X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmemcontrol.c;h=c5285afe2048985f0c61d1a0430522107adf7c38;hb=4a56d02e34baedbea5eb1fd558f2b856b8c7db1e;hp=1637575d33390e44a48739731a094c51ed340c1e;hpb=6d12e2d8ddbe653d80ea4f71578481c1bc933025;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1637575..c5285af 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -35,6 +36,7 @@ struct cgroup_subsys mem_cgroup_subsys; static const int MEM_CGROUP_RECLAIM_RETRIES = 5; +static struct kmem_cache *page_cgroup_cache; /* * Statistics for memory cgroup. @@ -89,6 +91,12 @@ enum mem_cgroup_zstat_index { }; struct mem_cgroup_per_zone { + /* + * spin_lock to protect the per cgroup LRU + */ + spinlock_t lru_lock; + struct list_head active_list; + struct list_head inactive_list; unsigned long count[NR_MEM_CGROUP_ZSTAT]; }; /* Macro for accessing counter */ @@ -122,29 +130,30 @@ struct mem_cgroup { /* * Per cgroup active and inactive list, similar to the * per zone LRU lists. - * TODO: Consider making these lists per zone */ - struct list_head active_list; - struct list_head inactive_list; struct mem_cgroup_lru_info info; - /* - * spin_lock to protect the per cgroup LRU - */ - spinlock_t lru_lock; - 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 @@ -154,37 +163,27 @@ 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 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() */ @@ -193,23 +192,21 @@ 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); } -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; @@ -234,120 +231,54 @@ 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) -{ - 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) +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; @@ -358,17 +289,17 @@ static void __mem_cgroup_remove_list(struct page_cgroup *pc) list_del_init(&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; - list_add(&pc->lru, &pc->mem_cgroup->inactive_list); + list_add(&pc->lru, &mz->inactive_list); } else { MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1; - list_add(&pc->lru, &pc->mem_cgroup->active_list); + list_add(&pc->lru, &mz->active_list); } mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true); } @@ -386,11 +317,11 @@ static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active) if (active) { MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1; pc->flags |= PAGE_CGROUP_FLAG_ACTIVE; - list_move(&pc->lru, &pc->mem_cgroup->active_list); + list_move(&pc->lru, &mz->active_list); } else { MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1; pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE; - list_move(&pc->lru, &pc->mem_cgroup->inactive_list); + list_move(&pc->lru, &mz->inactive_list); } } @@ -399,7 +330,7 @@ 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; } @@ -407,17 +338,113 @@ 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 mem_cgroup *mem; - if (!pc) + struct page_cgroup *pc; + struct mem_cgroup_per_zone *mz; + unsigned long 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; - mem = pc->mem_cgroup; + 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); +} + +/* + * Calculate mapped_ratio under memory controller. This will be used in + * vmscan.c for deteremining we have to reclaim mapped pages. + */ +int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem) +{ + long total, rss; + + /* + * usage is recorded in bytes. But, here, we assume the number of + * physical pages can be represented by "long" on any arch. + */ + total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L; + 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 + * page reclaiming, we should use using mem_cgroup's imbalance rather than + * zone's global lru imbalance. + */ +long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem) +{ + unsigned long active, inactive; + /* active and inactive are the number of pages. 'long' is ok.*/ + active = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_ACTIVE); + inactive = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_INACTIVE); + return (long) (active / (inactive + 1)); +} + +/* + * prev_priority control...this will be used in memory reclaim path. + */ +int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem) +{ + return mem->prev_priority; +} + +void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority) +{ + if (priority < mem->prev_priority) + mem->prev_priority = priority; +} + +void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority) +{ + mem->prev_priority = priority; +} + +/* + * Calculate # of pages to be scanned in this priority/zone. + * See also vmscan.c + * + * priority starts from "DEF_PRIORITY" and decremented in each loop. + * (see include/linux/mmzone.h) + */ + +long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem, + struct zone *zone, int priority) +{ + long nr_active; + int nid = zone->zone_pgdat->node_id; + int zid = zone_idx(zone); + struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid); + + nr_active = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE); + return (nr_active >> priority); +} + +long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem, + struct zone *zone, int priority) +{ + long nr_inactive; + int nid = zone->zone_pgdat->node_id; + int zid = zone_idx(zone); + struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid); - spin_lock(&mem->lru_lock); - __mem_cgroup_move_lists(pc, active); - spin_unlock(&mem->lru_lock); + nr_inactive = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE); + return (nr_inactive >> priority); } unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, @@ -433,19 +460,24 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, LIST_HEAD(pc_list); struct list_head *src; struct page_cgroup *pc, *tmp; + int nid = z->zone_pgdat->node_id; + 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 = &mem_cont->active_list; + src = &mz->active_list; else - src = &mem_cont->inactive_list; + src = &mz->inactive_list; - spin_lock(&mem_cont->lru_lock); + + spin_lock(&mz->lru_lock); scan = 0; list_for_each_entry_safe_reverse(pc, tmp, src, lru) { if (scan >= nr_to_scan) break; page = pc->page; - VM_BUG_ON(!pc); if (unlikely(!PageLRU(page))) continue; @@ -459,13 +491,6 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, continue; } - /* - * Reclaim, per zone - * TODO: make the active/inactive lists per zone - */ - if (page_zone(page) != z) - continue; - scan++; list_move(&pc->lru, &pc_list); @@ -476,7 +501,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, } list_splice(&pc_list, src); - spin_unlock(&mem_cont->lru_lock); + spin_unlock(&mz->lru_lock); *scanned = scan; return nr_taken; @@ -495,6 +520,10 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, struct page_cgroup *pc; unsigned long flags; unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES; + struct mem_cgroup_per_zone *mz; + + if (mem_cgroup_subsys.disabled) + return 0; /* * Should page_cgroup's go to their own slab? @@ -504,28 +533,23 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, * 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); + pc = kmem_cache_zalloc(page_cgroup_cache, gfp_mask); if (pc == NULL) goto err; @@ -539,18 +563,13 @@ retry: mm = &init_mm; rcu_read_lock(); - mem = rcu_dereference(mm->mem_cgroup); + mem = mem_cgroup_from_task(rcu_dereference(mm->owner)); /* - * 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; @@ -559,12 +578,12 @@ 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; @@ -572,17 +591,18 @@ retry: mem_cgroup_out_of_memory(mem, gfp_mask); goto out; } - 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; + 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 @@ -590,142 +610,147 @@ retry: */ res_counter_uncharge(&mem->res, PAGE_SIZE); css_put(&mem->css); - kfree(pc); - if (!page) - goto done; + kmem_cache_free(page_cgroup_cache, pc); goto retry; } + page_assign_page_cgroup(page, pc); - spin_lock_irqsave(&mem->lru_lock, flags); - /* Update statistics vector */ - __mem_cgroup_add_list(pc); - spin_unlock_irqrestore(&mem->lru_lock, flags); + 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(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) { 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; - struct mem_cgroup *mem; if (!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, + return mem_cgroup_charge_common(page, mm, gfp_mask, MEM_CGROUP_CHARGE_TYPE_CACHE); - css_put(&mem->css); - return ret; } /* * Uncharging is always a welcome operation, we never complain, simply * 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 page *page; + struct mem_cgroup_per_zone *mz; 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 */ + 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; - /* - * 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(&mem->lru_lock, flags); - __mem_cgroup_remove_list(pc); - spin_unlock_irqrestore(&mem->lru_lock, flags); - kfree(pc); - } + VM_BUG_ON(pc->page != page); + VM_BUG_ON(pc->ref_cnt <= 0); + + if (--(pc->ref_cnt) == 0) { + 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); } /* * 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; + + 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) + pc->ref_cnt++; unlock_page_cgroup(page); - return ret; + return pc != NULL; } void mem_cgroup_end_migration(struct page *page) { - struct page_cgroup *pc = page_get_page_cgroup(page); - mem_cgroup_uncharge(pc); + 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; + struct mem_cgroup_per_zone *mz; unsigned long flags; -retry: + + lock_page_cgroup(page); pc = page_get_page_cgroup(page); - if (!pc) + if (!pc) { + unlock_page_cgroup(page); return; - mem = pc->mem_cgroup; - if (clear_page_cgroup(page, pc) != pc) - goto retry; + } - spin_lock_irqsave(&mem->lru_lock, flags); + 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_cgroup_remove_list(pc); pc->page = newpage; lock_page_cgroup(newpage); page_assign_page_cgroup(newpage, pc); - unlock_page_cgroup(newpage); - __mem_cgroup_add_list(pc); - spin_unlock_irqrestore(&mem->lru_lock, flags); - return; + 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(newpage); } /* @@ -734,61 +759,68 @@ retry: * *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, struct list_head *list) +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; -retry: - count = FORCE_UNCHARGE_BATCH; - spin_lock_irqsave(&mem->lru_lock, flags); + if (active) + list = &mz->active_list; + else + list = &mz->inactive_list; - while (--count && !list_empty(list)) { + spin_lock_irqsave(&mz->lru_lock, flags); + 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; - } - spin_unlock_irqrestore(&mem->lru_lock, flags); - if (!list_empty(list)) { - cond_resched(); - goto retry; + 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); } - return; + spin_unlock_irqrestore(&mz->lru_lock, flags); } /* * 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; + + if (mem_cgroup_subsys.disabled) + return 0; + 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 (!(list_empty(&mem->active_list) && - list_empty(&mem->inactive_list))) { + while (mem->res.usage > 0) { if (atomic_read(&mem->css.cgroup->count) > 0) goto out; - /* drop all page_cgroup in active_list */ - mem_cgroup_force_empty_list(mem, &mem->active_list); - /* drop all page_cgroup in inactive_list */ - mem_cgroup_force_empty_list(mem, &mem->inactive_list); + for_each_node_state(node, N_POSSIBLE) + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + struct mem_cgroup_per_zone *mz; + mz = mem_cgroup_zoneinfo(mem, node, zid); + /* drop all page_cgroup in active_list */ + mem_cgroup_force_empty_list(mem, mz, 1); + /* drop all page_cgroup in inactive_list */ + mem_cgroup_force_empty_list(mem, mz, 0); + } } ret = 0; out: @@ -796,9 +828,7 @@ out: 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') @@ -811,13 +841,10 @@ int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp) 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) +static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) { - return res_counter_read(&mem_cgroup_from_cont(cont)->res, - cft->private, userbuf, nbytes, ppos, - NULL); + return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res, + cft->private); } static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft, @@ -829,87 +856,27 @@ static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft, mem_cgroup_write_strategy); } -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) +static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) { - 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: - 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) -{ - 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; @@ -918,9 +885,9 @@ static const struct mem_cgroup_stat_desc { [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, }, }; -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; @@ -930,8 +897,7 @@ 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 */ { @@ -941,75 +907,81 @@ 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, + .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, }, }; static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) { struct mem_cgroup_per_node *pn; - - pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, node); + struct mem_cgroup_per_zone *mz; + int zone, tmp = node; + /* + * This routine is called against possible nodes. + * But it's BUG to call kmalloc() against offline node. + * + * TODO: this routine can waste much memory for nodes which will + * never be onlined. It's better to use memory hotplug callback + * function. + */ + if (!node_state(node, N_NORMAL_MEMORY)) + tmp = -1; + pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, tmp); if (!pn) return 1; + mem->info.nodeinfo[node] = pn; memset(pn, 0, sizeof(*pn)); + + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + mz = &pn->zoneinfo[zone]; + INIT_LIST_HEAD(&mz->active_list); + INIT_LIST_HEAD(&mz->inactive_list); + spin_lock_init(&mz->lru_lock); + } return 0; } -static struct mem_cgroup init_mem_cgroup; +static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) +{ + kfree(mem->info.nodeinfo[node]); +} static struct cgroup_subsys_state * mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) @@ -1019,18 +991,16 @@ 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 + page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC); + } else { mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL); + } if (mem == NULL) - return NULL; + return ERR_PTR(-ENOMEM); res_counter_init(&mem->res); - INIT_LIST_HEAD(&mem->active_list); - INIT_LIST_HEAD(&mem->inactive_list); - spin_lock_init(&mem->lru_lock); - mem->control_type = MEM_CGROUP_TYPE_ALL; + memset(&mem->info, 0, sizeof(mem->info)); for_each_node_state(node, N_POSSIBLE) @@ -1040,10 +1010,10 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) return &mem->css; free_out: for_each_node_state(node, N_POSSIBLE) - kfree(mem->info.nodeinfo[node]); + 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, @@ -1060,7 +1030,7 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss, struct mem_cgroup *mem = mem_cgroup_from_cont(cont); for_each_node_state(node, N_POSSIBLE) - kfree(mem->info.nodeinfo[node]); + free_mem_cgroup_per_zone_info(mem, node); kfree(mem_cgroup_from_cont(cont)); } @@ -1068,6 +1038,8 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss, static int mem_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont) { + if (mem_cgroup_subsys.disabled) + return 0; return cgroup_add_files(cont, ss, mem_cgroup_files, ARRAY_SIZE(mem_cgroup_files)); } @@ -1080,6 +1052,9 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss, struct mm_struct *mm; struct mem_cgroup *mem, *old_mem; + if (mem_cgroup_subsys.disabled) + return; + mm = get_task_mm(p); if (mm == NULL) return; @@ -1094,16 +1069,11 @@ static void mem_cgroup_move_task(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); - rcu_assign_pointer(mm->mem_cgroup, mem); - css_put(&old_mem->css); - out: mmput(mm); - return; } struct cgroup_subsys mem_cgroup_subsys = {