2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* 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
|
2010-08-03 18:14:58 +07:00
|
|
|
*
|
2005-04-17 05:20:36 +07:00
|
|
|
* 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>
|
2005-06-27 15:55:12 +07:00
|
|
|
#include <linux/ioprio.h>
|
2011-11-24 08:12:59 +07:00
|
|
|
#include <linux/bug.h>
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2007-08-12 03:34:32 +07:00
|
|
|
#ifdef CONFIG_BLOCK
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
#include <asm/io.h>
|
|
|
|
|
2010-08-03 18:14:58 +07:00
|
|
|
/* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */
|
|
|
|
#include <linux/blk_types.h>
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
#define BIO_DEBUG
|
|
|
|
|
|
|
|
#ifdef BIO_DEBUG
|
|
|
|
#define BIO_BUG_ON BUG_ON
|
|
|
|
#else
|
|
|
|
#define BIO_BUG_ON
|
|
|
|
#endif
|
|
|
|
|
2006-06-25 19:49:32 +07:00
|
|
|
#define BIO_MAX_PAGES 256
|
2005-04-17 05:20:36 +07:00
|
|
|
#define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_CACHE_SHIFT)
|
|
|
|
#define BIO_MAX_SECTORS (BIO_MAX_SIZE >> 9)
|
|
|
|
|
2005-06-27 15:55:12 +07:00
|
|
|
/*
|
|
|
|
* 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)
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* various member access, note that bio_data should of course not be used
|
|
|
|
* on highmem page vectors
|
|
|
|
*/
|
2013-08-08 04:26:21 +07:00
|
|
|
#define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx])
|
2013-08-08 04:24:32 +07:00
|
|
|
|
2013-08-08 04:26:21 +07:00
|
|
|
#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)
|
2013-11-24 08:19:00 +07:00
|
|
|
|
2013-09-25 06:26:05 +07:00
|
|
|
#define bio_multiple_segments(bio) \
|
|
|
|
((bio)->bi_iter.bi_size != bio_iovec(bio).bv_len)
|
2013-10-12 05:44:27 +07:00
|
|
|
#define bio_sectors(bio) ((bio)->bi_iter.bi_size >> 9)
|
|
|
|
#define bio_end_sector(bio) ((bio)->bi_iter.bi_sector + bio_sectors((bio)))
|
2007-09-27 18:01:25 +07:00
|
|
|
|
2013-09-25 06:26:05 +07:00
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
}
|
|
|
|
|
2009-05-07 20:24:41 +07:00
|
|
|
static inline unsigned int bio_cur_bytes(struct bio *bio)
|
2007-09-27 18:01:25 +07:00
|
|
|
{
|
2013-09-25 06:26:05 +07:00
|
|
|
if (bio_has_data(bio))
|
2013-08-08 04:24:32 +07:00
|
|
|
return bio_iovec(bio).bv_len;
|
2008-08-06 00:01:53 +07:00
|
|
|
else /* dataless requests such as discard */
|
2013-10-12 05:44:27 +07:00
|
|
|
return bio->bi_iter.bi_size;
|
2007-09-27 18:01:25 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void *bio_data(struct bio *bio)
|
|
|
|
{
|
2013-09-25 06:26:05 +07:00
|
|
|
if (bio_has_data(bio))
|
2007-09-27 18:01:25 +07:00
|
|
|
return page_address(bio_page(bio)) + bio_offset(bio);
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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)
|
|
|
|
*/
|
2013-08-08 04:30:33 +07:00
|
|
|
#define __bio_kmap_atomic(bio, iter) \
|
|
|
|
(kmap_atomic(bio_iter_iovec((bio), (iter)).bv_page) + \
|
|
|
|
bio_iter_iovec((bio), (iter)).bv_offset)
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2013-08-08 04:30:33 +07:00
|
|
|
#define __bio_kunmap_atomic(addr) kunmap_atomic(addr)
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* merge helpers etc
|
|
|
|
*/
|
|
|
|
|
2008-10-29 20:10:51 +07:00
|
|
|
/* Default implementation of BIOVEC_PHYS_MERGEABLE */
|
|
|
|
#define __BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
|
|
|
|
((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* allow arch override, for eg virtualized architectures (put in asm/io.h)
|
|
|
|
*/
|
|
|
|
#ifndef BIOVEC_PHYS_MERGEABLE
|
|
|
|
#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
|
2008-10-29 20:10:51 +07:00
|
|
|
__BIOVEC_PHYS_MERGEABLE(vec1, vec2)
|
2005-04-17 05:20:36 +07:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \
|
|
|
|
(((addr1) | (mask)) == (((addr2) - 1) | (mask)))
|
|
|
|
#define BIOVEC_SEG_BOUNDARY(q, b1, b2) \
|
2009-05-23 04:17:50 +07:00
|
|
|
__BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q)))
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2007-09-27 17:47:43 +07:00
|
|
|
#define bio_io_error(bio) bio_endio((bio), -EIO)
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2013-02-07 03:23:11 +07:00
|
|
|
/*
|
|
|
|
* 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) \
|
2013-08-08 04:30:33 +07:00
|
|
|
for (i = 0, bvl = (bio)->bi_io_vec; i < (bio)->bi_vcnt; i++, bvl++)
|
2013-02-07 03:23:11 +07:00
|
|
|
|
2013-08-08 04:26:21 +07:00
|
|
|
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; \
|
|
|
|
(bvl) = bvec_iter_bvec((bio_vec), (iter)), \
|
|
|
|
(iter).bi_size; \
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2013-11-24 08:19:00 +07:00
|
|
|
#define __bio_for_each_segment(bvl, bio, iter, start) \
|
|
|
|
for (iter = (start); \
|
2013-08-08 04:26:21 +07:00
|
|
|
(iter).bi_size && \
|
|
|
|
((bvl = bio_iter_iovec((bio), (iter))), 1); \
|
|
|
|
bio_advance_iter((bio), &(iter), (bvl).bv_len))
|
2013-11-24 08:19:00 +07:00
|
|
|
|
|
|
|
#define bio_for_each_segment(bvl, bio, iter) \
|
|
|
|
__bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter)
|
|
|
|
|
2013-08-08 04:26:21 +07:00
|
|
|
#define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len)
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2013-09-25 06:26:05 +07:00
|
|
|
static inline unsigned bio_segments(struct bio *bio)
|
|
|
|
{
|
|
|
|
unsigned segs = 0;
|
|
|
|
struct bio_vec bv;
|
|
|
|
struct bvec_iter iter;
|
|
|
|
|
2014-02-11 08:45:50 +07:00
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
|
2013-09-25 06:26:05 +07:00
|
|
|
bio_for_each_segment(bv, bio, iter)
|
|
|
|
segs++;
|
|
|
|
|
|
|
|
return segs;
|
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* 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)
|
|
|
|
|
2008-07-01 01:04:41 +07:00
|
|
|
#if defined(CONFIG_BLK_DEV_INTEGRITY)
|
|
|
|
/*
|
|
|
|
* bio integrity payload
|
|
|
|
*/
|
|
|
|
struct bio_integrity_payload {
|
|
|
|
struct bio *bip_bio; /* parent bio */
|
|
|
|
|
2013-11-24 08:20:16 +07:00
|
|
|
struct bvec_iter bip_iter;
|
2008-07-01 01:04:41 +07:00
|
|
|
|
2013-11-24 08:20:16 +07:00
|
|
|
/* kill - should just use bip_vec */
|
2008-07-01 01:04:41 +07:00
|
|
|
void *bip_buf; /* generated integrity data */
|
|
|
|
|
2013-11-24 08:20:16 +07:00
|
|
|
bio_end_io_t *bip_end_io; /* saved I/O completion fn */
|
2008-07-01 01:04:41 +07:00
|
|
|
|
2009-06-26 20:37:49 +07:00
|
|
|
unsigned short bip_slab; /* slab the bip came from */
|
2008-07-01 01:04:41 +07:00
|
|
|
unsigned short bip_vcnt; /* # of integrity bio_vecs */
|
2012-09-04 23:54:22 +07:00
|
|
|
unsigned bip_owns_buf:1; /* should free bip_buf */
|
2008-07-01 01:04:41 +07:00
|
|
|
|
|
|
|
struct work_struct bip_work; /* I/O completion */
|
2012-10-13 03:18:27 +07:00
|
|
|
|
|
|
|
struct bio_vec *bip_vec;
|
|
|
|
struct bio_vec bip_inline_vecs[0];/* embedded bvec array */
|
2008-07-01 01:04:41 +07:00
|
|
|
};
|
|
|
|
#endif /* CONFIG_BLK_DEV_INTEGRITY */
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2013-08-08 01:14:32 +07:00
|
|
|
extern void bio_trim(struct bio *bio, int offset, int size);
|
2013-11-24 09:21:01 +07:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2008-12-10 21:35:05 +07:00
|
|
|
extern struct bio_set *bioset_create(unsigned int, unsigned int);
|
2005-04-17 05:20:36 +07:00
|
|
|
extern void bioset_free(struct bio_set *);
|
2012-10-13 05:29:33 +07:00
|
|
|
extern mempool_t *biovec_create_pool(struct bio_set *bs, int pool_entries);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2005-10-07 13:46:04 +07:00
|
|
|
extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *);
|
2005-04-17 05:20:36 +07:00
|
|
|
extern void bio_put(struct bio *);
|
|
|
|
|
2013-11-24 09:19:27 +07:00
|
|
|
extern void __bio_clone_fast(struct bio *, struct bio *);
|
|
|
|
extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
|
2012-09-07 05:35:02 +07:00
|
|
|
extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
|
|
|
|
|
2012-09-07 05:35:01 +07:00
|
|
|
extern struct bio_set *fs_bio_set;
|
2014-02-09 20:00:39 +07:00
|
|
|
unsigned int bio_integrity_tag_size(struct bio *bio);
|
2012-09-07 05:35:01 +07:00
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2012-09-07 05:35:02 +07:00
|
|
|
static inline struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
|
|
|
|
{
|
|
|
|
return bio_clone_bioset(bio, gfp_mask, fs_bio_set);
|
|
|
|
}
|
|
|
|
|
2012-09-07 05:35:01 +07:00
|
|
|
static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
|
|
|
|
{
|
|
|
|
return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
|
|
|
|
}
|
|
|
|
|
2012-09-07 05:35:02 +07:00
|
|
|
static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask)
|
|
|
|
{
|
|
|
|
return bio_clone_bioset(bio, gfp_mask, NULL);
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2007-09-27 17:47:43 +07:00
|
|
|
extern void bio_endio(struct bio *, int);
|
2013-11-24 09:34:15 +07:00
|
|
|
extern void bio_endio_nodec(struct bio *, int);
|
2005-04-17 05:20:36 +07:00
|
|
|
struct request_queue;
|
|
|
|
extern int bio_phys_segments(struct request_queue *, struct bio *);
|
|
|
|
|
2012-09-11 04:41:12 +07:00
|
|
|
extern int submit_bio_wait(int rw, struct bio *bio);
|
2012-09-29 03:17:55 +07:00
|
|
|
extern void bio_advance(struct bio *, unsigned);
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
extern void bio_init(struct bio *);
|
2012-09-07 05:34:58 +07:00
|
|
|
extern void bio_reset(struct bio *);
|
2013-11-24 09:34:15 +07:00
|
|
|
void bio_chain(struct bio *, struct bio *);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
|
2005-11-11 18:30:27 +07:00
|
|
|
extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
|
|
|
|
unsigned int, unsigned int);
|
2005-04-17 05:20:36 +07:00
|
|
|
extern int bio_get_nr_vecs(struct block_device *);
|
|
|
|
extern struct bio *bio_map_user(struct request_queue *, struct block_device *,
|
2008-08-28 14:17:05 +07:00
|
|
|
unsigned long, unsigned int, int, gfp_t);
|
2005-06-20 19:06:52 +07:00
|
|
|
struct sg_iovec;
|
2008-08-28 14:17:06 +07:00
|
|
|
struct rq_map_data;
|
2005-06-20 19:06:52 +07:00
|
|
|
extern struct bio *bio_map_user_iov(struct request_queue *,
|
|
|
|
struct block_device *,
|
2008-08-28 14:17:05 +07:00
|
|
|
struct sg_iovec *, int, int, gfp_t);
|
2005-04-17 05:20:36 +07:00
|
|
|
extern void bio_unmap_user(struct bio *);
|
2005-06-20 19:04:44 +07:00
|
|
|
extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
|
2005-10-21 14:20:48 +07:00
|
|
|
gfp_t);
|
2008-04-25 17:47:50 +07:00
|
|
|
extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int,
|
|
|
|
gfp_t, int);
|
2005-04-17 05:20:36 +07:00
|
|
|
extern void bio_set_pages_dirty(struct bio *bio);
|
|
|
|
extern void bio_check_pages_dirty(struct bio *bio);
|
2009-11-26 15:16:19 +07:00
|
|
|
|
|
|
|
#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
|
|
|
|
|
2012-09-11 03:57:51 +07:00
|
|
|
extern void bio_copy_data(struct bio *dst, struct bio *src);
|
2012-09-11 04:03:28 +07:00
|
|
|
extern int bio_alloc_pages(struct bio *bio, gfp_t gfp);
|
2012-09-11 03:57:51 +07:00
|
|
|
|
2008-08-28 14:17:06 +07:00
|
|
|
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 *,
|
2008-08-28 14:17:05 +07:00
|
|
|
int, int, gfp_t);
|
2005-04-17 05:20:36 +07:00
|
|
|
extern int bio_uncopy_user(struct bio *);
|
|
|
|
void zero_fill_bio(struct bio *bio);
|
2012-10-13 05:29:33 +07:00
|
|
|
extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);
|
|
|
|
extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int);
|
2008-07-01 01:04:41 +07:00
|
|
|
extern unsigned int bvec_nr_vecs(unsigned short idx);
|
2008-06-17 23:59:56 +07:00
|
|
|
|
2012-03-06 04:15:27 +07:00
|
|
|
#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 */
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
|
|
/*
|
2009-02-02 18:41:07 +07:00
|
|
|
* remember never ever reenable interrupts between a bvec_kmap_irq and
|
|
|
|
* bvec_kunmap_irq!
|
2005-04-17 05:20:36 +07:00
|
|
|
*/
|
2009-11-02 17:40:16 +07:00
|
|
|
static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
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);
|
2011-11-25 22:14:27 +07:00
|
|
|
addr = (unsigned long) kmap_atomic(bvec->bv_page);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
BUG_ON(addr & ~PAGE_MASK);
|
|
|
|
|
|
|
|
return (char *) addr + bvec->bv_offset;
|
|
|
|
}
|
|
|
|
|
2009-11-02 17:40:16 +07:00
|
|
|
static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
unsigned long ptr = (unsigned long) buffer & PAGE_MASK;
|
|
|
|
|
2011-11-25 22:14:27 +07:00
|
|
|
kunmap_atomic((void *) ptr);
|
2005-04-17 05:20:36 +07:00
|
|
|
local_irq_restore(*flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
#else
|
2010-10-21 15:32:29 +07:00
|
|
|
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;
|
|
|
|
}
|
2005-04-17 05:20:36 +07:00
|
|
|
#endif
|
|
|
|
|
2013-08-08 04:30:33 +07:00
|
|
|
static inline char *__bio_kmap_irq(struct bio *bio, struct bvec_iter iter,
|
2005-04-17 05:20:36 +07:00
|
|
|
unsigned long *flags)
|
|
|
|
{
|
2013-08-08 04:30:33 +07:00
|
|
|
return bvec_kmap_irq(&bio_iter_iovec(bio, iter), flags);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
#define __bio_kunmap_irq(buf, flags) bvec_kunmap_irq(buf, flags)
|
|
|
|
|
|
|
|
#define bio_kmap_irq(bio, flags) \
|
2013-08-08 04:30:33 +07:00
|
|
|
__bio_kmap_irq((bio), (bio)->bi_iter, (flags))
|
2005-04-17 05:20:36 +07:00
|
|
|
#define bio_kunmap_irq(buf,flags) __bio_kunmap_irq(buf, flags)
|
|
|
|
|
2009-04-08 00:55:13 +07:00
|
|
|
/*
|
2009-04-17 13:41:21 +07:00
|
|
|
* BIO list management for use by remapping drivers (e.g. DM or MD) and loop.
|
2009-04-08 00:55:13 +07:00
|
|
|
*
|
|
|
|
* 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;
|
|
|
|
}
|
|
|
|
|
blk-mq: new multi-queue block IO queueing mechanism
Linux currently has two models for block devices:
- The classic request_fn based approach, where drivers use struct
request units for IO. The block layer provides various helper
functionalities to let drivers share code, things like tag
management, timeout handling, queueing, etc.
- The "stacked" approach, where a driver squeezes in between the
block layer and IO submitter. Since this bypasses the IO stack,
driver generally have to manage everything themselves.
With drivers being written for new high IOPS devices, the classic
request_fn based driver doesn't work well enough. The design dates
back to when both SMP and high IOPS was rare. It has problems with
scaling to bigger machines, and runs into scaling issues even on
smaller machines when you have IOPS in the hundreds of thousands
per device.
The stacked approach is then most often selected as the model
for the driver. But this means that everybody has to re-invent
everything, and along with that we get all the problems again
that the shared approach solved.
This commit introduces blk-mq, block multi queue support. The
design is centered around per-cpu queues for queueing IO, which
then funnel down into x number of hardware submission queues.
We might have a 1:1 mapping between the two, or it might be
an N:M mapping. That all depends on what the hardware supports.
blk-mq provides various helper functions, which include:
- Scalable support for request tagging. Most devices need to
be able to uniquely identify a request both in the driver and
to the hardware. The tagging uses per-cpu caches for freed
tags, to enable cache hot reuse.
- Timeout handling without tracking request on a per-device
basis. Basically the driver should be able to get a notification,
if a request happens to fail.
- Optional support for non 1:1 mappings between issue and
submission queues. blk-mq can redirect IO completions to the
desired location.
- Support for per-request payloads. Drivers almost always need
to associate a request structure with some driver private
command structure. Drivers can tell blk-mq this at init time,
and then any request handed to the driver will have the
required size of memory associated with it.
- Support for merging of IO, and plugging. The stacked model
gets neither of these. Even for high IOPS devices, merging
sequential IO reduces per-command overhead and thus
increases bandwidth.
For now, this is provided as a potential 3rd queueing model, with
the hope being that, as it matures, it can replace both the classic
and stacked model. That would get us back to having just 1 real
model for block devices, leaving the stacked approach to dm/md
devices (as it was originally intended).
Contributions in this patch from the following people:
Shaohua Li <shli@fusionio.com>
Alexander Gordeev <agordeev@redhat.com>
Christoph Hellwig <hch@infradead.org>
Mike Christie <michaelc@cs.wisc.edu>
Matias Bjorling <m@bjorling.me>
Jeff Moyer <jmoyer@redhat.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-24 15:20:05 +07:00
|
|
|
#define BIO_EMPTY_LIST { NULL, NULL }
|
|
|
|
|
2009-04-08 00:55:13 +07:00
|
|
|
#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;
|
|
|
|
}
|
|
|
|
|
2009-06-10 11:38:40 +07:00
|
|
|
static inline struct bio *bio_list_peek(struct bio_list *bl)
|
|
|
|
{
|
|
|
|
return bl->head;
|
|
|
|
}
|
|
|
|
|
2009-04-08 00:55:13 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2012-08-24 18:56:11 +07:00
|
|
|
/*
|
|
|
|
* 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;
|
2012-10-13 05:29:33 +07:00
|
|
|
mempool_t *bvec_pool;
|
2012-08-24 18:56:11 +07:00
|
|
|
#if defined(CONFIG_BLK_DEV_INTEGRITY)
|
|
|
|
mempool_t *bio_integrity_pool;
|
2012-10-13 05:29:33 +07:00
|
|
|
mempool_t *bvec_integrity_pool;
|
2012-08-24 18:56:11 +07:00
|
|
|
#endif
|
block: Avoid deadlocks with bio allocation by stacking drivers
Previously, if we ever try to allocate more than once from the same bio
set while running under generic_make_request() (i.e. a stacking block
driver), we risk deadlock.
This is because of the code in generic_make_request() that converts
recursion to iteration; any bios we submit won't actually be submitted
(so they can complete and eventually be freed) until after we return -
this means if we allocate a second bio, we're blocking the first one
from ever being freed.
Thus if enough threads call into a stacking block driver at the same
time with bios that need multiple splits, and the bio_set's reserve gets
used up, we deadlock.
This can be worked around in the driver code - we could check if we're
running under generic_make_request(), then mask out __GFP_WAIT when we
go to allocate a bio, and if the allocation fails punt to workqueue and
retry the allocation.
But this is tricky and not a generic solution. This patch solves it for
all users by inverting the previously described technique. We allocate a
rescuer workqueue for each bio_set, and then in the allocation code if
there are bios on current->bio_list we would be blocking, we punt them
to the rescuer workqueue to be submitted.
This guarantees forward progress for bio allocations under
generic_make_request() provided each bio is submitted before allocating
the next, and provided the bios are freed after they complete.
Note that this doesn't do anything for allocation from other mempools.
Instead of allocating per bio data structures from a mempool, code
should use bio_set's front_pad.
Tested it by forcing the rescue codepath to be taken (by disabling the
first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot
of arbitrary bio splitting) and verified that the rescuer was being
invoked.
Signed-off-by: Kent Overstreet <koverstreet@google.com>
CC: Jens Axboe <axboe@kernel.dk>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-11 04:33:46 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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;
|
2012-08-24 18:56:11 +07:00
|
|
|
};
|
|
|
|
|
|
|
|
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
|
|
|
|
|
2008-07-01 01:04:41 +07:00
|
|
|
#if defined(CONFIG_BLK_DEV_INTEGRITY)
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-11-24 08:20:16 +07:00
|
|
|
#define bip_vec_idx(bip, idx) (&(bip->bip_vec[(idx)]))
|
|
|
|
|
|
|
|
#define bip_for_each_vec(bvl, bip, iter) \
|
|
|
|
for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter)
|
2008-07-01 01:04:41 +07:00
|
|
|
|
2010-09-11 01:50:10 +07:00
|
|
|
#define bio_for_each_integrity_vec(_bvl, _bio, _iter) \
|
|
|
|
for_each_bio(_bio) \
|
|
|
|
bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
|
|
|
|
|
2008-10-02 17:46:53 +07:00
|
|
|
#define bio_integrity(bio) (bio->bi_integrity != NULL)
|
2008-07-01 01:04:41 +07:00
|
|
|
|
|
|
|
extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
|
2012-09-07 05:34:56 +07:00
|
|
|
extern void bio_integrity_free(struct bio *);
|
2008-07-01 01:04:41 +07:00
|
|
|
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);
|
2012-09-07 05:34:56 +07:00
|
|
|
extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t);
|
2009-06-26 20:37:49 +07:00
|
|
|
extern int bioset_integrity_create(struct bio_set *, int);
|
|
|
|
extern void bioset_integrity_free(struct bio_set *);
|
|
|
|
extern void bio_integrity_init(void);
|
2008-07-01 01:04:41 +07:00
|
|
|
|
|
|
|
#else /* CONFIG_BLK_DEV_INTEGRITY */
|
|
|
|
|
2012-01-13 14:15:33 +07:00
|
|
|
static inline int bio_integrity(struct bio *bio)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int bio_integrity_enabled(struct bio *bio)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2012-09-07 05:34:56 +07:00
|
|
|
static inline void bio_integrity_free(struct bio *bio)
|
2012-01-13 14:15:33 +07:00
|
|
|
{
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2011-11-16 15:21:48 +07:00
|
|
|
static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
|
2012-09-07 05:34:56 +07:00
|
|
|
gfp_t gfp_mask)
|
2011-11-16 15:21:48 +07:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2012-01-13 14:15:33 +07:00
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
2008-07-01 01:04:41 +07:00
|
|
|
|
|
|
|
#endif /* CONFIG_BLK_DEV_INTEGRITY */
|
|
|
|
|
2007-08-12 03:34:32 +07:00
|
|
|
#endif /* CONFIG_BLOCK */
|
2005-04-17 05:20:36 +07:00
|
|
|
#endif /* __LINUX_BIO_H */
|