![Tejun Heo](/assets/img/avatar_default.png)
Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
166 lines
4.3 KiB
C
166 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_dequeue_request(struct request *rq);
|
|
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
|