#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
+#include <linux/limits.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/swap.h>
static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
{
struct mem_cgroup *mem = NULL;
+
+ if (!mm)
+ return NULL;
/*
* Because we have no locks, mm->owner's may be being moved to other
* cgroup. We use css_tryget() here even if this looks
int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
{
int ret;
+ struct mem_cgroup *curr = NULL;
task_lock(task);
- ret = task->mm && mm_match_cgroup(task->mm, mem);
+ rcu_read_lock();
+ curr = try_get_mem_cgroup_from_mm(task->mm);
+ rcu_read_unlock();
task_unlock(task);
+ if (!curr)
+ return 0;
+ if (curr->use_hierarchy)
+ ret = css_is_ancestor(&curr->css, &mem->css);
+ else
+ ret = (curr == mem);
+ css_put(&curr->css);
return ret;
}
-/*
- * Calculate mapped_ratio under memory controller. This will be used in
- * vmscan.c for deteremining we have to reclaim mapped pages.
- */
-int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
-{
- long total, rss;
-
- /*
- * usage is recorded in bytes. But, here, we assume the number of
- * physical pages can be represented by "long" on any arch.
- */
- total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L;
- rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
- return (int)((rss * 100L) / total);
-}
-
/*
* prev_priority control...this will be used in memory reclaim path.
*/
return swappiness;
}
+static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data)
+{
+ int *val = data;
+ (*val)++;
+ return 0;
+}
+
+/**
+ * mem_cgroup_print_mem_info: Called from OOM with tasklist_lock held in read mode.
+ * @memcg: The memory cgroup that went over limit
+ * @p: Task that is going to be killed
+ *
+ * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
+ * enabled
+ */
+void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+{
+ struct cgroup *task_cgrp;
+ struct cgroup *mem_cgrp;
+ /*
+ * Need a buffer in BSS, can't rely on allocations. The code relies
+ * on the assumption that OOM is serialized for memory controller.
+ * If this assumption is broken, revisit this code.
+ */
+ static char memcg_name[PATH_MAX];
+ int ret;
+
+ if (!memcg)
+ return;
+
+
+ rcu_read_lock();
+
+ mem_cgrp = memcg->css.cgroup;
+ task_cgrp = task_cgroup(p, mem_cgroup_subsys_id);
+
+ ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX);
+ if (ret < 0) {
+ /*
+ * Unfortunately, we are unable to convert to a useful name
+ * But we'll still print out the usage information
+ */
+ rcu_read_unlock();
+ goto done;
+ }
+ rcu_read_unlock();
+
+ printk(KERN_INFO "Task in %s killed", memcg_name);
+
+ rcu_read_lock();
+ ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX);
+ if (ret < 0) {
+ rcu_read_unlock();
+ goto done;
+ }
+ rcu_read_unlock();
+
+ /*
+ * Continues from above, so we don't need an KERN_ level
+ */
+ printk(KERN_CONT " as a result of limit of %s\n", memcg_name);
+done:
+
+ printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n",
+ res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
+ res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
+ res_counter_read_u64(&memcg->res, RES_FAILCNT));
+ printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, "
+ "failcnt %llu\n",
+ res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
+ res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
+ res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
+}
+
+/*
+ * This function returns the number of memcg under hierarchy tree. Returns
+ * 1(self count) if no children.
+ */
+static int mem_cgroup_count_children(struct mem_cgroup *mem)
+{
+ int num = 0;
+ mem_cgroup_walk_tree(mem, &num, mem_cgroup_count_children_cb);
+ return num;
+}
+
/*
* Visit the first child (need not be the first child as per the ordering
* of the cgroup list, since we track last_scanned_child) of @mem and use
*
* We give up and return to the caller when we visit root_mem twice.
* (other groups can be removed while we're walking....)
+ *
+ * If shrink==true, for avoiding to free too much, this returns immedieately.
*/
static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
- gfp_t gfp_mask, bool noswap)
+ gfp_t gfp_mask, bool noswap, bool shrink)
{
struct mem_cgroup *victim;
int ret, total = 0;
ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, noswap,
get_swappiness(victim));
css_put(&victim->css);
+ /*
+ * At shrinking usage, we can't check we should stop here or
+ * reclaim more. It's depends on callers. last_scanned_child
+ * will work enough for keeping fairness under tree.
+ */
+ if (shrink)
+ return ret;
total += ret;
if (mem_cgroup_check_under_limit(root_mem))
return 1 + total;
rcu_read_unlock();
return ret;
}
+
+static int record_last_oom_cb(struct mem_cgroup *mem, void *data)
+{
+ mem->last_oom_jiffies = jiffies;
+ return 0;
+}
+
+static void record_last_oom(struct mem_cgroup *mem)
+{
+ mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb);
+}
+
+
/*
* Unlike exported interface, "oom" parameter is added. if oom==true,
* oom-killer can be invoked.
goto nomem;
ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask,
- noswap);
+ noswap, false);
if (ret)
continue;
mutex_lock(&memcg_tasklist);
mem_cgroup_out_of_memory(mem_over_limit, gfp_mask);
mutex_unlock(&memcg_tasklist);
- mem_over_limit->last_oom_jiffies = jiffies;
+ record_last_oom(mem_over_limit);
}
goto nomem;
}
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);
+ /*
+ * Used bit of swapcache is solid under page lock.
+ */
+ 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();
+ }
return mem;
}
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;
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. */
}
+void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
+{
+ __mem_cgroup_commit_charge_swapin(page, ptr,
+ MEM_CGROUP_CHARGE_TYPE_MAPPED);
+}
+
void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
{
if (mem_cgroup_disabled())
MEM_CGROUP_CHARGE_TYPE_SWAPOUT);
/* record memcg information */
if (do_swap_account && memcg) {
- swap_cgroup_record(ent, memcg);
+ swap_cgroup_record(ent, css_id(&memcg->css));
mem_cgroup_get(memcg);
}
if (memcg)
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
return 0;
do {
- progress = mem_cgroup_hierarchical_reclaim(mem, gfp_mask, true);
+ progress = mem_cgroup_hierarchical_reclaim(mem,
+ gfp_mask, true, false);
progress += mem_cgroup_check_under_limit(mem);
} while (!progress && --retry);
static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
unsigned long long val)
{
-
- int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+ int retry_count;
int progress;
u64 memswlimit;
int ret = 0;
+ int children = mem_cgroup_count_children(memcg);
+ u64 curusage, oldusage;
+
+ /*
+ * For keeping hierarchical_reclaim simple, how long we should retry
+ * is depends on callers. We set our retry-count to be function
+ * of # of children which we should visit in this loop.
+ */
+ retry_count = MEM_CGROUP_RECLAIM_RETRIES * children;
+
+ oldusage = res_counter_read_u64(&memcg->res, RES_USAGE);
while (retry_count) {
if (signal_pending(current)) {
break;
progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL,
- false);
- if (!progress) retry_count--;
+ false, true);
+ curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
+ /* Usage is reduced ? */
+ if (curusage >= oldusage)
+ retry_count--;
+ else
+ oldusage = curusage;
}
return ret;
int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
unsigned long long val)
{
- int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+ int retry_count;
u64 memlimit, oldusage, curusage;
- int ret;
+ 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);
while (retry_count) {
if (signal_pending(current)) {
ret = -EINTR;
if (!ret)
break;
- oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
- mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true);
+ mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true, true);
curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+ /* Usage is reduced ? */
if (curusage >= oldusage)
retry_count--;
+ else
+ oldusage = curusage;
}
return ret;
}