block: Add fops atomic write support

Support atomic writes by submitting a single BIO with the REQ_ATOMIC set.

It must be ensured that the atomic write adheres to its rules, like
naturally aligned offset, so call blkdev_dio_invalid() ->
blkdev_atomic_write_valid() [with renaming blkdev_dio_unaligned() to
blkdev_dio_invalid()] for this purpose. The BIO submission path currently
checks for atomic writes which are too large, so no need to check here.

In blkdev_direct_IO(), if the nr_pages exceeds BIO_MAX_VECS, then we cannot
produce a single BIO, so error in this case.

Finally set FMODE_CAN_ATOMIC_WRITE when the bdev can support atomic writes
and the associated file flag is for O_DIRECT.

Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Link: https://lore.kernel.org/r/20240620125359.2684798-8-john.g.garry@oracle.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/fops.c b/block/fops.c
index 376265935714fd1da2b185056468dd3cd0c14462..be36c9fbd500bb8787dbd0d9169a4a9022ccce55 100644 (file)
--- a/block/fops.c
+++ b/block/fops.c
@@ -34,9 +34,12 @@ static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
        return opf;
 }
 
-static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
-                             struct iov_iter *iter)
+static bool blkdev_dio_invalid(struct block_device *bdev, loff_t pos,
+                               struct iov_iter *iter, bool is_atomic)
 {
+       if (is_atomic && !generic_atomic_write_valid(iter, pos))
+               return true;
+
        return pos & (bdev_logical_block_size(bdev) - 1) ||
                !bdev_iter_is_aligned(bdev, iter);
 }
@@ -72,6 +75,8 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
        bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
        bio.bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
        bio.bi_ioprio = iocb->ki_ioprio;
+       if (iocb->ki_flags & IOCB_ATOMIC)
+               bio.bi_opf |= REQ_ATOMIC;
 
        ret = bio_iov_iter_get_pages(&bio, iter);
        if (unlikely(ret))
@@ -343,6 +348,9 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
                task_io_account_write(bio->bi_iter.bi_size);
        }
 
+       if (iocb->ki_flags & IOCB_ATOMIC)
+               bio->bi_opf |= REQ_ATOMIC;
+
        if (iocb->ki_flags & IOCB_NOWAIT)
                bio->bi_opf |= REQ_NOWAIT;
 
@@ -359,12 +367,13 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 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);
+       bool is_atomic = iocb->ki_flags & IOCB_ATOMIC;
        unsigned int nr_pages;
 
        if (!iov_iter_count(iter))
                return 0;
 
-       if (blkdev_dio_unaligned(bdev, iocb->ki_pos, iter))
+       if (blkdev_dio_invalid(bdev, iocb->ki_pos, iter, is_atomic))
                return -EINVAL;
 
        nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
@@ -373,6 +382,8 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
                        return __blkdev_direct_IO_simple(iocb, iter, bdev,
                                                        nr_pages);
                return __blkdev_direct_IO_async(iocb, iter, bdev, nr_pages);
+       } else if (is_atomic) {
+               return -EINVAL;
        }
        return __blkdev_direct_IO(iocb, iter, bdev, bio_max_segs(nr_pages));
 }
@@ -612,6 +623,9 @@ static int blkdev_open(struct inode *inode, struct file *filp)
        if (!bdev)
                return -ENXIO;
 
+       if (bdev_can_atomic_write(bdev) && filp->f_flags & O_DIRECT)
+               filp->f_mode |= FMODE_CAN_ATOMIC_WRITE;
+
        ret = bdev_open(bdev, mode, filp->private_data, NULL, filp);
        if (ret)
                blkdev_put_no_open(bdev);