#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+/*
+ * lock ordering:
+ * page_lock
+ * pool->migrate_lock
+ * class->lock
+ * zspage->lock
+ */
+
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/pagemap.h>
#include <linux/fs.h>
+#include <linux/local_lock.h>
#define ZSPAGE_MAGIC 0x58
#define _PFN_BITS (MAX_POSSIBLE_PHYSMEM_BITS - PAGE_SHIFT)
-/*
- * Memory for allocating for handle keeps object position by
- * encoding <page, obj_idx> and the encoded value has a room
- * in least bit(ie, look at obj_to_location).
- * We use the bit to synchronize between object access by
- * user and migration.
- */
-#define HANDLE_PIN_BIT 0
-
/*
* Head in allocated object should have OBJ_ALLOCATED_TAG
* to identify the object was allocated or not.
#ifdef CONFIG_COMPACTION
struct inode *inode;
struct work_struct free_work;
- /* A wait queue for when migration races with async_free_zspage() */
- struct wait_queue_head migration_wait;
- atomic_long_t isolated_pages;
- bool destroying;
#endif
+ /* protect page/zspage migration */
+ rwlock_t migrate_lock;
};
struct zspage {
};
struct mapping_area {
+ local_lock_t lock;
char *vm_buf; /* copy buffer for objects that span pages */
char *vm_addr; /* address of kmap_atomic()'ed pages */
enum zs_mapmode vm_mm; /* mapping mode */
static void 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);
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 */
static void record_obj(unsigned long handle, unsigned long obj)
{
- /*
- * lsb of @obj represents handle lock while other bits
- * represent object value the handle is pointing so
- * updating shouldn't do store tearing.
- */
- WRITE_ONCE(*(unsigned long *)handle, obj);
+ *(unsigned long *)handle = obj;
}
/* zpool driver */
#endif /* CONFIG_ZPOOL */
/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
-static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
-
-static bool is_zspage_isolated(struct zspage *zspage)
-{
- return zspage->isolated;
-}
+static DEFINE_PER_CPU(struct mapping_area, zs_map_area) = {
+ .lock = INIT_LOCAL_LOCK(lock),
+};
static __maybe_unused int is_first_page(struct page *page)
{
enum fullness_group fullness)
{
VM_BUG_ON(list_empty(&class->fullness_list[fullness]));
- VM_BUG_ON(is_zspage_isolated(zspage));
list_del_init(&zspage->list);
class_stat_dec(class, fullness, 1);
if (newfg == currfg)
goto out;
- if (!is_zspage_isolated(zspage)) {
- remove_zspage(class, zspage, currfg);
- insert_zspage(class, zspage, newfg);
- }
-
+ remove_zspage(class, zspage, currfg);
+ insert_zspage(class, zspage, newfg);
set_zspage_mapping(zspage, class_idx, newfg);
-
out:
return newfg;
}
return true;
}
-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 pin_tag(unsigned long handle) __acquires(bitlock)
-{
- bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle);
-}
-
-static void unpin_tag(unsigned long handle) __releases(bitlock)
-{
- bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle);
-}
-
static void reset_page(struct page *page)
{
__ClearPageMovable(page);
VM_BUG_ON(get_zspage_inuse(zspage));
VM_BUG_ON(list_empty(&zspage->list));
+ /*
+ * Since zs_free couldn't be sleepable, this function cannot call
+ * lock_page. The page locks trylock_zspage got will be released
+ * by __free_zspage.
+ */
if (!trylock_zspage(zspage)) {
kick_deferred_free(pool);
return;
*/
BUG_ON(in_interrupt());
- /* From now on, migration cannot move the object */
- pin_tag(handle);
-
+ /* It guarantees it can get zspage from handle safely */
+ read_lock(&pool->migrate_lock);
obj = handle_to_obj(handle);
obj_to_location(obj, &page, &obj_idx);
zspage = get_zspage(page);
- /* migration cannot move any subpage in this zspage */
+ /*
+ * migration cannot move any zpages in this zspage. Here, class->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);
class = zspage_class(pool, zspage);
off = (class->size * obj_idx) & ~PAGE_MASK;
- area = &get_cpu_var(zs_map_area);
+ local_lock(&zs_map_area.lock);
+ area = this_cpu_ptr(&zs_map_area);
area->vm_mm = mm;
if (off + class->size <= PAGE_SIZE) {
/* this object is contained entirely within a page */
__zs_unmap_object(area, pages, off, class->size);
}
- put_cpu_var(zs_map_area);
+ local_unlock(&zs_map_area.lock);
migrate_read_unlock(zspage);
- unpin_tag(handle);
}
EXPORT_SYMBOL_GPL(zs_unmap_object);
size += ZS_HANDLE_SIZE;
class = pool->size_class[get_size_class_index(size)];
+ /* class->lock effectively protects the zpage migration */
spin_lock(&class->lock);
zspage = find_get_zspage(class);
if (likely(zspage)) {
unsigned long obj;
struct size_class *class;
enum fullness_group fullness;
- bool isolated;
if (unlikely(!handle))
return;
- pin_tag(handle);
+ /*
+ * The pool->migrate_lock protects the race with zpage's migration
+ * so it's safe to get the page from handle.
+ */
+ read_lock(&pool->migrate_lock);
obj = handle_to_obj(handle);
obj_to_page(obj, &f_page);
zspage = get_zspage(f_page);
-
- migrate_read_lock(zspage);
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);
fullness = fix_fullness_group(class, zspage);
- if (fullness != ZS_EMPTY) {
- migrate_read_unlock(zspage);
+ if (fullness != ZS_EMPTY)
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);
+ free_zspage(pool, class, zspage);
out:
-
spin_unlock(&class->lock);
- unpin_tag(handle);
cache_free_handle(pool, handle);
}
EXPORT_SYMBOL_GPL(zs_free);
offset += class->size * index;
while (offset < PAGE_SIZE) {
- if (obj_allocated(page, addr + offset, &handle)) {
- if (trypin_tag(handle))
- break;
- handle = 0;
- }
+ if (obj_allocated(page, addr + offset, &handle))
+ break;
offset += class->size;
index++;
/* Stop if there is no more space */
if (zspage_full(class, get_zspage(d_page))) {
- unpin_tag(handle);
ret = -ENOMEM;
break;
}
free_obj = obj_malloc(pool, get_zspage(d_page), handle);
zs_object_copy(class, free_obj, used_obj);
obj_idx++;
- /*
- * record_obj updates handle's value to free_obj and it will
- * invalidate lock bit(ie, HANDLE_PIN_BIT) of handle, which
- * breaks synchronization using pin_tag(e,g, zs_free) so
- * let's keep the lock bit.
- */
- free_obj |= BIT(HANDLE_PIN_BIT);
record_obj(handle, free_obj);
- unpin_tag(handle);
obj_free(class->size, used_obj);
}
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);
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);
static void dec_zspage_isolation(struct zspage *zspage)
{
+ VM_BUG_ON(zspage->isolated == 0);
zspage->isolated--;
}
-static void putback_zspage_deferred(struct zs_pool *pool,
- struct size_class *class,
- struct zspage *zspage)
-{
- enum fullness_group fg;
-
- fg = putback_zspage(class, zspage);
- if (fg == ZS_EMPTY)
- schedule_work(&pool->free_work);
-
-}
-
-static inline void zs_pool_dec_isolated(struct zs_pool *pool)
-{
- VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0);
- atomic_long_dec(&pool->isolated_pages);
- /*
- * Checking pool->destroying must happen after atomic_long_dec()
- * for pool->isolated_pages above. Paired with the smp_mb() in
- * zs_unregister_migration().
- */
- smp_mb__after_atomic();
- if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying)
- wake_up_all(&pool->migration_wait);
-}
-
static void replace_sub_page(struct size_class *class, struct zspage *zspage,
struct page *newpage, struct page *oldpage)
{
static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
{
- struct zs_pool *pool;
- struct size_class *class;
struct zspage *zspage;
- struct address_space *mapping;
/*
* Page is locked so zspage couldn't be destroyed. For detail, look at
VM_BUG_ON_PAGE(PageIsolated(page), page);
zspage = get_zspage(page);
-
- mapping = page_mapping(page);
- pool = mapping->private_data;
-
- class = zspage_class(pool, zspage);
-
- 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)) {
- enum fullness_group fullness;
- unsigned int class_idx;
-
- get_zspage_mapping(zspage, &class_idx, &fullness);
- atomic_long_inc(&pool->isolated_pages);
- remove_zspage(class, zspage, fullness);
- }
-
+ migrate_write_lock(zspage);
inc_zspage_isolation(zspage);
- spin_unlock(&class->lock);
+ migrate_write_unlock(zspage);
return true;
}
struct zspage *zspage;
struct page *dummy;
void *s_addr, *d_addr, *addr;
- int offset, pos;
+ int offset;
unsigned long handle;
unsigned long old_obj, new_obj;
unsigned int obj_idx;
- int ret = -EAGAIN;
/*
* We cannot support the _NO_COPY case here, because copy needs to
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);
pool = mapping->private_data;
+
+ /*
+ * The pool migrate_lock protects the race between zpage migration
+ * and zs_free.
+ */
+ write_lock(&pool->migrate_lock);
+ zspage = get_zspage(page);
class = zspage_class(pool, zspage);
- offset = get_first_obj_offset(page);
+ /*
+ * the class lock protects zpage alloc/free in the zspage.
+ */
spin_lock(&class->lock);
- if (!get_zspage_inuse(zspage)) {
- /*
- * Set "offset" to end of the page so that every loops
- * skips unnecessary object scanning.
- */
- offset = PAGE_SIZE;
- }
+ /* the migrate_write_lock protects zpage access via zs_map_object */
+ migrate_write_lock(zspage);
- pos = offset;
+ offset = get_first_obj_offset(page);
s_addr = kmap_atomic(page);
- while (pos < PAGE_SIZE) {
- if (obj_allocated(page, s_addr + pos, &handle)) {
- if (!trypin_tag(handle))
- goto unpin_objects;
- }
- pos += class->size;
- }
/*
* Here, any user cannot access all objects in the zspage so let's move.
memcpy(d_addr, s_addr, PAGE_SIZE);
kunmap_atomic(d_addr);
- for (addr = s_addr + offset; addr < s_addr + pos;
+ for (addr = s_addr + offset; addr < s_addr + PAGE_SIZE;
addr += class->size) {
if (obj_allocated(page, addr, &handle)) {
- BUG_ON(!testpin_tag(handle));
old_obj = handle_to_obj(handle);
obj_to_location(old_obj, &dummy, &obj_idx);
new_obj = (unsigned long)location_to_obj(newpage,
obj_idx);
- new_obj |= BIT(HANDLE_PIN_BIT);
record_obj(handle, new_obj);
}
}
+ kunmap_atomic(s_addr);
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.
+ * Since we complete the data copy and set up new zspage structure,
+ * it's okay to release migration_lock.
*/
- if (!is_zspage_isolated(zspage)) {
- /*
- * We cannot race with zs_destroy_pool() here because we wait
- * for isolation to hit zero before we start destroying.
- * Also, we ensure that everyone can see pool->destroying before
- * we start waiting.
- */
- putback_zspage_deferred(pool, class, zspage);
- zs_pool_dec_isolated(pool);
- }
+ write_unlock(&pool->migrate_lock);
+ spin_unlock(&class->lock);
+ dec_zspage_isolation(zspage);
+ migrate_write_unlock(zspage);
+ get_page(newpage);
if (page_zone(newpage) != page_zone(page)) {
dec_zone_page_state(page, NR_ZSPAGES);
inc_zone_page_state(newpage, NR_ZSPAGES);
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) {
- if (obj_allocated(page, addr, &handle)) {
- BUG_ON(!testpin_tag(handle));
- unpin_tag(handle);
- }
- }
- kunmap_atomic(s_addr);
- spin_unlock(&class->lock);
- migrate_write_unlock(zspage);
- return ret;
+ return MIGRATEPAGE_SUCCESS;
}
static void zs_page_putback(struct page *page)
{
- struct zs_pool *pool;
- struct size_class *class;
- 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);
- mapping = page_mapping(page);
- pool = mapping->private_data;
- class = zspage_class(pool, zspage);
-
- spin_lock(&class->lock);
+ migrate_write_lock(zspage);
dec_zspage_isolation(zspage);
- if (!is_zspage_isolated(zspage)) {
- /*
- * Due to page_lock, we cannot free zspage immediately
- * so let's defer.
- */
- putback_zspage_deferred(pool, class, zspage);
- zs_pool_dec_isolated(pool);
- }
- spin_unlock(&class->lock);
+ migrate_write_unlock(zspage);
}
static const struct address_space_operations zsmalloc_aops = {
return 0;
}
-static bool pool_isolated_are_drained(struct zs_pool *pool)
-{
- return atomic_long_read(&pool->isolated_pages) == 0;
-}
-
-/* Function for resolving migration */
-static void wait_for_isolated_drain(struct zs_pool *pool)
-{
-
- /*
- * We're in the process of destroying the pool, so there are no
- * active allocations. zs_page_isolate() fails for completely free
- * zspages, so we need only wait for the zs_pool's isolated
- * count to hit zero.
- */
- wait_event(pool->migration_wait,
- pool_isolated_are_drained(pool));
-}
-
static void zs_unregister_migration(struct zs_pool *pool)
{
- pool->destroying = true;
- /*
- * We need a memory barrier here to ensure global visibility of
- * pool->destroying. Thus pool->isolated pages will either be 0 in which
- * case we don't care, or it will be > 0 and pool->destroying will
- * ensure that we wake up once isolation hits 0.
- */
- smp_mb();
- wait_for_isolated_drain(pool); /* This can block */
flush_work(&pool->free_work);
iput(pool->inode);
}
spin_unlock(&class->lock);
}
-
list_for_each_entry_safe(zspage, tmp, &free_pages, list) {
list_del(&zspage->list);
lock_zspage(zspage);
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.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
break;
putback_zspage(class, dst_zspage);
+ migrate_write_unlock(dst_zspage);
+ dst_zspage = NULL;
+ if (rwlock_is_contended(&pool->migrate_lock))
+ break;
}
/* Stop if we couldn't find slot */
break;
putback_zspage(class, dst_zspage);
+ migrate_write_unlock(dst_zspage);
+
if (putback_zspage(class, src_zspage) == ZS_EMPTY) {
+ migrate_write_unlock(src_zspage);
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);
}
- 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);
return pages_freed;
}
return NULL;
init_deferred_free(pool);
+ rwlock_init(&pool->migrate_lock);
pool->name = kstrdup(name, GFP_KERNEL);
if (!pool->name)
goto err;
-#ifdef CONFIG_COMPACTION
- init_waitqueue_head(&pool->migration_wait);
-#endif
-
if (create_cache(pool))
goto err;
projects / linux-2.6-microblaze.git / blobdiff