path: root/mm/internal.h

/* 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/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/tracepoint-defs.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.
 */
#define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
			__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\
			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
			__GFP_ATOMIC)

/* The GFP flags allowed during early boot */
#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))

/* Control allocation cpuset and node placement constraints */
#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE)

/* Do not use these with a slab allocator */
#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)

void page_writeback_init(void);

int do_swap_page(struct vm_fault *vmf);

void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
		unsigned long floor, unsigned long ceiling);

static inline bool can_madv_dontneed_vma(struct vm_area_struct *vma)
{
	return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP));
}

void unmap_page_range(struct mmu_gather *tlb,
			     struct vm_area_struct *vma,
			     unsigned long addr, unsigned long end,
			     struct zap_details *details);

extern unsigned 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 (->_refcount == 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(page_ref_count(page), page);
	set_page_count(page, 1);
}

extern unsigned long highest_memmap_pfn;

/*
 * Maximum number of reclaim retries without progress before the OOM
 * killer is consider the only way forward.
 */
#define MAX_RECLAIM_RETRIES 16

/*
 * in mm/vmscan.c:
 */
extern int isolate_lru_page(struct page *page);
extern void putback_lru_page(struct page *page);

/*
 * 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 zoneref *preferred_zoneref;
	int migratetype;
	enum zone_type high_zoneidx;
	bool spread_dirty_pages;
};

#define ac_classzone_idx(ac) zonelist_zone_idx(ac->preferred_zoneref)

/*
 * 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_pfn(unsigned long page_pfn, unsigned int order)
{
	return page_pfn ^ (1 << order);
}

extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
				unsigned long end_pfn, struct zone *zone);

static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn,
				unsigned long end_pfn, struct zone *zone)
{
	if (zone->contiguous)
		return pfn_to_page(start_pfn);

	return __pageblock_pfn_to_page(start_pfn, end_pfn, zone);
}

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 void post_alloc_hook(struct page *page, unsigned int order,
					gfp_t gfp_flags);
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 */
	struct zone *zone;
	unsigned long nr_freepages;	/* Number of isolated free pages */
	unsigned long nr_migratepages;	/* Number of pages to migrate */
	unsigned long total_migrate_scanned;
	unsigned long total_free_scanned;
	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 */
	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
	int order;			/* order a direct compactor needs */
	int migratetype;		/* migratetype of direct compactor */
	const unsigned int alloc_flags;	/* alloc flags of a direct compactor */
	const int classzone_idx;	/* zone index of a direct compactor */
	enum migrate_mode mode;		/* Async or sync migration mode */
	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
	bool no_set_skip_hint;		/* Don't mark blocks for skipping */
	bool ignore_block_suitable;	/* Scan blocks considered unsuitable */
	bool direct_compaction;		/* False from kcompactd or /proc/... */
	bool whole_zone;		/* Whole zone should/has been scanned */
	bool contended;			/* Signal lock or sched contention */
	bool finishing_block;		/* Finishing current pageblock */
};

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);

#endif

/*
 * 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;
}

/*
 * These three helpers classifies VMAs for virtual memory accounting.
 */

/*
 * Executable code area - executable, not writable, not stack
 */
static inline bool is_exec_mapping(vm_flags_t flags)
{
	return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC;
}

/*
 * Stack area - atomatically grows in one direction
 *
 * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous:
 * do_mmap() forbids all other combinations.
 */
static inline bool is_stack_mapping(vm_flags_t flags)
{
	return (flags & VM_STACK) == VM_STACK;
}

/*
 * Data area - private, writable, not stack
 */
static inline bool is_data_mapping(vm_flags_t flags)
{
	return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE;
}

/* 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);

#ifdef CONFIG_MMU
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(s