(class, zspage);
- if (fullness == ZS_EMPTY) {
- zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
- class->size, class->pages_per_zspage));
- atomic_long_sub(class->pages_per_zspage,
- &pool->pages_allocated);
- free_zspage(pool, zspage);
+ if (fullness != ZS_EMPTY) {
+ migrate_read_unlock(zspage);
+ goto out;
}
+
+ isolated = is_zspage_isolated(zspage);
+ migrate_read_unlock(zspage);
+ /* If zspage is isolated, zs_page_putback will free the zspage */
+ if (likely(!isolated))
+ free_zspage(pool, class, zspage);
+out:
+
spin_unlock(&class->lock);
unpin_tag(handle);
-
cache_free_handle(pool, handle);
}
EXPORT_SYMBOL_GPL(zs_free);
* return handle.
*/
static unsigned long find_alloced_obj(struct size_class *class,
- struct page *page, int index)
+ struct page *page, int *obj_idx)
{
unsigned long head;
int offset = 0;
+ int index = *obj_idx;
unsigned long handle = 0;
void *addr = kmap_atomic(page);
offset += class->size * index;
while (offset < PAGE_SIZE) {
- head = obj_to_head(class, page, addr + offset);
+ head = obj_to_head(page, addr + offset);
if (head & OBJ_ALLOCATED_TAG) {
handle = head & ~OBJ_ALLOCATED_TAG;
if (trypin_tag(handle))
}
kunmap_atomic(addr);
+
+ *obj_idx = index;
+
return handle;
}
struct page *d_page;
/* Starting object index within @s_page which used for live object
* in the subpage. */
- int index;
+ int obj_idx;
};
static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
unsigned long handle;
struct page *s_page = cc->s_page;
struct page *d_page = cc->d_page;
- unsigned long index = cc->index;
+ int obj_idx = cc->obj_idx;
int ret = 0;
while (1) {
- handle = find_alloced_obj(class, s_page, index);
+ handle = find_alloced_obj(class, s_page, &obj_idx);
if (!handle) {
s_page = get_next_page(s_page);
if (!s_page)
break;
- index = 0;
+ obj_idx = 0;
continue;
}
used_obj = handle_to_obj(handle);
free_obj = obj_malloc(class, get_zspage(d_page), handle);
zs_object_copy(class, free_obj, used_obj);
- index++;
+ obj_idx++;
/*
* record_obj updates handle's value to free_obj and it will
* invalidate lock bit(ie, HANDLE_PIN_BIT) of handle, which
/* Remember last position in this iteration */
cc->s_page = s_page;
- cc->index = index;
+ cc->obj_idx = obj_idx;
return ret;
}
zspage = list_first_entry_or_null(&class->fullness_list[fg[i]],
struct zspage, list);
if (zspage) {
+ VM_BUG_ON(is_zspage_isolated(zspage));
remove_zspage(class, zspage, fg[i]);
return zspage;
}
{
enum fullness_group fullness;
+ VM_BUG_ON(is_zspage_isolated(zspage));
+
fullness = get_fullness_group(class, zspage);
insert_zspage(class, zspage, fullness);
set_zspage_mapping(zspage, class->index, fullness);
return fullness;
}
+#ifdef CONFIG_COMPACTION
+static struct dentry *zs_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
+{
+ static const struct dentry_operations ops = {
+ .d_dname = simple_dname,
+ };
+
+ return mount_pseudo(fs_type, "zsmalloc:", NULL, &ops, ZSMALLOC_MAGIC);
+}
+
+static struct file_system_type zsmalloc_fs = {
+ .name = "zsmalloc",
+ .mount = zs_mount,
+ .kill_sb = kill_anon_super,
+};
+
+static int zsmalloc_mount(void)
+{
+ int ret = 0;
+
+ zsmalloc_mnt = kern_mount(&zsmalloc_fs);
+ if (IS_ERR(zsmalloc_mnt))
+ ret = PTR_ERR(zsmalloc_mnt);
+
+ return ret;
+}
+
+static void zsmalloc_unmount(void)
+{
+ kern_unmount(zsmalloc_mnt);
+}
+
+static void migrate_lock_init(struct zspage *zspage)
+{
+ rwlock_init(&zspage->lock);
+}
+
+static void migrate_read_lock(struct zspage *zspage)
+{
+ read_lock(&zspage->lock);
+}
+
+static void migrate_read_unlock(struct zspage *zspage)
+{
+ 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);
+}
+
+/* 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)
+{
+ zspage->isolated--;
+}
+
+static void replace_sub_page(struct size_class *class, struct zspage *zspage,
+ struct page *newpage, struct page *oldpage)
+{
+ struct page *page;
+ struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE] = {NULL, };
+ int idx = 0;
+
+ page = get_first_page(zspage);
+ do {
+ if (page == oldpage)
+ pages[idx] = newpage;
+ else
+ pages[idx] = page;
+ idx++;
+ } while ((page = get_next_page(page)) != NULL);
+
+ create_page_chain(class, zspage, pages);
+ set_first_obj_offset(newpage, get_first_obj_offset(oldpage));
+ if (unlikely(PageHugeObject(oldpage)))
+ newpage->index = oldpage->index;
+ __SetPageMovable(newpage, page_mapping(oldpage));
+}
+
+bool zs_page_isolate(struct page *page, isolate_mode_t mode)
+{
+ struct zs_pool *pool;
+ struct size_class *class;
+ int class_idx;
+ enum fullness_group fullness;
+ struct zspage *zspage;
+ struct address_space *mapping;
+
+ /*
+ * 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);
+
+ /*
+ * Without class lock, fullness could be stale while class_idx is okay
+ * because class_idx is constant unless page is freed so we should get
+ * fullness again under class lock.
+ */
+ get_zspage_mapping(zspage, &class_idx, &fullness);
+ mapping = page_mapping(page);
+ pool = mapping->private_data;
+ class = pool->size_class[class_idx];
+
+ spin_lock(&class->lock);
+ if (get_zspage_inuse(zspage) == 0) {
+ spin_unlock(&class->lock);
+ return false;
+ }
+
+ /* zspage is isolated for object migration */
+ if (list_empty(&zspage->list) && !is_zspage_isolated(zspage)) {
+ spin_unlock(&class->lock);
+ return false;
+ }
+
+ /*
+ * If this is first time isolation for the zspage, isolate zspage from
+ * size_class to prevent further object allocation from the zspage.
+ */
+ if (!list_empty(&zspage->list) && !is_zspage_isolated(zspage)) {
+ get_zspage_mapping(zspage, &class_idx, &fullness);
+ remove_zspage(class, zspage, fullness);
+ }
+
+ inc_zspage_isolation(zspage);
+ spin_unlock(&class->lock);
+
+ return true;
+}
+
+int zs_page_migrate(struct address_space *mapping, struct page *newpage,
+ struct page *page, enum migrate_mode mode)
+{
+ struct zs_pool *pool;
+ struct size_class *class;
+ int class_idx;
+ enum fullness_group fullness;
+ struct zspage *zspage;
+ struct page *dummy;
+ void *s_addr, *d_addr, *addr;
+ int offset, pos;
+ unsigned long handle, head;
+ unsigned long old_obj, new_obj;
+ unsigned int obj_idx;
+ int ret = -EAGAIN;
+
+ VM_BUG_ON_PAGE(!PageMovable(page), page);
+ VM_BUG_ON_PAGE(!PageIsolated(page), page);
+
+ zspage = get_zspage(page);
+
+ /* Concurrent compactor cannot migrate any subpage in zspage */
+ migrate_write_lock(zspage);
+ get_zspage_mapping(zspage, &class_idx, &fullness);
+ pool = mapping->private_data;
+ class = pool->size_class[class_idx];
+ offset = get_first_obj_offset(page);
+
+ spin_lock(&class->lock);
+ if (!get_zspage_inuse(zspage)) {
+ ret = -EBUSY;
+ goto unlock_class;
+ }
+
+ pos = offset;
+ s_addr = kmap_atomic(page);
+ while (pos < PAGE_SIZE) {
+ head = obj_to_head(page, s_addr + pos);
+ if (head & OBJ_ALLOCATED_TAG) {
+ handle = head & ~OBJ_ALLOCATED_TAG;
+ if (!trypin_tag(handle))
+ goto unpin_objects;
+ }
+ pos += class->size;
+ }
+
+ /*
+ * 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);
+ kunmap_atomic(d_addr);
+
+ for (addr = s_addr + offset; addr < s_addr + pos;
+ addr += class->size) {
+ head = obj_to_head(page, addr);
+ if (head & OBJ_ALLOCATED_TAG) {
+ handle = head & ~OBJ_ALLOCATED_TAG;
+ if (!testpin_tag(handle))
+ BUG();
+
+ 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 |= BIT(HANDLE_PIN_BIT);
+ record_obj(handle, new_obj);
+ }
+ }
+
+ replace_sub_page(class, zspage, newpage, page);
+ get_page(newpage);
+
+ dec_zspage_isolation(zspage);
+
+ /*
+ * Page migration is done so let's putback isolated zspage to
+ * the list if @page is final isolated subpage in the zspage.
+ */
+ if (!is_zspage_isolated(zspage))
+ putback_zspage(class, zspage);
+
+ reset_page(page);
+ put_page(page);
+ page = newpage;
+
+ ret = MIGRATEPAGE_SUCCESS;
+unpin_objects:
+ for (addr = s_addr + offset; addr < s_addr + pos;
+ addr += class->size) {
+ head = obj_to_head(page, addr);
+ if (head & OBJ_ALLOCATED_TAG) {
+ handle = head & ~OBJ_ALLOCATED_TAG;
+ if (!testpin_tag(handle))
+ BUG();
+ unpin_tag(handle);
+ }
+ }
+ kunmap_atomic(s_addr);
+unlock_class:
+ spin_unlock(&class->lock);
+ migrate_write_unlock(zspage);
+
+ return ret;
+}
+
+void zs_page_putback(struct page *page)
+{
+ struct zs_pool *pool;
+ struct size_class *class;
+ int class_idx;
+ enum fullness_group fg;
+ struct address_space *mapping;
+ struct zspage *zspage;
+
+ VM_BUG_ON_PAGE(!PageMovable(page), page);
+ VM_BUG_ON_PAGE(!PageIsolated(page), page);
+
+ zspage = get_zspage(page);
+ get_zspage_mapping(zspage, &class_idx, &fg);
+ mapping = page_mapping(page);
+ pool = mapping->private_data;
+ class = pool->size_class[class_idx];
+
+ spin_lock(&class->lock);
+ dec_zspage_isolation(zspage);
+ if (!is_zspage_isolated(zspage)) {
+ fg = putback_zspage(class, zspage);
+ /*
+ * Due to page_lock, we cannot free zspage immediately
+ * so let's defer.
+ */
+ if (fg == ZS_EMPTY)
+ schedule_work(&pool->free_work);
+ }
+ spin_unlock(&class->lock);
+}
+
+const struct address_space_operations zsmalloc_aops = {
+ .isolate_page = zs_page_isolate,
+ .migratepage = zs_page_migrate,
+ .putback_page = zs_page_putback,
+};
+
+static int zs_register_migration(struct zs_pool *pool)
+{
+ pool->inode = alloc_anon_inode(zsmalloc_mnt->mnt_sb);
+ if (IS_ERR(pool->inode)) {
+ pool->inode = NULL;
+ return 1;
+ }
+
+ pool->inode->i_mapping->private_data = pool;
+ pool->inode->i_mapping->a_ops = &zsmalloc_aops;
+ return 0;
+}
+
+static void zs_unregister_migration(struct zs_pool *pool)
+{
+ flush_work(&pool->free_work);
+ iput(pool->inode);
+}
+
+/*
+ * Caller should hold page_lock of all pages in the zspage
+ * In here, we cannot use zspage meta data.
+ */
+static void async_free_zspage(struct work_struct *work)
+{
+ 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,
+ free_work);
+
+ for (i = 0; i < zs_size_classes; i++) {
+ class = pool->size_class[i];
+ if (class->index != i)
+ continue;
+
+ spin_lock(&class->lock);
+ list_splice_init(&class->fullness_list[ZS_EMPTY], &free_pages);
+ spin_unlock(&class->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);
+ __free_zspage(pool, pool->size_class[class_idx], zspage);
+ spin_unlock(&class->lock);
+ }
+};
+
+static void kick_deferred_free(struct zs_pool *pool)
+{
+ schedule_work(&pool->free_work);
+}
+
+static void init_deferred_free(struct zs_pool *pool)
+{
+ INIT_WORK(&pool->free_work, async_free_zspage);
+}
+
+static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage)
+{
+ struct page *page = get_first_page(zspage);
+
+ do {
+ WARN_ON(!trylock_page(page));
+ __SetPageMovable(page, pool->inode->i_mapping);
+ unlock_page(page);
+ } while ((page = get_next_page(page)) != NULL);
+}
+#endif
+
/*
*
* Based on the number of unused allocated objects calculate
return 0;
obj_wasted = obj_allocated - obj_used;
- obj_wasted /= get_maxobj_per_zspage(class->size,
- class->pages_per_zspage);
+ obj_wasted /= class->objs_per_zspage;
return obj_wasted * class->pages_per_zspage;
}
if (!zs_can_compact(class))
break;
- cc.index = 0;
- cc.s_page = src_zspage->first_page;
+ cc.obj_idx = 0;
+ cc.s_page = get_first_page(src_zspage);
while ((dst_zspage = isolate_zspage(class, false))) {
- cc.d_page = dst_zspage->first_page;
+ 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.
putback_zspage(class, dst_zspage);
if (putback_zspage(class, src_zspage) == ZS_EMPTY) {
- zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
- class->size, class->pages_per_zspage));
- atomic_long_sub(class->pages_per_zspage,
- &pool->pages_allocated);
- free_zspage(pool, src_zspage);
+ free_zspage(pool, class, src_zspage);
pool->stats.pages_compacted += class->pages_per_zspage;
}
spin_unlock(&class->lock);
/**
* zs_create_pool - Creates an allocation pool to work from.
- * @flags: allocation flags used to allocate pool metadata
+ * @name: pool name to be created
*
* This function must be called before anything when using
* the zsmalloc allocator.
if (!pool)
return NULL;
+ init_deferred_free(pool);
pool->size_class = kcalloc(zs_size_classes, sizeof(struct size_class *),
GFP_KERNEL);
if (!pool->size_class) {
for (i = zs_size_classes - 1; i >= 0; i--) {
int size;
int pages_per_zspage;
+ int objs_per_zspage;
struct size_class *class;
int fullness = 0;
if (size > ZS_MAX_ALLOC_SIZE)
size = ZS_MAX_ALLOC_SIZE;
pages_per_zspage = get_pages_per_zspage(size);
+ objs_per_zspage = pages_per_zspage * PAGE_SIZE / size;
/*
* size_class is used for normal zsmalloc operation such
* previous size_class if possible.
*/
if (prev_class) {
- if (can_merge(prev_class, size, pages_per_zspage)) {
+ if (can_merge(prev_class, pages_per_zspage, objs_per_zspage)) {
pool->size_class[i] = prev_class;
continue;
}
class->size = size;
class->index = i;
class->pages_per_zspage = pages_per_zspage;
- class->objs_per_zspage = class->pages_per_zspage *
- PAGE_SIZE / class->size;
- if (pages_per_zspage == 1 && class->objs_per_zspage == 1)
- class->huge = true;
+ class->objs_per_zspage = objs_per_zspage;
spin_lock_init(&class->lock);
pool->size_class[i] = class;
- for (fullness = ZS_ALMOST_FULL; fullness <= ZS_ALMOST_EMPTY;
- fullness++)
+ for (fullness = ZS_EMPTY; fullness < NR_ZS_FULLNESS;
+ fullness++)
INIT_LIST_HEAD(&class->fullness_list[fullness]);
prev_class = class;
/* debug only, don't abort if it fails */
zs_pool_stat_create(pool, name);
+ if (zs_register_migration(pool))
+ goto err;
+
/*
* Not critical, we still can use the pool
* and user can trigger compaction manually.
int i;
zs_unregister_shrinker(pool);
+ zs_unregister_migration(pool);
zs_pool_stat_destroy(pool);
for (i = 0; i < zs_size_classes; i++) {
if (class->index != i)
continue;
- for (fg = ZS_ALMOST_FULL; fg <= ZS_ALMOST_EMPTY; fg++) {
+ 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);
static int __init zs_init(void)
{
- int ret = zs_register_cpu_notifier();
+ int ret;
+
+ ret = zsmalloc_mount();
+ if (ret)
+ goto out;
+
+ ret = zs_register_cpu_notifier();
if (ret)
goto notifier_fail;
notifier_fail:
zs_unregister_cpu_notifier();
-
+ zsmalloc_unmount();
+out:
return ret;
}
#ifdef CONFIG_ZPOOL
zpool_unregister_driver(&zs_zpool_driver);
#endif
+ zsmalloc_unmount();
zs_unregister_cpu_notifier();
zs_stat_exit();
projects / cascardo / linux.git / blobdiff