From: John Garry <john.g.garry@oracle.com>
To: axboe@kernel.dk, kbusch@kernel.org, hch@lst.de, sagi@grimberg.me,
martin.petersen@oracle.com, djwong@kernel.org,
viro@zeniv.linux.org.uk, brauner@kernel.org, dchinner@redhat.com,
jejb@linux.ibm.com
Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-nvme@lists.infradead.org, linux-scsi@vger.kernel.org,
linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-security-module@vger.kernel.org, paul@paul-moore.com,
jmorris@namei.org, serge@hallyn.com,
John Garry <john.g.garry@oracle.com>
Subject: [PATCH RFC 10/16] block: Add fops atomic write support
Date: Wed, 3 May 2023 18:38:15 +0000 [thread overview]
Message-ID: <20230503183821.1473305-11-john.g.garry@oracle.com> (raw)
In-Reply-To: <20230503183821.1473305-1-john.g.garry@oracle.com>
Add support to set bio->atomic_write_unit
Signed-off-by: John Garry <john.g.garry@oracle.com>
---
block/fops.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 51 insertions(+), 5 deletions(-)
diff --git a/block/fops.c b/block/fops.c
index d2e6be4e3d1c..9a2c595cd93d 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -43,8 +43,17 @@ static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
}
static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
- struct iov_iter *iter)
+ struct iov_iter *iter, bool atomic_write)
{
+ if (atomic_write) {
+ unsigned int atomic_write_unit_min =
+ queue_atomic_write_unit_min(bdev_get_queue(bdev));
+ if (pos % atomic_write_unit_min)
+ return false;
+ if (iov_iter_count(iter) % atomic_write_unit_min)
+ return false;
+ }
+
return pos & (bdev_logical_block_size(bdev) - 1) ||
!bdev_iter_is_aligned(bdev, iter);
}
@@ -56,12 +65,21 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
{
struct block_device *bdev = iocb->ki_filp->private_data;
struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs;
+ bool is_read = iov_iter_rw(iter) == READ;
+ bool atomic_write = (iocb->ki_flags & IOCB_ATOMIC) && !is_read;
+ unsigned int max_align_bytes = 0;
loff_t pos = iocb->ki_pos;
bool should_dirty = false;
struct bio bio;
ssize_t ret;
- if (blkdev_dio_unaligned(bdev, pos, iter))
+ /* iov_iter_count() return value will change later, so calculate now */
+ if (atomic_write) {
+ max_align_bytes = bdev_find_max_atomic_write_alignment(bdev,
+ iocb->ki_pos, iov_iter_count(iter));
+ }
+
+ if (blkdev_dio_unaligned(bdev, pos, iter, atomic_write))
return -EINVAL;
if (nr_pages <= DIO_INLINE_BIO_VECS)
@@ -73,7 +91,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
return -ENOMEM;
}
- if (iov_iter_rw(iter) == READ) {
+ if (is_read) {
bio_init(&bio, bdev, vecs, nr_pages, REQ_OP_READ);
if (user_backed_iter(iter))
should_dirty = true;
@@ -82,6 +100,10 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
}
bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
bio.bi_ioprio = iocb->ki_ioprio;
+ if (atomic_write) {
+ bio.bi_opf |= REQ_ATOMIC;
+ bio.atomic_write_unit = max_align_bytes;
+ }
ret = bio_iov_iter_get_pages(&bio, iter);
if (unlikely(ret))
@@ -175,11 +197,19 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
struct blkdev_dio *dio;
struct bio *bio;
bool is_read = (iov_iter_rw(iter) == READ), is_sync;
+ bool atomic_write = (iocb->ki_flags & IOCB_ATOMIC) && !is_read;
blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
+ unsigned int max_align_bytes = 0;
loff_t pos = iocb->ki_pos;
int ret = 0;
- if (blkdev_dio_unaligned(bdev, pos, iter))
+ /* iov_iter_count() return value will change later, so calculate now */
+ if (atomic_write) {
+ max_align_bytes = bdev_find_max_atomic_write_alignment(bdev,
+ iocb->ki_pos, iov_iter_count(iter));
+ }
+
+ if (blkdev_dio_unaligned(bdev, pos, iter, atomic_write))
return -EINVAL;
if (iocb->ki_flags & IOCB_ALLOC_CACHE)
@@ -214,6 +244,8 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
bio->bi_private = dio;
bio->bi_end_io = blkdev_bio_end_io;
bio->bi_ioprio = iocb->ki_ioprio;
+ if (atomic_write)
+ bio->atomic_write_unit = max_align_bytes;
ret = bio_iov_iter_get_pages(bio, iter);
if (unlikely(ret)) {
@@ -244,8 +276,11 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
if (dio->flags & DIO_SHOULD_DIRTY)
bio_set_pages_dirty(bio);
} else {
+ if (atomic_write)
+ bio->bi_opf |= REQ_ATOMIC;
task_io_account_write(bio->bi_iter.bi_size);
}
+
dio->size += bio->bi_iter.bi_size;
pos += bio->bi_iter.bi_size;
@@ -313,14 +348,21 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
struct block_device *bdev = iocb->ki_filp->private_data;
bool is_read = iov_iter_rw(iter) == READ;
blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
+ bool atomic_write = (iocb->ki_flags & IOCB_ATOMIC) && !is_read;
+ unsigned int max_align_bytes = 0;
struct blkdev_dio *dio;
struct bio *bio;
loff_t pos = iocb->ki_pos;
int ret = 0;
- if (blkdev_dio_unaligned(bdev, pos, iter))
+ if (blkdev_dio_unaligned(bdev, pos, iter, atomic_write))
return -EINVAL;
+ if (atomic_write) {
+ max_align_bytes = bdev_find_max_atomic_write_alignment(bdev,
+ iocb->ki_pos, iov_iter_count(iter));
+ }
+
if (iocb->ki_flags & IOCB_ALLOC_CACHE)
opf |= REQ_ALLOC_CACHE;
bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL,
@@ -331,6 +373,8 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
bio->bi_end_io = blkdev_bio_end_io_async;
bio->bi_ioprio = iocb->ki_ioprio;
+ if (atomic_write)
+ bio->atomic_write_unit = max_align_bytes;
if (iov_iter_is_bvec(iter)) {
/*
@@ -355,6 +399,8 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
bio_set_pages_dirty(bio);
}
} else {
+ if (atomic_write)
+ bio->bi_opf |= REQ_ATOMIC;
task_io_account_write(bio->bi_iter.bi_size);
}
--
2.31.1
next prev parent reply other threads:[~2023-05-03 20:03 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-03 18:38 [PATCH RFC 00/16] block atomic writes John Garry
2023-05-03 18:38 ` [PATCH RFC 01/16] block: Add atomic write operations to request_queue limits John Garry
2023-05-03 21:39 ` Dave Chinner
2023-05-04 18:14 ` John Garry
2023-05-04 22:26 ` Dave Chinner
2023-05-05 7:54 ` John Garry
2023-05-05 22:00 ` Darrick J. Wong
2023-05-07 1:59 ` Martin K. Petersen
2023-05-05 23:18 ` Dave Chinner
2023-05-06 9:38 ` John Garry
2023-05-07 2:35 ` Martin K. Petersen
2023-05-05 22:47 ` Eric Biggers
2023-05-05 23:31 ` Dave Chinner
2023-05-06 0:08 ` Eric Biggers
2023-05-09 0:19 ` Mike Snitzer
2023-05-17 17:02 ` John Garry
2023-05-03 18:38 ` [PATCH RFC 02/16] fs/bdev: Add atomic write support info to statx John Garry
2023-05-03 21:58 ` Dave Chinner
2023-05-04 8:45 ` John Garry
2023-05-04 22:40 ` Dave Chinner
2023-05-05 8:01 ` John Garry
2023-05-05 22:04 ` Darrick J. Wong
2023-05-03 18:38 ` [PATCH RFC 03/16] xfs: Support atomic write for statx John Garry
2023-05-03 22:17 ` Dave Chinner
2023-05-05 22:10 ` Darrick J. Wong
2023-05-03 18:38 ` [PATCH RFC 04/16] fs: Add RWF_ATOMIC and IOCB_ATOMIC flags for atomic write support John Garry
2023-05-03 18:38 ` [PATCH RFC 05/16] block: Add REQ_ATOMIC flag John Garry
2023-05-03 18:38 ` [PATCH RFC 06/16] block: Limit atomic writes according to bio and queue limits John Garry
2023-05-03 18:53 ` Keith Busch
2023-05-04 8:24 ` John Garry
2023-05-03 18:38 ` [PATCH RFC 07/16] block: Add bdev_find_max_atomic_write_alignment() John Garry
2023-05-03 18:38 ` [PATCH RFC 08/16] block: Add support for atomic_write_unit John Garry
2023-05-03 18:38 ` [PATCH RFC 09/16] block: Add blk_validate_atomic_write_op() John Garry
2023-05-03 18:38 ` John Garry [this message]
2023-05-03 18:38 ` [PATCH RFC 11/16] fs: iomap: Atomic write support John Garry
2023-05-04 5:00 ` Dave Chinner
2023-05-05 21:19 ` Darrick J. Wong
2023-05-05 23:56 ` Dave Chinner
2023-05-03 18:38 ` [PATCH RFC 12/16] xfs: Add support for fallocate2 John Garry
2023-05-03 23:26 ` Dave Chinner
2023-05-05 22:23 ` Darrick J. Wong
2023-05-05 23:42 ` Dave Chinner
2023-05-03 18:38 ` [PATCH RFC 13/16] scsi: sd: Support reading atomic properties from block limits VPD John Garry
2023-05-03 18:38 ` [PATCH RFC 14/16] scsi: sd: Add WRITE_ATOMIC_16 support John Garry
2023-05-03 18:48 ` Bart Van Assche
2023-05-04 8:17 ` John Garry
2023-05-03 18:38 ` [PATCH RFC 15/16] scsi: scsi_debug: Atomic write support John Garry
2023-05-03 18:38 ` [PATCH RFC 16/16] nvme: Support atomic writes John Garry
2023-05-03 18:49 ` Bart Van Assche
2023-05-04 8:19 ` John Garry
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=20230503183821.1473305-11-john.g.garry@oracle.com \
--to=john.g.garry@oracle.com \
--cc=axboe@kernel.dk \
--cc=brauner@kernel.org \
--cc=dchinner@redhat.com \
--cc=djwong@kernel.org \
--cc=hch@lst.de \
--cc=jejb@linux.ibm.com \
--cc=jmorris@namei.org \
--cc=kbusch@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-scsi@vger.kernel.org \
--cc=linux-security-module@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=paul@paul-moore.com \
--cc=sagi@grimberg.me \
--cc=serge@hallyn.com \
--cc=viro@zeniv.linux.org.uk \
/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).