linux/block/blk.h
Tejun Heo 2e46e8b27a 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>
2009-05-11 09:50:54 +02:00

165 lines
4.3 KiB
C

#ifndef BLK_INTERNAL_H
#define BLK_INTERNAL_H
/* Amount of time in which a process may batch requests */
#define BLK_BATCH_TIME (HZ/50UL)
/* Number of requests a "batching" process may submit */
#define BLK_BATCH_REQ 32
extern struct kmem_cache *blk_requestq_cachep;
extern struct kobj_type blk_queue_ktype;
void init_request_from_bio(struct request *req, struct bio *bio);
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio);
void __blk_queue_free_tags(struct request_queue *q);
void blk_unplug_work(struct work_struct *work);
void blk_unplug_timeout(unsigned long data);
void blk_rq_timed_out_timer(unsigned long data);
void blk_delete_timer(struct request *);
void blk_add_timer(struct request *);
void __generic_unplug_device(struct request_queue *);
/*
* Internal atomic flags for request handling
*/
enum rq_atomic_flags {
REQ_ATOM_COMPLETE = 0,
};
/*
* EH timer and IO completion will both attempt to 'grab' the request, make
* sure that only one of them suceeds
*/
static inline int blk_mark_rq_complete(struct request *rq)
{
return test_and_set_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
}
static inline void blk_clear_rq_complete(struct request *rq)
{
clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
}
/*
* Internal elevator interface
*/
#define ELV_ON_HASH(rq) (!hlist_unhashed(&(rq)->hash))
static inline struct request *__elv_next_request(struct request_queue *q)
{
struct request *rq;
while (1) {
while (!list_empty(&q->queue_head)) {
rq = list_entry_rq(q->queue_head.next);
if (blk_do_ordered(q, &rq))
return rq;
}
if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
return NULL;
}
}
static inline void elv_activate_rq(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->ops->elevator_activate_req_fn)
e->ops->elevator_activate_req_fn(q, rq);
}
static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->ops->elevator_deactivate_req_fn)
e->ops->elevator_deactivate_req_fn(q, rq);
}
#ifdef CONFIG_FAIL_IO_TIMEOUT
int blk_should_fake_timeout(struct request_queue *);
ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
ssize_t part_timeout_store(struct device *, struct device_attribute *,
const char *, size_t);
#else
static inline int blk_should_fake_timeout(struct request_queue *q)
{
return 0;
}
#endif
struct io_context *current_io_context(gfp_t gfp_flags, int node);
int ll_back_merge_fn(struct request_queue *q, struct request *req,
struct bio *bio);
int ll_front_merge_fn(struct request_queue *q, struct request *req,
struct bio *bio);
int attempt_back_merge(struct request_queue *q, struct request *rq);
int attempt_front_merge(struct request_queue *q, struct request *rq);
void blk_recalc_rq_segments(struct request *rq);
void blk_queue_congestion_threshold(struct request_queue *q);
int blk_dev_init(void);
void elv_quiesce_start(struct request_queue *q);
void elv_quiesce_end(struct request_queue *q);
/*
* Return the threshold (number of used requests) at which the queue is
* considered to be congested. It include a little hysteresis to keep the
* context switch rate down.
*/
static inline int queue_congestion_on_threshold(struct request_queue *q)
{
return q->nr_congestion_on;
}
/*
* The threshold at which a queue is considered to be uncongested
*/
static inline int queue_congestion_off_threshold(struct request_queue *q)
{
return q->nr_congestion_off;
}
#if defined(CONFIG_BLK_DEV_INTEGRITY)
#define rq_for_each_integrity_segment(bvl, _rq, _iter) \
__rq_for_each_bio(_iter.bio, _rq) \
bip_for_each_vec(bvl, _iter.bio->bi_integrity, _iter.i)
#endif /* BLK_DEV_INTEGRITY */
static inline int blk_cpu_to_group(int cpu)
{
#ifdef CONFIG_SCHED_MC
const struct cpumask *mask = cpu_coregroup_mask(cpu);
return cpumask_first(mask);
#elif defined(CONFIG_SCHED_SMT)
return cpumask_first(topology_thread_cpumask(cpu));
#else
return cpu;
#endif
}
/*
* Contribute to IO statistics IFF:
*
* a) it's attached to a gendisk, and
* b) the queue had IO stats enabled when this request was started, and
* c) it's a file system request
*/
static inline int blk_do_io_stat(struct request *rq)
{
return rq->rq_disk && blk_rq_io_stat(rq) && blk_fs_request(rq) &&
blk_discard_rq(rq);
}
#endif