X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmemcontrol.c;h=f99f5991d6bba1b5ec224f0631124144a6c0a8bb;hb=ef8745c1e7fc5413d760b3b958f3fd3a0beaad72;hp=59dd8c1163724c464575bd2acc02dabb10d74c74;hpb=c077719be8e9e6b55702117513d1b5f41d80404a;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 59dd8c1..f99f599 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -27,6 +27,9 @@ #include #include #include +#include +#include +#include #include #include #include @@ -35,20 +38,24 @@ #include #include #include +#include "internal.h" #include struct cgroup_subsys mem_cgroup_subsys __read_mostly; #define MEM_CGROUP_RECLAIM_RETRIES 5 +struct mem_cgroup *root_mem_cgroup __read_mostly; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP -/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */ +/* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */ int do_swap_account __read_mostly; static int really_do_swap_account __initdata = 1; /* for remember boot option*/ #else #define do_swap_account (0) #endif +static DEFINE_MUTEX(memcg_tasklist); /* can be hold under cgroup_mutex */ +#define SOFTLIMIT_EVENTS_THRESH (1000) /* * Statistics for memory cgroup. @@ -58,9 +65,12 @@ 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_RSS, /* # of pages charged as anon rss */ + MEM_CGROUP_STAT_MAPPED_FILE, /* # of pages charged as file rss */ MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */ MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */ + MEM_CGROUP_STAT_EVENTS, /* sum of pagein + pageout for internal use */ + MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, }; @@ -73,6 +83,20 @@ struct mem_cgroup_stat { struct mem_cgroup_stat_cpu cpustat[0]; }; +static inline void +__mem_cgroup_stat_reset_safe(struct mem_cgroup_stat_cpu *stat, + enum mem_cgroup_stat_index idx) +{ + stat->count[idx] = 0; +} + +static inline s64 +__mem_cgroup_stat_read_local(struct mem_cgroup_stat_cpu *stat, + enum mem_cgroup_stat_index idx) +{ + return stat->count[idx]; +} + /* * For accounting under irq disable, no need for increment preempt count. */ @@ -92,6 +116,15 @@ static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat, return ret; } +static s64 mem_cgroup_local_usage(struct mem_cgroup_stat *stat) +{ + s64 ret; + + ret = mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_CACHE); + ret += mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_RSS); + return ret; +} + /* * per-zone information in memory controller. */ @@ -99,9 +132,16 @@ struct mem_cgroup_per_zone { /* * spin_lock to protect the per cgroup LRU */ - spinlock_t lru_lock; struct list_head lists[NR_LRU_LISTS]; unsigned long count[NR_LRU_LISTS]; + + struct zone_reclaim_stat reclaim_stat; + struct rb_node tree_node; /* RB tree node */ + unsigned long long usage_in_excess;/* Set to the value by which */ + /* the soft limit is exceeded*/ + bool on_tree; + struct mem_cgroup *mem; /* Back pointer, we cannot */ + /* use container_of */ }; /* Macro for accessing counter */ #define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)]) @@ -115,6 +155,26 @@ struct mem_cgroup_lru_info { }; /* + * Cgroups above their limits are maintained in a RB-Tree, independent of + * their hierarchy representation + */ + +struct mem_cgroup_tree_per_zone { + struct rb_root rb_root; + spinlock_t lock; +}; + +struct mem_cgroup_tree_per_node { + struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES]; +}; + +struct mem_cgroup_tree { + struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; +}; + +static struct mem_cgroup_tree soft_limit_tree __read_mostly; + +/* * 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, @@ -132,55 +192,312 @@ struct mem_cgroup { */ struct res_counter res; /* + * the counter to account for mem+swap usage. + */ + struct res_counter memsw; + /* * Per cgroup active and inactive list, similar to the * per zone LRU lists. */ struct mem_cgroup_lru_info info; + /* + protect against reclaim related member. + */ + spinlock_t reclaim_param_lock; + int prev_priority; /* for recording reclaim priority */ + + /* + * While reclaiming in a hiearchy, we cache the last child we + * reclaimed from. + */ + int last_scanned_child; + /* + * Should the accounting and control be hierarchical, per subtree? + */ + bool use_hierarchy; + unsigned long last_oom_jiffies; + atomic_t refcnt; + + unsigned int swappiness; + + /* set when res.limit == memsw.limit */ + bool memsw_is_minimum; + /* * statistics. This must be placed at the end of memcg. */ struct mem_cgroup_stat stat; }; +/* + * Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft + * limit reclaim to prevent infinite loops, if they ever occur. + */ +#define MEM_CGROUP_MAX_RECLAIM_LOOPS (100) +#define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS (2) + enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, MEM_CGROUP_CHARGE_TYPE_MAPPED, MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */ MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */ MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */ + MEM_CGROUP_CHARGE_TYPE_DROP, /* a page was unused swap cache */ NR_CHARGE_TYPE, }; /* only for here (for easy reading.) */ #define PCGF_CACHE (1UL << PCG_CACHE) #define PCGF_USED (1UL << PCG_USED) -#define PCGF_ACTIVE (1UL << PCG_ACTIVE) #define PCGF_LOCK (1UL << PCG_LOCK) -#define PCGF_FILE (1UL << PCG_FILE) -static const unsigned long -pcg_default_flags[NR_CHARGE_TYPE] = { - PCGF_CACHE | PCGF_FILE | PCGF_USED | PCGF_LOCK, /* File Cache */ - PCGF_ACTIVE | PCGF_USED | PCGF_LOCK, /* Anon */ - PCGF_ACTIVE | PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */ - 0, /* FORCE */ -}; +/* Not used, but added here for completeness */ +#define PCGF_ACCT (1UL << PCG_ACCT) + +/* for encoding cft->private value on file */ +#define _MEM (0) +#define _MEMSWAP (1) +#define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val)) +#define MEMFILE_TYPE(val) (((val) >> 16) & 0xffff) +#define MEMFILE_ATTR(val) ((val) & 0xffff) /* - * Always modified under lru lock. Then, not necessary to preempt_disable() + * Reclaim flags for mem_cgroup_hierarchical_reclaim */ +#define MEM_CGROUP_RECLAIM_NOSWAP_BIT 0x0 +#define MEM_CGROUP_RECLAIM_NOSWAP (1 << MEM_CGROUP_RECLAIM_NOSWAP_BIT) +#define MEM_CGROUP_RECLAIM_SHRINK_BIT 0x1 +#define MEM_CGROUP_RECLAIM_SHRINK (1 << MEM_CGROUP_RECLAIM_SHRINK_BIT) +#define MEM_CGROUP_RECLAIM_SOFT_BIT 0x2 +#define MEM_CGROUP_RECLAIM_SOFT (1 << MEM_CGROUP_RECLAIM_SOFT_BIT) + +static void mem_cgroup_get(struct mem_cgroup *mem); +static void mem_cgroup_put(struct mem_cgroup *mem); +static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem); + +static struct mem_cgroup_per_zone * +mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid) +{ + return &mem->info.nodeinfo[nid]->zoneinfo[zid]; +} + +static 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); + + if (!mem) + return NULL; + + return mem_cgroup_zoneinfo(mem, nid, zid); +} + +static struct mem_cgroup_tree_per_zone * +soft_limit_tree_node_zone(int nid, int zid) +{ + return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; +} + +static struct mem_cgroup_tree_per_zone * +soft_limit_tree_from_page(struct page *page) +{ + int nid = page_to_nid(page); + int zid = page_zonenum(page); + + return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; +} + +static void +__mem_cgroup_insert_exceeded(struct mem_cgroup *mem, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz, + unsigned long long new_usage_in_excess) +{ + struct rb_node **p = &mctz->rb_root.rb_node; + struct rb_node *parent = NULL; + struct mem_cgroup_per_zone *mz_node; + + if (mz->on_tree) + return; + + mz->usage_in_excess = new_usage_in_excess; + if (!mz->usage_in_excess) + return; + while (*p) { + parent = *p; + mz_node = rb_entry(parent, struct mem_cgroup_per_zone, + tree_node); + if (mz->usage_in_excess < mz_node->usage_in_excess) + p = &(*p)->rb_left; + /* + * We can't avoid mem cgroups that are over their soft + * limit by the same amount + */ + else if (mz->usage_in_excess >= mz_node->usage_in_excess) + p = &(*p)->rb_right; + } + rb_link_node(&mz->tree_node, parent, p); + rb_insert_color(&mz->tree_node, &mctz->rb_root); + mz->on_tree = true; +} + +static void +__mem_cgroup_remove_exceeded(struct mem_cgroup *mem, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) +{ + if (!mz->on_tree) + return; + rb_erase(&mz->tree_node, &mctz->rb_root); + mz->on_tree = false; +} + +static void +mem_cgroup_remove_exceeded(struct mem_cgroup *mem, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) +{ + spin_lock(&mctz->lock); + __mem_cgroup_remove_exceeded(mem, mz, mctz); + spin_unlock(&mctz->lock); +} + +static bool mem_cgroup_soft_limit_check(struct mem_cgroup *mem) +{ + bool ret = false; + int cpu; + s64 val; + struct mem_cgroup_stat_cpu *cpustat; + + cpu = get_cpu(); + cpustat = &mem->stat.cpustat[cpu]; + val = __mem_cgroup_stat_read_local(cpustat, MEM_CGROUP_STAT_EVENTS); + if (unlikely(val > SOFTLIMIT_EVENTS_THRESH)) { + __mem_cgroup_stat_reset_safe(cpustat, MEM_CGROUP_STAT_EVENTS); + ret = true; + } + put_cpu(); + return ret; +} + +static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page) +{ + unsigned long long excess; + struct mem_cgroup_per_zone *mz; + struct mem_cgroup_tree_per_zone *mctz; + int nid = page_to_nid(page); + int zid = page_zonenum(page); + mctz = soft_limit_tree_from_page(page); + + /* + * Necessary to update all ancestors when hierarchy is used. + * because their event counter is not touched. + */ + for (; mem; mem = parent_mem_cgroup(mem)) { + mz = mem_cgroup_zoneinfo(mem, nid, zid); + excess = res_counter_soft_limit_excess(&mem->res); + /* + * We have to update the tree if mz is on RB-tree or + * mem is over its softlimit. + */ + if (excess || mz->on_tree) { + spin_lock(&mctz->lock); + /* if on-tree, remove it */ + if (mz->on_tree) + __mem_cgroup_remove_exceeded(mem, mz, mctz); + /* + * Insert again. mz->usage_in_excess will be updated. + * If excess is 0, no tree ops. + */ + __mem_cgroup_insert_exceeded(mem, mz, mctz, excess); + spin_unlock(&mctz->lock); + } + } +} + +static void mem_cgroup_remove_from_trees(struct mem_cgroup *mem) +{ + int node, zone; + struct mem_cgroup_per_zone *mz; + struct mem_cgroup_tree_per_zone *mctz; + + for_each_node_state(node, N_POSSIBLE) { + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + mz = mem_cgroup_zoneinfo(mem, node, zone); + mctz = soft_limit_tree_node_zone(node, zone); + mem_cgroup_remove_exceeded(mem, mz, mctz); + } + } +} + +static inline unsigned long mem_cgroup_get_excess(struct mem_cgroup *mem) +{ + return res_counter_soft_limit_excess(&mem->res) >> PAGE_SHIFT; +} + +static struct mem_cgroup_per_zone * +__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +{ + struct rb_node *rightmost = NULL; + struct mem_cgroup_per_zone *mz; + +retry: + mz = NULL; + rightmost = rb_last(&mctz->rb_root); + if (!rightmost) + goto done; /* Nothing to reclaim from */ + + mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node); + /* + * Remove the node now but someone else can add it back, + * we will to add it back at the end of reclaim to its correct + * position in the tree. + */ + __mem_cgroup_remove_exceeded(mz->mem, mz, mctz); + if (!res_counter_soft_limit_excess(&mz->mem->res) || + !css_tryget(&mz->mem->css)) + goto retry; +done: + return mz; +} + +static struct mem_cgroup_per_zone * +mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +{ + struct mem_cgroup_per_zone *mz; + + spin_lock(&mctz->lock); + mz = __mem_cgroup_largest_soft_limit_node(mctz); + spin_unlock(&mctz->lock); + return mz; +} + +static void mem_cgroup_swap_statistics(struct mem_cgroup *mem, + bool charge) +{ + int val = (charge) ? 1 : -1; + struct mem_cgroup_stat *stat = &mem->stat; + struct mem_cgroup_stat_cpu *cpustat; + int cpu = get_cpu(); + + cpustat = &stat->cpustat[cpu]; + __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_SWAPOUT, val); + put_cpu(); +} + static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, struct page_cgroup *pc, bool charge) { - int val = (charge)? 1 : -1; + int val = (charge) ? 1 : -1; struct mem_cgroup_stat *stat = &mem->stat; struct mem_cgroup_stat_cpu *cpustat; + int cpu = get_cpu(); - VM_BUG_ON(!irqs_disabled()); - - cpustat = &stat->cpustat[smp_processor_id()]; + cpustat = &stat->cpustat[cpu]; if (PageCgroupCache(pc)) __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_CACHE, val); else @@ -192,25 +509,11 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, else __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_PGPGOUT_COUNT, 1); + __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_EVENTS, 1); + put_cpu(); } -static struct mem_cgroup_per_zone * -mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid) -{ - return &mem->info.nodeinfo[nid]->zoneinfo[zid]; -} - -static 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, +static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem, enum lru_list idx) { int nid, zid; @@ -246,138 +549,221 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) struct mem_cgroup, css); } -static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz, - struct page_cgroup *pc) +static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) { - int lru = LRU_BASE; - - if (PageCgroupUnevictable(pc)) - lru = LRU_UNEVICTABLE; - else { - if (PageCgroupActive(pc)) - lru += LRU_ACTIVE; - if (PageCgroupFile(pc)) - lru += LRU_FILE; - } - - MEM_CGROUP_ZSTAT(mz, lru) -= 1; + struct mem_cgroup *mem = NULL; - mem_cgroup_charge_statistics(pc->mem_cgroup, pc, false); - list_del(&pc->lru); + if (!mm) + return NULL; + /* + * Because we have no locks, mm->owner's may be being moved to other + * cgroup. We use css_tryget() here even if this looks + * pessimistic (rather than adding locks here). + */ + rcu_read_lock(); + do { + mem = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!mem)) + break; + } while (!css_tryget(&mem->css)); + rcu_read_unlock(); + return mem; } -static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz, - struct page_cgroup *pc, bool hot) +/* + * Call callback function against all cgroup under hierarchy tree. + */ +static int mem_cgroup_walk_tree(struct mem_cgroup *root, void *data, + int (*func)(struct mem_cgroup *, void *)) { - int lru = LRU_BASE; + int found, ret, nextid; + struct cgroup_subsys_state *css; + struct mem_cgroup *mem; - if (PageCgroupUnevictable(pc)) - lru = LRU_UNEVICTABLE; - else { - if (PageCgroupActive(pc)) - lru += LRU_ACTIVE; - if (PageCgroupFile(pc)) - lru += LRU_FILE; - } + if (!root->use_hierarchy) + return (*func)(root, data); - MEM_CGROUP_ZSTAT(mz, lru) += 1; - if (hot) - list_add(&pc->lru, &mz->lists[lru]); - else - list_add_tail(&pc->lru, &mz->lists[lru]); + nextid = 1; + do { + ret = 0; + mem = NULL; + + rcu_read_lock(); + css = css_get_next(&mem_cgroup_subsys, nextid, &root->css, + &found); + if (css && css_tryget(css)) + mem = container_of(css, struct mem_cgroup, css); + rcu_read_unlock(); - mem_cgroup_charge_statistics(pc->mem_cgroup, pc, true); + if (mem) { + ret = (*func)(mem, data); + css_put(&mem->css); + } + nextid = found + 1; + } while (!ret && css); + + return ret; } -static void __mem_cgroup_move_lists(struct page_cgroup *pc, enum lru_list lru) +static inline bool mem_cgroup_is_root(struct mem_cgroup *mem) { - struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc); - int active = PageCgroupActive(pc); - int file = PageCgroupFile(pc); - int unevictable = PageCgroupUnevictable(pc); - enum lru_list from = unevictable ? LRU_UNEVICTABLE : - (LRU_FILE * !!file + !!active); + return (mem == root_mem_cgroup); +} - if (lru == from) - return; +/* + * Following LRU functions are allowed to be used without PCG_LOCK. + * Operations are called by routine of global LRU independently from memcg. + * What we have to take care of here is validness of pc->mem_cgroup. + * + * Changes to pc->mem_cgroup happens when + * 1. charge + * 2. moving account + * In typical case, "charge" is done before add-to-lru. Exception is SwapCache. + * It is added to LRU before charge. + * If PCG_USED bit is not set, page_cgroup is not added to this private LRU. + * When moving account, the page is not on LRU. It's isolated. + */ + +void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru) +{ + struct page_cgroup *pc; + struct mem_cgroup_per_zone *mz; - MEM_CGROUP_ZSTAT(mz, from) -= 1; + if (mem_cgroup_disabled()) + return; + pc = lookup_page_cgroup(page); + /* can happen while we handle swapcache. */ + if (!TestClearPageCgroupAcctLRU(pc)) + return; + VM_BUG_ON(!pc->mem_cgroup); /* - * However this is done under mz->lru_lock, another flags, which - * are not related to LRU, will be modified from out-of-lock. - * We have to use atomic set/clear flags. + * We don't check PCG_USED bit. It's cleared when the "page" is finally + * removed from global LRU. */ - if (is_unevictable_lru(lru)) { - ClearPageCgroupActive(pc); - SetPageCgroupUnevictable(pc); - } else { - if (is_active_lru(lru)) - SetPageCgroupActive(pc); - else - ClearPageCgroupActive(pc); - ClearPageCgroupUnevictable(pc); - } + mz = page_cgroup_zoneinfo(pc); + MEM_CGROUP_ZSTAT(mz, lru) -= 1; + if (mem_cgroup_is_root(pc->mem_cgroup)) + return; + VM_BUG_ON(list_empty(&pc->lru)); + list_del_init(&pc->lru); + return; +} - MEM_CGROUP_ZSTAT(mz, lru) += 1; - list_move(&pc->lru, &mz->lists[lru]); +void mem_cgroup_del_lru(struct page *page) +{ + mem_cgroup_del_lru_list(page, page_lru(page)); } -int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) +void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru) { - int ret; + struct mem_cgroup_per_zone *mz; + struct page_cgroup *pc; - task_lock(task); - ret = task->mm && mm_match_cgroup(task->mm, mem); - task_unlock(task); - return ret; + if (mem_cgroup_disabled()) + return; + + pc = lookup_page_cgroup(page); + /* + * Used bit is set without atomic ops but after smp_wmb(). + * For making pc->mem_cgroup visible, insert smp_rmb() here. + */ + smp_rmb(); + /* unused or root page is not rotated. */ + if (!PageCgroupUsed(pc) || mem_cgroup_is_root(pc->mem_cgroup)) + return; + mz = page_cgroup_zoneinfo(pc); + list_move(&pc->lru, &mz->lists[lru]); } -/* - * This routine assumes that the appropriate zone's lru lock is already held - */ -void mem_cgroup_move_lists(struct page *page, enum lru_list lru) +void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru) { struct page_cgroup *pc; struct mem_cgroup_per_zone *mz; - unsigned long flags; - if (mem_cgroup_subsys.disabled) + if (mem_cgroup_disabled()) return; - + pc = lookup_page_cgroup(page); + VM_BUG_ON(PageCgroupAcctLRU(pc)); /* - * 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. + * Used bit is set without atomic ops but after smp_wmb(). + * For making pc->mem_cgroup visible, insert smp_rmb() here. */ - pc = lookup_page_cgroup(page); - if (!trylock_page_cgroup(pc)) + smp_rmb(); + if (!PageCgroupUsed(pc)) return; - if (pc && PageCgroupUsed(pc)) { - mz = page_cgroup_zoneinfo(pc); - spin_lock_irqsave(&mz->lru_lock, flags); - __mem_cgroup_move_lists(pc, lru); - spin_unlock_irqrestore(&mz->lru_lock, flags); - } - unlock_page_cgroup(pc); + + mz = page_cgroup_zoneinfo(pc); + MEM_CGROUP_ZSTAT(mz, lru) += 1; + SetPageCgroupAcctLRU(pc); + if (mem_cgroup_is_root(pc->mem_cgroup)) + return; + list_add(&pc->lru, &mz->lists[lru]); } /* - * Calculate mapped_ratio under memory controller. This will be used in - * vmscan.c for deteremining we have to reclaim mapped pages. + * At handling SwapCache, pc->mem_cgroup may be changed while it's linked to + * lru because the page may.be reused after it's fully uncharged (because of + * SwapCache behavior).To handle that, unlink page_cgroup from LRU when charge + * it again. This function is only used to charge SwapCache. It's done under + * lock_page and expected that zone->lru_lock is never held. */ -int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem) +static void mem_cgroup_lru_del_before_commit_swapcache(struct page *page) { - long total, rss; + unsigned long flags; + struct zone *zone = page_zone(page); + struct page_cgroup *pc = lookup_page_cgroup(page); + spin_lock_irqsave(&zone->lru_lock, flags); /* - * usage is recorded in bytes. But, here, we assume the number of - * physical pages can be represented by "long" on any arch. + * Forget old LRU when this page_cgroup is *not* used. This Used bit + * is guarded by lock_page() because the page is SwapCache. */ - 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); + if (!PageCgroupUsed(pc)) + mem_cgroup_del_lru_list(page, page_lru(page)); + spin_unlock_irqrestore(&zone->lru_lock, flags); +} + +static void mem_cgroup_lru_add_after_commit_swapcache(struct page *page) +{ + unsigned long flags; + struct zone *zone = page_zone(page); + struct page_cgroup *pc = lookup_page_cgroup(page); + + spin_lock_irqsave(&zone->lru_lock, flags); + /* link when the page is linked to LRU but page_cgroup isn't */ + if (PageLRU(page) && !PageCgroupAcctLRU(pc)) + mem_cgroup_add_lru_list(page, page_lru(page)); + spin_unlock_irqrestore(&zone->lru_lock, flags); +} + + +void mem_cgroup_move_lists(struct page *page, + enum lru_list from, enum lru_list to) +{ + if (mem_cgroup_disabled()) + return; + mem_cgroup_del_lru_list(page, from); + mem_cgroup_add_lru_list(page, to); +} + +int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) +{ + int ret; + struct mem_cgroup *curr = NULL; + + task_lock(task); + rcu_read_lock(); + curr = try_get_mem_cgroup_from_mm(task->mm); + rcu_read_unlock(); + task_unlock(task); + if (!curr) + return 0; + if (curr->use_hierarchy) + ret = css_is_ancestor(&curr->css, &mem->css); + else + ret = (curr == mem); + css_put(&curr->css); + return ret; } /* @@ -385,39 +771,127 @@ int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem) */ int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem) { - return mem->prev_priority; + int prev_priority; + + spin_lock(&mem->reclaim_param_lock); + prev_priority = mem->prev_priority; + spin_unlock(&mem->reclaim_param_lock); + + return prev_priority; } void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority) { + spin_lock(&mem->reclaim_param_lock); if (priority < mem->prev_priority) mem->prev_priority = priority; + spin_unlock(&mem->reclaim_param_lock); } void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority) { + spin_lock(&mem->reclaim_param_lock); mem->prev_priority = priority; + spin_unlock(&mem->reclaim_param_lock); } -/* - * 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) - */ +static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_pages) +{ + unsigned long active; + unsigned long inactive; + unsigned long gb; + unsigned long inactive_ratio; -long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone, - int priority, enum lru_list lru) + inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_ANON); + active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_ANON); + + gb = (inactive + active) >> (30 - PAGE_SHIFT); + if (gb) + inactive_ratio = int_sqrt(10 * gb); + else + inactive_ratio = 1; + + if (present_pages) { + present_pages[0] = inactive; + present_pages[1] = active; + } + + return inactive_ratio; +} + +int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg) +{ + unsigned long active; + unsigned long inactive; + unsigned long present_pages[2]; + unsigned long inactive_ratio; + + inactive_ratio = calc_inactive_ratio(memcg, present_pages); + + inactive = present_pages[0]; + active = present_pages[1]; + + if (inactive * inactive_ratio < active) + return 1; + + return 0; +} + +int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg) +{ + unsigned long active; + unsigned long inactive; + + inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_FILE); + active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_FILE); + + return (active > inactive); +} + +unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, + struct zone *zone, + enum lru_list lru) +{ + int nid = zone->zone_pgdat->node_id; + int zid = zone_idx(zone); + struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid); + + return MEM_CGROUP_ZSTAT(mz, lru); +} + +struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, + struct zone *zone) { - long nr_pages; int nid = zone->zone_pgdat->node_id; int zid = zone_idx(zone); - struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid); + struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid); + + return &mz->reclaim_stat; +} + +struct zone_reclaim_stat * +mem_cgroup_get_reclaim_stat_from_page(struct page *page) +{ + struct page_cgroup *pc; + struct mem_cgroup_per_zone *mz; - nr_pages = MEM_CGROUP_ZSTAT(mz, lru); + if (mem_cgroup_disabled()) + return NULL; + + pc = lookup_page_cgroup(page); + /* + * Used bit is set without atomic ops but after smp_wmb(). + * For making pc->mem_cgroup visible, insert smp_rmb() here. + */ + smp_rmb(); + if (!PageCgroupUsed(pc)) + return NULL; - return (nr_pages >> priority); + mz = page_cgroup_zoneinfo(pc); + if (!mz) + return NULL; + + return &mz->reclaim_stat; } unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, @@ -436,48 +910,352 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, int nid = z->zone_pgdat->node_id; int zid = zone_idx(z); struct mem_cgroup_per_zone *mz; - int lru = LRU_FILE * !!file + !!active; + int lru = LRU_FILE * file + active; + int ret; BUG_ON(!mem_cont); mz = mem_cgroup_zoneinfo(mem_cont, nid, zid); src = &mz->lists[lru]; - spin_lock(&mz->lru_lock); - scan = 0; - list_for_each_entry_safe_reverse(pc, tmp, src, lru) { - if (scan >= nr_to_scan) - break; - if (unlikely(!PageCgroupUsed(pc))) - continue; - page = pc->page; + scan = 0; + list_for_each_entry_safe_reverse(pc, tmp, src, lru) { + if (scan >= nr_to_scan) + break; + + page = pc->page; + if (unlikely(!PageCgroupUsed(pc))) + continue; + if (unlikely(!PageLRU(page))) + continue; + + scan++; + ret = __isolate_lru_page(page, mode, file); + switch (ret) { + case 0: + list_move(&page->lru, dst); + mem_cgroup_del_lru(page); + nr_taken++; + break; + case -EBUSY: + /* we don't affect global LRU but rotate in our LRU */ + mem_cgroup_rotate_lru_list(page, page_lru(page)); + break; + default: + break; + } + } + + *scanned = scan; + return nr_taken; +} + +#define mem_cgroup_from_res_counter(counter, member) \ + container_of(counter, struct mem_cgroup, member) + +static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem) +{ + if (do_swap_account) { + if (res_counter_check_under_limit(&mem->res) && + res_counter_check_under_limit(&mem->memsw)) + return true; + } else + if (res_counter_check_under_limit(&mem->res)) + return true; + return false; +} + +static unsigned int get_swappiness(struct mem_cgroup *memcg) +{ + struct cgroup *cgrp = memcg->css.cgroup; + unsigned int swappiness; + + /* root ? */ + if (cgrp->parent == NULL) + return vm_swappiness; + + spin_lock(&memcg->reclaim_param_lock); + swappiness = memcg->swappiness; + spin_unlock(&memcg->reclaim_param_lock); + + return swappiness; +} + +static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data) +{ + int *val = data; + (*val)++; + return 0; +} + +/** + * mem_cgroup_print_mem_info: Called from OOM with tasklist_lock held in read mode. + * @memcg: The memory cgroup that went over limit + * @p: Task that is going to be killed + * + * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is + * enabled + */ +void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) +{ + struct cgroup *task_cgrp; + struct cgroup *mem_cgrp; + /* + * Need a buffer in BSS, can't rely on allocations. The code relies + * on the assumption that OOM is serialized for memory controller. + * If this assumption is broken, revisit this code. + */ + static char memcg_name[PATH_MAX]; + int ret; + + if (!memcg) + return; + + + rcu_read_lock(); + + mem_cgrp = memcg->css.cgroup; + task_cgrp = task_cgroup(p, mem_cgroup_subsys_id); + + ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX); + if (ret < 0) { + /* + * Unfortunately, we are unable to convert to a useful name + * But we'll still print out the usage information + */ + rcu_read_unlock(); + goto done; + } + rcu_read_unlock(); + + printk(KERN_INFO "Task in %s killed", memcg_name); + + rcu_read_lock(); + ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX); + if (ret < 0) { + rcu_read_unlock(); + goto done; + } + rcu_read_unlock(); + + /* + * Continues from above, so we don't need an KERN_ level + */ + printk(KERN_CONT " as a result of limit of %s\n", memcg_name); +done: + + printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n", + res_counter_read_u64(&memcg->res, RES_USAGE) >> 10, + res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10, + res_counter_read_u64(&memcg->res, RES_FAILCNT)); + printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, " + "failcnt %llu\n", + res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10, + res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10, + res_counter_read_u64(&memcg->memsw, RES_FAILCNT)); +} + +/* + * This function returns the number of memcg under hierarchy tree. Returns + * 1(self count) if no children. + */ +static int mem_cgroup_count_children(struct mem_cgroup *mem) +{ + int num = 0; + mem_cgroup_walk_tree(mem, &num, mem_cgroup_count_children_cb); + return num; +} + +/* + * Visit the first child (need not be the first child as per the ordering + * of the cgroup list, since we track last_scanned_child) of @mem and use + * that to reclaim free pages from. + */ +static struct mem_cgroup * +mem_cgroup_select_victim(struct mem_cgroup *root_mem) +{ + struct mem_cgroup *ret = NULL; + struct cgroup_subsys_state *css; + int nextid, found; + + if (!root_mem->use_hierarchy) { + css_get(&root_mem->css); + ret = root_mem; + } + + while (!ret) { + rcu_read_lock(); + nextid = root_mem->last_scanned_child + 1; + css = css_get_next(&mem_cgroup_subsys, nextid, &root_mem->css, + &found); + if (css && css_tryget(css)) + ret = container_of(css, struct mem_cgroup, css); + + rcu_read_unlock(); + /* Updates scanning parameter */ + spin_lock(&root_mem->reclaim_param_lock); + if (!css) { + /* this means start scan from ID:1 */ + root_mem->last_scanned_child = 0; + } else + root_mem->last_scanned_child = found; + spin_unlock(&root_mem->reclaim_param_lock); + } + + return ret; +} + +/* + * Scan the hierarchy if needed to reclaim memory. We remember the last child + * we reclaimed from, so that we don't end up penalizing one child extensively + * based on its position in the children list. + * + * root_mem is the original ancestor that we've been reclaim from. + * + * We give up and return to the caller when we visit root_mem twice. + * (other groups can be removed while we're walking....) + * + * If shrink==true, for avoiding to free too much, this returns immedieately. + */ +static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, + struct zone *zone, + gfp_t gfp_mask, + unsigned long reclaim_options) +{ + struct mem_cgroup *victim; + int ret, total = 0; + int loop = 0; + bool noswap = reclaim_options & MEM_CGROUP_RECLAIM_NOSWAP; + bool shrink = reclaim_options & MEM_CGROUP_RECLAIM_SHRINK; + bool check_soft = reclaim_options & MEM_CGROUP_RECLAIM_SOFT; + unsigned long excess = mem_cgroup_get_excess(root_mem); + + /* If memsw_is_minimum==1, swap-out is of-no-use. */ + if (root_mem->memsw_is_minimum) + noswap = true; + + while (1) { + victim = mem_cgroup_select_victim(root_mem); + if (victim == root_mem) { + loop++; + if (loop >= 2) { + /* + * If we have not been able to reclaim + * anything, it might because there are + * no reclaimable pages under this hierarchy + */ + if (!check_soft || !total) { + css_put(&victim->css); + break; + } + /* + * We want to do more targetted reclaim. + * excess >> 2 is not to excessive so as to + * reclaim too much, nor too less that we keep + * coming back to reclaim from this cgroup + */ + if (total >= (excess >> 2) || + (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) { + css_put(&victim->css); + break; + } + } + } + if (!mem_cgroup_local_usage(&victim->stat)) { + /* this cgroup's local usage == 0 */ + css_put(&victim->css); + continue; + } + /* we use swappiness of local cgroup */ + if (check_soft) + ret = mem_cgroup_shrink_node_zone(victim, gfp_mask, + noswap, get_swappiness(victim), zone, + zone->zone_pgdat->node_id); + else + ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, + noswap, get_swappiness(victim)); + css_put(&victim->css); + /* + * At shrinking usage, we can't check we should stop here or + * reclaim more. It's depends on callers. last_scanned_child + * will work enough for keeping fairness under tree. + */ + if (shrink) + return ret; + total += ret; + if (check_soft) { + if (res_counter_check_under_soft_limit(&root_mem->res)) + return total; + } else if (mem_cgroup_check_under_limit(root_mem)) + return 1 + total; + } + return total; +} + +bool mem_cgroup_oom_called(struct task_struct *task) +{ + bool ret = false; + struct mem_cgroup *mem; + struct mm_struct *mm; + + rcu_read_lock(); + mm = task->mm; + if (!mm) + mm = &init_mm; + mem = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (mem && time_before(jiffies, mem->last_oom_jiffies + HZ/10)) + ret = true; + rcu_read_unlock(); + return ret; +} + +static int record_last_oom_cb(struct mem_cgroup *mem, void *data) +{ + mem->last_oom_jiffies = jiffies; + return 0; +} + +static void record_last_oom(struct mem_cgroup *mem) +{ + mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb); +} - if (unlikely(!PageLRU(page))) - continue; +/* + * Currently used to update mapped file statistics, but the routine can be + * generalized to update other statistics as well. + */ +void mem_cgroup_update_mapped_file_stat(struct page *page, int val) +{ + struct mem_cgroup *mem; + struct mem_cgroup_stat *stat; + struct mem_cgroup_stat_cpu *cpustat; + int cpu; + struct page_cgroup *pc; - /* - * TODO: play better with lumpy reclaim, grabbing anything. - */ - if (PageUnevictable(page) || - (PageActive(page) && !active) || - (!PageActive(page) && active)) { - __mem_cgroup_move_lists(pc, page_lru(page)); - continue; - } + if (!page_is_file_cache(page)) + return; - scan++; - list_move(&pc->lru, &pc_list); + pc = lookup_page_cgroup(page); + if (unlikely(!pc)) + return; - if (__isolate_lru_page(page, mode, file) == 0) { - list_move(&page->lru, dst); - nr_taken++; - } - } + lock_page_cgroup(pc); + mem = pc->mem_cgroup; + if (!mem) + goto done; - list_splice(&pc_list, src); - spin_unlock(&mz->lru_lock); + if (!PageCgroupUsed(pc)) + goto done; - *scanned = scan; - return nr_taken; + /* + * Preemption is already disabled, we don't need get_cpu() + */ + cpu = smp_processor_id(); + stat = &mem->stat; + cpustat = &stat->cpustat[cpu]; + + __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE, val); +done: + unlock_page_cgroup(pc); } /* @@ -485,40 +1263,67 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, * oom-killer can be invoked. */ static int __mem_cgroup_try_charge(struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcg, bool oom) + gfp_t gfp_mask, struct mem_cgroup **memcg, + bool oom, struct page *page) { - struct mem_cgroup *mem; + struct mem_cgroup *mem, *mem_over_limit; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; + struct res_counter *fail_res; + + if (unlikely(test_thread_flag(TIF_MEMDIE))) { + /* Don't account this! */ + *memcg = NULL; + return 0; + } + /* * We always charge the cgroup the mm_struct belongs to. * The mm_struct's mem_cgroup changes on task migration if the * thread group leader migrates. It's possible that mm is not * set, if so charge the init_mm (happens for pagecache usage). */ - if (likely(!*memcg)) { - rcu_read_lock(); - mem = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!mem)) { - rcu_read_unlock(); - return 0; - } - /* - * For every charge from the cgroup, increment reference count - */ - css_get(&mem->css); + mem = *memcg; + if (likely(!mem)) { + mem = try_get_mem_cgroup_from_mm(mm); *memcg = mem; - rcu_read_unlock(); } else { - mem = *memcg; css_get(&mem->css); } + if (unlikely(!mem)) + return 0; + VM_BUG_ON(css_is_removed(&mem->css)); + + while (1) { + int ret = 0; + unsigned long flags = 0; + + if (mem_cgroup_is_root(mem)) + goto done; + ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res); + if (likely(!ret)) { + if (!do_swap_account) + break; + ret = res_counter_charge(&mem->memsw, PAGE_SIZE, + &fail_res); + if (likely(!ret)) + break; + /* mem+swap counter fails */ + res_counter_uncharge(&mem->res, PAGE_SIZE); + flags |= MEM_CGROUP_RECLAIM_NOSWAP; + mem_over_limit = mem_cgroup_from_res_counter(fail_res, + memsw); + } else + /* mem counter fails */ + mem_over_limit = mem_cgroup_from_res_counter(fail_res, + res); - while (unlikely(res_counter_charge(&mem->res, PAGE_SIZE))) { if (!(gfp_mask & __GFP_WAIT)) goto nomem; - if (try_to_free_mem_cgroup_pages(mem, gfp_mask)) + ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL, + gfp_mask, flags); + if (ret) continue; /* @@ -527,43 +1332,86 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, * 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)) + if (mem_cgroup_check_under_limit(mem_over_limit)) continue; if (!nr_retries--) { - if (oom) - mem_cgroup_out_of_memory(mem, gfp_mask); + if (oom) { + mutex_lock(&memcg_tasklist); + mem_cgroup_out_of_memory(mem_over_limit, gfp_mask); + mutex_unlock(&memcg_tasklist); + record_last_oom(mem_over_limit); + } goto nomem; } } + /* + * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. + * if they exceeds softlimit. + */ + if (mem_cgroup_soft_limit_check(mem)) + mem_cgroup_update_tree(mem, page); +done: return 0; nomem: css_put(&mem->css); return -ENOMEM; } -/** - * mem_cgroup_try_charge - get charge of PAGE_SIZE. - * @mm: an mm_struct which is charged against. (when *memcg is NULL) - * @gfp_mask: gfp_mask for reclaim. - * @memcg: a pointer to memory cgroup which is charged against. - * - * charge against memory cgroup pointed by *memcg. if *memcg == NULL, estimated - * memory cgroup from @mm is got and stored in *memcg. - * - * Returns 0 if success. -ENOMEM at failure. - * This call can invoke OOM-Killer. +/* + * A helper function to get mem_cgroup from ID. must be called under + * rcu_read_lock(). The caller must check css_is_removed() or some if + * it's concern. (dropping refcnt from swap can be called against removed + * memcg.) */ +static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) +{ + struct cgroup_subsys_state *css; + + /* ID 0 is unused ID */ + if (!id) + return NULL; + css = css_lookup(&mem_cgroup_subsys, id); + if (!css) + return NULL; + return container_of(css, struct mem_cgroup, css); +} -int mem_cgroup_try_charge(struct mm_struct *mm, - gfp_t mask, struct mem_cgroup **memcg) +static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page) { - return __mem_cgroup_try_charge(mm, mask, memcg, true); + struct mem_cgroup *mem; + struct page_cgroup *pc; + unsigned short id; + swp_entry_t ent; + + VM_BUG_ON(!PageLocked(page)); + + if (!PageSwapCache(page)) + return NULL; + + pc = lookup_page_cgroup(page); + lock_page_cgroup(pc); + if (PageCgroupUsed(pc)) { + mem = pc->mem_cgroup; + if (mem && !css_tryget(&mem->css)) + mem = NULL; + } else { + ent.val = page_private(page); + id = lookup_swap_cgroup(ent); + rcu_read_lock(); + mem = mem_cgroup_lookup(id); + if (mem && !css_tryget(&mem->css)) + mem = NULL; + rcu_read_unlock(); + } + unlock_page_cgroup(pc); + return mem; } /* - * commit a charge got by mem_cgroup_try_charge() and makes page_cgroup to be + * commit a charge got by __mem_cgroup_try_charge() and makes page_cgroup to be * USED state. If already USED, uncharge and return. */ @@ -571,9 +1419,6 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, struct page_cgroup *pc, enum charge_type ctype) { - struct mem_cgroup_per_zone *mz; - unsigned long flags; - /* try_charge() can return NULL to *memcg, taking care of it. */ if (!mem) return; @@ -581,22 +1426,40 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, lock_page_cgroup(pc); if (unlikely(PageCgroupUsed(pc))) { unlock_page_cgroup(pc); - res_counter_uncharge(&mem->res, PAGE_SIZE); + if (!mem_cgroup_is_root(mem)) { + res_counter_uncharge(&mem->res, PAGE_SIZE); + if (do_swap_account) + res_counter_uncharge(&mem->memsw, PAGE_SIZE); + } css_put(&mem->css); return; } + pc->mem_cgroup = mem; /* - * If a page is accounted as a page cache, insert to inactive list. - * If anon, insert to active list. - */ - pc->flags = pcg_default_flags[ctype]; + * We access a page_cgroup asynchronously without lock_page_cgroup(). + * Especially when a page_cgroup is taken from a page, pc->mem_cgroup + * is accessed after testing USED bit. To make pc->mem_cgroup visible + * before USED bit, we need memory barrier here. + * See mem_cgroup_add_lru_list(), etc. + */ + smp_wmb(); + switch (ctype) { + case MEM_CGROUP_CHARGE_TYPE_CACHE: + case MEM_CGROUP_CHARGE_TYPE_SHMEM: + SetPageCgroupCache(pc); + SetPageCgroupUsed(pc); + break; + case MEM_CGROUP_CHARGE_TYPE_MAPPED: + ClearPageCgroupCache(pc); + SetPageCgroupUsed(pc); + break; + default: + break; + } - mz = page_cgroup_zoneinfo(pc); + mem_cgroup_charge_statistics(mem, pc, true); - spin_lock_irqsave(&mz->lru_lock, flags); - __mem_cgroup_add_list(mz, pc, true); - spin_unlock_irqrestore(&mz->lru_lock, flags); unlock_page_cgroup(pc); } @@ -607,8 +1470,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, * @to: mem_cgroup which the page is moved to. @from != @to. * * The caller must confirm following. - * 1. disable irq. - * 2. lru_lock of old mem_cgroup(@from) should be held. + * - page is not on LRU (isolate_page() is useful.) * * returns 0 at success, * returns -EBUSY when lock is busy or "pc" is unstable. @@ -623,16 +1485,19 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, struct mem_cgroup_per_zone *from_mz, *to_mz; int nid, zid; int ret = -EBUSY; + struct page *page; + int cpu; + struct mem_cgroup_stat *stat; + struct mem_cgroup_stat_cpu *cpustat; - VM_BUG_ON(!irqs_disabled()); VM_BUG_ON(from == to); + VM_BUG_ON(PageLRU(pc->page)); nid = page_cgroup_nid(pc); zid = page_cgroup_zid(pc); from_mz = mem_cgroup_zoneinfo(from, nid, zid); to_mz = mem_cgroup_zoneinfo(to, nid, zid); - if (!trylock_page_cgroup(pc)) return ret; @@ -642,18 +1507,42 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, if (pc->mem_cgroup != from) goto out; - if (spin_trylock(&to_mz->lru_lock)) { - __mem_cgroup_remove_list(from_mz, pc); - css_put(&from->css); + if (!mem_cgroup_is_root(from)) res_counter_uncharge(&from->res, PAGE_SIZE); - pc->mem_cgroup = to; - css_get(&to->css); - __mem_cgroup_add_list(to_mz, pc, false); - ret = 0; - spin_unlock(&to_mz->lru_lock); + mem_cgroup_charge_statistics(from, pc, false); + + page = pc->page; + if (page_is_file_cache(page) && page_mapped(page)) { + cpu = smp_processor_id(); + /* Update mapped_file data for mem_cgroup "from" */ + stat = &from->stat; + cpustat = &stat->cpustat[cpu]; + __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE, + -1); + + /* Update mapped_file data for mem_cgroup "to" */ + stat = &to->stat; + cpustat = &stat->cpustat[cpu]; + __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE, + 1); } + + if (do_swap_account && !mem_cgroup_is_root(from)) + res_counter_uncharge(&from->memsw, PAGE_SIZE); + css_put(&from->css); + + css_get(&to->css); + pc->mem_cgroup = to; + mem_cgroup_charge_statistics(to, pc, true); + ret = 0; out: unlock_page_cgroup(pc); + /* + * We charges against "to" which may not have any tasks. Then, "to" + * can be under rmdir(). But in current implementation, caller of + * this function is just force_empty() and it's garanteed that + * "to" is never removed. So, we don't check rmdir status here. + */ return ret; } @@ -665,36 +1554,55 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc, struct mem_cgroup *child, gfp_t gfp_mask) { + struct page *page = pc->page; struct cgroup *cg = child->css.cgroup; struct cgroup *pcg = cg->parent; struct mem_cgroup *parent; - struct mem_cgroup_per_zone *mz; - unsigned long flags; int ret; /* Is ROOT ? */ if (!pcg) return -EINVAL; + parent = mem_cgroup_from_cont(pcg); - ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false); - if (ret) + + ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false, page); + if (ret || !parent) return ret; - mz = mem_cgroup_zoneinfo(child, - page_cgroup_nid(pc), page_cgroup_zid(pc)); + if (!get_page_unless_zero(page)) { + ret = -EBUSY; + goto uncharge; + } + + ret = isolate_lru_page(page); + + if (ret) + goto cancel; - spin_lock_irqsave(&mz->lru_lock, flags); ret = mem_cgroup_move_account(pc, child, parent); - spin_unlock_irqrestore(&mz->lru_lock, flags); - /* drop extra refcnt */ + putback_lru_page(page); + if (!ret) { + put_page(page); + /* drop extra refcnt by try_charge() */ + css_put(&parent->css); + return 0; + } + +cancel: + put_page(page); +uncharge: + /* drop extra refcnt by try_charge() */ css_put(&parent->css); /* uncharge if move fails */ - if (ret) + if (!mem_cgroup_is_root(parent)) { res_counter_uncharge(&parent->res, PAGE_SIZE); - + if (do_swap_account) + res_counter_uncharge(&parent->memsw, PAGE_SIZE); + } return ret; } @@ -719,8 +1627,8 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, prefetchw(pc); mem = memcg; - ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true); - if (ret) + ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page); + if (ret || !mem) return ret; __mem_cgroup_commit_charge(mem, pc, ctype); @@ -730,7 +1638,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { - if (mem_cgroup_subsys.disabled) + if (mem_cgroup_disabled()) return 0; if (PageCompound(page)) return 0; @@ -749,10 +1657,17 @@ int mem_cgroup_newpage_charge(struct page *page, MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL); } +static void +__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, + enum charge_type ctype); + int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { - if (mem_cgroup_subsys.disabled) + struct mem_cgroup *mem = NULL; + int ret; + + if (mem_cgroup_disabled()) return 0; if (PageCompound(page)) return 0; @@ -764,6 +1679,8 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, * For GFP_NOWAIT case, the page may be pre-charged before calling * add_to_page_cache(). (See shmem.c) check it here and avoid to call * charge twice. (It works but has to pay a bit larger cost.) + * And when the page is SwapCache, it should take swap information + * into account. This is under lock_page() now. */ if (!(gfp_mask & __GFP_WAIT)) { struct page_cgroup *pc; @@ -780,63 +1697,132 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, unlock_page_cgroup(pc); } - if (unlikely(!mm)) + if (unlikely(!mm && !mem)) mm = &init_mm; if (page_is_file_cache(page)) return mem_cgroup_charge_common(page, mm, gfp_mask, MEM_CGROUP_CHARGE_TYPE_CACHE, NULL); - else - return mem_cgroup_charge_common(page, mm, gfp_mask, - MEM_CGROUP_CHARGE_TYPE_SHMEM, NULL); + + /* shmem */ + if (PageSwapCache(page)) { + ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem); + if (!ret) + __mem_cgroup_commit_charge_swapin(page, mem, + MEM_CGROUP_CHARGE_TYPE_SHMEM); + } else + ret = mem_cgroup_charge_common(page, mm, gfp_mask, + MEM_CGROUP_CHARGE_TYPE_SHMEM, mem); + + return ret; } -#ifdef CONFIG_SWAP -int mem_cgroup_cache_charge_swapin(struct page *page, - struct mm_struct *mm, gfp_t mask, bool locked) +/* + * While swap-in, try_charge -> commit or cancel, the page is locked. + * And when try_charge() successfully returns, one refcnt to memcg without + * struct page_cgroup is aquired. This refcnt will be cumsumed by + * "commit()" or removed by "cancel()" + */ +int mem_cgroup_try_charge_swapin(struct mm_struct *mm, + struct page *page, + gfp_t mask, struct mem_cgroup **ptr) { - int ret = 0; + struct mem_cgroup *mem; + int ret; - if (mem_cgroup_subsys.disabled) + if (mem_cgroup_disabled()) return 0; - if (unlikely(!mm)) - mm = &init_mm; - if (!locked) - lock_page(page); + + if (!do_swap_account) + goto charge_cur_mm; /* - * If not locked, the page can be dropped from SwapCache until - * we reach here. + * A racing thread's fault, or swapoff, may have already updated + * the pte, and even removed page from swap cache: return success + * to go on to do_swap_page()'s pte_same() test, which should fail. */ - if (PageSwapCache(page)) { - ret = mem_cgroup_charge_common(page, mm, mask, - MEM_CGROUP_CHARGE_TYPE_SHMEM, NULL); - } - if (!locked) - unlock_page(page); - + if (!PageSwapCache(page)) + return 0; + mem = try_get_mem_cgroup_from_swapcache(page); + if (!mem) + goto charge_cur_mm; + *ptr = mem; + ret = __mem_cgroup_try_charge(NULL, mask, ptr, true, page); + /* drop extra refcnt from tryget */ + css_put(&mem->css); return ret; +charge_cur_mm: + if (unlikely(!mm)) + mm = &init_mm; + return __mem_cgroup_try_charge(mm, mask, ptr, true, page); } -#endif -void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) +static void +__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, + enum charge_type ctype) { struct page_cgroup *pc; - if (mem_cgroup_subsys.disabled) + if (mem_cgroup_disabled()) return; if (!ptr) return; + cgroup_exclude_rmdir(&ptr->css); pc = lookup_page_cgroup(page); - __mem_cgroup_commit_charge(ptr, pc, MEM_CGROUP_CHARGE_TYPE_MAPPED); + mem_cgroup_lru_del_before_commit_swapcache(page); + __mem_cgroup_commit_charge(ptr, pc, ctype); + mem_cgroup_lru_add_after_commit_swapcache(page); + /* + * Now swap is on-memory. This means this page may be + * counted both as mem and swap....double count. + * Fix it by uncharging from memsw. Basically, this SwapCache is stable + * under lock_page(). But in do_swap_page()::memory.c, reuse_swap_page() + * may call delete_from_swap_cache() before reach here. + */ + if (do_swap_account && PageSwapCache(page)) { + swp_entry_t ent = {.val = page_private(page)}; + unsigned short id; + struct mem_cgroup *memcg; + + id = swap_cgroup_record(ent, 0); + rcu_read_lock(); + memcg = mem_cgroup_lookup(id); + if (memcg) { + /* + * This recorded memcg can be obsolete one. So, avoid + * calling css_tryget + */ + if (!mem_cgroup_is_root(memcg)) + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + mem_cgroup_swap_statistics(memcg, false); + mem_cgroup_put(memcg); + } + rcu_read_unlock(); + } + /* + * At swapin, we may charge account against cgroup which has no tasks. + * So, rmdir()->pre_destroy() can be called while we do this charge. + * In that case, we need to call pre_destroy() again. check it here. + */ + cgroup_release_and_wakeup_rmdir(&ptr->css); +} + +void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) +{ + __mem_cgroup_commit_charge_swapin(page, ptr, + MEM_CGROUP_CHARGE_TYPE_MAPPED); } void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) { - if (mem_cgroup_subsys.disabled) + if (mem_cgroup_disabled()) return; if (!mem) return; - res_counter_uncharge(&mem->res, PAGE_SIZE); + if (!mem_cgroup_is_root(mem)) { + res_counter_uncharge(&mem->res, PAGE_SIZE); + if (do_swap_account) + res_counter_uncharge(&mem->memsw, PAGE_SIZE); + } css_put(&mem->css); } @@ -844,34 +1830,36 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) /* * uncharge if !page_mapped(page) */ -static void +static struct mem_cgroup * __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) { struct page_cgroup *pc; - struct mem_cgroup *mem; + struct mem_cgroup *mem = NULL; struct mem_cgroup_per_zone *mz; - unsigned long flags; - if (mem_cgroup_subsys.disabled) - return; + if (mem_cgroup_disabled()) + return NULL; if (PageSwapCache(page)) - return; + return NULL; /* * Check if our page_cgroup is valid */ pc = lookup_page_cgroup(page); if (unlikely(!pc || !PageCgroupUsed(pc))) - return; + return NULL; lock_page_cgroup(pc); + mem = pc->mem_cgroup; + if (!PageCgroupUsed(pc)) goto unlock_out; switch (ctype) { case MEM_CGROUP_CHARGE_TYPE_MAPPED: + case MEM_CGROUP_CHARGE_TYPE_DROP: if (page_mapped(page)) goto unlock_out; break; @@ -886,23 +1874,38 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) break; } + if (!mem_cgroup_is_root(mem)) { + res_counter_uncharge(&mem->res, PAGE_SIZE); + if (do_swap_account && + (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)) + res_counter_uncharge(&mem->memsw, PAGE_SIZE); + } + if (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) + mem_cgroup_swap_statistics(mem, true); + mem_cgroup_charge_statistics(mem, pc, false); + ClearPageCgroupUsed(pc); - mem = pc->mem_cgroup; + /* + * pc->mem_cgroup is not cleared here. It will be accessed when it's + * freed from LRU. This is safe because uncharged page is expected not + * to be reused (freed soon). Exception is SwapCache, it's handled by + * special functions. + */ mz = page_cgroup_zoneinfo(pc); - spin_lock_irqsave(&mz->lru_lock, flags); - __mem_cgroup_remove_list(mz, pc); - spin_unlock_irqrestore(&mz->lru_lock, flags); unlock_page_cgroup(pc); - res_counter_uncharge(&mem->res, PAGE_SIZE); - css_put(&mem->css); + if (mem_cgroup_soft_limit_check(mem)) + mem_cgroup_update_tree(mem, page); + /* at swapout, this memcg will be accessed to record to swap */ + if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT) + css_put(&mem->css); - return; + return mem; unlock_out: unlock_page_cgroup(pc); - return; + return NULL; } void mem_cgroup_uncharge_page(struct page *page) @@ -922,10 +1925,61 @@ void mem_cgroup_uncharge_cache_page(struct page *page) __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE); } -void mem_cgroup_uncharge_swapcache(struct page *page) +#ifdef CONFIG_SWAP +/* + * called after __delete_from_swap_cache() and drop "page" account. + * memcg information is recorded to swap_cgroup of "ent" + */ +void +mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) +{ + struct mem_cgroup *memcg; + int ctype = MEM_CGROUP_CHARGE_TYPE_SWAPOUT; + + if (!swapout) /* this was a swap cache but the swap is unused ! */ + ctype = MEM_CGROUP_CHARGE_TYPE_DROP; + + memcg = __mem_cgroup_uncharge_common(page, ctype); + + /* record memcg information */ + if (do_swap_account && swapout && memcg) { + swap_cgroup_record(ent, css_id(&memcg->css)); + mem_cgroup_get(memcg); + } + if (swapout && memcg) + css_put(&memcg->css); +} +#endif + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +/* + * called from swap_entry_free(). remove record in swap_cgroup and + * uncharge "memsw" account. + */ +void mem_cgroup_uncharge_swap(swp_entry_t ent) { - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_SWAPOUT); + struct mem_cgroup *memcg; + unsigned short id; + + if (!do_swap_account) + return; + + id = swap_cgroup_record(ent, 0); + rcu_read_lock(); + memcg = mem_cgroup_lookup(id); + if (memcg) { + /* + * We uncharge this because swap is freed. + * This memcg can be obsolete one. We avoid calling css_tryget + */ + if (!mem_cgroup_is_root(memcg)) + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + mem_cgroup_swap_statistics(memcg, false); + mem_cgroup_put(memcg); + } + rcu_read_unlock(); } +#endif /* * Before starting migration, account PAGE_SIZE to mem_cgroup that the old @@ -937,7 +1991,7 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr) struct mem_cgroup *mem = NULL; int ret = 0; - if (mem_cgroup_subsys.disabled) + if (mem_cgroup_disabled()) return 0; pc = lookup_page_cgroup(page); @@ -949,7 +2003,8 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr) unlock_page_cgroup(pc); if (mem) { - ret = mem_cgroup_try_charge(NULL, GFP_HIGHUSER_MOVABLE, &mem); + ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false, + page); css_put(&mem->css); } *ptr = mem; @@ -966,7 +2021,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem, if (!mem) return; - + cgroup_exclude_rmdir(&mem->css); /* at migration success, oldpage->mapping is NULL. */ if (oldpage->mapping) { target = oldpage; @@ -1006,84 +2061,263 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem, */ if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED) mem_cgroup_uncharge_page(target); + /* + * At migration, we may charge account against cgroup which has no tasks + * So, rmdir()->pre_destroy() can be called while we do this charge. + * In that case, we need to call pre_destroy() again. check it here. + */ + cgroup_release_and_wakeup_rmdir(&mem->css); } /* - * A call to try to shrink memory usage under specified resource controller. - * This is typically used for page reclaiming for shmem for reducing side - * effect of page allocation from shmem, which is used by some mem_cgroup. + * A call to try to shrink memory usage on charge failure at shmem's swapin. + * Calling hierarchical_reclaim is not enough because we should update + * last_oom_jiffies to prevent pagefault_out_of_memory from invoking global OOM. + * Moreover considering hierarchy, we should reclaim from the mem_over_limit, + * not from the memcg which this page would be charged to. + * try_charge_swapin does all of these works properly. */ -int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask) +int mem_cgroup_shmem_charge_fallback(struct page *page, + struct mm_struct *mm, + gfp_t gfp_mask) { - struct mem_cgroup *mem; - int progress = 0; - int retry = MEM_CGROUP_RECLAIM_RETRIES; + struct mem_cgroup *mem = NULL; + int ret; + + if (mem_cgroup_disabled()) + return 0; + + ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem); + if (!ret) + mem_cgroup_cancel_charge_swapin(mem); /* it does !mem check */ + + return ret; +} + +static DEFINE_MUTEX(set_limit_mutex); + +static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, + unsigned long long val) +{ + int retry_count; + int progress; + u64 memswlimit; + int ret = 0; + int children = mem_cgroup_count_children(memcg); + u64 curusage, oldusage; + + /* + * For keeping hierarchical_reclaim simple, how long we should retry + * is depends on callers. We set our retry-count to be function + * of # of children which we should visit in this loop. + */ + retry_count = MEM_CGROUP_RECLAIM_RETRIES * children; + + oldusage = res_counter_read_u64(&memcg->res, RES_USAGE); + + while (retry_count) { + if (signal_pending(current)) { + ret = -EINTR; + break; + } + /* + * Rather than hide all in some function, I do this in + * open coded manner. You see what this really does. + * We have to guarantee mem->res.limit < mem->memsw.limit. + */ + mutex_lock(&set_limit_mutex); + memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); + if (memswlimit < val) { + ret = -EINVAL; + mutex_unlock(&set_limit_mutex); + break; + } + ret = res_counter_set_limit(&memcg->res, val); + if (!ret) { + if (memswlimit == val) + memcg->memsw_is_minimum = true; + else + memcg->memsw_is_minimum = false; + } + mutex_unlock(&set_limit_mutex); - if (mem_cgroup_subsys.disabled) - return 0; - if (!mm) - return 0; + if (!ret) + break; - rcu_read_lock(); - mem = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!mem)) { - rcu_read_unlock(); - return 0; + progress = mem_cgroup_hierarchical_reclaim(memcg, NULL, + GFP_KERNEL, + MEM_CGROUP_RECLAIM_SHRINK); + curusage = res_counter_read_u64(&memcg->res, RES_USAGE); + /* Usage is reduced ? */ + if (curusage >= oldusage) + retry_count--; + else + oldusage = curusage; } - css_get(&mem->css); - rcu_read_unlock(); - do { - progress = try_to_free_mem_cgroup_pages(mem, gfp_mask); - progress += res_counter_check_under_limit(&mem->res); - } while (!progress && --retry); - - css_put(&mem->css); - if (!retry) - return -ENOMEM; - return 0; + return ret; } -static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, - unsigned long long val) +static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, + unsigned long long val) { + int retry_count; + u64 memlimit, oldusage, curusage; + int children = mem_cgroup_count_children(memcg); + int ret = -EBUSY; - int retry_count = MEM_CGROUP_RECLAIM_RETRIES; - int progress; - int ret = 0; - - while (res_counter_set_limit(&memcg->res, val)) { + /* see mem_cgroup_resize_res_limit */ + retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; + oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); + while (retry_count) { if (signal_pending(current)) { ret = -EINTR; break; } - if (!retry_count) { - ret = -EBUSY; + /* + * Rather than hide all in some function, I do this in + * open coded manner. You see what this really does. + * We have to guarantee mem->res.limit < mem->memsw.limit. + */ + mutex_lock(&set_limit_mutex); + memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT); + if (memlimit > val) { + ret = -EINVAL; + mutex_unlock(&set_limit_mutex); break; } - progress = try_to_free_mem_cgroup_pages(memcg, - GFP_HIGHUSER_MOVABLE); - if (!progress) + ret = res_counter_set_limit(&memcg->memsw, val); + if (!ret) { + if (memlimit == val) + memcg->memsw_is_minimum = true; + else + memcg->memsw_is_minimum = false; + } + mutex_unlock(&set_limit_mutex); + + if (!ret) + break; + + mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL, + MEM_CGROUP_RECLAIM_NOSWAP | + MEM_CGROUP_RECLAIM_SHRINK); + curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); + /* Usage is reduced ? */ + if (curusage >= oldusage) retry_count--; + else + oldusage = curusage; } return ret; } +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, int nid, + int zid) +{ + unsigned long nr_reclaimed = 0; + struct mem_cgroup_per_zone *mz, *next_mz = NULL; + unsigned long reclaimed; + int loop = 0; + struct mem_cgroup_tree_per_zone *mctz; + unsigned long long excess; + + if (order > 0) + return 0; + + mctz = soft_limit_tree_node_zone(nid, zid); + /* + * This loop can run a while, specially if mem_cgroup's continuously + * keep exceeding their soft limit and putting the system under + * pressure + */ + do { + if (next_mz) + mz = next_mz; + else + mz = mem_cgroup_largest_soft_limit_node(mctz); + if (!mz) + break; + + reclaimed = mem_cgroup_hierarchical_reclaim(mz->mem, zone, + gfp_mask, + MEM_CGROUP_RECLAIM_SOFT); + nr_reclaimed += reclaimed; + spin_lock(&mctz->lock); + + /* + * If we failed to reclaim anything from this memory cgroup + * it is time to move on to the next cgroup + */ + next_mz = NULL; + if (!reclaimed) { + do { + /* + * Loop until we find yet another one. + * + * By the time we get the soft_limit lock + * again, someone might have aded the + * group back on the RB tree. Iterate to + * make sure we get a different mem. + * mem_cgroup_largest_soft_limit_node returns + * NULL if no other cgroup is present on + * the tree + */ + next_mz = + __mem_cgroup_largest_soft_limit_node(mctz); + if (next_mz == mz) { + css_put(&next_mz->mem->css); + next_mz = NULL; + } else /* next_mz == NULL or other memcg */ + break; + } while (1); + } + __mem_cgroup_remove_exceeded(mz->mem, mz, mctz); + excess = res_counter_soft_limit_excess(&mz->mem->res); + /* + * One school of thought says that we should not add + * back the node to the tree if reclaim returns 0. + * But our reclaim could return 0, simply because due + * to priority we are exposing a smaller subset of + * memory to reclaim from. Consider this as a longer + * term TODO. + */ + /* If excess == 0, no tree ops */ + __mem_cgroup_insert_exceeded(mz->mem, mz, mctz, excess); + spin_unlock(&mctz->lock); + css_put(&mz->mem->css); + loop++; + /* + * Could not reclaim anything and there are no more + * mem cgroups to try or we seem to be looping without + * reclaiming anything. + */ + if (!nr_reclaimed && + (next_mz == NULL || + loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS)) + break; + } while (!nr_reclaimed); + if (next_mz) + css_put(&next_mz->mem->css); + return nr_reclaimed; +} /* * This routine traverse page_cgroup in given list and drop them all. * *And* this routine doesn't reclaim page itself, just removes page_cgroup. */ static int mem_cgroup_force_empty_list(struct mem_cgroup *mem, - struct mem_cgroup_per_zone *mz, - enum lru_list lru) + int node, int zid, enum lru_list lru) { + struct zone *zone; + struct mem_cgroup_per_zone *mz; struct page_cgroup *pc, *busy; - unsigned long flags; - unsigned long loop; + unsigned long flags, loop; struct list_head *list; int ret = 0; + zone = &NODE_DATA(node)->node_zones[zid]; + mz = mem_cgroup_zoneinfo(mem, node, zid); list = &mz->lists[lru]; loop = MEM_CGROUP_ZSTAT(mz, lru); @@ -1092,21 +2326,21 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *mem, busy = NULL; while (loop--) { ret = 0; - spin_lock_irqsave(&mz->lru_lock, flags); + spin_lock_irqsave(&zone->lru_lock, flags); if (list_empty(list)) { - spin_unlock_irqrestore(&mz->lru_lock, flags); + spin_unlock_irqrestore(&zone->lru_lock, flags); break; } pc = list_entry(list->prev, struct page_cgroup, lru); if (busy == pc) { list_move(&pc->lru, list); busy = 0; - spin_unlock_irqrestore(&mz->lru_lock, flags); + spin_unlock_irqrestore(&zone->lru_lock, flags); continue; } - spin_unlock_irqrestore(&mz->lru_lock, flags); + spin_unlock_irqrestore(&zone->lru_lock, flags); - ret = mem_cgroup_move_parent(pc, mem, GFP_HIGHUSER_MOVABLE); + ret = mem_cgroup_move_parent(pc, mem, GFP_KERNEL); if (ret == -ENOMEM) break; @@ -1117,6 +2351,7 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *mem, } else busy = NULL; } + if (!ret && !list_empty(list)) return -EBUSY; return ret; @@ -1150,14 +2385,12 @@ move_account: /* This is for making all *used* pages to be on LRU. */ lru_add_drain_all(); ret = 0; - for_each_node_state(node, N_POSSIBLE) { + for_each_node_state(node, N_HIGH_MEMORY) { for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) { - struct mem_cgroup_per_zone *mz; enum lru_list l; - mz = mem_cgroup_zoneinfo(mem, node, zid); for_each_lru(l) { ret = mem_cgroup_force_empty_list(mem, - mz, l); + node, zid, l); if (ret) break; } @@ -1192,15 +2425,16 @@ try_to_free: ret = -EINTR; goto out; } - progress = try_to_free_mem_cgroup_pages(mem, - GFP_HIGHUSER_MOVABLE); + progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL, + false, get_swappiness(mem)); if (!progress) { nr_retries--; /* maybe some writeback is necessary */ - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } } + lru_add_drain(); /* try move_account...there may be some *locked* pages. */ if (mem->res.usage) goto move_account; @@ -1214,10 +2448,108 @@ int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event) } +static u64 mem_cgroup_hierarchy_read(struct cgroup *cont, struct cftype *cft) +{ + return mem_cgroup_from_cont(cont)->use_hierarchy; +} + +static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, + u64 val) +{ + int retval = 0; + struct mem_cgroup *mem = mem_cgroup_from_cont(cont); + struct cgroup *parent = cont->parent; + struct mem_cgroup *parent_mem = NULL; + + if (parent) + parent_mem = mem_cgroup_from_cont(parent); + + cgroup_lock(); + /* + * If parent's use_hiearchy is set, we can't make any modifications + * in the child subtrees. If it is unset, then the change can + * occur, provided the current cgroup has no children. + * + * For the root cgroup, parent_mem is NULL, we allow value to be + * set if there are no children. + */ + if ((!parent_mem || !parent_mem->use_hierarchy) && + (val == 1 || val == 0)) { + if (list_empty(&cont->children)) + mem->use_hierarchy = val; + else + retval = -EBUSY; + } else + retval = -EINVAL; + cgroup_unlock(); + + return retval; +} + +struct mem_cgroup_idx_data { + s64 val; + enum mem_cgroup_stat_index idx; +}; + +static int +mem_cgroup_get_idx_stat(struct mem_cgroup *mem, void *data) +{ + struct mem_cgroup_idx_data *d = data; + d->val += mem_cgroup_read_stat(&mem->stat, d->idx); + return 0; +} + +static void +mem_cgroup_get_recursive_idx_stat(struct mem_cgroup *mem, + enum mem_cgroup_stat_index idx, s64 *val) +{ + struct mem_cgroup_idx_data d; + d.idx = idx; + d.val = 0; + mem_cgroup_walk_tree(mem, &d, mem_cgroup_get_idx_stat); + *val = d.val; +} + static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) { - return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res, - cft->private); + struct mem_cgroup *mem = mem_cgroup_from_cont(cont); + u64 idx_val, val; + int type, name; + + type = MEMFILE_TYPE(cft->private); + name = MEMFILE_ATTR(cft->private); + switch (type) { + case _MEM: + if (name == RES_USAGE && mem_cgroup_is_root(mem)) { + mem_cgroup_get_recursive_idx_stat(mem, + MEM_CGROUP_STAT_CACHE, &idx_val); + val = idx_val; + mem_cgroup_get_recursive_idx_stat(mem, + MEM_CGROUP_STAT_RSS, &idx_val); + val += idx_val; + val <<= PAGE_SHIFT; + } else + val = res_counter_read_u64(&mem->res, name); + break; + case _MEMSWAP: + if (name == RES_USAGE && mem_cgroup_is_root(mem)) { + mem_cgroup_get_recursive_idx_stat(mem, + MEM_CGROUP_STAT_CACHE, &idx_val); + val = idx_val; + mem_cgroup_get_recursive_idx_stat(mem, + MEM_CGROUP_STAT_RSS, &idx_val); + val += idx_val; + mem_cgroup_get_recursive_idx_stat(mem, + MEM_CGROUP_STAT_SWAPOUT, &idx_val); + val <<= PAGE_SHIFT; + } else + val = res_counter_read_u64(&mem->memsw, name); + break; + default: + BUG(); + break; + } + return val; } /* * The user of this function is... @@ -1227,15 +2559,40 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, const char *buffer) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + int type, name; unsigned long long val; int ret; - switch (cft->private) { + type = MEMFILE_TYPE(cft->private); + name = MEMFILE_ATTR(cft->private); + switch (name) { case RES_LIMIT: + if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */ + ret = -EINVAL; + break; + } /* This function does all necessary parse...reuse it */ ret = res_counter_memparse_write_strategy(buffer, &val); - if (!ret) + if (ret) + break; + if (type == _MEM) ret = mem_cgroup_resize_limit(memcg, val); + else + ret = mem_cgroup_resize_memsw_limit(memcg, val); + break; + case RES_SOFT_LIMIT: + ret = res_counter_memparse_write_strategy(buffer, &val); + if (ret) + break; + /* + * For memsw, soft limits are hard to implement in terms + * of semantics, for now, we support soft limits for + * control without swap + */ + if (type == _MEM) + ret = res_counter_set_soft_limit(&memcg->res, val); + else + ret = -EINVAL; break; default: ret = -EINVAL; /* should be BUG() ? */ @@ -1244,70 +2601,241 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, return ret; } +static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg, + unsigned long long *mem_limit, unsigned long long *memsw_limit) +{ + struct cgroup *cgroup; + unsigned long long min_limit, min_memsw_limit, tmp; + + min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT); + min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); + cgroup = memcg->css.cgroup; + if (!memcg->use_hierarchy) + goto out; + + while (cgroup->parent) { + cgroup = cgroup->parent; + memcg = mem_cgroup_from_cont(cgroup); + if (!memcg->use_hierarchy) + break; + tmp = res_counter_read_u64(&memcg->res, RES_LIMIT); + min_limit = min(min_limit, tmp); + tmp = res_counter_read_u64(&memcg->memsw, RES_LIMIT); + min_memsw_limit = min(min_memsw_limit, tmp); + } +out: + *mem_limit = min_limit; + *memsw_limit = min_memsw_limit; + return; +} + static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) { struct mem_cgroup *mem; + int type, name; mem = mem_cgroup_from_cont(cont); - switch (event) { + type = MEMFILE_TYPE(event); + name = MEMFILE_ATTR(event); + switch (name) { case RES_MAX_USAGE: - res_counter_reset_max(&mem->res); + if (type == _MEM) + res_counter_reset_max(&mem->res); + else + res_counter_reset_max(&mem->memsw); break; case RES_FAILCNT: - res_counter_reset_failcnt(&mem->res); + if (type == _MEM) + res_counter_reset_failcnt(&mem->res); + else + res_counter_reset_failcnt(&mem->memsw); break; } + return 0; } -static const struct mem_cgroup_stat_desc { - const char *msg; - u64 unit; -} mem_cgroup_stat_desc[] = { - [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, }, - [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, }, - [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, }, - [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, }, + +/* For read statistics */ +enum { + MCS_CACHE, + MCS_RSS, + MCS_MAPPED_FILE, + MCS_PGPGIN, + MCS_PGPGOUT, + MCS_SWAP, + MCS_INACTIVE_ANON, + MCS_ACTIVE_ANON, + MCS_INACTIVE_FILE, + MCS_ACTIVE_FILE, + MCS_UNEVICTABLE, + NR_MCS_STAT, +}; + +struct mcs_total_stat { + s64 stat[NR_MCS_STAT]; +}; + +struct { + char *local_name; + char *total_name; +} memcg_stat_strings[NR_MCS_STAT] = { + {"cache", "total_cache"}, + {"rss", "total_rss"}, + {"mapped_file", "total_mapped_file"}, + {"pgpgin", "total_pgpgin"}, + {"pgpgout", "total_pgpgout"}, + {"swap", "total_swap"}, + {"inactive_anon", "total_inactive_anon"}, + {"active_anon", "total_active_anon"}, + {"inactive_file", "total_inactive_file"}, + {"active_file", "total_active_file"}, + {"unevictable", "total_unevictable"} }; + +static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data) +{ + struct mcs_total_stat *s = data; + s64 val; + + /* per cpu stat */ + val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_CACHE); + s->stat[MCS_CACHE] += val * PAGE_SIZE; + val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS); + s->stat[MCS_RSS] += val * PAGE_SIZE; + val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_MAPPED_FILE); + s->stat[MCS_MAPPED_FILE] += val * PAGE_SIZE; + val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGIN_COUNT); + s->stat[MCS_PGPGIN] += val; + val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT); + s->stat[MCS_PGPGOUT] += val; + if (do_swap_account) { + val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_SWAPOUT); + s->stat[MCS_SWAP] += val * PAGE_SIZE; + } + + /* per zone stat */ + val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON); + s->stat[MCS_INACTIVE_ANON] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_ANON); + s->stat[MCS_ACTIVE_ANON] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_FILE); + s->stat[MCS_INACTIVE_FILE] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_FILE); + s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_UNEVICTABLE); + s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE; + return 0; +} + +static void +mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s) +{ + mem_cgroup_walk_tree(mem, s, mem_cgroup_get_local_stat); +} + static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, struct cgroup_map_cb *cb) { struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont); - struct mem_cgroup_stat *stat = &mem_cont->stat; + struct mcs_total_stat mystat; int i; - for (i = 0; i < ARRAY_SIZE(stat->cpustat[0].count); i++) { - s64 val; + memset(&mystat, 0, sizeof(mystat)); + mem_cgroup_get_local_stat(mem_cont, &mystat); - val = mem_cgroup_read_stat(stat, i); - val *= mem_cgroup_stat_desc[i].unit; - cb->fill(cb, mem_cgroup_stat_desc[i].msg, val); + for (i = 0; i < NR_MCS_STAT; i++) { + if (i == MCS_SWAP && !do_swap_account) + continue; + cb->fill(cb, memcg_stat_strings[i].local_name, mystat.stat[i]); + } + + /* Hierarchical information */ + { + unsigned long long limit, memsw_limit; + memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit); + cb->fill(cb, "hierarchical_memory_limit", limit); + if (do_swap_account) + cb->fill(cb, "hierarchical_memsw_limit", memsw_limit); } - /* showing # of active pages */ + + memset(&mystat, 0, sizeof(mystat)); + mem_cgroup_get_total_stat(mem_cont, &mystat); + for (i = 0; i < NR_MCS_STAT; i++) { + if (i == MCS_SWAP && !do_swap_account) + continue; + cb->fill(cb, memcg_stat_strings[i].total_name, mystat.stat[i]); + } + +#ifdef CONFIG_DEBUG_VM + cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL)); + { - unsigned long active_anon, inactive_anon; - unsigned long active_file, inactive_file; - unsigned long unevictable; - - inactive_anon = mem_cgroup_get_all_zonestat(mem_cont, - LRU_INACTIVE_ANON); - active_anon = mem_cgroup_get_all_zonestat(mem_cont, - LRU_ACTIVE_ANON); - inactive_file = mem_cgroup_get_all_zonestat(mem_cont, - LRU_INACTIVE_FILE); - active_file = mem_cgroup_get_all_zonestat(mem_cont, - LRU_ACTIVE_FILE); - unevictable = mem_cgroup_get_all_zonestat(mem_cont, - LRU_UNEVICTABLE); - - cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE); - cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE); - cb->fill(cb, "active_file", (active_file) * PAGE_SIZE); - cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE); - cb->fill(cb, "unevictable", unevictable * PAGE_SIZE); + int nid, zid; + struct mem_cgroup_per_zone *mz; + unsigned long recent_rotated[2] = {0, 0}; + unsigned long recent_scanned[2] = {0, 0}; + + for_each_online_node(nid) + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + mz = mem_cgroup_zoneinfo(mem_cont, nid, zid); + + recent_rotated[0] += + mz->reclaim_stat.recent_rotated[0]; + recent_rotated[1] += + mz->reclaim_stat.recent_rotated[1]; + recent_scanned[0] += + mz->reclaim_stat.recent_scanned[0]; + recent_scanned[1] += + mz->reclaim_stat.recent_scanned[1]; + } + cb->fill(cb, "recent_rotated_anon", recent_rotated[0]); + cb->fill(cb, "recent_rotated_file", recent_rotated[1]); + cb->fill(cb, "recent_scanned_anon", recent_scanned[0]); + cb->fill(cb, "recent_scanned_file", recent_scanned[1]); + } +#endif + + return 0; +} + +static u64 mem_cgroup_swappiness_read(struct cgroup *cgrp, struct cftype *cft) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + + return get_swappiness(memcg); +} + +static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft, + u64 val) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *parent; + + if (val > 100) + return -EINVAL; + if (cgrp->parent == NULL) + return -EINVAL; + + parent = mem_cgroup_from_cont(cgrp->parent); + + cgroup_lock(); + + /* If under hierarchy, only empty-root can set this value */ + if ((parent->use_hierarchy) || + (memcg->use_hierarchy && !list_empty(&cgrp->children))) { + cgroup_unlock(); + return -EINVAL; } + + spin_lock(&memcg->reclaim_param_lock); + memcg->swappiness = val; + spin_unlock(&memcg->reclaim_param_lock); + + cgroup_unlock(); + return 0; } @@ -1315,24 +2843,30 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, static struct cftype mem_cgroup_files[] = { { .name = "usage_in_bytes", - .private = RES_USAGE, + .private = MEMFILE_PRIVATE(_MEM, RES_USAGE), .read_u64 = mem_cgroup_read, }, { .name = "max_usage_in_bytes", - .private = RES_MAX_USAGE, + .private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE), .trigger = mem_cgroup_reset, .read_u64 = mem_cgroup_read, }, { .name = "limit_in_bytes", - .private = RES_LIMIT, + .private = MEMFILE_PRIVATE(_MEM, RES_LIMIT), + .write_string = mem_cgroup_write, + .read_u64 = mem_cgroup_read, + }, + { + .name = "soft_limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), .write_string = mem_cgroup_write, .read_u64 = mem_cgroup_read, }, { .name = "failcnt", - .private = RES_FAILCNT, + .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), .trigger = mem_cgroup_reset, .read_u64 = mem_cgroup_read, }, @@ -1344,7 +2878,58 @@ static struct cftype mem_cgroup_files[] = { .name = "force_empty", .trigger = mem_cgroup_force_empty_write, }, + { + .name = "use_hierarchy", + .write_u64 = mem_cgroup_hierarchy_write, + .read_u64 = mem_cgroup_hierarchy_read, + }, + { + .name = "swappiness", + .read_u64 = mem_cgroup_swappiness_read, + .write_u64 = mem_cgroup_swappiness_write, + }, +}; + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +static struct cftype memsw_cgroup_files[] = { + { + .name = "memsw.usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), + .read_u64 = mem_cgroup_read, + }, + { + .name = "memsw.max_usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), + .trigger = mem_cgroup_reset, + .read_u64 = mem_cgroup_read, + }, + { + .name = "memsw.limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), + .write_string = mem_cgroup_write, + .read_u64 = mem_cgroup_read, + }, + { + .name = "memsw.failcnt", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), + .trigger = mem_cgroup_reset, + .read_u64 = mem_cgroup_read, + }, +}; + +static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss) +{ + if (!do_swap_account) + return 0; + return cgroup_add_files(cont, ss, memsw_cgroup_files, + ARRAY_SIZE(memsw_cgroup_files)); }; +#else +static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss) +{ + return 0; +} +#endif static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) { @@ -1371,9 +2956,11 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) for (zone = 0; zone < MAX_NR_ZONES; zone++) { mz = &pn->zoneinfo[zone]; - spin_lock_init(&mz->lru_lock); for_each_lru(l) INIT_LIST_HEAD(&mz->lists[l]); + mz->usage_in_excess = 0; + mz->on_tree = false; + mz->mem = mem; } return 0; } @@ -1404,19 +2991,62 @@ static struct mem_cgroup *mem_cgroup_alloc(void) return mem; } -static void mem_cgroup_free(struct mem_cgroup *mem) +/* + * At destroying mem_cgroup, references from swap_cgroup can remain. + * (scanning all at force_empty is too costly...) + * + * Instead of clearing all references at force_empty, we remember + * the number of reference from swap_cgroup and free mem_cgroup when + * it goes down to 0. + * + * Removal of cgroup itself succeeds regardless of refs from swap. + */ + +static void __mem_cgroup_free(struct mem_cgroup *mem) { + int node; + + mem_cgroup_remove_from_trees(mem); + free_css_id(&mem_cgroup_subsys, &mem->css); + + for_each_node_state(node, N_POSSIBLE) + free_mem_cgroup_per_zone_info(mem, node); + if (mem_cgroup_size() < PAGE_SIZE) kfree(mem); else vfree(mem); } +static void mem_cgroup_get(struct mem_cgroup *mem) +{ + atomic_inc(&mem->refcnt); +} + +static void mem_cgroup_put(struct mem_cgroup *mem) +{ + if (atomic_dec_and_test(&mem->refcnt)) { + struct mem_cgroup *parent = parent_mem_cgroup(mem); + __mem_cgroup_free(mem); + if (parent) + mem_cgroup_put(parent); + } +} + +/* + * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled. + */ +static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem) +{ + if (!mem->res.parent) + return NULL; + return mem_cgroup_from_res_counter(mem->res.parent, res); +} #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP static void __init enable_swap_cgroup(void) { - if (!mem_cgroup_subsys.disabled && really_do_swap_account) + if (!mem_cgroup_disabled() && really_do_swap_account) do_swap_account = 1; } #else @@ -1425,83 +3055,127 @@ static void __init enable_swap_cgroup(void) } #endif -static struct cgroup_subsys_state * +static int mem_cgroup_soft_limit_tree_init(void) +{ + struct mem_cgroup_tree_per_node *rtpn; + struct mem_cgroup_tree_per_zone *rtpz; + int tmp, node, zone; + + for_each_node_state(node, N_POSSIBLE) { + tmp = node; + if (!node_state(node, N_NORMAL_MEMORY)) + tmp = -1; + rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp); + if (!rtpn) + return 1; + + soft_limit_tree.rb_tree_per_node[node] = rtpn; + + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + rtpz = &rtpn->rb_tree_per_zone[zone]; + rtpz->rb_root = RB_ROOT; + spin_lock_init(&rtpz->lock); + } + } + return 0; +} + +static struct cgroup_subsys_state * __ref mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) { - struct mem_cgroup *mem; + struct mem_cgroup *mem, *parent; + long error = -ENOMEM; int node; mem = mem_cgroup_alloc(); if (!mem) - return ERR_PTR(-ENOMEM); - - res_counter_init(&mem->res); + return ERR_PTR(error); for_each_node_state(node, N_POSSIBLE) if (alloc_mem_cgroup_per_zone_info(mem, node)) goto free_out; + /* root ? */ - if (cont->parent == NULL) + if (cont->parent == NULL) { enable_swap_cgroup(); + parent = NULL; + root_mem_cgroup = mem; + if (mem_cgroup_soft_limit_tree_init()) + goto free_out; + + } else { + parent = mem_cgroup_from_cont(cont->parent); + mem->use_hierarchy = parent->use_hierarchy; + } + + if (parent && parent->use_hierarchy) { + res_counter_init(&mem->res, &parent->res); + res_counter_init(&mem->memsw, &parent->memsw); + /* + * We increment refcnt of the parent to ensure that we can + * safely access it on res_counter_charge/uncharge. + * This refcnt will be decremented when freeing this + * mem_cgroup(see mem_cgroup_put). + */ + mem_cgroup_get(parent); + } else { + res_counter_init(&mem->res, NULL); + res_counter_init(&mem->memsw, NULL); + } + mem->last_scanned_child = 0; + spin_lock_init(&mem->reclaim_param_lock); + if (parent) + mem->swappiness = get_swappiness(parent); + atomic_set(&mem->refcnt, 1); return &mem->css; free_out: - for_each_node_state(node, N_POSSIBLE) - free_mem_cgroup_per_zone_info(mem, node); - mem_cgroup_free(mem); - return ERR_PTR(-ENOMEM); + __mem_cgroup_free(mem); + root_mem_cgroup = NULL; + return ERR_PTR(error); } -static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss, +static int 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, false); + + return mem_cgroup_force_empty(mem, false); } 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); - - mem_cgroup_free(mem_cgroup_from_cont(cont)); + mem_cgroup_put(mem); } 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)); + int ret; + + ret = cgroup_add_files(cont, ss, mem_cgroup_files, + ARRAY_SIZE(mem_cgroup_files)); + + if (!ret) + ret = register_memsw_files(cont, ss); + return ret; } static void mem_cgroup_move_task(struct cgroup_subsys *ss, struct cgroup *cont, struct cgroup *old_cont, - struct task_struct *p) + struct task_struct *p, + bool threadgroup) { - 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); - + mutex_lock(&memcg_tasklist); /* - * Only thread group leaders are allowed to migrate, the mm_struct is - * in effect owned by the leader + * FIXME: It's better to move charges of this process from old + * memcg to new memcg. But it's just on TODO-List now. */ - if (!thread_group_leader(p)) - goto out; - -out: - mmput(mm); + mutex_unlock(&memcg_tasklist); } struct cgroup_subsys mem_cgroup_subsys = { @@ -1513,6 +3187,7 @@ struct cgroup_subsys mem_cgroup_subsys = { .populate = mem_cgroup_populate, .attach = mem_cgroup_move_task, .early_init = 0, + .use_id = 1, }; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP