linux/block/elevator.c

1121 lines
24 KiB
C
Raw Normal View History

/*
* Block device elevator/IO-scheduler.
*
* Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
*
* 30042000 Jens Axboe <axboe@kernel.dk> :
*
* Split the elevator a bit so that it is possible to choose a different
* one or even write a new "plug in". There are three pieces:
* - elevator_fn, inserts a new request in the queue list
* - elevator_merge_fn, decides whether a new buffer can be merged with
* an existing request
* - elevator_dequeue_fn, called when a request is taken off the active list
*
* 20082000 Dave Jones <davej@suse.de> :
* Removed tests for max-bomb-segments, which was breaking elvtune
* when run without -bN
*
* Jens:
* - Rework again to work with bio instead of buffer_heads
* - loose bi_dev comparisons, partition handling is right now
* - completely modularize elevator setup and teardown
*
*/
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/delay.h>
#include <linux/blktrace_api.h>
#include <linux/hash.h>
#include <linux/uaccess.h>
tracing/events: convert block trace points to TRACE_EVENT() TRACE_EVENT is a more generic way to define tracepoints. Doing so adds these new capabilities to this tracepoint: - zero-copy and per-cpu splice() tracing - binary tracing without printf overhead - structured logging records exposed under /debug/tracing/events - trace events embedded in function tracer output and other plugins - user-defined, per tracepoint filter expressions ... Cons: - no dev_t info for the output of plug, unplug_timer and unplug_io events. no dev_t info for getrq and sleeprq events if bio == NULL. no dev_t info for rq_abort,...,rq_requeue events if rq->rq_disk == NULL. This is mainly because we can't get the deivce from a request queue. But this may change in the future. - A packet command is converted to a string in TP_assign, not TP_print. While blktrace do the convertion just before output. Since pc requests should be rather rare, this is not a big issue. - In blktrace, an event can have 2 different print formats, but a TRACE_EVENT has a unique format, which means we have some unused data in a trace entry. The overhead is minimized by using __dynamic_array() instead of __array(). I've benchmarked the ioctl blktrace vs the splice based TRACE_EVENT tracing: dd dd + ioctl blktrace dd + TRACE_EVENT (splice) 1 7.36s, 42.7 MB/s 7.50s, 42.0 MB/s 7.41s, 42.5 MB/s 2 7.43s, 42.3 MB/s 7.48s, 42.1 MB/s 7.43s, 42.4 MB/s 3 7.38s, 42.6 MB/s 7.45s, 42.2 MB/s 7.41s, 42.5 MB/s So the overhead of tracing is very small, and no regression when using those trace events vs blktrace. And the binary output of TRACE_EVENT is much smaller than blktrace: # ls -l -h -rw-r--r-- 1 root root 8.8M 06-09 13:24 sda.blktrace.0 -rw-r--r-- 1 root root 195K 06-09 13:24 sda.blktrace.1 -rw-r--r-- 1 root root 2.7M 06-09 13:25 trace_splice.out Following are some comparisons between TRACE_EVENT and blktrace: plug: kjournald-480 [000] 303.084981: block_plug: [kjournald] kjournald-480 [000] 303.084981: 8,0 P N [kjournald] unplug_io: kblockd/0-118 [000] 300.052973: block_unplug_io: [kblockd/0] 1 kblockd/0-118 [000] 300.052974: 8,0 U N [kblockd/0] 1 remap: kjournald-480 [000] 303.085042: block_remap: 8,0 W 102736992 + 8 <- (8,8) 33384 kjournald-480 [000] 303.085043: 8,0 A W 102736992 + 8 <- (8,8) 33384 bio_backmerge: kjournald-480 [000] 303.085086: block_bio_backmerge: 8,0 W 102737032 + 8 [kjournald] kjournald-480 [000] 303.085086: 8,0 M W 102737032 + 8 [kjournald] getrq: kjournald-480 [000] 303.084974: block_getrq: 8,0 W 102736984 + 8 [kjournald] kjournald-480 [000] 303.084975: 8,0 G W 102736984 + 8 [kjournald] bash-2066 [001] 1072.953770: 8,0 G N [bash] bash-2066 [001] 1072.953773: block_getrq: 0,0 N 0 + 0 [bash] rq_complete: konsole-2065 [001] 300.053184: block_rq_complete: 8,0 W () 103669040 + 16 [0] konsole-2065 [001] 300.053191: 8,0 C W 103669040 + 16 [0] ksoftirqd/1-7 [001] 1072.953811: 8,0 C N (5a 00 08 00 00 00 00 00 24 00) [0] ksoftirqd/1-7 [001] 1072.953813: block_rq_complete: 0,0 N (5a 00 08 00 00 00 00 00 24 00) 0 + 0 [0] rq_insert: kjournald-480 [000] 303.084985: block_rq_insert: 8,0 W 0 () 102736984 + 8 [kjournald] kjournald-480 [000] 303.084986: 8,0 I W 102736984 + 8 [kjournald] Changelog from v2 -> v3: - use the newly introduced __dynamic_array(). Changelog from v1 -> v2: - use __string() instead of __array() to minimize the memory required to store hex dump of rq->cmd(). - support large pc requests. - add missing blk_fill_rwbs_rq() in block_rq_requeue TRACE_EVENT. - some cleanups. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> LKML-Reference: <4A2DF669.5070905@cn.fujitsu.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-09 07:43:05 +02:00
#include <trace/events/block.h>
#include "blk.h"
static DEFINE_SPINLOCK(elv_list_lock);
static LIST_HEAD(elv_list);
/*
* Merge hash stuff.
*/
static const int elv_hash_shift = 6;
#define ELV_HASH_BLOCK(sec) ((sec) >> 3)
#define ELV_HASH_FN(sec) \
(hash_long(ELV_HASH_BLOCK((sec)), elv_hash_shift))
#define ELV_HASH_ENTRIES (1 << elv_hash_shift)
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:39 +02:00
#define rq_hash_key(rq) (blk_rq_pos(rq) + blk_rq_sectors(rq))
/*
* Query io scheduler to see if the current process issuing bio may be
* merged with rq.
*/
static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
{
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
if (e->ops->elevator_allow_merge_fn)
return e->ops->elevator_allow_merge_fn(q, rq, bio);
return 1;
}
/*
* can we safely merge with this request?
*/
int elv_rq_merge_ok(struct request *rq, struct bio *bio)
{
if (!rq_mergeable(rq))
return 0;
/*
* Don't merge file system requests and discard requests
*/
if (bio_rw_flagged(bio, BIO_RW_DISCARD) !=
bio_rw_flagged(rq->bio, BIO_RW_DISCARD))
return 0;
/*
* different data direction or already started, don't merge
*/
if (bio_data_dir(bio) != rq_data_dir(rq))
return 0;
/*
* must be same device and not a special request
*/
if (rq->rq_disk != bio->bi_bdev->bd_disk || rq->special)
return 0;
/*
* only merge integrity protected bio into ditto rq
*/
if (bio_integrity(bio) != blk_integrity_rq(rq))
return 0;
if (!elv_iosched_allow_merge(rq, bio))
return 0;
return 1;
}
EXPORT_SYMBOL(elv_rq_merge_ok);
static inline int elv_try_merge(struct request *__rq, struct bio *bio)
{
int ret = ELEVATOR_NO_MERGE;
/*
* we can merge and sequence is ok, check if it's possible
*/
if (elv_rq_merge_ok(__rq, bio)) {
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:39 +02:00
if (blk_rq_pos(__rq) + blk_rq_sectors(__rq) == bio->bi_sector)
ret = ELEVATOR_BACK_MERGE;
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:39 +02:00
else if (blk_rq_pos(__rq) - bio_sectors(bio) == bio->bi_sector)
ret = ELEVATOR_FRONT_MERGE;
}
return ret;
}
static struct elevator_type *elevator_find(const char *name)
{
struct elevator_type *e;
list_for_each_entry(e, &elv_list, list) {
if (!strcmp(e->elevator_name, name))
return e;
}
return NULL;
}
static void elevator_put(struct elevator_type *e)
{
module_put(e->elevator_owner);
}
static struct elevator_type *elevator_get(const char *name)
{
struct elevator_type *e;
spin_lock(&elv_list_lock);
e = elevator_find(name);
if (!e) {
char elv[ELV_NAME_MAX + strlen("-iosched")];
spin_unlock(&elv_list_lock);
sprintf(elv, "%s-iosched", name);
request_module("%s", elv);
spin_lock(&elv_list_lock);
e = elevator_find(name);
}
if (e && !try_module_get(e->elevator_owner))
e = NULL;
spin_unlock(&elv_list_lock);
return e;
}
static void *elevator_init_queue(struct request_queue *q,
struct elevator_queue *eq)
{
return eq->ops->elevator_init_fn(q);
}
static void elevator_attach(struct request_queue *q, struct elevator_queue *eq,
void *data)
{
q->elevator = eq;
eq->elevator_data = data;
}
static char chosen_elevator[16];
static int __init elevator_setup(char *str)
{
/*
* Be backwards-compatible with previous kernels, so users
* won't get the wrong elevator.
*/
strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
return 1;
}
__setup("elevator=", elevator_setup);
static struct kobj_type elv_ktype;
static struct elevator_queue *elevator_alloc(struct request_queue *q,
struct elevator_type *e)
{
struct elevator_queue *eq;
int i;
eq = kmalloc_node(sizeof(*eq), GFP_KERNEL | __GFP_ZERO, q->node);
if (unlikely(!eq))
goto err;
eq->ops = &e->ops;
eq->elevator_type = e;
kobject_init(&eq->kobj, &elv_ktype);
mutex_init(&eq->sysfs_lock);
eq->hash = kmalloc_node(sizeof(struct hlist_head) * ELV_HASH_ENTRIES,
GFP_KERNEL, q->node);
if (!eq->hash)
goto err;
for (i = 0; i < ELV_HASH_ENTRIES; i++)
INIT_HLIST_HEAD(&eq->hash[i]);
return eq;
err:
kfree(eq);
elevator_put(e);
return NULL;
}
static void elevator_release(struct kobject *kobj)
{
struct elevator_queue *e;
e = container_of(kobj, struct elevator_queue, kobj);
elevator_put(e->elevator_type);
kfree(e->hash);
kfree(e);
}
int elevator_init(struct request_queue *q, char *name)
{
struct elevator_type *e = NULL;
struct elevator_queue *eq;
int ret = 0;
void *data;
INIT_LIST_HEAD(&q->queue_head);
q->last_merge = NULL;
q->end_sector = 0;
q->boundary_rq = NULL;
if (name) {
e = elevator_get(name);
if (!e)
return -EINVAL;
}
if (!e && *chosen_elevator) {
e = elevator_get(chosen_elevator);
if (!e)
printk(KERN_ERR "I/O scheduler %s not found\n",
chosen_elevator);
}
if (!e) {
e = elevator_get(CONFIG_DEFAULT_IOSCHED);
if (!e) {
printk(KERN_ERR
"Default I/O scheduler not found. " \
"Using noop.\n");
e = elevator_get("noop");
}
}
eq = elevator_alloc(q, e);
if (!eq)
return -ENOMEM;
data = elevator_init_queue(q, eq);
if (!data) {
kobject_put(&eq->kobj);
return -ENOMEM;
}
elevator_attach(q, eq, data);
return ret;
}
EXPORT_SYMBOL(elevator_init);
void elevator_exit(struct elevator_queue *e)
{
mutex_lock(&e->sysfs_lock);
if (e->ops->elevator_exit_fn)
e->ops->elevator_exit_fn(e);
e->ops = NULL;
mutex_unlock(&e->sysfs_lock);
kobject_put(&e->kobj);
}
EXPORT_SYMBOL(elevator_exit);
static inline void __elv_rqhash_del(struct request *rq)
{
hlist_del_init(&rq->hash);
}
static void elv_rqhash_del(struct request_queue *q, struct request *rq)
{
if (ELV_ON_HASH(rq))
__elv_rqhash_del(rq);
}
static void elv_rqhash_add(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
BUG_ON(ELV_ON_HASH(rq));
hlist_add_head(&rq->hash, &e->hash[ELV_HASH_FN(rq_hash_key(rq))]);
}
static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
{
__elv_rqhash_del(rq);
elv_rqhash_add(q, rq);
}
static struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
{
struct elevator_queue *e = q->elevator;
struct hlist_head *hash_list = &e->hash[ELV_HASH_FN(offset)];
struct hlist_node *entry, *next;
struct request *rq;
hlist_for_each_entry_safe(rq, entry, next, hash_list, hash) {
BUG_ON(!ELV_ON_HASH(rq));
if (unlikely(!rq_mergeable(rq))) {
__elv_rqhash_del(rq);
continue;
}
if (rq_hash_key(rq) == offset)
return rq;
}
return NULL;
}
/*
* RB-tree support functions for inserting/lookup/removal of requests
* in a sorted RB tree.
*/
struct request *elv_rb_add(struct rb_root *root, struct request *rq)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct request *__rq;
while (*p) {
parent = *p;
__rq = rb_entry(parent, struct request, rb_node);
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:39 +02:00
if (blk_rq_pos(rq) < blk_rq_pos(__rq))
p = &(*p)->rb_left;
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:39 +02:00
else if (blk_rq_pos(rq) > blk_rq_pos(__rq))
p = &(*p)->rb_right;
else
return __rq;
}
rb_link_node(&rq->rb_node, parent, p);
rb_insert_color(&rq->rb_node, root);
return NULL;
}
EXPORT_SYMBOL(elv_rb_add);
void elv_rb_del(struct rb_root *root, struct request *rq)
{
BUG_ON(RB_EMPTY_NODE(&rq->rb_node));
rb_erase(&rq->rb_node, root);
RB_CLEAR_NODE(&rq->rb_node);
}
EXPORT_SYMBOL(elv_rb_del);
struct request *elv_rb_find(struct rb_root *root, sector_t sector)
{
struct rb_node *n = root->rb_node;
struct request *rq;
while (n) {
rq = rb_entry(n, struct request, rb_node);
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:39 +02:00
if (sector < blk_rq_pos(rq))
n = n->rb_left;
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:39 +02:00
else if (sector > blk_rq_pos(rq))
n = n->rb_right;
else
return rq;
}
return NULL;
}
EXPORT_SYMBOL(elv_rb_find);
/*
* Insert rq into dispatch queue of q. Queue lock must be held on
* entry. rq is sort instead into the dispatch queue. To be used by
* specific elevators.
*/
void elv_dispatch_sort(struct request_queue *q, struct request *rq)
{
sector_t boundary;
struct list_head *entry;
int stop_flags;
if (q->last_merge == rq)
q->last_merge = NULL;
elv_rqhash_del(q, rq);
q->nr_sorted--;
boundary = q->end_sector;
stop_flags = REQ_SOFTBARRIER | REQ_HARDBARRIER | REQ_STARTED;
list_for_each_prev(entry, &q->queue_head) {
struct request *pos = list_entry_rq(entry);
if (blk_discard_rq(rq) != blk_discard_rq(pos))
break;
if (rq_data_dir(rq) != rq_data_dir(pos))
break;
if (pos->cmd_flags & stop_flags)
break;
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:39 +02:00
if (blk_rq_pos(rq) >= boundary) {
if (blk_rq_pos(pos) < boundary)
continue;
} else {
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:39 +02:00
if (blk_rq_pos(pos) >= boundary)
break;
}
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:39 +02:00
if (blk_rq_pos(rq) >= blk_rq_pos(pos))
break;
}
list_add(&rq->queuelist, entry);
}
EXPORT_SYMBOL(elv_dispatch_sort);
/*
* Insert rq into dispatch queue of q. Queue lock must be held on
* entry. rq is added to the back of the dispatch queue. To be used by
* specific elevators.
*/
void elv_dispatch_add_tail(struct request_queue *q, struct request *rq)
{
if (q->last_merge == rq)
q->last_merge = NULL;
elv_rqhash_del(q, rq);
q->nr_sorted--;
q->end_sector = rq_end_sector(rq);
q->boundary_rq = rq;
list_add_tail(&rq->queuelist, &q->queue_head);
}
EXPORT_SYMBOL(elv_dispatch_add_tail);
int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
{
struct elevator_queue *e = q->elevator;
struct request *__rq;
int ret;
/*
* First try one-hit cache.
*/
if (q->last_merge) {
ret = elv_try_merge(q->last_merge, bio);
if (ret != ELEVATOR_NO_MERGE) {
*req = q->last_merge;
return ret;
}
}
if (blk_queue_nomerges(q))
return ELEVATOR_NO_MERGE;
/*
* See if our hash lookup can find a potential backmerge.
*/
__rq = elv_rqhash_find(q, bio->bi_sector);
if (__rq && elv_rq_merge_ok(__rq, bio)) {
*req = __rq;
return ELEVATOR_BACK_MERGE;
}
if (e->ops->elevator_merge_fn)
return e->ops->elevator_merge_fn(q, req, bio);
return ELEVATOR_NO_MERGE;
}
void elv_merged_request(struct request_queue *q, struct request *rq, int type)
{
struct elevator_queue *e = q->elevator;
if (e->ops->elevator_merged_fn)
e->ops->elevator_merged_fn(q, rq, type);
if (type == ELEVATOR_BACK_MERGE)
elv_rqhash_reposition(q, rq);
q->last_merge = rq;
}
void elv_merge_requests(struct request_queue *q, struct request *rq,
struct request *next)
{
struct elevator_queue *e = q->elevator;
if (e->ops->elevator_merge_req_fn)
e->ops->elevator_merge_req_fn(q, rq, next);
elv_rqhash_reposition(q, rq);
elv_rqhash_del(q, next);
q->nr_sorted--;
q->last_merge = rq;
}
void elv_requeue_request(struct request_queue *q, struct request *rq)
{
/*
* it already went through dequeue, we need to decrement the
* in_flight count again
*/
if (blk_account_rq(rq)) {
q->in_flight[rq_is_sync(rq)]--;
if (blk_sorted_rq(rq))
elv_deactivate_rq(q, rq);
}
rq->cmd_flags &= ~REQ_STARTED;
elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE);
}
void elv_drain_elevator(struct request_queue *q)
{
static int printed;
while (q->elevator->ops->elevator_dispatch_fn(q, 1))
;
if (q->nr_sorted == 0)
return;
if (printed++ < 10) {
printk(KERN_ERR "%s: forced dispatching is broken "
"(nr_sorted=%u), please report this\n",
q->elevator->elevator_type->elevator_name, q->nr_sorted);
}
}
/*
* Call with queue lock held, interrupts disabled
*/
void elv_quiesce_start(struct request_queue *q)
{
if (!q->elevator)
return;
queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
/*
* make sure we don't have any requests in flight
*/
elv_drain_elevator(q);
while (q->rq.elvpriv) {
__blk_run_queue(q);
spin_unlock_irq(q->queue_lock);
msleep(10);
spin_lock_irq(q->queue_lock);
elv_drain_elevator(q);
}
}
void elv_quiesce_end(struct request_queue *q)
{
queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
}
void elv_insert(struct request_queue *q, struct request *rq, int where)
{
struct list_head *pos;
unsigned ordseq;
int unplug_it = 1;
trace_block_rq_insert(q, rq);
rq->q = q;
switch (where) {
case ELEVATOR_INSERT_FRONT:
rq->cmd_flags |= REQ_SOFTBARRIER;
list_add(&rq->queuelist, &q->queue_head);
break;
case ELEVATOR_INSERT_BACK:
rq->cmd_flags |= REQ_SOFTBARRIER;
elv_drain_elevator(q);
list_add_tail(&rq->queuelist, &q->queue_head);
/*
* We kick the queue here for the following reasons.
* - The elevator might have returned NULL previously
* to delay requests and returned them now. As the
* queue wasn't empty before this request, ll_rw_blk
* won't run the queue on return, resulting in hang.
* - Usually, back inserted requests won't be merged
* with anything. There's no point in delaying queue
* processing.
*/
__blk_run_queue(q);
break;
case ELEVATOR_INSERT_SORT:
BUG_ON(!blk_fs_request(rq) && !blk_discard_rq(rq));
rq->cmd_flags |= REQ_SORTED;
q->nr_sorted++;
if (rq_mergeable(rq)) {
elv_rqhash_add(q, rq);
if (!q->last_merge)
q->last_merge = rq;
}
/*
* Some ioscheds (cfq) run q->request_fn directly, so
* rq cannot be accessed after calling
* elevator_add_req_fn.
*/
q->elevator->ops->elevator_add_req_fn(q, rq);
break;
case ELEVATOR_INSERT_REQUEUE:
/*
* If ordered flush isn't in progress, we do front
* insertion; otherwise, requests should be requeued
* in ordseq order.
*/
rq->cmd_flags |= REQ_SOFTBARRIER;
/*
* Most requeues happen because of a busy condition,
* don't force unplug of the queue for that case.
*/
unplug_it = 0;
if (q->ordseq == 0) {
list_add(&rq->queuelist, &q->queue_head);
break;
}
ordseq = blk_ordered_req_seq(rq);
list_for_each(pos, &q->queue_head) {
struct request *pos_rq = list_entry_rq(pos);
if (ordseq <= blk_ordered_req_seq(pos_rq))
break;
}
list_add_tail(&rq->queuelist, pos);
break;
default:
printk(KERN_ERR "%s: bad insertion point %d\n",
__func__, where);
BUG();
}
if (unplug_it && blk_queue_plugged(q)) {
int nrq = q->rq.count[BLK_RW_SYNC] + q->rq.count[BLK_RW_ASYNC]
- queue_in_flight(q);
if (nrq >= q->unplug_thresh)
__generic_unplug_device(q);
}
}
void __elv_add_request(struct request_queue *q, struct request *rq, int where,
int plug)
{
if (q->ordcolor)
rq->cmd_flags |= REQ_ORDERED_COLOR;
if (rq->cmd_flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) {
/*
* toggle ordered color
*/
if (blk_barrier_rq(rq))
q->ordcolor ^= 1;
/*
* barriers implicitly indicate back insertion
*/
if (where == ELEVATOR_INSERT_SORT)
where = ELEVATOR_INSERT_BACK;
/*
* this request is scheduling boundary, update
* end_sector
*/
if (blk_fs_request(rq) || blk_discard_rq(rq)) {
q->end_sector = rq_end_sector(rq);
q->boundary_rq = rq;
}
} else if (!(rq->cmd_flags & REQ_ELVPRIV) &&
where == ELEVATOR_INSERT_SORT)
where = ELEVATOR_INSERT_BACK;
if (plug)
blk_plug_device(q);
elv_insert(q, rq, where);
}
EXPORT_SYMBOL(__elv_add_request);
void elv_add_request(struct request_queue *q, struct request *rq, int where,
int plug)
{
unsigned long flags;
spin_lock_irqsave(q->queue_lock, flags);
__elv_add_request(q, rq, where, plug);
spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(elv_add_request);
int elv_queue_empty(struct request_queue *q)
{
struct elevator_queue *e = q->elevator;
if (!list_empty(&q->queue_head))
return 0;
if (e->ops->elevator_queue_empty_fn)
return e->ops->elevator_queue_empty_fn(q);
return 1;
}
EXPORT_SYMBOL(elv_queue_empty);
struct request *elv_latter_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->ops->elevator_latter_req_fn)
return e->ops->elevator_latter_req_fn(q, rq);
return NULL;
}
struct request *elv_former_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->ops->elevator_former_req_fn)
return e->ops->elevator_former_req_fn(q, rq);
return NULL;
}
int elv_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
{
struct elevator_queue *e = q->elevator;
if (e->ops->elevator_set_req_fn)
return e->ops->elevator_set_req_fn(q, rq, gfp_mask);
rq->elevator_private = NULL;
return 0;
}
void elv_put_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->ops->elevator_put_req_fn)
e->ops->elevator_put_req_fn(rq);
}
int elv_may_queue(struct request_queue *q, int rw)
{
struct elevator_queue *e = q->elevator;
if (e->ops->elevator_may_queue_fn)
return e->ops->elevator_may_queue_fn(q, rw);
return ELV_MQUEUE_MAY;
}
void elv_abort_queue(struct request_queue *q)
{
struct request *rq;
while (!list_empty(&q->queue_head)) {
rq = list_entry_rq(q->queue_head.next);
rq->cmd_flags |= REQ_QUIET;
trace_block_rq_abort(q, rq);
/*
* Mark this request as started so we don't trigger
* any debug logic in the end I/O path.
*/
blk_start_request(rq);
__blk_end_request_all(rq, -EIO);
}
}
EXPORT_SYMBOL(elv_abort_queue);
void elv_completed_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
/*
* request is released from the driver, io must be done
*/
if (blk_account_rq(rq)) {
q->in_flight[rq_is_sync(rq)]--;
if (blk_sorted_rq(rq) && e->ops->elevator_completed_req_fn)
e->ops->elevator_completed_req_fn(q, rq);
}
/*
* Check if the queue is waiting for fs requests to be
* drained for flush sequence.
*/
if (unlikely(q->ordseq)) {
struct request *next = NULL;
if (!list_empty(&q->queue_head))
next = list_entry_rq(q->queue_head.next);
if (!queue_in_flight(q) &&
blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN &&
(!next || blk_ordered_req_seq(next) > QUEUE_ORDSEQ_DRAIN)) {
blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0);
__blk_run_queue(q);
}
}
}
#define to_elv(atr) container_of((atr), struct elv_fs_entry, attr)
static ssize_t
elv_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
struct elv_fs_entry *entry = to_elv(attr);
struct elevator_queue *e;
ssize_t error;
if (!entry->show)
return -EIO;
e = container_of(kobj, struct elevator_queue, kobj);
mutex_lock(&e->sysfs_lock);
error = e->ops ? entry->show(e, page) : -ENOENT;
mutex_unlock(&e->sysfs_lock);
return error;
}
static ssize_t
elv_attr_store(struct kobject *kobj, struct attribute *attr,
const char *page, size_t length)
{
struct elv_fs_entry *entry = to_elv(attr);
struct elevator_queue *e;
ssize_t error;
if (!entry->store)
return -EIO;
e = container_of(kobj, struct elevator_queue, kobj);
mutex_lock(&e->sysfs_lock);
error = e->ops ? entry->store(e, page, length) : -ENOENT;
mutex_unlock(&e->sysfs_lock);
return error;
}
static struct sysfs_ops elv_sysfs_ops = {
.show = elv_attr_show,
.store = elv_attr_store,
};
static struct kobj_type elv_ktype = {
.sysfs_ops = &elv_sysfs_ops,
.release = elevator_release,
};
int elv_register_queue(struct request_queue *q)
{
struct elevator_queue *e = q->elevator;
int error;
error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
if (!error) {
struct elv_fs_entry *attr = e->elevator_type->elevator_attrs;
if (attr) {
while (attr->attr.name) {
if (sysfs_create_file(&e->kobj, &attr->attr))
break;
attr++;
}
}
kobject_uevent(&e->kobj, KOBJ_ADD);
}
return error;
}
static void __elv_unregister_queue(struct elevator_queue *e)
{
kobject_uevent(&e->kobj, KOBJ_REMOVE);
kobject_del(&e->kobj);
}
void elv_unregister_queue(struct request_queue *q)
{
if (q)
__elv_unregister_queue(q->elevator);
}
void elv_register(struct elevator_type *e)
{
char *def = "";
spin_lock(&elv_list_lock);
BUG_ON(elevator_find(e->elevator_name));
list_add_tail(&e->list, &elv_list);
spin_unlock(&elv_list_lock);
if (!strcmp(e->elevator_name, chosen_elevator) ||
(!*chosen_elevator &&
!strcmp(e->elevator_name, CONFIG_DEFAULT_IOSCHED)))
def = " (default)";
printk(KERN_INFO "io scheduler %s registered%s\n", e->elevator_name,
def);
}
EXPORT_SYMBOL_GPL(elv_register);
void elv_unregister(struct elevator_type *e)
{
struct task_struct *g, *p;
/*
* Iterate every thread in the process to remove the io contexts.
*/
if (e->ops.trim) {
read_lock(&tasklist_lock);
do_each_thread(g, p) {
task_lock(p);
if (p->io_context)
e->ops.trim(p->io_context);
task_unlock(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
}
spin_lock(&elv_list_lock);
list_del_init(&e->list);
spin_unlock(&elv_list_lock);
}
EXPORT_SYMBOL_GPL(elv_unregister);
/*
* switch to new_e io scheduler. be careful not to introduce deadlocks -
* we don't free the old io scheduler, before we have allocated what we
* need for the new one. this way we have a chance of going back to the old
* one, if the new one fails init for some reason.
*/
static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
{
struct elevator_queue *old_elevator, *e;
void *data;
/*
* Allocate new elevator
*/
e = elevator_alloc(q, new_e);
if (!e)
return 0;
data = elevator_init_queue(q, e);
if (!data) {
kobject_put(&e->kobj);
return 0;
}
/*
* Turn on BYPASS and drain all requests w/ elevator private data
*/
spin_lock_irq(q->queue_lock);
elv_quiesce_start(q);
/*
* Remember old elevator.
*/
old_elevator = q->elevator;
/*
* attach and start new elevator
*/
elevator_attach(q, e, data);
spin_unlock_irq(q->queue_lock);
__elv_unregister_queue(old_elevator);
if (elv_register_queue(q))
goto fail_register;
/*
* finally exit old elevator and turn off BYPASS.
*/
elevator_exit(old_elevator);
spin_lock_irq(q->queue_lock);
elv_quiesce_end(q);
spin_unlock_irq(q->queue_lock);
blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name);
return 1;
fail_register:
/*
* switch failed, exit the new io scheduler and reattach the old
* one again (along with re-adding the sysfs dir)
*/
elevator_exit(e);
q->elevator = old_elevator;
elv_register_queue(q);
spin_lock_irq(q->queue_lock);
queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
spin_unlock_irq(q->queue_lock);
return 0;
}
ssize_t elv_iosched_store(struct request_queue *q, const char *name,
size_t count)
{
char elevator_name[ELV_NAME_MAX];
struct elevator_type *e;
if (!q->elevator)
return count;
strlcpy(elevator_name, name, sizeof(elevator_name));
e = elevator_get(strstrip(elevator_name));
if (!e) {
printk(KERN_ERR "elevator: type %s not found\n", elevator_name);
return -EINVAL;
}
if (!strcmp(elevator_name, q->elevator->elevator_type->elevator_name)) {
elevator_put(e);
return count;
}
if (!elevator_switch(q, e))
printk(KERN_ERR "elevator: switch to %s failed\n",
elevator_name);
return count;
}
ssize_t elv_iosched_show(struct request_queue *q, char *name)
{
struct elevator_queue *e = q->elevator;
struct elevator_type *elv;
struct elevator_type *__e;
int len = 0;
if (!q->elevator)
return sprintf(name, "none\n");
elv = e->elevator_type;
spin_lock(&elv_list_lock);
list_for_each_entry(__e, &elv_list, list) {
if (!strcmp(elv->elevator_name, __e->elevator_name))
len += sprintf(name+len, "[%s] ", elv->elevator_name);
else
len += sprintf(name+len, "%s ", __e->elevator_name);
}
spin_unlock(&elv_list_lock);
len += sprintf(len+name, "\n");
return len;
}
struct request *elv_rb_former_request(struct request_queue *q,
struct request *rq)
{
struct rb_node *rbprev = rb_prev(&rq->rb_node);
if (rbprev)
return rb_entry_rq(rbprev);
return NULL;
}
EXPORT_SYMBOL(elv_rb_former_request);
struct request *elv_rb_latter_request(struct request_queue *q,
struct request *rq)
{
struct rb_node *rbnext = rb_next(&rq->rb_node);
if (rbnext)
return rb_entry_rq(rbnext);
return NULL;
}
EXPORT_SYMBOL(elv_rb_latter_request);