linux-stable/include/linux/swap.h
Mel Gorman dac1d27bc8 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 08:58:18 -07:00

360 lines
9.9 KiB
C

#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 <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
#ifndef CONFIG_MIGRATION
#define MAX_SWAPFILES (1 << MAX_SWAPFILES_SHIFT)
#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;
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 *);
extern void lru_cache_add_active(struct page *);
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 int rotate_reclaimable_page(struct page *page);
extern void swap_setup(void);
/* linux/mm/vmscan.c */
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask);
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
gfp_t gfp_mask);
extern int __isolate_lru_page(struct page *page, int mode);
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;
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 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 *, gfp_t);
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 unsigned int nr_swapfiles;
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 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 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;
}
#define can_share_swap_page(p) (page_mapcount(p) == 1)
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 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 */