2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 05:04:00 +08:00
linux-next/include/linux/memcontrol.h
KAMEZAWA Hiroyuki 08e552c69c memcg: synchronized LRU
A big patch for changing memcg's LRU semantics.

Now,
  - page_cgroup is linked to mem_cgroup's its own LRU (per zone).

  - LRU of page_cgroup is not synchronous with global LRU.

  - page and page_cgroup is one-to-one and statically allocated.

  - To find page_cgroup is on what LRU, you have to check pc->mem_cgroup as
    - lru = page_cgroup_zoneinfo(pc, nid_of_pc, zid_of_pc);

  - SwapCache is handled.

And, when we handle LRU list of page_cgroup, we do following.

	pc = lookup_page_cgroup(page);
	lock_page_cgroup(pc); .....................(1)
	mz = page_cgroup_zoneinfo(pc);
	spin_lock(&mz->lru_lock);
	.....add to LRU
	spin_unlock(&mz->lru_lock);
	unlock_page_cgroup(pc);

But (1) is spin_lock and we have to be afraid of dead-lock with zone->lru_lock.
So, trylock() is used at (1), now. Without (1), we can't trust "mz" is correct.

This is a trial to remove this dirty nesting of locks.
This patch changes mz->lru_lock to be zone->lru_lock.
Then, above sequence will be written as

        spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU
	mem_cgroup_add/remove/etc_lru() {
		pc = lookup_page_cgroup(page);
		mz = page_cgroup_zoneinfo(pc);
		if (PageCgroupUsed(pc)) {
			....add to LRU
		}
        spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU

This is much simpler.
(*) We're safe even if we don't take lock_page_cgroup(pc). Because..
    1. When pc->mem_cgroup can be modified.
       - at charge.
       - at account_move().
    2. at charge
       the PCG_USED bit is not set before pc->mem_cgroup is fixed.
    3. at account_move()
       the page is isolated and not on LRU.

Pros.
  - easy for maintenance.
  - memcg can make use of laziness of pagevec.
  - we don't have to duplicated LRU/Active/Unevictable bit in page_cgroup.
  - LRU status of memcg will be synchronized with global LRU's one.
  - # of locks are reduced.
  - account_move() is simplified very much.
Cons.
  - may increase cost of LRU rotation.
    (no impact if memcg is not configured.)

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 08:31:05 -08:00

221 lines
5.8 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
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(struct mm_struct *mm,
gfp_t gfp_mask, struct mem_cgroup **ptr);
extern int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
struct page *page, gfp_t mask, struct mem_cgroup **ptr);
extern void mem_cgroup_commit_charge_swapin(struct page *page,
struct mem_cgroup *ptr);
extern void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *ptr);
extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask);
extern void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru);
extern void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru);
extern void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru);
extern void mem_cgroup_del_lru(struct page *page);
extern void mem_cgroup_move_lists(struct page *page,
enum lru_list from, enum lru_list to);
extern void mem_cgroup_uncharge_page(struct page *page);
extern void mem_cgroup_uncharge_cache_page(struct page *page);
extern int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask);
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, int file);
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, struct mem_cgroup **ptr);
extern void mem_cgroup_end_migration(struct mem_cgroup *mem,
struct page *oldpage, 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(struct mem_cgroup *mem, struct zone *zone,
int priority, enum lru_list lru);
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
extern int do_swap_account;
#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(struct mm_struct *mm,
gfp_t gfp_mask, struct mem_cgroup **ptr)
{
return 0;
}
static inline int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
struct page *page, gfp_t gfp_mask, struct mem_cgroup **ptr)
{
return 0;
}
static inline void mem_cgroup_commit_charge_swapin(struct page *page,
struct mem_cgroup *ptr)
{
}
static inline void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *ptr)
{
}
static inline void mem_cgroup_uncharge_page(struct page *page)
{
}
static inline void mem_cgroup_uncharge_cache_page(struct page *page)
{
}
static inline int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
{
return 0;
}
static inline void mem_cgroup_add_lru_list(struct page *page, int lru)
{
}
static inline void mem_cgroup_del_lru_list(struct page *page, int lru)
{
return ;
}
static inline void mem_cgroup_rotate_lru_list(struct page *page, int lru)
{
return ;
}
static inline void mem_cgroup_del_lru(struct page *page)
{
return ;
}
static inline void
mem_cgroup_move_lists(struct page *page, enum lru_list from, enum lru_list to)
{
}
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, struct mem_cgroup **ptr)
{
return 0;
}
static inline void mem_cgroup_end_migration(struct mem_cgroup *mem,
struct page *oldpage,
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(struct mem_cgroup *mem,
struct zone *zone, int priority,
enum lru_list lru)
{
return 0;
}
#endif /* CONFIG_CGROUP_MEM_CONT */
#endif /* _LINUX_MEMCONTROL_H */