#include <linux/seq_file.h>
#include <linux/vmalloc.h>
#include <linux/mm_inline.h>
+#include <linux/page_cgroup.h>
#include <asm/uaccess.h>
struct cgroup_subsys mem_cgroup_subsys __read_mostly;
-static struct kmem_cache *page_cgroup_cache __read_mostly;
#define MEM_CGROUP_RECLAIM_RETRIES 5
/*
/*
* For accounting under irq disable, no need for increment preempt count.
*/
-static void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat *stat,
+static inline void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat_cpu *stat,
enum mem_cgroup_stat_index idx, int val)
{
- int cpu = smp_processor_id();
- stat->cpustat[cpu].count[idx] += val;
+ stat->count[idx] += val;
}
static s64 mem_cgroup_read_stat(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 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
-#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
- * page_cgroup helps us identify information about the cgroup
- */
-struct page_cgroup {
- struct list_head lru; /* per cgroup LRU list */
- struct page *page;
- struct mem_cgroup *mem_cgroup;
- int flags;
-};
-#define PAGE_CGROUP_FLAG_CACHE (0x1) /* charged as cache */
-#define PAGE_CGROUP_FLAG_ACTIVE (0x2) /* page is active in this cgroup */
-#define PAGE_CGROUP_FLAG_FILE (0x4) /* page is file system backed */
-#define PAGE_CGROUP_FLAG_UNEVICTABLE (0x8) /* page is unevictableable */
-
-static int page_cgroup_nid(struct page_cgroup *pc)
-{
- return page_to_nid(pc->page);
-}
-
-static enum zone_type page_cgroup_zid(struct page_cgroup *pc)
-{
- return page_zonenum(pc->page);
-}
-
enum charge_type {
MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
MEM_CGROUP_CHARGE_TYPE_MAPPED,
- MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */
MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */
+ MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */
+ NR_CHARGE_TYPE,
+};
+
+/* only for here (for easy reading.) */
+#define PCGF_CACHE (1UL << PCG_CACHE)
+#define PCGF_USED (1UL << PCG_USED)
+#define PCGF_ACTIVE (1UL << PCG_ACTIVE)
+#define PCGF_LOCK (1UL << PCG_LOCK)
+#define PCGF_FILE (1UL << PCG_FILE)
+static const unsigned long
+pcg_default_flags[NR_CHARGE_TYPE] = {
+ PCGF_CACHE | PCGF_FILE | PCGF_USED | PCGF_LOCK, /* File Cache */
+ PCGF_ACTIVE | PCGF_USED | PCGF_LOCK, /* Anon */
+ PCGF_ACTIVE | PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */
+ 0, /* FORCE */
};
/*
* Always modified under lru lock. Then, not necessary to preempt_disable()
*/
-static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
- bool charge)
+static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
+ struct page_cgroup *pc,
+ bool charge)
{
int val = (charge)? 1 : -1;
struct mem_cgroup_stat *stat = &mem->stat;
+ struct mem_cgroup_stat_cpu *cpustat;
VM_BUG_ON(!irqs_disabled());
- if (flags & PAGE_CGROUP_FLAG_CACHE)
- __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
+
+ cpustat = &stat->cpustat[smp_processor_id()];
+ if (PageCgroupCache(pc))
+ __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_CACHE, val);
else
- __mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
+ __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_RSS, val);
if (charge)
- __mem_cgroup_stat_add_safe(stat,
+ __mem_cgroup_stat_add_safe(cpustat,
MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
else
- __mem_cgroup_stat_add_safe(stat,
+ __mem_cgroup_stat_add_safe(cpustat,
MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
}
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);
-}
-
-static void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
-{
- 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);
-}
-
-static void lock_page_cgroup(struct page *page)
-{
- bit_spin_lock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static int try_lock_page_cgroup(struct page *page)
-{
- return bit_spin_trylock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static void unlock_page_cgroup(struct page *page)
-{
- bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
struct page_cgroup *pc)
{
int lru = LRU_BASE;
- if (pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE)
+ if (PageCgroupUnevictable(pc))
lru = LRU_UNEVICTABLE;
else {
- if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+ if (PageCgroupActive(pc))
lru += LRU_ACTIVE;
- if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+ if (PageCgroupFile(pc))
lru += LRU_FILE;
}
MEM_CGROUP_ZSTAT(mz, lru) -= 1;
- mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, false);
+ mem_cgroup_charge_statistics(pc->mem_cgroup, pc, false);
list_del(&pc->lru);
}
{
int lru = LRU_BASE;
- if (pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE)
+ if (PageCgroupUnevictable(pc))
lru = LRU_UNEVICTABLE;
else {
- if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+ if (PageCgroupActive(pc))
lru += LRU_ACTIVE;
- if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+ if (PageCgroupFile(pc))
lru += LRU_FILE;
}
MEM_CGROUP_ZSTAT(mz, lru) += 1;
list_add(&pc->lru, &mz->lists[lru]);
- mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);
+ mem_cgroup_charge_statistics(pc->mem_cgroup, pc, true);
}
static void __mem_cgroup_move_lists(struct page_cgroup *pc, enum lru_list lru)
{
struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
- int active = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
- int file = pc->flags & PAGE_CGROUP_FLAG_FILE;
- int unevictable = pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE;
+ int active = PageCgroupActive(pc);
+ int file = PageCgroupFile(pc);
+ int unevictable = PageCgroupUnevictable(pc);
enum lru_list from = unevictable ? LRU_UNEVICTABLE :
(LRU_FILE * !!file + !!active);
return;
MEM_CGROUP_ZSTAT(mz, from) -= 1;
-
+ /*
+ * However this is done under mz->lru_lock, another flags, which
+ * are not related to LRU, will be modified from out-of-lock.
+ * We have to use atomic set/clear flags.
+ */
if (is_unevictable_lru(lru)) {
- pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
- pc->flags |= PAGE_CGROUP_FLAG_UNEVICTABLE;
+ ClearPageCgroupActive(pc);
+ SetPageCgroupUnevictable(pc);
} else {
if (is_active_lru(lru))
- pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
+ SetPageCgroupActive(pc);
else
- pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
- pc->flags &= ~PAGE_CGROUP_FLAG_UNEVICTABLE;
+ ClearPageCgroupActive(pc);
+ ClearPageCgroupUnevictable(pc);
}
MEM_CGROUP_ZSTAT(mz, lru) += 1;
* 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))
+ pc = lookup_page_cgroup(page);
+ if (!trylock_page_cgroup(pc))
return;
-
- pc = page_get_page_cgroup(page);
- if (pc) {
+ if (pc && PageCgroupUsed(pc)) {
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
__mem_cgroup_move_lists(pc, lru);
spin_unlock_irqrestore(&mz->lru_lock, flags);
}
- unlock_page_cgroup(page);
+ unlock_page_cgroup(pc);
}
/*
list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
if (scan >= nr_to_scan)
break;
+ if (unlikely(!PageCgroupUsed(pc)))
+ continue;
page = pc->page;
if (unlikely(!PageLRU(page)))
{
struct mem_cgroup *mem;
struct page_cgroup *pc;
- unsigned long flags;
unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
struct mem_cgroup_per_zone *mz;
+ unsigned long flags;
- pc = kmem_cache_alloc(page_cgroup_cache, gfp_mask);
- if (unlikely(pc == NULL))
- goto err;
-
+ pc = lookup_page_cgroup(page);
+ /* can happen at boot */
+ if (unlikely(!pc))
+ return 0;
+ prefetchw(pc);
/*
* We always charge the cgroup the mm_struct belongs to.
* The mm_struct's mem_cgroup changes on task migration if the
* thread group leader migrates. It's possible that mm is not
* set, if so charge the init_mm (happens for pagecache usage).
*/
+
if (likely(!memcg)) {
rcu_read_lock();
mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
if (unlikely(!mem)) {
rcu_read_unlock();
- kmem_cache_free(page_cgroup_cache, pc);
return 0;
}
/*
css_get(&memcg->css);
}
- while (res_counter_charge(&mem->res, PAGE_SIZE)) {
+ while (unlikely(res_counter_charge(&mem->res, PAGE_SIZE))) {
if (!(gfp_mask & __GFP_WAIT))
goto out;
}
}
+
+ lock_page_cgroup(pc);
+ if (unlikely(PageCgroupUsed(pc))) {
+ unlock_page_cgroup(pc);
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
+ css_put(&mem->css);
+
+ goto done;
+ }
pc->mem_cgroup = mem;
- pc->page = page;
/*
* If a page is accounted as a page cache, insert to inactive list.
* If anon, insert to active list.
*/
- if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE) {
- pc->flags = PAGE_CGROUP_FLAG_CACHE;
- if (page_is_file_cache(page))
- pc->flags |= PAGE_CGROUP_FLAG_FILE;
- else
- pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
- } else if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
- pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
- else /* MEM_CGROUP_CHARGE_TYPE_SHMEM */
- pc->flags = PAGE_CGROUP_FLAG_CACHE | PAGE_CGROUP_FLAG_ACTIVE;
-
- lock_page_cgroup(page);
- if (unlikely(page_get_page_cgroup(page))) {
- unlock_page_cgroup(page);
- res_counter_uncharge(&mem->res, PAGE_SIZE);
- css_put(&mem->css);
- kmem_cache_free(page_cgroup_cache, pc);
- goto done;
- }
- page_assign_page_cgroup(page, pc);
+ pc->flags = pcg_default_flags[ctype];
mz = page_cgroup_zoneinfo(pc);
+
spin_lock_irqsave(&mz->lru_lock, flags);
__mem_cgroup_add_list(mz, pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
+ unlock_page_cgroup(pc);
- unlock_page_cgroup(page);
done:
return 0;
out:
css_put(&mem->css);
- kmem_cache_free(page_cgroup_cache, pc);
-err:
return -ENOMEM;
}
{
if (mem_cgroup_subsys.disabled)
return 0;
-
+ if (PageCompound(page))
+ return 0;
/*
* If already mapped, we don't have to account.
* If page cache, page->mapping has address_space.
{
if (mem_cgroup_subsys.disabled)
return 0;
-
+ if (PageCompound(page))
+ return 0;
/*
* Corner case handling. This is called from add_to_page_cache()
* in usual. But some FS (shmem) precharges this page before calling it
if (!(gfp_mask & __GFP_WAIT)) {
struct page_cgroup *pc;
- lock_page_cgroup(page);
- pc = page_get_page_cgroup(page);
- if (pc) {
- VM_BUG_ON(pc->page != page);
- VM_BUG_ON(!pc->mem_cgroup);
- unlock_page_cgroup(page);
+
+ pc = lookup_page_cgroup(page);
+ if (!pc)
+ return 0;
+ lock_page_cgroup(pc);
+ if (PageCgroupUsed(pc)) {
+ unlock_page_cgroup(pc);
return 0;
}
- unlock_page_cgroup(page);
+ unlock_page_cgroup(pc);
}
if (unlikely(!mm))
mm = &init_mm;
- return mem_cgroup_charge_common(page, mm, gfp_mask,
+ if (page_is_file_cache(page))
+ return mem_cgroup_charge_common(page, mm, gfp_mask,
MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
+ else
+ return mem_cgroup_charge_common(page, mm, gfp_mask,
+ MEM_CGROUP_CHARGE_TYPE_SHMEM, NULL);
}
/*
/*
* Check if our page_cgroup is valid
*/
- lock_page_cgroup(page);
- pc = page_get_page_cgroup(page);
- if (unlikely(!pc))
- goto unlock;
-
- VM_BUG_ON(pc->page != page);
+ pc = lookup_page_cgroup(page);
+ if (unlikely(!pc || !PageCgroupUsed(pc)))
+ return;
- if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
- && ((pc->flags & PAGE_CGROUP_FLAG_CACHE)
- || page_mapped(page)))
- goto unlock;
+ lock_page_cgroup(pc);
+ if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED && page_mapped(page))
+ || !PageCgroupUsed(pc)) {
+ /* This happens at race in zap_pte_range() and do_swap_page()*/
+ unlock_page_cgroup(pc);
+ return;
+ }
+ ClearPageCgroupUsed(pc);
+ mem = pc->mem_cgroup;
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
__mem_cgroup_remove_list(mz, pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
+ unlock_page_cgroup(pc);
- page_assign_page_cgroup(page, NULL);
- unlock_page_cgroup(page);
-
- mem = pc->mem_cgroup;
res_counter_uncharge(&mem->res, PAGE_SIZE);
css_put(&mem->css);
- kmem_cache_free(page_cgroup_cache, pc);
return;
-unlock:
- unlock_page_cgroup(page);
}
void mem_cgroup_uncharge_page(struct page *page)
{
+ /* early check. */
+ if (page_mapped(page))
+ return;
+ if (page->mapping && !PageAnon(page))
+ return;
__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
}
void mem_cgroup_uncharge_cache_page(struct page *page)
{
VM_BUG_ON(page_mapped(page));
+ VM_BUG_ON(page->mapping);
__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
}
if (mem_cgroup_subsys.disabled)
return 0;
- lock_page_cgroup(page);
- pc = page_get_page_cgroup(page);
- if (pc) {
+ pc = lookup_page_cgroup(page);
+ lock_page_cgroup(pc);
+ if (PageCgroupUsed(pc)) {
mem = pc->mem_cgroup;
css_get(&mem->css);
- if (pc->flags & PAGE_CGROUP_FLAG_CACHE) {
+ if (PageCgroupCache(pc)) {
if (page_is_file_cache(page))
ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
else
ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
}
}
- unlock_page_cgroup(page);
+ unlock_page_cgroup(pc);
if (mem) {
ret = mem_cgroup_charge_common(newpage, NULL, GFP_KERNEL,
ctype, mem);
*/
if (!newpage->mapping)
__mem_cgroup_uncharge_common(newpage,
- MEM_CGROUP_CHARGE_TYPE_FORCE);
+ MEM_CGROUP_CHARGE_TYPE_FORCE);
else if (PageAnon(newpage))
mem_cgroup_uncharge_page(newpage);
}
while (!list_empty(list)) {
pc = list_entry(list->prev, struct page_cgroup, lru);
page = pc->page;
+ if (!PageCgroupUsed(pc))
+ break;
get_page(page);
spin_unlock_irqrestore(&mz->lru_lock, flags);
/*
count = FORCE_UNCHARGE_BATCH;
cond_resched();
}
- } else
- cond_resched();
+ } else {
+ spin_lock_irqsave(&mz->lru_lock, flags);
+ break;
+ }
spin_lock_irqsave(&mz->lru_lock, flags);
}
spin_unlock_irqrestore(&mz->lru_lock, flags);
while (mem->res.usage > 0) {
if (atomic_read(&mem->css.cgroup->count) > 0)
goto out;
+ /* This is for making all *used* pages to be on LRU. */
+ lru_add_drain_all();
for_each_node_state(node, N_POSSIBLE)
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
struct mem_cgroup_per_zone *mz;
for_each_lru(l)
mem_cgroup_force_empty_list(mem, mz, l);
}
+ cond_resched();
}
ret = 0;
out:
{
unsigned long active_anon, inactive_anon;
unsigned long active_file, inactive_file;
+ unsigned long unevictable;
inactive_anon = mem_cgroup_get_all_zonestat(mem_cont,
LRU_INACTIVE_ANON);
LRU_INACTIVE_FILE);
active_file = mem_cgroup_get_all_zonestat(mem_cont,
LRU_ACTIVE_FILE);
+ unevictable = mem_cgroup_get_all_zonestat(mem_cont,
+ LRU_UNEVICTABLE);
+
cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE);
cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE);
cb->fill(cb, "active_file", (active_file) * PAGE_SIZE);
cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE);
+ cb->fill(cb, "unevictable", unevictable * PAGE_SIZE);
+
}
return 0;
}
if (unlikely((cont->parent) == NULL)) {
mem = &init_mem_cgroup;
- page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
} else {
mem = mem_cgroup_alloc();
if (!mem)