7512102cf6
When moving tasks from old memcg (with move_charge_at_immigrate on new memcg), followed by removal of old memcg, hit General Protection Fault in mem_cgroup_lru_del_list() (called from release_pages called from free_pages_and_swap_cache from tlb_flush_mmu from tlb_finish_mmu from exit_mmap from mmput from exit_mm from do_exit). Somewhat reproducible, takes a few hours: the old struct mem_cgroup has been freed and poisoned by SLAB_DEBUG, but mem_cgroup_lru_del_list() is still trying to update its stats, and take page off lru before freeing. A task, or a charge, or a page on lru: each secures a memcg against removal. In this case, the last task has been moved out of the old memcg, and it is exiting: anonymous pages are uncharged one by one from the memcg, as they are zapped from its pagetables, so the charge gets down to 0; but the pages themselves are queued in an mmu_gather for freeing. Most of those pages will be on lru (and force_empty is careful to lru_add_drain_all, to add pages from pagevec to lru first), but not necessarily all: perhaps some have been isolated for page reclaim, perhaps some isolated for other reasons. So, force_empty may find no task, no charge and no page on lru, and let the removal proceed. There would still be no problem if these pages were immediately freed; but typically (and the put_page_testzero protocol demands it) they have to be added back to lru before they are found freeable, then removed from lru and freed. We don't see the issue when adding, because the mem_cgroup_iter() loops keep their own reference to the memcg being scanned; but when it comes to mem_cgroup_lru_del_list(). I believe this was not an issue in v3.2: there, PageCgroupAcctLRU and PageCgroupUsed flags were used (like a trick with mirrors) to deflect view of pc->mem_cgroup to the stable root_mem_cgroup when neither set.38c5d72f3e
("memcg: simplify LRU handling by new rule") mercifully removed those convolutions, but left this General Protection Fault. But it's surprisingly easy to restore the old behaviour: just check PageCgroupUsed in mem_cgroup_lru_add_list() (which decides on which lruvec to add), and reset pc to root_mem_cgroup if page is uncharged. A risky change? just going back to how it worked before; testing, and an audit of uses of pc->mem_cgroup, show no problem. And there's a nice bonus: with mem_cgroup_lru_add_list() itself making sure that an uncharged page goes to root lru, mem_cgroup_reset_owner() no longer has any purpose, and we can safely revert4e5f01c2b9
("memcg: clear pc->mem_cgroup if necessary"). Calling update_page_reclaim_stat() after add_page_to_lru_list() in swap.c is not strictly necessary: the lru_lock there, with RCU before memcg structures are freed, makes mem_cgroup_get_reclaim_stat_from_page safe without that; but it seems cleaner to rely on one dependency less. Signed-off-by: Hugh Dickins <hughd@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Konstantin Khlebnikov <khlebnikov@openvz.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
428 lines
11 KiB
C
428 lines
11 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>
|
|
|
|
struct mem_cgroup;
|
|
struct page_cgroup;
|
|
struct page;
|
|
struct mm_struct;
|
|
|
|
/* Stats that can be updated by kernel. */
|
|
enum mem_cgroup_page_stat_item {
|
|
MEMCG_NR_FILE_MAPPED, /* # of pages charged as file rss */
|
|
};
|
|
|
|
struct mem_cgroup_reclaim_cookie {
|
|
struct zone *zone;
|
|
int priority;
|
|
unsigned int generation;
|
|
};
|
|
|
|
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
|
|
/*
|
|
* All "charge" functions with gfp_mask should use GFP_KERNEL or
|
|
* (gfp_mask & GFP_RECLAIM_MASK). In current implementatin, memcg doesn't
|
|
* alloc memory but reclaims memory from all available zones. So, "where I want
|
|
* memory from" bits of gfp_mask has no meaning. So any bits of that field is
|
|
* available but adding a rule is better. charge functions' gfp_mask should
|
|
* be set to GFP_KERNEL or gfp_mask & GFP_RECLAIM_MASK for avoiding ambiguous
|
|
* codes.
|
|
* (Of course, if memcg does memory allocation in future, GFP_KERNEL is sane.)
|
|
*/
|
|
|
|
extern int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm,
|
|
gfp_t gfp_mask);
|
|
/* for swap handling */
|
|
extern int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
|
|
struct page *page, gfp_t mask, struct mem_cgroup **memcgp);
|
|
extern void mem_cgroup_commit_charge_swapin(struct page *page,
|
|
struct mem_cgroup *memcg);
|
|
extern void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg);
|
|
|
|
extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
|
|
gfp_t gfp_mask);
|
|
|
|
struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
|
|
struct lruvec *mem_cgroup_lru_add_list(struct zone *, struct page *,
|
|
enum lru_list);
|
|
void mem_cgroup_lru_del_list(struct page *, enum lru_list);
|
|
void mem_cgroup_lru_del(struct page *);
|
|
struct lruvec *mem_cgroup_lru_move_lists(struct zone *, struct page *,
|
|
enum lru_list, enum lru_list);
|
|
|
|
/* For coalescing uncharge for reducing memcg' overhead*/
|
|
extern void mem_cgroup_uncharge_start(void);
|
|
extern void mem_cgroup_uncharge_end(void);
|
|
|
|
extern void mem_cgroup_uncharge_page(struct page *page);
|
|
extern void mem_cgroup_uncharge_cache_page(struct page *page);
|
|
|
|
extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask);
|
|
int task_in_mem_cgroup(struct task_struct *task, const 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 *try_get_mem_cgroup_from_mm(struct mm_struct *mm);
|
|
|
|
extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
|
|
extern struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont);
|
|
|
|
static inline
|
|
int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
|
|
{
|
|
struct mem_cgroup *memcg;
|
|
rcu_read_lock();
|
|
memcg = mem_cgroup_from_task(rcu_dereference((mm)->owner));
|
|
rcu_read_unlock();
|
|
return cgroup == memcg;
|
|
}
|
|
|
|
extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
|
|
|
|
extern int
|
|
mem_cgroup_prepare_migration(struct page *page,
|
|
struct page *newpage, struct mem_cgroup **memcgp, gfp_t gfp_mask);
|
|
extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
|
|
struct page *oldpage, struct page *newpage, bool migration_ok);
|
|
|
|
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 mem_cgroup *memcg,
|
|
struct zone *zone);
|
|
int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg,
|
|
struct zone *zone);
|
|
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
|
|
unsigned long mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg,
|
|
int nid, int zid, unsigned int lrumask);
|
|
struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
|
|
struct zone *zone);
|
|
struct zone_reclaim_stat*
|
|
mem_cgroup_get_reclaim_stat_from_page(struct page *page);
|
|
extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
|
|
struct task_struct *p);
|
|
extern void mem_cgroup_replace_page_cache(struct page *oldpage,
|
|
struct page *newpage);
|
|
|
|
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
|
|
extern int do_swap_account;
|
|
#endif
|
|
|
|
static inline bool mem_cgroup_disabled(void)
|
|
{
|
|
if (mem_cgroup_subsys.disabled)
|
|
return true;
|
|
return false;
|
|
}
|
|
|
|
void mem_cgroup_update_page_stat(struct page *page,
|
|
enum mem_cgroup_page_stat_item idx,
|
|
int val);
|
|
|
|
static inline void mem_cgroup_inc_page_stat(struct page *page,
|
|
enum mem_cgroup_page_stat_item idx)
|
|
{
|
|
mem_cgroup_update_page_stat(page, idx, 1);
|
|
}
|
|
|
|
static inline void mem_cgroup_dec_page_stat(struct page *page,
|
|
enum mem_cgroup_page_stat_item idx)
|
|
{
|
|
mem_cgroup_update_page_stat(page, idx, -1);
|
|
}
|
|
|
|
unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
|
|
gfp_t gfp_mask,
|
|
unsigned long *total_scanned);
|
|
u64 mem_cgroup_get_limit(struct mem_cgroup *memcg);
|
|
|
|
void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
void mem_cgroup_split_huge_fixup(struct page *head);
|
|
#endif
|
|
|
|
#ifdef CONFIG_DEBUG_VM
|
|
bool mem_cgroup_bad_page_check(struct page *page);
|
|
void mem_cgroup_print_bad_page(struct page *page);
|
|
#endif
|
|
#else /* CONFIG_CGROUP_MEM_RES_CTLR */
|
|
struct mem_cgroup;
|
|
|
|
static inline int mem_cgroup_newpage_charge(struct page *page,
|
|
struct mm_struct *mm, gfp_t gfp_mask)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int mem_cgroup_cache_charge(struct page *page,
|
|
struct mm_struct *mm, gfp_t gfp_mask)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
|
|
struct page *page, gfp_t gfp_mask, struct mem_cgroup **memcgp)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void mem_cgroup_commit_charge_swapin(struct page *page,
|
|
struct mem_cgroup *memcg)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_uncharge_start(void)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_uncharge_end(void)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_uncharge_page(struct page *page)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_uncharge_cache_page(struct page *page)
|
|
{
|
|
}
|
|
|
|
static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
|
|
struct mem_cgroup *memcg)
|
|
{
|
|
return &zone->lruvec;
|
|
}
|
|
|
|
static inline struct lruvec *mem_cgroup_lru_add_list(struct zone *zone,
|
|
struct page *page,
|
|
enum lru_list lru)
|
|
{
|
|
return &zone->lruvec;
|
|
}
|
|
|
|
static inline void mem_cgroup_lru_del_list(struct page *page, enum lru_list lru)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_lru_del(struct page *page)
|
|
{
|
|
}
|
|
|
|
static inline struct lruvec *mem_cgroup_lru_move_lists(struct zone *zone,
|
|
struct page *page,
|
|
enum lru_list from,
|
|
enum lru_list to)
|
|
{
|
|
return &zone->lruvec;
|
|
}
|
|
|
|
static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int mm_match_cgroup(struct mm_struct *mm,
|
|
struct mem_cgroup *memcg)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline int task_in_mem_cgroup(struct task_struct *task,
|
|
const struct mem_cgroup *memcg)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline struct cgroup_subsys_state
|
|
*mem_cgroup_css(struct mem_cgroup *memcg)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int
|
|
mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
|
|
struct mem_cgroup **memcgp, gfp_t gfp_mask)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg,
|
|
struct page *oldpage, struct page *newpage, bool migration_ok)
|
|
{
|
|
}
|
|
|
|
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_get_reclaim_priority(struct mem_cgroup *memcg)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void mem_cgroup_note_reclaim_priority(struct mem_cgroup *memcg,
|
|
int priority)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_record_reclaim_priority(struct mem_cgroup *memcg,
|
|
int priority)
|
|
{
|
|
}
|
|
|
|
static inline bool mem_cgroup_disabled(void)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline int
|
|
mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg, struct zone *zone)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline int
|
|
mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg, struct zone *zone)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline unsigned long
|
|
mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid,
|
|
unsigned int lru_mask)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
|
|
static inline struct zone_reclaim_stat*
|
|
mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, struct zone *zone)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct zone_reclaim_stat*
|
|
mem_cgroup_get_reclaim_stat_from_page(struct page *page)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline void
|
|
mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_inc_page_stat(struct page *page,
|
|
enum mem_cgroup_page_stat_item idx)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_dec_page_stat(struct page *page,
|
|
enum mem_cgroup_page_stat_item 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
|
|
u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
|
|
{
|
|
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)
|
|
{
|
|
}
|
|
static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
|
|
struct page *newpage)
|
|
{
|
|
}
|
|
#endif /* CONFIG_CGROUP_MEM_CONT */
|
|
|
|
#if !defined(CONFIG_CGROUP_MEM_RES_CTLR) || !defined(CONFIG_DEBUG_VM)
|
|
static inline bool
|
|
mem_cgroup_bad_page_check(struct page *page)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline void
|
|
mem_cgroup_print_bad_page(struct page *page)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
enum {
|
|
UNDER_LIMIT,
|
|
SOFT_LIMIT,
|
|
OVER_LIMIT,
|
|
};
|
|
|
|
struct sock;
|
|
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_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_CGROUP_MEM_RES_CTLR_KMEM */
|
|
#endif /* _LINUX_MEMCONTROL_H */
|
|
|