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);
+ if (e->type->ops.elevator_allow_merge_fn)
+ return e->type->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)
+bool 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->bi_rw & REQ_DISCARD) != (rq->bio->bi_rw & REQ_DISCARD))
- return 0;
-
- /*
- * Don't merge discard requests and secure discard requests
- */
- if ((bio->bi_rw & REQ_SECURE) != (rq->bio->bi_rw & REQ_SECURE))
- 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))
+ if (!blk_rq_merge_ok(rq, bio))
return 0;
if (!elv_iosched_allow_merge(rq, bio))
}
EXPORT_SYMBOL(elv_rq_merge_ok);
-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 (blk_rq_pos(__rq) + blk_rq_sectors(__rq) == bio->bi_sector)
- ret = ELEVATOR_BACK_MERGE;
- 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;
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[ELV_NAME_MAX];
static int __init elevator_setup(char *str)
if (unlikely(!eq))
goto err;
- eq->ops = &e->ops;
- eq->elevator_type = e;
+ eq->type = e;
kobject_init(&eq->kobj, &elv_ktype);
mutex_init(&eq->sysfs_lock);
struct elevator_queue *e;
e = container_of(kobj, struct elevator_queue, kobj);
- elevator_put(e->elevator_type);
+ elevator_put(e->type);
kfree(e->hash);
kfree(e);
}
int elevator_init(struct request_queue *q, char *name)
{
struct elevator_type *e = NULL;
- struct elevator_queue *eq;
- void *data;
+ int err;
if (unlikely(q->elevator))
return 0;
}
}
- eq = elevator_alloc(q, e);
- if (!eq)
+ q->elevator = elevator_alloc(q, e);
+ if (!q->elevator)
return -ENOMEM;
- data = elevator_init_queue(q, eq);
- if (!data) {
- kobject_put(&eq->kobj);
- return -ENOMEM;
+ err = e->ops.elevator_init_fn(q);
+ if (err) {
+ kobject_put(&q->elevator->kobj);
+ return err;
}
- elevator_attach(q, eq, data);
return 0;
}
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;
+ if (e->type->ops.elevator_exit_fn)
+ e->type->ops.elevator_exit_fn(e);
mutex_unlock(&e->sysfs_lock);
kobject_put(&e->kobj);
/*
* First try one-hit cache.
*/
- if (q->last_merge) {
- ret = elv_try_merge(q->last_merge, bio);
+ if (q->last_merge && elv_rq_merge_ok(q->last_merge, bio)) {
+ ret = blk_try_merge(q->last_merge, bio);
if (ret != ELEVATOR_NO_MERGE) {
*req = q->last_merge;
return ret;
return ELEVATOR_BACK_MERGE;
}
- if (e->ops->elevator_merge_fn)
- return e->ops->elevator_merge_fn(q, req, bio);
+ if (e->type->ops.elevator_merge_fn)
+ return e->type->ops.elevator_merge_fn(q, req, bio);
return ELEVATOR_NO_MERGE;
}
{
struct elevator_queue *e = q->elevator;
- if (e->ops->elevator_merged_fn)
- e->ops->elevator_merged_fn(q, rq, type);
+ if (e->type->ops.elevator_merged_fn)
+ e->type->ops.elevator_merged_fn(q, rq, type);
if (type == ELEVATOR_BACK_MERGE)
elv_rqhash_reposition(q, rq);
struct elevator_queue *e = q->elevator;
const int next_sorted = next->cmd_flags & REQ_SORTED;
- if (next_sorted && e->ops->elevator_merge_req_fn)
- e->ops->elevator_merge_req_fn(q, rq, next);
+ if (next_sorted && e->type->ops.elevator_merge_req_fn)
+ e->type->ops.elevator_merge_req_fn(q, rq, next);
elv_rqhash_reposition(q, rq);
{
struct elevator_queue *e = q->elevator;
- if (e->ops->elevator_bio_merged_fn)
- e->ops->elevator_bio_merged_fn(q, rq, bio);
+ if (e->type->ops.elevator_bio_merged_fn)
+ e->type->ops.elevator_bio_merged_fn(q, rq, bio);
}
void elv_requeue_request(struct request_queue *q, struct request *rq)
lockdep_assert_held(q->queue_lock);
- while (q->elevator->ops->elevator_dispatch_fn(q, 1))
+ while (q->elevator->type->ops.elevator_dispatch_fn(q, 1))
;
if (q->nr_sorted && 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);
+ q->elevator->type->elevator_name, q->nr_sorted);
}
}
* rq cannot be accessed after calling
* elevator_add_req_fn.
*/
- q->elevator->ops->elevator_add_req_fn(q, rq);
+ q->elevator->type->ops.elevator_add_req_fn(q, rq);
break;
case ELEVATOR_INSERT_FLUSH:
{
struct elevator_queue *e = q->elevator;
- if (e->ops->elevator_latter_req_fn)
- return e->ops->elevator_latter_req_fn(q, rq);
+ if (e->type->ops.elevator_latter_req_fn)
+ return e->type->ops.elevator_latter_req_fn(q, rq);
return NULL;
}
{
struct elevator_queue *e = q->elevator;
- if (e->ops->elevator_former_req_fn)
- return e->ops->elevator_former_req_fn(q, rq);
+ if (e->type->ops.elevator_former_req_fn)
+ return e->type->ops.elevator_former_req_fn(q, rq);
return NULL;
}
{
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[0] = NULL;
+ if (e->type->ops.elevator_set_req_fn)
+ return e->type->ops.elevator_set_req_fn(q, rq, gfp_mask);
return 0;
}
{
struct elevator_queue *e = q->elevator;
- if (e->ops->elevator_put_req_fn)
- e->ops->elevator_put_req_fn(rq);
+ if (e->type->ops.elevator_put_req_fn)
+ e->type->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);
+ if (e->type->ops.elevator_may_queue_fn)
+ return e->type->ops.elevator_may_queue_fn(q, rw);
return ELV_MQUEUE_MAY;
}
if (blk_account_rq(rq)) {
q->in_flight[rq_is_sync(rq)]--;
if ((rq->cmd_flags & REQ_SORTED) &&
- e->ops->elevator_completed_req_fn)
- e->ops->elevator_completed_req_fn(q, rq);
+ e->type->ops.elevator_completed_req_fn)
+ e->type->ops.elevator_completed_req_fn(q, rq);
}
}
e = container_of(kobj, struct elevator_queue, kobj);
mutex_lock(&e->sysfs_lock);
- error = e->ops ? entry->show(e, page) : -ENOENT;
+ error = e->type ? entry->show(e, page) : -ENOENT;
mutex_unlock(&e->sysfs_lock);
return error;
}
e = container_of(kobj, struct elevator_queue, kobj);
mutex_lock(&e->sysfs_lock);
- error = e->ops ? entry->store(e, page, length) : -ENOENT;
+ error = e->type ? entry->store(e, page, length) : -ENOENT;
mutex_unlock(&e->sysfs_lock);
return error;
}
error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
if (!error) {
- struct elv_fs_entry *attr = e->elevator_type->elevator_attrs;
+ struct elv_fs_entry *attr = e->type->elevator_attrs;
if (attr) {
while (attr->attr.name) {
if (sysfs_create_file(&e->kobj, &attr->attr))
}
EXPORT_SYMBOL(elv_register_queue);
-static void __elv_unregister_queue(struct elevator_queue *e)
-{
- kobject_uevent(&e->kobj, KOBJ_REMOVE);
- kobject_del(&e->kobj);
- e->registered = 0;
-}
-
void elv_unregister_queue(struct request_queue *q)
{
- if (q)
- __elv_unregister_queue(q->elevator);
+ if (q) {
+ struct elevator_queue *e = q->elevator;
+
+ kobject_uevent(&e->kobj, KOBJ_REMOVE);
+ kobject_del(&e->kobj);
+ e->registered = 0;
+ }
}
EXPORT_SYMBOL(elv_unregister_queue);
-void elv_register(struct elevator_type *e)
+int elv_register(struct elevator_type *e)
{
char *def = "";
+ /* create icq_cache if requested */
+ if (e->icq_size) {
+ if (WARN_ON(e->icq_size < sizeof(struct io_cq)) ||
+ WARN_ON(e->icq_align < __alignof__(struct io_cq)))
+ return -EINVAL;
+
+ snprintf(e->icq_cache_name, sizeof(e->icq_cache_name),
+ "%s_io_cq", e->elevator_name);
+ e->icq_cache = kmem_cache_create(e->icq_cache_name, e->icq_size,
+ e->icq_align, 0, NULL);
+ if (!e->icq_cache)
+ return -ENOMEM;
+ }
+
+ /* register, don't allow duplicate names */
spin_lock(&elv_list_lock);
- BUG_ON(elevator_find(e->elevator_name));
+ if (elevator_find(e->elevator_name)) {
+ spin_unlock(&elv_list_lock);
+ if (e->icq_cache)
+ kmem_cache_destroy(e->icq_cache);
+ return -EBUSY;
+ }
list_add_tail(&e->list, &elv_list);
spin_unlock(&elv_list_lock);
+ /* print pretty message */
if (!strcmp(e->elevator_name, chosen_elevator) ||
(!*chosen_elevator &&
!strcmp(e->elevator_name, CONFIG_DEFAULT_IOSCHED)))
printk(KERN_INFO "io scheduler %s registered%s\n", e->elevator_name,
def);
+ return 0;
}
EXPORT_SYMBOL_GPL(elv_register);
void elv_unregister(struct elevator_type *e)
{
- struct task_struct *g, *p;
+ /* unregister */
+ spin_lock(&elv_list_lock);
+ list_del_init(&e->list);
+ spin_unlock(&elv_list_lock);
/*
- * Iterate every thread in the process to remove the io contexts.
+ * Destroy icq_cache if it exists. icq's are RCU managed. Make
+ * sure all RCU operations are complete before proceeding.
*/
- 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);
+ if (e->icq_cache) {
+ rcu_barrier();
+ kmem_cache_destroy(e->icq_cache);
+ e->icq_cache = NULL;
}
-
- spin_lock(&elv_list_lock);
- list_del_init(&e->list);
- spin_unlock(&elv_list_lock);
}
EXPORT_SYMBOL_GPL(elv_unregister);
*/
static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
{
- struct elevator_queue *old_elevator, *e;
- void *data;
+ struct elevator_queue *old = q->elevator;
+ bool registered = old->registered;
int err;
/*
- * Allocate new elevator
- */
- e = elevator_alloc(q, new_e);
- if (!e)
- return -ENOMEM;
-
- data = elevator_init_queue(q, e);
- if (!data) {
- kobject_put(&e->kobj);
- return -ENOMEM;
- }
-
- /*
- * Turn on BYPASS and drain all requests w/ elevator private data
+ * Turn on BYPASS and drain all requests w/ elevator private data.
+ * Block layer doesn't call into a quiesced elevator - all requests
+ * are directly put on the dispatch list without elevator data
+ * using INSERT_BACK. All requests have SOFTBARRIER set and no
+ * merge happens either.
*/
elv_quiesce_start(q);
- /*
- * Remember old elevator.
- */
- old_elevator = q->elevator;
+ /* unregister and clear all auxiliary data of the old elevator */
+ if (registered)
+ elv_unregister_queue(q);
- /*
- * attach and start new elevator
- */
spin_lock_irq(q->queue_lock);
- elevator_attach(q, e, data);
+ ioc_clear_queue(q);
spin_unlock_irq(q->queue_lock);
- if (old_elevator->registered) {
- __elv_unregister_queue(old_elevator);
+ /* allocate, init and register new elevator */
+ err = -ENOMEM;
+ q->elevator = elevator_alloc(q, new_e);
+ if (!q->elevator)
+ goto fail_init;
+
+ err = new_e->ops.elevator_init_fn(q);
+ if (err) {
+ kobject_put(&q->elevator->kobj);
+ goto fail_init;
+ }
+ if (registered) {
err = elv_register_queue(q);
if (err)
goto fail_register;
}
- /*
- * finally exit old elevator and turn off BYPASS.
- */
- elevator_exit(old_elevator);
+ /* done, kill the old one and finish */
+ elevator_exit(old);
elv_quiesce_end(q);
- blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name);
+ blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
return 0;
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;
+ elevator_exit(q->elevator);
+fail_init:
+ /* switch failed, restore and re-register old elevator */
+ q->elevator = old;
elv_register_queue(q);
elv_quiesce_end(q);
return -EINVAL;
}
- if (!strcmp(elevator_name, q->elevator->elevator_type->elevator_name)) {
+ if (!strcmp(elevator_name, q->elevator->type->elevator_name)) {
elevator_put(e);
return 0;
}
if (!q->elevator || !blk_queue_stackable(q))
return sprintf(name, "none\n");
- elv = e->elevator_type;
+ elv = e->type;
spin_lock(&elv_list_lock);
list_for_each_entry(__e, &elv_list, list) {
git.samba.org / sfrench / cifs-2.6.git / blobdiff