linux-kernel - [PATCH 10/21] block: Add fops atomic write support

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20230929102726.2985188-11-john.g.garry@oracle.com>
Date:   Fri, 29 Sep 2023 10:27:15 +0000
From:   John Garry <john.g.garry@...cle.com>
To:     axboe@...nel.dk, kbusch@...nel.org, hch@....de, sagi@...mberg.me,
        jejb@...ux.ibm.com, martin.petersen@...cle.com, djwong@...nel.org,
        viro@...iv.linux.org.uk, brauner@...nel.org,
        chandan.babu@...cle.com, dchinner@...hat.com
Cc:     linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-nvme@...ts.infradead.org, linux-xfs@...r.kernel.org,
        linux-fsdevel@...r.kernel.org, tytso@....edu, jbongio@...gle.com,
        linux-api@...r.kernel.org, John Garry <john.g.garry@...cle.com>
Subject: [PATCH 10/21] block: Add fops atomic write support

Add support for atomic writes, as follows:
- Ensure that the IO follows all the atomic writes rules, like must be
  naturally aligned
- Set REQ_ATOMIC

Signed-off-by: John Garry <john.g.garry@...cle.com>
---
 block/fops.c | 42 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 41 insertions(+), 1 deletion(-)

diff --git a/block/fops.c b/block/fops.c
index acff3d5d22d4..516669ad69e5 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -41,6 +41,29 @@ static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
 		!bdev_iter_is_aligned(bdev, iter);
 }
 
+static bool blkdev_atomic_write_valid(struct block_device *bdev, loff_t pos,
+			      struct iov_iter *iter)
+{
+	unsigned int atomic_write_unit_min_bytes =
+			queue_atomic_write_unit_min_bytes(bdev_get_queue(bdev));
+	unsigned int atomic_write_unit_max_bytes =
+			queue_atomic_write_unit_max_bytes(bdev_get_queue(bdev));
+
+	if (!atomic_write_unit_min_bytes)
+		return false;
+	if (pos % atomic_write_unit_min_bytes)
+		return false;
+	if (iov_iter_count(iter) % atomic_write_unit_min_bytes)
+		return false;
+	if (!is_power_of_2(iov_iter_count(iter)))
+		return false;
+	if (iov_iter_count(iter) > atomic_write_unit_max_bytes)
+		return false;
+	if (pos % iov_iter_count(iter))
+		return false;
+	return true;
+}
+
 #define DIO_INLINE_BIO_VECS 4
 
 static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
@@ -48,6 +71,8 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 {
 	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	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;
 	loff_t pos = iocb->ki_pos;
 	bool should_dirty = false;
 	struct bio bio;
@@ -56,6 +81,9 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 	if (blkdev_dio_unaligned(bdev, pos, iter))
 		return -EINVAL;
 
+	if (atomic_write && !blkdev_atomic_write_valid(bdev, pos, iter))
+		return -EINVAL;
+
 	if (nr_pages <= DIO_INLINE_BIO_VECS)
 		vecs = inline_vecs;
 	else {
@@ -65,7 +93,7 @@ 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;
@@ -74,6 +102,8 @@ 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;
 
 	ret = bio_iov_iter_get_pages(&bio, iter);
 	if (unlikely(ret))
@@ -167,10 +197,14 @@ 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);
 	loff_t pos = iocb->ki_pos;
 	int ret = 0;
 
+	if (atomic_write)
+		return -EINVAL;
+
 	if (blkdev_dio_unaligned(bdev, pos, iter))
 		return -EINVAL;
 
@@ -305,6 +339,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	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;
 	struct blkdev_dio *dio;
 	struct bio *bio;
 	loff_t pos = iocb->ki_pos;
@@ -313,6 +348,9 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	if (blkdev_dio_unaligned(bdev, pos, iter))
 		return -EINVAL;
 
+	if (atomic_write && !blkdev_atomic_write_valid(bdev, pos, iter))
+		return -EINVAL;
+
 	if (iocb->ki_flags & IOCB_ALLOC_CACHE)
 		opf |= REQ_ALLOC_CACHE;
 	bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL,
@@ -347,6 +385,8 @@ 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