[PATCH 5.15.y 2/6] block: use flags instead of bit fields for blkdev_dio

[Sasha Levin <sashal@kernel.org>]

From: Jens Axboe <axboe@kernel.dk>

[ Upstream commit 09ce8744253a038eb658c14f9dc3b77fa021fc9f ]

This generates a lot better code for me, and bumps performance from
7650K IOPS to 7750K IOPS. Looking at profiles for the run and running
perf diff, it confirms that we're now sending a lot less time there:

     6.38%     -2.80%  [kernel.vmlinux]  [k] blkdev_direct_IO

Taking it from the 2nd most cycle consumer to only the 9th most at
3.35% of the CPU time.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Stable-dep-of: e78dcb1f7ec2 ("usb: gadget: f_fs: Fix Use-After-Free in AIO error path")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 block/fops.c | 34 ++++++++++++++++++++--------------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/block/fops.c b/block/fops.c
index c23529d08929d..9359368ca7cf4 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -126,6 +126,12 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 	return ret;
 }
 
+enum {
+	DIO_MULTI_BIO		= 1,
+	DIO_SHOULD_DIRTY	= 2,
+	DIO_IS_SYNC		= 4,
+};
+
 struct blkdev_dio {
 	union {
 		struct kiocb		*iocb;
@@ -133,9 +139,7 @@ struct blkdev_dio {
 	};
 	size_t			size;
 	atomic_t		ref;
-	bool			multi_bio : 1;
-	bool			should_dirty : 1;
-	bool			is_sync : 1;
+	unsigned int		flags;
 	struct bio		bio;
 };
 
@@ -152,13 +156,13 @@ static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
 static void blkdev_bio_end_io(struct bio *bio)
 {
 	struct blkdev_dio *dio = bio->bi_private;
-	bool should_dirty = dio->should_dirty;
+	bool should_dirty = dio->flags & DIO_SHOULD_DIRTY;
 
 	if (bio->bi_status && !dio->bio.bi_status)
 		dio->bio.bi_status = bio->bi_status;
 
-	if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) {
-		if (!dio->is_sync) {
+	if (!(dio->flags & DIO_MULTI_BIO) || atomic_dec_and_test(&dio->ref)) {
+		if (!(dio->flags & DIO_IS_SYNC)) {
 			struct kiocb *iocb = dio->iocb;
 			ssize_t ret;
 
@@ -170,7 +174,7 @@ static void blkdev_bio_end_io(struct bio *bio)
 			}
 
 			dio->iocb->ki_complete(iocb, ret, 0);
-			if (dio->multi_bio)
+			if (dio->flags & DIO_MULTI_BIO)
 				bio_put(&dio->bio);
 		} else {
 			struct task_struct *waiter = dio->waiter;
@@ -210,17 +214,19 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
 
 	dio = container_of(bio, struct blkdev_dio, bio);
-	dio->is_sync = is_sync = is_sync_kiocb(iocb);
-	if (dio->is_sync) {
+	is_sync = is_sync_kiocb(iocb);
+	if (is_sync) {
+		dio->flags = DIO_IS_SYNC;
 		dio->waiter = current;
 		bio_get(bio);
 	} else {
+		dio->flags = 0;
 		dio->iocb = iocb;
 	}
 
 	dio->size = 0;
-	dio->multi_bio = false;
-	dio->should_dirty = is_read && iter_is_iovec(iter);
+	if (is_read && iter_is_iovec(iter))
+		dio->flags |= DIO_SHOULD_DIRTY;
 
 	/*
 	 * Don't plug for HIPRI/polled IO, as those should go straight
@@ -263,7 +269,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 
 		if (is_read) {
 			bio->bi_opf = REQ_OP_READ;
-			if (dio->should_dirty)
+			if (dio->flags & DIO_SHOULD_DIRTY)
 				bio_set_pages_dirty(bio);
 		} else {
 			bio->bi_opf = dio_bio_write_op(iocb);
@@ -285,7 +291,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 				WRITE_ONCE(iocb->ki_cookie, qc);
 			break;
 		}
-		if (!dio->multi_bio) {
+		if (!(dio->flags & DIO_MULTI_BIO)) {
 			/*
 			 * AIO needs an extra reference to ensure the dio
 			 * structure which is embedded into the first bio
@@ -293,7 +299,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			 */
 			if (!is_sync)
 				bio_get(bio);
-			dio->multi_bio = true;
+			dio->flags |= DIO_MULTI_BIO;
 			atomic_set(&dio->ref, 2);
 			do_poll = false;
 		} else {
-- 
2.53.0