linux_dsm_epyc7002/include/linux/bio.h

657 lines
17 KiB
C
Raw Normal View History

/*
* 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 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_end_sector(bio) ((bio)->bi_sector + bio_sectors((bio)))
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 20:24:41 +07:00
static inline unsigned int bio_cur_bytes(struct bio *bio)
{
if (bio->bi_vcnt)
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 20:24:41 +07:00
return bio_iovec(bio)->bv_len;
else /* dataless requests such as discard */
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 20:24:41 +07:00
return bio->bi_size;
}
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) + \
bio_iovec_idx((bio), (idx))->bv_offset)
#define __bio_kunmap_atomic(addr, kmtype) kunmap_atomic(addr)
/*
* 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)
/* 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)))
#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_ know what
* they're doing
*/
#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++)
/*
* 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_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \
i++)
#define bio_for_each_segment(bvl, bio, i) \
for (i = (bio)->bi_idx; \
bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \
i++)
/*
* 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 */
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 */
unsigned int bip_size;
unsigned short bip_slab; /* slab the bip came from */
unsigned short bip_vcnt; /* # of integrity bio_vecs */
unsigned short bip_idx; /* current bip_vec index */
unsigned bip_owns_buf:1; /* should free bip_buf */
struct work_struct bip_work; /* I/O completion */
struct bio_vec *bip_vec;
struct bio_vec bip_inline_vecs[0];/* embedded bvec array */
};
#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, int first_sectors);
extern void bio_pair_release(struct bio_pair *dbio);
extern struct bio_set *bioset_create(unsigned int, unsigned int);
extern void bioset_free(struct bio_set *);
extern mempool_t *biovec_create_pool(struct bio_set *bs, 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(struct bio *, struct bio *);
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);
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 *);
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 sector_t bio_sector_offset(struct bio *, unsigned short, unsigned int);
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);
#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 *, 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);
block: implement bio_associate_current() IO scheduling and cgroup are tied to the issuing task via io_context and cgroup of %current. Unfortunately, there are cases where IOs need to be routed via a different task which makes scheduling and cgroup limit enforcement applied completely incorrectly. For example, all bios delayed by blk-throttle end up being issued by a delayed work item and get assigned the io_context of the worker task which happens to serve the work item and dumped to the default block cgroup. This is double confusing as bios which aren't delayed end up in the correct cgroup and makes using blk-throttle and cfq propio together impossible. Any code which punts IO issuing to another task is affected which is getting more and more common (e.g. btrfs). As both io_context and cgroup are firmly tied to task including userland visible APIs to manipulate them, it makes a lot of sense to match up tasks to bios. This patch implements bio_associate_current() which associates the specified bio with %current. The bio will record the associated ioc and blkcg at that point and block layer will use the recorded ones regardless of which task actually ends up issuing the bio. bio release puts the associated ioc and blkcg. It grabs and remembers ioc and blkcg instead of the task itself because task may already be dead by the time the bio is issued making ioc and blkcg inaccessible and those are all block layer cares about. elevator_set_req_fn() is updated such that the bio elvdata is being allocated for is available to the elevator. This doesn't update block cgroup policies yet. Further patches will implement the support. -v2: #ifdef CONFIG_BLK_CGROUP added around bio->bi_ioc dereference in rq_ioc() to fix build breakage. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Kent Overstreet <koverstreet@google.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
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 */
#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, 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 bool bio_has_data(struct bio *bio)
{
if (bio && bio->bi_vcnt)
return true;
return false;
}
static inline bool bio_is_rw(struct bio *bio)
{
if (!bio_has_data(bio))
return false;
if (bio->bi_rw & REQ_WRITE_SAME)
return false;
return true;
}
static inline bool bio_mergeable(struct bio *bio)
{
if (bio->bi_rw & REQ_NOMERGE_FLAGS)
return false;
return true;
}
/*
* 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_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
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;
};
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_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)
#define bio_for_each_integrity_vec(_bvl, _bio, _iter) \
for_each_bio(_bio) \
bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
#define bio_integrity(bio) (bio->bi_integrity != NULL)
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 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 *, 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 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;
}
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_split(struct bio *bio, struct bio_pair *bp,
int sectors)
{
return;
}
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;
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */
#endif /* CONFIG_BLOCK */
#endif /* __LINUX_BIO_H */