linux-stable/include/linux/memcontrol.h
Andrey Ryabinin e3c1ac586c mm/vmscan: don't mess with pgdat->flags in memcg reclaim
memcg reclaim may alter pgdat->flags based on the state of LRU lists in
cgroup and its children.  PGDAT_WRITEBACK may force kswapd to sleep
congested_wait(), PGDAT_DIRTY may force kswapd to writeback filesystem
pages.  But the worst here is PGDAT_CONGESTED, since it may force all
direct reclaims to stall in wait_iff_congested().  Note that only kswapd
have powers to clear any of these bits.  This might just never happen if
cgroup limits configured that way.  So all direct reclaims will stall as
long as we have some congested bdi in the system.

Leave all pgdat->flags manipulations to kswapd.  kswapd scans the whole
pgdat, only kswapd can clear pgdat->flags once node is balanced, thus
it's reasonable to leave all decisions about node state to kswapd.

Why only kswapd? Why not allow to global direct reclaim change these
flags? It is because currently only kswapd can clear these flags.  I'm
less worried about the case when PGDAT_CONGESTED falsely not set, and
more worried about the case when it falsely set.  If direct reclaimer
sets PGDAT_CONGESTED, do we have guarantee that after the congestion
problem is sorted out, kswapd will be woken up and clear the flag? It
seems like there is no such guarantee.  E.g.  direct reclaimers may
eventually balance pgdat and kswapd simply won't wake up (see
wakeup_kswapd()).

Moving pgdat->flags manipulation to kswapd, means that cgroup2 recalim
now loses its congestion throttling mechanism.  Add per-cgroup
congestion state and throttle cgroup2 reclaimers if memcg is in
congestion state.

Currently there is no need in per-cgroup PGDAT_WRITEBACK and PGDAT_DIRTY
bits since they alter only kswapd behavior.

The problem could be easily demonstrated by creating heavy congestion in
one cgroup:

    echo "+memory" > /sys/fs/cgroup/cgroup.subtree_control
    mkdir -p /sys/fs/cgroup/congester
    echo 512M > /sys/fs/cgroup/congester/memory.max
    echo $$ > /sys/fs/cgroup/congester/cgroup.procs
    /* generate a lot of diry data on slow HDD */
    while true; do dd if=/dev/zero of=/mnt/sdb/zeroes bs=1M count=1024; done &
    ....
    while true; do dd if=/dev/zero of=/mnt/sdb/zeroes bs=1M count=1024; done &

and some job in another cgroup:

    mkdir /sys/fs/cgroup/victim
    echo 128M > /sys/fs/cgroup/victim/memory.max

    # time cat /dev/sda > /dev/null
    real    10m15.054s
    user    0m0.487s
    sys     1m8.505s

According to the tracepoint in wait_iff_congested(), the 'cat' spent 50%
of the time sleeping there.

With the patch, cat don't waste time anymore:

    # time cat /dev/sda > /dev/null
    real    5m32.911s
    user    0m0.411s
    sys     0m56.664s

[aryabinin@virtuozzo.com: congestion state should be per-node]
  Link: http://lkml.kernel.org/r/20180406135215.10057-1-aryabinin@virtuozzo.com
[ayabinin@virtuozzo.com: make congestion state per-cgroup-per-node instead of just per-cgroup[
  Link: http://lkml.kernel.org/r/20180406180254.8970-2-aryabinin@virtuozzo.com
Link: http://lkml.kernel.org/r/20180323152029.11084-5-aryabinin@virtuozzo.com
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Tejun Heo <tj@kernel.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-04-11 10:28:30 -07:00

1208 lines
29 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>
#include <linux/page_counter.h>
#include <linux/vmpressure.h>
#include <linux/eventfd.h>
#include <linux/mm.h>
#include <linux/vmstat.h>
#include <linux/writeback.h>
#include <linux/page-flags.h>
struct mem_cgroup;
struct page;
struct mm_struct;
struct kmem_cache;
/* Cgroup-specific page state, on top of universal node page state */
enum memcg_stat_item {
MEMCG_CACHE = NR_VM_NODE_STAT_ITEMS,
MEMCG_RSS,
MEMCG_RSS_HUGE,
MEMCG_SWAP,
MEMCG_SOCK,
/* XXX: why are these zone and not node counters? */
MEMCG_KERNEL_STACK_KB,
MEMCG_NR_STAT,
};
/* Cgroup-specific events, on top of universal VM events */
enum memcg_event_item {
MEMCG_LOW = NR_VM_EVENT_ITEMS,
MEMCG_HIGH,
MEMCG_MAX,
MEMCG_OOM,
MEMCG_NR_EVENTS,
};
struct mem_cgroup_reclaim_cookie {
pg_data_t *pgdat;
int priority;
unsigned int generation;
};
#ifdef CONFIG_MEMCG
#define MEM_CGROUP_ID_SHIFT 16
#define MEM_CGROUP_ID_MAX USHRT_MAX
struct mem_cgroup_id {
int id;
atomic_t ref;
};
/*
* Per memcg event counter is incremented at every pagein/pageout. With THP,
* it will be incremated by the number of pages. This counter is used for
* for trigger some periodic events. This is straightforward and better
* than using jiffies etc. to handle periodic memcg event.
*/
enum mem_cgroup_events_target {
MEM_CGROUP_TARGET_THRESH,
MEM_CGROUP_TARGET_SOFTLIMIT,
MEM_CGROUP_TARGET_NUMAINFO,
MEM_CGROUP_NTARGETS,
};
struct mem_cgroup_stat_cpu {
long count[MEMCG_NR_STAT];
unsigned long events[MEMCG_NR_EVENTS];
unsigned long nr_page_events;
unsigned long targets[MEM_CGROUP_NTARGETS];
};
struct mem_cgroup_reclaim_iter {
struct mem_cgroup *position;
/* scan generation, increased every round-trip */
unsigned int generation;
};
struct lruvec_stat {
long count[NR_VM_NODE_STAT_ITEMS];
};
/*
* per-zone information in memory controller.
*/
struct mem_cgroup_per_node {
struct lruvec lruvec;
struct lruvec_stat __percpu *lruvec_stat_cpu;
atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS];
unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1];
struct rb_node tree_node; /* RB tree node */
unsigned long usage_in_excess;/* Set to the value by which */
/* the soft limit is exceeded*/
bool on_tree;
bool congested; /* memcg has many dirty pages */
/* backed by a congested BDI */
struct mem_cgroup *memcg; /* Back pointer, we cannot */
/* use container_of */
};
struct mem_cgroup_threshold {
struct eventfd_ctx *eventfd;
unsigned long threshold;
};
/* For threshold */
struct mem_cgroup_threshold_ary {
/* An array index points to threshold just below or equal to usage. */
int current_threshold;
/* Size of entries[] */
unsigned int size;
/* Array of thresholds */
struct mem_cgroup_threshold entries[0];
};
struct mem_cgroup_thresholds {
/* Primary thresholds array */
struct mem_cgroup_threshold_ary *primary;
/*
* Spare threshold array.
* This is needed to make mem_cgroup_unregister_event() "never fail".
* It must be able to store at least primary->size - 1 entries.
*/
struct mem_cgroup_threshold_ary *spare;
};
enum memcg_kmem_state {
KMEM_NONE,
KMEM_ALLOCATED,
KMEM_ONLINE,
};
/*
* The memory controller data structure. The memory controller controls both
* page cache and RSS per cgroup. We would eventually like to provide
* statistics based on the statistics developed by Rik Van Riel for clock-pro,
* to help the administrator determine what knobs to tune.
*/
struct mem_cgroup {
struct cgroup_subsys_state css;
/* Private memcg ID. Used to ID objects that outlive the cgroup */
struct mem_cgroup_id id;
/* Accounted resources */
struct page_counter memory;
struct page_counter swap;
/* Legacy consumer-oriented counters */
struct page_counter memsw;
struct page_counter kmem;
struct page_counter tcpmem;
/* Normal memory consumption range */
unsigned long low;
unsigned long high;
/* Range enforcement for interrupt charges */
struct work_struct high_work;
unsigned long soft_limit;
/* vmpressure notifications */
struct vmpressure vmpressure;
/*
* Should the accounting and control be hierarchical, per subtree?
*/
bool use_hierarchy;
/* protected by memcg_oom_lock */
bool oom_lock;
int under_oom;
int swappiness;
/* OOM-Killer disable */
int oom_kill_disable;
/* handle for "memory.events" */
struct cgroup_file events_file;
/* protect arrays of thresholds */
struct mutex thresholds_lock;
/* thresholds for memory usage. RCU-protected */
struct mem_cgroup_thresholds thresholds;
/* thresholds for mem+swap usage. RCU-protected */
struct mem_cgroup_thresholds memsw_thresholds;
/* For oom notifier event fd */
struct list_head oom_notify;
/*
* Should we move charges of a task when a task is moved into this
* mem_cgroup ? And what type of charges should we move ?
*/
unsigned long move_charge_at_immigrate;
/*
* set > 0 if pages under this cgroup are moving to other cgroup.
*/
atomic_t moving_account;
/* taken only while moving_account > 0 */
spinlock_t move_lock;
struct task_struct *move_lock_task;
unsigned long move_lock_flags;
struct mem_cgroup_stat_cpu __percpu *stat_cpu;
atomic_long_t stat[MEMCG_NR_STAT];
atomic_long_t events[MEMCG_NR_EVENTS];
unsigned long socket_pressure;
/* Legacy tcp memory accounting */
bool tcpmem_active;
int tcpmem_pressure;
#ifndef CONFIG_SLOB
/* Index in the kmem_cache->memcg_params.memcg_caches array */
int kmemcg_id;
enum memcg_kmem_state kmem_state;
struct list_head kmem_caches;
#endif
int last_scanned_node;
#if MAX_NUMNODES > 1
nodemask_t scan_nodes;
atomic_t numainfo_events;
atomic_t numainfo_updating;
#endif
#ifdef CONFIG_CGROUP_WRITEBACK
struct list_head cgwb_list;
struct wb_domain cgwb_domain;
#endif
/* List of events which userspace want to receive */
struct list_head event_list;
spinlock_t event_list_lock;
struct mem_cgroup_per_node *nodeinfo[0];
/* WARNING: nodeinfo must be the last member here */
};
/*
* size of first charge trial. "32" comes from vmscan.c's magic value.
* TODO: maybe necessary to use big numbers in big irons.
*/
#define MEMCG_CHARGE_BATCH 32U
extern struct mem_cgroup *root_mem_cgroup;
static inline bool mem_cgroup_disabled(void)
{
return !cgroup_subsys_enabled(memory_cgrp_subsys);
}
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,
bool compound);
void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
bool lrucare, bool compound);
void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
bool compound);
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);
static struct mem_cgroup_per_node *
mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
{
return memcg->nodeinfo[nid];
}
/**
* mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
* @node: node of the wanted lruvec
* @memcg: memcg of the wanted lruvec
*
* Returns the lru list vector holding pages for a given @node or a given
* @memcg and @zone. This can be the node lruvec, if the memory controller
* is disabled.
*/
static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
struct mem_cgroup *memcg)
{
struct mem_cgroup_per_node *mz;
struct lruvec *lruvec;
if (mem_cgroup_disabled()) {
lruvec = node_lruvec(pgdat);
goto out;
}
mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
lruvec = &mz->lruvec;
out:
/*
* Since a node can be onlined after the mem_cgroup was created,
* we have to be prepared to initialize lruvec->pgdat here;
* and if offlined then reonlined, we need to reinitialize it.
*/
if (unlikely(lruvec->pgdat != pgdat))
lruvec->pgdat = pgdat;
return lruvec;
}
struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
static inline
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
return css ? container_of(css, struct mem_cgroup, css) : NULL;
}
#define mem_cgroup_from_counter(counter, member) \
container_of(counter, struct mem_cgroup, member)
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 *);
int mem_cgroup_scan_tasks(struct mem_cgroup *,
int (*)(struct task_struct *, void *), void *);
static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
{
if (mem_cgroup_disabled())
return 0;
return memcg->id.id;
}
struct mem_cgroup *mem_cgroup_from_id(unsigned short id);
static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
{
struct mem_cgroup_per_node *mz;
if (mem_cgroup_disabled())
return NULL;
mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
return mz->memcg;
}
/**
* parent_mem_cgroup - find the accounting parent of a memcg
* @memcg: memcg whose parent to find
*
* Returns the parent memcg, or NULL if this is the root or the memory
* controller is in legacy no-hierarchy mode.
*/
static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
{
if (!memcg->memory.parent)
return NULL;
return mem_cgroup_from_counter(memcg->memory.parent, memory);
}
static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
struct mem_cgroup *root)
{
if (root == memcg)
return true;
if (!root->use_hierarchy)
return false;
return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
}
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;
}
struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
ino_t page_cgroup_ino(struct page *page);
static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
{
if (mem_cgroup_disabled())
return true;
return !!(memcg->css.flags & CSS_ONLINE);
}
/*
* For memory reclaim.
*/
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
int zid, int nr_pages);
unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
int nid, unsigned int lru_mask);
static inline
unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
{
struct mem_cgroup_per_node *mz;
unsigned long nr_pages = 0;
int zid;
mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
for (zid = 0; zid < MAX_NR_ZONES; zid++)
nr_pages += mz->lru_zone_size[zid][lru];
return nr_pages;
}
static inline
unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
enum lru_list lru, int zone_idx)
{
struct mem_cgroup_per_node *mz;
mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
return mz->lru_zone_size[zone_idx][lru];
}
void mem_cgroup_handle_over_high(void);
unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg);
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_may_oom);
current->memcg_may_oom = 1;
}
static inline void mem_cgroup_oom_disable(void)
{
WARN_ON(!current->memcg_may_oom);
current->memcg_may_oom = 0;
}
static inline bool task_in_memcg_oom(struct task_struct *p)
{
return p->memcg_in_oom;
}
bool mem_cgroup_oom_synchronize(bool wait);
#ifdef CONFIG_MEMCG_SWAP
extern int do_swap_account;
#endif
struct mem_cgroup *lock_page_memcg(struct page *page);
void __unlock_page_memcg(struct mem_cgroup *memcg);
void unlock_page_memcg(struct page *page);
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
int idx)
{
long x = atomic_long_read(&memcg->stat[idx]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void __mod_memcg_state(struct mem_cgroup *memcg,
int idx, int val)
{
long x;
if (mem_cgroup_disabled())
return;
x = val + __this_cpu_read(memcg->stat_cpu->count[idx]);
if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
atomic_long_add(x, &memcg->stat[idx]);
x = 0;
}
__this_cpu_write(memcg->stat_cpu->count[idx], x);
}
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void mod_memcg_state(struct mem_cgroup *memcg,
int idx, int val)
{
unsigned long flags;
local_irq_save(flags);
__mod_memcg_state(memcg, idx, val);
local_irq_restore(flags);
}
/**
* mod_memcg_page_state - update page state statistics
* @page: the page
* @idx: page state item to account
* @val: number of pages (positive or negative)
*
* The @page must be locked or the caller must use lock_page_memcg()
* to prevent double accounting when the page is concurrently being
* moved to another memcg:
*
* lock_page(page) or lock_page_memcg(page)
* if (TestClearPageState(page))
* mod_memcg_page_state(page, state, -1);
* unlock_page(page) or unlock_page_memcg(page)
*
* Kernel pages are an exception to this, since they'll never move.
*/
static inline void __mod_memcg_page_state(struct page *page,
int idx, int val)
{
if (page->mem_cgroup)
__mod_memcg_state(page->mem_cgroup, idx, val);
}
static inline void mod_memcg_page_state(struct page *page,
int idx, int val)
{
if (page->mem_cgroup)
mod_memcg_state(page->mem_cgroup, idx, val);
}
static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
enum node_stat_item idx)
{
struct mem_cgroup_per_node *pn;
long x;
if (mem_cgroup_disabled())
return node_page_state(lruvec_pgdat(lruvec), idx);
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
x = atomic_long_read(&pn->lruvec_stat[idx]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
static inline void __mod_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
{
struct mem_cgroup_per_node *pn;
long x;
/* Update node */
__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
if (mem_cgroup_disabled())
return;
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
/* Update memcg */
__mod_memcg_state(pn->memcg, idx, val);
/* Update lruvec */
x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
atomic_long_add(x, &pn->lruvec_stat[idx]);
x = 0;
}
__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
}
static inline void mod_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
{
unsigned long flags;
local_irq_save(flags);
__mod_lruvec_state(lruvec, idx, val);
local_irq_restore(flags);
}
static inline void __mod_lruvec_page_state(struct page *page,
enum node_stat_item idx, int val)
{
pg_data_t *pgdat = page_pgdat(page);
struct lruvec *lruvec;
/* Untracked pages have no memcg, no lruvec. Update only the node */
if (!page->mem_cgroup) {
__mod_node_page_state(pgdat, idx, val);
return;
}
lruvec = mem_cgroup_lruvec(pgdat, page->mem_cgroup);
__mod_lruvec_state(lruvec, idx, val);
}
static inline void mod_lruvec_page_state(struct page *page,
enum node_stat_item idx, int val)
{
unsigned long flags;
local_irq_save(flags);
__mod_lruvec_page_state(page, idx, val);
local_irq_restore(flags);
}
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
gfp_t gfp_mask,
unsigned long *total_scanned);
/* idx can be of type enum memcg_event_item or vm_event_item */
static inline void __count_memcg_events(struct mem_cgroup *memcg,
int idx, unsigned long count)
{
unsigned long x;
if (mem_cgroup_disabled())
return;
x = count + __this_cpu_read(memcg->stat_cpu->events[idx]);
if (unlikely(x > MEMCG_CHARGE_BATCH)) {
atomic_long_add(x, &memcg->events[idx]);
x = 0;
}
__this_cpu_write(memcg->stat_cpu->events[idx], x);
}
static inline void count_memcg_events(struct mem_cgroup *memcg,
int idx, unsigned long count)
{
unsigned long flags;
local_irq_save(flags);
__count_memcg_events(memcg, idx, count);
local_irq_restore(flags);
}
/* idx can be of type enum memcg_event_item or vm_event_item */
static inline void count_memcg_page_event(struct page *page,
int idx)
{
if (page->mem_cgroup)
count_memcg_events(page->mem_cgroup, idx, 1);
}
static inline void count_memcg_event_mm(struct mm_struct *mm,
enum vm_event_item idx)
{
struct mem_cgroup *memcg;
if (mem_cgroup_disabled())
return;
rcu_read_lock();
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
if (likely(memcg)) {
count_memcg_events(memcg, idx, 1);
if (idx == OOM_KILL)
cgroup_file_notify(&memcg->events_file);
}
rcu_read_unlock();
}
static inline void mem_cgroup_event(struct mem_cgroup *memcg,
enum memcg_event_item event)
{
count_memcg_events(memcg, event, 1);
cgroup_file_notify(&memcg->events_file);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void mem_cgroup_split_huge_fixup(struct page *head);
#endif
#else /* CONFIG_MEMCG */
#define MEM_CGROUP_ID_SHIFT 0
#define MEM_CGROUP_ID_MAX 0
struct mem_cgroup;
static inline bool mem_cgroup_disabled(void)
{
return true;
}
static inline void mem_cgroup_event(struct mem_cgroup *memcg,
enum memcg_event_item event)
{
}
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,
bool compound)
{
*memcgp = NULL;
return 0;
}
static inline void mem_cgroup_commit_charge(struct page *page,
struct mem_cgroup *memcg,
bool lrucare, bool compound)
{
}
static inline void mem_cgroup_cancel_charge(struct page *page,
struct mem_cgroup *memcg,
bool compound)
{
}
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 *old, struct page *new)
{
}
static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
struct mem_cgroup *memcg)
{
return node_lruvec(pgdat);
}
static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
struct pglist_data *pgdat)
{
return &pgdat->lruvec;
}
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 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 int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
int (*fn)(struct task_struct *, void *), void *arg)
{
return 0;
}
static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
{
return 0;
}
static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
{
WARN_ON_ONCE(id);
/* XXX: This should always return root_mem_cgroup */
return NULL;
}
static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
{
return NULL;
}
static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
{
return true;
}
static inline unsigned long
mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
{
return 0;
}
static inline
unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
enum lru_list lru, int zone_idx)
{
return 0;
}
static inline unsigned long
mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
int nid, unsigned int lru_mask)
{
return 0;
}
static inline unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg)
{
return 0;
}
static inline void
mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
{
}
static inline struct mem_cgroup *lock_page_memcg(struct page *page)
{
return NULL;
}
static inline void __unlock_page_memcg(struct mem_cgroup *memcg)
{
}
static inline void unlock_page_memcg(struct page *page)
{
}
static inline void mem_cgroup_handle_over_high(void)
{
}
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 unsigned long memcg_page_state(struct mem_cgroup *memcg,
int idx)
{
return 0;
}
static inline void __mod_memcg_state(struct mem_cgroup *memcg,
int idx,
int nr)
{
}
static inline void mod_memcg_state(struct mem_cgroup *memcg,
int idx,
int nr)
{
}
static inline void __mod_memcg_page_state(struct page *page,
int idx,
int nr)
{
}
static inline void mod_memcg_page_state(struct page *page,
int idx,
int nr)
{
}
static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
enum node_stat_item idx)
{
return node_page_state(lruvec_pgdat(lruvec), idx);
}
static inline void __mod_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
{
__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
}
static inline void mod_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
{
mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
}
static inline void __mod_lruvec_page_state(struct page *page,
enum node_stat_item idx, int val)
{
__mod_node_page_state(page_pgdat(page), idx, val);
}
static inline void mod_lruvec_page_state(struct page *page,
enum node_stat_item idx, int val)
{
mod_node_page_state(page_pgdat(page), idx, val);
}
static inline
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, 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 count_memcg_events(struct mem_cgroup *memcg,
enum vm_event_item idx,
unsigned long count)
{
}
static inline void count_memcg_page_event(struct page *page,
int idx)
{
}
static inline
void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
{
}
#endif /* CONFIG_MEMCG */
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void __inc_memcg_state(struct mem_cgroup *memcg,
int idx)
{
__mod_memcg_state(memcg, idx, 1);
}
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void __dec_memcg_state(struct mem_cgroup *memcg,
int idx)
{
__mod_memcg_state(memcg, idx, -1);
}
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void __inc_memcg_page_state(struct page *page,
int idx)
{
__mod_memcg_page_state(page, idx, 1);
}
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void __dec_memcg_page_state(struct page *page,
int idx)
{
__mod_memcg_page_state(page, idx, -1);
}
static inline void __inc_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx)
{
__mod_lruvec_state(lruvec, idx, 1);
}
static inline void __dec_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx)
{
__mod_lruvec_state(lruvec, idx, -1);
}
static inline void __inc_lruvec_page_state(struct page *page,
enum node_stat_item idx)
{
__mod_lruvec_page_state(page, idx, 1);
}
static inline void __dec_lruvec_page_state(struct page *page,
enum node_stat_item idx)
{
__mod_lruvec_page_state(page, idx, -1);
}
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void inc_memcg_state(struct mem_cgroup *memcg,
int idx)
{
mod_memcg_state(memcg, idx, 1);
}
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void dec_memcg_state(struct mem_cgroup *memcg,
int idx)
{
mod_memcg_state(memcg, idx, -1);
}
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void inc_memcg_page_state(struct page *page,
int idx)
{
mod_memcg_page_state(page, idx, 1);
}
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void dec_memcg_page_state(struct page *page,
int idx)
{
mod_memcg_page_state(page, idx, -1);
}
static inline void inc_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx)
{
mod_lruvec_state(lruvec, idx, 1);
}
static inline void dec_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx)
{
mod_lruvec_state(lruvec, idx, -1);
}
static inline void inc_lruvec_page_state(struct page *page,
enum node_stat_item idx)
{
mod_lruvec_page_state(page, idx, 1);
}
static inline void dec_lruvec_page_state(struct page *page,
enum node_stat_item idx)
{
mod_lruvec_page_state(page, idx, -1);
}
#ifdef CONFIG_CGROUP_WRITEBACK
struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg);
struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
unsigned long *pheadroom, unsigned long *pdirty,
unsigned long *pwriteback);
#else /* CONFIG_CGROUP_WRITEBACK */
static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
{
return NULL;
}
static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
unsigned long *pfilepages,
unsigned long *pheadroom,
unsigned long *pdirty,
unsigned long *pwriteback)
{
}
#endif /* CONFIG_CGROUP_WRITEBACK */
struct sock;
bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
#ifdef CONFIG_MEMCG
extern struct static_key_false memcg_sockets_enabled_key;
#define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
void mem_cgroup_sk_alloc(struct sock *sk);
void mem_cgroup_sk_free(struct sock *sk);
static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
{
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure)
return true;
do {
if (time_before(jiffies, memcg->socket_pressure))
return true;
} while ((memcg = parent_mem_cgroup(memcg)));
return false;
}
#else
#define mem_cgroup_sockets_enabled 0
static inline void mem_cgroup_sk_alloc(struct sock *sk) { };
static inline void mem_cgroup_sk_free(struct sock *sk) { };
static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
{
return false;
}
#endif
struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
void memcg_kmem_put_cache(struct kmem_cache *cachep);
int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
struct mem_cgroup *memcg);
int memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
void memcg_kmem_uncharge(struct page *page, int order);
#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
extern struct static_key_false memcg_kmem_enabled_key;
extern struct workqueue_struct *memcg_kmem_cache_wq;
extern int memcg_nr_cache_ids;
void memcg_get_cache_ids(void);
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_branch_unlikely(&memcg_kmem_enabled_key);
}
/*
* helper for accessing a memcg's index. It will be used as an index in the
* child cache array in kmem_cache, and also to derive its name. This function
* will return -1 when this is not a kmem-limited memcg.
*/
static inline int memcg_cache_id(struct mem_cgroup *memcg)
{
return memcg ? memcg->kmemcg_id : -1;
}
#else
#define for_each_memcg_cache_index(_idx) \
for (; NULL; )
static inline bool memcg_kmem_enabled(void)
{
return false;
}
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)
{
}
#endif /* CONFIG_MEMCG && !CONFIG_SLOB */
#endif /* _LINUX_MEMCONTROL_H */