blk-mq-sched: add framework for MQ capable IO schedulers
This adds a set of hooks that intercepts the blk-mq path of
allocating/inserting/issuing/completing requests, allowing
us to develop a scheduler within that framework.
We reuse the existing elevator scheduler API on the registration
side, but augment that with the scheduler flagging support for
the blk-mq interfce, and with a separate set of ops hooks for MQ
devices.
We split driver and scheduler tags, so we can run the scheduling
independently of device queue depth.
Signed-off-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
diff --git a/block/elevator.c b/block/elevator.c
index 022a268..0e1ccdd 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -40,6 +40,7 @@
#include <trace/events/block.h>
#include "blk.h"
+#include "blk-mq-sched.h"
static DEFINE_SPINLOCK(elv_list_lock);
static LIST_HEAD(elv_list);
@@ -58,7 +59,9 @@ static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
- if (e->type->ops.sq.elevator_allow_bio_merge_fn)
+ if (e->uses_mq && e->type->ops.mq.allow_merge)
+ return e->type->ops.mq.allow_merge(q, rq, bio);
+ else if (!e->uses_mq && e->type->ops.sq.elevator_allow_bio_merge_fn)
return e->type->ops.sq.elevator_allow_bio_merge_fn(q, rq, bio);
return 1;
@@ -163,6 +166,7 @@ struct elevator_queue *elevator_alloc(struct request_queue *q,
kobject_init(&eq->kobj, &elv_ktype);
mutex_init(&eq->sysfs_lock);
hash_init(eq->hash);
+ eq->uses_mq = e->uses_mq;
return eq;
}
@@ -219,14 +223,26 @@ int elevator_init(struct request_queue *q, char *name)
if (!e) {
printk(KERN_ERR
"Default I/O scheduler not found. " \
- "Using noop.\n");
+ "Using noop/none.\n");
+ if (q->mq_ops) {
+ elevator_put(e);
+ return 0;
+ }
e = elevator_get("noop", false);
}
}
- err = e->ops.sq.elevator_init_fn(q, e);
- if (err)
+ if (e->uses_mq) {
+ err = blk_mq_sched_setup(q);
+ if (!err)
+ err = e->ops.mq.init_sched(q, e);
+ } else
+ err = e->ops.sq.elevator_init_fn(q, e);
+ if (err) {
+ if (e->uses_mq)
+ blk_mq_sched_teardown(q);
elevator_put(e);
+ }
return err;
}
EXPORT_SYMBOL(elevator_init);
@@ -234,7 +250,9 @@ EXPORT_SYMBOL(elevator_init);
void elevator_exit(struct elevator_queue *e)
{
mutex_lock(&e->sysfs_lock);
- if (e->type->ops.sq.elevator_exit_fn)
+ if (e->uses_mq && e->type->ops.mq.exit_sched)
+ e->type->ops.mq.exit_sched(e);
+ else if (!e->uses_mq && e->type->ops.sq.elevator_exit_fn)
e->type->ops.sq.elevator_exit_fn(e);
mutex_unlock(&e->sysfs_lock);
@@ -253,6 +271,7 @@ void elv_rqhash_del(struct request_queue *q, struct request *rq)
if (ELV_ON_HASH(rq))
__elv_rqhash_del(rq);
}
+EXPORT_SYMBOL_GPL(elv_rqhash_del);
void elv_rqhash_add(struct request_queue *q, struct request *rq)
{
@@ -262,6 +281,7 @@ void elv_rqhash_add(struct request_queue *q, struct request *rq)
hash_add(e->hash, &rq->hash, rq_hash_key(rq));
rq->rq_flags |= RQF_HASHED;
}
+EXPORT_SYMBOL_GPL(elv_rqhash_add);
void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
{
@@ -443,7 +463,9 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
return ELEVATOR_BACK_MERGE;
}
- if (e->type->ops.sq.elevator_merge_fn)
+ if (e->uses_mq && e->type->ops.mq.request_merge)
+ return e->type->ops.mq.request_merge(q, req, bio);
+ else if (!e->uses_mq && e->type->ops.sq.elevator_merge_fn)
return e->type->ops.sq.elevator_merge_fn(q, req, bio);
return ELEVATOR_NO_MERGE;
@@ -456,8 +478,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
*
* Returns true if we merged, false otherwise
*/
-static bool elv_attempt_insert_merge(struct request_queue *q,
- struct request *rq)
+bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq)
{
struct request *__rq;
bool ret;
@@ -495,7 +516,9 @@ void elv_merged_request(struct request_queue *q, struct request *rq, int type)
{
struct elevator_queue *e = q->elevator;
- if (e->type->ops.sq.elevator_merged_fn)
+ if (e->uses_mq && e->type->ops.mq.request_merged)
+ e->type->ops.mq.request_merged(q, rq, type);
+ else if (!e->uses_mq && e->type->ops.sq.elevator_merged_fn)
e->type->ops.sq.elevator_merged_fn(q, rq, type);
if (type == ELEVATOR_BACK_MERGE)
@@ -508,10 +531,15 @@ void elv_merge_requests(struct request_queue *q, struct request *rq,
struct request *next)
{
struct elevator_queue *e = q->elevator;
- const int next_sorted = next->rq_flags & RQF_SORTED;
+ bool next_sorted = false;
- if (next_sorted && e->type->ops.sq.elevator_merge_req_fn)
- e->type->ops.sq.elevator_merge_req_fn(q, rq, next);
+ if (e->uses_mq && e->type->ops.mq.requests_merged)
+ e->type->ops.mq.requests_merged(q, rq, next);
+ else if (e->type->ops.sq.elevator_merge_req_fn) {
+ next_sorted = next->rq_flags & RQF_SORTED;
+ if (next_sorted)
+ e->type->ops.sq.elevator_merge_req_fn(q, rq, next);
+ }
elv_rqhash_reposition(q, rq);
@@ -528,6 +556,9 @@ void elv_bio_merged(struct request_queue *q, struct request *rq,
{
struct elevator_queue *e = q->elevator;
+ if (WARN_ON_ONCE(e->uses_mq))
+ return;
+
if (e->type->ops.sq.elevator_bio_merged_fn)
e->type->ops.sq.elevator_bio_merged_fn(q, rq, bio);
}
@@ -574,11 +605,15 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
void elv_drain_elevator(struct request_queue *q)
{
+ struct elevator_queue *e = q->elevator;
static int printed;
+ if (WARN_ON_ONCE(e->uses_mq))
+ return;
+
lockdep_assert_held(q->queue_lock);
- while (q->elevator->type->ops.sq.elevator_dispatch_fn(q, 1))
+ while (e->type->ops.sq.elevator_dispatch_fn(q, 1))
;
if (q->nr_sorted && printed++ < 10) {
printk(KERN_ERR "%s: forced dispatching is broken "
@@ -682,8 +717,11 @@ struct request *elv_latter_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
- if (e->type->ops.sq.elevator_latter_req_fn)
+ if (e->uses_mq && e->type->ops.mq.next_request)
+ return e->type->ops.mq.next_request(q, rq);
+ else if (!e->uses_mq && e->type->ops.sq.elevator_latter_req_fn)
return e->type->ops.sq.elevator_latter_req_fn(q, rq);
+
return NULL;
}
@@ -691,7 +729,9 @@ struct request *elv_former_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
- if (e->type->ops.sq.elevator_former_req_fn)
+ if (e->uses_mq && e->type->ops.mq.former_request)
+ return e->type->ops.mq.former_request(q, rq);
+ if (!e->uses_mq && e->type->ops.sq.elevator_former_req_fn)
return e->type->ops.sq.elevator_former_req_fn(q, rq);
return NULL;
}
@@ -701,6 +741,9 @@ int elv_set_request(struct request_queue *q, struct request *rq,
{
struct elevator_queue *e = q->elevator;
+ if (WARN_ON_ONCE(e->uses_mq))
+ return 0;
+
if (e->type->ops.sq.elevator_set_req_fn)
return e->type->ops.sq.elevator_set_req_fn(q, rq, bio, gfp_mask);
return 0;
@@ -710,6 +753,9 @@ void elv_put_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
+ if (WARN_ON_ONCE(e->uses_mq))
+ return;
+
if (e->type->ops.sq.elevator_put_req_fn)
e->type->ops.sq.elevator_put_req_fn(rq);
}
@@ -718,6 +764,9 @@ int elv_may_queue(struct request_queue *q, unsigned int op)
{
struct elevator_queue *e = q->elevator;
+ if (WARN_ON_ONCE(e->uses_mq))
+ return 0;
+
if (e->type->ops.sq.elevator_may_queue_fn)
return e->type->ops.sq.elevator_may_queue_fn(q, op);
@@ -728,6 +777,9 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
+ if (WARN_ON_ONCE(e->uses_mq))
+ return;
+
/*
* request is released from the driver, io must be done
*/
@@ -803,7 +855,7 @@ int elv_register_queue(struct request_queue *q)
}
kobject_uevent(&e->kobj, KOBJ_ADD);
e->registered = 1;
- if (e->type->ops.sq.elevator_registered_fn)
+ if (!e->uses_mq && e->type->ops.sq.elevator_registered_fn)
e->type->ops.sq.elevator_registered_fn(q);
}
return error;
@@ -891,9 +943,14 @@ EXPORT_SYMBOL_GPL(elv_unregister);
static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
{
struct elevator_queue *old = q->elevator;
- bool registered = old->registered;
+ bool old_registered = false;
int err;
+ if (q->mq_ops) {
+ blk_mq_freeze_queue(q);
+ blk_mq_quiesce_queue(q);
+ }
+
/*
* Turn on BYPASS and drain all requests w/ elevator private data.
* Block layer doesn't call into a quiesced elevator - all requests
@@ -901,42 +958,76 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
* using INSERT_BACK. All requests have SOFTBARRIER set and no
* merge happens either.
*/
- blk_queue_bypass_start(q);
+ if (old) {
+ old_registered = old->registered;
- /* unregister and clear all auxiliary data of the old elevator */
- if (registered)
- elv_unregister_queue(q);
+ if (old->uses_mq)
+ blk_mq_sched_teardown(q);
- spin_lock_irq(q->queue_lock);
- ioc_clear_queue(q);
- spin_unlock_irq(q->queue_lock);
+ if (!q->mq_ops)
+ blk_queue_bypass_start(q);
+
+ /* unregister and clear all auxiliary data of the old elevator */
+ if (old_registered)
+ elv_unregister_queue(q);
+
+ spin_lock_irq(q->queue_lock);
+ ioc_clear_queue(q);
+ spin_unlock_irq(q->queue_lock);
+ }
/* allocate, init and register new elevator */
- err = new_e->ops.sq.elevator_init_fn(q, new_e);
- if (err)
- goto fail_init;
+ if (new_e) {
+ if (new_e->uses_mq) {
+ err = blk_mq_sched_setup(q);
+ if (!err)
+ err = new_e->ops.mq.init_sched(q, new_e);
+ } else
+ err = new_e->ops.sq.elevator_init_fn(q, new_e);
+ if (err)
+ goto fail_init;
- if (registered) {
err = elv_register_queue(q);
if (err)
goto fail_register;
- }
+ } else
+ q->elevator = NULL;
/* done, kill the old one and finish */
- elevator_exit(old);
- blk_queue_bypass_end(q);
+ if (old) {
+ elevator_exit(old);
+ if (!q->mq_ops)
+ blk_queue_bypass_end(q);
+ }
- blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+ if (q->mq_ops) {
+ blk_mq_unfreeze_queue(q);
+ blk_mq_start_stopped_hw_queues(q, true);
+ }
+
+ if (new_e)
+ blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+ else
+ blk_add_trace_msg(q, "elv switch: none");
return 0;
fail_register:
+ if (q->mq_ops)
+ blk_mq_sched_teardown(q);
elevator_exit(q->elevator);
fail_init:
/* switch failed, restore and re-register old elevator */
- q->elevator = old;
- elv_register_queue(q);
- blk_queue_bypass_end(q);
+ if (old) {
+ q->elevator = old;
+ elv_register_queue(q);
+ if (!q->mq_ops)
+ blk_queue_bypass_end(q);
+ }
+ if (q->mq_ops) {
+ blk_mq_unfreeze_queue(q);
+ blk_mq_start_stopped_hw_queues(q, true);
+ }
return err;
}
@@ -949,8 +1040,11 @@ static int __elevator_change(struct request_queue *q, const char *name)
char elevator_name[ELV_NAME_MAX];
struct elevator_type *e;
- if (!q->elevator)
- return -ENXIO;
+ /*
+ * Special case for mq, turn off scheduling
+ */
+ if (q->mq_ops && !strncmp(name, "none", 4))
+ return elevator_switch(q, NULL);
strlcpy(elevator_name, name, sizeof(elevator_name));
e = elevator_get(strstrip(elevator_name), true);
@@ -959,11 +1053,21 @@ static int __elevator_change(struct request_queue *q, const char *name)
return -EINVAL;
}
- if (!strcmp(elevator_name, q->elevator->type->elevator_name)) {
+ if (q->elevator &&
+ !strcmp(elevator_name, q->elevator->type->elevator_name)) {
elevator_put(e);
return 0;
}
+ if (!e->uses_mq && q->mq_ops) {
+ elevator_put(e);
+ return -EINVAL;
+ }
+ if (e->uses_mq && !q->mq_ops) {
+ elevator_put(e);
+ return -EINVAL;
+ }
+
return elevator_switch(q, e);
}
@@ -985,7 +1089,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
{
int ret;
- if (!q->elevator)
+ if (!(q->mq_ops || q->request_fn))
return count;
ret = __elevator_change(q, name);
@@ -999,24 +1103,34 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
ssize_t elv_iosched_show(struct request_queue *q, char *name)
{
struct elevator_queue *e = q->elevator;
- struct elevator_type *elv;
+ struct elevator_type *elv = NULL;
struct elevator_type *__e;
int len = 0;
- if (!q->elevator || !blk_queue_stackable(q))
+ if (!blk_queue_stackable(q))
return sprintf(name, "none\n");
- elv = e->type;
+ if (!q->elevator)
+ len += sprintf(name+len, "[none] ");
+ else
+ elv = e->type;
spin_lock(&elv_list_lock);
list_for_each_entry(__e, &elv_list, list) {
- if (!strcmp(elv->elevator_name, __e->elevator_name))
+ if (elv && !strcmp(elv->elevator_name, __e->elevator_name)) {
len += sprintf(name+len, "[%s] ", elv->elevator_name);
- else
+ continue;
+ }
+ if (__e->uses_mq && q->mq_ops)
+ len += sprintf(name+len, "%s ", __e->elevator_name);
+ else if (!__e->uses_mq && !q->mq_ops)
len += sprintf(name+len, "%s ", __e->elevator_name);
}
spin_unlock(&elv_list_lock);
+ if (q->mq_ops && q->elevator)
+ len += sprintf(name+len, "none");
+
len += sprintf(len+name, "\n");
return len;
}