linux/mm/internal.h
Wu Fengguang 20a0307c03 mm: introduce PageHuge() for testing huge/gigantic pages
A series of patches to enhance the /proc/pagemap interface and to add a
userspace executable which can be used to present the pagemap data.

Export 10 more flags to end users (and more for kernel developers):

        11. KPF_MMAP            (pseudo flag) memory mapped page
        12. KPF_ANON            (pseudo flag) memory mapped page (anonymous)
        13. KPF_SWAPCACHE       page is in swap cache
        14. KPF_SWAPBACKED      page is swap/RAM backed
        15. KPF_COMPOUND_HEAD   (*)
        16. KPF_COMPOUND_TAIL   (*)
        17. KPF_HUGE		hugeTLB pages
        18. KPF_UNEVICTABLE     page is in the unevictable LRU list
        19. KPF_HWPOISON        hardware detected corruption
        20. KPF_NOPAGE          (pseudo flag) no page frame at the address

        (*) For compound pages, exporting _both_ head/tail info enables
            users to tell where a compound page starts/ends, and its order.

a simple demo of the page-types tool

# ./page-types -h
page-types [options]
            -r|--raw                  Raw mode, for kernel developers
            -a|--addr    addr-spec    Walk a range of pages
            -b|--bits    bits-spec    Walk pages with specified bits
            -l|--list                 Show page details in ranges
            -L|--list-each            Show page details one by one
            -N|--no-summary           Don't show summay info
            -h|--help                 Show this usage message
addr-spec:
            N                         one page at offset N (unit: pages)
            N+M                       pages range from N to N+M-1
            N,M                       pages range from N to M-1
            N,                        pages range from N to end
            ,M                        pages range from 0 to M
bits-spec:
            bit1,bit2                 (flags & (bit1|bit2)) != 0
            bit1,bit2=bit1            (flags & (bit1|bit2)) == bit1
            bit1,~bit2                (flags & (bit1|bit2)) == bit1
            =bit1,bit2                flags == (bit1|bit2)
bit-names:
          locked              error         referenced           uptodate
           dirty                lru             active               slab
       writeback            reclaim              buddy               mmap
       anonymous          swapcache         swapbacked      compound_head
   compound_tail               huge        unevictable           hwpoison
          nopage           reserved(r)         mlocked(r)    mappedtodisk(r)
         private(r)       private_2(r)   owner_private(r)            arch(r)
        uncached(r)       readahead(o)       slob_free(o)     slub_frozen(o)
      slub_debug(o)
                                   (r) raw mode bits  (o) overloaded bits

# ./page-types
             flags      page-count       MB  symbolic-flags                     long-symbolic-flags
0x0000000000000000          487369     1903  _________________________________
0x0000000000000014               5        0  __R_D____________________________  referenced,dirty
0x0000000000000020               1        0  _____l___________________________  lru
0x0000000000000024              34        0  __R__l___________________________  referenced,lru
0x0000000000000028            3838       14  ___U_l___________________________  uptodate,lru
0x0001000000000028              48        0  ___U_l_______________________I___  uptodate,lru,readahead
0x000000000000002c            6478       25  __RU_l___________________________  referenced,uptodate,lru
0x000100000000002c              47        0  __RU_l_______________________I___  referenced,uptodate,lru,readahead
0x0000000000000040            8344       32  ______A__________________________  active
0x0000000000000060               1        0  _____lA__________________________  lru,active
0x0000000000000068             348        1  ___U_lA__________________________  uptodate,lru,active
0x0001000000000068              12        0  ___U_lA______________________I___  uptodate,lru,active,readahead
0x000000000000006c             988        3  __RU_lA__________________________  referenced,uptodate,lru,active
0x000100000000006c              48        0  __RU_lA______________________I___  referenced,uptodate,lru,active,readahead
0x0000000000004078               1        0  ___UDlA_______b__________________  uptodate,dirty,lru,active,swapbacked
0x000000000000407c              34        0  __RUDlA_______b__________________  referenced,uptodate,dirty,lru,active,swapbacked
0x0000000000000400             503        1  __________B______________________  buddy
0x0000000000000804               1        0  __R________M_____________________  referenced,mmap
0x0000000000000828            1029        4  ___U_l_____M_____________________  uptodate,lru,mmap
0x0001000000000828              43        0  ___U_l_____M_________________I___  uptodate,lru,mmap,readahead
0x000000000000082c             382        1  __RU_l_____M_____________________  referenced,uptodate,lru,mmap
0x000100000000082c              12        0  __RU_l_____M_________________I___  referenced,uptodate,lru,mmap,readahead
0x0000000000000868             192        0  ___U_lA____M_____________________  uptodate,lru,active,mmap
0x0001000000000868              12        0  ___U_lA____M_________________I___  uptodate,lru,active,mmap,readahead
0x000000000000086c             800        3  __RU_lA____M_____________________  referenced,uptodate,lru,active,mmap
0x000100000000086c              31        0  __RU_lA____M_________________I___  referenced,uptodate,lru,active,mmap,readahead
0x0000000000004878               2        0  ___UDlA____M__b__________________  uptodate,dirty,lru,active,mmap,swapbacked
0x0000000000001000             492        1  ____________a____________________  anonymous
0x0000000000005808               4        0  ___U_______Ma_b__________________  uptodate,mmap,anonymous,swapbacked
0x0000000000005868            2839       11  ___U_lA____Ma_b__________________  uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c              30        0  __RU_lA____Ma_b__________________  referenced,uptodate,lru,active,mmap,anonymous,swapbacked
             total          513968     2007

# ./page-types -r
             flags      page-count       MB  symbolic-flags                     long-symbolic-flags
0x0000000000000000          468002     1828  _________________________________
0x0000000100000000           19102       74  _____________________r___________  reserved
0x0000000000008000              41        0  _______________H_________________  compound_head
0x0000000000010000             188        0  ________________T________________  compound_tail
0x0000000000008014               1        0  __R_D__________H_________________  referenced,dirty,compound_head
0x0000000000010014               4        0  __R_D___________T________________  referenced,dirty,compound_tail
0x0000000000000020               1        0  _____l___________________________  lru
0x0000000800000024              34        0  __R__l__________________P________  referenced,lru,private
0x0000000000000028            3794       14  ___U_l___________________________  uptodate,lru
0x0001000000000028              46        0  ___U_l_______________________I___  uptodate,lru,readahead
0x0000000400000028              44        0  ___U_l_________________d_________  uptodate,lru,mappedtodisk
0x0001000400000028               2        0  ___U_l_________________d_____I___  uptodate,lru,mappedtodisk,readahead
0x000000000000002c            6434       25  __RU_l___________________________  referenced,uptodate,lru
0x000100000000002c              47        0  __RU_l_______________________I___  referenced,uptodate,lru,readahead
0x000000040000002c              14        0  __RU_l_________________d_________  referenced,uptodate,lru,mappedtodisk
0x000000080000002c              30        0  __RU_l__________________P________  referenced,uptodate,lru,private
0x0000000800000040            8124       31  ______A_________________P________  active,private
0x0000000000000040             219        0  ______A__________________________  active
0x0000000800000060               1        0  _____lA_________________P________  lru,active,private
0x0000000000000068             322        1  ___U_lA__________________________  uptodate,lru,active
0x0001000000000068              12        0  ___U_lA______________________I___  uptodate,lru,active,readahead
0x0000000400000068              13        0  ___U_lA________________d_________  uptodate,lru,active,mappedtodisk
0x0000000800000068              12        0  ___U_lA_________________P________  uptodate,lru,active,private
0x000000000000006c             977        3  __RU_lA__________________________  referenced,uptodate,lru,active
0x000100000000006c              48        0  __RU_lA______________________I___  referenced,uptodate,lru,active,readahead
0x000000040000006c               5        0  __RU_lA________________d_________  referenced,uptodate,lru,active,mappedtodisk
0x000000080000006c               3        0  __RU_lA_________________P________  referenced,uptodate,lru,active,private
0x0000000c0000006c               3        0  __RU_lA________________dP________  referenced,uptodate,lru,active,mappedtodisk,private
0x0000000c00000068               1        0  ___U_lA________________dP________  uptodate,lru,active,mappedtodisk,private
0x0000000000004078               1        0  ___UDlA_______b__________________  uptodate,dirty,lru,active,swapbacked
0x000000000000407c              34        0  __RUDlA_______b__________________  referenced,uptodate,dirty,lru,active,swapbacked
0x0000000000000400             538        2  __________B______________________  buddy
0x0000000000000804               1        0  __R________M_____________________  referenced,mmap
0x0000000000000828            1029        4  ___U_l_____M_____________________  uptodate,lru,mmap
0x0001000000000828              43        0  ___U_l_____M_________________I___  uptodate,lru,mmap,readahead
0x000000000000082c             382        1  __RU_l_____M_____________________  referenced,uptodate,lru,mmap
0x000100000000082c              12        0  __RU_l_____M_________________I___  referenced,uptodate,lru,mmap,readahead
0x0000000000000868             192        0  ___U_lA____M_____________________  uptodate,lru,active,mmap
0x0001000000000868              12        0  ___U_lA____M_________________I___  uptodate,lru,active,mmap,readahead
0x000000000000086c             800        3  __RU_lA____M_____________________  referenced,uptodate,lru,active,mmap
0x000100000000086c              31        0  __RU_lA____M_________________I___  referenced,uptodate,lru,active,mmap,readahead
0x0000000000004878               2        0  ___UDlA____M__b__________________  uptodate,dirty,lru,active,mmap,swapbacked
0x0000000000001000             492        1  ____________a____________________  anonymous
0x0000000000005008               2        0  ___U________a_b__________________  uptodate,anonymous,swapbacked
0x0000000000005808               4        0  ___U_______Ma_b__________________  uptodate,mmap,anonymous,swapbacked
0x000000000000580c               1        0  __RU_______Ma_b__________________  referenced,uptodate,mmap,anonymous,swapbacked
0x0000000000005868            2839       11  ___U_lA____Ma_b__________________  uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c              29        0  __RU_lA____Ma_b__________________  referenced,uptodate,lru,active,mmap,anonymous,swapbacked
             total          513968     2007

# ./page-types --raw --list --no-summary --bits reserved
offset  count   flags
0       15      _____________________r___________
31      4       _____________________r___________
159     97      _____________________r___________
4096    2067    _____________________r___________
6752    2390    _____________________r___________
9355    3       _____________________r___________
9728    14526   _____________________r___________

This patch:

Introduce PageHuge(), which identifies huge/gigantic pages by their
dedicated compound destructor functions.

Also move prep_compound_gigantic_page() to hugetlb.c and make
__free_pages_ok() non-static.

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-16 19:47:36 -07:00

269 lines
7.3 KiB
C

/* internal.h: mm/ internal definitions
*
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef __MM_INTERNAL_H
#define __MM_INTERNAL_H
#include <linux/mm.h>
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
unsigned long floor, unsigned long ceiling);
static inline void set_page_count(struct page *page, int v)
{
atomic_set(&page->_count, v);
}
/*
* Turn a non-refcounted page (->_count == 0) into refcounted with
* a count of one.
*/
static inline void set_page_refcounted(struct page *page)
{
VM_BUG_ON(PageTail(page));
VM_BUG_ON(atomic_read(&page->_count));
set_page_count(page, 1);
}
static inline void __put_page(struct page *page)
{
atomic_dec(&page->_count);
}
/*
* in mm/vmscan.c:
*/
extern int isolate_lru_page(struct page *page);
extern void putback_lru_page(struct page *page);
/*
* in mm/page_alloc.c
*/
extern unsigned long highest_memmap_pfn;
extern void __free_pages_bootmem(struct page *page, unsigned int order);
extern void prep_compound_page(struct page *page, unsigned long order);
/*
* function for dealing with page's order in buddy system.
* zone->lock is already acquired when we use these.
* So, we don't need atomic page->flags operations here.
*/
static inline unsigned long page_order(struct page *page)
{
VM_BUG_ON(!PageBuddy(page));
return page_private(page);
}
#ifdef CONFIG_HAVE_MLOCK
extern long mlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
extern void munlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
{
munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end);
}
#endif
#ifdef CONFIG_UNEVICTABLE_LRU
/*
* unevictable_migrate_page() called only from migrate_page_copy() to
* migrate unevictable flag to new page.
* Note that the old page has been isolated from the LRU lists at this
* point so we don't need to worry about LRU statistics.
*/
static inline void unevictable_migrate_page(struct page *new, struct page *old)
{
if (TestClearPageUnevictable(old))
SetPageUnevictable(new);
}
#else
static inline void unevictable_migrate_page(struct page *new, struct page *old)
{
}
#endif
#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT
/*
* Called only in fault path via page_evictable() for a new page
* to determine if it's being mapped into a LOCKED vma.
* If so, mark page as mlocked.
*/
static inline int is_mlocked_vma(struct vm_area_struct *vma, struct page *page)
{
VM_BUG_ON(PageLRU(page));
if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED))
return 0;
if (!TestSetPageMlocked(page)) {
inc_zone_page_state(page, NR_MLOCK);
count_vm_event(UNEVICTABLE_PGMLOCKED);
}
return 1;
}
/*
* must be called with vma's mmap_sem held for read, and page locked.
*/
extern void mlock_vma_page(struct page *page);
/*
* Clear the page's PageMlocked(). This can be useful in a situation where
* we want to unconditionally remove a page from the pagecache -- e.g.,
* on truncation or freeing.
*
* It is legal to call this function for any page, mlocked or not.
* If called for a page that is still mapped by mlocked vmas, all we do
* is revert to lazy LRU behaviour -- semantics are not broken.
*/
extern void __clear_page_mlock(struct page *page);
static inline void clear_page_mlock(struct page *page)
{
if (unlikely(TestClearPageMlocked(page)))
__clear_page_mlock(page);
}
/*
* mlock_migrate_page - called only from migrate_page_copy() to
* migrate the Mlocked page flag; update statistics.
*/
static inline void mlock_migrate_page(struct page *newpage, struct page *page)
{
if (TestClearPageMlocked(page)) {
unsigned long flags;
local_irq_save(flags);
__dec_zone_page_state(page, NR_MLOCK);
SetPageMlocked(newpage);
__inc_zone_page_state(newpage, NR_MLOCK);
local_irq_restore(flags);
}
}
#else /* CONFIG_HAVE_MLOCKED_PAGE_BIT */
static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
{
return 0;
}
static inline void clear_page_mlock(struct page *page) { }
static inline void mlock_vma_page(struct page *page) { }
static inline void mlock_migrate_page(struct page *new, struct page *old) { }
#endif /* CONFIG_HAVE_MLOCKED_PAGE_BIT */
/*
* Return the mem_map entry representing the 'offset' subpage within
* the maximally aligned gigantic page 'base'. Handle any discontiguity
* in the mem_map at MAX_ORDER_NR_PAGES boundaries.
*/
static inline struct page *mem_map_offset(struct page *base, int offset)
{
if (unlikely(offset >= MAX_ORDER_NR_PAGES))
return pfn_to_page(page_to_pfn(base) + offset);
return base + offset;
}
/*
* Iterator over all subpages withing the maximally aligned gigantic
* page 'base'. Handle any discontiguity in the mem_map.
*/
static inline struct page *mem_map_next(struct page *iter,
struct page *base, int offset)
{
if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) {
unsigned long pfn = page_to_pfn(base) + offset;
if (!pfn_valid(pfn))
return NULL;
return pfn_to_page(pfn);
}
return iter + 1;
}
/*
* FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
* so all functions starting at paging_init should be marked __init
* in those cases. SPARSEMEM, however, allows for memory hotplug,
* and alloc_bootmem_node is not used.
*/
#ifdef CONFIG_SPARSEMEM
#define __paginginit __meminit
#else
#define __paginginit __init
#endif
/* Memory initialisation debug and verification */
enum mminit_level {
MMINIT_WARNING,
MMINIT_VERIFY,
MMINIT_TRACE
};
#ifdef CONFIG_DEBUG_MEMORY_INIT
extern int mminit_loglevel;
#define mminit_dprintk(level, prefix, fmt, arg...) \
do { \
if (level < mminit_loglevel) { \
printk(level <= MMINIT_WARNING ? KERN_WARNING : KERN_DEBUG); \
printk(KERN_CONT "mminit::" prefix " " fmt, ##arg); \
} \
} while (0)
extern void mminit_verify_pageflags_layout(void);
extern void mminit_verify_page_links(struct page *page,
enum zone_type zone, unsigned long nid, unsigned long pfn);
extern void mminit_verify_zonelist(void);
#else
static inline void mminit_dprintk(enum mminit_level level,
const char *prefix, const char *fmt, ...)
{
}
static inline void mminit_verify_pageflags_layout(void)
{
}
static inline void mminit_verify_page_links(struct page *page,
enum zone_type zone, unsigned long nid, unsigned long pfn)
{
}
static inline void mminit_verify_zonelist(void)
{
}
#endif /* CONFIG_DEBUG_MEMORY_INIT */
/* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */
#if defined(CONFIG_SPARSEMEM)
extern void mminit_validate_memmodel_limits(unsigned long *start_pfn,
unsigned long *end_pfn);
#else
static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
unsigned long *end_pfn)
{
}
#endif /* CONFIG_SPARSEMEM */
#define GUP_FLAGS_WRITE 0x1
#define GUP_FLAGS_FORCE 0x2
#define GUP_FLAGS_IGNORE_VMA_PERMISSIONS 0x4
#define GUP_FLAGS_IGNORE_SIGKILL 0x8
int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, int len, int flags,
struct page **pages, struct vm_area_struct **vmas);
#endif