#include <linux/mm_inline.h>
#include <linux/page_cgroup.h>
#include <linux/cpu.h>
+#include <linux/oom.h>
#include "internal.h"
#include <asm/uaccess.h>
+#include <trace/events/vmscan.h>
+
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 = 1 */
int do_swap_account __read_mostly;
-static int really_do_swap_account __initdata = 1; /* for remember boot option*/
+
+/* for remember boot option*/
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED
+static int really_do_swap_account __initdata = 1;
+#else
+static int really_do_swap_account __initdata = 0;
+#endif
+
#else
#define do_swap_account (0)
#endif
-/*
- * Per memcg event counter is incremented at every pagein/pageout. This counter
- * is used for trigger some periodic events. This is straightforward and better
- * than using jiffies etc. to handle periodic memcg event.
- *
- * These values will be used as !((event) & ((1 <<(thresh)) - 1))
- */
-#define THRESHOLDS_EVENTS_THRESH (7) /* once in 128 */
-#define SOFTLIMIT_EVENTS_THRESH (10) /* once in 1024 */
/*
* Statistics for memory cgroup.
MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
MEM_CGROUP_STAT_FILE_MAPPED, /* # 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_SWAPOUT, /* # of pages, swapped out */
- MEM_CGROUP_EVENTS, /* incremented at every pagein/pageout */
-
+ MEM_CGROUP_STAT_DATA, /* end of data requires synchronization */
+ MEM_CGROUP_ON_MOVE, /* someone is moving account between groups */
MEM_CGROUP_STAT_NSTATS,
};
+enum mem_cgroup_events_index {
+ MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */
+ MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */
+ MEM_CGROUP_EVENTS_COUNT, /* # of pages paged in/out */
+ MEM_CGROUP_EVENTS_NSTATS,
+};
+/*
+ * Per memcg event counter is incremented at every pagein/pageout. With THP,
+ * it will be incremated by the number of pages. This counter is used for
+ * for trigger some periodic events. This is straightforward and better
+ * than using jiffies etc. to handle periodic memcg event.
+ */
+enum mem_cgroup_events_target {
+ MEM_CGROUP_TARGET_THRESH,
+ MEM_CGROUP_TARGET_SOFTLIMIT,
+ MEM_CGROUP_NTARGETS,
+};
+#define THRESHOLDS_EVENTS_TARGET (128)
+#define SOFTLIMIT_EVENTS_TARGET (1024)
+
struct mem_cgroup_stat_cpu {
- s64 count[MEM_CGROUP_STAT_NSTATS];
+ long count[MEM_CGROUP_STAT_NSTATS];
+ unsigned long events[MEM_CGROUP_EVENTS_NSTATS];
+ unsigned long targets[MEM_CGROUP_NTARGETS];
};
/*
/* Array of thresholds */
struct mem_cgroup_threshold entries[0];
};
+
+struct mem_cgroup_thresholds {
+ /* Primary thresholds array */
+ struct mem_cgroup_threshold_ary *primary;
+ /*
+ * Spare threshold array.
+ * This is needed to make mem_cgroup_unregister_event() "never fail".
+ * It must be able to store at least primary->size - 1 entries.
+ */
+ struct mem_cgroup_threshold_ary *spare;
+};
+
/* for OOM */
struct mem_cgroup_eventfd_list {
struct list_head list;
* 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 hierarchy, we cache the last child we
* reclaimed from.
struct mutex thresholds_lock;
/* thresholds for memory usage. RCU-protected */
- struct mem_cgroup_threshold_ary *thresholds;
+ struct mem_cgroup_thresholds thresholds;
/* thresholds for mem+swap usage. RCU-protected */
- struct mem_cgroup_threshold_ary *memsw_thresholds;
+ struct mem_cgroup_thresholds memsw_thresholds;
/* For oom notifier event fd */
struct list_head oom_notify;
* percpu counter.
*/
struct mem_cgroup_stat_cpu *stat;
+ /*
+ * used when a cpu is offlined or other synchronizations
+ * See mem_cgroup_read_stat().
+ */
+ struct mem_cgroup_stat_cpu nocpu_base;
+ spinlock_t pcp_counter_lock;
};
/* Stuffs for move charges at task migration. */
/* "mc" and its members are protected by cgroup_mutex */
static struct move_charge_struct {
+ spinlock_t lock; /* for from, to */
struct mem_cgroup *from;
struct mem_cgroup *to;
unsigned long precharge;
struct task_struct *moving_task; /* a task moving charges */
wait_queue_head_t waitq; /* a waitq for other context */
} mc = {
+ .lock = __SPIN_LOCK_UNLOCKED(mc.lock),
.waitq = __WAIT_QUEUE_HEAD_INITIALIZER(mc.waitq),
};
NR_CHARGE_TYPE,
};
-/* only for here (for easy reading.) */
-#define PCGF_CACHE (1UL << PCG_CACHE)
-#define PCGF_USED (1UL << PCG_USED)
-#define PCGF_LOCK (1UL << PCG_LOCK)
-/* 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)
}
static struct mem_cgroup_per_zone *
-page_cgroup_zoneinfo(struct page_cgroup *pc)
+page_cgroup_zoneinfo(struct mem_cgroup *mem, struct page *page)
{
- struct mem_cgroup *mem = pc->mem_cgroup;
- int nid = page_cgroup_nid(pc);
- int zid = page_cgroup_zid(pc);
-
- if (!mem)
- return NULL;
+ int nid = page_to_nid(page);
+ int zid = page_zonenum(page);
return mem_cgroup_zoneinfo(mem, nid, zid);
}
}
}
-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)
{
return mz;
}
-static s64 mem_cgroup_read_stat(struct mem_cgroup *mem,
- enum mem_cgroup_stat_index idx)
+/*
+ * Implementation Note: reading percpu statistics for memcg.
+ *
+ * Both of vmstat[] and percpu_counter has threshold and do periodic
+ * synchronization to implement "quick" read. There are trade-off between
+ * reading cost and precision of value. Then, we may have a chance to implement
+ * a periodic synchronizion of counter in memcg's counter.
+ *
+ * But this _read() function is used for user interface now. The user accounts
+ * memory usage by memory cgroup and he _always_ requires exact value because
+ * he accounts memory. Even if we provide quick-and-fuzzy read, we always
+ * have to visit all online cpus and make sum. So, for now, unnecessary
+ * synchronization is not implemented. (just implemented for cpu hotplug)
+ *
+ * If there are kernel internal actions which can make use of some not-exact
+ * value, and reading all cpu value can be performance bottleneck in some
+ * common workload, threashold and synchonization as vmstat[] should be
+ * implemented.
+ */
+static long mem_cgroup_read_stat(struct mem_cgroup *mem,
+ enum mem_cgroup_stat_index idx)
{
+ long val = 0;
int cpu;
- s64 val = 0;
- for_each_possible_cpu(cpu)
+ get_online_cpus();
+ for_each_online_cpu(cpu)
val += per_cpu(mem->stat->count[idx], cpu);
+#ifdef CONFIG_HOTPLUG_CPU
+ spin_lock(&mem->pcp_counter_lock);
+ val += mem->nocpu_base.count[idx];
+ spin_unlock(&mem->pcp_counter_lock);
+#endif
+ put_online_cpus();
return val;
}
-static s64 mem_cgroup_local_usage(struct mem_cgroup *mem)
+static long mem_cgroup_local_usage(struct mem_cgroup *mem)
{
- s64 ret;
+ long ret;
ret = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS);
ret += mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE);
this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_SWAPOUT], val);
}
-static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
- struct page_cgroup *pc,
- bool charge)
+static unsigned long mem_cgroup_read_events(struct mem_cgroup *mem,
+ enum mem_cgroup_events_index idx)
{
- int val = (charge) ? 1 : -1;
+ unsigned long val = 0;
+ int cpu;
+ for_each_online_cpu(cpu)
+ val += per_cpu(mem->stat->events[idx], cpu);
+#ifdef CONFIG_HOTPLUG_CPU
+ spin_lock(&mem->pcp_counter_lock);
+ val += mem->nocpu_base.events[idx];
+ spin_unlock(&mem->pcp_counter_lock);
+#endif
+ return val;
+}
+
+static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
+ bool file, int nr_pages)
+{
preempt_disable();
- if (PageCgroupCache(pc))
- __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_CACHE], val);
+ if (file)
+ __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_CACHE], nr_pages);
else
- __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_RSS], val);
+ __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_RSS], nr_pages);
+
+ /* pagein of a big page is an event. So, ignore page size */
+ if (nr_pages > 0)
+ __this_cpu_inc(mem->stat->events[MEM_CGROUP_EVENTS_PGPGIN]);
+ else {
+ __this_cpu_inc(mem->stat->events[MEM_CGROUP_EVENTS_PGPGOUT]);
+ nr_pages = -nr_pages; /* for event */
+ }
- if (charge)
- __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGIN_COUNT]);
- else
- __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGOUT_COUNT]);
- __this_cpu_inc(mem->stat->count[MEM_CGROUP_EVENTS]);
+ __this_cpu_add(mem->stat->events[MEM_CGROUP_EVENTS_COUNT], nr_pages);
preempt_enable();
}
return total;
}
-static bool __memcg_event_check(struct mem_cgroup *mem, int event_mask_shift)
+static bool __memcg_event_check(struct mem_cgroup *mem, int target)
{
- s64 val;
+ unsigned long val, next;
+
+ val = this_cpu_read(mem->stat->events[MEM_CGROUP_EVENTS_COUNT]);
+ next = this_cpu_read(mem->stat->targets[target]);
+ /* from time_after() in jiffies.h */
+ return ((long)next - (long)val < 0);
+}
- val = this_cpu_read(mem->stat->count[MEM_CGROUP_EVENTS]);
+static void __mem_cgroup_target_update(struct mem_cgroup *mem, int target)
+{
+ unsigned long val, next;
+
+ val = this_cpu_read(mem->stat->events[MEM_CGROUP_EVENTS_COUNT]);
+
+ switch (target) {
+ case MEM_CGROUP_TARGET_THRESH:
+ next = val + THRESHOLDS_EVENTS_TARGET;
+ break;
+ case MEM_CGROUP_TARGET_SOFTLIMIT:
+ next = val + SOFTLIMIT_EVENTS_TARGET;
+ break;
+ default:
+ return;
+ }
- return !(val & ((1 << event_mask_shift) - 1));
+ this_cpu_write(mem->stat->targets[target], next);
}
/*
static void memcg_check_events(struct mem_cgroup *mem, struct page *page)
{
/* threshold event is triggered in finer grain than soft limit */
- if (unlikely(__memcg_event_check(mem, THRESHOLDS_EVENTS_THRESH))) {
+ if (unlikely(__memcg_event_check(mem, MEM_CGROUP_TARGET_THRESH))) {
mem_cgroup_threshold(mem);
- if (unlikely(__memcg_event_check(mem, SOFTLIMIT_EVENTS_THRESH)))
+ __mem_cgroup_target_update(mem, MEM_CGROUP_TARGET_THRESH);
+ if (unlikely(__memcg_event_check(mem,
+ MEM_CGROUP_TARGET_SOFTLIMIT))){
mem_cgroup_update_tree(mem, page);
+ __mem_cgroup_target_update(mem,
+ MEM_CGROUP_TARGET_SOFTLIMIT);
+ }
}
}
return mem;
}
-/*
- * 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 *))
+/* The caller has to guarantee "mem" exists before calling this */
+static struct mem_cgroup *mem_cgroup_start_loop(struct mem_cgroup *mem)
{
- int found, ret, nextid;
struct cgroup_subsys_state *css;
- struct mem_cgroup *mem;
-
- if (!root->use_hierarchy)
- return (*func)(root, data);
+ int found;
- nextid = 1;
- do {
- ret = 0;
+ if (!mem) /* ROOT cgroup has the smallest ID */
+ return root_mem_cgroup; /*css_put/get against root is ignored*/
+ if (!mem->use_hierarchy) {
+ if (css_tryget(&mem->css))
+ return mem;
+ return NULL;
+ }
+ rcu_read_lock();
+ /*
+ * searching a memory cgroup which has the smallest ID under given
+ * ROOT cgroup. (ID >= 1)
+ */
+ css = css_get_next(&mem_cgroup_subsys, 1, &mem->css, &found);
+ if (css && css_tryget(css))
+ mem = container_of(css, struct mem_cgroup, css);
+ else
mem = NULL;
+ rcu_read_unlock();
+ return mem;
+}
+
+static struct mem_cgroup *mem_cgroup_get_next(struct mem_cgroup *iter,
+ struct mem_cgroup *root,
+ bool cond)
+{
+ int nextid = css_id(&iter->css) + 1;
+ int found;
+ int hierarchy_used;
+ struct cgroup_subsys_state *css;
+
+ hierarchy_used = iter->use_hierarchy;
+
+ css_put(&iter->css);
+ /* If no ROOT, walk all, ignore hierarchy */
+ if (!cond || (root && !hierarchy_used))
+ return NULL;
+
+ if (!root)
+ root = root_mem_cgroup;
+ do {
+ iter = NULL;
rcu_read_lock();
- css = css_get_next(&mem_cgroup_subsys, nextid, &root->css,
- &found);
+
+ css = css_get_next(&mem_cgroup_subsys, nextid,
+ &root->css, &found);
if (css && css_tryget(css))
- mem = container_of(css, struct mem_cgroup, css);
+ iter = container_of(css, struct mem_cgroup, css);
rcu_read_unlock();
-
- if (mem) {
- ret = (*func)(mem, data);
- css_put(&mem->css);
- }
+ /* If css is NULL, no more cgroups will be found */
nextid = found + 1;
- } while (!ret && css);
+ } while (css && !iter);
- return ret;
+ return iter;
}
+/*
+ * for_eacn_mem_cgroup_tree() for visiting all cgroup under tree. Please
+ * be careful that "break" loop is not allowed. We have reference count.
+ * Instead of that modify "cond" to be false and "continue" to exit the loop.
+ */
+#define for_each_mem_cgroup_tree_cond(iter, root, cond) \
+ for (iter = mem_cgroup_start_loop(root);\
+ iter != NULL;\
+ iter = mem_cgroup_get_next(iter, root, cond))
+
+#define for_each_mem_cgroup_tree(iter, root) \
+ for_each_mem_cgroup_tree_cond(iter, root, true)
+
+#define for_each_mem_cgroup_all(iter) \
+ for_each_mem_cgroup_tree_cond(iter, NULL, true)
+
static inline bool mem_cgroup_is_root(struct mem_cgroup *mem)
{
* We don't check PCG_USED bit. It's cleared when the "page" is finally
* removed from global LRU.
*/
- mz = page_cgroup_zoneinfo(pc);
- MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+ mz = page_cgroup_zoneinfo(pc->mem_cgroup, page);
+ /* huge page split is done under lru_lock. so, we have no races. */
+ MEM_CGROUP_ZSTAT(mz, lru) -= 1 << compound_order(page);
if (mem_cgroup_is_root(pc->mem_cgroup))
return;
VM_BUG_ON(list_empty(&pc->lru));
list_del_init(&pc->lru);
- return;
}
void mem_cgroup_del_lru(struct page *page)
mem_cgroup_del_lru_list(page, page_lru(page));
}
-void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru)
+/*
+ * Writeback is about to end against a page which has been marked for immediate
+ * reclaim. If it still appears to be reclaimable, move it to the tail of the
+ * inactive list.
+ */
+void mem_cgroup_rotate_reclaimable_page(struct page *page)
{
struct mem_cgroup_per_zone *mz;
struct page_cgroup *pc;
+ enum lru_list lru = page_lru(page);
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.
- */
+ /* unused or root page is not rotated. */
+ if (!PageCgroupUsed(pc))
+ return;
+ /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
smp_rmb();
+ if (mem_cgroup_is_root(pc->mem_cgroup))
+ return;
+ mz = page_cgroup_zoneinfo(pc->mem_cgroup, page);
+ list_move_tail(&pc->lru, &mz->lists[lru]);
+}
+
+void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru)
+{
+ struct mem_cgroup_per_zone *mz;
+ struct page_cgroup *pc;
+
+ if (mem_cgroup_disabled())
+ return;
+
+ pc = lookup_page_cgroup(page);
/* unused or root page is not rotated. */
- if (!PageCgroupUsed(pc) || mem_cgroup_is_root(pc->mem_cgroup))
+ if (!PageCgroupUsed(pc))
+ return;
+ /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
+ smp_rmb();
+ if (mem_cgroup_is_root(pc->mem_cgroup))
return;
- mz = page_cgroup_zoneinfo(pc);
+ mz = page_cgroup_zoneinfo(pc->mem_cgroup, page);
list_move(&pc->lru, &mz->lists[lru]);
}
return;
pc = lookup_page_cgroup(page);
VM_BUG_ON(PageCgroupAcctLRU(pc));
- /*
- * 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;
-
- mz = page_cgroup_zoneinfo(pc);
- MEM_CGROUP_ZSTAT(mz, lru) += 1;
+ /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
+ smp_rmb();
+ mz = page_cgroup_zoneinfo(pc->mem_cgroup, page);
+ /* huge page split is done under lru_lock. so, we have no races. */
+ MEM_CGROUP_ZSTAT(mz, lru) += 1 << compound_order(page);
SetPageCgroupAcctLRU(pc);
if (mem_cgroup_is_root(pc->mem_cgroup))
return;
}
/*
- * 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.
+ * At handling SwapCache and other FUSE stuff, pc->mem_cgroup may be changed
+ * while it's linked to lru because the page may be reused after it's fully
+ * uncharged. To handle that, unlink page_cgroup from LRU when charge it again.
+ * It's done under lock_page and expected that zone->lru_lock isnever held.
*/
-static void mem_cgroup_lru_del_before_commit_swapcache(struct page *page)
+static void mem_cgroup_lru_del_before_commit(struct page *page)
{
unsigned long flags;
struct zone *zone = page_zone(page);
struct page_cgroup *pc = lookup_page_cgroup(page);
+ /*
+ * Doing this check without taking ->lru_lock seems wrong but this
+ * is safe. Because if page_cgroup's USED bit is unset, the page
+ * will not be added to any memcg's LRU. If page_cgroup's USED bit is
+ * set, the commit after this will fail, anyway.
+ * This all charge/uncharge is done under some mutual execustion.
+ * So, we don't need to taking care of changes in USED bit.
+ */
+ if (likely(!PageLRU(page)))
+ return;
+
spin_lock_irqsave(&zone->lru_lock, flags);
/*
* Forget old LRU when this page_cgroup is *not* used. This Used bit
spin_unlock_irqrestore(&zone->lru_lock, flags);
}
-static void mem_cgroup_lru_add_after_commit_swapcache(struct page *page)
+static void mem_cgroup_lru_add_after_commit(struct page *page)
{
unsigned long flags;
struct zone *zone = page_zone(page);
struct page_cgroup *pc = lookup_page_cgroup(page);
+ /* taking care of that the page is added to LRU while we commit it */
+ if (likely(!PageLRU(page)))
+ return;
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))
{
int ret;
struct mem_cgroup *curr = NULL;
+ struct task_struct *p;
- task_lock(task);
- rcu_read_lock();
- curr = try_get_mem_cgroup_from_mm(task->mm);
- rcu_read_unlock();
- task_unlock(task);
+ p = find_lock_task_mm(task);
+ if (!p)
+ return 0;
+ curr = try_get_mem_cgroup_from_mm(p->mm);
+ task_unlock(p);
if (!curr)
return 0;
/*
return ret;
}
-/*
- * prev_priority control...this will be used in memory reclaim path.
- */
-int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
-{
- 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);
-}
-
static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_pages)
{
unsigned long active;
struct zone *zone,
enum lru_list lru)
{
- int nid = zone->zone_pgdat->node_id;
+ int nid = zone_to_nid(zone);
int zid = zone_idx(zone);
struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);
struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
struct zone *zone)
{
- int nid = zone->zone_pgdat->node_id;
+ int nid = zone_to_nid(zone);
int zid = zone_idx(zone);
struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);
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;
-
- mz = page_cgroup_zoneinfo(pc);
- if (!mz)
- return NULL;
-
+ /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
+ smp_rmb();
+ mz = page_cgroup_zoneinfo(pc->mem_cgroup, page);
return &mz->reclaim_stat;
}
LIST_HEAD(pc_list);
struct list_head *src;
struct page_cgroup *pc, *tmp;
- int nid = z->zone_pgdat->node_id;
+ int nid = zone_to_nid(z);
int zid = zone_idx(z);
struct mem_cgroup_per_zone *mz;
int lru = LRU_FILE * file + active;
if (scan >= nr_to_scan)
break;
- page = pc->page;
if (unlikely(!PageCgroupUsed(pc)))
continue;
+
+ page = lookup_cgroup_page(pc);
+
if (unlikely(!PageLRU(page)))
continue;
case 0:
list_move(&page->lru, dst);
mem_cgroup_del_lru(page);
- nr_taken++;
+ nr_taken += hpage_nr_pages(page);
break;
case -EBUSY:
/* we don't affect global LRU but rotate in our LRU */
}
*scanned = scan;
+
+ trace_mm_vmscan_memcg_isolate(0, nr_to_scan, scan, nr_taken,
+ 0, 0, 0, mode);
+
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)
+/**
+ * mem_cgroup_margin - calculate chargeable space of a memory cgroup
+ * @mem: the memory cgroup
+ *
+ * Returns the maximum amount of memory @mem can be charged with, in
+ * pages.
+ */
+static unsigned long mem_cgroup_margin(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;
+ unsigned long long margin;
+
+ margin = res_counter_margin(&mem->res);
+ if (do_swap_account)
+ margin = min(margin, res_counter_margin(&mem->memsw));
+ return margin >> PAGE_SHIFT;
}
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 memcg->swappiness;
+}
- return swappiness;
+static void mem_cgroup_start_move(struct mem_cgroup *mem)
+{
+ int cpu;
+
+ get_online_cpus();
+ spin_lock(&mem->pcp_counter_lock);
+ for_each_online_cpu(cpu)
+ per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1;
+ mem->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1;
+ spin_unlock(&mem->pcp_counter_lock);
+ put_online_cpus();
+
+ synchronize_rcu();
}
-static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data)
+static void mem_cgroup_end_move(struct mem_cgroup *mem)
{
- int *val = data;
- (*val)++;
- return 0;
+ int cpu;
+
+ if (!mem)
+ return;
+ get_online_cpus();
+ spin_lock(&mem->pcp_counter_lock);
+ for_each_online_cpu(cpu)
+ per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1;
+ mem->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1;
+ spin_unlock(&mem->pcp_counter_lock);
+ put_online_cpus();
+}
+/*
+ * 2 routines for checking "mem" is under move_account() or not.
+ *
+ * mem_cgroup_stealed() - checking a cgroup is mc.from or not. This is used
+ * for avoiding race in accounting. If true,
+ * pc->mem_cgroup may be overwritten.
+ *
+ * mem_cgroup_under_move() - checking a cgroup is mc.from or mc.to or
+ * under hierarchy of moving cgroups. This is for
+ * waiting at hith-memory prressure caused by "move".
+ */
+
+static bool mem_cgroup_stealed(struct mem_cgroup *mem)
+{
+ VM_BUG_ON(!rcu_read_lock_held());
+ return this_cpu_read(mem->stat->count[MEM_CGROUP_ON_MOVE]) > 0;
+}
+
+static bool mem_cgroup_under_move(struct mem_cgroup *mem)
+{
+ struct mem_cgroup *from;
+ struct mem_cgroup *to;
+ bool ret = false;
+ /*
+ * Unlike task_move routines, we access mc.to, mc.from not under
+ * mutual exclusion by cgroup_mutex. Here, we take spinlock instead.
+ */
+ spin_lock(&mc.lock);
+ from = mc.from;
+ to = mc.to;
+ if (!from)
+ goto unlock;
+ if (from == mem || to == mem
+ || (mem->use_hierarchy && css_is_ancestor(&from->css, &mem->css))
+ || (mem->use_hierarchy && css_is_ancestor(&to->css, &mem->css)))
+ ret = true;
+unlock:
+ spin_unlock(&mc.lock);
+ return ret;
+}
+
+static bool mem_cgroup_wait_acct_move(struct mem_cgroup *mem)
+{
+ if (mc.moving_task && current != mc.moving_task) {
+ if (mem_cgroup_under_move(mem)) {
+ DEFINE_WAIT(wait);
+ prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE);
+ /* moving charge context might have finished. */
+ if (mc.moving_task)
+ schedule();
+ finish_wait(&mc.waitq, &wait);
+ return true;
+ }
+ }
+ return false;
}
/**
static int mem_cgroup_count_children(struct mem_cgroup *mem)
{
int num = 0;
- mem_cgroup_walk_tree(mem, &num, mem_cgroup_count_children_cb);
+ struct mem_cgroup *iter;
+
+ for_each_mem_cgroup_tree(iter, mem)
+ num++;
return num;
}
+/*
+ * Return the memory (and swap, if configured) limit for a memcg.
+ */
+u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
+{
+ u64 limit;
+ u64 memsw;
+
+ limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
+ limit += total_swap_pages << PAGE_SHIFT;
+
+ memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+ /*
+ * If memsw is finite and limits the amount of swap space available
+ * to this memcg, return that limit.
+ */
+ return min(limit, memsw);
+}
+
/*
* 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
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;
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);
+ unsigned long excess;
+
+ excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;
/* If memsw_is_minimum==1, swap-out is of-no-use. */
if (root_mem->memsw_is_minimum)
break;
}
/*
- * We want to do more targetted reclaim.
+ * We want to do more targeted 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
/* 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);
+ noswap, get_swappiness(victim), zone);
else
ret = try_to_free_mem_cgroup_pages(victim, gfp_mask,
noswap, get_swappiness(victim));
return ret;
total += ret;
if (check_soft) {
- if (res_counter_check_under_soft_limit(&root_mem->res))
+ if (!res_counter_soft_limit_excess(&root_mem->res))
return total;
- } else if (mem_cgroup_check_under_limit(root_mem))
+ } else if (mem_cgroup_margin(root_mem))
return 1 + total;
}
return total;
}
-static int mem_cgroup_oom_lock_cb(struct mem_cgroup *mem, void *data)
-{
- int *val = (int *)data;
- int x;
- /*
- * Logically, we can stop scanning immediately when we find
- * a memcg is already locked. But condidering unlock ops and
- * creation/removal of memcg, scan-all is simple operation.
- */
- x = atomic_inc_return(&mem->oom_lock);
- *val = max(x, *val);
- return 0;
-}
/*
* Check OOM-Killer is already running under our hierarchy.
* If someone is running, return false.
*/
static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)
{
- int lock_count = 0;
+ int x, lock_count = 0;
+ struct mem_cgroup *iter;
- mem_cgroup_walk_tree(mem, &lock_count, mem_cgroup_oom_lock_cb);
+ for_each_mem_cgroup_tree(iter, mem) {
+ x = atomic_inc_return(&iter->oom_lock);
+ lock_count = max(x, lock_count);
+ }
if (lock_count == 1)
return true;
return false;
}
-static int mem_cgroup_oom_unlock_cb(struct mem_cgroup *mem, void *data)
+static int mem_cgroup_oom_unlock(struct mem_cgroup *mem)
{
+ struct mem_cgroup *iter;
+
/*
* When a new child is created while the hierarchy is under oom,
* mem_cgroup_oom_lock() may not be called. We have to use
* atomic_add_unless() here.
*/
- atomic_add_unless(&mem->oom_lock, -1, 0);
+ for_each_mem_cgroup_tree(iter, mem)
+ atomic_add_unless(&iter->oom_lock, -1, 0);
return 0;
}
-static void mem_cgroup_oom_unlock(struct mem_cgroup *mem)
-{
- mem_cgroup_walk_tree(mem, NULL, mem_cgroup_oom_unlock_cb);
-}
static DEFINE_MUTEX(memcg_oom_mutex);
static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
static void memcg_oom_recover(struct mem_cgroup *mem)
{
- if (mem->oom_kill_disable && atomic_read(&mem->oom_lock))
+ if (mem && atomic_read(&mem->oom_lock))
memcg_wakeup_oom(mem);
}
/*
* Currently used to update mapped file statistics, but the routine can be
* generalized to update other statistics as well.
+ *
+ * Notes: Race condition
+ *
+ * We usually use page_cgroup_lock() for accessing page_cgroup member but
+ * it tends to be costly. But considering some conditions, we doesn't need
+ * to do so _always_.
+ *
+ * Considering "charge", lock_page_cgroup() is not required because all
+ * file-stat operations happen after a page is attached to radix-tree. There
+ * are no race with "charge".
+ *
+ * Considering "uncharge", we know that memcg doesn't clear pc->mem_cgroup
+ * at "uncharge" intentionally. So, we always see valid pc->mem_cgroup even
+ * if there are race with "uncharge". Statistics itself is properly handled
+ * by flags.
+ *
+ * Considering "move", this is an only case we see a race. To make the race
+ * small, we check MEM_CGROUP_ON_MOVE percpu value and detect there are
+ * possibility of race condition. If there is, we take a lock.
*/
-void mem_cgroup_update_file_mapped(struct page *page, int val)
+
+void mem_cgroup_update_page_stat(struct page *page,
+ enum mem_cgroup_page_stat_item idx, int val)
{
struct mem_cgroup *mem;
- struct page_cgroup *pc;
+ struct page_cgroup *pc = lookup_page_cgroup(page);
+ bool need_unlock = false;
+ unsigned long uninitialized_var(flags);
- pc = lookup_page_cgroup(page);
if (unlikely(!pc))
return;
- lock_page_cgroup(pc);
+ rcu_read_lock();
mem = pc->mem_cgroup;
- if (!mem || !PageCgroupUsed(pc))
- goto done;
+ if (unlikely(!mem || !PageCgroupUsed(pc)))
+ goto out;
+ /* pc->mem_cgroup is unstable ? */
+ if (unlikely(mem_cgroup_stealed(mem)) || PageTransHuge(page)) {
+ /* take a lock against to access pc->mem_cgroup */
+ move_lock_page_cgroup(pc, &flags);
+ need_unlock = true;
+ mem = pc->mem_cgroup;
+ if (!mem || !PageCgroupUsed(pc))
+ goto out;
+ }
- /*
- * Preemption is already disabled. We can use __this_cpu_xxx
- */
- if (val > 0) {
- __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
- SetPageCgroupFileMapped(pc);
- } else {
- __this_cpu_dec(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
- ClearPageCgroupFileMapped(pc);
+ switch (idx) {
+ case MEMCG_NR_FILE_MAPPED:
+ if (val > 0)
+ SetPageCgroupFileMapped(pc);
+ else if (!page_mapped(page))
+ ClearPageCgroupFileMapped(pc);
+ idx = MEM_CGROUP_STAT_FILE_MAPPED;
+ break;
+ default:
+ BUG();
}
-done:
- unlock_page_cgroup(pc);
+ this_cpu_add(mem->stat->count[idx], val);
+
+out:
+ if (unlikely(need_unlock))
+ move_unlock_page_cgroup(pc, &flags);
+ rcu_read_unlock();
+ return;
}
+EXPORT_SYMBOL(mem_cgroup_update_page_stat);
/*
* size of first charge trial. "32" comes from vmscan.c's magic value.
* TODO: maybe necessary to use big numbers in big irons.
*/
-#define CHARGE_SIZE (32 * PAGE_SIZE)
+#define CHARGE_BATCH 32U
struct memcg_stock_pcp {
struct mem_cgroup *cached; /* this never be root cgroup */
- int charge;
+ unsigned int nr_pages;
struct work_struct work;
};
static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
static atomic_t memcg_drain_count;
/*
- * Try to consume stocked charge on this cpu. If success, PAGE_SIZE is consumed
+ * Try to consume stocked charge on this cpu. If success, one page is consumed
* from local stock and true is returned. If the stock is 0 or charges from a
* cgroup which is not current target, returns false. This stock will be
* refilled.
bool ret = true;
stock = &get_cpu_var(memcg_stock);
- if (mem == stock->cached && stock->charge)
- stock->charge -= PAGE_SIZE;
+ if (mem == stock->cached && stock->nr_pages)
+ stock->nr_pages--;
else /* need to call res_counter_charge */
ret = false;
put_cpu_var(memcg_stock);
{
struct mem_cgroup *old = stock->cached;
- if (stock->charge) {
- res_counter_uncharge(&old->res, stock->charge);
+ if (stock->nr_pages) {
+ unsigned long bytes = stock->nr_pages * PAGE_SIZE;
+
+ res_counter_uncharge(&old->res, bytes);
if (do_swap_account)
- res_counter_uncharge(&old->memsw, stock->charge);
+ res_counter_uncharge(&old->memsw, bytes);
+ stock->nr_pages = 0;
}
stock->cached = NULL;
- stock->charge = 0;
}
/*
* Cache charges(val) which is from res_counter, to local per_cpu area.
* This will be consumed by consume_stock() function, later.
*/
-static void refill_stock(struct mem_cgroup *mem, int val)
+static void refill_stock(struct mem_cgroup *mem, unsigned int nr_pages)
{
struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
drain_stock(stock);
stock->cached = mem;
}
- stock->charge += val;
+ stock->nr_pages += nr_pages;
put_cpu_var(memcg_stock);
}
atomic_dec(&memcg_drain_count);
}
-static int __cpuinit memcg_stock_cpu_callback(struct notifier_block *nb,
+/*
+ * This function drains percpu counter value from DEAD cpu and
+ * move it to local cpu. Note that this function can be preempted.
+ */
+static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *mem, int cpu)
+{
+ int i;
+
+ spin_lock(&mem->pcp_counter_lock);
+ for (i = 0; i < MEM_CGROUP_STAT_DATA; i++) {
+ long x = per_cpu(mem->stat->count[i], cpu);
+
+ per_cpu(mem->stat->count[i], cpu) = 0;
+ mem->nocpu_base.count[i] += x;
+ }
+ for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
+ unsigned long x = per_cpu(mem->stat->events[i], cpu);
+
+ per_cpu(mem->stat->events[i], cpu) = 0;
+ mem->nocpu_base.events[i] += x;
+ }
+ /* need to clear ON_MOVE value, works as a kind of lock. */
+ per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0;
+ spin_unlock(&mem->pcp_counter_lock);
+}
+
+static void synchronize_mem_cgroup_on_move(struct mem_cgroup *mem, int cpu)
+{
+ int idx = MEM_CGROUP_ON_MOVE;
+
+ spin_lock(&mem->pcp_counter_lock);
+ per_cpu(mem->stat->count[idx], cpu) = mem->nocpu_base.count[idx];
+ spin_unlock(&mem->pcp_counter_lock);
+}
+
+static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb,
unsigned long action,
void *hcpu)
{
int cpu = (unsigned long)hcpu;
struct memcg_stock_pcp *stock;
+ struct mem_cgroup *iter;
+
+ if ((action == CPU_ONLINE)) {
+ for_each_mem_cgroup_all(iter)
+ synchronize_mem_cgroup_on_move(iter, cpu);
+ return NOTIFY_OK;
+ }
- if (action != CPU_DEAD)
+ if ((action != CPU_DEAD) || action != CPU_DEAD_FROZEN)
return NOTIFY_OK;
+
+ for_each_mem_cgroup_all(iter)
+ mem_cgroup_drain_pcp_counter(iter, cpu);
+
stock = &per_cpu(memcg_stock, cpu);
drain_stock(stock);
return NOTIFY_OK;
}
+
+/* See __mem_cgroup_try_charge() for details */
+enum {
+ CHARGE_OK, /* success */
+ CHARGE_RETRY, /* need to retry but retry is not bad */
+ CHARGE_NOMEM, /* we can't do more. return -ENOMEM */
+ CHARGE_WOULDBLOCK, /* GFP_WAIT wasn't set and no enough res. */
+ CHARGE_OOM_DIE, /* the current is killed because of OOM */
+};
+
+static int mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask,
+ unsigned int nr_pages, bool oom_check)
+{
+ unsigned long csize = nr_pages * PAGE_SIZE;
+ struct mem_cgroup *mem_over_limit;
+ struct res_counter *fail_res;
+ unsigned long flags = 0;
+ int ret;
+
+ ret = res_counter_charge(&mem->res, csize, &fail_res);
+
+ if (likely(!ret)) {
+ if (!do_swap_account)
+ return CHARGE_OK;
+ ret = res_counter_charge(&mem->memsw, csize, &fail_res);
+ if (likely(!ret))
+ return CHARGE_OK;
+
+ res_counter_uncharge(&mem->res, csize);
+ mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
+ flags |= MEM_CGROUP_RECLAIM_NOSWAP;
+ } else
+ mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
+ /*
+ * nr_pages can be either a huge page (HPAGE_PMD_NR), a batch
+ * of regular pages (CHARGE_BATCH), or a single regular page (1).
+ *
+ * Never reclaim on behalf of optional batching, retry with a
+ * single page instead.
+ */
+ if (nr_pages == CHARGE_BATCH)
+ return CHARGE_RETRY;
+
+ if (!(gfp_mask & __GFP_WAIT))
+ return CHARGE_WOULDBLOCK;
+
+ ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL,
+ gfp_mask, flags);
+ if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
+ return CHARGE_RETRY;
+ /*
+ * Even though the limit is exceeded at this point, reclaim
+ * may have been able to free some pages. Retry the charge
+ * before killing the task.
+ *
+ * Only for regular pages, though: huge pages are rather
+ * unlikely to succeed so close to the limit, and we fall back
+ * to regular pages anyway in case of failure.
+ */
+ if (nr_pages == 1 && ret)
+ return CHARGE_RETRY;
+
+ /*
+ * At task move, charge accounts can be doubly counted. So, it's
+ * better to wait until the end of task_move if something is going on.
+ */
+ if (mem_cgroup_wait_acct_move(mem_over_limit))
+ return CHARGE_RETRY;
+
+ /* If we don't need to call oom-killer at el, return immediately */
+ if (!oom_check)
+ return CHARGE_NOMEM;
+ /* check OOM */
+ if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask))
+ return CHARGE_OOM_DIE;
+
+ return CHARGE_RETRY;
+}
+
/*
* Unlike exported interface, "oom" parameter is added. if oom==true,
* 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,
+ unsigned int nr_pages,
+ struct mem_cgroup **memcg,
+ bool oom)
{
- struct mem_cgroup *mem, *mem_over_limit;
- int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
- struct res_counter *fail_res;
- int csize = CHARGE_SIZE;
+ unsigned int batch = max(CHARGE_BATCH, nr_pages);
+ int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
+ struct mem_cgroup *mem = NULL;
+ int ret;
/*
* Unlike gloval-vm's OOM-kill, we're not in memory shortage
* thread group leader migrates. It's possible that mm is not
* set, if so charge the init_mm (happens for pagecache usage).
*/
- mem = *memcg;
- if (likely(!mem)) {
- mem = try_get_mem_cgroup_from_mm(mm);
- *memcg = mem;
- } else {
+ if (!*memcg && !mm)
+ goto bypass;
+again:
+ if (*memcg) { /* css should be a valid one */
+ mem = *memcg;
+ VM_BUG_ON(css_is_removed(&mem->css));
+ if (mem_cgroup_is_root(mem))
+ goto done;
+ if (nr_pages == 1 && consume_stock(mem))
+ goto done;
css_get(&mem->css);
- }
- if (unlikely(!mem))
- return 0;
-
- VM_BUG_ON(css_is_removed(&mem->css));
- if (mem_cgroup_is_root(mem))
- goto done;
-
- while (1) {
- int ret = 0;
- unsigned long flags = 0;
+ } else {
+ struct task_struct *p;
- if (consume_stock(mem))
+ rcu_read_lock();
+ p = rcu_dereference(mm->owner);
+ /*
+ * Because we don't have task_lock(), "p" can exit.
+ * In that case, "mem" can point to root or p can be NULL with
+ * race with swapoff. Then, we have small risk of mis-accouning.
+ * But such kind of mis-account by race always happens because
+ * we don't have cgroup_mutex(). It's overkill and we allo that
+ * small race, here.
+ * (*) swapoff at el will charge against mm-struct not against
+ * task-struct. So, mm->owner can be NULL.
+ */
+ mem = mem_cgroup_from_task(p);
+ if (!mem || mem_cgroup_is_root(mem)) {
+ rcu_read_unlock();
goto done;
-
- ret = res_counter_charge(&mem->res, csize, &fail_res);
- if (likely(!ret)) {
- if (!do_swap_account)
- break;
- ret = res_counter_charge(&mem->memsw, csize, &fail_res);
- if (likely(!ret))
- break;
- /* mem+swap counter fails */
- res_counter_uncharge(&mem->res, csize);
- 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);
-
- /* reduce request size and retry */
- if (csize > PAGE_SIZE) {
- csize = PAGE_SIZE;
- continue;
}
- if (!(gfp_mask & __GFP_WAIT))
- goto nomem;
+ if (nr_pages == 1 && consume_stock(mem)) {
+ /*
+ * It seems dagerous to access memcg without css_get().
+ * But considering how consume_stok works, it's not
+ * necessary. If consume_stock success, some charges
+ * from this memcg are cached on this cpu. So, we
+ * don't need to call css_get()/css_tryget() before
+ * calling consume_stock().
+ */
+ rcu_read_unlock();
+ goto done;
+ }
+ /* after here, we may be blocked. we need to get refcnt */
+ if (!css_tryget(&mem->css)) {
+ rcu_read_unlock();
+ goto again;
+ }
+ rcu_read_unlock();
+ }
- ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL,
- gfp_mask, flags);
- if (ret)
- continue;
+ do {
+ bool oom_check;
- /*
- * try_to_free_mem_cgroup_pages() might not give us a full
- * picture of reclaim. Some pages are reclaimed and might be
- * moved to swap cache or just unmapped from the cgroup.
- * Check the limit again to see if the reclaim reduced the
- * current usage of the cgroup before giving up
- *
- */
- if (mem_cgroup_check_under_limit(mem_over_limit))
- continue;
+ /* If killed, bypass charge */
+ if (fatal_signal_pending(current)) {
+ css_put(&mem->css);
+ goto bypass;
+ }
- /* try to avoid oom while someone is moving charge */
- if (mc.moving_task && current != mc.moving_task) {
- struct mem_cgroup *from, *to;
- bool do_continue = false;
- /*
- * There is a small race that "from" or "to" can be
- * freed by rmdir, so we use css_tryget().
- */
- from = mc.from;
- to = mc.to;
- if (from && css_tryget(&from->css)) {
- if (mem_over_limit->use_hierarchy)
- do_continue = css_is_ancestor(
- &from->css,
- &mem_over_limit->css);
- else
- do_continue = (from == mem_over_limit);
- css_put(&from->css);
- }
- if (!do_continue && to && css_tryget(&to->css)) {
- if (mem_over_limit->use_hierarchy)
- do_continue = css_is_ancestor(
- &to->css,
- &mem_over_limit->css);
- else
- do_continue = (to == mem_over_limit);
- css_put(&to->css);
- }
- if (do_continue) {
- DEFINE_WAIT(wait);
- prepare_to_wait(&mc.waitq, &wait,
- TASK_INTERRUPTIBLE);
- /* moving charge context might have finished. */
- if (mc.moving_task)
- schedule();
- finish_wait(&mc.waitq, &wait);
- continue;
- }
+ oom_check = false;
+ if (oom && !nr_oom_retries) {
+ oom_check = true;
+ nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
}
- if (!nr_retries--) {
- if (!oom)
+ ret = mem_cgroup_do_charge(mem, gfp_mask, batch, oom_check);
+ switch (ret) {
+ case CHARGE_OK:
+ break;
+ case CHARGE_RETRY: /* not in OOM situation but retry */
+ batch = nr_pages;
+ css_put(&mem->css);
+ mem = NULL;
+ goto again;
+ case CHARGE_WOULDBLOCK: /* !__GFP_WAIT */
+ css_put(&mem->css);
+ goto nomem;
+ case CHARGE_NOMEM: /* OOM routine works */
+ if (!oom) {
+ css_put(&mem->css);
goto nomem;
- if (mem_cgroup_handle_oom(mem_over_limit, gfp_mask)) {
- nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
- continue;
}
- /* When we reach here, current task is dying .*/
+ /* If oom, we never return -ENOMEM */
+ nr_oom_retries--;
+ break;
+ case CHARGE_OOM_DIE: /* Killed by OOM Killer */
css_put(&mem->css);
goto bypass;
}
- }
- if (csize > PAGE_SIZE)
- refill_stock(mem, csize - PAGE_SIZE);
+ } while (ret != CHARGE_OK);
+
+ if (batch > nr_pages)
+ refill_stock(mem, batch - nr_pages);
+ css_put(&mem->css);
done:
+ *memcg = mem;
return 0;
nomem:
- css_put(&mem->css);
+ *memcg = NULL;
return -ENOMEM;
bypass:
*memcg = NULL;
* gotten by try_charge().
*/
static void __mem_cgroup_cancel_charge(struct mem_cgroup *mem,
- unsigned long count)
+ unsigned int nr_pages)
{
if (!mem_cgroup_is_root(mem)) {
- res_counter_uncharge(&mem->res, PAGE_SIZE * count);
+ unsigned long bytes = nr_pages * PAGE_SIZE;
+
+ res_counter_uncharge(&mem->res, bytes);
if (do_swap_account)
- res_counter_uncharge(&mem->memsw, PAGE_SIZE * count);
- VM_BUG_ON(test_bit(CSS_ROOT, &mem->css.flags));
- WARN_ON_ONCE(count > INT_MAX);
- __css_put(&mem->css, (int)count);
+ res_counter_uncharge(&mem->memsw, bytes);
}
- /* we don't need css_put for root */
-}
-
-static void mem_cgroup_cancel_charge(struct mem_cgroup *mem)
-{
- __mem_cgroup_cancel_charge(mem, 1);
}
/*
return mem;
}
-/*
- * commit a charge got by __mem_cgroup_try_charge() and makes page_cgroup to be
- * USED state. If already USED, uncharge and return.
- */
-
static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
- struct page_cgroup *pc,
- enum charge_type ctype)
+ struct page *page,
+ unsigned int nr_pages,
+ struct page_cgroup *pc,
+ enum charge_type ctype)
{
- /* try_charge() can return NULL to *memcg, taking care of it. */
- if (!mem)
- return;
-
lock_page_cgroup(pc);
if (unlikely(PageCgroupUsed(pc))) {
unlock_page_cgroup(pc);
- mem_cgroup_cancel_charge(mem);
+ __mem_cgroup_cancel_charge(mem, nr_pages);
return;
}
-
+ /*
+ * we don't need page_cgroup_lock about tail pages, becase they are not
+ * accessed by any other context at this point.
+ */
pc->mem_cgroup = mem;
/*
* We access a page_cgroup asynchronously without lock_page_cgroup().
break;
}
- mem_cgroup_charge_statistics(mem, pc, true);
-
+ mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), nr_pages);
unlock_page_cgroup(pc);
/*
* "charge_statistics" updated event counter. Then, check it.
* Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
* if they exceeds softlimit.
*/
- memcg_check_events(mem, pc->page);
+ memcg_check_events(mem, page);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MOVE_LOCK) |\
+ (1 << PCG_ACCT_LRU) | (1 << PCG_MIGRATION))
+/*
+ * Because tail pages are not marked as "used", set it. We're under
+ * zone->lru_lock, 'splitting on pmd' and compund_lock.
+ */
+void mem_cgroup_split_huge_fixup(struct page *head, struct page *tail)
+{
+ struct page_cgroup *head_pc = lookup_page_cgroup(head);
+ struct page_cgroup *tail_pc = lookup_page_cgroup(tail);
+ unsigned long flags;
+
+ if (mem_cgroup_disabled())
+ return;
+ /*
+ * We have no races with charge/uncharge but will have races with
+ * page state accounting.
+ */
+ move_lock_page_cgroup(head_pc, &flags);
+
+ tail_pc->mem_cgroup = head_pc->mem_cgroup;
+ smp_wmb(); /* see __commit_charge() */
+ if (PageCgroupAcctLRU(head_pc)) {
+ enum lru_list lru;
+ struct mem_cgroup_per_zone *mz;
+
+ /*
+ * LRU flags cannot be copied because we need to add tail
+ *.page to LRU by generic call and our hook will be called.
+ * We hold lru_lock, then, reduce counter directly.
+ */
+ lru = page_lru(head);
+ mz = page_cgroup_zoneinfo(head_pc->mem_cgroup, head);
+ MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+ }
+ tail_pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
+ move_unlock_page_cgroup(head_pc, &flags);
}
+#endif
/**
- * __mem_cgroup_move_account - move account of the page
+ * mem_cgroup_move_account - move account of the page
+ * @page: the page
+ * @nr_pages: number of regular pages (>1 for huge pages)
* @pc: page_cgroup of the page.
* @from: mem_cgroup which the page is moved from.
* @to: mem_cgroup which the page is moved to. @from != @to.
*
* The caller must confirm following.
* - page is not on LRU (isolate_page() is useful.)
- * - the pc is locked, used, and ->mem_cgroup points to @from.
+ * - compound_lock is held when nr_pages > 1
*
* This function doesn't do "charge" nor css_get to new cgroup. It should be
- * done by a caller(__mem_cgroup_try_charge would be usefull). If @uncharge is
+ * done by a caller(__mem_cgroup_try_charge would be useful). If @uncharge is
* true, this function does "uncharge" from old cgroup, but it doesn't if
* @uncharge is false, so a caller should do "uncharge".
*/
-
-static void __mem_cgroup_move_account(struct page_cgroup *pc,
- struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge)
+static int mem_cgroup_move_account(struct page *page,
+ unsigned int nr_pages,
+ struct page_cgroup *pc,
+ struct mem_cgroup *from,
+ struct mem_cgroup *to,
+ bool uncharge)
{
+ unsigned long flags;
+ int ret;
+
VM_BUG_ON(from == to);
- VM_BUG_ON(PageLRU(pc->page));
- VM_BUG_ON(!PageCgroupLocked(pc));
- VM_BUG_ON(!PageCgroupUsed(pc));
- VM_BUG_ON(pc->mem_cgroup != from);
+ VM_BUG_ON(PageLRU(page));
+ /*
+ * The page is isolated from LRU. So, collapse function
+ * will not handle this page. But page splitting can happen.
+ * Do this check under compound_page_lock(). The caller should
+ * hold it.
+ */
+ ret = -EBUSY;
+ if (nr_pages > 1 && !PageTransHuge(page))
+ goto out;
+
+ lock_page_cgroup(pc);
+
+ ret = -EINVAL;
+ if (!PageCgroupUsed(pc) || pc->mem_cgroup != from)
+ goto unlock;
+
+ move_lock_page_cgroup(pc, &flags);
if (PageCgroupFileMapped(pc)) {
/* Update mapped_file data for mem_cgroup */
__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
preempt_enable();
}
- mem_cgroup_charge_statistics(from, pc, false);
+ mem_cgroup_charge_statistics(from, PageCgroupCache(pc), -nr_pages);
if (uncharge)
/* This is not "cancel", but cancel_charge does all we need. */
- mem_cgroup_cancel_charge(from);
+ __mem_cgroup_cancel_charge(from, nr_pages);
/* caller should have done css_get */
pc->mem_cgroup = to;
- mem_cgroup_charge_statistics(to, pc, true);
+ mem_cgroup_charge_statistics(to, PageCgroupCache(pc), nr_pages);
/*
* 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 move charge, so it's
- * garanteed that "to" is never removed. So, we don't check rmdir
+ * guaranteed that "to" is never removed. So, we don't check rmdir
* status here.
*/
-}
-
-/*
- * check whether the @pc is valid for moving account and call
- * __mem_cgroup_move_account()
- */
-static int mem_cgroup_move_account(struct page_cgroup *pc,
- struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge)
-{
- int ret = -EINVAL;
- lock_page_cgroup(pc);
- if (PageCgroupUsed(pc) && pc->mem_cgroup == from) {
- __mem_cgroup_move_account(pc, from, to, uncharge);
- ret = 0;
- }
+ move_unlock_page_cgroup(pc, &flags);
+ ret = 0;
+unlock:
unlock_page_cgroup(pc);
/*
* check events
*/
- memcg_check_events(to, pc->page);
- memcg_check_events(from, pc->page);
+ memcg_check_events(to, page);
+ memcg_check_events(from, page);
+out:
return ret;
}
* move charges to its parent.
*/
-static int mem_cgroup_move_parent(struct page_cgroup *pc,
+static int mem_cgroup_move_parent(struct page *page,
+ 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;
+ unsigned int nr_pages;
+ unsigned long uninitialized_var(flags);
int ret;
/* Is ROOT ? */
if (isolate_lru_page(page))
goto put;
+ nr_pages = hpage_nr_pages(page);
+
parent = mem_cgroup_from_cont(pcg);
- ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false);
+ ret = __mem_cgroup_try_charge(NULL, gfp_mask, nr_pages, &parent, false);
if (ret || !parent)
goto put_back;
- ret = mem_cgroup_move_account(pc, child, parent, true);
+ if (nr_pages > 1)
+ flags = compound_lock_irqsave(page);
+
+ ret = mem_cgroup_move_account(page, nr_pages, pc, child, parent, true);
if (ret)
- mem_cgroup_cancel_charge(parent);
+ __mem_cgroup_cancel_charge(parent, nr_pages);
+
+ if (nr_pages > 1)
+ compound_unlock_irqrestore(page, flags);
put_back:
putback_lru_page(page);
put:
* < 0 if the cgroup is over its limit
*/
static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask, enum charge_type ctype,
- struct mem_cgroup *memcg)
+ gfp_t gfp_mask, enum charge_type ctype)
{
- struct mem_cgroup *mem;
+ struct mem_cgroup *mem = NULL;
+ unsigned int nr_pages = 1;
struct page_cgroup *pc;
+ bool oom = true;
int ret;
+ if (PageTransHuge(page)) {
+ nr_pages <<= compound_order(page);
+ VM_BUG_ON(!PageTransHuge(page));
+ /*
+ * Never OOM-kill a process for a huge page. The
+ * fault handler will fall back to regular pages.
+ */
+ oom = false;
+ }
+
pc = lookup_page_cgroup(page);
- /* can happen at boot */
- if (unlikely(!pc))
- return 0;
- prefetchw(pc);
+ BUG_ON(!pc); /* XXX: remove this and move pc lookup into commit */
- mem = memcg;
- ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true);
+ ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &mem, oom);
if (ret || !mem)
return ret;
- __mem_cgroup_commit_charge(mem, pc, ctype);
+ __mem_cgroup_commit_charge(mem, page, nr_pages, pc, ctype);
return 0;
}
{
if (mem_cgroup_disabled())
return 0;
- if (PageCompound(page))
- return 0;
/*
* If already mapped, we don't have to account.
* If page cache, page->mapping has address_space.
if (unlikely(!mm))
mm = &init_mm;
return mem_cgroup_charge_common(page, mm, gfp_mask,
- MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
+ MEM_CGROUP_CHARGE_TYPE_MAPPED);
}
static void
__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
enum charge_type ctype);
+static void
+__mem_cgroup_commit_charge_lrucare(struct page *page, struct mem_cgroup *mem,
+ enum charge_type ctype)
+{
+ struct page_cgroup *pc = lookup_page_cgroup(page);
+ /*
+ * In some case, SwapCache, FUSE(splice_buf->radixtree), the page
+ * is already on LRU. It means the page may on some other page_cgroup's
+ * LRU. Take care of it.
+ */
+ mem_cgroup_lru_del_before_commit(page);
+ __mem_cgroup_commit_charge(mem, page, 1, pc, ctype);
+ mem_cgroup_lru_add_after_commit(page);
+ return;
+}
+
int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask)
{
if (!(gfp_mask & __GFP_WAIT)) {
struct page_cgroup *pc;
-
pc = lookup_page_cgroup(page);
if (!pc)
return 0;
unlock_page_cgroup(pc);
}
- if (unlikely(!mm && !mem))
+ if (unlikely(!mm))
mm = &init_mm;
- if (page_is_file_cache(page))
- return mem_cgroup_charge_common(page, mm, gfp_mask,
- MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
+ if (page_is_file_cache(page)) {
+ ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, &mem, true);
+ if (ret || !mem)
+ return ret;
+ /*
+ * FUSE reuses pages without going through the final
+ * put that would remove them from the LRU list, make
+ * sure that they get relinked properly.
+ */
+ __mem_cgroup_commit_charge_lrucare(page, mem,
+ MEM_CGROUP_CHARGE_TYPE_CACHE);
+ return ret;
+ }
/* shmem */
if (PageSwapCache(page)) {
ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem);
MEM_CGROUP_CHARGE_TYPE_SHMEM);
} else
ret = mem_cgroup_charge_common(page, mm, gfp_mask,
- MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
+ MEM_CGROUP_CHARGE_TYPE_SHMEM);
return ret;
}
struct mem_cgroup *mem;
int ret;
+ *ptr = NULL;
+
if (mem_cgroup_disabled())
return 0;
if (!mem)
goto charge_cur_mm;
*ptr = mem;
- ret = __mem_cgroup_try_charge(NULL, mask, ptr, true);
- /* drop extra refcnt from tryget */
+ ret = __mem_cgroup_try_charge(NULL, mask, 1, ptr, true);
css_put(&mem->css);
return ret;
charge_cur_mm:
if (unlikely(!mm))
mm = &init_mm;
- return __mem_cgroup_try_charge(mm, mask, ptr, true);
+ return __mem_cgroup_try_charge(mm, mask, 1, ptr, true);
}
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_disabled())
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, ctype);
- mem_cgroup_lru_add_after_commit_swapcache(page);
+
+ __mem_cgroup_commit_charge_lrucare(page, ptr, ctype);
/*
* Now swap is on-memory. This means this page may be
* counted both as mem and swap....double count.
return;
if (!mem)
return;
- mem_cgroup_cancel_charge(mem);
+ __mem_cgroup_cancel_charge(mem, 1);
}
-static void
-__do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype)
+static void mem_cgroup_do_uncharge(struct mem_cgroup *mem,
+ unsigned int nr_pages,
+ const enum charge_type ctype)
{
struct memcg_batch_info *batch = NULL;
bool uncharge_memsw = true;
+
/* If swapout, usage of swap doesn't decrease */
if (!do_swap_account || ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
uncharge_memsw = false;
batch->memcg = mem;
/*
* do_batch > 0 when unmapping pages or inode invalidate/truncate.
- * In those cases, all pages freed continously can be expected to be in
+ * In those cases, all pages freed continuously can be expected to be in
* the same cgroup and we have chance to coalesce uncharges.
* But we do uncharge one by one if this is killed by OOM(TIF_MEMDIE)
* because we want to do uncharge as soon as possible.
if (!batch->do_batch || test_thread_flag(TIF_MEMDIE))
goto direct_uncharge;
+ if (nr_pages > 1)
+ goto direct_uncharge;
+
/*
* In typical case, batch->memcg == mem. This means we can
* merge a series of uncharges to an uncharge of res_counter.
if (batch->memcg != mem)
goto direct_uncharge;
/* remember freed charge and uncharge it later */
- batch->bytes += PAGE_SIZE;
+ batch->nr_pages++;
if (uncharge_memsw)
- batch->memsw_bytes += PAGE_SIZE;
+ batch->memsw_nr_pages++;
return;
direct_uncharge:
- res_counter_uncharge(&mem->res, PAGE_SIZE);
+ res_counter_uncharge(&mem->res, nr_pages * PAGE_SIZE);
if (uncharge_memsw)
- res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+ res_counter_uncharge(&mem->memsw, nr_pages * PAGE_SIZE);
if (unlikely(batch->memcg != mem))
memcg_oom_recover(mem);
return;
static struct mem_cgroup *
__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
{
- struct page_cgroup *pc;
struct mem_cgroup *mem = NULL;
- struct mem_cgroup_per_zone *mz;
+ unsigned int nr_pages = 1;
+ struct page_cgroup *pc;
if (mem_cgroup_disabled())
return NULL;
if (PageSwapCache(page))
return NULL;
+ if (PageTransHuge(page)) {
+ nr_pages <<= compound_order(page);
+ VM_BUG_ON(!PageTransHuge(page));
+ }
/*
* Check if our page_cgroup is valid
*/
break;
}
- if (!mem_cgroup_is_root(mem))
- __do_uncharge(mem, ctype);
- if (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
- mem_cgroup_swap_statistics(mem, true);
- mem_cgroup_charge_statistics(mem, pc, false);
+ mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), -nr_pages);
ClearPageCgroupUsed(pc);
/*
* special functions.
*/
- mz = page_cgroup_zoneinfo(pc);
unlock_page_cgroup(pc);
-
+ /*
+ * even after unlock, we have mem->res.usage here and this memcg
+ * will never be freed.
+ */
memcg_check_events(mem, page);
- /* at swapout, this memcg will be accessed to record to swap */
- if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
- css_put(&mem->css);
+ if (do_swap_account && ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) {
+ mem_cgroup_swap_statistics(mem, true);
+ mem_cgroup_get(mem);
+ }
+ if (!mem_cgroup_is_root(mem))
+ mem_cgroup_do_uncharge(mem, nr_pages, ctype);
return mem;
/* We can do nest. */
if (current->memcg_batch.do_batch == 1) {
current->memcg_batch.memcg = NULL;
- current->memcg_batch.bytes = 0;
- current->memcg_batch.memsw_bytes = 0;
+ current->memcg_batch.nr_pages = 0;
+ current->memcg_batch.memsw_nr_pages = 0;
}
}
* This "batch->memcg" is valid without any css_get/put etc...
* bacause we hide charges behind us.
*/
- if (batch->bytes)
- res_counter_uncharge(&batch->memcg->res, batch->bytes);
- if (batch->memsw_bytes)
- res_counter_uncharge(&batch->memcg->memsw, batch->memsw_bytes);
+ if (batch->nr_pages)
+ res_counter_uncharge(&batch->memcg->res,
+ batch->nr_pages * PAGE_SIZE);
+ if (batch->memsw_nr_pages)
+ res_counter_uncharge(&batch->memcg->memsw,
+ batch->memsw_nr_pages * PAGE_SIZE);
memcg_oom_recover(batch->memcg);
/* forget this pointer (for sanity check) */
batch->memcg = NULL;
memcg = __mem_cgroup_uncharge_common(page, ctype);
- /* record memcg information */
- if (do_swap_account && swapout && memcg) {
+ /*
+ * record memcg information, if swapout && memcg != NULL,
+ * mem_cgroup_get() was called in uncharge().
+ */
+ 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
*/
if (!mem_cgroup_is_root(to))
res_counter_uncharge(&to->res, PAGE_SIZE);
- css_put(&to->css);
}
return 0;
}
* page belongs to.
*/
int mem_cgroup_prepare_migration(struct page *page,
- struct page *newpage, struct mem_cgroup **ptr)
+ struct page *newpage, struct mem_cgroup **ptr, gfp_t gfp_mask)
{
- struct page_cgroup *pc;
struct mem_cgroup *mem = NULL;
+ struct page_cgroup *pc;
enum charge_type ctype;
int ret = 0;
+ *ptr = NULL;
+
+ VM_BUG_ON(PageTransHuge(page));
if (mem_cgroup_disabled())
return 0;
return 0;
*ptr = mem;
- ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false);
+ ret = __mem_cgroup_try_charge(NULL, gfp_mask, 1, ptr, false);
css_put(&mem->css);/* drop extra refcnt */
if (ret || *ptr == NULL) {
if (PageAnon(page)) {
ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
else
ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
- __mem_cgroup_commit_charge(mem, pc, ctype);
+ __mem_cgroup_commit_charge(mem, page, 1, pc, ctype);
return ret;
}
/* remove redundant charge if migration failed*/
void mem_cgroup_end_migration(struct mem_cgroup *mem,
- struct page *oldpage, struct page *newpage)
+ struct page *oldpage, struct page *newpage, bool migration_ok)
{
struct page *used, *unused;
struct page_cgroup *pc;
return;
/* blocks rmdir() */
cgroup_exclude_rmdir(&mem->css);
- /* at migration success, oldpage->mapping is NULL. */
- if (oldpage->mapping) {
+ if (!migration_ok) {
used = oldpage;
unused = newpage;
} else {
ClearPageCgroupMigration(pc);
unlock_page_cgroup(pc);
- if (unused != oldpage)
- pc = lookup_page_cgroup(unused);
__mem_cgroup_uncharge_common(unused, MEM_CGROUP_CHARGE_TYPE_FORCE);
- pc = lookup_page_cgroup(used);
/*
* If a page is a file cache, radix-tree replacement is very atomic
* and we can skip this check. When it was an Anon page, its mapcount
struct mm_struct *mm,
gfp_t gfp_mask)
{
- struct mem_cgroup *mem = NULL;
+ struct mem_cgroup *mem;
int ret;
if (mem_cgroup_disabled())
return ret;
}
+#ifdef CONFIG_DEBUG_VM
+static struct page_cgroup *lookup_page_cgroup_used(struct page *page)
+{
+ struct page_cgroup *pc;
+
+ pc = lookup_page_cgroup(page);
+ if (likely(pc) && PageCgroupUsed(pc))
+ return pc;
+ return NULL;
+}
+
+bool mem_cgroup_bad_page_check(struct page *page)
+{
+ if (mem_cgroup_disabled())
+ return false;
+
+ return lookup_page_cgroup_used(page) != NULL;
+}
+
+void mem_cgroup_print_bad_page(struct page *page)
+{
+ struct page_cgroup *pc;
+
+ pc = lookup_page_cgroup_used(page);
+ if (pc) {
+ int ret = -1;
+ char *path;
+
+ printk(KERN_ALERT "pc:%p pc->flags:%lx pc->mem_cgroup:%p",
+ pc, pc->flags, pc->mem_cgroup);
+
+ path = kmalloc(PATH_MAX, GFP_KERNEL);
+ if (path) {
+ rcu_read_lock();
+ ret = cgroup_path(pc->mem_cgroup->css.cgroup,
+ path, PATH_MAX);
+ rcu_read_unlock();
+ }
+
+ printk(KERN_CONT "(%s)\n",
+ (ret < 0) ? "cannot get the path" : path);
+ kfree(path);
+ }
+}
+#endif
+
static DEFINE_MUTEX(set_limit_mutex);
static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
}
unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
- gfp_t gfp_mask, int nid,
- int zid)
+ gfp_t gfp_mask)
{
unsigned long nr_reclaimed = 0;
struct mem_cgroup_per_zone *mz, *next_mz = NULL;
if (order > 0)
return 0;
- mctz = soft_limit_tree_node_zone(nid, zid);
+ mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone));
/*
* This loop can run a while, specially if mem_cgroup's continuously
* keep exceeding their soft limit and putting the system under
loop += 256;
busy = NULL;
while (loop--) {
+ struct page *page;
+
ret = 0;
spin_lock_irqsave(&zone->lru_lock, flags);
if (list_empty(list)) {
}
spin_unlock_irqrestore(&zone->lru_lock, flags);
- ret = mem_cgroup_move_parent(pc, mem, GFP_KERNEL);
+ page = lookup_cgroup_page(pc);
+
+ ret = mem_cgroup_move_parent(page, pc, mem, GFP_KERNEL);
if (ret == -ENOMEM)
break;
lru_add_drain_all();
drain_all_stock_sync();
ret = 0;
+ mem_cgroup_start_move(mem);
for_each_node_state(node, N_HIGH_MEMORY) {
for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
enum lru_list l;
if (ret)
break;
}
+ mem_cgroup_end_move(mem);
memcg_oom_recover(mem);
/* it seems parent cgroup doesn't have enough mem */
if (ret == -ENOMEM)
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)
+static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *mem,
+ enum mem_cgroup_stat_index idx)
{
- struct mem_cgroup_idx_data *d = data;
- d->val += mem_cgroup_read_stat(mem, d->idx);
- return 0;
-}
+ struct mem_cgroup *iter;
+ long val = 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;
+ /* Per-cpu values can be negative, use a signed accumulator */
+ for_each_mem_cgroup_tree(iter, mem)
+ val += mem_cgroup_read_stat(iter, idx);
+
+ if (val < 0) /* race ? */
+ val = 0;
+ return val;
}
static inline u64 mem_cgroup_usage(struct mem_cgroup *mem, bool swap)
{
- u64 idx_val, val;
+ u64 val;
if (!mem_cgroup_is_root(mem)) {
if (!swap)
return res_counter_read_u64(&mem->memsw, RES_USAGE);
}
- 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 = mem_cgroup_recursive_stat(mem, MEM_CGROUP_STAT_CACHE);
+ val += mem_cgroup_recursive_stat(mem, MEM_CGROUP_STAT_RSS);
- if (swap) {
- mem_cgroup_get_recursive_idx_stat(mem,
- MEM_CGROUP_STAT_SWAPOUT, &idx_val);
- val += idx_val;
- }
+ if (swap)
+ val += mem_cgroup_recursive_stat(mem, MEM_CGROUP_STAT_SWAPOUT);
return val << PAGE_SHIFT;
}
};
-static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data)
+static void
+mem_cgroup_get_local_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
{
- struct mcs_total_stat *s = data;
s64 val;
/* per cpu stat */
s->stat[MCS_RSS] += val * PAGE_SIZE;
val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_FILE_MAPPED);
s->stat[MCS_FILE_MAPPED] += val * PAGE_SIZE;
- val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_PGPGIN_COUNT);
+ val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGPGIN);
s->stat[MCS_PGPGIN] += val;
- val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_PGPGOUT_COUNT);
+ val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGPGOUT);
s->stat[MCS_PGPGOUT] += val;
if (do_swap_account) {
val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_SWAPOUT);
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);
+ struct mem_cgroup *iter;
+
+ for_each_mem_cgroup_tree(iter, mem)
+ mem_cgroup_get_local_stat(iter, s);
}
static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
return -EINVAL;
}
- spin_lock(&memcg->reclaim_param_lock);
memcg->swappiness = val;
- spin_unlock(&memcg->reclaim_param_lock);
cgroup_unlock();
rcu_read_lock();
if (!swap)
- t = rcu_dereference(memcg->thresholds);
+ t = rcu_dereference(memcg->thresholds.primary);
else
- t = rcu_dereference(memcg->memsw_thresholds);
+ t = rcu_dereference(memcg->memsw_thresholds.primary);
if (!t)
goto unlock;
static void mem_cgroup_threshold(struct mem_cgroup *memcg)
{
- __mem_cgroup_threshold(memcg, false);
- if (do_swap_account)
- __mem_cgroup_threshold(memcg, true);
+ while (memcg) {
+ __mem_cgroup_threshold(memcg, false);
+ if (do_swap_account)
+ __mem_cgroup_threshold(memcg, true);
+
+ memcg = parent_mem_cgroup(memcg);
+ }
}
static int compare_thresholds(const void *a, const void *b)
return _a->threshold - _b->threshold;
}
-static int mem_cgroup_oom_notify_cb(struct mem_cgroup *mem, void *data)
+static int mem_cgroup_oom_notify_cb(struct mem_cgroup *mem)
{
struct mem_cgroup_eventfd_list *ev;
static void mem_cgroup_oom_notify(struct mem_cgroup *mem)
{
- mem_cgroup_walk_tree(mem, NULL, mem_cgroup_oom_notify_cb);
+ struct mem_cgroup *iter;
+
+ for_each_mem_cgroup_tree(iter, mem)
+ mem_cgroup_oom_notify_cb(iter);
}
static int mem_cgroup_usage_register_event(struct cgroup *cgrp,
struct cftype *cft, struct eventfd_ctx *eventfd, const char *args)
{
struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
- struct mem_cgroup_threshold_ary *thresholds, *thresholds_new;
+ struct mem_cgroup_thresholds *thresholds;
+ struct mem_cgroup_threshold_ary *new;
int type = MEMFILE_TYPE(cft->private);
u64 threshold, usage;
- int size;
- int i, ret;
+ int i, size, ret;
ret = res_counter_memparse_write_strategy(args, &threshold);
if (ret)
return ret;
mutex_lock(&memcg->thresholds_lock);
+
if (type == _MEM)
- thresholds = memcg->thresholds;
+ thresholds = &memcg->thresholds;
else if (type == _MEMSWAP)
- thresholds = memcg->memsw_thresholds;
+ thresholds = &memcg->memsw_thresholds;
else
BUG();
usage = mem_cgroup_usage(memcg, type == _MEMSWAP);
/* Check if a threshold crossed before adding a new one */
- if (thresholds)
+ if (thresholds->primary)
__mem_cgroup_threshold(memcg, type == _MEMSWAP);
- if (thresholds)
- size = thresholds->size + 1;
- else
- size = 1;
+ size = thresholds->primary ? thresholds->primary->size + 1 : 1;
/* Allocate memory for new array of thresholds */
- thresholds_new = kmalloc(sizeof(*thresholds_new) +
- size * sizeof(struct mem_cgroup_threshold),
+ new = kmalloc(sizeof(*new) + size * sizeof(struct mem_cgroup_threshold),
GFP_KERNEL);
- if (!thresholds_new) {
+ if (!new) {
ret = -ENOMEM;
goto unlock;
}
- thresholds_new->size = size;
+ new->size = size;
/* Copy thresholds (if any) to new array */
- if (thresholds)
- memcpy(thresholds_new->entries, thresholds->entries,
- thresholds->size *
+ if (thresholds->primary) {
+ memcpy(new->entries, thresholds->primary->entries, (size - 1) *
sizeof(struct mem_cgroup_threshold));
+ }
+
/* Add new threshold */
- thresholds_new->entries[size - 1].eventfd = eventfd;
- thresholds_new->entries[size - 1].threshold = threshold;
+ new->entries[size - 1].eventfd = eventfd;
+ new->entries[size - 1].threshold = threshold;
/* Sort thresholds. Registering of new threshold isn't time-critical */
- sort(thresholds_new->entries, size,
- sizeof(struct mem_cgroup_threshold),
+ sort(new->entries, size, sizeof(struct mem_cgroup_threshold),
compare_thresholds, NULL);
/* Find current threshold */
- thresholds_new->current_threshold = -1;
+ new->current_threshold = -1;
for (i = 0; i < size; i++) {
- if (thresholds_new->entries[i].threshold < usage) {
+ if (new->entries[i].threshold < usage) {
/*
- * thresholds_new->current_threshold will not be used
- * until rcu_assign_pointer(), so it's safe to increment
+ * new->current_threshold will not be used until
+ * rcu_assign_pointer(), so it's safe to increment
* it here.
*/
- ++thresholds_new->current_threshold;
+ ++new->current_threshold;
}
}
- if (type == _MEM)
- rcu_assign_pointer(memcg->thresholds, thresholds_new);
- else
- rcu_assign_pointer(memcg->memsw_thresholds, thresholds_new);
+ /* Free old spare buffer and save old primary buffer as spare */
+ kfree(thresholds->spare);
+ thresholds->spare = thresholds->primary;
- /* To be sure that nobody uses thresholds before freeing it */
+ rcu_assign_pointer(thresholds->primary, new);
+
+ /* To be sure that nobody uses thresholds */
synchronize_rcu();
- kfree(thresholds);
unlock:
mutex_unlock(&memcg->thresholds_lock);
return ret;
}
-static int mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
+static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
struct cftype *cft, struct eventfd_ctx *eventfd)
{
struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
- struct mem_cgroup_threshold_ary *thresholds, *thresholds_new;
+ struct mem_cgroup_thresholds *thresholds;
+ struct mem_cgroup_threshold_ary *new;
int type = MEMFILE_TYPE(cft->private);
u64 usage;
- int size = 0;
- int i, j, ret = 0;
+ int i, j, size;
mutex_lock(&memcg->thresholds_lock);
if (type == _MEM)
- thresholds = memcg->thresholds;
+ thresholds = &memcg->thresholds;
else if (type == _MEMSWAP)
- thresholds = memcg->memsw_thresholds;
+ thresholds = &memcg->memsw_thresholds;
else
BUG();
__mem_cgroup_threshold(memcg, type == _MEMSWAP);
/* Calculate new number of threshold */
- for (i = 0; i < thresholds->size; i++) {
- if (thresholds->entries[i].eventfd != eventfd)
+ size = 0;
+ for (i = 0; i < thresholds->primary->size; i++) {
+ if (thresholds->primary->entries[i].eventfd != eventfd)
size++;
}
+ new = thresholds->spare;
+
/* Set thresholds array to NULL if we don't have thresholds */
if (!size) {
- thresholds_new = NULL;
- goto assign;
+ kfree(new);
+ new = NULL;
+ goto swap_buffers;
}
- /* Allocate memory for new array of thresholds */
- thresholds_new = kmalloc(sizeof(*thresholds_new) +
- size * sizeof(struct mem_cgroup_threshold),
- GFP_KERNEL);
- if (!thresholds_new) {
- ret = -ENOMEM;
- goto unlock;
- }
- thresholds_new->size = size;
+ new->size = size;
/* Copy thresholds and find current threshold */
- thresholds_new->current_threshold = -1;
- for (i = 0, j = 0; i < thresholds->size; i++) {
- if (thresholds->entries[i].eventfd == eventfd)
+ new->current_threshold = -1;
+ for (i = 0, j = 0; i < thresholds->primary->size; i++) {
+ if (thresholds->primary->entries[i].eventfd == eventfd)
continue;
- thresholds_new->entries[j] = thresholds->entries[i];
- if (thresholds_new->entries[j].threshold < usage) {
+ new->entries[j] = thresholds->primary->entries[i];
+ if (new->entries[j].threshold < usage) {
/*
- * thresholds_new->current_threshold will not be used
+ * new->current_threshold will not be used
* until rcu_assign_pointer(), so it's safe to increment
* it here.
*/
- ++thresholds_new->current_threshold;
+ ++new->current_threshold;
}
j++;
}
-assign:
- if (type == _MEM)
- rcu_assign_pointer(memcg->thresholds, thresholds_new);
- else
- rcu_assign_pointer(memcg->memsw_thresholds, thresholds_new);
+swap_buffers:
+ /* Swap primary and spare array */
+ thresholds->spare = thresholds->primary;
+ rcu_assign_pointer(thresholds->primary, new);
- /* To be sure that nobody uses thresholds before freeing it */
+ /* To be sure that nobody uses thresholds */
synchronize_rcu();
- kfree(thresholds);
-unlock:
mutex_unlock(&memcg->thresholds_lock);
-
- return ret;
}
static int mem_cgroup_oom_register_event(struct cgroup *cgrp,
return 0;
}
-static int mem_cgroup_oom_unregister_event(struct cgroup *cgrp,
+static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp,
struct cftype *cft, struct eventfd_ctx *eventfd)
{
struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
}
mutex_unlock(&memcg_oom_mutex);
-
- return 0;
}
static int mem_cgroup_oom_control_read(struct cgroup *cgrp,
return 0;
}
-/*
- */
static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
struct cftype *cft, u64 val)
{
return -EINVAL;
}
mem->oom_kill_disable = val;
+ if (!val)
+ memcg_oom_recover(mem);
cgroup_unlock();
return 0;
}
*/
if (!node_state(node, N_NORMAL_MEMORY))
tmp = -1;
- pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, tmp);
+ pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp);
if (!pn)
return 1;
mem->info.nodeinfo[node] = pn;
- memset(pn, 0, sizeof(*pn));
-
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
mz = &pn->zoneinfo[zone];
for_each_lru(l)
/* Can be very big if MAX_NUMNODES is very big */
if (size < PAGE_SIZE)
- mem = kmalloc(size, GFP_KERNEL);
+ mem = kzalloc(size, GFP_KERNEL);
else
- mem = vmalloc(size);
+ mem = vzalloc(size);
if (!mem)
return NULL;
- memset(mem, 0, size);
mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
- if (!mem->stat) {
- if (size < PAGE_SIZE)
- kfree(mem);
- else
- vfree(mem);
- mem = NULL;
- }
+ if (!mem->stat)
+ goto out_free;
+ spin_lock_init(&mem->pcp_counter_lock);
return mem;
+
+out_free:
+ if (size < PAGE_SIZE)
+ kfree(mem);
+ else
+ vfree(mem);
+ return NULL;
}
/*
&per_cpu(memcg_stock, cpu);
INIT_WORK(&stock->work, drain_local_stock);
}
- hotcpu_notifier(memcg_stock_cpu_callback, 0);
+ hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
} else {
parent = mem_cgroup_from_cont(cont->parent);
mem->use_hierarchy = parent->use_hierarchy;
res_counter_init(&mem->memsw, NULL);
}
mem->last_scanned_child = 0;
- spin_lock_init(&mem->reclaim_param_lock);
INIT_LIST_HEAD(&mem->oom_notify);
if (parent)
goto one_by_one;
}
mc.precharge += count;
- VM_BUG_ON(test_bit(CSS_ROOT, &mem->css.flags));
- WARN_ON_ONCE(count > INT_MAX);
- __css_get(&mem->css, (int)count);
return ret;
}
one_by_one:
batch_count = PRECHARGE_COUNT_AT_ONCE;
cond_resched();
}
- ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false);
+ ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, 1, &mem, false);
if (ret || !mem)
/* mem_cgroup_clear_mc() will do uncharge later */
return -ENOMEM;
pte_t *pte;
spinlock_t *ptl;
+ split_huge_page_pmd(walk->mm, pmd);
+
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE)
if (is_target_pte_for_mc(vma, addr, *pte, NULL))
static int mem_cgroup_precharge_mc(struct mm_struct *mm)
{
- return mem_cgroup_do_precharge(mem_cgroup_count_precharge(mm));
+ unsigned long precharge = mem_cgroup_count_precharge(mm);
+
+ VM_BUG_ON(mc.moving_task);
+ mc.moving_task = current;
+ return mem_cgroup_do_precharge(precharge);
}
-static void mem_cgroup_clear_mc(void)
+/* cancels all extra charges on mc.from and mc.to, and wakes up all waiters. */
+static void __mem_cgroup_clear_mc(void)
{
+ struct mem_cgroup *from = mc.from;
+ struct mem_cgroup *to = mc.to;
+
/* we must uncharge all the leftover precharges from mc.to */
if (mc.precharge) {
__mem_cgroup_cancel_charge(mc.to, mc.precharge);
mc.precharge = 0;
- memcg_oom_recover(mc.to);
}
/*
* we didn't uncharge from mc.from at mem_cgroup_move_account(), so
if (mc.moved_charge) {
__mem_cgroup_cancel_charge(mc.from, mc.moved_charge);
mc.moved_charge = 0;
- memcg_oom_recover(mc.from);
}
/* we must fixup refcnts and charges */
if (mc.moved_swap) {
- WARN_ON_ONCE(mc.moved_swap > INT_MAX);
/* uncharge swap account from the old cgroup */
if (!mem_cgroup_is_root(mc.from))
res_counter_uncharge(&mc.from->memsw,
*/
res_counter_uncharge(&mc.to->res,
PAGE_SIZE * mc.moved_swap);
- VM_BUG_ON(test_bit(CSS_ROOT, &mc.to->css.flags));
- __css_put(&mc.to->css, mc.moved_swap);
}
/* we've already done mem_cgroup_get(mc.to) */
-
mc.moved_swap = 0;
}
+ memcg_oom_recover(from);
+ memcg_oom_recover(to);
+ wake_up_all(&mc.waitq);
+}
+
+static void mem_cgroup_clear_mc(void)
+{
+ struct mem_cgroup *from = mc.from;
+
+ /*
+ * we must clear moving_task before waking up waiters at the end of
+ * task migration.
+ */
+ mc.moving_task = NULL;
+ __mem_cgroup_clear_mc();
+ spin_lock(&mc.lock);
mc.from = NULL;
mc.to = NULL;
- mc.moving_task = NULL;
- wake_up_all(&mc.waitq);
+ spin_unlock(&mc.lock);
+ mem_cgroup_end_move(from);
}
static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
VM_BUG_ON(mc.precharge);
VM_BUG_ON(mc.moved_charge);
VM_BUG_ON(mc.moved_swap);
- VM_BUG_ON(mc.moving_task);
+ mem_cgroup_start_move(from);
+ spin_lock(&mc.lock);
mc.from = from;
mc.to = mem;
- mc.precharge = 0;
- mc.moved_charge = 0;
- mc.moved_swap = 0;
- mc.moving_task = current;
+ spin_unlock(&mc.lock);
+ /* We set mc.moving_task later */
ret = mem_cgroup_precharge_mc(mm);
if (ret)
pte_t *pte;
spinlock_t *ptl;
+ split_huge_page_pmd(walk->mm, pmd);
retry:
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; addr += PAGE_SIZE) {
if (isolate_lru_page(page))
goto put;
pc = lookup_page_cgroup(page);
- if (!mem_cgroup_move_account(pc,
- mc.from, mc.to, false)) {
+ if (!mem_cgroup_move_account(page, 1, pc,
+ mc.from, mc.to, false)) {
mc.precharge--;
/* we uncharge from mc.from later. */
mc.moved_charge++;
struct vm_area_struct *vma;
lru_add_drain_all();
- down_read(&mm->mmap_sem);
+retry:
+ if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
+ /*
+ * Someone who are holding the mmap_sem might be waiting in
+ * waitq. So we cancel all extra charges, wake up all waiters,
+ * and retry. Because we cancel precharges, we might not be able
+ * to move enough charges, but moving charge is a best-effort
+ * feature anyway, so it wouldn't be a big problem.
+ */
+ __mem_cgroup_clear_mc();
+ cond_resched();
+ goto retry;
+ }
for (vma = mm->mmap; vma; vma = vma->vm_next) {
int ret;
struct mm_walk mem_cgroup_move_charge_walk = {
};
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+static int __init enable_swap_account(char *s)
+{
+ /* consider enabled if no parameter or 1 is given */
+ if (!(*s) || !strcmp(s, "=1"))
+ really_do_swap_account = 1;
+ else if (!strcmp(s, "=0"))
+ really_do_swap_account = 0;
+ return 1;
+}
+__setup("swapaccount", enable_swap_account);
static int __init disable_swap_account(char *s)
{
- really_do_swap_account = 0;
+ printk_once("noswapaccount is deprecated and will be removed in 2.6.40. Use swapaccount=0 instead\n");
+ enable_swap_account("=0");
return 1;
}
__setup("noswapaccount", disable_swap_account);