redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases Activity

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>
hifive-unleashed-5.1
Jens Axboe 2017-01-17 06:03:22 -07:00
parent 2af8cbe305
commit bd166ef183
17 changed files with 983 additions and 193 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
block/Makefile
View File

@ -6,7 +6,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
blk-mq-sysfs.o blk-mq-cpumap.o ioctl.o \
blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
badblocks.o partitions/

24
block/blk-cgroup.c
View File

@ -1223,7 +1223,11 @@ int blkcg_activate_policy(struct request_queue *q,
if (blkcg_policy_enabled(q, pol))
return 0;
blk_queue_bypass_start(q);
if (q->mq_ops) {
blk_mq_freeze_queue(q);
blk_mq_quiesce_queue(q);
} else
blk_queue_bypass_start(q);
pd_prealloc:
if (!pd_prealloc) {
pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
@ -1261,7 +1265,10 @@ pd_prealloc:
spin_unlock_irq(q->queue_lock);
out_bypass_end:
blk_queue_bypass_end(q);
if (q->mq_ops)
blk_mq_unfreeze_queue(q);
else
blk_queue_bypass_end(q);
if (pd_prealloc)
pol->pd_free_fn(pd_prealloc);
return ret;
@ -1284,7 +1291,12 @@ void blkcg_deactivate_policy(struct request_queue *q,
if (!blkcg_policy_enabled(q, pol))
return;
blk_queue_bypass_start(q);
if (q->mq_ops) {
blk_mq_freeze_queue(q);
blk_mq_quiesce_queue(q);
} else
blk_queue_bypass_start(q);
spin_lock_irq(q->queue_lock);
__clear_bit(pol->plid, q->blkcg_pols);
@ -1304,7 +1316,11 @@ void blkcg_deactivate_policy(struct request_queue *q,
}
spin_unlock_irq(q->queue_lock);
blk_queue_bypass_end(q);
if (q->mq_ops)
blk_mq_unfreeze_queue(q);
else
blk_queue_bypass_end(q);
}
EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);

4
block/blk-core.c
View File

@ -39,6 +39,7 @@
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-sched.h"
#include "blk-wbt.h"
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
@ -134,6 +135,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
rq->cmd = rq->__cmd;
rq->cmd_len = BLK_MAX_CDB;
rq->tag = -1;
rq->internal_tag = -1;
rq->start_time = jiffies;
set_start_time_ns(rq);
rq->part = NULL;
@ -2127,7 +2129,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
if (q->mq_ops) {
if (blk_queue_io_stat(q))
blk_account_io_start(rq, true);
blk_mq_insert_request(rq, false, true, false);
blk_mq_sched_insert_request(rq, false, true, false);
return 0;
}

3
block/blk-exec.c
View File

@ -9,6 +9,7 @@
#include <linux/sched/sysctl.h>
#include "blk.h"
#include "blk-mq-sched.h"
/*
* for max sense size
@ -65,7 +66,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
* be reused after dying flag is set
*/
if (q->mq_ops) {
blk_mq_insert_request(rq, at_head, true, false);
blk_mq_sched_insert_request(rq, at_head, true, false);
return;
}

12
block/blk-flush.c
View File

@ -74,6 +74,7 @@
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"
#include "blk-mq-sched.h"
/* FLUSH/FUA sequences */
enum {
@ -391,9 +392,10 @@ static void mq_flush_data_end_io(struct request *rq, int error)
* the comment in flush_end_io().
*/
spin_lock_irqsave(&fq->mq_flush_lock, flags);
if (blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error))
blk_mq_run_hw_queue(hctx, true);
blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error);
spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
blk_mq_run_hw_queue(hctx, true);
}
/**
@ -453,9 +455,9 @@ void blk_insert_flush(struct request *rq)
*/
if ((policy & REQ_FSEQ_DATA) &&
!(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
if (q->mq_ops) {
blk_mq_insert_request(rq, false, true, false);
} else
if (q->mq_ops)
blk_mq_sched_insert_request(rq, false, true, false);
else
list_add_tail(&rq->queuelist, &q->queue_head);
return;
}

8
block/blk-ioc.c
View File

@ -43,7 +43,9 @@ static void ioc_exit_icq(struct io_cq *icq)
if (icq->flags & ICQ_EXITED)
return;
if (et->ops.sq.elevator_exit_icq_fn)
if (et->uses_mq && et->ops.mq.exit_icq)
et->ops.mq.exit_icq(icq);
else if (!et->uses_mq && et->ops.sq.elevator_exit_icq_fn)
et->ops.sq.elevator_exit_icq_fn(icq);
icq->flags |= ICQ_EXITED;
@ -383,7 +385,9 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) {
hlist_add_head(&icq->ioc_node, &ioc->icq_list);
list_add(&icq->q_node, &q->icq_list);
if (et->ops.sq.elevator_init_icq_fn)
if (et->uses_mq && et->ops.mq.init_icq)
et->ops.mq.init_icq(icq);
else if (!et->uses_mq && et->ops.sq.elevator_init_icq_fn)
et->ops.sq.elevator_init_icq_fn(icq);
} else {
kmem_cache_free(et->icq_cache, icq);

2
block/blk-merge.c
View File

@ -763,7 +763,7 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.sq.elevator_allow_rq_merge_fn)
if (!e->uses_mq && e->type->ops.sq.elevator_allow_rq_merge_fn)
if (!e->type->ops.sq.elevator_allow_rq_merge_fn(q, rq, next))
return 0;

368
block/blk-mq-sched.c 100644
View File

@ -0,0 +1,368 @@
/*
* blk-mq scheduling framework
*
* Copyright (C) 2016 Jens Axboe
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/blk-mq.h>
#include <trace/events/block.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-sched.h"
#include "blk-mq-tag.h"
#include "blk-wbt.h"
void blk_mq_sched_free_hctx_data(struct request_queue *q,
void (*exit)(struct blk_mq_hw_ctx *))
{
struct blk_mq_hw_ctx *hctx;
int i;
queue_for_each_hw_ctx(q, hctx, i) {
if (exit && hctx->sched_data)
exit(hctx);
kfree(hctx->sched_data);
hctx->sched_data = NULL;
}
}
EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
int (*init)(struct blk_mq_hw_ctx *),
void (*exit)(struct blk_mq_hw_ctx *))
{
struct blk_mq_hw_ctx *hctx;
int ret;
int i;
queue_for_each_hw_ctx(q, hctx, i) {
hctx->sched_data = kmalloc_node(size, GFP_KERNEL, hctx->numa_node);
if (!hctx->sched_data) {
ret = -ENOMEM;
goto error;
}
if (init) {
ret = init(hctx);
if (ret) {
/*
* We don't want to give exit() a partially
* initialized sched_data. init() must clean up
* if it fails.
*/
kfree(hctx->sched_data);
hctx->sched_data = NULL;
goto error;
}
}
}
return 0;
error:
blk_mq_sched_free_hctx_data(q, exit);
return ret;
}
EXPORT_SYMBOL_GPL(blk_mq_sched_init_hctx_data);
static void __blk_mq_sched_assign_ioc(struct request_queue *q,
struct request *rq, struct io_context *ioc)
{
struct io_cq *icq;
spin_lock_irq(q->queue_lock);
icq = ioc_lookup_icq(ioc, q);
spin_unlock_irq(q->queue_lock);
if (!icq) {
icq = ioc_create_icq(ioc, q, GFP_ATOMIC);
if (!icq)
return;
}
rq->elv.icq = icq;
if (!blk_mq_sched_get_rq_priv(q, rq)) {
rq->rq_flags |= RQF_ELVPRIV;
get_io_context(icq->ioc);
return;
}
rq->elv.icq = NULL;
}
static void blk_mq_sched_assign_ioc(struct request_queue *q,
struct request *rq, struct bio *bio)
{
struct io_context *ioc;
ioc = rq_ioc(bio);
if (ioc)
__blk_mq_sched_assign_ioc(q, rq, ioc);
}
struct request *blk_mq_sched_get_request(struct request_queue *q,
struct bio *bio,
unsigned int op,
struct blk_mq_alloc_data *data)
{
struct elevator_queue *e = q->elevator;
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
struct request *rq;
const bool is_flush = op & (REQ_PREFLUSH | REQ_FUA);
blk_queue_enter_live(q);
ctx = blk_mq_get_ctx(q);
hctx = blk_mq_map_queue(q, ctx->cpu);
blk_mq_set_alloc_data(data, q, 0, ctx, hctx);
if (e) {
data->flags |= BLK_MQ_REQ_INTERNAL;
/*
* Flush requests are special and go directly to the
* dispatch list.
*/
if (!is_flush && e->type->ops.mq.get_request) {
rq = e->type->ops.mq.get_request(q, op, data);
if (rq)
rq->rq_flags |= RQF_QUEUED;
} else
rq = __blk_mq_alloc_request(data, op);
} else {
rq = __blk_mq_alloc_request(data, op);
data->hctx->tags->rqs[rq->tag] = rq;
}
if (rq) {
if (!is_flush) {
rq->elv.icq = NULL;
if (e && e->type->icq_cache)
blk_mq_sched_assign_ioc(q, rq, bio);
}
data->hctx->queued++;
return rq;
}
blk_queue_exit(q);
return NULL;
}
void blk_mq_sched_put_request(struct request *rq)
{
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
if (rq->rq_flags & RQF_ELVPRIV) {
blk_mq_sched_put_rq_priv(rq->q, rq);
if (rq->elv.icq) {
put_io_context(rq->elv.icq->ioc);
rq->elv.icq = NULL;
}
}
if ((rq->rq_flags & RQF_QUEUED) && e && e->type->ops.mq.put_request)
e->type->ops.mq.put_request(rq);
else
blk_mq_finish_request(rq);
}
void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
{
struct elevator_queue *e = hctx->queue->elevator;
LIST_HEAD(rq_list);
if (unlikely(blk_mq_hctx_stopped(hctx)))
return;
hctx->run++;
/*
* If we have previous entries on our dispatch list, grab them first for
* more fair dispatch.
*/
if (!list_empty_careful(&hctx->dispatch)) {
spin_lock(&hctx->lock);
if (!list_empty(&hctx->dispatch))
list_splice_init(&hctx->dispatch, &rq_list);
spin_unlock(&hctx->lock);
}
/*
* Only ask the scheduler for requests, if we didn't have residual
* requests from the dispatch list. This is to avoid the case where
* we only ever dispatch a fraction of the requests available because
* of low device queue depth. Once we pull requests out of the IO
* scheduler, we can no longer merge or sort them. So it's best to
* leave them there for as long as we can. Mark the hw queue as
* needing a restart in that case.
*/
if (list_empty(&rq_list)) {
if (e && e->type->ops.mq.dispatch_requests)
e->type->ops.mq.dispatch_requests(hctx, &rq_list);
else
blk_mq_flush_busy_ctxs(hctx, &rq_list);
} else
blk_mq_sched_mark_restart(hctx);
blk_mq_dispatch_rq_list(hctx, &rq_list);
}
void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
struct list_head *rq_list,
struct request *(*get_rq)(struct blk_mq_hw_ctx *))
{
do {
struct request *rq;
rq = get_rq(hctx);
if (!rq)
break;
list_add_tail(&rq->queuelist, rq_list);
} while (1);
}
EXPORT_SYMBOL_GPL(blk_mq_sched_move_to_dispatch);
bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio)
{
struct request *rq;
int ret;
ret = elv_merge(q, &rq, bio);
if (ret == ELEVATOR_BACK_MERGE) {
if (!blk_mq_sched_allow_merge(q, rq, bio))
return false;
if (bio_attempt_back_merge(q, rq, bio)) {
if (!attempt_back_merge(q, rq))
elv_merged_request(q, rq, ret);
return true;
}
} else if (ret == ELEVATOR_FRONT_MERGE) {
if (!blk_mq_sched_allow_merge(q, rq, bio))
return false;
if (bio_attempt_front_merge(q, rq, bio)) {
if (!attempt_front_merge(q, rq))
elv_merged_request(q, rq, ret);
return true;
}
}
return false;
}
EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.mq.bio_merge) {
struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
blk_mq_put_ctx(ctx);
return e->type->ops.mq.bio_merge(hctx, bio);
}
return false;
}
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq)
{
return rq_mergeable(rq) && elv_attempt_insert_merge(q, rq);
}
EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge);
void blk_mq_sched_request_inserted(struct request *rq)
{
trace_block_rq_insert(rq->q, rq);
}
EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);
bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq)
{
if (rq->tag == -1) {
rq->rq_flags |= RQF_SORTED;
return false;
}
/*
* If we already have a real request tag, send directly to
* the dispatch list.
*/
spin_lock(&hctx->lock);
list_add(&rq->queuelist, &hctx->dispatch);
spin_unlock(&hctx->lock);
return true;
}
EXPORT_SYMBOL_GPL(blk_mq_sched_bypass_insert);
static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
struct blk_mq_hw_ctx *hctx,
unsigned int hctx_idx)
{
if (hctx->sched_tags) {
blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx);
blk_mq_free_rq_map(hctx->sched_tags);
hctx->sched_tags = NULL;
}
}
int blk_mq_sched_setup(struct request_queue *q)
{
struct blk_mq_tag_set *set = q->tag_set;
struct blk_mq_hw_ctx *hctx;
int ret, i;
/*
* Default to 256, since we don't split into sync/async like the
* old code did. Additionally, this is a per-hw queue depth.
*/
q->nr_requests = 2 * BLKDEV_MAX_RQ;
/*
* We're switching to using an IO scheduler, so setup the hctx
* scheduler tags and switch the request map from the regular
* tags to scheduler tags. First allocate what we need, so we
* can safely fail and fallback, if needed.
*/
ret = 0;
queue_for_each_hw_ctx(q, hctx, i) {
hctx->sched_tags = blk_mq_alloc_rq_map(set, i, q->nr_requests, 0);
if (!hctx->sched_tags) {
ret = -ENOMEM;
break;
}
ret = blk_mq_alloc_rqs(set, hctx->sched_tags, i, q->nr_requests);
if (ret)
break;
}
/*
* If we failed, free what we did allocate
*/
if (ret) {
queue_for_each_hw_ctx(q, hctx, i) {
if (!hctx->sched_tags)
continue;
blk_mq_sched_free_tags(set, hctx, i);
}
return ret;
}
return 0;
}
void blk_mq_sched_teardown(struct request_queue *q)
{
struct blk_mq_tag_set *set = q->tag_set;
struct blk_mq_hw_ctx *hctx;
int i;
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_sched_free_tags(set, hctx, i);
}

170
block/blk-mq-sched.h 100644
View File

@ -0,0 +1,170 @@
#ifndef BLK_MQ_SCHED_H
#define BLK_MQ_SCHED_H
#include "blk-mq.h"
#include "blk-mq-tag.h"
int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
int (*init)(struct blk_mq_hw_ctx *),
void (*exit)(struct blk_mq_hw_ctx *));
void blk_mq_sched_free_hctx_data(struct request_queue *q,
void (*exit)(struct blk_mq_hw_ctx *));
struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bio, unsigned int op, struct blk_mq_alloc_data *data);
void blk_mq_sched_put_request(struct request *rq);
void blk_mq_sched_request_inserted(struct request *rq);
bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq);
bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio);
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
struct list_head *rq_list,
struct request *(*get_rq)(struct blk_mq_hw_ctx *));
int blk_mq_sched_setup(struct request_queue *q);
void blk_mq_sched_teardown(struct request_queue *q);
static inline bool
blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
struct elevator_queue *e = q->elevator;
if (!e || blk_queue_nomerges(q) || !bio_mergeable(bio))
return false;
return __blk_mq_sched_bio_merge(q, bio);
}
static inline int blk_mq_sched_get_rq_priv(struct request_queue *q,
struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e && e->type->ops.mq.get_rq_priv)
return e->type->ops.mq.get_rq_priv(q, rq);
return 0;
}
static inline void blk_mq_sched_put_rq_priv(struct request_queue *q,
struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e && e->type->ops.mq.put_rq_priv)
e->type->ops.mq.put_rq_priv(q, rq);
}
static inline void
blk_mq_sched_insert_request(struct request *rq, bool at_head, bool run_queue,
bool async)
{
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
struct blk_mq_ctx *ctx = rq->mq_ctx;
struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
if (e && e->type->ops.mq.insert_requests) {
LIST_HEAD(list);
list_add(&rq->queuelist, &list);
e->type->ops.mq.insert_requests(hctx, &list, at_head);
} else {
spin_lock(&ctx->lock);
__blk_mq_insert_request(hctx, rq, at_head);
spin_unlock(&ctx->lock);
}
if (run_queue)
blk_mq_run_hw_queue(hctx, async);
}
static inline void
blk_mq_sched_insert_requests(struct request_queue *q, struct blk_mq_ctx *ctx,
struct list_head *list, bool run_queue_async)
{
struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
struct elevator_queue *e = hctx->queue->elevator;
if (e && e->type->ops.mq.insert_requests)
e->type->ops.mq.insert_requests(hctx, list, false);
else
blk_mq_insert_requests(hctx, ctx, list);
blk_mq_run_hw_queue(hctx, run_queue_async);
}
static inline bool
blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
struct bio *bio)
{
struct elevator_queue *e = q->elevator;
if (e && e->type->ops.mq.allow_merge)
return e->type->ops.mq.allow_merge(q, rq, bio);
return true;
}
static inline void
blk_mq_sched_completed_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
{
struct elevator_queue *e = hctx->queue->elevator;
if (e && e->type->ops.mq.completed_request)
e->type->ops.mq.completed_request(hctx, rq);
BUG_ON(rq->internal_tag == -1);
blk_mq_put_tag(hctx, hctx->sched_tags, rq->mq_ctx, rq->internal_tag);
if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
blk_mq_run_hw_queue(hctx, true);
}
}
static inline void blk_mq_sched_started_request(struct request *rq)
{
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
if (e && e->type->ops.mq.started_request)
e->type->ops.mq.started_request(rq);
}
static inline void blk_mq_sched_requeue_request(struct request *rq)
{
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
if (e && e->type->ops.mq.requeue_request)
e->type->ops.mq.requeue_request(rq);
}
static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx)
{
struct elevator_queue *e = hctx->queue->elevator;
if (e && e->type->ops.mq.has_work)
return e->type->ops.mq.has_work(hctx);
return false;
}
static inline void blk_mq_sched_mark_restart(struct blk_mq_hw_ctx *hctx)
{
if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
}
static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
{
return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
}
#endif

13
block/blk-mq-sysfs.c
View File

@ -231,6 +231,14 @@ static ssize_t blk_mq_hw_sysfs_rq_list_show(struct blk_mq_hw_ctx *hctx,
return ret;
}
static ssize_t blk_mq_hw_sysfs_sched_tags_show(struct blk_mq_hw_ctx *hctx, char *page)
{
if (hctx->sched_tags)
return blk_mq_tag_sysfs_show(hctx->sched_tags, page);
return 0;
}
static ssize_t blk_mq_hw_sysfs_tags_show(struct blk_mq_hw_ctx *hctx, char *page)
{
return blk_mq_tag_sysfs_show(hctx->tags, page);
@ -345,6 +353,10 @@ static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_pending = {
.attr = {.name = "pending", .mode = S_IRUGO },
.show = blk_mq_hw_sysfs_rq_list_show,
};
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_sched_tags = {
.attr = {.name = "sched_tags", .mode = S_IRUGO },
.show = blk_mq_hw_sysfs_sched_tags_show,
};
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_tags = {
.attr = {.name = "tags", .mode = S_IRUGO },
.show = blk_mq_hw_sysfs_tags_show,
@ -370,6 +382,7 @@ static struct attribute *default_hw_ctx_attrs[] = {
&blk_mq_hw_sysfs_dispatched.attr,
&blk_mq_hw_sysfs_pending.attr,
&blk_mq_hw_sysfs_tags.attr,
&blk_mq_hw_sysfs_sched_tags.attr,
&blk_mq_hw_sysfs_cpus.attr,
&blk_mq_hw_sysfs_active.attr,
&blk_mq_hw_sysfs_poll.attr,

318
block/blk-mq.c
View File

@ -32,6 +32,7 @@
#include "blk-mq-tag.h"
#include "blk-stat.h"
#include "blk-wbt.h"
#include "blk-mq-sched.h"
static DEFINE_MUTEX(all_q_mutex);
static LIST_HEAD(all_q_list);
@ -41,7 +42,9 @@ static LIST_HEAD(all_q_list);
*/
static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
{
return sbitmap_any_bit_set(&hctx->ctx_map);
return sbitmap_any_bit_set(&hctx->ctx_map) ||
!list_empty_careful(&hctx->dispatch) ||
blk_mq_sched_has_work(hctx);
}
/*
@ -223,15 +226,23 @@ struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
tag = blk_mq_get_tag(data);
if (tag != BLK_MQ_TAG_FAIL) {
rq = data->hctx->tags->static_rqs[tag];
struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
rq = tags->static_rqs[tag];
if (blk_mq_tag_busy(data->hctx)) {
rq->rq_flags = RQF_MQ_INFLIGHT;
atomic_inc(&data->hctx->nr_active);
}
rq->tag = tag;
data->hctx->tags->rqs[tag] = rq;
if (data->flags & BLK_MQ_REQ_INTERNAL) {
rq->tag = -1;
rq->internal_tag = tag;
} else {
rq->tag = tag;
rq->internal_tag = -1;
}
blk_mq_rq_ctx_init(data->q, data->ctx, rq, op);
return rq;
}
@ -243,26 +254,21 @@ EXPORT_SYMBOL_GPL(__blk_mq_alloc_request);
struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
unsigned int flags)
{
struct blk_mq_ctx *ctx;
struct blk_mq_hw_ctx *hctx;
struct request *rq;
struct blk_mq_alloc_data alloc_data;
struct request *rq;
int ret;
ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT);
if (ret)
return ERR_PTR(ret);
ctx = blk_mq_get_ctx(q);
hctx = blk_mq_map_queue(q, ctx->cpu);
blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
rq = __blk_mq_alloc_request(&alloc_data, rw);
blk_mq_put_ctx(ctx);
rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
if (!rq) {
blk_queue_exit(q);
blk_mq_put_ctx(alloc_data.ctx);
blk_queue_exit(q);
if (!rq)
return ERR_PTR(-EWOULDBLOCK);
}
rq->__data_len = 0;
rq->__sector = (sector_t) -1;
@ -322,10 +328,10 @@ out_queue_exit:
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
struct request *rq)
void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
struct request *rq)
{
const int tag = rq->tag;
const int sched_tag = rq->internal_tag;
struct request_queue *q = rq->q;
if (rq->rq_flags & RQF_MQ_INFLIGHT)
@ -336,22 +342,30 @@ void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
blk_mq_put_tag(hctx, hctx->tags, ctx, tag);
if (rq->tag != -1)
blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
if (sched_tag != -1)
blk_mq_sched_completed_request(hctx, rq);
blk_queue_exit(q);
}
static void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *hctx,
static void blk_mq_finish_hctx_request(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
ctx->rq_completed[rq_is_sync(rq)]++;
__blk_mq_free_request(hctx, ctx, rq);
__blk_mq_finish_request(hctx, ctx, rq);
}
void blk_mq_finish_request(struct request *rq)
{
blk_mq_finish_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
}
void blk_mq_free_request(struct request *rq)
{
blk_mq_free_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
blk_mq_sched_put_request(rq);
}
EXPORT_SYMBOL_GPL(blk_mq_free_request);
@ -469,6 +483,8 @@ void blk_mq_start_request(struct request *rq)
{
struct request_queue *q = rq->q;
blk_mq_sched_started_request(rq);
trace_block_rq_issue(q, rq);
rq->resid_len = blk_rq_bytes(rq);
@ -517,6 +533,7 @@ static void __blk_mq_requeue_request(struct request *rq)
trace_block_rq_requeue(q, rq);
wbt_requeue(q->rq_wb, &rq->issue_stat);
blk_mq_sched_requeue_request(rq);
if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
if (q->dma_drain_size && blk_rq_bytes(rq))
@ -551,13 +568,13 @@ static void blk_mq_requeue_work(struct work_struct *work)
rq->rq_flags &= ~RQF_SOFTBARRIER;
list_del_init(&rq->queuelist);
blk_mq_insert_request(rq, true, false, false);
blk_mq_sched_insert_request(rq, true, false, false);
}
while (!list_empty(&rq_list)) {
rq = list_entry(rq_list.next, struct request, queuelist);
list_del_init(&rq->queuelist);
blk_mq_insert_request(rq, false, false, false);
blk_mq_sched_insert_request(rq, false, false, false);
}
blk_mq_run_hw_queues(q, false);
@ -765,6 +782,12 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
continue;
el_ret = blk_try_merge(rq, bio);
if (el_ret == ELEVATOR_NO_MERGE)
continue;
if (!blk_mq_sched_allow_merge(q, rq, bio))
break;
if (el_ret == ELEVATOR_BACK_MERGE) {
if (bio_attempt_back_merge(q, rq, bio)) {
ctx->rq_merged++;
@ -824,6 +847,59 @@ static inline unsigned int queued_to_index(unsigned int queued)
return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
}
static bool blk_mq_get_driver_tag(struct request *rq,
struct blk_mq_hw_ctx **hctx, bool wait)
{
struct blk_mq_alloc_data data = {
.q = rq->q,
.ctx = rq->mq_ctx,
.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
};
if (blk_mq_hctx_stopped(data.hctx))
return false;
if (rq->tag != -1) {
done:
if (hctx)
*hctx = data.hctx;
return true;
}
rq->tag = blk_mq_get_tag(&data);
if (rq->tag >= 0) {
data.hctx->tags->rqs[rq->tag] = rq;
goto done;
}
return false;
}
/*
* If we fail getting a driver tag because all the driver tags are already
* assigned and on the dispatch list, BUT the first entry does not have a
* tag, then we could deadlock. For that case, move entries with assigned
* driver tags to the front, leaving the set of tagged requests in the
* same order, and the untagged set in the same order.
*/
static bool reorder_tags_to_front(struct list_head *list)
{
struct request *rq, *tmp, *first = NULL;
list_for_each_entry_safe_reverse(rq, tmp, list, queuelist) {
if (rq == first)
break;
if (rq->tag != -1) {
list_move(&rq->queuelist, list);
if (!first)
first = rq;
}
}
return first != NULL;
}
bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
{
struct request_queue *q = hctx->queue;
@ -846,6 +922,12 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
struct blk_mq_queue_data bd;
rq = list_first_entry(list, struct request, queuelist);
if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
if (!queued && reorder_tags_to_front(list))
continue;
blk_mq_sched_mark_restart(hctx);
break;
}
list_del_init(&rq->queuelist);
bd.rq = rq;
@ -899,48 +981,17 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
* the requests in rq_list might get lost.
*
* blk_mq_run_hw_queue() already checks the STOPPED bit
**/
blk_mq_run_hw_queue(hctx, true);
*
* If RESTART is set, then let completion restart the queue
* instead of potentially looping here.
*/
if (!blk_mq_sched_needs_restart(hctx))
blk_mq_run_hw_queue(hctx, true);
}
return ret != BLK_MQ_RQ_QUEUE_BUSY;
}
/*
* Run this hardware queue, pulling any software queues mapped to it in.
* Note that this function currently has various problems around ordering
* of IO. In particular, we'd like FIFO behaviour on handling existing
* items on the hctx->dispatch list. Ignore that for now.
*/
static void blk_mq_process_rq_list(struct blk_mq_hw_ctx *hctx)
{
LIST_HEAD(rq_list);
LIST_HEAD(driver_list);
if (unlikely(blk_mq_hctx_stopped(hctx)))
return;
hctx->run++;
/*
* Touch any software queue that has pending entries.
*/
blk_mq_flush_busy_ctxs(hctx, &rq_list);
/*
* If we have previous entries on our dispatch list, grab them
* and stuff them at the front for more fair dispatch.
*/
if (!list_empty_careful(&hctx->dispatch)) {
spin_lock(&hctx->lock);
if (!list_empty(&hctx->dispatch))
list_splice_init(&hctx->dispatch, &rq_list);
spin_unlock(&hctx->lock);
}
blk_mq_dispatch_rq_list(hctx, &rq_list);
}
static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
{
int srcu_idx;
@ -950,11 +1001,11 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
rcu_read_lock();
blk_mq_process_rq_list(hctx);
blk_mq_sched_dispatch_requests(hctx);
rcu_read_unlock();
} else {
srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
blk_mq_process_rq_list(hctx);
blk_mq_sched_dispatch_requests(hctx);
srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
}
}
@ -1010,8 +1061,7 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async)
int i;
queue_for_each_hw_ctx(q, hctx, i) {
if ((!blk_mq_hctx_has_pending(hctx) &&
list_empty_careful(&hctx->dispatch)) ||
if (!blk_mq_hctx_has_pending(hctx) ||
blk_mq_hctx_stopped(hctx))
continue;
@ -1148,32 +1198,10 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
blk_mq_hctx_mark_pending(hctx, ctx);
}
void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
bool async)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
struct request_queue *q = rq->q;
struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
spin_lock(&ctx->lock);
__blk_mq_insert_request(hctx, rq, at_head);
spin_unlock(&ctx->lock);
if (run_queue)
blk_mq_run_hw_queue(hctx, async);
}
static void blk_mq_insert_requests(struct request_queue *q,
struct blk_mq_ctx *ctx,
struct list_head *list,
int depth,
bool from_schedule)
void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
struct list_head *list)
{
struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
trace_block_unplug(q, depth, !from_schedule);
/*
* preemption doesn't flush plug list, so it's possible ctx->cpu is
* offline now
@ -1189,8 +1217,6 @@ static void blk_mq_insert_requests(struct request_queue *q,
}
blk_mq_hctx_mark_pending(hctx, ctx);
spin_unlock(&ctx->lock);
blk_mq_run_hw_queue(hctx, from_schedule);
}
static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
@ -1226,9 +1252,10 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
BUG_ON(!rq->q);
if (rq->mq_ctx != this_ctx) {
if (this_ctx) {
blk_mq_insert_requests(this_q, this_ctx,
&ctx_list, depth,
from_schedule);
trace_block_unplug(this_q, depth, from_schedule);
blk_mq_sched_insert_requests(this_q, this_ctx,
&ctx_list,
from_schedule);
}
this_ctx = rq->mq_ctx;
@ -1245,8 +1272,9 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
* on 'ctx_list'. Do those.
*/
if (this_ctx) {
blk_mq_insert_requests(this_q, this_ctx, &ctx_list, depth,
from_schedule);
trace_block_unplug(this_q, depth, from_schedule);
blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
from_schedule);
}
}
@ -1284,51 +1312,39 @@ insert_rq:
}
spin_unlock(&ctx->lock);
__blk_mq_free_request(hctx, ctx, rq);
__blk_mq_finish_request(hctx, ctx, rq);
return true;
}
}
static struct request *blk_mq_map_request(struct request_queue *q,
struct bio *bio,
struct blk_mq_alloc_data *data)
{
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
struct request *rq;
blk_queue_enter_live(q);
ctx = blk_mq_get_ctx(q);
hctx = blk_mq_map_queue(q, ctx->cpu);
trace_block_getrq(q, bio, bio->bi_opf);
blk_mq_set_alloc_data(data, q, 0, ctx, hctx);
rq = __blk_mq_alloc_request(data, bio->bi_opf);
data->hctx->queued++;
return rq;
}
static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
{
return blk_tag_to_qc_t(rq->tag, hctx->queue_num, false);
if (rq->tag != -1)
return blk_tag_to_qc_t(rq->tag, hctx->queue_num, false);
return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
}
static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
{
int ret;
struct request_queue *q = rq->q;
struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
struct blk_mq_queue_data bd = {
.rq = rq,
.list = NULL,
.last = 1
};
blk_qc_t new_cookie = request_to_qc_t(hctx, rq);
struct blk_mq_hw_ctx *hctx;
blk_qc_t new_cookie;
int ret;
if (blk_mq_hctx_stopped(hctx))
if (q->elevator)
goto insert;
if (!blk_mq_get_driver_tag(rq, &hctx, false))
goto insert;
new_cookie = request_to_qc_t(hctx, rq);
/*
* For OK queue, we are done. For error, kill it. Any other
* error (busy), just add it to our list as we previously
@ -1350,7 +1366,7 @@ static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
}
insert:
blk_mq_insert_request(rq, false, true, true);
blk_mq_sched_insert_request(rq, false, true, true);
}
/*
@ -1383,9 +1399,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
return BLK_QC_T_NONE;
if (blk_mq_sched_bio_merge(q, bio))
return BLK_QC_T_NONE;
wb_acct = wbt_wait(q->rq_wb, bio, NULL);
rq = blk_mq_map_request(q, bio, &data);
trace_block_getrq(q, bio, bio->bi_opf);
rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
if (unlikely(!rq)) {
__wbt_done(q->rq_wb, wb_acct);
return BLK_QC_T_NONE;
@ -1397,6 +1418,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
if (unlikely(is_flush_fua)) {
blk_mq_bio_to_request(rq, bio);
blk_mq_get_driver_tag(rq, NULL, true);
blk_insert_flush(rq);
goto run_queue;
}
@ -1447,6 +1469,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
goto done;
}
if (q->elevator) {
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
blk_mq_sched_insert_request(rq, false, true, true);
goto done;
}
if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
/*
* For a SYNC request, send it to the hardware immediately. For
@ -1492,9 +1520,14 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
} else
request_count = blk_plug_queued_count(q);
if (blk_mq_sched_bio_merge(q, bio))
return BLK_QC_T_NONE;
wb_acct = wbt_wait(q->rq_wb, bio, NULL);
rq = blk_mq_map_request(q, bio, &data);
trace_block_getrq(q, bio, bio->bi_opf);
rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
if (unlikely(!rq)) {
__wbt_done(q->rq_wb, wb_acct);
return BLK_QC_T_NONE;
@ -1506,6 +1539,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
if (unlikely(is_flush_fua)) {
blk_mq_bio_to_request(rq, bio);
blk_mq_get_driver_tag(rq, NULL, true);
blk_insert_flush(rq);
goto run_queue;
}
@ -1544,6 +1578,12 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
return cookie;
}
if (q->elevator) {
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
blk_mq_sched_insert_request(rq, false, true, true);
goto done;
}
if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
/*
* For a SYNC request, send it to the hardware immediately. For
@ -1556,6 +1596,7 @@ run_queue:
}
blk_mq_put_ctx(data.ctx);
done:
return cookie;
}
@ -1925,9 +1966,11 @@ static bool __blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, int hctx_idx)
static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
unsigned int hctx_idx)
{
blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx);
blk_mq_free_rq_map(set->tags[hctx_idx]);
set->tags[hctx_idx] = NULL;
if (set->tags[hctx_idx]) {
blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx);
blk_mq_free_rq_map(set->tags[hctx_idx]);
set->tags[hctx_idx] = NULL;
}
}
static void blk_mq_map_swqueue(struct request_queue *q,
@ -2084,6 +2127,8 @@ void blk_mq_release(struct request_queue *q)
struct blk_mq_hw_ctx *hctx;
unsigned int i;
blk_mq_sched_teardown(q);
/* hctx kobj stays in hctx */
queue_for_each_hw_ctx(q, hctx, i) {
if (!hctx)
@ -2504,14 +2549,22 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
struct blk_mq_hw_ctx *hctx;
int i, ret;
if (!set || nr > set->queue_depth)
if (!set)
return -EINVAL;
ret = 0;
queue_for_each_hw_ctx(q, hctx, i) {
if (!hctx->tags)
continue;
ret = blk_mq_tag_update_depth(hctx->tags, nr);
/*
* If we're using an MQ scheduler, just update the scheduler
* queue depth. This is similar to what the old code would do.
*/
if (!hctx->sched_tags)
ret = blk_mq_tag_update_depth(hctx->tags,
min(nr, set->queue_depth));
else
ret = blk_mq_tag_update_depth(hctx->sched_tags, nr);
if (ret)
break;
}
@ -2704,7 +2757,10 @@ bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
blk_flush_plug_list(plug, false);
hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
if (!blk_qc_t_is_internal(cookie))
rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
else
rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie));
return __blk_mq_poll(hctx, rq);
}

8
block/blk-mq.h
View File

@ -52,6 +52,8 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
*/
void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
bool at_head);
void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
struct list_head *list);
/*
* CPU hotplug helpers
*/
@ -124,6 +126,9 @@ static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
{
if (data->flags & BLK_MQ_REQ_INTERNAL)
return data->hctx->sched_tags;
return data->hctx->tags;
}
@ -132,8 +137,9 @@ static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data
*/
void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
struct request *rq, unsigned int op);
void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
struct request *rq);
void blk_mq_finish_request(struct request *rq);
struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
unsigned int op);

1
block/blk-tag.c
View File

@ -272,6 +272,7 @@ void blk_queue_end_tag(struct request_queue *q, struct request *rq)
list_del_init(&rq->queuelist);
rq->rq_flags &= ~RQF_QUEUED;
rq->tag = -1;
rq->internal_tag = -1;
if (unlikely(bqt->tag_index[tag] == NULL))
printk(KERN_ERR "%s: tag %d is missing\n",

202
block/elevator.c
View File

@ -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;
}

5
include/linux/blk-mq.h
View File

@ -22,6 +22,7 @@ struct blk_mq_hw_ctx {
unsigned long flags; /* BLK_MQ_F_* flags */
void *sched_data;
struct request_queue *queue;
struct blk_flush_queue *fq;
@ -35,6 +36,7 @@ struct blk_mq_hw_ctx {
atomic_t wait_index;
struct blk_mq_tags *tags;
struct blk_mq_tags *sched_tags;
struct srcu_struct queue_rq_srcu;
@ -156,6 +158,7 @@ enum {
BLK_MQ_S_STOPPED = 0,
BLK_MQ_S_TAG_ACTIVE = 1,
BLK_MQ_S_SCHED_RESTART = 2,
BLK_MQ_MAX_DEPTH = 10240,
@ -179,13 +182,13 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
void blk_mq_insert_request(struct request *, bool, bool, bool);
void blk_mq_free_request(struct request *rq);
bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
enum {
BLK_MQ_REQ_NOWAIT = (1 << 0), /* return when out of requests */
BLK_MQ_REQ_RESERVED = (1 << 1), /* allocate from reserved pool */
BLK_MQ_REQ_INTERNAL = (1 << 2), /* allocate internal/sched tag */
};
struct request *blk_mq_alloc_request(struct request_queue *q, int rw,

4
include/linux/blkdev.h
View File

@ -154,6 +154,7 @@ struct request {
/* the following two fields are internal, NEVER access directly */
unsigned int __data_len; /* total data len */
int tag;
sector_t __sector; /* sector cursor */
struct bio *bio;
@ -220,9 +221,10 @@ struct request {
unsigned short ioprio;
int internal_tag;
void *special; /* opaque pointer available for LLD use */
int tag;
int errors;
/*

32
include/linux/elevator.h
View File

@ -77,6 +77,34 @@ struct elevator_ops
elevator_registered_fn *elevator_registered_fn;
};
struct blk_mq_alloc_data;
struct blk_mq_hw_ctx;
struct elevator_mq_ops {
int (*init_sched)(struct request_queue *, struct elevator_type *);
void (*exit_sched)(struct elevator_queue *);
bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *);
int (*request_merge)(struct request_queue *q, struct request **, struct bio *);
void (*request_merged)(struct request_queue *, struct request *, int);
void (*requests_merged)(struct request_queue *, struct request *, struct request *);
struct request *(*get_request)(struct request_queue *, unsigned int, struct blk_mq_alloc_data *);
void (*put_request)(struct request *);
void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
void (*dispatch_requests)(struct blk_mq_hw_ctx *, struct list_head *);
bool (*has_work)(struct blk_mq_hw_ctx *);
void (*completed_request)(struct blk_mq_hw_ctx *, struct request *);
void (*started_request)(struct request *);
void (*requeue_request)(struct request *);
struct request *(*former_request)(struct request_queue *, struct request *);
struct request *(*next_request)(struct request_queue *, struct request *);
int (*get_rq_priv)(struct request_queue *, struct request *);
void (*put_rq_priv)(struct request_queue *, struct request *);
void (*init_icq)(struct io_cq *);
void (*exit_icq)(struct io_cq *);
};
#define ELV_NAME_MAX (16)
struct elv_fs_entry {
@ -96,12 +124,14 @@ struct elevator_type
/* fields provided by elevator implementation */
union {
struct elevator_ops sq;
struct elevator_mq_ops mq;
} ops;
size_t icq_size; /* see iocontext.h */
size_t icq_align; /* ditto */
struct elv_fs_entry *elevator_attrs;
char elevator_name[ELV_NAME_MAX];
struct module *elevator_owner;
bool uses_mq;
/* managed by elevator core */
char icq_cache_name[ELV_NAME_MAX + 5]; /* elvname + "_io_cq" */
@ -125,6 +155,7 @@ struct elevator_queue
struct kobject kobj;
struct mutex sysfs_lock;
unsigned int registered:1;
unsigned int uses_mq:1;
DECLARE_HASHTABLE(hash, ELV_HASH_BITS);
};
@ -141,6 +172,7 @@ extern void elv_merge_requests(struct request_queue *, struct request *,
extern void elv_merged_request(struct request_queue *, struct request *, int);
extern void elv_bio_merged(struct request_queue *q, struct request *,
struct bio *);
extern bool elv_attempt_insert_merge(struct request_queue *, struct request *);
extern void elv_requeue_request(struct request_queue *, struct request *);
extern struct request *elv_former_request(struct request_queue *, struct request *);
extern struct request *elv_latter_request(struct request_queue *, struct request *);