summaryrefslogtreecommitdiffstats
path: root/mm/memcontrol.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/memcontrol.c')
-rw-r--r--mm/memcontrol.c122
1 files changed, 73 insertions, 49 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 36db05fa8acb..75e74408cc8f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -207,6 +207,7 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
/* "mc" and its members are protected by cgroup_mutex */
static struct move_charge_struct {
spinlock_t lock; /* for from, to */
+ struct mm_struct *mm;
struct mem_cgroup *from;
struct mem_cgroup *to;
unsigned long flags;
@@ -1022,22 +1023,40 @@ out:
* @lru: index of lru list the page is sitting on
* @nr_pages: positive when adding or negative when removing
*
- * This function must be called when a page is added to or removed from an
- * lru list.
+ * This function must be called under lru_lock, just before a page is added
+ * to or just after a page is removed from an lru list (that ordering being
+ * so as to allow it to check that lru_size 0 is consistent with list_empty).
*/
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
int nr_pages)
{
struct mem_cgroup_per_zone *mz;
unsigned long *lru_size;
+ long size;
+ bool empty;
+
+ __update_lru_size(lruvec, lru, nr_pages);
if (mem_cgroup_disabled())
return;
mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
lru_size = mz->lru_size + lru;
- *lru_size += nr_pages;
- VM_BUG_ON((long)(*lru_size) < 0);
+ empty = list_empty(lruvec->lists + lru);
+
+ if (nr_pages < 0)
+ *lru_size += nr_pages;
+
+ size = *lru_size;
+ if (WARN_ONCE(size < 0 || empty != !size,
+ "%s(%p, %d, %d): lru_size %ld but %sempty\n",
+ __func__, lruvec, lru, nr_pages, size, empty ? "" : "not ")) {
+ VM_BUG_ON(1);
+ *lru_size = 0;
+ }
+
+ if (nr_pages > 0)
+ *lru_size += nr_pages;
}
bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg)
@@ -1089,6 +1108,8 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
limit = READ_ONCE(memcg->memsw.limit);
if (count <= limit)
margin = min(margin, limit - count);
+ else
+ margin = 0;
}
return margin;
@@ -1256,6 +1277,7 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
*/
if (fatal_signal_pending(current) || task_will_free_mem(current)) {
mark_oom_victim(current);
+ try_oom_reaper(current);
goto unlock;
}
@@ -1282,6 +1304,8 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
mem_cgroup_iter_break(memcg, iter);
if (chosen)
put_task_struct(chosen);
+ /* Set a dummy value to return "true". */
+ chosen = (void *) 1;
goto unlock;
case OOM_SCAN_OK:
break;
@@ -1388,14 +1412,11 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
mem_cgroup_may_update_nodemask(memcg);
node = memcg->last_scanned_node;
- node = next_node(node, memcg->scan_nodes);
- if (node == MAX_NUMNODES)
- node = first_node(memcg->scan_nodes);
+ node = next_node_in(node, memcg->scan_nodes);
/*
- * We call this when we hit limit, not when pages are added to LRU.
- * No LRU may hold pages because all pages are UNEVICTABLE or
- * memcg is too small and all pages are not on LRU. In that case,
- * we use curret node.
+ * mem_cgroup_may_update_nodemask might have seen no reclaimmable pages
+ * last time it really checked all the LRUs due to rate limiting.
+ * Fallback to the current node in that case for simplicity.
*/
if (unlikely(node == MAX_NUMNODES))
node = numa_node_id();
@@ -2635,8 +2656,7 @@ static inline bool memcg_has_children(struct mem_cgroup *memcg)
}
/*
- * Reclaims as many pages from the given memcg as possible and moves
- * the rest to the parent.
+ * Reclaims as many pages from the given memcg as possible.
*
* Caller is responsible for holding css reference for memcg.
*/
@@ -2876,6 +2896,7 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
* ordering is imposed by list_lru_node->lock taken by
* memcg_drain_all_list_lrus().
*/
+ rcu_read_lock(); /* can be called from css_free w/o cgroup_mutex */
css_for_each_descendant_pre(css, &memcg->css) {
child = mem_cgroup_from_css(css);
BUG_ON(child->kmemcg_id != kmemcg_id);
@@ -2883,6 +2904,8 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
if (!memcg->use_hierarchy)
break;
}
+ rcu_read_unlock();
+
memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id);
memcg_free_cache_id(kmemcg_id);
@@ -4289,24 +4312,6 @@ static int mem_cgroup_do_precharge(unsigned long count)
return 0;
}
-/**
- * get_mctgt_type - get target type of moving charge
- * @vma: the vma the pte to be checked belongs
- * @addr: the address corresponding to the pte to be checked
- * @ptent: the pte to be checked
- * @target: the pointer the target page or swap ent will be stored(can be NULL)
- *
- * Returns
- * 0(MC_TARGET_NONE): if the pte is not a target for move charge.
- * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for
- * move charge. if @target is not NULL, the page is stored in target->page
- * with extra refcnt got(Callers should handle it).
- * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
- * target for charge migration. if @target is not NULL, the entry is stored
- * in target->ent.
- *
- * Called with pte lock held.
- */
union mc_target {
struct page *page;
swp_entry_t ent;
@@ -4495,6 +4500,25 @@ out:
return ret;
}
+/**
+ * get_mctgt_type - get target type of moving charge
+ * @vma: the vma the pte to be checked belongs
+ * @addr: the address corresponding to the pte to be checked
+ * @ptent: the pte to be checked
+ * @target: the pointer the target page or swap ent will be stored(can be NULL)
+ *
+ * Returns
+ * 0(MC_TARGET_NONE): if the pte is not a target for move charge.
+ * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for
+ * move charge. if @target is not NULL, the page is stored in target->page
+ * with extra refcnt got(Callers should handle it).
+ * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
+ * target for charge migration. if @target is not NULL, the entry is stored
+ * in target->ent.
+ *
+ * Called with pte lock held.
+ */
+
static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
unsigned long addr, pte_t ptent, union mc_target *target)
{
@@ -4667,6 +4691,8 @@ static void __mem_cgroup_clear_mc(void)
static void mem_cgroup_clear_mc(void)
{
+ struct mm_struct *mm = mc.mm;
+
/*
* we must clear moving_task before waking up waiters at the end of
* task migration.
@@ -4676,7 +4702,10 @@ static void mem_cgroup_clear_mc(void)
spin_lock(&mc.lock);
mc.from = NULL;
mc.to = NULL;
+ mc.mm = NULL;
spin_unlock(&mc.lock);
+
+ mmput(mm);
}
static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
@@ -4733,6 +4762,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
VM_BUG_ON(mc.moved_swap);
spin_lock(&mc.lock);
+ mc.mm = mm;
mc.from = from;
mc.to = memcg;
mc.flags = move_flags;
@@ -4742,8 +4772,9 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
ret = mem_cgroup_precharge_mc(mm);
if (ret)
mem_cgroup_clear_mc();
+ } else {
+ mmput(mm);
}
- mmput(mm);
return ret;
}
@@ -4852,11 +4883,11 @@ put: /* get_mctgt_type() gets the page */
return ret;
}
-static void mem_cgroup_move_charge(struct mm_struct *mm)
+static void mem_cgroup_move_charge(void)
{
struct mm_walk mem_cgroup_move_charge_walk = {
.pmd_entry = mem_cgroup_move_charge_pte_range,
- .mm = mm,
+ .mm = mc.mm,
};
lru_add_drain_all();
@@ -4868,7 +4899,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
atomic_inc(&mc.from->moving_account);
synchronize_rcu();
retry:
- if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
+ if (unlikely(!down_read_trylock(&mc.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,
@@ -4885,23 +4916,16 @@ retry:
* additional charge, the page walk just aborts.
*/
walk_page_range(0, ~0UL, &mem_cgroup_move_charge_walk);
- up_read(&mm->mmap_sem);
+ up_read(&mc.mm->mmap_sem);
atomic_dec(&mc.from->moving_account);
}
-static void mem_cgroup_move_task(struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(void)
{
- struct cgroup_subsys_state *css;
- struct task_struct *p = cgroup_taskset_first(tset, &css);
- struct mm_struct *mm = get_task_mm(p);
-
- if (mm) {
- if (mc.to)
- mem_cgroup_move_charge(mm);
- mmput(mm);
- }
- if (mc.to)
+ if (mc.to) {
+ mem_cgroup_move_charge();
mem_cgroup_clear_mc();
+ }
}
#else /* !CONFIG_MMU */
static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
@@ -4911,7 +4935,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
{
}
-static void mem_cgroup_move_task(struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(void)
{
}
#endif
@@ -5195,7 +5219,7 @@ struct cgroup_subsys memory_cgrp_subsys = {
.css_reset = mem_cgroup_css_reset,
.can_attach = mem_cgroup_can_attach,
.cancel_attach = mem_cgroup_cancel_attach,
- .attach = mem_cgroup_move_task,
+ .post_attach = mem_cgroup_move_task,
.bind = mem_cgroup_bind,
.dfl_cftypes = memory_files,
.legacy_cftypes = mem_cgroup_legacy_files,
OpenPOWER on IntegriCloud