davidlt/kernel-ark
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
33baefe5e7
kernel-ark/include/linux/swap.h
Michal Hocko 0a0337e0d1 mm, oom: rework oom detection 
__alloc_pages_slowpath has traditionally relied on the direct reclaim
and did_some_progress as an indicator that it makes sense to retry
allocation rather than declaring OOM.  shrink_zones had to rely on
zone_reclaimable if shrink_zone didn't make any progress to prevent from
a premature OOM killer invocation - the LRU might be full of dirty or
writeback pages and direct reclaim cannot clean those up.

zone_reclaimable allows to rescan the reclaimable lists several times
and restart if a page is freed.  This is really subtle behavior and it
might lead to a livelock when a single freed page keeps allocator
looping but the current task will not be able to allocate that single
page.  OOM killer would be more appropriate than looping without any
progress for unbounded amount of time.

This patch changes OOM detection logic and pulls it out from shrink_zone
which is too low to be appropriate for any high level decisions such as
OOM which is per zonelist property.  It is __alloc_pages_slowpath which
knows how many attempts have been done and what was the progress so far
therefore it is more appropriate to implement this logic.

The new heuristic is implemented in should_reclaim_retry helper called
from __alloc_pages_slowpath.  It tries to be more deterministic and
easier to follow.  It builds on an assumption that retrying makes sense
only if the currently reclaimable memory + free pages would allow the
current allocation request to succeed (as per __zone_watermark_ok) at
least for one zone in the usable zonelist.

This alone wouldn't be sufficient, though, because the writeback might
get stuck and reclaimable pages might be pinned for a really long time
or even depend on the current allocation context.  Therefore there is a
backoff mechanism implemented which reduces the reclaim target after
each reclaim round without any progress.  This means that we should
eventually converge to only NR_FREE_PAGES as the target and fail on the
wmark check and proceed to OOM.  The backoff is simple and linear with
1/16 of the reclaimable pages for each round without any progress.  We
are optimistic and reset counter for successful reclaim rounds.

Costly high order pages mostly preserve their semantic and those without
__GFP_REPEAT fail right away while those which have the flag set will
back off after the amount of reclaimable pages reaches equivalent of the
requested order.  The only difference is that if there was no progress
during the reclaim we rely on zone watermark check.  This is more
logical thing to do than previous 1<<order attempts which were a result
of zone_reclaimable faking the progress.

[vdavydov@virtuozzo.com: check classzone_idx for shrink_zone]
[hannes@cmpxchg.org: separate the heuristic into should_reclaim_retry]
[rientjes@google.com: use zone_page_state_snapshot for NR_FREE_PAGES]
[rientjes@google.com: shrink_zones doesn't need to return anything]
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-20 17:58:30 -07:00

589 lines
18 KiB
C
Raw Blame History

#ifndef _LINUX_SWAP_H
#define _LINUX_SWAP_H
#include <linux/spinlock.h>
#include <linux/linkage.h>
#include <linux/mmzone.h>
#include <linux/list.h>
#include <linux/memcontrol.h>
#include <linux/sched.h>
#include <linux/node.h>
#include <linux/fs.h>
#include <linux/atomic.h>
#include <linux/page-flags.h>
#include <asm/page.h>
struct notifier_block;
struct bio;
#define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */
#define SWAP_FLAG_PRIO_MASK 0x7fff
#define SWAP_FLAG_PRIO_SHIFT 0
#define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */
#define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */
#define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */
#define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \
SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \
SWAP_FLAG_DISCARD_PAGES)
static inline int current_is_kswapd(void)
{
return current->flags & PF_KSWAPD;
}
/*
* MAX_SWAPFILES defines the maximum number of swaptypes: things which can
* be swapped to. The swap type and the offset into that swap type are
* encoded into pte's and into pgoff_t's in the swapcache. Using five bits
* for the type means that the maximum number of swapcache pages is 27 bits
* on 32-bit-pgoff_t architectures. And that assumes that the architecture packs
* the type/offset into the pte as 5/27 as well.
*/
#define MAX_SWAPFILES_SHIFT 5
/*
* Use some of the swap files numbers for other purposes. This
* is a convenient way to hook into the VM to trigger special
* actions on faults.
*/
/*
* NUMA node memory migration support
*/
#ifdef CONFIG_MIGRATION
#define SWP_MIGRATION_NUM 2
#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM)
#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1)
#else
#define SWP_MIGRATION_NUM 0
#endif
/*
* Handling of hardware poisoned pages with memory corruption.
*/
#ifdef CONFIG_MEMORY_FAILURE
#define SWP_HWPOISON_NUM 1
#define SWP_HWPOISON MAX_SWAPFILES
#else
#define SWP_HWPOISON_NUM 0
#endif
#define MAX_SWAPFILES \
((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
/*
* Magic header for a swap area. The first part of the union is
* what the swap magic looks like for the old (limited to 128MB)
* swap area format, the second part of the union adds - in the
* old reserved area - some extra information. Note that the first
* kilobyte is reserved for boot loader or disk label stuff...
*
* Having the magic at the end of the PAGE_SIZE makes detecting swap
* areas somewhat tricky on machines that support multiple page sizes.
* For 2.5 we'll probably want to move the magic to just beyond the
* bootbits...
*/
union swap_header {
struct {
char reserved[PAGE_SIZE - 10];
char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */
} magic;
struct {
char bootbits[1024]; /* Space for disklabel etc. */
__u32 version;
__u32 last_page;
__u32 nr_badpages;
unsigned char sws_uuid[16];
unsigned char sws_volume[16];
__u32 padding[117];
__u32 badpages[1];
} info;
};
/*
* current->reclaim_state points to one of these when a task is running
* memory reclaim
*/
struct reclaim_state {
unsigned long reclaimed_slab;
};
#ifdef __KERNEL__
struct address_space;
struct sysinfo;
struct writeback_control;
struct zone;
/*
* A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of
* disk blocks. A list of swap extents maps the entire swapfile. (Where the
* term `swapfile' refers to either a blockdevice or an IS_REG file. Apart
* from setup, they're handled identically.
*
* We always assume that blocks are of size PAGE_SIZE.
*/
struct swap_extent {
struct list_head list;
pgoff_t start_page;
pgoff_t nr_pages;
sector_t start_block;
};
/*
* Max bad pages in the new format..
*/
#define __swapoffset(x) ((unsigned long)&((union swap_header *)0)->x)
#define MAX_SWAP_BADPAGES \
((__swapoffset(magic.magic) - __swapoffset(info.badpages)) / sizeof(int))
enum {
SWP_USED = (1 << 0), /* is slot in swap_info[] used? */
SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */
SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */
SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */
SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */
SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */
SWP_BLKDEV = (1 << 6), /* its a block device */
SWP_FILE = (1 << 7), /* set after swap_activate success */
SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */
SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */
/* add others here before... */
SWP_SCANNING = (1 << 10), /* refcount in scan_swap_map */
};
#define SWAP_CLUSTER_MAX 32UL
#define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
/*
* Ratio between zone->managed_pages and the "gap" that above the per-zone
* "high_wmark". While balancing nodes, We allow kswapd to shrink zones that
* do not meet the (high_wmark + gap) watermark, even which already met the
* high_wmark, in order to provide better per-zone lru behavior. We are ok to
* spend not more than 1% of the memory for this zone balancing "gap".
*/
#define KSWAPD_ZONE_BALANCE_GAP_RATIO 100
#define SWAP_MAP_MAX 0x3e /* Max duplication count, in first swap_map */
#define SWAP_MAP_BAD 0x3f /* Note pageblock is bad, in first swap_map */
#define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */
#define SWAP_CONT_MAX 0x7f /* Max count, in each swap_map continuation */
#define COUNT_CONTINUED 0x80 /* See swap_map continuation for full count */
#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs, in first swap_map */
/*
* We use this to track usage of a cluster. A cluster is a block of swap disk
* space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All
* free clusters are organized into a list. We fetch an entry from the list to
* get a free cluster.
*
* The data field stores next cluster if the cluster is free or cluster usage
* counter otherwise. The flags field determines if a cluster is free. This is
* protected by swap_info_struct.lock.
*/
struct swap_cluster_info {
unsigned int data:24;
unsigned int flags:8;
};
#define CLUSTER_FLAG_FREE 1 /* This cluster is free */
#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
/*
* We assign a cluster to each CPU, so each CPU can allocate swap entry from
* its own cluster and swapout sequentially. The purpose is to optimize swapout
* throughput.
*/
struct percpu_cluster {
struct swap_cluster_info index; /* Current cluster index */
unsigned int next; /* Likely next allocation offset */
};
/*
* The in-memory structure used to track swap areas.
*/
struct swap_info_struct {
unsigned long flags; /* SWP_USED etc: see above */
signed short prio; /* swap priority of this type */
struct plist_node list; /* entry in swap_active_head */
struct plist_node avail_list; /* entry in swap_avail_head */
signed char type; /* strange name for an index */
unsigned int max; /* extent of the swap_map */
unsigned char *swap_map; /* vmalloc'ed array of usage counts */
struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
struct swap_cluster_info free_cluster_head; /* free cluster list head */
struct swap_cluster_info free_cluster_tail; /* free cluster list tail */
unsigned int lowest_bit; /* index of first free in swap_map */
unsigned int highest_bit; /* index of last free in swap_map */
unsigned int pages; /* total of usable pages of swap */
unsigned int inuse_pages; /* number of those currently in use */
unsigned int cluster_next; /* likely index for next allocation */
unsigned int cluster_nr; /* countdown to next cluster search */
struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
struct swap_extent *curr_swap_extent;
struct swap_extent first_swap_extent;
struct block_device *bdev; /* swap device or bdev of swap file */
struct file *swap_file; /* seldom referenced */
unsigned int old_block_size; /* seldom referenced */
#ifdef CONFIG_FRONTSWAP
unsigned long *frontswap_map; /* frontswap in-use, one bit per page */
atomic_t frontswap_pages; /* frontswap pages in-use counter */
#endif
spinlock_t lock; /*
* protect map scan related fields like
* swap_map, lowest_bit, highest_bit,
* inuse_pages, cluster_next,
* cluster_nr, lowest_alloc,
* highest_alloc, free/discard cluster
* list. other fields are only changed
* at swapon/swapoff, so are protected
* by swap_lock. changing flags need
* hold this lock and swap_lock. If
* both locks need hold, hold swap_lock
* first.
*/
struct work_struct discard_work; /* discard worker */
struct swap_cluster_info discard_cluster_head; /* list head of discard clusters */
struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */
};
/* linux/mm/workingset.c */
void *workingset_eviction(struct address_space *mapping, struct page *page);
bool workingset_refault(void *shadow);
void workingset_activation(struct page *page);
extern struct list_lru workingset_shadow_nodes;
static inline unsigned int workingset_node_pages(struct radix_tree_node *node)
{
return node->count & RADIX_TREE_COUNT_MASK;
}
static inline void workingset_node_pages_inc(struct radix_tree_node *node)
{
node->count++;
}
static inline void workingset_node_pages_dec(struct radix_tree_node *node)
{
node->count--;
}
static inline unsigned int workingset_node_shadows(struct radix_tree_node *node)
{
return node->count >> RADIX_TREE_COUNT_SHIFT;
}
static inline void workingset_node_shadows_inc(struct radix_tree_node *node)
{
node->count += 1U << RADIX_TREE_COUNT_SHIFT;
}
static inline void workingset_node_shadows_dec(struct radix_tree_node *node)
{
node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
}
/* linux/mm/page_alloc.c */
extern unsigned long totalram_pages;
extern unsigned long totalreserve_pages;
extern unsigned long nr_free_buffer_pages(void);
extern unsigned long nr_free_pagecache_pages(void);
/* Definition of global_page_state not available yet */
#define nr_free_pages() global_page_state(NR_FREE_PAGES)
/* linux/mm/swap.c */
extern void lru_cache_add(struct page *);
extern void lru_cache_add_anon(struct page *page);
extern void lru_cache_add_file(struct page *page);
extern void lru_add_page_tail(struct page *page, struct page *page_tail,
struct lruvec *lruvec, struct list_head *head);
extern void activate_page(struct page *);
extern void mark_page_accessed(struct page *);
extern void lru_add_drain(void);
extern void lru_add_drain_cpu(int cpu);
extern void lru_add_drain_all(void);
extern void rotate_reclaimable_page(struct page *page);
extern void deactivate_file_page(struct page *page);
extern void deactivate_page(struct page *page);
extern void swap_setup(void);
extern void add_page_to_unevictable_list(struct page *page);
extern void lru_cache_add_active_or_unevictable(struct page *page,
struct vm_area_struct *vma);
/* linux/mm/vmscan.c */
extern unsigned long zone_reclaimable_pages(struct zone *zone);
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *mask);
extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
unsigned long nr_pages,
gfp_t gfp_mask,
bool may_swap);
extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
gfp_t gfp_mask, bool noswap,
struct zone *zone,
unsigned long *nr_scanned);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;
extern int remove_mapping(struct address_space *mapping, struct page *page);
extern unsigned long vm_total_pages;
#ifdef CONFIG_NUMA
extern int zone_reclaim_mode;
extern int sysctl_min_unmapped_ratio;
extern int sysctl_min_slab_ratio;
extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
#else
#define zone_reclaim_mode 0
static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
{
return 0;
}
#endif
extern int page_evictable(struct page *page);
extern void check_move_unevictable_pages(struct page **, int nr_pages);
extern int kswapd_run(int nid);
extern void kswapd_stop(int nid);
#ifdef CONFIG_SWAP
/* linux/mm/page_io.c */
extern int swap_readpage(struct page *);
extern int swap_writepage(struct page *page, struct writeback_control *wbc);
extern void end_swap_bio_write(struct bio *bio);
extern int __swap_writepage(struct page *page, struct writeback_control *wbc,
bio_end_io_t end_write_func);
extern int swap_set_page_dirty(struct page *page);
int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
unsigned long nr_pages, sector_t start_block);
int generic_swapfile_activate(struct swap_info_struct *, struct file *,
sector_t *);
/* linux/mm/swap_state.c */
extern struct address_space swapper_spaces[];
#define swap_address_space(entry) (&swapper_spaces[swp_type(entry)])
extern unsigned long total_swapcache_pages(void);
extern void show_swap_cache_info(void);
extern int add_to_swap(struct page *, struct list_head *list);
extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t);
extern int __add_to_swap_cache(struct page *page, swp_entry_t entry);
extern void __delete_from_swap_cache(struct page *);
extern void delete_from_swap_cache(struct page *);
extern void free_page_and_swap_cache(struct page *);
extern void free_pages_and_swap_cache(struct page **, int);
extern struct page *lookup_swap_cache(swp_entry_t);
extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
struct vm_area_struct *vma, unsigned long addr);
extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t,
struct vm_area_struct *vma, unsigned long addr,
bool *new_page_allocated);
extern struct page *swapin_readahead(swp_entry_t, gfp_t,
struct vm_area_struct *vma, unsigned long addr);
/* linux/mm/swapfile.c */
extern atomic_long_t nr_swap_pages;
extern long total_swap_pages;
/* Swap 50% full? Release swapcache more aggressively.. */
static inline bool vm_swap_full(void)
{
return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages;
}
static inline long get_nr_swap_pages(void)
{
return atomic_long_read(&nr_swap_pages);
}
extern void si_swapinfo(struct sysinfo *);
extern swp_entry_t get_swap_page(void);
extern swp_entry_t get_swap_page_of_type(int);
extern int add_swap_count_continuation(swp_entry_t, gfp_t);
extern void swap_shmem_alloc(swp_entry_t);
extern int swap_duplicate(swp_entry_t);
extern int swapcache_prepare(swp_entry_t);
extern void swap_free(swp_entry_t);
extern void swapcache_free(swp_entry_t);
extern int free_swap_and_cache(swp_entry_t);
extern int swap_type_of(dev_t, sector_t, struct block_device **);
extern unsigned int count_swap_pages(int, int);
extern sector_t map_swap_page(struct page *, struct block_device **);
extern sector_t swapdev_block(int, pgoff_t);
extern int page_swapcount(struct page *);
extern int swp_swapcount(swp_entry_t entry);
extern struct swap_info_struct *page_swap_info(struct page *);
extern bool reuse_swap_page(struct page *, int *);
extern int try_to_free_swap(struct page *);
struct backing_dev_info;
#else /* CONFIG_SWAP */
#define swap_address_space(entry) (NULL)
#define get_nr_swap_pages() 0L
#define total_swap_pages 0L
#define total_swapcache_pages() 0UL
#define vm_swap_full() 0
#define si_swapinfo(val) \
do { (val)->freeswap = (val)->totalswap = 0; } while (0)
/* only sparc can not include linux/pagemap.h in this file
* so leave put_page and release_pages undeclared... */
#define free_page_and_swap_cache(page) \
put_page(page)
#define free_pages_and_swap_cache(pages, nr) \
release_pages((pages), (nr), false);
static inline void show_swap_cache_info(void)
{
}
#define free_swap_and_cache(swp) is_migration_entry(swp)
#define swapcache_prepare(swp) is_migration_entry(swp)
static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask)
{
return 0;
}
static inline void swap_shmem_alloc(swp_entry_t swp)
{
}
static inline int swap_duplicate(swp_entry_t swp)
{
return 0;
}
static inline void swap_free(swp_entry_t swp)
{
}
static inline void swapcache_free(swp_entry_t swp)
{
}
static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr)
{
return NULL;
}
static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
{
return 0;
}
static inline struct page *lookup_swap_cache(swp_entry_t swp)
{
return NULL;
}
static inline int add_to_swap(struct page *page, struct list_head *list)
{
return 0;
}
static inline int add_to_swap_cache(struct page *page, swp_entry_t entry,
gfp_t gfp_mask)
{
return -1;
}
static inline void __delete_from_swap_cache(struct page *page)
{
}
static inline void delete_from_swap_cache(struct page *page)
{
}
static inline int page_swapcount(struct page *page)
{
return 0;
}
static inline int swp_swapcount(swp_entry_t entry)
{
return 0;
}
#define reuse_swap_page(page, total_mapcount) \
(page_trans_huge_mapcount(page, total_mapcount) == 1)
static inline int try_to_free_swap(struct page *page)
{
return 0;
}
static inline swp_entry_t get_swap_page(void)
{
swp_entry_t entry;
entry.val = 0;
return entry;
}
#endif /* CONFIG_SWAP */
#ifdef CONFIG_MEMCG
static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
{
/* Cgroup2 doesn't have per-cgroup swappiness */
if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
return vm_swappiness;
/* root ? */
if (mem_cgroup_disabled() || !memcg->css.parent)
return vm_swappiness;
return memcg->swappiness;
}
#else
static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
{
return vm_swappiness;
}
#endif
#ifdef CONFIG_MEMCG_SWAP
extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
extern void mem_cgroup_uncharge_swap(swp_entry_t entry);
extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
extern bool mem_cgroup_swap_full(struct page *page);
#else
static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
{
}
static inline int mem_cgroup_try_charge_swap(struct page *page,
swp_entry_t entry)
{
return 0;
}
static inline void mem_cgroup_uncharge_swap(swp_entry_t entry)
{
}
static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
{
return get_nr_swap_pages();
}
static inline bool mem_cgroup_swap_full(struct page *page)
{
return vm_swap_full();
}
#endif
#endif /* __KERNEL__*/
#endif /* _LINUX_SWAP_H */
Reference in New Issue View Git Blame Copy Permalink