12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238 |
- /*
- * 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>
- #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)
- #define rq_hash_key(rq) ((rq)->sector + (rq)->nr_sectors)
- #define ELV_ON_HASH(rq) (!hlist_unhashed(&(rq)->hash))
- /*
- * 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;
- elevator_t *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_discard(bio) != bio_discard(rq->bio))
- 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)) {
- if (__rq->sector + __rq->nr_sectors == bio->bi_sector)
- ret = ELEVATOR_BACK_MERGE;
- else if (__rq->sector - 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);
- if (!strcmp(name, "anticipatory"))
- sprintf(elv, "as-iosched");
- else
- 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.
- */
- if (!strcmp(str, "as"))
- strcpy(chosen_elevator, "anticipatory");
- else
- strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
- return 1;
- }
- __setup("elevator=", elevator_setup);
- static struct kobj_type elv_ktype;
- static elevator_t *elevator_alloc(struct request_queue *q,
- struct elevator_type *e)
- {
- elevator_t *eq;
- int i;
- eq = kmalloc_node(sizeof(elevator_t), 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)
- {
- elevator_t *e = container_of(kobj, elevator_t, 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(elevator_t *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 void elv_activate_rq(struct request_queue *q, struct request *rq)
- {
- elevator_t *e = q->elevator;
- if (e->ops->elevator_activate_req_fn)
- e->ops->elevator_activate_req_fn(q, rq);
- }
- static void elv_deactivate_rq(struct request_queue *q, struct request *rq)
- {
- elevator_t *e = q->elevator;
- if (e->ops->elevator_deactivate_req_fn)
- e->ops->elevator_deactivate_req_fn(q, rq);
- }
- 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)
- {
- elevator_t *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)
- {
- elevator_t *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);
- if (rq->sector < __rq->sector)
- p = &(*p)->rb_left;
- else if (rq->sector > __rq->sector)
- 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);
- if (sector < rq->sector)
- n = n->rb_left;
- else if (sector > rq->sector)
- 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;
- if (rq->sector >= boundary) {
- if (pos->sector < boundary)
- continue;
- } else {
- if (pos->sector >= boundary)
- break;
- }
- if (rq->sector >= pos->sector)
- 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)
- {
- elevator_t *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)
- {
- elevator_t *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)
- {
- elevator_t *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--;
- if (blk_sorted_rq(rq))
- elv_deactivate_rq(q, rq);
- }
- rq->cmd_flags &= ~REQ_STARTED;
- elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE);
- }
- static 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);
- }
- }
- void elv_insert(struct request_queue *q, struct request *rq, int where)
- {
- struct list_head *pos;
- unsigned ordseq;
- int unplug_it = 1;
- blk_add_trace_rq(q, rq, BLK_TA_INSERT);
- 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_remove_plug(q);
- q->request_fn(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[READ] + q->rq.count[WRITE]
- - q->in_flight;
- 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);
- 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;
- }
- }
- struct request *elv_next_request(struct request_queue *q)
- {
- struct request *rq;
- int ret;
- while ((rq = __elv_next_request(q)) != NULL) {
- /*
- * Kill the empty barrier place holder, the driver must
- * not ever see it.
- */
- if (blk_empty_barrier(rq)) {
- __blk_end_request(rq, 0, blk_rq_bytes(rq));
- continue;
- }
- if (!(rq->cmd_flags & REQ_STARTED)) {
- /*
- * This is the first time the device driver
- * sees this request (possibly after
- * requeueing). Notify IO scheduler.
- */
- if (blk_sorted_rq(rq))
- elv_activate_rq(q, rq);
- /*
- * just mark as started even if we don't start
- * it, a request that has been delayed should
- * not be passed by new incoming requests
- */
- rq->cmd_flags |= REQ_STARTED;
- blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
- /*
- * We are now handing the request to the hardware,
- * add the timeout handler
- */
- blk_add_timer(rq);
- }
- if (!q->boundary_rq || q->boundary_rq == rq) {
- q->end_sector = rq_end_sector(rq);
- q->boundary_rq = NULL;
- }
- if (rq->cmd_flags & REQ_DONTPREP)
- break;
- if (q->dma_drain_size && rq->data_len) {
- /*
- * make sure space for the drain appears we
- * know we can do this because max_hw_segments
- * has been adjusted to be one fewer than the
- * device can handle
- */
- rq->nr_phys_segments++;
- }
- if (!q->prep_rq_fn)
- break;
- ret = q->prep_rq_fn(q, rq);
- if (ret == BLKPREP_OK) {
- break;
- } else if (ret == BLKPREP_DEFER) {
- /*
- * the request may have been (partially) prepped.
- * we need to keep this request in the front to
- * avoid resource deadlock. REQ_STARTED will
- * prevent other fs requests from passing this one.
- */
- if (q->dma_drain_size && rq->data_len &&
- !(rq->cmd_flags & REQ_DONTPREP)) {
- /*
- * remove the space for the drain we added
- * so that we don't add it again
- */
- --rq->nr_phys_segments;
- }
- rq = NULL;
- break;
- } else if (ret == BLKPREP_KILL) {
- rq->cmd_flags |= REQ_QUIET;
- __blk_end_request(rq, -EIO, blk_rq_bytes(rq));
- } else {
- printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
- break;
- }
- }
- return rq;
- }
- EXPORT_SYMBOL(elv_next_request);
- void elv_dequeue_request(struct request_queue *q, struct request *rq)
- {
- BUG_ON(list_empty(&rq->queuelist));
- BUG_ON(ELV_ON_HASH(rq));
- list_del_init(&rq->queuelist);
- /*
- * the time frame between a request being removed from the lists
- * and to it is freed is accounted as io that is in progress at
- * the driver side.
- */
- if (blk_account_rq(rq))
- q->in_flight++;
- }
- EXPORT_SYMBOL(elv_dequeue_request);
- int elv_queue_empty(struct request_queue *q)
- {
- elevator_t *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)
- {
- elevator_t *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)
- {
- elevator_t *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)
- {
- elevator_t *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)
- {
- elevator_t *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)
- {
- elevator_t *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;
- blk_add_trace_rq(q, rq, BLK_TA_ABORT);
- __blk_end_request(rq, -EIO, blk_rq_bytes(rq));
- }
- }
- EXPORT_SYMBOL(elv_abort_queue);
- void elv_completed_request(struct request_queue *q, struct request *rq)
- {
- elevator_t *e = q->elevator;
- /*
- * request is released from the driver, io must be done
- */
- if (blk_account_rq(rq)) {
- q->in_flight--;
- 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 *first_rq = list_entry_rq(q->queue_head.next);
- if (q->in_flight == 0 &&
- blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN &&
- blk_ordered_req_seq(first_rq) > QUEUE_ORDSEQ_DRAIN) {
- blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0);
- q->request_fn(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)
- {
- elevator_t *e = container_of(kobj, elevator_t, kobj);
- struct elv_fs_entry *entry = to_elv(attr);
- ssize_t error;
- if (!entry->show)
- return -EIO;
- 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)
- {
- elevator_t *e = container_of(kobj, elevator_t, kobj);
- struct elv_fs_entry *entry = to_elv(attr);
- ssize_t error;
- if (!entry->store)
- return -EIO;
- 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)
- {
- elevator_t *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(elevator_t *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)
- {
- elevator_t *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);
- queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
- elv_drain_elevator(q);
- while (q->rq.elvpriv) {
- blk_remove_plug(q);
- q->request_fn(q);
- spin_unlock_irq(q->queue_lock);
- msleep(10);
- spin_lock_irq(q->queue_lock);
- elv_drain_elevator(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);
- queue_flag_clear(QUEUE_FLAG_ELVSWITCH, 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];
- size_t len;
- struct elevator_type *e;
- elevator_name[sizeof(elevator_name) - 1] = '\0';
- strncpy(elevator_name, name, sizeof(elevator_name) - 1);
- len = strlen(elevator_name);
- if (len && elevator_name[len - 1] == '\n')
- elevator_name[len - 1] = '\0';
- e = elevator_get(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)
- {
- elevator_t *e = q->elevator;
- struct elevator_type *elv = e->elevator_type;
- struct elevator_type *__e;
- int len = 0;
- 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);
|