| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20250814033522.770575-6-yukuai1@huaweicloud.com>
Date: Thu, 14 Aug 2025 11:35:11 +0800
From: Yu Kuai <yukuai1@...weicloud.com>
To: axboe@...nel.dk,
yukuai3@...wei.com,
bvanassche@....org,
nilay@...ux.ibm.com,
hare@...e.de,
ming.lei@...hat.com
Cc: linux-block@...r.kernel.org,
linux-kernel@...r.kernel.org,
yukuai1@...weicloud.com,
yi.zhang@...wei.com,
yangerkun@...wei.com,
johnny.chenyi@...wei.com
Subject: [PATCH 05/16] blk-mq: fix elevator depth_updated method
From: Yu Kuai <yukuai3@...wei.com>
Current depth_updated has some problems:
1) depth_updated() will be called for each hctx, while all elevators
will update async_depth for the disk level, this is not related to hctx;
2) In blk_mq_update_nr_requests(), if previous hctx update succeed and
this hctx update failed, q->nr_requests will not be updated, while
async_depth is already updated with new nr_reqeuests in previous
depth_updated();
3) All elevators are using q->nr_requests to calculate async_depth now,
however, q->nr_requests is still the old value when depth_updated() is
called from blk_mq_update_nr_requests();
Fix those problems by:
- pass in request_queue instead of hctx;
- move depth_updated() after q->nr_requests is updated in
blk_mq_update_nr_requests();
- add depth_updated() call in blk_mq_init_sched();
- remove init_hctx() method for mq-deadline and bfq that is useless now;
Fixes: 77f1e0a52d26 ("bfq: update internal depth state when queue depth changes")
Fixes: 39823b47bbd4 ("block/mq-deadline: Fix the tag reservation code")
Fixes: 42e6c6ce03fd ("lib/sbitmap: convert shallow_depth from one word to the whole sbitmap")
Signed-off-by: Yu Kuai <yukuai3@...wei.com>
---
block/bfq-iosched.c | 21 ++++-----------------
block/blk-mq-sched.c | 3 +++
block/blk-mq-sched.h | 11 +++++++++++
block/blk-mq.c | 24 ++++++++++++------------
block/elevator.h | 2 +-
block/kyber-iosched.c | 10 ++++------
block/mq-deadline.c | 15 ++-------------
7 files changed, 37 insertions(+), 49 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 50e51047e1fe..c0c398998aa1 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -7109,9 +7109,10 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
* See the comments on bfq_limit_depth for the purpose of
* the depths set in the function. Return minimum shallow depth we'll use.
*/
-static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
+static void bfq_depth_updated(struct request_queue *q)
{
- unsigned int nr_requests = bfqd->queue->nr_requests;
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+ unsigned int nr_requests = q->nr_requests;
/*
* In-word depths if no bfq_queue is being weight-raised:
@@ -7143,21 +7144,8 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
bfqd->async_depths[1][0] = max((nr_requests * 3) >> 4, 1U);
/* no more than ~37% of tags for sync writes (~20% extra tags) */
bfqd->async_depths[1][1] = max((nr_requests * 6) >> 4, 1U);
-}
-
-static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)
-{
- struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
- struct blk_mq_tags *tags = hctx->sched_tags;
- bfq_update_depths(bfqd, &tags->bitmap_tags);
- sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, 1);
-}
-
-static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
-{
- bfq_depth_updated(hctx);
- return 0;
+ blk_mq_set_min_shallow_depth(q, 1);
}
static void bfq_exit_queue(struct elevator_queue *e)
@@ -7628,7 +7616,6 @@ static struct elevator_type iosched_bfq_mq = {
.request_merged = bfq_request_merged,
.has_work = bfq_has_work,
.depth_updated = bfq_depth_updated,
- .init_hctx = bfq_init_hctx,
.init_sched = bfq_init_queue,
.exit_sched = bfq_exit_queue,
},
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 9a8a0b5e04a9..c6a1e5a25fec 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -588,6 +588,9 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e,
}
}
}
+
+ if (e->ops.depth_updated)
+ e->ops.depth_updated(q);
return 0;
out:
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 0582d4bc3987..8e21a6b1415d 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -92,4 +92,15 @@ static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
}
+static inline void blk_mq_set_min_shallow_depth(struct request_queue *q,
+ unsigned int depth)
+{
+ struct blk_mq_hw_ctx *hctx;
+ unsigned long i;
+
+ queue_for_each_hw_ctx(q, hctx, i)
+ sbitmap_queue_min_shallow_depth(&hctx->sched_tags->bitmap_tags,
+ depth);
+}
+
#endif
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e86cab125a2d..14446d3927dd 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4938,22 +4938,22 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr);
if (ret)
- break;
- if (q->elevator && q->elevator->type->ops.depth_updated)
- q->elevator->type->ops.depth_updated(hctx);
+ goto out;
}
- if (!ret) {
- q->nr_requests = nr;
- if (blk_mq_is_shared_tags(set->flags)) {
- if (q->elevator)
- blk_mq_tag_update_sched_shared_tags(q);
- else
- blk_mq_tag_resize_shared_tags(set, nr);
- }
+
+ q->nr_requests = nr;
+ if (q->elevator && q->elevator->type->ops.depth_updated)
+ q->elevator->type->ops.depth_updated(q);
+
+ if (blk_mq_is_shared_tags(set->flags)) {
+ if (q->elevator)
+ blk_mq_tag_update_sched_shared_tags(q);
+ else
+ blk_mq_tag_resize_shared_tags(set, nr);
}
+out:
blk_mq_unquiesce_queue(q);
-
return ret;
}
diff --git a/block/elevator.h b/block/elevator.h
index adc5c157e17e..c4d20155065e 100644
--- a/block/elevator.h
+++ b/block/elevator.h
@@ -37,7 +37,7 @@ struct elevator_mq_ops {
void (*exit_sched)(struct elevator_queue *);
int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int);
void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
- void (*depth_updated)(struct blk_mq_hw_ctx *);
+ void (*depth_updated)(struct request_queue *);
bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
bool (*bio_merge)(struct request_queue *, struct bio *, unsigned int);
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index 70cbc7b2deb4..49ae52aa20d9 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -440,13 +440,12 @@ static void kyber_ctx_queue_init(struct kyber_ctx_queue *kcq)
INIT_LIST_HEAD(&kcq->rq_list[i]);
}
-static void kyber_depth_updated(struct blk_mq_hw_ctx *hctx)
+static void kyber_depth_updated(struct request_queue *q)
{
- struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
- struct blk_mq_tags *tags = hctx->sched_tags;
+ struct kyber_queue_data *kqd = q->elevator->elevator_data;
- kqd->async_depth = hctx->queue->nr_requests * KYBER_ASYNC_PERCENT / 100U;
- sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, kqd->async_depth);
+ kqd->async_depth = q->nr_requests * KYBER_ASYNC_PERCENT / 100U;
+ blk_mq_set_min_shallow_depth(q, kqd->async_depth);
}
static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
@@ -493,7 +492,6 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
khd->batching = 0;
hctx->sched_data = khd;
- kyber_depth_updated(hctx);
return 0;
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index b9b7cdf1d3c9..578bc79c5654 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -507,22 +507,12 @@ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
}
/* Called by blk_mq_update_nr_requests(). */
-static void dd_depth_updated(struct blk_mq_hw_ctx *hctx)
+static void dd_depth_updated(struct request_queue *q)
{
- struct request_queue *q = hctx->queue;
struct deadline_data *dd = q->elevator->elevator_data;
- struct blk_mq_tags *tags = hctx->sched_tags;
dd->async_depth = q->nr_requests;
-
- sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, 1);
-}
-
-/* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */
-static int dd_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
-{
- dd_depth_updated(hctx);
- return 0;
+ blk_mq_set_min_shallow_depth(q, 1);
}
static void dd_exit_sched(struct elevator_queue *e)
@@ -1048,7 +1038,6 @@ static struct elevator_type mq_deadline = {
.has_work = dd_has_work,
.init_sched = dd_init_sched,
.exit_sched = dd_exit_sched,
- .init_hctx = dd_init_hctx,
},
#ifdef CONFIG_BLK_DEBUG_FS
--
2.39.2
Powered by blists - more mailing lists