Merge tag 'for-5.1/block-20190302' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "Not a huge amount of changes in this round, the biggest one is that we
  finally have Mings multi-page bvec support merged. Apart from that,
  this pull request contains:

   - Small series that avoids quiescing the queue for sysfs changes that
     match what we currently have (Aleksei)

   - Series of bcache fixes (via Coly)

   - Series of lightnvm fixes (via Mathias)

   - NVMe pull request from Christoph. Nothing major, just SPDX/license
     cleanups, RR mp policy (Hannes), and little fixes (Bart,
     Chaitanya).

   - BFQ series (Paolo)

   - Save blk-mq cpu -> hw queue mapping, removing a pointer indirection
     for the fast path (Jianchao)

   - fops->iopoll() added for async IO polling, this is a feature that
     the upcoming io_uring interface will use (Christoph, me)

   - Partition scan loop fixes (Dongli)

   - mtip32xx conversion from managed resource API (Christoph)

   - cdrom registration race fix (Guenter)

   - MD pull from Song, two minor fixes.

   - Various documentation fixes (Marcos)

   - Multi-page bvec feature. This brings a lot of nice improvements
     with it, like more efficient splitting, larger IOs can be supported
     without growing the bvec table size, and so on. (Ming)

   - Various little fixes to core and drivers"

* tag 'for-5.1/block-20190302' of git://git.kernel.dk/linux-block: (117 commits)
  block: fix updating bio's front segment size
  block: Replace function name in string with __func__
  nbd: propagate genlmsg_reply return code
  floppy: remove set but not used variable 'q'
  null_blk: fix checking for REQ_FUA
  block: fix NULL pointer dereference in register_disk
  fs: fix guard_bio_eod to check for real EOD errors
  blk-mq: use HCTX_TYPE_DEFAULT but not 0 to index blk_mq_tag_set->map
  block: optimize bvec iteration in bvec_iter_advance
  block: introduce mp_bvec_for_each_page() for iterating over page
  block: optimize blk_bio_segment_split for single-page bvec
  block: optimize __blk_segment_map_sg() for single-page bvec
  block: introduce bvec_nth_page()
  iomap: wire up the iopoll method
  block: add bio_set_polled() helper
  block: wire up block device iopoll method
  fs: add an iopoll method to struct file_operations
  loop: set GENHD_FL_NO_PART_SCAN after blkdev_reread_part()
  loop: do not print warn message if partition scan is successful
  block: bounce: make sure that bvec table is updated
  ...

21 files changed, 123 insertions, 53 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 58a4c1217fa8..e9faa52bb489 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -211,6 +211,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 	ssize_t ret;
 	blk_qc_t qc;
 	int i;
+	struct bvec_iter_all iter_all;
 
 	if ((pos | iov_iter_alignment(iter)) &
 	    (bdev_logical_block_size(bdev) - 1))
@@ -247,7 +248,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 		task_io_account_write(ret);
 	}
 	if (iocb->ki_flags & IOCB_HIPRI)
-		bio.bi_opf |= REQ_HIPRI;
+		bio_set_polled(&bio, iocb);
 
 	qc = submit_bio(&bio);
 	for (;;) {
@@ -260,7 +261,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 	}
 	__set_current_state(TASK_RUNNING);
 
-	bio_for_each_segment_all(bvec, &bio, i) {
+	bio_for_each_segment_all(bvec, &bio, i, iter_all) {
 		if (should_dirty && !PageCompound(bvec->bv_page))
 			set_page_dirty_lock(bvec->bv_page);
 		put_page(bvec->bv_page);
@@ -293,6 +294,14 @@ struct blkdev_dio {
 
 static struct bio_set blkdev_dio_pool;
 
+static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
+{
+	struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host);
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait);
+}
+
 static void blkdev_bio_end_io(struct bio *bio)
 {
 	struct blkdev_dio *dio = bio->bi_private;
@@ -329,8 +338,9 @@ static void blkdev_bio_end_io(struct bio *bio)
 	} else {
 		struct bio_vec *bvec;
 		int i;
+		struct bvec_iter_all iter_all;
 
-		bio_for_each_segment_all(bvec, bio, i)
+		bio_for_each_segment_all(bvec, bio, i, iter_all)
 			put_page(bvec->bv_page);
 		bio_put(bio);
 	}
@@ -406,10 +416,17 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 
 		nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES);
 		if (!nr_pages) {
-			if (iocb->ki_flags & IOCB_HIPRI)
-				bio->bi_opf |= REQ_HIPRI;
+			bool polled = false;
+
+			if (iocb->ki_flags & IOCB_HIPRI) {
+				bio_set_polled(bio, iocb);
+				polled = true;
+			}
 
 			qc = submit_bio(bio);
+
+			if (polled)
+				WRITE_ONCE(iocb->ki_cookie, qc);
 			break;
 		}
 
@@ -2076,6 +2093,7 @@ const struct file_operations def_blk_fops = {
 	.llseek		= block_llseek,
 	.read_iter	= blkdev_read_iter,
 	.write_iter	= blkdev_write_iter,
+	.iopoll		= blkdev_iopoll,
 	.mmap		= generic_file_mmap,
 	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index eb8e20b740d6..4f2a8ae0aa42 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -162,13 +162,14 @@ csum_failed:
 	} else {
 		int i;
 		struct bio_vec *bvec;
+		struct bvec_iter_all iter_all;
 
 		/*
 		 * we have verified the checksum already, set page
 		 * checked so the end_io handlers know about it
 		 */
 		ASSERT(!bio_flagged(bio, BIO_CLONED));
-		bio_for_each_segment_all(bvec, cb->orig_bio, i)
+		bio_for_each_segment_all(bvec, cb->orig_bio, i, iter_all)
 			SetPageChecked(bvec->bv_page);
 
 		bio_endio(cb->orig_bio);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 5216e7b3f9ad..f0cdb53f3e2d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -833,9 +833,10 @@ static blk_status_t btree_csum_one_bio(struct bio *bio)
 	struct bio_vec *bvec;
 	struct btrfs_root *root;
 	int i, ret = 0;
+	struct bvec_iter_all iter_all;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
-	bio_for_each_segment_all(bvec, bio, i) {
+	bio_for_each_segment_all(bvec, bio, i, iter_all) {
 		root = BTRFS_I(bvec->bv_page->mapping->host)->root;
 		ret = csum_dirty_buffer(root->fs_info, bvec->bv_page);
 		if (ret)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index ca259c75bbcd..ab705183d749 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -152,11 +152,12 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
 {
 	blk_status_t ret = 0;
 	struct bio_vec *bvec = bio_last_bvec_all(bio);
-	struct page *page = bvec->bv_page;
+	struct bio_vec bv;
 	struct extent_io_tree *tree = bio->bi_private;
 	u64 start;
 
-	start = page_offset(page) + bvec->bv_offset;
+	mp_bvec_last_segment(bvec, &bv);
+	start = page_offset(bv.bv_page) + bv.bv_offset;
 
 	bio->bi_private = NULL;
 
@@ -2379,7 +2380,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	int read_mode = 0;
 	blk_status_t status;
 	int ret;
-	unsigned failed_bio_pages = bio_pages_all(failed_bio);
+	unsigned failed_bio_pages = failed_bio->bi_iter.bi_size >> PAGE_SHIFT;
 
 	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
 
@@ -2451,9 +2452,10 @@ static void end_bio_extent_writepage(struct bio *bio)
 	u64 start;
 	u64 end;
 	int i;
+	struct bvec_iter_all iter_all;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
-	bio_for_each_segment_all(bvec, bio, i) {
+	bio_for_each_segment_all(bvec, bio, i, iter_all) {
 		struct page *page = bvec->bv_page;
 		struct inode *inode = page->mapping->host;
 		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -2522,9 +2524,10 @@ static void end_bio_extent_readpage(struct bio *bio)
 	int mirror;
 	int ret;
 	int i;
+	struct bvec_iter_all iter_all;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
-	bio_for_each_segment_all(bvec, bio, i) {
+	bio_for_each_segment_all(bvec, bio, i, iter_all) {
 		struct page *page = bvec->bv_page;
 		struct inode *inode = page->mapping->host;
 		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -3641,9 +3644,10 @@ static void end_bio_extent_buffer_writepage(struct bio *bio)
 	struct bio_vec *bvec;
 	struct extent_buffer *eb;
 	int i, done;
+	struct bvec_iter_all iter_all;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
-	bio_for_each_segment_all(bvec, bio, i) {
+	bio_for_each_segment_all(bvec, bio, i, iter_all) {
 		struct page *page = bvec->bv_page;
 
 		eb = (struct extent_buffer *)page->private;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3f180b857e20..82fdda8ff5ab 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7829,6 +7829,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio)
 	struct bio_vec *bvec;
 	struct extent_io_tree *io_tree, *failure_tree;
 	int i;
+	struct bvec_iter_all iter_all;
 
 	if (bio->bi_status)
 		goto end;
@@ -7840,7 +7841,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio)
 
 	done->uptodate = 1;
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
-	bio_for_each_segment_all(bvec, bio, i)
+	bio_for_each_segment_all(bvec, bio, i, iter_all)
 		clean_io_failure(BTRFS_I(inode)->root->fs_info, failure_tree,
 				 io_tree, done->start, bvec->bv_page,
 				 btrfs_ino(BTRFS_I(inode)), 0);
@@ -7919,6 +7920,7 @@ static void btrfs_retry_endio(struct bio *bio)
 	int uptodate;
 	int ret;
 	int i;
+	struct bvec_iter_all iter_all;
 
 	if (bio->bi_status)
 		goto end;
@@ -7932,7 +7934,7 @@ static void btrfs_retry_endio(struct bio *bio)
 	failure_tree = &BTRFS_I(inode)->io_failure_tree;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
-	bio_for_each_segment_all(bvec, bio, i) {
+	bio_for_each_segment_all(bvec, bio, i, iter_all) {
 		ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page,
 					     bvec->bv_offset, done->start,
 					     bvec->bv_len);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index e74455eb42f9..1869ba8e5981 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1443,10 +1443,11 @@ static void set_bio_pages_uptodate(struct bio *bio)
 {
 	struct bio_vec *bvec;
 	int i;
+	struct bvec_iter_all iter_all;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
 
-	bio_for_each_segment_all(bvec, bio, i)
+	bio_for_each_segment_all(bvec, bio, i, iter_all)
 		SetPageUptodate(bvec->bv_page);
 }
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 48318fb74938..ce357602f471 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3027,13 +3027,23 @@ void guard_bio_eod(int op, struct bio *bio)
 	/* Uhhuh. We've got a bio that straddles the device size! */
 	truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
 
+	/*
+	 * The bio contains more than one segment which spans EOD, just return
+	 * and let IO layer turn it into an EIO
+	 */
+	if (truncated_bytes > bvec->bv_len)
+		return;
+
 	/* Truncate the bio.. */
 	bio->bi_iter.bi_size -= truncated_bytes;
 	bvec->bv_len -= truncated_bytes;
 
 	/* ..and clear the end of the buffer for reads */
 	if (op == REQ_OP_READ) {
-		zero_user(bvec->bv_page, bvec->bv_offset + bvec->bv_len,
+		struct bio_vec bv;
+
+		mp_bvec_last_segment(bvec, &bv);
+		zero_user(bv.bv_page, bv.bv_offset + bv.bv_len,
 				truncated_bytes);
 	}
 }
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
index 0959044c5cee..5759bcd018cd 100644
--- a/fs/crypto/bio.c
+++ b/fs/crypto/bio.c
@@ -30,8 +30,9 @@ static void __fscrypt_decrypt_bio(struct bio *bio, bool done)
 {
 	struct bio_vec *bv;
 	int i;
+	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bv, bio, i) {
+	bio_for_each_segment_all(bv, bio, i, iter_all) {
 		struct page *page = bv->bv_page;
 		int ret = fscrypt_decrypt_page(page->mapping->host, page,
 				PAGE_SIZE, 0, page->index);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index ec2fb6fe6d37..9bb015bc4a83 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -551,7 +551,9 @@ static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio)
 	if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) {
 		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
-		bio_for_each_segment_all(bvec, bio, i) {
+		struct bvec_iter_all iter_all;
+
+		bio_for_each_segment_all(bvec, bio, i, iter_all) {
 			struct page *page = bvec->bv_page;
 
 			if (dio->op == REQ_OP_READ && !PageCompound(page) &&
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 5331a15a61f1..24a8e34882e9 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -420,8 +420,9 @@ static void _clear_bio(struct bio *bio)
 {
 	struct bio_vec *bv;
 	unsigned i;
+	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bv, bio, i) {
+	bio_for_each_segment_all(bv, bio, i, iter_all) {
 		unsigned this_count = bv->bv_len;
 
 		if (likely(PAGE_SIZE == this_count))
diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c
index 199590f36203..e83bab54b03e 100644
--- a/fs/exofs/ore_raid.c
+++ b/fs/exofs/ore_raid.c
@@ -468,11 +468,12 @@ static void _mark_read4write_pages_uptodate(struct ore_io_state *ios, int ret)
 	/* loop on all devices all pages */
 	for (d = 0; d < ios->numdevs; d++) {
 		struct bio *bio = ios->per_dev[d].bio;
+		struct bvec_iter_all iter_all;
 
 		if (!bio)
 			continue;
 
-		bio_for_each_segment_all(bv, bio, i) {
+		bio_for_each_segment_all(bv, bio, i, iter_all) {
 			struct page *page = bv->bv_page;
 
 			SetPageUptodate(page);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 2aa62d58d8dd..cff4c4aa7a9c 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -63,8 +63,9 @@ static void ext4_finish_bio(struct bio *bio)
 {
 	int i;
 	struct bio_vec *bvec;
+	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, i) {
+	bio_for_each_segment_all(bvec, bio, i, iter_all) {
 		struct page *page = bvec->bv_page;
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 		struct page *data_page = NULL;
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index 6aa282ee455a..e53639784892 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -72,6 +72,7 @@ static void mpage_end_io(struct bio *bio)
 {
 	struct bio_vec *bv;
 	int i;
+	struct bvec_iter_all iter_all;
 
 	if (ext4_bio_encrypted(bio)) {
 		if (bio->bi_status) {
@@ -81,7 +82,7 @@ static void mpage_end_io(struct bio *bio)
 			return;
 		}
 	}
-	bio_for_each_segment_all(bv, bio, i) {
+	bio_for_each_segment_all(bv, bio, i, iter_all) {
 		struct page *page = bv->bv_page;
 
 		if (!bio->bi_status) {
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f91d8630c9a2..da060b77f64d 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -87,8 +87,9 @@ static void __read_end_io(struct bio *bio)
 	struct page *page;
 	struct bio_vec *bv;
 	int i;
+	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bv, bio, i) {
+	bio_for_each_segment_all(bv, bio, i, iter_all) {
 		page = bv->bv_page;
 
 		/* PG_error was set if any post_read step failed */
@@ -164,13 +165,14 @@ static void f2fs_write_end_io(struct bio *bio)
 	struct f2fs_sb_info *sbi = bio->bi_private;
 	struct bio_vec *bvec;
 	int i;
+	struct bvec_iter_all iter_all;
 
 	if (time_to_inject(sbi, FAULT_WRITE_IO)) {
 		f2fs_show_injection_info(FAULT_WRITE_IO);
 		bio->bi_status = BLK_STS_IOERR;
 	}
 
-	bio_for_each_segment_all(bvec, bio, i) {
+	bio_for_each_segment_all(bvec, bio, i, iter_all) {
 		struct page *page = bvec->bv_page;
 		enum count_type type = WB_DATA_TYPE(page);
 
@@ -347,6 +349,7 @@ static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
 	struct bio_vec *bvec;
 	struct page *target;
 	int i;
+	struct bvec_iter_all iter_all;
 
 	if (!io->bio)
 		return false;
@@ -354,7 +357,7 @@ static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
 	if (!inode && !page && !ino)
 		return true;
 
-	bio_for_each_segment_all(bvec, io->bio, i) {
+	bio_for_each_segment_all(bvec, io->bio, i, iter_all) {
 
 		if (bvec->bv_page->mapping)
 			target = bvec->bv_page;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index a2dea5bc0427..58a768e59712 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1280,6 +1280,7 @@ const struct file_operations gfs2_file_fops = {
 	.llseek		= gfs2_llseek,
 	.read_iter	= gfs2_file_read_iter,
 	.write_iter	= gfs2_file_write_iter,
+	.iopoll		= iomap_dio_iopoll,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,
 	.open		= gfs2_open,
@@ -1310,6 +1311,7 @@ const struct file_operations gfs2_file_fops_nolock = {
 	.llseek		= gfs2_llseek,
 	.read_iter	= gfs2_file_read_iter,
 	.write_iter	= gfs2_file_write_iter,
+	.iopoll		= iomap_dio_iopoll,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,
 	.open		= gfs2_open,
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 2295042bc625..8722c60b11fe 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -168,7 +168,8 @@ u64 gfs2_log_bmap(struct gfs2_sbd *sdp)
  * that is pinned in the pagecache.
  */
 
-static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec,
+static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp,
+				  struct bio_vec *bvec,
 				  blk_status_t error)
 {
 	struct buffer_head *bh, *next;
@@ -207,6 +208,7 @@ static void gfs2_end_log_write(struct bio *bio)
 	struct bio_vec *bvec;
 	struct page *page;
 	int i;
+	struct bvec_iter_all iter_all;
 
 	if (bio->bi_status) {
 		fs_err(sdp, "Error %d writing to journal, jid=%u\n",
@@ -214,7 +216,7 @@ static void gfs2_end_log_write(struct bio *bio)
 		wake_up(&sdp->sd_logd_waitq);
 	}
 
-	bio_for_each_segment_all(bvec, bio, i) {
+	bio_for_each_segment_all(bvec, bio, i, iter_all) {
 		page = bvec->bv_page;
 		if (page_has_buffers(page))
 			gfs2_end_log_write_bh(sdp, bvec, bio->bi_status);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index be9c0bf697fe..3201342404a7 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -190,8 +190,9 @@ static void gfs2_meta_read_endio(struct bio *bio)
 {
 	struct bio_vec *bvec;
 	int i;
+	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, i) {
+	bio_for_each_segment_all(bvec, bio, i, iter_all) {
 		struct page *page = bvec->bv_page;
 		struct buffer_head *bh = page_buffers(page);
 		unsigned int len = bvec->bv_len;
diff --git a/fs/iomap.c b/fs/iomap.c
index 897c60215dd1..97cb9d486a7d 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -274,8 +274,9 @@ iomap_read_end_io(struct bio *bio)
 	int error = blk_status_to_errno(bio->bi_status);
 	struct bio_vec *bvec;
 	int i;
+	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, i)
+	bio_for_each_segment_all(bvec, bio, i, iter_all)
 		iomap_read_page_end_io(bvec, error);
 	bio_put(bio);
 }
@@ -324,7 +325,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	 */
 	sector = iomap_sector(iomap, pos);
 	if (ctx->bio && bio_end_sector(ctx->bio) == sector) {
-		if (__bio_try_merge_page(ctx->bio, page, plen, poff))
+		if (__bio_try_merge_page(ctx->bio, page, plen, poff, true))
 			goto done;
 		is_contig = true;
 	}
@@ -355,7 +356,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		ctx->bio->bi_end_io = iomap_read_end_io;
 	}
 
-	__bio_add_page(ctx->bio, page, plen, poff);
+	bio_add_page(ctx->bio, page, plen, poff);
 done:
 	/*
 	 * Move the caller beyond our range so that it keeps making progress.
@@ -1463,6 +1464,28 @@ struct iomap_dio {
 	};
 };
 
+int iomap_dio_iopoll(struct kiocb *kiocb, bool spin)
+{
+	struct request_queue *q = READ_ONCE(kiocb->private);
+
+	if (!q)
+		return 0;
+	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), spin);
+}
+EXPORT_SYMBOL_GPL(iomap_dio_iopoll);
+
+static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
+		struct bio *bio)
+{
+	atomic_inc(&dio->ref);
+
+	if (dio->iocb->ki_flags & IOCB_HIPRI)
+		bio_set_polled(bio, dio->iocb);
+
+	dio->submit.last_queue = bdev_get_queue(iomap->bdev);
+	dio->submit.cookie = submit_bio(bio);
+}
+
 static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	struct kiocb *iocb = dio->iocb;
@@ -1568,14 +1591,15 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 	} else {
 		struct bio_vec *bvec;
 		int i;
+		struct bvec_iter_all iter_all;
 
-		bio_for_each_segment_all(bvec, bio, i)
+		bio_for_each_segment_all(bvec, bio, i, iter_all)
 			put_page(bvec->bv_page);
 		bio_put(bio);
 	}
 }
 
-static blk_qc_t
+static void
 iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 		unsigned len)
 {
@@ -1589,15 +1613,10 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 	bio->bi_private = dio;
 	bio->bi_end_io = iomap_dio_bio_end_io;
 
-	if (dio->iocb->ki_flags & IOCB_HIPRI)
-		flags |= REQ_HIPRI;
-
 	get_page(page);
 	__bio_add_page(bio, page, len, 0);
 	bio_set_op_attrs(bio, REQ_OP_WRITE, flags);
-
-	atomic_inc(&dio->ref);
-	return submit_bio(bio);
+	iomap_dio_submit_bio(dio, iomap, bio);
 }
 
 static loff_t
@@ -1700,9 +1719,6 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 				bio_set_pages_dirty(bio);
 		}
 
-		if (dio->iocb->ki_flags & IOCB_HIPRI)
-			bio->bi_opf |= REQ_HIPRI;
-
 		iov_iter_advance(dio->submit.iter, n);
 
 		dio->size += n;
@@ -1710,11 +1726,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 		copied += n;
 
 		nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
-
-		atomic_inc(&dio->ref);
-
-		dio->submit.last_queue = bdev_get_queue(iomap->bdev);
-		dio->submit.cookie = submit_bio(bio);
+		iomap_dio_submit_bio(dio, iomap, bio);
 	} while (nr_pages);
 
 	/*
@@ -1925,6 +1937,9 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (dio->flags & IOMAP_DIO_WRITE_FUA)
 		dio->flags &= ~IOMAP_DIO_NEED_SYNC;
 
+	WRITE_ONCE(iocb->ki_cookie, dio->submit.cookie);
+	WRITE_ONCE(iocb->private, dio->submit.last_queue);
+
 	/*
 	 * We are about to drop our additional submission reference, which
 	 * might be the last reference to the dio.  There are three three
diff --git a/fs/mpage.c b/fs/mpage.c
index c820dc9bebab..3f19da75178b 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -48,8 +48,9 @@ static void mpage_end_io(struct bio *bio)
 {
 	struct bio_vec *bv;
 	int i;
+	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bv, bio, i) {
+	bio_for_each_segment_all(bv, bio, i, iter_all) {
 		struct page *page = bv->bv_page;
 		page_endio(page, bio_op(bio),
 			   blk_status_to_errno(bio->bi_status));
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 7b8bb6bde981..3619e9e8d359 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -63,7 +63,7 @@ xfs_find_daxdev_for_inode(
 static void
 xfs_finish_page_writeback(
 	struct inode		*inode,
-	struct bio_vec		*bvec,
+	struct bio_vec	*bvec,
 	int			error)
 {
 	struct iomap_page	*iop = to_iomap_page(bvec->bv_page);
@@ -99,6 +99,7 @@ xfs_destroy_ioend(
 	for (bio = &ioend->io_inline_bio; bio; bio = next) {
 		struct bio_vec	*bvec;
 		int		i;
+		struct bvec_iter_all iter_all;
 
 		/*
 		 * For the last bio, bi_private points to the ioend, so we
@@ -110,7 +111,7 @@ xfs_destroy_ioend(
 			next = bio->bi_private;
 
 		/* walk each page on bio, ending page IO on them */
-		bio_for_each_segment_all(bvec, bio, i)
+		bio_for_each_segment_all(bvec, bio, i, iter_all)
 			xfs_finish_page_writeback(inode, bvec, error);
 		bio_put(bio);
 	}
@@ -661,12 +662,12 @@ xfs_add_to_ioend(
 				wpc->imap.br_state, offset, bdev, sector);
 	}
 
-	if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff)) {
+	if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff, true)) {
 		if (iop)
 			atomic_inc(&iop->write_count);
 		if (bio_full(wpc->ioend->io_bio))
 			xfs_chain_bio(wpc->ioend, wbc, bdev, sector);
-		__bio_add_page(wpc->ioend->io_bio, page, len, poff);
+		bio_add_page(wpc->ioend->io_bio, page, len, poff);
 	}
 
 	wpc->ioend->io_size += len;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 770cc2edf777..1f2e2845eb76 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1216,6 +1216,7 @@ const struct file_operations xfs_file_operations = {
 	.write_iter	= xfs_file_write_iter,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
+	.iopoll		= iomap_dio_iopoll,
 	.unlocked_ioctl	= xfs_file_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= xfs_file_compat_ioctl,