path: root/include/linux/pagemap.h

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PAGEMAP_H
#define _LINUX_PAGEMAP_H

/*
 * Copyright 1995 Linus Torvalds
 */
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/compiler.h>
#include <linux/uaccess.h>
#include <linux/gfp.h>
#include <linux/bitops.h>
#include <linux/hardirq.h> /* for in_interrupt() */
#include <linux/hugetlb_inline.h>

struct pagevec;

/*
 * Bits in mapping->flags.
 */
enum mapping_flags {
	AS_EIO		= 0,	/* IO error on async write */
	AS_ENOSPC	= 1,	/* ENOSPC on async write */
	AS_MM_ALL_LOCKS	= 2,	/* under mm_take_all_locks() */
	AS_UNEVICTABLE	= 3,	/* e.g., ramdisk, SHM_LOCK */
	AS_EXITING	= 4, 	/* final truncate in progress */
	/* writeback related tags are not used */
	AS_NO_WRITEBACK_TAGS = 5,
	AS_THP_SUPPORT = 6,	/* THPs supported */
};

/**
 * mapping_set_error - record a writeback error in the address_space
 * @mapping: the mapping in which an error should be set
 * @error: the error to set in the mapping
 *
 * When writeback fails in some way, we must record that error so that
 * userspace can be informed when fsync and the like are called.  We endeavor
 * to report errors on any file that was open at the time of the error.  Some
 * internal callers also need to know when writeback errors have occurred.
 *
 * When a writeback error occurs, most filesystems will want to call
 * mapping_set_error to record the error in the mapping so that it can be
 * reported when the application calls fsync(2).
 */
static inline void mapping_set_error(struct address_space *mapping, int error)
{
	if (likely(!error))
		return;

	/* Record in wb_err for checkers using errseq_t based tracking */
	__filemap_set_wb_err(mapping, error);

	/* Record it in superblock */
	if (mapping->host)
		errseq_set(&mapping->host->i_sb->s_wb_err, error);

	/* Record it in flags for now, for legacy callers */
	if (error == -ENOSPC)
		set_bit(AS_ENOSPC, &mapping->flags);
	else
		set_bit(AS_EIO, &mapping->flags);
}

static inline void mapping_set_unevictable(struct address_space *mapping)
{
	set_bit(AS_UNEVICTABLE, &mapping->flags);
}

static inline void mapping_clear_unevictable(struct address_space *mapping)
{
	clear_bit(AS_UNEVICTABLE, &mapping->flags);
}

static inline bool mapping_unevictable(struct address_space *mapping)
{
	return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags);
}

static inline void mapping_set_exiting(struct address_space *mapping)
{
	set_bit(AS_EXITING, &mapping->flags);
}

static inline int mapping_exiting(struct address_space *mapping)
{
	return test_bit(AS_EXITING, &mapping->flags);
}

static inline void mapping_set_no_writeback_tags(struct address_space *mapping)
{
	set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
}

static inline int mapping_use_writeback_tags(struct address_space *mapping)
{
	return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
}

static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
{
	return mapping->gfp_mask;
}

/* Restricts the given gfp_mask to what the mapping allows. */
static inline gfp_t mapping_gfp_constraint(struct address_space *mapping,
		gfp_t gfp_mask)
{
	return mapping_gfp_mask(mapping) & gfp_mask;
}

/*
 * This is non-atomic.  Only to be used before the mapping is activated.
 * Probably needs a barrier...
 */
static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
{
	m->gfp_mask = mask;
}

static inline bool mapping_thp_support(struct address_space *mapping)
{
	return test_bit(AS_THP_SUPPORT, &mapping->flags);
}

static inline int filemap_nr_thps(struct address_space *mapping)
{
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
	return atomic_read(&mapping->nr_thps);
#else
	return 0;
#endif
}

static inline void filemap_nr_thps_inc(struct address_space *mapping)
{
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
	if (!mapping_thp_support(mapping))
		atomic_inc(&mapping->nr_thps);
#else
	WARN_ON_ONCE(1);
#endif
}

static inline void filemap_nr_thps_dec(struct address_space *mapping)
{
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
	if (!mapping_thp_support(mapping))
		atomic_dec(&mapping->nr_thps);
#else
	WARN_ON_ONCE(1);
#endif
}

void release_pages(struct page **pages, int nr);

/*
 * speculatively take a reference to a page.
 * If the page is free (_refcount == 0), then _refcount is untouched, and 0
 * is returned. Otherwise, _refcount is incremented by 1 and 1 is returned.
 *
 * This function must be called inside the same rcu_read_lock() section as has
 * been used to lookup the page in the pagecache radix-tree (or page table):
 * this allows allocators to use a synchronize_rcu() to stabilize _refcount.
 *
 * Unless an RCU grace period has passed, the count of all pages coming out
 * of the allocator must be considered unstable. page_count may return higher
 * than expected, and put_page must be able to do the right thing when the
 * page has been finished with, no matter what it is subsequently allocated
 * for (because put_page is what is used here to drop an invalid speculative
 * reference).
 *
 * This is the interesting part of the lockless pagecache (and lockless
 * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page)
 * has the following pattern:
 * 1. find page in radix tree
 * 2. conditionally increment refcount
 * 3. check the page is still in pagecache (if no, goto 1)
 *
 * Remove-side that cares about stability of _refcount (eg. reclaim) has the
 * following (with the i_pages lock held):
 * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg)
 * B. remove page from pagecache
 * C. free the page
 *
 * There are 2 critical interleavings that matter:
 * - 2 runs before A: in this case, A sees elevated refcount and bails out
 * - A runs before 2: in this case, 2 sees zero refcount and retries;
 *   subsequently, B will complete and 1 will find no page, causing the
 *   lookup to return NULL.
 *
 * It is possible that between 1 and 2, the page is removed then the exact same
 * page is inserted into the same position in pagecache. That's OK: the
 * old find_get_page using a lock could equally have run before or after
 * such a re-insertion, depending on order that locks are granted.
 *
 * Lookups racing against pagecache insertion isn't a big problem: either 1
 * will find the page or it will not. Likewise, the old find_get_page could run
 * either before the insertion or afterwards, depending on timing.
 */
static inline int __page_cache_add_speculative(struct page *page, int count)
{
#ifdef CONFIG_TINY_RCU
# ifdef CONFIG_PREEMPT_COUNT
	VM_BUG_ON(!in_atomic() && !irqs_disabled());
# endif
	/*
	 * Preempt must be disabled here - we rely on rcu_read_lock doing
	 * this for us.
	 *
	 * Pagecache won't be truncated from interrupt context, so if we have
	 * found a page in the radix tree here, we have pinned its refcount by
	 * disabling preempt, and hence no need for the "speculative get" that
	 * SMP requires.
	 */
	VM_BUG_ON_PAGE(page_count(page) == 0, page);
	page_re