mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-04 09:59:32 +00:00
![Andrea Arcangeli](/assets/img/avatar_default.png)
Lately I've been working to make KVM use hugepages transparently without the usual restrictions of hugetlbfs. Some of the restrictions I'd like to see removed: 1) hugepages have to be swappable or the guest physical memory remains locked in RAM and can't be paged out to swap 2) if a hugepage allocation fails, regular pages should be allocated instead and mixed in the same vma without any failure and without userland noticing 3) if some task quits and more hugepages become available in the buddy, guest physical memory backed by regular pages should be relocated on hugepages automatically in regions under madvise(MADV_HUGEPAGE) (ideally event driven by waking up the kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes not null) 4) avoidance of reservation and maximization of use of hugepages whenever possible. Reservation (needed to avoid runtime fatal faliures) may be ok for 1 machine with 1 database with 1 database cache with 1 database cache size known at boot time. It's definitely not feasible with a virtualization hypervisor usage like RHEV-H that runs an unknown number of virtual machines with an unknown size of each virtual machine with an unknown amount of pagecache that could be potentially useful in the host for guest not using O_DIRECT (aka cache=off). hugepages in the virtualization hypervisor (and also in the guest!) are much more important than in a regular host not using virtualization, becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24 to 19 in case only the hypervisor uses transparent hugepages, and they decrease the tlb-miss cacheline accesses from 19 to 15 in case both the linux hypervisor and the linux guest both uses this patch (though the guest will limit the addition speedup to anonymous regions only for now...). Even more important is that the tlb miss handler is much slower on a NPT/EPT guest than for a regular shadow paging or no-virtualization scenario. So maximizing the amount of virtual memory cached by the TLB pays off significantly more with NPT/EPT than without (even if there would be no significant speedup in the tlb-miss runtime). The first (and more tedious) part of this work requires allowing the VM to handle anonymous hugepages mixed with regular pages transparently on regular anonymous vmas. This is what this patch tries to achieve in the least intrusive possible way. We want hugepages and hugetlb to be used in a way so that all applications can benefit without changes (as usual we leverage the KVM virtualization design: by improving the Linux VM at large, KVM gets the performance boost too). The most important design choice is: always fallback to 4k allocation if the hugepage allocation fails! This is the _very_ opposite of some large pagecache patches that failed with -EIO back then if a 64k (or similar) allocation failed... Second important decision (to reduce the impact of the feature on the existing pagetable handling code) is that at any time we can split an hugepage into 512 regular pages and it has to be done with an operation that can't fail. This way the reliability of the swapping isn't decreased (no need to allocate memory when we are short on memory to swap) and it's trivial to plug a split_huge_page* one-liner where needed without polluting the VM. Over time we can teach mprotect, mremap and friends to handle pmd_trans_huge natively without calling split_huge_page*. The fact it can't fail isn't just for swap: if split_huge_page would return -ENOMEM (instead of the current void) we'd need to rollback the mprotect from the middle of it (ideally including undoing the split_vma) which would be a big change and in the very wrong direction (it'd likely be simpler not to call split_huge_page at all and to teach mprotect and friends to handle hugepages instead of rolling them back from the middle). In short the very value of split_huge_page is that it can't fail. The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and incremental and it'll just be an "harmless" addition later if this initial part is agreed upon. It also should be noted that locking-wise replacing regular pages with hugepages is going to be very easy if compared to what I'm doing below in split_huge_page, as it will only happen when page_count(page) matches page_mapcount(page) if we can take the PG_lock and mmap_sem in write mode. collapse_huge_page will be a "best effort" that (unlike split_huge_page) can fail at the minimal sign of trouble and we can try again later. collapse_huge_page will be similar to how KSM works and the madvise(MADV_HUGEPAGE) will work similar to madvise(MADV_MERGEABLE). The default I like is that transparent hugepages are used at page fault time. This can be changed with /sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set to three values "always", "madvise", "never" which mean respectively that hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions, or never used. /sys/kernel/mm/transparent_hugepage/defrag instead controls if the hugepage allocation should defrag memory aggressively "always", only inside "madvise" regions, or "never". The pmd_trans_splitting/pmd_trans_huge locking is very solid. The put_page (from get_user_page users that can't use mmu notifier like O_DIRECT) that runs against a __split_huge_page_refcount instead was a pain to serialize in a way that would result always in a coherent page count for both tail and head. I think my locking solution with a compound_lock taken only after the page_first is valid and is still a PageHead should be safe but it surely needs review from SMP race point of view. In short there is no current existing way to serialize the O_DIRECT final put_page against split_huge_page_refcount so I had to invent a new one (O_DIRECT loses knowledge on the mapping status by the time gup_fast returns so...). And I didn't want to impact all gup/gup_fast users for now, maybe if we change the gup interface substantially we can avoid this locking, I admit I didn't think too much about it because changing the gup unpinning interface would be invasive. If we ignored O_DIRECT we could stick to the existing compound refcounting code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM (and any other mmu notifier user) would call it without FOLL_GET (and if FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the current task mmu notifier list yet). But O_DIRECT is fundamental for decent performance of virtualized I/O on fast storage so we can't avoid it to solve the race of put_page against split_huge_page_refcount to achieve a complete hugepage feature for KVM. Swap and oom works fine (well just like with regular pages ;). MMU notifier is handled transparently too, with the exception of the young bit on the pmd, that didn't have a range check but I think KVM will be fine because the whole point of hugepages is that EPT/NPT will also use a huge pmd when they notice gup returns pages with PageCompound set, so they won't care of a range and there's just the pmd young bit to check in that case. NOTE: in some cases if the L2 cache is small, this may slowdown and waste memory during COWs because 4M of memory are accessed in a single fault instead of 8k (the payoff is that after COW the program can run faster). So we might want to switch the copy_huge_page (and clear_huge_page too) to not temporal stores. I also extensively researched ways to avoid this cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k up to 1M (I can send those patches that fully implemented prefault) but I concluded they're not worth it and they add an huge additional complexity and they remove all tlb benefits until the full hugepage has been faulted in, to save a little bit of memory and some cache during app startup, but they still don't improve substantially the cache-trashing during startup if the prefault happens in >4k chunks. One reason is that those 4k pte entries copied are still mapped on a perfectly cache-colored hugepage, so the trashing is the worst one can generate in those copies (cow of 4k page copies aren't so well colored so they trashes less, but again this results in software running faster after the page fault). Those prefault patches allowed things like a pte where post-cow pages were local 4k regular anon pages and the not-yet-cowed pte entries were pointing in the middle of some hugepage mapped read-only. If it doesn't payoff substantially with todays hardware it will payoff even less in the future with larger l2 caches, and the prefault logic would blot the VM a lot. If one is emebdded transparent_hugepage can be disabled during boot with sysfs or with the boot commandline parameter transparent_hugepage=0 (or transparent_hugepage=2 to restrict hugepages inside madvise regions) that will ensure not a single hugepage is allocated at boot time. It is simple enough to just disable transparent hugepage globally and let transparent hugepages be allocated selectively by applications in the MADV_HUGEPAGE region (both at page fault time, and if enabled with the collapse_huge_page too through the kernel daemon). This patch supports only hugepages mapped in the pmd, archs that have smaller hugepages will not fit in this patch alone. Also some archs like power have certain tlb limits that prevents mixing different page size in the same regions so they will not fit in this framework that requires "graceful fallback" to basic PAGE_SIZE in case of physical memory fragmentation. hugetlbfs remains a perfect fit for those because its software limits happen to match the hardware limits. hugetlbfs also remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped to be found not fragmented after a certain system uptime and that would be very expensive to defragment with relocation, so requiring reservation. hugetlbfs is the "reservation way", the point of transparent hugepages is not to have any reservation at all and maximizing the use of cache and hugepages at all times automatically. Some performance result: vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep ages3 memset page fault 1566023 memset tlb miss 453854 memset second tlb miss 453321 random access tlb miss 41635 random access second tlb miss 41658 vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3 memset page fault 1566471 memset tlb miss 453375 memset second tlb miss 453320 random access tlb miss 41636 random access second tlb miss 41637 vmx andrea # ./largepages3 memset page fault 1566642 memset tlb miss 453417 memset second tlb miss 453313 random access tlb miss 41630 random access second tlb miss 41647 vmx andrea # ./largepages3 memset page fault 1566872 memset tlb miss 453418 memset second tlb miss 453315 random access tlb miss 41618 random access second tlb miss 41659 vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage vmx andrea # ./largepages3 memset page fault 2182476 memset tlb miss 460305 memset second tlb miss 460179 random access tlb miss 44483 random access second tlb miss 44186 vmx andrea # ./largepages3 memset page fault 2182791 memset tlb miss 460742 memset second tlb miss 459962 random access tlb miss 43981 random access second tlb miss 43988 ============ #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/time.h> #define SIZE (3UL*1024*1024*1024) int main() { char *p = malloc(SIZE), *p2; struct timeval before, after; gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset page fault %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); return 0; } ============ Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
513 lines
15 KiB
C
513 lines
15 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
|
|
#define SWAP_FLAG_DISCARD 0x10000 /* discard swap cluster after use */
|
|
|
|
static inline int current_is_kswapd(void)
|
|
{
|
|
return current->flags & PF_KSWAPD;
|
|
}
|
|
|
|
/*
|
|
* MAX_SWAPFILES defines the maximum number of swaptypes: things which can
|
|
* be swapped to. The swap type and the offset into that swap type are
|
|
* encoded into pte's and into pgoff_t's in the swapcache. Using five bits
|
|
* for the type means that the maximum number of swapcache pages is 27 bits
|
|
* on 32-bit-pgoff_t architectures. And that assumes that the architecture packs
|
|
* the type/offset into the pte as 5/27 as well.
|
|
*/
|
|
#define MAX_SWAPFILES_SHIFT 5
|
|
|
|
/*
|
|
* Use some of the swap files numbers for other purposes. This
|
|
* is a convenient way to hook into the VM to trigger special
|
|
* actions on faults.
|
|
*/
|
|
|
|
/*
|
|
* NUMA node memory migration support
|
|
*/
|
|
#ifdef CONFIG_MIGRATION
|
|
#define SWP_MIGRATION_NUM 2
|
|
#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM)
|
|
#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1)
|
|
#else
|
|
#define SWP_MIGRATION_NUM 0
|
|
#endif
|
|
|
|
/*
|
|
* Handling of hardware poisoned pages with memory corruption.
|
|
*/
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
#define SWP_HWPOISON_NUM 1
|
|
#define SWP_HWPOISON MAX_SWAPFILES
|
|
#else
|
|
#define SWP_HWPOISON_NUM 0
|
|
#endif
|
|
|
|
#define MAX_SWAPFILES \
|
|
((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
|
|
|
|
/*
|
|
* Magic header for a swap area. The first part of the union is
|
|
* what the swap magic looks like for the old (limited to 128MB)
|
|
* swap area format, the second part of the union adds - in the
|
|
* old reserved area - some extra information. Note that the first
|
|
* kilobyte is reserved for boot loader or disk label stuff...
|
|
*
|
|
* Having the magic at the end of the PAGE_SIZE makes detecting swap
|
|
* areas somewhat tricky on machines that support multiple page sizes.
|
|
* For 2.5 we'll probably want to move the magic to just beyond the
|
|
* bootbits...
|
|
*/
|
|
union swap_header {
|
|
struct {
|
|
char reserved[PAGE_SIZE - 10];
|
|
char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */
|
|
} magic;
|
|
struct {
|
|
char bootbits[1024]; /* Space for disklabel etc. */
|
|
__u32 version;
|
|
__u32 last_page;
|
|
__u32 nr_badpages;
|
|
unsigned char sws_uuid[16];
|
|
unsigned char sws_volume[16];
|
|
__u32 padding[117];
|
|
__u32 badpages[1];
|
|
} info;
|
|
};
|
|
|
|
/* 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), /* swapon+blkdev support discard */
|
|
SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */
|
|
SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */
|
|
SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */
|
|
SWP_BLKDEV = (1 << 6), /* its a block device */
|
|
/* add others here before... */
|
|
SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */
|
|
};
|
|
|
|
#define SWAP_CLUSTER_MAX 32
|
|
#define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
|
|
|
|
#define SWAP_MAP_MAX 0x3e /* Max duplication count, in first swap_map */
|
|
#define SWAP_MAP_BAD 0x3f /* Note pageblock is bad, in first swap_map */
|
|
#define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */
|
|
#define SWAP_CONT_MAX 0x7f /* Max count, in each swap_map continuation */
|
|
#define COUNT_CONTINUED 0x80 /* See swap_map continuation for full count */
|
|
#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs, in first swap_map */
|
|
|
|
/*
|
|
* The in-memory structure used to track swap areas.
|
|
*/
|
|
struct swap_info_struct {
|
|
unsigned long flags; /* SWP_USED etc: see above */
|
|
signed short prio; /* swap priority of this type */
|
|
signed char type; /* strange name for an index */
|
|
signed char next; /* next type on the swap list */
|
|
unsigned int max; /* extent of the swap_map */
|
|
unsigned char *swap_map; /* vmalloc'ed array of usage counts */
|
|
unsigned int lowest_bit; /* index of first free in swap_map */
|
|
unsigned int highest_bit; /* index of last free in swap_map */
|
|
unsigned int pages; /* total of usable pages of swap */
|
|
unsigned int inuse_pages; /* number of those currently in use */
|
|
unsigned int cluster_next; /* likely index for next allocation */
|
|
unsigned int cluster_nr; /* countdown to next cluster search */
|
|
unsigned int lowest_alloc; /* while preparing discard cluster */
|
|
unsigned int highest_alloc; /* while preparing discard cluster */
|
|
struct swap_extent *curr_swap_extent;
|
|
struct swap_extent first_swap_extent;
|
|
struct block_device *bdev; /* swap device or bdev of swap file */
|
|
struct file *swap_file; /* seldom referenced */
|
|
unsigned int old_block_size; /* seldom referenced */
|
|
};
|
|
|
|
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 lru_add_page_tail(struct zone* zone,
|
|
struct page *page, struct page *page_tail);
|
|
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_file(struct page *page)
|
|
{
|
|
__lru_cache_add(page, LRU_INACTIVE_FILE);
|
|
}
|
|
|
|
/* LRU Isolation modes. */
|
|
#define ISOLATE_INACTIVE 0 /* Isolate inactive pages. */
|
|
#define ISOLATE_ACTIVE 1 /* Isolate active pages. */
|
|
#define ISOLATE_BOTH 2 /* Isolate both active and inactive pages. */
|
|
|
|
/* 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 unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
|
|
gfp_t gfp_mask, bool noswap,
|
|
unsigned int swappiness,
|
|
struct zone *zone);
|
|
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,
|
|
void __user *, size_t *, loff_t *);
|
|
#ifdef CONFIG_NUMA
|
|
extern int scan_unevictable_register_node(struct node *node);
|
|
extern void scan_unevictable_unregister_node(struct node *node);
|
|
#else
|
|
static inline int scan_unevictable_register_node(struct node *node)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void scan_unevictable_unregister_node(struct node *node)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
extern int kswapd_run(int nid);
|
|
extern void kswapd_stop(int nid);
|
|
|
|
#ifdef CONFIG_MMU
|
|
/* linux/mm/shmem.c */
|
|
extern int shmem_unuse(swp_entry_t entry, struct page *page);
|
|
#endif /* CONFIG_MMU */
|
|
|
|
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
|
|
extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff,
|
|
struct page **pagep, swp_entry_t *ent);
|
|
#endif
|
|
|
|
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 int valid_swaphandles(swp_entry_t, unsigned long *);
|
|
extern int add_swap_count_continuation(swp_entry_t, gfp_t);
|
|
extern void swap_shmem_alloc(swp_entry_t);
|
|
extern int swap_duplicate(swp_entry_t);
|
|
extern int swapcache_prepare(swp_entry_t);
|
|
extern void swap_free(swp_entry_t);
|
|
extern void swapcache_free(swp_entry_t, 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 page *, struct block_device **);
|
|
extern sector_t swapdev_block(int, pgoff_t);
|
|
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);
|
|
extern int mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep);
|
|
#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 int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void swap_shmem_alloc(swp_entry_t swp)
|
|
{
|
|
}
|
|
|
|
static inline int swap_duplicate(swp_entry_t swp)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void swap_free(swp_entry_t swp)
|
|
{
|
|
}
|
|
|
|
static inline void swapcache_free(swp_entry_t swp, 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 */
|
|
static inline void put_swap_token(struct mm_struct *mm)
|
|
{
|
|
}
|
|
|
|
static inline void grab_swap_token(struct mm_struct *mm)
|
|
{
|
|
}
|
|
|
|
static inline int has_swap_token(struct mm_struct *mm)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void disable_swap_token(void)
|
|
{
|
|
}
|
|
|
|
static inline void
|
|
mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
|
|
{
|
|
}
|
|
|
|
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
|
|
static inline int
|
|
mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#endif /* CONFIG_SWAP */
|
|
#endif /* __KERNEL__*/
|
|
#endif /* _LINUX_SWAP_H */
|