ae41be3742
While using memory control cgroup, page-migration under it works as following.
==
1. uncharge all refs at try to unmap.
2. charge regs again remove_migration_ptes()
==
This is simple but has following problems.
==
The page is uncharged and charged back again if *mapped*.
- This means that cgroup before migration can be different from one after
migration
- If page is not mapped but charged as page cache, charge is just ignored
(because not mapped, it will not be uncharged before migration)
This is memory leak.
==
This patch tries to keep memory cgroup at page migration by increasing
one refcnt during it. 3 functions are added.
mem_cgroup_prepare_migration() --- increase refcnt of page->page_cgroup
mem_cgroup_end_migration() --- decrease refcnt of page->page_cgroup
mem_cgroup_page_migration() --- copy page->page_cgroup from old page to
new page.
During migration
- old page is under PG_locked.
- new page is under PG_locked, too.
- both old page and new page is not on LRU.
These 3 facts guarantee that page_cgroup() migration has no race.
Tested and worked well in x86_64/fake-NUMA box.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Paul Menage <menage@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Kirill Korotaev <dev@sw.ru>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: David Rientjes <rientjes@google.com>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
142 lines
3.6 KiB
C
142 lines
3.6 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/rcupdate.h>
|
|
#include <linux/mm.h>
|
|
|
|
struct mem_cgroup;
|
|
struct page_cgroup;
|
|
struct page;
|
|
struct mm_struct;
|
|
|
|
#ifdef CONFIG_CGROUP_MEM_CONT
|
|
|
|
extern void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p);
|
|
extern void mm_free_cgroup(struct mm_struct *mm);
|
|
extern void page_assign_page_cgroup(struct page *page,
|
|
struct page_cgroup *pc);
|
|
extern struct page_cgroup *page_get_page_cgroup(struct page *page);
|
|
extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
|
|
gfp_t gfp_mask);
|
|
extern void mem_cgroup_uncharge(struct page_cgroup *pc);
|
|
extern void mem_cgroup_move_lists(struct page_cgroup *pc, bool active);
|
|
extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
|
|
struct list_head *dst,
|
|
unsigned long *scanned, int order,
|
|
int mode, struct zone *z,
|
|
struct mem_cgroup *mem_cont,
|
|
int active);
|
|
extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
|
|
extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
|
|
gfp_t gfp_mask);
|
|
int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
|
|
|
|
static inline struct mem_cgroup *mm_cgroup(const struct mm_struct *mm)
|
|
{
|
|
return rcu_dereference(mm->mem_cgroup);
|
|
}
|
|
|
|
static inline void mem_cgroup_uncharge_page(struct page *page)
|
|
{
|
|
mem_cgroup_uncharge(page_get_page_cgroup(page));
|
|
}
|
|
|
|
extern int mem_cgroup_prepare_migration(struct page *page);
|
|
extern void mem_cgroup_end_migration(struct page *page);
|
|
extern void mem_cgroup_page_migration(struct page *page, struct page *newpage);
|
|
|
|
#else /* CONFIG_CGROUP_MEM_CONT */
|
|
static inline void mm_init_cgroup(struct mm_struct *mm,
|
|
struct task_struct *p)
|
|
{
|
|
}
|
|
|
|
static inline void mm_free_cgroup(struct mm_struct *mm)
|
|
{
|
|
}
|
|
|
|
static inline void page_assign_page_cgroup(struct page *page,
|
|
struct page_cgroup *pc)
|
|
{
|
|
}
|
|
|
|
static inline struct page_cgroup *page_get_page_cgroup(struct page *page)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
|
|
gfp_t gfp_mask)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void mem_cgroup_uncharge(struct page_cgroup *pc)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_uncharge_page(struct page *page)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_move_lists(struct page_cgroup *pc,
|
|
bool active)
|
|
{
|
|
}
|
|
|
|
static inline int mem_cgroup_cache_charge(struct page *page,
|
|
struct mm_struct *mm,
|
|
gfp_t gfp_mask)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline struct mem_cgroup *mm_cgroup(const struct mm_struct *mm)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int task_in_mem_cgroup(struct task_struct *task,
|
|
const struct mem_cgroup *mem)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline int mem_cgroup_prepare_migration(struct page *page)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void mem_cgroup_end_migration(struct page *page)
|
|
{
|
|
}
|
|
|
|
static inline void
|
|
mem_cgroup_page_migration(struct page *page, struct page *newpage)
|
|
{
|
|
}
|
|
|
|
|
|
#endif /* CONFIG_CGROUP_MEM_CONT */
|
|
|
|
#endif /* _LINUX_MEMCONTROL_H */
|
|
|