/* Writing them here to avoid exposing memcg's inner layout */
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
-#ifdef CONFIG_INET
#include <net/sock.h>
#include <net/ip.h>
static bool mem_cgroup_is_root(struct mem_cgroup *memcg);
void sock_update_memcg(struct sock *sk)
{
- if (static_branch(&memcg_socket_limit_enabled)) {
+ if (mem_cgroup_sockets_enabled) {
struct mem_cgroup *memcg;
BUG_ON(!sk->sk_prot->proto_cgroup);
void sock_release_memcg(struct sock *sk)
{
- if (static_branch(&memcg_socket_limit_enabled) && sk->sk_cgrp) {
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
struct mem_cgroup *memcg;
WARN_ON(!sk->sk_cgrp->memcg);
memcg = sk->sk_cgrp->memcg;
}
}
+#ifdef CONFIG_INET
struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
{
if (!memcg || mem_cgroup_is_root(memcg))
struct mem_cgroup_per_zone *mz;
struct mem_cgroup_tree_per_zone *mctz;
- for_each_node_state(node, N_POSSIBLE) {
+ for_each_node(node) {
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
mz = mem_cgroup_zoneinfo(memcg, node, zone);
mctz = soft_limit_tree_node_zone(node, zone);
return &zone->lruvec;
pc = lookup_page_cgroup(page);
- VM_BUG_ON(PageCgroupAcctLRU(pc));
- /*
- * putback: charge:
- * SetPageLRU SetPageCgroupUsed
- * smp_mb smp_mb
- * PageCgroupUsed && add to memcg LRU PageLRU && add to memcg LRU
- *
- * Ensure that one of the two sides adds the page to the memcg
- * LRU during a race.
- */
- smp_mb();
- /*
- * If the page is uncharged, it may be freed soon, but it
- * could also be swap cache (readahead, swapoff) that needs to
- * be reclaimable in the future. root_mem_cgroup will babysit
- * it for the time being.
- */
- if (PageCgroupUsed(pc)) {
- /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
- smp_rmb();
- memcg = pc->mem_cgroup;
- SetPageCgroupAcctLRU(pc);
- } else
- memcg = root_mem_cgroup;
+ memcg = pc->mem_cgroup;
mz = page_cgroup_zoneinfo(memcg, page);
/* compound_order() is stabilized through lru_lock */
MEM_CGROUP_ZSTAT(mz, lru) += 1 << compound_order(page);
return;
pc = lookup_page_cgroup(page);
- /*
- * root_mem_cgroup babysits uncharged LRU pages, but
- * PageCgroupUsed is cleared when the page is about to get
- * freed. PageCgroupAcctLRU remembers whether the
- * LRU-accounting happened against pc->mem_cgroup or
- * root_mem_cgroup.
- */
- if (TestClearPageCgroupAcctLRU(pc)) {
- VM_BUG_ON(!pc->mem_cgroup);
- memcg = pc->mem_cgroup;
- } else
- memcg = root_mem_cgroup;
+ memcg = pc->mem_cgroup;
+ VM_BUG_ON(!memcg);
mz = page_cgroup_zoneinfo(memcg, page);
/* huge page split is done under lru_lock. so, we have no races. */
+ VM_BUG_ON(MEM_CGROUP_ZSTAT(mz, lru) < (1 << compound_order(page)));
MEM_CGROUP_ZSTAT(mz, lru) -= 1 << compound_order(page);
}
return mem_cgroup_lru_add_list(zone, page, to);
}
-/*
- * 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(struct page *page)
-{
- enum lru_list lru;
- 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);
- lru = page_lru(page);
- /*
- * The uncharged page could still be registered to the LRU of
- * the stale pc->mem_cgroup.
- *
- * As pc->mem_cgroup is about to get overwritten, the old LRU
- * accounting needs to be taken care of. Let root_mem_cgroup
- * babysit the page until the new memcg is responsible for it.
- *
- * The PCG_USED bit is guarded by lock_page() as the page is
- * swapcache/pagecache.
- */
- if (PageLRU(page) && PageCgroupAcctLRU(pc) && !PageCgroupUsed(pc)) {
- del_page_from_lru_list(zone, page, lru);
- add_page_to_lru_list(zone, page, lru);
- }
- spin_unlock_irqrestore(&zone->lru_lock, flags);
-}
-
-static void mem_cgroup_lru_add_after_commit(struct page *page)
-{
- enum lru_list lru;
- unsigned long flags;
- struct zone *zone = page_zone(page);
- struct page_cgroup *pc = lookup_page_cgroup(page);
- /*
- * putback: charge:
- * SetPageLRU SetPageCgroupUsed
- * smp_mb smp_mb
- * PageCgroupUsed && add to memcg LRU PageLRU && add to memcg LRU
- *
- * Ensure that one of the two sides adds the page to the memcg
- * LRU during a race.
- */
- smp_mb();
- /* 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);
- lru = page_lru(page);
- /*
- * If the page is not on the LRU, someone will soon put it
- * there. If it is, and also already accounted for on the
- * memcg-side, it must be on the right lruvec as setting
- * pc->mem_cgroup and PageCgroupUsed is properly ordered.
- * Otherwise, root_mem_cgroup has been babysitting the page
- * during the charge. Move it to the new memcg now.
- */
- if (PageLRU(page) && !PageCgroupAcctLRU(pc)) {
- del_page_from_lru_list(zone, page, lru);
- add_page_to_lru_list(zone, page, lru);
- }
- spin_unlock_irqrestore(&zone->lru_lock, flags);
-}
-
/*
* Checks whether given mem is same or in the root_mem_cgroup's
* hierarchy subtree
struct task_struct *p;
p = find_lock_task_mm(task);
- if (!p)
- return 0;
- curr = try_get_mem_cgroup_from_mm(p->mm);
- task_unlock(p);
+ if (p) {
+ curr = try_get_mem_cgroup_from_mm(p->mm);
+ task_unlock(p);
+ } else {
+ /*
+ * All threads may have already detached their mm's, but the oom
+ * killer still needs to detect if they have already been oom
+ * killed to prevent needlessly killing additional tasks.
+ */
+ task_lock(task);
+ curr = mem_cgroup_from_task(task);
+ if (curr)
+ css_get(&curr->css);
+ task_unlock(task);
+ }
if (!curr)
return 0;
/*
}
/*
- * Unlike exported interface, "oom" parameter is added. if oom==true,
- * oom-killer can be invoked.
+ * __mem_cgroup_try_charge() does
+ * 1. detect memcg to be charged against from passed *mm and *ptr,
+ * 2. update res_counter
+ * 3. call memory reclaim if necessary.
+ *
+ * In some special case, if the task is fatal, fatal_signal_pending() or
+ * has TIF_MEMDIE, this function returns -EINTR while writing root_mem_cgroup
+ * to *ptr. There are two reasons for this. 1: fatal threads should quit as soon
+ * as possible without any hazards. 2: all pages should have a valid
+ * pc->mem_cgroup. If mm is NULL and the caller doesn't pass a valid memcg
+ * pointer, that is treated as a charge to root_mem_cgroup.
+ *
+ * So __mem_cgroup_try_charge() will return
+ * 0 ... on success, filling *ptr with a valid memcg pointer.
+ * -ENOMEM ... charge failure because of resource limits.
+ * -EINTR ... if thread is fatal. *ptr is filled with root_mem_cgroup.
+ *
+ * Unlike the exported interface, an "oom" parameter is added. if oom==true,
+ * the oom-killer can be invoked.
*/
static int __mem_cgroup_try_charge(struct mm_struct *mm,
gfp_t gfp_mask,
* set, if so charge the init_mm (happens for pagecache usage).
*/
if (!*ptr && !mm)
- goto bypass;
+ *ptr = root_mem_cgroup;
again:
if (*ptr) { /* css should be a valid one */
memcg = *ptr;
* task-struct. So, mm->owner can be NULL.
*/
memcg = mem_cgroup_from_task(p);
- if (!memcg || mem_cgroup_is_root(memcg)) {
+ if (!memcg)
+ memcg = root_mem_cgroup;
+ if (mem_cgroup_is_root(memcg)) {
rcu_read_unlock();
goto done;
}
*ptr = NULL;
return -ENOMEM;
bypass:
- *ptr = NULL;
- return 0;
+ *ptr = root_mem_cgroup;
+ return -EINTR;
}
/*
mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), nr_pages);
unlock_page_cgroup(pc);
+ WARN_ON_ONCE(PageLRU(page));
/*
* "charge_statistics" updated event counter. Then, check it.
* Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MOVE_LOCK) |\
- (1 << PCG_ACCT_LRU) | (1 << PCG_MIGRATION))
+ (1 << PCG_MIGRATION))
/*
* Because tail pages are not marked as "used", set it. We're under
* zone->lru_lock, 'splitting on pmd' and compound_lock.
pc = head_pc + i;
pc->mem_cgroup = head_pc->mem_cgroup;
smp_wmb();/* see __commit_charge() */
- /*
- * LRU flags cannot be copied because we need to add tail
- * page to LRU by generic call and our hooks will be called.
- */
pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
}
-
- if (PageCgroupAcctLRU(head_pc)) {
- enum lru_list lru;
- struct mem_cgroup_per_zone *mz;
- /*
- * 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) -= HPAGE_PMD_NR - 1;
- }
}
-#endif
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/**
* mem_cgroup_move_account - move account of the page
parent = mem_cgroup_from_cont(pcg);
ret = __mem_cgroup_try_charge(NULL, gfp_mask, nr_pages, &parent, false);
- if (ret || !parent)
+ if (ret)
goto put_back;
if (nr_pages > 1)
pc = lookup_page_cgroup(page);
ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &memcg, oom);
- if (ret || !memcg)
+ if (ret == -ENOMEM)
return ret;
-
__mem_cgroup_commit_charge(memcg, page, nr_pages, pc, ctype);
return 0;
}
enum charge_type ctype)
{
struct page_cgroup *pc = lookup_page_cgroup(page);
+ struct zone *zone = page_zone(page);
+ unsigned long flags;
+ bool removed = false;
+
/*
* 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);
+ spin_lock_irqsave(&zone->lru_lock, flags);
+ if (PageLRU(page)) {
+ del_page_from_lru_list(zone, page, page_lru(page));
+ ClearPageLRU(page);
+ removed = true;
+ }
__mem_cgroup_commit_charge(memcg, page, 1, pc, ctype);
- mem_cgroup_lru_add_after_commit(page);
+ if (removed) {
+ add_page_to_lru_list(zone, page, page_lru(page));
+ SetPageLRU(page);
+ }
+ spin_unlock_irqrestore(&zone->lru_lock, flags);
return;
}
gfp_t gfp_mask)
{
struct mem_cgroup *memcg = NULL;
+ enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
int ret;
if (mem_cgroup_disabled())
if (unlikely(!mm))
mm = &init_mm;
+ if (!page_is_file_cache(page))
+ type = MEM_CGROUP_CHARGE_TYPE_SHMEM;
- if (page_is_file_cache(page)) {
- ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, &memcg, true);
- if (ret || !memcg)
- 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, memcg,
- MEM_CGROUP_CHARGE_TYPE_CACHE);
- return ret;
- }
- /* shmem */
- if (PageSwapCache(page)) {
+ if (!PageSwapCache(page))
+ ret = mem_cgroup_charge_common(page, mm, gfp_mask, type);
+ else { /* page is swapcache/shmem */
ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg);
if (!ret)
- __mem_cgroup_commit_charge_swapin(page, memcg,
- MEM_CGROUP_CHARGE_TYPE_SHMEM);
- } else
- ret = mem_cgroup_charge_common(page, mm, gfp_mask,
- MEM_CGROUP_CHARGE_TYPE_SHMEM);
-
+ __mem_cgroup_commit_charge_swapin(page, memcg, type);
+ }
return ret;
}
*memcgp = memcg;
ret = __mem_cgroup_try_charge(NULL, mask, 1, memcgp, true);
css_put(&memcg->css);
+ if (ret == -EINTR)
+ ret = 0;
return ret;
charge_cur_mm:
if (unlikely(!mm))
mm = &init_mm;
- return __mem_cgroup_try_charge(mm, mask, 1, memcgp, true);
+ ret = __mem_cgroup_try_charge(mm, mask, 1, memcgp, true);
+ if (ret == -EINTR)
+ ret = 0;
+ return ret;
}
static void
batch->memcg = NULL;
}
+/*
+ * A function for resetting pc->mem_cgroup for newly allocated pages.
+ * This function should be called if the newpage will be added to LRU
+ * before start accounting.
+ */
+void mem_cgroup_reset_owner(struct page *newpage)
+{
+ struct page_cgroup *pc;
+
+ if (mem_cgroup_disabled())
+ return;
+
+ pc = lookup_page_cgroup(newpage);
+ VM_BUG_ON(PageCgroupUsed(pc));
+ pc->mem_cgroup = root_mem_cgroup;
+}
+
#ifdef CONFIG_SWAP
/*
* called after __delete_from_swap_cache() and drop "page" account.
*memcgp = memcg;
ret = __mem_cgroup_try_charge(NULL, gfp_mask, 1, memcgp, false);
css_put(&memcg->css);/* drop extra refcnt */
- if (ret || *memcgp == NULL) {
+ if (ret) {
if (PageAnon(page)) {
lock_page_cgroup(pc);
ClearPageCgroupMigration(pc);
*/
mem_cgroup_uncharge_page(page);
}
+ /* we'll need to revisit this error code (we have -EINTR) */
return -ENOMEM;
}
/*
ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
else
ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
- __mem_cgroup_commit_charge(memcg, page, 1, pc, ctype);
+ __mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype);
return ret;
}
{
struct mem_cgroup *memcg;
struct page_cgroup *pc;
- struct zone *zone;
enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
- unsigned long flags;
if (mem_cgroup_disabled())
return;
if (PageSwapBacked(oldpage))
type = MEM_CGROUP_CHARGE_TYPE_SHMEM;
- zone = page_zone(newpage);
- pc = lookup_page_cgroup(newpage);
/*
* Even if newpage->mapping was NULL before starting replacement,
* the newpage may be on LRU(or pagevec for LRU) already. We lock
* LRU while we overwrite pc->mem_cgroup.
*/
- spin_lock_irqsave(&zone->lru_lock, flags);
- if (PageLRU(newpage))
- del_page_from_lru_list(zone, newpage, page_lru(newpage));
- __mem_cgroup_commit_charge(memcg, newpage, 1, pc, type);
- if (PageLRU(newpage))
- add_page_to_lru_list(zone, newpage, page_lru(newpage));
- spin_unlock_irqrestore(&zone->lru_lock, flags);
+ __mem_cgroup_commit_charge_lrucare(newpage, memcg, type);
}
#ifdef CONFIG_DEBUG_VM
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",
+ printk(KERN_ALERT "pc:%p pc->flags:%lx pc->mem_cgroup:%p\n",
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
pc = lookup_page_cgroup(page);
ret = mem_cgroup_move_parent(page, pc, memcg, GFP_KERNEL);
- if (ret == -ENOMEM)
+ if (ret == -ENOMEM || ret == -EINTR)
break;
if (ret == -EBUSY || ret == -EINVAL) {
mem_cgroup_remove_from_trees(memcg);
free_css_id(&mem_cgroup_subsys, &memcg->css);
- for_each_node_state(node, N_POSSIBLE)
+ for_each_node(node)
free_mem_cgroup_per_zone_info(memcg, node);
free_percpu(memcg->stat);
struct mem_cgroup_tree_per_zone *rtpz;
int tmp, node, zone;
- for_each_node_state(node, N_POSSIBLE) {
+ for_each_node(node) {
tmp = node;
if (!node_state(node, N_NORMAL_MEMORY))
tmp = -1;
rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
if (!rtpn)
- return 1;
+ goto err_cleanup;
soft_limit_tree.rb_tree_per_node[node] = rtpn;
}
}
return 0;
+
+err_cleanup:
+ for_each_node(node) {
+ if (!soft_limit_tree.rb_tree_per_node[node])
+ break;
+ kfree(soft_limit_tree.rb_tree_per_node[node]);
+ soft_limit_tree.rb_tree_per_node[node] = NULL;
+ }
+ return 1;
+
}
static struct cgroup_subsys_state * __ref
if (!memcg)
return ERR_PTR(error);
- for_each_node_state(node, N_POSSIBLE)
+ for_each_node(node)
if (alloc_mem_cgroup_per_zone_info(memcg, node))
goto free_out;
}
ret = __mem_cgroup_try_charge(NULL,
GFP_KERNEL, 1, &memcg, false);
- if (ret || !memcg)
+ if (ret)
/* mem_cgroup_clear_mc() will do uncharge later */
- return -ENOMEM;
+ return ret;
mc.precharge++;
}
return ret;