diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Makefile | 1 | ||||
| -rw-r--r-- | mm/bootmem.c | 27 | ||||
| -rw-r--r-- | mm/filemap.c | 16 | ||||
| -rw-r--r-- | mm/memcontrol.c | 1192 | ||||
| -rw-r--r-- | mm/memory.c | 47 | ||||
| -rw-r--r-- | mm/migrate.c | 19 | ||||
| -rw-r--r-- | mm/oom_kill.c | 85 | ||||
| -rw-r--r-- | mm/page_alloc.c | 3 | ||||
| -rw-r--r-- | mm/rmap.c | 47 | ||||
| -rw-r--r-- | mm/shmem.c | 28 | ||||
| -rw-r--r-- | mm/swap.c | 2 | ||||
| -rw-r--r-- | mm/swapfile.c | 47 | ||||
| -rw-r--r-- | mm/vmscan.c | 495 |
13 files changed, 1792 insertions, 217 deletions
diff --git a/mm/Makefile b/mm/Makefile index 4af5dff37277..9f117bab5322 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -32,4 +32,5 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_SMP) += allocpercpu.o obj-$(CONFIG_QUICKLIST) += quicklist.o +obj-$(CONFIG_CGROUP_MEM_CONT) += memcontrol.o diff --git a/mm/bootmem.c b/mm/bootmem.c index 00a96970b237..f6ff4337b424 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -111,11 +111,12 @@ static unsigned long __init init_bootmem_core(pg_data_t *pgdat, * might be used for boot-time allocations - or it might get added * to the free page pool later on. */ -static void __init reserve_bootmem_core(bootmem_data_t *bdata, unsigned long addr, - unsigned long size) +static int __init reserve_bootmem_core(bootmem_data_t *bdata, + unsigned long addr, unsigned long size, int flags) { unsigned long sidx, eidx; unsigned long i; + int ret; /* * round up, partially reserved pages are considered @@ -133,7 +134,20 @@ static void __init reserve_bootmem_core(bootmem_data_t *bdata, unsigned long add #ifdef CONFIG_DEBUG_BOOTMEM printk("hm, page %08lx reserved twice.\n", i*PAGE_SIZE); #endif + if (flags & BOOTMEM_EXCLUSIVE) { + ret = -EBUSY; + goto err; + } } + + return 0; + +err: + /* unreserve memory we accidentally reserved */ + for (i--; i >= sidx; i--) + clear_bit(i, bdata->node_bootmem_map); + + return ret; } static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr, @@ -374,9 +388,9 @@ unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn, } void __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, - unsigned long size) + unsigned long size, int flags) { - reserve_bootmem_core(pgdat->bdata, physaddr, size); + reserve_bootmem_core(pgdat->bdata, physaddr, size, flags); } void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, @@ -398,9 +412,10 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages) } #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE -void __init reserve_bootmem(unsigned long addr, unsigned long size) +int __init reserve_bootmem(unsigned long addr, unsigned long size, + int flags) { - reserve_bootmem_core(NODE_DATA(0)->bdata, addr, size); + return reserve_bootmem_core(NODE_DATA(0)->bdata, addr, size, flags); } #endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ diff --git a/mm/filemap.c b/mm/filemap.c index 81fb9bff0d4f..5357fcc4643b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -33,6 +33,7 @@ #include <linux/syscalls.h> #include <linux/cpuset.h> #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */ +#include <linux/memcontrol.h> #include "internal.h" /* @@ -118,6 +119,7 @@ void __remove_from_page_cache(struct page *page) { struct address_space *mapping = page->mapping; + mem_cgroup_uncharge_page(page); radix_tree_delete(&mapping->page_tree, page->index); page->mapping = NULL; mapping->nrpages--; @@ -458,8 +460,12 @@ int filemap_write_and_wait_range(struct address_space *mapping, int add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { - int error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM); + int error = mem_cgroup_cache_charge(page, current->mm, + gfp_mask & ~__GFP_HIGHMEM); + if (error) + goto out; + error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM); if (error == 0) { write_lock_irq(&mapping->tree_lock); error = radix_tree_insert(&mapping->page_tree, offset, page); @@ -470,10 +476,14 @@ int add_to_page_cache(struct page *page, struct address_space *mapping, page->index = offset; mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); - } + } else + mem_cgroup_uncharge_page(page); + write_unlock_irq(&mapping->tree_lock); radix_tree_preload_end(); - } + } else + mem_cgroup_uncharge_page(page); +out: return error; } EXPORT_SYMBOL(add_to_page_cache); diff --git a/mm/memcontrol.c b/mm/memcontrol.c new file mode 100644 index 000000000000..5c2c702af617 --- /dev/null +++ b/mm/memcontrol.c @@ -0,0 +1,1192 @@ +/* memcontrol.c - Memory Controller + * + * Copyright IBM Corporation, 2007 + * Author Balbir Singh <balbir@linux.vnet.ibm.com> + * + * Copyright 2007 OpenVZ SWsoft Inc + * Author: Pavel Emelianov <xemul@openvz.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/res_counter.h> +#include <linux/memcontrol.h> +#include <linux/cgroup.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/page-flags.h> +#include <linux/backing-dev.h> +#include <linux/bit_spinlock.h> +#include <linux/rcupdate.h> +#include <linux/swap.h> +#include <linux/spinlock.h> +#include <linux/fs.h> +#include <linux/seq_file.h> + +#include <asm/uaccess.h> + +struct cgroup_subsys mem_cgroup_subsys; +static const int MEM_CGROUP_RECLAIM_RETRIES = 5; + +/* + * Statistics for memory cgroup. + */ +enum mem_cgroup_stat_index { + /* + * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss. + */ + MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ + MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */ + + MEM_CGROUP_STAT_NSTATS, +}; + +struct mem_cgroup_stat_cpu { + s64 count[MEM_CGROUP_STAT_NSTATS]; +} ____cacheline_aligned_in_smp; + +struct mem_cgroup_stat { + struct mem_cgroup_stat_cpu cpustat[NR_CPUS]; +}; + +/* + * For accounting under irq disable, no need for increment preempt count. + */ +static void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat *stat, + enum mem_cgroup_stat_index idx, int val) +{ + int cpu = smp_processor_id(); + stat->cpustat[cpu].count[idx] += val; +} + +static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat, + enum mem_cgroup_stat_index idx) +{ + int cpu; + s64 ret = 0; + for_each_possible_cpu(cpu) + ret += stat->cpustat[cpu].count[idx]; + return ret; +} + +/* + * per-zone information in memory controller. + */ + +enum mem_cgroup_zstat_index { + MEM_CGROUP_ZSTAT_ACTIVE, + MEM_CGROUP_ZSTAT_INACTIVE, + + NR_MEM_CGROUP_ZSTAT, +}; + +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 */ +#define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)]) + +struct mem_cgroup_per_node { + struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; +}; + +struct mem_cgroup_lru_info { + struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES]; +}; + +/* + * The memory controller data structure. The memory controller controls both + * page cache and RSS per cgroup. We would eventually like to provide + * statistics based on the statistics developed by Rik Van Riel for clock-pro, + * to help the administrator determine what knobs to tune. + * + * TODO: Add a water mark for the memory controller. Reclaim will begin when + * we hit the water mark. May be even add a low water mark, such that + * no reclaim occurs from a cgroup at it's low water mark, this is + * a feature that will be implemented much later in the future. + */ +struct mem_cgroup { + struct cgroup_subsys_state css; + /* + * the counter to account for memory usage + */ + struct res_counter res; + /* + * Per cgroup active and inactive list, similar to the + * per zone LRU lists. + */ + struct mem_cgroup_lru_info info; + + int prev_priority; /* for recording reclaim priority */ + /* + * statistics. + */ + struct mem_cgroup_stat stat; +}; + +/* + * 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) + */ +#define PAGE_CGROUP_LOCK_BIT 0x0 +#define PAGE_CGROUP_LOCK (1 << PAGE_CGROUP_LOCK_BIT) + +/* + * 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; + atomic_t ref_cnt; /* Helpful when pages move b/w */ + /* mapped and cached states */ + 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) +{ + return page_to_nid(pc->page); +} + +static inline 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() + */ +static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags, + bool charge) +{ + int val = (charge)? 1 : -1; + struct mem_cgroup_stat *stat = &mem->stat; + VM_BUG_ON(!irqs_disabled()); + + if (flags & PAGE_CGROUP_FLAG_CACHE) + __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 * +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 * +page_cgroup_zoneinfo(struct page_cgroup *pc) +{ + struct mem_cgroup *mem = pc->mem_cgroup; + int nid = page_cgroup_nid(pc); + int zid = page_cgroup_zid(pc); + + return mem_cgroup_zoneinfo(mem, nid, zid); +} + +static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem, + enum mem_cgroup_zstat_index idx) +{ + int nid, zid; + struct mem_cgroup_per_zone *mz; + u64 total = 0; + + for_each_online_node(nid) + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + mz = mem_cgroup_zoneinfo(mem, nid, zid); + total += MEM_CGROUP_ZSTAT(mz, idx); + } + return total; +} + +static struct mem_cgroup init_mem_cgroup; + +static inline +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); +} + +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); +} + +struct page_cgroup *page_get_page_cgroup(struct page *page) +{ + return (struct page_cgroup *) + (page->page_cgroup & ~PAGE_CGROUP_LOCK); +} + +static void __always_inline 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) +{ + 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; +} + +static void __mem_cgroup_remove_list(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; + else + MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1; + + mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, false); + list_del_init(&pc->lru); +} + +static void __mem_cgroup_add_list(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, &mz->inactive_list); + } else { + MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1; + list_add(&pc->lru, &mz->active_list); + } + mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true); +} + +static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active) +{ + 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; + else + MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1; + + if (active) { + MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1; + pc->flags |= PAGE_CGROUP_FLAG_ACTIVE; + 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, &mz->inactive_list); + } +} + +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; + task_unlock(task); + return ret; +} + +/* + * This routine assumes that the appropriate zone's lru lock is already held + */ +void mem_cgroup_move_lists(struct page_cgroup *pc, bool active) +{ + struct mem_cgroup_per_zone *mz; + unsigned long flags; + + if (!pc) + 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); +} + +/* + * 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); + + 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, + struct list_head *dst, + unsigned long *scanned, int order, + int mode, struct zone *z, + struct mem_cgroup *mem_cont, + int active) +{ + unsigned long nr_taken = 0; + struct page *page; + unsigned long 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; + + mz = mem_cgroup_zoneinfo(mem_cont, nid, zid); + if (active) + src = &mz->active_list; + else + src = &mz->inactive_list; + + + 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; + + if (PageActive(page) && !active) { + __mem_cgroup_move_lists(pc, true); + continue; + } + if (!PageActive(page) && active) { + __mem_cgroup_move_lists(pc, false); + continue; + } + + scan++; + list_move(&pc->lru, &pc_list); + + if (__isolate_lru_page(page, mode) == 0) { + list_move(&page->lru, dst); + nr_taken++; + } + } + + list_splice(&pc_list, src); + spin_unlock(&mz->lru_lock); + + *scanned = scan; + return nr_taken; +} + +/* + * 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 *mem; + struct page_cgroup *pc; + unsigned long flags; + 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) + goto err; + + /* + * 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 (!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 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; + + if (try_to_free_mem_cgroup_pages(mem, gfp_mask)) + 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 + */ + if (res_counter_check_under_limit(&mem->res)) + continue; + + if (!nr_retries--) { + 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 (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE) + pc->flags |= PAGE_CGROUP_FLAG_CACHE; + + 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. + */ + res_counter_uncharge(&mem->res, PAGE_SIZE); + css_put(&mem->css); + kfree(pc); + if (!page) + goto done; + goto retry; + } + + mz = page_cgroup_zoneinfo(pc); + spin_lock_irqsave(&mz->lru_lock, flags); + /* Update statistics vector */ + __mem_cgroup_add_list(pc); + spin_unlock_irqrestore(&mz->lru_lock, flags); + +done: + return 0; +out: + css_put(&mem->css); + kfree(pc); +err: + return -ENOMEM; +} + +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); +} + +/* + * See if the cached pages should be charged at all? + */ +int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask) +{ + int ret = 0; + if (!mm) + mm = &init_mm; + + ret = mem_cgroup_charge_common(page, mm, gfp_mask, + MEM_CGROUP_CHARGE_TYPE_CACHE); + return ret; +} + +/* + * Uncharging is always a welcome operation, we never complain, simply + * uncharge. This routine should be called with lock_page_cgroup held + */ +void mem_cgroup_uncharge(struct page_cgroup *pc) +{ + struct mem_cgroup *mem; + struct mem_cgroup_per_zone *mz; + struct page *page; + unsigned long flags; + + /* + * Check if our page_cgroup is valid + */ + if (!pc) + return; + + 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. + */ + unlock_page_cgroup(page); + if (clear_page_cgroup(page, pc) == pc) { + mem = pc->mem_cgroup; + css_put(&mem->css); + res_counter_uncharge(&mem->res, PAGE_SIZE); + spin_lock_irqsave(&mz->lru_lock, flags); + __mem_cgroup_remove_list(pc); + spin_unlock_irqrestore(&mz->lru_lock, flags); + kfree(pc); + } + lock_page_cgroup(page); + } +} + +void mem_cgroup_uncharge_page(struct page *page) +{ + lock_page_cgroup(page); + mem_cgroup_uncharge(page_get_page_cgroup(page)); + unlock_page_cgroup(page); +} + +/* + * Returns non-zero if a page (under migration) has valid page_cgroup member. + * Refcnt of page_cgroup is incremented. + */ + +int mem_cgroup_prepare_migration(struct page *page) +{ + struct page_cgroup *pc; + int ret = 0; + lock_page_cgroup(page); + pc = page_get_page_cgroup(page); + if (pc && atomic_inc_not_zero(&pc->ref_cnt)) + ret = 1; + unlock_page_cgroup(page); + return ret; +} + +void mem_cgroup_end_migration(struct page *page) +{ + struct page_cgroup *pc; + + lock_page_cgroup(page); + pc = page_get_page_cgroup(page); + mem_cgroup_uncharge(pc); + unlock_page_cgroup(page); +} +/* + * We know both *page* and *newpage* are now not-on-LRU and Pg_locked. + * And no race with uncharge() routines because page_cgroup for *page* + * has extra one reference by mem_cgroup_prepare_migration. + */ + +void mem_cgroup_page_migration(struct page *page, struct page *newpage) +{ + struct page_cgroup *pc; + struct mem_cgroup *mem; + unsigned long flags; + struct mem_cgroup_per_zone *mz; +retry: + 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); + + __mem_cgroup_remove_list(pc); + spin_unlock_irqrestore(&mz->lru_lock, flags); + + pc->page = newpage; + lock_page_cgroup(newpage); + page_assign_page_cgroup(newpage, pc); + unlock_page_cgroup(newpage); + + mz = page_cgroup_zoneinfo(pc); + spin_lock_irqsave(&mz->lru_lock, flags); + __mem_cgroup_add_list(pc); + spin_unlock_irqrestore(&mz->lru_lock, flags); + return; +} + +/* + * 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, + struct mem_cgroup_per_zone *mz, + int active) +{ + struct page_cgroup *pc; + struct page *page; + int count; + unsigned long flags; + struct list_head *list; + + if (active) + list = &mz->active_list; + else + list = &mz->inactive_list; + + if (list_empty(list)) + return; +retry: + count = FORCE_UNCHARGE_BATCH; + spin_lock_irqsave(&mz->lru_lock, flags); + + while (--count && !list_empty(list)) { + 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(&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) +{ + 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. + * So, we have to do loop here until all lists are empty. + */ + while (mem->res.usage > 0) { + if (atomic_read(&mem->css.cgroup->count) > 0) + goto out; + 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: + css_put(&mem->css); + 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) +{ + return res_counter_write(&mem_cgroup_from_cont(cont)->res, + cft->private, userbuf, nbytes, ppos, + mem_cgroup_write_strategy); +} + +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; +} + +/* + * 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) +{ + return -EINVAL; +} + + +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, }, +}; + +static int mem_control_stat_show(struct seq_file *m, void *arg) +{ + 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; + + for (i = 0; i < ARRAY_SIZE(stat->cpustat[0].count); i++) { + s64 val; + + 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); + } + /* showing # of active pages */ + { + unsigned long active, inactive; + + inactive = mem_cgroup_get_all_zonestat(mem_cont, + 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); + } + 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, + }, + { + .name = "limit_in_bytes", + .private = RES_LIMIT, + .write = mem_cgroup_write, + .read = mem_cgroup_read, + }, + { + .name = "failcnt", + .private = RES_FAILCNT, + .read = mem_cgroup_read, + }, + { + .name = "force_empty", + .write = mem_force_empty_write, + .read = mem_force_empty_read, + }, + { + .name = "stat", + .open = mem_control_stat_open, + }, +}; + +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; + /* + * 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_HIGH_MEMORY)) + pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, node); + else + pn = kmalloc(sizeof(*pn), GFP_KERNEL); + 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 void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) +{ + kfree(mem->info.nodeinfo[node]); +} + + +static struct mem_cgroup init_mem_cgroup; + +static struct cgroup_subsys_state * +mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) +{ + struct mem_cgroup *mem; + int node; + + 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; + + res_counter_init(&mem->res); + + 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; + + return &mem->css; +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; +} + +static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss, + struct cgroup *cont) +{ + struct mem_cgroup *mem = mem_cgroup_from_cont(cont); + mem_cgroup_force_empty(mem); +} + +static void mem_cgroup_destroy(struct cgroup_subsys *ss, + struct cgroup *cont) +{ + int node; + struct mem_cgroup *mem = mem_cgroup_from_cont(cont); + + for_each_node_state(node, N_POSSIBLE) + free_mem_cgroup_per_zone_info(mem, node); + + kfree(mem_cgroup_from_cont(cont)); +} + +static int mem_cgroup_populate(struct cgroup_subsys *ss, + struct cgroup *cont) +{ + return cgroup_add_files(cont, ss, mem_cgroup_files, + ARRAY_SIZE(mem_cgroup_files)); +} + +static void mem_cgroup_move_task(struct cgroup_subsys *ss, + struct cgroup *cont, + struct cgroup *old_cont, + struct task_struct *p) +{ + struct mm_struct *mm; + struct mem_cgroup *mem, *old_mem; + + mm = get_task_mm(p); + if (mm == NULL) + return; + + 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) + 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 = { + .name = "memory", + .subsys_id = mem_cgroup_subsys_id, + .create = mem_cgroup_create, + .pre_destroy = mem_cgroup_pre_destroy, + .destroy = mem_cgroup_destroy, + .populate = mem_cgroup_populate, + .attach = mem_cgroup_move_task, + .early_init = 0, +}; diff --git a/mm/memory.c b/mm/memory.c index 9d073fa0a2d0..153a54b2013c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -50,6 +50,7 @@ #include <linux/delayacct.h> #include <linux/init.h> #include <linux/writeback.h> +#include <linux/memcontrol.h> #include <asm/pgalloc.h> #include <asm/uaccess.h> @@ -1144,16 +1145,20 @@ static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *pa { int retval; pte_t *pte; - spinlock_t *ptl; + spinlock_t *ptl; + + retval = mem_cgroup_charge(page, mm, GFP_KERNEL); + if (retval) + goto out; retval = -EINVAL; if (PageAnon(page)) - goto out; + goto out_uncharge; retval = -ENOMEM; flush_dcache_page(page); pte = get_locked_pte(mm, addr, &ptl); if (!pte) - goto out; + goto out_uncharge; retval = -EBUSY; if (!pte_none(*pte)) goto out_unlock; @@ -1165,8 +1170,12 @@ static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *pa set_pte_at(mm, addr, pte, mk_pte(page, prot)); retval = 0; + pte_unmap_unlock(pte, ptl); + return retval; out_unlock: pte_unmap_unlock(pte, ptl); +out_uncharge: + mem_cgroup_uncharge_page(page); out: return retval; } @@ -1641,6 +1650,9 @@ gotten: cow_user_page(new_page, old_page, address, vma); __SetPageUptodate(new_page); + if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) + goto oom_free_new; + /* * Re-check the pte - we dropped the lock */ @@ -1672,7 +1684,9 @@ gotten: /* Free the old page.. */ new_page = old_page; ret |= VM_FAULT_WRITE; - } + } else + mem_cgroup_uncharge_page(new_page); + if (new_page) page_cache_release(new_page); if (old_page) @@ -1696,6 +1710,8 @@ unlock: put_page(dirty_page); } return ret; +oom_free_new: + __free_page(new_page); oom: if (old_page) page_cache_release(old_page); @@ -2036,6 +2052,12 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(PGMAJFAULT); } + if (mem_cgroup_charge(page, mm, GFP_KERNEL)) { + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + ret = VM_FAULT_OOM; + goto out; + } + mark_page_accessed(page); lock_page(page); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); @@ -2073,8 +2095,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, if (write_access) { /* XXX: We could OR the do_wp_page code with this one? */ if (do_wp_page(mm, vma, address, - page_table, pmd, ptl, pte) & VM_FAULT_OOM) + page_table, pmd, ptl, pte) & VM_FAULT_OOM) { + mem_cgroup_uncharge_page(page); ret = VM_FAULT_OOM; + } goto out; } @@ -2085,6 +2109,7 @@ unlock: out: return ret; out_nomap: + mem_cgroup_uncharge_page(page); pte_unmap_unlock(page_table, ptl); unlock_page(page); page_cache_release(page); @@ -2114,6 +2139,9 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, goto oom; __SetPageUptodate(page); + if (mem_cgroup_charge(page, mm, GFP_KERNEL)) + goto oom_free_page; + entry = mk_pte(page, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -2131,8 +2159,11 @@ unlock: pte_unmap_unlock(page_table, ptl); return 0; release: + mem_cgroup_uncharge_page(page); page_cache_release(page); goto unlock; +oom_free_page: + __free_page(page); oom: return VM_FAULT_OOM; } @@ -2246,6 +2277,11 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, } + if (mem_cgroup_charge(page, mm, GFP_KERNEL)) { + ret = VM_FAULT_OOM; + goto out; + } + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); /* @@ -2281,6 +2317,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache(vma, address, entry); } else { + mem_cgroup_uncharge_page(page); if (anon) page_cache_release(page); else diff --git a/mm/migrate.c b/mm/migrate.c index 857a987e3690..a73504ff5ab9 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -29,6 +29,7 @@ #include <linux/mempolicy.h> #include <linux/vmalloc.h> #include <linux/security.h> +#include <linux/memcontrol.h> #include "internal.h" @@ -152,6 +153,11 @@ static void remove_migration_pte(struct vm_area_struct *vma, return; } + if (mem_cgroup_charge(new, mm, GFP_KERNEL)) { + pte_unmap(ptep); + return; + } + ptl = pte_lockptr(mm, pmd); spin_lock(ptl); pte = *ptep; @@ -587,9 +593,10 @@ static int move_to_new_page(struct page *newpage, struct page *page) else rc = fallback_migrate_page(mapping, newpage, page); - if (!rc) + if (!rc) { + mem_cgroup_page_migration(page, newpage); remove_migration_ptes(page, newpage); - else + } else newpage->mapping = NULL; unlock_page(newpage); @@ -608,6 +615,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, int *result = NULL; struct page *newpage = get_new_page(page, private, &result); int rcu_locked = 0; + int charge = 0; if (!newpage) return -ENOMEM; @@ -667,14 +675,19 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, goto rcu_unlock; } + charge = mem_cgroup_prepare_migration(page); /* Establish migration ptes or remove ptes */ try_to_unmap(page, 1); if (!page_mapped(page)) rc = move_to_new_page(newpage, page); - if (rc) + if (rc) { remove_migration_ptes(page, page); + if (charge) + mem_cgroup_end_migration(page); + } else if (charge) + mem_cgroup_end_migration(newpage); rcu_unlock: if (rcu_locked) rcu_read_unlock(); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c1850bf991cd..4194b9db0104 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -25,9 +25,11 @@ #include <linux/cpuset.h> #include <linux/module.h> #include <linux/notifier.h> +#include <linux/memcontrol.h> int sysctl_panic_on_oom; int sysctl_oom_kill_allocating_task; +int sysctl_oom_dump_tasks; static DEFINE_SPINLOCK(zone_scan_mutex); /* #define DEBUG */ @@ -50,7 +52,8 @@ static DEFINE_SPINLOCK(zone_scan_mutex); * of least surprise ... (be careful when you change it) */ -unsigned long badness(struct task_struct *p, unsigned long uptime) +unsigned long badness(struct task_struct *p, unsigned long uptime, + struct mem_cgroup *mem) { unsigned long points, cpu_time, run_time, s; struct mm_struct *mm; @@ -193,7 +196,8 @@ static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist, * * (not docbooked, we don't want this one cluttering up the manual) */ -static struct task_struct *select_bad_process(unsigned long *ppoints) +static struct task_struct *select_bad_process(unsigned long *ppoints, + struct mem_cgroup *mem) { struct task_struct *g, *p; struct task_struct *chosen = NULL; @@ -213,6 +217,8 @@ static struct task_struct *select_bad_process(unsigned long *ppoints) /* skip the init task */ if (is_global_init(p)) continue; + if (mem && !task_in_mem_cgroup(p, mem)) + continue; /* * This task already has access to memory reserves and is @@ -247,7 +253,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints) if (p->oomkilladj == OOM_DISABLE) continue; - points = badness(p, uptime.tv_sec); + points = badness(p, uptime.tv_sec, mem); if (points > *ppoints || !chosen) { chosen = p; *ppoints = points; @@ -258,6 +264,41 @@ static struct task_struct *select_bad_process(unsigned long *ppoints) } /** + * Dumps the current memory state of all system tasks, excluding kernel threads. + * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj + * score, and name. + * + * If the actual is non-NULL, only tasks that are a member of the mem_cgroup are + * shown. + * + * Call with tasklist_lock read-locked. + */ +static void dump_tasks(const struct mem_cgroup *mem) +{ + struct task_struct *g, *p; + + printk(KERN_INFO "[ pid ] uid tgid total_vm rss cpu oom_adj " + "name\n"); + do_each_thread(g, p) { + /* + * total_vm and rss sizes do not exist for tasks with a + * detached mm so there's no need to report them. + */ + if (!p->mm) + continue; + if (mem && !task_in_mem_cgroup(p, mem)) + continue; + + task_lock(p); + printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n", + p->pid, p->uid, p->tgid, p->mm->total_vm, + get_mm_rss(p->mm), (int)task_cpu(p), p->oomkilladj, + p->comm); + task_unlock(p); + } while_each_thread(g, p); +} + +/** * Send SIGKILL to the selected process irrespective of CAP_SYS_RAW_IO * flag though it's unlikely that we select a process with CAP_SYS_RAW_IO * set. @@ -334,7 +375,8 @@ static int oom_kill_task(struct task_struct *p) } static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, - unsigned long points, const char *message) + unsigned long points, struct mem_cgroup *mem, + const char *message) { struct task_struct *c; @@ -344,6 +386,8 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, current->comm, gfp_mask, order, current->oomkilladj); dump_stack(); show_mem(); + if (sysctl_oom_dump_tasks) + dump_tasks(mem); } /* @@ -368,6 +412,31 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, return oom_kill_task(p); } +#ifdef CONFIG_CGROUP_MEM_CONT +void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask) +{ + unsigned long points = 0; + struct task_struct *p; + + cgroup_lock(); + rcu_read_lock(); +retry: + p = select_bad_process(&points, mem); + if (PTR_ERR(p) == -1UL) + goto out; + + if (!p) + p = current; + + if (oom_kill_process(p, gfp_mask, 0, points, mem, + "Memory cgroup out of memory")) + goto retry; +out: + rcu_read_unlock(); + cgroup_unlock(); +} +#endif + static BLOCKING_NOTIFIER_HEAD(oom_notify_list); int register_oom_notifier(struct notifier_block *nb) @@ -465,7 +534,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order) switch (constraint) { case CONSTRAINT_MEMORY_POLICY: - oom_kill_process(current, gfp_mask, order, points, + oom_kill_process(current, gfp_mask, order, points, NULL, "No available memory (MPOL_BIND)"); break; @@ -475,7 +544,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order) /* Fall-through */ case CONSTRAINT_CPUSET: if (sysctl_oom_kill_allocating_task) { - oom_kill_process(current, gfp_mask, order, points, + oom_kill_process(current, gfp_mask, order, points, NULL, "Out of memory (oom_kill_allocating_task)"); break; } @@ -484,7 +553,7 @@ retry: * Rambo mode: Shoot down a process and hope it solves whatever * issues we may have. */ - p = select_bad_process(&points); + p = select_bad_process(&points, NULL); if (PTR_ERR(p) == -1UL) goto out; @@ -495,7 +564,7 @@ retry: panic("Out of memory and no killable processes...\n"); } - if (oom_kill_process(p, gfp_mask, order, points, + if (oom_kill_process(p, gfp_mask, order, points, NULL, "Out of memory")) goto retry; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 37576b822f06..26a54a17dc9f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -43,6 +43,7 @@ #include <linux/backing-dev.h> #include <linux/fault-inject.h> #include <linux/page-isolation.h> +#include <linux/memcontrol.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -987,6 +988,7 @@ static void free_hot_cold_page(struct page *page, int cold) if (!PageHighMem(page)) debug_check_no_locks_freed(page_address(page), PAGE_SIZE); + VM_BUG_ON(page_get_page_cgroup(page)); arch_free_page(page, 0); kernel_map_pages(page, 1, 0); @@ -2525,6 +2527,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, set_page_links(page, zone, nid, pfn); init_page_count(page); reset_page_mapcount(page); + page_assign_page_cgroup(page, NULL); SetPageReserved(page); /* diff --git a/mm/rmap.c b/mm/rmap.c index 57ad276900c9..a0e92a263d12 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -48,6 +48,7 @@ #include <linux/rcupdate.h> #include <linux/module.h> #include <linux/kallsyms.h> +#include <linux/memcontrol.h> #include <asm/tlbflush.h> @@ -301,7 +302,8 @@ out: return referenced; } -static int page_referenced_anon(struct page *page) +static int page_referenced_anon(struct page *page, + struct mem_cgroup *mem_cont) { unsigned int mapcount; struct anon_vma *anon_vma; @@ -314,6 +316,13 @@ static int page_referenced_anon(struct page *page) mapcount = page_mapcount(page); list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + /* + * If we are reclaiming on behalf of a cgroup, skip + * counting on behalf of references from different + * cgroups + */ + if (mem_cont && (mm_cgroup(vma->vm_mm) != mem_cont)) + continue; referenced += page_referenced_one(page, vma, &mapcount); if (!mapcount) break; @@ -334,7 +343,8 @@ static int page_referenced_anon(struct page *page) * * This function is only called from page_referenced for object-based pages. */ -static int page_referenced_file(struct page *page) +static int page_referenced_file(struct page *page, + struct mem_cgroup *mem_cont) { unsigned int mapcount; struct address_space *mapping = page->mapping; @@ -367,6 +377,13 @@ static int page_referenced_file(struct page *page) mapcount = page_mapcount(page); vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + /* + * If we are reclaiming on behalf of a cgroup, skip + * counting on behalf of references from different + * cgroups + */ + if (mem_cont && (mm_cgroup(vma->vm_mm) != mem_cont)) + continue; if ((vma->vm_flags & (VM_LOCKED|VM_MAYSHARE)) == (VM_LOCKED|VM_MAYSHARE)) { referenced++; @@ -389,7 +406,8 @@ static int page_referenced_file(struct page *page) * Quick test_and_clear_referenced for all mappings to a page, * returns the number of ptes which referenced the page. */ -int page_referenced(struct page *page, int is_locked) +int page_referenced(struct page *page, int is_locked, + struct mem_cgroup *mem_cont) { int referenced = 0; @@ -401,14 +419,15 @@ int page_referenced(struct page *page, int is_locked) if (page_mapped(page) && page->mapping) { if (PageAnon(page)) - referenced += page_referenced_anon(page); + referenced += page_referenced_anon(page, mem_cont); else if (is_locked) - referenced += page_referenced_file(page); + referenced += page_referenced_file(page, mem_cont); else if (TestSetPageLocked(page)) referenced++; else { if (page->mapping) - referenced += page_referenced_file(page); + referenced += + page_referenced_file(page, mem_cont); unlock_page(page); } } @@ -554,8 +573,14 @@ void page_add_anon_rmap(struct page *page, VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); if (atomic_inc_and_test(&page->_mapcount)) __page_set_anon_rmap(page, vma, address); - else + else { __page_check_anon_rmap(page, vma, address); + /* + * We unconditionally charged during prepare, we uncharge here + * This takes care of balancing the reference counts + */ + mem_cgroup_uncharge_page(page); + } } /* @@ -586,6 +611,12 @@ void page_add_file_rmap(struct page *page) { if (atomic_inc_and_test(&page->_mapcount)) __inc_zone_page_state(page, NR_FILE_MAPPED); + else + /* + * We unconditionally charged during prepare, we uncharge here + * This takes care of balancing the reference counts + */ + mem_cgroup_uncharge_page(page); } #ifdef CONFIG_DEBUG_VM @@ -646,6 +677,8 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma) page_clear_dirty(page); set_page_dirty(page); } + mem_cgroup_uncharge_page(page); + __dec_zone_page_state(page, PageAnon(page) ? NR_ANON_PAGES : NR_FILE_MAPPED); } diff --git a/mm/shmem.c b/mm/shmem.c index 0f246c44a574..85bed948fafc 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -912,9 +912,13 @@ found: error = 1; if (!inode) goto out; - error = radix_tree_preload(GFP_KERNEL); + /* Precharge page while we can wait, compensate afterwards */ + error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); if (error) goto out; + error = radix_tree_preload(GFP_KERNEL); + if (error) + goto uncharge; error = 1; spin_lock(&info->lock); @@ -947,6 +951,8 @@ found: shmem_swp_unmap(ptr); spin_unlock(&info->lock); radix_tree_preload_end(); +uncharge: + mem_cgroup_uncharge_page(page); out: unlock_page(page); page_cache_release(page); @@ -1308,6 +1314,13 @@ repeat: spin_unlock(&info->lock); unlock_page(swappage); page_cache_release(swappage); + if (error == -ENOMEM) { + /* allow reclaim from this memory cgroup */ + error = mem_cgroup_cache_charge(NULL, + current->mm, gfp & ~__GFP_HIGHMEM); + if (error) + goto failed; + } goto repeat; } } else if (sgp == SGP_READ && !filepage) { @@ -1353,6 +1366,17 @@ repeat: goto failed; } + /* Precharge page while we can wait, compensate after */ + error = mem_cgroup_cache_charge(filepage, current->mm, + gfp & ~__GFP_HIGHMEM); + if (error) { + page_cache_release(filepage); + shmem_unacct_blocks(info->flags, 1); + shmem_free_blocks(inode, 1); + filepage = NULL; + goto failed; + } + spin_lock(&info->lock); entry = shmem_swp_alloc(info, idx, sgp); if (IS_ERR(entry)) @@ -1364,6 +1388,7 @@ repeat: if (error || swap.val || 0 != add_to_page_cache_lru( filepage, mapping, idx, GFP_NOWAIT)) { spin_unlock(&info->lock); + mem_cgroup_uncharge_page(filepage); page_cache_release(filepage); shmem_unacct_blocks(info->flags, 1); shmem_free_blocks(inode, 1); @@ -1372,6 +1397,7 @@ repeat: goto failed; goto repeat; } + mem_cgroup_uncharge_page(filepage); info->flags |= SHMEM_PAGEIN; } diff --git a/mm/swap.c b/mm/swap.c index 57b7e25a939c..710a20bb9749 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -29,6 +29,7 @@ #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> +#include <linux/memcontrol.h> /* How many pages do we try to swap or page in/out together? */ int page_cluster; @@ -175,6 +176,7 @@ void activate_page(struct page *page) SetPageActive(page); add_page_to_active_list(zone, page); __count_vm_event(PGACTIVATE); + mem_cgroup_move_lists(page_get_page_cgroup(page), true); } spin_unlock_irq(&zone->lru_lock); } diff --git a/mm/swapfile.c b/mm/swapfile.c index eade24da9310..02ccab5ad9d9 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -27,6 +27,7 @@ #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> +#include <linux/memcontrol.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -511,11 +512,16 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, { spinlock_t *ptl; pte_t *pte; - int found = 1; + int ret = 1; + + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) + ret = -ENOMEM; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) { - found = 0; + if (ret > 0) + mem_cgroup_uncharge_page(page); + ret = 0; goto out; } @@ -532,7 +538,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, activate_page(page); out: pte_unmap_unlock(pte, ptl); - return found; + return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, @@ -541,7 +547,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, { pte_t swp_pte = swp_entry_to_pte(entry); pte_t *pte; - int found = 0; + int ret = 0; /* * We don't actually need pte lock while scanning for swp_pte: since @@ -560,15 +566,15 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, */ if (unlikely(pte_same(*pte, swp_pte))) { pte_unmap(pte); - found = unuse_pte(vma, pmd, addr, entry, page); - if (found) + ret = unuse_pte(vma, pmd, addr, entry, page); + if (ret) goto out; pte = pte_offset_map(pmd, addr); } } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap(pte - 1); out: - return found; + return ret; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, @@ -577,14 +583,16 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, { pmd_t *pmd; unsigned long next; + int ret; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; - if (unuse_pte_range(vma, pmd, addr, next, entry, page)) - return 1; + ret = unuse_pte_range(vma, pmd, addr, next, entry, page); + if (ret) + return ret; } while (pmd++, addr = next, addr != end); return 0; } @@ -595,14 +603,16 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, { pud_t *pud; unsigned long next; + int ret; pud = pud_offset(pgd, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - if (unuse_pmd_range(vma, pud, addr, next, entry, page)) - return 1; + ret = unuse_pmd_range(vma, pud, addr, next, entry, page); + if (ret) + return ret; } while (pud++, addr = next, addr != end); return 0; } @@ -612,6 +622,7 @@ static int unuse_vma(struct vm_area_struct *vma, { pgd_t *pgd; unsigned long addr, end, next; + int ret; if (page->mapping) { addr = page_address_in_vma(page, vma); @@ -629,8 +640,9 @@ static int unuse_vma(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - if (unuse_pud_range(vma, pgd, addr, next, entry, page)) - return 1; + ret = unuse_pud_range(vma, pgd, addr, next, entry, page); + if (ret) + return ret; } while (pgd++, addr = next, addr != end); return 0; } @@ -639,6 +651,7 @@ static int unuse_mm(struct mm_struct *mm, swp_entry_t entry, struct page *page) { struct vm_area_struct *vma; + int ret = 0; if (!down_read_trylock(&mm->mmap_sem)) { /* @@ -651,15 +664,11 @@ static int unuse_mm(struct mm_struct *mm, lock_page(page); } for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (vma->anon_vma && unuse_vma(vma, entry, page)) + if (vma->anon_vma && (ret = unuse_vma(vma, entry, page))) break; } up_read(&mm->mmap_sem); - /* - * Currently unuse_mm cannot fail, but leave error handling - * at call sites for now, since we change it from time to time. - */ - return 0; + return (ret < 0)? ret: 0; } /* diff --git a/mm/vmscan.c b/mm/vmscan.c index e5a9597e3bbc..a26dabd62fed 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -37,6 +37,7 @@ #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> +#include <linux/memcontrol.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -68,6 +69,22 @@ struct scan_control { int all_unreclaimable; int order; + + /* + * Pages that have (or should have) IO pending. If we run into + * a lot of these, we're better off waiting a little for IO to + * finish rather than scanning more pages in the VM. + */ + int nr_io_pages; + + /* Which cgroup do we reclaim from */ + struct mem_cgroup *mem_cgroup; + + /* Pluggable isolate pages callback */ + unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst, + unsigned long *scanned, int order, int mode, + struct zone *z, struct mem_cgroup *mem_cont, + int active); }; #define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru)) @@ -109,6 +126,12 @@ long vm_total_pages; /* The total number of pages which the VM controls */ static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); +#ifdef CONFIG_CGROUP_MEM_CONT +#define scan_global_lru(sc) (!(sc)->mem_cgroup) +#else +#define scan_global_lru(sc) (1) +#endif + /* * Add a shrinker callback to be called from the vm */ @@ -489,11 +512,13 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ if (sync_writeback == PAGEOUT_IO_SYNC && may_enter_fs) wait_on_page_writeback(page); - else + else { + sc->nr_io_pages++; goto keep_locked; + } } - referenced = page_referenced(page, 1); + referenced = page_referenced(page, 1, sc->mem_cgroup); /* In active use or really unfreeable? Activate it. */ if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && referenced && page_mapping_inuse(page)) @@ -529,8 +554,10 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (PageDirty(page)) { if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && referenced) goto keep_locked; - if (!may_enter_fs) + if (!may_enter_fs) { + sc->nr_io_pages++; goto keep_locked; + } if (!sc->may_writepage) goto keep_locked; @@ -541,8 +568,10 @@ static unsigned long shrink_page_list(struct list_head *page_list, case PAGE_ACTIVATE: goto activate_locked; case PAGE_SUCCESS: - if (PageWriteback(page) || PageDirty(page)) + if (PageWriteback(page) || PageDirty(page)) { + sc->nr_io_pages++; goto keep; + } /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the page. @@ -626,7 +655,7 @@ keep: * * returns 0 on success, -ve errno on failure. */ -static int __isolate_lru_page(struct page *page, int mode) +int __isolate_lru_page(struct page *page, int mode) { int ret = -EINVAL; @@ -760,6 +789,21 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, return nr_taken; } +static unsigned long isolate_pages_global(unsigned long nr, + struct list_head *dst, + unsigned long *scanned, int order, + int mode, struct zone *z, + struct mem_cgroup *mem_cont, + int active) +{ + if (active) + return isolate_lru_pages(nr, &z->active_list, dst, + scanned, order, mode); + else + return isolate_lru_pages(nr, &z->inactive_list, dst, + scanned, order, mode); +} + /* * clear_active_flags() is a helper for shrink_active_list(), clearing * any active bits from the pages in the list. @@ -801,18 +845,19 @@ static unsigned long shrink_inactive_list(unsigned long max_scan, unsigned long nr_freed; unsigned long nr_active; - nr_taken = isolate_lru_pages(sc->swap_cluster_max, - &zone->inactive_list, + nr_taken = sc->isolate_pages(sc->swap_cluster_max, &page_list, &nr_scan, sc->order, (sc->order > PAGE_ALLOC_COSTLY_ORDER)? - ISOLATE_BOTH : ISOLATE_INACTIVE); + ISOLATE_BOTH : ISOLATE_INACTIVE, + zone, sc->mem_cgroup, 0); nr_active = clear_active_flags(&page_list); __count_vm_events(PGDEACTIVATE, nr_active); __mod_zone_page_state(zone, NR_ACTIVE, -nr_active); __mod_zone_page_state(zone, NR_INACTIVE, -(nr_taken - nr_active)); - zone->pages_scanned += nr_scan; + if (scan_global_lru(sc)) + zone->pages_scanned += nr_scan; spin_unlock_irq(&zone->lru_lock); nr_scanned += nr_scan; @@ -844,8 +889,9 @@ static unsigned long shrink_inactive_list(unsigned long max_scan, if (current_is_kswapd()) { __count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan); __count_vm_events(KSWAPD_STEAL, nr_freed); - } else + } else if (scan_global_lru(sc)) __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan); + __count_zone_vm_events(PGSTEAL, zone, nr_freed); if (nr_taken == 0) @@ -899,6 +945,113 @@ static inline int zone_is_near_oom(struct zone *zone) } /* + * Determine we should try to reclaim mapped pages. + * This is called only when sc->mem_cgroup is NULL. + */ +static int calc_reclaim_mapped(struct scan_control *sc, struct zone *zone, + int priority) +{ + long mapped_ratio; + long distress; + long swap_tendency; + long imbalance; + int reclaim_mapped = 0; + int prev_priority; + + if (scan_global_lru(sc) && zone_is_near_oom(zone)) + return 1; + /* + * `distress' is a measure of how much trouble we're having + * reclaiming pages. 0 -> no problems. 100 -> great trouble. + */ + if (scan_global_lru(sc)) + prev_priority = zone->prev_priority; + else + prev_priority = mem_cgroup_get_reclaim_priority(sc->mem_cgroup); + + distress = 100 >> min(prev_priority, priority); + + /* + * The point of this algorithm is to decide when to start + * reclaiming mapped memory instead of just pagecache. Work out + * how much memory + * is mapped. + */ + if (scan_global_lru(sc)) + mapped_ratio = ((global_page_state(NR_FILE_MAPPED) + + global_page_state(NR_ANON_PAGES)) * 100) / + vm_total_pages; + else + mapped_ratio = mem_cgroup_calc_mapped_ratio(sc->mem_cgroup); + + /* + * Now decide how much we really want to unmap some pages. The + * mapped ratio is downgraded - just because there's a lot of + * mapped memory doesn't necessarily mean that page reclaim + * isn't succeeding. + * + * The distress ratio is important - we don't want to start + * going oom. + * + * A 100% value of vm_swappiness overrides this algorithm + * altogether. + */ + swap_tendency = mapped_ratio / 2 + distress + sc->swappiness; + + /* + * If there's huge imbalance between active and inactive + * (think active 100 times larger than inactive) we should + * become more permissive, or the system will take too much + * cpu before it start swapping during memory pressure. + * Distress is about avoiding early-oom, this is about + * making swappiness graceful despite setting it to low + * values. + * + * Avoid div by zero with nr_inactive+1, and max resulting + * value is vm_total_pages. + */ + if (scan_global_lru(sc)) { + imbalance = zone_page_state(zone, NR_ACTIVE); + imbalance /= zone_page_state(zone, NR_INACTIVE) + 1; + } else + imbalance = mem_cgroup_reclaim_imbalance(sc->mem_cgroup); + + /* + * Reduce the effect of imbalance if swappiness is low, + * this means for a swappiness very low, the imbalance + * must be much higher than 100 for this logic to make + * the difference. + * + * Max temporary value is vm_total_pages*100. + */ + imbalance *= (vm_swappiness + 1); + imbalance /= 100; + + /* + * If not much of the ram is mapped, makes the imbalance + * less relevant, it's high priority we refill the inactive + * list with mapped pages only in presence of high ratio of + * mapped pages. + * + * Max temporary value is vm_total_pages*100. + */ + imbalance *= mapped_ratio; + imbalance /= 100; + + /* apply imbalance feedback to swap_tendency */ + swap_tendency += imbalance; + + /* + * Now use this metric to decide whether to start moving mapped + * memory onto the inactive list. + */ + if (swap_tendency >= 100) + reclaim_mapped = 1; + + return reclaim_mapped; +} + +/* * This moves pages from the active list to the inactive list. * * We move them the other way if the page is referenced by one or more @@ -915,6 +1068,8 @@ static inline int zone_is_near_oom(struct zone *zone) * The downside is that we have to touch page->_count against each page. * But we had to alter page->flags anyway. */ + + static void shrink_active_list(unsigned long nr_pages, struct zone *zone, struct scan_control *sc, int priority) { @@ -928,99 +1083,21 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, struct pagevec pvec; int reclaim_mapped = 0; - if (sc->may_swap) { - long mapped_ratio; - long distress; - long swap_tendency; - long imbalance; - - if (zone_is_near_oom(zone)) - goto force_reclaim_mapped; - - /* - * `distress' is a measure of how much trouble we're having - * reclaiming pages. 0 -> no problems. 100 -> great trouble. - */ - distress = 100 >> min(zone->prev_priority, priority); - - /* - * The point of this algorithm is to decide when to start - * reclaiming mapped memory instead of just pagecache. Work out - * how much memory - * is mapped. - */ - mapped_ratio = ((global_page_state(NR_FILE_MAPPED) + - global_page_state(NR_ANON_PAGES)) * 100) / - vm_total_pages; - - /* - * Now decide how much we really want to unmap some pages. The - * mapped ratio is downgraded - just because there's a lot of - * mapped memory doesn't necessarily mean that page reclaim - * isn't succeeding. - * - * The distress ratio is important - we don't want to start - * going oom. - * - * A 100% value of vm_swappiness overrides this algorithm - * altogether. - */ - swap_tendency = mapped_ratio / 2 + distress + sc->swappiness; - - /* - * If there's huge imbalance between active and inactive - * (think active 100 times larger than inactive) we should - * become more permissive, or the system will take too much - * cpu before it start swapping during memory pressure. - * Distress is about avoiding early-oom, this is about - * making swappiness graceful despite setting it to low - * values. - * - * Avoid div by zero with nr_inactive+1, and max resulting - * value is vm_total_pages. - */ - imbalance = zone_page_state(zone, NR_ACTIVE); - imbalance /= zone_page_state(zone, NR_INACTIVE) + 1; - - /* - * Reduce the effect of imbalance if swappiness is low, - * this means for a swappiness very low, the imbalance - * must be much higher than 100 for this logic to make - * the difference. - * - * Max temporary value is vm_total_pages*100. - */ - imbalance *= (vm_swappiness + 1); - imbalance /= 100; - - /* - * If not much of the ram is mapped, makes the imbalance - * less relevant, it's high priority we refill the inactive - * list with mapped pages only in presence of high ratio of - * mapped pages. - * - * Max temporary value is vm_total_pages*100. - */ - imbalance *= mapped_ratio; - imbalance /= 100; - - /* apply imbalance feedback to swap_tendency */ - swap_tendency += imbalance; - - /* - * Now use this metric to decide whether to start moving mapped - * memory onto the inactive list. - */ - if (swap_tendency >= 100) -force_reclaim_mapped: - reclaim_mapped = 1; - } + if (sc->may_swap) + reclaim_mapped = calc_reclaim_mapped(sc, zone, priority); lru_add_drain(); spin_lock_irq(&zone->lru_lock); - pgmoved = isolate_lru_pages(nr_pages, &zone->active_list, - &l_hold, &pgscanned, sc->order, ISOLATE_ACTIVE); - zone->pages_scanned += pgscanned; + pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order, + ISOLATE_ACTIVE, zone, + sc->mem_cgroup, 1); + /* + * zone->pages_scanned is used for detect zone's oom + * mem_cgroup remembers nr_scan by itself. + */ + if (scan_global_lru(sc)) + zone->pages_scanned += pgscanned; + __mod_zone_page_state(zone, NR_ACTIVE, -pgmoved); spin_unlock_irq(&zone->lru_lock); @@ -1031,7 +1108,7 @@ force_reclaim_mapped: if (page_mapped(page)) { if (!reclaim_mapped || (total_swap_pages == 0 && PageAnon(page)) || - page_referenced(page, 0)) { + page_referenced(page, 0, sc->mem_cgroup)) { list_add(&page->lru, &l_active); continue; } @@ -1051,6 +1128,7 @@ force_reclaim_mapped: ClearPageActive(page); list_move(&page->lru, &zone->inactive_list); + mem_cgroup_move_lists(page_get_page_cgroup(page), false); pgmoved++; if (!pagevec_add(&pvec, page)) { __mod_zone_page_state(zone, NR_INACTIVE, pgmoved); @@ -1079,6 +1157,7 @@ force_reclaim_mapped: SetPageLRU(page); VM_BUG_ON(!PageActive(page)); list_move(&page->lru, &zone->active_list); + mem_cgroup_move_lists(page_get_page_cgroup(page), true); pgmoved++; if (!pagevec_add(&pvec, page)) { __mod_zone_page_state(zone, NR_ACTIVE, pgmoved); @@ -1108,25 +1187,39 @@ static unsigned long shrink_zone(int priority, struct zone *zone, unsigned long nr_to_scan; unsigned long nr_reclaimed = 0; - /* - * Add one to `nr_to_scan' just to make sure that the kernel will - * slowly sift through the active list. - */ - zone->nr_scan_active += - (zone_page_state(zone, NR_ACTIVE) >> priority) + 1; - nr_active = zone->nr_scan_active; - if (nr_active >= sc->swap_cluster_max) - zone->nr_scan_active = 0; - else - nr_active = 0; + if (scan_global_lru(sc)) { + /* + * Add one to nr_to_scan just to make sure that the kernel + * will slowly sift through the active list. + */ + zone->nr_scan_active += + (zone_page_state(zone, NR_ACTIVE) >> priority) + 1; + nr_active = zone->nr_scan_active; + zone->nr_scan_inactive += + (zone_page_state(zone, NR_INACTIVE) >> priority) + 1; + nr_inactive = zone->nr_scan_inactive; + if (nr_inactive >= sc->swap_cluster_max) + zone->nr_scan_inactive = 0; + else + nr_inactive = 0; + + if (nr_active >= sc->swap_cluster_max) + zone->nr_scan_active = 0; + else + nr_active = 0; + } else { + /* + * This reclaim occurs not because zone memory shortage but + * because memory controller hits its limit. + * Then, don't modify zone reclaim related data. + */ + nr_active = mem_cgroup_calc_reclaim_active(sc->mem_cgroup, + zone, priority); + + nr_inactive = mem_cgroup_calc_reclaim_inactive(sc->mem_cgroup, + zone, priority); + } - zone->nr_scan_inactive += - (zone_page_state(zone, NR_INACTIVE) >> priority) + 1; - nr_inactive = zone->nr_scan_inactive; - if (nr_inactive >= sc->swap_cluster_max) - zone->nr_scan_inactive = 0; - else - nr_inactive = 0; while (nr_active || nr_inactive) { if (nr_active) { @@ -1171,25 +1264,39 @@ static unsigned long shrink_zones(int priority, struct zone **zones, unsigned long nr_reclaimed = 0; int i; + sc->all_unreclaimable = 1; for (i = 0; zones[i] != NULL; i++) { struct zone *zone = zones[i]; if (!populated_zone(zone)) continue; + /* + * Take care memory controller reclaiming has small influence + * to global LRU. + */ + if (scan_global_lru(sc)) { + if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) + continue; + note_zone_scanning_priority(zone, priority); - if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) - continue; - - note_zone_scanning_priority(zone, priority); - - if (zone_is_all_unreclaimable(zone) && priority != DEF_PRIORITY) - continue; /* Let kswapd poll it */ - - sc->all_unreclaimable = 0; + if (zone_is_all_unreclaimable(zone) && + priority != DEF_PRIORITY) + continue; /* Let kswapd poll it */ + sc->all_unreclaimable = 0; + } else { + /* + * Ignore cpuset limitation here. We just want to reduce + * # of used pages by us regardless of memory shortage. + */ + sc->all_unreclaimable = 0; + mem_cgroup_note_reclaim_priority(sc->mem_cgroup, + priority); + } nr_reclaimed += shrink_zone(priority, zone, sc); } + return nr_reclaimed; } @@ -1206,7 +1313,8 @@ static unsigned long shrink_zones(int priority, struct zone **zones, * holds filesystem locks which prevent writeout this might not work, and the * allocation attempt will fail. */ -unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask) +static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask, + struct scan_control *sc) { int priority; int ret = 0; @@ -1215,39 +1323,43 @@ unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask) struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long lru_pages = 0; int i; - struct scan_control sc = { - .gfp_mask = gfp_mask, - .may_writepage = !laptop_mode, - .swap_cluster_max = SWAP_CLUSTER_MAX, - .may_swap = 1, - .swappiness = vm_swappiness, - .order = order, - }; - - count_vm_event(ALLOCSTALL); - for (i = 0; zones[i] != NULL; i++) { - struct zone *zone = zones[i]; + if (scan_global_lru(sc)) + count_vm_event(ALLOCSTALL); + /* + * mem_cgroup will not do shrink_slab. + */ + if (scan_global_lru(sc)) { + for (i = 0; zones[i] != NULL; i++) { + struct zone *zone = zones[i]; - if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) - continue; + if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) + continue; - lru_pages += zone_page_state(zone, NR_ACTIVE) - + zone_page_state(zone, NR_INACTIVE); + lru_pages += zone_page_state(zone, NR_ACTIVE) + + zone_page_state(zone, NR_INACTIVE); + } } for (priority = DEF_PRIORITY; priority >= 0; priority--) { - sc.nr_scanned = 0; + sc->nr_scanned = 0; + sc->nr_io_pages = 0; if (!priority) disable_swap_token(); - nr_reclaimed += shrink_zones(priority, zones, &sc); - shrink_slab(sc.nr_scanned, gfp_mask, lru_pages); - if (reclaim_state) { - nr_reclaimed += reclaim_state->reclaimed_slab; - reclaim_state->reclaimed_slab = 0; + nr_reclaimed += shrink_zones(priority, zones, sc); + /* + * Don't shrink slabs when reclaiming memory from + * over limit cgroups + */ + if (scan_global_lru(sc)) { + shrink_slab(sc->nr_scanned, gfp_mask, lru_pages); + if (reclaim_state) { + nr_reclaimed += reclaim_state->reclaimed_slab; + reclaim_state->reclaimed_slab = 0; + } } - total_scanned += sc.nr_scanned; - if (nr_reclaimed >= sc.swap_cluster_max) { + total_scanned += sc->nr_scanned; + if (nr_reclaimed >= sc->swap_cluster_max) { ret = 1; goto out; } @@ -1259,18 +1371,19 @@ unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask) * that's undesirable in laptop mode, where we *want* lumpy * writeout. So in laptop mode, write out the whole world. */ - if (total_scanned > sc.swap_cluster_max + - sc.swap_cluster_max / 2) { + if (total_scanned > sc->swap_cluster_max + + sc->swap_cluster_max / 2) { wakeup_pdflush(laptop_mode ? 0 : total_scanned); - sc.may_writepage = 1; + sc->may_writepage = 1; } /* Take a nap, wait for some writeback to complete */ - if (sc.nr_scanned && priority < DEF_PRIORITY - 2) + if (sc->nr_scanned && priority < DEF_PRIORITY - 2 && + sc->nr_io_pages > sc->swap_cluster_max) congestion_wait(WRITE, HZ/10); } /* top priority shrink_caches still had more to do? don't OOM, then */ - if (!sc.all_unreclaimable) + if (!sc->all_unreclaimable && scan_global_lru(sc)) ret = 1; out: /* @@ -1282,17 +1395,63 @@ out: */ if (priority < 0) priority = 0; - for (i = 0; zones[i] != NULL; i++) { - struct zone *zone = zones[i]; - if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) - continue; + if (scan_global_lru(sc)) { + for (i = 0; zones[i] != NULL; i++) { + struct zone *zone = zones[i]; + + if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) + continue; + + zone->prev_priority = priority; + } + } else + mem_cgroup_record_reclaim_priority(sc->mem_cgroup, priority); - zone->prev_priority = priority; - } return ret; } +unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask) +{ + struct scan_control sc = { + .gfp_mask = gfp_mask, + .may_writepage = !laptop_mode, + .swap_cluster_max = SWAP_CLUSTER_MAX, + .may_swap = 1, + .swappiness = vm_swappiness, + .order = order, + .mem_cgroup = NULL, + .isolate_pages = isolate_pages_global, + }; + + return do_try_to_free_pages(zones, gfp_mask, &sc); +} + +#ifdef CONFIG_CGROUP_MEM_CONT + +unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, + gfp_t gfp_mask) +{ + struct scan_control sc = { + .gfp_mask = gfp_mask, + .may_writepage = !laptop_mode, + .may_swap = 1, + .swap_cluster_max = SWAP_CLUSTER_MAX, + .swappiness = vm_swappiness, + .order = 0, + .mem_cgroup = mem_cont, + .isolate_pages = mem_cgroup_isolate_pages, + }; + struct zone **zones; + int target_zone = gfp_zone(GFP_HIGHUSER_MOVABLE); + + zones = NODE_DATA(numa_node_id())->node_zonelists[target_zone].zones; + if (do_try_to_free_pages(zones, sc.gfp_mask, &sc)) + return 1; + return 0; +} +#endif + /* * For kswapd, balance_pgdat() will work across all this node's zones until * they are all at pages_high. @@ -1328,6 +1487,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order) .swap_cluster_max = SWAP_CLUSTER_MAX, .swappiness = vm_swappiness, .order = order, + .mem_cgroup = NULL, + .isolate_pages = isolate_pages_global, }; /* * temp_priority is used to remember the scanning priority at which @@ -1352,6 +1513,7 @@ loop_again: if (!priority) disable_swap_token(); + sc.nr_io_pages = 0; all_zones_ok = 1; /* @@ -1444,7 +1606,8 @@ loop_again: * OK, kswapd is getting into trouble. Take a nap, then take * another pass across the zones. */ - if (total_scanned && priority < DEF_PRIORITY - 2) + if (total_scanned && priority < DEF_PRIORITY - 2 && + sc.nr_io_pages > sc.swap_cluster_max) congestion_wait(WRITE, HZ/10); /* @@ -1649,6 +1812,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages) .swap_cluster_max = nr_pages, .may_writepage = 1, .swappiness = vm_swappiness, + .isolate_pages = isolate_pages_global, }; current->reclaim_state = &reclaim_state; @@ -1834,6 +1998,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) SWAP_CLUSTER_MAX), .gfp_mask = gfp_mask, .swappiness = vm_swappiness, + .isolate_pages = isolate_pages_global, }; unsigned long slab_reclaimable; |