@@ -34,9 +34,22 @@ 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_atomic_write_valid(struct block_device *bdev, loff_t pos,
+ struct iov_iter *iter)
{
+ struct request_queue *q = bdev_get_queue(bdev);
+ unsigned int min_bytes = queue_atomic_write_unit_min_bytes(q);
+ unsigned int max_bytes = queue_atomic_write_unit_max_bytes(q);
+
+ return generic_atomic_write_valid(pos, iter, min_bytes, max_bytes);
+}
+
+static bool blkdev_dio_invalid(struct block_device *bdev, loff_t pos,
+ struct iov_iter *iter, bool is_atomic)
+{
+ if (is_atomic && !blkdev_atomic_write_valid(bdev, pos, iter))
+ return true;
+
return pos & (bdev_logical_block_size(bdev) - 1) ||
!bdev_iter_is_aligned(bdev, iter);
}
@@ -71,6 +84,8 @@ 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 (iocb->ki_flags & IOCB_ATOMIC)
+ bio.bi_opf |= REQ_ATOMIC;
ret = bio_iov_iter_get_pages(&bio, iter);
if (unlikely(ret))
@@ -340,6 +355,9 @@ 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;
@@ -356,12 +374,13 @@ 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);
@@ -370,6 +389,8 @@ 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));
}
@@ -615,6 +636,9 @@ static int blkdev_open(struct inode *inode, struct file *filp)
if (bdev_nowait(handle->bdev))
filp->f_mode |= FMODE_NOWAIT;
+ if (bdev_can_atomic_write(handle->bdev) && filp->f_flags & O_DIRECT)
+ filp->f_mode |= FMODE_CAN_ATOMIC_WRITE;
+
filp->f_mapping = handle->bdev->bd_inode->i_mapping;
filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
filp->private_data = handle;
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. 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. Signed-off-by: John Garry <john.g.garry@oracle.com> --- block/fops.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-)