[PATCH v4 1/5] fs: kiocb: introduce IOCB_DONT_DIRTY_PAGE flag for direct IO

[Ming Lei <ming.lei@canonical.com>]

When direct IO is submitted from kernel, it is often unnecessary
to dirty pages, for example of loop, dirtying pages have been
considered in the upper filesystem(over loop) side already, and
they don't need to be dirtied again.

So this patch introduces IOCB_DONT_DIRTY_PAGE flag for direct IO,
and other ITER_BVEC and ITER_KVEC cases might benefit from it too,
then it can be used for other dio cases which may have different
rules to deal with page dirtying.

The patch is based on previous Dave's patch.

Cc: Dave Kleikamp <dave.kleikamp@oracle.com>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
---
 fs/direct-io.c     | 9 ++++++---
 include/linux/fs.h | 1 +
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/fs/direct-io.c b/fs/direct-io.c
index 745d234..78964c0 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -120,6 +120,7 @@ struct dio {
 	int page_errors;		/* errno from get_user_pages() */
 	int is_async;			/* is IO async ? */
 	bool defer_completion;		/* defer AIO completion to workqueue? */
+	bool should_dirty;		/* if pages should be dirtied */
 	int io_error;			/* IO error in completion path */
 	unsigned long refcount;		/* direct_io_worker() and bios */
 	struct bio *bio_list;		/* singly linked via bi_private */
@@ -393,7 +394,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
 	dio->refcount++;
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 
-	if (dio->is_async && dio->rw == READ)
+	if (dio->is_async && dio->rw == READ && dio->should_dirty)
 		bio_set_pages_dirty(bio);
 
 	if (sdio->submit_io)
@@ -464,13 +465,14 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
 	if (!uptodate)
 		dio->io_error = -EIO;
 
-	if (dio->is_async && dio->rw == READ) {
+	if (dio->is_async && dio->rw == READ && dio->should_dirty) {
 		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
 		bio_for_each_segment_all(bvec, bio, i) {
 			struct page *page = bvec->bv_page;
 
-			if (dio->rw == READ && !PageCompound(page))
+			if (dio->rw == READ && !PageCompound(page) &&
+					dio->should_dirty)
 				set_page_dirty_lock(page);
 			page_cache_release(page);
 		}
@@ -1217,6 +1219,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	spin_lock_init(&dio->bio_lock);
 	dio->refcount = 1;
 
+	dio->should_dirty = !(iocb->ki_flags & IOCB_DONT_DIRTY_PAGE);
 	sdio.iter = iter;
 	sdio.final_block_in_request =
 		(offset + iov_iter_count(iter)) >> blkbits;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ff4135e..54027ad 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -316,6 +316,7 @@ struct writeback_control;
 #define IOCB_EVENTFD		(1 << 0)
 #define IOCB_APPEND		(1 << 1)
 #define IOCB_DIRECT		(1 << 2)
+#define IOCB_DONT_DIRTY_PAGE	(1 << 3)
 
 struct kiocb {
 	struct file		*ki_filp;
-- 
1.9.1