[deliverable/linux.git] / include / linux / bio.h

/*
 * 2.5 block I/O model
 *
 * Copyright (C) 2001 Jens Axboe <axboe@suse.de>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of

 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public Licens
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
 */
#ifndef __LINUX_BIO_H
#define __LINUX_BIO_H

#include <linux/highmem.h>
#include <linux/mempool.h>
#include <linux/ioprio.h>

#ifdef CONFIG_BLOCK

#include <asm/io.h>

#define BIO_DEBUG

#ifdef BIO_DEBUG
#define BIO_BUG_ON	BUG_ON
#else
#define BIO_BUG_ON
#endif

#define BIO_MAX_PAGES		256
#define BIO_MAX_SIZE		(BIO_MAX_PAGES << PAGE_CACHE_SHIFT)
#define BIO_MAX_SECTORS		(BIO_MAX_SIZE >> 9)

/*
 * was unsigned short, but we might as well be ready for > 64kB I/O pages
 */
struct bio_vec {
	struct page	*bv_page;
	unsigned int	bv_len;
	unsigned int	bv_offset;
};

struct bio_set;
struct bio;
struct bio_integrity_payload;
typedef void (bio_end_io_t) (struct bio *, int);
typedef void (bio_destructor_t) (struct bio *);

/*
 * main unit of I/O for the block layer and lower layers (ie drivers and
 * stacking drivers)
 */
struct bio {
	sector_t		bi_sector;	/* device address in 512 byte
						   sectors */
	struct bio		*bi_next;	/* request queue link */
	struct block_device	*bi_bdev;
	unsigned long		bi_flags;	/* status, command, etc */
	unsigned long		bi_rw;		/* bottom bits READ/WRITE,
						 * top bits priority
						 */

	unsigned short		bi_vcnt;	/* how many bio_vec's */
	unsigned short		bi_idx;		/* current index into bvl_vec */

	/* Number of segments in this BIO after
	 * physical address coalescing is performed.
	 */
	unsigned int		bi_phys_segments;

	unsigned int		bi_size;	/* residual I/O count */

	unsigned int		bi_max_vecs;	/* max bvl_vecs we can hold */

	unsigned int		bi_comp_cpu;	/* completion CPU */

	struct bio_vec		*bi_io_vec;	/* the actual vec list */

	bio_end_io_t		*bi_end_io;
	atomic_t		bi_cnt;		/* pin count */

	void			*bi_private;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
	struct bio_integrity_payload *bi_integrity;  /* data integrity */
#endif

	bio_destructor_t	*bi_destructor;	/* destructor */
};

/*
 * bio flags
 */
#define BIO_UPTODATE	0	/* ok after I/O completion */
#define BIO_RW_BLOCK	1	/* RW_AHEAD set, and read/write would block */
#define BIO_EOF		2	/* out-out-bounds error */
#define BIO_SEG_VALID	3	/* bi_phys_segments valid */
#define BIO_CLONED	4	/* doesn't own data */
#define BIO_BOUNCED	5	/* bio is a bounce bio */
#define BIO_USER_MAPPED 6	/* contains user pages */
#define BIO_EOPNOTSUPP	7	/* not supported */
#define BIO_CPU_AFFINE	8	/* complete bio on same CPU as submitted */
#define bio_flagged(bio, flag)	((bio)->bi_flags & (1 << (flag)))

/*
 * top 4 bits of bio flags indicate the pool this bio came from
 */
#define BIO_POOL_BITS		(4)
#define BIO_POOL_OFFSET		(BITS_PER_LONG - BIO_POOL_BITS)
#define BIO_POOL_MASK		(1UL << BIO_POOL_OFFSET)
#define BIO_POOL_IDX(bio)	((bio)->bi_flags >> BIO_POOL_OFFSET)	

/*
 * bio bi_rw flags
 *
 * bit 0 -- read (not set) or write (set)
 * bit 1 -- rw-ahead when set
 * bit 2 -- barrier
 * bit 3 -- fail fast, don't want low level driver retries
 * bit 4 -- synchronous I/O hint: the block layer will unplug immediately
 * bit 5 -- metadata request
 * bit 6 -- discard sectors
 */
#define BIO_RW		0	/* Must match RW in req flags (blkdev.h) */
#define BIO_RW_AHEAD	1	/* Must match FAILFAST in req flags */
#define BIO_RW_BARRIER	2
#define BIO_RW_FAILFAST	3
#define BIO_RW_SYNC	4
#define BIO_RW_META	5
#define BIO_RW_DISCARD	6

/*
 * upper 16 bits of bi_rw define the io priority of this bio
 */
#define BIO_PRIO_SHIFT	(8 * sizeof(unsigned long) - IOPRIO_BITS)
#define bio_prio(bio)	((bio)->bi_rw >> BIO_PRIO_SHIFT)
#define bio_prio_valid(bio)	ioprio_valid(bio_prio(bio))

#define bio_set_prio(bio, prio)		do {			\
	WARN_ON(prio >= (1 << IOPRIO_BITS));			\
	(bio)->bi_rw &= ((1UL << BIO_PRIO_SHIFT) - 1);		\
	(bio)->bi_rw |= ((unsigned long) (prio) << BIO_PRIO_SHIFT);	\
} while (0)

/*
 * various member access, note that bio_data should of course not be used
 * on highmem page vectors
 */
#define bio_iovec_idx(bio, idx)	(&((bio)->bi_io_vec[(idx)]))
#define bio_iovec(bio)		bio_iovec_idx((bio), (bio)->bi_idx)
#define bio_page(bio)		bio_iovec((bio))->bv_page
#define bio_offset(bio)		bio_iovec((bio))->bv_offset
#define bio_segments(bio)	((bio)->bi_vcnt - (bio)->bi_idx)
#define bio_sectors(bio)	((bio)->bi_size >> 9)
#define bio_barrier(bio)	((bio)->bi_rw & (1 << BIO_RW_BARRIER))
#define bio_sync(bio)		((bio)->bi_rw & (1 << BIO_RW_SYNC))
#define bio_failfast(bio)	((bio)->bi_rw & (1 << BIO_RW_FAILFAST))
#define bio_rw_ahead(bio)	((bio)->bi_rw & (1 << BIO_RW_AHEAD))
#define bio_rw_meta(bio)	((bio)->bi_rw & (1 << BIO_RW_META))
#define bio_discard(bio)	((bio)->bi_rw & (1 << BIO_RW_DISCARD))
#define bio_empty_barrier(bio)	(bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio))

static inline unsigned int bio_cur_sectors(struct bio *bio)
{
	if (bio->bi_vcnt)
		return bio_iovec(bio)->bv_len >> 9;
	else /* dataless requests such as discard */
		return bio->bi_size >> 9;
}

static inline void *bio_data(struct bio *bio)
{
	if (bio->bi_vcnt)
		return page_address(bio_page(bio)) + bio_offset(bio);

	return NULL;
}

/*
 * will die
 */
#define bio_to_phys(bio)	(page_to_phys(bio_page((bio))) + (unsigned long) bio_offset((bio)))
#define bvec_to_phys(bv)	(page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset)

/*
 * queues that have highmem support enabled may still need to revert to
 * PIO transfers occasionally and thus map high pages temporarily. For
 * permanent PIO fall back, user is probably better off disabling highmem
 * I/O completely on that queue (see ide-dma for example)
 */
#define __bio_kmap_atomic(bio, idx, kmtype)				\
	(kmap_atomic(bio_iovec_idx((bio), (idx))->bv_page, kmtype) +	\
		bio_iovec_idx((bio), (idx))->bv_offset)

#define __bio_kunmap_atomic(addr, kmtype) kunmap_atomic(addr, kmtype)

/*
 * merge helpers etc
 */

#define __BVEC_END(bio)		bio_iovec_idx((bio), (bio)->bi_vcnt - 1)
#define __BVEC_START(bio)	bio_iovec_idx((bio), (bio)->bi_idx)

/*
 * allow arch override, for eg virtualized architectures (put in asm/io.h)
 */
#ifndef BIOVEC_PHYS_MERGEABLE
#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)	\
	((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
#endif

#define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \
	(((addr1) | (mask)) == (((addr2) - 1) | (mask)))
#define BIOVEC_SEG_BOUNDARY(q, b1, b2) \
	__BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, (q)->seg_boundary_mask)
#define BIO_SEG_BOUNDARY(q, b1, b2) \
	BIOVEC_SEG_BOUNDARY((q), __BVEC_END((b1)), __BVEC_START((b2)))

#define bio_io_error(bio) bio_endio((bio), -EIO)

/*
 * drivers should not use the __ version unless they _really_ want to
 * run through the entire bio and not just pending pieces
 */
#define __bio_for_each_segment(bvl, bio, i, start_idx)			\
	for (bvl = bio_iovec_idx((bio), (start_idx)), i = (start_idx);	\
	     i < (bio)->bi_vcnt;					\
	     bvl++, i++)

#define bio_for_each_segment(bvl, bio, i)				\
	__bio_for_each_segment(bvl, bio, i, (bio)->bi_idx)

/*
 * get a reference to a bio, so it won't disappear. the intended use is
 * something like:
 *
 * bio_get(bio);
 * submit_bio(rw, bio);
 * if (bio->bi_flags ...)
 *	do_something
 * bio_put(bio);
 *
 * without the bio_get(), it could potentially complete I/O before submit_bio
 * returns. and then bio would be freed memory when if (bio->bi_flags ...)
 * runs
 */
#define bio_get(bio)	atomic_inc(&(bio)->bi_cnt)

#if defined(CONFIG_BLK_DEV_INTEGRITY)
/*
 * bio integrity payload
 */
struct bio_integrity_payload {
	struct bio		*bip_bio;	/* parent bio */
	struct bio_vec		*bip_vec;	/* integrity data vector */

	sector_t		bip_sector;	/* virtual start sector */

	void			*bip_buf;	/* generated integrity data */
	bio_end_io_t		*bip_end_io;	/* saved I/O completion fn */

	int			bip_error;	/* saved I/O error */
	unsigned int		bip_size;

	unsigned short		bip_pool;	/* pool the ivec came from */
	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
	unsigned short		bip_idx;	/* current bip_vec index */

	struct work_struct	bip_work;	/* I/O completion */
};
#endif /* CONFIG_BLK_DEV_INTEGRITY */

/*
 * A bio_pair is used when we need to split a bio.
 * This can only happen for a bio that refers to just one
 * page of data, and in the unusual situation when the
 * page crosses a chunk/device boundary
 *
 * The address of the master bio is stored in bio1.bi_private
 * The address of the pool the pair was allocated from is stored
 *   in bio2.bi_private
 */
struct bio_pair {
	struct bio			bio1, bio2;
	struct bio_vec			bv1, bv2;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
	struct bio_integrity_payload	bip1, bip2;
	struct bio_vec			iv1, iv2;
#endif
	atomic_t			cnt;
	int				error;
};
extern struct bio_pair *bio_split(struct bio *bi, mempool_t *pool,
				  int first_sectors);
extern mempool_t *bio_split_pool;
extern void bio_pair_release(struct bio_pair *dbio);

extern struct bio_set *bioset_create(int, int);
extern void bioset_free(struct bio_set *);

extern struct bio *bio_alloc(gfp_t, int);
extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *);
extern void bio_put(struct bio *);
extern void bio_free(struct bio *, struct bio_set *);

extern void bio_endio(struct bio *, int);
struct request_queue;
extern int bio_phys_segments(struct request_queue *, struct bio *);

extern void __bio_clone(struct bio *, struct bio *);
extern struct bio *bio_clone(struct bio *, gfp_t);

extern void bio_init(struct bio *);

extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
			   unsigned int, unsigned int);
extern int bio_get_nr_vecs(struct block_device *);
extern struct bio *bio_map_user(struct request_queue *, struct block_device *,
				unsigned long, unsigned int, int, gfp_t);
struct sg_iovec;
struct rq_map_data;
extern struct bio *bio_map_user_iov(struct request_queue *,
				    struct block_device *,
				    struct sg_iovec *, int, int, gfp_t);
extern void bio_unmap_user(struct bio *);
extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
				gfp_t);
extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int,
				 gfp_t, int);
extern void bio_set_pages_dirty(struct bio *bio);
extern void bio_check_pages_dirty(struct bio *bio);
extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *,
				 unsigned long, unsigned int, int, gfp_t);
extern struct bio *bio_copy_user_iov(struct request_queue *,
				     struct rq_map_data *, struct sg_iovec *,
				     int, int, gfp_t);
extern int bio_uncopy_user(struct bio *);
void zero_fill_bio(struct bio *bio);
extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set *);
extern unsigned int bvec_nr_vecs(unsigned short idx);

/*
 * Allow queuer to specify a completion CPU for this bio
 */
static inline void bio_set_completion_cpu(struct bio *bio, unsigned int cpu)
{
	bio->bi_comp_cpu = cpu;
}

/*
 * bio_set is used to allow other portions of the IO system to
 * allocate their own private memory pools for bio and iovec structures.
 * These memory pools in turn all allocate from the bio_slab
 * and the bvec_slabs[].
 */
#define BIO_POOL_SIZE 2
#define BIOVEC_NR_POOLS 6

struct bio_set {
	mempool_t *bio_pool;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
	mempool_t *bio_integrity_pool;
#endif
	mempool_t *bvec_pools[BIOVEC_NR_POOLS];
};

struct biovec_slab {
	int nr_vecs;
	char *name;
	struct kmem_cache *slab;
};

extern struct bio_set *fs_bio_set;

/*
 * a small number of entries is fine, not going to be performance critical.
 * basically we just need to survive
 */
#define BIO_SPLIT_ENTRIES 2

#ifdef CONFIG_HIGHMEM
/*
 * remember to add offset! and never ever reenable interrupts between a
 * bvec_kmap_irq and bvec_kunmap_irq!!
 *
 * This function MUST be inlined - it plays with the CPU interrupt flags.
 */
static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags)
{
	unsigned long addr;

	/*
	 * might not be a highmem page, but the preempt/irq count
	 * balancing is a lot nicer this way
	 */
	local_irq_save(*flags);
	addr = (unsigned long) kmap_atomic(bvec->bv_page, KM_BIO_SRC_IRQ);

	BUG_ON(addr & ~PAGE_MASK);

	return (char *) addr + bvec->bv_offset;
}

static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags)
{
	unsigned long ptr = (unsigned long) buffer & PAGE_MASK;

	kunmap_atomic((void *) ptr, KM_BIO_SRC_IRQ);
	local_irq_restore(*flags);
}

#else
#define bvec_kmap_irq(bvec, flags)	(page_address((bvec)->bv_page) + (bvec)->bv_offset)
#define bvec_kunmap_irq(buf, flags)	do { *(flags) = 0; } while (0)
#endif

static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx,
				   unsigned long *flags)
{
	return bvec_kmap_irq(bio_iovec_idx(bio, idx), flags);
}
#define __bio_kunmap_irq(buf, flags)	bvec_kunmap_irq(buf, flags)

#define bio_kmap_irq(bio, flags) \
	__bio_kmap_irq((bio), (bio)->bi_idx, (flags))
#define bio_kunmap_irq(buf,flags)	__bio_kunmap_irq(buf, flags)

/*
 * Check whether this bio carries any data or not. A NULL bio is allowed.
 */
static inline int bio_has_data(struct bio *bio)
{
	return bio && bio->bi_io_vec != NULL;
}

#if defined(CONFIG_BLK_DEV_INTEGRITY)

#define bip_vec_idx(bip, idx)	(&(bip->bip_vec[(idx)]))
#define bip_vec(bip)		bip_vec_idx(bip, 0)

#define __bip_for_each_vec(bvl, bip, i, start_idx)			\
	for (bvl = bip_vec_idx((bip), (start_idx)), i = (start_idx);	\
	     i < (bip)->bip_vcnt;					\
	     bvl++, i++)

#define bip_for_each_vec(bvl, bip, i)					\
	__bip_for_each_vec(bvl, bip, i, (bip)->bip_idx)

static inline int bio_integrity(struct bio *bio)
{
#if defined(CONFIG_BLK_DEV_INTEGRITY)
	return bio->bi_integrity != NULL;
#else
	return 0;
#endif
}

extern struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *, gfp_t, unsigned int, struct bio_set *);
extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
extern void bio_integrity_free(struct bio *, struct bio_set *);
extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
extern int bio_integrity_enabled(struct bio *bio);
extern int bio_integrity_set_tag(struct bio *, void *, unsigned int);
extern int bio_integrity_get_tag(struct bio *, void *, unsigned int);
extern int bio_integrity_prep(struct bio *);
extern void bio_integrity_endio(struct bio *, int);
extern void bio_integrity_advance(struct bio *, unsigned int);
extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int);
extern void bio_integrity_split(struct bio *, struct bio_pair *, int);
extern int bio_integrity_clone(struct bio *, struct bio *, struct bio_set *);
extern int bioset_integrity_create(struct bio_set *, int);
extern void bioset_integrity_free(struct bio_set *);
extern void bio_integrity_init_slab(void);

#else /* CONFIG_BLK_DEV_INTEGRITY */

#define bio_integrity(a)		(0)
#define bioset_integrity_create(a, b)	(0)
#define bio_integrity_prep(a)		(0)
#define bio_integrity_enabled(a)	(0)
#define bio_integrity_clone(a, b, c)	(0)
#define bioset_integrity_free(a)	do { } while (0)
#define bio_integrity_free(a, b)	do { } while (0)
#define bio_integrity_endio(a, b)	do { } while (0)
#define bio_integrity_advance(a, b)	do { } while (0)
#define bio_integrity_trim(a, b, c)	do { } while (0)
#define bio_integrity_split(a, b, c)	do { } while (0)
#define bio_integrity_set_tag(a, b, c)	do { } while (0)
#define bio_integrity_get_tag(a, b, c)	do { } while (0)
#define bio_integrity_init_slab(a)	do { } while (0)

#endif /* CONFIG_BLK_DEV_INTEGRITY */

#endif /* CONFIG_BLOCK */
#endif /* __LINUX_BIO_H */
Commit	Line	Data
1da177e4 LT	1	/*
	2	* 2.5 block I/O model
	3	*
	4	* Copyright (C) 2001 Jens Axboe <axboe@suse.de>
	5	*
	6	* This program is free software; you can redistribute it and/or modify
	7	* it under the terms of the GNU General Public License version 2 as
	8	* published by the Free Software Foundation.
	9	*
	10	* This program is distributed in the hope that it will be useful,
	11	* but WITHOUT ANY WARRANTY; without even the implied warranty of
	12
	13	* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
	14	* GNU General Public License for more details.
	15	*
	16	* You should have received a copy of the GNU General Public Licens
	17	* along with this program; if not, write to the Free Software
	18	* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-
	19	*/
	20	#ifndef __LINUX_BIO_H
	21	#define __LINUX_BIO_H
	22
	23	#include <linux/highmem.h>
	24	#include <linux/mempool.h>
22e2c507	25	#include <linux/ioprio.h>
1da177e4	26
02a5e0ac DH	27	#ifdef CONFIG_BLOCK
02a5e0ac DH	28
1da177e4 LT	29	#include <asm/io.h>
1da177e4 LT	30
1da177e4 LT	31	#define BIO_DEBUG
	32
	33	#ifdef BIO_DEBUG
	34	#define BIO_BUG_ON BUG_ON
	35	#else
	36	#define BIO_BUG_ON
	37	#endif
	38
d84a8477	39	#define BIO_MAX_PAGES 256
1da177e4 LT	40	#define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_CACHE_SHIFT)
	41	#define BIO_MAX_SECTORS (BIO_MAX_SIZE >> 9)
	42
	43	/*
	44	* was unsigned short, but we might as well be ready for > 64kB I/O pages
	45	*/
	46	struct bio_vec {
	47	struct page *bv_page;
	48	unsigned int bv_len;
	49	unsigned int bv_offset;
	50	};
	51
	52	struct bio_set;
	53	struct bio;
7ba1ba12	54	struct bio_integrity_payload;
6712ecf8	55	typedef void (bio_end_io_t) (struct bio *, int);
1da177e4 LT	56	typedef void (bio_destructor_t) (struct bio *);
	57
	58	/*
	59	* main unit of I/O for the block layer and lower layers (ie drivers and
	60	* stacking drivers)
	61	*/
	62	struct bio {
2c2345c2 RG	63	sector_t bi_sector; /* device address in 512 byte
2c2345c2 RG	64	sectors */
1da177e4 LT	65	struct bio bi_next; / request queue link */
	66	struct block_device *bi_bdev;
	67	unsigned long bi_flags; /* status, command, etc */
	68	unsigned long bi_rw; /* bottom bits READ/WRITE,
	69	* top bits priority
	70	*/
	71
	72	unsigned short bi_vcnt; /* how many bio_vec's */
	73	unsigned short bi_idx; /* current index into bvl_vec */
	74
	75	/* Number of segments in this BIO after
	76	* physical address coalescing is performed.
	77	*/
5b99c2ff	78	unsigned int bi_phys_segments;
1da177e4	79
1da177e4 LT	80	unsigned int bi_size; /* residual I/O count */
1da177e4 LT	81
1da177e4 LT	82	unsigned int bi_max_vecs; /* max bvl_vecs we can hold */
1da177e4 LT	83
c7c22e4d JA	84	unsigned int bi_comp_cpu; /* completion CPU */
c7c22e4d JA	85
1da177e4 LT	86	struct bio_vec bi_io_vec; / the actual vec list */
	87
	88	bio_end_io_t *bi_end_io;
	89	atomic_t bi_cnt; /* pin count */
	90
	91	void *bi_private;
7ba1ba12 MP	92	#if defined(CONFIG_BLK_DEV_INTEGRITY)
	93	struct bio_integrity_payload bi_integrity; / data integrity */
	94	#endif
1da177e4 LT	95
1da177e4 LT	96	bio_destructor_t bi_destructor; / destructor */
1da177e4 LT	97	};
	98
	99	/*
	100	* bio flags
	101	*/
	102	#define BIO_UPTODATE 0 /* ok after I/O completion */
	103	#define BIO_RW_BLOCK 1 /* RW_AHEAD set, and read/write would block */
	104	#define BIO_EOF 2 /* out-out-bounds error */
5df97b91	105	#define BIO_SEG_VALID 3 /* bi_phys_segments valid */
1da177e4 LT	106	#define BIO_CLONED 4 /* doesn't own data */
	107	#define BIO_BOUNCED 5 /* bio is a bounce bio */
	108	#define BIO_USER_MAPPED 6 /* contains user pages */
	109	#define BIO_EOPNOTSUPP 7 /* not supported */
c7c22e4d	110	#define BIO_CPU_AFFINE 8 /* complete bio on same CPU as submitted */
1da177e4 LT	111	#define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag)))
	112
	113	/*
	114	* top 4 bits of bio flags indicate the pool this bio came from
	115	*/
	116	#define BIO_POOL_BITS (4)
	117	#define BIO_POOL_OFFSET (BITS_PER_LONG - BIO_POOL_BITS)
	118	#define BIO_POOL_MASK (1UL << BIO_POOL_OFFSET)
	119	#define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET)
	120
	121	/*
	122	* bio bi_rw flags
	123	*
	124	* bit 0 -- read (not set) or write (set)
	125	* bit 1 -- rw-ahead when set
	126	* bit 2 -- barrier
	127	* bit 3 -- fail fast, don't want low level driver retries
	128	* bit 4 -- synchronous I/O hint: the block layer will unplug immediately
fb2dce86 DW	129	* bit 5 -- metadata request
fb2dce86 DW	130	* bit 6 -- discard sectors
1da177e4	131	*/
d628eaef DW	132	#define BIO_RW 0 /* Must match RW in req flags (blkdev.h) */
d628eaef DW	133	#define BIO_RW_AHEAD 1 /* Must match FAILFAST in req flags */
1da177e4 LT	134	#define BIO_RW_BARRIER 2
	135	#define BIO_RW_FAILFAST 3
	136	#define BIO_RW_SYNC 4
5404bc7a	137	#define BIO_RW_META 5
fb2dce86	138	#define BIO_RW_DISCARD 6
1da177e4	139
22e2c507 JA	140	/*
	141	* upper 16 bits of bi_rw define the io priority of this bio
	142	*/
	143	#define BIO_PRIO_SHIFT (8 * sizeof(unsigned long) - IOPRIO_BITS)
	144	#define bio_prio(bio) ((bio)->bi_rw >> BIO_PRIO_SHIFT)
	145	#define bio_prio_valid(bio) ioprio_valid(bio_prio(bio))
	146
	147	#define bio_set_prio(bio, prio) do { \
	148	WARN_ON(prio >= (1 << IOPRIO_BITS)); \
	149	(bio)->bi_rw &= ((1UL << BIO_PRIO_SHIFT) - 1); \
	150	(bio)->bi_rw \|= ((unsigned long) (prio) << BIO_PRIO_SHIFT); \
	151	} while (0)
	152
1da177e4 LT	153	/*
	154	* various member access, note that bio_data should of course not be used
	155	* on highmem page vectors
	156	*/
	157	#define bio_iovec_idx(bio, idx) (&((bio)->bi_io_vec[(idx)]))
	158	#define bio_iovec(bio) bio_iovec_idx((bio), (bio)->bi_idx)
	159	#define bio_page(bio) bio_iovec((bio))->bv_page
	160	#define bio_offset(bio) bio_iovec((bio))->bv_offset
	161	#define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx)
	162	#define bio_sectors(bio) ((bio)->bi_size >> 9)
1da177e4 LT	163	#define bio_barrier(bio) ((bio)->bi_rw & (1 << BIO_RW_BARRIER))
	164	#define bio_sync(bio) ((bio)->bi_rw & (1 << BIO_RW_SYNC))
	165	#define bio_failfast(bio) ((bio)->bi_rw & (1 << BIO_RW_FAILFAST))
	166	#define bio_rw_ahead(bio) ((bio)->bi_rw & (1 << BIO_RW_AHEAD))
5404bc7a	167	#define bio_rw_meta(bio) ((bio)->bi_rw & (1 << BIO_RW_META))
fb2dce86	168	#define bio_discard(bio) ((bio)->bi_rw & (1 << BIO_RW_DISCARD))
e17fc0a1	169	#define bio_empty_barrier(bio) (bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio))
bf2de6f5 JA	170
	171	static inline unsigned int bio_cur_sectors(struct bio *bio)
	172	{
	173	if (bio->bi_vcnt)
	174	return bio_iovec(bio)->bv_len >> 9;
fb2dce86 DW	175	else /* dataless requests such as discard */
fb2dce86 DW	176	return bio->bi_size >> 9;
bf2de6f5 JA	177	}
	178
	179	static inline void bio_data(struct bio bio)
	180	{
	181	if (bio->bi_vcnt)
	182	return page_address(bio_page(bio)) + bio_offset(bio);
	183
	184	return NULL;
	185	}
1da177e4 LT	186
	187	/*
	188	* will die
	189	*/
	190	#define bio_to_phys(bio) (page_to_phys(bio_page((bio))) + (unsigned long) bio_offset((bio)))
	191	#define bvec_to_phys(bv) (page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset)
	192
	193	/*
	194	* queues that have highmem support enabled may still need to revert to
	195	* PIO transfers occasionally and thus map high pages temporarily. For
	196	* permanent PIO fall back, user is probably better off disabling highmem
	197	* I/O completely on that queue (see ide-dma for example)
	198	*/
	199	#define __bio_kmap_atomic(bio, idx, kmtype) \
	200	(kmap_atomic(bio_iovec_idx((bio), (idx))->bv_page, kmtype) + \
	201	bio_iovec_idx((bio), (idx))->bv_offset)
	202
	203	#define __bio_kunmap_atomic(addr, kmtype) kunmap_atomic(addr, kmtype)
	204
	205	/*
	206	* merge helpers etc
	207	*/
	208
	209	#define __BVEC_END(bio) bio_iovec_idx((bio), (bio)->bi_vcnt - 1)
	210	#define __BVEC_START(bio) bio_iovec_idx((bio), (bio)->bi_idx)
	211
	212	/*
	213	* allow arch override, for eg virtualized architectures (put in asm/io.h)
	214	*/
	215	#ifndef BIOVEC_PHYS_MERGEABLE
	216	#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
	217	((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
	218	#endif
	219
1da177e4 LT	220	#define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \
	221	(((addr1) \| (mask)) == (((addr2) - 1) \| (mask)))
	222	#define BIOVEC_SEG_BOUNDARY(q, b1, b2) \
	223	__BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, (q)->seg_boundary_mask)
	224	#define BIO_SEG_BOUNDARY(q, b1, b2) \
	225	BIOVEC_SEG_BOUNDARY((q), __BVEC_END((b1)), __BVEC_START((b2)))
	226
6712ecf8	227	#define bio_io_error(bio) bio_endio((bio), -EIO)
1da177e4 LT	228
	229	/*
	230	* drivers should not use the __ version unless they _really_ want to
	231	* run through the entire bio and not just pending pieces
	232	*/
	233	#define __bio_for_each_segment(bvl, bio, i, start_idx) \
	234	for (bvl = bio_iovec_idx((bio), (start_idx)), i = (start_idx); \
	235	i < (bio)->bi_vcnt; \
	236	bvl++, i++)
	237
	238	#define bio_for_each_segment(bvl, bio, i) \
	239	__bio_for_each_segment(bvl, bio, i, (bio)->bi_idx)
	240
	241	/*
	242	* get a reference to a bio, so it won't disappear. the intended use is
	243	* something like:
	244	*
	245	* bio_get(bio);
	246	* submit_bio(rw, bio);
	247	* if (bio->bi_flags ...)
	248	* do_something
	249	* bio_put(bio);
	250	*
	251	* without the bio_get(), it could potentially complete I/O before submit_bio
	252	* returns. and then bio would be freed memory when if (bio->bi_flags ...)
	253	* runs
	254	*/
	255	#define bio_get(bio) atomic_inc(&(bio)->bi_cnt)
	256
7ba1ba12 MP	257	#if defined(CONFIG_BLK_DEV_INTEGRITY)
	258	/*
	259	* bio integrity payload
	260	*/
	261	struct bio_integrity_payload {
	262	struct bio bip_bio; / parent bio */
	263	struct bio_vec bip_vec; / integrity data vector */
	264
	265	sector_t bip_sector; /* virtual start sector */
	266
	267	void bip_buf; / generated integrity data */
	268	bio_end_io_t bip_end_io; / saved I/O completion fn */
	269
	270	int bip_error; /* saved I/O error */
	271	unsigned int bip_size;
	272
	273	unsigned short bip_pool; /* pool the ivec came from */
	274	unsigned short bip_vcnt; /* # of integrity bio_vecs */
	275	unsigned short bip_idx; /* current bip_vec index */
	276
	277	struct work_struct bip_work; /* I/O completion */
	278	};
	279	#endif /* CONFIG_BLK_DEV_INTEGRITY */
1da177e4 LT	280
	281	/*
	282	* A bio_pair is used when we need to split a bio.
	283	* This can only happen for a bio that refers to just one
	284	* page of data, and in the unusual situation when the
	285	* page crosses a chunk/device boundary
	286	*
	287	* The address of the master bio is stored in bio1.bi_private
	288	* The address of the pool the pair was allocated from is stored
	289	* in bio2.bi_private
	290	*/
	291	struct bio_pair {
7ba1ba12 MP	292	struct bio bio1, bio2;
	293	struct bio_vec bv1, bv2;
	294	#if defined(CONFIG_BLK_DEV_INTEGRITY)
	295	struct bio_integrity_payload bip1, bip2;
	296	struct bio_vec iv1, iv2;
	297	#endif
	298	atomic_t cnt;
	299	int error;
1da177e4 LT	300	};
	301	extern struct bio_pair bio_split(struct bio bi, mempool_t *pool,
	302	int first_sectors);
	303	extern mempool_t *bio_split_pool;
	304	extern void bio_pair_release(struct bio_pair *dbio);
	305
5972511b	306	extern struct bio_set *bioset_create(int, int);
1da177e4 LT	307	extern void bioset_free(struct bio_set *);
1da177e4 LT	308
dd0fc66f AV	309	extern struct bio *bio_alloc(gfp_t, int);
dd0fc66f AV	310	extern struct bio bio_alloc_bioset(gfp_t, int, struct bio_set );
1da177e4	311	extern void bio_put(struct bio *);
3676347a	312	extern void bio_free(struct bio , struct bio_set );
1da177e4	313
6712ecf8	314	extern void bio_endio(struct bio *, int);
1da177e4 LT	315	struct request_queue;
1da177e4 LT	316	extern int bio_phys_segments(struct request_queue , struct bio );
1da177e4 LT	317
1da177e4 LT	318	extern void __bio_clone(struct bio , struct bio );
dd0fc66f	319	extern struct bio bio_clone(struct bio , gfp_t);
1da177e4 LT	320
	321	extern void bio_init(struct bio *);
	322
	323	extern int bio_add_page(struct bio , struct page , unsigned int,unsigned int);
6e68af66 MC	324	extern int bio_add_pc_page(struct request_queue , struct bio , struct page *,
6e68af66 MC	325	unsigned int, unsigned int);
1da177e4 LT	326	extern int bio_get_nr_vecs(struct block_device *);
1da177e4 LT	327	extern struct bio bio_map_user(struct request_queue , struct block_device *,
a3bce90e	328	unsigned long, unsigned int, int, gfp_t);
f1970baf	329	struct sg_iovec;
152e283f	330	struct rq_map_data;
f1970baf JB	331	extern struct bio bio_map_user_iov(struct request_queue ,
f1970baf JB	332	struct block_device *,
a3bce90e	333	struct sg_iovec *, int, int, gfp_t);
1da177e4	334	extern void bio_unmap_user(struct bio *);
df46b9a4	335	extern struct bio bio_map_kern(struct request_queue , void *, unsigned int,
27496a8c	336	gfp_t);
68154e90 FT	337	extern struct bio bio_copy_kern(struct request_queue , void *, unsigned int,
68154e90 FT	338	gfp_t, int);
1da177e4 LT	339	extern void bio_set_pages_dirty(struct bio *bio);
1da177e4 LT	340	extern void bio_check_pages_dirty(struct bio *bio);
152e283f FT	341	extern struct bio bio_copy_user(struct request_queue , struct rq_map_data *,
	342	unsigned long, unsigned int, int, gfp_t);
	343	extern struct bio bio_copy_user_iov(struct request_queue ,
	344	struct rq_map_data , struct sg_iovec ,
a3bce90e	345	int, int, gfp_t);
1da177e4 LT	346	extern int bio_uncopy_user(struct bio *);
1da177e4 LT	347	void zero_fill_bio(struct bio *bio);
51d654e1	348	extern struct bio_vec bvec_alloc_bs(gfp_t, int, unsigned long , struct bio_set *);
7ba1ba12	349	extern unsigned int bvec_nr_vecs(unsigned short idx);
51d654e1	350
c7c22e4d JA	351	/*
	352	* Allow queuer to specify a completion CPU for this bio
	353	*/
	354	static inline void bio_set_completion_cpu(struct bio *bio, unsigned int cpu)
	355	{
	356	bio->bi_comp_cpu = cpu;
	357	}
	358
51d654e1 MP	359	/*
	360	* bio_set is used to allow other portions of the IO system to
	361	* allocate their own private memory pools for bio and iovec structures.
	362	* These memory pools in turn all allocate from the bio_slab
	363	* and the bvec_slabs[].
	364	*/
	365	#define BIO_POOL_SIZE 2
	366	#define BIOVEC_NR_POOLS 6
	367
	368	struct bio_set {
	369	mempool_t *bio_pool;
7ba1ba12 MP	370	#if defined(CONFIG_BLK_DEV_INTEGRITY)
	371	mempool_t *bio_integrity_pool;
	372	#endif
51d654e1 MP	373	mempool_t *bvec_pools[BIOVEC_NR_POOLS];
	374	};
	375
	376	struct biovec_slab {
	377	int nr_vecs;
	378	char *name;
	379	struct kmem_cache *slab;
	380	};
	381
	382	extern struct bio_set *fs_bio_set;
	383
	384	/*
	385	* a small number of entries is fine, not going to be performance critical.
	386	* basically we just need to survive
	387	*/
	388	#define BIO_SPLIT_ENTRIES 2
1da177e4 LT	389
	390	#ifdef CONFIG_HIGHMEM
	391	/*
	392	* remember to add offset! and never ever reenable interrupts between a
	393	* bvec_kmap_irq and bvec_kunmap_irq!!
	394	*
	395	* This function MUST be inlined - it plays with the CPU interrupt flags.
1da177e4	396	*/
c2d08dad	397	static inline char bvec_kmap_irq(struct bio_vec bvec, unsigned long *flags)
1da177e4 LT	398	{
	399	unsigned long addr;
	400
	401	/*
	402	* might not be a highmem page, but the preempt/irq count
	403	* balancing is a lot nicer this way
	404	*/
	405	local_irq_save(*flags);
	406	addr = (unsigned long) kmap_atomic(bvec->bv_page, KM_BIO_SRC_IRQ);
	407
	408	BUG_ON(addr & ~PAGE_MASK);
	409
	410	return (char *) addr + bvec->bv_offset;
	411	}
	412
c2d08dad	413	static inline void bvec_kunmap_irq(char buffer, unsigned long flags)
1da177e4 LT	414	{
	415	unsigned long ptr = (unsigned long) buffer & PAGE_MASK;
	416
	417	kunmap_atomic((void *) ptr, KM_BIO_SRC_IRQ);
	418	local_irq_restore(*flags);
	419	}
	420
	421	#else
	422	#define bvec_kmap_irq(bvec, flags) (page_address((bvec)->bv_page) + (bvec)->bv_offset)
	423	#define bvec_kunmap_irq(buf, flags) do { *(flags) = 0; } while (0)
	424	#endif
	425
c2d08dad	426	static inline char __bio_kmap_irq(struct bio bio, unsigned short idx,
1da177e4 LT	427	unsigned long *flags)
	428	{
	429	return bvec_kmap_irq(bio_iovec_idx(bio, idx), flags);
	430	}
	431	#define __bio_kunmap_irq(buf, flags) bvec_kunmap_irq(buf, flags)
	432
	433	#define bio_kmap_irq(bio, flags) \
	434	__bio_kmap_irq((bio), (bio)->bi_idx, (flags))
	435	#define bio_kunmap_irq(buf,flags) __bio_kunmap_irq(buf, flags)
	436
7a67f63b JA	437	/*
	438	* Check whether this bio carries any data or not. A NULL bio is allowed.
	439	*/
	440	static inline int bio_has_data(struct bio *bio)
	441	{
	442	return bio && bio->bi_io_vec != NULL;
	443	}
	444
7ba1ba12 MP	445	#if defined(CONFIG_BLK_DEV_INTEGRITY)
	446
	447	#define bip_vec_idx(bip, idx) (&(bip->bip_vec[(idx)]))
	448	#define bip_vec(bip) bip_vec_idx(bip, 0)
	449
	450	#define __bip_for_each_vec(bvl, bip, i, start_idx) \
	451	for (bvl = bip_vec_idx((bip), (start_idx)), i = (start_idx); \
	452	i < (bip)->bip_vcnt; \
	453	bvl++, i++)
	454
	455	#define bip_for_each_vec(bvl, bip, i) \
	456	__bip_for_each_vec(bvl, bip, i, (bip)->bip_idx)
	457
6e2401ad JA	458	static inline int bio_integrity(struct bio *bio)
	459	{
	460	#if defined(CONFIG_BLK_DEV_INTEGRITY)
	461	return bio->bi_integrity != NULL;
	462	#else
	463	return 0;
	464	#endif
	465	}
7ba1ba12 MP	466
	467	extern struct bio_integrity_payload bio_integrity_alloc_bioset(struct bio , gfp_t, unsigned int, struct bio_set *);
	468	extern struct bio_integrity_payload bio_integrity_alloc(struct bio , gfp_t, unsigned int);
	469	extern void bio_integrity_free(struct bio , struct bio_set );
	470	extern int bio_integrity_add_page(struct bio , struct page , unsigned int, unsigned int);
	471	extern int bio_integrity_enabled(struct bio *bio);
	472	extern int bio_integrity_set_tag(struct bio , void , unsigned int);
	473	extern int bio_integrity_get_tag(struct bio , void , unsigned int);
	474	extern int bio_integrity_prep(struct bio *);
	475	extern void bio_integrity_endio(struct bio *, int);
	476	extern void bio_integrity_advance(struct bio *, unsigned int);
	477	extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int);
	478	extern void bio_integrity_split(struct bio , struct bio_pair , int);
	479	extern int bio_integrity_clone(struct bio , struct bio , struct bio_set *);
	480	extern int bioset_integrity_create(struct bio_set *, int);
	481	extern void bioset_integrity_free(struct bio_set *);
	482	extern void bio_integrity_init_slab(void);
	483
	484	#else /* CONFIG_BLK_DEV_INTEGRITY */
	485
	486	#define bio_integrity(a) (0)
	487	#define bioset_integrity_create(a, b) (0)
	488	#define bio_integrity_prep(a) (0)
	489	#define bio_integrity_enabled(a) (0)
	490	#define bio_integrity_clone(a, b, c) (0)
	491	#define bioset_integrity_free(a) do { } while (0)
	492	#define bio_integrity_free(a, b) do { } while (0)
	493	#define bio_integrity_endio(a, b) do { } while (0)
	494	#define bio_integrity_advance(a, b) do { } while (0)
	495	#define bio_integrity_trim(a, b, c) do { } while (0)
	496	#define bio_integrity_split(a, b, c) do { } while (0)
	497	#define bio_integrity_set_tag(a, b, c) do { } while (0)
	498	#define bio_integrity_get_tag(a, b, c) do { } while (0)
	499	#define bio_integrity_init_slab(a) do { } while (0)
	500
	501	#endif /* CONFIG_BLK_DEV_INTEGRITY */
	502
02a5e0ac	503	#endif /* CONFIG_BLOCK */
1da177e4	504	#endif /* __LINUX_BIO_H */