From: Keith Busch <kbusch@meta.com>
To: <linux-block@vger.kernel.org>, <linux-nvme@lists.infradead.org>,
<linux-scsi@vger.kernel.org>, <io-uring@vger.kernel.org>
Cc: <linux-fsdevel@vger.kernel.org>, <hch@lst.de>,
<joshi.k@samsung.com>, <javier.gonz@samsung.com>,
<bvanassche@acm.org>, Keith Busch <kbusch@kernel.org>
Subject: [PATCHv9 4/7] block, fs: add write hint to kiocb
Date: Fri, 25 Oct 2024 14:36:42 -0700 [thread overview]
Message-ID: <20241025213645.3464331-5-kbusch@meta.com> (raw)
In-Reply-To: <20241025213645.3464331-1-kbusch@meta.com>
From: Keith Busch <kbusch@kernel.org>
This prepares for sources other than the inode to provide a write hint.
The block layer will use it for direct IO if the requested hint is
within the block device's capabilities.
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
block/fops.c | 26 +++++++++++++++++++++++---
include/linux/fs.h | 1 +
2 files changed, 24 insertions(+), 3 deletions(-)
diff --git a/block/fops.c b/block/fops.c
index 2d01c90076813..e3f3f1957d86d 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -71,7 +71,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb));
}
bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
- bio.bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
+ bio.bi_write_hint = iocb->ki_write_hint;
bio.bi_ioprio = iocb->ki_ioprio;
if (iocb->ki_flags & IOCB_ATOMIC)
bio.bi_opf |= REQ_ATOMIC;
@@ -200,7 +200,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
for (;;) {
bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
- bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
+ bio->bi_write_hint = iocb->ki_write_hint;
bio->bi_private = dio;
bio->bi_end_io = blkdev_bio_end_io;
bio->bi_ioprio = iocb->ki_ioprio;
@@ -316,7 +316,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
dio->flags = 0;
dio->iocb = iocb;
bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
- bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
+ bio->bi_write_hint = iocb->ki_write_hint;
bio->bi_end_io = blkdev_bio_end_io_async;
bio->bi_ioprio = iocb->ki_ioprio;
@@ -362,6 +362,23 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
return -EIOCBQUEUED;
}
+static u16 blkdev_write_hint(struct kiocb *iocb, struct block_device *bdev)
+{
+ u16 hint = iocb->ki_write_hint;
+
+ if (!hint)
+ return file_inode(iocb->ki_filp)->i_write_hint;
+
+ if (hint > bdev_max_write_hints(bdev))
+ return file_inode(iocb->ki_filp)->i_write_hint;
+
+ if (bdev_is_partition(bdev) &&
+ !test_bit(hint - 1, bdev->write_hint_mask))
+ return file_inode(iocb->ki_filp)->i_write_hint;
+
+ return hint;
+}
+
static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
@@ -373,6 +390,9 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
if (blkdev_dio_invalid(bdev, iocb, iter))
return -EINVAL;
+ if (iov_iter_rw(iter) == WRITE)
+ iocb->ki_write_hint = blkdev_write_hint(iocb, bdev);
+
nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
if (likely(nr_pages <= BIO_MAX_VECS)) {
if (is_sync_kiocb(iocb))
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4b5cad44a1268..1a00accf412e5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -370,6 +370,7 @@ struct kiocb {
void *private;
int ki_flags;
u16 ki_ioprio; /* See linux/ioprio.h */
+ u16 ki_write_hint;
union {
/*
* Only used for async buffered reads, where it denotes the
--
2.43.5
next prev parent reply other threads:[~2024-10-25 21:37 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-25 21:36 [PATCHv9 0/7] write hints with nvme fdp, scsi streams Keith Busch
2024-10-25 21:36 ` [PATCHv9 3/7] block: allow ability to limit partition write hints Keith Busch
2024-10-28 11:58 ` Christoph Hellwig
2024-10-28 14:49 ` Keith Busch
2024-10-28 14:40 ` Kanchan Joshi
2024-10-28 18:27 ` Bart Van Assche
2024-10-28 19:46 ` Keith Busch
2024-10-25 21:36 ` Keith Busch [this message]
2024-10-28 11:59 ` [PATCHv9 4/7] block, fs: add write hint to kiocb Christoph Hellwig
2024-10-28 14:38 ` Keith Busch
2024-10-28 16:08 ` Christoph Hellwig
2024-10-25 21:36 ` [PATCHv9 7/7] scsi: set permanent stream count in block limits Keith Busch
2024-10-28 16:13 ` Bart Van Assche
2024-10-29 7:10 ` Hannes Reinecke
2024-10-28 11:49 ` [PATCHv9 0/7] write hints with nvme fdp, scsi streams Christoph Hellwig
[not found] ` <20241025213645.3464331-3-kbusch@meta.com>
2024-10-28 11:51 ` [PATCHv9 2/7] block: introduce max_write_hints queue limit Christoph Hellwig
2024-10-28 11:52 ` Christoph Hellwig
[not found] ` <20241025213645.3464331-2-kbusch@meta.com>
2024-10-28 18:19 ` [PATCHv9 1/7] block: use generic u16 for write hints Bart Van Assche
2024-10-28 18:38 ` Keith Busch
[not found] ` <20241025213645.3464331-6-kbusch@meta.com>
2024-10-29 12:46 ` [PATCHv9 5/7] io_uring: enable per-io hinting capability Anuj gupta
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=20241025213645.3464331-5-kbusch@meta.com \
--to=kbusch@meta.com \
--cc=bvanassche@acm.org \
--cc=hch@lst.de \
--cc=io-uring@vger.kernel.org \
--cc=javier.gonz@samsung.com \
--cc=joshi.k@samsung.com \
--cc=kbusch@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-scsi@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;
as well as URLs for NNTP newsgroup(s).