X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmemcontrol.c;h=0f1f7a7374bade23cf0052719a349a97322c5af4;hb=8c8bee1d7ca47fc75b6bd24a8085c525a2394c02;hp=315dee18012943541300d0a7003512058c5f0b9a;hpb=072c56c13e1302fcdc39961dc64e76485731ad67;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 315dee1..0f1f7a7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -26,15 +26,18 @@ #include #include #include +#include #include #include #include #include +#include #include -struct cgroup_subsys mem_cgroup_subsys; -static const int MEM_CGROUP_RECLAIM_RETRIES = 5; +struct cgroup_subsys mem_cgroup_subsys __read_mostly; +static struct kmem_cache *page_cgroup_cache __read_mostly; +#define MEM_CGROUP_RECLAIM_RETRIES 5 /* * Statistics for memory cgroup. @@ -45,6 +48,8 @@ enum mem_cgroup_stat_index { */ MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */ + MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */ + MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */ MEM_CGROUP_STAT_NSTATS, }; @@ -131,21 +136,27 @@ struct mem_cgroup { */ struct mem_cgroup_lru_info info; - unsigned long control_type; /* control RSS or RSS+Pagecache */ int prev_priority; /* for recording reclaim priority */ /* * statistics. */ 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 @@ -155,37 +166,27 @@ struct page_cgroup { 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 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, + MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */ }; - /* * Always modified under lru lock. Then, not necessary to preempt_disable() */ @@ -194,23 +195,28 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags, { 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); + + if (charge) + __mem_cgroup_stat_add_safe(stat, + MEM_CGROUP_STAT_PGPGIN_COUNT, 1); + else + __mem_cgroup_stat_add_safe(stat, + MEM_CGROUP_STAT_PGPGOUT_COUNT, 1); } -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; @@ -235,120 +241,54 @@ static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem, 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) { return container_of(task_subsys_state(p, mem_cgroup_subsys_id), struct mem_cgroup, css); } -void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p) -{ - struct mem_cgroup *mem; - - mem = mem_cgroup_from_task(p); - css_get(&mem->css); - mm->mem_cgroup = mem; -} - -void mm_free_cgroup(struct mm_struct *mm) -{ - css_put(&mm->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) +static int try_lock_page_cgroup(struct page *page) { - bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup); + return bit_spin_trylock(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 void unlock_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; -} - -/* - * 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) -{ - 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) +static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz, + struct page_cgroup *pc) { int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE; - struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc); if (from) MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1; @@ -356,13 +296,13 @@ static void __mem_cgroup_remove_list(struct page_cgroup *pc) MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1; mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, false); - list_del_init(&pc->lru); + list_del(&pc->lru); } -static void __mem_cgroup_add_list(struct page_cgroup *pc) +static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz, + struct page_cgroup *pc) { int to = pc->flags & PAGE_CGROUP_FLAG_ACTIVE; - struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc); if (!to) { MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1; @@ -400,7 +340,7 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) 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; } @@ -408,18 +348,33 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) /* * 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) + if (mem_cgroup_subsys.disabled) 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); + /* + * 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; + + 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); } /* @@ -438,6 +393,7 @@ int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem) 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 @@ -501,7 +457,6 @@ long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem, 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); } @@ -522,6 +477,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, int zid = zone_idx(z); struct mem_cgroup_per_zone *mz; + BUG_ON(!mem_cont); mz = mem_cgroup_zoneinfo(mem_cont, nid, zid); if (active) src = &mz->active_list; @@ -535,7 +491,6 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, if (scan >= nr_to_scan) break; page = pc->page; - VM_BUG_ON(!pc); if (unlikely(!PageLRU(page))) continue; @@ -572,7 +527,8 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, * < 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) + gfp_t gfp_mask, enum charge_type ctype, + struct mem_cgroup *memcg) { struct mem_cgroup *mem; struct page_cgroup *pc; @@ -580,37 +536,8 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES; struct mem_cgroup_per_zone *mz; - /* - * Should page_cgroup's go to their own slab? - * One could optimize the performance of the charging routine - * by saving a bit in the page_flags and using it as a lock - * to see if the cgroup page already has a page_cgroup associated - * 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; - } - } - unlock_page_cgroup(page); - } - - pc = kzalloc(sizeof(struct page_cgroup), gfp_mask); - if (pc == NULL) + pc = kmem_cache_alloc(page_cgroup_cache, gfp_mask); + if (unlikely(pc == NULL)) goto err; /* @@ -619,22 +546,19 @@ retry: * thread group leader migrates. It's possible that mm is not * set, if so charge the init_mm (happens for pagecache usage). */ - if (!mm) - mm = &init_mm; - - rcu_read_lock(); - mem = rcu_dereference(mm->mem_cgroup); - /* - * For every charge from the cgroup, increment reference - * count - */ - css_get(&mem->css); - rcu_read_unlock(); + if (likely(!memcg)) { + rcu_read_lock(); + mem = mem_cgroup_from_task(rcu_dereference(mm->owner)); + /* + * For every charge from the cgroup, increment reference count + */ + css_get(&mem->css); + rcu_read_unlock(); + } else { + mem = memcg; + css_get(&memcg->css); + } - /* - * 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; @@ -643,12 +567,12 @@ retry: 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; @@ -656,184 +580,276 @@ retry: mem_cgroup_out_of_memory(mem, gfp_mask); goto out; } - congestion_wait(WRITE, HZ/10); } - atomic_set(&pc->ref_cnt, 1); pc->mem_cgroup = mem; pc->page = page; - pc->flags = PAGE_CGROUP_FLAG_ACTIVE; + /* + * 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; + pc->flags = PAGE_CGROUP_FLAG_CACHE; + else + pc->flags = PAGE_CGROUP_FLAG_ACTIVE; - if (!page || page_cgroup_assign_new_page_cgroup(page, pc)) { - /* - * Another charge has been added to this page already. - * We take lock_page_cgroup(page) again and read - * page->cgroup, increment refcnt.... just retry is OK. - */ + 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); - kfree(pc); - if (!page) - goto done; - goto retry; + kmem_cache_free(page_cgroup_cache, pc); + goto done; } + 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); + __mem_cgroup_add_list(mz, pc); spin_unlock_irqrestore(&mz->lru_lock, flags); + unlock_page_cgroup(page); done: return 0; out: css_put(&mem->css); - kfree(pc); + kmem_cache_free(page_cgroup_cache, pc); err: 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) { + if (mem_cgroup_subsys.disabled) + return 0; + + /* + * If already mapped, we don't have to account. + * If page cache, page->mapping has address_space. + * But page->mapping may have out-of-use anon_vma pointer, + * detecit it by PageAnon() check. newly-mapped-anon's page->mapping + * is NULL. + */ + if (page_mapped(page) || (page->mapping && !PageAnon(page))) + return 0; + if (unlikely(!mm)) + mm = &init_mm; return mem_cgroup_charge_common(page, mm, gfp_mask, - MEM_CGROUP_CHARGE_TYPE_MAPPED); + MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL); } -/* - * 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; - struct mem_cgroup *mem; - if (!mm) + if (mem_cgroup_subsys.disabled) + 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 + * and call add_to_page_cache() with GFP_NOWAIT. + * + * For GFP_NOWAIT case, the page may be pre-charged before calling + * add_to_page_cache(). (See shmem.c) check it here and avoid to call + * charge twice. (It works but has to pay a bit larger cost.) + */ + 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); + return 0; + } + unlock_page_cgroup(page); + } + + if (unlikely(!mm)) mm = &init_mm; - rcu_read_lock(); - mem = rcu_dereference(mm->mem_cgroup); - css_get(&mem->css); - rcu_read_unlock(); - if (mem->control_type == MEM_CGROUP_TYPE_ALL) - ret = mem_cgroup_charge_common(page, mm, gfp_mask, - MEM_CGROUP_CHARGE_TYPE_CACHE); - css_put(&mem->css); - return ret; + return mem_cgroup_charge_common(page, mm, gfp_mask, + MEM_CGROUP_CHARGE_TYPE_CACHE, NULL); } /* - * Uncharging is always a welcome operation, we never complain, simply - * uncharge. + * uncharge if !page_mapped(page) */ -void mem_cgroup_uncharge(struct page_cgroup *pc) +static void +__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) { + struct page_cgroup *pc; struct mem_cgroup *mem; struct mem_cgroup_per_zone *mz; - struct page *page; unsigned long flags; + if (mem_cgroup_subsys.disabled) + return; + /* - * This can handle cases when a page is not charged at all and we - * are switching between handling the control_type. + * Check if our page_cgroup is valid */ - if (!pc) - return; + lock_page_cgroup(page); + pc = page_get_page_cgroup(page); + if (unlikely(!pc)) + goto unlock; - if (atomic_dec_and_test(&pc->ref_cnt)) { - page = pc->page; - mz = page_cgroup_zoneinfo(pc); - /* - * get page->cgroup and clear it under lock. - * force_empty can drop page->cgroup without checking refcnt. - */ - 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); - } - } + VM_BUG_ON(pc->page != page); + + if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED) + && ((pc->flags & PAGE_CGROUP_FLAG_CACHE) + || page_mapped(page))) + goto unlock; + + 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); + + 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) +{ + __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)); + __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE); } /* - * Returns non-zero if a page (under migration) has valid page_cgroup member. - * Refcnt of page_cgroup is incremented. + * Before starting migration, account against new page. */ - -int mem_cgroup_prepare_migration(struct page *page) +int mem_cgroup_prepare_migration(struct page *page, struct page *newpage) { 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 && atomic_inc_not_zero(&pc->ref_cnt)) - ret = 1; + if (pc) { + mem = pc->mem_cgroup; + css_get(&mem->css); + if (pc->flags & PAGE_CGROUP_FLAG_CACHE) + ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; + } unlock_page_cgroup(page); + if (mem) { + ret = mem_cgroup_charge_common(newpage, NULL, GFP_KERNEL, + ctype, mem); + css_put(&mem->css); + } return ret; } -void mem_cgroup_end_migration(struct page *page) +/* remove redundant charge if migration failed*/ +void mem_cgroup_end_migration(struct page *newpage) { - struct page_cgroup *pc = page_get_page_cgroup(page); - mem_cgroup_uncharge(pc); + /* + * 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. + */ + if (!newpage->mapping) + __mem_cgroup_uncharge_common(newpage, + MEM_CGROUP_CHARGE_TYPE_FORCE); + else if (PageAnon(newpage)) + mem_cgroup_uncharge_page(newpage); } + /* - * 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. + * A call to try to shrink memory usage under specified resource controller. + * This is typically used for page reclaiming for shmem for reducing side + * effect of page allocation from shmem, which is used by some mem_cgroup. */ - -void mem_cgroup_page_migration(struct page *page, struct page *newpage) +int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask) { - struct page_cgroup *pc; struct mem_cgroup *mem; - unsigned long flags; - struct mem_cgroup_per_zone *mz; -retry: - pc = page_get_page_cgroup(page); - if (!pc) - 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); + int progress = 0; + int retry = MEM_CGROUP_RECLAIM_RETRIES; - __mem_cgroup_remove_list(pc); - spin_unlock_irqrestore(&mz->lru_lock, flags); + if (mem_cgroup_subsys.disabled) + return 0; + if (!mm) + return 0; + + rcu_read_lock(); + mem = mem_cgroup_from_task(rcu_dereference(mm->owner)); + css_get(&mem->css); + rcu_read_unlock(); - pc->page = newpage; - lock_page_cgroup(newpage); - page_assign_page_cgroup(newpage, pc); - unlock_page_cgroup(newpage); + do { + progress = try_to_free_mem_cgroup_pages(mem, gfp_mask); + } while (!progress && --retry); - 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; + css_put(&mem->css); + if (!retry) + return -ENOMEM; + return 0; } +int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val) +{ + + int retry_count = MEM_CGROUP_RECLAIM_RETRIES; + int progress; + int ret = 0; + + while (res_counter_set_limit(&memcg->res, val)) { + if (signal_pending(current)) { + ret = -EINTR; + break; + } + if (!retry_count) { + ret = -EBUSY; + break; + } + progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL); + if (!progress) + retry_count--; + } + return ret; +} + + /* * This routine traverse page_cgroup in given list and drop them all. - * This routine ignores page_cgroup->ref_cnt. * *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; @@ -842,46 +858,44 @@ mem_cgroup_force_empty_list(struct mem_cgroup *mem, 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); + /* + * 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 + 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) { @@ -903,131 +917,70 @@ out: return ret; } - - -int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp) -{ - *tmp = memparse(buf, &buf); - if (*buf != '\0') - return -EINVAL; - - /* - * Round up the value to the closest page size - */ - *tmp = ((*tmp + PAGE_SIZE - 1) >> PAGE_SHIFT) << PAGE_SHIFT; - return 0; -} - -static ssize_t mem_cgroup_read(struct cgroup *cont, - struct cftype *cft, struct file *file, - char __user *userbuf, size_t nbytes, loff_t *ppos) -{ - return res_counter_read(&mem_cgroup_from_cont(cont)->res, - cft->private, userbuf, nbytes, ppos, - NULL); -} - -static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft, - struct file *file, const char __user *userbuf, - size_t nbytes, loff_t *ppos) +static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) { - return res_counter_write(&mem_cgroup_from_cont(cont)->res, - cft->private, userbuf, nbytes, ppos, - mem_cgroup_write_strategy); + return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res, + cft->private); } - -static ssize_t mem_control_type_write(struct cgroup *cont, - struct cftype *cft, struct file *file, - const char __user *userbuf, - size_t nbytes, loff_t *pos) +/* + * The user of this function is... + * RES_LIMIT. + */ +static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, + const char *buffer) { + struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + unsigned long long val; int ret; - char *buf, *end; - unsigned long tmp; - struct mem_cgroup *mem; - - mem = mem_cgroup_from_cont(cont); - buf = kmalloc(nbytes + 1, GFP_KERNEL); - ret = -ENOMEM; - if (buf == NULL) - goto out; - - buf[nbytes] = 0; - ret = -EFAULT; - if (copy_from_user(buf, userbuf, nbytes)) - goto out_free; - ret = -EINVAL; - tmp = simple_strtoul(buf, &end, 10); - if (*end != '\0') - goto out_free; - - if (tmp <= MEM_CGROUP_TYPE_UNSPEC || tmp >= MEM_CGROUP_TYPE_MAX) - goto out_free; - - mem->control_type = tmp; - ret = nbytes; -out_free: - kfree(buf); -out: + switch (cft->private) { + case RES_LIMIT: + /* This function does all necessary parse...reuse it */ + ret = res_counter_memparse_write_strategy(buffer, &val); + if (!ret) + ret = mem_cgroup_resize_limit(memcg, val); + break; + default: + ret = -EINVAL; /* should be BUG() ? */ + break; + } return ret; } -static ssize_t mem_control_type_read(struct cgroup *cont, - struct cftype *cft, - struct file *file, char __user *userbuf, - size_t nbytes, loff_t *ppos) +static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) { - unsigned long val; - char buf[64], *s; struct mem_cgroup *mem; mem = mem_cgroup_from_cont(cont); - s = buf; - val = mem->control_type; - s += sprintf(s, "%lu\n", val); - return simple_read_from_buffer((void __user *)userbuf, nbytes, - ppos, buf, s - buf); -} - - -static ssize_t mem_force_empty_write(struct cgroup *cont, - struct cftype *cft, struct file *file, - const char __user *userbuf, - size_t nbytes, loff_t *ppos) -{ - struct mem_cgroup *mem = mem_cgroup_from_cont(cont); - int ret; - ret = mem_cgroup_force_empty(mem); - if (!ret) - ret = nbytes; - return ret; + switch (event) { + case RES_MAX_USAGE: + res_counter_reset_max(&mem->res); + break; + case RES_FAILCNT: + res_counter_reset_failcnt(&mem->res); + break; + } + return 0; } -/* - * 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, - size_t nbytes, loff_t *ppos) +static int mem_force_empty_write(struct cgroup *cont, unsigned int event) { - return -EINVAL; + return mem_cgroup_force_empty(mem_cgroup_from_cont(cont)); } - static const struct mem_cgroup_stat_desc { const char *msg; u64 unit; } mem_cgroup_stat_desc[] = { [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, }, [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, }, + [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, }, + [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, }, }; -static int mem_control_stat_show(struct seq_file *m, void *arg) +static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, + struct cgroup_map_cb *cb) { - struct cgroup *cont = m->private; struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont); struct mem_cgroup_stat *stat = &mem_cont->stat; int i; @@ -1037,8 +990,7 @@ static int mem_control_stat_show(struct seq_file *m, void *arg) val = mem_cgroup_read_stat(stat, i); val *= mem_cgroup_stat_desc[i].unit; - seq_printf(m, "%s %lld\n", mem_cgroup_stat_desc[i].msg, - (long long)val); + cb->fill(cb, mem_cgroup_stat_desc[i].msg, val); } /* showing # of active pages */ { @@ -1048,59 +1000,43 @@ static int mem_control_stat_show(struct seq_file *m, void *arg) MEM_CGROUP_ZSTAT_INACTIVE); active = mem_cgroup_get_all_zonestat(mem_cont, MEM_CGROUP_ZSTAT_ACTIVE); - seq_printf(m, "active %ld\n", (active) * PAGE_SIZE); - seq_printf(m, "inactive %ld\n", (inactive) * PAGE_SIZE); + cb->fill(cb, "active", (active) * PAGE_SIZE); + cb->fill(cb, "inactive", (inactive) * PAGE_SIZE); } return 0; } -static const struct file_operations mem_control_stat_file_operations = { - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int mem_control_stat_open(struct inode *unused, struct file *file) -{ - /* XXX __d_cont */ - struct cgroup *cont = file->f_dentry->d_parent->d_fsdata; - - file->f_op = &mem_control_stat_file_operations; - return single_open(file, mem_control_stat_show, cont); -} - - - static struct cftype mem_cgroup_files[] = { { .name = "usage_in_bytes", .private = RES_USAGE, - .read = mem_cgroup_read, + .read_u64 = mem_cgroup_read, + }, + { + .name = "max_usage_in_bytes", + .private = RES_MAX_USAGE, + .trigger = mem_cgroup_reset, + .read_u64 = mem_cgroup_read, }, { .name = "limit_in_bytes", .private = RES_LIMIT, - .write = mem_cgroup_write, - .read = mem_cgroup_read, + .write_string = mem_cgroup_write, + .read_u64 = mem_cgroup_read, }, { .name = "failcnt", .private = RES_FAILCNT, - .read = mem_cgroup_read, - }, - { - .name = "control_type", - .write = mem_control_type_write, - .read = mem_control_type_read, + .trigger = mem_cgroup_reset, + .read_u64 = mem_cgroup_read, }, { .name = "force_empty", - .write = mem_force_empty_write, - .read = mem_force_empty_read, + .trigger = mem_force_empty_write, }, { .name = "stat", - .open = mem_control_stat_open, + .read_map = mem_control_stat_show, }, }; @@ -1108,7 +1044,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) { struct mem_cgroup_per_node *pn; struct mem_cgroup_per_zone *mz; - int zone; + int zone, tmp = node; /* * This routine is called against possible nodes. * But it's BUG to call kmalloc() against offline node. @@ -1117,10 +1053,9 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) * never be onlined. It's better to use memory hotplug callback * function. */ - if (node_state(node, N_HIGH_MEMORY)) - pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, node); - else - pn = kmalloc(sizeof(*pn), GFP_KERNEL); + if (!node_state(node, N_NORMAL_MEMORY)) + tmp = -1; + pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, tmp); if (!pn) return 1; @@ -1141,8 +1076,28 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) kfree(mem->info.nodeinfo[node]); } +static struct mem_cgroup *mem_cgroup_alloc(void) +{ + struct mem_cgroup *mem; + + if (sizeof(*mem) < PAGE_SIZE) + mem = kmalloc(sizeof(*mem), GFP_KERNEL); + else + mem = vmalloc(sizeof(*mem)); + + if (mem) + memset(mem, 0, sizeof(*mem)); + return mem; +} + +static void mem_cgroup_free(struct mem_cgroup *mem) +{ + if (sizeof(*mem) < PAGE_SIZE) + kfree(mem); + else + vfree(mem); +} -static struct mem_cgroup init_mem_cgroup; static struct cgroup_subsys_state * mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) @@ -1152,18 +1107,15 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) if (unlikely((cont->parent) == NULL)) { mem = &init_mem_cgroup; - init_mm.mem_cgroup = mem; - } else - mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL); - - if (mem == NULL) - return NULL; + page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC); + } else { + mem = mem_cgroup_alloc(); + if (!mem) + return ERR_PTR(-ENOMEM); + } res_counter_init(&mem->res); - mem->control_type = MEM_CGROUP_TYPE_ALL; - memset(&mem->info, 0, sizeof(mem->info)); - for_each_node_state(node, N_POSSIBLE) if (alloc_mem_cgroup_per_zone_info(mem, node)) goto free_out; @@ -1173,8 +1125,8 @@ free_out: for_each_node_state(node, N_POSSIBLE) free_mem_cgroup_per_zone_info(mem, node); if (cont->parent != NULL) - kfree(mem); - return NULL; + mem_cgroup_free(mem); + return ERR_PTR(-ENOMEM); } static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss, @@ -1193,7 +1145,7 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss, for_each_node_state(node, N_POSSIBLE) free_mem_cgroup_per_zone_info(mem, node); - kfree(mem_cgroup_from_cont(cont)); + mem_cgroup_free(mem_cgroup_from_cont(cont)); } static int mem_cgroup_populate(struct cgroup_subsys *ss, @@ -1218,23 +1170,15 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss, mem = mem_cgroup_from_cont(cont); old_mem = mem_cgroup_from_cont(old_cont); - if (mem == old_mem) - goto out; - /* * 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); - rcu_assign_pointer(mm->mem_cgroup, mem); - css_put(&old_mem->css); - out: mmput(mm); - return; } struct cgroup_subsys mem_cgroup_subsys = {