From nobody Fri Oct 10 09:22:18 2025 Received: from dggsgout12.his.huawei.com (dggsgout12.his.huawei.com [45.249.212.56]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 5EA8A3594F; Sat, 14 Jun 2025 09:31:45 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.56 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749893509; cv=none; b=ksTjpcg31S4SkYU8FEvUNqQdnZr4aCSfNPCRvjhiH5xzLUsCVkKL+zYbI0TWGLRayw2yc+9EfkTSb8h6KesmJUeWFMxiyISL7Qto68TJKcbIR0n4HvhqV5e9lludOiMEsZTeJUGCSR4exD2pg+xD2rNfL2eOh8vB71N4ani2P1Q= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749893509; c=relaxed/simple; bh=wEQGdWGsmpfrovUYNN+akxZhK07M41/34FemLEAhQbE=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=LAXGq4dki7NiYCC9ftx5IgS/JOVWPNkMf4YbmM2uZPMjZk3apIgtk0k1D71Z2p87qkky7zWr/RK+/B5t7D10FVqXTK3ssXl7NgwcxRJqm4K03MRnWRXwM+Yt3WINN6Kpk2s/mLFo4rgoBQ2gkHjH7g5KJNe6MX6XXrWR2op5ygg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com; spf=pass smtp.mailfrom=huaweicloud.com; arc=none smtp.client-ip=45.249.212.56 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=huaweicloud.com Received: from mail.maildlp.com (unknown [172.19.93.142]) by dggsgout12.his.huawei.com (SkyGuard) with ESMTPS id 4bK9y82Tg6zKHNQy; Sat, 14 Jun 2025 17:31:44 +0800 (CST) Received: from mail02.huawei.com (unknown [10.116.40.128]) by mail.maildlp.com (Postfix) with ESMTP id AA8AC1A0DEE; Sat, 14 Jun 2025 17:31:42 +0800 (CST) Received: from huaweicloud.com (unknown [10.175.104.67]) by APP4 (Coremail) with SMTP id gCh0CgAni19zQU1oHxfvPQ--.9099S5; Sat, 14 Jun 2025 17:31:42 +0800 (CST) From: Yu Kuai To: ming.lei@redhat.com, yukuai3@huawei.com, tj@kernel.org, josef@toxicpanda.com, axboe@kernel.dk Cc: linux-block@vger.kernel.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, yukuai1@huaweicloud.com, yi.zhang@huawei.com, yangerkun@huawei.com, johnny.chenyi@huawei.com Subject: [PATCH RFC v2 1/5] elevator: introduce global lock for sq_shared elevator Date: Sat, 14 Jun 2025 17:25:24 +0800 Message-Id: <20250614092528.2352680-2-yukuai1@huaweicloud.com> X-Mailer: git-send-email 2.39.2 In-Reply-To: <20250614092528.2352680-1-yukuai1@huaweicloud.com> References: <20250614092528.2352680-1-yukuai1@huaweicloud.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-CM-TRANSID: gCh0CgAni19zQU1oHxfvPQ--.9099S5 X-Coremail-Antispam: 1UD129KBjvJXoWxCF45GF4fuF48AF4xtrWDurg_yoWrtF4kpF 45Jan0kr4qqr47Za4xAa17Jw43t3929ry3ZrWfAw45tFyxGrWxXF18GFy8ZF4xZrs3CFsF qr4ktFZ8WFyIg3DanT9S1TB71UUUUU7qnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDU0xBIdaVrnRJUUUm014x267AKxVWrJVCq3wAFc2x0x2IEx4CE42xK8VAvwI8IcIk0 rVWrJVCq3wAFIxvE14AKwVWUJVWUGwA2048vs2IY020E87I2jVAFwI0_Jr4l82xGYIkIc2 x26xkF7I0E14v26r4j6ryUM28lY4IEw2IIxxk0rwA2F7IY1VAKz4vEj48ve4kI8wA2z4x0 Y4vE2Ix0cI8IcVAFwI0_Ar0_tr1l84ACjcxK6xIIjxv20xvEc7CjxVAFwI0_Gr1j6F4UJw A2z4x0Y4vEx4A2jsIE14v26rxl6s0DM28EF7xvwVC2z280aVCY1x0267AKxVW0oVCq3wAS 0I0E0xvYzxvE52x082IY62kv0487Mc02F40EFcxC0VAKzVAqx4xG6I80ewAv7VC0I7IYx2 IY67AKxVWUXVWUAwAv7VC2z280aVAFwI0_Jr0_Gr1lOx8S6xCaFVCjc4AY6r1j6r4UM4x0 Y48IcxkI7VAKI48JM4x0x7Aq67IIx4CEVc8vx2IErcIFxwACI402YVCY1x02628vn2kIc2 xKxwCY1x0262kKe7AKxVWUtVW8ZwCF04k20xvY0x0EwIxGrwCFx2IqxVCFs4IE7xkEbVWU JVW8JwC20s026c02F40E14v26r1j6r18MI8I3I0E7480Y4vE14v26r106r1rMI8E67AF67 kF1VAFwI0_Jw0_GFylIxkGc2Ij64vIr41lIxAIcVC0I7IYx2IY67AKxVWUJVWUCwCI42IY 6xIIjxv20xvEc7CjxVAFwI0_Gr0_Cr1lIxAIcVCF04k26cxKx2IYs7xG6r1j6r1xMIIF0x vEx4A2jsIE14v26r1j6r4UMIIF0xvEx4A2jsIEc7CjxVAFwI0_Gr0_Gr1UYxBIdaVFxhVj vjDU0xZFpf9x0JUIiiDUUUUU= X-CM-SenderInfo: 51xn3trlr6x35dzhxuhorxvhhfrp/ Content-Type: text/plain; charset="utf-8" From: Yu Kuai Currently, both mq-deadline and bfq have internal global lock, prepare to convert them to use this high level lock and support batch request dispatching. Signed-off-by: Yu Kuai --- block/blk-mq-sched.c | 4 +-- block/blk-mq.c | 5 ++-- block/elevator.c | 1 + block/elevator.h | 61 ++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 64 insertions(+), 7 deletions(-) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 55a0fd105147..c1390d3e6381 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -113,7 +113,7 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_= ctx *hctx) if (budget_token < 0) break; =20 - rq =3D e->type->ops.dispatch_request(hctx); + rq =3D elevator_dispatch_request(hctx); if (!rq) { blk_mq_put_dispatch_budget(q, budget_token); /* @@ -342,7 +342,7 @@ bool blk_mq_sched_bio_merge(struct request_queue *q, st= ruct bio *bio, enum hctx_type type; =20 if (e && e->type->ops.bio_merge) { - ret =3D e->type->ops.bio_merge(q, bio, nr_segs); + ret =3D elevator_bio_merge(q, bio, nr_segs); goto out_put; } =20 diff --git a/block/blk-mq.c b/block/blk-mq.c index 4806b867e37d..2650b7b28d1e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2637,7 +2637,7 @@ static void blk_mq_insert_request(struct request *rq,= blk_insert_t flags) WARN_ON_ONCE(rq->tag !=3D BLK_MQ_NO_TAG); =20 list_add(&rq->queuelist, &list); - q->elevator->type->ops.insert_requests(hctx, &list, flags); + elevator_insert_requests(hctx, &list, flags); } else { trace_block_rq_insert(rq); =20 @@ -2912,8 +2912,7 @@ static void blk_mq_dispatch_list(struct rq_list *rqs,= bool from_sched) spin_unlock(&this_hctx->lock); blk_mq_run_hw_queue(this_hctx, from_sched); } else if (this_hctx->queue->elevator) { - this_hctx->queue->elevator->type->ops.insert_requests(this_hctx, - &list, 0); + elevator_insert_requests(this_hctx, &list, 0); blk_mq_run_hw_queue(this_hctx, from_sched); } else { blk_mq_insert_requests(this_hctx, this_ctx, &list, from_sched); diff --git a/block/elevator.c b/block/elevator.c index ab22542e6cf0..91df270d9d91 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -144,6 +144,7 @@ struct elevator_queue *elevator_alloc(struct request_qu= eue *q, eq->type =3D e; kobject_init(&eq->kobj, &elv_ktype); mutex_init(&eq->sysfs_lock); + spin_lock_init(&eq->lock); hash_init(eq->hash); =20 return eq; diff --git a/block/elevator.h b/block/elevator.h index a07ce773a38f..8399dfe5c3b6 100644 --- a/block/elevator.h +++ b/block/elevator.h @@ -110,12 +110,12 @@ struct request *elv_rqhash_find(struct request_queue = *q, sector_t offset); /* * each queue has an elevator_queue associated with it */ -struct elevator_queue -{ +struct elevator_queue { struct elevator_type *type; void *elevator_data; struct kobject kobj; struct mutex sysfs_lock; + spinlock_t lock; unsigned long flags; DECLARE_HASHTABLE(hash, ELV_HASH_BITS); }; @@ -186,4 +186,61 @@ extern struct request *elv_rb_find(struct rb_root *, s= ector_t); void blk_mq_sched_reg_debugfs(struct request_queue *q); void blk_mq_sched_unreg_debugfs(struct request_queue *q); =20 +#define elevator_lock(e) spin_lock_irq(&(e)->lock) +#define elevator_unlock(e) spin_unlock_irq(&(e)->lock) + +static inline struct request *elevator_dispatch_request( + struct blk_mq_hw_ctx *hctx) +{ + struct request_queue *q =3D hctx->queue; + struct elevator_queue *e =3D q->elevator; + bool sq_shared =3D blk_queue_sq_sched(q); + struct request *rq; + + if (sq_shared) + elevator_lock(e); + + rq =3D e->type->ops.dispatch_request(hctx); + + if (sq_shared) + elevator_unlock(e); + + return rq; +} + +static inline void elevator_insert_requests(struct blk_mq_hw_ctx *hctx, + struct list_head *list, + blk_insert_t flags) +{ + struct request_queue *q =3D hctx->queue; + struct elevator_queue *e =3D q->elevator; + bool sq_shared =3D blk_queue_sq_sched(q); + + if (sq_shared) + elevator_lock(e); + + e->type->ops.insert_requests(hctx, list, flags); + + if (sq_shared) + elevator_unlock(e); +} + +static inline bool elevator_bio_merge(struct request_queue *q, struct bio = *bio, + unsigned int nr_segs) +{ + struct elevator_queue *e =3D q->elevator; + bool sq_shared =3D blk_queue_sq_sched(q); + bool ret; + + if (sq_shared) + elevator_lock(e); + + ret =3D e->type->ops.bio_merge(q, bio, nr_segs); + + if (sq_shared) + elevator_unlock(e); + + return ret; +} + #endif /* _ELEVATOR_H */ --=20 2.39.2 From nobody Fri Oct 10 09:22:18 2025 Received: from dggsgout11.his.huawei.com (dggsgout11.his.huawei.com [45.249.212.51]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 998D231A60; Sat, 14 Jun 2025 09:31:45 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.51 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749893509; cv=none; b=RSkx3dPcRn/o9V3u0Qtd4s1OG8re/GrDgF6JaPAUCn8BTWklxcNgIbpJ7ETfnpCaoNskNZ4452oubVqRl+sn5lyZoGygoCyfAGBOaIxb/2Dw/gMK/SWGbReuyMVaKNTEvJcmmGHUUbGvbENlXUk5AyEc/syP2XdCZqKnWH6Twg4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749893509; c=relaxed/simple; bh=qeh1+fR1IImcil0TG6swzubXA9h57FNZibCbV9JWoDU=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=Vm/dixEq4uu/xBEotTLts/UyONnQ0Cd29pJhahYKegvIMXtPDDiT9zz5BbxqcGJTJmZxiwC7jjXKN3vRfHYh3dL6wsmqCQGkVDYx9zW8eTJ3G2Skf9V43PlE7zcV7Ecpn/z9w8q57dGrTjfQpzauKShY4ts2Ct2v0zImmtqmOeY= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com; spf=pass smtp.mailfrom=huaweicloud.com; arc=none smtp.client-ip=45.249.212.51 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=huaweicloud.com Received: from mail.maildlp.com (unknown [172.19.163.235]) by dggsgout11.his.huawei.com (SkyGuard) with ESMTPS id 4bK9y81TTLzYQtw1; Sat, 14 Jun 2025 17:31:44 +0800 (CST) Received: from mail02.huawei.com (unknown [10.116.40.128]) by mail.maildlp.com (Postfix) with ESMTP id 2FF931A089E; Sat, 14 Jun 2025 17:31:43 +0800 (CST) Received: from huaweicloud.com (unknown [10.175.104.67]) by APP4 (Coremail) with SMTP id gCh0CgAni19zQU1oHxfvPQ--.9099S6; Sat, 14 Jun 2025 17:31:43 +0800 (CST) From: Yu Kuai To: ming.lei@redhat.com, yukuai3@huawei.com, tj@kernel.org, josef@toxicpanda.com, axboe@kernel.dk Cc: linux-block@vger.kernel.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, yukuai1@huaweicloud.com, yi.zhang@huawei.com, yangerkun@huawei.com, johnny.chenyi@huawei.com Subject: [PATCH RFC v2 2/5] mq-deadline: switch to use elevator lock Date: Sat, 14 Jun 2025 17:25:25 +0800 Message-Id: <20250614092528.2352680-3-yukuai1@huaweicloud.com> X-Mailer: git-send-email 2.39.2 In-Reply-To: <20250614092528.2352680-1-yukuai1@huaweicloud.com> References: <20250614092528.2352680-1-yukuai1@huaweicloud.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-CM-TRANSID: gCh0CgAni19zQU1oHxfvPQ--.9099S6 X-Coremail-Antispam: 1UD129KBjvJXoW3XryrGFyfKFWrZFW8ZF18Zrb_yoW3CFyrpF W5Ka1ayw4rXFsrXF1DJayDZr4agw4Iv347tr93Gw4fKF1DAr9ruF1UGF1Fvrs3Ar97CFsI gF4qqa98JF17JwUanT9S1TB71UUUUU7qnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDU0xBIdaVrnRJUUUm014x267AKxVWrJVCq3wAFc2x0x2IEx4CE42xK8VAvwI8IcIk0 rVWrJVCq3wAFIxvE14AKwVWUJVWUGwA2048vs2IY020E87I2jVAFwI0_Jryl82xGYIkIc2 x26xkF7I0E14v26ryj6s0DM28lY4IEw2IIxxk0rwA2F7IY1VAKz4vEj48ve4kI8wA2z4x0 Y4vE2Ix0cI8IcVAFwI0_Ar0_tr1l84ACjcxK6xIIjxv20xvEc7CjxVAFwI0_Gr1j6F4UJw A2z4x0Y4vEx4A2jsIE14v26rxl6s0DM28EF7xvwVC2z280aVCY1x0267AKxVW0oVCq3wAS 0I0E0xvYzxvE52x082IY62kv0487Mc02F40EFcxC0VAKzVAqx4xG6I80ewAv7VC0I7IYx2 IY67AKxVWUXVWUAwAv7VC2z280aVAFwI0_Jr0_Gr1lOx8S6xCaFVCjc4AY6r1j6r4UM4x0 Y48IcxkI7VAKI48JM4x0x7Aq67IIx4CEVc8vx2IErcIFxwACI402YVCY1x02628vn2kIc2 xKxwCY1x0262kKe7AKxVWUtVW8ZwCF04k20xvY0x0EwIxGrwCFx2IqxVCFs4IE7xkEbVWU JVW8JwC20s026c02F40E14v26r1j6r18MI8I3I0E7480Y4vE14v26r106r1rMI8E67AF67 kF1VAFwI0_Jw0_GFylIxkGc2Ij64vIr41lIxAIcVC0I7IYx2IY67AKxVWUJVWUCwCI42IY 6xIIjxv20xvEc7CjxVAFwI0_Gr0_Cr1lIxAIcVCF04k26cxKx2IYs7xG6r1j6r1xMIIF0x vEx4A2jsIE14v26r1j6r4UMIIF0xvEx4A2jsIEc7CjxVAFwI0_Gr0_Gr1UYxBIdaVFxhVj vjDU0xZFpf9x0JUl9a9UUUUU= X-CM-SenderInfo: 51xn3trlr6x35dzhxuhorxvhhfrp/ Content-Type: text/plain; charset="utf-8" From: Yu Kuai Convert 'dd->lock' to high level 'q->elevator->lock', prepare to support batch requests dispatching. Signed-off-by: Yu Kuai --- block/mq-deadline.c | 58 ++++++++++++++++++--------------------------- 1 file changed, 23 insertions(+), 35 deletions(-) diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 2edf1cac06d5..6b993a5bf69f 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -101,7 +101,7 @@ struct deadline_data { u32 async_depth; int prio_aging_expire; =20 - spinlock_t lock; + spinlock_t *lock; }; =20 /* Maps an I/O priority class to a deadline scheduler priority. */ @@ -213,7 +213,7 @@ static void dd_merged_requests(struct request_queue *q,= struct request *req, const u8 ioprio_class =3D dd_rq_ioclass(next); const enum dd_prio prio =3D ioprio_class_to_prio[ioprio_class]; =20 - lockdep_assert_held(&dd->lock); + lockdep_assert_held(dd->lock); =20 dd->per_prio[prio].stats.merged++; =20 @@ -253,7 +253,7 @@ static u32 dd_queued(struct deadline_data *dd, enum dd_= prio prio) { const struct io_stats_per_prio *stats =3D &dd->per_prio[prio].stats; =20 - lockdep_assert_held(&dd->lock); + lockdep_assert_held(dd->lock); =20 return stats->inserted - atomic_read(&stats->completed); } @@ -323,7 +323,7 @@ static struct request *__dd_dispatch_request(struct dea= dline_data *dd, enum dd_prio prio; u8 ioprio_class; =20 - lockdep_assert_held(&dd->lock); + lockdep_assert_held(dd->lock); =20 if (!list_empty(&per_prio->dispatch)) { rq =3D list_first_entry(&per_prio->dispatch, struct request, @@ -434,7 +434,7 @@ static struct request *dd_dispatch_prio_aged_requests(s= truct deadline_data *dd, enum dd_prio prio; int prio_cnt; =20 - lockdep_assert_held(&dd->lock); + lockdep_assert_held(dd->lock); =20 prio_cnt =3D !!dd_queued(dd, DD_RT_PRIO) + !!dd_queued(dd, DD_BE_PRIO) + !!dd_queued(dd, DD_IDLE_PRIO); @@ -466,10 +466,9 @@ static struct request *dd_dispatch_request(struct blk_= mq_hw_ctx *hctx) struct request *rq; enum dd_prio prio; =20 - spin_lock(&dd->lock); rq =3D dd_dispatch_prio_aged_requests(dd, now); if (rq) - goto unlock; + return rq; =20 /* * Next, dispatch requests in priority order. Ignore lower priority @@ -481,9 +480,6 @@ static struct request *dd_dispatch_request(struct blk_m= q_hw_ctx *hctx) break; } =20 -unlock: - spin_unlock(&dd->lock); - return rq; } =20 @@ -552,9 +548,9 @@ static void dd_exit_sched(struct elevator_queue *e) WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_READ])); WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_WRITE])); =20 - spin_lock(&dd->lock); + spin_lock(dd->lock); queued =3D dd_queued(dd, prio); - spin_unlock(&dd->lock); + spin_unlock(dd->lock); =20 WARN_ONCE(queued !=3D 0, "statistics for priority %d: i %u m %u d %u c %u\n", @@ -601,7 +597,7 @@ static int dd_init_sched(struct request_queue *q, struc= t elevator_type *e) dd->last_dir =3D DD_WRITE; dd->fifo_batch =3D fifo_batch; dd->prio_aging_expire =3D prio_aging_expire; - spin_lock_init(&dd->lock); + dd->lock =3D &eq->lock; =20 /* We dispatch from request queue wide instead of hw queue */ blk_queue_flag_set(QUEUE_FLAG_SQ_SCHED, q); @@ -653,14 +649,10 @@ static int dd_request_merge(struct request_queue *q, = struct request **rq, static bool dd_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { - struct deadline_data *dd =3D q->elevator->elevator_data; struct request *free =3D NULL; bool ret; =20 - spin_lock(&dd->lock); ret =3D blk_mq_sched_try_merge(q, bio, nr_segs, &free); - spin_unlock(&dd->lock); - if (free) blk_mq_free_request(free); =20 @@ -681,7 +673,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hct= x, struct request *rq, struct dd_per_prio *per_prio; enum dd_prio prio; =20 - lockdep_assert_held(&dd->lock); + lockdep_assert_held(dd->lock); =20 prio =3D ioprio_class_to_prio[ioprio_class]; per_prio =3D &dd->per_prio[prio]; @@ -721,11 +713,8 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *h= ctx, struct list_head *list, blk_insert_t flags) { - struct request_queue *q =3D hctx->queue; - struct deadline_data *dd =3D q->elevator->elevator_data; LIST_HEAD(free); =20 - spin_lock(&dd->lock); while (!list_empty(list)) { struct request *rq; =20 @@ -733,7 +722,6 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hc= tx, list_del_init(&rq->queuelist); dd_insert_request(hctx, rq, flags, &free); } - spin_unlock(&dd->lock); =20 blk_mq_free_requests(&free); } @@ -849,13 +837,13 @@ static const struct elv_fs_entry deadline_attrs[] =3D= { #define DEADLINE_DEBUGFS_DDIR_ATTRS(prio, data_dir, name) \ static void *deadline_##name##_fifo_start(struct seq_file *m, \ loff_t *pos) \ - __acquires(&dd->lock) \ + __acquires(dd->lock) \ { \ struct request_queue *q =3D m->private; \ struct deadline_data *dd =3D q->elevator->elevator_data; \ struct dd_per_prio *per_prio =3D &dd->per_prio[prio]; \ \ - spin_lock(&dd->lock); \ + spin_lock(dd->lock); \ return seq_list_start(&per_prio->fifo_list[data_dir], *pos); \ } \ \ @@ -870,12 +858,12 @@ static void *deadline_##name##_fifo_next(struct seq_f= ile *m, void *v, \ } \ \ static void deadline_##name##_fifo_stop(struct seq_file *m, void *v) \ - __releases(&dd->lock) \ + __releases(dd->lock) \ { \ struct request_queue *q =3D m->private; \ struct deadline_data *dd =3D q->elevator->elevator_data; \ \ - spin_unlock(&dd->lock); \ + spin_unlock(dd->lock); \ } \ \ static const struct seq_operations deadline_##name##_fifo_seq_ops =3D { \ @@ -941,11 +929,11 @@ static int dd_queued_show(void *data, struct seq_file= *m) struct deadline_data *dd =3D q->elevator->elevator_data; u32 rt, be, idle; =20 - spin_lock(&dd->lock); + spin_lock(dd->lock); rt =3D dd_queued(dd, DD_RT_PRIO); be =3D dd_queued(dd, DD_BE_PRIO); idle =3D dd_queued(dd, DD_IDLE_PRIO); - spin_unlock(&dd->lock); + spin_unlock(dd->lock); =20 seq_printf(m, "%u %u %u\n", rt, be, idle); =20 @@ -957,7 +945,7 @@ static u32 dd_owned_by_driver(struct deadline_data *dd,= enum dd_prio prio) { const struct io_stats_per_prio *stats =3D &dd->per_prio[prio].stats; =20 - lockdep_assert_held(&dd->lock); + lockdep_assert_held(dd->lock); =20 return stats->dispatched + stats->merged - atomic_read(&stats->completed); @@ -969,11 +957,11 @@ static int dd_owned_by_driver_show(void *data, struct= seq_file *m) struct deadline_data *dd =3D q->elevator->elevator_data; u32 rt, be, idle; =20 - spin_lock(&dd->lock); + spin_lock(dd->lock); rt =3D dd_owned_by_driver(dd, DD_RT_PRIO); be =3D dd_owned_by_driver(dd, DD_BE_PRIO); idle =3D dd_owned_by_driver(dd, DD_IDLE_PRIO); - spin_unlock(&dd->lock); + spin_unlock(dd->lock); =20 seq_printf(m, "%u %u %u\n", rt, be, idle); =20 @@ -983,13 +971,13 @@ static int dd_owned_by_driver_show(void *data, struct= seq_file *m) #define DEADLINE_DISPATCH_ATTR(prio) \ static void *deadline_dispatch##prio##_start(struct seq_file *m, \ loff_t *pos) \ - __acquires(&dd->lock) \ + __acquires(dd->lock) \ { \ struct request_queue *q =3D m->private; \ struct deadline_data *dd =3D q->elevator->elevator_data; \ struct dd_per_prio *per_prio =3D &dd->per_prio[prio]; \ \ - spin_lock(&dd->lock); \ + spin_lock(dd->lock); \ return seq_list_start(&per_prio->dispatch, *pos); \ } \ \ @@ -1004,12 +992,12 @@ static void *deadline_dispatch##prio##_next(struct s= eq_file *m, \ } \ \ static void deadline_dispatch##prio##_stop(struct seq_file *m, void *v) \ - __releases(&dd->lock) \ + __releases(dd->lock) \ { \ struct request_queue *q =3D m->private; \ struct deadline_data *dd =3D q->elevator->elevator_data; \ \ - spin_unlock(&dd->lock); \ + spin_unlock(dd->lock); \ } \ \ static const struct seq_operations deadline_dispatch##prio##_seq_ops =3D {= \ --=20 2.39.2 From nobody Fri Oct 10 09:22:18 2025 Received: from dggsgout12.his.huawei.com (dggsgout12.his.huawei.com [45.249.212.56]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 09EAF15E5BB; Sat, 14 Jun 2025 09:31:45 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.56 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749893510; cv=none; b=LvWZe9jdO0NITNYGwkR7/6uGUxME7hBqsrZtAEMVz2Dvd5Lu8QbZa8T71tS4CqmNJYLke1D92PaBL3fpAgK2NkBklvzLFrBL3MtZcLxVqo+4/TvMTqRYHIWyI/5NbuWmFvvfk6MtCs2hhPn7rrr1YYIFv6REvMNNJ+WK97ja6ww= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749893510; c=relaxed/simple; bh=SuPqZnoUl5cN0mQBBZZdsrZLQjAzocXjgpUF4FZc4n0=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=lo2rsofY7bA/H29Ai28O/hdpTCHsvYiQlhc8yPafHRcNcpldtR7wmZ6PLd57AnwHUTTsngKwQjfdPg4CtPqbybAM2VuK81kHalgS0zhiAUu5zAIn7khHra+ohuVqN894M49rT2StyNcYQuKkU0+CazNi3p0tl7hsFdIKW0DRQRA= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com; spf=none smtp.mailfrom=huaweicloud.com; arc=none smtp.client-ip=45.249.212.56 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com Authentication-Results: smtp.subspace.kernel.org; spf=none smtp.mailfrom=huaweicloud.com Received: from mail.maildlp.com (unknown [172.19.163.216]) by dggsgout12.his.huawei.com (SkyGuard) with ESMTPS id 4bK9y92SjDzKHNXs; Sat, 14 Jun 2025 17:31:45 +0800 (CST) Received: from mail02.huawei.com (unknown [10.116.40.128]) by mail.maildlp.com (Postfix) with ESMTP id AD3271A1F67; Sat, 14 Jun 2025 17:31:43 +0800 (CST) Received: from huaweicloud.com (unknown [10.175.104.67]) by APP4 (Coremail) with SMTP id gCh0CgAni19zQU1oHxfvPQ--.9099S7; Sat, 14 Jun 2025 17:31:43 +0800 (CST) From: Yu Kuai To: ming.lei@redhat.com, yukuai3@huawei.com, tj@kernel.org, josef@toxicpanda.com, axboe@kernel.dk Cc: linux-block@vger.kernel.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, yukuai1@huaweicloud.com, yi.zhang@huawei.com, yangerkun@huawei.com, johnny.chenyi@huawei.com Subject: [PATCH RFC v2 3/5] block, bfq: switch to use elevator lock Date: Sat, 14 Jun 2025 17:25:26 +0800 Message-Id: <20250614092528.2352680-4-yukuai1@huaweicloud.com> X-Mailer: git-send-email 2.39.2 In-Reply-To: <20250614092528.2352680-1-yukuai1@huaweicloud.com> References: <20250614092528.2352680-1-yukuai1@huaweicloud.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-CM-TRANSID: gCh0CgAni19zQU1oHxfvPQ--.9099S7 X-Coremail-Antispam: 1UD129KBjvJXoW3XFWfKw1UGr1ruw4UCFyDKFg_yoWfAryrpa 1fKanIyw48Xr1FqF48Gw4qqr42gws3u3srKryxX3yftrZYywnxX3WFyryFvF4SqFs7Crsx Wr1jg39ayF4UJa7anT9S1TB71UUUUU7qnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDU0xBIdaVrnRJUUUm014x267AKxVWrJVCq3wAFc2x0x2IEx4CE42xK8VAvwI8IcIk0 rVWrJVCq3wAFIxvE14AKwVWUJVWUGwA2048vs2IY020E87I2jVAFwI0_JrWl82xGYIkIc2 x26xkF7I0E14v26ryj6s0DM28lY4IEw2IIxxk0rwA2F7IY1VAKz4vEj48ve4kI8wA2z4x0 Y4vE2Ix0cI8IcVAFwI0_Ar0_tr1l84ACjcxK6xIIjxv20xvEc7CjxVAFwI0_Gr1j6F4UJw A2z4x0Y4vEx4A2jsIE14v26rxl6s0DM28EF7xvwVC2z280aVCY1x0267AKxVW0oVCq3wAS 0I0E0xvYzxvE52x082IY62kv0487Mc02F40EFcxC0VAKzVAqx4xG6I80ewAv7VC0I7IYx2 IY67AKxVWUXVWUAwAv7VC2z280aVAFwI0_Jr0_Gr1lOx8S6xCaFVCjc4AY6r1j6r4UM4x0 Y48IcxkI7VAKI48JM4x0x7Aq67IIx4CEVc8vx2IErcIFxwACI402YVCY1x02628vn2kIc2 xKxwCY1x0262kKe7AKxVWUtVW8ZwCF04k20xvY0x0EwIxGrwCFx2IqxVCFs4IE7xkEbVWU JVW8JwC20s026c02F40E14v26r1j6r18MI8I3I0E7480Y4vE14v26r106r1rMI8E67AF67 kF1VAFwI0_Jw0_GFylIxkGc2Ij64vIr41lIxAIcVC0I7IYx2IY67AKxVWUJVWUCwCI42IY 6xIIjxv20xvEc7CjxVAFwI0_Gr0_Cr1lIxAIcVCF04k26cxKx2IYs7xG6r1j6r1xMIIF0x vEx4A2jsIE14v26r1j6r4UMIIF0xvEx4A2jsIEc7CjxVAFwI0_Gr0_Gr1UYxBIdaVFxhVj vjDU0xZFpf9x0JULBMNUUUUU= X-CM-SenderInfo: 51xn3trlr6x35dzhxuhorxvhhfrp/ Content-Type: text/plain; charset="utf-8" From: Yu Kuai Convert 'bfqd->lock' to high level 'q->elevator->lock', prepare to support batch requests dispatching. Signed-off-by: Yu Kuai --- block/bfq-cgroup.c | 4 ++-- block/bfq-iosched.c | 53 +++++++++++++++------------------------------ block/bfq-iosched.h | 2 +- 3 files changed, 21 insertions(+), 38 deletions(-) diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 9fb9f3533150..1717bac7eccc 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -878,7 +878,7 @@ static void bfq_pd_offline(struct blkg_policy_data *pd) unsigned long flags; int i; =20 - spin_lock_irqsave(&bfqd->lock, flags); + spin_lock_irqsave(bfqd->lock, flags); =20 if (!entity) /* root group */ goto put_async_queues; @@ -923,7 +923,7 @@ static void bfq_pd_offline(struct blkg_policy_data *pd) put_async_queues: bfq_put_async_queues(bfqd, bfqg); =20 - spin_unlock_irqrestore(&bfqd->lock, flags); + spin_unlock_irqrestore(bfqd->lock, flags); /* * @blkg is going offline and will be ignored by * blkg_[rw]stat_recursive_sum(). Transfer stats to the parent so diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 0cb1e9873aab..fd6d81a185f7 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -473,7 +473,7 @@ static struct bfq_io_cq *bfq_bic_lookup(struct request_= queue *q) */ void bfq_schedule_dispatch(struct bfq_data *bfqd) { - lockdep_assert_held(&bfqd->lock); + lockdep_assert_held(bfqd->lock); =20 if (bfqd->queued !=3D 0) { bfq_log(bfqd, "schedule dispatch"); @@ -598,7 +598,7 @@ static bool bfqq_request_over_limit(struct bfq_data *bf= qd, int level; =20 retry: - spin_lock_irq(&bfqd->lock); + spin_lock_irq(bfqd->lock); bfqq =3D bic_to_bfqq(bic, op_is_sync(opf), act_idx); if (!bfqq) goto out; @@ -610,7 +610,7 @@ static bool bfqq_request_over_limit(struct bfq_data *bf= qd, /* +1 for bfqq entity, root cgroup not included */ depth =3D bfqg_to_blkg(bfqq_group(bfqq))->blkcg->css.cgroup->level + 1; if (depth > alloc_depth) { - spin_unlock_irq(&bfqd->lock); + spin_unlock_irq(bfqd->lock); if (entities !=3D inline_entities) kfree(entities); entities =3D kmalloc_array(depth, sizeof(*entities), GFP_NOIO); @@ -668,7 +668,7 @@ static bool bfqq_request_over_limit(struct bfq_data *bf= qd, } } out: - spin_unlock_irq(&bfqd->lock); + spin_unlock_irq(bfqd->lock); if (entities !=3D inline_entities) kfree(entities); return ret; @@ -2458,18 +2458,9 @@ static bool bfq_bio_merge(struct request_queue *q, s= truct bio *bio, { struct bfq_data *bfqd =3D q->elevator->elevator_data; struct request *free =3D NULL; - /* - * bfq_bic_lookup grabs the queue_lock: invoke it now and - * store its return value for later use, to avoid nesting - * queue_lock inside the bfqd->lock. We assume that the bic - * returned by bfq_bic_lookup does not go away before - * bfqd->lock is taken. - */ struct bfq_io_cq *bic =3D bfq_bic_lookup(q); bool ret; =20 - spin_lock_irq(&bfqd->lock); - if (bic) { /* * Make sure cgroup info is uptodate for current process before @@ -2485,8 +2476,6 @@ static bool bfq_bio_merge(struct request_queue *q, st= ruct bio *bio, bfqd->bio_bic =3D bic; =20 ret =3D blk_mq_sched_try_merge(q, bio, nr_segs, &free); - - spin_unlock_irq(&bfqd->lock); if (free) blk_mq_free_request(free); =20 @@ -2661,7 +2650,7 @@ static void bfq_end_wr(struct bfq_data *bfqd) struct bfq_queue *bfqq; int i; =20 - spin_lock_irq(&bfqd->lock); + spin_lock_irq(bfqd->lock); =20 for (i =3D 0; i < bfqd->num_actuators; i++) { list_for_each_entry(bfqq, &bfqd->active_list[i], bfqq_list) @@ -2671,7 +2660,7 @@ static void bfq_end_wr(struct bfq_data *bfqd) bfq_bfqq_end_wr(bfqq); bfq_end_wr_async(bfqd); =20 - spin_unlock_irq(&bfqd->lock); + spin_unlock_irq(bfqd->lock); } =20 static sector_t bfq_io_struct_pos(void *io_struct, bool request) @@ -5317,8 +5306,6 @@ static struct request *bfq_dispatch_request(struct bl= k_mq_hw_ctx *hctx) struct bfq_queue *in_serv_queue; bool waiting_rq, idle_timer_disabled =3D false; =20 - spin_lock_irq(&bfqd->lock); - in_serv_queue =3D bfqd->in_service_queue; waiting_rq =3D in_serv_queue && bfq_bfqq_wait_request(in_serv_queue); =20 @@ -5328,7 +5315,6 @@ static struct request *bfq_dispatch_request(struct bl= k_mq_hw_ctx *hctx) waiting_rq && !bfq_bfqq_wait_request(in_serv_queue); } =20 - spin_unlock_irq(&bfqd->lock); bfq_update_dispatch_stats(hctx->queue, rq, idle_timer_disabled ? in_serv_queue : NULL, idle_timer_disabled); @@ -5506,9 +5492,9 @@ static void bfq_exit_icq(struct io_cq *icq) * this is the last time these queues are accessed. */ if (bfqd) { - spin_lock_irqsave(&bfqd->lock, flags); + spin_lock_irqsave(bfqd->lock, flags); _bfq_exit_icq(bic, bfqd->num_actuators); - spin_unlock_irqrestore(&bfqd->lock, flags); + spin_unlock_irqrestore(bfqd->lock, flags); } else { _bfq_exit_icq(bic, BFQ_MAX_ACTUATORS); } @@ -6264,10 +6250,8 @@ static void bfq_insert_request(struct blk_mq_hw_ctx = *hctx, struct request *rq, if (!cgroup_subsys_on_dfl(io_cgrp_subsys) && rq->bio) bfqg_stats_update_legacy_io(q, rq); #endif - spin_lock_irq(&bfqd->lock); bfqq =3D bfq_init_rq(rq); if (blk_mq_sched_try_insert_merge(q, rq, &free)) { - spin_unlock_irq(&bfqd->lock); blk_mq_free_requests(&free); return; } @@ -6300,7 +6284,6 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *= hctx, struct request *rq, * merge). */ cmd_flags =3D rq->cmd_flags; - spin_unlock_irq(&bfqd->lock); =20 bfq_update_insert_stats(q, bfqq, idle_timer_disabled, cmd_flags); @@ -6681,7 +6664,7 @@ static void bfq_finish_requeue_request(struct request= *rq) rq->io_start_time_ns, rq->cmd_flags); =20 - spin_lock_irqsave(&bfqd->lock, flags); + spin_lock_irqsave(bfqd->lock, flags); if (likely(rq->rq_flags & RQF_STARTED)) { if (rq =3D=3D bfqd->waited_rq) bfq_update_inject_limit(bfqd, bfqq); @@ -6691,7 +6674,7 @@ static void bfq_finish_requeue_request(struct request= *rq) bfqq_request_freed(bfqq); bfq_put_queue(bfqq); RQ_BIC(rq)->requests--; - spin_unlock_irqrestore(&bfqd->lock, flags); + spin_unlock_irqrestore(bfqd->lock, flags); =20 /* * Reset private fields. In case of a requeue, this allows @@ -7022,7 +7005,7 @@ bfq_idle_slice_timer_body(struct bfq_data *bfqd, stru= ct bfq_queue *bfqq) enum bfqq_expiration reason; unsigned long flags; =20 - spin_lock_irqsave(&bfqd->lock, flags); + spin_lock_irqsave(bfqd->lock, flags); =20 /* * Considering that bfqq may be in race, we should firstly check @@ -7032,7 +7015,7 @@ bfq_idle_slice_timer_body(struct bfq_data *bfqd, stru= ct bfq_queue *bfqq) * been cleared in __bfq_bfqd_reset_in_service func. */ if (bfqq !=3D bfqd->in_service_queue) { - spin_unlock_irqrestore(&bfqd->lock, flags); + spin_unlock_irqrestore(bfqd->lock, flags); return; } =20 @@ -7060,7 +7043,7 @@ bfq_idle_slice_timer_body(struct bfq_data *bfqd, stru= ct bfq_queue *bfqq) =20 schedule_dispatch: bfq_schedule_dispatch(bfqd); - spin_unlock_irqrestore(&bfqd->lock, flags); + spin_unlock_irqrestore(bfqd->lock, flags); } =20 /* @@ -7186,10 +7169,10 @@ static void bfq_exit_queue(struct elevator_queue *e) =20 hrtimer_cancel(&bfqd->idle_slice_timer); =20 - spin_lock_irq(&bfqd->lock); + spin_lock_irq(bfqd->lock); list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list) bfq_deactivate_bfqq(bfqd, bfqq, false, false); - spin_unlock_irq(&bfqd->lock); + spin_unlock_irq(bfqd->lock); =20 for (actuator =3D 0; actuator < bfqd->num_actuators; actuator++) WARN_ON_ONCE(bfqd->rq_in_driver[actuator]); @@ -7203,10 +7186,10 @@ static void bfq_exit_queue(struct elevator_queue *e) #ifdef CONFIG_BFQ_GROUP_IOSCHED blkcg_deactivate_policy(bfqd->queue->disk, &blkcg_policy_bfq); #else - spin_lock_irq(&bfqd->lock); + spin_lock_irq(bfqd->lock); bfq_put_async_queues(bfqd, bfqd->root_group); kfree(bfqd->root_group); - spin_unlock_irq(&bfqd->lock); + spin_unlock_irq(bfqd->lock); #endif =20 blk_stat_disable_accounting(bfqd->queue); @@ -7371,7 +7354,7 @@ static int bfq_init_queue(struct request_queue *q, st= ruct elevator_type *e) /* see comments on the definition of next field inside bfq_data */ bfqd->actuator_load_threshold =3D 4; =20 - spin_lock_init(&bfqd->lock); + bfqd->lock =3D &eq->lock; =20 /* * The invocation of the next bfq_create_group_hierarchy diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 687a3a7ba784..d70eb6529dab 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -795,7 +795,7 @@ struct bfq_data { /* fallback dummy bfqq for extreme OOM conditions */ struct bfq_queue oom_bfqq; =20 - spinlock_t lock; + spinlock_t *lock; =20 /* * bic associated with the task issuing current bio for --=20 2.39.2 From nobody Fri Oct 10 09:22:18 2025 Received: from dggsgout12.his.huawei.com (dggsgout12.his.huawei.com [45.249.212.56]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 09F1E186E2E; Sat, 14 Jun 2025 09:31:45 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.56 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749893508; cv=none; b=D//tfCbQFig0907k/7zjGmKCPjhMK/irU8ARkMB1fXh+J18h9TxWkpovqSFO0AIOEJzrE8jZ9g4qjp3qcnWEUEhHieW+QqXpe4DccVoCsZBYKtbfycaoWnTwp+MhsCtr5Zu/oq7IxTJNwlrtaeD7jnsLxJRfp31RLURjqTd7UMY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749893508; c=relaxed/simple; bh=cj1lp7miltldS+zIRF7ZF/Uu0o9BFCo4+/taIQ0homk=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=K4/lScdWgFc0kC7SeO/MBhS0rdZvW+25HS6xbXK7LrDcxEUhfv/0uofS91Swh/iKOUpqvz3Rvn0aGrqQIuJF6ryWOzseK7TkWfLC1Fs6sTbqnUVP7KoRJUkRITcidY8Lv5KQQarvU21Hsr6Tg5Oc7wTnGT3uj62DIH5rMU9546A= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com; spf=none smtp.mailfrom=huaweicloud.com; arc=none smtp.client-ip=45.249.212.56 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com Authentication-Results: smtp.subspace.kernel.org; spf=none smtp.mailfrom=huaweicloud.com Received: from mail.maildlp.com (unknown [172.19.93.142]) by dggsgout12.his.huawei.com (SkyGuard) with ESMTPS id 4bK9y96F6fzKHNYL; Sat, 14 Jun 2025 17:31:45 +0800 (CST) Received: from mail02.huawei.com (unknown [10.116.40.128]) by mail.maildlp.com (Postfix) with ESMTP id 3A1BD1A179F; Sat, 14 Jun 2025 17:31:44 +0800 (CST) Received: from huaweicloud.com (unknown [10.175.104.67]) by APP4 (Coremail) with SMTP id gCh0CgAni19zQU1oHxfvPQ--.9099S8; Sat, 14 Jun 2025 17:31:44 +0800 (CST) From: Yu Kuai To: ming.lei@redhat.com, yukuai3@huawei.com, tj@kernel.org, josef@toxicpanda.com, axboe@kernel.dk Cc: linux-block@vger.kernel.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, yukuai1@huaweicloud.com, yi.zhang@huawei.com, yangerkun@huawei.com, johnny.chenyi@huawei.com Subject: [PATCH RFC v2 4/5] blk-mq-sched: refactor __blk_mq_do_dispatch_sched() Date: Sat, 14 Jun 2025 17:25:27 +0800 Message-Id: <20250614092528.2352680-5-yukuai1@huaweicloud.com> X-Mailer: git-send-email 2.39.2 In-Reply-To: <20250614092528.2352680-1-yukuai1@huaweicloud.com> References: <20250614092528.2352680-1-yukuai1@huaweicloud.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-CM-TRANSID: gCh0CgAni19zQU1oHxfvPQ--.9099S8 X-Coremail-Antispam: 1UD129KBjvJXoW3Wr45uw17CF1xtrW5try8uFg_yoWxZr48pF 4fGa13J395XF4jqFyI9w43Jw1Sy3yxWasrWryrKr4fJws8Zrs5Jrn5JFyUAFs7JrZ5uFW2 9r4DWr98AFs2qFDanT9S1TB71UUUUU7qnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDU0xBIdaVrnRJUUUmI14x267AKxVWrJVCq3wAFc2x0x2IEx4CE42xK8VAvwI8IcIk0 rVWrJVCq3wAFIxvE14AKwVWUJVWUGwA2048vs2IY020E87I2jVAFwI0_JF0E3s1l82xGYI kIc2x26xkF7I0E14v26ryj6s0DM28lY4IEw2IIxxk0rwA2F7IY1VAKz4vEj48ve4kI8wA2 z4x0Y4vE2Ix0cI8IcVAFwI0_Ar0_tr1l84ACjcxK6xIIjxv20xvEc7CjxVAFwI0_Gr1j6F 4UJwA2z4x0Y4vEx4A2jsIE14v26rxl6s0DM28EF7xvwVC2z280aVCY1x0267AKxVW0oVCq 3wAS0I0E0xvYzxvE52x082IY62kv0487Mc02F40EFcxC0VAKzVAqx4xG6I80ewAv7VC0I7 IYx2IY67AKxVWUXVWUAwAv7VC2z280aVAFwI0_Jr0_Gr1lOx8S6xCaFVCjc4AY6r1j6r4U M4x0Y48IcxkI7VAKI48JM4x0x7Aq67IIx4CEVc8vx2IErcIFxwACI402YVCY1x02628vn2 kIc2xKxwCY1x0262kKe7AKxVWUtVW8ZwCF04k20xvY0x0EwIxGrwCFx2IqxVCFs4IE7xkE bVWUJVW8JwC20s026c02F40E14v26r1j6r18MI8I3I0E7480Y4vE14v26r106r1rMI8E67 AF67kF1VAFwI0_Jw0_GFylIxkGc2Ij64vIr41lIxAIcVC0I7IYx2IY67AKxVWUJVWUCwCI 42IY6xIIjxv20xvEc7CjxVAFwI0_Cr0_Gr1UMIIF0xvE42xK8VAvwI8IcIk0rVWUJVWUCw CI42IY6I8E87Iv67AKxVWUJVW8JwCI42IY6I8E87Iv6xkF7I0E14v26r4j6r4UJbIYCTnI WIevJa73UjIFyTuYvjfUo73vUUUUU X-CM-SenderInfo: 51xn3trlr6x35dzhxuhorxvhhfrp/ Content-Type: text/plain; charset="utf-8" From: Yu Kuai Introduce struct sched_dispatch_ctx, and split the helper into elevator_dispatch_one_request() and elevator_finish_dispatch(). Make code cleaner and prepare to support request batch dispatching. Signed-off-by: Yu Kuai --- block/blk-mq-sched.c | 181 ++++++++++++++++++++++++++----------------- 1 file changed, 109 insertions(+), 72 deletions(-) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index c1390d3e6381..990d0f19594a 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -74,85 +74,88 @@ static bool blk_mq_dispatch_hctx_list(struct list_head = *rq_list) =20 #define BLK_MQ_BUDGET_DELAY 3 /* ms units */ =20 -/* - * 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() 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 int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) -{ - struct request_queue *q =3D hctx->queue; - struct elevator_queue *e =3D q->elevator; - bool multi_hctxs =3D false, run_queue =3D false; - bool dispatched =3D false, busy =3D false; - unsigned int max_dispatch; - LIST_HEAD(rq_list); - int count =3D 0; +struct sched_dispatch_ctx { + struct blk_mq_hw_ctx *hctx; + struct elevator_queue *e; + struct request_queue *q; =20 - if (hctx->dispatch_busy) - max_dispatch =3D 1; - else - max_dispatch =3D hctx->queue->nr_requests; + struct list_head rq_list; + int count; =20 - do { - struct request *rq; - int budget_token; + bool multi_hctxs; + bool run_queue; + bool busy; +}; =20 - if (e->type->ops.has_work && !e->type->ops.has_work(hctx)) - break; +static bool elevator_can_dispatch(struct sched_dispatch_ctx *ctx) +{ + if (ctx->e->type->ops.has_work && + !ctx->e->type->ops.has_work(ctx->hctx)) + return false; =20 - if (!list_empty_careful(&hctx->dispatch)) { - busy =3D true; - break; - } + if (!list_empty_careful(&ctx->hctx->dispatch)) { + ctx->busy =3D true; + return false; + } =20 - budget_token =3D blk_mq_get_dispatch_budget(q); - if (budget_token < 0) - break; + return true; +} =20 - rq =3D elevator_dispatch_request(hctx); - if (!rq) { - blk_mq_put_dispatch_budget(q, budget_token); - /* - * 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 =3D true; - break; - } +static bool elevator_dispatch_one_request(struct sched_dispatch_ctx *ctx) +{ + struct request *rq; + int budget_token; =20 - blk_mq_set_rq_budget_token(rq, budget_token); + if (!elevator_can_dispatch(ctx)) + return false; =20 - /* - * Now this rq owns the budget which has to be released - * if this rq won't be queued to driver via .queue_rq() - * in blk_mq_dispatch_rq_list(). - */ - list_add_tail(&rq->queuelist, &rq_list); - count++; - if (rq->mq_hctx !=3D hctx) - multi_hctxs =3D true; + budget_token =3D blk_mq_get_dispatch_budget(ctx->q); + if (budget_token < 0) + return false; =20 + rq =3D elevator_dispatch_request(ctx->hctx); + if (!rq) { + blk_mq_put_dispatch_budget(ctx->q, budget_token); /* - * If we cannot get tag for the request, stop dequeueing - * requests from the IO scheduler. We are unlikely to be able - * to submit them anyway and it creates false impression for - * scheduling heuristics that the device can take more IO. + * 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. */ - if (!blk_mq_get_driver_tag(rq)) - break; - } while (count < max_dispatch); + ctx->run_queue =3D true; + return false; + } =20 - if (!count) { - if (run_queue) - blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); - } else if (multi_hctxs) { + blk_mq_set_rq_budget_token(rq, budget_token); + + /* + * Now this rq owns the budget which has to be released + * if this rq won't be queued to driver via .queue_rq() + * in blk_mq_dispatch_rq_list(). + */ + list_add_tail(&rq->queuelist, &ctx->rq_list); + ctx->count++; + if (rq->mq_hctx !=3D ctx->hctx) + ctx->multi_hctxs =3D true; + + /* + * If we cannot get tag for the request, stop dequeueing + * requests from the IO scheduler. We are unlikely to be able + * to submit them anyway and it creates false impression for + * scheduling heuristics that the device can take more IO. + */ + return blk_mq_get_driver_tag(rq); +} + +static int elevator_finish_dispatch(struct sched_dispatch_ctx *ctx) +{ + bool dispatched =3D false; + + if (!ctx->count) { + if (ctx->run_queue) + blk_mq_delay_run_hw_queues(ctx->q, BLK_MQ_BUDGET_DELAY); + } else if (ctx->multi_hctxs) { /* * Requests from different hctx may be dequeued from some * schedulers, such as bfq and deadline. @@ -160,19 +163,53 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_h= w_ctx *hctx) * 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); + list_sort(NULL, &ctx->rq_list, sched_rq_cmp); do { - dispatched |=3D blk_mq_dispatch_hctx_list(&rq_list); - } while (!list_empty(&rq_list)); + dispatched |=3D blk_mq_dispatch_hctx_list(&ctx->rq_list); + } while (!list_empty(&ctx->rq_list)); } else { - dispatched =3D blk_mq_dispatch_rq_list(hctx, &rq_list, false); + dispatched =3D blk_mq_dispatch_rq_list(ctx->hctx, &ctx->rq_list, + false); } =20 - if (busy) + if (ctx->busy) return -EAGAIN; + return !!dispatched; } =20 +/* + * 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() 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 int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) +{ + unsigned int max_dispatch; + struct sched_dispatch_ctx ctx =3D { + .hctx =3D hctx, + .q =3D hctx->queue, + .e =3D hctx->queue->elevator, + }; + + INIT_LIST_HEAD(&ctx.rq_list); + + if (hctx->dispatch_busy) + max_dispatch =3D 1; + else + max_dispatch =3D hctx->queue->nr_requests; + + do { + if (!elevator_dispatch_one_request(&ctx)) + break; + } while (ctx.count < max_dispatch); + + return elevator_finish_dispatch(&ctx); +} + static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) { unsigned long end =3D jiffies + HZ; --=20 2.39.2 From nobody Fri Oct 10 09:22:18 2025 Received: from dggsgout11.his.huawei.com (dggsgout11.his.huawei.com [45.249.212.51]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A13C3155CBD; Sat, 14 Jun 2025 09:31:46 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.51 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749893509; cv=none; b=GTO9hPFcCoCQEE7Fwd2rpEiJw00yLQIaOobCdoYvvZ2Dk240C9roxiIdwZCNvKHjqLzdHFrn4tx/UrzvuFIhRujSSgySX+rAQu2EiEjhg7NBhtkM1u5o0Kk0/zyxflV6mbPN5Gu2a6p9b5qpr0yyQqHpU1HrW8v5G282sLLtVQs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749893509; c=relaxed/simple; bh=m157EbdqaysdWSxG7epQ+w2dupFLoeJrQFDqv9WR4ww=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=s8YK7mzduUhILdOnSr98HDEwSI/mVOozIbJ6IEM9o/ulp4VcHCmnCZbCKECczACbVL2y0WQg+tg5+DFx5dg0w3cVMWtwob9Td3MlkPj0d9c0MHCtqIKfoHL6RO39RQZC19MuDJa48+zAlm65kGsXBQfl5sJQrckwEUPQi6lwWCs= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com; spf=none smtp.mailfrom=huaweicloud.com; arc=none smtp.client-ip=45.249.212.51 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com Authentication-Results: smtp.subspace.kernel.org; spf=none smtp.mailfrom=huaweicloud.com Received: from mail.maildlp.com (unknown [172.19.93.142]) by dggsgout11.his.huawei.com (SkyGuard) with ESMTPS id 4bK9y95WlrzYQvP4; Sat, 14 Jun 2025 17:31:45 +0800 (CST) Received: from mail02.huawei.com (unknown [10.116.40.128]) by mail.maildlp.com (Postfix) with ESMTP id B95C51A17A7; Sat, 14 Jun 2025 17:31:44 +0800 (CST) Received: from huaweicloud.com (unknown [10.175.104.67]) by APP4 (Coremail) with SMTP id gCh0CgAni19zQU1oHxfvPQ--.9099S9; Sat, 14 Jun 2025 17:31:44 +0800 (CST) From: Yu Kuai To: ming.lei@redhat.com, yukuai3@huawei.com, tj@kernel.org, josef@toxicpanda.com, axboe@kernel.dk Cc: linux-block@vger.kernel.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, yukuai1@huaweicloud.com, yi.zhang@huawei.com, yangerkun@huawei.com, johnny.chenyi@huawei.com Subject: [PATCH RFC v2 5/5] blk-mq-sched: support request batch dispatching for sq elevator Date: Sat, 14 Jun 2025 17:25:28 +0800 Message-Id: <20250614092528.2352680-6-yukuai1@huaweicloud.com> X-Mailer: git-send-email 2.39.2 In-Reply-To: <20250614092528.2352680-1-yukuai1@huaweicloud.com> References: <20250614092528.2352680-1-yukuai1@huaweicloud.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-CM-TRANSID: gCh0CgAni19zQU1oHxfvPQ--.9099S9 X-Coremail-Antispam: 1UD129KBjvJXoWxCF45Cr43KrW3tFW3Zr1DJrb_yoW5ur45pF 4rGa1YkryqqFnFqFy3Aw47J3W5J3yI9r9rWrW3Kr43JFs7Xrsxt3WrJa4UJF4xJr4rCFsr ur4DWFyDuF1Iva7anT9S1TB71UUUUU7qnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDU0xBIdaVrnRJUUUmI14x267AKxVWrJVCq3wAFc2x0x2IEx4CE42xK8VAvwI8IcIk0 rVWrJVCq3wAFIxvE14AKwVWUJVWUGwA2048vs2IY020E87I2jVAFwI0_JF0E3s1l82xGYI kIc2x26xkF7I0E14v26ryj6s0DM28lY4IEw2IIxxk0rwA2F7IY1VAKz4vEj48ve4kI8wA2 z4x0Y4vE2Ix0cI8IcVAFwI0_Ar0_tr1l84ACjcxK6xIIjxv20xvEc7CjxVAFwI0_Gr1j6F 4UJwA2z4x0Y4vEx4A2jsIE14v26rxl6s0DM28EF7xvwVC2z280aVCY1x0267AKxVW0oVCq 3wAS0I0E0xvYzxvE52x082IY62kv0487Mc02F40EFcxC0VAKzVAqx4xG6I80ewAv7VC0I7 IYx2IY67AKxVWUXVWUAwAv7VC2z280aVAFwI0_Jr0_Gr1lOx8S6xCaFVCjc4AY6r1j6r4U M4x0Y48IcxkI7VAKI48JM4x0x7Aq67IIx4CEVc8vx2IErcIFxwACI402YVCY1x02628vn2 kIc2xKxwCY1x0262kKe7AKxVWUtVW8ZwCF04k20xvY0x0EwIxGrwCFx2IqxVCFs4IE7xkE bVWUJVW8JwC20s026c02F40E14v26r1j6r18MI8I3I0E7480Y4vE14v26r106r1rMI8E67 AF67kF1VAFwI0_Jw0_GFylIxkGc2Ij64vIr41lIxAIcVC0I7IYx2IY67AKxVWUCVW8JwCI 42IY6xIIjxv20xvEc7CjxVAFwI0_Cr0_Gr1UMIIF0xvE42xK8VAvwI8IcIk0rVWUJVWUCw CI42IY6I8E87Iv67AKxVWUJVW8JwCI42IY6I8E87Iv6xkF7I0E14v26r4j6r4UJbIYCTnI WIevJa73UjIFyTuYvjfUo73vUUUUU X-CM-SenderInfo: 51xn3trlr6x35dzhxuhorxvhhfrp/ Content-Type: text/plain; charset="utf-8" From: Yu Kuai Before this patch, each context will hold a global lock to dispatch one request at a time, which introduce intense lock competition: lock ops.dispatch_request unlock Hence support dispatch a batch of requests while holding the lock to reduce lock contention. Signed-off-by: Yu Kuai --- block/blk-mq-sched.c | 55 ++++++++++++++++++++++++++++++++++++++++---- block/blk-mq.h | 21 +++++++++++++++++ 2 files changed, 72 insertions(+), 4 deletions(-) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 990d0f19594a..d7cb88c8e8c7 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -101,6 +101,49 @@ static bool elevator_can_dispatch(struct sched_dispatc= h_ctx *ctx) return true; } =20 +static void elevator_dispatch_requests(struct sched_dispatch_ctx *ctx) +{ + struct request *rq; + int budget_token[BUDGET_TOKEN_BATCH]; + int count; + int i; + + while (true) { + if (!elevator_can_dispatch(ctx)) + return; + + count =3D blk_mq_get_dispatch_budgets(ctx->q, budget_token); + if (count <=3D 0) + return; + + elevator_lock(ctx->e); + for (i =3D 0; i < count; ++i) { + rq =3D ctx->e->type->ops.dispatch_request(ctx->hctx); + if (!rq) { + ctx->run_queue =3D true; + goto err_free_budgets; + } + + blk_mq_set_rq_budget_token(rq, budget_token[i]); + list_add_tail(&rq->queuelist, &ctx->rq_list); + ctx->count++; + if (rq->mq_hctx !=3D ctx->hctx) + ctx->multi_hctxs =3D true; + + if (!blk_mq_get_driver_tag(rq)) { + i++; + goto err_free_budgets; + } + } + elevator_unlock(ctx->e); + } + +err_free_budgets: + elevator_unlock(ctx->e); + for (; i < count; ++i) + blk_mq_put_dispatch_budget(ctx->q, budget_token[i]); +} + static bool elevator_dispatch_one_request(struct sched_dispatch_ctx *ctx) { struct request *rq; @@ -202,10 +245,14 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_h= w_ctx *hctx) else max_dispatch =3D hctx->queue->nr_requests; =20 - do { - if (!elevator_dispatch_one_request(&ctx)) - break; - } while (ctx.count < max_dispatch); + if (!hctx->dispatch_busy && blk_queue_sq_sched(ctx.q)) + elevator_dispatch_requests(&ctx); + else { + do { + if (!elevator_dispatch_one_request(&ctx)) + break; + } while (ctx.count < max_dispatch); + } =20 return elevator_finish_dispatch(&ctx); } diff --git a/block/blk-mq.h b/block/blk-mq.h index affb2e14b56e..450c16a07841 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -37,6 +37,7 @@ enum { }; =20 #define BLK_MQ_CPU_WORK_BATCH (8) +#define BUDGET_TOKEN_BATCH (8) =20 typedef unsigned int __bitwise blk_insert_t; #define BLK_MQ_INSERT_AT_HEAD ((__force blk_insert_t)0x01) @@ -262,6 +263,26 @@ static inline int blk_mq_get_dispatch_budget(struct re= quest_queue *q) return 0; } =20 +static inline int blk_mq_get_dispatch_budgets(struct request_queue *q, + int *budget_token) +{ + int count =3D 0; + + while (count < BUDGET_TOKEN_BATCH) { + int token =3D 0; + + if (q->mq_ops->get_budget) + token =3D q->mq_ops->get_budget(q); + + if (token < 0) + return count; + + budget_token[count++] =3D token; + } + + return count; +} + static inline void blk_mq_set_rq_budget_token(struct request *rq, int toke= n) { if (token < 0) --=20 2.39.2