fs: direct-io: don't dirtying pages for ITER_BVEC/ITER_KVEC direct read

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

diff --git a/fs/direct-io.c b/fs/direct-io.c
index 11256291642e5df1f66fd1880109cf7c260796cc..3ae0e0427191c7849fc70301e58792515f5f181c 100644 (file)
--- 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)
@@ -464,14 +465,15 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
        if (bio->bi_error)
                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 */
                err = bio->bi_error;
        } 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);
                }
@@ -1219,6 +1221,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
        spin_lock_init(&dio->bio_lock);
        dio->refcount = 1;
 
+       dio->should_dirty = (iter->type == ITER_IOVEC);
        sdio.iter = iter;
        sdio.final_block_in_request =
                (offset + iov_iter_count(iter)) >> blkbits;