- 根目录:
- 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>
#include <linux/bug.h>
#ifdef CONFIG_BLOCK
#include <asm/io.h>
/* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */
#include <linux/blk_types.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)
/*
* 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 __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx])
#define bvec_iter_page(bvec, iter) \
(__bvec_iter_bvec((bvec), (iter))->bv_page)
#define bvec_iter_len(bvec, iter) \
min((iter).bi_size, \
__bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done)
#define bvec_iter_offset(bvec, iter) \
(__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done)
#define bvec_iter_bvec(bvec, iter) \
((struct bio_vec) { \
.bv_page = bvec_iter_page((bvec), (iter)), \
.bv_len = bvec_iter_len((bvec), (iter)), \
.bv_offset = bvec_iter_offset((bvec), (iter)), \
})
#define bio_iter_iovec(bio, iter) \
bvec_iter_bvec((bio)->bi_io_vec, (iter))
#define bio_iter_page(bio, iter) \
bvec_iter_page((bio)->bi_io_vec, (iter))
#define bio_iter_len(bio, iter) \
bvec_iter_len((bio)->bi_io_vec, (iter))
#define bio_iter_offset(bio, iter) \
bvec_iter_offset((bio)->bi_io_vec, (iter))
#define bio_page(bio) bio_iter_page((bio), (bio)->bi_iter)
#define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter)
#define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter)
#define bio_multiple_segments(bio) \
((bio)->bi_iter.bi_size != bio_iovec(bio).bv_len)
#define bio_sectors(bio) ((bio)->bi_iter.bi_size >> 9)
#define bio_end_sector(bio) ((bio)->bi_iter.bi_sector + bio_sectors((bio)))
/*
* Check whether this bio carries any data or not. A NULL bio is allowed.
*/
static inline bool bio_has_data(struct bio *bio)
{
if (bio &&
bio->bi_iter.bi_size &&
!(bio->bi_rw & REQ_DISCARD))
return true;
return false;
}
static inline bool bio_is_rw(struct bio *bio)
{
if (!bio_has_data(bio))
return false;
if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK)
return false;
return true;
}
static inline bool bio_mergeable(struct bio *bio)
{
if (bio->bi_rw & REQ_NOMERGE_FLAGS)
return false;
return true;
}
static inline unsigned int bio_cur_bytes(struct bio *bio)
{
if (bio_has_data(bio))
return bio_iovec(bio).bv_len;
else /* dataless requests such as discard */
return bio->bi_iter.bi_size;
}
static inline void *bio_data(struct bio *bio)
{
if (bio_has_data(bio))
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, iter) \
(kmap_atomic(bio_iter_iovec((bio), (iter)).bv_page) + \
bio_iter_iovec((bio), (iter)).bv_offset)
#define __bio_kunmap_atomic(addr) kunmap_atomic(addr)
/*
* merge helpers etc
*/
/* Default implementation of BIOVEC_PHYS_MERGEABLE */
#define __BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
/*
* allow arch override, for eg virtualized architectures (put in asm/io.h)
*/
#ifndef BIOVEC_PHYS_MERGEABLE
#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
__BIOVEC_PHYS_MERGEABLE(vec1, 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, queue_segment_boundary((q)))
/*
* Check if adding a bio_vec after bprv with offset would create a gap in
* the SG list. Most drivers don't care about this, but some do.
*/
static inline bool bvec_gap_to_prev(struct bio_vec *bprv, unsigned int offset)
{
return offset || ((bprv->bv_offset + bprv->bv_len) & (PAGE_SIZE - 1));
}
#define bio_io_error(bio) bio_endio((bio), -EIO)
/*
* drivers should _never_ use the all version - the bio may have been split
* before it got to the driver and the driver won't own all of it
*/
#define bio_for_each_segment_all(bvl, bio, i) \
for (i = 0, bvl = (bio)->bi_io_vec; i < (bio)->bi_vcnt; i++, bvl++)
static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter,
unsigned bytes)
{
WARN_ONCE(bytes > iter->bi_size,
"Attempted to advance past end of bvec iter\n");
while (bytes) {
unsigned len = min(bytes, bvec_iter_len(bv, *iter));
bytes -= len;
iter->bi_size -= len;
iter->bi_bvec_done += len;
if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) {
iter->bi_bvec_done = 0;
iter->bi_idx++;
}
}
}
#define for_each_bvec(bvl, bio_vec, iter, start) \
for (iter = (start); \
(iter).bi_size && \
((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \
bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter,
unsigned bytes)
{
iter->bi_sector += bytes >> 9;
if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK)
iter->bi_size -= bytes;
else
bvec_iter_advance(bio->bi_io_vec, iter, bytes);
}
#define __bio_for_each_segment(bvl, bio, iter, start) \
for (iter = (start); \
(iter).bi_size && \
((bvl = bio_iter_iovec((bio), (iter))), 1); \
bio_advance_iter((bio), &(iter), (bvl).bv_len))
#define bio_for_each_segment(bvl, bio, iter) \
__bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter)
#define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len)
static inline unsigned bio_segments(struct bio *bio)
{
unsigned segs = 0;
struct bio_vec bv;
struct bvec_iter iter;
/*
* We special case discard/write same, because they interpret bi_size
* differently:
*/
if (bio->bi_rw & REQ_DISCARD)
return 1;
if (bio->bi_rw & REQ_WRITE_SAME)
return 1;
bio_for_each_segment(bv, bio, iter)
segs++;
return segs;
}
/*
* 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)
enum bip_flags {
BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */
BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */
BIP_CTRL_NOCHECK = 1 << 2, /* disable HBA integrity checking */
BIP_DISK_NOCHECK = 1 << 3, /* disable disk integrity checking */
BIP_IP_CHECKSUM = 1 << 4, /* IP checksum */
};
#if defined(CONFIG_BLK_DEV_INTEGRITY)
static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
{
if (bio->bi_rw & REQ_INTEGRITY)
return bio->bi_integrity;
return NULL;
}
/*
* bio integrity payload
*/
struct bio_integrity_payload {
struct bio *bip_bio; /* parent bio */
struct bvec_iter bip_iter;
bio_end_io_t *bip_end_io; /* saved I/O completion fn */
unsigned short bip_slab; /* slab the bip came from */
unsigned short bip_vcnt; /* # of integrity bio_vecs */
unsigned short bip_max_vcnt; /* integrity bio_vec slots */
unsigned short bip_flags; /* control flags */
struct work_struct bip_work; /* I/O completion */
struct bio_vec *bip_vec;
struct bio_vec bip_inline_vecs[0];/* embedded bvec array */
};
static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
{
struct bio_integrity_payload *bip = bio_integrity(bio);
if (bip)
return bip->bip_flags & flag;
return false;
}
static inline sector_t bip_get_seed(struct bio_integrity_payload *bip)
{
return bip->bip_iter.bi_sector;
}
static inline void bip_set_seed(struct bio_integrity_payload *bip,
sector_t seed)
{
bip->bip_iter.bi_sector = seed;
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */
extern void bio_trim(struct bio *bio, int offset, int size);
extern struct bio *bio_split(struct bio *bio, int sectors,
gfp_t gfp, struct bio_set *bs);
/**
* bio_next_split - get next @sectors from a bio, splitting if necessary
* @bio: bio to split
* @sectors: number of sectors to split from the front of @bio
* @gfp: gfp mask
* @bs: bio set to allocate from
*
* Returns a bio representing the next @sectors of @bio - if the bio is smaller
* than @sectors, returns the original bio unchanged.
*/
static inline struct bio *bio_next_split(struct bio *bio, int sectors,
gfp_t gfp, struct bio_set *bs)
{
if (sectors >= bio_sectors(bio))
return bio;
return bio_split(bio, sectors, gfp, bs);
}
extern struct bio_set *bioset_create(unsigned int, unsigned int);
extern struct bio_set *bioset_create_nobvec(unsigned int, unsigned int);
extern void bioset_free(struct bio_set *);
extern mempool_t *biovec_create_pool(int pool_entries);
extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *);
extern void bio_put(struct bio *);
extern void __bio_clone_fast(struct bio *, struct bio *);
extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
extern struct bio_set *fs_bio_set;
static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
{
return bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
}
static inline struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
{
return bio_clone_bioset(bio, gfp_mask, fs_bio_set);
}
static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
{
return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
}
static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask)
{
return bio_clone_bioset(bio, gfp_mask, NULL);
}
extern void bio_endio(struct bio *, int);
extern void bio_endio_nodec(struct bio *, int);
struct request_queue;
extern int bio_phys_segments(struct request_queue *, struct bio *);
extern int submit_bio_wait(int rw, struct bio *bio);
extern void bio_advance(struct bio *, unsigned);
extern void bio_init(struct bio *);
extern void bio_reset(struct bio *);
void bio_chain(struct bio *, 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 *,
const 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);
#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
#endif
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
extern void bio_flush_dcache_pages(struct bio *bi);
#else
static inline void bio_flush_dcache_pages(struct bio *bi)
{
}
#endif
extern void bio_copy_data(struct bio *dst, struct bio *src);
extern int bio_alloc_pages(struct bio *bio, gfp_t gfp);
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 *,
const 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(gfp_t, int, unsigned long *, mempool_t *);
extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int);
extern unsigned int bvec_nr_vecs(unsigned short idx);
#ifdef CONFIG_BLK_CGROUP
int bio_associate_current(struct bio *bio);
void bio_disassociate_task(struct bio *bio);
#else /* CONFIG_BLK_CGROUP */
static inline int bio_associate_current(struct bio *bio) { return -ENOENT; }
static inline void bio_disassociate_task(struct bio *bio) { }
#endif /* CONFIG_BLK_CGROUP */
#ifdef CONFIG_HIGHMEM
/*
* remember never ever reenable interrupts between a bvec_kmap_irq and
* bvec_kunmap_irq!
*/
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);
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);
local_irq_restore(*flags);
}
#else
static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags)
{
return page_address(bvec->bv_page) + bvec->bv_offset;
}
static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags)
{
*flags = 0;
}
#endif
static inline char *__bio_kmap_irq(struct bio *bio, struct bvec_iter iter,
unsigned long *flags)
{
return bvec_kmap_irq(&bio_iter_iovec(bio, iter), flags);
}
#define __bio_kunmap_irq(buf, flags) bvec_kunmap_irq(buf, flags)
#define bio_kmap_irq(bio, flags) \
__bio_kmap_irq((bio), (bio)->bi_iter, (flags))
#define bio_kunmap_irq(buf,flags) __bio_kunmap_irq(buf, flags)
/*
* BIO list management for use by remapping drivers (e.g. DM or MD) and loop.
*
* A bio_list anchors a singly-linked list of bios chained through the bi_next
* member of the bio. The bio_list also caches the last list member to allow
* fast access to the tail.
*/
struct bio_list {
struct bio *head;
struct bio *tail;
};
static inline int bio_list_empty(const struct bio_list *bl)
{
return bl->head == NULL;
}
static inline void bio_list_init(struct bio_list *bl)
{
bl->head = bl->tail = NULL;
}
#define BIO_EMPTY_LIST { NULL, NULL }
#define bio_list_for_each(bio, bl) \
for (bio = (bl)->head; bio; bio = bio->bi_next)
static inline unsigned bio_list_size(const struct bio_list *bl)
{
unsigned sz = 0;
struct bio *bio;
bio_list_for_each(bio, bl)
sz++;
return sz;
}
static inline void bio_list_add(struct bio_list *bl, struct bio *bio)
{
bio->bi_next = NULL;
if (bl->tail)
bl->tail->bi_next = bio;
else
bl->head = bio;
bl->tail = bio;
}
static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio)
{
bio->bi_next = bl->head;
bl->head = bio;
if (!bl->tail)
bl->tail = bio;
}
static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2)
{
if (!bl2->head)
return;
if (bl->tail)
bl->tail->bi_next = bl2->head;
else
bl->head = bl2->head;
bl->tail = bl2->tail;
}
static inline void bio_list_merge_head(struct bio_list *bl,
struct bio_list *bl2)
{
if (!bl2->head)
return;
if (bl->head)
bl2->tail->bi_next = bl->head;
else
bl->tail = bl2->tail;
bl->head = bl2->head;
}
static inline struct bio *bio_list_peek(struct bio_list *bl)
{
return bl->head;
}
static inline struct bio *bio_list_pop(struct bio_list *bl)
{
struct bio *bio = bl->head;
if (bio) {
bl->head = bl->head->bi_next;
if (!bl->head)
bl->tail = NULL;
bio->bi_next = NULL;
}
return bio;
}
static inline struct bio *bio_list_get(struct bio_list *bl)
{
struct bio *bio = bl->head;
bl->head = bl->tail = NULL;
return bio;
}
/*
* 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
#define BIOVEC_MAX_IDX (BIOVEC_NR_POOLS - 1)
struct bio_set {
struct kmem_cache *bio_slab;
unsigned int front_pad;
mempool_t *bio_pool;
mempool_t *bvec_pool;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
mempool_t *bio_integrity_pool;
mempool_t *bvec_integrity_pool;
#endif
/*
* Deadlock avoidance for stacking block drivers: see comments in
* bio_alloc_bioset() for details
*/
spinlock_t rescue_lock;
struct bio_list rescue_list;
struct work_struct rescue_work;
struct workqueue_struct *rescue_workqueue;
};
struct biovec_slab {
int nr_vecs;
char *name;
struct kmem_cache *slab;
};
/*
* a small number of entries is fine, not going to be performance critical.
* basically we just need to survive
*/
#define BIO_SPLIT_ENTRIES 2
#if defined(CONFIG_BLK_DEV_INTEGRITY)
#define bip_for_each_vec(bvl, bip, iter) \
for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter)
#define bio_for_each_integrity_vec(_bvl, _bio, _iter) \
for_each_bio(_bio) \
bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
extern void bio_integrity_free(struct bio *);
extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
extern bool bio_integrity_enabled(struct bio *bio);
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 int bio_integrity_clone(struct bio *, struct bio *, gfp_t);
extern int bioset_integrity_create(struct bio_set *, int);
extern void bioset_integrity_free(struct bio_set *);
extern void bio_integrity_init(void);
#else /* CONFIG_BLK_DEV_INTEGRITY */
static inline void *bio_integrity(struct bio *bio)
{
return NULL;
}
static inline bool bio_integrity_enabled(struct bio *bio)
{
return false;
}
static inline int bioset_integrity_create(struct bio_set *bs, int pool_size)
{
return 0;
}
static inline void bioset_integrity_free (struct bio_set *bs)
{
return;
}
static inline int bio_integrity_prep(struct bio *bio)
{
return 0;
}
static inline void bio_integrity_free(struct bio *bio)
{
return;
}
static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
gfp_t gfp_mask)
{
return 0;
}
static inline void bio_integrity_advance(struct bio *bio,
unsigned int bytes_done)
{
return;
}
static inline void bio_integrity_trim(struct bio *bio, unsigned int offset,
unsigned int sectors)
{
return;
}
static inline void bio_integrity_init(void)
{
return;
}
static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
{
return false;
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */
#endif /* CONFIG_BLOCK */
#endif /* __LINUX_BIO_H */