2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-17 01:34:00 +08:00
linux-next/include/linux/swap.h

411 lines
11 KiB
C
Raw Normal View 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 <asm/atomic.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
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
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
#ifndef CONFIG_MIGRATION
#define MAX_SWAPFILES (1 << MAX_SWAPFILES_SHIFT)
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
#else
/* Use last two entries for page migration swap entries */
#define MAX_SWAPFILES ((1 << MAX_SWAPFILES_SHIFT)-2)
#define SWP_MIGRATION_READ MAX_SWAPFILES
#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + 1)
#endif
/*
* 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;
};
/* A swap entry has to fit into a "unsigned long", as
* the entry is hidden in the "index" field of the
* swapper address space.
*/
typedef struct {
unsigned long val;
} swp_entry_t;
/*
* 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_ACTIVE = (SWP_USED | SWP_WRITEOK),
/* add others here before... */
SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */
};
#define SWAP_CLUSTER_MAX 32
#define SWAP_MAP_MAX 0x7fff
#define SWAP_MAP_BAD 0x8000
/*
* The in-memory structure used to track swap areas.
*/
struct swap_info_struct {
unsigned int flags;
int prio; /* swap priority */
struct file *swap_file;
struct block_device *bdev;
struct list_head extent_list;
struct swap_extent *curr_swap_extent;
unsigned old_block_size;
unsigned short * swap_map;
unsigned int lowest_bit;
unsigned int highest_bit;
unsigned int cluster_next;
unsigned int cluster_nr;
unsigned int pages;
unsigned int max;
unsigned int inuse_pages;
int next; /* next entry on swap list */
};
struct swap_list_t {
int head; /* head of priority-ordered swapfile list */
int next; /* swapfile to be used next */
};
/* Swap 50% full? Release swapcache more aggressively.. */
#define vm_swap_full() (nr_swap_pages*2 < total_swap_pages)
/* linux/mm/page_alloc.c */
extern unsigned long totalram_pages;
[PATCH] overcommit: add calculate_totalreserve_pages() These patches are an enhancement of OVERCOMMIT_GUESS algorithm in __vm_enough_memory(). - why the kernel needed patching When the kernel can't allocate anonymous pages in practice, currnet OVERCOMMIT_GUESS could return success. This implementation might be the cause of oom kill in memory pressure situation. If the Linux runs with page reservation features like /proc/sys/vm/lowmem_reserve_ratio and without swap region, I think the oom kill occurs easily. - the overall design approach in the patch When the OVERCOMMET_GUESS algorithm calculates number of free pages, the reserved free pages are regarded as non-free pages. This change helps to avoid the pitfall that the number of free pages become less than the number which the kernel tries to keep free. - testing results I tested the patches using my test kernel module. If the patches aren't applied to the kernel, __vm_enough_memory() returns success in the situation but autual page allocation is failed. On the other hand, if the patches are applied to the kernel, memory allocation failure is avoided since __vm_enough_memory() returns failure in the situation. I checked that on i386 SMP 16GB memory machine. I haven't tested on nommu environment currently. This patch adds totalreserve_pages for __vm_enough_memory(). Calculate_totalreserve_pages() checks maximum lowmem_reserve pages and pages_high in each zone. Finally, the function stores the sum of each zone to totalreserve_pages. The totalreserve_pages is calculated when the VM is initilized. And the variable is updated when /proc/sys/vm/lowmem_reserve_raito or /proc/sys/vm/min_free_kbytes are changed. Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-04-11 13:52:59 +08:00
extern unsigned long totalreserve_pages;
extern long nr_swap_pages;
extern unsigned int nr_free_buffer_pages(void);
extern unsigned int 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 *, enum lru_list lru);
extern void lru_cache_add_lru(struct page *, enum lru_list lru);
extern void activate_page(struct page *);
extern void mark_page_accessed(struct page *);
extern void lru_add_drain(void);
extern int lru_add_drain_all(void);
extern void rotate_reclaimable_page(struct page *page);
extern void swap_setup(void);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
extern void add_page_to_unevictable_list(struct page *page);
/**
* lru_cache_add: add a page to the page lists
* @page: the page to add
*/
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
static inline void lru_cache_add_anon(struct page *page)
{
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
__lru_cache_add(page, LRU_INACTIVE_ANON);
}
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
static inline void lru_cache_add_active_anon(struct page *page)
{
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
__lru_cache_add(page, LRU_ACTIVE_ANON);
}
static inline void lru_cache_add_file(struct page *page)
{
__lru_cache_add(page, LRU_INACTIVE_FILE);
}
static inline void lru_cache_add_active_file(struct page *page)
{
__lru_cache_add(page, LRU_ACTIVE_FILE);
}
/* linux/mm/vmscan.c */
mm: use zonelists instead of zones when direct reclaiming pages The following patches replace multiple zonelists per node with two zonelists that are filtered based on the GFP flags. The patches as a set fix a bug with regard to the use of MPOL_BIND and ZONE_MOVABLE. With this patchset, the MPOL_BIND will apply to the two highest zones when the highest zone is ZONE_MOVABLE. This should be considered as an alternative fix for the MPOL_BIND+ZONE_MOVABLE in 2.6.23 to the previously discussed hack that filters only custom zonelists. The first patch cleans up an inconsistency where direct reclaim uses zonelist->zones where other places use zonelist. The second patch introduces a helper function node_zonelist() for looking up the appropriate zonelist for a GFP mask which simplifies patches later in the set. The third patch defines/remembers the "preferred zone" for numa statistics, as it is no longer always the first zone in a zonelist. The forth patch replaces multiple zonelists with two zonelists that are filtered. The two zonelists are due to the fact that the memoryless patchset introduces a second set of zonelists for __GFP_THISNODE. The fifth patch introduces helper macros for retrieving the zone and node indices of entries in a zonelist. The final patch introduces filtering of the zonelists based on a nodemask. Two zonelists exist per node, one for normal allocations and one for __GFP_THISNODE. Performance results varied depending on the machine configuration. In real workloads the gain/loss will depend on how much the userspace portion of the benchmark benefits from having more cache available due to reduced referencing of zonelists. These are the range of performance losses/gains when running against 2.6.24-rc4-mm1. The set and these machines are a mix of i386, x86_64 and ppc64 both NUMA and non-NUMA. loss to gain Total CPU time on Kernbench: -0.86% to 1.13% Elapsed time on Kernbench: -0.79% to 0.76% page_test from aim9: -4.37% to 0.79% brk_test from aim9: -0.71% to 4.07% fork_test from aim9: -1.84% to 4.60% exec_test from aim9: -0.71% to 1.08% This patch: The allocator deals with zonelists which indicate the order in which zones should be targeted for an allocation. Similarly, direct reclaim of pages iterates over an array of zones. For consistency, this patch converts direct reclaim to use a zonelist. No functionality is changed by this patch. This simplifies zonelist iterators in the next patch. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Christoph Lameter <clameter@sgi.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:12 +08:00
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
gfp_t gfp_mask);
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
gfp_t gfp_mask);
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
extern int __isolate_lru_page(struct page *page, int mode, int file);
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 long vm_total_pages;
#ifdef CONFIG_NUMA
extern int zone_reclaim_mode;
extern int sysctl_min_unmapped_ratio;
[PATCH] zone_reclaim: dynamic slab reclaim Currently one can enable slab reclaim by setting an explicit option in /proc/sys/vm/zone_reclaim_mode. Slab reclaim is then used as a final option if the freeing of unmapped file backed pages is not enough to free enough pages to allow a local allocation. However, that means that the slab can grow excessively and that most memory of a node may be used by slabs. We have had a case where a machine with 46GB of memory was using 40-42GB for slab. Zone reclaim was effective in dealing with pagecache pages. However, slab reclaim was only done during global reclaim (which is a bit rare on NUMA systems). This patch implements slab reclaim during zone reclaim. Zone reclaim occurs if there is a danger of an off node allocation. At that point we 1. Shrink the per node page cache if the number of pagecache pages is more than min_unmapped_ratio percent of pages in a zone. 2. Shrink the slab cache if the number of the nodes reclaimable slab pages (patch depends on earlier one that implements that counter) are more than min_slab_ratio (a new /proc/sys/vm tunable). The shrinking of the slab cache is a bit problematic since it is not node specific. So we simply calculate what point in the slab we want to reach (current per node slab use minus the number of pages that neeed to be allocated) and then repeately run the global reclaim until that is unsuccessful or we have reached the limit. I hope we will have zone based slab reclaim at some point which will make that easier. The default for the min_slab_ratio is 5% Also remove the slab option from /proc/sys/vm/zone_reclaim_mode. [akpm@osdl.org: cleanups] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 14:31:52 +08:00
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
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
#ifdef CONFIG_UNEVICTABLE_LRU
extern int page_evictable(struct page *page, struct vm_area_struct *vma);
extern void scan_mapping_unevictable_pages(struct address_space *);
extern unsigned long scan_unevictable_pages;
extern int scan_unevictable_handler(struct ctl_table *, int, struct file *,
void __user *, size_t *, loff_t *);
extern int scan_unevictable_register_node(struct node *node);
extern void scan_unevictable_unregister_node(struct node *node);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
#else
static inline int page_evictable(struct page *page,
struct vm_area_struct *vma)
{
return 1;
}
static inline void scan_mapping_unevictable_pages(struct address_space *mapping)
{
}
static inline int scan_unevictable_register_node(struct node *node)
{
return 0;
}
static inline void scan_unevictable_unregister_node(struct node *node) { }
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
#endif
extern int kswapd_run(int nid);
#ifdef CONFIG_MMU
/* linux/mm/shmem.c */
extern int shmem_unuse(swp_entry_t entry, struct page *page);
#endif /* CONFIG_MMU */
extern void swap_unplug_io_fn(struct backing_dev_info *, struct page *);
#ifdef CONFIG_SWAP
/* linux/mm/page_io.c */
extern int swap_readpage(struct file *, struct page *);
extern int swap_writepage(struct page *page, struct writeback_control *wbc);
extern void end_swap_bio_read(struct bio *bio, int err);
/* linux/mm/swap_state.c */
extern struct address_space swapper_space;
#define total_swapcache_pages swapper_space.nrpages
extern void show_swap_cache_info(void);
extern int add_to_swap(struct page *);
extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t);
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 *swapin_readahead(swp_entry_t, gfp_t,
struct vm_area_struct *vma, unsigned long addr);
/* linux/mm/swapfile.c */
extern long total_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 swap_duplicate(swp_entry_t);
extern int valid_swaphandles(swp_entry_t, unsigned long *);
extern void swap_free(swp_entry_t);
extern void 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 swap_info_struct *, pgoff_t);
extern sector_t swapdev_block(int, pgoff_t);
extern struct swap_info_struct *get_swap_info_struct(unsigned);
extern int reuse_swap_page(struct page *);
mm: try_to_free_swap replaces remove_exclusive_swap_page remove_exclusive_swap_page(): its problem is in living up to its name. It doesn't matter if someone else has a reference to the page (raised page_count); it doesn't matter if the page is mapped into userspace (raised page_mapcount - though that hints it may be worth keeping the swap): all that matters is that there be no more references to the swap (and no writeback in progress). swapoff (try_to_unuse) has been removing pages from swapcache for years, with no concern for page count or page mapcount, and we used to have a comment in lookup_swap_cache() recognizing that: if you go for a page of swapcache, you'll get the right page, but it could have been removed from swapcache by the time you get page lock. So, give up asking for exclusivity: get rid of remove_exclusive_swap_page(), and remove_exclusive_swap_page_ref() and remove_exclusive_swap_page_count() which were spawned for the recent LRU work: replace them by the simpler try_to_free_swap() which just checks page_swapcount(). Similarly, remove the page_count limitation from free_swap_and_count(), but assume that it's worth holding on to the swap if page is mapped and swap nowhere near full. Add a vm_swap_full() test in free_swap_cache()? It would be consistent, but I think we probably have enough for now. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:39:36 +08:00
extern int try_to_free_swap(struct page *);
struct backing_dev_info;
/* linux/mm/thrash.c */
extern struct mm_struct * swap_token_mm;
extern void grab_swap_token(void);
extern void __put_swap_token(struct mm_struct *);
static inline int has_swap_token(struct mm_struct *mm)
{
return (mm == swap_token_mm);
}
static inline void put_swap_token(struct mm_struct *mm)
{
if (has_swap_token(mm))
__put_swap_token(mm);
}
static inline void disable_swap_token(void)
{
put_swap_token(swap_token_mm);
}
#else /* CONFIG_SWAP */
#define total_swap_pages 0
#define total_swapcache_pages 0UL
#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 page_cache_release and release_pages undeclared... */
#define free_page_and_swap_cache(page) \
page_cache_release(page)
#define free_pages_and_swap_cache(pages, nr) \
release_pages((pages), (nr), 0);
static inline void show_swap_cache_info(void)
{
}
static inline void free_swap_and_cache(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 struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr)
{
return NULL;
}
static inline struct page *lookup_swap_cache(swp_entry_t swp)
{
return NULL;
}
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)
{
}
#define reuse_swap_page(page) (page_mapcount(page) == 1)
mm: try_to_free_swap replaces remove_exclusive_swap_page remove_exclusive_swap_page(): its problem is in living up to its name. It doesn't matter if someone else has a reference to the page (raised page_count); it doesn't matter if the page is mapped into userspace (raised page_mapcount - though that hints it may be worth keeping the swap): all that matters is that there be no more references to the swap (and no writeback in progress). swapoff (try_to_unuse) has been removing pages from swapcache for years, with no concern for page count or page mapcount, and we used to have a comment in lookup_swap_cache() recognizing that: if you go for a page of swapcache, you'll get the right page, but it could have been removed from swapcache by the time you get page lock. So, give up asking for exclusivity: get rid of remove_exclusive_swap_page(), and remove_exclusive_swap_page_ref() and remove_exclusive_swap_page_count() which were spawned for the recent LRU work: replace them by the simpler try_to_free_swap() which just checks page_swapcount(). Similarly, remove the page_count limitation from free_swap_and_count(), but assume that it's worth holding on to the swap if page is mapped and swap nowhere near full. Add a vm_swap_full() test in free_swap_cache()? It would be consistent, but I think we probably have enough for now. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:39:36 +08:00
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;
}
/* linux/mm/thrash.c */
#define put_swap_token(x) do { } while(0)
#define grab_swap_token() do { } while(0)
#define has_swap_token(x) 0
#define disable_swap_token() do { } while(0)
#endif /* CONFIG_SWAP */
#endif /* __KERNEL__*/
#endif /* _LINUX_SWAP_H */