#include <linux/memcontrol.h>
#include <linux/cgroup.h>
#include <linux/mm.h>
+#include <linux/pagemap.h>
#include <linux/smp.h>
#include <linux/page-flags.h>
#include <linux/backing-dev.h>
#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
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */
+int do_swap_account __read_mostly;
+static int really_do_swap_account __initdata = 1; /* for remember boot option*/
+#else
+#define do_swap_account (0)
+#endif
+
+
/*
* Statistics for memory cgroup.
*/
} ____cacheline_aligned_in_smp;
struct mem_cgroup_stat {
- struct mem_cgroup_stat_cpu cpustat[NR_CPUS];
+ struct mem_cgroup_stat_cpu cpustat[0];
};
/*
* 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,
int prev_priority; /* for recording reclaim priority */
/*
- * statistics.
+ * statistics. This must be placed at the end of memcg.
*/
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 */
+ MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */
+ 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);
}
static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
- struct page_cgroup *pc)
+ struct page_cgroup *pc, bool hot)
{
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]);
+ if (hot)
+ list_add(&pc->lru, &mz->lists[lru]);
+ else
+ list_add_tail(&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)))
}
/*
- * Charge the memory controller for page usage.
- * Return
- * 0 if the charge was successful
- * < 0 if the cgroup is over its limit
+ * Unlike exported interface, "oom" parameter is added. if oom==true,
+ * oom-killer can be invoked.
*/
-static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask, enum charge_type ctype,
- struct mem_cgroup *memcg)
+static int __mem_cgroup_try_charge(struct mm_struct *mm,
+ gfp_t gfp_mask, struct mem_cgroup **memcg, bool oom)
{
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;
-
- pc = kmem_cache_alloc(page_cgroup_cache, gfp_mask);
- if (unlikely(pc == NULL))
- goto err;
-
+ int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
/*
* 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)) {
+ 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;
}
/*
* For every charge from the cgroup, increment reference count
*/
css_get(&mem->css);
+ *memcg = mem;
rcu_read_unlock();
} else {
- mem = memcg;
- css_get(&memcg->css);
+ mem = *memcg;
+ css_get(&mem->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;
+ goto nomem;
if (try_to_free_mem_cgroup_pages(mem, gfp_mask))
continue;
continue;
if (!nr_retries--) {
- mem_cgroup_out_of_memory(mem, gfp_mask);
- goto out;
+ if (oom)
+ mem_cgroup_out_of_memory(mem, gfp_mask);
+ goto nomem;
}
}
+ return 0;
+nomem:
+ css_put(&mem->css);
+ return -ENOMEM;
+}
+
+/**
+ * mem_cgroup_try_charge - get charge of PAGE_SIZE.
+ * @mm: an mm_struct which is charged against. (when *memcg is NULL)
+ * @gfp_mask: gfp_mask for reclaim.
+ * @memcg: a pointer to memory cgroup which is charged against.
+ *
+ * charge against memory cgroup pointed by *memcg. if *memcg == NULL, estimated
+ * memory cgroup from @mm is got and stored in *memcg.
+ *
+ * Returns 0 if success. -ENOMEM at failure.
+ * This call can invoke OOM-Killer.
+ */
+int mem_cgroup_try_charge(struct mm_struct *mm,
+ gfp_t mask, struct mem_cgroup **memcg)
+{
+ return __mem_cgroup_try_charge(mm, mask, memcg, true);
+}
+
+/*
+ * commit a charge got by mem_cgroup_try_charge() and makes page_cgroup to be
+ * USED state. If already USED, uncharge and return.
+ */
+
+static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
+ struct page_cgroup *pc,
+ enum charge_type ctype)
+{
+ struct mem_cgroup_per_zone *mz;
+ unsigned long flags;
+
+ /* try_charge() can return NULL to *memcg, taking care of it. */
+ if (!mem)
+ return;
+
+ lock_page_cgroup(pc);
+ if (unlikely(PageCgroupUsed(pc))) {
+ unlock_page_cgroup(pc);
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
+ css_put(&mem->css);
+ return;
+ }
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);
+ __mem_cgroup_add_list(mz, pc, true);
spin_unlock_irqrestore(&mz->lru_lock, flags);
+ unlock_page_cgroup(pc);
+}
- unlock_page_cgroup(page);
-done:
- return 0;
+/**
+ * mem_cgroup_move_account - move account of the page
+ * @pc: page_cgroup of the page.
+ * @from: mem_cgroup which the page is moved from.
+ * @to: mem_cgroup which the page is moved to. @from != @to.
+ *
+ * The caller must confirm following.
+ * 1. disable irq.
+ * 2. lru_lock of old mem_cgroup(@from) should be held.
+ *
+ * returns 0 at success,
+ * returns -EBUSY when lock is busy or "pc" is unstable.
+ *
+ * This function does "uncharge" from old cgroup but doesn't do "charge" to
+ * new cgroup. It should be done by a caller.
+ */
+
+static int mem_cgroup_move_account(struct page_cgroup *pc,
+ struct mem_cgroup *from, struct mem_cgroup *to)
+{
+ struct mem_cgroup_per_zone *from_mz, *to_mz;
+ int nid, zid;
+ int ret = -EBUSY;
+
+ VM_BUG_ON(!irqs_disabled());
+ VM_BUG_ON(from == to);
+
+ nid = page_cgroup_nid(pc);
+ zid = page_cgroup_zid(pc);
+ from_mz = mem_cgroup_zoneinfo(from, nid, zid);
+ to_mz = mem_cgroup_zoneinfo(to, nid, zid);
+
+
+ if (!trylock_page_cgroup(pc))
+ return ret;
+
+ if (!PageCgroupUsed(pc))
+ goto out;
+
+ if (pc->mem_cgroup != from)
+ goto out;
+
+ if (spin_trylock(&to_mz->lru_lock)) {
+ __mem_cgroup_remove_list(from_mz, pc);
+ css_put(&from->css);
+ res_counter_uncharge(&from->res, PAGE_SIZE);
+ pc->mem_cgroup = to;
+ css_get(&to->css);
+ __mem_cgroup_add_list(to_mz, pc, false);
+ ret = 0;
+ spin_unlock(&to_mz->lru_lock);
+ }
out:
- css_put(&mem->css);
- kmem_cache_free(page_cgroup_cache, pc);
-err:
- return -ENOMEM;
+ unlock_page_cgroup(pc);
+ return ret;
}
-int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
+/*
+ * move charges to its parent.
+ */
+
+static int mem_cgroup_move_parent(struct page_cgroup *pc,
+ struct mem_cgroup *child,
+ gfp_t gfp_mask)
{
- if (mem_cgroup_subsys.disabled)
+ struct cgroup *cg = child->css.cgroup;
+ struct cgroup *pcg = cg->parent;
+ struct mem_cgroup *parent;
+ struct mem_cgroup_per_zone *mz;
+ unsigned long flags;
+ int ret;
+
+ /* Is ROOT ? */
+ if (!pcg)
+ return -EINVAL;
+
+ parent = mem_cgroup_from_cont(pcg);
+
+ ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false);
+ if (ret)
+ return ret;
+
+ mz = mem_cgroup_zoneinfo(child,
+ page_cgroup_nid(pc), page_cgroup_zid(pc));
+
+ spin_lock_irqsave(&mz->lru_lock, flags);
+ ret = mem_cgroup_move_account(pc, child, parent);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+
+ /* drop extra refcnt */
+ css_put(&parent->css);
+ /* uncharge if move fails */
+ if (ret)
+ res_counter_uncharge(&parent->res, PAGE_SIZE);
+
+ return ret;
+}
+
+/*
+ * Charge the memory controller for page usage.
+ * Return
+ * 0 if the charge was successful
+ * < 0 if the cgroup is over its limit
+ */
+static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
+ gfp_t gfp_mask, enum charge_type ctype,
+ struct mem_cgroup *memcg)
+{
+ struct mem_cgroup *mem;
+ struct page_cgroup *pc;
+ int ret;
+
+ pc = lookup_page_cgroup(page);
+ /* can happen at boot */
+ if (unlikely(!pc))
return 0;
+ prefetchw(pc);
+
+ mem = memcg;
+ ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true);
+ if (ret)
+ return ret;
+ __mem_cgroup_commit_charge(mem, pc, ctype);
+ return 0;
+}
+
+int mem_cgroup_newpage_charge(struct page *page,
+ struct mm_struct *mm, gfp_t gfp_mask)
+{
+ 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);
}
+#ifdef CONFIG_SWAP
+int mem_cgroup_cache_charge_swapin(struct page *page,
+ struct mm_struct *mm, gfp_t mask, bool locked)
+{
+ int ret = 0;
+
+ if (mem_cgroup_subsys.disabled)
+ return 0;
+ if (unlikely(!mm))
+ mm = &init_mm;
+ if (!locked)
+ lock_page(page);
+ /*
+ * If not locked, the page can be dropped from SwapCache until
+ * we reach here.
+ */
+ if (PageSwapCache(page)) {
+ ret = mem_cgroup_charge_common(page, mm, mask,
+ MEM_CGROUP_CHARGE_TYPE_SHMEM, NULL);
+ }
+ if (!locked)
+ unlock_page(page);
+
+ return ret;
+}
+#endif
+
+void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
+{
+ struct page_cgroup *pc;
+
+ if (mem_cgroup_subsys.disabled)
+ return;
+ if (!ptr)
+ return;
+ pc = lookup_page_cgroup(page);
+ __mem_cgroup_commit_charge(ptr, pc, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+}
+
+void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
+{
+ if (mem_cgroup_subsys.disabled)
+ return;
+ if (!mem)
+ return;
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
+ css_put(&mem->css);
+}
+
+
/*
* uncharge if !page_mapped(page)
*/
if (mem_cgroup_subsys.disabled)
return;
+ if (PageSwapCache(page))
+ return;
+
/*
* Check if our page_cgroup is valid
*/
- lock_page_cgroup(page);
- pc = page_get_page_cgroup(page);
- if (unlikely(!pc))
- goto unlock;
+ pc = lookup_page_cgroup(page);
+ if (unlikely(!pc || !PageCgroupUsed(pc)))
+ return;
- VM_BUG_ON(pc->page != page);
+ lock_page_cgroup(pc);
- if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
- && ((pc->flags & PAGE_CGROUP_FLAG_CACHE)
- || page_mapped(page)))
- goto unlock;
+ if (!PageCgroupUsed(pc))
+ goto unlock_out;
+
+ switch (ctype) {
+ case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+ if (page_mapped(page))
+ goto unlock_out;
+ break;
+ case MEM_CGROUP_CHARGE_TYPE_SWAPOUT:
+ if (!PageAnon(page)) { /* Shared memory */
+ if (page->mapping && !page_is_file_cache(page))
+ goto unlock_out;
+ } else if (page_mapped(page)) /* Anon */
+ goto unlock_out;
+ break;
+ default:
+ break;
+ }
+
+ 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);
+
+unlock_out:
+ unlock_page_cgroup(pc);
+ return;
}
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);
}
__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
}
+void mem_cgroup_uncharge_swapcache(struct page *page)
+{
+ __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_SWAPOUT);
+}
+
/*
- * Before starting migration, account against new page.
+ * Before starting migration, account PAGE_SIZE to mem_cgroup that the old
+ * page belongs to.
*/
-int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
+int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
{
struct page_cgroup *pc;
struct mem_cgroup *mem = NULL;
- enum charge_type ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
int ret = 0;
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 (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);
+ ret = mem_cgroup_try_charge(NULL, GFP_HIGHUSER_MOVABLE, &mem);
css_put(&mem->css);
}
+ *ptr = mem;
return ret;
}
/* remove redundant charge if migration failed*/
-void mem_cgroup_end_migration(struct page *newpage)
+void mem_cgroup_end_migration(struct mem_cgroup *mem,
+ struct page *oldpage, struct page *newpage)
{
+ struct page *target, *unused;
+ struct page_cgroup *pc;
+ enum charge_type ctype;
+
+ if (!mem)
+ return;
+
+ /* at migration success, oldpage->mapping is NULL. */
+ if (oldpage->mapping) {
+ target = oldpage;
+ unused = NULL;
+ } else {
+ target = newpage;
+ unused = oldpage;
+ }
+
+ if (PageAnon(target))
+ ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
+ else if (page_is_file_cache(target))
+ ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+ else
+ ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
+
+ /* unused page is not on radix-tree now. */
+ if (unused)
+ __mem_cgroup_uncharge_common(unused, ctype);
+
+ pc = lookup_page_cgroup(target);
/*
- * At success, page->mapping is not NULL.
- * special rollback care is necessary when
- * 1. at migration failure. (newpage->mapping is cleared in this case)
- * 2. the newpage was moved but not remapped again because the task
- * exits and the newpage is obsolete. In this case, the new page
- * may be a swapcache. So, we just call mem_cgroup_uncharge_page()
- * always for avoiding mess. The page_cgroup will be removed if
- * unnecessary. File cache pages is still on radix-tree. Don't
- * care it.
+ * __mem_cgroup_commit_charge() check PCG_USED bit of page_cgroup.
+ * So, double-counting is effectively avoided.
+ */
+ __mem_cgroup_commit_charge(mem, pc, ctype);
+
+ /*
+ * Both of oldpage and newpage are still under lock_page().
+ * Then, we don't have to care about race in radix-tree.
+ * But we have to be careful that this page is unmapped or not.
+ *
+ * There is a case for !page_mapped(). At the start of
+ * migration, oldpage was mapped. But now, it's zapped.
+ * But we know *target* page is not freed/reused under us.
+ * mem_cgroup_uncharge_page() does all necessary checks.
*/
- if (!newpage->mapping)
- __mem_cgroup_uncharge_common(newpage,
- MEM_CGROUP_CHARGE_TYPE_FORCE);
- else if (PageAnon(newpage))
- mem_cgroup_uncharge_page(newpage);
+ if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
+ mem_cgroup_uncharge_page(target);
}
/*
return 0;
}
-int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val)
+static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
+ unsigned long long val)
{
int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
ret = -EBUSY;
break;
}
- progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL);
+ progress = try_to_free_mem_cgroup_pages(memcg,
+ GFP_HIGHUSER_MOVABLE);
if (!progress)
retry_count--;
}
* This routine traverse page_cgroup in given list and drop them all.
* *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 int mem_cgroup_force_empty_list(struct mem_cgroup *mem,
struct mem_cgroup_per_zone *mz,
enum lru_list lru)
{
- struct page_cgroup *pc;
- struct page *page;
- int count = FORCE_UNCHARGE_BATCH;
+ struct page_cgroup *pc, *busy;
unsigned long flags;
+ unsigned long loop;
struct list_head *list;
+ int ret = 0;
list = &mz->lists[lru];
- spin_lock_irqsave(&mz->lru_lock, flags);
- while (!list_empty(list)) {
+ loop = MEM_CGROUP_ZSTAT(mz, lru);
+ /* give some margin against EBUSY etc...*/
+ loop += 256;
+ busy = NULL;
+ while (loop--) {
+ ret = 0;
+ spin_lock_irqsave(&mz->lru_lock, flags);
+ if (list_empty(list)) {
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+ break;
+ }
pc = list_entry(list->prev, struct page_cgroup, lru);
- page = pc->page;
- get_page(page);
+ if (busy == pc) {
+ list_move(&pc->lru, list);
+ busy = 0;
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+ continue;
+ }
spin_unlock_irqrestore(&mz->lru_lock, flags);
- /*
- * Check if this page is on LRU. !LRU page can be found
- * if it's under page migration.
- */
- if (PageLRU(page)) {
- __mem_cgroup_uncharge_common(page,
- MEM_CGROUP_CHARGE_TYPE_FORCE);
- put_page(page);
- if (--count <= 0) {
- count = FORCE_UNCHARGE_BATCH;
- cond_resched();
- }
- } else
+
+ ret = mem_cgroup_move_parent(pc, mem, GFP_HIGHUSER_MOVABLE);
+ if (ret == -ENOMEM)
+ break;
+
+ if (ret == -EBUSY || ret == -EINVAL) {
+ /* found lock contention or "pc" is obsolete. */
+ busy = pc;
cond_resched();
- spin_lock_irqsave(&mz->lru_lock, flags);
+ } else
+ busy = NULL;
}
- spin_unlock_irqrestore(&mz->lru_lock, flags);
+ if (!ret && !list_empty(list))
+ return -EBUSY;
+ return ret;
}
/*
* make mem_cgroup's charge to be 0 if there is no task.
* This enables deleting this mem_cgroup.
*/
-static int mem_cgroup_force_empty(struct mem_cgroup *mem)
+static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all)
{
- int ret = -EBUSY;
- int node, zid;
+ int ret;
+ int node, zid, shrink;
+ int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+ struct cgroup *cgrp = mem->css.cgroup;
css_get(&mem->css);
- /*
- * page reclaim code (kswapd etc..) will move pages between
- * active_list <-> inactive_list while we don't take a lock.
- * So, we have to do loop here until all lists are empty.
- */
+
+ shrink = 0;
+ /* should free all ? */
+ if (free_all)
+ goto try_to_free;
+move_account:
while (mem->res.usage > 0) {
- if (atomic_read(&mem->css.cgroup->count) > 0)
+ ret = -EBUSY;
+ if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
+ goto out;
+ ret = -EINTR;
+ if (signal_pending(current))
goto out;
- for_each_node_state(node, N_POSSIBLE)
- for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+ /* This is for making all *used* pages to be on LRU. */
+ lru_add_drain_all();
+ ret = 0;
+ for_each_node_state(node, N_POSSIBLE) {
+ for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
struct mem_cgroup_per_zone *mz;
enum lru_list l;
mz = mem_cgroup_zoneinfo(mem, node, zid);
- for_each_lru(l)
- mem_cgroup_force_empty_list(mem, mz, l);
+ for_each_lru(l) {
+ ret = mem_cgroup_force_empty_list(mem,
+ mz, l);
+ if (ret)
+ break;
+ }
}
+ if (ret)
+ break;
+ }
+ /* it seems parent cgroup doesn't have enough mem */
+ if (ret == -ENOMEM)
+ goto try_to_free;
+ cond_resched();
}
ret = 0;
out:
css_put(&mem->css);
return ret;
+
+try_to_free:
+ /* returns EBUSY if there is a task or if we come here twice. */
+ if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children) || shrink) {
+ ret = -EBUSY;
+ goto out;
+ }
+ /* we call try-to-free pages for make this cgroup empty */
+ lru_add_drain_all();
+ /* try to free all pages in this cgroup */
+ shrink = 1;
+ while (nr_retries && mem->res.usage > 0) {
+ int progress;
+
+ if (signal_pending(current)) {
+ ret = -EINTR;
+ goto out;
+ }
+ progress = try_to_free_mem_cgroup_pages(mem,
+ GFP_HIGHUSER_MOVABLE);
+ if (!progress) {
+ nr_retries--;
+ /* maybe some writeback is necessary */
+ congestion_wait(WRITE, HZ/10);
+ }
+
+ }
+ /* try move_account...there may be some *locked* pages. */
+ if (mem->res.usage)
+ goto move_account;
+ ret = 0;
+ goto out;
+}
+
+int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
+{
+ return mem_cgroup_force_empty(mem_cgroup_from_cont(cont), true);
}
+
static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
{
return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res,
return 0;
}
-static int mem_force_empty_write(struct cgroup *cont, unsigned int event)
-{
- return mem_cgroup_force_empty(mem_cgroup_from_cont(cont));
-}
-
static const struct mem_cgroup_stat_desc {
const char *msg;
u64 unit;
return 0;
}
+
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
.read_u64 = mem_cgroup_read,
},
{
- .name = "force_empty",
- .trigger = mem_force_empty_write,
- },
- {
.name = "stat",
.read_map = mem_control_stat_show,
},
+ {
+ .name = "force_empty",
+ .trigger = mem_cgroup_force_empty_write,
+ },
};
static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
kfree(mem->info.nodeinfo[node]);
}
+static int mem_cgroup_size(void)
+{
+ int cpustat_size = nr_cpu_ids * sizeof(struct mem_cgroup_stat_cpu);
+ return sizeof(struct mem_cgroup) + cpustat_size;
+}
+
static struct mem_cgroup *mem_cgroup_alloc(void)
{
struct mem_cgroup *mem;
+ int size = mem_cgroup_size();
- if (sizeof(*mem) < PAGE_SIZE)
- mem = kmalloc(sizeof(*mem), GFP_KERNEL);
+ if (size < PAGE_SIZE)
+ mem = kmalloc(size, GFP_KERNEL);
else
- mem = vmalloc(sizeof(*mem));
+ mem = vmalloc(size);
if (mem)
- memset(mem, 0, sizeof(*mem));
+ memset(mem, 0, size);
return mem;
}
static void mem_cgroup_free(struct mem_cgroup *mem)
{
- if (sizeof(*mem) < PAGE_SIZE)
+ if (mem_cgroup_size() < PAGE_SIZE)
kfree(mem);
else
vfree(mem);
}
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+static void __init enable_swap_cgroup(void)
+{
+ if (!mem_cgroup_subsys.disabled && really_do_swap_account)
+ do_swap_account = 1;
+}
+#else
+static void __init enable_swap_cgroup(void)
+{
+}
+#endif
+
static struct cgroup_subsys_state *
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
struct mem_cgroup *mem;
int node;
- 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)
- return ERR_PTR(-ENOMEM);
- }
+ mem = mem_cgroup_alloc();
+ if (!mem)
+ return ERR_PTR(-ENOMEM);
res_counter_init(&mem->res);
for_each_node_state(node, N_POSSIBLE)
if (alloc_mem_cgroup_per_zone_info(mem, node))
goto free_out;
+ /* root ? */
+ if (cont->parent == NULL)
+ enable_swap_cgroup();
return &mem->css;
free_out:
for_each_node_state(node, N_POSSIBLE)
free_mem_cgroup_per_zone_info(mem, node);
- if (cont->parent != NULL)
- mem_cgroup_free(mem);
+ mem_cgroup_free(mem);
return ERR_PTR(-ENOMEM);
}
struct cgroup *cont)
{
struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
- mem_cgroup_force_empty(mem);
+ mem_cgroup_force_empty(mem, false);
}
static void mem_cgroup_destroy(struct cgroup_subsys *ss,
.attach = mem_cgroup_move_task,
.early_init = 0,
};
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+
+static int __init disable_swap_account(char *s)
+{
+ really_do_swap_account = 0;
+ return 1;
+}
+__setup("noswapaccount", disable_swap_account);
+#endif
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff