Merge branch 'for-4.4/core' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "This is the core block pull request for 4.4.  I've got a few more
  topic branches this time around, some of them will layer on top of the
  core+drivers changes and will come in a separate round.  So not a huge
  chunk of changes in this round.

  This pull request contains:

   - Enable blk-mq page allocation tracking with kmemleak, from Catalin.

   - Unused prototype removal in blk-mq from Christoph.

   - Cleanup of the q->blk_trace exchange, using cmpxchg instead of two
     xchg()'s, from Davidlohr.

   - A plug flush fix from Jeff.

   - Also from Jeff, a fix that means we don't have to update shared tag
     sets at init time unless we do a state change.  This cuts down boot
     times on thousands of devices a lot with scsi/blk-mq.

   - blk-mq waitqueue barrier fix from Kosuke.

   - Various fixes from Ming:

        - Fixes for segment merging and splitting, and checks, for
          the old core and blk-mq.

        - Potential blk-mq speedup by marking ctx pending at the end
          of a plug insertion batch in blk-mq.

        - direct-io no page dirty on kernel direct reads.

   - A WRITE_SYNC fix for mpage from Roman"

* 'for-4.4/core' of git://git.kernel.dk/linux-block:
  blk-mq: avoid excessive boot delays with large lun counts
  blktrace: re-write setting q->blk_trace
  blk-mq: mark ctx as pending at batch in flush plug path
  blk-mq: fix for trace_block_plug()
  block: check bio_mergeable() early before merging
  blk-mq: check bio_mergeable() early before merging
  block: avoid to merge splitted bio
  block: setup bi_phys_segments after splitting
  block: fix plug list flushing for nomerge queues
  blk-mq: remove unused blk_mq_clone_flush_request prototype
  blk-mq: fix waitqueue_active without memory barrier in block/blk-mq-tag.c
  fs: direct-io: don't dirtying pages for ITER_BVEC/ITER_KVEC direct read
  fs/mpage.c: forgotten WRITE_SYNC in case of data integrity write
  block: kmemleak: Track the page allocations for struct request

2 files changed, 21 insertions, 11 deletions

diff --git a/fs/direct-io.c b/fs/direct-io.c
index 11256291642e..3ae0e0427191 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)
@@ -464,14 +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;
diff --git a/fs/mpage.c b/fs/mpage.c
index a7c34274f207..09abba7653aa 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -485,6 +485,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	struct buffer_head map_bh;
 	loff_t i_size = i_size_read(inode);
 	int ret = 0;
+	int wr = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
 
 	if (page_has_buffers(page)) {
 		struct buffer_head *head = page_buffers(page);
@@ -593,7 +594,7 @@ page_is_mapped:
 	 * This page will go to BIO.  Do we need to send this BIO off first?
 	 */
 	if (bio && mpd->last_block_in_bio != blocks[0] - 1)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 alloc_new:
 	if (bio == NULL) {
@@ -620,7 +621,7 @@ alloc_new:
 	wbc_account_io(wbc, page, PAGE_SIZE);
 	length = first_unmapped << blkbits;
 	if (bio_add_page(bio, page, length, 0) < length) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		goto alloc_new;
 	}
 
@@ -630,7 +631,7 @@ alloc_new:
 	set_page_writeback(page);
 	unlock_page(page);
 	if (boundary || (first_unmapped != blocks_per_page)) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		if (boundary_block) {
 			write_boundary_block(boundary_bdev,
 					boundary_block, 1 << blkbits);
@@ -642,7 +643,7 @@ alloc_new:
 
 confused:
 	if (bio)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 	if (mpd->use_writepage) {
 		ret = mapping->a_ops->writepage(page, wbc);
@@ -698,8 +699,11 @@ mpage_writepages(struct address_space *mapping,
 		};
 
 		ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
-		if (mpd.bio)
-			mpage_bio_submit(WRITE, mpd.bio);
+		if (mpd.bio) {
+			int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+				  WRITE_SYNC : WRITE);
+			mpage_bio_submit(wr, mpd.bio);
+		}
 	}
 	blk_finish_plug(&plug);
 	return ret;
@@ -716,8 +720,11 @@ int mpage_writepage(struct page *page, get_block_t get_block,
 		.use_writepage = 0,
 	};
 	int ret = __mpage_writepage(page, wbc, &mpd);
-	if (mpd.bio)
-		mpage_bio_submit(WRITE, mpd.bio);
+	if (mpd.bio) {
+		int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+			  WRITE_SYNC : WRITE);
+		mpage_bio_submit(wr, mpd.bio);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(mpage_writepage);