mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 07:48:58 +07:00
ac39cf8cb8
FILE_MAPPED per memcg of migrated file cache is not properly updated,
because our hook in page_add_file_rmap() can't know to which memcg
FILE_MAPPED should be counted.
Basically, this patch is for fixing the bug but includes some big changes
to fix up other messes.
Now, at migrating mapped file, events happen in following sequence.
1. allocate a new page.
2. get memcg of an old page.
3. charge ageinst a new page before migration. But at this point,
no changes to new page's page_cgroup, no commit for the charge.
(IOW, PCG_USED bit is not set.)
4. page migration replaces radix-tree, old-page and new-page.
5. page migration remaps the new page if the old page was mapped.
6. Here, the new page is unlocked.
7. memcg commits the charge for newpage, Mark the new page's page_cgroup
as PCG_USED.
Because "commit" happens after page-remap, we can count FILE_MAPPED
at "5", because we should avoid to trust page_cgroup->mem_cgroup.
if PCG_USED bit is unset.
(Note: memcg's LRU removal code does that but LRU-isolation logic is used
for helping it. When we overwrite page_cgroup->mem_cgroup, page_cgroup is
not on LRU or page_cgroup->mem_cgroup is NULL.)
We can lose file_mapped accounting information at 5 because FILE_MAPPED
is updated only when mapcount changes 0->1. So we should catch it.
BTW, historically, above implemntation comes from migration-failure
of anonymous page. Because we charge both of old page and new page
with mapcount=0, we can't catch
- the page is really freed before remap.
- migration fails but it's freed before remap
or .....corner cases.
New migration sequence with memcg is:
1. allocate a new page.
2. mark PageCgroupMigration to the old page.
3. charge against a new page onto the old page's memcg. (here, new page's pc
is marked as PageCgroupUsed.)
4. page migration replaces radix-tree, page table, etc...
5. At remapping, new page's page_cgroup is now makrked as "USED"
We can catch 0->1 event and FILE_MAPPED will be properly updated.
And we can catch SWAPOUT event after unlock this and freeing this
page by unmap() can be caught.
7. Clear PageCgroupMigration of the old page.
So, FILE_MAPPED will be correctly updated.
Then, for what MIGRATION flag is ?
Without it, at migration failure, we may have to charge old page again
because it may be fully unmapped. "charge" means that we have to dive into
memory reclaim or something complated. So, it's better to avoid
charge it again. Before this patch, __commit_charge() was working for
both of the old/new page and fixed up all. But this technique has some
racy condtion around FILE_MAPPED and SWAPOUT etc...
Now, the kernel use MIGRATION flag and don't uncharge old page until
the end of migration.
I hope this change will make memcg's page migration much simpler. This
page migration has caused several troubles. Worth to add a flag for
simplification.
Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
316 lines
8.2 KiB
C
316 lines
8.2 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>
|
|
struct mem_cgroup;
|
|
struct page_cgroup;
|
|
struct page;
|
|
struct mm_struct;
|
|
|
|
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);
|
|
|
|
#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 **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);
|
|
|
|
/* 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 int mem_cgroup_shmem_charge_fallback(struct page *page,
|
|
struct mm_struct *mm, gfp_t gfp_mask);
|
|
|
|
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 *try_get_mem_cgroup_from_page(struct page *page);
|
|
extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
|
|
|
|
static inline
|
|
int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
|
|
{
|
|
struct mem_cgroup *mem;
|
|
rcu_read_lock();
|
|
mem = mem_cgroup_from_task(rcu_dereference((mm)->owner));
|
|
rcu_read_unlock();
|
|
return cgroup == mem;
|
|
}
|
|
|
|
extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem);
|
|
|
|
extern int
|
|
mem_cgroup_prepare_migration(struct page *page,
|
|
struct page *newpage, 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_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);
|
|
int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg);
|
|
int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg);
|
|
unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
|
|
struct zone *zone,
|
|
enum lru_list lru);
|
|
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);
|
|
|
|
#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_file_mapped(struct page *page, int val);
|
|
unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
|
|
gfp_t gfp_mask, int nid,
|
|
int zid);
|
|
#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 **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_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 int mem_cgroup_shmem_charge_fallback(struct page *page,
|
|
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 struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
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 struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int
|
|
mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
|
|
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_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 bool mem_cgroup_disabled(void)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline int
|
|
mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline int
|
|
mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline unsigned long
|
|
mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, struct zone *zone,
|
|
enum lru_list lru)
|
|
{
|
|
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_update_file_mapped(struct page *page,
|
|
int val)
|
|
{
|
|
}
|
|
|
|
static inline
|
|
unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
|
|
gfp_t gfp_mask, int nid, int zid)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#endif /* CONFIG_CGROUP_MEM_CONT */
|
|
|
|
#endif /* _LINUX_MEMCONTROL_H */
|
|
|