616 lines
16 KiB
C
616 lines
16 KiB
C
/* memcontrol.h - Memory Controller
|
|
*
|
|
* Copyright IBM Corporation, 2007
|
|
* Author Balbir Singh <balbir@linux.vnet.ibm.com>
|
|
*
|
|
* Copyright 2007 OpenVZ SWsoft Inc
|
|
* Author: Pavel Emelianov <xemul@openvz.org>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*/
|
|
|
|
#ifndef _LINUX_MEMCONTROL_H
|
|
#define _LINUX_MEMCONTROL_H
|
|
#include <linux/cgroup.h>
|
|
#include <linux/vm_event_item.h>
|
|
#include <linux/hardirq.h>
|
|
#include <linux/jump_label.h>
|
|
|
|
struct mem_cgroup;
|
|
struct page;
|
|
struct mm_struct;
|
|
struct kmem_cache;
|
|
|
|
/*
|
|
* The corresponding mem_cgroup_stat_names is defined in mm/memcontrol.c,
|
|
* These two lists should keep in accord with each other.
|
|
*/
|
|
enum mem_cgroup_stat_index {
|
|
/*
|
|
* For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
|
|
*/
|
|
MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
|
|
MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
|
|
MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */
|
|
MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
|
|
MEM_CGROUP_STAT_DIRTY, /* # of dirty pages in page cache */
|
|
MEM_CGROUP_STAT_WRITEBACK, /* # of pages under writeback */
|
|
MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
|
|
MEM_CGROUP_STAT_NSTATS,
|
|
};
|
|
|
|
struct mem_cgroup_reclaim_cookie {
|
|
struct zone *zone;
|
|
int priority;
|
|
unsigned int generation;
|
|
};
|
|
|
|
enum mem_cgroup_events_index {
|
|
MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */
|
|
MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */
|
|
MEM_CGROUP_EVENTS_PGFAULT, /* # of page-faults */
|
|
MEM_CGROUP_EVENTS_PGMAJFAULT, /* # of major page-faults */
|
|
MEM_CGROUP_EVENTS_NSTATS,
|
|
/* default hierarchy events */
|
|
MEMCG_LOW = MEM_CGROUP_EVENTS_NSTATS,
|
|
MEMCG_HIGH,
|
|
MEMCG_MAX,
|
|
MEMCG_OOM,
|
|
MEMCG_NR_EVENTS,
|
|
};
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
extern struct cgroup_subsys_state *mem_cgroup_root_css;
|
|
|
|
void mem_cgroup_events(struct mem_cgroup *memcg,
|
|
enum mem_cgroup_events_index idx,
|
|
unsigned int nr);
|
|
|
|
bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
|
|
|
|
int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
|
|
gfp_t gfp_mask, struct mem_cgroup **memcgp);
|
|
void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
|
|
bool lrucare);
|
|
void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg);
|
|
void mem_cgroup_uncharge(struct page *page);
|
|
void mem_cgroup_uncharge_list(struct list_head *page_list);
|
|
|
|
void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
|
|
bool lrucare);
|
|
|
|
struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
|
|
struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
|
|
|
|
bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
|
|
struct mem_cgroup *root);
|
|
bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
|
|
|
|
extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
|
|
extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
|
|
|
|
extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
|
|
extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css);
|
|
|
|
static inline bool mm_match_cgroup(struct mm_struct *mm,
|
|
struct mem_cgroup *memcg)
|
|
{
|
|
struct mem_cgroup *task_memcg;
|
|
bool match = false;
|
|
|
|
rcu_read_lock();
|
|
task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
|
|
if (task_memcg)
|
|
match = mem_cgroup_is_descendant(task_memcg, memcg);
|
|
rcu_read_unlock();
|
|
return match;
|
|
}
|
|
|
|
extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
|
|
extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
|
|
|
|
struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
|
|
struct mem_cgroup *,
|
|
struct mem_cgroup_reclaim_cookie *);
|
|
void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
|
|
|
|
/*
|
|
* For memory reclaim.
|
|
*/
|
|
int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec);
|
|
bool mem_cgroup_lruvec_online(struct lruvec *lruvec);
|
|
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
|
|
unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list);
|
|
void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int);
|
|
extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
|
|
struct task_struct *p);
|
|
|
|
static inline void mem_cgroup_oom_enable(void)
|
|
{
|
|
WARN_ON(current->memcg_oom.may_oom);
|
|
current->memcg_oom.may_oom = 1;
|
|
}
|
|
|
|
static inline void mem_cgroup_oom_disable(void)
|
|
{
|
|
WARN_ON(!current->memcg_oom.may_oom);
|
|
current->memcg_oom.may_oom = 0;
|
|
}
|
|
|
|
static inline bool task_in_memcg_oom(struct task_struct *p)
|
|
{
|
|
return p->memcg_oom.memcg;
|
|
}
|
|
|
|
bool mem_cgroup_oom_synchronize(bool wait);
|
|
|
|
#ifdef CONFIG_MEMCG_SWAP
|
|
extern int do_swap_account;
|
|
#endif
|
|
|
|
static inline bool mem_cgroup_disabled(void)
|
|
{
|
|
if (memory_cgrp_subsys.disabled)
|
|
return true;
|
|
return false;
|
|
}
|
|
|
|
struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page);
|
|
void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
|
|
enum mem_cgroup_stat_index idx, int val);
|
|
void mem_cgroup_end_page_stat(struct mem_cgroup *memcg);
|
|
|
|
static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
|
|
enum mem_cgroup_stat_index idx)
|
|
{
|
|
mem_cgroup_update_page_stat(memcg, idx, 1);
|
|
}
|
|
|
|
static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg,
|
|
enum mem_cgroup_stat_index idx)
|
|
{
|
|
mem_cgroup_update_page_stat(memcg, idx, -1);
|
|
}
|
|
|
|
unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
|
|
gfp_t gfp_mask,
|
|
unsigned long *total_scanned);
|
|
|
|
void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
|
|
static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
|
|
enum vm_event_item idx)
|
|
{
|
|
if (mem_cgroup_disabled())
|
|
return;
|
|
__mem_cgroup_count_vm_event(mm, idx);
|
|
}
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
void mem_cgroup_split_huge_fixup(struct page *head);
|
|
#endif
|
|
|
|
#else /* CONFIG_MEMCG */
|
|
struct mem_cgroup;
|
|
|
|
#define mem_cgroup_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
|
|
|
|
static inline void mem_cgroup_events(struct mem_cgroup *memcg,
|
|
enum mem_cgroup_events_index idx,
|
|
unsigned int nr)
|
|
{
|
|
}
|
|
|
|
static inline bool mem_cgroup_low(struct mem_cgroup *root,
|
|
struct mem_cgroup *memcg)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
|
|
gfp_t gfp_mask,
|
|
struct mem_cgroup **memcgp)
|
|
{
|
|
*memcgp = NULL;
|
|
return 0;
|
|
}
|
|
|
|
static inline void mem_cgroup_commit_charge(struct page *page,
|
|
struct mem_cgroup *memcg,
|
|
bool lrucare)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_cancel_charge(struct page *page,
|
|
struct mem_cgroup *memcg)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_uncharge(struct page *page)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_migrate(struct page *oldpage,
|
|
struct page *newpage,
|
|
bool lrucare)
|
|
{
|
|
}
|
|
|
|
static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
|
|
struct mem_cgroup *memcg)
|
|
{
|
|
return &zone->lruvec;
|
|
}
|
|
|
|
static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
|
|
struct zone *zone)
|
|
{
|
|
return &zone->lruvec;
|
|
}
|
|
|
|
static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline bool mm_match_cgroup(struct mm_struct *mm,
|
|
struct mem_cgroup *memcg)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline bool task_in_mem_cgroup(struct task_struct *task,
|
|
const struct mem_cgroup *memcg)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline struct cgroup_subsys_state
|
|
*mem_cgroup_css(struct mem_cgroup *memcg)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct mem_cgroup *
|
|
mem_cgroup_iter(struct mem_cgroup *root,
|
|
struct mem_cgroup *prev,
|
|
struct mem_cgroup_reclaim_cookie *reclaim)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline void mem_cgroup_iter_break(struct mem_cgroup *root,
|
|
struct mem_cgroup *prev)
|
|
{
|
|
}
|
|
|
|
static inline bool mem_cgroup_disabled(void)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline int
|
|
mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline unsigned long
|
|
mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void
|
|
mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
|
|
int increment)
|
|
{
|
|
}
|
|
|
|
static inline void
|
|
mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
|
|
{
|
|
}
|
|
|
|
static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_oom_enable(void)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_oom_disable(void)
|
|
{
|
|
}
|
|
|
|
static inline bool task_in_memcg_oom(struct task_struct *p)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool mem_cgroup_oom_synchronize(bool wait)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
|
|
enum mem_cgroup_stat_index idx)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg,
|
|
enum mem_cgroup_stat_index idx)
|
|
{
|
|
}
|
|
|
|
static inline
|
|
unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
|
|
gfp_t gfp_mask,
|
|
unsigned long *total_scanned)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void mem_cgroup_split_huge_fixup(struct page *head)
|
|
{
|
|
}
|
|
|
|
static inline
|
|
void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
|
|
{
|
|
}
|
|
#endif /* CONFIG_MEMCG */
|
|
|
|
enum {
|
|
UNDER_LIMIT,
|
|
SOFT_LIMIT,
|
|
OVER_LIMIT,
|
|
};
|
|
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
|
struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg);
|
|
#endif
|
|
|
|
struct sock;
|
|
#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM)
|
|
void sock_update_memcg(struct sock *sk);
|
|
void sock_release_memcg(struct sock *sk);
|
|
#else
|
|
static inline void sock_update_memcg(struct sock *sk)
|
|
{
|
|
}
|
|
static inline void sock_release_memcg(struct sock *sk)
|
|
{
|
|
}
|
|
#endif /* CONFIG_INET && CONFIG_MEMCG_KMEM */
|
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
extern struct static_key memcg_kmem_enabled_key;
|
|
|
|
extern int memcg_nr_cache_ids;
|
|
extern void memcg_get_cache_ids(void);
|
|
extern void memcg_put_cache_ids(void);
|
|
|
|
/*
|
|
* Helper macro to loop through all memcg-specific caches. Callers must still
|
|
* check if the cache is valid (it is either valid or NULL).
|
|
* the slab_mutex must be held when looping through those caches
|
|
*/
|
|
#define for_each_memcg_cache_index(_idx) \
|
|
for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++)
|
|
|
|
static inline bool memcg_kmem_enabled(void)
|
|
{
|
|
return static_key_false(&memcg_kmem_enabled_key);
|
|
}
|
|
|
|
bool memcg_kmem_is_active(struct mem_cgroup *memcg);
|
|
|
|
/*
|
|
* In general, we'll do everything in our power to not incur in any overhead
|
|
* for non-memcg users for the kmem functions. Not even a function call, if we
|
|
* can avoid it.
|
|
*
|
|
* Therefore, we'll inline all those functions so that in the best case, we'll
|
|
* see that kmemcg is off for everybody and proceed quickly. If it is on,
|
|
* we'll still do most of the flag checking inline. We check a lot of
|
|
* conditions, but because they are pretty simple, they are expected to be
|
|
* fast.
|
|
*/
|
|
bool __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg,
|
|
int order);
|
|
void __memcg_kmem_commit_charge(struct page *page,
|
|
struct mem_cgroup *memcg, int order);
|
|
void __memcg_kmem_uncharge_pages(struct page *page, int order);
|
|
|
|
int memcg_cache_id(struct mem_cgroup *memcg);
|
|
|
|
struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
|
|
void __memcg_kmem_put_cache(struct kmem_cache *cachep);
|
|
|
|
struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr);
|
|
|
|
int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
|
|
unsigned long nr_pages);
|
|
void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages);
|
|
|
|
/**
|
|
* memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
|
|
* @gfp: the gfp allocation flags.
|
|
* @memcg: a pointer to the memcg this was charged against.
|
|
* @order: allocation order.
|
|
*
|
|
* returns true if the memcg where the current task belongs can hold this
|
|
* allocation.
|
|
*
|
|
* We return true automatically if this allocation is not to be accounted to
|
|
* any memcg.
|
|
*/
|
|
static inline bool
|
|
memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
|
|
{
|
|
if (!memcg_kmem_enabled())
|
|
return true;
|
|
|
|
/*
|
|
* __GFP_NOFAIL allocations will move on even if charging is not
|
|
* possible. Therefore we don't even try, and have this allocation
|
|
* unaccounted. We could in theory charge it forcibly, but we hope
|
|
* those allocations are rare, and won't be worth the trouble.
|
|
*/
|
|
if (gfp & __GFP_NOFAIL)
|
|
return true;
|
|
if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
|
|
return true;
|
|
|
|
/* If the test is dying, just let it go. */
|
|
if (unlikely(fatal_signal_pending(current)))
|
|
return true;
|
|
|
|
return __memcg_kmem_newpage_charge(gfp, memcg, order);
|
|
}
|
|
|
|
/**
|
|
* memcg_kmem_uncharge_pages: uncharge pages from memcg
|
|
* @page: pointer to struct page being freed
|
|
* @order: allocation order.
|
|
*/
|
|
static inline void
|
|
memcg_kmem_uncharge_pages(struct page *page, int order)
|
|
{
|
|
if (memcg_kmem_enabled())
|
|
__memcg_kmem_uncharge_pages(page, order);
|
|
}
|
|
|
|
/**
|
|
* memcg_kmem_commit_charge: embeds correct memcg in a page
|
|
* @page: pointer to struct page recently allocated
|
|
* @memcg: the memcg structure we charged against
|
|
* @order: allocation order.
|
|
*
|
|
* Needs to be called after memcg_kmem_newpage_charge, regardless of success or
|
|
* failure of the allocation. if @page is NULL, this function will revert the
|
|
* charges. Otherwise, it will commit @page to @memcg.
|
|
*/
|
|
static inline void
|
|
memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
|
|
{
|
|
if (memcg_kmem_enabled() && memcg)
|
|
__memcg_kmem_commit_charge(page, memcg, order);
|
|
}
|
|
|
|
/**
|
|
* memcg_kmem_get_cache: selects the correct per-memcg cache for allocation
|
|
* @cachep: the original global kmem cache
|
|
* @gfp: allocation flags.
|
|
*
|
|
* All memory allocated from a per-memcg cache is charged to the owner memcg.
|
|
*/
|
|
static __always_inline struct kmem_cache *
|
|
memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
|
|
{
|
|
if (!memcg_kmem_enabled())
|
|
return cachep;
|
|
if (gfp & __GFP_NOFAIL)
|
|
return cachep;
|
|
if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
|
|
return cachep;
|
|
if (unlikely(fatal_signal_pending(current)))
|
|
return cachep;
|
|
|
|
return __memcg_kmem_get_cache(cachep);
|
|
}
|
|
|
|
static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
|
|
{
|
|
if (memcg_kmem_enabled())
|
|
__memcg_kmem_put_cache(cachep);
|
|
}
|
|
|
|
static __always_inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
|
|
{
|
|
if (!memcg_kmem_enabled())
|
|
return NULL;
|
|
return __mem_cgroup_from_kmem(ptr);
|
|
}
|
|
#else
|
|
#define for_each_memcg_cache_index(_idx) \
|
|
for (; NULL; )
|
|
|
|
static inline bool memcg_kmem_enabled(void)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool
|
|
memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline void memcg_kmem_uncharge_pages(struct page *page, int order)
|
|
{
|
|
}
|
|
|
|
static inline void
|
|
memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
|
|
{
|
|
}
|
|
|
|
static inline int memcg_cache_id(struct mem_cgroup *memcg)
|
|
{
|
|
return -1;
|
|
}
|
|
|
|
static inline void memcg_get_cache_ids(void)
|
|
{
|
|
}
|
|
|
|
static inline void memcg_put_cache_ids(void)
|
|
{
|
|
}
|
|
|
|
static inline struct kmem_cache *
|
|
memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
|
|
{
|
|
return cachep;
|
|
}
|
|
|
|
static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
|
|
{
|
|
}
|
|
|
|
static inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
|
|
{
|
|
return NULL;
|
|
}
|
|
#endif /* CONFIG_MEMCG_KMEM */
|
|
#endif /* _LINUX_MEMCONTROL_H */
|
|
|