linux-sg2042/include/linux/swap.h

320 lines
9.6 KiB
C
Raw Normal View History

#ifndef _LINUX_SWAP_H
#define _LINUX_SWAP_H
#include <linux/config.h>
#include <linux/spinlock.h>
#include <linux/linkage.h>
#include <linux/mmzone.h>
#include <linux/list.h>
#include <linux/sched.h>
#include <asm/atomic.h>
#include <asm/page.h>
#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
#define MAX_SWAPFILES (1 << MAX_SWAPFILES_SHIFT)
/*
* 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. */
unsigned int version;
unsigned int last_page;
unsigned int nr_badpages;
unsigned int padding[125];
unsigned int 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/oom_kill.c */
extern void out_of_memory(gfp_t gfp_mask, int order);
/* linux/mm/memory.c */
extern void swapin_readahead(swp_entry_t, unsigned long, struct vm_area_struct *);
/* linux/mm/page_alloc.c */
extern unsigned long totalram_pages;
extern unsigned long totalhigh_pages;
extern long nr_swap_pages;
extern unsigned int nr_free_pages(void);
extern unsigned int nr_free_pages_pgdat(pg_data_t *pgdat);
extern unsigned int nr_free_buffer_pages(void);
extern unsigned int nr_free_pagecache_pages(void);
/* linux/mm/swap.c */
extern void FASTCALL(lru_cache_add(struct page *));
extern void FASTCALL(lru_cache_add_active(struct page *));
extern void FASTCALL(activate_page(struct page *));
extern void FASTCALL(mark_page_accessed(struct page *));
extern void lru_add_drain(void);
extern int lru_add_drain_all(void);
extern int rotate_reclaimable_page(struct page *page);
extern void swap_setup(void);
/* linux/mm/vmscan.c */
extern int try_to_free_pages(struct zone **, gfp_t);
extern int shrink_all_memory(int);
extern int vm_swappiness;
#ifdef CONFIG_NUMA
extern int zone_reclaim_mode;
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
#ifdef CONFIG_MIGRATION
[PATCH] Swap Migration V5: LRU operations This is the start of the `swap migration' patch series. Swap migration allows the moving of the physical location of pages between nodes in a numa system while the process is running. This means that the virtual addresses that the process sees do not change. However, the system rearranges the physical location of those pages. The main intent of page migration patches here is to reduce the latency of memory access by moving pages near to the processor where the process accessing that memory is running. The patchset allows a process to manually relocate the node on which its pages are located through the MF_MOVE and MF_MOVE_ALL options while setting a new memory policy. The pages of process can also be relocated from another process using the sys_migrate_pages() function call. Requires CAP_SYS_ADMIN. The migrate_pages function call takes two sets of nodes and moves pages of a process that are located on the from nodes to the destination nodes. Manual migration is very useful if for example the scheduler has relocated a process to a processor on a distant node. A batch scheduler or an administrator can detect the situation and move the pages of the process nearer to the new processor. sys_migrate_pages() could be used on non-numa machines as well, to force all of a particualr process's pages out to swap, if someone thinks that's useful. Larger installations usually partition the system using cpusets into sections of nodes. Paul has equipped cpusets with the ability to move pages when a task is moved to another cpuset. This allows automatic control over locality of a process. If a task is moved to a new cpuset then also all its pages are moved with it so that the performance of the process does not sink dramatically (as is the case today). Swap migration works by simply evicting the page. The pages must be faulted back in. The pages are then typically reallocated by the system near the node where the process is executing. For swap migration the destination of the move is controlled by the allocation policy. Cpusets set the allocation policy before calling sys_migrate_pages() in order to move the pages as intended. No allocation policy changes are performed for sys_migrate_pages(). This means that the pages may not faulted in to the specified nodes if no allocation policy was set by other means. The pages will just end up near the node where the fault occurred. There's another patch series in the pipeline which implements "direct migration". The direct migration patchset extends the migration functionality to avoid going through swap. The destination node of the relation is controllable during the actual moving of pages. The crutch of using the allocation policy to relocate is not necessary and the pages are moved directly to the target. Its also faster since swap is not used. And sys_migrate_pages() can then move pages directly to the specified node. Implement functions to isolate pages from the LRU and put them back later. This patch: An earlier implementation was provided by Hirokazu Takahashi <taka@valinux.co.jp> and IWAMOTO Toshihiro <iwamoto@valinux.co.jp> for the memory hotplug project. From: Magnus This breaks out isolate_lru_page() and putpack_lru_page(). Needed for swap migration. Signed-off-by: Magnus Damm <magnus.damm@gmail.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:45 +08:00
extern int isolate_lru_page(struct page *p);
extern int putback_lru_pages(struct list_head *l);
extern int migrate_pages(struct list_head *l, struct list_head *t,
struct list_head *moved, struct list_head *failed);
#else
static inline int isolate_lru_page(struct page *p) { return -ENOSYS; }
static inline int putback_lru_pages(struct list_head *l) { return 0; }
static inline int migrate_pages(struct list_head *l, struct list_head *t,
struct list_head *moved, struct list_head *failed) { return -ENOSYS; }
#endif
[PATCH] Swap Migration V5: migrate_pages() function This adds the basic page migration function with a minimal implementation that only allows the eviction of pages to swap space. Page eviction and migration may be useful to migrate pages, to suspend programs or for remapping single pages (useful for faulty pages or pages with soft ECC failures) The process is as follows: The function wanting to migrate pages must first build a list of pages to be migrated or evicted and take them off the lru lists via isolate_lru_page(). isolate_lru_page determines that a page is freeable based on the LRU bit set. Then the actual migration or swapout can happen by calling migrate_pages(). migrate_pages does its best to migrate or swapout the pages and does multiple passes over the list. Some pages may only be swappable if they are not dirty. migrate_pages may start writing out dirty pages in the initial passes over the pages. However, migrate_pages may not be able to migrate or evict all pages for a variety of reasons. The remaining pages may be returned to the LRU lists using putback_lru_pages(). Changelog V4->V5: - Use the lru caches to return pages to the LRU Changelog V3->V4: - Restructure code so that applying patches to support full migration does require minimal changes. Rename swapout_pages() to migrate_pages(). Changelog V2->V3: - Extract common code from shrink_list() and swapout_pages() Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: "Michael Kerrisk" <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:48 +08:00
#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 int rw_swap_page_sync(int, swp_entry_t, struct page *);
/* 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 *, gfp_t);
extern void __delete_from_swap_cache(struct page *);
extern void delete_from_swap_cache(struct page *);
extern int move_to_swap_cache(struct page *, swp_entry_t);
extern int move_from_swap_cache(struct page *, unsigned long,
struct address_space *);
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, struct vm_area_struct *vma,
unsigned long addr);
/* linux/mm/swapfile.c */
extern long total_swap_pages;
extern unsigned int nr_swapfiles;
extern struct swap_info_struct swap_info[];
extern void si_swapinfo(struct sysinfo *);
extern swp_entry_t get_swap_page(void);
extern swp_entry_t get_swap_page_of_type(int type);
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 sector_t map_swap_page(struct swap_info_struct *, pgoff_t);
extern struct swap_info_struct *get_swap_info_struct(unsigned);
extern int can_share_swap_page(struct page *);
extern int remove_exclusive_swap_page(struct page *);
struct backing_dev_info;
extern spinlock_t swap_lock;
/* linux/mm/thrash.c */
extern struct mm_struct * swap_token_mm;
extern unsigned long swap_token_default_timeout;
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);
#define show_swap_cache_info() /*NOTHING*/
#define free_swap_and_cache(swp) /*NOTHING*/
#define swap_duplicate(swp) /*NOTHING*/
#define swap_free(swp) /*NOTHING*/
#define read_swap_cache_async(swp,vma,addr) NULL
#define lookup_swap_cache(swp) NULL
#define valid_swaphandles(swp, off) 0
#define can_share_swap_page(p) 0
#define move_to_swap_cache(p, swp) 1
#define move_from_swap_cache(p, i, m) 1
#define __delete_from_swap_cache(p) /*NOTHING*/
#define delete_from_swap_cache(p) /*NOTHING*/
#define swap_token_default_timeout 0
static inline int remove_exclusive_swap_page(struct page *p)
{
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 */