[PATCH v2 2/2] block: only use REQ_FUA for direct writes if the device supports it

From: Zhenxian Ma <[email protected]>

When a block device does not support FUA natively, the block layer
emulates it by adding a cache flush to every write bio.  An O_DSYNC
direct write that spans N bios then costs N flushes, rather than the
single generic_write_sync() issued after the write completes.

Introduce blkdev_dio_fua() to decide when REQ_FUA is set.  A synchronous
write can rely on generic_write_sync() when the device lacks FUA, so it
sets REQ_FUA only when bdev_fua() is true.  An asynchronous write
completes in blkdev_bio_end_io() and cannot call the blocking
generic_write_sync(), so it keeps REQ_FUA (emulated when needed) to stay
durable.

Suggested-by: Christoph Hellwig <[email protected]>
Signed-off-by: Zhenxian Ma <[email protected]>
Signed-off-by: Zhenxian Ma <[email protected]>
---
 block/fops.c | 32 +++++++++++++++++++++++++++-----
 1 file changed, 27 insertions(+), 5 deletions(-)

diff --git a/block/fops.c b/block/fops.c
index a2c3af38106b..e7d073620271 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -26,12 +26,26 @@ static inline struct inode *bdev_file_inode(struct file *file)
 	return file->f_mapping->host;
 }
 
-static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
+static bool blkdev_dio_fua(struct kiocb *iocb, struct block_device *bdev)
+{
+	if (!iocb_is_dsync(iocb))
+		return false;
+	/*
+	 * Async writes cannot fall back to generic_write_sync(), so they must
+	 * use FUA (emulated if needed); sync writes only need it when the
+	 * device supports FUA natively.
+	 */
+	if (!is_sync_kiocb(iocb))
+		return true;
+	return bdev_fua(bdev);
+}
+
+static blk_opf_t dio_bio_write_op(struct kiocb *iocb, struct block_device *bdev)
 {
 	blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
 
 	/* avoid the need for a I/O completion work item */
-	if (iocb_is_dsync(iocb))
+	if (blkdev_dio_fua(iocb, bdev))
 		opf |= REQ_FUA;
 	return opf;
 }
@@ -75,7 +89,8 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 		if (user_backed_iter(iter))
 			should_dirty = true;
 	} else {
-		bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb));
+		bio_init(&bio, bdev, vecs, nr_pages,
+			 dio_bio_write_op(iocb, bdev));
 	}
 	bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
 	bio.bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
@@ -179,7 +194,7 @@ 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;
-	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
+	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb, bdev);
 	loff_t pos = iocb->ki_pos;
 	int ret = 0;
 
@@ -323,7 +338,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 					unsigned int nr_pages)
 {
 	bool is_read = iov_iter_rw(iter) == READ;
-	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
+	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb, bdev);
 	struct blkdev_dio *dio;
 	struct bio *bio;
 	loff_t pos = iocb->ki_pos;
@@ -768,6 +783,13 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			ret = direct_write_fallback(iocb, from, ret,
 					blkdev_buffered_write(iocb, from));
 			need_sync = true;
+		} else if (ret > 0 && !blkdev_dio_fua(iocb, bdev)) {
+			/*
+			 * The device does not support FUA, so REQ_FUA was not
+			 * set and the O_DSYNC direct write still needs a flush
+			 * to be made durable.
+			 */
+			need_sync = true;
 		}
 	} else {
 		/*
-- 
2.43.5