#ifdef CONFIG_MEMCG_KMEM
extern spinlock_t css_set_lock;
-static int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
- unsigned int nr_pages);
-static void __memcg_kmem_uncharge(struct mem_cgroup *memcg,
- unsigned int nr_pages);
+static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
+ unsigned int nr_pages);
static void obj_cgroup_release(struct percpu_ref *ref)
{
spin_lock_irqsave(&css_set_lock, flags);
memcg = obj_cgroup_memcg(objcg);
if (nr_pages)
- __memcg_kmem_uncharge(memcg, nr_pages);
+ obj_cgroup_uncharge_pages(objcg, nr_pages);
list_del(&objcg->list);
mem_cgroup_put(memcg);
spin_unlock_irqrestore(&css_set_lock, flags);
int val)
{
struct page *head = compound_head(page); /* rmap on tail pages */
- struct mem_cgroup *memcg = page_memcg(head);
+ struct mem_cgroup *memcg;
pg_data_t *pgdat = page_pgdat(page);
struct lruvec *lruvec;
+ rcu_read_lock();
+ memcg = page_memcg(head);
/* Untracked pages have no memcg, no lruvec. Update only the node */
if (!memcg) {
+ rcu_read_unlock();
__mod_node_page_state(pgdat, idx, val);
return;
}
lruvec = mem_cgroup_lruvec(memcg, pgdat);
__mod_lruvec_state(lruvec, idx, val);
+ rcu_read_unlock();
}
EXPORT_SYMBOL(__mod_lruvec_page_state);
return current->active_memcg;
}
-static __always_inline struct mem_cgroup *get_active_memcg(void)
-{
- struct mem_cgroup *memcg;
-
- rcu_read_lock();
- memcg = active_memcg();
- /* remote memcg must hold a ref. */
- if (memcg && WARN_ON_ONCE(!css_tryget(&memcg->css)))
- memcg = root_mem_cgroup;
- rcu_read_unlock();
-
- return memcg;
-}
-
static __always_inline bool memcg_kmem_bypass(void)
{
/* Allow remote memcg charging from any context. */
return false;
}
-/**
- * If active memcg is set, do not fallback to current->mm->memcg.
- */
-static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void)
-{
- if (memcg_kmem_bypass())
- return NULL;
-
- if (unlikely(active_memcg()))
- return get_active_memcg();
-
- return get_mem_cgroup_from_mm(current->mm);
-}
-
/**
* mem_cgroup_iter - iterate over memory cgroup hierarchy
* @root: hierarchy root
mutex_unlock(&percpu_charge_mutex);
}
-static int memcg_hotplug_cpu_dead(unsigned int cpu)
+static void memcg_flush_lruvec_page_state(struct mem_cgroup *memcg, int cpu)
{
- struct memcg_stock_pcp *stock;
- struct mem_cgroup *memcg;
-
- stock = &per_cpu(memcg_stock, cpu);
- drain_stock(stock);
+ int nid;
- for_each_mem_cgroup(memcg) {
+ for_each_node(nid) {
+ struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
+ unsigned long stat[NR_VM_NODE_STAT_ITEMS];
+ struct batched_lruvec_stat *lstatc;
int i;
+ lstatc = per_cpu_ptr(pn->lruvec_stat_cpu, cpu);
for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
- int nid;
+ stat[i] = lstatc->count[i];
+ lstatc->count[i] = 0;
+ }
- for_each_node(nid) {
- struct batched_lruvec_stat *lstatc;
- struct mem_cgroup_per_node *pn;
- long x;
+ do {
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+ atomic_long_add(stat[i], &pn->lruvec_stat[i]);
+ } while ((pn = parent_nodeinfo(pn, nid)));
+ }
+}
- pn = memcg->nodeinfo[nid];
- lstatc = per_cpu_ptr(pn->lruvec_stat_cpu, cpu);
+static int memcg_hotplug_cpu_dead(unsigned int cpu)
+{
+ struct memcg_stock_pcp *stock;
+ struct mem_cgroup *memcg;
- x = lstatc->count[i];
- lstatc->count[i] = 0;
+ stock = &per_cpu(memcg_stock, cpu);
+ drain_stock(stock);
- if (x) {
- do {
- atomic_long_add(x, &pn->lruvec_stat[i]);
- } while ((pn = parent_nodeinfo(pn, nid)));
- }
- }
- }
- }
+ for_each_mem_cgroup(memcg)
+ memcg_flush_lruvec_page_state(memcg, cpu);
return 0;
}
page->memcg_data = (unsigned long)memcg;
}
+static struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
+{
+ struct mem_cgroup *memcg;
+
+ rcu_read_lock();
+retry:
+ memcg = obj_cgroup_memcg(objcg);
+ if (unlikely(!css_tryget(&memcg->css)))
+ goto retry;
+ rcu_read_unlock();
+
+ return memcg;
+}
+
#ifdef CONFIG_MEMCG_KMEM
int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
gfp_t gfp, bool new_page)
ida_simple_remove(&memcg_cache_ida, id);
}
-/**
- * __memcg_kmem_charge: charge a number of kernel pages to a memcg
- * @memcg: memory cgroup to charge
+/*
+ * obj_cgroup_uncharge_pages: uncharge a number of kernel pages from a objcg
+ * @objcg: object cgroup to uncharge
+ * @nr_pages: number of pages to uncharge
+ */
+static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
+ unsigned int nr_pages)
+{
+ struct mem_cgroup *memcg;
+
+ memcg = get_mem_cgroup_from_objcg(objcg);
+
+ if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+ page_counter_uncharge(&memcg->kmem, nr_pages);
+ refill_stock(memcg, nr_pages);
+
+ css_put(&memcg->css);
+}
+
+/*
+ * obj_cgroup_charge_pages: charge a number of kernel pages to a objcg
+ * @objcg: object cgroup to charge
* @gfp: reclaim mode
* @nr_pages: number of pages to charge
*
* Returns 0 on success, an error code on failure.
*/
-static int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
- unsigned int nr_pages)
+static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp,
+ unsigned int nr_pages)
{
struct page_counter *counter;
+ struct mem_cgroup *memcg;
int ret;
+ memcg = get_mem_cgroup_from_objcg(objcg);
+
ret = try_charge(memcg, gfp, nr_pages);
if (ret)
- return ret;
+ goto out;
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
!page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) {
*/
if (gfp & __GFP_NOFAIL) {
page_counter_charge(&memcg->kmem, nr_pages);
- return 0;
+ goto out;
}
cancel_charge(memcg, nr_pages);
- return -ENOMEM;
+ ret = -ENOMEM;
}
- return 0;
-}
-
-/**
- * __memcg_kmem_uncharge: uncharge a number of kernel pages from a memcg
- * @memcg: memcg to uncharge
- * @nr_pages: number of pages to uncharge
- */
-static void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages)
-{
- if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
- page_counter_uncharge(&memcg->kmem, nr_pages);
+out:
+ css_put(&memcg->css);
- refill_stock(memcg, nr_pages);
+ return ret;
}
/**
*/
int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
{
- struct mem_cgroup *memcg;
+ struct obj_cgroup *objcg;
int ret = 0;
- memcg = get_mem_cgroup_from_current();
- if (memcg && !mem_cgroup_is_root(memcg)) {
- ret = __memcg_kmem_charge(memcg, gfp, 1 << order);
+ objcg = get_obj_cgroup_from_current();
+ if (objcg) {
+ ret = obj_cgroup_charge_pages(objcg, gfp, 1 << order);
if (!ret) {
- page->memcg_data = (unsigned long)memcg |
+ page->memcg_data = (unsigned long)objcg |
MEMCG_DATA_KMEM;
return 0;
}
- css_put(&memcg->css);
+ obj_cgroup_put(objcg);
}
return ret;
}
*/
void __memcg_kmem_uncharge_page(struct page *page, int order)
{
- struct mem_cgroup *memcg = page_memcg(page);
+ struct obj_cgroup *objcg;
unsigned int nr_pages = 1 << order;
- if (!memcg)
+ if (!PageMemcgKmem(page))
return;
- VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
- __memcg_kmem_uncharge(memcg, nr_pages);
+ objcg = __page_objcg(page);
+ obj_cgroup_uncharge_pages(objcg, nr_pages);
page->memcg_data = 0;
- css_put(&memcg->css);
+ obj_cgroup_put(objcg);
}
static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
unsigned int nr_pages = stock->nr_bytes >> PAGE_SHIFT;
unsigned int nr_bytes = stock->nr_bytes & (PAGE_SIZE - 1);
- if (nr_pages) {
- rcu_read_lock();
- __memcg_kmem_uncharge(obj_cgroup_memcg(old), nr_pages);
- rcu_read_unlock();
- }
+ if (nr_pages)
+ obj_cgroup_uncharge_pages(old, nr_pages);
/*
* The leftover is flushed to the centralized per-memcg value.
int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size)
{
- struct mem_cgroup *memcg;
unsigned int nr_pages, nr_bytes;
int ret;
* refill_obj_stock(), called from this function or
* independently later.
*/
- rcu_read_lock();
-retry:
- memcg = obj_cgroup_memcg(objcg);
- if (unlikely(!css_tryget(&memcg->css)))
- goto retry;
- rcu_read_unlock();
-
nr_pages = size >> PAGE_SHIFT;
nr_bytes = size & (PAGE_SIZE - 1);
if (nr_bytes)
nr_pages += 1;
- ret = __memcg_kmem_charge(memcg, gfp, nr_pages);
+ ret = obj_cgroup_charge_pages(objcg, gfp, nr_pages);
if (!ret && nr_bytes)
refill_obj_stock(objcg, PAGE_SIZE - nr_bytes);
- css_put(&memcg->css);
return ret;
}
for (i = 1; i < nr; i++)
head[i].memcg_data = head->memcg_data;
- css_get_many(&memcg->css, nr - 1);
+
+ if (PageMemcgKmem(head))
+ obj_cgroup_get_many(__page_objcg(head), nr - 1);
+ else
+ css_get_many(&memcg->css, nr - 1);
}
#ifdef CONFIG_MEMCG_SWAP
}
}
-static void memcg_flush_lruvec_page_state(struct mem_cgroup *memcg)
-{
- int node;
-
- for_each_node(node) {
- struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];
- unsigned long stat[NR_VM_NODE_STAT_ITEMS] = { 0 };
- struct mem_cgroup_per_node *pi;
- int cpu, i;
-
- for_each_online_cpu(cpu)
- for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
- stat[i] += per_cpu(
- pn->lruvec_stat_cpu->count[i], cpu);
-
- for (pi = pn; pi; pi = parent_nodeinfo(pi, node))
- for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
- atomic_long_add(stat[i], &pi->lruvec_stat[i]);
- }
-}
-
#ifdef CONFIG_MEMCG_KMEM
static int memcg_online_kmem(struct mem_cgroup *memcg)
{
static void mem_cgroup_free(struct mem_cgroup *memcg)
{
+ int cpu;
+
memcg_wb_domain_exit(memcg);
/*
* Flush percpu lruvec stats to guarantee the value
* correctness on parent's and all ancestor levels.
*/
- memcg_flush_lruvec_page_state(memcg);
+ for_each_online_cpu(cpu)
+ memcg_flush_lruvec_page_state(memcg, cpu);
__mem_cgroup_free(memcg);
}
atomic_long_read(&parent->memory.children_low_usage)));
}
+static int __mem_cgroup_charge(struct page *page, struct mem_cgroup *memcg,
+ gfp_t gfp)
+{
+ unsigned int nr_pages = thp_nr_pages(page);
+ int ret;
+
+ ret = try_charge(memcg, gfp, nr_pages);
+ if (ret)
+ goto out;
+
+ css_get(&memcg->css);
+ commit_charge(page, memcg);
+
+ local_irq_disable();
+ mem_cgroup_charge_statistics(memcg, page, nr_pages);
+ memcg_check_events(memcg, page);
+ local_irq_enable();
+out:
+ return ret;
+}
+
/**
* mem_cgroup_charge - charge a newly allocated page to a cgroup
* @page: page to charge
* Try to charge @page to the memcg that @mm belongs to, reclaiming
* pages according to @gfp_mask if necessary.
*
+ * Do not use this for pages allocated for swapin.
+ *
* Returns 0 on success. Otherwise, an error code is returned.
*/
int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
{
- unsigned int nr_pages = thp_nr_pages(page);
- struct mem_cgroup *memcg = NULL;
- int ret = 0;
+ struct mem_cgroup *memcg;
+ int ret;
if (mem_cgroup_disabled())
- goto out;
+ return 0;
- if (PageSwapCache(page)) {
- swp_entry_t ent = { .val = page_private(page), };
- unsigned short id;
+ memcg = get_mem_cgroup_from_mm(mm);
+ ret = __mem_cgroup_charge(page, memcg, gfp_mask);
+ css_put(&memcg->css);
- /*
- * Every swap fault against a single page tries to charge the
- * page, bail as early as possible. shmem_unuse() encounters
- * already charged pages, too. page and memcg binding is
- * protected by the page lock, which serializes swap cache
- * removal, which in turn serializes uncharging.
- */
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- if (page_memcg(compound_head(page)))
- goto out;
+ return ret;
+}
- id = lookup_swap_cgroup_id(ent);
- rcu_read_lock();
- memcg = mem_cgroup_from_id(id);
- if (memcg && !css_tryget_online(&memcg->css))
- memcg = NULL;
- rcu_read_unlock();
- }
+/**
+ * mem_cgroup_swapin_charge_page - charge a newly allocated page for swapin
+ * @page: page to charge
+ * @mm: mm context of the victim
+ * @gfp: reclaim mode
+ * @entry: swap entry for which the page is allocated
+ *
+ * This function charges a page allocated for swapin. Please call this before
+ * adding the page to the swapcache.
+ *
+ * Returns 0 on success. Otherwise, an error code is returned.
+ */
+int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
+ gfp_t gfp, swp_entry_t entry)
+{
+ struct mem_cgroup *memcg;
+ unsigned short id;
+ int ret;
- if (!memcg)
- memcg = get_mem_cgroup_from_mm(mm);
+ if (mem_cgroup_disabled())
+ return 0;
- ret = try_charge(memcg, gfp_mask, nr_pages);
- if (ret)
- goto out_put;
+ id = lookup_swap_cgroup_id(entry);
+ rcu_read_lock();
+ memcg = mem_cgroup_from_id(id);
+ if (!memcg || !css_tryget_online(&memcg->css))
+ memcg = get_mem_cgroup_from_mm(mm);
+ rcu_read_unlock();
- css_get(&memcg->css);
- commit_charge(page, memcg);
+ ret = __mem_cgroup_charge(page, memcg, gfp);
- local_irq_disable();
- mem_cgroup_charge_statistics(memcg, page, nr_pages);
- memcg_check_events(memcg, page);
- local_irq_enable();
+ css_put(&memcg->css);
+ return ret;
+}
+/*
+ * mem_cgroup_swapin_uncharge_swap - uncharge swap slot
+ * @entry: swap entry for which the page is charged
+ *
+ * Call this function after successfully adding the charged page to swapcache.
+ *
+ * Note: This function assumes the page for which swap slot is being uncharged
+ * is order 0 page.
+ */
+void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry)
+{
/*
* Cgroup1's unified memory+swap counter has been charged with the
* new swapcache page, finish the transfer by uncharging the swap
* correspond 1:1 to page and swap slot lifetimes: we charge the
* page to memory here, and uncharge swap when the slot is freed.
*/
- if (do_memsw_account() && PageSwapCache(page)) {
- swp_entry_t entry = { .val = page_private(page) };
+ if (!mem_cgroup_disabled() && do_memsw_account()) {
/*
* The swap entry might not get freed for a long time,
* let's not wait for it. The page already received a
* memory+swap charge, drop the swap entry duplicate.
*/
- mem_cgroup_uncharge_swap(entry, nr_pages);
+ mem_cgroup_uncharge_swap(entry, 1);
}
-
-out_put:
- css_put(&memcg->css);
-out:
- return ret;
}
struct uncharge_gather {
struct mem_cgroup *memcg;
- unsigned long nr_pages;
+ unsigned long nr_memory;
unsigned long pgpgout;
unsigned long nr_kmem;
struct page *dummy_page;
{
unsigned long flags;
- if (!mem_cgroup_is_root(ug->memcg)) {
- page_counter_uncharge(&ug->memcg->memory, ug->nr_pages);
+ if (ug->nr_memory) {
+ page_counter_uncharge(&ug->memcg->memory, ug->nr_memory);
if (do_memsw_account())
- page_counter_uncharge(&ug->memcg->memsw, ug->nr_pages);
+ page_counter_uncharge(&ug->memcg->memsw, ug->nr_memory);
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && ug->nr_kmem)
page_counter_uncharge(&ug->memcg->kmem, ug->nr_kmem);
memcg_oom_recover(ug->memcg);
local_irq_save(flags);
__count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout);
- __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages);
+ __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_memory);
memcg_check_events(ug->memcg, ug->dummy_page);
local_irq_restore(flags);
static void uncharge_page(struct page *page, struct uncharge_gather *ug)
{
unsigned long nr_pages;
+ struct mem_cgroup *memcg;
+ struct obj_cgroup *objcg;
VM_BUG_ON_PAGE(PageLRU(page), page);
- if (!page_memcg(page))
- return;
-
/*
* Nobody should be changing or seriously looking at
- * page_memcg(page) at this point, we have fully
+ * page memcg or objcg at this point, we have fully
* exclusive access to the page.
*/
+ if (PageMemcgKmem(page)) {
+ objcg = __page_objcg(page);
+ /*
+ * This get matches the put at the end of the function and
+ * kmem pages do not hold memcg references anymore.
+ */
+ memcg = get_mem_cgroup_from_objcg(objcg);
+ } else {
+ memcg = __page_memcg(page);
+ }
- if (ug->memcg != page_memcg(page)) {
+ if (!memcg)
+ return;
+
+ if (ug->memcg != memcg) {
if (ug->memcg) {
uncharge_batch(ug);
uncharge_gather_clear(ug);
}
- ug->memcg = page_memcg(page);
+ ug->memcg = memcg;
+ ug->dummy_page = page;
/* pairs with css_put in uncharge_batch */
- css_get(&ug->memcg->css);
+ css_get(&memcg->css);
}
nr_pages = compound_nr(page);
- ug->nr_pages += nr_pages;
- if (PageMemcgKmem(page))
+ if (PageMemcgKmem(page)) {
+ ug->nr_memory += nr_pages;
ug->nr_kmem += nr_pages;
- else
+
+ page->memcg_data = 0;
+ obj_cgroup_put(objcg);
+ } else {
+ /* LRU pages aren't accounted at the root level */
+ if (!mem_cgroup_is_root(memcg))
+ ug->nr_memory += nr_pages;
ug->pgpgout++;
- ug->dummy_page = page;
- page->memcg_data = 0;
- css_put(&ug->memcg->css);
+ page->memcg_data = 0;
+ }
+
+ css_put(&memcg->css);
}
/**
projects / linux-2.6-microblaze.git / blobdiff