#define MEM_CGROUP_RECLAIM_RETRIES 5
#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
* 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 */
unsigned int swappiness;
+ /* set when res.limit == memsw.limit */
+ bool memsw_is_minimum;
+
/*
* statistics. This must be placed at the end of memcg.
*/
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,
};
return mem;
}
-static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
-{
- if (!mem)
- return true;
- return css_is_removed(&mem->css);
-}
-
-
/*
* Call callback function against all cgroup under hierarchy tree.
*/
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 zid = zone_idx(z);
struct mem_cgroup_per_zone *mz;
int lru = LRU_FILE * !!file + !!active;
+ int ret;
BUG_ON(!mem_cont);
mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
continue;
scan++;
- if (__isolate_lru_page(page, mode, file) == 0) {
+ 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;
}
}
int ret, total = 0;
int loop = 0;
+ /* If memsw_is_minimum==1, swap-out is of-no-use. */
+ if (root_mem->memsw_is_minimum)
+ noswap = true;
+
while (loop < 2) {
victim = mem_cgroup_select_victim(root_mem);
if (victim == root_mem)
mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb);
}
+/*
+ * 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;
+
+ if (!page_is_file_cache(page))
+ return;
+
+ pc = lookup_page_cgroup(page);
+ if (unlikely(!pc))
+ return;
+
+ lock_page_cgroup(pc);
+ mem = pc->mem_cgroup;
+ if (!mem)
+ goto done;
+
+ if (!PageCgroupUsed(pc))
+ goto done;
+
+ /*
+ * 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);
+}
/*
* Unlike exported interface, "oom" parameter is added. if oom==true,
if (unlikely(!mem))
return 0;
- VM_BUG_ON(mem_cgroup_is_obsolete(mem));
+ VM_BUG_ON(css_is_removed(&mem->css));
while (1) {
int ret;
return -ENOMEM;
}
+
+/*
+ * 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);
+}
+
static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
{
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;
- ent.val = page_private(page);
- mem = lookup_swap_cgroup(ent);
- if (!mem)
- return NULL;
- if (!css_tryget(&mem->css))
- 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;
}
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(from == to);
VM_BUG_ON(PageLRU(pc->page));
res_counter_uncharge(&from->res, PAGE_SIZE);
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)
res_counter_uncharge(&from->memsw, PAGE_SIZE);
css_put(&from->css);
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;
}
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)
{
unlock_page_cgroup(pc);
}
- if (do_swap_account && PageSwapCache(page)) {
- mem = try_get_mem_cgroup_from_swapcache(page);
- if (mem)
- mm = NULL;
- else
- mem = NULL;
- /* SwapCache may be still linked to LRU now. */
- mem_cgroup_lru_del_before_commit_swapcache(page);
- }
-
if (unlikely(!mm && !mem))
mm = &init_mm;
return mem_cgroup_charge_common(page, mm, gfp_mask,
MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
- ret = mem_cgroup_charge_common(page, mm, gfp_mask,
- MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
- if (mem)
- css_put(&mem->css);
- if (PageSwapCache(page))
- mem_cgroup_lru_add_after_commit_swapcache(page);
+ /* 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);
- if (do_swap_account && !ret && PageSwapCache(page)) {
- swp_entry_t ent = {.val = page_private(page)};
- /* avoid double counting */
- mem = swap_cgroup_record(ent, NULL);
- if (mem) {
- res_counter_uncharge(&mem->memsw, PAGE_SIZE);
- mem_cgroup_put(mem);
- }
- }
return ret;
}
return __mem_cgroup_try_charge(mm, mask, ptr, true);
}
-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;
return;
if (!ptr)
return;
+ cgroup_exclude_rmdir(&ptr->css);
pc = lookup_page_cgroup(page);
mem_cgroup_lru_del_before_commit_swapcache(page);
- __mem_cgroup_commit_charge(ptr, pc, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+ __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
*/
if (do_swap_account && PageSwapCache(page)) {
swp_entry_t ent = {.val = page_private(page)};
+ unsigned short id;
struct mem_cgroup *memcg;
- memcg = swap_cgroup_record(ent, NULL);
+
+ 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
+ */
res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
mem_cgroup_put(memcg);
}
-
+ rcu_read_unlock();
}
- /* add this page(page_cgroup) to the LRU we want. */
+ /*
+ * 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)
switch (ctype) {
case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+ case MEM_CGROUP_CHARGE_TYPE_DROP:
if (page_mapped(page))
goto unlock_out;
break;
__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
}
+#ifdef CONFIG_SWAP
/*
- * called from __delete_from_swap_cache() and drop "page" account.
+ * 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)
+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);
- memcg = __mem_cgroup_uncharge_common(page,
- MEM_CGROUP_CHARGE_TYPE_SWAPOUT);
/* record memcg information */
- if (do_swap_account && memcg) {
- swap_cgroup_record(ent, memcg);
+ if (do_swap_account && swapout && memcg) {
+ swap_cgroup_record(ent, css_id(&memcg->css));
mem_cgroup_get(memcg);
}
- if (memcg)
+ if (swapout && memcg)
css_put(&memcg->css);
}
+#endif
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
/*
void mem_cgroup_uncharge_swap(swp_entry_t ent)
{
struct mem_cgroup *memcg;
+ unsigned short id;
if (!do_swap_account)
return;
- memcg = swap_cgroup_record(ent, NULL);
+ 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
+ */
res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
mem_cgroup_put(memcg);
}
+ rcu_read_unlock();
}
#endif
if (!mem)
return;
-
+ cgroup_exclude_rmdir(&mem->css);
/* at migration success, oldpage->mapping is NULL. */
if (oldpage->mapping) {
target = oldpage;
*/
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 page *page,
+int mem_cgroup_shmem_charge_fallback(struct page *page,
struct mm_struct *mm,
gfp_t gfp_mask)
{
struct mem_cgroup *mem = NULL;
- int progress = 0;
- int retry = MEM_CGROUP_RECLAIM_RETRIES;
+ int ret;
if (mem_cgroup_disabled())
return 0;
- if (page)
- mem = try_get_mem_cgroup_from_swapcache(page);
- if (!mem && mm)
- mem = try_get_mem_cgroup_from_mm(mm);
- if (unlikely(!mem))
- return 0;
- do {
- progress = mem_cgroup_hierarchical_reclaim(mem,
- gfp_mask, true, false);
- progress += mem_cgroup_check_under_limit(mem);
- } while (!progress && --retry);
+ ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem);
+ if (!ret)
+ mem_cgroup_cancel_charge_swapin(mem); /* it does !mem check */
- css_put(&mem->css);
- if (!retry)
- return -ENOMEM;
- return 0;
+ return ret;
}
static DEFINE_MUTEX(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 (!ret)
return ret;
}
-int mem_cgroup_resize_memsw_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;
- if (!do_swap_account)
- return -EINVAL;
/* see mem_cgroup_resize_res_limit */
retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
break;
}
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)
if (!progress) {
nr_retries--;
/* maybe some writeback is necessary */
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
}
}
val = res_counter_read_u64(&mem->res, name);
break;
case _MEMSWAP:
- if (do_swap_account)
- val = res_counter_read_u64(&mem->memsw, name);
+ val = res_counter_read_u64(&mem->memsw, name);
break;
default:
BUG();
enum {
MCS_CACHE,
MCS_RSS,
+ MCS_MAPPED_FILE,
MCS_PGPGIN,
MCS_PGPGOUT,
MCS_INACTIVE_ANON,
} memcg_stat_strings[NR_MCS_STAT] = {
{"cache", "total_cache"},
{"rss", "total_rss"},
+ {"mapped_file", "total_mapped_file"},
{"pgpgin", "total_pgpgin"},
{"pgpgout", "total_pgpgout"},
{"inactive_anon", "total_inactive_anon"},
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);