From: Keith Busch <kbusch@meta.com>
To: <linux-nvme@lists.infradead.org>, <linux-block@vger.kernel.org>,
<joshi.k@samsung.com>, <axboe@kernel.dk>, <hch@lst.de>,
<xiaoguang.wang@linux.alibaba.com>
Cc: Keith Busch <kbusch@kernel.org>
Subject: [RFC 1/3] nvme: skip block cgroups for passthrough commands
Date: Mon, 1 May 2023 08:33:04 -0700 [thread overview]
Message-ID: <20230501153306.537124-2-kbusch@meta.com> (raw)
In-Reply-To: <20230501153306.537124-1-kbusch@meta.com>
From: Keith Busch <kbusch@kernel.org>
Passthrough requests don't go through the submit_bio() path, so all the
overhead of setting up the bio's cgroup is wasted cycles. Provide a path
to skip this setup.
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
drivers/nvme/host/ioctl.c | 2 +-
include/linux/bio.h | 7 ++++++-
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index d24ea2e051564..3804e5205b42b 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -192,7 +192,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
goto out;
bio = req->bio;
if (bdev)
- bio_set_dev(bio, bdev);
+ __bio_set_dev(bio, bdev);
if (bdev && meta_buffer && meta_len) {
meta = nvme_add_user_metadata(req, meta_buffer, meta_len,
diff --git a/include/linux/bio.h b/include/linux/bio.h
index d766be7152e15..bf003412653dc 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -509,12 +509,17 @@ static inline void bio_clone_blkg_association(struct bio *dst,
struct bio *src) { }
#endif /* CONFIG_BLK_CGROUP */
-static inline void bio_set_dev(struct bio *bio, struct block_device *bdev)
+static inline void __bio_set_dev(struct bio *bio, struct block_device *bdev)
{
bio_clear_flag(bio, BIO_REMAPPED);
if (bio->bi_bdev != bdev)
bio_clear_flag(bio, BIO_BPS_THROTTLED);
bio->bi_bdev = bdev;
+}
+
+static inline void bio_set_dev(struct bio *bio, struct block_device *bdev)
+{
+ __bio_set_dev(bio, bdev);
bio_associate_blkg(bio);
}
--
2.34.1
next prev parent reply other threads:[~2023-05-01 15:33 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20230501154403epcas5p388c607114ad6f9d20dfd3ec958d88947@epcas5p3.samsung.com>
2023-05-01 15:33 ` [RFC 0/3] nvme uring passthrough diet Keith Busch
2023-05-01 15:33 ` Keith Busch [this message]
2023-05-03 5:04 ` [RFC 1/3] nvme: skip block cgroups for passthrough commands Christoph Hellwig
2023-05-03 15:25 ` Keith Busch
2023-05-15 15:47 ` Keith Busch
2023-05-01 15:33 ` [RFC 2/3] nvme: fix cdev name leak Keith Busch
2023-05-01 15:33 ` [RFC 3/3] nvme: create special request queue for cdev Keith Busch
2023-05-02 12:20 ` Johannes Thumshirn
2023-05-03 5:04 ` Christoph Hellwig
2023-05-03 14:56 ` Keith Busch
2023-05-01 19:01 ` [RFC 0/3] nvme uring passthrough diet Kanchan Joshi
2023-05-01 19:31 ` Keith Busch
2023-05-03 7:27 ` Kanchan Joshi
2023-05-03 15:20 ` Keith Busch
2023-05-05 8:14 ` Kanchan Joshi
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=20230501153306.537124-2-kbusch@meta.com \
--to=kbusch@meta.com \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=joshi.k@samsung.com \
--cc=kbusch@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=xiaoguang.wang@linux.alibaba.com \
/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;
as well as URLs for NNTP newsgroup(s).