kernel-ark/include/linux/memcontrol.h
Balbir Singh cf475ad28a cgroups: add an owner to the mm_struct
Remove the mem_cgroup member from mm_struct and instead adds an owner.

This approach was suggested by Paul Menage.  The advantage of this approach
is that, once the mm->owner is known, using the subsystem id, the cgroup
can be determined.  It also allows several control groups that are
virtually grouped by mm_struct, to exist independent of the memory
controller i.e., without adding mem_cgroup's for each controller, to
mm_struct.

A new config option CONFIG_MM_OWNER is added and the memory resource
controller selects this config option.

This patch also adds cgroup callbacks to notify subsystems when mm->owner
changes.  The mm_cgroup_changed callback is called with the task_lock() of
the new task held and is called just prior to changing the mm->owner.

I am indebted to Paul Menage for the several reviews of this patchset and
helping me make it lighter and simpler.

This patch was tested on a powerpc box, it was compiled with both the
MM_OWNER config turned on and off.

After the thread group leader exits, it's moved to init_css_state by
cgroup_exit(), thus all future charges from runnings threads would be
redirected to the init_css_set's subsystem.

Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Hirokazu Takahashi <taka@valinux.co.jp>
Cc: David Rientjes <rientjes@google.com>,
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Reviewed-by: Paul Menage <menage@google.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 08:06:10 -07:00

169 lines
4.4 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
struct mem_cgroup;
struct page_cgroup;
struct page;
struct mm_struct;
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
#define page_reset_bad_cgroup(page) ((page)->page_cgroup = 0)
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 int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask);
extern void mem_cgroup_uncharge_page(struct page *page);
extern void mem_cgroup_move_lists(struct page *page, 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);
int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
#define mm_match_cgroup(mm, cgroup) \
((cgroup) == mem_cgroup_from_task((mm)->owner))
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);
/*
* For memory reclaim.
*/
extern int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem);
extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem);
extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem);
extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
int priority);
extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
int priority);
extern long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
struct zone *zone, int priority);
extern long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
struct zone *zone, int priority);
#else /* CONFIG_CGROUP_MEM_RES_CTLR */
static inline void page_reset_bad_cgroup(struct page *page)
{
}
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 int mem_cgroup_cache_charge(struct page *page,
struct mm_struct *mm, gfp_t gfp_mask)
{
return 0;
}
static inline void mem_cgroup_uncharge_page(struct page *page)
{
}
static inline void mem_cgroup_move_lists(struct page *page, bool active)
{
}
static inline int mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *mem)
{
return 1;
}
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)
{
}
static inline int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
{
return 0;
}
static inline int mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
{
return 0;
}
static inline int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
{
return 0;
}
static inline void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
int priority)
{
}
static inline void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
int priority)
{
}
static inline long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
struct zone *zone, int priority)
{
return 0;
}
static inline long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
struct zone *zone, int priority)
{
return 0;
}
#endif /* CONFIG_CGROUP_MEM_CONT */
#endif /* _LINUX_MEMCONTROL_H */