[PATCHv10,5/9] block, fs: add write hint to kiocb

Commit Message

Keith Busch Oct. 29, 2024, 3:19 p.m. UTC

From: Keith Busch <[e-mail]>

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 allowed hints.

Signed-off-by: Keith Busch <[e-mail]>
---
 block/fops.c       | 31 ++++++++++++++++++++++++++++---
 include/linux/fs.h |  1 +
 2 files changed, 29 insertions(+), 3 deletions(-)

Patch

diff --git a/block/fops.c b/block/fops.c
index 2d01c90076813..bb3855ee044f0 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 int 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 -EINVAL;
+
+	if (bdev_is_partition(bdev) &&
+	    !test_bit(hint - 1, bdev->write_hint_mask))
+		return -EINVAL;
+
+	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 +390,14 @@  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) {
+		int hint = blkdev_write_hint(iocb, bdev);
+
+		if (hint < 0)
+			return hint;
+		iocb->ki_write_hint = hint;
+	}
+
 	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