mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 03:10:12 +00:00
![Hugh Dickins](/assets/img/avatar_default.png)
If a kthread happens to use get_user_pages() on an mm (as KSM does), there's a chance that it will end up trying to read in a swap page, then oops in grab_swap_token() because the kthread has no mm: GUP passes down the right mm, so grab_swap_token() ought to be using it. We have not identified a stronger case than KSM's daemon (not yet in mainline), but the issue must have come up before, since RHEL has included a fix for this for years (though a different fix, they just back out of grab_swap_token if current->mm is unset: which is what we first proposed, but using the right mm here seems more correct). Reported-by: Izik Eidus <ieidus@redhat.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
434 lines
12 KiB
C
434 lines
12 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 <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
|
|
#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_DISCARDABLE = (1 << 2), /* blkdev supports discard */
|
|
SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */
|
|
SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */
|
|
/* add others here before... */
|
|
SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */
|
|
};
|
|
|
|
#define SWAP_CLUSTER_MAX 32
|
|
|
|
#define SWAP_MAP_MAX 0x7ffe
|
|
#define SWAP_MAP_BAD 0x7fff
|
|
#define SWAP_HAS_CACHE 0x8000 /* There is a swap cache of entry. */
|
|
#define SWAP_COUNT_MASK (~SWAP_HAS_CACHE)
|
|
/*
|
|
* The in-memory structure used to track swap areas.
|
|
*/
|
|
struct swap_info_struct {
|
|
unsigned long flags;
|
|
int prio; /* swap priority */
|
|
int next; /* next entry on swap list */
|
|
struct file *swap_file;
|
|
struct block_device *bdev;
|
|
struct list_head extent_list;
|
|
struct swap_extent *curr_swap_extent;
|
|
unsigned short *swap_map;
|
|
unsigned int lowest_bit;
|
|
unsigned int highest_bit;
|
|
unsigned int lowest_alloc; /* while preparing discard cluster */
|
|
unsigned int highest_alloc; /* while preparing discard cluster */
|
|
unsigned int cluster_next;
|
|
unsigned int cluster_nr;
|
|
unsigned int pages;
|
|
unsigned int max;
|
|
unsigned int inuse_pages;
|
|
unsigned int old_block_size;
|
|
};
|
|
|
|
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 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);
|
|
|
|
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
|
|
*/
|
|
static inline void lru_cache_add_anon(struct page *page)
|
|
{
|
|
__lru_cache_add(page, LRU_INACTIVE_ANON);
|
|
}
|
|
|
|
static inline void lru_cache_add_active_anon(struct page *page)
|
|
{
|
|
__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 */
|
|
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
|
|
gfp_t gfp_mask, nodemask_t *mask);
|
|
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
|
|
gfp_t gfp_mask, bool noswap,
|
|
unsigned int swappiness);
|
|
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;
|
|
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, 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);
|
|
|
|
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 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 nr_swap_pages;
|
|
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 void swap_duplicate(swp_entry_t);
|
|
extern int swapcache_prepare(swp_entry_t);
|
|
extern int valid_swaphandles(swp_entry_t, unsigned long *);
|
|
extern void swap_free(swp_entry_t);
|
|
extern void swapcache_free(swp_entry_t, struct page *page);
|
|
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 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 *);
|
|
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(struct mm_struct *);
|
|
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);
|
|
}
|
|
|
|
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
|
|
extern void
|
|
mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout);
|
|
#else
|
|
static inline void
|
|
mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
|
|
{
|
|
}
|
|
#endif
|
|
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
|
|
extern void mem_cgroup_uncharge_swap(swp_entry_t ent);
|
|
#else
|
|
static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#else /* CONFIG_SWAP */
|
|
|
|
#define nr_swap_pages 0L
|
|
#define total_swap_pages 0L
|
|
#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)
|
|
{
|
|
}
|
|
|
|
#define free_swap_and_cache(swp) is_migration_entry(swp)
|
|
#define swapcache_prepare(swp) is_migration_entry(swp)
|
|
|
|
static inline void swap_duplicate(swp_entry_t swp)
|
|
{
|
|
}
|
|
|
|
static inline void swap_free(swp_entry_t swp)
|
|
{
|
|
}
|
|
|
|
static inline void swapcache_free(swp_entry_t swp, struct page *page)
|
|
{
|
|
}
|
|
|
|
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)
|
|
{
|
|
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)
|
|
{
|
|
}
|
|
|
|
#define reuse_swap_page(page) (page_mapcount(page) == 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;
|
|
}
|
|
|
|
/* linux/mm/thrash.c */
|
|
#define put_swap_token(mm) do { } while (0)
|
|
#define grab_swap_token(mm) do { } while (0)
|
|
#define has_swap_token(mm) 0
|
|
#define disable_swap_token() do { } while (0)
|
|
|
|
static inline void
|
|
mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
|
|
{
|
|
}
|
|
|
|
#endif /* CONFIG_SWAP */
|
|
#endif /* __KERNEL__*/
|
|
#endif /* _LINUX_SWAP_H */
|