#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmalloc.h>
+#include <linux/mm_inline.h>
#include <asm/uaccess.h>
/*
* 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];
+ struct list_head lists[NR_LRU_LISTS];
+ unsigned long count[NR_LRU_LISTS];
};
/* Macro for accessing counter */
#define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)])
struct mem_cgroup *mem_cgroup;
int flags;
};
-#define PAGE_CGROUP_FLAG_CACHE (0x1) /* charged as cache */
-#define PAGE_CGROUP_FLAG_ACTIVE (0x2) /* page is active in this cgroup */
+#define PAGE_CGROUP_FLAG_CACHE (0x1) /* charged as cache */
+#define PAGE_CGROUP_FLAG_ACTIVE (0x2) /* page is active in this cgroup */
+#define PAGE_CGROUP_FLAG_FILE (0x4) /* page is file system backed */
+#define PAGE_CGROUP_FLAG_UNEVICTABLE (0x8) /* page is unevictableable */
static int page_cgroup_nid(struct page_cgroup *pc)
{
MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
MEM_CGROUP_CHARGE_TYPE_MAPPED,
MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */
+ MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */
};
/*
}
static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
- enum mem_cgroup_zstat_index idx)
+ enum lru_list idx)
{
int nid, zid;
struct mem_cgroup_per_zone *mz;
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
+ /*
+ * mm_update_next_owner() may clear mm->owner to NULL
+ * if it races with swapoff, page migration, etc.
+ * So this can be called with p == NULL.
+ */
+ if (unlikely(!p))
+ return NULL;
+
return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
struct mem_cgroup, css);
}
static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
struct page_cgroup *pc)
{
- int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+ int lru = LRU_BASE;
+
+ if (pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE)
+ lru = LRU_UNEVICTABLE;
+ else {
+ if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+ lru += LRU_ACTIVE;
+ if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+ lru += LRU_FILE;
+ }
- if (from)
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
- else
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1;
+ MEM_CGROUP_ZSTAT(mz, lru) -= 1;
mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, false);
list_del(&pc->lru);
static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
struct page_cgroup *pc)
{
- int to = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
-
- 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);
+ int lru = LRU_BASE;
+
+ if (pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE)
+ lru = LRU_UNEVICTABLE;
+ else {
+ if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+ lru += LRU_ACTIVE;
+ if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+ lru += LRU_FILE;
}
+
+ MEM_CGROUP_ZSTAT(mz, lru) += 1;
+ list_add(&pc->lru, &mz->lists[lru]);
+
mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);
}
-static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
+static void __mem_cgroup_move_lists(struct page_cgroup *pc, enum lru_list lru)
{
- int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
+ int active = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+ int file = pc->flags & PAGE_CGROUP_FLAG_FILE;
+ int unevictable = pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE;
+ enum lru_list from = unevictable ? LRU_UNEVICTABLE :
+ (LRU_FILE * !!file + !!active);
- if (from)
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
- else
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1;
+ if (lru == from)
+ return;
- 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;
+ MEM_CGROUP_ZSTAT(mz, from) -= 1;
+
+ if (is_unevictable_lru(lru)) {
pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
- list_move(&pc->lru, &mz->inactive_list);
+ pc->flags |= PAGE_CGROUP_FLAG_UNEVICTABLE;
+ } else {
+ if (is_active_lru(lru))
+ pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
+ else
+ pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
+ pc->flags &= ~PAGE_CGROUP_FLAG_UNEVICTABLE;
}
+
+ MEM_CGROUP_ZSTAT(mz, lru) += 1;
+ list_move(&pc->lru, &mz->lists[lru]);
}
int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
/*
* This routine assumes that the appropriate zone's lru lock is already held
*/
-void mem_cgroup_move_lists(struct page *page, bool active)
+void mem_cgroup_move_lists(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)
+ return;
+
/*
* We cannot lock_page_cgroup while holding zone's lru_lock,
* because other holders of lock_page_cgroup can be interrupted
if (pc) {
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_move_lists(pc, active);
+ __mem_cgroup_move_lists(pc, lru);
spin_unlock_irqrestore(&mz->lru_lock, flags);
}
unlock_page_cgroup(page);
}
/*
- * 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)
* (see include/linux/mmzone.h)
*/
-long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
- struct zone *zone, int priority)
+long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
+ int priority, enum lru_list lru)
{
- long nr_active;
+ 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);
- nr_active = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE);
- return (nr_active >> priority);
-}
+ nr_pages = MEM_CGROUP_ZSTAT(mz, lru);
-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);
+ return (nr_pages >> priority);
}
unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
unsigned long *scanned, int order,
int mode, struct zone *z,
struct mem_cgroup *mem_cont,
- int active)
+ int active, int file)
{
unsigned long nr_taken = 0;
struct page *page;
int nid = z->zone_pgdat->node_id;
int zid = zone_idx(z);
struct mem_cgroup_per_zone *mz;
+ int lru = LRU_FILE * !!file + !!active;
BUG_ON(!mem_cont);
mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
- if (active)
- src = &mz->active_list;
- else
- src = &mz->inactive_list;
-
+ src = &mz->lists[lru];
spin_lock(&mz->lru_lock);
scan = 0;
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);
+ /*
+ * 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;
}
scan++;
list_move(&pc->lru, &pc_list);
- if (__isolate_lru_page(page, mode) == 0) {
+ if (__isolate_lru_page(page, mode, file) == 0) {
list_move(&page->lru, dst);
nr_taken++;
}
unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
struct mem_cgroup_per_zone *mz;
- if (mem_cgroup_subsys.disabled)
- return 0;
-
- /*
- * Should page_cgroup's go to their own slab?
- * 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:
- lock_page_cgroup(page);
- pc = page_get_page_cgroup(page);
- /*
- * The page_cgroup exists and
- * the page has already been accounted.
- */
- if (unlikely(pc)) {
- VM_BUG_ON(pc->page != page);
- VM_BUG_ON(!pc->mem_cgroup);
- unlock_page_cgroup(page);
- goto done;
- }
- unlock_page_cgroup(page);
-
pc = kmem_cache_alloc(page_cgroup_cache, gfp_mask);
if (unlikely(pc == NULL))
goto err;
if (likely(!memcg)) {
rcu_read_lock();
mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+ if (unlikely(!mem)) {
+ rcu_read_unlock();
+ kmem_cache_free(page_cgroup_cache, pc);
+ return 0;
+ }
/*
* For every charge from the cgroup, increment reference count
*/
* If a page is accounted as a page cache, insert to inactive list.
* If anon, insert to active list.
*/
- if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE)
+ if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE) {
pc->flags = PAGE_CGROUP_FLAG_CACHE;
- else
+ if (page_is_file_cache(page))
+ pc->flags |= PAGE_CGROUP_FLAG_FILE;
+ else
+ pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
+ } else if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
+ else /* MEM_CGROUP_CHARGE_TYPE_SHMEM */
+ pc->flags = PAGE_CGROUP_FLAG_CACHE | PAGE_CGROUP_FLAG_ACTIVE;
lock_page_cgroup(page);
if (unlikely(page_get_page_cgroup(page))) {
unlock_page_cgroup(page);
- /*
- * 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);
kmem_cache_free(page_cgroup_cache, pc);
- goto retry;
+ goto done;
}
page_assign_page_cgroup(page, pc);
int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
{
+ if (mem_cgroup_subsys.disabled)
+ return 0;
+
/*
* If already mapped, we don't have to account.
* If page cache, page->mapping has address_space.
int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask)
{
+ if (mem_cgroup_subsys.disabled)
+ return 0;
+
+ /*
+ * Corner case handling. This is called from add_to_page_cache()
+ * in usual. But some FS (shmem) precharges this page before calling it
+ * and call add_to_page_cache() with GFP_NOWAIT.
+ *
+ * For GFP_NOWAIT case, the page may be pre-charged before calling
+ * add_to_page_cache(). (See shmem.c) check it here and avoid to call
+ * charge twice. (It works but has to pay a bit larger cost.)
+ */
+ if (!(gfp_mask & __GFP_WAIT)) {
+ struct page_cgroup *pc;
+
+ lock_page_cgroup(page);
+ pc = page_get_page_cgroup(page);
+ if (pc) {
+ VM_BUG_ON(pc->page != page);
+ VM_BUG_ON(!pc->mem_cgroup);
+ unlock_page_cgroup(page);
+ return 0;
+ }
+ unlock_page_cgroup(page);
+ }
+
if (unlikely(!mm))
mm = &init_mm;
+
return mem_cgroup_charge_common(page, mm, gfp_mask,
MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
}
if (pc) {
mem = pc->mem_cgroup;
css_get(&mem->css);
- if (pc->flags & PAGE_CGROUP_FLAG_CACHE)
- ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+ if (pc->flags & PAGE_CGROUP_FLAG_CACHE) {
+ if (page_is_file_cache(page))
+ ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+ else
+ ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
+ }
}
unlock_page_cgroup(page);
if (mem) {
int progress = 0;
int retry = MEM_CGROUP_RECLAIM_RETRIES;
+ if (mem_cgroup_subsys.disabled)
+ return 0;
+ if (!mm)
+ return 0;
+
rcu_read_lock();
mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+ if (unlikely(!mem)) {
+ rcu_read_unlock();
+ return 0;
+ }
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);
return 0;
}
+int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val)
+{
+
+ int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+ int progress;
+ int ret = 0;
+
+ while (res_counter_set_limit(&memcg->res, val)) {
+ if (signal_pending(current)) {
+ ret = -EINTR;
+ break;
+ }
+ if (!retry_count) {
+ ret = -EBUSY;
+ break;
+ }
+ progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL);
+ if (!progress)
+ retry_count--;
+ }
+ return ret;
+}
+
+
/*
* This routine traverse page_cgroup in given list and drop them all.
* *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)
+ enum lru_list lru)
{
struct page_cgroup *pc;
struct page *page;
unsigned long flags;
struct list_head *list;
- if (active)
- list = &mz->active_list;
- else
- list = &mz->inactive_list;
+ list = &mz->lists[lru];
spin_lock_irqsave(&mz->lru_lock, flags);
while (!list_empty(list)) {
int ret = -EBUSY;
int node, zid;
- if (mem_cgroup_subsys.disabled)
- return 0;
-
css_get(&mem->css);
/*
* page reclaim code (kswapd etc..) will move pages between
for_each_node_state(node, N_POSSIBLE)
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
struct mem_cgroup_per_zone *mz;
+ enum lru_list l;
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);
+ for_each_lru(l)
+ mem_cgroup_force_empty_list(mem, mz, l);
}
}
ret = 0;
return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res,
cft->private);
}
-
+/*
+ * The user of this function is...
+ * RES_LIMIT.
+ */
static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
const char *buffer)
{
- return res_counter_write(&mem_cgroup_from_cont(cont)->res,
- cft->private, buffer,
- res_counter_memparse_write_strategy);
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ unsigned long long val;
+ int ret;
+
+ switch (cft->private) {
+ case RES_LIMIT:
+ /* This function does all necessary parse...reuse it */
+ ret = res_counter_memparse_write_strategy(buffer, &val);
+ if (!ret)
+ ret = mem_cgroup_resize_limit(memcg, val);
+ break;
+ default:
+ ret = -EINVAL; /* should be BUG() ? */
+ break;
+ }
+ return ret;
}
static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
}
/* 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);
- cb->fill(cb, "active", (active) * PAGE_SIZE);
- cb->fill(cb, "inactive", (inactive) * PAGE_SIZE);
+ 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);
+
}
return 0;
}
{
struct mem_cgroup_per_node *pn;
struct mem_cgroup_per_zone *mz;
+ enum lru_list l;
int zone, tmp = node;
/*
* This routine is called against possible nodes.
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);
+ for_each_lru(l)
+ INIT_LIST_HEAD(&mz->lists[l]);
}
return 0;
}
static int mem_cgroup_populate(struct cgroup_subsys *ss,
struct cgroup *cont)
{
- if (mem_cgroup_subsys.disabled)
- return 0;
return cgroup_add_files(cont, ss, mem_cgroup_files,
ARRAY_SIZE(mem_cgroup_files));
}
struct mm_struct *mm;
struct mem_cgroup *mem, *old_mem;
- if (mem_cgroup_subsys.disabled)
- return;
-
mm = get_task_mm(p);
if (mm == NULL)
return;
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