__free_page(page);
}
+#define ZS_PAGE_UNLOCKED 0
+#define ZS_PAGE_WRLOCKED -1
+
+struct zspage_lock {
+ spinlock_t lock;
+ int cnt;
+ struct lockdep_map dep_map;
+};
+
struct zspage {
struct {
unsigned int huge:HUGE_BITS;
struct zpdesc *first_zpdesc;
struct list_head list; /* fullness list */
struct zs_pool *pool;
- rwlock_t lock;
+ struct zspage_lock zsl;
};
struct mapping_area {
enum zs_mapmode vm_mm; /* mapping mode */
};
+static void zspage_lock_init(struct zspage *zspage)
+{
+ static struct lock_class_key __key;
+ struct zspage_lock *zsl = &zspage->zsl;
+
+ lockdep_init_map(&zsl->dep_map, "zspage->lock", &__key, 0);
+ spin_lock_init(&zsl->lock);
+ zsl->cnt = ZS_PAGE_UNLOCKED;
+}
+
+/*
+ * The zspage lock can be held from atomic contexts, but it needs to remain
+ * preemptible when held for reading because it remains held outside of those
+ * atomic contexts, otherwise we unnecessarily lose preemptibility.
+ *
+ * To achieve this, the following rules are enforced on readers and writers:
+ *
+ * - Writers are blocked by both writers and readers, while readers are only
+ * blocked by writers (i.e. normal rwlock semantics).
+ *
+ * - Writers are always atomic (to allow readers to spin waiting for them).
+ *
+ * - Writers always use trylock (as the lock may be held be sleeping readers).
+ *
+ * - Readers may spin on the lock (as they can only wait for atomic writers).
+ *
+ * - Readers may sleep while holding the lock (as writes only use trylock).
+ */
+static void zspage_read_lock(struct zspage *zspage)
+{
+ struct zspage_lock *zsl = &zspage->zsl;
+
+ rwsem_acquire_read(&zsl->dep_map, 0, 0, _RET_IP_);
+
+ spin_lock(&zsl->lock);
+ zsl->cnt++;
+ spin_unlock(&zsl->lock);
+
+ lock_acquired(&zsl->dep_map, _RET_IP_);
+}
+
+static void zspage_read_unlock(struct zspage *zspage)
+{
+ struct zspage_lock *zsl = &zspage->zsl;
+
+ rwsem_release(&zsl->dep_map, _RET_IP_);
+
+ spin_lock(&zsl->lock);
+ zsl->cnt--;
+ spin_unlock(&zsl->lock);
+}
+
+static __must_check bool zspage_write_trylock(struct zspage *zspage)
+{
+ struct zspage_lock *zsl = &zspage->zsl;
+
+ spin_lock(&zsl->lock);
+ if (zsl->cnt == ZS_PAGE_UNLOCKED) {
+ zsl->cnt = ZS_PAGE_WRLOCKED;
+ rwsem_acquire(&zsl->dep_map, 0, 1, _RET_IP_);
+ lock_acquired(&zsl->dep_map, _RET_IP_);
+ return true;
+ }
+
+ spin_unlock(&zsl->lock);
+ return false;
+}
+
+static void zspage_write_unlock(struct zspage *zspage)
+{
+ struct zspage_lock *zsl = &zspage->zsl;
+
+ rwsem_release(&zsl->dep_map, _RET_IP_);
+
+ zsl->cnt = ZS_PAGE_UNLOCKED;
+ spin_unlock(&zsl->lock);
+}
+
/* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */
static void SetZsHugePage(struct zspage *zspage)
{
return zspage->huge;
}
-static void migrate_lock_init(struct zspage *zspage);
-static void migrate_read_lock(struct zspage *zspage);
-static void migrate_read_unlock(struct zspage *zspage);
-static void migrate_write_lock(struct zspage *zspage);
-static void migrate_write_unlock(struct zspage *zspage);
-
#ifdef CONFIG_COMPACTION
static void kick_deferred_free(struct zs_pool *pool);
static void init_deferred_free(struct zs_pool *pool);
return NULL;
zspage->magic = ZSPAGE_MAGIC;
- migrate_lock_init(zspage);
+ zspage->pool = pool;
+ zspage->class = class->index;
+ zspage_lock_init(zspage);
for (i = 0; i < class->pages_per_zspage; i++) {
struct zpdesc *zpdesc;
create_page_chain(class, zspage, zpdescs);
init_zspage(class, zspage);
- zspage->pool = pool;
- zspage->class = class->index;
return zspage;
}
* zs_unmap_object API so delegate the locking from class to zspage
* which is smaller granularity.
*/
- migrate_read_lock(zspage);
+ zspage_read_lock(zspage);
read_unlock(&pool->lock);
class = zspage_class(pool, zspage);
}
local_unlock(&zs_map_area.lock);
- migrate_read_unlock(zspage);
+ zspage_read_unlock(zspage);
}
EXPORT_SYMBOL_GPL(zs_unmap_object);
/*
* Pages we haven't locked yet can be migrated off the list while we're
* trying to lock them, so we need to be careful and only attempt to
- * lock each page under migrate_read_lock(). Otherwise, the page we lock
+ * lock each page under zspage_read_lock(). Otherwise, the page we lock
* may no longer belong to the zspage. This means that we may wait for
* the wrong page to unlock, so we must take a reference to the page
- * prior to waiting for it to unlock outside migrate_read_lock().
+ * prior to waiting for it to unlock outside zspage_read_lock().
*/
while (1) {
- migrate_read_lock(zspage);
+ zspage_read_lock(zspage);
zpdesc = get_first_zpdesc(zspage);
if (zpdesc_trylock(zpdesc))
break;
zpdesc_get(zpdesc);
- migrate_read_unlock(zspage);
+ zspage_read_unlock(zspage);
zpdesc_wait_locked(zpdesc);
zpdesc_put(zpdesc);
}
curr_zpdesc = zpdesc;
} else {
zpdesc_get(zpdesc);
- migrate_read_unlock(zspage);
+ zspage_read_unlock(zspage);
zpdesc_wait_locked(zpdesc);
zpdesc_put(zpdesc);
- migrate_read_lock(zspage);
+ zspage_read_lock(zspage);
}
}
- migrate_read_unlock(zspage);
+ zspage_read_unlock(zspage);
}
#endif /* CONFIG_COMPACTION */
-static void migrate_lock_init(struct zspage *zspage)
-{
- rwlock_init(&zspage->lock);
-}
-
-static void migrate_read_lock(struct zspage *zspage) __acquires(&zspage->lock)
-{
- read_lock(&zspage->lock);
-}
-
-static void migrate_read_unlock(struct zspage *zspage) __releases(&zspage->lock)
-{
- read_unlock(&zspage->lock);
-}
-
-static void migrate_write_lock(struct zspage *zspage)
-{
- write_lock(&zspage->lock);
-}
-
-static void migrate_write_unlock(struct zspage *zspage)
-{
- write_unlock(&zspage->lock);
-}
-
#ifdef CONFIG_COMPACTION
static const struct movable_operations zsmalloc_mops;
VM_BUG_ON_PAGE(!zpdesc_is_isolated(zpdesc), zpdesc_page(zpdesc));
- /* We're committed, tell the world that this is a Zsmalloc page. */
- __zpdesc_set_zsmalloc(newzpdesc);
-
/* The page is locked, so this pointer must remain valid */
zspage = get_zspage(zpdesc);
pool = zspage->pool;
* 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);
+ /* the zspage write_lock protects zpage access via zs_map_object */
+ if (!zspage_write_trylock(zspage)) {
+ spin_unlock(&class->lock);
+ write_unlock(&pool->lock);
+ return -EINVAL;
+ }
+
+ /* We're committed, tell the world that this is a Zsmalloc page. */
+ __zpdesc_set_zsmalloc(newzpdesc);
offset = get_first_obj_offset(zpdesc);
s_addr = kmap_local_zpdesc(zpdesc);
*/
write_unlock(&pool->lock);
spin_unlock(&class->lock);
- migrate_write_unlock(zspage);
+ zspage_write_unlock(zspage);
zpdesc_get(newzpdesc);
if (zpdesc_zone(newzpdesc) != zpdesc_zone(zpdesc)) {
if (!src_zspage)
break;
- migrate_write_lock(src_zspage);
+ if (!zspage_write_trylock(src_zspage))
+ break;
+
migrate_zspage(pool, src_zspage, dst_zspage);
- migrate_write_unlock(src_zspage);
+ zspage_write_unlock(src_zspage);
fg = putback_zspage(class, src_zspage);
if (fg == ZS_INUSE_RATIO_0) {
projects / linux-block.git / commitdiff