[linux-block.git] / include / linux / buffer_head.h

/* SPDX-License-Identifier: GPL-2.0 */
/*
 * include/linux/buffer_head.h
 *
 * Everything to do with buffer_heads.
 */

#ifndef _LINUX_BUFFER_HEAD_H
#define _LINUX_BUFFER_HEAD_H

#include <linux/types.h>
#include <linux/blk_types.h>
#include <linux/fs.h>
#include <linux/linkage.h>
#include <linux/pagemap.h>
#include <linux/wait.h>
#include <linux/atomic.h>

#ifdef CONFIG_BLOCK

enum bh_state_bits {
	BH_Uptodate,	/* Contains valid data */
	BH_Dirty,	/* Is dirty */
	BH_Lock,	/* Is locked */
	BH_Req,		/* Has been submitted for I/O */

	BH_Mapped,	/* Has a disk mapping */
	BH_New,		/* Disk mapping was newly created by get_block */
	BH_Async_Read,	/* Is under end_buffer_async_read I/O */
	BH_Async_Write,	/* Is under end_buffer_async_write I/O */
	BH_Delay,	/* Buffer is not yet allocated on disk */
	BH_Boundary,	/* Block is followed by a discontiguity */
	BH_Write_EIO,	/* I/O error on write */
	BH_Unwritten,	/* Buffer is allocated on disk but not written */
	BH_Quiet,	/* Buffer Error Prinks to be quiet */
	BH_Meta,	/* Buffer contains metadata */
	BH_Prio,	/* Buffer should be submitted with REQ_PRIO */
	BH_Defer_Completion, /* Defer AIO completion to workqueue */

	BH_PrivateStart,/* not a state bit, but the first bit available
			 * for private allocation by other entities
			 */
};

#define MAX_BUF_PER_PAGE (PAGE_SIZE / 512)

struct page;
struct buffer_head;
struct address_space;
typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate);

/*
 * Historically, a buffer_head was used to map a single block
 * within a page, and of course as the unit of I/O through the
 * filesystem and block layers.  Nowadays the basic I/O unit
 * is the bio, and buffer_heads are used for extracting block
 * mappings (via a get_block_t call), for tracking state within
 * a page (via a page_mapping) and for wrapping bio submission
 * for backward compatibility reasons (e.g. submit_bh).
 */
struct buffer_head {
	unsigned long b_state;		/* buffer state bitmap (see above) */
	struct buffer_head *b_this_page;/* circular list of page's buffers */
	struct page *b_page;		/* the page this bh is mapped to */

	sector_t b_blocknr;		/* start block number */
	size_t b_size;			/* size of mapping */
	char *b_data;			/* pointer to data within the page */

	struct block_device *b_bdev;
	bh_end_io_t *b_end_io;		/* I/O completion */
 	void *b_private;		/* reserved for b_end_io */
	struct list_head b_assoc_buffers; /* associated with another mapping */
	struct address_space *b_assoc_map;	/* mapping this buffer is
						   associated with */
	atomic_t b_count;		/* users using this buffer_head */
	spinlock_t b_uptodate_lock;	/* Used by the first bh in a page, to
					 * serialise IO completion of other
					 * buffers in the page */
};

/*
 * macro tricks to expand the set_buffer_foo(), clear_buffer_foo()
 * and buffer_foo() functions.
 * To avoid reset buffer flags that are already set, because that causes
 * a costly cache line transition, check the flag first.
 */
#define BUFFER_FNS(bit, name)						\
static __always_inline void set_buffer_##name(struct buffer_head *bh)	\
{									\
	if (!test_bit(BH_##bit, &(bh)->b_state))			\
		set_bit(BH_##bit, &(bh)->b_state);			\
}									\
static __always_inline void clear_buffer_##name(struct buffer_head *bh)	\
{									\
	clear_bit(BH_##bit, &(bh)->b_state);				\
}									\
static __always_inline int buffer_##name(const struct buffer_head *bh)	\
{									\
	return test_bit(BH_##bit, &(bh)->b_state);			\
}

/*
 * test_set_buffer_foo() and test_clear_buffer_foo()
 */
#define TAS_BUFFER_FNS(bit, name)					\
static __always_inline int test_set_buffer_##name(struct buffer_head *bh) \
{									\
	return test_and_set_bit(BH_##bit, &(bh)->b_state);		\
}									\
static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \
{									\
	return test_and_clear_bit(BH_##bit, &(bh)->b_state);		\
}									\

/*
 * Emit the buffer bitops functions.   Note that there are also functions
 * of the form "mark_buffer_foo()".  These are higher-level functions which
 * do something in addition to setting a b_state bit.
 */
BUFFER_FNS(Dirty, dirty)
TAS_BUFFER_FNS(Dirty, dirty)
BUFFER_FNS(Lock, locked)
BUFFER_FNS(Req, req)
TAS_BUFFER_FNS(Req, req)
BUFFER_FNS(Mapped, mapped)
BUFFER_FNS(New, new)
BUFFER_FNS(Async_Read, async_read)
BUFFER_FNS(Async_Write, async_write)
BUFFER_FNS(Delay, delay)
BUFFER_FNS(Boundary, boundary)
BUFFER_FNS(Write_EIO, write_io_error)
BUFFER_FNS(Unwritten, unwritten)
BUFFER_FNS(Meta, meta)
BUFFER_FNS(Prio, prio)
BUFFER_FNS(Defer_Completion, defer_completion)

static __always_inline void set_buffer_uptodate(struct buffer_head *bh)
{
	/*
	 * If somebody else already set this uptodate, they will
	 * have done the memory barrier, and a reader will thus
	 * see *some* valid buffer state.
	 *
	 * Any other serialization (with IO errors or whatever that
	 * might clear the bit) has to come from other state (eg BH_Lock).
	 */
	if (test_bit(BH_Uptodate, &bh->b_state))
		return;

	/*
	 * make it consistent with folio_mark_uptodate
	 * pairs with smp_load_acquire in buffer_uptodate
	 */
	smp_mb__before_atomic();
	set_bit(BH_Uptodate, &bh->b_state);
}

static __always_inline void clear_buffer_uptodate(struct buffer_head *bh)
{
	clear_bit(BH_Uptodate, &bh->b_state);
}

static __always_inline int buffer_uptodate(const struct buffer_head *bh)
{
	/*
	 * make it consistent with folio_test_uptodate
	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
	 */
	return test_bit_acquire(BH_Uptodate, &bh->b_state);
}

#define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)

/* If we *know* page->private refers to buffer_heads */
#define page_buffers(page)					\
	({							\
		BUG_ON(!PagePrivate(page));			\
		((struct buffer_head *)page_private(page));	\
	})
#define page_has_buffers(page)	PagePrivate(page)
#define folio_buffers(folio)		folio_get_private(folio)

void buffer_check_dirty_writeback(struct folio *folio,
				     bool *dirty, bool *writeback);

/*
 * Declarations
 */

void mark_buffer_dirty(struct buffer_head *bh);
void mark_buffer_write_io_error(struct buffer_head *bh);
void touch_buffer(struct buffer_head *bh);
void set_bh_page(struct buffer_head *bh,
		struct page *page, unsigned long offset);
bool try_to_free_buffers(struct folio *);
struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
		bool retry);
void create_empty_buffers(struct page *, unsigned long,
			unsigned long b_state);
void end_buffer_read_sync(struct buffer_head *bh, int uptodate);
void end_buffer_write_sync(struct buffer_head *bh, int uptodate);
void end_buffer_async_write(struct buffer_head *bh, int uptodate);

/* Things to do with buffers at mapping->private_list */
void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode);
int inode_has_buffers(struct inode *);
void invalidate_inode_buffers(struct inode *);
int remove_inode_buffers(struct inode *inode);
int sync_mapping_buffers(struct address_space *mapping);
void clean_bdev_aliases(struct block_device *bdev, sector_t block,
			sector_t len);
static inline void clean_bdev_bh_alias(struct buffer_head *bh)
{
	clean_bdev_aliases(bh->b_bdev, bh->b_blocknr, 1);
}

void mark_buffer_async_write(struct buffer_head *bh);
void __wait_on_buffer(struct buffer_head *);
wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
			unsigned size);
struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block,
				  unsigned size, gfp_t gfp);
void __brelse(struct buffer_head *);
void __bforget(struct buffer_head *);
void __breadahead(struct block_device *, sector_t block, unsigned int size);
struct buffer_head *__bread_gfp(struct block_device *,
				sector_t block, unsigned size, gfp_t gfp);
void invalidate_bh_lrus(void);
void invalidate_bh_lrus_cpu(void);
bool has_bh_in_lru(int cpu, void *dummy);
struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
void free_buffer_head(struct buffer_head * bh);
void unlock_buffer(struct buffer_head *bh);
void __lock_buffer(struct buffer_head *bh);
int sync_dirty_buffer(struct buffer_head *bh);
int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
void submit_bh(blk_opf_t, struct buffer_head *);
void write_boundary_block(struct block_device *bdev,
			sector_t bblock, unsigned blocksize);
int bh_uptodate_or_lock(struct buffer_head *bh);
int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait);
void __bh_read_batch(int nr, struct buffer_head *bhs[],
		     blk_opf_t op_flags, bool force_lock);

extern int buffer_heads_over_limit;

/*
 * Generic address_space_operations implementations for buffer_head-backed
 * address_spaces.
 */
void block_invalidate_folio(struct folio *folio, size_t offset, size_t length);
int block_write_full_page(struct page *page, get_block_t *get_block,
				struct writeback_control *wbc);
int __block_write_full_page(struct inode *inode, struct page *page,
			get_block_t *get_block, struct writeback_control *wbc,
			bh_end_io_t *handler);
int block_read_full_folio(struct folio *, get_block_t *);
bool block_is_partially_uptodate(struct folio *, size_t from, size_t count);
int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
		struct page **pagep, get_block_t *get_block);
int __block_write_begin(struct page *page, loff_t pos, unsigned len,
		get_block_t *get_block);
int block_write_end(struct file *, struct address_space *,
				loff_t, unsigned, unsigned,
				struct page *, void *);
int generic_write_end(struct file *, struct address_space *,
				loff_t, unsigned, unsigned,
				struct page *, void *);
void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
void clean_page_buffers(struct page *page);
int cont_write_begin(struct file *, struct address_space *, loff_t,
			unsigned, struct page **, void **,
			get_block_t *, loff_t *);
int generic_cont_expand_simple(struct inode *inode, loff_t size);
int block_commit_write(struct page *page, unsigned from, unsigned to);
int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
				get_block_t get_block);
/* Convert errno to return value from ->page_mkwrite() call */
static inline vm_fault_t block_page_mkwrite_return(int err)
{
	if (err == 0)
		return VM_FAULT_LOCKED;
	if (err == -EFAULT || err == -EAGAIN)
		return VM_FAULT_NOPAGE;
	if (err == -ENOMEM)
		return VM_FAULT_OOM;
	/* -ENOSPC, -EDQUOT, -EIO ... */
	return VM_FAULT_SIGBUS;
}
sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
int block_truncate_page(struct address_space *, loff_t, get_block_t *);

#ifdef CONFIG_MIGRATION
extern int buffer_migrate_folio(struct address_space *,
		struct folio *dst, struct folio *src, enum migrate_mode);
extern int buffer_migrate_folio_norefs(struct address_space *,
		struct folio *dst, struct folio *src, enum migrate_mode);
#else
#define buffer_migrate_folio NULL
#define buffer_migrate_folio_norefs NULL
#endif

void buffer_init(void);

/*
 * inline definitions
 */

static inline void get_bh(struct buffer_head *bh)
{
        atomic_inc(&bh->b_count);
}

static inline void put_bh(struct buffer_head *bh)
{
        smp_mb__before_atomic();
        atomic_dec(&bh->b_count);
}

static inline void brelse(struct buffer_head *bh)
{
	if (bh)
		__brelse(bh);
}

static inline void bforget(struct buffer_head *bh)
{
	if (bh)
		__bforget(bh);
}

static inline struct buffer_head *
sb_bread(struct super_block *sb, sector_t block)
{
	return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
}

static inline struct buffer_head *
sb_bread_unmovable(struct super_block *sb, sector_t block)
{
	return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, 0);
}

static inline void
sb_breadahead(struct super_block *sb, sector_t block)
{
	__breadahead(sb->s_bdev, block, sb->s_blocksize);
}

static inline struct buffer_head *
sb_getblk(struct super_block *sb, sector_t block)
{
	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
}


static inline struct buffer_head *
sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp)
{
	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp);
}

static inline struct buffer_head *
sb_find_get_block(struct super_block *sb, sector_t block)
{
	return __find_get_block(sb->s_bdev, block, sb->s_blocksize);
}

static inline void
map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block)
{
	set_buffer_mapped(bh);
	bh->b_bdev = sb->s_bdev;
	bh->b_blocknr = block;
	bh->b_size = sb->s_blocksize;
}

static inline void wait_on_buffer(struct buffer_head *bh)
{
	might_sleep();
	if (buffer_locked(bh))
		__wait_on_buffer(bh);
}

static inline int trylock_buffer(struct buffer_head *bh)
{
	return likely(!test_and_set_bit_lock(BH_Lock, &bh->b_state));
}

static inline void lock_buffer(struct buffer_head *bh)
{
	might_sleep();
	if (!trylock_buffer(bh))
		__lock_buffer(bh);
}

static inline struct buffer_head *getblk_unmovable(struct block_device *bdev,
						   sector_t block,
						   unsigned size)
{
	return __getblk_gfp(bdev, block, size, 0);
}

static inline struct buffer_head *__getblk(struct block_device *bdev,
					   sector_t block,
					   unsigned size)
{
	return __getblk_gfp(bdev, block, size, __GFP_MOVABLE);
}

static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags)
{
	if (!buffer_uptodate(bh) && trylock_buffer(bh)) {
		if (!buffer_uptodate(bh))
			__bh_read(bh, op_flags, false);
		else
			unlock_buffer(bh);
	}
}

static inline void bh_read_nowait(struct buffer_head *bh, blk_opf_t op_flags)
{
	if (!bh_uptodate_or_lock(bh))
		__bh_read(bh, op_flags, false);
}

/* Returns 1 if buffer uptodated, 0 on success, and -EIO on error. */
static inline int bh_read(struct buffer_head *bh, blk_opf_t op_flags)
{
	if (bh_uptodate_or_lock(bh))
		return 1;
	return __bh_read(bh, op_flags, true);
}

static inline void bh_read_batch(int nr, struct buffer_head *bhs[])
{
	__bh_read_batch(nr, bhs, 0, true);
}

static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[],
				      blk_opf_t op_flags)
{
	__bh_read_batch(nr, bhs, op_flags, false);
}

/**
 *  __bread() - reads a specified block and returns the bh
 *  @bdev: the block_device to read from
 *  @block: number of block
 *  @size: size (in bytes) to read
 *
 *  Reads a specified block, and returns buffer head that contains it.
 *  The page cache is allocated from movable area so that it can be migrated.
 *  It returns NULL if the block was unreadable.
 */
static inline struct buffer_head *
__bread(struct block_device *bdev, sector_t block, unsigned size)
{
	return __bread_gfp(bdev, block, size, __GFP_MOVABLE);
}

bool block_dirty_folio(struct address_space *mapping, struct folio *folio);

#else /* CONFIG_BLOCK */

static inline void buffer_init(void) {}
static inline bool try_to_free_buffers(struct folio *folio) { return true; }
static inline int inode_has_buffers(struct inode *inode) { return 0; }
static inline void invalidate_inode_buffers(struct inode *inode) {}
static inline int remove_inode_buffers(struct inode *inode) { return 1; }
static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
static inline void invalidate_bh_lrus_cpu(void) {}
static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; }
#define buffer_heads_over_limit 0

#endif /* CONFIG_BLOCK */
#endif /* _LINUX_BUFFER_HEAD_H */
Commit	Line	Data
b2441318	1	/* SPDX-License-Identifier: GPL-2.0 */
1da177e4 LT	2	/*
	3	* include/linux/buffer_head.h
	4	*
	5	* Everything to do with buffer_heads.
	6	*/
	7
	8	#ifndef _LINUX_BUFFER_HEAD_H
	9	#define _LINUX_BUFFER_HEAD_H
	10
	11	#include <linux/types.h>
3ae72869	12	#include <linux/blk_types.h>
1da177e4 LT	13	#include <linux/fs.h>
	14	#include <linux/linkage.h>
	15	#include <linux/pagemap.h>
	16	#include <linux/wait.h>
60063497	17	#include <linux/atomic.h>
1da177e4	18
9361401e DH	19	#ifdef CONFIG_BLOCK
9361401e DH	20
1da177e4 LT	21	enum bh_state_bits {
	22	BH_Uptodate, /* Contains valid data */
	23	BH_Dirty, /* Is dirty */
	24	BH_Lock, /* Is locked */
	25	BH_Req, /* Has been submitted for I/O */
	26
	27	BH_Mapped, /* Has a disk mapping */
	28	BH_New, /* Disk mapping was newly created by get_block */
	29	BH_Async_Read, /* Is under end_buffer_async_read I/O */
	30	BH_Async_Write, /* Is under end_buffer_async_write I/O */
	31	BH_Delay, /* Buffer is not yet allocated on disk */
	32	BH_Boundary, /* Block is followed by a discontiguity */
	33	BH_Write_EIO, /* I/O error on write */
33a266dd	34	BH_Unwritten, /* Buffer is allocated on disk but not written */
08bafc03	35	BH_Quiet, /* Buffer Error Prinks to be quiet */
877f962c TT	36	BH_Meta, /* Buffer contains metadata */
877f962c TT	37	BH_Prio, /* Buffer should be submitted with REQ_PRIO */
7b7a8665	38	BH_Defer_Completion, /* Defer AIO completion to workqueue */
1da177e4 LT	39
	40	BH_PrivateStart,/* not a state bit, but the first bit available
	41	* for private allocation by other entities
	42	*/
	43	};
	44
09cbfeaf	45	#define MAX_BUF_PER_PAGE (PAGE_SIZE / 512)
1da177e4 LT	46
	47	struct page;
	48	struct buffer_head;
	49	struct address_space;
	50	typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate);
	51
	52	/*
205f87f6 BP	53	* Historically, a buffer_head was used to map a single block
	54	* within a page, and of course as the unit of I/O through the
	55	* filesystem and block layers. Nowadays the basic I/O unit
	56	* is the bio, and buffer_heads are used for extracting block
	57	* mappings (via a get_block_t call), for tracking state within
	58	* a page (via a page_mapping) and for wrapping bio submission
	59	* for backward compatibility reasons (e.g. submit_bh).
1da177e4 LT	60	*/
1da177e4 LT	61	struct buffer_head {
1da177e4 LT	62	unsigned long b_state; /* buffer state bitmap (see above) */
	63	struct buffer_head b_this_page;/ circular list of page's buffers */
	64	struct page b_page; / the page this bh is mapped to */
1da177e4	65
205f87f6 BP	66	sector_t b_blocknr; /* start block number */
	67	size_t b_size; /* size of mapping */
	68	char b_data; / pointer to data within the page */
1da177e4 LT	69
	70	struct block_device *b_bdev;
	71	bh_end_io_t b_end_io; / I/O completion */
	72	void b_private; / reserved for b_end_io */
	73	struct list_head b_assoc_buffers; /* associated with another mapping */
58ff407b JK	74	struct address_space b_assoc_map; / mapping this buffer is
58ff407b JK	75	associated with */
205f87f6	76	atomic_t b_count; /* users using this buffer_head */
f1e67e35 TG	77	spinlock_t b_uptodate_lock; /* Used by the first bh in a page, to
	78	* serialise IO completion of other
	79	* buffers in the page */
1da177e4 LT	80	};
	81
	82	/*
	83	* macro tricks to expand the set_buffer_foo(), clear_buffer_foo()
	84	* and buffer_foo() functions.
60f91826 KW	85	* To avoid reset buffer flags that are already set, because that causes
60f91826 KW	86	* a costly cache line transition, check the flag first.
1da177e4 LT	87	*/
1da177e4 LT	88	#define BUFFER_FNS(bit, name) \
ee91ef61	89	static __always_inline void set_buffer_##name(struct buffer_head *bh) \
1da177e4	90	{ \
60f91826 KW	91	if (!test_bit(BH_##bit, &(bh)->b_state)) \
60f91826 KW	92	set_bit(BH_##bit, &(bh)->b_state); \
1da177e4	93	} \
ee91ef61	94	static __always_inline void clear_buffer_##name(struct buffer_head *bh) \
1da177e4 LT	95	{ \
	96	clear_bit(BH_##bit, &(bh)->b_state); \
	97	} \
ee91ef61	98	static __always_inline int buffer_##name(const struct buffer_head *bh) \
1da177e4 LT	99	{ \
	100	return test_bit(BH_##bit, &(bh)->b_state); \
	101	}
	102
	103	/*
	104	* test_set_buffer_foo() and test_clear_buffer_foo()
	105	*/
	106	#define TAS_BUFFER_FNS(bit, name) \
ee91ef61	107	static __always_inline int test_set_buffer_##name(struct buffer_head *bh) \
1da177e4 LT	108	{ \
	109	return test_and_set_bit(BH_##bit, &(bh)->b_state); \
	110	} \
ee91ef61	111	static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \
1da177e4 LT	112	{ \
	113	return test_and_clear_bit(BH_##bit, &(bh)->b_state); \
	114	} \
	115
	116	/*
	117	* Emit the buffer bitops functions. Note that there are also functions
	118	* of the form "mark_buffer_foo()". These are higher-level functions which
	119	* do something in addition to setting a b_state bit.
	120	*/
1da177e4 LT	121	BUFFER_FNS(Dirty, dirty)
	122	TAS_BUFFER_FNS(Dirty, dirty)
	123	BUFFER_FNS(Lock, locked)
1da177e4 LT	124	BUFFER_FNS(Req, req)
	125	TAS_BUFFER_FNS(Req, req)
	126	BUFFER_FNS(Mapped, mapped)
	127	BUFFER_FNS(New, new)
	128	BUFFER_FNS(Async_Read, async_read)
	129	BUFFER_FNS(Async_Write, async_write)
	130	BUFFER_FNS(Delay, delay)
	131	BUFFER_FNS(Boundary, boundary)
	132	BUFFER_FNS(Write_EIO, write_io_error)
33a266dd	133	BUFFER_FNS(Unwritten, unwritten)
877f962c TT	134	BUFFER_FNS(Meta, meta)
877f962c TT	135	BUFFER_FNS(Prio, prio)
7b7a8665	136	BUFFER_FNS(Defer_Completion, defer_completion)
1da177e4	137
d4252071 MP	138	static __always_inline void set_buffer_uptodate(struct buffer_head *bh)
d4252071 MP	139	{
2f79cdfe LT	140	/*
	141	* If somebody else already set this uptodate, they will
	142	* have done the memory barrier, and a reader will thus
	143	* see some valid buffer state.
	144	*
	145	* Any other serialization (with IO errors or whatever that
	146	* might clear the bit) has to come from other state (eg BH_Lock).
	147	*/
	148	if (test_bit(BH_Uptodate, &bh->b_state))
	149	return;
	150
d4252071 MP	151	/*
	152	* make it consistent with folio_mark_uptodate
	153	* pairs with smp_load_acquire in buffer_uptodate
	154	*/
	155	smp_mb__before_atomic();
	156	set_bit(BH_Uptodate, &bh->b_state);
	157	}
	158
	159	static __always_inline void clear_buffer_uptodate(struct buffer_head *bh)
	160	{
	161	clear_bit(BH_Uptodate, &bh->b_state);
	162	}
	163
	164	static __always_inline int buffer_uptodate(const struct buffer_head *bh)
	165	{
	166	/*
	167	* make it consistent with folio_test_uptodate
	168	* pairs with smp_mb__before_atomic in set_buffer_uptodate
	169	*/
8238b457	170	return test_bit_acquire(BH_Uptodate, &bh->b_state);
d4252071 MP	171	}
d4252071 MP	172
1da177e4	173	#define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK)
1da177e4 LT	174
	175	/* If we know page->private refers to buffer_heads */
	176	#define page_buffers(page) \
	177	({ \
4c21e2f2 HD	178	BUG_ON(!PagePrivate(page)); \
4c21e2f2 HD	179	((struct buffer_head *)page_private(page)); \
1da177e4 LT	180	})
1da177e4 LT	181	#define page_has_buffers(page) PagePrivate(page)
cd1067be	182	#define folio_buffers(folio) folio_get_private(folio)
1da177e4	183
520f301c	184	void buffer_check_dirty_writeback(struct folio *folio,
b4597226 MG	185	bool dirty, bool writeback);
b4597226 MG	186
1da177e4 LT	187	/*
	188	* Declarations
	189	*/
	190
b3c97528	191	void mark_buffer_dirty(struct buffer_head *bh);
87354e5d	192	void mark_buffer_write_io_error(struct buffer_head *bh);
f0059afd	193	void touch_buffer(struct buffer_head *bh);
1da177e4 LT	194	void set_bh_page(struct buffer_head *bh,
1da177e4 LT	195	struct page *page, unsigned long offset);
68189fef	196	bool try_to_free_buffers(struct folio *);
1da177e4	197	struct buffer_head alloc_page_buffers(struct page page, unsigned long size,
640ab98f	198	bool retry);
1da177e4 LT	199	void create_empty_buffers(struct page *, unsigned long,
	200	unsigned long b_state);
	201	void end_buffer_read_sync(struct buffer_head *bh, int uptodate);
	202	void end_buffer_write_sync(struct buffer_head *bh, int uptodate);
35c80d5f	203	void end_buffer_async_write(struct buffer_head *bh, int uptodate);
1da177e4 LT	204
	205	/* Things to do with buffers at mapping->private_list */
	206	void mark_buffer_dirty_inode(struct buffer_head bh, struct inode inode);
	207	int inode_has_buffers(struct inode *);
	208	void invalidate_inode_buffers(struct inode *);
	209	int remove_inode_buffers(struct inode *inode);
	210	int sync_mapping_buffers(struct address_space *mapping);
29f3ad7d JK	211	void clean_bdev_aliases(struct block_device *bdev, sector_t block,
29f3ad7d JK	212	sector_t len);
e64855c6 JK	213	static inline void clean_bdev_bh_alias(struct buffer_head *bh)
	214	{
	215	clean_bdev_aliases(bh->b_bdev, bh->b_blocknr, 1);
	216	}
1da177e4 LT	217
1da177e4 LT	218	void mark_buffer_async_write(struct buffer_head *bh);
1da177e4 LT	219	void __wait_on_buffer(struct buffer_head *);
1da177e4 LT	220	wait_queue_head_t bh_waitq_head(struct buffer_head bh);
3991d3bd TK	221	struct buffer_head __find_get_block(struct block_device bdev, sector_t block,
3991d3bd TK	222	unsigned size);
3b5e6454 GK	223	struct buffer_head __getblk_gfp(struct block_device bdev, sector_t block,
3b5e6454 GK	224	unsigned size, gfp_t gfp);
1da177e4 LT	225	void __brelse(struct buffer_head *);
1da177e4 LT	226	void __bforget(struct buffer_head *);
3991d3bd	227	void __breadahead(struct block_device *, sector_t block, unsigned int size);
3b5e6454 GK	228	struct buffer_head __bread_gfp(struct block_device ,
3b5e6454 GK	229	sector_t block, unsigned size, gfp_t gfp);
f9a14399	230	void invalidate_bh_lrus(void);
243418e3	231	void invalidate_bh_lrus_cpu(void);
8cc621d2	232	bool has_bh_in_lru(int cpu, void *dummy);
dd0fc66f	233	struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
1da177e4	234	void free_buffer_head(struct buffer_head * bh);
b3c97528 HH	235	void unlock_buffer(struct buffer_head *bh);
b3c97528 HH	236	void __lock_buffer(struct buffer_head *bh);
1da177e4	237	int sync_dirty_buffer(struct buffer_head *bh);
3ae72869 BVA	238	int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
3ae72869 BVA	239	void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
5bdf402a	240	void submit_bh(blk_opf_t, struct buffer_head *);
1da177e4 LT	241	void write_boundary_block(struct block_device *bdev,
1da177e4 LT	242	sector_t bblock, unsigned blocksize);
389d1b08	243	int bh_uptodate_or_lock(struct buffer_head *bh);
fdee117e ZY	244	int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait);
	245	void __bh_read_batch(int nr, struct buffer_head *bhs[],
	246	blk_opf_t op_flags, bool force_lock);
1da177e4 LT	247
	248	extern int buffer_heads_over_limit;
	249
	250	/*
	251	* Generic address_space_operations implementations for buffer_head-backed
	252	* address_spaces.
	253	*/
7ba13abb	254	void block_invalidate_folio(struct folio *folio, size_t offset, size_t length);
1da177e4 LT	255	int block_write_full_page(struct page page, get_block_t get_block,
1da177e4 LT	256	struct writeback_control *wbc);
b4bba389 BM	257	int __block_write_full_page(struct inode inode, struct page page,
	258	get_block_t get_block, struct writeback_control wbc,
	259	bh_end_io_t *handler);
2c69e205	260	int block_read_full_folio(struct folio , get_block_t );
2e7e80f7	261	bool block_is_partially_uptodate(struct folio *, size_t from, size_t count);
155130a4	262	int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
b3992d1e	263	struct page *pagep, get_block_t get_block);
6e1db88d CH	264	int __block_write_begin(struct page *page, loff_t pos, unsigned len,
6e1db88d CH	265	get_block_t *get_block);
afddba49 NP	266	int block_write_end(struct file , struct address_space ,
	267	loff_t, unsigned, unsigned,
	268	struct page , void );
	269	int generic_write_end(struct file , struct address_space ,
	270	loff_t, unsigned, unsigned,
	271	struct page , void );
	272	void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
f892760a	273	void clean_page_buffers(struct page *page);
89e10787	274	int cont_write_begin(struct file , struct address_space , loff_t,
be3bbbc5	275	unsigned, struct page , void ,
89e10787	276	get_block_t , loff_t );
05eb0b51	277	int generic_cont_expand_simple(struct inode *inode, loff_t size);
1da177e4	278	int block_commit_write(struct page *page, unsigned from, unsigned to);
c2ec175c	279	int block_page_mkwrite(struct vm_area_struct vma, struct vm_fault vmf,
54171690	280	get_block_t get_block);
24da4fab	281	/* Convert errno to return value from ->page_mkwrite() call */
401b25aa	282	static inline vm_fault_t block_page_mkwrite_return(int err)
24da4fab JK	283	{
	284	if (err == 0)
	285	return VM_FAULT_LOCKED;
0911d004	286	if (err == -EFAULT \|\| err == -EAGAIN)
24da4fab JK	287	return VM_FAULT_NOPAGE;
	288	if (err == -ENOMEM)
	289	return VM_FAULT_OOM;
	290	/* -ENOSPC, -EDQUOT, -EIO ... */
	291	return VM_FAULT_SIGBUS;
	292	}
1da177e4	293	sector_t generic_block_bmap(struct address_space , sector_t, get_block_t );
1da177e4	294	int block_truncate_page(struct address_space , loff_t, get_block_t );
1da177e4	295
67235182 MWO	296	#ifdef CONFIG_MIGRATION
	297	extern int buffer_migrate_folio(struct address_space *,
	298	struct folio dst, struct folio src, enum migrate_mode);
	299	extern int buffer_migrate_folio_norefs(struct address_space *,
	300	struct folio dst, struct folio src, enum migrate_mode);
	301	#else
	302	#define buffer_migrate_folio NULL
	303	#define buffer_migrate_folio_norefs NULL
	304	#endif
1da177e4	305
b6cd0b77	306	void buffer_init(void);
1da177e4 LT	307
	308	/*
	309	* inline definitions
	310	*/
	311
1da177e4 LT	312	static inline void get_bh(struct buffer_head *bh)
	313	{
	314	atomic_inc(&bh->b_count);
	315	}
	316
	317	static inline void put_bh(struct buffer_head *bh)
	318	{
4e857c58	319	smp_mb__before_atomic();
1da177e4 LT	320	atomic_dec(&bh->b_count);
	321	}
	322
	323	static inline void brelse(struct buffer_head *bh)
	324	{
	325	if (bh)
	326	__brelse(bh);
	327	}
	328
	329	static inline void bforget(struct buffer_head *bh)
	330	{
	331	if (bh)
	332	__bforget(bh);
	333	}
	334
	335	static inline struct buffer_head *
	336	sb_bread(struct super_block *sb, sector_t block)
	337	{
3b5e6454 GK	338	return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
	339	}
	340
	341	static inline struct buffer_head *
	342	sb_bread_unmovable(struct super_block *sb, sector_t block)
	343	{
	344	return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, 0);
1da177e4 LT	345	}
	346
	347	static inline void
	348	sb_breadahead(struct super_block *sb, sector_t block)
	349	{
	350	__breadahead(sb->s_bdev, block, sb->s_blocksize);
	351	}
	352
	353	static inline struct buffer_head *
	354	sb_getblk(struct super_block *sb, sector_t block)
	355	{
3b5e6454	356	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
1da177e4 LT	357	}
1da177e4 LT	358
bd7ade3c NB	359
	360	static inline struct buffer_head *
	361	sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp)
	362	{
	363	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp);
	364	}
	365
1da177e4 LT	366	static inline struct buffer_head *
	367	sb_find_get_block(struct super_block *sb, sector_t block)
	368	{
	369	return __find_get_block(sb->s_bdev, block, sb->s_blocksize);
	370	}
	371
	372	static inline void
	373	map_bh(struct buffer_head bh, struct super_block sb, sector_t block)
	374	{
	375	set_buffer_mapped(bh);
	376	bh->b_bdev = sb->s_bdev;
	377	bh->b_blocknr = block;
b0cf2321	378	bh->b_size = sb->s_blocksize;
1da177e4 LT	379	}
1da177e4 LT	380
1da177e4 LT	381	static inline void wait_on_buffer(struct buffer_head *bh)
	382	{
	383	might_sleep();
a9877cc2	384	if (buffer_locked(bh))
1da177e4 LT	385	__wait_on_buffer(bh);
	386	}
	387
ca5de404 NP	388	static inline int trylock_buffer(struct buffer_head *bh)
ca5de404 NP	389	{
51b07fc3	390	return likely(!test_and_set_bit_lock(BH_Lock, &bh->b_state));
ca5de404 NP	391	}
ca5de404 NP	392
1da177e4 LT	393	static inline void lock_buffer(struct buffer_head *bh)
	394	{
	395	might_sleep();
ca5de404	396	if (!trylock_buffer(bh))
1da177e4 LT	397	__lock_buffer(bh);
	398	}
	399
3b5e6454 GK	400	static inline struct buffer_head getblk_unmovable(struct block_device bdev,
	401	sector_t block,
	402	unsigned size)
	403	{
	404	return __getblk_gfp(bdev, block, size, 0);
	405	}
	406
	407	static inline struct buffer_head __getblk(struct block_device bdev,
	408	sector_t block,
	409	unsigned size)
	410	{
	411	return __getblk_gfp(bdev, block, size, __GFP_MOVABLE);
	412	}
	413
fdee117e ZY	414	static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags)
	415	{
	416	if (!buffer_uptodate(bh) && trylock_buffer(bh)) {
	417	if (!buffer_uptodate(bh))
	418	__bh_read(bh, op_flags, false);
	419	else
	420	unlock_buffer(bh);
	421	}
	422	}
	423
	424	static inline void bh_read_nowait(struct buffer_head *bh, blk_opf_t op_flags)
	425	{
	426	if (!bh_uptodate_or_lock(bh))
	427	__bh_read(bh, op_flags, false);
	428	}
	429
	430	/* Returns 1 if buffer uptodated, 0 on success, and -EIO on error. */
	431	static inline int bh_read(struct buffer_head *bh, blk_opf_t op_flags)
	432	{
	433	if (bh_uptodate_or_lock(bh))
	434	return 1;
	435	return __bh_read(bh, op_flags, true);
	436	}
	437
	438	static inline void bh_read_batch(int nr, struct buffer_head *bhs[])
	439	{
	440	__bh_read_batch(nr, bhs, 0, true);
	441	}
	442
	443	static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[],
	444	blk_opf_t op_flags)
	445	{
	446	__bh_read_batch(nr, bhs, op_flags, false);
	447	}
	448
3b5e6454 GK	449	/**
	450	* __bread() - reads a specified block and returns the bh
	451	* @bdev: the block_device to read from
	452	* @block: number of block
	453	* @size: size (in bytes) to read
	454	*
	455	* Reads a specified block, and returns buffer head that contains it.
	456	* The page cache is allocated from movable area so that it can be migrated.
	457	* It returns NULL if the block was unreadable.
	458	*/
	459	static inline struct buffer_head *
	460	__bread(struct block_device *bdev, sector_t block, unsigned size)
	461	{
	462	return __bread_gfp(bdev, block, size, __GFP_MOVABLE);
	463	}
	464
e621900a	465	bool block_dirty_folio(struct address_space mapping, struct folio folio);
9361401e DH	466
	467	#else /* CONFIG_BLOCK */
	468
	469	static inline void buffer_init(void) {}
68189fef	470	static inline bool try_to_free_buffers(struct folio *folio) { return true; }
9361401e DH	471	static inline int inode_has_buffers(struct inode *inode) { return 0; }
	472	static inline void invalidate_inode_buffers(struct inode *inode) {}
	473	static inline int remove_inode_buffers(struct inode *inode) { return 1; }
	474	static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
243418e3	475	static inline void invalidate_bh_lrus_cpu(void) {}
6de522d1	476	static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; }
d2de7ea4	477	#define buffer_heads_over_limit 0
9361401e DH	478
9361401e DH	479	#endif /* CONFIG_BLOCK */
1da177e4	480	#endif /* _LINUX_BUFFER_HEAD_H */