*/
struct mem_cgroup_stat stat;
};
+static struct mem_cgroup init_mem_cgroup;
/*
* We use the lower bit of the page->page_cgroup pointer as a bit spin
- * lock. We need to ensure that page->page_cgroup is atleast two
- * byte aligned (based on comments from Nick Piggin)
+ * lock. We need to ensure that page->page_cgroup is at least two
+ * byte aligned (based on comments from Nick Piggin). But since
+ * bit_spin_lock doesn't actually set that lock bit in a non-debug
+ * uniprocessor kernel, we should avoid setting it here too.
*/
#define PAGE_CGROUP_LOCK_BIT 0x0
-#define PAGE_CGROUP_LOCK (1 << PAGE_CGROUP_LOCK_BIT)
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+#define PAGE_CGROUP_LOCK (1 << PAGE_CGROUP_LOCK_BIT)
+#else
+#define PAGE_CGROUP_LOCK 0x0
+#endif
/*
* A page_cgroup page is associated with every page descriptor. The
struct list_head lru; /* per cgroup LRU list */
struct page *page;
struct mem_cgroup *mem_cgroup;
- atomic_t ref_cnt; /* Helpful when pages move b/w */
- /* mapped and cached states */
- int flags;
+ int ref_cnt; /* cached, mapped, migrating */
+ int flags;
};
#define PAGE_CGROUP_FLAG_CACHE (0x1) /* charged as cache */
#define PAGE_CGROUP_FLAG_ACTIVE (0x2) /* page is active in this cgroup */
-static inline int page_cgroup_nid(struct page_cgroup *pc)
+static int page_cgroup_nid(struct page_cgroup *pc)
{
return page_to_nid(pc->page);
}
-static inline enum zone_type page_cgroup_zid(struct page_cgroup *pc)
+static enum zone_type page_cgroup_zid(struct page_cgroup *pc)
{
return page_zonenum(pc->page);
}
-enum {
- MEM_CGROUP_TYPE_UNSPEC = 0,
- MEM_CGROUP_TYPE_MAPPED,
- MEM_CGROUP_TYPE_CACHED,
- MEM_CGROUP_TYPE_ALL,
- MEM_CGROUP_TYPE_MAX,
-};
-
enum charge_type {
MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
MEM_CGROUP_CHARGE_TYPE_MAPPED,
};
-
/*
* Always modified under lru lock. Then, not necessary to preempt_disable()
*/
{
int val = (charge)? 1 : -1;
struct mem_cgroup_stat *stat = &mem->stat;
- VM_BUG_ON(!irqs_disabled());
+ VM_BUG_ON(!irqs_disabled());
if (flags & PAGE_CGROUP_FLAG_CACHE)
- __mem_cgroup_stat_add_safe(stat,
- MEM_CGROUP_STAT_CACHE, val);
+ __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
else
__mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
}
-static inline struct mem_cgroup_per_zone *
+static struct mem_cgroup_per_zone *
mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
{
- BUG_ON(!mem->info.nodeinfo[nid]);
return &mem->info.nodeinfo[nid]->zoneinfo[zid];
}
-static inline struct mem_cgroup_per_zone *
+static struct mem_cgroup_per_zone *
page_cgroup_zoneinfo(struct page_cgroup *pc)
{
struct mem_cgroup *mem = pc->mem_cgroup;
return total;
}
-static struct mem_cgroup init_mem_cgroup;
-
-static inline
-struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
+static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
{
return container_of(cgroup_subsys_state(cont,
mem_cgroup_subsys_id), struct mem_cgroup,
css);
}
-static inline
-struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
+static struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
struct mem_cgroup, css);
static inline int page_cgroup_locked(struct page *page)
{
- return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT,
- &page->page_cgroup);
+ return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}
-void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
+static void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
{
- int locked;
-
- /*
- * While resetting the page_cgroup we might not hold the
- * page_cgroup lock. free_hot_cold_page() is an example
- * of such a scenario
- */
- if (pc)
- VM_BUG_ON(!page_cgroup_locked(page));
- locked = (page->page_cgroup & PAGE_CGROUP_LOCK);
- page->page_cgroup = ((unsigned long)pc | locked);
+ VM_BUG_ON(!page_cgroup_locked(page));
+ page->page_cgroup = ((unsigned long)pc | PAGE_CGROUP_LOCK);
}
struct page_cgroup *page_get_page_cgroup(struct page *page)
{
- return (struct page_cgroup *)
- (page->page_cgroup & ~PAGE_CGROUP_LOCK);
+ return (struct page_cgroup *) (page->page_cgroup & ~PAGE_CGROUP_LOCK);
}
-static void __always_inline lock_page_cgroup(struct page *page)
+static void lock_page_cgroup(struct page *page)
{
bit_spin_lock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
- VM_BUG_ON(!page_cgroup_locked(page));
-}
-
-static void __always_inline unlock_page_cgroup(struct page *page)
-{
- bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}
-/*
- * Tie new page_cgroup to struct page under lock_page_cgroup()
- * This can fail if the page has been tied to a page_cgroup.
- * If success, returns 0.
- */
-static int page_cgroup_assign_new_page_cgroup(struct page *page,
- struct page_cgroup *pc)
+static int try_lock_page_cgroup(struct page *page)
{
- int ret = 0;
-
- lock_page_cgroup(page);
- if (!page_get_page_cgroup(page))
- page_assign_page_cgroup(page, pc);
- else /* A page is tied to other pc. */
- ret = 1;
- unlock_page_cgroup(page);
- return ret;
+ return bit_spin_trylock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}
-/*
- * Clear page->page_cgroup member under lock_page_cgroup().
- * If given "pc" value is different from one page->page_cgroup,
- * page->cgroup is not cleared.
- * Returns a value of page->page_cgroup at lock taken.
- * A can can detect failure of clearing by following
- * clear_page_cgroup(page, pc) == pc
- */
-
-static struct page_cgroup *clear_page_cgroup(struct page *page,
- struct page_cgroup *pc)
+static void unlock_page_cgroup(struct page *page)
{
- struct page_cgroup *ret;
- /* lock and clear */
- lock_page_cgroup(page);
- ret = page_get_page_cgroup(page);
- if (likely(ret == pc))
- page_assign_page_cgroup(page, NULL);
- unlock_page_cgroup(page);
- return ret;
+ bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}
static void __mem_cgroup_remove_list(struct page_cgroup *pc)
int ret;
task_lock(task);
- ret = task->mm && mm_cgroup(task->mm) == mem;
+ ret = task->mm && mm_match_cgroup(task->mm, mem);
task_unlock(task);
return ret;
}
/*
* This routine assumes that the appropriate zone's lru lock is already held
*/
-void mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
+void mem_cgroup_move_lists(struct page *page, bool active)
{
+ struct page_cgroup *pc;
struct mem_cgroup_per_zone *mz;
unsigned long flags;
- if (!pc)
+ /*
+ * We cannot lock_page_cgroup while holding zone's lru_lock,
+ * because other holders of lock_page_cgroup can be interrupted
+ * with an attempt to rotate_reclaimable_page. But we cannot
+ * safely get to page_cgroup without it, so just try_lock it:
+ * mem_cgroup_isolate_pages allows for page left on wrong list.
+ */
+ if (!try_lock_page_cgroup(page))
return;
- mz = page_cgroup_zoneinfo(pc);
- spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_move_lists(pc, active);
- spin_unlock_irqrestore(&mz->lru_lock, flags);
+ pc = page_get_page_cgroup(page);
+ if (pc) {
+ mz = page_cgroup_zoneinfo(pc);
+ spin_lock_irqsave(&mz->lru_lock, flags);
+ __mem_cgroup_move_lists(pc, active);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+ }
+ unlock_page_cgroup(page);
}
/*
rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
return (int)((rss * 100L) / total);
}
+
/*
* This function is called from vmscan.c. In page reclaiming loop. balance
* between active and inactive list is calculated. For memory controller
struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
nr_inactive = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE);
-
return (nr_inactive >> priority);
}
if (scan >= nr_to_scan)
break;
page = pc->page;
- VM_BUG_ON(!pc);
if (unlikely(!PageLRU(page)))
continue;
* with it
*/
retry:
- if (page) {
- lock_page_cgroup(page);
- pc = page_get_page_cgroup(page);
- /*
- * The page_cgroup exists and
- * the page has already been accounted.
- */
- if (pc) {
- if (unlikely(!atomic_inc_not_zero(&pc->ref_cnt))) {
- /* this page is under being uncharged ? */
- unlock_page_cgroup(page);
- cpu_relax();
- goto retry;
- } else {
- unlock_page_cgroup(page);
- goto done;
- }
- }
+ lock_page_cgroup(page);
+ pc = page_get_page_cgroup(page);
+ /*
+ * The page_cgroup exists and
+ * the page has already been accounted.
+ */
+ if (pc) {
+ VM_BUG_ON(pc->page != page);
+ VM_BUG_ON(pc->ref_cnt <= 0);
+
+ pc->ref_cnt++;
unlock_page_cgroup(page);
+ goto done;
}
+ unlock_page_cgroup(page);
pc = kzalloc(sizeof(struct page_cgroup), gfp_mask);
if (pc == NULL)
rcu_read_lock();
mem = rcu_dereference(mm->mem_cgroup);
/*
- * For every charge from the cgroup, increment reference
- * count
+ * For every charge from the cgroup, increment reference count
*/
css_get(&mem->css);
rcu_read_unlock();
- /*
- * If we created the page_cgroup, we should free it on exceeding
- * the cgroup limit.
- */
while (res_counter_charge(&mem->res, PAGE_SIZE)) {
if (!(gfp_mask & __GFP_WAIT))
goto out;
continue;
/*
- * try_to_free_mem_cgroup_pages() might not give us a full
- * picture of reclaim. Some pages are reclaimed and might be
- * moved to swap cache or just unmapped from the cgroup.
- * Check the limit again to see if the reclaim reduced the
- * current usage of the cgroup before giving up
- */
+ * try_to_free_mem_cgroup_pages() might not give us a full
+ * picture of reclaim. Some pages are reclaimed and might be
+ * moved to swap cache or just unmapped from the cgroup.
+ * Check the limit again to see if the reclaim reduced the
+ * current usage of the cgroup before giving up
+ */
if (res_counter_check_under_limit(&mem->res))
continue;
congestion_wait(WRITE, HZ/10);
}
- atomic_set(&pc->ref_cnt, 1);
+ pc->ref_cnt = 1;
pc->mem_cgroup = mem;
pc->page = page;
pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE)
pc->flags |= PAGE_CGROUP_FLAG_CACHE;
- if (!page || page_cgroup_assign_new_page_cgroup(page, pc)) {
+ lock_page_cgroup(page);
+ if (page_get_page_cgroup(page)) {
+ unlock_page_cgroup(page);
/*
* Another charge has been added to this page already.
* We take lock_page_cgroup(page) again and read
res_counter_uncharge(&mem->res, PAGE_SIZE);
css_put(&mem->css);
kfree(pc);
- if (!page)
- goto done;
goto retry;
}
+ page_assign_page_cgroup(page, pc);
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
- /* Update statistics vector */
__mem_cgroup_add_list(pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
+ unlock_page_cgroup(page);
done:
return 0;
out:
return -ENOMEM;
}
-int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask)
+int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
{
return mem_cgroup_charge_common(page, mm, gfp_mask,
- MEM_CGROUP_CHARGE_TYPE_MAPPED);
+ MEM_CGROUP_CHARGE_TYPE_MAPPED);
}
-/*
- * See if the cached pages should be charged at all?
- */
int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask)
{
- int ret = 0;
if (!mm)
mm = &init_mm;
-
- ret = mem_cgroup_charge_common(page, mm, gfp_mask,
+ return mem_cgroup_charge_common(page, mm, gfp_mask,
MEM_CGROUP_CHARGE_TYPE_CACHE);
- return ret;
}
/*
* Uncharging is always a welcome operation, we never complain, simply
- * uncharge. This routine should be called with lock_page_cgroup held
+ * uncharge.
*/
-void mem_cgroup_uncharge(struct page_cgroup *pc)
+void mem_cgroup_uncharge_page(struct page *page)
{
+ struct page_cgroup *pc;
struct mem_cgroup *mem;
struct mem_cgroup_per_zone *mz;
- struct page *page;
unsigned long flags;
/*
* Check if our page_cgroup is valid
*/
+ lock_page_cgroup(page);
+ pc = page_get_page_cgroup(page);
if (!pc)
- return;
+ goto unlock;
- if (atomic_dec_and_test(&pc->ref_cnt)) {
- page = pc->page;
+ VM_BUG_ON(pc->page != page);
+ VM_BUG_ON(pc->ref_cnt <= 0);
+
+ if (--(pc->ref_cnt) == 0) {
mz = page_cgroup_zoneinfo(pc);
- /*
- * get page->cgroup and clear it under lock.
- * force_empty can drop page->cgroup without checking refcnt.
- */
+ spin_lock_irqsave(&mz->lru_lock, flags);
+ __mem_cgroup_remove_list(pc);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+
+ page_assign_page_cgroup(page, NULL);
unlock_page_cgroup(page);
- if (clear_page_cgroup(page, pc) == pc) {
- mem = pc->mem_cgroup;
- css_put(&mem->css);
- res_counter_uncharge(&mem->res, PAGE_SIZE);
- spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_remove_list(pc);
- spin_unlock_irqrestore(&mz->lru_lock, flags);
- kfree(pc);
- }
- lock_page_cgroup(page);
+
+ mem = pc->mem_cgroup;
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
+ css_put(&mem->css);
+
+ kfree(pc);
+ return;
}
-}
-void mem_cgroup_uncharge_page(struct page *page)
-{
- lock_page_cgroup(page);
- mem_cgroup_uncharge(page_get_page_cgroup(page));
+unlock:
unlock_page_cgroup(page);
}
* Returns non-zero if a page (under migration) has valid page_cgroup member.
* Refcnt of page_cgroup is incremented.
*/
-
int mem_cgroup_prepare_migration(struct page *page)
{
struct page_cgroup *pc;
- int ret = 0;
+
lock_page_cgroup(page);
pc = page_get_page_cgroup(page);
- if (pc && atomic_inc_not_zero(&pc->ref_cnt))
- ret = 1;
+ if (pc)
+ pc->ref_cnt++;
unlock_page_cgroup(page);
- return ret;
+ return pc != NULL;
}
void mem_cgroup_end_migration(struct page *page)
{
- struct page_cgroup *pc;
-
- lock_page_cgroup(page);
- pc = page_get_page_cgroup(page);
- mem_cgroup_uncharge(pc);
- unlock_page_cgroup(page);
+ mem_cgroup_uncharge_page(page);
}
+
/*
- * We know both *page* and *newpage* are now not-on-LRU and Pg_locked.
+ * We know both *page* and *newpage* are now not-on-LRU and PG_locked.
* And no race with uncharge() routines because page_cgroup for *page*
* has extra one reference by mem_cgroup_prepare_migration.
*/
-
void mem_cgroup_page_migration(struct page *page, struct page *newpage)
{
struct page_cgroup *pc;
- struct mem_cgroup *mem;
- unsigned long flags;
struct mem_cgroup_per_zone *mz;
-retry:
+ unsigned long flags;
+
+ lock_page_cgroup(page);
pc = page_get_page_cgroup(page);
- if (!pc)
+ if (!pc) {
+ unlock_page_cgroup(page);
return;
- mem = pc->mem_cgroup;
+ }
+
mz = page_cgroup_zoneinfo(pc);
- if (clear_page_cgroup(page, pc) != pc)
- goto retry;
spin_lock_irqsave(&mz->lru_lock, flags);
-
__mem_cgroup_remove_list(pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
+ page_assign_page_cgroup(page, NULL);
+ unlock_page_cgroup(page);
+
pc->page = newpage;
lock_page_cgroup(newpage);
page_assign_page_cgroup(newpage, pc);
- unlock_page_cgroup(newpage);
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
__mem_cgroup_add_list(pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
- return;
+
+ unlock_page_cgroup(newpage);
}
/*
* *And* this routine doesn't reclaim page itself, just removes page_cgroup.
*/
#define FORCE_UNCHARGE_BATCH (128)
-static void
-mem_cgroup_force_empty_list(struct mem_cgroup *mem,
+static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
struct mem_cgroup_per_zone *mz,
int active)
{
struct page_cgroup *pc;
struct page *page;
- int count;
+ int count = FORCE_UNCHARGE_BATCH;
unsigned long flags;
struct list_head *list;
else
list = &mz->inactive_list;
- if (list_empty(list))
- return;
-retry:
- count = FORCE_UNCHARGE_BATCH;
spin_lock_irqsave(&mz->lru_lock, flags);
-
- while (--count && !list_empty(list)) {
+ while (!list_empty(list)) {
pc = list_entry(list->prev, struct page_cgroup, lru);
page = pc->page;
- /* Avoid race with charge */
- atomic_set(&pc->ref_cnt, 0);
- if (clear_page_cgroup(page, pc) == pc) {
- css_put(&mem->css);
- res_counter_uncharge(&mem->res, PAGE_SIZE);
- __mem_cgroup_remove_list(pc);
- kfree(pc);
- } else /* being uncharged ? ...do relax */
- break;
+ get_page(page);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+ mem_cgroup_uncharge_page(page);
+ put_page(page);
+ if (--count <= 0) {
+ count = FORCE_UNCHARGE_BATCH;
+ cond_resched();
+ }
+ spin_lock_irqsave(&mz->lru_lock, flags);
}
spin_unlock_irqrestore(&mz->lru_lock, flags);
- if (!list_empty(list)) {
- cond_resched();
- goto retry;
- }
- return;
}
/*
* make mem_cgroup's charge to be 0 if there is no task.
* This enables deleting this mem_cgroup.
*/
-
-int mem_cgroup_force_empty(struct mem_cgroup *mem)
+static int mem_cgroup_force_empty(struct mem_cgroup *mem)
{
int ret = -EBUSY;
int node, zid;
+
css_get(&mem->css);
/*
* page reclaim code (kswapd etc..) will move pages between
-` * active_list <-> inactive_list while we don't take a lock.
+ * active_list <-> inactive_list while we don't take a lock.
* So, we have to do loop here until all lists are empty.
*/
while (mem->res.usage > 0) {
return ret;
}
-
-
-int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp)
+static int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp)
{
*tmp = memparse(buf, &buf);
if (*buf != '\0')
size_t nbytes, loff_t *ppos)
{
struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
- int ret;
- ret = mem_cgroup_force_empty(mem);
+ int ret = mem_cgroup_force_empty(mem);
if (!ret)
ret = nbytes;
return ret;
/*
* Note: This should be removed if cgroup supports write-only file.
*/
-
static ssize_t mem_force_empty_read(struct cgroup *cont,
struct cftype *cft,
struct file *file, char __user *userbuf,
return -EINVAL;
}
-
static const struct mem_cgroup_stat_desc {
const char *msg;
u64 unit;
return single_open(file, mem_control_stat_show, cont);
}
-
-
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
kfree(mem->info.nodeinfo[node]);
}
-
-static struct mem_cgroup init_mem_cgroup;
-
static struct cgroup_subsys_state *
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);
if (mem == NULL)
- return NULL;
+ return ERR_PTR(-ENOMEM);
res_counter_init(&mem->res);
free_mem_cgroup_per_zone_info(mem, node);
if (cont->parent != NULL)
kfree(mem);
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
* Only thread group leaders are allowed to migrate, the mm_struct is
* in effect owned by the leader
*/
- if (p->tgid != p->pid)
+ if (!thread_group_leader(p))
goto out;
css_get(&mem->css);
out:
mmput(mm);
- return;
}
struct cgroup_subsys mem_cgroup_subsys = {
git.samba.org / sfrench / cifs-2.6.git / blobdiff