public inbox for linux-block@vger.kernel.org
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: "linux-block@vger.kernel.org" <linux-block@vger.kernel.org>
Subject: [PATCH] block: ensure that struct blk_mq_alloc_data is fully initialized
Date: Tue, 15 Apr 2025 08:51:39 -0600	[thread overview]
Message-ID: <1720cf81-6170-4cac-abf3-e19a4493653b@kernel.dk> (raw)

On x86, rep stos will be emitted to clear the the blk_mq_alloc_data
struct, as not all members are being initialied. Depending on the
type of CPU, this is a noticeable slowdown compared to just ensuring
that the struct is fully initialized when setup.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

---

diff --git a/block/blk-mq.c b/block/blk-mq.c
index c2697db59109..9fb43b09a401 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -584,9 +584,13 @@ static struct request *blk_mq_rq_cache_fill(struct request_queue *q,
 	struct blk_mq_alloc_data data = {
 		.q		= q,
 		.flags		= flags,
+		.shallow_depth	= 0,
 		.cmd_flags	= opf,
+		.rq_flags	= 0,
 		.nr_tags	= plug->nr_ios,
 		.cached_rqs	= &plug->cached_rqs,
+		.ctx		= NULL,
+		.hctx		= NULL
 	};
 	struct request *rq;
 
@@ -646,8 +650,13 @@ struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf,
 		struct blk_mq_alloc_data data = {
 			.q		= q,
 			.flags		= flags,
+			.shallow_depth	= 0,
 			.cmd_flags	= opf,
+			.rq_flags	= 0,
 			.nr_tags	= 1,
+			.cached_rqs	= NULL,
+			.ctx		= NULL,
+			.hctx		= NULL
 		};
 		int ret;
 
@@ -675,8 +684,13 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	struct blk_mq_alloc_data data = {
 		.q		= q,
 		.flags		= flags,
+		.shallow_depth	= 0,
 		.cmd_flags	= opf,
+		.rq_flags	= 0,
 		.nr_tags	= 1,
+		.cached_rqs	= NULL,
+		.ctx		= NULL,
+		.hctx		= NULL
 	};
 	u64 alloc_time_ns = 0;
 	struct request *rq;
@@ -2969,8 +2983,14 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 {
 	struct blk_mq_alloc_data data = {
 		.q		= q,
-		.nr_tags	= 1,
+		.flags		= 0,
+		.shallow_depth	= 0,
 		.cmd_flags	= bio->bi_opf,
+		.rq_flags	= 0,
+		.nr_tags	= 1,
+		.cached_rqs	= NULL,
+		.ctx		= NULL,
+		.hctx		= NULL
 	};
 	struct request *rq;
 
-- 
Jens Axboe


             reply	other threads:[~2025-04-15 14:51 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-15 14:51 Jens Axboe [this message]
2025-04-15 15:39 ` [PATCH] block: ensure that struct blk_mq_alloc_data is fully initialized Chaitanya Kulkarni
2025-04-15 15:50 ` Bart Van Assche
2025-04-15 15:59   ` Jens Axboe
2025-04-15 16:13     ` Bart Van Assche
2025-04-15 16:15       ` Jens Axboe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1720cf81-6170-4cac-abf3-e19a4493653b@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=linux-block@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox