From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/block/blk-mq-sched.c | 481 ++++++++++++++++++++++++++++++++--------------------
1 files changed, 294 insertions(+), 187 deletions(-)
diff --git a/kernel/block/blk-mq-sched.c b/kernel/block/blk-mq-sched.c
index d89a757..91b7626 100644
--- a/kernel/block/blk-mq-sched.c
+++ b/kernel/block/blk-mq-sched.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* blk-mq scheduling framework
*
@@ -6,6 +7,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/blk-mq.h>
+#include <linux/list_sort.h>
#include <trace/events/block.h>
@@ -16,30 +18,22 @@
#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);
-
-void blk_mq_sched_assign_ioc(struct request *rq, struct bio *bio)
+void blk_mq_sched_assign_ioc(struct request *rq)
{
struct request_queue *q = rq->q;
- struct io_context *ioc = rq_ioc(bio);
+ struct io_context *ioc;
struct io_cq *icq;
- spin_lock_irq(q->queue_lock);
+ /*
+ * May not have an IO context if it's a passthrough request
+ */
+ ioc = current->io_context;
+ if (!ioc)
+ return;
+
+ spin_lock_irq(&q->queue_lock);
icq = ioc_lookup_icq(ioc, q);
- spin_unlock_irq(q->queue_lock);
+ spin_unlock_irq(&q->queue_lock);
if (!icq) {
icq = ioc_create_icq(ioc, q, GFP_ATOMIC);
@@ -51,8 +45,7 @@
}
/*
- * Mark a hardware queue as needing a restart. For shared queues, maintain
- * a count of how many hardware queues are marked for restart.
+ * Mark a hardware queue as needing a restart.
*/
void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
{
@@ -81,30 +74,85 @@
blk_mq_run_hw_queue(hctx, true);
}
+static int sched_rq_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+ struct request *rqa = container_of(a, struct request, queuelist);
+ struct request *rqb = container_of(b, struct request, queuelist);
+
+ return rqa->mq_hctx > rqb->mq_hctx;
+}
+
+static bool blk_mq_dispatch_hctx_list(struct list_head *rq_list)
+{
+ struct blk_mq_hw_ctx *hctx =
+ list_first_entry(rq_list, struct request, queuelist)->mq_hctx;
+ struct request *rq;
+ LIST_HEAD(hctx_list);
+ unsigned int count = 0;
+
+ list_for_each_entry(rq, rq_list, queuelist) {
+ if (rq->mq_hctx != hctx) {
+ list_cut_before(&hctx_list, rq_list, &rq->queuelist);
+ goto dispatch;
+ }
+ count++;
+ }
+ list_splice_tail_init(rq_list, &hctx_list);
+
+dispatch:
+ return blk_mq_dispatch_rq_list(hctx, &hctx_list, count);
+}
+
+#define BLK_MQ_BUDGET_DELAY 3 /* ms units */
+
/*
* Only SCSI implements .get_budget and .put_budget, and SCSI restarts
* its queue by itself in its completion handler, so we don't need to
- * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE.
+ * restart queue if .get_budget() fails to get the budget.
+ *
+ * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to
+ * be run again. This is necessary to avoid starving flushes.
*/
-static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
+static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
{
struct request_queue *q = hctx->queue;
struct elevator_queue *e = q->elevator;
+ bool multi_hctxs = false, run_queue = false;
+ bool dispatched = false, busy = false;
+ unsigned int max_dispatch;
LIST_HEAD(rq_list);
+ int count = 0;
+
+ if (hctx->dispatch_busy)
+ max_dispatch = 1;
+ else
+ max_dispatch = hctx->queue->nr_requests;
do {
struct request *rq;
- if (e->type->ops.mq.has_work &&
- !e->type->ops.mq.has_work(hctx))
+ if (e->type->ops.has_work && !e->type->ops.has_work(hctx))
break;
- if (!blk_mq_get_dispatch_budget(hctx))
+ if (!list_empty_careful(&hctx->dispatch)) {
+ busy = true;
+ break;
+ }
+
+ if (!blk_mq_get_dispatch_budget(q))
break;
- rq = e->type->ops.mq.dispatch_request(hctx);
+ rq = e->type->ops.dispatch_request(hctx);
if (!rq) {
- blk_mq_put_dispatch_budget(hctx);
+ blk_mq_put_dispatch_budget(q);
+ /*
+ * We're releasing without dispatching. Holding the
+ * budget could have blocked any "hctx"s with the
+ * same queue and if we didn't dispatch then there's
+ * no guarantee anyone will kick the queue. Kick it
+ * ourselves.
+ */
+ run_queue = true;
break;
}
@@ -113,14 +161,57 @@
* if this rq won't be queued to driver via .queue_rq()
* in blk_mq_dispatch_rq_list().
*/
- list_add(&rq->queuelist, &rq_list);
- } while (blk_mq_dispatch_rq_list(q, &rq_list, true));
+ list_add_tail(&rq->queuelist, &rq_list);
+ if (rq->mq_hctx != hctx)
+ multi_hctxs = true;
+ } while (++count < max_dispatch);
+
+ if (!count) {
+ if (run_queue)
+ blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY);
+ } else if (multi_hctxs) {
+ /*
+ * Requests from different hctx may be dequeued from some
+ * schedulers, such as bfq and deadline.
+ *
+ * Sort the requests in the list according to their hctx,
+ * dispatch batching requests from same hctx at a time.
+ */
+ list_sort(NULL, &rq_list, sched_rq_cmp);
+ do {
+ dispatched |= blk_mq_dispatch_hctx_list(&rq_list);
+ } while (!list_empty(&rq_list));
+ } else {
+ dispatched = blk_mq_dispatch_rq_list(hctx, &rq_list, count);
+ }
+
+ if (busy)
+ return -EAGAIN;
+ return !!dispatched;
+}
+
+static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
+{
+ unsigned long end = jiffies + HZ;
+ int ret;
+
+ do {
+ ret = __blk_mq_do_dispatch_sched(hctx);
+ if (ret != 1)
+ break;
+ if (need_resched() || time_is_before_jiffies(end)) {
+ blk_mq_delay_run_hw_queue(hctx, 0);
+ break;
+ }
+ } while (1);
+
+ return ret;
}
static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *ctx)
{
- unsigned idx = ctx->index_hw;
+ unsigned short idx = ctx->index_hw[hctx->type];
if (++idx == hctx->nr_ctx)
idx = 0;
@@ -131,26 +222,42 @@
/*
* Only SCSI implements .get_budget and .put_budget, and SCSI restarts
* its queue by itself in its completion handler, so we don't need to
- * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE.
+ * restart queue if .get_budget() fails to get the budget.
+ *
+ * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to
+ * be run again. This is necessary to avoid starving flushes.
*/
-static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
+static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
{
struct request_queue *q = hctx->queue;
LIST_HEAD(rq_list);
struct blk_mq_ctx *ctx = READ_ONCE(hctx->dispatch_from);
+ int ret = 0;
+ struct request *rq;
do {
- struct request *rq;
+ if (!list_empty_careful(&hctx->dispatch)) {
+ ret = -EAGAIN;
+ break;
+ }
if (!sbitmap_any_bit_set(&hctx->ctx_map))
break;
- if (!blk_mq_get_dispatch_budget(hctx))
+ if (!blk_mq_get_dispatch_budget(q))
break;
rq = blk_mq_dequeue_from_ctx(hctx, ctx);
if (!rq) {
- blk_mq_put_dispatch_budget(hctx);
+ blk_mq_put_dispatch_budget(q);
+ /*
+ * We're releasing without dispatching. Holding the
+ * budget could have blocked any "hctx"s with the
+ * same queue and if we didn't dispatch then there's
+ * no guarantee anyone will kick the queue. Kick it
+ * ourselves.
+ */
+ blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY);
break;
}
@@ -164,23 +271,19 @@
/* round robin for fair dispatch */
ctx = blk_mq_next_ctx(hctx, rq->mq_ctx);
- } while (blk_mq_dispatch_rq_list(q, &rq_list, true));
+ } while (blk_mq_dispatch_rq_list(rq->mq_hctx, &rq_list, 1));
WRITE_ONCE(hctx->dispatch_from, ctx);
+ return ret;
}
-void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
+static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
{
struct request_queue *q = hctx->queue;
struct elevator_queue *e = q->elevator;
- const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
+ const bool has_sched_dispatch = e && e->type->ops.dispatch_request;
+ int ret = 0;
LIST_HEAD(rq_list);
-
- /* RCU or SRCU read lock is needed before checking quiesced flag */
- if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
- return;
-
- hctx->run++;
/*
* If we have previous entries on our dispatch list, grab them first for
@@ -208,136 +311,78 @@
*/
if (!list_empty(&rq_list)) {
blk_mq_sched_mark_restart_hctx(hctx);
- if (blk_mq_dispatch_rq_list(q, &rq_list, false)) {
+ if (blk_mq_dispatch_rq_list(hctx, &rq_list, 0)) {
if (has_sched_dispatch)
- blk_mq_do_dispatch_sched(hctx);
+ ret = blk_mq_do_dispatch_sched(hctx);
else
- blk_mq_do_dispatch_ctx(hctx);
+ ret = blk_mq_do_dispatch_ctx(hctx);
}
} else if (has_sched_dispatch) {
- blk_mq_do_dispatch_sched(hctx);
+ ret = blk_mq_do_dispatch_sched(hctx);
} else if (hctx->dispatch_busy) {
/* dequeue request one by one from sw queue if queue is busy */
- blk_mq_do_dispatch_ctx(hctx);
+ ret = blk_mq_do_dispatch_ctx(hctx);
} else {
blk_mq_flush_busy_ctxs(hctx, &rq_list);
- blk_mq_dispatch_rq_list(q, &rq_list, false);
+ blk_mq_dispatch_rq_list(hctx, &rq_list, 0);
}
+
+ return ret;
}
-bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
- struct request **merged_request)
+void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
{
- struct request *rq;
+ struct request_queue *q = hctx->queue;
- switch (elv_merge(q, &rq, bio)) {
- case ELEVATOR_BACK_MERGE:
- if (!blk_mq_sched_allow_merge(q, rq, bio))
- return false;
- if (!bio_attempt_back_merge(q, rq, bio))
- return false;
- *merged_request = attempt_back_merge(q, rq);
- if (!*merged_request)
- elv_merged_request(q, rq, ELEVATOR_BACK_MERGE);
- return true;
- case ELEVATOR_FRONT_MERGE:
- if (!blk_mq_sched_allow_merge(q, rq, bio))
- return false;
- if (!bio_attempt_front_merge(q, rq, bio))
- return false;
- *merged_request = attempt_front_merge(q, rq);
- if (!*merged_request)
- elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE);
- return true;
- case ELEVATOR_DISCARD_MERGE:
- return bio_attempt_discard_merge(q, rq, bio);
- default:
- return false;
+ /* RCU or SRCU read lock is needed before checking quiesced flag */
+ if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
+ return;
+
+ hctx->run++;
+
+ /*
+ * A return of -EAGAIN is an indication that hctx->dispatch is not
+ * empty and we must run again in order to avoid starving flushes.
+ */
+ if (__blk_mq_sched_dispatch_requests(hctx) == -EAGAIN) {
+ if (__blk_mq_sched_dispatch_requests(hctx) == -EAGAIN)
+ blk_mq_run_hw_queue(hctx, true);
}
}
-EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
-/*
- * Iterate list of requests and see if we can merge this bio with any
- * of them.
- */
-bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
- struct bio *bio)
-{
- struct request *rq;
- int checked = 8;
-
- list_for_each_entry_reverse(rq, list, queuelist) {
- bool merged = false;
-
- if (!checked--)
- break;
-
- if (!blk_rq_merge_ok(rq, bio))
- continue;
-
- switch (blk_try_merge(rq, bio)) {
- case ELEVATOR_BACK_MERGE:
- if (blk_mq_sched_allow_merge(q, rq, bio))
- merged = bio_attempt_back_merge(q, rq, bio);
- break;
- case ELEVATOR_FRONT_MERGE:
- if (blk_mq_sched_allow_merge(q, rq, bio))
- merged = bio_attempt_front_merge(q, rq, bio);
- break;
- case ELEVATOR_DISCARD_MERGE:
- merged = bio_attempt_discard_merge(q, rq, bio);
- break;
- default:
- continue;
- }
-
- return merged;
- }
-
- return false;
-}
-EXPORT_SYMBOL_GPL(blk_mq_bio_list_merge);
-
-/*
- * Reverse check our software queue for entries that we could potentially
- * merge with. Currently includes a hand-wavy stop count of 8, to not spend
- * too much time checking for merges.
- */
-static bool blk_mq_attempt_merge(struct request_queue *q,
- struct blk_mq_ctx *ctx, struct bio *bio)
-{
- lockdep_assert_held(&ctx->lock);
-
- if (blk_mq_bio_list_merge(q, &ctx->rq_list, bio)) {
- ctx->rq_merged++;
- return true;
- }
-
- return false;
-}
-
-bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
+bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
+ unsigned int nr_segs)
{
struct elevator_queue *e = q->elevator;
- struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
- struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+ struct blk_mq_ctx *ctx;
+ struct blk_mq_hw_ctx *hctx;
bool ret = false;
+ enum hctx_type type;
- if (e && e->type->ops.mq.bio_merge) {
- blk_mq_put_ctx(ctx);
- return e->type->ops.mq.bio_merge(hctx, bio);
+ if (e && e->type->ops.bio_merge)
+ return e->type->ops.bio_merge(q, bio, nr_segs);
+
+ ctx = blk_mq_get_ctx(q);
+ hctx = blk_mq_map_queue(q, bio->bi_opf, ctx);
+ type = hctx->type;
+ if (!(hctx->flags & BLK_MQ_F_SHOULD_MERGE) ||
+ list_empty_careful(&ctx->rq_lists[type]))
+ return false;
+
+ /* default per sw-queue merge */
+ spin_lock(&ctx->lock);
+ /*
+ * Reverse check our software queue for entries that we could
+ * potentially merge with. Currently includes a hand-wavy stop
+ * count of 8, to not spend too much time checking for merges.
+ */
+ if (blk_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) {
+ ctx->rq_merged++;
+ ret = true;
}
- if ((hctx->flags & BLK_MQ_F_SHOULD_MERGE) &&
- !list_empty_careful(&ctx->rq_list)) {
- /* default per sw-queue merge */
- spin_lock(&ctx->lock);
- ret = blk_mq_attempt_merge(q, ctx, bio);
- spin_unlock(&ctx->lock);
- }
+ spin_unlock(&ctx->lock);
- blk_mq_put_ctx(ctx);
return ret;
}
@@ -357,13 +402,19 @@
bool has_sched,
struct request *rq)
{
- /* dispatch flush rq directly */
- if (rq->rq_flags & RQF_FLUSH_SEQ) {
- spin_lock(&hctx->lock);
- list_add(&rq->queuelist, &hctx->dispatch);
- spin_unlock(&hctx->lock);
+ /*
+ * dispatch flush and passthrough rq directly
+ *
+ * passthrough request has to be added to hctx->dispatch directly.
+ * For some reason, device may be in one situation which can't
+ * handle FS request, so STS_RESOURCE is always returned and the
+ * FS request will be added to hctx->dispatch. However passthrough
+ * request may be required at that time for fixing the problem. If
+ * passthrough request is added to scheduler queue, there isn't any
+ * chance to dispatch it given we prioritize requests in hctx->dispatch.
+ */
+ if ((rq->rq_flags & RQF_FLUSH_SEQ) || blk_rq_is_passthrough(rq))
return true;
- }
if (has_sched)
rq->rq_flags |= RQF_SORTED;
@@ -377,24 +428,42 @@
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);
+ struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
- /* flush rq in flush machinery need to be dispatched directly */
- if (!(rq->rq_flags & RQF_FLUSH_SEQ) && op_is_flush(rq->cmd_flags)) {
- blk_insert_flush(rq);
+ WARN_ON(e && (rq->tag != BLK_MQ_NO_TAG));
+
+ if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) {
+ /*
+ * Firstly normal IO request is inserted to scheduler queue or
+ * sw queue, meantime we add flush request to dispatch queue(
+ * hctx->dispatch) directly and there is at most one in-flight
+ * flush request for each hw queue, so it doesn't matter to add
+ * flush request to tail or front of the dispatch queue.
+ *
+ * Secondly in case of NCQ, flush request belongs to non-NCQ
+ * command, and queueing it will fail when there is any
+ * in-flight normal IO request(NCQ command). When adding flush
+ * rq to the front of hctx->dispatch, it is easier to introduce
+ * extra time to flush rq's latency because of S_SCHED_RESTART
+ * compared with adding to the tail of dispatch queue, then
+ * chance of flush merge is increased, and less flush requests
+ * will be issued to controller. It is observed that ~10% time
+ * is saved in blktests block/004 on disk attached to AHCI/NCQ
+ * drive when adding flush rq to the front of hctx->dispatch.
+ *
+ * Simply queue flush rq to the front of hctx->dispatch so that
+ * intensive flush workloads can benefit in case of NCQ HW.
+ */
+ at_head = (rq->rq_flags & RQF_FLUSH_SEQ) ? true : at_head;
+ blk_mq_request_bypass_insert(rq, at_head, false);
goto run;
}
- WARN_ON(e && (rq->tag != -1));
-
- if (blk_mq_sched_bypass_insert(hctx, !!e, rq))
- goto run;
-
- if (e && e->type->ops.mq.insert_requests) {
+ if (e && e->type->ops.insert_requests) {
LIST_HEAD(list);
list_add(&rq->queuelist, &list);
- e->type->ops.mq.insert_requests(hctx, &list, at_head);
+ e->type->ops.insert_requests(hctx, &list, at_head);
} else {
spin_lock(&ctx->lock);
__blk_mq_insert_request(hctx, rq, at_head);
@@ -406,15 +475,23 @@
blk_mq_run_hw_queue(hctx, async);
}
-void blk_mq_sched_insert_requests(struct request_queue *q,
+void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
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;
+ struct elevator_queue *e;
+ struct request_queue *q = hctx->queue;
- if (e && e->type->ops.mq.insert_requests)
- e->type->ops.mq.insert_requests(hctx, list, false);
+ /*
+ * blk_mq_sched_insert_requests() is called from flush plug
+ * context only, and hold one usage counter to prevent queue
+ * from being released.
+ */
+ percpu_ref_get(&q->q_usage_counter);
+
+ e = hctx->queue->elevator;
+ if (e && e->type->ops.insert_requests)
+ e->type->ops.insert_requests(hctx, list, false);
else {
/*
* try to issue requests directly if the hw queue isn't
@@ -424,21 +501,25 @@
if (!hctx->dispatch_busy && !e && !run_queue_async) {
blk_mq_try_issue_list_directly(hctx, list);
if (list_empty(list))
- return;
+ goto out;
}
blk_mq_insert_requests(hctx, ctx, list);
}
blk_mq_run_hw_queue(hctx, run_queue_async);
+ out:
+ percpu_ref_put(&q->q_usage_counter);
}
static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
struct blk_mq_hw_ctx *hctx,
unsigned int hctx_idx)
{
+ unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
+
if (hctx->sched_tags) {
blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx);
- blk_mq_free_rq_map(hctx->sched_tags);
+ blk_mq_free_rq_map(hctx->sched_tags, flags);
hctx->sched_tags = NULL;
}
}
@@ -448,10 +529,12 @@
unsigned int hctx_idx)
{
struct blk_mq_tag_set *set = q->tag_set;
+ /* Clear HCTX_SHARED so tags are init'ed */
+ unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
int ret;
hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests,
- set->reserved_tags);
+ set->reserved_tags, flags);
if (!hctx->sched_tags)
return -ENOMEM;
@@ -462,14 +545,21 @@
return ret;
}
+/* called in queue's release handler, tagset has gone away */
static void blk_mq_sched_tags_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);
+ queue_for_each_hw_ctx(q, hctx, i) {
+ /* Clear HCTX_SHARED so tags are freed */
+ unsigned int flags = hctx->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
+
+ if (hctx->sched_tags) {
+ blk_mq_free_rq_map(hctx->sched_tags, flags);
+ hctx->sched_tags = NULL;
+ }
+ }
}
int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
@@ -499,17 +589,18 @@
goto err;
}
- ret = e->ops.mq.init_sched(q, e);
+ ret = e->ops.init_sched(q, e);
if (ret)
goto err;
blk_mq_debugfs_register_sched(q);
queue_for_each_hw_ctx(q, hctx, i) {
- if (e->ops.mq.init_hctx) {
- ret = e->ops.mq.init_hctx(hctx, i);
+ if (e->ops.init_hctx) {
+ ret = e->ops.init_hctx(hctx, i);
if (ret) {
eq = q->elevator;
+ blk_mq_sched_free_requests(q);
blk_mq_exit_sched(q, eq);
kobject_put(&eq->kobj);
return ret;
@@ -521,9 +612,25 @@
return 0;
err:
+ blk_mq_sched_free_requests(q);
blk_mq_sched_tags_teardown(q);
q->elevator = NULL;
return ret;
+}
+
+/*
+ * called in either blk_queue_cleanup or elevator_switch, tagset
+ * is required for freeing requests
+ */
+void blk_mq_sched_free_requests(struct request_queue *q)
+{
+ struct blk_mq_hw_ctx *hctx;
+ int i;
+
+ queue_for_each_hw_ctx(q, hctx, i) {
+ if (hctx->sched_tags)
+ blk_mq_free_rqs(q->tag_set, hctx->sched_tags, i);
+ }
}
void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
@@ -533,14 +640,14 @@
queue_for_each_hw_ctx(q, hctx, i) {
blk_mq_debugfs_unregister_sched_hctx(hctx);
- if (e->type->ops.mq.exit_hctx && hctx->sched_data) {
- e->type->ops.mq.exit_hctx(hctx, i);
+ if (e->type->ops.exit_hctx && hctx->sched_data) {
+ e->type->ops.exit_hctx(hctx, i);
hctx->sched_data = NULL;
}
}
blk_mq_debugfs_unregister_sched(q);
- if (e->type->ops.mq.exit_sched)
- e->type->ops.mq.exit_sched(e);
+ if (e->type->ops.exit_sched)
+ e->type->ops.exit_sched(e);
blk_mq_sched_tags_teardown(q);
q->elevator = NULL;
}
--
Gitblit v1.6.2