[Devel] [PATCH rh7 29/30] fs: direct-io: don't dirtying pages for ITER_BVEC/ITER_KVEC direct read

[Kirill Tkhai]

From: Ming Lei <ming.lei at canonical.com>

ms commit 53cbf3b157a0

When direct read 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 doesn't dirtying pages for ITER_BVEC/ITER_KVEC
direct read, and loop should be the 1st case to use ITER_BVEC/ITER_KVEC
for direct read I/O.

The patch is based on previous Dave's patch.

Reviewed-by: Dave Kleikamp <dave.kleikamp at oracle.com>
Reviewed-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Ming Lei <ming.lei at canonical.com>
Signed-off-by: Jens Axboe <axboe at fb.com>

Otherwise bio_set_pages_dirty() results in deadlock for bvec pages.

Signed-off-by: Kirill Tkhai <ktkhai at virtuozzo.com>
---
 fs/direct-io.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/direct-io.c b/fs/direct-io.c
index f7e464d8bcdb..1c3a4851e5cf 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -129,6 +129,7 @@ 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 */
@@ -471,7 +472,7 @@ 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)
@@ -542,13 +543,14 @@ 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);
 		}
@@ -1324,6 +1326,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	spin_lock_init(&dio->bio_lock);
 	dio->refcount = 1;
 
+	dio->should_dirty = iov_iter_has_iovec(iter);
 	sdio.iter = iter;
 	sdio.final_block_in_request =
 		(offset + iov_iter_count(iter)) >> blkbits;