blob: 6979b2bd3227a69eb9ef3386dfcd580af4a2b3e0 [file] [log] [blame]
/* internal.h: mm/ internal definitions
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (
* 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/fs.h>
#include <linux/mm.h>
* The set of flags that only affect watermark checking and reclaim
* behaviour. This is used by the MM to obey the caller constraints
* about IO, FS and watermark checking while ignoring placement
* hints such as HIGHMEM usage.
/* The GFP flags allowed during early boot */
/* Control allocation cpuset and node placement constraints */
/* Do not use these with a slab allocator */
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);
extern int __do_page_cache_readahead(struct address_space *mapping,
struct file *filp, pgoff_t offset, unsigned long nr_to_read,
unsigned long lookahead_size);
* Submit IO for the read-ahead request in file_ra_state.
static inline unsigned long ra_submit(struct file_ra_state *ra,
struct address_space *mapping, struct file *filp)
return __do_page_cache_readahead(mapping, filp,
ra->start, ra->size, ra->async_size);
* 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_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(atomic_read(&page->_count), page);
set_page_count(page, 1);
static inline void __get_page_tail_foll(struct page *page,
bool get_page_head)
* If we're getting a tail page, the elevated page->_count is
* required only in the head page and we will elevate the head
* page->_count and tail page->_mapcount.
* We elevate page_tail->_mapcount for tail pages to force
* page_tail->_count to be zero at all times to avoid getting
* false positives from get_page_unless_zero() with
* speculative page access (like in
* page_cache_get_speculative()) on tail pages.
VM_BUG_ON_PAGE(atomic_read(&compound_head(page)->_count) <= 0, page);
if (get_page_head)
* This is meant to be called as the FOLL_GET operation of
* follow_page() and it must be called while holding the proper PT
* lock while the pte (or pmd_trans_huge) is still mapping the page.
static inline void get_page_foll(struct page *page)
if (unlikely(PageTail(page)))
* This is safe only because
* __split_huge_page_refcount() can't run under
* get_page_foll() because we hold the proper PT lock.
__get_page_tail_foll(page, true);
else {
* Getting a normal page or the head of a compound page
* requires to already have an elevated page->_count.
VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page);
extern unsigned long highest_memmap_pfn;
* in mm/vmscan.c:
extern int isolate_lru_page(struct page *page);
extern void putback_lru_page(struct page *page);
extern bool zone_reclaimable(struct zone *zone);
* in mm/rmap.c:
extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
* in mm/page_alloc.c
* Structure for holding the mostly immutable allocation parameters passed
* between functions involved in allocations, including the alloc_pages*
* family of functions.
* nodemask, migratetype and high_zoneidx are initialized only once in
* __alloc_pages_nodemask() and then never change.
* zonelist, preferred_zone and classzone_idx are set first in
* __alloc_pages_nodemask() for the fast path, and might be later changed
* in __alloc_pages_slowpath(). All other functions pass the whole strucure
* by a const pointer.
struct alloc_context {
struct zonelist *zonelist;
nodemask_t *nodemask;
struct zone *preferred_zone;
int classzone_idx;
int migratetype;
enum zone_type high_zoneidx;
bool spread_dirty_pages;
* Locate the struct page for both the matching buddy in our
* pair (buddy1) and the combined O(n+1) page they form (page).
* 1) Any buddy B1 will have an order O twin B2 which satisfies
* the following equation:
* B2 = B1 ^ (1 << O)
* For example, if the starting buddy (buddy2) is #8 its order
* 1 buddy is #10:
* B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
* 2) Any buddy B will have an order O+1 parent P which
* satisfies the following equation:
* P = B & ~(1 << O)
* Assumption: *_mem_map is contiguous at least up to MAX_ORDER
static inline unsigned long
__find_buddy_index(unsigned long page_idx, unsigned int order)
return page_idx ^ (1 << order);
extern int __isolate_free_page(struct page *page, unsigned int order);
extern void __free_pages_bootmem(struct page *page, unsigned long pfn,
unsigned int order);
extern void prep_compound_page(struct page *page, unsigned int order);
extern bool is_free_buddy_page(struct page *page);
extern int user_min_free_kbytes;
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
* in mm/compaction.c
* compact_control is used to track pages being migrated and the free pages
* they are being migrated to during memory compaction. The free_pfn starts
* at the end of a zone and migrate_pfn begins at the start. Movable pages
* are moved to the end of a zone during a compaction run and the run
* completes when free_pfn <= migrate_pfn
struct compact_control {
struct list_head freepages; /* List of free pages to migrate to */
struct list_head migratepages; /* List of pages being migrated */
unsigned long nr_freepages; /* Number of isolated free pages */
unsigned long nr_migratepages; /* Number of pages to migrate */
unsigned long free_pfn; /* isolate_freepages search base */
unsigned long migrate_pfn; /* isolate_migratepages search base */
unsigned long last_migrated_pfn;/* Not yet flushed page being freed */
enum migrate_mode mode; /* Async or sync migration mode */
bool ignore_skip_hint; /* Scan blocks even if marked skip */
int order; /* order a direct compactor needs */
const gfp_t gfp_mask; /* gfp mask of a direct compactor */
const int alloc_flags; /* alloc flags of a direct compactor */
const int classzone_idx; /* zone index of a direct compactor */
struct zone *zone;
int contended; /* Signal need_sched() or lock
* contention detected during
* compaction
unsigned long
isolate_freepages_range(struct compact_control *cc,
unsigned long start_pfn, unsigned long end_pfn);
unsigned long
isolate_migratepages_range(struct compact_control *cc,
unsigned long low_pfn, unsigned long end_pfn);
int find_suitable_fallback(struct free_area *area, unsigned int order,
int migratetype, bool only_stealable, bool *can_steal);
* This function returns the order of a free page in the buddy system. In
* general, page_zone(page)->lock must be held by the caller to prevent the
* page from being allocated in parallel and returning garbage as the order.
* If a caller does not hold page_zone(page)->lock, it must guarantee that the
* page cannot be allocated or merged in parallel. Alternatively, it must
* handle invalid values gracefully, and use page_order_unsafe() below.
static inline unsigned int page_order(struct page *page)
/* PageBuddy() must be checked by the caller */
return page_private(page);
* Like page_order(), but for callers who cannot afford to hold the zone lock.
* PageBuddy() should be checked first by the caller to minimize race window,
* and invalid values must be handled gracefully.
* READ_ONCE is used so that if the caller assigns the result into a local
* variable and e.g. tests it for valid range before using, the compiler cannot
* decide to remove the variable and inline the page_private(page) multiple
* times, potentially observing different values in the tests and the actual
* use of the result.
#define page_order_unsafe(page) READ_ONCE(page_private(page))
static inline bool is_cow_mapping(vm_flags_t flags)
return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
/* mm/util.c */
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev, struct rb_node *rb_parent);
extern long populate_vma_page_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end, int *nonblocking);
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);
* must be called with vma's mmap_sem held for read or write, and page locked.
extern void mlock_vma_page(struct page *page);
extern unsigned int munlock_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);
* mlock_migrate_page - called only from migrate_misplaced_transhuge_page()
* (because that does not go through the full procedure of migration ptes):
* to migrate the Mlocked page flag; update statistics.
static inline void mlock_migrate_page(struct page *newpage, struct page *page)
if (TestClearPageMlocked(page)) {
int nr_pages = hpage_nr_pages(page);
/* Holding pmd lock, no change in irq context: __mod is safe */
__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
__mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages);
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
extern unsigned long vma_address(struct page *page,
struct vm_area_struct *vma);
#else /* !CONFIG_MMU */
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_MMU */
* 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 nth_page(base, offset);
return base + offset;
* Iterator over all subpages within 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.
#define __paginginit __meminit
#define __paginginit __init
/* Memory initialisation debug and verification */
enum mminit_level {
extern int mminit_loglevel;
#define mminit_dprintk(level, prefix, fmt, arg...) \
do { \
if (level < mminit_loglevel) { \
if (level <= MMINIT_WARNING) \
printk(KERN_WARNING "mminit::" prefix " " fmt, ##arg); \
else \
printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \
} \
} while (0)
extern void mminit_verify_pageflags_layout(void);
extern void mminit_verify_zonelist(void);
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_zonelist(void)
/* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */
extern void mminit_validate_memmodel_limits(unsigned long *start_pfn,
unsigned long *end_pfn);
static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
unsigned long *end_pfn)
extern int hwpoison_filter(struct page *p);
extern u32 hwpoison_filter_dev_major;
extern u32 hwpoison_filter_dev_minor;
extern u64 hwpoison_filter_flags_mask;
extern u64 hwpoison_filter_flags_value;
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;
extern unsigned long vm_mmap_pgoff(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
extern void set_pageblock_order(void);
unsigned long reclaim_clean_pages_from_list(struct zone *zone,
struct list_head *page_list);
/* The ALLOC_WMARK bits are used as an index to zone->watermark */
#define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */
/* Mask to get the watermark bits */
#define ALLOC_HARDER 0x10 /* try to alloc harder */
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
#define ALLOC_FAIR 0x100 /* fair zone allocation */
enum ttu_flags;
struct tlbflush_unmap_batch;
void try_to_unmap_flush(void);
void try_to_unmap_flush_dirty(void);
static inline void try_to_unmap_flush(void)
static inline void try_to_unmap_flush_dirty(void)
#endif /* __MM_INTERNAL_H */